## Why
Contextual fragments and extension-owned world-state sections currently return strings, limiting them to text content.
## What changed
- Return `ContentItem` from fragment bodies and rendering, preserving classification and attribution. Apply text markers only to `InputText`; pass other content through unchanged.
- Allow extension prompt and world-state contributions to carry typed content, and preserve media in context-window hints.
- Hash non-text world-state fragments by their serialized content and role while retaining the existing text hashing behavior.
- Add shared content-to-tool-output conversion that preserves image references, image detail, and audio.
## Testing
Add coverage for typed world-state hashing and preservation of image content and attribution. Expand code-mode output tests to cover input text, output text, file-backed and inline images, and audio.
GitOrigin-RevId: 2ed00d466a3f169b151202f3eef71e667ea64be1
## Why
Unknown fields in TUI keymaps and profile TUI settings fail deserialization even when strict config validation is disabled.
## What changed
Remove Serde's `deny_unknown_fields` from these settings so unknown fields are ignored during deserialization and reported by the shared strict-config policy. Keep `schemars(deny_unknown_fields)` so the generated schema continues to disallow unknown fields.
GitOrigin-RevId: 06985161bc3bbb35648712288c1d00bdd50953ba
## What changed
Launch managed app-server and updater processes directly through the shared background command helper, removing the macOS `taskpolicy -b` wrapper and its availability probe. Remove the associated launch-policy tests and macOS daemon-startup test serialization.
Retain the 30-second macOS readiness timeout because older updaters can pass background policy to replacement daemons during upgrades.
GitOrigin-RevId: d8620a49139bd2a5c226c624cf7908e06ba7ba38
## Why
Curated plugin archives should preserve executable permissions without applying setuid, setgid, or sticky bits.
## What changed
- Upgrade `zip` from 2.4.2 to 9.0.0, retaining the previous feature set and selecting the existing `bzip2-sys` backend explicitly. Update the Cargo and Bazel lockfiles.
- Adapt plugin extraction to fallible entry names and apply Unix permissions through the open output file, using the mode filtered by `zip`.
## Testing
Add a Unix regression test that encodes special permission bits directly in an archive entry and verifies that the extracted file has mode `0o755`.
GitOrigin-RevId: 75ee6879a372a36b34208c1359f42b670c9d3837
## Why
Schema strings and sequences do not grow after construction, and most schema nodes do not contain maps. Retaining collection capacity and inline optional maps adds unnecessary memory overhead.
## What changed
Store `JsonSchema` strings and sequences as boxed strings and slices, and box optional property and definition maps. Adapt constructors, schema consumers, and existing test expectations to the new representation while preserving the serialized JSON Schema format.
GitOrigin-RevId: 0a249b1ae32932cbbfe3c575c32bfd20b060c303
## What changed
- Display the leading `/` in the prompt marker instead of the editable text, sharing prefix state with shell mode's `!`.
- Preserve command prefixes and text element offsets across submission, queuing, history, and external editing. Keep prefixes literal in plain-text composers.
- Track composer-owned slash command elements separately, omit them from exported draft elements, and refresh them when command availability changes.
- Let backward deletion at the start of the text remove the prompt prefix while preserving selected-text deletion and Vim Replace recovery.
## Testing
Add regression coverage for slash prompt cursor placement, prefix deletion, history search highlighting, dynamic command availability, and Vim Replace restoration, including Unicode text. Update rendering snapshots for the slash prompt marker.
GitOrigin-RevId: 0da42da8e98bf7885f9b0ba2c8d5ad4f44d6847e
## What changed
Add the `multi_env_copy_file` feature flag, disabled by default and marked as under development, to the feature registry and configuration schema. Install the file-copy extension in app-server threads and CLI debug prompt construction when the flag is enabled.
GitOrigin-RevId: 6d8b4c7479974f4b70c39f52333491c13d60d2a2
## Why
Removing a directory while its lock file is open can leave `.nfs*` entries on NFS and prevent cleanup.
## What changed
- Drop the `Arg0PathEntryGuard` lock file before its temporary directory.
- On Unix, rename stale helper directories while locked, then close the lock before deleting them. This prevents initializers from publishing at the old path during cleanup.
## Testing
Extend the guard lifetime test to all platforms and assert that its directory is removed after main returns. Strengthen the janitor test to check that cleanup leaves the temporary root empty.
GitOrigin-RevId: 2524afcc63ed7769a7d16b622c1d447918f9478b
## What changed
Pass `BUILDBUDDY_API_KEY` to Linux, macOS, and Windows voice release builds, and give the dedicated macOS and Windows voice jobs access to the `bazel` environment without creating deployments.
Use the shared Bazel preparation action and BuildBuddy wrapper for Linux and macOS voice builds so they inherit the existing repository cache and remote cache configuration.
GitOrigin-RevId: 52cdf05bc4567f3e8c460d2509e57bb30e667868
## Why
Publishing a draft prerelease emits a `published` event instead of a `prereleased` event.
## What changed
Create GitHub prereleases with `--draft=false` so they emit `prereleased` events. Keep stable releases as drafts until all asset uploads succeed.
GitOrigin-RevId: 145fd84f852d7ee9cb3c4edff7007a34c3389e1c
## Why
Prereleases were published before their assets finished uploading, exposing incomplete releases.
## What changed
Create new prereleases as drafts, matching stable releases, and publish them only after all asset uploads succeed. Publishing a draft emits a `published` event rather than a `prereleased` event.
GitOrigin-RevId: 0d1c52038bb9b7beb4b5b9bf52f0ef4c3734de61
## What changed
Add `third_party/v8/icu.BUILD.bazel` and wire V8's ICU repository to use it instead of patching upstream `bazel/BUILD.icu`.
Select ICU's custom libc++ flags and runtime dependencies through `//third_party/v8:use_rusty_v8_custom_libcxx`, keeping ICU aligned with V8 and its host generators.
GitOrigin-RevId: 92a1b883f5d42d9a3a464002e922295ab166f2bd
## What changed
Read `desktop.uninstall_codex_home` from the owner's current `config.toml` before recursively deleting a desktop-created Codex home during Windows sandbox uninstall.
- Preserve the home by default for ordinary installations; retain the deletion default for OEM preinstalls when no preference is set.
- Let an explicit boolean preference override either default. Preserve the home when configuration is unreadable, malformed, or contains an invalid preference.
- Capture OEM metadata before Windows removes it during uninstall, and revoke sandbox permissions on retained homes.
## Testing
Add unit tests for missing preferences, explicit overrides, malformed or invalid configuration, and configuration read failures across both installation defaults.
GitOrigin-RevId: 46afc2a7b0f4ecf7f447e46b515e50d0d278e4a8
## Why
MCP tool discovery discarded response-level `_meta`, leaving server-status clients unable to inspect metadata associated with the tool catalog.
## What changed
- Preserve opaque `_meta` from the first `tools/list` page through catalog refreshes and caches.
- Expose it as `toolListMeta` in `McpServerStatus`, with `null` when unavailable, and update generated schemas and bindings.
- Scope cached Apps catalog metadata to discovery settings, including client capabilities and extensions, while retaining tools from older caches without metadata.
- Restrict server capabilities in status snapshots to the selected servers.
## Testing
Add regression coverage for listing legacy cached Apps tools during failed startup, and update protocol serialization expectations for nullable `toolListMeta`.
GitOrigin-RevId: 62335e2fd8c482067a7a78a7612b58c3eaa9fb55
## Why
A thread ID alone does not identify the backend that owns a session. Resume and fork selections must retain that ownership across connection replacement so they cannot operate on another backend, even when thread IDs match.
## What changed
- Add a process-local `BackendId` to app-server sessions and session targets, preserving it across reconnects and auxiliary picker connections.
- Reject selections from a different backend before changing session state or sending resume, fork, or unarchive requests.
- Disable local-daemon fallback to an embedded server for auxiliary pickers and after selecting a session, while retaining fallback for fresh startup.
## Testing
Add regression coverage for foreign selections with matching thread IDs, startup resume and fork rejection before requests, shared ownership across picker connections, and fallback eligibility.
GitOrigin-RevId: 05a3ca0a901a8dc24337d130548aa2c048b4d586
## Why
MCP tool calls reported every aborted approval as "user cancelled MCP tool call", including interrupted requests and automatic cancellations in `exec` mode.
## What changed
Carry `user`, `interrupted`, or `non_interactive` cancellation reasons through MCP approval metadata and resolution. Mark explicit TUI cancellations as user actions, interrupted requests as interruptions, and automatic `exec` cancellations as non-interactive.
Use the reason to report when a call was cancelled before approval or because interactive approval is unavailable in `exec` mode. Preserve the existing cancellation message for clients that omit the reason.
## Testing
Update tests to verify that a closed approval response carries the interruption reason and that `exec` cancellation responses include the non-interactive reason.
GitOrigin-RevId: be2a5f7fef539b5db2add53b46aea27e2b8a66fc
## What changed
Add the `codex-multi-env-copy-file` extension, exposing `multi_env_copy_file` when registered by the host. Copy files between distinct selected environments without loading their contents into model context, and return `bytes_copied` on completion.
Require absolute paths in each environment's native path convention and enforce each endpoint's sandbox policy and permission grants. Stream file contents where supported, with a buffered fallback for older executors. Reject same-environment copies and report I/O error kinds without exposing connection details. Warn that failed writes may leave a truncated or partially written target.
## Testing
Add integration tests for binary transfers in both directions, local and remote executors, path validation, opt-in tool visibility, endpoint permissions and grants, and unavailable or disconnected executors. Verify that copied contents stay outside model context.
GitOrigin-RevId: f5d9e423d105019834e0288828cb68c5711b3a49
## What changed
- Switch argument-comment lint, rusty-v8 release, and V8 canary jobs to `prepare-bazel-ci` to restore repository caches and configure execution logs. Use `bazel-argument-comment-lint` and `bazel-v8` cache scopes.
- Include changes to `prepare-bazel-ci` in V8 canary path detection.
- Pass `BUILDBUDDY_API_KEY` to the `MODULE.bazel.lock` check.
GitOrigin-RevId: 6ef150f93413d1d30287f0728358eed26e792204
## What changed
Add `ThreadStoreError::Retryable` for transient failures known to be safe to retry and `ThreadStoreError::OutcomeUnknown` for writes that may already have committed. Recovery remains the operation owner's responsibility; neither category automatically triggers retries.
Preserve existing app-server error mappings and fatal session startup behavior, and report the new categories in shutdown diagnostics without exposing raw error payloads.
## Testing
Add coverage for conservative SQLx error classification, mutation error mappings, session initialization categories, and shutdown diagnostics that omit raw error payloads.
GitOrigin-RevId: 259a9bfaa6ff3cbfa2ee61a01a1f1e744c90f118
## Why
MCP servers can expose new tools during discovery. Refreshing the catalog after a tool-list notification lets Codex discover and call those tools in the same turn.
## What changed
- Add the disabled-by-default `mcp_tool_list_changed` feature for ordinary MCP servers.
- Track notifications in transport order and refresh catalogs before subsequent discovery or tool binding. Coalesce concurrent refreshes and retry listings invalidated by notifications, including during pagination.
- Retain the previous catalog on refresh failure, apply a retry cooldown, and invalidate affected startup caches. Allow notification refreshes to proceed while admitted calls finish.
## Testing
Add coverage for same-turn discovery and invocation in direct and Code Mode, notifications during startup and pagination, disabled behavior, cache invalidation, and concurrent refreshes with timeout recovery.
GitOrigin-RevId: 9afee8deba00dd9851b5f32625f61f96965aa00c
## Why
Dynamic tool calls should remain independent while waiting for client responses, so one pending call does not block another from reaching the client.
## What changed
Enable parallel execution in `DynamicToolHandler`, allowing code mode programs to issue concurrent dynamic tool calls with `Promise.all`.
## Testing
Add a code mode regression test that waits for two dynamic tool requests before responding, resolves them in reverse order, and verifies that `Promise.all` preserves the expected result order.
GitOrigin-RevId: c93c1fea720f76c772b0e3452ddc8c01fb1a08d8
## Why
Authorization server metadata can advertise scopes unrelated to the MCP resource. Using that list for discovery can request broader scopes than the resource requires.
## What changed
Update `rmcp` and use its initial scope selection during OAuth discovery: prefer scopes from the initial `WWW-Authenticate` challenge, fall back to protected resource metadata, and include `offline_access` when supported. Stop using the authorization server's general scope list as the discovered resource scopes.
## Testing
Add coverage for challenge scope precedence, resource metadata fallback, scope normalization, and exclusion of unrelated authorization server scopes. Add a no-browser login regression test for a preregistered client whose authorization server advertises neither scopes nor dynamic registration.
GitOrigin-RevId: 68d83cf61fb0b73dac9e861e476f484990fd93b6
## What changed
Wait for the rejected socket to close before advancing Tokio's clock through
capped retry delays. Keep socket I/O on real time so pending handshakes cannot
auto-advance their own timeouts.
Return bodyless HTTP 409 responses in the test server, check that neither
rejection restarts fast retries, and assert that recovery preserves the expected
reconnect attempt count. Both cursor and cursorless cases use the updated helper.
GitOrigin-RevId: da167312f28b7e24b864e6929be749865ea70081
## What changed
- Attempt each `npm publish` up to three times, with 10- and 20-second delays and fresh OIDC credentials on each attempt. Continue skipping already-published versions.
- Enable verbose npm logging and retain debug logs as artifacts for seven days, including on failure.
- Use `macos-15-intel` to verify provisioned `x86_64-apple-darwin` packages, while keeping `aarch64-apple-darwin` verification on `macos-15-xlarge`.
GitOrigin-RevId: 1876c66993ecd8cdb44088ab17a3363d21135ec4
## Why
Thread history materialization allocated a buffer for the entire unread rollout suffix before processing records, increasing memory use for large rollouts.
## What changed
Read records incrementally with a buffered reader bounded to the captured file end. Reuse the line buffer, preserve trailing partial records for the next pass, and report unexpected EOF if the rollout shrinks during reading.
## Testing
Extend the partial-line boundary test with 64 KiB of padding per record to verify byte offsets and deferred processing until the final newline is durable.
GitOrigin-RevId: c0426e3e364748b117285b248f6988a4fe064b94
## Why
Noise handshake failures before connection readiness returned a generic error even when the transport had reported a specific disconnect reason. No `RpcClient` was reading the connection event channel at that point.
## What changed
Read the pending disconnect event when a Noise rendezvous handshake fails and append its reason to the handshake error when available.
## Testing
Add a regression test covering unexpected text frames and relay stream resets, checking that each produces the expected transport reason in the handshake error.
GitOrigin-RevId: 9b8ef9c8dcba75b46d51dc67784af46d4ca74b85
## What changed
Replace fixed release pins for app-server/exec-server compatibility tests with the latest stable version and the stable release published closest to 60 days ago. Exclude drafts and prereleases, and prefer the higher version when publication dates are equally close.
Resolve release versions and SHA-256 asset digests before Linux Bazel CI runs, passing them through `CODEX_COMPAT_RELEASES` to the release archive repositories. Reuse the argument comment lint action so it also prepares compatibility releases. Add bounded retries for transient GitHub release reads.
## Testing
Add unit coverage for stable release filtering, version ordering, nearest publication dates, tie-breaking, and deduplication when both selections resolve to the same release.
GitOrigin-RevId: 5a8cf8bdabd77ab3fa89bbb711367b5d9ce8044b
## Why
A plugin's scripts can change without changing its hook declaration. Declaration-only approval therefore lets changed plugin code run under an existing hook approval.
## What changed
- Fingerprint plugin bundle contents and include the content hash in the approval value returned by `hooks/list`. Persist it as `trusted_content_hash`, keeping `trusted_hash` compatible with older clients.
- Verify contents before each command or MCP hook execution, within the hook's timeout, and require renewed approval when approved contents change.
- Migrate legacy declaration-only approvals to a shared, immutable content baseline per plugin and config home.
- Exclude generated Python bytecode, `.venv`, and `.egg-info` entries from fingerprints. Run app-server hook listing on blocking tasks.
## Testing
Extend integration coverage for plugin upgrades and rollbacks requiring approval, same-turn script changes preventing further hook execution, shared legacy approval baselines, and generated Python artifacts preserving trust.
GitOrigin-RevId: faaf7658210d8adb2534ddd614c72ec993920840
## What changed
Recognize `codex_app.create_thread` deliveries when capturing sender context so Guardian receives the sender's recent user messages and assistant context for delegated tasks.
## Testing
Extend the sender-context integration test to cover `create_thread`, including reviewer-only context and clearing the snapshot on a subsequent delivery without sender provenance.
GitOrigin-RevId: 7a47c3ac5b9c9405e6728010c494529274b7b73d
## Why
The optional Guardian Decisions comparison rejected non-user messages and trusted skill evidence, and folded trusted tool evidence into the classification rubric.
## What changed
Send evidence as separate messages with their original roles, content order, boundaries, and optional `phase`. Support both `input_text` and `output_text`, keeping trusted tool and skill evidence separate from the rubric. Continue to accept inline images only in user messages and reject unsupported evidence.
## Testing
Update adapter and HTTP contract tests to cover mixed message roles and assistant output. Extend lifecycle coverage to verify that trusted skill evidence reaches Decisions while comparison results leave the baseline risk unchanged.
GitOrigin-RevId: 1b6814fe6db5891fb61604d6846a008c9e456054
## Why
Optimized `Array.prototype.sort` can write objects into incompatible array element storage when receiver element kinds differ and the comparator mutates the array.
## What changed
- Upgrade `v8` to `152.2.0`, the Bazel V8 source to `15.2.124.1`, and ICU data and initialization to version 78.
- Backport element-kind agreement checks for sort inlining in TurboFan and Maglev. Apply the patch to Bazel builds and Windows MSVC source builds, and include it in source-build cache keys and canary triggers.
- Refresh pinned sandbox archives and bindings, extend Bazel prebuilt coverage to musl Linux, and use matching sandbox bindings on Windows MSVC.
- Update Bazel integration patches and runtime dependencies for the new V8 release, and download the pinned Windows build tools in source-build workflows.
## Testing
Include the upstream sort regression test covering mixed element kinds, comparator mutation, and continued optimization for matching kinds. Add a test requiring canary and Windows source builds when the backport changes, and update artifact-fetch tests for the new version.
GitOrigin-RevId: 138b7821cddd25466c10aced1dd22be24837caf0
## What changed
Add `write_file_stream` to `ExecutorFileSystem` and `EnvironmentAccess`, preserving the accessor's captured sandbox permissions. Local and streaming-capable remote filesystems replace files one bounded chunk at a time and return the byte count. Older executors buffer the input before sending a single `writeFile` request.
Close remote handles on completion or failure, perform best-effort cleanup after cancellation, and invalidate pending metadata lookups. Document that failure or cancellation can leave a truncated or partial file and that in-flight I/O may outlive cancellation.
## Testing
Add coverage for sequential writes, binary and empty files across local and remote filesystems, source failures, handle cleanup, metadata invalidation after cancellation, and compatibility with older executors.
GitOrigin-RevId: d3eb44e0ac2f0f336e9e157d686464f4d45a3f26
## What changed
Replace the Tokio mutex protecting `RemoteFileSystem`'s in-flight metadata request map with `std::sync::Mutex`. Keep metadata I/O outside the lock and centralize locking in a helper that recovers poisoned guards.
Update the existing concurrent metadata request test to use the locking helper.
GitOrigin-RevId: 78aaecfbd8e8af9c1e5ea273758a414b0ad679a5
## Why
Missing protected metadata paths already receive read-only synthetic mounts, as established in https://github.com/openai/codex/pull/39629. The fallback creation monitor no longer receives any targets because those paths are included in the read-only mount list.
## What changed
Remove `ProtectedCreateTarget` tracking and its inotify monitor, deletion fallback, registry markers, startup pipe, and policy-violation exit override. Keep synthetic mount cleanup and propagate the bubblewrap child's exit status directly.
GitOrigin-RevId: ac747860cad845ebb89ada5a9c1009e56835c4fb
## What changed
- Add `--executor-credential-stdin` to read newline-delimited JSON credentials bound to the configured environment. Require an initial credential within 30 seconds and accept subsequent rotations.
- Reject expired credentials on each request, and stop the executor on invalid input or stdin closure. Limit credential frames to 16 KiB.
- Use scoped bearer authentication for registry requests without account credential fallback or WebSocket authentication headers. Skip workload identity loading and configured telemetry exporters in this mode.
## Testing
Add unit and integration coverage for rotation, expiry, malformed frames, environment mismatches, stdin closure, registry-only authentication, credential redaction, and telemetry exporter isolation.
GitOrigin-RevId: 30a94478165395144a765450f5ec6b3697acdd55
## What changed
- Show `Exited (status N)` instead of `Failed (exit N)` for compact command output, and remove the red bullet styling.
- Label compact exploration counts as `nonzero exit` or `nonzero exits` instead of `failed`, and remove the red styling from the count.
## Testing
Update snapshots for compact command output and exploration summaries to reflect the new labels and styling.
GitOrigin-RevId: 043593720cc3837ca530d1c008565695abcd5af1
## Why
Remote credential masking previously supported only Bash commands without login startup or shell snapshots, leaving Zsh commands with unmasked credentials.
## What changed
- Enable masking for Zsh login commands using shell snapshots on Linux and macOS.
- Capture trusted startup profiles per launch, bind the credential broker to the resulting environment, and replace credentials and supported aliases with placeholders before snapshot replay.
- Preserve explicit environment overrides, credential unsets, and launcher-managed proxy settings during replay.
- Warn and fall back to unmasked startup when a snapshot cannot safely replay credentials; stop execution if protected snapshot restoration fails.
## Testing
Extend remote execution tests for inherited and profile-defined credentials, overrides, destination changes, and unsupported-profile fallback. Add a Zsh scenario snapshot showing a credential placeholder in command output.
GitOrigin-RevId: 83193d6cbc05f3deb0d6d0b9ae80974b353ce900
## What changed
Add optional `remote_plugin_id`, `release_id`, and `auto_provision` fields to `PluginConfig` and the configuration schema. Store remote plugin identity, release, and provisioning metadata without fetching releases or triggering provisioning. Entries containing only this metadata continue to inherit existing plugin activation defaults.
## Testing
Extend configuration round-trip and plugin loader tests to cover remote metadata entries with inherited enablement and with `plugins._default.enabled = false`.
GitOrigin-RevId: bb657c25929cab100982b37120ab62b089eb7044
## Why
Explicitly selecting the default daemon socket previously classified the TUI connection as remote, changing how local configuration and thread parameters were handled. A socket at that path may also be an SSH forward, so the path alone cannot establish that the daemon is local.
## What changed
- Verify the default daemon endpoint before classifying an explicit connection as local. On Unix, check the expected symlink target and the private socket directory's ownership and permissions, then connect to the protected endpoint directly.
- Preserve local workspace behavior and local thread parameters for verified attachments while keeping directly bound Unix sockets classified as remote.
- Report a missing explicitly requested socket, disable embedded fallback for explicit attachments, and restrict daemon auto-start to implicit connections.
## Testing
Extend tests to cover explicit and implicit local target selection, verified socket resolution, and rejection of a directly bound socket as a local daemon endpoint.
GitOrigin-RevId: ac2226ca1c5f60b26aad9571f945e3325d3bebfa
## What changed
Add optional `inputImages` metadata containing each referenced local image's path and SHA-256 hash of the bytes read before normalization. Compute the hash from the same bytes used to prepare the edit request.
Preserve this metadata through completion events, persisted thread history, resume, and legacy rollout migration. Update app-server schemas and generated TypeScript and Python types; older items continue to deserialize without the field.
## Testing
Add coverage for input ordering, changed contents at the same path, unreadable or invalid references, serialization, persisted history and resume, and legacy migration.
GitOrigin-RevId: 522be8ec1e39c9b2bbe5b9ccb37ea67d17f0e21a
## Why
Flowcharts with `<br>` tags in node labels previously fell back to source instead of rendering as terminal diagrams.
## What changed
Render `<br>`, `<br/>`, and `<br />` as line breaks in quoted and unquoted flowchart node labels. Apply the 40-display-cell label limit per line and keep the decision marker on the first line. Continue rejecting other HTML, break tags in edge labels, and labels containing only breaks or whitespace.
## Testing
Extend rendering snapshots across all four flowchart directions and cover per-line width limits and unsupported markup. Update TUI streaming tests to cover multiline rendering, resizing, source fallback, and preservation of the original source for copying.
GitOrigin-RevId: 61f2a84c8bb161ac4a1c26ddaa0569f52bfea749
## Why
SQLite page reclamation on NFS creates I/O load and contention.
## What changed
Detect whether `sqlite_home` is on NFS on Linux and skip reclamation before opening a maintenance connection. Cache successful filesystem probes across `SqliteConfig` clones while allowing failed probes to retry.
## Testing
Add tests for shared probe caching and recovery after a missing directory is created. Update reclamation coverage to expect no reclaimed pages or file shrinkage on NFS.
GitOrigin-RevId: 4f627cabc6ad712171654c3f8b8659d2f632bbba
## Why
Live descendants previously blocked suspension of an unfinished root turn, requiring callers to stop and unload them before recovering the root elsewhere.
## What changed
Allow `suspend_turn_and_shutdown` to suspend the root and initiate shutdown of all sessions sharing its local agent runtime, fencing new starts. Remove `SuspendTurnOutcome::HasLiveDescendants`.
Success confirms that the root has stopped and its history writer is flushed and closed; descendant cleanup completes separately. Callers must finish tree shutdown or fence and terminate the tree's persistence writers before transferring ownership. Interrupted descendants are not automatically recovered.
## Testing
Extend integration coverage to verify child shutdown, recovery under the original root turn ID without restarting children, and separate reporting of child writer failures.
GitOrigin-RevId: 5adc240ae6e34654209154ee9324621a2bd604d5
## What changed
- Launch managed processes through `taskpolicy -b` on macOS when a five-second probe succeeds, preserving the managed process PID. Fall back to direct launch if the probe fails or times out.
- Increase the macOS startup timeout from 10 to 30 seconds to accommodate background CPU and I/O scheduling, and serialize daemon startup test fixtures on macOS.
- Use the shared background command helper and retain `CREATE_NO_WINDOW` alongside Windows detachment flags.
## Testing
Add macOS tests for PID preservation, background priority when available, and direct-launch fallback after a probe timeout.
GitOrigin-RevId: ab3328e2e8f62218ac9602e4172563c00056875b
## What changed
- Upload generated images to the attachment store and expose `fileId` in image-generation items when available, with inline `result` fallback on upload or decoding failure.
- Preserve file references through legacy events, persisted rollouts, thread history, and task output summaries. Keep model-facing image preparation separate.
- Add attachment request tags and mark generated-image uploads with `usage=image_gen`, preserving the thread's ephemeral setting.
- Update public schemas and SDK types to accept either image representation, retain the Python `ImageGenerationThreadItem` alias, and prefer `fileId` when reading records containing both fields.
## Testing
Add coverage for file-backed generation and rollout persistence, legacy history replay, inline and transitional serialization, task output visibility, and Python SDK alias compatibility.
GitOrigin-RevId: f7a2bb5707e2f277348a547a988bc33c8e96d891
## Why
Opening an initialized database in `DELETE` journal mode previously attempted to convert it to `WAL`, which could fail while another connection held a write lock.
## What changed
- Initialize `WAL` and incremental auto-vacuum only for databases without a schema, including files left by interrupted initialization.
- Preserve journal and vacuum modes for initialized databases, use `synchronous = EXTRA` for `DELETE` connections, and retain `NORMAL` for `WAL`.
- Close failed initialization pools before retrying and restrict background page reclamation to `WAL` databases.
## Testing
Extend SQLite tests to cover interrupted initialization, opening `DELETE` databases under a write lock across all pool connections, persistence after reopening, and lock release after failed initialization.
GitOrigin-RevId: 23acecfe472618dde8545815e9a1058a51591235
## What changed
Add current terminal title and status line options to the preset picker. Generate `/title` and `/statusline` commands that preserve item order and duplicates, normalize item aliases, and retain the status line color setting. Use `--clear` for empty layouts and disable options containing unavailable items.
## Testing
Extend picker tests and snapshots to cover the new options, generated commands, empty layouts, and unavailable terminal title items.
GitOrigin-RevId: b836b15e87c03249cf479b1c3baf0bd71931a6be
## What changed
Allow inline item selection, such as `/title model reasoning` and `/statusline current-dir --no-colors`, without changing saved defaults. Support `--clear` for both commands and `--colors` or `--no-colors` for `/statusline`, including color-only updates that preserve the current items.
Carry overrides with per-thread input state across navigation and reconnects, and allow these local commands in parent-owned subagent threads. Reject invalid or conflicting arguments before applying changes. Saved editor selections supersede the corresponding overrides.
## Testing
Add coverage for argument parsing, atomic updates, rate-limit item aliases and ambiguity, thread-state restoration, saved-setting interactions, and local command submission in parent-owned threads.
GitOrigin-RevId: 909cc2ede026fbf5c7f9cd52c8cf2ae835084f14
## Why
Creating a preset from current settings only offered the model. Permission presets need to preserve the profile, approval policy, and reviewer to restore the same settings.
## What changed
- Add a “Current permissions” option alongside “Current model” when creating a preset from settings.
- Extend `/permissions` with `--approval-policy` and `--reviewer`, including granular policies and quoted profile names.
- Share argument parsing between `/model` and `/permissions`, supporting quoted arguments and both `--setting=value` and `--setting value` forms.
- Keep full-access confirmation for every reviewer and reject automatic review when unavailable.
## Testing
Add parser tests, preset picker snapshots, and permission-selection tests covering complete settings restoration, invalid arguments, unavailable automatic review, and full-access confirmation.
GitOrigin-RevId: f4c9c3f6e264ee8ea4c5244c79f39f2deb15b771
## What changed
Allow `/permissions <profile-id>` to select a built-in or custom permission profile, for example `/permissions :read-only`. Support `:ask-for-approval` and `:approve-for-me` aliases while preserving feature gates, profile requirements, full-access confirmation, and Windows sandbox setup.
Hold queued input until the selection is confirmed, and retain it on cancellation or failure. Reload custom profile definitions on re-selection without leaving unchanged requests pending.
## Testing
Add coverage for unknown and disabled profiles, approval aliases, confirmation and cancellation, discovery retries, Windows sandbox setup, and queued prompts waiting for server confirmation.
GitOrigin-RevId: ada38d3cfc6d6ac4e84ce5645fe33432c55d63cc
## What changed
Replace the `/presets` recall picker with a responsive menu above the composer. Press `0`–`9` to run a saved preset or create one in an empty slot; use `n`, `s`, `e`, and `d` to create, start from current settings, edit, and delete presets.
Add `tui.keymap.chat.open_presets` with an implicit `leader p` shortcut that yields to existing bindings and explicit configuration. Show the action in `/keymap` and add a shortcut tooltip.
Preserve the composer draft, respect popup ownership, and consume held-key repeats after menu actions.
## Testing
Add snapshots for empty, populated, and narrow preset menus, plus coverage for draft preservation, cancellation, held-key handling, transcript search precedence, and default shortcut conflicts.
GitOrigin-RevId: f438c7015dbd416c90cdeb479d2a15d9d6d24954
## What changed
- Add a TUI picker with ten numbered preset slots, an editor, and confirmation before replacement or deletion.
- Create presets from composer text or current model, reasoning effort, and speed settings. Run saved inputs through the normal queued submission path while preserving the composer draft.
- Persist presets under `tui.presets` in the active user configuration, respecting configuration layer ownership and leaving in-memory settings unchanged when writes fail.
- Preserve permissions when changing effort or speed for the effective model, keep default collaboration settings intact in Plan mode, and allow standard-speed selection with older app servers.
## Testing
Add persistence tests for save, replace, delete, configuration ownership, and write failures; picker and confirmation snapshots; and regression coverage for model permissions and standard-speed fallback.
GitOrigin-RevId: 5f11699112cd404cc8e954872d53495c6edd0c0a
## What changed
Add `tui.presets` entries keyed by a single digit from `0` to `9`, each with an `input` prompt or slash command and an optional `label`. Expose presets in the configuration schema, load them into runtime configuration, and preserve them in TUI local settings.
Reject invalid slots, blank inputs, shell commands beginning with `!` after leading whitespace, and inputs exceeding 8,000 UTF-8 bytes.
## Testing
Extend the runtime configuration test to verify loading both a slash command with a label and a prompt without one.
GitOrigin-RevId: d2911e540bc50f05b4a5224abf17ce4ef5a18ea3
## What changed
Allow `/model [model] --reasoning <level> --speed <tier>` to update the current session without changing saved defaults. Both space-separated and `=` flag values are supported; omitting the model applies settings to the current model. Bare `/model` still opens the picker.
Validate model availability, supported reasoning levels, and speed tiers before applying changes. Reject unknown flags, duplicate settings, and missing values. Apply model, reasoning, and speed together after server acceptance.
Restore each thread's speed when switching threads, and use destination configuration defaults for new sessions instead of carrying over the active session's speed.
## Testing
Extend regression coverage for inline commands, invalid arguments, unchanged saved defaults, settings-only updates to hidden current models, destination speed defaults, and speed restoration on the next turn after switching threads.
GitOrigin-RevId: ad9cecbdb3554e34a6518367364978a37fb68439
## Why
Competing SQLite writers can cause database opening and writes to fail with `SQLITE_BUSY`. Deferred write transactions can also encounter contention after taking a read snapshot.
## What changed
- Add up to two retries with 100 ms and 200 ms delays for SQLite busy errors during pool opening, writer admission, and standalone writes.
- Use a shared `BEGIN IMMEDIATE` helper across state, thread history, and agent message board writes to acquire the writer slot before reading.
- Preserve bound arguments when retrying standalone writes, and commit writes using `RETURNING` before exposing their results. Retry transaction admission without replaying an already-started transaction.
## Testing
Add tests using real SQLite writer contention to verify recovery after a competing writer releases its lock. Queue tests cover enqueue, update, and delete, checking preserved payloads, single revision increments, and no duplicate messages or unintended deletions.
GitOrigin-RevId: ac5bd31a87c67cc47fb385bf3fa5435a54ff70f0
## Why
When a command starts before an assistant message completes, the TUI can flush the streamed text and then render it again when the completion arrives. This duplicates the preamble in both live output and replay.
## What changed
Track the turn ID, item ID, and source text of the flushed message. Skip rendering its completion again when the identity and text match, allowing for the trailing newline added during stream finalization. Continue rendering completions whose identity or text differs.
## Testing
Add an end-to-end test that delays message completion until a command starts and checks that live and replayed transcripts contain the preamble once. Add regression coverage for completions with different text or item IDs.
GitOrigin-RevId: 59af0198a99f26ba8ba2a47644ba662301c30011
## What changed
On Windows, omit network roots whose filesystem identity cannot be inspected when expanding implicit `:root` read access. Retain inspectable shares and roots containing the policy or command working directory, and apply the same filtering during policy inspection and command launch.
Keep explicit grants unchanged and continue expanding `:root` write and deny rules across all executor volumes.
## Testing
Extend policy tests to cover filtered read roots, explicit grant precedence, and approved-command write access across all volumes.
GitOrigin-RevId: c4d7c8ce2c9138cdb4518385e2cd05f66518628e
## Why
A thread-wide index can scan earlier turns when a turn's final item page is underfilled.
## What changed
Force `idx_thread_items_by_turn_page` for turn-scoped item queries when neither `item_ids` nor `after_updated_at_ordinal` is set.
GitOrigin-RevId: 63c86fafa08446351a5d9828b479c497c76a8555
## What changed
- Add `RemoteEnvironmentConfig::with_executor_credential_auth()` for Noise transport, requiring exactly one `Authorization: Bearer <credential>` header without accompanying account credentials.
- Require HTTPS registry URLs except on loopback, and bypass system proxies for loopback HTTP requests.
- Mark credentials as sensitive, suppress registry diagnostics that could echo them, and reject registration responses containing the credential while preserving recognized retry error codes.
- Reject scoped executor credentials for Direct registration and WebSocket connections. Keep legacy authentication as the default.
## Testing
Add tests for invalid credential headers, HTTPS and loopback restrictions, proxy bypass, credential echoes in registry responses, and rejection before Direct transport sends requests.
GitOrigin-RevId: a427d648a0520d2e187dd40ca63268903a949f94
## What changed
Replace duplicated content-kind strings with constants shared by fragment producers and consumers, including authorization checks, forked-history filtering, and memory instructions. Share the compaction summary kind between core and Guardian's transcript filter.
## Testing
Add a regression test verifying that Guardian excludes compaction summaries while retaining surrounding user messages, including a user message with identical text.
GitOrigin-RevId: 36dbdf0f82c61b52d2571ac1c392fb151c98151b
## Why
Syntax theme colors can have insufficient contrast against the terminal background or the shaded proposed-plan surface.
## What changed
- Adapt themed Markdown foreground colors to the terminal background while preserving inline code colors from the syntax theme.
- Adjust proposed-plan foreground colors after applying the plan background, including retained styles used for reflow. Apply the same styling to streamed and completed plans.
## Testing
Expand snapshots across syntax themes and light and dark backgrounds, and cover proposed-plan tables and streamed plans with wrapped hyperlinks. Update streaming assertions to expect contrast-adjusted blockquote colors.
GitOrigin-RevId: 0e358412562c438af17be5bcded9d058b56212b7
## What changed
Negotiate executor support for `credential_masking` and enable built-in credential brokerage in executor-local network proxies. Supported non-login Bash commands on Linux and macOS receive credential placeholders, with real credentials injected by the proxy for matching destinations.
Retain credential mappings across process launches within the same executor session, scoped by environment, conversation, and broker configuration. Keep credentials and destination context on the executor.
Fall back to unmasked execution for unsupported shells or shell startup, and for configured credential providers. Emit warnings when masking is unavailable, preserving shell profiles and snapshots.
## Testing
Add coverage for capability negotiation, fallback behavior, mapping reuse and isolation, proxy credential injection, and keeping executor credentials out of model-visible request history. Test warning, removal, and rejection modes for credentials left unmasked during preparation.
GitOrigin-RevId: f64e916a5de8350fa0d289d3440ec29761accd75
## Why
Local compaction stores generated summaries with the `user` wire role, but those summaries are not user authorization. Guardian transcripts need to preserve that distinction when reviewing compacted history.
## What changed
Classify messages marked with `compaction.summary` as assistant entries in Guardian transcripts, while preserving the attribution of actual user messages.
## Testing
Add transcript collection coverage and regression tests for both line and JSON transcripts that verify generated summaries are attributed to the assistant and original user instructions remain attributed to the user.
GitOrigin-RevId: 66183028ce70a2500d47d3347b110f95471ba868
## What changed
- Add `ComposedContext::retain_new_images` and use it in Guardian review sessions and the async scorer. Compare host-prepared image references against admitted history, ignoring image detail, and skip scanning history when no images need checking.
- Restore `ConversationState` directly from a checkpoint, retaining committed history for rollback or transferring it with `take_history` for ephemeral forks.
## Testing
Extend tests for prepared-image matching across differing detail levels, image-free continuations that avoid scanning history, and checkpoint restoration and history transfer.
GitOrigin-RevId: bafeb6de9babc721182be43d0eb1a653955a0ebb
## Why
On case-insensitive macOS filesystems, paths such as `.GIT/config` refer to protected `.git/config` metadata but can pass case-sensitive write permission checks.
## What changed
Check native filesystem case sensitivity when matching protected metadata paths, including case aliases in workspace roots. Recheck both the target and policy entries with normalized aliases so explicit metadata grants and narrower restrictions retain their precedence. Return errors when filesystem case sensitivity cannot be established.
## Testing
Add macOS coverage for metadata and workspace-root case aliases, explicit grants, narrower restrictions, and missing directories. Strengthen the patch regression test to assert the approval rejection message for both direct `apply_patch` calls and shell interception.
GitOrigin-RevId: 8ae2eb97ce6ec71c51bead130515b9ce6c1cdfab
## What changed
Add an integration test that approves a sandboxed `exec_command` attempt, simulates a sandbox denial, and denies the subsequent unsandboxed retry. Verify that Guardian reviews the retry separately with `require_escalated`, that the denied retry never reaches the executor, and that the tool result includes the denial rationale.
Use a fake executor to exercise the sandbox denial consistently across hosts.
GitOrigin-RevId: cd644255f7a7b7561c9e52a5b6e40f0859b70547
## Why
A failed Guardian inference can retain its input in a reusable session. Tracking transcript progress only after successful reviews can admit the same evidence again on retry.
## What changed
Advance transcript progress when a failed turn has retained its input and the session remains reusable, without counting it as a completed review or changing the committed fork checkpoint. Leave progress unchanged when failure occurs before input admission.
## Testing
Extend regression coverage for encrypted agent messages across review retries, pending evidence after compaction failures, and fork checkpoints after transcript admission without a completed review.
GitOrigin-RevId: 36239ec9d47f484bcfe68d65e7c8d8ab8660db0d
## Why
Guardian approval covers the permissions of the reviewed action. A retry outside the sandbox needs a fresh review of its broader permissions.
## What changed
- Track the initial approval source so Guardian approval does not preapprove an escalated retry, while preserving existing user and hook approval behavior.
- For exec retries that can run without the sandbox, set the approval action to `RequireEscalated` and clear `additional_permissions` so review and caching reflect the retry's actual permissions.
GitOrigin-RevId: 06f8d53745a7bcfe9fdb5628ff9e85da6060547d
## Why
Trimming interleaved realtime transcripts by utterance order can discard the latest speech from an earlier utterance. Evicting after each delta can also drop one speaker before the other speaker's delta from the same frame arrives, losing recent instructions at handoff.
## What changed
Use raw frame recency to trim timed frameless bidirectional transcripts within the 8 KiB budget. Defer eviction until the frame advances or the transcript is consumed, and retain both speakers' suffixes when they share the newest frame. Preserve conversation order and fall back to FIFO eviction when timing is unavailable.
Track trimmed prefixes so final transcripts can extend retained speech without making delayed finals appear newer.
## Testing
Add regression coverage for frame recency, same-frame event ordering, UTF-8 truncation, delayed finals, and untimed fallback. Add an app-server handoff test verifying that both speakers' recent speech and the latest user instruction survive while live transcript notifications remain unchanged.
GitOrigin-RevId: b01b729d8bdd4acb26e0385442ce40819355deac
## What changed
- Verify that freeform `apply_patch` calls and shell-intercepted patches cannot modify `.git/config` through `.GIT/config` when approvals are disabled, while an ordinary workspace file remains writable.
- Add macOS Seatbelt coverage for uppercase protected metadata paths, including absent directories, existing directories with either casing, and case variants of the workspace root. Assert that metadata creation and modification are denied while sibling workspace writes succeed.
The tests skip filesystems that do not support the case-insensitive aliases they exercise.
GitOrigin-RevId: 5cf6b0c36eee348e1ba0db0bc2d3bff072458364
## What changed
Use the active syntax theme's markup foregrounds for headings, emphasis, strong text, list markers, links, and blockquotes. Preserve existing bold, italic, and underline modifiers, and retain previous styles when a scope provides no foreground.
## Testing
Update rendering snapshots and streaming blockquote assertions for themed colors. Exercise existing fallback expectations with an empty syntax theme.
GitOrigin-RevId: b00aa4af30f73f538ff5f888a0f9b4edbdc15893
## What changed
Render local viewed images and generated image artifacts as bounded thumbnails in the rich fullscreen transcript using Kitty or Sixel graphics. Viewed images appear when their activity is expanded or the detailed presentation is active; generated images appear alongside their saved-path entry.
Keep previews clipped to the viewport, retain graphics across unrelated redraws, and remove them when overlays open. Bound image decoding and cache memory, and preserve text-only entries for remote workspaces, unsupported terminals, missing files, and oversized images. Image rows do not enter searchable or selectable text.
## Testing
Add layout and snapshot coverage for disclosure, viewport clipping, rewrapping, raw-mode fallback, deleted files, and oversized rasters. Add terminal coverage for retained Kitty graphics, repainting after a clear, local-file transport, and overlay cleanup.
GitOrigin-RevId: fb2ec146331acfcfc82b2b283616671c9ee93757
## What changed
- Remove feature-flag checks from managed worktree creation and repository-aware session discovery, while retaining local workspace and trust checks.
- Make TUI voice availability follow platform support instead of `features.realtime_conversation`.
- Ignore `features.worktrees` and `features.realtime_conversation` configuration overrides, warn when managed requirements reference them, and hide both flags from `/experimental`, including catalogs from older servers.
## Testing
Add coverage for ignored configuration overrides and managed requirements, and update session filtering, worktree grouping, and experimental feature discovery tests for the retired flags.
GitOrigin-RevId: 1d64e890e6e2f8a78926a9ea163126c0890b068e
## Why
MCP servers at `https://gov.chatgpt.com` were treated as untrusted for ChatGPT authentication and switched to OAuth, preventing local Gov Apps from retaining the ChatGPT auth provider.
## What changed
Trust the `https://gov.chatgpt.com` origin alongside the existing ChatGPT origin when resolving MCP server authentication. Origin matching preserves scheme, host, and port restrictions.
## Testing
Add regression coverage for Gov Apps URL construction, trusted origin normalization, rejection of lookalike hosts and nonstandard schemes or ports, and retention of the local ChatGPT auth provider. Verify that explicit OAuth servers and servers in remote environments do not receive the host provider.
GitOrigin-RevId: 7ceaf7c524d963005d9f23204489bbde269f0dd5
## Why
The app server retained its startup model provider for catalog requests, so signing in or out could leave `model/list` using stale provider settings or requiring a restart after managed provider requirements changed.
## What changed
- Invalidate the catalog after successful login and logout, then reload the effective configuration on the next model list or background refresh. Rebuild the models manager when the provider or catalog changes, while preserving existing threads' routes.
- Retain the original project context and the TUI's `--oss` provider selection across reloads. Retry configuration loading after falling back to defaults so temporary failures do not pin the fallback catalog.
- Keep provider policy checks for cached catalogs and apply runtime `api_key_model_discovery` toggles to the active catalog manager.
## Testing
Add and extend tests for provider selection and definition changes after login, catalog reloads after logout, OAuth gateway transitions, fallback recovery, project context, and runtime model discovery toggles.
GitOrigin-RevId: bce2e23ff567e1a52eac2b6ad736a6e63ff61e2b
## Why
The `/keymap` action catalog and root-config binding lookup duplicated the same action inventory, requiring both to be maintained together.
## What changed
Use `define_keymap_actions!` to generate `KEYMAP_ACTIONS` and `binding_slot` from a single declaration grouped by context. Preserve the existing action order, descriptions, feature gates, and binding mappings.
GitOrigin-RevId: 182e937d9642a8b5a4aa787691da793712f29010
## Why
Direct mode serves executor requests but applied the client's 8 KiB inbound request limit, causing larger `fs/writeFile` requests to disconnect the executor.
## What changed
Use a dedicated direct WebSocket connection constructor that omits the client inbound request limit while retaining WebSocket message and frame limits.
## Testing
Add a regression test that runs the direct environment and verifies successful file writes above the client request limit using both text and binary WebSocket messages.
GitOrigin-RevId: e8e77a5e8581ab9eb98446e23b77a6da41d64868
## What changed
Tag `codex.tools.incremental_updates` counters with the qualified tool name alongside the action. Continue excluding initial catalogs and namespace headers, while counting each removed namespace member.
Add `codex.tools.spec_description_bytes` to measure UTF-8 description bytes when an existing tool definition is replaced. Skip definitions without descriptions and use logarithmic histogram boundaries up to 1 MiB.
## Testing
Extend namespace transition tests to check per-tool counts and description sizes. Add scenario assertions for replacement metrics with incremental tool updates and their absence on the non-incremental request path.
GitOrigin-RevId: e20e6d81f21a867b285df1f0da005c2806dd03c6
## Why
With granular sandbox approvals disabled, `write_stdin` rejected input to terminals retaining additional permissions even when those permissions were still granted.
## What changed
Let input reach approval review when the terminal's retained permissions match active grants for its environment. Require identical filesystem grants, including entry order, and an active network grant when retained permissions enable network access. Each input still requires review.
Keep rejecting input when retained authority is no longer covered or the approval policy changes to `Never`.
## Testing
Add regression coverage for user and Guardian review, turn grant expiry, session grants, and switching to `Never`. Cover filesystem restrictions, protected metadata, symlinks, and ordered denials, and verify that rejected input never reaches the terminal.
GitOrigin-RevId: 9abf7da8d03b1526d26ca2a718e36349a255330b
## Why
Terminal status previously collapsed completed and failed turns into `idle` and reported blocking prompts without a reason. Blocking detection also depended on terminal title settings.
## What changed
- Emit `done` and `error` through OSC 7501 for live turn results, retaining them until deliberate keyboard, paste, or mouse input acknowledges them. Mouse movement does not acknowledge results.
- Classify blocking requests with `kind=permission`, `kind=question`, or `kind=auth`, including requests hidden behind another view or delayed while typing, independently of terminal title settings.
- Keep pending follow-up work and active goals `working`. Treat interrupted turns and replayed results as `idle` rather than new results.
- Preserve the existing iTerm2 OSC 21337 labels and indicators, mapping `done` and `error` to `Idle`.
## Testing
Add lifecycle and input-acknowledgment tests covering approvals, completion, failure, interruption, replay, pending follow-ups, and active goals. Extend blocking-request assertions and terminal protocol snapshots for the new states and reasons.
GitOrigin-RevId: 90bad1d54d8b3b9e3cec66fbd3bf3df0c42b995b
## What changed
Use the stable and experimental bundles generated by `//bazel/schema:app-server` as compile-time inputs for `app-server-protocol` instead of the checked-in bundles.
Generalize `schema_generator_sources` to `schema_sources` so it can stage Rust sources alongside generated bundles. Keep empty bundle placeholders for the on-demand schema generator, which derives its output from Rust sources.
GitOrigin-RevId: a976c420a3698d631f3ea7c698b15b82391158e5
## What changed
Wait for the subprocess readiness marker before cancelling in
`process_exec_tool_call_cancellation_allows_sigterm_cleanup`, removing the
one-second polling cutoff. Poll readiness alongside execution under the existing
five-second timeout, then cancel and await execution if that timeout expires so
cleanup completes before the test fails.
GitOrigin-RevId: ba47dad9ba87fb5dc3bd087380811655387f825a
## Why
Environment tool availability and selectors should remain stable as selected environments become ready.
## What changed
- Keep configured environment tools advertised even when no execution environment is ready, and derive `environment_id` selectors from all selected environments.
- Return guidance to wait when an environment is unavailable, while preserving errors for unknown environment IDs. Require a usable primary environment for `write_stdin`.
- Always include `shell` and `login` in the `exec_command` schema and mark `stable_environment_tools` as removed.
## Testing
Update integration tests to expect environment tools with empty or starting environments, and remove explicit feature opt-ins from affected scenarios.
GitOrigin-RevId: 1590c1b5be16a39e4a370663c552b881602545b5
## What changed
Emit the Daybreak notice after replacing or removing the placeholder session header so the notice follows the configured header.
## Testing
Extend the resumed-history snapshot test to start with a placeholder header and verify the full transcript order: session header, Daybreak notice, and replayed user and assistant messages.
GitOrigin-RevId: 536f717b2859d2fe319756f52123b4cd0407cb66
## What changed
- Add `//bazel/schema:app-server` to generate stable and experimental schemas from Rust sources without depending on committed precomputed bundles.
- Add `//sdk/python:generated` to generate Python SDK models, the notification registry, and API methods from the stable schema in scratch space, using dependencies from `uv.lock`.
- Add `generate-types --no-format` to skip formatters for build outputs while preserving formatting by default.
## Testing
Extend contract generation tests to regenerate in a temporary SDK copy, checking byte equality for formatted output and AST equality for unformatted output.
GitOrigin-RevId: 9ca7daa8ac0a33c4106a9e95c2f48bbded07df21
## Why
MCP request failures and tool errors reported only through `codex/telemetry` metadata previously received an `unknown` error code, obscuring the failure category.
## What changed
- Classify typed request failures into bounded codes such as `request_timeout`, `transport_closed`, and `protocol_error`, and carry them into MCP call metrics and spans before errors become strings.
- Preserve typed timeouts when a prepared tool call exhausts its deadline during trusted access lookup.
- Accept allowlisted `error_code` values from `codex/telemetry` as a fallback after structured content and connector authentication metadata. Keep model output unchanged and ignore unrecognized metadata codes.
## Testing
Add coverage for typed errors wrapped in context, prepared-call timeout classification, metadata precedence and rejection, unchanged model output, and exported span error attributes.
GitOrigin-RevId: d7a440a6c9119b8a07a7f1fad697eb25af506f00
## What changed
- Upgrade `rules_python` from 1.7.0 to 2.4.2 and update `MODULE.bazel.lock`.
- Enable `--windows_enable_symlinks` in `.bazelrc`, as `rules_python` 2.x requires symlink support for Windows Python launchers.
GitOrigin-RevId: 303da258c74b18d0d0df8d4eebb830c57f14cca4
## Why
Advancing the test clock expires the review, but command cancellation and output drainage still run asynchronously. The model can poll before the final timeout failure is available.
## What changed
Hold the initial tool result until the command emits `ExecCommandEnd`, with a bounded wait that also catches unexpected approval requests or turn completion. Only request a poll when the initial result reports a running process, and accept the timeout output from either `exec_command` or `write_stdin`.
Keep the assertions that the model receives the timeout explanation without a user approval prompt or a misleading user-rejection message.
GitOrigin-RevId: 219a1579dce35caf8f0d45b1d92a7343ec1a8935
## What changed
Add `ListKeymap::vertical_action_for` and `ScrollState::apply_vertical_action` to share key resolution, selection movement, and visibility handling across the experimental features, hooks, memories, skills, and multi-select views. Preserve navigation priority, search input handling, and item reordering precedence.
## Testing
Update scroll-state tests to exercise the shared action handler and picker tests to navigate through key events. Cover overlapping page-down and move-left bindings when item reordering is disabled.
GitOrigin-RevId: 29927b0a4de0fbeb4c0dd19c418b8f60fffb8a7d
## Why
Coordinated MCP OAuth refresh must stop retrying a definitively rejected refresh token, including after the runtime is rebuilt.
## What changed
Remove the rejected refresh token while preserving the access token and credential record. Compare stored credentials under the appropriate locks before writing so a replacement login is preserved, and update file entries using their existing keys.
Keep rejection handling alive through caller cancellation and prevent reuse within the runtime even if persistence fails. For ordinary direct-keyring credentials shared across `CODEX_HOME` directories, retire the token only in the current runtime because locking does not span those directories. Report persistence failures without exposing backend diagnostics.
## Testing
Add coverage for reauthentication after runtime rebuild, legacy file keys, cancellation with a concurrent credential replacement, keyring scope, and persistence failures with diagnostic redaction.
GitOrigin-RevId: a6e602ca2e2893ed711d853becc45142d9575fab
## Why
PowerShell safety checks can mistake a literal `start` argument for a URL-launch command, or combine a process launch with a URL from a separate command.
## What changed
Classify independently parsed literal PowerShell commands separately so commands such as `Write-Output start 'https://example.com'` do not trigger URL-launch checks. Retain conservative checks for pipelines, script state, executable strings, and shell or terminal wrappers, while continuing to detect actual URL launches and destructive commands.
## Testing
Add policy regression coverage for literal arguments, separate commands, URL launches, wrappers, and destructive commands, plus a Windows integration test covering execution and policy rejection.
GitOrigin-RevId: 2878aa86bc36b44c60230cc1de3430922b28b81a
## What changed
Rename the grant manager and supporting modules in `codex-rs/login` to expose `OAuthSessionManager`, its configuration and status types, `OAuthLoginControl`, and `subscribe_oauth_session_status`.
Keep the existing gateway API names as compatibility aliases and retain the credential storage paths and namespace so saved credentials remain usable. Update the existing authentication tests to use the OAuth session API.
GitOrigin-RevId: 72cea12be606dde28cf42809e7f8b8807cbc4a2a
## Why
Remote MCP environment filtering could drop `SystemDrive` and `LocalAppData`. Explicit overrides also need Windows-aware merging to replace inherited variables with differently cased names.
## What changed
- Preserve `SYSTEMDRIVE` and `LOCALAPPDATA` when remote environment variables activate the allowlist.
- Apply explicit environment overrides through the executor environment policy, while retaining the final overlay for variables excluded by the allowlist.
## Testing
Extend environment-policy tests to cover the additional Windows variables, overrides with differently cased names, and the final overlay used by older executors.
GitOrigin-RevId: 36df69117f248536e47cf7e1d855b99a138fe698
## Why
Unarchiving a thread previously read rollout metadata across both active and archived history, including unrelated threads.
## What changed
Use `RolloutReferenceIndex::scan_archived_threads` to restrict discovery to archived files whose canonical filenames match the requested thread. Continue validating ownership through session metadata and include compressed and reverted rollouts.
## Testing
Add coverage for compressed and replacement archived rollouts, metadata ownership mismatches, unrelated filenames, and exclusion of active rollouts.
GitOrigin-RevId: 8784f3502b839dcb4a3839744010e350d0196545
## Why
Thread stores need a way to reuse history and writer state loaded while preparing a resume, rather than loading them again during session startup.
## What changed
- Add an opaque, single-use `ThreadStoreResumePreparation` and an optional preparation in `StartThreadOptions`.
- Pass preparation through session startup to `ThreadStore::resume_thread_with_preparation`, which defaults to an unsupported-operation error.
- Reject preparation for ephemeral threads or threads without resumed history. Continue using `resume_thread` when no preparation is supplied.
## Testing
Add a regression test verifying that supplied preparation selects the prepared store path and propagates its unsupported-operation error instead of falling back to ordinary resume.
GitOrigin-RevId: 26537d9b83443bd56341d6afc713f32b999dc67c
## Why
Native extensions need configured Responses metadata for request attribution, but extension calls used the MCP metadata template, which omits it. Image requests also did not forward the turn metadata to the backend.
## What changed
Use the Responses metadata template for native extension calls while continuing to exclude tool inventory. Forward the resulting metadata in the `x-codex-turn-metadata` header on image generation and edit requests.
## Testing
Extend metadata tests to cover configured values in extension calls and app-server tests to verify `display_name` and `turn_trigger` on image generation and edit requests, including a Unicode display name.
GitOrigin-RevId: a2ffaa4d15259c662917612391b8717ee34b9c6c
## Why
Unsupported evidence currently shares a single Decisions comparison reason, making it difficult to distinguish why a comparison was skipped.
## What changed
Report separate reasons for unsupported developer messages, other non-user messages, trusted skills, images, and audio. Keep these outcomes classified as `skipped` and retain the generic reason for other unsupported evidence. Expose `TrustedSkills::KIND` for identifying trusted skill fragments.
## Testing
Expand adapter tests for the distinct rejection reasons and add a lifecycle case verifying that trusted skill evidence skips the Decisions request, reports `trusted_skills`, and preserves the baseline score.
GitOrigin-RevId: 98f076d1aa6771d0209e7f5910eed0dcc40c6263
## Why
Concurrent TLS client builds can independently load the same platform trust store. Share overlapping loads while preserving fresh trust reads for later builds.
## What changed
- Share one in-flight native root load without reusing completed loads.
- Bypass sharing when `SSL_CERT_FILE` or `SSL_CERT_DIR` is set, and continue reading custom CA bundles independently for every build.
## Testing
Add tests for overlapping loads, fresh trust after completion, and recovery from a panicking loader. Extend TLS handshake coverage to verify that replacing a custom CA file affects new configurations while existing configurations retain their trust, and that empty or removed files produce errors.
GitOrigin-RevId: 1465ef3faf82f53651d9dbfe314341b17346580b
## Why
Clients need a way to update individual turn metadata entries without replacing the existing client metadata map.
## What changed
Add the experimental `responsesapiClientMetadataPatch` field to `turn/start` and `turn/steer`. Patches add or overwrite entries while retaining other keys and apply after `responsesapiClientMetadata` when both are supplied. The existing field retains replacement semantics, including clearing unprotected entries with an empty map.
Continue protecting reserved metadata keys and preserving targeted `misalignment_override` continuations across updates.
## Testing
Extend the app-server metadata integration test to cover replacement and patch steering, patch precedence at turn start, preservation of unrelated entries during patches, and protection of targeted continuations.
GitOrigin-RevId: 8c4da3ba1b87329da20b5295846bdcf3a88126de
## Why
A queued skill refresh can outlive the workspace it was requested for when the working directory changes.
## What changed
- Refresh skills for the current working directory when the skills management popup closes.
- Ignore queued `ListSkills` commands whose directories do not include the current working directory.
- Require an explicit working directory when constructing `WorkspaceCommand` and always pass it to app-server command execution. Update Git and GitHub metadata probes to use the constructor.
## Testing
Extend regression tests to verify that closing skill management refreshes the configured working directory and that stale skill refreshes after a directory change do not issue a `skills/list` request.
GitOrigin-RevId: 47ad1d95930840b3f6f0e20d7d8fe8d025e789e6
## Why
The Agent Command Center does not open a workspace, so viewing it should not require consent for the launch directory.
## What changed
Skip startup folder consent when opening the agents overview, while preserving initialization for the embedded fallback. Check folder trust before starting the first task, including through `/new` after dismissing the overview. On Windows, retain the sandbox setup prompt after folder trust is granted.
## Testing
Add CLI tests for starting a task from an untrusted folder through the overview and through `/new` after dismissing it. A terminal snapshot verifies that the overview appears before folder consent.
GitOrigin-RevId: 129be14a354b8abde2e8430c81599e2064ccac87
## Why
Replaying an in-progress turn reset the TUI's `Working` timer to zero, hiding time already spent on the turn.
## What changed
Initialize the status timer from the turn's `started_at` timestamp when replaying turns or turn-start notifications. Keep the zero-time fallback when the timestamp is missing, and clamp future timestamps to zero elapsed time.
## Testing
Extend history replay tests to verify elapsed time for both thread snapshots and replayed in-progress turns, and normalize the timer in rendering snapshots.
GitOrigin-RevId: 36a48f43d0d7aa530f1bfe6dbefa9f0885cbd6c7
## What changed
- Preserve approval resolution sources through tool errors and tag cancelled MCP approvals with `error_type=approval`, `error_code=cancelled`, and `approval_source` (`guardian`, `user`, `hook`, or `unknown`). The source identifies the reviewer, not who caused cancellation.
- Record `context_changed` when validating a Guardian allow against changed authorization or review context, even when a concurrent stop or history reset determines the outcome. Retain the flag across retries and fresh-checkpoint recovery, and include it in the Guardian review counter.
GitOrigin-RevId: a19a986a7565f9a78a9bb2eaabdb5651834d28b8
## Why
Loading older history could place transcript entries before the `Thread forked from` notice, separating fork lineage from the session header.
## What changed
Treat fork lineage as a session prefix in both the TUI transcript and transcript overlay so older pages are inserted after it.
## Testing
Add regression tests for repeated history prepends in both paths, verifying that fork lineage stays first.
GitOrigin-RevId: 71497fb7ffa992c72ee08617d318aa3119e71275
## Why
An asynchronous approval currently waits for the redundant synchronous review to finish cancellation cleanup before returning a decision.
## What changed
Cancel the redundant review and let it drain under the parent's `ReviewerTasks` tracker so a current approval can return immediately. Revalidate the approval and check cancellation before approving the action. Hosts without a task tracker continue to wait for cleanup.
Keep the reviewer reservation held until cleanup completes, and let shutdown join the tracked attempt. Discard late results and evidence from the cancelled review.
## Testing
Add tests covering current, invalidated, and cancelled approvals while cleanup is blocked, suppression of late evidence, reviewer reservations during cleanup, and shutdown waiting for abandoned attempts.
GitOrigin-RevId: f227738e545243f99c19a6c557a78d330f9d2767
## What changed
Increase memory extension resource retention from 7 to 14 days before pruning.
## Testing
Update pruning and startup test fixtures for the 14-day retention window, including resources at the exact cutoff.
GitOrigin-RevId: 5044a1262c8806245d90d567cd84b21aa0d3da43
## Why
Collecting a diff previously launched a Git process for every untracked file at once, allowing process counts to grow with the number of files.
## What changed
Limit untracked-file diffs to eight concurrent operations per collection while preserving patch order and skipping failed file diffs. Concurrent collections each retain their own limit.
## Testing
Add tests for independent concurrency limits, failed-file handling, and patch order and application with tracked changes, binary files, and filenames containing spaces or a leading dash.
GitOrigin-RevId: 896e896eae62ba9b7acf3e8946c235fe725ced40
## Why
Windows MXC needs valid host startup variables, while an empty child environment must remain empty for the SDK to select Windows user-profile defaults.
## What changed
- Replace caller overrides of `SystemDrive` and `LOCALAPPDATA` case-insensitively with nonempty Unicode host values, failing before launch if either is unavailable.
- Track whether the original child environment was empty, ignoring launcher transport keys. Supply host `SystemRoot` for launcher bootstrap in that case, then clear the bootstrap environment before the SDK selects defaults.
## Testing
Extend transport tests to cover host-value replacement and preservation of empty child environments. Strengthen the PowerShell fallback RPC test to require `SystemDrive`, `LOCALAPPDATA`, `USERPROFILE`, and `PATH` in the child.
GitOrigin-RevId: a097e1079069ef897ebb5ba5e63546328c5faeaa
## Why
Compression replaces `.jsonl` rollout files with `.jsonl.zst` files, so checking only the original path can skip existing sessions. Compression can also replace a file between path lookup and canonicalization.
## What changed
- Resolve compressed rollout alternatives when selecting the latest local session.
- Retry rollout path resolution when files disappear during lookup or canonicalization.
## Testing
Extend coverage to verify latest-session filtering after startup compression and resuming a compressed rollout through its original relative `.jsonl` path with preserved turns.
GitOrigin-RevId: a4d5c399567ab4c7cd8aaa8b5f38821ee8b8d802
## Why
Doctor's rollout statistics only counted `.jsonl` files, omitting storage used by compressed `.jsonl.zst` rollouts.
## What changed
Recognize compressed rollouts when collecting active and archived file counts, total bytes, and average bytes. Count both physical files when plain and compressed representations coexist, while continuing to ignore unrelated files and compression temporary files.
## Testing
Extend the rollout statistics test to cover nested plain and compressed files, coexisting representations, archived compressed rollouts, and ignored files, with a snapshot of the reported counts and sizes.
GitOrigin-RevId: 46197f9741884668b50fb6a1d0a07060020f12ed
## Why
Filesystem lookups by thread or rollout ID check whether unrelated compressed rollouts have an uncompressed sibling. These checks are unnecessary when the filename does not match the requested ID.
## What changed
Apply the thread or rollout ID filter before resolving plain/compressed file precedence. Preserve preference for uncompressed files and selection of the newest rollout for a thread.
## Testing
Extend lookup tests to cover unrelated compressed files, uncompressed-file precedence, missing rollout IDs, and rollout ID tie-breaking for files with the same timestamp.
GitOrigin-RevId: 5bdb56ebec8031fceb5f6adbfcf644ad010e52f2
## What changed
Include a `refresh_reason` diagnostic in ChatGPT OAuth token refresh requests to distinguish `proactive_expiry`, `scheduled`, `unauthorized_recovery`, and `forced` refreshes. Omit the field for gateway refresh requests.
## Testing
Extend refresh tests to check the reported reasons, including scheduled refreshes when access token expiry is unavailable.
GitOrigin-RevId: b0294a61ffc3089a66e7b132d4f45661a9e18d38
## Why
A remote primary environment could supply its working directory and workspace roots to host plugins and MCP processes, breaking relative MCP executable resolution and applying the wrong workspace permissions.
## What changed
- Build host configuration from the local environment, falling back to the session's host working directory and runtime workspace roots when no local environment is selected. Preserve explicitly empty local roots.
- Use the same host configuration for MCP startup and refresh, and refresh MCP state when runtime workspace roots change.
- Keep repository skill discovery paired with the primary executor's working directory and filesystem.
- Box skill warmup and turn context construction futures to reduce enclosing future sizes.
## Testing
Extend the MCP integration test to cover a remote primary with populated, empty, or absent local roots; relative executable resolution before and after refresh; workspace-root revocation; and remote repository skill discovery.
GitOrigin-RevId: 21a73c90507b55fd94261e7bf348695ff8466a24
## Why
Stale authorization requires refreshing local evidence, so service retry backoff unnecessarily delays the next review attempt.
## What changed
Yield cooperatively before retrying `StaleAuthorization`, then check cancellation and the shared deadline. Keep retries within the existing attempt budget.
## Testing
Extend paused-time tests to cover recovery with fresh evidence and exhaustion of the shared attempt budget, asserting that retries incur no backoff and return the final attempt's evidence.
GitOrigin-RevId: fda7ddd040a761d08883740bb5e7aaecacfa6091
## Why
PTY reads can split a redraw while the reconnect notice is temporarily erased. The test can then submit `/status` before reconnection finishes, when Enter is suppressed.
## What changed
Make the `discovered` daemon startup test inspect only completed synchronized terminal updates. Type `/status` separately from Enter and wait for its command popup before submitting. Gate both inputs on a replacement daemon PID and the absence of the reconnect notice.
GitOrigin-RevId: a99af0f26753d81458dbce2c30ecc120ff78d3f4
Extend phase-one request tests for both memory versions with reasoning,
developer messages, and assistant ciphertext whose combined size exceeds
the reader budget while individual records remain below the record limit.
Verify that earlier extraction evidence and assistant text alongside large
ciphertext remain in the request, with `encrypted_content` excluded.
GitOrigin-RevId: f0e85e368e5a94d491d0aa4ae1688f47d873ccd9
## Why
Blocking rollout reads can continue decompressing and scanning history after the calling async task is dropped.
## What changed
Propagate caller cancellation through rollout readers, prefix validation, model-context scans, history materialization, and working-directory lookup. Check cancellation during compressed input and output, bounded reads, seeks, and between history records. Return an error on cancellation so partial history cannot be mistaken for a complete read.
## Testing
Add regression coverage for dropping a caller during decompression, cancelling compressed input and output (including skippable frames), cancelling reads and seeks on plain and decoded snapshots, and cancelling history materialization between records.
GitOrigin-RevId: e3dac952789b53402f2a5f17c2a2232506feb9d6
## What changed
Read rollout evidence from newest to oldest for both memory versions, retaining up to 8 MiB of sanitized response items and inter-agent communications, then restore chronological order. Skip malformed records and records larger than 1 MiB, and require valid session metadata in the first record within that limit.
## Testing
Add coverage for the retained byte budget, newest-record ordering, malformed and oversized records, and unsupported session metadata. Extend extraction request tests for both memory versions to verify that evidence after an oversized record reaches the model.
GitOrigin-RevId: 55ccbc2477ecb059830d3a55be12bcbc21235303
## Why
Compaction could record partial output before the response completed, leaving failed summaries in conversation history and persisted rollouts.
## What changed
Buffer compaction output until `response.completed` so failed or incomplete attempts leave no partial output in history. Record successful output before the response completion notification, preserving its compaction metadata.
## Testing
Add regression coverage for preserving messages, tool results, and token usage after a disconnected compaction stream, including after restart. Verify incomplete compaction output is excluded from subsequent requests and successful output remains observable and persisted.
GitOrigin-RevId: 8651200b2aae616000c55c1ed63283f3e2c1b8d5
## Why
Archiving or deleting a task blocked dashboard navigation until the server request finished.
## What changed
Keep the dashboard interactive for browsing while archive and delete requests are pending. Hide the affected task immediately and show an inline progress message. Allow selection movement and search while preventing task switching, new tasks, and leaving the dashboard until the request completes.
Preserve the dashboard selection when removing the current task detaches the session.
## Testing
Update archive and delete progress tests and snapshots to cover navigation, resize handling, immediate task hiding, and suppression of task switching and creation while requests are pending.
GitOrigin-RevId: ff6555602bcd84d38e00de55c3032f442589fdcb
## Why
Daemon package tests copy full debug CLI packages. Running these I/O-heavy cases alongside other tests can increase shared-disk writeback pressure.
## What changed
- Move package installation and replacement coverage into the `app_server_daemon_package` test binary, sharing daemon fixtures with the lifecycle tests.
- Reserve all nextest test threads for each package test and add an exclusive Bazel target that runs the cases serially on Linux and macOS.
- Hard-link the prepared fixture executable during package setup, while retaining real independent package copies in the installer.
GitOrigin-RevId: 255ac8caf75d9eb61bafe68f1f9bcfa99ee72484
## Why
Persisted subagent threads could be reported as unavailable when selected after unloading, even though their saved history could be restored.
## What changed
Attempt to resume selected threads marked closed, including those with a cached live channel, and restore their transcript through the existing attachment flow.
## Testing
Extend coverage for V1 and V2 subagents to verify saved transcript restoration, the appropriate direct-input behavior, and reattachment when a close notification from the previous runtime is still queued.
GitOrigin-RevId: f45d16b954ce5f9f30ca4c6c6f640937390dd78d
## Why
Standalone thread settings updates cleared the running turn's continuation lineage, preventing recovery after a daemon restart.
## What changed
Preserve continuation lineage while a task is registered. Continue invalidating pending continuations for idle, reserved, and finishing turns, and record started-turn lineage atomically with task registration.
## Testing
Extend settings invalidation coverage to idle, reserved, and finishing turns. Exercise an in-flight reasoning effort update before compaction, then verify cold resume preserves the turn's frozen settings and allows continuation. Wait for thread idle before testing idle continuation.
GitOrigin-RevId: d7c316af6a4c871790bb57f0af9892bb30871ac8
## Why
Incremental-tool windows recorded base instructions only at setup, so a catalog refresh for the same model could leave active instructions stale. Instruction changes need to reach the model without rewriting the existing history prefix.
## What changed
- Track model identity and instruction content independently, appending a `model_instructions` developer message when either changes. Explicitly mark replacement or removal of base instructions, and avoid repeating unchanged updates.
- Start new windows after compaction with the latest model instructions while preserving custom base instructions.
- Preserve the recorded window base during local compaction retries, including empty instructions, and rebuild current model instructions when reconstructing child context.
## Testing
Add integration tests and request snapshots for catalog refreshes, instruction removal, model switches, compaction, restart, and forks. Extend regression coverage for legacy snapshots and local compaction retries.
GitOrigin-RevId: eeca69067b4d9cd91c817732d79b4d5c1faa18b9
## What changed
- Add `terminal_columns` and `terminal_rows` buckets to `codex.tui.start`.
- Record `codex.tui.terminal_size` for new turns in the active thread and for resize bucket changes after the terminal size settles for 15 seconds. Reuse launch context and suppress duplicate turn notifications.
- Respect analytics consent for the built-in metrics exporter while allowing explicitly configured OTLP collectors. Apply consent checks to the active exporter across provider replacements.
## Testing
Add coverage for exporter replacement and consent after config reloads. Extend the PTY integration test to verify startup size buckets, turn-start observations, and delayed resize observations with analytics disabled and an explicit OTLP collector.
GitOrigin-RevId: e01a900cd3f04a36731078f725c75374596cb01b
## Why
Daemon installation rereads staged files to verify the executable and hash the normalized WinGet package, even though staging already computed their digests.
## What changed
Cache file digests while copying the package and reuse them for the staged executable comparison and final WinGet tree hash. Update cached paths when moving WinGet executables and refresh digests when rewriting manifests.
Continue hashing source packages and existing releases from disk so digest reuse does not bypass content validation.
## Testing
Extend the installation test to corrupt an existing release's `codex-package.json` and verify that reinstalling rejects it while preserving the current selection.
GitOrigin-RevId: 429da2ad8b2ee50f07ffb14b79281ab262a2d1a1
## Why
The updater bound its socket directly beneath `CODEX_HOME`, which can exceed Unix socket path limits. Bootstrap could also report success before the updater's manual-update socket was ready.
## What changed
- Reuse the control socket's protected binding and cleanup guard for the updater, with a symlink at the advertised socket path.
- Remove stale updater socket entries before startup while preserving regular files.
- Wait up to 30 seconds for supported automatic updaters to publish their socket, without connecting as a readiness probe. Report updater exit or timeout with stderr log context.
- Preserve compatibility with older updaters that lack the manual-update command.
## Testing
Add Unix integration tests for updater readiness with a long `CODEX_HOME` path and bootstrap failure when a regular file blocks the updater socket, verifying that the file is preserved and the daemon remains running.
GitOrigin-RevId: 57fdcbe4e6907ece68ba66178cf81f258527560c
## Why
Message roles and content classifications do not identify who supplied each context part. Source attribution needs to survive prompt assembly and history truncation, including messages that combine text from different producers.
## What changed
- Add per-part `ContentItemMetadata` for user input, developer instructions, `AGENTS.md`, skills, harness context, command hooks, and tool context with optional callable namespaces.
- Carry attribution alongside content and classifications through contextual fragments, extension prompts, hook output, and agent messages. Keep tool-provided context-window hints separate from harness text.
- Preserve the source of retained text slices during compaction and attribute generated truncation notices to the harness. Default missing historical attribution to unknown.
- Attribute host MCP calls using cached tool namespaces only when catalog revisions remain stable, without starting servers or refreshing catalogs for attribution.
- Send the new metadata to Responses Lite and strip it from requests to endpoints that do not support it.
## Testing
Extend compaction tests to cover mixed sources, missing or extra metadata entries, and discarded media. Update Responses Lite request assertions to verify endpoint-specific attribution handling.
GitOrigin-RevId: b0ebc929b7c60f3ec49d1affbf897312d63edcc8
## What changed
- Record the current and previous dedicated daemon selections in `selection-history`, bound to the selection link's identity. Preserve that history when an install leaves the selection unchanged.
- Prune unused releases after package preparation and scheduled update processing, including updates that require no restart. Retain the current and previous selections, packages used by the daemon or updater, and the calling executable's package.
- Require lifecycle and installer locks, valid selection history, and verified package boundaries before cleanup. Skip unsafe or unrecognized packages and retire releases before best-effort deletion so partial failures are not retried.
- Resolve the updater's actual executable identity after an executable handoff that preserves its PID.
## Testing
Extend coverage for stale selection history, retention of the last two selections, packages containing external symlinks, partial deletion and reinstall, cleanup without restarting the daemon, and repeated installs preserving selection history.
GitOrigin-RevId: 19a04db1cc356a2219f2afb137b9525e249ab6fb
## What changed
Check the selected thread's app-server metadata before resuming it in the TUI. Reject Guardian review threads with a clear error and suggest `codex resume <parent_thread_id>` when a parent session is available. Preserve existing resume behavior if the metadata read fails.
## Testing
Add a regression test for Guardian thread rejection and the parent-session hint. Update daemon startup coverage to select a saved session when testing `resume`.
GitOrigin-RevId: 64b43bb24b5e24eec14c8204c6e15232387dade8
## Why
WinGet archives place the CLI and code mode host at the package root, while daemon installation expects them under `bin/`. This layout mismatch prevents installing the daemon from a WinGet CLI package.
## What changed
Validate WinGet packages in their original layout before converting the staged copy to the daemon layout. Move the executables under `bin/`, update the package entrypoint and optional voice manifest checksum key, and hash the final tree for release reuse. Leave the source package unchanged.
## Testing
Add a Windows integration test covering daemon startup, repeated `update --from-cli --yes` calls, rewritten manifests, and rejection of an incomplete package without changing the selected release or source manifests.
GitOrigin-RevId: e78c461a557a4d005fe1f5fe37fb5ba05bb38608
## Why
Workspace routing reported generic requirements load and reload failures, hiding the cause. Raw configuration errors can contain secrets, so exposing their messages directly is unsafe.
## What changed
Include a safe reason in configuration load and reload errors: file locations or non-file line and column numbers, cloud error categories and HTTP status codes, known network policy denials, or OS error details. Exclude raw parser messages, configuration contents, and backend-supplied policy names and IDs.
## Testing
Add regression coverage for configuration locations, cloud failures, and network policy denials. Verify that malformed local and cloud configuration reports useful errors without exposing secret values or policy identifiers, and still prevents workspace routing from falling back to startup configuration.
GitOrigin-RevId: a71484c700d32662ced9e19041dbedda5d1da8a5
## Why
Archive and delete progress replaced the task list, hiding the selected task and surrounding context while the request was pending.
## What changed
Render progress as a centered dialog over the Agent command center. Preserve the selected task and shared scroll/filter state, and re-render the backdrop on terminal resize.
## Testing
Update narrow-terminal snapshots for both archive and delete to cover the progress overlay, task list, and selected row. Adapt the existing modal input-isolation test to supply a backdrop.
GitOrigin-RevId: e155478aeaddef189fbc53b27b8ff05d54bc3711
## What changed
- Launch background compaction at eligible pre-turn, mid-turn, and post-turn checkpoints when `AsyncCompaction` is enabled, capturing the current world state and client routing state.
- Adopt ready results at compaction checkpoints while preserving newer messages, tool outputs, and world-state updates. Continue normally if an optional result is rejected.
- Run one foreground compaction if an adopted result still exceeds the context limit.
- Prevent cancelled turns from launching new background work while preserving already-running work for later reuse.
## Testing
Add unit and scenario coverage for stale history and account changes, cancellation, pending-result reuse and fallback, retained tool outputs, compaction event pairing, and token usage accounting. Add a context snapshot covering a collaboration-mode change while compaction runs.
GitOrigin-RevId: 04ac028d9fe2e3ea64aacaaeb351c3c776cf3940
## Why
Assistant messages delivered during a pending Guardian review can change its evidence. Previously, these context changes aborted the review instead of triggering a fresh assessment.
## What changed
Treat changes to local or root review context as stale authorization so Guardian retries with updated evidence. Cancellation and history resets still abort the review.
## Testing
Extend local and worker delivery tests to cover refreshed allow and deny decisions, verify that the new review includes the delivered message, and ensure commands execute exactly once after approval and never on stale approval or denial.
GitOrigin-RevId: 019205bee6d3f4e8cf6b9268f72bbc5db6b3899e
Set `config.model_catalog` to the bundled catalog in
`mcp_invalidation_refreshes_threads_that_are_still_starting` so model
resolution completes locally before the test waits for the startup
lifecycle hook.
GitOrigin-RevId: fd12df5140670dad4c9e2d22fabe73b0437af2b4
## Why
Cancelling an async migration caller can leave its blocking compression or decompression worker running. Releasing migration locks before that worker finishes allows other writers or migrations to access files still being processed.
## What changed
Share maintenance, cross-process writer, and local writer locks with blocking workers during migration and recovery. Keep those locks held until file work completes, releasing cross-process locks before allowing local writers to proceed.
## Testing
Add a regression test for cancelled compression and decompression callers that verifies locks remain held until the worker finishes and the output is complete. Preserve the Unix check that decompression temporaries have owner-only permissions.
GitOrigin-RevId: 74855250d89ecab81eaadc2956e328d37b65e72e
## Why
Keychain signing reconstructs its own authentication context, so invalidating the caller's context does not reliably cancel the context that owns the biometric prompt.
## What changed
Evaluate the stored key's access-control policy explicitly with `LAContext` before signing. On cancellation, invalidate that context and wait for its authorization callback before releasing the lifecycle lock, rejecting any late success. Reload the key with the authorized context and disable further interaction so signing cannot open another prompt.
## Testing
Update unit tests to cover waiting for cancellation completion and rejecting completed authorization after cancellation. Add an ignored macOS hardware test and setup instructions covering persisted Secure Enclave key reuse, signature verification, cancellation, retry signing, and cleanup.
GitOrigin-RevId: 4ea9756430c5649654e95e047d1666617503072c
## What changed
Add optional `voiceSessionId` to realtime start parameters and forward it as the `voice-session-id` header for WebSocket, WebRTC, and existing-call transports. Keep this client-generated voice session identifier distinct from `realtimeSessionId`, which uses `x-session-id`.
## Testing
Extend serialization tests and add coverage for distinct session ID headers, WebRTC request forwarding, and existing-call handshake forwarding.
GitOrigin-RevId: cb558dbb9d438f2d34e281199a7e81fe5d33b879
`nearestExistingParent` already checks whether the cache path exists and is a directory. Remove the duplicate `stat` check from `usableCacheDir` in the OpenAI docs manual fetcher, retaining the existing parent lookup and write/execute permission checks.
GitOrigin-RevId: 42583353bfdd06881171d8b24fa2b2d5b6fb3135
## What changed
- Return qualified skill names such as `team:deploy` and parsed `dependencies` and `policy` instead of a separate namespace and raw metadata file. Share `agents/openai.yaml` parsing and validation between skill loaders and executor discovery.
- Include each standalone skill's search-root ID and path in `discoveryRoot`, while accepting responses from older executors that omit it.
- Add plugin `displayName`, falling back to the manifest name or installation directory.
- Materialize inline MCP declarations in `mcpConfig` with the manifest as their source path, and report incomplete discovery when declared MCP or Apps configuration files have no returned contents.
## Testing
Add coverage for JSON round trips, omitted `discoveryRoot`, optional and invalid skill metadata, qualified names, display-name fallbacks, and inline MCP configuration. Verify standalone search roots survive cached discovery and sandboxed RPC responses.
GitOrigin-RevId: 4124972444ad7c2fb8c6418acbf9a589d797fad2
## What changed
- Accept `super` modifiers and normalize `cmd` and `command` aliases to `super`. Support capturing, displaying, and using these bindings in shortcuts, chords, and leaders.
- Add `super-left`, `super-right`, and `super-backspace` editor defaults for moving to the start or end of a line and deleting to its start.
- Honor safe Super-modified editor shortcuts during startup without treating them as text or inserting a pending paste newline.
- Save keymap edits through `config/value/write` when connected to a local daemon so it can validate bindings before they are saved or applied. Preserve the configuration and active keymap if the daemon rejects the edit.
## Testing
Add coverage for modifier aliases, shortcut capture and labels, chords and leaders, line editing, startup input, and daemon acceptance or rejection of keymap edits. Extend the startup PTY test with Command editing sequences.
GitOrigin-RevId: 8ed74f8253c89d423d5dfe87aa092844ce834454
## What changed
Apply `tui.copy_on_select` to composer mouse selections on release, including X11 PRIMARY publication when enabled. Keep editable selections highlighted so typing can replace the selected text, even when `tui.copy_on_select_clear_selection` is enabled.
Share clipboard destination handling across the transcript, footer, and composer. Apply automatic deselection to footer selections after confirmed delivery, and release composer and footer PRIMARY ownership on focus loss or resume. Update configuration descriptions to clarify the behavior across all three surfaces.
## Testing
Add composer tests covering copy on release, retained selection highlights, replacement by typing, PRIMARY ownership lifetime, and clipboard-only status reporting for pending copies.
GitOrigin-RevId: 46999a32170149193fca561741000e97dfc458cf
## Why
`codex app-server daemon restart` previously reused saved settings without applying feature flags supplied on the command line.
## What changed
Apply `--enable`, `--disable`, and boolean `-c features.*` overrides during an explicit restart and persist them for subsequent restarts. Accept nested `enabled` values, normalize feature aliases, and replace conflicting saved aliases while preserving unrelated settings.
Reject invalid feature toggles before stopping the daemon or saving settings.
## Testing
Add integration coverage for overrides on stopped and running daemons, alias replacement, preservation of saved settings, restarts without flags, and rejection of non-toggle keys without interrupting the running daemon.
GitOrigin-RevId: 14a657bc4758b9c248e363f9dac58f8887070a04
## What changed
When the remote global catalog is active, let a cached `visualize@openai-curated-remote` install supersede `visualize@openai-bundled`, matching the existing Sites behavior. A disabled remote install also suppresses the bundled plugin; a missing remote bundle preserves the bundled fallback.
## Testing
Extend the agent-turn compatibility tests to cover Visualize with enabled, disabled, and missing remote bundles, asserting which skills appear in the developer prompt.
GitOrigin-RevId: 7d0cc564189249e597d5bd29b5800353d89a9060
## What changed
Update the OpenAI docs sample resolver to return only `model`, `migrationGuideUrl`, and `promptingGuideUrl`, and remove the model-to-slug conversion helper.
GitOrigin-RevId: d7cea29ff8121b1a4df3b062d54dcbed6a1589bd
## What changed
- Add the disabled-by-default `executor_capability_discovery_v2` feature to acquire `capabilities/discoverV2` inventories from supporting remote executors using each selected environment's working directory and sandbox.
- Share snapshots with MCP and world-state contributors and skill providers without activating discovered plugins or publishing discovered skills to the model.
- Cache inventories by environment instance, executor session, working directory, and sandbox. Coalesce concurrent requests, refresh the cache at turn start, retry transient failures, and refresh MCP projections after recovery.
- Resolve the system skills root in the executor and pass it explicitly to capability location discovery.
## Testing
Add coverage for feature gating, unsupported executors, inert inventories, cache reuse and eviction, turn refreshes, failure recovery, executor replacement, and system skill locations.
GitOrigin-RevId: 1bdca28fa7f17622b27e2713ab3dcc0c13426889
## What changed
Use `conversation` when neither a local `async_classifier_mode` override nor a model default specifies a mode. Keep `snapshot` available as an explicit override and update the configuration documentation and schema to describe the new fallback.
## Testing
Expand configuration tests to cover all local override and model default combinations. Update app-server approval tests to exercise conversation mode without an explicit override, and explicitly select snapshot mode in tests that depend on it.
GitOrigin-RevId: a62479a3f6454bf28d589373a236d8b0ab5023b9
## Why
Compressed rollout searches recompiled the same query patterns for every file.
## What changed
Lazily compile and reuse the JSON-escaped and content search patterns across each scan, including the fallback scan when `ripgrep` is unavailable. Keep compilation failures within the existing per-file error handling and open files before compiling patterns.
## Testing
Add regression coverage verifying that an oversized query does not fail the compressed rollout scan and that a missing file still returns `NotFound` before query compilation.
GitOrigin-RevId: 0d41cbca6e1f716fc234c268493d8dd94c34975e
## Why
Opening the in-app resume picker created a new app-server session without the active session's remote working directory override, dropping the remote directory filter from the thread list.
## What changed
Pass the active session's remote working directory override to the picker session so its `thread/list` request retains the `cwd` filter.
## Testing
Add a regression test that opens the in-app picker against a recording remote server and verifies that `thread/list` includes the remote working directory in `cwd`.
GitOrigin-RevId: 0073ed77e9d9b0ffdd647fcb9f157d20ea2aa599
## What changed
Select label-only web link rendering when `TERM_PROGRAM` is `rex`, matched case-insensitively. Preserve the existing visible-destination fallback for multiplexers and `dumb`, `screen`, or `tmux` terminal modes.
## Testing
Add a regression test verifying that Rex renders `[label](https://example.com)` with the label-only policy.
GitOrigin-RevId: 615ca6186d84fc17cef9286e75848877b542b6ab
## What changed
- Register `capabilities/discoverV2` for initialized sessions and expose it through `ExecServerClient` and remote `Environment` APIs, checking executor support before calling it.
- Reuse startup discovery locations and retry failed prewarming on demand. Replay discovery once after executor recovery while preserving the request parameters.
- Track whether all required filesystem watches registered successfully and reload locations and metadata on each request when registration fails.
## Testing
Add coverage for RPC metadata refresh, omission of skill instruction bodies, sandbox isolation, startup scan recovery, disconnect replay, and successful or failed watch registration.
GitOrigin-RevId: 726e8f7e8b4d835b877f31d1d8a9f8eea1ad9c8b
## What changed
- Default `features.api_key_cyber_access_programs` to `true` and allow `codex exec` to select Daybreak with an OpenAI API key. Select the advertised standard program when `daybreak=false`, while respecting explicit feature opt-outs.
- Resolve API-key eligibility for TUI background turns from the target thread's feature settings, including project opt-outs. Omit access-program overrides when the server cannot report those settings.
- Preserve automatic server treatment for unlisted models and missing or empty Cyber program metadata in exec and TUI. Continue rejecting Daybreak when a nonempty program list does not offer it.
## Testing
Update regression coverage for API-key Daybreak selection, the off override, explicit opt-outs, resumed sessions, target-thread settings, and missing model metadata.
GitOrigin-RevId: f3cf7bd95a2754d4b4281bc70b18c7da4b177552
## Why
MCP servers must forward sandbox policy unchanged to `codex sandbox --sandbox-state-json`, while interpreting launcher information to find the Codex CLI. Keep those contracts separate so consumers can preserve unknown policy fields.
## What changed
- Accept the experimental `codex/sandbox-state` capability alongside the deprecated `codex/sandbox-state-meta` capability, and send identical policy values under both `_meta` keys.
- Move `codexExecutable` out of the policy into `codex/sandbox-launcher`, supplied only when a verified CLI path is available for a local stdio server.
- Replace stale sandbox metadata while retaining unrelated entries, and remove stale launcher metadata when no launcher is available.
- Document the metadata contract and how servers should forward policy and retain authority for long-lived subprocesses.
## Testing
Update unit and integration coverage for policy serialization, identical state aliases, launcher availability across execution environments, and stale metadata replacement.
GitOrigin-RevId: e544c06e6e023953b1fc8069b7b1affa065262d1
## Why
Rewriting source agent names and instruction filenames inside URLs and email addresses can change their destinations when importing external agent content.
## What changed
Use `linkify` to preserve recognized URLs and email addresses while rewriting surrounding text, including Markdown link labels and titles. Continue migrating instruction filename references to `AGENTS.md`, including relative links and references with line or column suffixes.
## Testing
Add rewrite coverage for URLs, email addresses, Markdown links, and surrounding Unicode text. Extend skill import and app-server configuration import tests to verify that link labels migrate while URL destinations remain unchanged.
GitOrigin-RevId: c4d210a287c99b6440438c99527364d379c568bd
## What changed
- Mark `cli_daybreak` as stable and enable it by default.
- Apply Daybreak to background turns only for eligible OpenAI accounts, allowing API-key accounts when `api_key_cyber_access_programs` is enabled. Preserve saved settings for ineligible accounts and report account lookup failures when Daybreak is enabled for the OpenAI provider.
- Skip inheriting Daybreak configuration when the app server does not support reading effective configuration.
## Testing
Expand dynamic-tool request tests to cover the feature toggle, ChatGPT and API-key authentication, API-key program eligibility, and unsupported configuration reads.
GitOrigin-RevId: 55a57315c9f527f977dd8305ea62d4096ed7dae9
## Why
Pending classifications can outlive the `max_tool_call_lag` window in which their scores are reusable, keeping metadata waits or classifier transports active after the result becomes stale.
## What changed
- Expire pending classifications when tool-call progress exceeds the configured lag allowance, preserving the wrapper discount while nested code-mode actions remain active.
- Cancel metadata waits and sampling in snapshot and conversation modes, including snapshot response drains after an early score.
- Treat expiry as supersession, preserving cached scores and the last completed conversation checkpoint and transcript cursor.
## Testing
Add regression coverage for lag boundaries, active wrapper discounts, transport cancellation before and after early scores, expired requests skipping preparation, and conversation history and transcript deltas surviving cancellation.
GitOrigin-RevId: 892ff13a05fd2b1573cef9842b934d1fc865d951
## Why
Canceled classifier requests need bounded cleanup that preserves received token usage and returns only safe WebSocket connections to the pool.
## What changed
- Own classifier response streams and connection leases together, interrupting dropped responses with a one-second cleanup deadline.
- Require a matching interruption acknowledgement and response completion before reusing a canceled response's socket. Retire sockets on rejection, invalid acknowledgements, or timeout while preserving any received completion and token usage.
- Skip requests canceled before dispatch and return their unused sockets to the pool.
- Distinguish cancellation from ordinary steering, which continues draining without requiring an interruption acknowledgement.
## Testing
Add regression coverage for cancellation, acknowledgement ordering and failures, cleanup timeouts, socket reuse, and token accounting under backpressure. Extend steering tests to cover rejected and missing acknowledgements.
GitOrigin-RevId: c4e7aac49d36cea2c2d0e9f2ba5f6147f67471dd
## What changed
Add transcript select-mode state with an underlined cursor, grapheme-aware movement via arrow keys or `h`/`j`/`k`/`l`, and vertical movement that preserves the preferred display column. Support marking with `v`, Space, or Shift-arrow keys and copying through the existing selection machinery.
Keep the displayed transcript snapshot and reading position paused during selection and after exiting the mode. Add entry and exit methods; this change does not yet bind mode entry to a user-facing key.
## Testing
Add unit tests for initial cursor placement, movement across empty lines and entry boundaries, wrapped text, preferred-column preservation, and Enter behavior with and without a marked range.
GitOrigin-RevId: e5bc380ea0eb6e2c6157ba73ac063d548a7de145
## Why
Encrypted compaction payloads can include sampled-token replay caches that increase their size roughly threefold. Budgeting them as ordinary text can reject checkpoints that fit the model context budget.
## What changed
Use a shared estimate of one token per twelve ciphertext bytes, rounded up, for encrypted `Compaction` and `ContextCompaction` items in history and Guardian context budgeting. Guardian continues to count framing and metadata separately.
Check parent compactions against the configured token budget and a separate hard wire-size limit. Preserve the complete encrypted checkpoint when it fits. The token estimate remains a heuristic and can underestimate legacy checkpoints without replay caches.
## Testing
Add coverage for token-estimate rounding, parent compaction token and wire-size limits, and reviewer continuation with a cached compaction preserved intact.
GitOrigin-RevId: cc18ca29802491865167eef992830efcf93d97da
## Why
Servers can advertise cyber access programs without accepting them for API-key accounts. The TUI must account for server support before exposing those programs.
## What changed
- Check `features.api_key_cyber_access_programs` at startup and when loading models for API-key accounts, clearing `available_access_programs` when forwarding is unavailable.
- Use thread-scoped feature settings after thread creation and honor feature requirements and CLI overrides at startup.
- Refresh account-scoped models when switching to or from API-key authentication or changing API-key thread context, clearing cached access programs while the refresh is pending.
## Testing
Extend session tests to cover enabled and disabled server settings, CLI overrides, and catalog filtering before and after thread creation. Update account-change tests to handle the model refresh.
GitOrigin-RevId: c80de30a0063b84949098d137715d8678bd70587
## Why
Prediction forks need to retain their parent's context even when it exceeds the automatic compaction threshold. Compaction or context resets can otherwise replace the history used for the prediction.
## What changed
- Apply a thread-local `AutoCompactionDisabled` policy to experimental prediction forks without changing model or skill budgets.
- Skip automatic compaction before, during, and after turns, including context-limit recovery, and suppress new token-budget reminders.
- Reject `new_context` requests for these threads and report context-limit failures without compacting their history.
## Testing
Add regression tests for legacy and paginated prediction forks across compaction thresholds, unchanged parent compaction and skill/tool inputs, context-limit failures, and rejected context resets. Add a request-history snapshot verifying inherited context and reminders survive without compaction or additional reminders after a tool call.
GitOrigin-RevId: 7df374287f4142f776981bb6c22e5caa564d74a5
## What changed
Replace `softprops/action-gh-release` in `.github/workflows/rust-release.yml` with explicit `gh` commands:
- Look up the release by tag, including drafts, and fail on API errors.
- Create stable releases as drafts until assets are uploaded. Create prereleases directly to preserve prerelease events.
- Upload sorted assets with `--clobber`, then publish the release with the configured title, notes, prerelease status, and latest status.
- Cap release notes at 124,999 characters, including a trailing newline.
GitOrigin-RevId: f343e4f265b06e047d85fe5a2b89a92690c7a7fb
## Why
A transient Apps MCP startup failure can remove cached tools that the model has already discovered, preventing a later Code Mode invocation from using them.
## What changed
Keep cached Apps tools in the model's tool catalog while startup recovery runs. Let invocation readiness start or join a shared retry before acquiring the tool execution lock, while tool discovery remains nonblocking. Keep recovery running if a waiting invocation is cancelled.
## Testing
Extend connection-manager tests to cover cached tool bindings and shared recovery. Add a Code Mode regression test that discovers a cached Calendar tool, invokes it after startup fails, and verifies that it succeeds after recovery while unrelated tools remain able to execute.
GitOrigin-RevId: e888501a1050884a50a473e71b893cf6672fe256
## Why
Terminal `response.incomplete` errors discard reported token usage. Counting that usage as a new context baseline can also double-count input and trigger unnecessary compaction on the next turn.
## What changed
- Carry the response ID and valid reported usage with incomplete-response errors.
- Record usage for sampling and foreground compaction in cumulative totals, rollout records, budgets, and token-usage contributors without replacing the context baseline. Preserve the original terminal error, including when accounting exhausts the budget or cancellation races the error.
- Charge incomplete background compaction requests to the rollout budget without publishing foreground token usage.
- Ignore missing or malformed usage rather than estimating it.
## Testing
Extend coverage for SSE and WebSocket incomplete responses, rollout usage records, compaction accounting, deferred token-count events, and token-usage contributors. Add regressions for unnecessary compaction on the next turn and background compaction publishing foreground usage.
GitOrigin-RevId: bf1ee6df3912052ab7c19e1c6af8ad3dc4b07675
## Why
The remote exec-server parent-lifetime test can hide an early process exit behind a connection timeout, making startup failures harder to diagnose.
## What changed
- Race the WebSocket connection against the child process exiting so startup exits are reported immediately.
- Include the registration request count and child status when attachment fails, without inspecting request headers or bodies containing authentication data.
- Enable remote exec-server info logging in the test while keeping other logs at error level.
GitOrigin-RevId: 75739fc93d7f28ba0a3f447a14d4d20b2dbdfd14
## What changed
Move child configuration, task path construction, fork usage hints, and backend spawning into `core::thread_spawn`. Add request, result, and error types that distinguish preparation failures from backend errors.
Route the v2 `spawn_agent` handler through the shared helper while retaining tool-specific telemetry, activity events, and response formatting in the handler.
GitOrigin-RevId: a09a8f66beb41c1403220750d236a12717dbfc6c
## Why
`with_executor_hooks` clones the hook registry to create an executor-specific view. Copying the configured handlers, plugin sources, and diagnostics on every clone is unnecessary when that configuration is unchanged.
## What changed
Store hook configuration in `Arc`-backed collections and use copy-on-write when replacing executor-scoped handlers. Skip handler mutation when there are no executor hooks to add or remove.
## Testing
Extend the executor hook registration test to verify that updating a cloned engine leaves the previous engine's handlers unchanged.
GitOrigin-RevId: 6b188ca6ca21772ccd7336344d98c023f769834e
## Why
Cancellation after initial input admission could leave a child registered even though the spawn caller had not received its result.
## What changed
Resolve the child's status and configuration before committing reservations and releasing provisional ownership. This keeps cancellation cleanup active through the final awaits and lets the spawn result return without yielding after commitment. Cancellation after the result returns does not retract the accepted child.
## Testing
Add a regression test that cancels spawn during the final status lookup after input admission and verifies that the child is unregistered, terminated, and unloaded, and that shutdown completes. Extend the provisional-child cancellation test to cover both native V1 and V2 callers.
GitOrigin-RevId: 028b873ad4c1fac2c4b5d1dc823b4561ff19e6bf
## What changed
Allow Guardian Decisions to use `OPENAI_API_KEY` when the default `openai` provider has no custom base URL and neither `CODEX_GUARDIAN_DECISIONS_API_KEY` nor a cached API key is available. Preserve cached API key precedence over the environment fallback.
Report missing credentials as `credentials_unavailable` instead of `provider_error` in Decisions failure metrics.
## Testing
Add tests for cached API key precedence and the environment fallback with ChatGPT authentication. Run each test in a child process to isolate environment changes.
GitOrigin-RevId: fbb772dcb9287d9e1be1b34292ad9bdffeb3d6b3
## Why
Non-parallel tool calls can acquire their lock in either order, making the shared board scenario's `last_message_id` snapshot nondeterministic.
## What changed
Send each `collaboration.post` call in a separate mocked response to order the writes before snapshotting. Update the `board_connections` snapshot and expected request count from 15 to 17 to reflect the additional responses.
GitOrigin-RevId: a290a01f5071a2081d4d0b1531b1b31bfbb8a6e6
Empty drafts need not survive a daemon restart. Update the `discovered`
scenario in `codex-rs/cli/tests/daemon_startup.rs` to rename the thread before
restarting the daemon and include `thread-name` in the status line. Wait for
the confirmed footer name before issuing `/daemon` so the test proceeds only
after the thread is materialized.
GitOrigin-RevId: a91508582826fa1bd0cc7b89d9a1af7e8b4e1999
## What changed
Emit `codex.guardian.review.truncation` counts and `codex.guardian.review.truncation.bytes` histograms after successful input finalization. Aggregate observations across reduction stages by component and disposition (`truncated` or `omitted`), recording original, retained, and omitted byte totals. Exclude feasibility checks and failed retries from loss telemetry.
Keep blocking command-hook cancellation fixtures in the local environment and use double quotes for the Python command.
## Testing
Add metric-export tests covering aggregation across multiple reductions, separate truncation and omission totals, no loss metrics for rejected inputs, and no duplicate reporting on repeated finalization.
GitOrigin-RevId: 69182fc7afe230be69dd2469caedb5ae4494947b
## Why
Remote process exit can arrive before the final output, and inherited pipes can keep the output stream open after exit. Removing the session at exit can lose output that should remain available to `write_stdin` polls.
## What changed
- Retain remote sessions with open or unread output after exit, including early exits and cancelled initial collection.
- Collect pending output when `write_stdin` races with exit, skipping stdin writes once remote exit is known.
- After initial collection finishes and the process exits, allow a five-second grace period before a final background read. Respect active polling deadlines and keep later polls available while that read recovers retained output.
- Let explicit termination stop output collection even when the process has already exited, and install the exit watcher before cancellable cleanup.
## Testing
Extend remote process event tests to cover output arriving after the initial yield, polling during a delayed final read, active polls exceeding the background grace period, resumable cancellation, and termination before the initial yield.
GitOrigin-RevId: b1671fad8b61a2cdecf7cf9fdf92e57c028c7af8
## What changed
- Await a compatible pending background request when foreground compaction is needed, and share the result installation path with foreground requests.
- Validate the captured history generation, prefix length, model, and authentication owner before installing a prepared result. Fall back to foreground compaction when required if the result is rejected.
- Replace only the captured history prefix, preserving later messages, retained tool outputs, goal edits, and the current world-state baseline. Record installation analytics and completion events only after a result is installed.
GitOrigin-RevId: 798963f2fc603c3febba2c21eafa1bcb094b3ebf
## What changed
Add `features.multi_agent_v2.disable_native_tools` to hide native multi-agent tools while keeping the V2 runtime and its instructions enabled for host-provided tools. The option defaults to `false`, preserving existing tool exposure.
## Testing
Extend configuration parsing tests for the new option and parameterize the multi-agent catalog scenario to cover both settings. Add a snapshot showing native tools are absent while the V2 runtime and instructions remain enabled.
GitOrigin-RevId: 21a53584d2395bb678813c876a8b7927bea61c90
## What changed
- Capture history, prompt metadata, routing state, authentication ownership, and context-window identity for background compaction requests.
- Send background requests over HTTP while preserving foreground routing, and retain the latest candidate in session memory.
- Add feature and threshold eligibility checks and deduplicate attempts by history version, model, compaction hash, and authentication ownership.
- Cancel and drain background tasks during session shutdown, preserving completed usage accounting.
The background launch helper is not yet connected to the turn loop.
GitOrigin-RevId: 0e5e6ab7dac4d98a836733668a775ac48b5a59f1
## What changed
- Extract an HTTP Responses executor that can run without owning a turn's WebSocket state, with optional authentication-owner checks.
- Add cancellation-aware compaction output collection that records background token usage against the rollout budget.
- Support installing a compacted history prefix while preserving later history items and placing initial context around real user or agent messages.
- Allow callers to supply a context window for history trimming and a captured window for compaction request metadata.
GitOrigin-RevId: 29f3ca0ae8841f295058feb207e3a225af9a1487
## What changed
Register the disabled-by-default `async_compaction` feature and accept either a boolean or a `[features.async_compaction]` table. Add `model_async_compact_threshold_percent` with a default of 65 and a valid range of 1–100, validated even when the feature is disabled. Setting a threshold alone does not enable the feature.
Expose the threshold in the runtime configuration and update the JSON schema for both configuration forms.
## Testing
Add configuration loader tests covering boolean and table forms, default and custom thresholds, explicit enablement, and rejection of out-of-range values.
GitOrigin-RevId: cf33de76878e7044bc8cf5d146375a07ea9eb078
## What changed
- Reuse `custom_terminal::ModifierDiff` when writing history spans.
- Share the terminal default-color probe and cache implementation between Unix and Windows.
Both changes remove duplicate implementations while preserving existing behavior.
GitOrigin-RevId: 35f8d77ade972b791c6beac0678d2fe2be3aa763
## Why
Policy evaluation and upstream parsers must not select different `Host` field lines from the same request.
## What changed
Return `400 Bad Request` for multiple `Host` headers, including identical values, before policy evaluation, upstream forwarding, or Unix socket routing. Apply the check to both plain HTTP requests and `CONNECT` requests.
## Testing
Add regression tests covering identical and conflicting headers in origin-form, absolute-form, and `CONNECT` requests, verifying rejection without an upstream connection. Also cover single-header forwarding and rejection before Unix socket routing.
GitOrigin-RevId: 8ec95171e120f784629d3121b9a1bedbaf88e7cd
## Why
Saving an Effects preference refreshes the picker. When users toggle repeatedly before saves finish, that refresh can discard newer choices and cause subsequent toggles to use stale values.
## What changed
- Update Effects checkboxes immediately and track pending saves per row, preserving newer choices when an earlier save takes effect.
- Preserve pending Composer stars choices while Animations disables the row, and clear pending state on a regular panel refresh.
- Use the shared list toggle handling for Effects, including Space support, while giving configured key bindings precedence over Space toggling.
## Testing
Add regression tests for repeated toggles across save refreshes, pending Composer stars choices while disabled, clearing pending state, and a Space cancel binding taking precedence over toggling. Update the Effects picker snapshot.
GitOrigin-RevId: 847dcc2dfd40448c7adc56c8c40879db28b1fc39
## What changed
Update `codex-rs/Cargo.lock` and `MODULE.bazel.lock` for `quinn-proto` 0.11.18, replacing 0.11.15. Refresh its resolved dependencies to use `rand` 0.10.1 and `getrandom` 0.4.2, and add `rand_pcg` 0.10.2.
GitOrigin-RevId: 642bdeccbff8017f2f97b640a2b2c48294c97bba
## Why
WSLg clipboard initialization can block indefinitely, and PowerShell clipboard writes can stall while receiving input or exiting. These stalls can prevent subsequent TUI copy requests from completing.
## What changed
- Try the Windows clipboard first for `/copy` and `Ctrl+O` on WSL, falling back to the native clipboard and terminal delivery when needed.
- Give Windows executable discovery and writing a shared five-second deadline, with a separate one-second deadline for native clipboard setup. Reuse pending setup tasks after timeouts to avoid accumulating blocked threads.
- Launch PowerShell through a native shell and stop its process group on write failures or timeouts. Reap the writer before returning so an older copy cannot overwrite a newer one, and suppress stderr that could expose clipboard contents.
## Testing
Add tests for command compatibility, large Unicode input, expired requests, and cleanup of stalled writers and subprocesses. Update routing tests to cover Windows-first copying and native fallback with HTML and clipboard leases.
GitOrigin-RevId: 218c8541a169a16536db0370455e076a31a42b1f
## Why
Inputs arriving during turn finalization could be queued after the final batch had already been drained, or recorded ahead of that batch.
## What changed
Mark active turns as finishing before draining pending input. Reject injection into finishing turns and make late client responses and notifications wait until the final batch is recorded before appending to history. Continue accepting input into turns reserved but not yet started.
## Testing
Extend the task-completion test to block final recording, verify that input admission is closed, and confirm that a late notification is recorded after queued input while preserving the notification truncation budget. Strengthen the retained-tool-output scenario to assert tool output names and ordering.
GitOrigin-RevId: a57e44bd974e60e134183dab989795e2c3538596
## Why
Incomplete responses such as `max_output_tokens` were classified as stream errors, allowing retries and compaction model fallback after the response had hit its output limit.
## What changed
Introduce `ResponseIncomplete` errors that preserve the server-provided reason and stop stream processing immediately. Make these errors non-retryable and stop compaction without falling back to the selected model. Record incomplete responses separately in sampler failure metrics.
## Testing
Add regression tests that verify incomplete responses surface a terminal error without retries over SSE and WebSocket, and that compaction stops without retrying or switching models for both local and remote compaction.
GitOrigin-RevId: 6e107d441b9bf03fa47ea47b88eeb94b71a9f729
## Why
Repeated turn diff notifications can print the same file changes multiple times, including after an unrelated command.
## What changed
Track the last diff and print nonempty updates only when they differ from the previous notification. Remember empty updates so a restored diff prints again, and reset the tracked diff when a new turn starts.
## Testing
Add a stderr snapshot test covering repeated, changed, empty, restored, and new-turn diffs. Add an integration test that applies one edit, runs an unrelated command, and verifies that the diff appears exactly once.
GitOrigin-RevId: db0a2aa8b77b800ca661e7d1314ed1e571743e74
## Why
Hermetic LLVM targets the GNU ABI on Windows even when an MSVC platform is selected. Native MSVC builds need the runner's MSVC toolchains and SDK environment.
## What changed
- Register the local x64 and ARM64 C++ toolchains in `ci-windows-msvc`.
- Apply `--config=ci-windows-msvc` to the native Windows Bazel test job.
- Allow the native Windows test job to run on `workflow_dispatch` as well as pushes to `main` so toolchain changes can be tested manually.
GitOrigin-RevId: b9fbd3f2bba8a3a8bf226cafda19a921c8738acd
## Why
RGB and extended indexed theme colors cannot be displayed directly on 16-color terminals, causing status line items to lose their color accents.
## What changed
Use each status line item's existing ANSI fallback accent when its theme foreground requires RGB or an indexed color beyond the first 16 colors.
## Testing
Add regression coverage for uncolored output with `FORCE_COLOR=0` and ANSI status line accents with `FORCE_COLOR=1`. Give the RGB styling test explicit terminal colors so it consistently exercises true-color behavior.
GitOrigin-RevId: 213ca5c6c366f0a3c696aab256a0b146558a2837
## Why
`TERM_SESSION_ID` is not specific to Apple Terminal. Treating it as an Apple Terminal identifier can mask Windows Terminal detection and the `TERM` fallback.
## What changed
Remove the `TERM_SESSION_ID` detection heuristic. Apple Terminal remains detectable through `TERM_PROGRAM=Apple_Terminal`.
## Testing
Update tests to cover Windows Terminal detection and the `TERM` fallback when `TERM_SESSION_ID` is present, and Apple Terminal detection with its version and user-agent token.
GitOrigin-RevId: 27db11cb7bcca8f94888f9e21a6cdfcf31561b1b
## Why
Pending requests can outlive a session switch, and different threads or connections can reuse request IDs. Replies and resolution notifications must stay associated with the request that prompted them.
## What changed
- Retain the original app-server reply handle for pending and buffered requests, including requests replayed after thread attachment or session reset.
- Scope user input, MCP elicitation, and user verification bookkeeping by thread, and send user input answers to the requesting thread.
- Keep background resolution notifications from dismissing foreground prompts.
- Consume failed replies to closed connections and clear pending replay state without falling through to another request route.
## Testing
Add WebSocket regression tests for direct and buffered approvals with colliding request IDs and replies to closed connections. Extend coverage for foreground prompt preservation and thread-scoped user verification cancellation.
GitOrigin-RevId: 541acb9910e92f6f2e83c27d2a2384185d4f8fec
## Why
Several configuration toggles required restarting Codex, and settings search only filtered the current group. Narrow terminals also truncated setting values and descriptions.
## What changed
- Apply animations, composer stars, paste detection, automatic recaps, and tips without restarting Codex. Update active motion effects and paste detection when their preferences change.
- Group animations and composer stars in an Effects picker that refreshes after saving and requires animations for composer stars.
- Search across all configuration groups, show each result's group, and preserve the query when switching groups.
- Keep setting values visible in narrow terminals and show the selected description below the list. Reserve space to keep the panel height stable and tailor footer hints to the selected action.
- Simplify configuration notices and omit routine save confirmations.
## Testing
Add and update tests and snapshots for live preference saves while offline, paste detection updates, Effects picker refreshes, global search, and stable panel height at narrow widths.
GitOrigin-RevId: 83773da2f6457ce461ef16f0cddde0df640a36c3
## Why
Managed runtime package registration errors lacked the terminal status, separate async and deployment error codes, and deployment activity ID needed to diagnose failures.
## What changed
Include these diagnostics in registration errors and distinguish failures in `GetResults`, the `ExtendedErrorCode` getter, and deployment itself. Preserve the original completion error; failures to read diagnostic fields do not turn successful registration into failure. Keep free-form Windows error text out of diagnostic summaries.
## Testing
Add unit tests for distinct async and deployment errors, failed or canceled result retrieval, and diagnostic getter failures, including preservation of native error codes and omission of free-form diagnostic text.
GitOrigin-RevId: 7f3a46741304ef04f5c3e2aa575bcfc4392dff62
## What changed
Add a Linux app-server integration test that resumes a saved read-only thread after the default permissions change to `:danger-full-access`. Verify that the live network proxy honors restored grants, requests approval for a new host, persists the approved rule, and reuses it without another approval.
The test also verifies that proxied requests succeed while direct access remains blocked.
GitOrigin-RevId: 08f63efb8752d738df0ee97e4e98c3366ae54f56
## Why
Restoring unnamed thread permissions after configuration loading leaves network proxy initialization and permission validation using the configured default. A saved read-only thread should also resume when that default is incompatible with current managed requirements.
## What changed
Apply eligible saved permission profiles during configuration loading, before network preparation and final validation. Keep explicit permission overrides and managed requirements authoritative, preserve managed deny-read restrictions, and reject saved external enforcement or materialized filesystem grants. Include the saved profile in the app-server's prepared resume configuration state.
## Testing
Add regression coverage for resuming saved read-only permissions with an incompatible full-access default and for retaining managed, remembered, and newly approved network domains in the restored profile's proxy allowlist.
GitOrigin-RevId: 73e32b0a31ac678fd3f60a8ccf8fa9df627f16c3
## Why
Windows and WSL can share `CODEX_HOME` without sharing a lock namespace, allowing cleanup to remove another platform's live helpers. Older clients can also clean helpers stored under the shared `tmp/arg0` root.
## What changed
Create helpers under `CODEX_HOME/tmp/arg0-<os>` and limit stale-directory cleanup to that operating system's root. Keep permission discovery compatible with both the current platform's root and legacy `tmp/arg0` directories, while ignoring other platforms' aliases.
## Testing
Add regression coverage for cleanup isolation, live helper preservation during legacy cleanup, and selection of the first session alias directory from either supported root.
GitOrigin-RevId: f34292748b5b1d3c25629604d849db4b133dfa3a
## Why
Local message boards were scoped to an agent tree. Independently created Codex runtimes need a way to share a board while receiving different access permissions.
## What changed
- Add `LocalBoard` and `LocalBoardConnection` so hosts can supply read-only or read-write access through `thread_extension_init`, including for isolated, ephemeral runtimes.
- Allow read-only connections to read and manage their own subscriptions; reject posting, replying, channel creation, and changes to another agent's subscriptions. Expose effective permissions in channel discovery.
- Use unique runtime paths and require matching board IDs and canonical database paths when resolving agents or delivering notifications.
- Document explicit extension installation and connection setup for new runtimes, cold resumes, and forks.
## Testing
Add a scenario and context snapshot covering an independent writer and isolated Guardian sharing a board through a symlink alias, read-only permission denials, subscription and explicit notifications, and rejection of notifications to an unconnected runtime before a post is written.
GitOrigin-RevId: f92410c3a5c6a46920c3e0e71849c85dc83d9c31
## Why
The generic `parent_compaction_error` classification metric does not distinguish serialization failures, oversized compactions, and unusable compactions.
## What changed
Record separate `failure_reason` values for each case: `parent_compaction_serialization`, `parent_compaction_oversized`, and `parent_compaction_unusable`.
## Testing
Extend parent-compaction reuse tests to cover unusable checkpoints in parent-context mode and assert specific failure reasons. Verify rejected compactions receive the maximum risk score, provide no cached approval, and do not reuse stale context.
GitOrigin-RevId: 103c4173b2ebbdc33eb71bce7f8ecb56f73055f6
## Why
Reading `OPENAI_API_KEY` directly bypasses login credentials reloaded by `AuthManager`.
## What changed
Use the API key from `AuthManager`'s cached authentication for Guardian decisions when the provider is `openai` and has no custom base URL. Keep `CODEX_GUARDIAN_DECISIONS_API_KEY` as the highest-priority override.
## Testing
Add a regression test covering a reloaded API-key login, override precedence, and rejection of the login-key fallback for a custom base URL. Assertions avoid printing credentials on failure.
GitOrigin-RevId: 10b2e6c28d3268c3808c25b2be94d9b6c31f597a
## Why
`unsafe-libyaml` is unmaintained and has no patched release. It remains a transitive dependency through `serde_yaml`.
## What changed
Add `RUSTSEC-2024-0449` to the ignore lists in `codex-rs/.cargo/audit.toml` and `codex-rs/deny.toml`. Document the dependency path and require removing the exception when the affected users migrate off `serde_yaml`/`unsafe-libyaml`.
GitOrigin-RevId: 6f4cf32e55d2877d90bf00d2c12a1c85f18d229e
## Why
With `multi_agent_v2.disable_direct_message` enabled, an unavailable agent message board could cause tool router construction to reject the turn.
## What changed
Remove the requirement that the router expose the board's `post` tool. Unavailable board calls return an unsupported-call error to the model, allowing the turn to continue.
## Testing
Update scenario coverage for a disabled board feature, legacy agents, and ephemeral sessions. Assert that unavailable board calls return an error to the model, that `post`, `send_message`, and `followup_task` are not advertised, and that no board database is created.
GitOrigin-RevId: cb9571459c128d84c3c96f185e70c404e0463473
## What changed
Remove eight tests covering experimental API schema filtering and marking,
end-of-file unified diffs, MCP prompt auto-approval, and local-link regex
initialization. Remove the associated unused test imports and regex coverage
comment. Runtime behavior is unchanged.
GitOrigin-RevId: 91f59cab82393d43000eadf4e7c55e3a6ec2aa14
## What changed
Add a unified execution test where `exec_command` yields a session and a subsequent `write_stdin` poll completes after the remote process exits while its output stream remains open. Verify that the poll returns the delayed output and exit code, emits the command completion event, and removes the background session without issuing a `process/read` request.
GitOrigin-RevId: 3a316eb9f6b29682da81a2ecbdda52f659f4b792
## Why
A remote process can exit while its output stream remains open, leaving the exit watcher waiting and delaying `ExecCommandEnd` even after output collection finishes.
## What changed
Cancel the process output token after final collection or polling, on one-shot cancellation, and after confirmed termination. This releases the exit watcher while allowing delayed output to be collected before the final poll completes.
## Testing
Add remote process event tests for output streams that remain open at the collection deadline, during interruption, and during explicit termination. Assert that `ExecCommandEnd` preserves the exit code and aggregated output, background terminals are cleared, and interruption and termination require no extra `process/read` requests.
GitOrigin-RevId: 8346e5ce446280915b6e2ffa362fcfd79280bfff
## Why
`Ctrl+V` previously attempted only image paste, so a text-only clipboard produced an image-paste error. `Shift+Insert` did not use the clipboard paste path.
## What changed
- On Windows, let `Ctrl+V` and `Shift+Insert` paste images first, then read clipboard text asynchronously when no image is available. Keep clipboard access errors distinct from missing images.
- Allow keyboard paste into composer selections and active history or Vim search queries, including inline mode with right-click paste disabled.
- Flush buffered typing before explicit paste to preserve input order. Discard pending clipboard text when the thread or editable target changes, while allowing shortcut releases and repeated paste shortcuts to leave the read pending.
## Testing
Extend shortcut and clipboard-worker tests to cover text fallback, multiline Unicode text, stale-read cancellation, shortcut releases and repeats, and read-only drafts. Add assertions for history-search preview stability and selection changes.
GitOrigin-RevId: 080c1c05a4587e325cea938a6e28c646b9ac5837
## Why
After a thread was archived externally, the TUI still advertised the Left-arrow agents shortcut, but pressing it in an empty composer did not open the agents view.
## What changed
Reuse the agents navigation handler when connected to an unavailable thread. Preserve the existing empty-composer and editor guards, and require a key press so repeated Left-arrow events do not open the view.
## Testing
Add a regression test for external thread archiving that verifies draft editing, the shortcut hint, ignored key repeats, and opening the agents command center, with a snapshot of the resulting view.
GitOrigin-RevId: a3f36b42bafee948ed7f5842fcb425e414d7e024
## Why
Startup configuration warnings can reflect settings from when the background server started, even after those settings have been fixed. A restart lets users refresh the server without leaving the TUI.
## What changed
- Add a confirmed restart action to `/daemon`, warning that active or queued work in other chats may be interrupted. Reconnect automatically and let an in-progress restart finish if the TUI exits.
- Verify that Codex manages a local server before enabling restart, including servers discovered with auto-start disabled and those started by `codex agents`.
- Show a restart hint on the first startup configuration warning for managed servers, preserving the original diagnostic for copying and dismissal.
- Repaint the full surface of centered dialogs to restore background colors over cached blank cells.
## Testing
Add CLI integration coverage for agents startup and restarting a discovered daemon with auto-start disabled. Extend TUI tests for confirmation, cancellation, unmanaged servers, warning hints and dismissal, and dialog background rendering.
GitOrigin-RevId: 8e4319fab84f13bf6e7335deb93364fccaff14a7
## What changed
Remove `Terminal::autoresize` and the fallible `try_draw` helpers. Render directly in `draw_with_size`, retaining automatic size updates and the existing buffer flush and cursor handling.
Update the cursor-ordering test to use `draw`, preserving its assertion that the cursor moves before it is shown.
GitOrigin-RevId: 5889e9603d772945660e7ae35690d2b7326b10ae
## Why
Dropping the event receiver before shutdown lets an in-flight notification fail delivery and terminate the worker before it sends the WebSocket close frame.
## What changed
Keep the event receiver alive until `RemoteAppServerClient::shutdown` finishes waiting for the worker, allowing it to process the shutdown command and close the WebSocket.
## Testing
Extend regression tests to verify that an event remains deliverable after shutdown is queued and that the server receives `Message::Close(None)` with an extra notification in flight.
GitOrigin-RevId: ba14bc97ffa3453b7b59660144db6da9e688983d
## What changed
Add `Alt+Left` / `Alt+Right` to the shortcut overlay's Session group as “Subagents (empty prompt)”, using the existing previous/next agent binding labels.
## Testing
Update shortcut help snapshots for narrow and wide layouts, configured bindings, and running sessions to include the new entry.
GitOrigin-RevId: 534be840e1fe5646cfb9465e78049322d7e72b4c
## Why
Turn tips are visible outside transcript history, but their text could not be selected for copying.
## What changed
Register rendered working and completion tip rows for mouse selection. Keep tips in place when selection hints or copy status appear, and use the hint “Selecting text · esc cancel”.
## Testing
Extend mouse-selection tests and snapshots to cover selecting `/help` in working and completion tips with copy-on-select enabled, and clearing the selection when a working tip disappears.
GitOrigin-RevId: 25b3f02e7e93a53e777de455943d47fbab388ff1
## Why
Cold resume can replace saved unnamed permissions with current configuration defaults or recover an executor's permissions from turn context. A first-turn context can also predate an acknowledged settings update.
## What changed
- Restore eligible unnamed permission profiles from settings snapshots owned by the resumed thread, honoring explicit caller overrides and current managed requirements.
- Use owned snapshots as the authority for named permission profiles and reapply workspace permissions for the resumed workspace roots.
- Persist a thread-owned settings checkpoint after the first turn's context, serialized with settings updates so older checkpoints cannot supersede newer settings.
## Testing
Extend regression coverage for cold resume with changed defaults, managed permission restrictions, workspace-root overrides, foreign snapshots, and settings updates during first-turn processing.
GitOrigin-RevId: e411d9fd3d586a4162498c9c77c4184459071bd1
## Why
Startup recovery treated a buffered Vim Replace key as an insertion, so the recovered unsent text could differ from the eventual edit. Replacing the first character of `abcd` with `X` should recover `Xbcd`, not `Xabcd`.
## What changed
Preserve the distinction between held typed keys and buffered pastes when building recovery snapshots. Apply Vim Replace semantics to held keys, including mouse selections and the bash-mode prefix offset, without consuming live pending input. Keep buffered pastes literal so the live paste path retains responsibility for large-paste and image classification.
## Testing
Add regression tests for recovery after startup draft handoff and replacement of mouse-selected text with and without the bash-mode prefix. Verify that taking a recovery snapshot leaves live input unchanged and that flushing the held key produces the same text.
GitOrigin-RevId: 97fada635ad9f0f01042b8e96020372d6df9d951
## Why
Piping `codex plugin list` into a consumer such as `head` can close stdout before the full catalog is written, causing a panic.
## What changed
Write both table and JSON output through a fallible writer and treat broken pipes during writing or flushing as success. Continue propagating other output errors.
## Testing
Add unit tests for write and flush failures in both output formats, plus CLI tests that close stdout early and verify a successful exit without a panic.
GitOrigin-RevId: cc4a64e10ad723d26b6de9e731efdc534dbee492
## Why
Server request IDs can be reused across connections. Retained replies need to target the connection that emitted the request, even if the UI selection later changes.
## What changed
- Expose `AppServerReplyHandle` through `AppServerRequestHandle::server_request_reply_handle`, capturing the originating client and request ID for explicit `resolve` or `reject` calls.
- Share single-use completion state across clones so only the first reply is submitted. Dropping a handle sends nothing; stale connections return I/O errors without retrying or switching connections.
- Route existing client reply methods through request handles and use the new API in the managed worktree model test.
## Testing
Add in-process and WebSocket tests for replies on separate connections with identical request IDs, rejection routing, duplicate completion, and stale handles after worker shutdown. Also check that debug output redacts handle details.
GitOrigin-RevId: 940d0951ab67529b05919ca8ec7adb5813834b8c
## What changed
- Group preferences into Appearance, Notifications, Input, Sessions, and Text selection tabs, with search and links to existing theme, status line, terminal title, and keyboard editors.
- Persist preference changes to the selected local configuration file, apply supported changes immediately, and show save errors, configuration overrides, and restart requirements in the panel.
- Add a delayed notification test and controls for notification timing while preserving custom event filters.
- Add `tui.copy_on_select_clear_selection`, disabled by default, to clear transcript selection highlights only after confirmed automatic clipboard delivery.
- Keep local configuration editors usable while disconnected and prevent held activation keys or buffered input from triggering actions across editor and reconnect transitions.
## Testing
Add regression tests and rendering snapshots for panel navigation, search, dependency states, editor handoffs, offline persistence, notification timers, custom filter preservation, and confirmed-copy deselection.
GitOrigin-RevId: a16d218046060fcb6e61705a803fcd9297266e6e
## What changed
- Update the pinned `rmcp` dependency and Cargo/Bazel lockfiles, and migrate MCP handlers and fixtures to `ClientConfig` and `ServerConfig`.
- Stop requiring responses for cancelled elicitation requests in cancellation tests while retaining checks for cleanup and continued connection usability.
- Handle client disconnects during WebSocket writes in the TUI test server, use an asynchronous HTTP mock for loopback proxy testing, and improve remote executor test diagnostics and the Windows subprocess fixture.
- Use `invalid_prompt` for the memory worker failure fixture.
## Testing
Add a regression test covering transport EOF during both form elicitation and user verification. Keep the client alive while checking that pending response channels close, the timeout pause clears, and the service exits with `QuitReason::Closed`.
GitOrigin-RevId: c0166b83fab3b59d84a5207c6630cb6adcf3b230
## Why
An unfinished terminal control sequence can prevent buffered input from draining before a startup modal appears. Propagating that timeout aborts modal handling instead of keeping the screen available for an explicit user decision.
## What changed
Treat input-drain timeouts as a reason to keep startup modal input quarantined. Discard key, paste, and mouse events while retrying the drain, and continue processing server events. Preserve this protection when another request resolves and when the agent overview is restored after reconnecting.
## Testing
Add a Unix PTY regression test covering unfinished control sequences, queued approval and overview shortcuts, unrelated request resolution, and overview reconnection. Verify that buffered input cannot answer an approval or create a task, while fresh shortcuts work after the drain completes.
GitOrigin-RevId: 476bedbd45f13a15d0019e4ce2e875406d4a53ca
## Why
WSL clipboard reads previously launched PowerShell for every paste. Process creation can hang under WSL and stall the shared clipboard worker.
## What changed
- Reuse a persistent PowerShell reader on a dedicated thread, keeping clipboard requests bounded by their deadlines and restarting the reader after errors.
- Prewarm the reader at startup when right-click paste is allowed on WSL, without accessing clipboard contents.
- Use length-framed UTF-8 responses to preserve whitespace and distinguish consecutive pastes while enforcing message size limits.
## Testing
Update the command-reader test to cover consecutive responses from one process, large clipboard text, UTF-8 and whitespace preservation, and read timeouts.
GitOrigin-RevId: 36af338097d6b178ab4887faa5918240c47e1515
## Why
Raw pastes can arrive as thousands of character, Enter, and Tab events. Redrawing the entire owned transcript before each buffered key defeats the composer's paste batching.
## What changed
Skip those redraws while the composer is capturing a paste burst. Continue refreshing geometry immediately for transcript interactions, shortcuts, and non-text keys, including Enter when an accepted Find owns it.
## Testing
Add regression tests and a render snapshot covering multiline raw paste with tabs and Korean text, deferred rendering until the burst flushes, and a single submission of the complete pasted text. Also verify that an accepted Find still handles Enter during a paste burst without submitting the draft.
GitOrigin-RevId: 49d89958a89c165249322463e6075377c517bd8e
## Why
Large test futures can occupy their caller's stack frame even when passed directly to `Box::pin`.
## What changed
- Add a non-inlined `box_future` helper and `boxed_future!` macro to construct and box futures outside the caller's poll frame. Use them for heavyweight TUI fixtures and test scenarios.
- Return the shared `App` fixture as `Box<App>` to keep it on the heap.
- Treat `ConnectionAborted` as a closed connection in the realtime speech test server, alongside `BrokenPipe` and `ConnectionReset`.
GitOrigin-RevId: 7bbf2020a5ec12bae8e0365ddf5641deef93b544
Extend `hung_grpc_stdio_host_is_reaped_and_the_session_recovers` to assert that the first execution after host replacement reports lost stored values and running cells. Verify that this rejected execution does not store a value and that the next execution succeeds.
GitOrigin-RevId: 2fc5550c32774321a969b56ba59153de0e497f19
## Why
Progress updates change task timestamps, causing recency-based sorting to move rows within the same status group on refresh.
## What changed
Retain each task's relative order while it remains in the same status group. Append new tasks and tasks that change groups after existing rows in their destination group. Forget the order of removed tasks so rediscovered tasks behave like new arrivals.
Search and status filters preserve the retained order, and pinned tasks continue to use their explicit ordering.
## Testing
Add regression tests and a snapshot covering progress refreshes, selection stability, arrivals, status transitions (including changes caused by descendants), removal and rediscovery, filters, and pins.
GitOrigin-RevId: 54008a66de5c4cf509759e25ee8c1cb6e2a70100
## Why
Client-supplied tool outputs can carry task instructions. Even when marked with `retain: true`, these instructions could be trimmed before compaction and disappear from the compacted history.
## What changed
Add the disabled-by-default `retain_client_tool_outputs` feature to honor retention for explicitly marked, named `function_call_output` items without a `call_id`.
- Preserve eligible outputs in remote compaction v2 and when starting a new context window, keeping their original role.
- Stop emergency tool-output trimming at a retained output.
- Share the existing 64,000-token retention budget, keeping outputs whole and dropping an oversized output and older items rather than partially truncating it.
- Place initial context before retained standalone outputs and account for their images in retained-image counts.
## Testing
Add a scenario covering enabled and disabled retention, emergency trimming, oversized-output handling, and preservation of the latest instruction after compaction and cold resume. Verify that retention annotations stay out of model requests.
GitOrigin-RevId: 449179670e4d2be2623928700738758e43b5dc1a
The initial user item seals realtime transcript segments, so starting speech before it completes can split the segment under test. Wait for its `item/completed` notification and assert that it is a `ThreadItem::UserMessage` before triggering speech, so only the steering under test can split that segment.
GitOrigin-RevId: 932443f4a0d6c4284cf95f44e64912506769a180
## Why
Replacing a gRPC code-mode runtime loses stored values and running cells. Silently continuing after reconnection hides that loss, while prior external tool operations may already have completed.
## What changed
- Capture the runtime generation when `execute` and `wait` calls are created. If recovery replaces it, reject those calls with an explicit reset error, including concurrent calls and calls first polled after recovery.
- Explain the lost state and advise inspecting prior tool results before retrying. Allow a fresh `exec` call to continue on the replacement runtime.
- Keep `terminate` from reopening the runtime so cleanup cannot hide a reset from the next request.
## Testing
Extend gRPC recovery tests to cover reset errors after host restarts, missing sessions, and route loss, rejection of queued calls, and successful fresh execution with cleared stored state.
GitOrigin-RevId: 914cab3bb45e30a3f3b2afacb5631e42b18e21b0
## What changed
Clicking a pinned prompt header with an unmodified left click now scrolls the transcript to the original prompt. The click also ends text selection, cancels search, and clears activity focus. Track the prompt by entry identity so navigation remains correct when history is prepended.
## Testing
Update the prompt-header snapshot test to navigate by clicking the header after prepending history and verify that the original prompt becomes visible.
GitOrigin-RevId: dea811693853e3740909ab675b1339f701e01e02
## Why
Voice failure metrics lacked cause and lifecycle phase, and session durations were recorded before the final outcome was known. A failed control send could also overwrite a more specific WebRTC error.
## What changed
- Tag `codex.voice.session.failure` with bounded `cause` and `phase` values, recording at most one failure per session.
- Capture duration when stopping and emit `codex.voice.session.duration` at cleanup with a `success` or `failure` outcome.
- Carry typed WebRTC errors into the TUI, preserve existing errors when control sends fail, and avoid duplicate errors after startup failure.
- Record app-server disconnect failures for background voice sessions as well as the visible session.
## Testing
Add coverage for terminal outcome and failure metric attributes, preservation of specific startup and audio-session errors, and startup failures without duplicate control-channel errors.
GitOrigin-RevId: 5aeda6e766093e3fce7206560aa83b6f7770dddb
## Why
A catchable exception lets JavaScript continue after `exit()`, including in `catch`, `finally`, and queued promise callbacks. Exiting should finish the cell successfully without further output or state changes.
## What changed
- Terminate V8 execution when `exit()` is called and complete the cell even if its module promise remains pending.
- Guard host callbacks against effects after exit, including when getters or value conversion request exit.
- Preserve stored writes made before exit and suppress errors when exit occurs during exception formatting.
## Testing
Add regression tests for synchronous and asynchronous exit, timers, parallel promises, value conversion, exception getters, and resuming after a yield and tool response. Verify that only prior output and stored writes survive, and separately exercise host guards while JavaScript continues running.
GitOrigin-RevId: e9487ba65ef0358612c5009bd26953b786a12798
## What changed
- Add the disabled-by-default `output_token_replay` feature to request `output.encrypted_content` from OpenAI providers.
- Preserve encrypted message and tool-call output, message and function-call status, and output-text `annotations` and `logprobs` through history and replay. Update the generated protocol schemas and SDK types.
- Strip output ciphertext from requests to other providers while retaining it in stored history, including after replay is disabled. Remove encrypted content from memory extraction inputs.
## Testing
Add integration coverage for the feature/provider combinations, metadata replay across follow-up requests, and history preservation when resuming with replay disabled.
GitOrigin-RevId: 77729a021b6771933402aebe74ece8eb39c057e2
## What changed
Add `model_messages.tools.incremental_tools` overrides for the update hint, tool and namespace removal headers, and namespace instruction update and clearing messages. Missing, null, or over-512-byte values fall back to bundled wording; empty strings omit static text while retaining runtime names and instructions.
Substitute `{name}` in namespace message templates and append runtime instructions verbatim. Wording changes alone do not trigger tool catalog updates.
## Testing
Extend unit tests and MCP request-history snapshots to cover custom wording, empty notices, tool removal and restoration, and namespace instruction changes and clearing without repeating unchanged tools or notices.
GitOrigin-RevId: 22dea0a6fb4cfcd646f5e65346424834c8b7d5a2
## Why
Lifecycle status reporting was limited to direct iTerm2 sessions. OSC 7501 lets other terminals receive Codex's program state.
## What changed
- Emit OSC 7501 with `app=codex` and states `idle`, `working`, or `blocked` whenever stdout is a terminal, including multiplexed sessions. Report `blocked` when user action is required.
- Continue emitting iTerm2's OSC 21337 status and bounded activity details in direct iTerm2 sessions.
- Clear status before handing the terminal to an external program, as well as on suspension and exit, and re-emit the current state after returning.
## Testing
Add coverage for OSC 7501 encoding, combined iTerm2 output, clearing both protocols, and protocol selection across terminal and multiplexer environments. Update lifecycle tests and status snapshots for the new protocol.
GitOrigin-RevId: 6d2a6885687b0e7af825e954fab72db0765c9a07
## What changed
Expose `Environment::observe_connection_attempts` and `ConnectionAttemptOutcome` to report elapsed time and success, failure, or cancellation for initial connections. Measure from the end of provisioning through client installation, including connection retries.
The first registered observer wins. Past attempts and reconnections are omitted.
## Testing
Extend tests to assert failure followed by success when startup is retried, and a single cancellation notification when an environment is replaced during startup.
GitOrigin-RevId: 88300f38dcf9428b824c5ff36aa1b40d7d466b6f
## What changed
- Add `grpc+stdio://` as a host transport and the disabled-by-default `code_mode_host_grpc` feature flag to select it.
- Share a lazy HTTP/2 channel and host process across code-mode sessions while keeping session state isolated.
- Use HTTP/2 keepalives to detect unresponsive hosts, kill and reap disconnected children, and spawn a fresh host on reconnect. Exit the host when its stdio connection closes.
## Testing
Add coverage for shared-host session isolation, host exit on stdin EOF, and recovery after an unresponsive host is reaped. Exercise nested tool calls with both legacy stdio and gRPC stdio, asserting that the feature flag selects the expected transport.
GitOrigin-RevId: 31389d8540de236b8e0571d3c24e29e117b75c4a
## Why
Graceful shutdown rejects new sessions with an invalid-request error. Give clients a structured shutdown reason and show command center users why session creation is paused.
## What changed
- Add `data: {"reason":"serverShuttingDown"}` to app-server shutdown admission errors while retaining JSON-RPC code `-32600`.
- Show a dedicated shutdown message explaining the wait for active turns and automatic reconnection for non-embedded servers. Recognize older servers by their exact draining message only when error data is absent, and preserve retained-worktree cleanup guidance.
- Keep the command center reconnect presentation when a shutdown error covers the initial overview and no conversation is open.
## Testing
Extend admission and WebSocket shutdown assertions, add embedded and daemon shutdown message snapshots, and cover reconnection with a shutdown error over the initial command center.
GitOrigin-RevId: f167144c0ddc77872afdf3daac8bb1c89f3425b4
## Why
PSEC API symbols can be present on transitional Windows builds where MXC is not enabled. Availability detection needs to verify that a native process security environment can actually be created.
## What changed
- Replace `mxc-sdk` with pinned `appcontainer_common`, `learning_mode_windows`, and `wxc_common` dependencies, and update Cargo and Bazel dependency metadata.
- Use MXC's cached create/close probe for `is_available()` and query native deny-path support through `SecurityEnvironmentApi` before launching requests with denied paths.
- Adapt request construction and the existing policy test to the vector-based environment field, and update the sandbox documentation.
GitOrigin-RevId: e8cc6a35d46884d0a069b747d33e711512ec1596
## Why
Account discovery and cloud configuration GETs can fail after connecting but before receiving response headers. These request failures previously bypassed system proxy fallback.
## What changed
Allow bootstrap GETs to retry through the system proxy on request errors, alongside the existing connection failure and timeout cases, when fallback is enabled.
## Testing
Add regression coverage for connections closed before response headers on `accounts/check` and `config/bundle`, verifying successful proxy retries with the original request headers. Extend coverage to ensure HTTP responses with status `401`, `403`, `407`, `429`, or `503` do not trigger fallback, and network policy denials prevent requests to both the origin and proxy.
GitOrigin-RevId: ac34c3bcfe3bd81c905a7e616d8b821879fbe2c9
Use Codex `0.162.1` instead of `0.156.1` for
`exec-server-stable-release-test`, updating the Bazel release archive version,
checksum, and repository reference.
GitOrigin-RevId: 304108b223da1e5506483f53c476a55a8f31ce71
## Why
Equivalent local source paths can fail to match an already-added marketplace, and redirected managed roots can lose their managed classification on Windows.
## What changed
- Compare local marketplace sources after filesystem normalization.
- Reuse the resolved request path when locating an existing local marketplace so retargeting a configured junction does not switch the returned root.
- Accept both the configured managed root and its canonical target on Windows while continuing to reject unowned aliases to that target.
## Testing
Add Windows regression tests for canonical and legacy path spellings, retargeted local-source junctions, and redirected managed roots with unowned aliases.
GitOrigin-RevId: f1ae46e8e7384075ed1baa6b33b2821f795e17f8
## What changed
Pass the parent turn's `cyber_access_program` to Guardian reviewers and asynchronous classifiers. Use `daybreak_blue` for either Daybreak selection, preserve `standard`, and omit `access_programs` when no program is selected.
Capture the selection with the owning turn so asynchronous observations retain it across later turns. Resolve classifier programs using current authentication and the same provider and API-key feature policy as ordinary model requests.
## Testing
Add regression tests for program changes across reused reviewer sessions with API-key and ChatGPT authentication, snapshot and conversation classifiers at low and high risk, and enabled, disabled, and unsupported-provider API-key policies. Verify parent requests retain their selected program.
GitOrigin-RevId: 447f306df3a6bd6805464b819950690c751b04b4
## What changed
Add an optional `retain` flag to `TurnToolOutput` for `turn/start`. When set to `true`, pass the output to the core with a retention annotation to request retention in the thread's model history. The flag defaults to `false`, preserving existing behavior.
Update the generated JSON schemas, TypeScript types, and Python bindings to expose the flag.
## Testing
Add an integration test verifying that a retained tool output reaches the model and preserves client-authored sender metadata in persisted history, including the receiver message ID.
GitOrigin-RevId: 52893a8fcb308f26e77ba8f0bee9990073b26d54
## Why
Reentering V8 during termination can replace uncatchable cancellation with a catchable JavaScript exception, allowing a script to continue after cancellation.
## What changed
Skip JSON conversion and exception throwing while V8 execution is terminating, preserving cancellation through `image()` getters and JSON fallback.
## Testing
Add regression coverage for cancellation during JSON fallback and reentrant image getters, including prompt termination through the standalone host and continued usability of another session. Extend serialization error tests to cover failing image getters alongside circular JSON.
GitOrigin-RevId: f03dd131a62724106fad96111292ddf5b9dc99f6
## Why
A credential mismatch can trigger setup that rotates both sandbox account passwords. Before allowing repair, validate the account that logged on successfully and ensure that neither account has been replaced or has an unowned runtime registration.
## What changed
- Validate runtime records and successful logon tokens, checking account SIDs, rejecting administrators, and requiring enabled `CodexSandboxUsers` membership.
- Before repair, verify recorded account SIDs and reject existing same-family package registrations for unrecorded accounts. Propagate package-query failures while allowing initial migration when no registrations exist.
## Testing
Add tests for malformed records and unrelated logon errors, plus an ignored disposable Windows Sandbox fixture covering successful logons, group membership, SID changes, migration, and unowned registrations.
GitOrigin-RevId: bafedb52cf9bd484250ccac3b163d2041891283f
## Why
JavaScript objects containing Serde's reserved JSON keys can be reinterpreted during deserialization, allowing nested `RawValue` markers to bypass the parser's normal recursion limit.
## What changed
Reject `$serde_json::private::RawValue` and `$serde_json::private::Number` object keys before passing V8's serialized JSON to `serde_json`. Report a `reserved JSON object key` serialization error while continuing to allow marker text in strings and longer keys.
## Testing
Add runtime regression coverage for nested and escaped marker keys, recursion limits, normal JSON conversion, and session recovery without overwriting stored values. Extend the host-backed integration test to verify that stored values remain available across turns after rejection.
GitOrigin-RevId: 27ddce08e1ffe98ec9dffe02473a815ceae2cc89
## Why
Remote configuration reads need a bounded wait without disrupting valid in-flight work on connections that cannot reconnect.
## What changed
- Add `read_environment_config_with_timeout` to `ExecServerClient` and `Environment`, bounding RPC sending and receiving after connection establishment. Local reads retain their existing behavior.
- Return a typed `ExecServerError::RpcTimedOut` and classify it as retryable for read-only preparation.
- Share timeout handling with environment-info requests. Close the timed-out transport and request recovery only when a reconnect strategy exists; otherwise, keep the connection open.
## Testing
Add a regression test verifying that a timed-out configuration read preserves an in-flight stdio read and allows subsequent reads on the same connection, including after a late response.
GitOrigin-RevId: 6785d5846f4c3b07a6e7c505e359238609c3a6b6
## Why
Resumed threads can retain stale capability root locations when the current environment supplies an explicit owner configuration. Matching roots from that configuration previously could not refresh persisted thread roots.
## What changed
Refresh persisted roots from the current attachment when both the root ID and environment ID match, including roots selected by owner-provided configuration. Preserve persisted locations when no matching root is supplied, and continue using the owner's selected roots rather than the executor's shared roots.
Apply the same merge behavior to capability root inspection and per-step resolution.
## Testing
Extend the remote environment regression test to cover owner-provided configurations with and without refreshed roots, including an executor root location that differs from the owner's selection.
GitOrigin-RevId: ad3a639924b348d6d5337ccc64dc8c08234276e3
## What changed
Move `ExecServerProcess` into `core_test_support::exec_server` and update the sandbox, plugin, access, and turn-input tests to use it. Preserve the fixture's startup timeout, temporary `CODEX_HOME`, WebSocket URL discovery, and child-process cleanup.
GitOrigin-RevId: 152de3a83f4ad39e2c1223e15438608dba452850
## What changed
Add `TurnInput::AnnotatedResponseItem` with a caller-supplied `retain` annotation. For function-call outputs, `retain: true` sets `client_authored` history metadata while keeping annotations out of model requests. Accept annotated items through the existing turn submission paths, including continuation.
## Testing
Add an integration test covering retention metadata during turn start, steering, idle submission, and rollout storage. Verify that ordinary outputs remain unmarked and model requests contain neither `retain` nor `client_authored`.
GitOrigin-RevId: 7285dde31149b17b0dcf31d4ea1c7cba66d9efe6
## Why
A credential bound to a host with MITM hooks could also be used at an alias without hooks, allowing the proxy to inject the real credential without enforcing hook policy.
## What changed
Reject requests to unhooked aliases when their selected brokered credentials are also bound to a hooked host. Check both HTTP forwarding and MITM requests before replacing dummy credentials, returning `403` with `blocked-by-mitm-hook` for denied requests.
Use the same destination and credential-selection rules for alias checks and injection, including configured URL prefixes, safe paths, equivalent credentials, merged Basic authentication fields, and environment scope.
## Testing
Add regression coverage for built-in and configured provider aliases, IPv6 destinations, credential selection, and unrelated credentials. Add an agent-started proxy test that verifies credential masking and alias denial.
GitOrigin-RevId: 12be41654761cedcf87b170f7661d6566f7a864e
## Why
A tool can return before its background watcher emits `ExecCommandEnd`. Waiting for that event first can discard an earlier `TurnComplete`, causing the shell snapshot test helper to time out.
## What changed
Update `run_tool_turn_on_harness` to track both the matching `ExecCommandEnd` and `TurnComplete` in a single event loop, returning only after both have arrived regardless of order.
GitOrigin-RevId: c9b749a46eda1244aa3e80fd88b663d110d67d1b
## What changed
Add the disabled-by-default `subagent_default_context_limits` feature and expose it in the configuration schema. When enabled, shared configuration for spawning and resuming subagents clears inherited `model_context_window` and `model_auto_compact_token_limit` overrides so subagents use their model's default context window and auto-compaction threshold.
GitOrigin-RevId: 5168ae2b4fbe72c533d8c6152922a8bceb2c5cbd
## Why
A local command can exit while a descendant keeps its inherited output pipes open, delaying `exec_command` completion and turn completion.
## What changed
Start the bounded output drain when a local exec-server process exits, whether exit is reported by an event or recovered through `process/read`. Remote execution continues waiting for output closure so buffered or delayed output is retained.
## Testing
Add regression coverage for local shell snapshot execution completing before a descendant releases stdout, preserving the foreground output and exit code. Add remote event-stream cases that retain output arriving after both reported and recovered process exit.
GitOrigin-RevId: d38bcd394be42cf48d2af02733e883b02d1dd62f
## Why
A running shared background server owns its feature settings until it restarts. Differences from a client's configuration files or defaults should not trigger a compatibility warning or a restart request.
## What changed
- Check shared-service features only when explicitly overridden on the command line.
- Exclude overrides superseded by active legacy managed configuration or feature requirements, while supporting older servers without `configRequirements/read`.
- Pass only the remaining explicit feature overrides to a requested daemon restart.
## Testing
Update compatibility tests for stale daemon overrides, explicit enable/disable requests, managed configuration, and older servers. Extend CLI startup tests to verify the feature overrides persisted after a restart.
GitOrigin-RevId: ac92c9c02cd70fa233203ebef1182fd119325dd1
## Why
Interrupted automatic goal continuations reset the empty-response counter, allowing repeated interruptions without activity to keep a goal running indefinitely.
## What changed
Count interrupted automatic continuations without activity toward the existing three-turn limit that marks a goal as `blocked`. Defer evaluation until the thread is idle and serialize it with turn-start accounting. Activity and user turns still reset the counter.
## Testing
Extend accounting tests to cover interrupted and mixed empty continuations, including resets after tool activity or user turns. Add an app-server regression case where a `PreCompact` hook repeatedly interrupts automatic continuations and verify the `thread/goal/updated` notification reports `blocked`.
GitOrigin-RevId: 4c34e3ed1ae612e97cf067c2aa76836b10c50ef5
## What changed
Add `thread/items/read` to retrieve persisted items by `threadId`, `turnId`, and 1–100 `itemIds`. Return matching items in canonical stored order, omitting missing IDs and items outside the requested turn.
Add item ID filtering to the thread store while preserving inherited history and fork cutoffs. Require the experimental API capability for the new endpoint.
## Testing
Add coverage for stored ordering, turn scoping, missing IDs, request size limits, experimental capability gating, and inherited items across fork cutoffs.
GitOrigin-RevId: 9b243dd87577bd4fe36900c388a386b2e26ff2e0
## Why
Background workspace routing reads reload configuration even when signed out or using an API key, although routing requires ChatGPT authentication.
## What changed
Check cached authentication before reading accounts for workspace routing at app-server startup and connection initialization. Skip these background reads without ChatGPT authentication, while preserving configuration reloads for explicit `account/read` requests.
## Testing
Add regression tests covering signed-out and API-key startup and connection initialization, explicit `account/read` configuration reloads, and routing after ChatGPT sign-in, including propagation of configuration errors.
GitOrigin-RevId: 8b90ee609ed24f8618cd21f160eb7001703b8bd1
## What changed
- Move the SQLite schema, database filename, and shared pool registry into `local/pool.rs`.
- Share channel insertion between runtime writes and template setup, using typed board IDs and channel descriptions.
GitOrigin-RevId: c57a79c49fe9003b3c73f38010ce9293275a714c
## What changed
Expose `LocalBoardSetup` and `configure_local_board` to load initial channels and optional descriptions before agents start. Add a `configure_board` example and setup documentation.
Save version 1 templates and channels atomically in SQLite. Identical templates are safe to retry; conflicting templates, previously used boards without a pinned template, and deleted boards are rejected. Setup accepts an optional creation timestamp and leaves agent access unchanged. Remove the pinned template when deleting a board.
## Testing
Add an integration test covering channel metadata after reopen, identical retries, conflicting template rejection, retries after adding a channel, and rejection after board deletion.
GitOrigin-RevId: 0b5c5439ab127fb5c275f024962a373a56635ad0
## Why
The Linux sandbox uses bubblewrap for filesystem isolation and seccomp for syscall filtering, but its command type, syscall-filter module, and integration test suite still used Landlock names.
## What changed
- Rename `LandlockCommand` to `LinuxSandboxCommand`, `src/landlock.rs` to `src/seccomp.rs`, and `tests/suite/landlock.rs` to `tests/suite/sandbox.rs`, updating imports and existing tests.
- Clarify the retained legacy Landlock implementation and its filesystem-policy limitations.
- Update the README to describe existing network filtering, `AF_VSOCK` and `io_uring` restrictions, and managed-proxy Unix socket behavior, including allowed Unix socket pairs.
Sandbox enforcement behavior is unchanged.
GitOrigin-RevId: be4769d5a10b90605990eb58451e83fdf1c31222
## Why
Requests with `Connection: close` must not reuse the connection even when the server responds with `Connection: keep-alive`.
## What changed
Update `hyper` from 1.8.1 to 1.11.1 in `codex-rs/Cargo.lock` and add the corresponding Bazel lockfile metadata.
## Testing
Add a regression test that sends two requests with `Connection: close` to a server that ignores the header and verifies that the second request uses a new connection.
GitOrigin-RevId: 72b464c8ea3d9a1ad5d9e62f7896ea9a4f15a93c
## Why
The remote environment test can steer before the wait tool call is recorded, discarding the call. The session replacement test can close the client while agents overview RPCs are still pending, leaving the proxy writing to a closed socket.
## What changed
- Wait for the `wait-for-active-environment` function call event before steering the active turn.
- Wait for `AgentsOverviewThreadsLoaded` before shutting down session replacement test cases that open the agents overview.
GitOrigin-RevId: 886112a56ff6e1016efe30dbbd0256807bc1cc85
## Why
Remote boards can allow replies while denying new threads. Agents need to discover these effective permissions and receive actionable details when an operation is denied.
## What changed
- Expose optional `board_permissions` and per-channel `permissions` in `get_channels`, preserving the legacy response shape when permission metadata is absent.
- Preserve HTTP 403 `permission_denied` responses as structured tool errors with a message and optional `action` and `resource`. Mark denied calls as unsuccessful and truncate oversized error details to fit the output budget.
- Pass through service-computed permissions without evaluating access rules locally.
## Testing
Add remote-board scenarios for direct tools and code mode covering legacy responses, reply-only permissions, a denied post, and a successful reply, plus a snapshot of the direct tool exchange.
GitOrigin-RevId: 76594bbc0a1283ff3c3c8682bd7615baa5ade428
## Why
Herdr sessions can gain attached clients after Codex starts. Successful native clipboard copying should still forward the text to the attached terminal, even without inherited SSH variables.
## What changed
Detect Herdr sessions with `HERDR_ENV=1` and enable terminal forwarding for `/copy` and `Ctrl+O` even when native copying succeeds. Use OSC 52 directly when outside tmux, while preserving the native copy result.
## Testing
Add a routing test verifying that a Herdr session copies natively before sending OSC 52 and retains the successful native clipboard lease.
GitOrigin-RevId: c43c08ca037ff51e902267dc8636889493f5c30c
## What changed
Add `preserve_fork_prefix` to the multi-agent v2 configuration, defaulting to `false`. When enabled, full forks retain the parent's model-visible history, including commentary and tool records, and append the child's instructions. Legacy compaction without a reusable context baseline still rebuilds the child context.
Mark copied history as inherited, complete unfinished tool calls in the fork snapshot, and exclude inherited manual approvals from authorization review while retaining them in model context.
## Testing
Add coverage for preserved request prefixes, child instructions, legacy and paginated histories, Code Mode, missing inherited tool outputs, compaction fallback, and approval isolation across checkpoint replay. Update the noisy helper failure test to read its response before starting cleanup.
GitOrigin-RevId: ce9235dfa111c88d6ce66cb93d564fb63b326489
## Why
Pasting text ending in a newline into a composer line beginning with `> ` adds an unnecessary empty quoted line before the next Markdown block.
## What changed
Remove one trailing newline from nonempty blockquote paste content before adding quote prefixes. Preserve interior blank lines and the two unquoted newlines that move the cursor to the next block.
## Testing
Add a trailing-newline regression case, update the CRLF/CR expectations, and exercise trailing-newline input in the existing rendering snapshot test.
GitOrigin-RevId: 2367efa8253dd0512de8ba6333b39eba6381fba8
## Why
Clients need to mark threads read or unread without overwriting unseen results or another window's explicit mark.
## What changed
Add `thread/readState/update` for eligible durable local threads, gated by `initialize.capabilities.experimentalApi`. Requests include `threadId`, `expectedRevision`, and an operation of `{type:"read"}` or `{type:"unread"}`.
Marking read clears `firstUnread`; marking unread sets it to `threadStart`. Successful updates return the read state and notify subscribers through `thread/readState/changed`. Both operations require an exact revision match. Stale requests return `-32600` with `readStateConflict` and the current read state, requiring a fresh user action rather than a blind retry. Updates do not change thread recency.
## Testing
Add app-server coverage for experimental capability gating, explicit unread marks and notifications, conflicts for both stale operations, and marking read with a fresh revision.
GitOrigin-RevId: 775f6e9584dc91bd3c2ee9a309144b5baf0edffa
## What changed
Add the experimental `thread/readState/changed` notification with `threadId` and the committed `readState` receipt. Send it to existing thread subscribers when terminal activity updates read state or a revert clears a removed unread position. Emit terminal read-state updates before `turn/completed` so completion remains the last notification for that result.
Expose the notification in generated JSON schemas, TypeScript types, and Python SDK models. Document experimental capability gating, subscription lifetime, notification opt-out, and refreshing receipts when concurrent responses disagree.
## Testing
Extend the read-state integration test to assert that the notification receipt matches the receipt returned by `thread/read` after terminal activity.
GitOrigin-RevId: 28935352a881b7a5e2e7f629173c3b2061bd7941
## Why
Sessions sharing a transport can be admitted to different hosts. Each session needs its own routing token so subsequent RPCs reach the host holding its state.
## What changed
- Capture the optional `x-code-mode-route` metadata from successful `OpenSession` responses and attach it to subsequent session RPCs. Reject tokens longer than 256 bytes and keep new admission attempts free of existing session routes.
- Invalidate a routed session when an `Unavailable` response explicitly sets `x-code-mode-route-lost: true`, allowing a later operation to reopen it without replaying the failed execution. Ordinary `Unavailable` responses preserve the session.
- Allow up to five admission attempts for `Unavailable` and `ResourceExhausted`, with an immediate first retry followed by jittered exponential backoff.
- Order session failure with shutdown so late callback errors cannot cancel an in-flight `CloseSession` RPC.
## Testing
Add regression coverage for independent routing on a shared provider, route-loss recovery without execution replay, preservation of unaffected session state, and callback failures racing shutdown. Extend admission tests to verify the five-attempt limit and recovery tests to distinguish explicit route loss from ordinary unavailability.
GitOrigin-RevId: 5d60ef1afa56beb8c70ba7ab27865128225b0d3d
## Why
Realtime v3 voice validation used the v1 voice list, limiting the available voice choices.
## What changed
- Add a dedicated `v3` voice list containing the v1 voices and 16 additional voices, and use it to validate v3 requests.
- Expose `v3` in `RealtimeVoicesList`, defaulting to an empty list when omitted during deserialization.
- Update the configuration and app-server schemas, generated TypeScript and Python types, and voice-list test expectations.
GitOrigin-RevId: 7fc8060fe01d840f28eb92c3dfe49c5878c3c258
## What changed
- Add experimental `readState` to `thread/read` and a thread-ID-keyed `readStates` map to `thread/list` for eligible durable local user threads. Each receipt contains `firstUnread` and an opaque `revision`.
- Publish new visible terminal results before `turn/completed`, after flushing the rollout. Reading snapshots leaves activity unread; replayed history does not publish new activity.
- Clear unread positions removed by a paginated thread revert while preserving explicit thread-start marks and concurrent receipt updates.
## Testing
Add an integration test covering completed-turn receipts, repeated reads without acknowledgement, matching list receipts, and revert cleanup with a changed revision.
GitOrigin-RevId: e7f6ddfbb1fc2fa95d1ef2876d7f0f7b9f99ff65
## Why
A stale read acknowledgement must not clear unread results published after the client’s snapshot or overwrite another read-state edit. Read state also needs to survive thread metadata rebuilds.
## What changed
- Add `thread_read_receipts` and state APIs to query read state, publish thread attention, and mark threads read or unread.
- Track the first unread turn and require matching revisions for explicit edits, returning the current state on conflicts. Allow manually marking even an empty thread unread.
- Retain the last published turn across acknowledgements to suppress duplicate delivery. Keep receipts independent of rebuildable metadata and remove them on thread deletion.
- Return initial read states without creating receipt rows.
## Testing
Add tests covering stale edits, thread-specific initial revisions, repeated unread marks, duplicate publication, persistence across metadata rebuilds and restarts, clearing a reverted turn’s unread position, and deleted-thread handling.
GitOrigin-RevId: fee8c05c20903b1d7aea7e8b61c9248c7f623a72
## Why
Wrapping can retain a cursor sentinel one byte past the end of the input. Using that range to slice source text during hyperlink remapping can panic.
## What changed
Clamp wrapped range boundaries to the input length before calculating hyperlink columns and recording logical source ranges, keeping both aligned with the visible text.
## Testing
Add a regression test that extends a wrapped range past the input boundary and verifies that the line, hyperlinks, and logical source are preserved.
GitOrigin-RevId: c83c817df8d3ea790f7d126768092ae317ff9217
## What changed
- Remove `ContentItemMetadata`, provenance and namespace types, and the `content_item_metadata` protocol field while retaining `content_item_kinds` classifications.
- Simplify context fragments, extension contributions, and hook output to carry content without source attribution. Return MCP tool results directly without an attribution wrapper.
- Render context-window hints together in a single text fragment.
## Testing
Update Responses and Responses Lite request assertions to expect content-kind classifications without per-content attribution, and adapt context, hook, and extension tests to the simplified types.
GitOrigin-RevId: 201894cd4c93c6d4b4c41c845e7a9af1dd3c95ca
## What changed
Add `history_initialization` to `x-codex-turn-metadata`, distinguishing `new`, `cleared`, `cold_resume`, `warm_fork`, `cold_fork`, and `supplied_history`.
Classify forks by whether the source runtime is loaded and has not shut down. Preserve the classification for the runtime's lifetime, including warm resumes and compaction. This records how history was initialized; it does not establish whether tool metadata is missing. Reserve the field against client-supplied overrides.
## Testing
Extend coverage for warm and cold forks, cold resumes, warm reconnects, supplied history, WebSocket metadata serialization, and reserved-field filtering.
GitOrigin-RevId: 468153512a84d0f4d4ea742198a29e0fa3873a72
## Why
Durable remote-control RPC changes need to update the managed daemon's launch settings so future launches use the saved preference.
## What changed
- Save non-ephemeral `remoteControl/enable` and `remoteControl/disable` requests to `remoteControlEnabled` in `app-server-daemon/settings.json` for managed daemons.
- Preserve other settings and write updates atomically. Skip persistence when `daemon.lock` is held so concurrent lifecycle operations take precedence without blocking the RPC.
- Leave daemon settings untouched for ephemeral requests and unmanaged servers.
## Testing
Add integration coverage for durable enable and disable, ephemeral requests, and lock contention. Extend the unmanaged-server test to verify that no daemon settings file is created.
GitOrigin-RevId: 2baf261ed62f7c7ad87c9779ffb91c59e923f0f8
## What changed
- Add the disabled-by-default `features.credential_masking` flag to enable credential brokerage through an already enabled network proxy, retaining custom credential providers and managed configuration precedence.
- Prevent project configuration from overriding credential masking and apply existing credential-broker protections to project shell settings when masking is enabled.
- Keep brokerage inactive when the proxy is disabled. Warn at startup and after permission-profile changes when masking is inactive because sandboxing or the proxy is disabled, or provider environment keys conflict.
## Testing
Add coverage for configuration precedence, project protections in both configuration loaders, permission-profile transitions, inactive-masking warnings, and shell snapshot masking of built-in and custom credentials.
GitOrigin-RevId: 4bcb293356e8c1524bdaa4f1b95cbc1e935a5271
## Why
Parallel Bazel artifacts are advisory while Cargo remains the release path.
## What changed
- Set `continue-on-error` for Bazel matrix jobs covering builds, Windows symbols and signing, and macOS signing, packaging, and verification.
- Assign the main release build jobs in both workflows to the `bazel` environment with `deployment: false`.
GitOrigin-RevId: e8a0fd522ec6482c0f39abdfc8677018be409361
## What changed
Move incremental tool guidance out of namespace descriptions and into a developer message preceding each namespace declaration batch after the initial catalog. The notice covers newly added namespaces as well as changed ones, explaining that earlier tools remain available unless explicitly removed and that newer definitions replace earlier ones.
Retain the notice alongside tool declarations in full-history agent forks, and discard it when legacy compaction forks rebuild those declarations.
## Testing
Add unit coverage for multiple new namespaces sharing one notice. Update request-history snapshots for tool changes, removals and restoration, and regular Responses requests. Extend resume and fork tests to cover notice preservation without duplication and removal when rebuilding declarations.
GitOrigin-RevId: 05f79f5eb378a355cf935eabf63951015a9b454b
Remove the repeated `selected_capability_roots` initializers from the two
`TurnEnvironmentSelection` fixtures in
`mcp_context_preserves_selected_executor_order_and_unavailability` so the
test can compile.
GitOrigin-RevId: 6e773cdcba84b95220eb024d51619fea67780617
## Why
Disabling OpenAI analytics also disabled explicitly configured OTLP metrics collectors. Users should be able to export metrics to their own collectors independently of `analytics.enabled`.
## What changed
Apply the analytics preference only to the built-in `statsig` metrics exporter. Keep custom OTLP HTTP and gRPC exporters enabled regardless of that preference, and use `otel.metrics_exporter = "none"` to disable metrics export. Clarify these settings in config documentation and the schema.
## Testing
Cover exporter selection across explicit and default analytics preferences. Update app-server and daemon telemetry tests to verify custom metrics export with analytics disabled, and worktree tests to disable metrics through the exporter setting.
GitOrigin-RevId: 0c61f0f01e2b694db642ac7e7fd1dac9965c7d96
## Why
Domain wildcards need to retain the byte-based behavior of `globset`. Counting Unicode scalar values changes how `?` matches non-ASCII hosts.
## What changed
Match domain patterns against UTF-8 bytes so `?` consumes exactly one byte. For example, `api??.com` matches `apié.com`. Match hosts through borrowed byte slices, avoiding the per-match character-vector allocation.
Document ASCII case insensitivity and the absence of IDNA conversion: hosts supplied as Punycode require patterns using their Punycode spelling.
## Testing
Compare Unicode wildcard cases against `globset` for both allowlists and denylists, including multibyte characters, combining marks, Punycode, and case sensitivity. Update the exhaustive dynamic-programming comparison and retry-boundary tests to operate on bytes.
GitOrigin-RevId: fae5b3b1ae60b469cd61a44c5c6e245730adc8ba
## What changed
- Add debug spans with review, thread, turn, and tool-call identifiers to correlate approval reviews and background scoring.
- Log review retry scheduling with failure details, attempt limits, backoff, and remaining deadline budget.
- Emit warnings for Guardian V2 background scoring failures with the failure reason, context mode, and duration, even when metrics are unavailable.
GitOrigin-RevId: 3e20d16836576f834998af473815bfb55e671de5
## What changed
- Add `tui.keymap.global.leader`, defaulting to `ctrl-x`, and symbolic bindings such as `leader c` that follow the configured prefix. The default prefix yields to existing custom shortcuts and chord prefixes.
- Keep leader shortcut hints open until completion or cancellation, while ordinary chords retain their one-second timeout. Pressing `esc` or repeating the leader cancels the pending shortcut.
- Add leader configuration and a `Use leader...` capture option to `/keymap`, with resolved shortcut labels and conflict validation.
- Cancel pending chords when input targets change, on paste or focus loss, and on mouse actions other than movement.
- Move the default voice mute shortcut from `ctrl-x` to `f9` and update its tests and displayed hints.
GitOrigin-RevId: 35b964cccd2812c73200f0c26b0f19506821df92
## What changed
Allow mouse selection and plain-text copying of rendered status and footer text, honoring `tui.copy_on_select` and existing selection keyboard controls. Keep the selected region stable while other content updates, preserve Unicode and terminal hyperlinks, and clear selections when their region becomes invalid.
Defer warning clicks until a stationary mouse release so dragging selects text without opening the warning viewer. Preserve the composer draft and cursor while selecting footer text.
## Testing
Add unit and snapshot coverage for visible-text copying, Unicode and hyperlinks, selection invalidation, keyboard ownership, and stationary clicks versus drags. Add a fullscreen integration test for warning selection and draft preservation.
GitOrigin-RevId: dd14d7ede52e97e507be24c4d6ac0299f7388a9b
## Why
Fixed argument limits truncated recorded tool calls even when their metadata fit within the available message budget.
## What changed
- Remove the 8 KiB per-call and 32 KiB per-output argument limits for direct calls and Code Mode.
- Preserve full recorded arguments while retaining message metadata budgets, pending-call limits, and the direct metadata retention limit.
- Rename the normalization helper to `normalize_executed_tool_call_completeness`; it now only clears completeness when calls or tool names were lost.
## Testing
Update regression coverage for large arguments, escaped inputs, reserved-key wrappers, and argument and result metadata preservation across Code Mode waits.
GitOrigin-RevId: 8c199ccf39191d5d44eef02d28b1773654735b43
## What changed
- Reformat Markdown tables and lists, login pages, inline visualization HTML, and sample JavaScript scripts.
- Escape union-type pipes in Python SDK API tables so they render within their cells.
- Keep the formatting-recipe test focused on the working directory and formatter commands by removing assertions on comment text.
GitOrigin-RevId: ae46d5b40fd013553de8b5ccf2c41d76be65aba8
## What changed
Add the disabled-by-default `guardian_trust_orchestrator_connectors` feature flag. When enabled, Guardian V2 accepts connectors with nonblank IDs from the host-owned plugin service orchestrator as a trusted source without requiring a matching user configuration declaration.
Distinguish orchestrator provenance from user configuration in trusted-tool context. Trust remains scoped to the exact server or connector identity and source; descriptions, outputs, other tools, and other connectors remain untrusted.
## Testing
Add coverage for host-owned connector context, rejection of extension-owned Apps lookalikes and blank connector IDs, source-specific trust metadata, and context token limits. Snapshot the connector approval request history.
GitOrigin-RevId: fbd87dd71110ca7b2b92d50eef02e1e739a74a02
## Why
Tools that do not opt into parallel execution acquire an exclusive scheduler lock, serializing independent reads.
## What changed
Allow skill listing and reading, memory listing, reading and searching, conversation history search and reading, plugin listing, agent listing, current time, remaining context, and `get_goal` to run in parallel. Keep goal creation and updates serialized.
## Testing
Add `cloud_skill_reads_run_in_parallel`, which uses a barrier to require two cloud skill reads to overlap and verifies that each returns the expected resource contents.
GitOrigin-RevId: 97b5634f1f84be2ba092be89e6e9c634ca75c07b
## Why
Subagents should retain the spawning turn's selected skills and plugin choices whether `fork_turns` is `none` or `all`. Capability selection should not depend on copied conversation metadata.
## What changed
- Use a shared child startup path for fresh and history-forked agents, inheriting selected capability roots from the spawning environment snapshot.
- Pass the spawning turn's `disabled_plugin_ids` through both spawn handlers. When omitted, inherit the parent's current choices; explicit lists, including an empty list, override them.
- Resolve the parent before startup so inherited client MCP settings apply even when only the session source identifies the parent.
- Carry plugin choices into delegates with inherited isolation and preserve saved capability roots when resuming a child.
## Testing
Add regression coverage for executor skill listing and reading, plugin MCP registration with both history modes, plugin overrides, capability-root precedence and isolation, and restoring saved child settings after parent settings change.
GitOrigin-RevId: 2a6891a9bc6372fd2d1f30add2b5611f96b60594
## Why
A host can reject a request for an unknown session while its lease streams remain open. Keeping that session binding prevents subsequent execution from recovering.
## What changed
Invalidate the session when `Execute` (including its response stream), `Wait`, or `Terminate` returns `NOT_FOUND`, allowing the next execution to open a fresh session. Return the failed call's error without replaying execution.
Document that these RPCs reserve `NOT_FOUND` for unknown sessions, while `CompleteToolCall` can use it for a missing invocation.
## Testing
Add regression coverage for recovery with lease streams still open, no replay of failed execution, and preservation of session state after `INVALID_ARGUMENT`. Add a cancellation-race test confirming that a late tool-completion `NOT_FOUND` leaves the session open.
GitOrigin-RevId: 85b38fdbd6d59268447b6aa6a85ea7c60ec869a7
## What changed
- Add optional `websocketRequestId` to `environment/add` and send it as `X-Request-ID` on direct WebSocket upgrades, including reconnects. It requires a secure transport or a loopback destination.
- Echo a supplied `X-Request-ID` in the exec-server WebSocket upgrade response.
## Testing
Add coverage for `websocketRequestId` serialization and for handshake header forwarding and echoing, both with and without a request ID.
GitOrigin-RevId: 235303ff7e1150405b7e1158d6024223144e0cc3
## Why
API-key accounts could retain a saved Daybreak preference without `ApiKeyCyberAccessPrograms` enabled. Eligible API-key turns also omitted the `standard` access program when Daybreak was off.
## What changed
- Require both `CliDaybreak` and `ApiKeyCyberAccessPrograms` for known API-key accounts, and refresh Daybreak state when either flag changes.
- Use account eligibility consistently for normal turns, continuations, and background tasks so eligible API-key accounts can select the catalog's `standard` program when Daybreak is off.
- Preserve resumed preferences while account state is unknown and update `/daybreak` help to reflect API-key eligibility.
## Testing
Extend regression coverage for feature-flag combinations, API-key continuations, resumed preferences, and `/daybreak` help.
GitOrigin-RevId: 966f4789c9d685ff122da196a13da50c60a4b393
## Why
The iTerm2 session status reports `Working` without describing the current activity.
## What changed
Populate the OSC 21337 `detail` field from the TUI status header during foreground work, for example `Reading source`. Leave it empty for idle, waiting, background-only work, and the generic `Working` header.
Reuse terminal-title text filtering and the 240-character limit, then escape semicolons and backslashes for the status payload. Include detail in the emission cache so activity changes update the terminal even when the lifecycle state stays the same.
## Testing
Add coverage for foreground-only details, payload encoding, text filtering and truncation, and cache updates when the detail changes.
GitOrigin-RevId: b27a287b80e0db52be6cd9d5d246f03897e2996b
Remove the obsolete `default_zsh_path` argument from the call to
`Config::rebuild_with_session_layers` in
`local_mxc_preference_preserves_configured_backend` to match its current
signature.
GitOrigin-RevId: ddb7a73535cc605917971b974333d69bf3a92a93
## Why
Daemon updates must honor application network restrictions and stop when their configuration cannot be loaded.
## What changed
Activate the configured application network policy before creating the HTTP client for daemon updates and the PID update loop. Propagate configuration errors instead of falling back to a default HTTP client.
## Testing
Add tests for configuration error propagation and managed network requirements, covering denied and unlisted destinations as well as an allowed destination. Retain coverage for `features.respect_system_proxy`.
GitOrigin-RevId: 960485c7c57f34654402d7316cab9e0f66f24af3
## What changed
Support `plugins._default.enabled` with explicit per-plugin `enabled` overrides. Omission preserves existing source and account enablement; configuration cannot activate a plugin disabled at its source. Plugin settings such as remembered tool approvals inherit the default unless `enabled` is explicitly set.
Apply the policy to plugin skills, MCP servers, Apps, and hooks, including selected executor roots and runtime configuration refreshes. Preserve the latest plugin policy when adding MCP dependencies and rebuild hooks when concurrent configuration updates replace their inputs.
Report effective enablement in `plugin/list`, `plugin/installed`, `plugin/read`, and `plugin/share/list`. Remote installation still installs disabled packages, but skips MCP and Apps authentication setup without writing an enablement override.
## Testing
Add regression coverage for default inheritance and explicit overrides, source-disabled plugins, policy refreshes during active turns, disabled or malformed selected plugin roots, and remote installation authentication behavior.
GitOrigin-RevId: 83b70c5b47fc95474fec292f248683f1f887221e
## Why
Standalone MCP commands must honor `application.network` restrictions during OAuth discovery and login, even when the MCP server is allowed by its identity requirements.
## What changed
- Apply local network policy to cloud configuration bootstrap authentication and activate the effective policy on the loaded CLI configuration.
- Load `codex mcp add` through the shared cloud configuration loader and use its resolved `codex_home` when saving server configuration.
- Block disallowed OAuth discovery requests before connecting while preserving the ability to save a server when discovery is unavailable.
## Testing
Add isolated regression tests for blocked MCP discovery and login, discovery with network policy disabled, allowed and denied HTTPS destinations, and rejection of malformed managed network policy. Connection checks verify that denied requests never reach a TCP listener.
GitOrigin-RevId: f91401b51d6e6b9472bb01838f0d0903f83d62f3
## What changed
Remove the patched `zsh` resource from package assembly and macOS signing, along with the `--zsh-bin` and `--zsh-manifest` packaging options.
Delete the standalone `codex-zsh` release workflow, build scripts, and DotSlash manifests. Update package documentation and layout and signing tests to match the remaining resources.
GitOrigin-RevId: 429a8db55048fed7facec89957910206523b6013
## What changed
Emit `Idle`, `Working`, or `Waiting` with colored indicators through iTerm2's `OSC 21337` session status protocol. Pending user action takes precedence over running tasks and background processes.
Limit emission to direct iTerm2 TTY sessions without a terminal multiplexer. Deduplicate successful writes, refresh status after terminal handoffs and resume, and clear status on suspension and exit.
## Testing
Add coverage for lifecycle transitions, protocol encoding, terminal detection, write retries, deduplication, and re-emission after terminal handoffs.
GitOrigin-RevId: 750e9ec92aeefc57651886a08ef6aea07675d175
## Why
In `/plugins`, Space edits a nonempty search query, leaving filtered plugins without the advertised toggle shortcut. Refreshing the popup also clears the query.
## What changed
- Add `Tab` to enable or disable the selected plugin while searching, and update toggle hints.
- Preserve the search query and selected plugin when the popup refreshes after a toggle.
- Give configured list bindings precedence over the `Tab` toggle and hide its hints when `Tab` is already bound.
## Testing
Add regression tests and snapshots for filtered toggles, search and selection preservation, and custom `Tab` binding precedence and hints.
GitOrigin-RevId: de98ba2bb3f9d8928ced7216dcc5e4b4fa4c4968
## What changed
- Add `ContentItemMetadata` to distinguish user input, developer instructions, `AGENTS.md`, skills, harness context, and tool-supplied context independently of message role and content classification.
- Keep attribution attached to content through prompt assembly, history processing, and hook-output spilling. Distinguish command hooks from MCP hooks and retain tool namespaces when known.
- Treat missing historical attribution as unknown and send per-content metadata only to Responses Lite.
## Testing
Update request and history assertions to cover attribution persistence and Responses Lite metadata handling.
GitOrigin-RevId: 24e56005f5bdb98bf82f2b3943f29c4c81f3d587
## What changed
Add `windows.require_mxc` to managed requirements. When set to `true` on Windows, reject configurations whose effective local sandbox backend is not MXC without changing the selected backend.
Validate after cloud configuration loads and outside startup recovery fallbacks. Apply the check to app-server startup and configuration loads, in-process bootstrap, session creation, sandbox debugging, and runtime configuration refreshes.
## Testing
Extend configuration tests to cover required and optional MXC selection, separately loaded policy requirements, and runtime refresh validation. Expand app-server startup tests to cover local and cloud MXC requirements, cloud preference selection, and failures without default-config recovery.
GitOrigin-RevId: 16456611bfd9df77e7f959b52515f1885b59ac75
## Why
Navigating to another thread discarded side conversations, preventing users from returning to them later.
## What changed
- Keep side conversations and their event listeners, channels, and pending requests across thread switches and session resets.
- Reopen a parent's existing side conversation with `/side` and submit any supplied question there. Resolve side toggles by the current thread's parent relationship.
- Limit explicit return-and-discard behavior to the active side conversation, and shut down retained side conversations when exiting.
## Testing
Extend regression tests to cover reopening a side conversation after navigating away, preserving its listener and pending approval during a reset, and restricting discard selection to the active side.
GitOrigin-RevId: ff80566970414ba190ff650d5e413ef63dc65449
## What changed
- Accept an optional `description` in `create_channel` and return it in channel summaries so agents can describe a channel's purpose.
- Enforce a limit of 512 UTF-8 bytes and account for JSON escaping in the output budget before creating the channel.
- Store descriptions in both board backends and migrate existing SQLite databases, leaving older channels without descriptions.
## Testing
Add coverage for UTF-8 byte limits, serialization, output budgets, legacy database migration, and persistence after reopening. Update the model-context scenario to create and list a described channel before posting and reading a message.
GitOrigin-RevId: cf6f395944da23e238e078eefa5de201c8b9c197
## Why
MCP servers receiving sandbox state need a usable Codex executable to launch commands with the issuing call's policy. HTTP and remote servers cannot assume access to the host's filesystem.
## What changed
- Include optional `codexExecutable` metadata for local stdio servers when the host supplies an absolute, UTF-8 path to a CLI supporting `sandbox --sandbox-state-json`. Cache capability probes by executable path and bound them to five seconds.
- Document forwarding the sandbox state unchanged and requiring an explicit opt-out rather than silently falling back to PATH lookup or unsandboxed execution when the launcher is absent.
- Honor `useMxc` from forwarded sandbox state when selecting the Windows sandbox backend and network proxy policies, preserving a parent's selection made through CLI overrides.
## Testing
Add coverage for launcher eligibility across local, remote, and HTTP servers, invalid or missing executable paths, and binaries without sandbox-state support. Extend metadata integration and serialization tests to cover the optional launcher field, legacy state, and unknown future fields.
GitOrigin-RevId: ea8cd3770616e5a620b423a01052a7bc828bceb9
## What changed
On Linux and macOS, strip the packaged copies of source-built release entrypoint and `codex-code-mode-host` binaries while retaining symbols in the original build outputs.
Add `--strip auto|all|none` and `--strip-tool`. The default `auto` preserves prebuilt inputs and other build profiles; `all` also strips those package copies, and `none` disables stripping. Select target-compatible strip tools and fail on missing tools or strip errors. Leave third-party resources unchanged.
## Testing
Add a regression test that compiles an executable with debug information, verifies stripped package binaries are smaller and still runnable, and checks that original inputs, preserved package copies, and third-party resources remain byte-for-byte unchanged.
GitOrigin-RevId: dc363c04690aa9e772690417a52a8eff31650278
Send `User-Agent: codex-package` when downloading archives in
`scripts/codex_package/dotslash.py`.
GitOrigin-RevId: b12dc962b28d795704ba780b020fbf7ab91f5d50
## Why
GovCloud guidance was tied to Bedrock credential setup, so users with an already configured provider could miss it.
## What changed
Check for GovCloud during TUI startup using the app server's resolved provider, including when connecting to a server. Require acknowledgment before proceeding and save `notice.hide_gov_cloud_guidance = true` to suppress the screen on subsequent launches. Quitting the guidance exits startup without saving acknowledgment.
## Testing
Add a terminal integration test covering acknowledgment persistence, quitting without saving, and suppression after restart. Retain coverage for explicit acknowledgment and scrolling in short panes.
GitOrigin-RevId: f09fd73a66fb02f94ebdd3c3b0dbe5712dfa9be7
## What changed
Add `include_environment_context_time`, enabled by default. Setting it to `false` omits `<current_date>` and `<timezone>` while retaining the rest of the environment context, and skips the clock read used to populate the date.
## Testing
Extend configuration, session context, and external time provider tests to cover enabled and disabled time fields, context updates across turns, and current-time reminder behavior.
GitOrigin-RevId: 5071ce1701c044b680624d0cdbba7e0bc2b5bbe6
## What changed
- Use the standard shell executor and remove the zsh fork escalation runtime, `codex-execve-wrapper`, and `shell-escalation` crate.
- Ignore `shell_zsh_fork` and `unified_exec_zsh_fork`, emit migration notices for legacy configuration, and warn when ignoring managed requirements for these flags.
- Keep the active session's `apply_patch` alias directory readable under restricted filesystem permissions.
## Testing
Add coverage for legacy configuration startup and shell execution, migration notice rendering, active alias directory selection, and nested `apply_patch` execution while other files in `CODEX_HOME` remain unreadable.
GitOrigin-RevId: 43af461fea32b4980550ee7237effd2bc0646ed8
## Why
Command processes need thread and tool call labels for correlation, without stale values from inherited environments or cached shell snapshots.
## What changed
- Export the originating `exec_command` call ID as `CODEX_TOOL_CALL_ID`; later `write_stdin` calls leave it unchanged.
- Apply executor metadata as `CODEX_THREAD_ID` and `CODEX_TOOL_CALL_ID` after environment policies, overlays, and snapshot replay. Clear omitted fields when metadata is present; without metadata, preserve thread context and remove the call ID.
- Exclude both IDs from newly captured snapshots and omit the call ID from capture and validation helpers.
- Preserve empty call IDs, omit NUL-containing IDs, and handle case-insensitive environment names on Windows. Document that these labels support correlation, not authorization.
## Testing
Add regression coverage for metadata precedence, missing and invalid IDs, snapshot capture and replay, local and remote execution with pipes and TTYs, sandboxed remote execution, and preservation of the originating call ID across later input.
GitOrigin-RevId: 1027212b5d495d8e7cfac0f498c3134e060aa897
## Why
Persisted multi-agent v2 children created after the client disconnects need lifecycle listeners so their runtimes can be released once idle. Listener attachment must also wait for an earlier runtime's cleanup to finish.
## What changed
- Start lifecycle listeners for persisted v2 children even when no initialized clients are connected, and defer attachment until pending unload cleanup completes.
- Keep ephemeral children loaded so follow-up tasks retain their model context.
- Raise the default `thread_unload_delay_secs` from 60 seconds to 1800 seconds (30 minutes), updating the configuration documentation and sample.
## Testing
Add regression coverage for children spawned after disconnect with zero- and one-second unload delays, including waiting for pending cleanup, keeping running threads loaded, releasing idle runtimes, and preserving an ephemeral child's earlier reply across a follow-up. Update configuration tests for the new default and explicit overrides.
GitOrigin-RevId: 2fecc77b5c03237aa8fd7eacc4bd119b99d36e0a
All callers already check that an assessment payload is present before parsing it. Change `parse_guardian_assessment` to accept `&str` instead of `Option<&str>` and remove its redundant missing-payload check.
Update the callers and existing parser tests to pass text directly.
GitOrigin-RevId: e4fb4bf7aca5b20f25f5b27300ce9a6f22c97939
## What changed
Add a scenario test that queues a message for an idle worker, evicts it, and resumes it with `followup_task`. Assert that the same worker is reloaded and that queuing mail and eviction do not start another model turn.
Snapshot the complete parent and worker request histories and the resumed worker's mailbox to verify that earlier context and unread mail survive eviction in order.
GitOrigin-RevId: 2d0f7c63a2221df9c3d7e378eecaf14b8441d2b9
## Why
A conversation classifier waiting for preparation or full response completion can block newer classifications. Concurrent reviews also need to prevent a later action's evidence or low-risk score from being reused for an earlier action.
## What changed
- Run conversation classifications independently, forking the latest compatible completed history from an earlier action. Only a valid completion with a newer action index can replace retained history.
- Keep admission and observation ordering atomic, and hold capacity permits through full response completion.
- Reject cached low-risk scores from later actions for tool-linked approvals, including initial approval checks.
- Track originating tool-call IDs separately from approval display IDs, preserving stdin write provenance and excluding synthetic MCP elicitation IDs from tool ordering.
## Testing
Add regression coverage for delayed preparation, capacity admission, out-of-order completion, cancellation, invalid retained output, and history snapshots. Exercise pending approval ordering in both `snapshot` and `conversation` modes, and verify linked and unlinked MCP elicitation provenance.
GitOrigin-RevId: 097476ccb3b8718369a69f55c3c39132f7f1a4c1
## What changed
Extend `steered_input_checkpoint_controls_next_request` to cover user input with `InstantInterrupt` enabled under both background and synchronous checkpoint policies. Keep the original response gated until the follow-up request arrives to prove that interruption advances the turn while preserving checkpoint ordering.
Explicitly disable `InstantInterrupt` for user-input cases that wait for response completion, and enable it for the tool-output case to verify that tool outputs still wait for completion and synchronous persistence.
GitOrigin-RevId: d39544ce6f5ad83489fd8a80b1e731a64c7a876c
## What changed
Add `cancelled_v2_send_finishes_reload_registration` to verify that cancelling a multi-agent V2 send during an evicted child's reload does not cancel registration. The test checks that the thread-created notification arrives and evicted-environment state is cleared.
Evict and reload the child again with only one child slot available to catch leaked residency pins or reservations, and verify that only the subsequent follow-up message is delivered.
GitOrigin-RevId: ce6ed90d0049245370f26d8dbb35b9f1cd0b3063
## What changed
- Route app-server idle unloading of multi-agent v2 children through local eviction that preserves unread mail and environment selections for reload.
- Hold residency pins through input submission so newly reloaded children cannot be evicted before receiving their work.
- Guard listener cleanup against replacement runtimes and subscriptions, and reject local eviction of host-controlled threads.
## Testing
Add coverage for unsubscribe-driven eviction followed by `followup_task`, verifying restored conversation context and exactly-once delivery of queued mail. Extend tests to check that residency pins block eviction and that rejected host eviction preserves the thread and mailbox.
GitOrigin-RevId: e36723730af683d2081e495e637f0e6d23548b8d
## What changed
Record local MXC availability and the selected Windows sandbox backend at app-server and session startup. Log the backend again when an accepted session settings update changes the Windows sandbox level, using a blocking task for the log write.
Selection entries distinguish `mxc`, `disabled`, `unelevated`, and `elevated` in the sandbox logs under `.sandbox` in Codex home.
## Testing
Update the remote thread persistence assertion to allow the `.sandbox` directory on Windows, since startup logs are not thread persistence artifacts.
GitOrigin-RevId: 4130b59ac7761223775ac9b6afb096abb7fb4615
## Why
Compaction analytics lack a voice session ID. A compaction event can arrive after its voice session has closed or another session has started, so attribution needs to account for when compaction began.
## What changed
Add `voice_session_id` to compaction events. Track realtime session starts, ID updates, and closures, retaining up to 16 recent closed session windows. Resolve the session from the compaction start timestamp, falling back to the turn's voice session ID.
Forward realtime session ID updates from the app server to analytics and update the active turn's attribution.
## Testing
Add coverage for realtime session boundary facts, compaction event serialization, and delayed compaction events across consecutive voice sessions.
GitOrigin-RevId: 981da0ea2c38a87079b6bab33daf2c88fd95160f
## What changed
Add `functions_namespace_functions_description_prefixes` to model tool messages, keyed by unqualified tool name. Prepend this guidance to descriptions in the `functions` namespace across direct declarations, Code Mode documentation, and tool-search results, including custom tools.
Trim prefixes, ignore empty values and unavailable functions, and enforce a combined 256-byte UTF-8 limit including separators for reachable tools. Keep overrides local to each step, preserve search ranking text, and retain runtime caches for unaffected tools.
## Testing
Extend coverage for direct and indirect descriptions, clearing prefixes when switching models, namespace scoping for deferred dynamic tools, and tool-search cache reuse and reset.
GitOrigin-RevId: f434e37cec010764fe3e09fb12c339e933b3c21c
## Why
Disabling `experimental_request_user_input_enabled` previously left `request_user_input_async` available when the model advertised support for it.
## What changed
Require the user input setting to be enabled before registering `request_user_input_async`, while preserving the root-agent restriction and support for both current and legacy model capability names.
## Testing
Add parameterized tests covering enabled and disabled settings, current and legacy capability names, missing capabilities, and subagents. Also verify that `send_message_to_user_async` remains available to root agents independently of the user input setting.
GitOrigin-RevId: 27156a3fe7da38d10fccb6384f28e755c39abc39
## Why
Network domain rules need explicit wildcard semantics independent of filesystem glob syntax, including matching Unicode hosts with `?`.
## What changed
Replace `globset` in network allowlist and denylist matching with a domain matcher. Make `?` consume one Unicode scalar value, retain ASCII case-insensitive matching and existing host normalization, and preserve the distinction between `*.example.com` and `**.example.com`.
Reject empty patterns, repeated wildcards outside the supported `**.` prefix, character classes, brace expansions, escapes, slashes, and embedded whitespace when loading policies. Continue allowing global wildcards only in allowlists.
## Testing
Add coverage for Unicode wildcard semantics, unsupported syntax, IPv6 normalization, invalid entries in either policy list, and adversarial matching inputs. Compare the matcher against an independent dynamic-programming implementation over exhaustive short inputs.
GitOrigin-RevId: 64f65fcda1a50998d70e046445d22cd2d2dcf27a
## Why
Windows sandbox setup diagnostics previously displayed only the outer error context, hiding native failure causes needed to diagnose ACL failures.
## What changed
Preserve full error chains in ACL refresh summaries, setup logs, and sandbox binary directory lock failure reports. Include the requested access rights in ACL update open errors, and retain recorded ACL failures even when writing their log entries fails.
## Testing
Add tests covering error chains for ACL checks, grants, and denies; preservation of accumulated failures when logging fails; and native directory-open errors surviving a structured setup report round trip on Windows.
GitOrigin-RevId: 0a44a56b13d13b52b92ec673aaa2da7bc6cf0753
## Why
Full WebSocket requests previously used the generic `other` reason when continuation failed because request properties or input changed, obscuring why incremental reuse was unavailable.
## What changed
- Report specific reasons for changed request properties, shortened or mismatched input, and missing response state or response IDs.
- Add `previous_item_type` and `current_item_type` labels to continuation metrics and failure traces. Diagnostics use bounded labels without request contents or identifiers.
- Centralize response item type names in `ResponseItem::item_type()` and reuse them for output logging.
## Testing
Add coverage for unavailable response state and empty response IDs. Expand WebSocket tests to check fallback reasons and item types for rewritten or shortened input, replaced input, changed model, and changed output schema, including precedence when multiple properties change.
GitOrigin-RevId: 3951853dfe87d40b7046af6f6a8efd5d4f5b06d1
## What changed
Record `codex.tools.incremental_updates` through session telemetry with an `action` tag for `added`, `removed`, and `schema_changed`. Definition changes include description edits.
Exclude initial catalogs, unchanged tools, and namespace headers from the counts. Count each removed namespace member even when the removal notice lists only the namespace.
## Testing
Extend the namespace transition snapshot test with in-memory metric assertions covering additions, removals, definition changes, and excluded initial or unchanged catalogs.
GitOrigin-RevId: 0fadb40a3aa7abf5ef1757811ebfb5749505b3d9
## Why
Truncating recorded arguments does not lose the call inventory. Clearing `tool_calls_complete` in that case incorrectly treats retained calls and tool names as incomplete.
## What changed
Define `tool_calls_complete` as completeness of the ordered call inventory, independent of recorded arguments. Preserve it for direct tool outputs and Code Mode cells when argument limits or message budgets truncate arguments, including across later waits. Continue clearing completeness when calls are omitted or tool names are truncated.
## Testing
Update protocol, recorder, and integration tests to verify completeness survives argument truncation and message budgeting. Add coverage confirming that omitted calls and truncated tool names still clear completeness.
GitOrigin-RevId: 1534dbfabbd1291b840dd6fb6738ed51bcd4c0c4
## Why
`MODULE.bazel` already references `mxc-sdk_utf8_resources.patch`, but the patch file and its Bazel export are missing.
## What changed
Add and export the patch to pass `/c65001` to the Windows resource compiler when embedding `mxc-sdk` binary version information, selecting UTF-8 as the resource code page.
GitOrigin-RevId: 80cd64e6a8056c61868b5e20fd8e2fee69c1b96b
## Why
Prediction forks need to preserve the parent's effective context and request settings to maximize prompt-cache reuse.
## What changed
- Add `experimentalPredictionMode` to `thread/fork` for ephemeral forks of loaded, persisted parents. Reject configuration overrides, `path`, `lastTurnId`, and `beforeTurnId` in this mode.
- Inherit the parent's effective configuration, tools, environments, collaboration settings, disabled plugins, and persisted history.
- Enable `features.reasoning_effort_override` on the fork while preserving the parent's request-effort baseline, including when overrides were disabled on the parent.
- Report the fork's effective model, service tier, and reasoning effort in the response.
## Testing
Add coverage for matching parent and fork requests and prompt-cache keys across legacy and paginated history, invalid fork parameters, and reasoning-effort inheritance. Add a context snapshot for identical parent and fork continuations.
GitOrigin-RevId: 46b41f2ac331562b441dadff1a0a9f926c94880d
## Why
Global requests can inherit project settings from the app-server's launch directory. This can prevent marketplace removal or expose project-only feature settings, and config reloads can fail if that directory is deleted.
## What changed
- Load configuration without project context when no working directory is supplied, using `CODEX_HOME` to materialize `Config.cwd`.
- Use global configuration for marketplace mutations, marketplace upgrade reloads, and MCP requests without thread context.
- Pass the launch directory explicitly during startup to preserve project-aware startup configuration.
## Testing
Update regression tests to verify that marketplace removal ignores launch-project configuration and leaves the project config intact. Extend feature-list coverage to verify that global requests ignore project features, thread requests retain them, and global requests work after the launch directory is deleted on Unix.
GitOrigin-RevId: b77063a7ea0b09fd0a79cfc4040db9f1d02606b3
## What changed
Add the `codex.tools.registered` histogram to count finalized tool registrations by `exposure` and `tool_mode`, including zero counts for empty exposure categories. Record it once per sampling request before transport retries, excluding hosted tools. These counts describe the registered inventory, not model visibility or tool reachability.
## Testing
Add an integration test covering a stream retry, direct and deferred namespace tools, a model-only tool, and hosted web search. Verify that registrations are recorded once, hosted tools are excluded, and metric labels contain no tool names or descriptions.
GitOrigin-RevId: 02b450743886e3d487d6c3bcda12eb65f6d1104b
## Why
Rendering an entire question title as one terminal line removes line endings and misaligns hyperlink source ranges with the visible text.
## What changed
Wrap and annotate each logical line of asynchronous question titles separately, preserving blank lines and handling both LF and CRLF endings while retaining complete hyperlink destinations.
## Testing
Add a rendering regression test and snapshot covering multiline titles with code fences, Unicode text, and a URL. Check LF and CRLF rendering equivalence and hyperlink destinations at narrow and wide widths.
GitOrigin-RevId: ccd7256dbaed91ce98374e52b17d3a1b87645574
## Why
Generated app IDs produce opaque plugin mention labels. A selected `@foo` plugin mention also prevented a separate `$foo` skill mention from being submitted.
## What changed
- Use eligible display names, such as `@Postman`, for plugins named `app-` followed by 32 lowercase hexadecimal characters, while preserving the plugin binding. Accept 1–64 ASCII letters, digits, underscores, or hyphens, excluding common environment variable names; otherwise retain the existing naming fallback.
- Only `$` mention bindings suppress automatic skill selection, allowing `@foo $foo` to submit both the plugin and the skill.
## Testing
Add naming tests for accepted display names and fallback cases, a composer snapshot verifying `@Postman` and its plugin binding, and a submission regression test for a plugin and skill sharing the name `foo`.
GitOrigin-RevId: aa8c98f293d12e62d32d43206e076cbe1fcb2a3b
## Why
Detect changes to the default model-visible prefix relative to a released CLI, requiring those changes to be gated behind a default-off feature key.
## What changed
Add `prompt_prefix_matches_release` to compare instructions, tools, and input preceding the user message using the same client and inputs. Each binary uses its bundled model catalog and feature defaults. The comparison removes response item IDs and transport metadata and normalizes fixture paths and session identifiers while preserving prompt text, whitespace, tool descriptions, schemas, and array ordering.
Use the released binary supplied by `CONTRACT_EXECUTOR_BIN` when available; otherwise, compare two runs of the current binary to check determinism.
GitOrigin-RevId: 1a69fb3abb6fc3df90a095e01bcf0d5de1818fac
## What changed
- Add Cargo and Bazel build matrices for Linux, macOS, and Windows, carrying both through signing, packaging, and artifact verification.
- Publish Bazel binaries, packages, and symbols with a `-bazel` suffix while preserving Cargo artifact names. Keep Python runtime wheels and the Windows installer on the Cargo path.
- Use `--config=release` for native voice builds and Windows voice tests, set the macOS voice build minimum to 14.0, and increase the Windows binary build timeout to 120 minutes while both build paths coexist.
GitOrigin-RevId: 77bcdd7b2a573d0ae2a4c3392e0708445b386f23
## What changed
Add a `build-system` input to `build-codex-packages`, defaulting to `cargo`, and extract binary builds into dedicated Cargo and Bazel actions. The Bazel path stages binaries and symbols for the shared CLI and app-server packaging and smoke-test steps, with support for `release` and `debug` build modes.
Resolve the package source root before invoking nested actions, and use Bash to export the Bazel repository cache path.
GitOrigin-RevId: ebd5e7c84451733419838da5956dc090cd09b19a
## What changed
- Add `runtime_package` targets for combined, primary, app-server, and Windows helper bundles, plus per-binary release archives.
- Apply release settings automatically and retain unstripped binaries with macOS dSYM or Windows PDB symbols. Require platform-specific symbols and validate that dSYM bundles contain nonempty DWARF data.
- Support a `debug` build mode for faster package smoke builds and configure platform-specific release settings, including native Windows MSVC toolchains.
- Add a composite action that refreshes Cargo workspace metadata, builds the selected archive, and extracts writable files for existing signing and packaging steps.
GitOrigin-RevId: 21109875cde228aaef67b2ba9812b3e4854aee84
## Why
Cargo and Bazel embed different PDB filenames in the Windows code-mode host executable. The package smoke test must support both names while verifying that the debug symbols match the packaged executable.
## What changed
- Keep the archived PDB and copy it to `codex_code_mode_host.pdb`, allowing `dumpbin /PDBPATH` to resolve either name. Accept either path in the assertion.
- Set `sandbox_workspace_write.writable_roots = []` explicitly in the smoke-test configuration.
GitOrigin-RevId: fc2610f580dad49e38848582bc63f1f829cb766d
## Why
Bazel release builds need Cargo-compatible Rust and native build-script settings. Platform-specific issues also include Windows command-line limits, MSVC runtime conflicts with V8's allocator, and a missing V8 `__clear_cache` symbol on ARM64 musl.
## What changed
- Add `--config=release` settings for thin LTO, four target codegen units, and disabled debug assertions and overflow checks, with separate settings for build tools.
- Add opt-in Cargo release profile support for build-script optimization and debug information, preserving explicit C/C++ flags. Give optimized Bubblewrap builds `-O3`, debug symbols, and enabled native assertions.
- Statically link the MSVC CRT for Rust and C/C++ target and host dependencies, and disable SQLite intrinsics on x64 MSVC to avoid startup crashes on older CPUs.
- Let the Rust process wrapper read its arguments from a multiline parameter file to avoid Windows command-line limits.
- Select the ARM64 musl V8 archive containing compiler-rt builtins and raise the Rust recursion limit to `256` in the app-server client, exec, and TUI entry points for release compilation.
GitOrigin-RevId: 8f61e62b8735c36209ee92e04a0e0339a70badc5
## What changed
Expose resolved Cargo package names in `DEP_DATA`, set `CARGO_PKG_NAME` for Rust compilation, and pass the package name to build scripts. Propagate `rustc_env` to generated binary targets so they receive the same package metadata as libraries.
## Testing
Strengthen the packaged CLI smoke test to require `--version` to print exactly `codex-cli <version>`, using the workspace package version from `codex-rs/Cargo.toml`.
GitOrigin-RevId: 274b741067af76313358f44c1bd9b2521938fa9c
## What changed
Wire existing sandbox integrity checks into local command preparation, exec-server process preparation, and sandboxed filesystem helper and file-open operations. Make execution request preparation asynchronous so callers can await the checks.
The checks remain observational: failures and timeouts do not prevent command execution.
## Testing
Add regression tests that launch a real command after checker preparation fails or exceeds its timeout, verifying successful output and exit status.
GitOrigin-RevId: a82399f8aeb8b08f9965e6121b4c7f460552af3f
## What changed
Export `run_integrity_checks` from `exec-server` to check whether the effective filesystem policy permits writing containment dependencies on Linux, macOS, and Windows. Run preparation and checks on a blocking worker, limit waiting to five seconds, and keep results observational without affecting execution.
Skip mismatched sandbox backends, full-disk-write policies, and `EscalatedSandboxWithRestrictions` overrides. Continue checking ordinary configured policies with root write access and deny restrictions.
Record check outcomes, preparation time, and total duration with bounded metric tags that omit filesystem paths.
## Testing
Add coverage for findings, clean results, missing dependencies, preparation errors, eligibility rules, and timeouts. Verify that timed-out workers emit no late results and that metrics contain no filesystem paths.
GitOrigin-RevId: a234f4a2f629f9bb090da622cea352c99456cb00
## What changed
Enable the exec server's `sandbox_integrity` module on macOS and select the Seatbelt backend. Inventory the Codex executable and the system Seatbelt executable as critical dependencies.
Preserve the filesystem sandbox policy unchanged: Seatbelt handles deny globs as native patterns, so no snapshot scan is needed.
GitOrigin-RevId: 78299dd61e168f5ce34454c8b3bb887e67c5f342
## What changed
Add Linux dependency discovery and policy preparation to `exec-server`'s sandbox integrity module. Inventory bundled and system `bwrap` candidates and the deny-glob scanner using the launcher's location and the command's `PATH` and working directory.
Resolve `:tmpdir` and tilde-prefixed deny globs using the command's `TMPDIR` and `HOME`, with account home-directory fallback. Reuse Linux sandbox helpers to expand deny globs in the command's explicit environment.
## Testing
Add Linux tests covering symlinked launchers, relative and empty `PATH` entries, and empty, relative, and tilde-prefixed `TMPDIR` values alongside home-relative deny globs.
GitOrigin-RevId: fe404fa4be77ece677b22d52d77a7234dbf0cffe
## What changed
Mark `code_mode_interrupt` as stable and enable it by default, so interrupting a turn terminates active code mode cells and nested tool calls.
## Testing
Update the existing interruption test to use the feature default instead of explicitly enabling `CodeModeInterrupt`. It verifies that active cells and nested tools are aborted while stored session values remain available.
GitOrigin-RevId: 17be94f208713bc232e2292feb48261938254db3
## What changed
Add Windows MXC backend helpers to inventory the Codex executable, sandbox
launcher, and available `rg` scanner when deny globs are configured. Prepare
filesystem policies for inspection by reusing MXC temporary-directory and volume
resolution and replacing deny globs with concrete path snapshots.
Allow Windows deny-glob resolution to run its scanner with an explicit command
environment and working directory, including an empty environment. The integrity
helpers are not yet invoked by an execution runner.
## Testing
Add a backend test verifying that deny-glob snapshots replace the original
patterns, including empty snapshots, and affect `FileContentsChecker` results.
GitOrigin-RevId: 409c527663d230d76d65be3bf0a37959f694d77e
## What changed
Export `FileContentsChecker` and structured integrity findings from `codex-rs/sandboxing` to identify existing containment dependency files whose contents are writable under a prepared filesystem policy. Findings include the requested target, its resolved path, and the write roots that permit modification.
Resolve symlinks in targets, write roots, and read-only carveouts, and respect protected metadata paths and deny globs matching resolved contents. Missing targets produce no finding; non-file targets return an error. Callers remain responsible for dependency inventory, reporting, enforcement, and handling full-disk write access.
## Testing
Add unit tests covering write grants, read-only and denied carveouts, overlapping grants, deny globs, symlink resolution, protected metadata, and missing targets.
GitOrigin-RevId: 4f52faed822a1bbb4ed33a9975af0718a5f85662
## Why
Prepared MCP calls cloned `ToolInfo` already stored in the binding's model-visible catalog, duplicating tool metadata.
## What changed
Store the binding catalog in an `Arc<[ToolInfo]>` and let prepared calls reference its entries by index. Keep separately owned metadata for tools hidden from the model and calls prepared outside the binding catalog.
## Testing
Extend the binding test to assert that advertised and prepared tool metadata share the same address, while preserving ready-client catalog selection and hidden-tool behavior when tool names collide.
GitOrigin-RevId: 24b92f7e1dbb421c9ebce875b9b1024f7d697c5e
## Why
Opening active EXE/DLL files with `MAXIMUM_ALLOWED` can request access that causes sharing violations during sandbox runtime ACL repair.
## What changed
Restrict `MAXIMUM_ALLOWED` opens to directories that need to suppress child ACL propagation. For files, request `READ_CONTROL | WRITE_DAC` only when an ACL update is needed.
Preserve the non-inheriting grant behavior from https://github.com/openai/codex/pull/49690, including existing permissions, deny ACEs, and null DACLs.
## Testing
Extend the Windows runtime repair regression test to hold `node.exe` open with `FILE_SHARE_READ` throughout repair and revalidation, while checking read/execute access and preserved denials.
GitOrigin-RevId: 2e087b51adc0221d0eda061fa0a34d2e98409662
## What changed
- Replace the separate MXC crates with the pinned `mxc-sdk` 1.0.0 dependency and update Cargo and Bazel lockfiles.
- Use the cached PSEC API-set check for availability and the SDK's native deny-path capability check before launch. Native creation and request-specific capabilities are validated at launch.
- Map empty environments to `None` to retain Windows user-profile defaults, while keeping nonempty environments explicit. Document the SDK's `SystemRoot` and `LOCALAPPDATA` requirements.
- Configure Bazel's LLVM resource compiler for Windows GNU builds, document Cargo's `RC_PATH` requirement, and add `libproc` and `libsandbox` to the macOS SDK libraries.
## Testing
Update the request-building test to verify that nonempty environments remain explicit and empty environments become `None`.
GitOrigin-RevId: f3ccbb92ceaa71f16c5d6cb185a7602a5bb8da53
## What changed
Enable `instant_interrupt` by default so new user input can preempt responses and yield foreground code-mode observations. Keep the feature marked as under development and update feature-policy tests to allow this exception.
Explicitly disable instant interrupts in core, TUI, and Python SDK tests that depend on responses completing before steering or processing subsequent input.
GitOrigin-RevId: a8cab2d6c445bfdbd10b0b2abcf7893d32ee8595
## Why
User-verification cancellations previously discarded failure reasons, leaving MCP servers unable to distinguish user cancellation from unavailable approval, interruption, or invalid proof.
## What changed
- Carry a bounded `openai/userVerificationReason` value in response `_meta` for verification failures, declines, and cancellations across the TUI, app server, and MCP client.
- Preserve recognized reasons and classify invalid responses, missing or invalid proofs, response errors, closed response channels, interruptions, and unavailable approval.
- Discard unknown reasons and unrelated metadata. Keep proof material out of decline and cancellation responses, and keep display messages and raw error diagnostics out of response metadata.
## Testing
Add and update tests for typed failure propagation, metadata filtering, invalid proofs, response-channel failures, interrupted requests, and unavailable approval, including TUI RPC and native MCP response coverage.
GitOrigin-RevId: 6b7f855ce8eb13e759b5b86d0dc2b1afdfcff7b3
Remove repeated `selected_capability_roots` initializers from two
`TurnEnvironmentSelection` fixtures so the registry test can compile.
GitOrigin-RevId: bef3fba18dd786b80610703a37d6d3243cf33401
## What changed
Add the `ultrafast` service tier to bundled catalogs for `openai.gpt-6.1-sol` on Bedrock Mantle and `global.openai.gpt-6.1-sol` and `us.openai.gpt-6.1-sol` on Bedrock Runtime. This exposes `/ultrafast` for these models while keeping tier selection opt-in.
## Testing
Extend catalog, app-server, core request, and TUI tests to cover GPT-6.1 Sol tier discovery and selection across all three model IDs, including toggling back to the default tier and honoring custom catalog commands.
GitOrigin-RevId: b5bbde8615b73a1d73eb16db7952b10d044b9fa6
## What changed
Move `SandboxOverride` into the shared protocol and carry the controller's selection through tool attempts, execution requests, and exec-server process and filesystem sandbox preparation. Include it as `sandboxOverride` in filesystem sandbox contexts for observation without granting broader permissions or altering sandbox commands.
Default missing values to `NoOverride` and omit that value when serializing to preserve compatibility with existing requests.
## Testing
Extend tests to cover override propagation, wire round-trips for all three variants, and deserialization of requests without `sandboxOverride`.
GitOrigin-RevId: 2f438cf4aef1134e3149959d14aa731682168ae5
## Why
Tokio runtime tracing can cause SQLite log writes to enqueue more writes and exporter activity to generate further OTLP exports.
## What changed
- Exclude `tokio` and `runtime` spans from OTLP export alongside `h2` spans.
- Limit `tokio::` and `runtime::` targets to `INFO` in the default log filter, and reject their `TRACE` events directly in the SQLite sink even without an outer filter.
- Box and pin the session-loop future before spawning it.
- Reorder tracing and Tokio test attributes, restrict the skills concurrency test's subscriber to the catalog-refresh span, and use the default log filter in the SQLite formatter comparison test.
GitOrigin-RevId: f545013a2469088d7f9890c1f46bb93eb5446d2d
## What changed
Update the bundled `openai-docs` references to cover GPT-6 Astra, GPT-6.1 Sol, GPT-6 Sol, and GPT-6 Luna with model-specific reasoning, tool-calling, parameter, and data residency guidance.
Require verification of the exact target's availability and compatibility, preserve explicitly requested models, and use live guidance for model selection. Replace fixed role mappings with verified targets and clarify when to load migration and prompting fallbacks.
GitOrigin-RevId: 59067d0fc97af36d2e5b6508c45488181c6a4ace
## What changed
Consume enabled tool definitions and borrow their metadata when installing `tools` and `ALL_TOOLS`, avoiding copies of the tool catalog. Retain only tool names and kinds in runtime callback state, preserving each cell's original callback indices for its lifetime.
GitOrigin-RevId: 62eaf62abce6de1a0cd5cdb3332fbed754a23993
## What changed
Remove the duplicate tool metadata stored in `CachedMcpHandler` and compare incoming metadata directly with `McpHandler::tool_info()`.
Preserve complete agent plugin namespace descriptions in the handler, applying the existing 1,000-byte limit when building tool specs and search metadata. Truncation continues to respect UTF-8 character boundaries.
## Testing
Extend the agent plugin namespace description test to verify that the handler retains the full description while search output remains bounded.
GitOrigin-RevId: d0a9d5f6796143315235e658e77e059657e85f13
## Why
Guardian cannot capture sender instructions from another host when the sender thread is absent from the receiver's local runtime.
## What changed
Fall back to the authenticated thread store to reconstruct sender history without resuming the sender. Respect compaction and rollback, and label persisted evidence to indicate that newer unpersisted messages may be missing.
Limit storage reads to five seconds and capture sender context before acquiring the active-turn lock. Bind the captured evidence to the turn that accepts the delivery, allowing an existing turn to finish while the read is pending.
## Testing
Add cross-host scenarios for legacy and paginated history that verify sender evidence reaches only Guardian and excludes rolled-back permissions. Add a gated storage-read test that verifies turn completion remains unblocked and evidence is bound to the newly accepted turn.
GitOrigin-RevId: fe896f4e82fe3e32017fe4884846f3fa90a87949
Background discovery can cache a successful response before the test mounts
its unauthorized-response mock, bypassing the intended token refresh.
Mount the `401` mock before invalidating the route cached during login in
`external_auth_refreshes_on_unauthorized`.
GitOrigin-RevId: 8c280ca7287dab09230d534a44ca80d0835d2ef2
## What changed
Apply `code_mode_tool_description_first` when preparing nested tool definitions for Code Mode execution and tool search. When enabled, place each tool's description before its namespace description; otherwise, preserve namespace-first ordering.
Reuse cached MCP definitions only when both the input schema budget and description-order setting match.
## Testing
Extend deferred app tool integration tests to cover both description orders with and without ranked search, including consistency between search results and `ALL_TOOLS`. Extend the MCP cache test to reject reuse when the description-order setting changes.
GitOrigin-RevId: 1e3f84d2d95c200aef21ad710d367274b2169b4b
## What changed
Register `code_mode_tool_description_first` as an under-development feature, disabled by default, for placing tool descriptions before namespace descriptions in Code Mode. Add the boolean option to the configuration schema.
GitOrigin-RevId: 5d7e2f7cef87a040f9d96b0d97c2697880c12c17
Replace fixed 500 ms sleeps in `helper_attempt_is_shared_after_cancellation` with polling of the helper completion marker every 10 ms, bounded by a five-second timeout.
This lets the test observe completion independently of the cancelled headers or refresh request without assuming the helper finishes within 500 ms. Preserve the assertions that subsequent calls reuse the same helper attempt.
GitOrigin-RevId: 2612679aff756306ea3e05ef7bb9b4db02633fd5
## Why
Authorization updates during a pending Guardian approval can invalidate its decision. Retries need the updated guidance without inheriting the invalidated review or losing earlier valid context.
## What changed
- Validate authorization while the reviewer is reserved, before publishing its history checkpoint.
- Roll back stale attempts to the last committed review, preserving earlier valid reviews across repeated invalidations.
- Pin the issuing action's repository instruction snapshot for reviewers and retries, avoiding fresh instruction discovery through disconnected executors.
- Treat stale authorization as a request for a new review rather than a failed decision.
## Testing
Add regression coverage for repeated approval invalidation, retention of earlier valid context, exclusion of stale decisions, and execution of the pending action exactly once. Extend the disconnected-executor test to verify that retries retain repository instructions and use updated authorization.
GitOrigin-RevId: 0bff6cc551fee1f0905082eb97ccdecaa8628867
## Why
Elevated Windows sandbox tests share machine-wide accounts. Running them in the sharded core suite can consume test deadlines while shards wait for the account lock.
## What changed
Move the Windows sandbox tests into the Windows-only `windows_sandbox` integration-test binary. Update the nextest account-sharing group to select the entire binary instead of individual test names, so tests queue before their timeouts start. Keep the existing guard for coordination with other test binaries.
GitOrigin-RevId: 613925c9398b5acc8440fa34c658680f31f65c8b
## What changed
Increment `codex.agents_md.edit` for committed `apply_patch` changes to `AGENTS.md` and `AGENTS.override.md`, matching filenames case-insensitively and tagging the counter with the normalized filename.
Count additions, deletions, updates, and distinct move destinations, including changes committed before a later patch failure.
GitOrigin-RevId: bcbfa671acb37a2a24fe7e4effc9318981a22ec7
## Why
Failed Guardian review evidence was process-local, so restarting Codex lost the context needed for later diagnostic reports.
## What changed
- Persist failed-review records in SQLite before reviewer cleanup, retaining at most 64 records globally, eight per thread, and 8 MiB of evidence. Delete persisted evidence when its reviewed thread is deleted.
- Recover and deduplicate persisted and in-memory records for the reported task tree when uploading `auto-review-failures.jsonl`.
- Bound persistence attempts to 250 ms and retain an in-memory fallback when storage is unavailable. Keep capture gated by user opt-in and non-ephemeral sessions, and export evidence only when logs are included.
## Testing
Add coverage for persistence across reopen and process restart, retention limits, cascading deletion, busy-storage fallback, and report uploads with and without logs, including SQLite log failures.
GitOrigin-RevId: ea2da1818d4a5da3da29f211042ca45e834342bc
## Why
Resolving unapproved hostnames discloses them to DNS even when the proxy ultimately rejects the request. Allowing local binding in a managed macOS sandbox also granted direct outbound access to port `53`.
## What changed
- Require an allowlist match or policy approval before resolving a hostname for address checks.
- Recheck baseline restrictions after local and remote policy approval so approval cannot bypass explicit denies or local/private address restrictions.
- Preserve DNS checks for inner HTTPS requests after an approved CONNECT, including hosts without a persisted allowlist entry.
- Remove the Seatbelt allowance for external DNS while retaining local binding and loopback proxy access.
## Testing
Add regression tests for zero DNS lookups on unapproved hosts, private-address rejection after approval, local and remote approval ordering, and DNS checks after approved CONNECT requests. Add a macOS Seatbelt child test that verifies external UDP and TCP port `53` access is denied while local binding and proxy connectivity remain available.
GitOrigin-RevId: 490790462c51928e831dd8375ac098bc3a257bac
## What changed
Update retained instruction splitting and empty assistant-context detection to match `SectionContent::Other`, and convert assistant framing markers into `SectionContent`.
## Testing
Extend the snapshot-splitting regression test to use `prepare_transcript` with both line and JSON formats, with and without source message IDs. It checks evidence preservation, deduplication, and a stable instruction prefix as assistant context and reviews change.
GitOrigin-RevId: e2205eaf9b31a2b8291dc6c0c22a899596b10206
## Why
Retained assistant context changes as the conversation grows. Keeping it separate from retained user instructions lets independent Guardian snapshots preserve a reusable instruction and transcript prefix.
## What changed
Move retained user instructions before the transcript and place assistant originals and their omission notice in a separate `RETAINED ASSISTANT CONTEXT` section afterward. Preserve evidence, delivery roles, source metadata, and deduplication across both retained sections. Clear omission delivery metadata when a split assistant notice cannot be attributed to a single section.
## Testing
Add regression coverage for prefix stability as assistant context and previous reviews change, evidence preservation, repeated preparation, and deduplication. Update approval-routing and scorer tests to check the new section order and retention of assistant text outside a smaller transcript budget.
GitOrigin-RevId: 15cda59d24bee0106f6a66c067f6a790fa91df69
## Why
Published MCP elicitation requests could lose their response waiter without notifying the event consumer that the request was no longer answerable.
## What changed
- Add `ElicitationAbandoned` with the original server name and response token for requests published through unbounded event channels.
- Emit abandonment exactly once when a waiter is dropped, response delivery fails, or the MCP runtime shuts down.
- Close the elicitation router during shutdown, reject new requests on unbounded sources, and wait for terminal deliveries before shutdown completes. Preserve bounded sources' request-only behavior and backpressure.
## Testing
Add router tests for ordered, exactly-once abandonment, closed receivers, failed response delivery, shutdown coordination, and bounded-channel backpressure. Add a core integration scenario verifying that a pending form's abandonment precedes `ShutdownComplete`.
GitOrigin-RevId: 53fe9f4a8b32f7324be180288aa492f31f4d2057
## Why
DB-only listing and pagination failures must not look like exhausted history. This hardens the DB-only listing added in https://github.com/openai/codex/pull/18502 and page refilling added in https://github.com/openai/codex/pull/7509.
## What changed
- Return JSON-RPC error `-32603` when `useStateDbOnly: true` cannot query the local state database, including requests with an empty `cwd` array.
- Track all cursors encountered while filling a page and return `-32603` for repeated cursors, including on full pages.
- Document that callers can retry these errors; a successful response with `nextCursor: null` still indicates exhaustion. Default scan-and-repair requests retain their filesystem fallback.
## Testing
Add regression tests for missing or mismatched state databases versus healthy empty history, with active and archived listings and null or empty `cwd` filters. Cover repeated cursors during page refilling and on full pages using the in-memory thread store.
GitOrigin-RevId: 09653a84fc65f47316d8bbae9e4cf3dd8ce9948a
## Why
Clients displaying a saved manual thread order need to list the remaining threads without repeating those already loaded separately.
## What changed
Add optional `excludedThreadIds` to `thread/list` and the generated protocol bindings. Apply exclusions before the result limit, refilling pages until the requested limit is reached or history is exhausted while preserving existing filters and ordering. Clients must send the same exclusions on each page.
Accept up to 100 entries, counting duplicates toward the bound. Reject invalid IDs or oversized lists with JSON-RPC error `-32602` rather than truncating them. Omitted, null, and empty lists preserve existing behavior.
## Testing
Add integration coverage for page refill across database-only and scan/repair paths, archived threads, sort directions, and project/section scopes. Cover duplicate and unknown IDs, the 100-entry boundary, invalid input, and preservation of section order.
GitOrigin-RevId: e9a884e642ae25d166aff7e275469d1d43179c6c
## What changed
- Extract `create_parser()`, `assemble_package()`, and `archive_package()` from the packaging CLI so callers can assemble a package directory, add files, and archive it separately.
- Support DotSlash artifacts with `format: "gz"` by decompressing the executable directly to its destination.
## Testing
Extend the zsh manifest override test to verify executable contents for both `tar.gz` and `gz` artifacts.
GitOrigin-RevId: 3542b795eea1f2320bef1402d575a9396be43df2
## Why
Interrupting a turn or terminating a Code Mode cell can drop a pending dynamic tool handler before it publishes its completion. Cancellation needs to settle the call in live events and persisted history without allowing a late response into model context.
## What changed
- Let dynamic tool handlers observe cancellation and publish their terminal item before dispatch finishes. Calls cancelled while awaiting a response complete with a failed item and a cancellation error.
- Keep readiness, dispatch admission, registry lock waits, hooks, and output processing cancellable so cancellation can finish even when a hook is blocked.
- Report an aborted tool lifecycle outcome when cancellation interrupts dispatch, including before handler execution.
## Testing
Add regression tests for turn interruption with pending calls or blocked hooks, cell termination with persisted failure and late-response exclusion, cancellation before dispatch admission, and exactly one completion when a response races cancellation.
GitOrigin-RevId: 0112fc74c8652c91503ed5bbfb334ae2e26930ef
## What changed
Add `windows.allow_mxc` to configuration and its JSON schema. Setting it to `false` blocks automatic MXC selection even when `features.prefer_mxc` is enabled, and rejects explicit `windows.sandbox = "mxc"` configuration with a clear error. Omitting the setting preserves existing behavior.
## Testing
Extend configuration tests to cover disabling automatic MXC selection and rejecting explicit MXC configuration when `windows.allow_mxc = false`.
GitOrigin-RevId: bf7c0648cfcb3cc1d0dc41b9faffcb8078672780
## Why
A delayed detach or cleanup from an older realtime conversation must not close its replacement or end the replacement's history segment. Realtime start parameters can also contain credentials in text and transport endpoints, so diagnostics should avoid exposing them.
## What changed
- Add `RealtimeConversationAttach` to report the connection attempt's result through a reply channel, using the sequential start path.
- Add `RealtimeConversationDetach` to close only the matching `realtime_session_id` after earlier starts finish. Detaching an older session leaves the replacement connected.
- Emit the previous conversation's close event before starting its replacement, and prevent stale fanout cleanup from closing or clearing the replacement's context.
- Limit `ConversationStartParams` debug output to output modality, initial item count, and protocol version.
## Testing
Add coverage for attachment completion after the handshake, stale detaches, failed replacement and retry, natural-close ordering, handoff history after replacement, and debug redaction for existing-call and WebRTC transports.
GitOrigin-RevId: 23aee6f70522f0b17e6aa9349dbbcc2ea985f233
## Why
User ripgrep configuration can suppress the file list used to construct Linux sandbox deny masks. For example, `--quiet` in `RIPGREP_CONFIG_PATH` can leave files matching deny globs unmasked.
## What changed
Pass `--no-config` to the ripgrep invocation that expands denied-file globs.
## Testing
Extend the multiple-denied-files regression test with a ripgrep configuration containing `--quiet`, checking that denied files remain unreadable and unwritable while allowed files remain accessible. Skip the ripgrep-specific case when no protected `rg` executable is available.
GitOrigin-RevId: 06a6e27e0edec92e79e99af5144b57f86079953f
## Why
Executor config reads omitted the startup `features.prefer_mxc` override, so clients could not see the CLI sandbox preference.
## What changed
- Include the explicit CLI `features.prefer_mxc` value in `environmentConfig/read` as a `session-flags` layer, above project config and below legacy managed file and MDM config.
- Retain only this preference from startup overrides.
- Expose `windows_mxc_allowed_by_config` to share MXC eligibility checks after callers resolve the active permission profile.
## Testing
Add CLI and remote executor coverage for preference propagation and filtering, plus a unit test verifying that both legacy managed config sources retain precedence.
GitOrigin-RevId: 5ac6f5257f1e807c2f197dcf5dcb2385cedca0ea
## Why
Attachment stores need to distinguish uploads from ephemeral threads, which intentionally skip durable persistence.
## What changed
Add `ephemeral` to `UploadRequest` and propagate the turn configuration through image preparation for messages, tool outputs, and history replay. Include the flag in debug output while keeping attachment bytes redacted.
## Testing
Extend the Guardian context-budget test to assert that a persistent Guardian uploads exactly one image with `ephemeral: false`. Update the attachment debug-output assertion to include the new field.
GitOrigin-RevId: 42814c514a571ed6798e4dcf79a22028ee4efc28
## Why
Agent tree shutdown previously returned a generic error without identifying which operation or thread failed, making cleanup failures difficult to diagnose.
## What changed
- Add `AgentTreeShutdown::wait_detailed()` and public report types while preserving the existing `wait()` result and error message.
- Record operation, optional thread ID, and either an abandoned teardown guard or a failed phase with a payload-free error category across session cleanup, child spawn cleanup, and resident eviction.
- Give each tree a correlation ID, log each failure, and retain up to 64 failures with a count of additional failures omitted. Record failures before releasing tree membership so all completed waiters observe the same report.
## Testing
Add unit coverage for aborted and completed teardown, cloned guard context, concurrent and repeated waiters, omitted failure counts, and report formatting without raw error payloads. Extend integration coverage for successful tree shutdown and persistence writer failures, including compatibility with `wait()`.
GitOrigin-RevId: 68784af28b63e875b00a55d78729f0cc5b01ac15
## Why
Windows temp grants could fall back to host `TEMP`/`TMP` values and bypass read-only or denied subpaths. Sandbox permissions must match the environment passed to the child process.
## What changed
- Resolve `:tmpdir` from absolute `TEMP`/`TMP` paths in the completed workload environment, preserving access modes and missing-path rules without falling back to host values.
- Deduplicate Windows environment keys case-insensitively in a deterministic order so permission resolution and the child environment select the same value.
- Use the resolved temp policy for elevated sandbox overrides across core execution, exec-server, and direct spawning.
- Launch direct-spawn sandbox wrappers with the supplied Codex executable, materializing an inner helper only when it is that executable.
## Testing
Add Windows regression coverage for temp-only writes, read-only and denied carveouts, mixed-case and duplicate environment keys, unavailable temp paths, and empty or missing write-root overrides. Exercise core execution and direct spawning, and extend exec-server RPC coverage to the elevated backend with temp values set through the environment policy.
GitOrigin-RevId: 16b8bd4702cc434fd743a08c75a3e4515780bff3
## Why
On Windows 10, strict native opens can reject the DOS drive alias itself as a reparse point, preventing no-follow filesystem operations on ordinary drive-letter paths.
## What changed
Retry rejected drive-letter opens relative to a verified local volume root. Require the root to resolve to a physical disk volume directory without reparse attributes, and retain `OBJ_DONT_REPARSE` for paths beneath it so junctions remain blocked.
## Testing
Add Windows tests for file creation and reading through the volume fallback, opening the drive root, and rejecting junction traversal and creation. Validate accepted volume-root names and verify that named pipes are rejected without establishing a client connection.
GitOrigin-RevId: 51ffde4f77d2af45d18dfc4cb026d73a0e69b061
## Why
Live preferences can be newer than the last successful configuration load. Starting a new thread after a reload failure could overwrite those preferences with stale settings.
## What changed
Carry local settings alongside the new-session configuration, retaining the live settings when reloading fails and applying the staged settings when the new thread starts. During resume and agent selection, replace staged local settings only when the directory-trust check actually reloads configuration.
## Testing
Add a regression test that changes a live rendering preference, writes invalid `config.toml`, and verifies that loading a new thread's configuration preserves the live local settings.
GitOrigin-RevId: 4ac3c70de6d627e1609cc0a5d4ba5df5a61a8b20
## Why
MCP contributors need the complete executor selection to distinguish an unavailable primary executor from a ready secondary. Ready capability roots alone do not preserve pending or failed selections.
## What changed
Add `with_selected_environments` and `selected_environments` to `McpServerContributionContext`, and pass the captured selections during thread MCP resolution and model-step plugin selection. Preserve priority order and pending or failed entries. Use `None` for threadless discovery and `Some(&[])` for an explicitly empty selection.
## Testing
Add regression coverage for executor ordering with pending and failed selections, environment context in model-step plugin selection, and the distinction between absent and explicitly empty selections.
GitOrigin-RevId: 2c1222fae72c7e2c75b2f40abfad3b2048cf9316
## Why
A stalled rendezvous WebSocket upgrade can prevent reconnects, while short-lived connections reset reconnect backoff too early. Blocked relay writes also prevent received pongs from clearing their heartbeat deadline.
## What changed
- Bound rendezvous WebSocket connection attempts with `DEFAULT_REMOTE_EXEC_SERVER_CONNECT_TIMEOUT`.
- Retain exponential reconnect backoff across short-lived connections, resetting it only after a connection lasts at least 120 seconds.
- Process pongs during blocked data writes while preserving the in-flight send and its independent write timeout. Prefer queued pongs over an expired heartbeat deadline.
- Abort the relay writer when its owning connection task is dropped.
## Testing
Add coverage for pongs arriving during blocked writes, missing and queued pongs, independent write timeouts, and writer cancellation. Extend reconnect tests to cover stalled WebSocket upgrades without re-registration and backoff reset after a stable session.
GitOrigin-RevId: 0efa350c2b4ada9b89e23df8909063fbb69f33dc
## What changed
- Use `p` to pin or unpin the selected task, with a configurable `agents.toggle_pin` binding.
- Display pinned tasks first in a `Pinned` group, preserving shared section order and applying search and status filters.
- Load pins from the shared thread section, including tasks outside the recent-task window, and refresh after pin changes. Disable pinning when the server does not support shared sections.
## Testing
Add coverage for shared pin/unpin state, paginated pin discovery and refreshing pins on reopen, shortcut dispatch and duplicate-action suppression, and pinned-group and custom-help snapshots.
GitOrigin-RevId: d1a2cab6642d059c3c8df8480b5c59a10c493936
## What changed
Move full rollout history reading and parsing into one blocking worker for both plain `.jsonl` and compressed `.jsonl.zst` files. Use the shared cancellation-aware line iterator so canceled loads stop before processing another record, while preserving rollout items, thread IDs, and parse-error counts.
## Testing
Add regression tests for cancellation between records and equivalent history-loading results across plain and compressed files, including Unicode, CRLF line endings, malformed records, empty files, and invalid UTF-8.
GitOrigin-RevId: 65e1bd7ebcdbbd0ab5f560e73b2c7f074f627f8f
## Why
Capability discovery needs the roots captured with each environment snapshot. Threads sharing an executor can select different roots, and changing environment order must preserve executor skill aliases.
## What changed
- Attach the receiving thread's capability roots when constructing `TurnEnvironmentSelection` at startup and settings updates, including roots loaded from saved history.
- Resolve capability roots from environment snapshots while preserving their original order. Retain startup roots so deselecting and reselecting an environment restores its capabilities.
- Match inherited configuration by environment and workspace so differences in capability root metadata do not interrupt configuration propagation.
## Testing
Add regression coverage for root ordering across environment states and configuration changes, independent root selections on a shared executor, reselection with startup or saved roots, active turn updates, and pending configuration failures reaching child and grandchild threads.
GitOrigin-RevId: 4f2e4bb414d27195a6752406117a6050718a1198
## What changed
Remove `workspace_roots`, `current_date`, `timezone`, `network`, `personality`, and `multi_agent_mode` from `TurnContextItem` and stop recording them in rollouts. Update the precomputed protocol schema accordingly.
Make `summary` optional when reading turn context and write `"none"` as a compatibility placeholder for older readers, rather than persisting the active reasoning-summary setting.
## Testing
Update protocol tests to cover omitted `summary` fields and compatibility-placeholder serialization. Extend compaction tests to verify that model requests retain the updated reasoning-summary setting after compaction while the rollout checkpoint records the placeholder.
GitOrigin-RevId: d49eabaa1b340be1d79f7f09115281a307ea8a64
## Why
A malformed plugin manifest still marks a capability root as plugin-owned. Discovery or metadata failures must not be treated as evidence that a root is standalone.
## What changed
- Add `ExecutorPluginProvider::root_ownership` and export `PluginRootOwnership` to distinguish plugin-owned roots from standalone roots before capability parsing.
- Use discovery results when conclusive; otherwise probe manifest files at the selected root and its ancestors using the supplied filesystem sandbox. Nested plugin manifests do not establish ownership of their parent root.
- Share manifest lookup with plugin resolution and pipeline up to 256 metadata probes while preserving ancestor and manifest priority, including error ordering.
## Testing
Add tests for malformed ancestor manifests, discovery failures, ancestor versus nested ownership, concurrent probe ordering, and sandboxed metadata checks without reading manifest contents.
GitOrigin-RevId: 3512452cf1df22f52c2a2b422f96c760d98c24ac
## Why
Rendezvous connection warnings report only a generic WebSocket error, while debug logs include raw error text. Structured diagnostics make failures easier to investigate without logging potentially sensitive error payloads.
## What changed
- Generate a request ID for each connection attempt, send it as `x-request-id`, and include it in the connection span and connection, disconnection, and failure logs alongside the attempt count.
- Replace raw error logging with typed error categories, I/O error kinds, HTTP status codes, and allowlisted values from `x-codex-rendezvous-rejection-reason`.
- Ignore unknown rejection reasons and response bodies.
## Testing
Add tests for rejection-header allowlisting, typed I/O failures, and a rejected WebSocket handshake that verifies the request ID header and preserves the HTTP status and known rejection reason.
GitOrigin-RevId: a8274fec965bcf5b8453b047c0bb79396cdf6ba4
## Why
Skill selection and disabled-path matching need to recognize equivalent Windows paths across case and separator differences while preserving literal spaces, `%`, and `#` in native filenames.
## What changed
- Carry `PathUri` through skill metadata, discovery mappings, filesystem lookups, disabled-path sets, and invocation analytics.
- Match linked skill mentions and TUI selections by parsed path identity.
- Use `LegacyAppPathString` for app-server skill paths and regenerate schemas and SDK types, preserving native path strings on the wire.
- Preserve native catalog display paths and ordering. Keep host filesystem probes and configuration writes restricted to host-compatible paths.
## Testing
Add regression tests for Windows path identity and disabled-skill matching, literal filename characters, catalog resource reads, native path ordering, and foreign-path analytics normalization.
GitOrigin-RevId: c212916dc9fef0e7616542726e107f0d6a313267
## Why
Changing the incremental tools setting on resume should not move tool declarations and base instructions within an existing context window.
## What changed
- Determine the current window's tool declaration mode from its history, and apply the incremental tools setting when building a new window after compaction or a context reset.
- Use that mode consistently for sampling, remote compaction, startup prewarm, prompt debugging, and Guardian input budgeting.
- Preserve tool declarations alongside their comparison baseline in full-history agent forks, including compacted histories; remove them together when rebuilding context.
## Testing
Add request snapshots covering legacy resume, migration after remote compaction or a context reset, disabling incremental tools, and tool updates after restart. Extend agent fork and WebSocket startup prewarm tests to cover retained declarations and incremental tools.
GitOrigin-RevId: 7c46849a1788027a8435082e4d1f7e7f48d2700c
## Why
The hooks browser rendered detail URLs as plain text. Long URLs in hook commands can wrap or be truncated, so their visible text may omit part of the destination.
## What changed
Render web URLs in hook details as terminal hyperlinks, preserving the complete destination across wrapped lines and truncated text. Keep truncation ellipses outside the links.
## Testing
Add a regression test and snapshot for a wrapped, truncated hook command URL, checking that linked cells retain the complete destination and the ellipsis remains unlinked.
GitOrigin-RevId: 488562266bd5ef880c03bf313bc4cfa7d3104c7b
## What changed
Render web URLs in selection labels and descriptions as terminal hyperlinks, preserving their complete destinations when text wraps or is truncated. Carry hyperlink ranges through two-column layouts and keep truncation ellipses outside links.
## Testing
Add regression assertions and a snapshot covering wrapped and single-line rows, prefixed labels, descriptions, and wide Unicode characters. Verify that visible URL fragments retain complete destinations and ellipses are not linked.
GitOrigin-RevId: 9d50b3ced79cbd29200e48a676445ec169d60758
## What changed
Render web URLs in pending steers, rejected steers, and queued follow-up messages as terminal hyperlinks. Preserve the complete destination when the visible URL is clipped to the preview width.
Add `HyperlinkRows` to render already-wrapped rows without changing their spacing or row count, clipping text and hyperlink ranges to the viewport.
## Testing
Add regression coverage for complete URL destinations across all three preview sections, plus snapshots for oversized URLs and clipping overflow text and the edit hint in a narrow preview.
GitOrigin-RevId: 959df27bba381b1b3895f5a86cc2ecb1419806b1
## What changed
For managed app-server daemons using Unix sockets, raise the soft
`RLIMIT_NOFILE` limit to 4096 at startup, capped by the inherited hard limit.
Preserve existing higher soft limits and log a warning if the adjustment fails.
GitOrigin-RevId: 2ef27370e55cd86a7a62cbc3d47041933b89ac21
## Why
Submission diagnostics need approval and turn metadata without logging user input, tool responses, commands, paths, or instruction payloads.
## What changed
- Log thread and submission IDs, operation kind, and parent/root turn IDs as explicit fields.
- Give `Op` and `ThreadSettingsOverrides` selective `Debug` output that retains identifiers, approval decisions, and policy categories while omitting payloads.
- Preserve Guardian review identifiers and status when logging approval of a denied-action retry.
## Testing
Add an app-server integration test that verifies command approval, Guardian review, and turn policy metadata reach SQLite-backed diagnostic logs with `RUST_LOG=off`.
GitOrigin-RevId: 308acb7b70e4849cf31514b11e4d9b46eaf6a09b
## What changed
Introduce `TranscriptRecord` and `PreparedTranscript` to retain attributed transcript text through preparation and composition. Cache rendered content, byte counts, and token estimates, refreshing them when text or framing changes.
Keep JSON records structured during budget recovery so truncation replaces only `text`, preserving metadata, field order, and framing without reparsing serialized JSON. Preserve whole-entry truncation for line transcripts and update synchronous and asynchronous consumers to use the preparation API.
## Testing
Expand coverage for cached estimates and delivery with escaped text, Unicode, and large payloads; metadata and framing preservation during recovery; and stable asynchronous history prefixes in both line and JSON formats.
GitOrigin-RevId: 8b3b5231ca4a6ee47d17dcc788ea68c56dd1a9bc
## Why
Transcript content can contain forged role headers, transcript boundaries, or claims of user approval. Guardian needs to distinguish that content from host-assigned authorship metadata.
## What changed
- Add `features.guardianv2.transcript_mode` with `line` (the default) and `json` options for synchronous review and asynchronous scoring.
- Render JSON transcript entries with host-assigned metadata and escaped `text`, and prepend matching provenance instructions to reviewer and classifier prompts.
- Preserve JSON metadata when budget recovery shortens historical text, and keep provenance instructions outside the configured classifier prompt limit.
## Testing
Add coverage for forged roles and approvals remaining within their original entries, JSON metadata surviving budget recovery, and provenance instructions surviving prompt limits. Extend review and scoring integration tests to verify JSON evidence and matching instructions.
GitOrigin-RevId: 81a3580390d3c4d1a664e554976cda5f1adc9a2c
## What changed
Add `model` and `reasoningEffort` to `subAgentActivity` items for multi-agent v2 spawns. Capture startup settings before the child begins its turn and resolve the reported effort against model metadata, including model defaults, while preserving the child's configured effort.
Carry these fields through live notifications, persisted activity, thread history, and legacy rollout migration. Update the JSON schemas and generated TypeScript and Python types. Older records and other activity kinds retain null values.
## Testing
Add coverage for resolved spawn settings matching the child's request across legacy and paginated history, preserving configured effort, forwarding metadata through events and history, and reading and migrating older records without the new fields.
GitOrigin-RevId: a9e4241ae21bb8db1ead293f78ffba8257cca0ae
## Why
Instant Connect can return a call ID before ICE activates the call, causing sideband attachment to briefly fail with HTTP `404` while the client connects media.
## What changed
Retry `404` responses from `connect_existing_call_sideband` up to three times, waiting 100, 300, and 800 milliseconds. Return the error once this activation retry budget is exhausted, and preserve the existing handling of other errors.
## Testing
Add WebSocket coverage for successful attachment after three `404` responses, failure after four `404` responses, and no retry on HTTP `410`. Verify that successful attachment does not overwrite the prepared session configuration.
GitOrigin-RevId: 5d18ff7eeeb9abd56388808828382f7350c7ae57
## What changed
Render help text in Windows sandbox setup and fallback prompts with `HyperlinkText` so each wrapped URL fragment links to the complete destination. Strip OSC 8 sequences when rendering popup snapshots to keep assertions focused on visible text.
## Testing
Add a regression test covering both prompts at 40 columns, asserting that every linked cell retains the complete destination and the visible link text remains intact. Include a snapshot of the wrapped setup prompt.
GitOrigin-RevId: 98bd60f04ab3ec8d6552a0b74b9637cce26169d5
## What changed
Render user verification titles and request details with `HyperlinkText` so URLs carry terminal hyperlinks, including in the waiting-for-verification view.
## Testing
Extend the narrow-prompt regression test to verify that wrapped URLs retain their full hyperlink targets before and during verification. Strip OSC 8 annotations when comparing visible text in snapshots.
GitOrigin-RevId: 9b2fba963c028eaa2b177220b0487364b44d04bb
## Why
The ChatGPT usage URL in the status card loses its terminal hyperlink when it wraps across lines in a narrow terminal.
## What changed
Attach the usage URL destination to each underlined span so every wrapped fragment remains clickable.
## Testing
Extend status hyperlink coverage at widths of 24, 42, and 120 columns to verify that linked fragments reconstruct the full URL and all point to the same destination.
GitOrigin-RevId: 516421380763f48da8af63b4d374e2b352722ddb
## What changed
Render URLs in TUI banner titles and descriptions as terminal hyperlinks, preserving the full destination when a URL wraps across lines.
## Testing
Add a regression test that checks hyperlink destinations for a wrapped URL and snapshots the visible banner layout.
GitOrigin-RevId: 1b1957570c1c0940a60f5a202648b0eeed5b95e1
## What changed
Render web URLs in warning details as terminal hyperlinks, preserving the full destination when a URL wraps across lines or the viewer scrolls.
## Testing
Add a regression test for hyperlink destinations after wrapping and scrolling, plus a snapshot of a warning containing a wrapped URL.
GitOrigin-RevId: 6500e6129a95b2dea8e8f53296ca056e63196a57
## What changed
Render web URLs in TUI MCP elicitation prompts as terminal hyperlinks. Preserve the full destination when a URL wraps across lines, while retaining the existing styling for answered and unanswered prompts.
## Testing
Add a regression test that verifies each linked cell of a wrapped URL targets the complete URL, including its query string, and a snapshot of the rendered form.
GitOrigin-RevId: 74baabbee6b72b695e1534d694296a3352f7e47d
## What changed
Render web URLs in `request_user_input` question text as terminal hyperlinks. Preserve the complete destination when a URL wraps across rows, along with explicit newlines and blank lines in the question.
## Testing
Add a regression test that checks each linked fragment retains the complete URL, including its query string, and snapshots the wrapped question layout.
GitOrigin-RevId: 473c8a8a00797c0b353a9cdb762dea2c718d9190
Use `TurnEnvironmentRequests` and the executor environment's `request()` in the MCP turn metadata test to match `ThreadSettingsOverrides`. Allow additional fields when matching `TurnInputSubmission::Started` in the pending input test.
GitOrigin-RevId: 6f7f7c60511d999274079f715ba2a68163e69caf
## Why
WebSocket rate-limit and overload errors ignored `Retry-After` advice and ended turns even when the server supplied a retry delay.
## What changed
Extract retry advice from nested `error.headers`, falling back to top-level `headers` when nested advice is missing or invalid. Use the shared HTTP header validation and retry-delay parser, and preserve the delay when mapping WebSocket errors.
## Testing
Add coverage for nested-header precedence, malformed headers, HTTP header validation, and recovery after an advised rate limit. Verify that overloads retry only while advice is present, without falling back to HTTP, and that headerless rate limits, usage limits, and `flex_unavailable` errors remain terminal.
GitOrigin-RevId: 61add0c36197e10402d6d3c325332aac72a5a521
## What changed
Render command, permission, patch, and MCP elicitation approval headers with `HyperlinkText`, which annotates web URLs and preserves their full destinations across wrapping and clipping.
## Testing
Add a regression test covering wrapped URL destinations in all four header types, plus a snapshot of the wrapped command approval header.
GitOrigin-RevId: 7f6b79484c9297cd03514da2d6805b0d239fee63
## What changed
Replace generic `Hook 1` labels with trimmed `status_message` titles, falling back to `Unnamed hook` when the message is missing or blank. Show aligned, dimmed row numbers alongside the titles and retain trust-status suffixes.
Render rows with `Paragraph` to preserve full-row selection styling and per-span dimming, including titles containing wide characters and emoji.
## Testing
Add snapshot and buffer assertions for title trimming, blank and missing messages, wide characters, selection styling, and dimmed indices. Update snapshots for long-title truncation and scrolling across two-digit row numbers.
GitOrigin-RevId: a9b20ea91e7252b6399d1c8a9fa849186f16a651
## Why
An interrupt or turn replacement can invalidate a pending-work wakeup while its turn context is being constructed. Task startup could then recreate a turn whose reservation was no longer active.
## What changed
- Recheck that the wakeup still owns the active turn reservation immediately before calling `start_task`, and return if it does not.
- Allow the remote-control re-enrollment test up to 45 seconds for the connection following reconnect backoff.
## Testing
Add a regression test that pauses wakeup context construction, processes an interrupt, and then resumes construction. It verifies that no additional turn starts and only the initial model request is sent.
GitOrigin-RevId: c857fdd9f0fac3790d35a95a1f21a6d41977bb29
## What changed
Stop setting `BAZEL_HOST_JVM_ARG=-Xint` in the Windows release workflow and remove support for forwarding `BAZEL_HOST_JVM_ARG` as `--host_jvm_args` in `.github/scripts/run-bazel-ci.sh`.
GitOrigin-RevId: 49ff5a56dc00b14c529ebefab917cb1d68216431
## What changed
Require `--prerelease false` before publishing the R2 `codex/install.sh` and `codex/install.ps1` aliases when updating the `latest` channel. This keeps prereleases marked latest from overwriting the stable installer aliases.
GitOrigin-RevId: 2ee7a8aee03f5242fb3b85af377655017e0d23b8
## What changed
Add `TurnEnvironmentRequests` to carry environment requests together with their fallback working directory. Update thread settings overrides and active turn settings to accept requests, constructing `TurnEnvironmentSelection` values in the receiving thread before validation and runtime use.
Adapt app-server callers, reviewer settings, and existing tests to supply requests or explicitly convert runtime selections back into requests.
GitOrigin-RevId: 8028f804bebe3fde553f57bb450f6dca3970cc4a
## What changed
Add the turn's `root_turn_id` to `_codex_apps` request metadata for host-owned Apps MCP calls. Remove any tool-supplied value before populating it from turn metadata, and omit the field for user-configured or extension-owned Apps servers.
## Testing
Extend unit coverage to verify that host-owned Apps calls replace an untrusted `root_turn_id` and user-configured Apps calls omit it. Update integration assertions for default and explicitly supplied root turn IDs, including approval flows, and verify that extension-owned calls omit the field.
GitOrigin-RevId: 754a642c2fff36a866b8cffa9fb3e161f232de08
## Why
Idle thread unloading stopped waiting after ten seconds, leaving the thread loaded when resource cleanup took longer.
## What changed
Keep awaiting the same shutdown future after the ten-second deadline, emitting `codex.app_server.thread_shutdown_slow` as a warning. Once shutdown completes, remove the thread and send `thread/closed` without requiring another unload request.
## Testing
Add a regression test that blocks writer-lock cleanup past the warning deadline, verifies the thread remains loaded while cleanup is blocked, then releases the lock and checks for `thread/closed` and an empty loaded-thread list.
GitOrigin-RevId: 18c411f86fd69e710e472a4e3572d75f18682147
## Why
Queue-only agent mail can wake a sleeping session without starting a new task. The wake turn needs to retain the previous turn's attribution so delegated work reports completion to the initiating agent, including after a reload.
## What changed
Capture the previous turn's attribution while reserving the pending-work turn. Reuse its trigger, parent and root turn IDs, and initiating agent path for queue-only wakes. Mail that explicitly starts a new task continues to supply its own attribution.
## Testing
Extend regression coverage for live and reloaded sleep wakes, delegated and unknown attribution, settings changes while asleep, and subsequent task-triggering mail. Verify that a reloaded sleeping worker routes completion to the initiating turn.
GitOrigin-RevId: 28e38474028bdbf35a0538c1202165f056bb3dc3
## Why
Clients starting delegated work need to attribute descendant turns to the original turn and retain that attribution through completion and history reads.
## What changed
- Accept optional `parentTurnId` and `rootTurnId` in `turn/start`, and expose `rootTurnId` on returned turns and lifecycle notifications.
- Default new turns to their own root when none is supplied. Preserve the active turn's root when steering, ignoring incoming lineage fields.
- Carry root IDs through completion, interruption, recovery, and fork boundaries, and persist them for paginated history reads. Leave unknown roots null in older history.
- Update protocol schemas and generated TypeScript and Python bindings.
## Testing
Extend coverage for default and explicit roots, steering without changing lineage, interrupted and recovered turns, history reads after restart in both history modes, nested fork pagination, and compatibility with older database writers.
GitOrigin-RevId: f1a570a12bd11742929fd2e8b017e5d35aa07dcb
## Why
Legacy terminals report key auto-repeat as new presses, which can trigger repeated image pastes when presses accumulate during a slow paste.
## What changed
Suppress repeated `Ctrl+V` and `Alt+V` image paste presses within a sliding 250 ms window, refreshed after each suppressed press and after a paste completes. Clear suppression on other ordinary key presses or key release events so a fresh paste can proceed immediately.
## Testing
Add regression coverage for repeated presses, window expiry, and resetting suppression on another key press or a key release. Update the shortcut remapping test to release the key between image pastes.
GitOrigin-RevId: 45abc056e5bda47d1c9704702e369e63dcce29db
## Why
Deny-read glob expansion runs before sandbox confinement. Resolving `rg` directly from `PATH` could execute a writable workspace binary at that stage.
## What changed
Use the existing protected executable lookup to select a canonical `rg` path under the filesystem policy. Fall back to the native glob walker when no suitable executable is found, preserving masks for matching denied paths.
## Testing
Extend denied-file integration tests to verify that a writable workspace `rg` never runs, a protected `rg` is used when available, and denied files remain blocked with the native fallback.
GitOrigin-RevId: f06674f3535c8a72a4656871762e45fa13c732f2
## Why
Recovering an interrupted turn replaced its original trigger with `retry` and restored only its root lineage from model context. Turns suspended before that context was written could lose their attribution entirely.
## What changed
- Persist regular-turn attribution in `TurnStartedEvent` and compaction resume metadata, including the trigger, parent and root turn IDs, and initiating agent path.
- Restore matching attribution during recovery, keep unknown triggers absent, and retain the model-context root fallback for older records.
- Reconstruct attribution from surviving turns across rollback and late completion or abort events, and clear inherited attribution when spawning a forked agent.
## Testing
Add coverage for repeated cold recovery, suspension before context persistence, legacy rollouts, fresh attribution on subsequent turns, compaction checkpoints, rollback, and late terminal events.
GitOrigin-RevId: 85b5763e8fbd48a1ea2c07cfda8196e63c2cd33a
## Why
A low-risk score for a later action could release an earlier pending Guardian review when the thread's score lag reached zero, bypassing that action's synchronous review result.
## What changed
Track the accepted score's source action and allow it to release a pending review only when it comes from that action or an earlier one. Keep cached-score approval available before synchronous review starts, but prevent the initial computer-use allowance from releasing an already pending review.
## Testing
Add an app-server regression test with two pending reviews: a later low-risk score approves its own action while the earlier action remains pending and honors its synchronous denial.
GitOrigin-RevId: ed8b9c4793b2538f634edfc5699797a6983358cc
## Why
A synchronous Guardian review could keep an action waiting even after an asynchronous score supplied valid low-risk evidence for approval.
## What changed
- In adaptive mode, race the synchronous review against score updates that satisfy the existing cached-approval checks, unless a fresh review is required.
- When asynchronous approval wins, cancel and drain the pending review, then revalidate the action and history lifetime and enforce cancellation and timeout limits before approving.
- Emit an approved review completion without a synchronous assessment or risk level, and use the cached-approval path for the final decision.
## Testing
Add an app-server regression case that holds the synchronous review pending, releases a low-risk score, and verifies approval completes without a risk level. Sequence existing scenarios to finish synchronous reviews before releasing classification results when they test synchronous evidence.
GitOrigin-RevId: 04f5ad6b960b819b565fccb1b85c8039ccbd0479
## What changed
Render web URLs in TUI asynchronous question titles as terminal hyperlinks, preserving the full destination when a URL wraps across lines or is partially clipped. Exclude trailing question punctuation such as `)?` from detected URLs while preserving balanced parentheses and query strings.
## Testing
Add a rendering regression test and snapshot for a wrapped URL, checking complete hyperlink destinations at full and reduced heights. Extend URL detection tests for trailing question punctuation and balanced parentheses in query strings.
GitOrigin-RevId: 6c9a807466d7b7e3a23bc6e86aae8410ae378161
## Why
Serial connection opens let a stalled handshake delay healthy sockets. Waiting until the idle pool is empty to refill also leaves classification bursts using HTTP fallback.
## What changed
- Open up to four WebSockets concurrently and start replenishing when the idle pool falls to half capacity. Preserve successful in-flight opens when another open fails or times out.
- Make explicit prewarming wait for an existing refill before checking readiness.
- Add `ResponsesWebsocketClient::connect_with_connector` and reuse one connector per sampler, initializing TLS configuration on a blocking task while retaining per-connection authentication and destination policy checks.
- Record connection lease durations for admission, setup, and total time, tagged by transport.
## Testing
Add regression tests for a stalled handshake alongside a healthy socket and replenishment before the last idle socket is leased. Update cooldown, authentication, and transport retry tests to account for concurrent handshake completion.
GitOrigin-RevId: f4a8258977c1f2a58e00c6badc7b599280ef22ad
## Why
Spawn failures can share an error kind and message despite different causes, such as execution and residency capacity limits. Telemetry needs enough detail to distinguish these failures without using error messages or correlation IDs as metric labels.
## What changed
- Add `AgentErrorContext` annotations for capacity limits, registry rejections, runtime availability, and spawn stages. Preserve the first annotation so outer stages retain the more precise failure origin.
- Add bounded `detail` and `error_kind` labels to spawn failure metrics, using `unknown` when no context is available.
- Emit spawn failure trace events with these classifications and the call and turn IDs for both multi-agent versions.
## Testing
Add tests for distinct capacity and registry failure contexts, preservation of manager, fork, and shutdown errors, and metric aggregation across different error messages and correlation IDs. Verify that annotations preserve existing error kinds and user-visible messages.
GitOrigin-RevId: 5bbe3d32f6ce408622f38e559fddeab05b8ccb65
## Why
File replay can accommodate shell state larger than the 512 KiB budget used for environment replay.
## What changed
Allow up to 4 MiB of shell state and 8 MiB of capture output for file replay. Keep captured environments capped at 512 KiB and preserve the 512 KiB combined state-and-environment limit for environment replay. Report distinct failures for oversized capture output, state, and environments.
## Testing
Add replay-specific size-limit tests and enlarge the Bash integration-test snapshot to exercise file replay beyond the environment replay budget.
GitOrigin-RevId: 0210848eb398d75426cb8b4b3bfaa0bce25264b8
## What changed
Add `codex.shell_snapshot.command` and `codex.shell_snapshot.wait_ms` metrics for eligible command preparations in the unified exec runtime and exec server. Tag observations with snapshot version, availability state, and whether replay was selected (`used`) or normal shell startup was used (`fallback`). Exclude background prewarming from command observations; `used` measures replay selection, not successful restoration or command completion.
## Testing
Extend snapshot retry tests to verify command counts and wait observations across fallback and recovery, excluding prewarm captures. Extend credential-broker approval tests to verify one `protected` snapshot observation for login-shell commands.
GitOrigin-RevId: d3d9f370b6bbba6dfc930a44044ce09373841799
Refresh the ranked tool catalog and partial-answer fork snapshots to reflect instructions requiring `fork_turns: "none"` when overriding the model or reasoning effort. Update the affected collaboration tool and message hashes.
GitOrigin-RevId: 5c3cbdd734f57eaefee0b0412e555e3882b1472e
## What changed
Increment `codex.guardian.denial_limit_reached` when automatic approval review reaches a turn's denial limit, immediately before interrupting the turn. Record the counter once per turn, matching the denial warning's existing behavior.
GitOrigin-RevId: ec8eeeff6a681a261572496e59cf694e87e813ce
## What changed
Carry `multi_agent_version` from the turn context through resolved configuration facts into turn analytics events.
## Testing
Extend the turn event serialization test to assert that `MultiAgentVersion::V2` is emitted as `"v2"` in `multi_agent_version`.
GitOrigin-RevId: f3e8c98588926d41a18c3db9aa229677e68cf5c1
## What changed
Record elapsed time for completed `wait_agent` waits in `codex.multi_agent.wait.duration_ms`, with an `outcome` tag of `mailbox`, `steered`, or `timed_out`. Exclude dropped waits because they have no observed outcome.
GitOrigin-RevId: 6378b98bfadab69d47aa2e9c93fa9d720f9cd0ef
## What changed
Increment `codex.multi_agent.result_delivery` when sending a terminal child result to its parent, with `outcome=queued` for queue acceptance and `outcome=failed` for delivery errors.
GitOrigin-RevId: 7571f66c2c2d2baea1a54dce3741f6393e809b66
## What changed
Add `codex.guardian.decision.duration_ms` around the complete approval decision operation, including fast decisions, preparation, and cancellation alongside model review time.
GitOrigin-RevId: e5a8d5a3b9a0ff81e1b866be87b8f3a439ae6a1d
## What changed
- Limit multi-agent V2 `fork_turns` guidance to `all` and `none`. Accept legacy positive integer strings as full-history forks instead of truncating parent history.
- Remove partial-history fork handling and telemetry, and direct model override usage to `fork_turns: "none"`.
- Strip inherited `multi_agent.role_instructions` and `multi_agent.usage_hint` content by kind, including persisted hints whose wording predates the current bundled instructions.
## Testing
Update regression coverage for legacy `"1"` and `"3"` values inheriting full history, invalid and zero values being rejected, and stale parent hints being removed from compacted history with both marked and unmarked instructions.
GitOrigin-RevId: 8f6017dc66ad8deefd7745399ef76e1bb1435bb2
## Why
Messages with the `partial_answer` phase contain answer text without declaring a terminal answer. They should remain searchable and speakable without being treated as final messages.
## What changed
- Preserve explicit `partial_answer` phases in streamed and completed realtime handoffs, bypassing legacy channel-prefix parsing and routing them to the `speakable` channel.
- Treat partial answers as nonterminal in V1 handoffs and omit the final-message prefix.
- Include partial answers in thread occurrence searches and normalize them to the final conversation channel in rollout traces.
## Testing
Extend coverage for realtime phase routing, streamed and completed handoffs, partial-answer search results, and rollout normalization. Verify that turn summaries still exclude nonterminal messages.
GitOrigin-RevId: aa183da783f6e7e0b78ddd51073cba533297e121
## Why
A native launcher can pass PowerShell 7 module paths to Windows PowerShell, preventing `Get-FileHash` from loading and blocking archive checksum verification.
## What changed
Update `scripts/install/install.ps1` to compute SHA-256 directly with .NET APIs after resolving the archive path. Dispose the file stream and hash provider, and retain the existing checksum mismatch error.
GitOrigin-RevId: 86e6232bd83c888811fc3b76fcad0aaf046f4bf8
## Why
A stopped provisioning service is treated as unavailable by the connection path, preventing registered Core setup from provisioning the sandbox.
## What changed
Start a stopped Windows sandbox service before provisioning during explicit registered Core setup. Request service-start permission through the Windows Service Control Manager and tolerate the service already running if another caller starts it concurrently. Preserve existing unavailable-service handling when the service is missing or marked for deletion.
GitOrigin-RevId: fab87c10dfabd4324f631077262f7e0dccc170f6
## Why
Fast mode previously gated both Fast and Ultra Fast, preventing policies from allowing one while disabling the other.
## What changed
- Add the default-enabled `features.ultrafast_mode` flag and enforce it independently of `features.fast_mode` in service-tier selection, requests, and agent prewarming.
- Filter TUI service-tier commands and selections by the corresponding policy and model catalog support.
- Report `supportsIndependentSpeedModes: true` from `configRequirements/read` and update the protocol schemas and generated bindings. Retain the shared Fast gate when connecting to older servers that omit this capability.
- Preserve legacy cloud speed denials by translating `rbac-fast-mode` fragments with `fast_mode = false` into a denial of both modes, while retaining higher-priority enterprise overrides.
## Testing
Add coverage for all four Fast/Ultra Fast policy combinations in requirements responses and request routing, agent prewarm inheritance, TUI command visibility and saved selections, and legacy cloud denial normalization and override precedence.
GitOrigin-RevId: 147e08524c4b228ea9d46b25a9f8aa64c359e169
## Why
Partial answers contain answer fragments while a turn is still in progress. Treating them as final answers defers mailbox delivery and can count empty fragments as empty final responses; filtering them from forked histories and guardian transcripts loses answer content.
## What changed
- Allow mailbox preemption after `partial_answer` messages and keep mailbox delivery open.
- Preserve partial answers in forked agent histories and include them as protected assistant entries in guardian transcripts.
- Exclude empty partial answers from empty-final-response accounting for goals.
## Testing
Add regression coverage for partial-answer phases in live events, sampling continuations, follow-up requests, and forked child requests, plus mailbox preemption, goal accounting, and guardian transcript inclusion.
GitOrigin-RevId: 208c8933e211b42b6c2d0bec6952527b8c9c120e
## Why
Assistant answer text may be followed by more output or tools. A distinct `partial_answer` phase lets callers represent this separately from commentary and a terminal `final_answer`.
## What changed
- Add `MessagePhase::PartialAnswer` and expose `partial_answer` in the app-server schemas and generated TypeScript and Python types.
- Keep the TUI working indicator visible after partial answers and exclude them from the thread history's final-answer summary field.
- Route partial answers to the speakable channel in realtime V3 BEM-tag mode.
## Testing
Add coverage for phase preservation through serialization, input-message conversion, and SSE item start/completion events. Extend TUI snapshot coverage to verify that partial answers keep the working indicator visible while final answers hide it.
GitOrigin-RevId: 1ae3ad9264b6e36ae1cbe6b93df3d345ab4460e6
## What changed
Remove `SelectionItem::is_default` and stop appending `(default)` to model picker entries. Keep the `(current)` marker and explicitly label the workspace owner notification prompt's negative option as `No (default)`.
## Testing
Update the model selection popup snapshot to reflect the removed label and adjusted column spacing.
GitOrigin-RevId: 1f8b85f896541ef7354d5979b4244d7df4b867d6
## Why
Session activity can move unread threads ahead of a pagination cursor, and timestamp-only cursors can skip threads with equal creation times. Either can prevent a session label lookup from detecting duplicate labels. Database failures must also remain distinguishable from an exhausted listing.
## What changed
- Resolve session labels using database-only listings ordered by `CreatedAt`, with thread IDs breaking timestamp ties. Accept unique matches across pages with valid timestamp-and-ID cursors, while retaining ambiguity errors for older cursors that cannot establish uniqueness.
- Preserve timestamp index ranges for database continuation queries and timestamp-only cursors for listings that may fall back to the filesystem.
- Propagate database-only listing and name-resolution failures. Keep best-effort name enrichment for ordinary listings and retry latest-session lookup with scan-and-repair after a database-only error.
- Keep loaded sessions selectable in the resume and fork pickers when a later page fails, stop further pagination, and display `Could not load more sessions`.
## Testing
Add regression coverage for creation-time continuation after session activity, cursor query plans, filesystem fallback, database and name-query errors, cross-page label uniqueness, older server cursors, and selection after picker pagination failures.
GitOrigin-RevId: 264ab2e69b8ad12d9edaa31fd253cb9805a46a90
## What changed
- Remove `instructions_variables`, its protocol type, and unused personality templates. Continue accepting older catalogs by ignoring their legacy variables.
- Report `supports_personality` as `false` in app-server model listings and TUI model presets.
- Preserve pinned model metadata and base instructions when only personality settings change. Reuse Guardian review sessions across friendly and pragmatic settings, while keeping the `none` opt-out distinct.
## Testing
Update coverage for legacy catalog deserialization, personality override notifications, opt-out behavior during model switches, and preservation of instructions and history on resume.
GitOrigin-RevId: bee8a263ef84046301888d02347f43929ececce9
## What changed
Introduce `TurnEnvironmentRequest` for caller-supplied environment input and construct `TurnEnvironmentSelection` at session startup and app-server settings boundaries. Update thread startup, default environments, and inherited environment handoffs to use requests, with explicit conversions when reusing runtime selections.
Move the environment types into `protocol::environment` while retaining their `protocol` re-exports. Update test fixtures and existing tests to build request inputs separately from runtime selections.
GitOrigin-RevId: 12e7daaece95aae136afae8b055b4dbaebdffc75
## Why
Some metrics backends require cumulative metrics, while configured OTLP exporters previously always used delta temporality.
## What changed
Read `OTEL_EXPORTER_OTLP_METRICS_TEMPORALITY_PREFERENCE` for configured HTTP and gRPC metrics exporters. Accept `delta`, `cumulative`, and `lowmemory` case-insensitively, retaining delta for unset, empty, or unrecognized values. Document the setting and preserve existing temporality for the built-in Statsig exporter and runtime snapshots.
## Testing
Update the HTTP loopback test to set the preference in an isolated subprocess and assert that the exported counter uses cumulative aggregation temporality.
GitOrigin-RevId: ca212eea20054b947005d323186c8b9a819ace9d
## What changed
- Carry opaque `review_target` values through misalignment errors and expose optional `reviewTarget` in the app-server protocol and generated clients. Preserve the value verbatim and redact it from debug output.
- Keep target-based `misalignment_override` metadata on turn requests, preserve it across steering updates, and exclude it from compaction and external MCP metadata. Reject overrides from global Responses metadata while retaining legacy timestamp behavior for per-turn overrides.
## Testing
Extend coverage for error propagation, debug and rollout redaction, steering preservation, and metadata filtering. Verify that automatic compaction omits the review target while turn requests before and after compaction retain it.
GitOrigin-RevId: 8c1abb076a206ff5927a4acc31bd25e3efc2bff9
## What changed
Record the total serialized JSON size of raw MCP tool definitions in the `codex.mcp.binding_catalog.raw_definition_json_bytes` histogram, before filtering or model preparation.
Emit an `mcp.binding_catalog` trace event for each server with its tool count, definition size, server kind, plugin ID, and cached or live catalog source. Reuse bounded product SKU attribution for both metrics and events, and skip size measurement when neither telemetry output is enabled.
GitOrigin-RevId: abda7cbf46d5470eb321455f047dd7429084740e
## Why
Bubblewrap discovery probes executables before confinement. Excluding only the command's current directory leaves candidates in other writable roots eligible to run outside the sandbox.
## What changed
- Filter canonical `PATH` candidates using the filesystem policy and effective user permissions, including writable ancestors, symlinked roots, and full-disk write access. Preserve protected system installations while rejecting replaceable paths.
- Select the launcher with the command's permissions before the proc-mount preflight, retaining the bundled bubblewrap fallback.
- Use the effective permission profile and policy working directory for startup warning probes.
## Testing
Add unit coverage for writable roots, symlinks, read-only carveouts, replaceable parents, and full-disk policies. Add Linux integration tests showing writable `bwrap` candidates are neither probed nor launched, including when the command runs in a workspace subdirectory or uses managed networking with full-disk write access.
GitOrigin-RevId: 188c9f45e727eaace062f5abb1205dc23fdf3c51
## What changed
- Add the default-disabled `code_mode_tool_search` feature to expose `await tools.tool_search({query: "...", limit: 8})` in code mode when the model supports tool search.
- Return BM25-ranked deferred tools as `{tools: [{name, description}]}`, including callable names and TypeScript declarations for use in later code cells.
- Filter results through the current step's nested-tool policy before applying the limit, preserving namespace restrictions, normalized identities, description prefixes, and schema budgets.
- Add ranked-search guidance while retaining `ALL_TOOLS` catalog discovery and description overrides.
## Testing
Add coverage for feature and model-capability gating, namespace restrictions, argument validation, schema budgets, and discovery followed by deferred MCP and dynamic tool calls. Extend the scenario snapshot to cover search, invocation, yielding, and completion through `wait`.
GitOrigin-RevId: 092a29dd5f0773c518f53a001b9cafb917422f13
## What changed
Add `features.cli_daybreak`, disabled by default, to gate Daybreak controls and automatic access-program selection in the TUI and `codex exec`. Apply the gate to resumed sessions and background task turns, and hide `/daybreak` when disabled. Explicit `--cyber-access-program` overrides remain available.
## Testing
Extend tests to cover disabled controls, history replay, foreground and background turn requests, exec resume/fork behavior, and explicit access-program overrides with the feature disabled.
GitOrigin-RevId: ae96a4a8c7ab97c619716b9f39ea9f295df6e5a6
## Why
Reloaded subagent threads did not emit initialization analytics, and subagent initialization events always reported `new`.
## What changed
Emit initialization events for resumed spawned subagents before notifying thread listeners. Inherit parent client metadata before reserving a residency slot can evict the parent, preserve the thread's original `created_at`, and report `initialization_mode` as `resumed`. Refresh stored analytics metadata when a subagent resumes; newly created subagents continue to report `new`.
## Testing
Extend the cold-resume integration test to verify a single worker initialization event with the expected session, parent, source, resume mode, and original creation timestamp. Update serialization and session tests to check initialization modes.
GitOrigin-RevId: e78b0c4d88b6ddbe993ca7e1fe7717b6f74bf3d9
## Why
Updating a CRLF file with `apply_patch` previously normalized its line endings to LF unless preservation was explicitly enabled. Preserve the file's existing line endings without requiring an opt-in.
## What changed
- Use line-ending-preserving updates for both tool calls and standalone `apply_patch` invocations, removing the legacy normalization mode.
- Mark `apply_patch_preserve_line_endings` as removed.
- Always set `CODEX_APPLY_PATCH_PRESERVE_LINE_ENDINGS=1` in child environments for compatibility with older patch executables, overriding stale values.
## Testing
Update CLI, tool-call, shell-heredoc, and app-server tests to check CRLF preservation by default. Keep coverage for overriding stale compatibility environment values.
GitOrigin-RevId: 96d0b0e5350faa3fc7a45d63627a132657b44523
## Why
Removing a whole namespace previously listed both the namespace and every member as unavailable tools.
## What changed
Emit separate namespace and individual-tool sections in one removal notice for Responses Lite. A removed namespace subsumes its members, with instructions allowing tools declared in a later update to become available again. Keep individual removal notices for tools in surviving namespaces and for built-ins.
## Testing
Expand unit tests and snapshots to cover mixed removals, empty catalogs, restoration, and replacing a namespace with a built-in of the same name. Extend the MCP refresh scenario to verify namespace removal and restoration, successful calls after restoration, preserved request history, and no repeated updates on unchanged turns.
GitOrigin-RevId: 66aa43a41db956cb5458121ea1db8c673a7ce948
## What changed
Update `.bazelversion` from 9.0.0 to 9.2.0 and refresh
`MODULE.bazel.lock`, including lockfile format version 28, registry hashes,
module extension digests, and cached crate metadata.
GitOrigin-RevId: 52689e818bf0eb37d9339df8d8a09c6cbe43e4d8
## Why
Release builds for different tags can run concurrently, but publication must remain serialized so channel checks and updates cannot race or move release pointers backward.
## What changed
Scope workflow concurrency to `${{ github.workflow }}-${{ github.ref }}`. Keep `release`, `publish-r2`, `publish-npm`, `winget`, and `update-branch` on a shared `rust-release` concurrency group with `queue: max` and `cancel-in-progress: false`.
GitOrigin-RevId: 75b42fd765db6091fb9190aae2ecccd2bb959d08
## What changed
Support `browser_use.extension.request_headers` as a list of `name`/`value` pairs and expose it through `config/requirements/read` as `browserUse.extension.requestHeaders`. Update the generated JSON schemas, TypeScript types, and Python models.
Preserve header values, including template strings, verbatim. Higher-priority requirement layers replace the entire header list, including with an explicit empty list. Redact header values in Rust debug output while retaining them in API serialization.
## Testing
Add coverage for parsing and malformed entries, extension scoping, empty-list overrides, API mapping and read responses, and debug redaction without changing serialized values.
GitOrigin-RevId: 02299e82a91aa863966d0277091bc5e8cc1ebe07
Extend the app-server thread metadata test to archive a thread after pinning
and unpinning it, before any turn starts. Assert that the thread appears in
`thread/list` results with `archived: true` and `use_state_db_only: true`.
GitOrigin-RevId: dde58e892b28843870bc3f678134fc86b93cd79c
## What changed
Install a temporary `SIGCONT` handler and unblock the signal during `Ctrl+Z` suspension. After sending `SIGTSTP`, wait for the handler to confirm resumption, returning a timeout error if no confirmation arrives within the bounded wait.
Restore the previous signal handler and thread signal mask, resume terminal stderr handling, and reapply terminal modes even when suspension fails. Propagate signal setup, delivery, and restoration errors to the caller.
GitOrigin-RevId: 1a7e10e982b1f6b2c7c7d75362a01989409b3b4d
## Why
Unix control-socket shutdown removes the socket and rendezvous link but leaves the startup lock file behind.
## What changed
Keep a removable startup lock with the control-socket guard and release the lock after publishing the rendezvous link. On cleanup, reacquire the lock and verify that the path still identifies the same file before removing it.
Use nonblocking acquisition with asynchronous retries, checking file identity after acquisition to handle lock-file replacement.
## Testing
Add tests for nonblocking lock contention and dangling symlink rejection, and extend the control-socket lifecycle test to verify that the lock file is removed on shutdown.
GitOrigin-RevId: 469ed5269f32ae1c0655d40d28519ef5e94ba6be
## What changed
- Record nonempty base instructions as a developer message after tool declarations at the start of each incremental tool context window, and omit the request-level `instructions` field.
- Preserve this prefix when rebuilding history after local or remote compaction, while keeping the compaction summary last.
- Count recorded base instructions once when estimating context usage and trimming tool outputs.
## Testing
Add regression coverage for instruction placement, omission of request-level instructions, compaction ordering, and token accounting. Exercise remote compaction trimming with both request-level and recorded base instructions.
GitOrigin-RevId: 6a6fda92c5c6eb33852a77b38d34c028cf78b164
## Why
Publishing an older stable version should not replace a newer release as the default download or installation target.
## What changed
- Compare stable versions before marking a GitHub release as latest, allowing same-version reruns to finish publication.
- Guard npm `latest` and platform dist-tags, publishing older versions under separate `release-<version>-<tag>` tags.
- Check R2's `latest` channel before updating it or the installer aliases, while allowing same-version reruns to repair interrupted installer updates.
- Reject invalid existing stable release metadata and consolidate GitHub latest and canary checks in `releases.py`.
## Testing
Add regression tests for stable version ordering, same-version reruns, npm package and platform tags, and invalid channel metadata. All 21 tests in `.github/scripts/test_releases.py` pass.
GitOrigin-RevId: e6bad3ee163b279ac1661b9070712a41eedd50ff
## Why
Transient admission errors or connection resets can prevent a code-mode session from opening before any execution starts.
## What changed
- Retry `OpenSession` and the initial lease message on `Unavailable` or `ResourceExhausted`, with at most three attempts and 100 ms and 200 ms delays within a single startup deadline.
- Classify HTTP connection and request failures as `Unavailable` so admission can recover from connection resets, while preserving error sources.
- Keep retries limited to initial admission so established executions are never replayed.
## Testing
Add gRPC integration tests covering transient status recovery, the retry limit, immediate failure for non-retryable statuses, and successful session execution after a connection reset.
GitOrigin-RevId: 3b654bcd377a5addf7c3ed58bb1c72a449b2f7f7
## Why
Thread-owned Guardian context is always enabled, and `guardianv2.thread_context` is deprecated and ignored.
## What changed
Remove explicit `GuardianThreadContext` enables from retained-context and heartbeat tests. Parameterize the heartbeat skill-context test with optional feature lists so it covers the default behavior and `GuardianRootHandoffContext`, each with one or three heartbeats.
GitOrigin-RevId: 78e3159832bff08b79c7977d876d9acb587e9c71
## What changed
Extend the Windows signing action with an `additional-files` input and sign `scripts/install/install.ps1` with Azure Trusted Signing in the x64 release job. Stage the architecture-independent installer after compression so it remains a plain script, and publish the signed artifact as `install.ps1` instead of copying the unsigned source.
## Testing
The Windows release workflow verifies that the installer has a valid Authenticode signature and a timestamp certificate before staging it, failing the job if either check fails.
GitOrigin-RevId: 6f16a084b8f350fbf3644c36d75651a6f4b88506
## What changed
- Accept per-environment `skills.required` lists through `environment/add` and `environments.toml`.
- Before inference, require each named skill to be enabled and supplied by the selected environment. Missing skills fail the turn before a model request, including when environment setup fails.
- Stop applying an environment's requirements after it is deselected. Exempt isolated Guardian reviewers, which have no skill catalog.
## Testing
Add tests for available, missing, disabled, and wrong-environment skills, failed environment setup, recovery after deselection, and propagation of TOML requirements to the correct environment.
GitOrigin-RevId: 302ced4774697d2f414f745fe0535e71f747eda2
## What changed
Move base instructions from the top-level `instructions` field into a prefixed `developer` message in `input` for standard Responses requests, matching Responses Lite. Remove the field from HTTP and WebSocket request types and assign instruction messages stable IDs derived from the thread and instruction text.
## Testing
Extend standard and Responses Lite tests to cover instruction message serialization, stable IDs, and resume consistency. Update WebSocket tests to verify that changed instructions trigger a full request without `previous_response_id`.
GitOrigin-RevId: e2de4b8e30a9339377fac133ceda981abd1a112b
## What changed
Give the initial Guardian review and its checkpoint recovery attempt separate recovery flags instead of resetting a shared flag. Keep the single restart under the original review deadline.
Represent reviewer selection explicitly with `ReuseIfAvailable` and `FreshParentCheckpoint`, so recovery requires a fresh session and ignores reusable fork snapshots.
GitOrigin-RevId: 35f63f375e2a8bef10271944e222ffce1d1939c4
## Why
A Guardian review restarting from the parent checkpoint must bypass cached reviewer sessions and snapshots, even when another review is using the cached session.
## What changed
- Add `ReviewerRequest::requires_fresh_session` and enable it for parent-checkpoint recovery.
- Replace an idle cached session with a fresh reusable session, or start a fresh ephemeral session when the cached session is busy. Neither recovery path inherits a cached snapshot.
- Reserve the review permit before validating a cached session and before exposing a newly spawned session to concurrent requests.
## Testing
Add tests covering recovery with idle and busy cached sessions, verifying that recovery receives no cached snapshot and that subsequent reviews reuse the appropriate session.
GitOrigin-RevId: 894f685736da54312336932aa2037e74a20629d9
## Why
Reviewer compaction can invalidate previously admitted transcript evidence. When a parent checkpoint is available, restarting from that checkpoint preserves the captured parent context instead of relying on a lossy reviewer summary.
## What changed
- Restart an invalidated reviewer once from the action-time parent checkpoint, within the original review deadline.
- Preserve fresh checkpoints during startup and fit review input using the existing budget selection.
- Select transcript evidence from the checkpoint actually loaded by the reviewer. Track the transcript source so cursors remain valid across legacy-history eviction and reset when the source changes.
- Resume transcript deltas after successful recovery, including authorization added after the parent checkpoint.
## Testing
Add regression coverage for checkpoint recovery, post-checkpoint authorization, resumed deltas, and stopping after one restart. Extend history tests to cover both legacy retention and parent-checkpoint reuse, and update the checkpoint-migration snapshot.
GitOrigin-RevId: bc20fb9489afaad963303beff1c79f62fa5023f7
## What changed
Use `OPENAI_API_KEY` for the Guardian Decisions sampler when `CODEX_GUARDIAN_DECISIONS_API_KEY` is absent, the provider is `openai`, and no custom base URL is configured. Preserve dedicated-key precedence, including empty values, and do not fall back for other providers or custom base URLs.
## Testing
Add a credential-selection test covering fallback, dedicated-key precedence, empty dedicated keys, and provider and base URL restrictions.
GitOrigin-RevId: a2a62c28789597f013544b51e142b21f9e214080
## What changed
Expose two JavaScript globals for consuming results as inputs settle:
- `as_settled(promises)` returns an async iterator of fulfilled and rejected records in settlement order, preserving queued results while the consumer is busy.
- `stream_settled(promises, emit)` delivers those records to a callback, awaiting each invocation and propagating callback errors.
Records include an `index`, a `status`, and either a `value` or a `reason`. Iterable inputs use positional indices; `Map` inputs retain their keys. Both helpers accept promises, thenables, and plain values.
## Testing
Add runtime coverage for ordering, input types, object identity, callback behavior, early iteration exit, and termination. Add stdio and gRPC host tests for partial results across waits, plus a scenario snapshot verifying fulfilled and rejected records reach the model.
GitOrigin-RevId: cddc9f3679ae04f2421e154caa0417afb15f550d
## Why
Incremental namespace declarations contain only changed or added tools. Their descriptions need to make clear that previously declared tools remain available unless explicitly marked unavailable, and that redefinitions replace earlier definitions.
## What changed
Append this guidance to updates of existing namespaces, preserving any namespace description. Leave initial declarations and catalog hashes unchanged.
## Testing
Extend unit and request-history coverage for the namespace hint, unchanged turns that append no tool definitions, and MCP tool removals that append a standalone notice without rewriting history or repeating the notice on the next turn.
GitOrigin-RevId: e32f3c9948efb44a1253868fe67967f117cc21e8
## Why
Manual, pre-turn, and post-turn compaction previously deferred rebuilding initial context until the next turn. Their saved replacement history could omit refreshed instructions and skill catalogs.
## What changed
- Install initial context during local and remote compaction, before the last real user message or summary, keeping the compaction summary last.
- Persist matching full world-state and turn-context baselines with every replacement instead of retaining only partial extension metadata.
- Build replacement context and recompute token usage for the current model even when the previous model performs compaction. Reuse that captured context for eligible current-model retries.
- Capture manual compaction context centrally and propagate preparation errors to the task runner.
## Testing
Update assertions and snapshots for context ordering, refreshed instructions, resume and fork history, current-model checkpoint baselines, and cloud skill catalog retention across compaction and resume.
GitOrigin-RevId: 8572a76c31c6884a3c580b3bbb350d49af876bd1
## Why
The Decisions adapter rejected developer messages, including host-annotated trusted-tool context. Requests containing that context could not be classified.
## What changed
Append developer text annotated with `TrustedTool::KIND` to the classification rubric, preserving its authority while keeping user evidence in the input messages. Accept only a single text part with a single matching annotation; continue rejecting other developer messages and unsupported evidence.
## Testing
Add a regression test covering trusted-tool context alongside untrusted user text, plus rejection of incorrect roles, missing or mismatched annotations, multiple annotations or content parts, and image content.
GitOrigin-RevId: 65b6301b2ee1ac54d67275978ccb5e37dcac7c16
## Why
MCP elicitation reviews used turn-start context, which could omit remote environments that became ready before the tool invocation and use stale environment permissions.
## What changed
Capture the issuing step's Guardian review context with each live MCP invocation and reuse it for elicitation reviews. Fall back to turn context when no matching live invocation is available, and preserve the captured context for in-flight actions.
## Testing
Extend the deferred-executor regression test to cover MCP elicitations, checking that Guardian receives the newly ready remote environment and its denied paths, excludes stale local denied paths, and returns the denial to the parent model.
GitOrigin-RevId: 0cc58b8f30543a9af87d53e1a90f574a8e6a2f84
## What changed
Measure `responses_duration` directly around `sampler.sample()` in the snapshot classification path. Leave it unset for conversation classification instead of timing submission and waiting for the score.
GitOrigin-RevId: 4cfac9db6f19f3c8513d7bf839ea9631d41bf3ac
## Why
Aborting a refresh task cannot retract a response already queued for delivery. The test helper could consume that stale response and return before the replacement refresh completed.
## What changed
Make `finish_overview_refresh` skip responses whose request ID does not match the active refresh. Extend the lifecycle test to queue an invalidated response before removing a task, exercising the wait for the replacement refresh.
GitOrigin-RevId: 97341681682e8dce9a9512fbcc1d5c0351b084f5
## Why
An already-cancelled delegate spawn can report a runtime admission or startup error instead of `TurnAborted`, including when runtime shutdown has been requested.
## What changed
Check the cancellation token before runtime admission and session startup so prior cancellation returns `TurnAborted` immediately after approval-policy validation.
## Testing
Extend the pre-cancelled spawn test to cover both normal operation and requested runtime shutdown, asserting `TurnAborted` within a one-second timeout.
GitOrigin-RevId: 5a25a211acdd5c246a3c638243ccc8b7240fd051
## Why
Snapshot classifier requests can arrive out of order, so continuation tests need to keep the next tool blocked until the current tool's classifier request has been captured and checked.
## What changed
Gate every mock Guardian review in high-risk review continuation scenarios. Release each review after checking the corresponding classifier request, preserving the ordering needed by the existing assertions.
GitOrigin-RevId: 9e52acd2bb1ce2fb71100fe0e1b92304d29e9634
## Why
The warning assertions need tracing callsite interest to remain independent of untraced parallel tests, even when the test runner already owns the global subscriber.
## What changed
Run the test on a current-thread Tokio runtime and capture warnings with a thread-local subscriber and an explicit buffer. Keep a `NoSubscriber` dispatch alive to stabilize callsite interest, and assert the deferral warning and `client_echo` directly against the captured logs.
GitOrigin-RevId: 5bf22b2cbfefcf8f65016d2cc1444112d9f6a6c7
## What changed
Add `tools_change_count` to turn profiles and turn analytics events. Compare the full model-visible tool list before each sampling request, retaining the previous list across turns and connection resets. The first list establishes a baseline; subsequent changes increment the current turn's count.
## Testing
Add coverage for schema changes, tool additions, ordering changes, empty lists, and tracking across sessions and transport fallback. Extend the turn event serialization test to include `tools_change_count`.
GitOrigin-RevId: 44a15c42dc7d0b35c166666faeb9627b718b33dd
## What changed
Add the default-off `stable_environment_tools` feature flag. When enabled, advertise environment-backed tools before an executor is ready, keep environment selectors stable as readiness changes, and include the `shell` and `login` parameters. Execution still requires a usable environment and its policy.
When disabled, expose environment-backed tools only when a usable environment exists, derive selectors from usable environments, and condition shell parameters on the execution configuration. Restore tool-specific unavailable-environment errors and skip the environment readiness check for `write_stdin`.
## Testing
Parameterize the empty-environment tool availability test for both flag states, check that commands require a ready transport by default, and explicitly opt tests that rely on stable tool exposure into the feature.
GitOrigin-RevId: 68c6240fb3adf85d7f9b407804d4823c515abfdc
## Why
Malformed `deny_read_acl_state.json` previously caused deny-read ACL reconciliation to fail. Recovery must restore bookkeeping without removing unknown existing restrictions or modifying a linked file's contents.
## What changed
- Retry malformed reads for up to two seconds, then rebuild bookkeeping only after excluding active writers and successfully applying current deny-read ACLs. Preserve unknown historical denies and continue propagating I/O errors.
- Validate the opened state file before reading or writing, rejecting reparse points and files with multiple hard links.
- Write state in place without truncating before validation, preserving file identity and permissions. Retry sharing violations during writes while preventing replacement through delete access.
## Testing
Add Windows tests for corrupt-state recovery, linked-file rejection, concurrent writer and delete-handle behavior, file identity and ACL preservation, and subsequent permission-profile changes. Extend the elevated sandbox integration test to verify that denied reads remain blocked after recovery while allowed writes and deletes succeed.
GitOrigin-RevId: 4aca32df00d015df3763fdc447ffdfbe3fd6cec0
## Why
Fresh starts connected to an app server can bootstrap with stale client model settings before reading the server configuration. An empty model catalog can also prevent startup even when managed new-thread defaults provide a model.
## What changed
- Read server configuration before model bootstrap for fresh starts using a local daemon or remote server without an explicit profile.
- Preserve explicit model and reasoning-effort overrides, clear implicit client settings when `config/read` is unsupported, and allow managed new-thread defaults to supply a model when the catalog is empty.
- Use the launch directory for local daemon configuration reads and the server directory for remote reads.
## Testing
Update startup-default tests to cover managed model selection with an empty catalog. Strengthen the reconnect test with a stale client model and an assertion that `config/read` uses the server directory.
GitOrigin-RevId: 8fe1485c6e66c8d46560b34d904ce1724458993a
## Why
New embedded TUI threads forced reasoning summaries off when no summary was explicitly configured, overriding the model's default. Client settings could also override the destination server's reasoning summary configuration.
## What changed
Use the same launch override handling for embedded and remote thread starts so server configuration and model defaults determine reasoning summaries. Forward explicit profile and command-line choices for `model_reasoning_summary` and `features.concurrent_reasoning_summaries`, preserving both enabled and disabled values.
## Testing
Extend coverage for model defaults reaching Responses requests, concurrent summary delivery, direct startup, and replacement sessions with profile and command-line overrides.
GitOrigin-RevId: c60e33d077298d7a89d6b95f94b1292c175d6c77
## What changed
- Remove redundant snapshot fixtures and selected rendering test cases across the TUI.
- Replace several full-output snapshots with direct assertions on messages, popup state, status indicators, and rendered content.
- Consolidate slash-command aliases, command-prefix selection, category titles, and hook events into shared test loops.
- Use shared snapshots for the setup import prompt and paginated transcript overlay across platforms.
GitOrigin-RevId: 461e30ebaf70ba930d91a135d2fc598ee4f04f27
## Why
A review can fail before the UI receives the event that enters review mode. Failed-turn completion also needs to preserve the running indicator when a queued `/review` has already been submitted and is awaiting startup.
## What changed
- Emit the review-entry lifecycle before starting the review task, after aborting existing tasks and clearing connector selection.
- When a live failed-turn completion repeats an already handled error, refresh task state only if no user turn is pending startup, and continue processing queued input.
## Testing
Add regression tests for lifecycle ordering on a server-overload response and for preserving the running indicator while a queued review awaits startup after a failed turn.
GitOrigin-RevId: 0f91d3d1a1a983542c54c2686630de9c232321b1
## What changed
Make plain `codex remote-control` start or reuse the managed daemon and enable remote control when daemon auto-start is enabled and the environment is eligible. Fall back to the foreground server when no managed backend is available or Windows restricts detached launch.
Add `codex remote-control --no-daemon` to explicitly run the foreground server, and honor the top-level `--no-daemon` flag. Reject this flag with `start`, `stop`, or `pair`. Keep `--json` and launches with configuration overrides or unsupported environments on the foreground path.
GitOrigin-RevId: cb28ae3f6074993b748660972c3cb7cbf6612c2f
## Why
Some Windows policies deny in-process reparse-point mutation while allowing the system junction creator, preventing managed daemon release selection.
## What changed
Fall back to `cmd.exe` with `mklink /J` when native junction creation or retargeting returns `PermissionDenied`. Pass quoted paths through environment variables and disable delayed expansion to handle shell metacharacters.
Create the replacement junction before moving the existing `current` junction aside, and attempt to restore the previous junction if installation fails. Preserve it for recovery if restoration also fails.
## Testing
Extend the Windows junction test to cover fallback creation, native retargeting, and fallback replacement under a path containing spaces, `&`, `%`, and `!`, while verifying that no standalone CLI installation is created.
GitOrigin-RevId: 039ee850f8c788f44f08116614ca3927e3e9952f
## Why
Pressing `/` in Vim Normal mode starts a composer search, even when the draft is empty. Allow this key to open slash commands directly on an empty draft.
## What changed
When slash commands are enabled, a standalone `/` on an empty draft switches to Insert mode, inserts `/`, and opens command completion. Preserve Vim search behavior for nonempty drafts, `?`, and pending operators.
## Testing
Add a snapshot test for the Insert mode transition and command picker. Exercise Vim slash-command entry in the transcript overlay test across terminal sizes, and extend command sparkle coverage to Vim mode.
GitOrigin-RevId: 806c2f6b841190ccdc1a258f88dfa590773ba33a
## Why
Command Center previously reset to project grouping on startup, losing the user's selected grouping.
## What changed
Save grouping changes to `tui.agents_overview_grouping` in the client’s user configuration and restore the saved choice at startup. Support `project`, `status`, and `model`, with `project` as the default. Report save failures in Command Center while keeping the selected grouping active.
## Testing
Add tests for cycling through and persisting all grouping modes, preserving unrelated settings in a custom configuration file, displaying save errors, and restoring saved grouping during startup.
GitOrigin-RevId: fd56dfecb4b79cfa8439f54420ce58cc0ed66ec7
## Why
Executable scanners can briefly hold newly staged files without delete sharing, causing the rename that publishes a managed daemon release to fail on Windows.
## What changed
Retry publication on permission-denied or sharing-violation errors at 50 ms intervals, up to 100 retries. Report the staging and release paths if publication fails.
## Testing
Add a Windows test that holds the staging directory open without delete sharing, releases the handle after a delay, and verifies that publication succeeds with the payload intact.
GitOrigin-RevId: 4fbd50934ec8937d3b440d38203a2cb7356a316d
## Why
MCP startup notifications from unrelated threads could create TUI event channels, allowing subsequent approval requests from those threads to appear in the current session.
## What changed
Check the parent of an untracked subagent before accepting its MCP startup notifications. Read thread metadata with bounded retries for threads that are not yet found or loaded, and ignore notifications unless the parent belongs to the TUI.
Share thread ownership checks across notification and approval routing, including side threads.
## Testing
Extend approval-routing coverage to verify that owned subagent approvals are preserved both before thread-start notifications and after MCP startup notifications, while unrelated threads do not create event channels or display approval prompts.
GitOrigin-RevId: 6f78f237f7441aadf10b491ed191357df75c3a6a
## Why
`/archive` was disabled during a running turn, preventing users from archiving the current session until the turn ended.
## What changed
Enable `/archive` during a running turn and warn in the confirmation dialog that archiving will stop the current turn. Cancelling the dialog leaves the turn running.
## Testing
Extend confirmation tests to cover both idle and running sessions, add a snapshot of the running-turn warning, and verify that cancellation leaves the task running without emitting archive events or operations.
GitOrigin-RevId: c7c530aa671b5f04e5dc2a637e3d27a81d98d8bf
## Why
Side conversations hide unavailable slash commands, leaving users without an explanation when searching for a known command.
## What changed
- Show matching unavailable commands as disabled rows with the reason `not available in a side conversation`. For example, `/arch` now shows a disabled `/archive` entry. Keep these commands hidden from the unfiltered `/` menu.
- Rank available matches first and skip disabled rows during keyboard selection and completion.
- Prevent `Tab` from queuing input when only disabled matches are visible, and insert `/` normally when no selectable command is present.
## Testing
Add a rendering snapshot and regression tests for unavailable command discovery, navigation, available command completion and queuing, blocked queuing of unavailable matches, and slash insertion.
GitOrigin-RevId: 7160b308ca57a24a5dcb6e2686b5248a8eb4b6a7
## Why
Environment readiness previously changed which tools and command parameters were advertised to the model, even when the selected environments stayed the same.
## What changed
- Keep enabled command, patch, image, and permission tools exposed when environments are absent, starting, or failed.
- Return a consistent message asking the model to wait when no usable execution environment is available, while preserving distinct errors for unknown environment IDs.
- Derive environment selectors from all selected environments rather than only ready ones.
- Always advertise `exec_command`'s `shell` and `login` parameters while continuing to enforce login policy at execution time.
## Testing
Expand integration coverage for empty, pending, failed, ready, and recovered environments, including stable command parameters and login-policy rejection. Update subagent and skill-catalog snapshots, with separate Windows expectations.
GitOrigin-RevId: bb08084066896a9f14b3b568c081c3eaac981db7
## What changed
- Display reasoning effort alongside the model in the agents overview, using `Unknown` when unavailable.
- Place model, reasoning, project, and usage information before attention details, activity, and the last message.
- Truncate long model and reasoning values with an ellipsis to keep each on one line.
## Testing
Update overview snapshots for the new layout and extend fixtures to cover a known model and long model and custom reasoning values.
GitOrigin-RevId: 1f36e5e1e0ccf09a851f8982bbbe4fbc7d9c7461
## Why
Windows Terminal's `sendInput` mapping delivers `ESC[13;2u` as individual console key events. Decode it as `Shift+Enter` so the mapping inserts a newline in the composer.
## What changed
- Wrap the Windows event stream with a decoder for the complete Escape-prefixed sequence, including interleaved key releases.
- Use a fixed 50 ms deadline for partial sequences and replay incomplete or mismatched input unchanged. Preserve literal text, paste events, and native key events.
- Update the `crossterm` revision and dependency lockfiles.
## Testing
Add tests for repeated and fragmented mappings, deadline handling, unchanged input, error and end-of-stream replay, and composer newline rendering with a snapshot.
GitOrigin-RevId: 95ab39960510d71322824c63817710633a2fda23
## Why
Foreground remote control on Windows should let the transport create its socket parent with a protected DACL instead of inheriting the broader ACL from a temporary directory.
## What changed
Use `codex-remote-control/rc-<pid>.sock` under `std::env::temp_dir()` on Windows, leaving parent directory creation to the transport. Keep the existing temporary socket directory behavior on other platforms.
GitOrigin-RevId: 6482ed0fc4ebc6b0e5de4e1d0e13adc93afa56d1
## Why
Path-like link labels were collapsed into their destinations, discarding the author's label text and formatting.
## What changed
Preserve nonblank local link labels alongside the formatted destination as `label (target)`, including in tables. Empty or whitespace-only labels show only the destination. Keep destination formatting and fall back to the original destination when a local file URL cannot be parsed.
Render file citations without a label so they continue to display only the formatted destination.
## Testing
Update rendering and transcript-copy tests and snapshots to cover preserved path labels, styled labels, empty labels, malformed file URLs, tables, and Markdown escaping.
GitOrigin-RevId: 2810b70f1ecdc59d7f90fa1b254b1e9069c8fc29
## Why
Third-party exposure settings can eagerly expose tool schemas or exclude tools from `exec`. Keeping eligible tools deferred lets MCP catalogs change between turns without changing the model's eager tool prefix.
## What changed
Add the disabled-by-default `code_mode_only_strict_3p_tools` feature, applied only when the effective model tool mode is Code Mode Only.
- Defer eligible MCP, app, and client-supplied dynamic tools while keeping them discoverable and callable through `exec`.
- Override `deferLoading`, MCP/app `omit_tools_from`, and direct-only or excluded namespace settings. Log conflicts without adding prompt warnings.
- Preserve disabled, app-only, policy-denied, and over-budget tool restrictions. Keep built-in tool exposure unchanged, including when a dynamic tool has the same name.
## Testing
Add unit and integration coverage for exposure overrides, effective model modes, tool eligibility, and app discovery and dispatch. Add an MCP refresh scenario that verifies the eager tool prefix stays unchanged as tools are added, replaced, and removed while `exec` tracks the current catalog.
GitOrigin-RevId: a6a8e401214119bb02ea4711473c8fa3ec85c81a
## Why
The plan confirmation prompt allowed transcript scrolling but blocked selecting and copying the visible plan text.
## What changed
Allow mouse selection and copying in the visible transcript while a bottom modal is open, preserving drags across redraws. Keep other keyboard input with the modal and suppress transcript link activation, disclosure toggles, and follow-control clicks during modal mouse handling.
## Testing
Extend the plan prompt test to cover selection, `Ctrl+Insert` copying, selection highlighting, and popup bounds. Add coverage confirming that ordinary and Control-clicks do not open links in selection-only mouse handling.
GitOrigin-RevId: 9e1fdfcb4bc18215e62a714f173bc8cb372b090a
## Why
Tool availability can change between calls. Conditioning discovery guidance on whether deferred tools are currently present changes the `exec` description when the catalog changes.
## What changed
Always include the configured discovery guidance in the Code Mode `exec` description, even when no deferred tools are present. The default guidance explains how to find tools in `ALL_TOOLS` and notes that availability can change between calls. Custom guidance and explicit empty overrides remain supported.
## Testing
Add regression coverage for stable guidance with empty and populated deferred tool catalogs in both Code Mode configurations, including custom and empty overrides. Update tool-description assertions and request snapshots.
GitOrigin-RevId: 086ea19a48e3c51ec8c429a619676a936d658721
## Why
Releases can contain different resources while shipping identical executable bytes. The daemon must recognize those release changes, while a stale updater should be able to hand off without restarting an already-current daemon.
## What changed
- Include a digest of the resolved executable path in `ExecutableIdentity` to distinguish release generations with identical binaries.
- Keep content-only comparisons for package preparation and manual update reporting.
- Check the running daemon's identity and version before restarting during updater adoption, manual updates, and production restoration. Preserve scheduled retries when the daemon is not ready.
## Testing
Add coverage for path-sensitive identity, scheduled no-op updates that preserve the daemon, and resource-only release updates that restart it despite identical executable bytes.
GitOrigin-RevId: bbea06cf502abb2251e70d4ba4b422cae867116c
## Why
`AbsolutePathBuf::relative_to_current_dir` previously read the current directory even for absolute paths, causing resolution to fail if the current directory had been deleted.
## What changed
Route absolute inputs through `from_absolute_path` without querying the current directory. Relative inputs continue to resolve against the current directory.
## Testing
Extend the Unix regression test to verify that `relative_to_current_dir` succeeds with a deleted current directory and produces the same normalized path as `from_absolute_path`.
GitOrigin-RevId: 6bc6cb43d9f4d57359639708c4d30524d89cfa92
## Why
The managed daemon writes an executable and Unix-style state beneath `CODEX_HOME`. Windows-mounted WSL filesystems (DrvFS/9p) do not reliably support the required permission semantics, which can cause startup to fail before the TUI opens.
## What changed
Detect WSL homes on 9p filesystems, checking an existing ancestor when `CODEX_HOME` does not yet exist. Keep the TUI in embedded mode instead of automatically starting the shared background server, and show a startup warning explaining the exclusion.
## Testing
Extend the daemon exclusion warning snapshot to cover the Windows-mounted WSL message.
GitOrigin-RevId: 995e6236d79d8190b0ab1e6b4761eeef3c068467
## Why
In `CodeModeOnly`, MCP resource helper definitions changed when the first server was added or the last server was removed.
## What changed
Always register `list_mcp_resources`, `list_mcp_resource_templates`, and `read_mcp_resource` in `CodeModeOnly`, even without configured MCP servers. This keeps their definitions stable across server configuration changes.
## Testing
Add a regression scenario that calls all three helpers before adding a server, with a server registered, and after removing it. Assert identical tool definitions across requests, empty resource and template lists, and the expected error when reading from an unknown server.
GitOrigin-RevId: c5777efac250b83dd4bb1c9100a6b6169470556f
## What changed
When `IncrementalTools` is enabled for Responses Lite, track tool definitions in world state and conversation history. Send the initial catalog once, then append only added or changed definitions while preserving earlier request history. Emit developer notices for removed tools and namespace instruction changes.
Use history-supplied definitions for normal requests and remote compaction, and omit empty `additional_tools` prefixes. Keep the existing tool delivery behavior for the Responses API and when the feature is disabled.
## Testing
Add unit and snapshot coverage for catalog and namespace transitions, empty catalogs, and stable hashing across JSON object key order. Add a request-history scenario covering unchanged tools, a model switch that changes one definition, persisted catalog hashes, and Responses API behavior.
GitOrigin-RevId: 76bde175973b81f8ad23873919da3c8ddcdf6065
## Why
Changing a deferred tool's output schema could add or remove the shared MCP type preamble from the `exec` description.
## What changed
Include the default or configured MCP TypeScript preamble whenever `code_mode_only` is enabled, regardless of the available tools' output schemas. Preserve an empty preamble override as a way to omit the section.
## Testing
Add a regression test that checks description stability when a deferred tool gains an MCP output schema, covering default, custom, and empty preambles. Update description expectations, request snapshots, and two Guardian context-budget test thresholds for the added preamble.
GitOrigin-RevId: 725035d6159e9da3c4beff5482c426c082e768b4
## Why
When `flush_transcript_tail_on_session_end` is enabled, remaining speech must be available in thread history as soon as realtime closure is reported, even while a model response is still running. Saving that transcript should not trigger another model request.
## What changed
Record the transcript tail directly in model and client history, attaching it to the active turn or creating a completed history turn when idle. Flush persistence before emitting `RealtimeConversationClosed`, and keep realtime context active until recording finishes so the return to text instructions follow the transcript.
## Testing
Extend core and app-server tests to cover immediate history visibility in paginated and legacy modes, idle and active turns, closure without extra inference, transcript reuse in subsequent text turns, and interruption after closure.
GitOrigin-RevId: ae323b711f22aa88db1432e24ad4bb3eb3f08f6b
## Why
Flattened notification settings prevent `serde_ignored` from detecting unknown keys in `[tui]`, allowing them to pass `--strict-config` validation.
## What changed
Detect unknown TUI keys by comparing configured keys with a serialized `Tui`, keeping accepted keys derived from the configuration type. Apply this check to config files and `-c`/`--config` overrides so keys such as `tui.bogus_key_xyz` produce an unknown-field error while valid notification settings remain accepted.
## Testing
Add regression coverage for unknown TUI keys, diagnostic source ranges, valid notification settings, and generic validation behavior. Extend CLI tests to cover TUI overrides and config validation before terminal checks.
GitOrigin-RevId: b04467523442183e7a54415d82c3f632f97ef319
## What changed
Add a scenario test and snapshot covering the request before remote `/compact`, the compaction request, the persisted replacement history, and the first subsequent user turn.
Capture the replacement history before the next turn can update its context, and assert that the compaction request contains one `compaction_trigger` and the next request includes the returned encrypted checkpoint.
GitOrigin-RevId: e22e12f16bdb11b1296e81a2e0ffd5f70e560ff6
## What changed
After successful Amazon Bedrock setup, check whether the configuration uses AWS GovCloud. If detected, show application configuration and security guidance with a terminal hyperlink and require an explicit Enter press to continue. Allow scrolling in short panes while keeping the acknowledgment visible.
Continue onboarding without the warning for non-GovCloud configurations, failed checks, or checks that exceed the 15-second timeout.
## Testing
Add snapshots and tests for the checking and warning screens, explicit acknowledgment, guidance hyperlinks, and scrolling in short panes, including a one-row content viewport.
GitOrigin-RevId: d5d0352af0a50b58e8b8feab5daf75fde428ece7
## What changed
Persist the service's last reported lifecycle reason and numeric HRESULT in the existing service registry key. Distinguish requested stops, shutdown, owner removal, startup failure, broker failure, and interrupted registration, and reset the record on startup. Recording is best-effort and does not affect the service lifecycle.
Emit `codex.windows_sandbox.service_stopped` when a provisioning client observes a stopped service, including the recorded reason, HRESULT, and Windows service exit codes. Recheck the service status and registry record before emitting to avoid pairing inconsistent evidence during a concurrent restart. The metric counts observations, not unique outages; the recorded reason is advisory.
Update the cached service status only after `SetServiceStatus` succeeds. Extract diagnostic error codes from typed errors without collecting error text or user data.
## Testing
Add a test covering Win32-to-HRESULT conversion, preservation of Windows HRESULTs through error context, and a zero fallback for untyped error text.
GitOrigin-RevId: d0d39d091410e2b5499a0803475804d12235f836
## Why
Archiving or deleting the selected task could make Command Center selection jump to the current task instead of a neighboring task in the displayed list.
## What changed
Choose the next surviving task in displayed order before removing tasks, falling back to the previous task when needed. Apply this selection behavior to archive, delete, and hide actions, respecting filtering and grouping.
Preserve the pending selection across view rebuilds, batched removals, and duplicate server notifications. Allow selection to fall back when a rename target disappears while retaining the existing notice about its unsubmitted title.
## Testing
Add regression tests and snapshots for archive/delete selection across project, status, and model grouping, with and without filtering. Cover removal of the attached task, external removal notifications, removal of a pending successor, repeated repaints, and an empty task list. Update the disappeared-rename-target snapshot to verify that the remaining selection is preserved.
GitOrigin-RevId: ca93d664fadbc602993fbdae316c7a375b449345
## What changed
Render confirmation dialogs as centered overlays while preserving the composer or parent picker behind them. Share dialog sizing and cursor placement across stacked views and full transcript rendering, with input still routed exclusively to the active dialog.
Use the shared confirmation preset for prompts including full access, session archive/delete, goal changes, and log upload consent.
## Testing
Add coverage for backdrop retention and cursor routing at multiple terminal sizes, and for preserving the compact viewport and composer draft after dismissing a confirmation without replaying history. Update confirmation snapshots to show the retained backdrop.
GitOrigin-RevId: 026af89904ec345e2b330317b8cc844512125d0e
## Why
Accepting a Find result must not let a held `Enter` submit the composer draft, including when terminals report repeated keys as fresh presses.
## What changed
- Make `Enter` accept the displayed result for reading, while `Ctrl+P` and `Ctrl+N` navigate older and newer matches.
- Make `Escape` cancel query editing and restore the pre-search presentation; after acceptance, it returns to the latest transcript content.
- Consume unmodified `Enter` while reading a result, but let modified `Enter` reach configured composer bindings.
- Update footer hints to show acceptance, cancellation, and the active Find state.
## Testing
Extend input-routing coverage for repeated `Enter` presses and modified composer bindings. Update search tests and footer snapshots for acceptance, cancellation, and result navigation.
GitOrigin-RevId: 2a2b7c389240ffa941e3623d7fb7d877455fa9a5
## Why
Daemon updates discard installer stderr, leaving failed installs with only an exit status and no installer diagnostics.
## What changed
Capture the last 2 KiB of installer stderr and append it to errors when the installer exits unsuccessfully. Drain stderr concurrently and wait at most one second after failure so subprocesses holding the pipe open cannot delay error reporting indefinitely. Keep captured details within the manual update response limit, and configure PowerShell output as UTF-8 to preserve non-ASCII diagnostics.
## Testing
Add coverage for stderr tail truncation, bounded draining when a subprocess keeps stderr open, and manual update responses containing heavily escaped diagnostics. Extend the Windows installer test to check non-ASCII error text.
GitOrigin-RevId: d0da19b233006f97770d3f7f5f057e5e98fd2913
## Why
Registration-only refreshes retain the existing sandbox, so package maintenance should not require another cloud-policy fetch.
## What changed
Skip managed configuration loading when a provisioning request has both `registered_core` and `refresh_only` set. The registered-runtime transaction still checks the existing owner, accounts, and unchanged settings under the setup lock. Other provisioning requests continue to enforce managed policy.
## Testing
Update the invalid-impersonation-token test to cover all four flag combinations, verifying that only registered refreshes succeed without loading configuration.
GitOrigin-RevId: e65ba1359be65e6314fa483b24fb66ed57a444ac
## What changed
Remove the fixed 64 KiB output cap from `WorkspaceCommand` and send
`output_bytes_cap: None` in `command/exec` requests so bounded commands use
the app-server default. Preserve `disable_output_cap` for commands that need
uncapped output, including Git diffs.
GitOrigin-RevId: 6f2ed0d127d9ff2317670851894ae4988f7c7508
## Why
Bedrock catalogs cleared all service-tier metadata, and requests omitted every selected tier. This prevented users from selecting `ultrafast` or using tiers defined in custom catalogs.
## What changed
- Advertise `ultrafast` for `openai.gpt-6-astra` on Mantle and the `global.openai.gpt-6-astra` and `us.openai.gpt-6-astra` Runtime variants, while retaining the implicit default tier unless users select otherwise.
- Preserve custom catalog speed tiers, service-tier definitions, and defaults while continuing to normalize Bedrock web search compatibility.
- Send selected service tiers only when the Bedrock model advertises them, including `flex`.
## Testing
Add coverage for `model/list` tier discovery, custom catalog preservation, configured and per-turn HTTP request tiers, and TUI slash-command selection, toggling, and model switching.
GitOrigin-RevId: 4793e7af7b9f604a6b7812611030da6adb8acd35
## Why
Truncating the preview alone can leave the serialized MCP tool result above its byte budget because JSON escaping and the result wrapper add bytes.
## What changed
Measure the complete serialized replacement and progressively reduce the preview budget until the result fits or the preview is empty.
## Testing
Strengthen the regression test with quotes, backslashes, and newlines. Assert that the serialized result fits within the 1,024-byte budget and that truncating it again returns the existing result unchanged.
GitOrigin-RevId: ebd97b1a6ca71343941a96e472cb313028ac680c
## Why
Copying rendered transcript selections added Markdown formatting and escapes to the plain-text clipboard payload. Selecting bold text such as `hello` could paste as `**hello**`.
## What changed
Separate the literal selection text from the Markdown source used to render clipboard HTML. Plain-text copies omit inline formatting delimiters, added code fences, and Markdown escapes while retaining list and table structure. Rich-text pastes continue to preserve formatting through HTML.
## Testing
Update clipboard and transcript selection tests to verify literal text alongside rich HTML, including lists, inline code, paths with Markdown punctuation, hard breaks, streamed code blocks, and tables across layout widths.
GitOrigin-RevId: 980ee2ed0b0e201b581a3a301fa04d796c65af2e
## Why
Remote executors need to recover from confirmed authentication-service outages and spread reconnect attempts after a shared outage. Registration retries must remain limited to confirmed failures before a write, since replaying an ambiguous request can replace a newer registration.
## What changed
- Retry registry responses with HTTP 502 and `authentication_service_unavailable`, alongside the existing HTTP 503 `registration_conflict` retries.
- Accept structured registry errors in `detail`, keeping the canonical `error` authoritative when both are present.
- Randomize reconnect delays between half and all of the current exponential backoff, retaining the 30-second cap.
## Testing
Add coverage for reconnect jitter bounds, authentication-outage retry cancellation, error-envelope precedence, and preservation of Noise identity and initialized sessions across retries. Make the HTTP-header helper cleanup test wait for the helper PID before cancellation and verify process termination when the provider is dropped.
GitOrigin-RevId: 35fdb57732d17b0bbfeca8a4dc557a0988e29a31
Register `incremental_tools` as an under-development feature that is disabled by default, and expose it in the configuration schema for top-level and profile feature settings.
GitOrigin-RevId: 9579822c745e9fce598085bdc5ef8da6aabb06d7
## Why
Delegated turns can begin without a user message, leaving threads without a task preview. Populate the preview from delegated input so these threads are discoverable before a user follow-up.
## What changed
- Extract previews from completed `create_thread` and `send_message_to_thread` outputs in the `codex_app` and `codex_tui` namespaces.
- Unwrap recognized `<codex_delegation>` inputs and decode their escaped task text for display, preserving model content. Keep plain or unrecognized wrappers as text and ignore blank inputs.
- Fill missing previews in state metadata extraction and live thread metadata updates without replacing existing previews or setting the title or `first_user_message`.
## Testing
Add tests for delegation decoding and tool filtering, preview-only metadata updates, preservation of later user-message metadata, and database listing before a user follow-up in both legacy and paginated history modes.
GitOrigin-RevId: f7b3c60ef75e08c76b4084d043e3967bf2bade22
## What changed
Allow Responses-compatible providers to configure live web access and remote compaction under `model_providers.<id>.capabilities`:
```toml
[model_providers.custom.capabilities]
external_web_access = false
remote_compaction = "v2"
```
`external_web_access = false` keeps hosted web search from accessing the live web. `remote_compaction` accepts `v2` to send `compaction_trigger` items through the Responses endpoint, or `unsupported` to use local compaction. Omitted capabilities retain existing provider defaults.
## Testing
Add unit coverage for preserving unspecified defaults and a request-snapshot scenario verifying cached web search and V2 compaction for a custom provider.
GitOrigin-RevId: fbcc4870aa51c112af575d711679a3941d1e7878
## Why
Paginated thread history can persist large MCP results in completed tool-call items. Bound these stored results to avoid retaining multi-megabyte payloads.
## What changed
Apply a 64 KiB preview budget when persisting oversized MCP results in paginated history. Replace the result with a truncated text preview of its serialized JSON, preserving `is_error` and clearing `structuredContent` and `_meta`. Leave small results unchanged.
Share the truncation helper with the existing MCP tool-call event path.
## Testing
Add helper tests for unchanged small results and oversized results with structured content and metadata. Add a thread-history test verifying that persisted MCP results contain a bounded preview with the beginning, end, and truncation marker while preserving tool arguments.
GitOrigin-RevId: 09dce73c70bfd357c9b9630f456e9e5c1d8492cf
## What changed
- Record original and persisted item sizes in `codex.rollout.persistence.item_bytes_v2`, distinguished by stage, and record positive size reductions in `codex.rollout.persistence.bytes_removed`. Count the full original size as removed for dropped items.
- Use explicit histogram boundaries from 1 KiB to 64 MiB for item sizes, bytes removed, and `codex.rollout.persistence.turn_bytes_v2`. Larger values remain represented in the overflow bucket and histogram sum.
- Align item and turn size stages and report a measurement error when a kept item's persisted size cannot be measured.
GitOrigin-RevId: 6487acf1c6f2c041ab9680ab398491d3c1541388
## What changed
- Remove `namespace_tools` from `ProviderCapabilities` and `namespaceTools` from `ModelProviderCapabilitiesReadResponse`, updating generated schemas and SDK types.
- Preserve tool namespaces and configured collaboration tool namespaces without a provider capability check, and always use Responses Lite tool serialization for Responses Lite requests.
- Gate tool search on `supports_search_tool` and retain the existing image generation and web search checks without requiring a namespace capability.
GitOrigin-RevId: ae1843563736765a40e03a02c41ff5e470018a93
## What changed
- Combine file-backed rollouts and buffered rollout prefixes into `rollouts.tar.gz`, keeping diagnostics as separate attachments.
- Bound the archive and its upload envelope by the existing size limit, skip invalid or duplicate archive filenames, and fall back to individual rollout attachments if archiving fails.
- Add `rollout_archive_filename` to the report thread index so rollout filenames identify archive entries or fallback attachments.
## Testing
Add an upload test that extracts the archive and verifies the filenames and contents of both a compressed file-backed rollout and a buffered rollout. Update the thread index test to check the archive filename.
GitOrigin-RevId: 973da6eec2249b04ef7992b5e1e4fd27f044b80f
## What changed
Strengthen `tool_call_timing_guard_ignores_code_mode_source` to capture tracing output and assert that direct and nested code-mode calls together emit exactly one `codex.tool_call` event. Disable ANSI formatting and keep callsite interest independent of untraced parallel test threads.
GitOrigin-RevId: cbf0c9bf6d4e5a72b6a1eb08e6aac43e257f2dcb
## Why
Tokio's paused clock can auto-advance while tests await the V8 thread. The service tests need explicit control over time when checking yield limits and grace periods.
## What changed
- Hold virtual time with a blocking-task guard that is released when dropped.
- Replace bounded polling loops with tool-start notifications and direct awaits of response tasks.
- Return an error from the test helper if the cell closes before a nested tool starts.
## Testing
Add tests covering tool-start acknowledgement when a cell throws or is terminated before invoking a nested tool, including assertions on the resulting cell responses.
GitOrigin-RevId: c221c0501ec0354052102c0211cc651008babff3
## What changed
Add optional `native_usage_usd_micros` fields to thread usage totals and breakdown groups, and carry backend values through the client alongside existing credit and USD estimates. Missing or null native amounts remain `None`, while explicit zero amounts remain `Some(0)`.
## Testing
Add coverage for native totals and group amounts, mixed batches with legacy responses, and the distinction between missing, null, and zero native group amounts.
GitOrigin-RevId: 53891fc95807138e2eccb99d4cda1520b857dba4
## Why
World-state sections could return only a single optional text fragment, with message separation controlled by the fragment itself. They could not contribute explicit `ResponseItem` values alongside instructions.
## What changed
- Let sections return ordered `WorldStateUpdate` values containing fragments or response items, with `Prefix`, `Standalone`, or `Mergeable` placement.
- Preserve explicit item boundaries when grouping context updates, and place prefix updates first when assembling initial context.
- Move standalone-message decisions from fragments to world-state updates and retain snapshot handling.
## Testing
Add tests for mixed fragment/item ordering, role and standalone boundaries, initial-context prefix placement, and snapshot restoration without repeated updates.
GitOrigin-RevId: c2514c3c98538da83f5140c10a9d89f531de6549
## What changed
Add `codex sandbox uninstall` to remove machine-wide legacy Windows sandbox accounts and network rules with administrator privileges. Run cleanup without loading configuration, preserving Codex home, sandbox directories, and filesystem permissions. Reject the command on other platforms.
Keep commands after `--` forwarded to the sandbox, including `codex sandbox -- uninstall --help`.
## Testing
Add parsing coverage for the uninstall subcommand and command separator. Add an integration test verifying that help and invalid arguments work with malformed configuration and leave configuration and credentials unchanged.
GitOrigin-RevId: d2b02ef7bc0a05742dd5eb3c47292ad517d46664
## Why
`additional_tools` response items were excluded from rollout persistence, dropping their tool definitions from saved history.
## What changed
- Persist `additional_tools` items in both legacy and paginated history modes.
- Expose the variant in generated JSON schemas, TypeScript types, and Python models, with an optional `id`, a `role`, and arbitrary JSON tool definitions.
## Testing
Add a recorder round-trip test that verifies tool definitions survive recording and loading in both history modes without parse errors.
GitOrigin-RevId: 0e7c7b1c10401ec6513fb744de642a1cf9e461d7
## What changed
- Make `/copy` select the latest completed response directly in the owned transcript. Navigate user messages, code blocks, and blockquotes with arrow keys or `j`/`k`, use `g`/`G` to jump to the ends, and press Enter to copy or Escape to close.
- Highlight selected blocks and keep surrounding context visible during navigation and resizing. Preserve source payloads for code and quotes, including rendered Mermaid diagrams and fenced Markdown tables.
- Pause queued submissions until copy mode closes, and report clipboard results in the transcript footer.
## Testing
Add tests for copy routing, keyboard navigation, highlighting and resize behavior, source whitespace and line endings, clipboard completion, and queued-input resumption.
GitOrigin-RevId: bd4f58ec17568f95d0e91014e5ddba33ca8bd57c
## What changed
Allow accounts using an API key with the OpenAI provider to access `/daybreak` and Daybreak policy notices. Model availability and the connected server still determine program access.
Use the same eligibility checks for turn submission, continuation, and retries. For API-key accounts, send the selected `cyberAccessProgram` when Daybreak is enabled and omit it when Daybreak is off.
## Testing
Extend session lifecycle coverage to check API-key turn parameters with Daybreak enabled and disabled. Add an API-key `/daybreak` help snapshot and update the signed-out error snapshot.
GitOrigin-RevId: ab6d4313c430f316ef9835d4facb878aab0b9725
## What changed
Keep Markdown link destinations attached to prompt and last-message previews in the agents overview details pane as text wraps and is clipped. Render visible links as terminal hyperlinks, while keeping truncation ellipses unlinked.
## Testing
Add a regression test and snapshot covering links that span multiple rows, prompt links, and clipped previews with unlinked ellipses.
GitOrigin-RevId: d121e062b197790ce45a70d6d64aadcb181e4dde
## Why
Paginated history previously persisted completed commands' full `aggregated_output`, allowing large command outputs to inflate stored history.
## What changed
- Limit persisted command `aggregated_output` to 64 KiB, including a truncation marker. Preserve the beginning and end of the output without splitting UTF-8 characters.
- Apply the shared persistence policy to rollout recording, thread-store appends, and legacy-to-paginated history migration.
- Measure persisted payload bytes after truncation so persistence metrics reflect the stored representation.
## Testing
Add coverage for the byte limit, UTF-8 boundaries, unchanged inputs that fit, and markers that exceed the budget. Verify capped output in paginated thread history and migrated legacy history, and verify persistence metrics use the truncated payload size.
GitOrigin-RevId: 01d420d396ad34b42dc5dc208c0bf88d890639ee
## Why
Streamed `response.failed` events can carry retry advice in `response.error.headers`. Ignoring it loses server-provided delays or uses a conflicting delay from a rate-limit message.
## What changed
- Parse nested `Retry-After` headers using the existing HTTP header validation and retry parser, and preserve them for rate-limit, overload, and generic retryable failures.
- Prefer valid headers over rate-limit message advice, falling back to the message when the header is absent or invalid. Keep terminal error classifications unchanged.
- Reject unrepresentable plaintext retry durations without panicking.
## Testing
Add regression coverage for header precedence, validation, and terminal errors, plus retry-loop coverage for SSE sampling, remote compaction, and WebSocket failures.
GitOrigin-RevId: 46433c2e9e6d5e804211ef96950fadd70e322b49
## What changed
Label the `/new` and `/fork` picker options “Use current Git worktree” and “Create new Git worktree”. Explain that creating a worktree makes a separate checkout of the repository in another directory.
## Testing
Update picker assertions and snapshots for both commands to cover the revised labels and description.
GitOrigin-RevId: b7fb1aac3107e39c324707f9ae69c210a97346d7
## What changed
- Remove `stdout`, `stderr`, and `formatted_output` from `CommandExecutionItem` and `ExecCommandEndEvent`, retaining `aggregated_output` as the output field.
- Update command event producers, legacy conversion, rollout traces, and the precomputed schema. Use aggregated output for terminal trace results.
- Clear `interaction_input` in emitted and migrated command completion items.
## Testing
Update command execution and trace tests to use aggregated output, and assert that legacy rollout migration preserves `aggregatedOutput`.
GitOrigin-RevId: ed59827d4a5ec9a767084ee4feac72c2042440f2
## Why
Transcript scrolling hardcoded `PageUp` and `PageDown` to full-page movement, ignoring customized pager bindings.
## What changed
Resolve unmodified `PageUp` and `PageDown` through the pager's scroll bindings so they can scroll by a full page, half a page, or one row, or remain unbound. Preserve the one-row overlap for full-page scrolling and leave pager typing shortcuts unhandled by the transcript.
## Testing
Add a regression test and snapshot covering default, half-page, single-row, and unbound configurations. Verify that `PageDown` reverses `PageUp` scrolling and that `j` and `Ctrl+u` remain unhandled.
GitOrigin-RevId: 945e99d7370f84f326ab71037be2924dddada32c
## Why
Transcript selection can consume a configured composer shortcut such as `ctrl-space`, preventing it from submitting a prompt or steering a running turn.
## What changed
Let explicitly configured shortcuts for active actions take precedence over transcript key handling when no transcript interaction is active. Include global binding fallbacks, while preserving empty `Enter` returning to the latest transcript content and default `PageUp` scrolling.
## Testing
Add regression coverage for `ctrl-space` submission with idle and running turns, default `PageUp` scrolling, and empty `Enter` returning to latest with composer or global submit bindings.
GitOrigin-RevId: 16613043a7634b47fd24e4ee9feacdce94a9fabd
Set `OAI_RCODESIGN_ARM64_16K_CODE_PAGES=true` to pass
`--arm64-16k-code-pages` when signing with `rcodesign`. The option is
disabled by default.
GitOrigin-RevId: ee7d4992f89a8fe2eb355fb2516a0188e7583812
## Why
If required MCP startup outlasts the requesting connection's cleanup, the newly created thread can remain loaded without subscribers because its listener is never started.
## What changed
Start the thread listener even when the requesting connection has already closed, allowing normal idle unloading to clean up the thread while preserving the `ConnectionClosed` result.
## Testing
Add a regression test that disconnects during blocked required MCP startup, then releases startup and verifies a `thread/closed` notification, an empty `thread/loaded/list`, and MCP process exit on Unix.
GitOrigin-RevId: 4ad912a82177266316042d806f5faa1713a48fa4
## Why
GNU Screen truncates Unicode in OSC titles to a byte, which can turn visible characters into control bytes and spill title text into the terminal.
## What changed
Detect Screen through `STY` and convert the full terminal title to printable ASCII. Map activity spinners and the status dot to ASCII equivalents, and replace other non-ASCII content with `?`. Keep Unicode titles outside Screen and preserve Unicode in TUI status rendering.
## Testing
Add coverage for ASCII title output with activity indicators and Unicode names, preserved Unicode outside Screen, and removal of control and invisible formatting characters.
GitOrigin-RevId: e6b45b9be0d06ab3c3eece89885647f3e9db17da
## What changed
Remove `initial_messages` from `SessionConfiguredEvent` and the corresponding schema. Stop attaching replay history to startup events for resumed or rejoined threads, and remove `InitialHistory::get_event_msgs`.
## Testing
Update the MCP resume test to verify persisted tool events through `load_history`, and retain coverage that resumed requests include prior conversation items.
GitOrigin-RevId: 54b72bc44423c9b1ef2051891ef392c0ede32fe5
## Why
Hook system messages were rendered as plain text, leaving ANSI formatting uninterpreted.
## What changed
Parse hook system messages into styled spans so colors and text styles render across lines. Preserve hook prefixes, continuation indentation, and trailing blank lines.
## Testing
Add a snapshot test for multiline ANSI styling and style resets, and extend multiline coverage to include a combining character and a trailing newline.
GitOrigin-RevId: 0a5a88ec26fac114fc66efa656bacf6fa15a1adf
Return a clone immediately when the current path is not a prefix of any
registered legacy config key. This avoids recursively visiting unrelated
subtrees while preserving alias normalization along matching paths.
GitOrigin-RevId: 1c7e62898e12ab3f468b978f865805989914ac44
## Why
Closed WebSocket connections previously triggered immediate reconnects, and successful handshakes reset backoff even when connections were short-lived.
## What changed
- Delay automatic reconnects before token refresh or enrollment, and report `Connecting` while waiting.
- Use exponential backoff with jitter between half and all of the delay, starting at 5 seconds and capped at 30 seconds.
- Retain backoff across short-lived connections and reset it after a connection lasts at least 60 seconds.
- Interrupt the reconnect delay on shutdown, auth owner invalidation, or enable/disable changes, including an immediate disable/enable pair.
## Testing
Add connection tests for delayed token refresh, backoff retention and reset, explicit re-enabling, and prompt shutdown. Update retry tests to check jitter bounds, saturation during sustained failures, and backoff retention after a successful handshake.
GitOrigin-RevId: 0b9055ff64ff7d96f2d974b73ced8d4ffd02ac9e
## Why
Cached subagents can remain in the TUI picker after being archived, including when archive notifications are missed.
## What changed
- Hide archived threads from the picker and keyboard navigation, and restore them when unarchived.
- Refresh both active and archived descendants to reconcile cached visibility, including after dropped server events. Queue a follow-up refresh when needed and preserve visibility changes received during an in-flight refresh.
- Preserve picker selection by thread ID as visible rows change, and mark archived thread attachments as replay-only.
## Testing
Extend regression coverage for missed archives, unarchive notifications, hidden subagent navigation, and the subagent enable prompt when only archived subagents are cached.
GitOrigin-RevId: 9e75906dfe6946b1400583a386922453e2b77ea1
## What changed
Add an MCP integration test that forwards sandbox state from tool-call metadata unchanged to `codex sandbox --sandbox-state-json` and runs a real subprocess.
Verify that workspace writes succeed, overwriting an existing file outside the workspace fails and preserves its contents, and relative paths resolve against `sandboxCwd` rather than the MCP server's working directory.
GitOrigin-RevId: 768513c74679010e806a62dffdde6b7cccbfb41f
## What changed
Record `agree`, `disagree`, or `unavailable` comparisons between Decisions risk classifications and accepted Responses scores. Emit paired latency histograms only when both backends succeed, and include request preparation and queue time in Decisions duration. Report unavailable comparisons when the comparison feature is enabled but the Decisions sampler is not initialized.
## Testing
Extend lifecycle coverage for an uninitialized Decisions sampler, checking skipped outcome and unavailable comparison metrics while preserving the baseline score.
GitOrigin-RevId: f11789ab5d5fd6957b7913d849bbb2ae7006d3ed
## Why
A hung tmux command or a descendant holding stdout open can block terminal input setup indefinitely.
## What changed
Run tmux option probes on a worker thread with a shared one-second deadline, returning default input options when the wait times out. Prevent overlapping probes and kill and reap commands that exceed the deadline.
Capture stdout in a temporary file so completed commands do not wait for descendants to close it, and read at most 4 KiB of output.
## Testing
Add Unix regression tests for successful output, killing and reaping a timed-out command, and returning promptly when a descendant keeps stdout open.
GitOrigin-RevId: a5a4c9323a3e18d1baada5ab1cf3734ce6a9403a
## What changed
Replace the rename field with a single-line `TextArea` that honors configured editor bindings and the composer's Vim setting. Start renaming in insert mode and support Vim Escape recovery on legacy terminals.
Strip carriage returns and newlines from titles and pasted text, keep Vim linewise pastes inline, and scroll horizontally at grapheme boundaries to keep the cursor visible.
## Testing
Add single-line editor coverage for newline filtering, Vim commands, repeat edits, and inline yanks. Extend command-center tests to cover Vim renaming across status-filter changes and cursor placement in narrow layouts.
GitOrigin-RevId: 8d320d6b6de9f77e18292169418383929ca6ceda
## Why
Windows Terminal forwards `Ctrl+Insert` when its Copy action has no native terminal selection. Recognize this shortcut so it can copy text selected within Codex.
## What changed
Add `Ctrl+Insert` to the shared copy-key detection used by transcript and composer selections. Use the same detection for transcript input ownership so the selection consumes the shortcut before other input handlers.
## Testing
Extend transcript tests to verify `Ctrl+Insert` input ownership and copying. Extend composer tests and snapshots to verify that failed or unconfirmed copies preserve the selection, while confirmed copies clear it without changing the draft or cursor.
GitOrigin-RevId: 5a33c72cff4c4395511779a7051fc92f8bd5e5d7
## What changed
Add `tui.mouse_scroll_speed` as a finite positive multiplier for transcript mouse wheel scrolling, including transcript overlays and session previews. Change the default from three rows to one row per wheel event; set the multiplier to `3.0` to retain the previous speed.
Fractional values accumulate movement across events and discard the remainder when direction reverses. For example, `0.5` scrolls one row every two events. Following the latest output pauses only when a whole row moves.
## Testing
Add tests for configuration validation, integer and fractional scroll speeds, direction changes, decimal accumulation, and following behavior. Extend local settings coverage to include a command-line override for the new setting.
GitOrigin-RevId: d355e246fd943415f0ce5a6affe849f77f3615e6
## Why
Table holdback kept completed tables and subsequent content mutable until the response finished. Releasing completed tables earlier also requires a final scrollback reflow when late reference-link definitions change previously emitted content.
## What changed
- Release table holdback once the containing top-level Markdown block is stable, rescanning the remaining tail for later tables.
- Track completed-block boundaries across incremental and full renders.
- Request scrollback reflow at answer completion when reference-link definitions are present, including definitions pending without a trailing newline.
## Testing
Add regression assertions and snapshots for completed tables entering scrollback while later tables remain mutable, and for late reference-link definitions resolving correctly at completion. Cover reflow requests with and without a trailing newline and reference handling with inline visualizations enabled.
GitOrigin-RevId: a6b2aac74496281495b53840bbb1daf06bef60d2
## What changed
Add `configured TUI mode` to the configuration details in human-readable and JSON doctor reports. Report `fullscreen` when `tui.fullscreen_transcript` is enabled and `scrollback` when it is disabled.
## Testing
Add an integration test covering both configuration values in JSON output and update the human-readable report snapshot to include the mode.
GitOrigin-RevId: beb62ddfa62a3516a64b5a69d5a41b257434f5d5
## Why
Account-update notifications include authentication mode and plan information but
omit the email, causing `/status` to lose the signed-in account's email after an
update.
## What changed
Fetch the ChatGPT account email asynchronously after account updates, with a
30-second timeout, without blocking terminal input. Apply the result only if its
request ID is still current, invalidating pending results on subsequent account
updates and disconnects.
## Testing
Extend the account-update test to verify that the email is restored and a stale
result is ignored. Update the status snapshot to include the account email and
plan alongside credits and limits.
GitOrigin-RevId: 202421f78f3d6a7b373194f9c65d1c22d70a04c1
## What changed
Allow the issuer `https://mcp.mercadopago.com/mcp` to use authorization endpoints on `https://auth.mercadopago.com` and token endpoints on `https://mcp.mercadopago.com` without issuer-bound callbacks. Remove the previous Figma exception.
## Testing
Update the provider-exception test to accept the Mercado Pago combination and reject lookalike issuer hosts, unrelated token hosts, and HTTP issuer and token URLs.
GitOrigin-RevId: 3838c7e4c32d6a2022f0011d6020e383035fe67f
Teach the issue labeler to suggest `dots` for issues about setting up
ChatGPT dots or managing their ongoing work. Exclude these issues from
the generic `agent` fallback.
GitOrigin-RevId: 6950c1bbde3aaf7f050e64484658f4ed1e4ae6e8
## What changed
Advertise `fileWriteStreaming` and support `fs/open` with `mode: "replace"` to create or truncate a file for writing. Implement `fs/writeBlock` with explicit offsets and nonempty chunks of up to 1 MiB, rejecting ranges beyond the signed 64-bit file offset limit.
Apply write sandbox permissions when opening writable handles, including when full-disk reads are allowed. Keep `read` as the default open mode.
## Testing
Add integration coverage for positional writes, chunk and offset bounds, replacement truncation, read/write handle permissions, and sandbox write restrictions. Verify that duplicate handle IDs and exhausted handle capacity reject replacement opens without creating or truncating files.
GitOrigin-RevId: 696ee6437dd5f5b69d5a7667dddea0ff44472094
## Why
Local secrets storage pulled in the unmaintained `proc-macro-error2` through `age` and `i18n-embed-fl`, requiring an exception for `RUSTSEC-2026-0173`.
## What changed
Upgrade `age` to `0.12.1` and update the Cargo and Bazel lockfiles. The updated dependency chain uses `proc-macro-error3`, allowing removal of the advisory exception from both `cargo-audit` and `cargo-deny` configuration.
GitOrigin-RevId: 7e18dec4d71d9260512f54fbfe71dbe4e6ee8a5d
## Why
The per-connection limit of 128 file read handles was checked only after opening the file, leaving pending opens outside the limit.
## What changed
Reserve a semaphore permit before polling the file-open future, counting pending opens and registered handles against the same limit. Release capacity when an open fails or is cancelled, or when a handle closes, even if a read still retains the file.
Use synchronous handle-table locks that never cross an await, and recheck duplicate IDs after opening to preserve the winning handle during concurrent opens.
## Testing
Add tests for stalled-open progress, pending-open admission limits, permit cleanup after failure or cancellation, capacity reuse while a file remains in use, and concurrent duplicate IDs.
GitOrigin-RevId: caabf38c74dda5951f2fc75234a7149daaa01263
## What changed
Expose `create_worktree`, `get_worktree_creation_status`, and `list_worktrees` through MCP when the worktrees feature is enabled for a trusted local project and attachment storage is available. Support both embedded and local daemon sessions.
Create worktrees asynchronously and attach them to the requesting task, with ownership and attachments retained across restarts. Default to the repository's remote default branch unless `ref` is supplied. Keep the task's working directory and execution environment unchanged, and leave uncommitted source changes in place.
Reject creation in ephemeral side conversations and explicitly untrusted source projects, reuse pending operations, and reject configured MCP servers that conflict with the TUI tools namespace.
## Testing
Add integration and model-request snapshot coverage for creation, polling, listing, attachment persistence across restart, task isolation, trust checks, namespace conflicts, and worker failure reporting.
GitOrigin-RevId: b6a57e92cf5f6fc51fd6d4028543d6fabaf5ac49
## Why
Permission shortcuts checked local configuration while the picker used the connected server's catalog and requirements. Shortcuts should respect the same server restrictions, including model-specific auto-review requirements.
## What changed
- Share a cached server catalog between the permission picker and shortcuts. Show the loading picker when no catalog is available and reuse an outstanding fetch.
- Clear the cache on session, account, working-directory, or connection changes.
- Give discovery RPCs distinct request IDs for each fetch and profile page so repeated requests after timeouts do not collide.
## Testing
Add coverage for loading and catalog reuse, managed permission restrictions, and refetching after disconnect. Update timeout coverage to verify that repeated discovery attempts use distinct IDs and each reports a timeout.
GitOrigin-RevId: 7d79874294136bfe3a654bb306eb7caf36d4df1e
## What changed
Add `codex tcp-tunnel --diagnostics-json` to emit versioned, newline-delimited JSON diagnostics on stderr. Records classify startup, CONNECT, transport, and control failures without exposing credentials, addresses, headers, or raw error messages. Rejected CONNECT records may include a validated `http_status`.
Distinguish terminal failures from recoverable stream and transport events, flush terminal records before returning a generic error, and preserve stdout readiness and credential acknowledgments. Keep human-readable diagnostics as the default and document the version 1 schema and consumer fallback rules.
## Testing
Add tests for bounded output, error-chain suppression, terminal flushing, control error classification, CONNECT status validation, legacy behavior, and flag parsing. Extend the reconnect test to exercise a rejected CONNECT followed by a successful connection in JSON mode.
GitOrigin-RevId: 350f67fe8e3f313e8a6d3bb0fd891952b77647fd
## Why
When Codex runs on Unix and launches a stdio MCP server on a Windows executor, explicit remote environment variables activate an allowlist based on Unix defaults. This can filter out Windows runtime and temporary-directory variables.
## What changed
Include `SYSTEMROOT`, `TEMP`, and `TMP` in the remote environment allowlist whenever explicit remote variables are requested.
## Testing
Extend the environment-filtering test to verify that `SystemRoot`, `TEMP`, and `TMP` survive alongside requested variables while unrequested secrets remain excluded.
GitOrigin-RevId: 059c9e23833be66aaf5b65ba5f95013f94f0f792
## What changed
Add `CodexThread::current_turn_model` to return the model slug selected for the named running turn's next step, independently of settings for future turns. Return `None` when the turn ID does not match, the task is cancelled, or the turn is no longer running.
## Testing
Extend the step-settings test to verify that the accessor ignores model changes for future turns, reflects active-turn model updates, and returns `None` for a mismatched ID or a completed turn.
GitOrigin-RevId: 2cae7c07fa761ed4d64befaa3419a2f9bce4b161
## What changed
Add `codex-cloud-client`, a reusable Rust client for `ThreadService.Resume` and live `ThreadService.Attach` over HTTP/2. Callers supply the native gRPC origin, bearer token, account ID, and `HttpClientFactory`.
- Reuse shared proxy, custom CA, and network policy handling for HTTPS. Reject redirects and allow plaintext HTTP only on direct loopback with unrestricted, unmanaged policy.
- Preserve notification and server-request protobuf payloads as opaque bytes and expose native gRPC status details while redacting credentials, payloads, and error details from diagnostics.
- Bound resume and attach setup to 150 seconds without retrying requests or imposing an idle deadline on live streams. Attach ends on its first error and provides no history or automatic reconnect.
- Select Rustls in `HttpClientBuilder::http2_prior_knowledge()` so HTTPS advertises `h2` through ALPN.
Include a standalone attach example and documentation of admission semantics and stream behavior.
## Testing
Add HTTP/2 fixture tests for protobuf framing, authentication metadata, status trailers, event preservation, malformed responses, stream cancellation, redirect rejection, and diagnostic redaction. Add checks for unsafe origins, network policy restrictions, and TLS `h2` advertisement.
GitOrigin-RevId: 55db70438bb5e59272c6995c67a46ced5fa28ff4
## What changed
Move the voice connection spinner into shared helpers in `codex-rs/tui/src/motion.rs`, keeping its 100 ms animation cadence and static reduced-motion glyph. The helpers handle frame scheduling, and `loading_glyph_with_delay` supports hiding the animated spinner until a specified delay expires.
GitOrigin-RevId: c4ebe5e6a33239999aab2f4432c9145432c8f4fd
## Why
Long drafts need to remain browsable while leaving room for the transcript. Remote image attachments also need to leave an editable prompt row visible.
## What changed
- Cap the fullscreen composer, including padding and hints, at two-thirds of the screen, with a minimum of eight rows when the screen allows.
- Support mouse-wheel browsing without moving the caret or changing transcript selection, search, or activity focus. Show arrows for hidden prompt rows and hide the cursor when the caret is offscreen.
- Resume caret following on editor input, paste, and external edits.
- Keep the selected remote image visible while reserving space for prompt text.
## Testing
Add regression tests and snapshots for fullscreen scrolling, caret restoration after navigation, paste and external edits, remote image navigation and deletion, resizing at scroll boundaries, and disconnected editing.
GitOrigin-RevId: 9a1e4ce14b3b3747e6d136207546327531339258
## What changed
Move footer property construction, mode resolution, hint overrides, quit shortcut hints, and custom footer height calculation from `chat_composer.rs` into `chat_composer/footer_state.rs`. Preserve existing behavior and expose the moved helpers to the parent module where needed.
GitOrigin-RevId: 4a23753ac1648352ab19d4bcc3da9f368c48f619
## What changed
Add the disabled-by-default `guardianv2_decisions_comparison` feature to run Decisions alongside Guardian V2 snapshot classification using the same policy and evidence. Initialize the comparison sampler with `CODEX_GUARDIAN_DECISIONS_API_KEY`.
Publish the baseline score before awaiting comparison results, and keep comparison results and failures from changing approvals. Apply Guardian's input token budget, skip conversation evidence, and cancel comparison work when the baseline classification is superseded. Record success, failure, and skip outcomes with bounded diagnostic reasons, including setup failures.
## Testing
Add lifecycle tests covering disabled comparison, disagreeing classifications, backend failures, unchanged published scores, matching policy and evidence, and rejection of over-budget requests before either backend sends them.
GitOrigin-RevId: 743d34c8ee440362da94f001058366027b39bd11
## Why
`thread/attachment/list` lists attachments for a known thread. Clients also need to find the threads associated with a given attachment identity.
## What changed
Add `thread/attachmentOwner/list` to return owning thread IDs and archive status for an exact `attachmentType` and `identityKey`. Support cursor pagination and an optional `archived` filter, including both archived and non-archived threads by default.
Wire the request through the thread store and update documentation, protocol schemas, and generated TypeScript and Python types. The lookup is limited to the configured thread store and reports current membership, not an atomic resource-cleanup check.
## Testing
Extend app-server integration tests to cover exact type-and-key matching, multiple owners, archive filtering, and invalid cursor rejection.
GitOrigin-RevId: 30f4a20e00243d0023246d465a9b95213b3adeb6
## Why
Reloading an unloaded root from a surviving child can supply the shared instruction wrapper already registered for that root. Replacing its underlying provider with that same wrapper makes instruction loading recurse into itself.
## What changed
Reuse the existing wrapper without replacing its provider when both are the same `Arc`. Continue to accept distinct replacement providers.
## Testing
Extend regression coverage to reload the root from a surviving child and verify that shared instructions still update. Check wrapper reuse, replacement with a distinct shared provider, and freezing the shared snapshot when switching to a provider that does not share with subagents.
GitOrigin-RevId: 7b6b2f9031f206e203f6fa14e1478a36b305ec39
## Why
Unread queue-only messages prevented idle agents from unloading, and sending a
message to an evicted agent reloaded its session. Pending mail should not require
an idle recipient to occupy a loaded thread slot.
## What changed
- Retain queue-only mail in an in-memory runtime mailbox when a session unloads.
Queue new messages for locally evicted agents without reloading them or
starting a turn.
- Add `AgentControl::take_mailbox` and `AgentControl::watch_mailbox` so sessions
can consume retained mail and react to host mailbox notifications.
- Preserve message order across eviction, reload, and subsequent follow-ups.
Keep agents with outstanding durable sleep or turn-triggering mail loaded,
and discard retained mail when an agent is removed or its tree shuts down.
## Testing
Add integration coverage for retaining mail across eviction, sending while
unloaded, and ordering messages around a follow-up after reload. Add a host
controller test verifying that mailbox notifications wake `wait_agent` and
that the message is delivered exactly once.
GitOrigin-RevId: 4b55647f9ee9d1aaf3753f0688863bda81617327
## What changed
Add `StateRuntime::list_thread_attachment_threads` to find threads by exact `attachment_type` and `identity_key`, including threads without previews. Return thread IDs and archive state, with filters for all, archived, or non-archived threads.
Order results by thread ID and bind pagination cursors to the attachment identity and archive filter. Add a database index on `(attachment_type, identity_key, thread_id)` to support the lookup.
## Testing
Add coverage for exact identity matching, archive filters, pagination, rejection of cursors reused with different lookup parameters, and membership updates after attachment removal or thread deletion.
GitOrigin-RevId: 21f32eb0cb1845a82d740d67b374080b6e12eb03
## Why
Subagents spawned without forked history do not receive their parent's client-defined dynamic tools, preventing them from using those tools for delegated work.
## What changed
Add the disabled-by-default `multi_agent_v2_dynamic_tools` feature flag. When enabled, fresh V2 subagents inherit the parent's dynamic tool definitions and persist them in session metadata.
## Testing
Add coverage for V1 and V2 feature gating, tool persistence, and a fresh V2 subagent calling an inherited tool and receiving its result without inheriting parent history. Update TUI assertions and a snapshot to reflect blank-line separation and question text in recovered answers.
GitOrigin-RevId: a17a16bf5570f54ce922c1521cffb883022354f2
## What changed
Add a Decisions sampler under `#[cfg(test)]` for Guardian's optional comparison classifier, without wiring a runtime caller.
- Encode text and inline image evidence as a `guardian_risk` choice request using `gpt-6-luna`, accepting only `low` or `high` responses. Reject the complete request when evidence cannot be represented.
- Bound concurrency to 16 requests, cancel the oldest unfinished request at capacity, and abort unfinished work when its owning task is dropped.
- Enforce a six-second HTTP deadline, an 8 MiB inline image data limit, and a 16 KiB response limit. Keep credentials and wire bodies out of errors.
## Testing
Add tests for the HTTP contract, unsupported evidence, inline image preservation and size limits, response validation, oldest-request cancellation, and capacity release when a caller is dropped while awaiting completion.
GitOrigin-RevId: e7209ca49a04505acf10ff1aeaca941514589e13
## Why
Bubblewrap consumes and closes the file descriptor for each `--ro-bind-data` mount. Reusing one descriptor across multiple file masks prevents the sandbox from starting.
## What changed
Open and preserve a separate `/dev/null` descriptor for each empty-file mask.
## Testing
Extend unit tests to verify distinct descriptors for multiple denied files and missing-path masks. Add integration coverage for exact-path and glob deny rules, checking that the sandbox starts, denied files remain unreadable and unwritable, and allowed files remain accessible.
GitOrigin-RevId: 85158c83699afd36bb7aca453b2652d777cf65e4
## What changed
- Centralize `windows-sys` at version `0.61.2` in the workspace and migrate dependent crates to it.
- Adapt Windows API calls to the updated handle, boolean, and type definitions. Replace custom handle owners with `OwnedHandle` and use `BorrowedHandle` where ownership stays with the caller.
- Add explicit wrappers for non-owning Windows handles passed between threads.
## Testing
Enable the MCP refresh cleanup test on Windows. Retain process handles to verify that a superseded MCP server stays alive during an in-flight call, exits after cancellation, and leaves the replacement running until shutdown.
GitOrigin-RevId: 86f53d9b300d13edff7154f4a7c32e34dacd2919
## What changed
Update `post_sampling_token_estimate_is_disabled_by_always_on_sinks` to register explicit event metadata with the subscriber and assert that its interest is `never`. This replaces the scoped default subscriber and global interest-cache rebuild with a direct check of the configured logging layers.
GitOrigin-RevId: 7c4ecd9c4adef148fd222394ad1ad326e8033d95
## Why
When a turn ends, unsent question answers are recovered into the main composer. Recovering only the answers loses which question each answer belongs to.
## What changed
Prepend each recovered answer with its question title as a Markdown blockquote. Separate questions, answers, and existing composer text with blank lines.
Sanitize question titles and limit them to 512 bytes at a UTF-8 character boundary, adding an ellipsis when truncated. Keep answer text untruncated.
## Testing
Add coverage for bounded titles, multibyte characters, control characters, and multiline question-and-answer submission. Update recovery assertions and snapshots for turn completion, failure, interruption, large pastes, and Vim undo.
GitOrigin-RevId: 141dacfb64bcad5fcabc5be217d2340ef7de1eb5
## Why
Environment changes and overlapping catalog refreshes can cause a step to use another step's selected plugins or executor skills. Model context and skill tools need to agree on the capabilities captured for that step.
## What changed
- Resolve selected plugins from each step's ready capability roots, honoring disabled plugins, and retain the snapshot with the step's extension data.
- Use that snapshot for skill attribution in World State and the first step's active-plugin telemetry.
- Return executor skill catalogs directly from refresh so overlapping requests render their own results while retaining thread caches.
## Testing
Add regression coverage for overlapping executor catalogs and environment changes during step preparation. Verify that `skills.list` retains the original step's skills, the next step advertises the new skills, and disabled executor and plugin skills remain absent from model context.
GitOrigin-RevId: 37d3cbe8c7e062fd06290aa985ada4d3b3462d43
## Why
Cygwin records installation timestamps in an unused Java truststore, changing Bazel action cache keys when the same tools are reinstalled.
## What changed
Exclude `cygwin/etc/pki/ca-trust/extracted/java/cacerts` from the generated `cygwin` filegroup in `.github/scripts/voice_windows_tools.py`.
GitOrigin-RevId: 8fdd910fadba7d977b45718546232652d073cdc8
## Why
Starting Find expanded the entire transcript into detailed mode. Searching hidden content should preserve the compact view and manually expanded activities.
## What changed
- Search full transcript content, including hidden live output, and temporarily expand only the current matching entry.
- Preserve manual disclosure state and retained text revisions while reading or selecting a match. Allow activity controls while reading results.
- Use `Enter` or `Ctrl+P` for older matches and `Ctrl+N` for newer matches, with matching footer hints.
## Testing
Add regression tests and snapshots for selective expansion, manual disclosures, hidden live matches, retained selections across updates and resizing, and Find in compact transcript overlays.
GitOrigin-RevId: 618ee47ba6c3f3a5138c9e3fe0961e7faa3383da
## Why
Closing Find previously restored the pre-search view, making it difficult to read a match and its surrounding transcript context.
## What changed
- Make `Esc` with a nonempty query close query editing while preserving the query, highlighted match, and expanded output. A second `Esc` returns to the latest output; `Ctrl+C` cancels Find and restores the pre-search presentation.
- Allow paging through surrounding context and loading older history without losing the query. Keep `Ctrl+N` and `Ctrl+P` available for match navigation, and reopen Find to edit the retained query.
- Show context above matches when space permits, preserve match layouts across resizing, and display navigation and history status while reading results.
## Testing
Add regression tests and snapshots for retained results, surrounding context, resizing, paging around live output, older-history loading, and footer status. Update interaction tests for the additional `Esc` transition.
GitOrigin-RevId: d822956d3c6ffab88fc1665ebdf0c86ccf110899
## Why
Legacy MCP tool discovery discarded pagination cursors, leaving tools on later pages unavailable.
## What changed
Pass `tools/list` pagination cursors to the existing collector in both legacy and modern protocol modes. Legacy discovery now follows subsequent pages and applies the same pagination limits and cursor validation as modern discovery.
## Testing
Extend integration coverage to both protocol modes, checking that tools from later pages reach the model and can be called successfully, while catalogs with oversized cursors are rejected. Update the legacy discovery test to expect an error for a repeated cursor.
GitOrigin-RevId: a6daa8034d2a403c1f2a5846e385789d8a620af7
## Why
A user restriction such as “Cancel the deployment” can fall outside the recent-message window after unrelated status questions. Guardian reviews need that restriction when assessing delegated actions.
## What changed
- Preserve root user messages during handoff relevance filtering, subject to the existing shared message cap.
- Apply handoff filtering during heartbeats while retaining saved heartbeat instructions and the active turn's trusted skills.
- Mark assistant context as incomplete when handoff filtering omits it, so ordinary user replies are not interpreted without their missing context.
## Testing
Add regression coverage for restrictions followed by status questions, bounded user history, omitted assistant questions, and trusted skills across first and repeated heartbeats. Update the delegation request-history snapshot.
GitOrigin-RevId: 67f77313572dc54225713cd7cdb90f06b0fbe030
## What changed
Add `CODEX_GUARDIAN_DECISIONS_API_KEY` to the non-inheritable environment variables and the HTTP header environment denylist. Case-insensitive filtering removes it from child process environments, including explicit shell policy and command overrides, and rejects its use through `http/request` header `value_env_var`.
## Testing
Extend regression coverage for inherited and overridden variables, mixed-case names, and HTTP header rejection before any network request is sent.
GitOrigin-RevId: 1adeef814fdccb2d6c77dd68f7a5dfcec0b41cc6
## Why
Concurrent Linux test spawns can inherit writable descriptors for executable fixtures, preventing those fixtures from being executed even after the writing test closes its descriptor.
## What changed
Replace direct executable fixture writes and copies across the Rust tests with `codex_utils_cargo_bin::write_executable` and `copy_executable`. These existing helpers complete writes and copies in separate processes on Linux.
Remove the empty temporary inode before creating fake bubblewrap executables, and stage tampered bubblewrap bytes in a separate data file before copying them into the executable fixture. Add the required test dependencies.
GitOrigin-RevId: c875c83088731a4933ef1574e8d79d8cecc12f54
## Why
Fresh TUI threads should use the app server's model settings unless the launch explicitly overrides them. Sending resolved configuration values in `thread/start` turns defaults into explicit overrides.
## What changed
- Track explicit launch choices for `model`, `model_provider`, and `model_reasoning_effort`, and omit unselected settings from the initial `thread/start` request.
- Preserve accepted model migrations as explicit model and reasoning-effort choices.
- Keep explicit profile launches on the existing resolved-configuration path.
## Testing
Update startup request tests to cover omitted defaults, CLI model and provider overrides, repeated model overrides, reasoning-effort overrides, accepted migrations, and explicit profiles.
GitOrigin-RevId: 4e2661ba42322a80e2b769a55c62f61a576762b0
## Why
The rolling retained-context window can change as assistant messages are added or evicted. Placing it before the transcript invalidates the reusable history prefix.
## What changed
Move retained user instructions and context after the transcript and action-specific attestations, immediately before the planned action in asynchronous Guardian requests. Keep synchronous section ordering unchanged.
## Testing
Extend the cache-prefix regression test to cover retained assistant message growth and eviction alongside changing attestations. Update app-server and async scorer assertions to verify the new request ordering.
GitOrigin-RevId: 59953d582d4b174ce3e083606626c7532ce0776d
## What changed
- Add `EmaAuthenticatedHttpClient` to cache and renew resource bearers, serialize concurrent renewals, and include authentication time in the request deadline. Confine bearers to the configured MCP endpoint and reject redirects.
- Return authentication-required errors for `401` responses without replaying MCP operations. Preserve a newer cached bearer when a delayed response rejects an older one.
- Add revocable request authority that cancels pending requests and ends response streams.
- Pin enterprise credentials to a persistent version advanced on save or deletion. Use short credential locks and invalidate rejected grants only when their record and version are still current, preserving newer logins.
- Hide keyring account identifiers from enterprise credential errors and traces while preserving authentication failure classification.
## Testing
Add tests for token expiry and renewal, endpoint confinement, redirects, request deadlines, revocation during renewal and streaming, delayed `401` responses, credential replacement and logout races, and credential error privacy.
GitOrigin-RevId: ee3e5cf7ecbba3d09e1ab29ed4fbb2a35eacc60d
## Why
Retaining process output, publishing events, and serving reads cloned the underlying byte buffers. Sharing those buffers avoids copying output bytes when chunks are cloned.
## What changed
Store `ByteChunk` bytes in `Arc<Vec<u8>>` and retain `ProcessOutputChunk` values directly. Add borrowed byte access for the MCP process transport while preserving base64 serialization and owned byte extraction through `into_inner()`.
## Testing
Add a unit test covering base64 serialization, deserialization, and independent owned bytes extracted from shared chunks.
GitOrigin-RevId: 6bba114af48424aa844487aa75163cfc604e0575
## What changed
Add a test that appends an original and updated name for one thread alongside another thread's entry. Verify that lookup returns the updated name and that removing the first thread's name entries leaves only the other thread's entry.
GitOrigin-RevId: cedf260a639f0c0e76aeda0d446559c3821bd911
Use `LazyLock` to compile the placeholder regex once and reuse it across
argument strings, avoiding repeated compilation during template expansion.
Preserve regex error propagation and placeholder substitution behavior.
GitOrigin-RevId: 2ac8aec86de3430335c068e47d09422dcd276f7c
## Why
Short sender replies such as `👍` need preceding assistant context to be understood during a delegation review. User messages alone omit that context.
## What changed
- Capture preceding assistant context alongside up to three recent sender user messages at delivery, for Guardian only. Label assistant messages as untrusted context rather than authorization or verified questions.
- Share the existing 900-byte budget per exchange, prioritize user evidence, and report unavailable assistant context.
- Recognize `cloud_threads.send_message` deliveries and accept both compact and indented delegation envelopes.
## Testing
Expand integration coverage for app, TUI, and cloud-thread deliveries, contextual replies, and budget-driven omissions. Assert that sender user and assistant context stays out of the delegated agent's prompt.
GitOrigin-RevId: 4eca369cbb30241635273f729dec81b78ea57faf
## Why
The asynchronous matcher can return results for the previous query while a new query is still running. Labeling those results with the latest query produces a mismatched search snapshot.
## What changed
Only report a file search snapshot when its pattern atoms match the currently requested pattern. Extract snapshot conversion into `snapshot::for_query`, which skips pending results from an older pattern.
## Testing
Add a regression test that changes the query from empty to `bet`, verifies that the old snapshot is withheld, and checks that the completed snapshot contains `beta.txt` with the expected match indices and counts.
GitOrigin-RevId: 01b62b822db69e15480d3233b66ec55c45646fad
## Why
`codex exec` and the TypeScript SDK need a way to request a Cyber access program for an individual turn. Resuming with an API key can also leave compaction using a saved program that the current credentials cannot access.
## What changed
- Add `--cyber-access-program` with `standard`, `daybreak_blue`, and `daybreak_red`, and expose the equivalent `cyberAccessProgram` turn option and `CyberAccessProgram` type in the TypeScript SDK.
- Apply explicit selections to new, resumed, and prompted fork turns. Override automatic Daybreak selection for that turn without changing the saved choice. Reject the flag for review and forks without a prompt.
- Filter Cyber programs by the built-in OpenAI provider when starting turns and restoring previous-turn settings for compaction.
- Allow previous-model compaction fallback with API-key authentication, comparing both model and program so a program change can trigger a retry with the current pair even when the model is unchanged.
## Testing
Add CLI help, argument parsing, exec, and SDK coverage for per-turn selection and unsupported commands. Extend core tests for API-key compaction retries, denied explicit selections, custom-provider filtering, remote compaction, and WebSocket response reuse.
GitOrigin-RevId: 586f25b621924f3bc509c9a39b39fe2020ff9cd2
## Why
Forcing `approval_policy` to `never` on temporary structured threads can trigger configuration warnings when managed requirements allow only `on-request`. These hidden threads also need to reject unexpected interaction requests without prompting the user.
## What changed
Inherit the app server's approval policy when starting temporary structured threads. Reject their server requests before dynamic tool handling or interactive TUI routing.
## Testing
Extend regression tests to verify inherited `on-request` approval without approval-policy warnings, and error responses for recap-thread approval and user-input requests even when the thread is marked active and primary.
GitOrigin-RevId: 2d0a071d3687742c83ba933a7ef1357feea53403
## Why
Deserializing keybindings through an untagged enum hides the specific validation error, making invalid `tui.keymap` settings harder to diagnose.
## What changed
Deserialize single keybinding strings and lists by value type so validation errors reach the user. Errors now retain the reason a binding is invalid and the affected configuration key, including when loading configuration for `codex mcp list`.
## Testing
Add TOML regression tests for unknown keys, invalid chord strokes, and overly long chords in both string and list forms. Add a CLI snapshot test verifying that `codex mcp list` reports the invalid keybinding reason and configuration key.
GitOrigin-RevId: 26e3dea93fc43db21e993ea5cf93df53ce93a43e
## Why
Executor skill reads need to use the environments and permissions captured for the current step, including newly approved grants. Cached continuation pages must remain bound to the filesystem and permissions that produced them.
## What changed
- Supply borrowed `EnvironmentAccess` to turn-input contributors and extension tools, with session and originating-turn grants already applied.
- Require executor skill reads to use filesystem access from an environment available to the callback, and replace separate optional read contexts with `SkillReadContext`.
- Bind skill pagination snapshots to `EnvironmentAccessKey`, which identifies the source filesystem and callback permissions.
- Route image-generation filesystem operations through the same accessor.
## Testing
Extend skill-read integration coverage to verify that a denied reference becomes readable after a turn-scoped grant is captured by the next model step. Update Windows coverage to verify that restricted reads fail when the executor cannot enforce a sandbox, and add a test requiring turn environment selection before exposing capability roots.
GitOrigin-RevId: 825b49302319965835d61c77fc5bcdb951e10543
## What changed
Replace the separate `WorldStateSection::snapshot` method with a typed `SectionTransition` returned by `render_diff`. Snapshot updates and model-context fragments are independently optional; omitting a snapshot preserves the stored comparison state.
Update all section implementations to use this contract, skip snapshot updates for unchanged sections where applicable, and cache the multi-agent usage-hint fingerprint.
## Testing
Adapt world-state and context-history tests to the combined return value, including an assertion that unchanged permissions return neither a snapshot nor a context fragment.
GitOrigin-RevId: 79c1977a87481009ff193ea4cce4546be87458fe
## Why
Background code-mode cells can continue running after a new turn starts. Looking up grants and strict review requirements through the active turn can make those cells lose their approved access or use another turn's permissions.
## What changed
- Keep turn-scoped grants and strict review state in `TurnContext`, retained by captured steps and background cells.
- Record permission responses against the requesting turn, including requests made after a later turn starts.
- Share live session-scoped grants across turns while keeping turn-scoped grants isolated.
- Use the originating turn's permissions and review requirements for tool execution, patches, MCP calls, file uploads, and terminal input.
## Testing
Add regression coverage for background cells retaining grants across turn changes, turn versus session scope, permission requests after the next turn starts, and strict review enabled while `write_stdin` is queued.
GitOrigin-RevId: 641502fbfd43553c2c42424d4aaa53ae8020c850
## What changed
Remove personality from TUI turn commands and cached thread session state, and stop applying personality from thread settings notifications. Send no personality override in `turn/start` requests.
Forward `personality` through session configuration only when explicitly supplied as a CLI override, rather than deriving it from the effective local configuration.
## Testing
Extend configuration override coverage to verify that `personality = "none"` is forwarded only when supplied through CLI overrides.
GitOrigin-RevId: bd3c3bacc90e0561016c0cac557eb1b0e50d32c0
## Why
Startup presentation needs client preferences before thread initialization establishes effective execution permissions. The startup header should not infer permission state from local configuration.
## What changed
- Load `LocalSettings` directly from bootstrap TOML, preserving preference defaults and overrides, accessibility settings, and audio settings that exclude project layers.
- Use those settings for first-frame presentation and pass `LocalSettings` plus the working directory to the startup draft instead of a full `Config`.
- Stop showing the YOLO indicator in the startup header while execution permissions are unknown.
## Testing
Update tests to compare bootstrap settings with resolved configuration, verify first-frame keybindings and paste preferences with an unresolved permission-profile parent, and snapshot the configured startup header. Adapt startup editor tests to the settings-based interface.
GitOrigin-RevId: f33cf8f42c53a9ddcbe0273491b5a849da9e6808
## What changed
Replace `https://chatgpt.com/codex/settings/usage` with
`https://chatgpt.com/settings/usage` in usage-limit errors, the `/status`
card, and backend banner actions. Credit purchase actions retain
`?credits_modal=true`.
## Testing
Update error-message assertions, banner action tests, status hyperlink
assertions, and TUI snapshots to expect the new URL.
GitOrigin-RevId: 1e1db971284a25a781120da30a6dea5ff9c3d957
## What changed
Add a selectable `daybreak` item to the status line and terminal title, including setup previews and terminal-title validation. Display `Daybreak on` when enabled for the thread and `Daybreak off` otherwise, including during side conversations.
## Testing
Add coverage for on/off rendering and side conversations, update setup preview snapshots, and verify that terminal-title diagnostics accept `daybreak`.
GitOrigin-RevId: b0b7a6f0ee0a107ba4ee2d56113a5b9b6ebd1d41
## Why
Cyber-policy refusal guidance did not distinguish whether Daybreak was on or off, and policy continuations and background task turns omitted `cyberAccessProgram`.
## What changed
- Show refusal guidance for the current Daybreak setting and offer eligible users an “Enable Daybreak” picker for their next request. Persist the selection without automatically retrying the refused request, and suppress the picker during history replay and when viewing parent-owned threads.
- Select and validate the cyber access program for policy continuations and background task turns using account eligibility, model support, and the thread's Daybreak setting.
- Resolve new background threads' Daybreak defaults from effective configuration unless launch flags or a selected profile explicitly override them. Use the target thread's saved setting for follow-up messages.
## Testing
Add unit, snapshot, and request-recording coverage for refusal guidance, picker behavior, continuation access programs, and background tasks retaining Daybreak after configuration changes.
GitOrigin-RevId: 94dee39c067e8eea5791cb31d5fe65fc600e5a18
## What changed
- Add `/daybreak` with account-aware help and availability messages for broader access for cybersecurity work.
- Save the selection in thread metadata and the `daybreak` default for new threads, restore it on resume, and confirm that it applies to new turns.
- Select `cyberAccessProgram` from the connected server's model catalog. Require a signed-in ChatGPT account, the OpenAI provider, and confirmed model support when Daybreak is enabled, including for faster-model retries. Keep Daybreak disabled for side conversations.
## Testing
Add tests for toggle persistence, turn access-program selection, unsupported-model rejection, side-conversation behavior, command help, and the resumed-thread banner.
GitOrigin-RevId: e3c028b0a6a8e0a862c16fdc766f374aae618ef1
## What changed
Select cyber refusal notices from the current model's `available_access_programs` for ChatGPT accounts using the OpenAI provider. Show Astra-specific guidance only when an Astra model offers standard cyber access without Daybreak access, and use the limited notice when Daybreak access is available. Otherwise, show application guidance.
Remove the separate account eligibility request, background prefetching, and notice cache.
## Testing
Update tests to cover catalog-based notice selection, missing model metadata, isolation from other models' access programs, and rendering the application notice for a cyber policy error.
GitOrigin-RevId: 88e9522bd6ece2d2b9caa6cff01a4178768babb7
## What changed
- Add the `daybreak` configuration key, defaulting to `false`, with per-invocation overrides such as `-c daybreak=true`.
- Resolve access programs from the model catalog, preferring `daybreak_blue` over `daybreak_red` when enabled and selecting advertised `standard` access when disabled for signed-in ChatGPT accounts. Require the OpenAI provider, a signed-in ChatGPT account, and a compatible model to enable Daybreak.
- Save the choice for new persistent threads and inherit it on resume and fork, including ephemeral forks. Explicit CLI overrides apply only to the current invocation.
## Testing
Add protocol tests for advertised-program selection and exec integration tests for account and provider restrictions, saved choices, ephemeral forks, and invocation-only overrides.
GitOrigin-RevId: ac955f08b5a891e720cfc5f67fabb7b0f6d32bb8
## Why
The Windows shared daemon rejects elevated launches so shared clients cannot inherit administrator privileges. Local TUI sessions launched as administrator should still be able to start.
## What changed
Select embedded mode before daemon discovery or startup for elevated local Windows sessions. Show a startup warning explaining that the shared background server is disabled and that restarting Codex in a non-elevated terminal enables it. Record `elevated_windows` as the server selection reason.
## Testing
Add Windows integration coverage for elevated normal, `resume`, and `fork` launches without creating daemon directories, and verify that explicit daemon `start` and `restart` still reject elevation. Add a snapshot test for the startup warning in the warning center.
GitOrigin-RevId: 89594e86d6ee19b080dfb11553cee8676395f188
## Why
Skipped report attachments lacked diagnostic logs, and upload failures logged only the HTTP status. Transport error strings can also contain credential-bearing URLs.
## What changed
- Log why attachments are skipped, including missing rollout files, non-regular files, size limits, rate limits, and upload deadlines.
- Log attachment failures at error level with the error chain and available HTTP status.
- Replace `RouteAwareRequestError` details with the failure class and timeout, connection, request, and body flags before logging, avoiding credential-bearing transport URLs.
GitOrigin-RevId: 1bfd1cc74137ea83d05098e9dbf58ed7b62385cc
## Why
Windows processes hold their working directory open for their lifetime, and sandbox setup may broaden its ACL. Managed children should avoid pinning the launching project's directory or changing permissions on the private daemon state directory.
## What changed
Create a `workdir` subdirectory alongside the PID files and use it as the working directory for both the managed app-server and updater on Windows.
## Testing
Add a Windows regression test covering both managed children. It verifies that relative files land in `workdir`, the state directory still passes private-directory validation, and stopping each child removes its PID file.
GitOrigin-RevId: 12ca95463ff3c80899a5b1a8800fead849f48017
## What changed
Return snapshots and model-visible fragments together from world-state rendering, and use those snapshots for history baselines, step updates, compaction, and new context windows.
Update `WorldStateSectionContribution` so its renderer returns an optional replacement snapshot and an optional fragment. A missing snapshot preserves stored section state, even when retained history requires a fresh render; a null snapshot removes the section. Derive step patches from the history baseline rather than a separately captured live world state.
Adapt skills and Git attribution contributors to the new contract.
## Testing
Add coverage for skipped snapshot updates, explicit section removal, changed-state patch replay, unchanged-state deduplication, and matching live and persisted checkpoints when starting a new context window.
GitOrigin-RevId: af71606a278358ae937853cb76e8a019a501408e
## What changed
Add `turn_extension_init` to thread startup and settings, and expose `WithTurnExtensionData` for turn input, recovery, and settings requests. Accept or reject data updates together with the request that supplies them.
Each new turn captures the configured data, including automatically started turns. Accepted steering updates the data for future turns while preserving the running turn's capture. Plain requests preserve the configured data; an empty initializer clears it. The data is not persisted and must be supplied again on cold resume.
Expose `current_turn_extension_data` to retrieve typed data only when the requested turn is still running and has not been cancelled.
## Testing
Add an integration test covering initial capture, accepted and rejected steering, inheritance by an automatic turn, clearing future data without changing the active capture, and rejection of lookups for an earlier turn.
GitOrigin-RevId: dd81eda3e32c7b62d783c772221858f4c0e68264
## Why
Detached launches truncate stderr logs, losing details from previous failures. Updater handoffs can also leave existing writers with stale offsets after truncation.
## What changed
- Record daemon lifecycle and update stages with timings, outcomes, and typed OS errors, omitting error messages and context.
- Preserve the last 256 KiB of nonempty stderr logs before truncation and use append handles to prevent gaps during handoff. Preservation failures do not block launch.
- Attach current and previous updater log tails when log inclusion is enabled for a report, with a 512 KiB total limit and legacy filename fallback. Skip missing, empty, and nonregular files.
## Testing
Add regression coverage for diagnostic error redaction, bounded log preservation, append behavior during handoff, attachment selection, and updater logs in captured report uploads.
GitOrigin-RevId: 918317022ab9dcfd1b13d676872706c77e9ffbb2
## Why
Mixing every input on a multichannel audio device can include playback channels in microphone capture. Selecting only microphone inputs keeps those playback channels out of the captured audio.
## What changed
- Add `audio.microphone_channel` with one-based channel numbers, accepting a single value or an array such as `[1, 2]`. Leaving it unset preserves mixing of all inputs.
- Add an input-channel picker for the selected microphone when it has at least three channels. Require a nonempty selection and save it locally for the next voice conversation.
- Average only the selected channels, deduplicate selections, and reject empty or unavailable selections without falling back to other inputs.
- Clear saved channel selections when saving an input device and report configuration overrides that prevent the reset from taking effect.
## Testing
Add regression coverage for excluding playback channels, sample conversion, subset mixing, invalid selections, configuration loading, local persistence and overrides, and picker selection and cancellation. Update UI snapshots and verify channel selections are passed to the voice helper.
GitOrigin-RevId: 99960dcfa7b10cf38270768a90bb84a4be95a406
## Why
When saving the default service tier fails, users need the underlying configuration error and guidance on how to retry without interrupting their task.
## What changed
Format the error with `format_config_error` and explain that the task can continue. Tell users to resolve the error, then switch to a different tier and back to the desired tier to retry saving the default.
## Testing
Add a snapshot assertion for a rejected service tier save caused by malformed configuration, covering the detailed error and recovery guidance.
GitOrigin-RevId: d666f7915f185d219396d24034412b175c49173e
## Why
Managed daemons and updaters can outlive their launching directory. Restarts and updater replacement need to keep working after that directory is removed.
## What changed
- Share working-directory preparation between background launches and Unix updater re-execution. Fall back to the daemon state directory when the Unix working directory is missing, while retaining usable working directories and the existing Windows state-directory behavior.
- Preserve configured `CODEX_HOME` paths and valid symlink aliases, and make certificate and AWS environment paths absolute before launching children. Handle both `npm_config_cafile` and `NPM_CONFIG_CAFILE`, preserving supported home-relative values.
- Log warnings when scheduled daemon updates fail.
## Testing
Add Unix regression coverage for restarting the daemon and updater from a deleted working directory, and for updater re-execution with preserved environment paths, `CODEX_HOME` symlink aliases, and a Linux non-Unicode home path.
GitOrigin-RevId: f45aefd8ff060adc6e025badf0bb8c81f842bf88
## What changed
Add `FsHelperOpenParams` with only a `path` field and use it for the exec-server filesystem helper's `fs/open` requests. Replace reuse of `FsReadFileParams`, removing unused read-file options from the open request type.
GitOrigin-RevId: ca84447d06fbf391cc5ad189ac6c46e6aeaa1f63
## What changed
Add the experimental `account/bedrock/checkGovCloudRequirements` RPC so clients can check the active Bedrock configuration after login or setup. It returns `isGovCloud` and `shouldWarn`, warning for GovCloud when managed requirements lack API-only login or enabled application network restrictions with an explicit allow entry for the active endpoint domain.
Reload configuration and requirements on each check while preserving the current session's authentication. Official Bedrock endpoint hostnames determine the region; otherwise, resolve it using the current authentication state. Non-Bedrock providers and commercial regions return both fields as `false`; configuration and region resolution failures return RPC errors. The check is advisory and does not block login or certify the entire network configuration.
## Testing
Add integration coverage for configuration and requirements updates without a restart, login changes, unreadable saved credentials, Mantle and Runtime endpoints, custom proxies, official endpoint region precedence, and invalid requirements.
GitOrigin-RevId: 24bfa91326cf5c73ada176c47351445de91b60a0
Stop adding an informational message to chat history when `open_url_in_browser` succeeds. Continue displaying an error when opening the browser fails.
GitOrigin-RevId: 28d33917c1a2e354017470e785e44aa0032c3b46
## What changed
Expose `ThreadManager::request_agent_tree_shutdown` and an `AgentTreeShutdown::wait` handle. Requests reject new starts in the shared runtime, cancel pending startup, and signal every session in that tree, including delegates outside the thread registry. Waiting covers admitted operations and session teardown, and reports cleanup or persistence writer failures. Other root trees remain unaffected; registry removal and persistence handoff remain caller responsibilities.
Retain tree membership through startup, cancelled spawn cleanup, residency eviction, and completion watchers. Release persistence resources before returning startup failures, and stop completion watchers during tree shutdown without reporting shutdown as a child result.
## Testing
Add coverage for tree isolation, children removed from the registry, delegate teardown, cancellation during required MCP initialization, aborted teardown, persistence writer failures, and successful retry after a failed resume releases its writer.
GitOrigin-RevId: a109e25adf23d20baf7595891099947050c6b6b5
## Why
Codex rejected `us-gov-east-1` and `us-gov-west-1` as unsupported Amazon Bedrock regions.
## What changed
Accept both GovCloud regions and construct their regional Bedrock Mantle endpoint URLs.
## Testing
Extend the endpoint URL unit test to cover both GovCloud regions alongside the existing `ap-northeast-1` case.
GitOrigin-RevId: ef9ca83fa7b73af1df100fcae722e24edac38643
## Why
Shadow skill selection runs synchronously during turn input construction, making turn preparation wait for experimental rankings.
## What changed
Run ranking on background blocking workers with a process-wide limit of two concurrent rankings. Wait for capacity in the background and hold each slot until its blocking worker finishes, even if the async evaluation is cancelled.
Freeze catalog, query, and relevance history at turn start. Record eligible invocations immediately for future turns, then score queued observations against the frozen rankings once they are ready, including observations queued before the turn state is dropped.
## Testing
Add tests for turn preparation and history updates while ranking is blocked, deferred invocation scoring against each turn's history, and shared ranking capacity that remains occupied until cancelled workers finish. Update existing metric assertions to collect asynchronous observations across snapshots.
GitOrigin-RevId: f7776e9aaeb45d3a792de167abbe35f7ec5a513e
## What changed
Register `fs/writeBlock` and require filesystem initialization before handling it. Validate the file handle ID, then return an invalid-request error stating that writable file streams are unsupported.
GitOrigin-RevId: 13440e497a88ca6505ee60d95bbb771d3cae06b8
## Why
Without a UI flush tick, expired paste detection can cause Enter to be treated as part of a paste instead of submitting buffered input.
## What changed
Flush due characters and paste buffers before classifying Enter during submission, including in Vim insert mode. Preserve the buffered text when submission is blocked for a parent-owned thread.
## Testing
Add regression tests for held characters and buffered bursts with and without Vim mode and parent-owned threads, plus a snapshot test for Enter submitting expired input in Vim insert mode.
GitOrigin-RevId: 1d0d309b57e9d2151e0d9c1774a3401d05413d3c
## Why
Explicit launch permissions such as `--yolo` can be lost during reconnect recovery, causing subsequent input to use different approval and sandbox settings.
## What changed
Remember explicit local launch approval policies, approvals reviewers, and permission profiles at startup and when creating new sessions. Restore the approvals reviewer independently of profile overrides during reconnect recovery. Keep constrained profiles that cannot be expressed through legacy turn parameters under server control.
## Testing
Add regression coverage for `--yolo` across new sessions and reconnects, later permission-picker choices, reviewer-only overrides, and server-owned constrained profiles. Extend the reconnect integration test to submit the preserved draft and verify its approval and sandbox settings.
GitOrigin-RevId: 7a77dc41b2a357ab17fec9ba6cb2361f4a8f4aa5
## What changed
- Mark `api_key_model_discovery` as stable and enable it by default, while preserving explicit user opt-outs and provider catalog requirements.
- Fall back to bundled models when discovery is disabled at runtime, including when a remote catalog has already been loaded.
## Testing
Extend model-list coverage for default enablement, app overrides, and user configuration precedence. Add a regression assertion that runtime opt-outs hide loaded catalogs without additional fetches, and update daemon compatibility tests for the new default.
GitOrigin-RevId: feaf732757792cc58063f21a5327d0e633f079f4
## Why
New error variants should not prevent older clients from handling app-server errors.
## What changed
- Deserialize unknown `CodexErrorInfo` strings and objects as `Other` in Rust, while preserving known variants and the `"other"` serialization.
- Allow arbitrary strings and objects in the exported JSON schemas and TypeScript type.
- Update Python SDK generation and generated models to accept unknown error strings and object payloads.
## Testing
Add Rust tests for `"other"` round trips, unknown string and object fallbacks, known structured variants, and rejection of null, boolean, numeric, and array values.
GitOrigin-RevId: 40c17896019924b2ef7970ee2205ea0154d0d1b3
## Why
Older executors can ignore the file open mode and silently return a read-only handle for a writable open.
## What changed
Add `ExecServerClient::fs_write_block` and require the `file_write_streaming` capability for both block writes and `FsOpenMode::Replace` opens. Return a protocol error before sending either request when the executor lacks support, while allowing read-only opens.
## Testing
Add a WebSocket regression test verifying that unsupported writable opens and block writes are rejected locally and read-only opens still reach the executor.
GitOrigin-RevId: f206e1da80c12af76ead14c75f8ffe71f82cce89
## What changed
Render Control, Shift, and Alt as `⌃`, `⇧`, and `⌥` on macOS, and Control as `^` on Linux. Keep textual modifier labels on other platforms.
Route hard-coded shortcut hints through the shared key-label formatter so footers, overlays, pickers, and transcript notices use consistent notation.
## Testing
Update modifier-combination and chord label assertions, along with rendering snapshots and narrow-layout expectations for the shorter hints.
GitOrigin-RevId: 0d20fa218e4a11dfe7a81c8de64f8d25e093af03
## What changed
Pin `dtolnay/rust-toolchain` to a revision from `master` in the argument-comment lint package CI and release build workflows. Both continue to request `nightly-2026-08-20`.
GitOrigin-RevId: 63801f669b91d4bfa1d69fc05d728d838ca8add0
## Why
A saved side conversation transcript can outlive its ephemeral server thread. The resulting `turn/interrupt` error prevented side conversation cleanup and blocked archiving the parent thread.
## What changed
Treat the specific `thread not found` interrupt error as successful interruption for replay-only side conversations, allowing unsubscribe and local cleanup to finish. Continue sending interrupt requests because replay-only conversations may still be running after reconnect.
## Testing
Expand archive lifecycle coverage for local daemon and remote server connections to include live side conversations, replay-only conversations with existing threads, and replay-only conversations whose threads are gone. Assert that interruption, unsubscribe, archiving, and local cleanup occur.
GitOrigin-RevId: 0528c9f5b5278931fd3a7941073071117f2f3612
## Why
The TUI unconditionally forwarded its resolved `web_search` mode, allowing implicit client settings to replace server defaults or saved thread settings.
## What changed
- Forward `web_search` on thread start, resume, and fork only when the winning choice comes from session flags or a selected profile.
- Translate legacy search feature flags into a canonical `web_search` override while preserving precedence, and remove those flags from forwarded feature overrides.
- Honor shared feature requirements for embedded sessions while letting remote servers enforce their own requirements on explicit search choices.
## Testing
Add coverage for configuration origins, canonical and legacy search precedence, and embedded versus remote feature requirements. Extend the Responses integration test to verify that a remote server's live search setting survives thread start and resume when the client's configuration disables search.
GitOrigin-RevId: c714f9cf0321aca9a5fa292a350720af5a2d02d4
## What changed
Return `Arc<EnvironmentInfo>` from `ExecServerClient::environment_info()` so repeated reads and cloned clients share cached metadata without cloning its contents. Wrap metadata from initialization and lazy RPC fetches in `Arc`, while preserving the owned return value in `LazyRemoteExecServerClient`.
## Testing
Extend the cache test to assert pointer identity across cloned clients for both initialization-provided metadata and lazy fetching after connecting to a legacy server.
GitOrigin-RevId: 3f56f4d51a4aebc0c4821c0b128a70efb23933d4
## Why
Guardian review continuations can repeat retained-instruction omission notices even when availability has not changed. When retained context becomes complete, earlier notices also need to be superseded explicitly.
## What changed
Track delivered user-instruction and assistant-context omission states in host metadata scoped to the retained-instructions section. Suppress redundant notice-only sections when the state is unchanged, and emit an availability-change notice when an earlier omission clears, including when no retained originals remain.
Treat missing delivery metadata as unknown. Matching notice text in coalesced tool output cannot establish host delivery, and incomplete history entries discard omission delivery proof.
## Testing
Add coverage for repeated notices, independent histories, availability recovery, and matching notice text in multimodal REPL output. Extend app-server review-continuation tests to assert that each effective classifier context contains the retained user-instruction omission notice exactly once.
GitOrigin-RevId: c6d52dd1dafb284af34b46174aecc7c8cc9b8404
## Why
Retained Guardian classifier conversations already contain previously delivered synchronous reviews. Appending those reviews again repeats evidence and consumes input budget.
## What changed
Track each review completion with a stable identity in host-only history metadata. Filter already delivered reviews before composing and budgeting continuation input, while preserving distinct completions even when their text is identical.
Fresh conversations receive the review evidence again, and shortened messages no longer count as complete delivery. Delivery metadata stays out of model requests.
## Testing
Add coverage for delivering retained reviews once, appending newly completed reviews, restoring evidence after failed streams, and retaining reviews when history lacks complete delivery metadata.
GitOrigin-RevId: b8d58ffdd7d9c484676af707c65fa50020aae73c
## What changed
- Add `features.guardianv2.async_classifier_mode` with `snapshot` and `conversation` modes. Local configuration overrides model defaults; snapshots remain the fallback.
- Retain completed classifier requests and responses in conversation mode, appending transcript deltas without repeating previously delivered user instructions.
- Rebuild retained history when authorization, classifier instructions, or parent compaction changes, after an incomplete response, or when the next request exceeds the configured token limit. Add `async_classifier_conversation_token_limit`, defaulting to 100,000 tokens, while preserving the model's input limit for fresh requests.
- Serialize conversation requests in observation order, bound outstanding work, and reject stale work after authorization changes or thread shutdown. Record retained and new input token costs.
## Testing
Add tests for configuration precedence, history reuse and resets, ordered admission, queue overflow, and stale or stopped requests. Exercise the approval matrix in both modes, including resume, fork, mandatory review, authorization changes, and stream failure after an early score.
GitOrigin-RevId: 35b9800104648cde4f467086e678dee12458c3e5
## What changed
- Add request preparation that preserves committed classifier history and appends transcript deltas, filtering instructions and images already delivered. Account for the complete input budget before transferring history; rejected requests leave the checkpoint and cursor intact.
- Add retained sampling that publishes the early score while collecting completed assistant output and encrypted reasoning for reuse. Preserve item IDs and input metadata, and discard unusable history without retracting an already published score.
- Keep the existing snapshot sampling path and share input preparation and execution with the new retained path. Retained sampling is not yet wired into the active backend.
## Testing
Add coverage for transcript and image deduplication, immutable history prefixes, budget boundaries, rejected preparation, WebSocket output retention, and retention failures that preserve the early score.
GitOrigin-RevId: 0fa33db8b8ea4483eb64d75e207690f1d349123b
## What changed
Remove the repository-root `AGENTS.md` from `codex-rs/core` test data and from the root Bazel `exports_files` list.
GitOrigin-RevId: 644052d50f79b4c798baf40e53aab824f0fd73c3
## What changed
When the model catalog is provided in context and model overrides are exposed, tell V2 `spawn_agent` callers to inherit the current model unless the user explicitly asks for a different model. Include this guidance even when spawn metadata is hidden.
## Testing
Extend tool-description tests to cover hidden metadata with both inline and context catalogs, and update request-level assertions for V1 and V2 model override guidance.
GitOrigin-RevId: b70b0f09b0b5987a0eccba578196b8ef7cee4baf
## Why
Naming a paginated thread before its first turn must make it durable so it can be resumed immediately and after an app-server restart.
## What changed
Persist the live rollout before updating name metadata in SQLite. Propagate persistence failures before saving the name.
## Testing
Add thread-store tests for empty-thread persistence and failure handling, plus an app-server regression test that resumes a named empty thread before and after a restart and completes its first turn.
GitOrigin-RevId: 2f7556c7de65f6a86177130c39e1a17951496931
## What changed
Register `browser_annotation_api` as a stable, default-enabled feature intended for requirements rather than user configuration. It controls websites opening and customizing annotation tools in desktop apps, independently of ordinary user-driven annotation.
Add the key to the configuration schema, extending the browser requirements support introduced in https://github.com/openai/codex/pull/18956.
## Testing
Extend `browser_feature_requirements_are_valid` to verify that enterprise requirements setting `browser_annotation_api = false` disable the feature.
GitOrigin-RevId: 8c7bb65932e08560040958b4472fe45f6d1c916f
## Why
Switching to a fork can interrupt approval routing for source and child threads that remain on a local daemon or remote app server. Their pending requests and event listeners need to survive the switch.
## What changed
- Retain background request routing and event listeners for tracked threads when switching to a daemon-backed fork, preserving pending approvals without duplicating them.
- Register the source thread before the `fork_thread` tool creates a fork so its requests remain routable during the operation.
- Route requests for the currently viewed thread to the active UI, even when that thread is also tracked in the agents overview.
## Testing
Add regression coverage for local daemon and remote forks retaining source and child threads, replaying pending requests when returning to the source, and displaying active-thread file-change approvals. Verify that embedded forks still discard the source thread state and that `fork_thread` registers its source before issuing the fork request.
GitOrigin-RevId: 63139e2b9a6eff373ab05a31e0140a432ce47389
## Why
Failed shell snapshot captures could leave processes launched by shell startup files running after the capture ended.
## What changed
Run each Unix shell snapshot capture in its own process group and kill that group on failure, timeout, or cancellation. Keep the capture leader unreaped until output and exit status are validated so its process group ID cannot be reused during cleanup. Preserve startup helpers after a successful capture.
## Testing
Add regression coverage for startup child cleanup after nonzero exits, invalid output, cancellation, and timeout, alongside fallback and retry behavior. Verify that successful captures preserve delayed startup output and background services and reuse the cached snapshot.
GitOrigin-RevId: a56ef5d8615325952bdc8bb78727de1559e7e9c7
## What changed
Capture each environment's effective Windows sandbox backend in the MCP runtime and include it as `useMxc` in sandbox state metadata for supporting servers. Use the server's captured environment selection, including local fallback, so the local MXC preference does not leak into attached environments. Default missing backend information to `false`.
## Testing
Extend tests to cover MXC metadata handoff, attachment isolation, local fallback without a selected local environment, and preservation of captured backend settings across runtime refreshes.
GitOrigin-RevId: f559bffeff383838334e5a475b1eab608d571fa1
## What changed
- Add `read` and `replace` modes to `fs/open`, defaulting omitted modes to `read` for existing callers.
- Define `fs/writeBlock` request and response types for offset-based writes, with a maximum decoded chunk size of 1 MiB.
- Add the `fileWriteStreaming` capability, defaulting to `false`. Keep writable streams unsupported in the server and explicitly reject replacement opens.
## Testing
Add a protocol test verifying that legacy `fs/open` requests without a mode deserialize as read-only opens.
GitOrigin-RevId: 4d3997717e821cd1f62df12a03c8eec36332a66d
## What changed
Fetch optional security setup notices asynchronously for local ChatGPT sessions using the OpenAI provider. Verify that saved credentials match the connected app server, ignore stale account responses, and validate notice text and HTTPS actions on `chatgpt.com`.
Show notices as dismissible inline banners with a browser action, while giving applicable usage banners priority. Preserve notice state and dismissal across thread changes, reconnects, and banner replacement for the same account and user.
## Testing
Add authenticated HTTP fixture tests, notice validation tests, and TUI tests covering stale responses, dismissal persistence, usage banner priority, browser actions, and wrapping in narrow terminals.
GitOrigin-RevId: b8635fcf6a26b42b6a06640601c8517d8d5e47e8
## What changed
Allow API-key sessions using the OpenAI provider to forward explicit cyber access programs when `features.api_key_cyber_access_programs` is enabled, regardless of `features.api_key_model_discovery`.
## Testing
Expand the app-server test to cover all four combinations of the two feature flags, checking forwarded programs and failures when forwarding is disabled. Default the API-key test helper to model discovery disabled.
GitOrigin-RevId: f9cf1d2bd7c231645d50178cc6721b55a8d63268
## What changed
Delete the root `AGENTS.md`, the skills under `.codex/skills/` and their supporting scripts, tests, and references, and `.codex/environments/environment.toml`.
GitOrigin-RevId: 555482804c79d17f9aa5587c4d26ea03337db8d9
## Why
Token-budget truncation uses byte counts to estimate tokens, but previously scanned the entire string to count characters, including the discarded middle.
## What changed
Use UTF-8 boundary lookups to select the retained prefix and suffix for token-budget truncation. Skip character counting for a zero-token budget and defer it to paths that need character counts.
## Testing
Add regression coverage for multibyte characters crossing both retained boundaries, checking the truncated output and original token estimate.
GitOrigin-RevId: 37fee0c8d4ede8e74b491d3d641b0ea0e9003dd4
## What changed
Preserve the underlying error in `LocalStateDbStartupError` and use its error chain to decide whether CLI startup failures qualify for automatic database backup and recovery.
Replace corruption checks against error-message text with SQLite result-code classification, including SQLx extended result codes and directly wrapped `SqliteError` values.
## Testing
Update the embedded startup corruption test to verify that the startup error retains a detectable SQLite corruption cause and the failed database path.
GitOrigin-RevId: 6e8ecd0ee67f3c239183ddea3fc75c4e4cd5744a
## Why
Session index updates perform synchronous file I/O and wait on a blocking mutex inside async functions, blocking runtime threads.
## What changed
Run appends and thread-name removals in `spawn_blocking` workers. Acquire a Tokio mutex before dispatch and keep its owned guard in the worker so queued and running updates remain serialized even if the awaiting task is cancelled. Move the lookup's file-existence check into its blocking worker as well.
## Testing
Add tests for lock retention after cancellation of running and queued updates, write ordering after cancellation, and removal that preserves other thread names and malformed lines.
GitOrigin-RevId: 368745d8e5bbf24c527facc0a62ddd0fb76f0ffb
## What changed
- Move the lint to `nightly-2026-08-20` and Dylint `6.1.0`, updating CI, release artifacts, Bazel configuration, and installation instructions.
- Adapt to the updated rustc and Clippy APIs, including resolving `Option::None` through type aliases when checking for uncommented arguments.
- Set the `chatgpt` crate's `recursion_limit` to `256`.
## Testing
Extend the UI fixture to expect an uncommented-argument warning for `OptionalString::None`, where `OptionalString` aliases `Option<String>`.
GitOrigin-RevId: 34e1b173972f0bfa9b6c8fd3342ca652539efe2f
## Why
Publishing an older alpha or alpha hotfix can overwrite npm dist-tags that already point to a newer release.
## What changed
Check each package's current npm dist-tag before publishing an alpha release, using the existing release version comparison and workflow concurrency lock. Handle `alpha` and platform-specific tags independently for Codex, the SDK, and the responses API proxy.
When the release does not advance the current version, publish under `release-<version>-<tag>` to keep it installable without changing the alpha or `latest` tags. Abort publishing if the registry lookup fails.
## Testing
Add unit tests for package and platform tag selection, older releases, dotted alpha hotfixes, missing tags, and registry lookup failures.
GitOrigin-RevId: 9c0edec1149bf78c01aac0f700e963630316eaea
## What changed
Rename `file_read` to `file_handle` and `FileReadHandleManager` to `FileHandleManager`. Update the filesystem handler field, handle ID validation helper, and related constants to use file handle terminology. File operations, limits, and error messages remain unchanged.
GitOrigin-RevId: 25ad81a917386da23fd42ecff79bd47a482ce430
## Why
A database can open successfully while containing corruption that startup previously missed. Detecting it before runtime initialization completes allows recoverable databases to be rebuilt while preserving the damaged files.
## What changed
- Run `PRAGMA quick_check(1)` when opening writable databases, with a 100 ms scan budget. Share attempts across cloned `SqliteConfig` instances by file identity so repeated opens skip validation and replacement files are checked again.
- Back up and rebuild runtime databases that support recovery. Report corruption without rebuilding thread history or other databases without an automatic recovery policy. Treat interrupted or locked checks as incomplete rather than confirmed corruption.
- Collect startup backups across recovery retries and include their locations in the app server warning. Explain that saved conversations can restore the thread list and history, while some database-only metadata may be unavailable.
- Record confirmed corruption in `codex.sqlite.corruption.count`.
## Testing
Add tests for recovery policies, backup preservation, validation caching and concurrency, cancelled and interrupted checks, and locked databases. Add app server coverage for recovery warnings and saved conversation restoration, a TUI warning snapshot, and message board post preservation.
GitOrigin-RevId: 43e26328888e0301def642d69bd324acee867566
## What changed
Run direct `read_file` operations in a blocking task with bounded read chunks and cancellation checks. Dropping the async caller cancels further reads between chunks. Preserve the 512 MiB size limit, symlink-following options, and regular-file validation.
## Testing
Add regression coverage for 4 MiB reads and oversized-file rejection with both symlink-following options, cancellation after the first chunk, and FIFO rejection without waiting for a writer.
GitOrigin-RevId: 19f2816de15a03bd89b463de6b002367e6a692a9
## What changed
Move directory enumeration and candidate metadata lookups into blocking workers, batching updated-time candidate collection into one worker per scan. Check cancellation between entries and metadata lookups so dropping the async waiter stops further scanning.
Share synchronous rollout metadata resolution with the async helper, preserving plain-file precedence over compressed siblings. Retain scan limits, stable file ordering, and directory-level early stopping for creation-time listings.
## Testing
Add tests for cancellation during directory enumeration and candidate discovery in both flat and date-partitioned layouts, including plain-sibling metadata precedence and filtering of unrelated files, directories, and symlinks.
GitOrigin-RevId: 324289003b29a7d2b3220da03e3c002ab5e23eec
## What changed
Run rollout file opening, metadata lookup, seeking, reading, and record
projection together in a single `tokio::task::spawn_blocking` call. Use
synchronous file I/O in `read_projection_steps_sync` and carry the current
tracing span into the blocking task.
GitOrigin-RevId: a231a8b9a328f6d2e2095a29cde1718ccb6b3901
## Why
Compressed snippet searches schedule a blocking task for every line read. Keeping the scan on one worker avoids repeated task scheduling.
## What changed
Use `RolloutLineReader::find_map` to scan compressed rollouts on a single blocking worker, stopping at the first matching snippet. Preserve read metrics and stop delivering records when the search is canceled, including cancellation during a read.
## Testing
Add tests for first-match snippets, case-insensitive literal matching, malformed records, missing matches, stream errors before a match, and cancellation between lines or during a read.
GitOrigin-RevId: 295206b1a00e861bc44606bd843f6ed8c3e6aae1
## Why
An inaccessible user profile directory can prevent sandboxed PowerShell from preserving its working directory and resolving relative paths in a project beneath that profile.
## What changed
Pass `USERPROFILE` to elevated setup and refresh. When the command's working directory is beneath an absolute profile path, grant the sandbox group non-inheriting `FILE_READ_ATTRIBUTES` access to the profile directory.
Preserve existing permissions and deny ACEs during non-inheriting ACL updates without propagating changes to descendants. Expand generic deny masks when checking for conflicting permissions.
## Testing
Add a Windows regression test that checks PowerShell's working directory and reading `.\public.txt` beneath a protected profile. Add an ACL test that verifies a non-inheriting grant leaves an unprotected child's security descriptor unchanged.
GitOrigin-RevId: 7f142a7ffdee795c3255d4a6e79568fa9391c055
## What changed
Emit `codex.skill_invocation` logs for explicit skill injection and detected implicit use, including skill-tool reads. Include skill name, invocation type, conversation, turn, model, and client metadata, plus scope, plugin ID, and ChatGPT user and account IDs when available.
Exclude skill contents, resource paths, email addresses, prompts, and tool payloads. Use the existing OTEL log exporter without an additional opt-in; `otel.exporter = "none"` continues to export no logs.
Document the event fields, exporter configuration, and detection semantics in `codex-rs/otel/README.md`.
GitOrigin-RevId: 0f9c492c3f224455f3de3660be89692d776c1951
## What changed
- Start a turn-owned notification receiver using the same remote board client and session identity as the board tools. Deliver post previews as agent messages and cancel the receiver when the turn stops, aborts, or errors.
- Wait for the initial connection attempt before inference, then retry failed or disconnected streams without waking idle agents.
- Skip malformed notices, mismatched recipients or turns, and oversized previews. Reject delivery to stale or canceled turns and bound remote notices to a 1 KiB context budget.
## Testing
Extend remote board tests to cover interrupted setup, connection failures, reconnection, invalid and stale notices, preview delivery into model context, and receiver shutdown after turn completion.
GitOrigin-RevId: c7c8d977fe74b7a5cb3bd8216dc0146f3f297e44
## What changed
Register `in_app_voice` as a stable, default-enabled feature and add it to the configuration schema. The gate is intended for managed requirements to control permission for voice in desktop apps; permission does not establish voice availability or provider support.
## Testing
Add app-server coverage for reporting `in_app_voice = false` from `requirements.toml` in both requirements and feature-list responses. Extend the CLI feature-list test to verify that cloud-managed requirements disable the gate despite a user-configured `true` value, without rewriting the user configuration.
GitOrigin-RevId: 6ec3bc0176fdb3e1714b0136bf812bd56591f6a1
## Why
When a turn ends, recovered question answers are appended to the composer draft. If that draft starts with a shell or slash command, submitting the combined text can interpret it as a command instead of a prompt.
## What changed
Escape command prefixes before appending recovered answers so the combined draft stays editable and submits as literal prompt text. Convert shell mode's separate `!` prefix into escaped composer text, and leave slash-prefixed paths such as `/tmp/file` unchanged.
Keep prefix escaping and answer recovery in the same Vim undo edit.
## Testing
Add regression coverage for immediate and queued submission, whitespace around command prefixes, slash-prefixed paths, and already escaped commands. Extend Vim undo coverage to shell and slash command drafts, including shell mode, and add a snapshot of the recovered shell draft.
GitOrigin-RevId: 03c40f72a834a65bf367103cb9170a86dc35ad98
## Why
Gateways that inspect request bodies incrementally need routing fields before potentially multi-megabyte prompts so they can route requests without buffering the input first.
## What changed
Serialize `model`, `stream`, and optional `service_tier` before `input` in both HTTP Responses requests and WebSocket `response.create` messages. Preserve field values and omission of unset `service_tier`.
## Testing
Add an HTTP regression test with a 2 MiB input that checks routing field order and unchanged JSON contents. Extend WebSocket serialization coverage to assert the routing fields appear first, and check that HTTP requests omit unset `service_tier`.
GitOrigin-RevId: dbc174e1fe7ca30d0c00f075bc37dd5f97b27b37
## Why
`windows.allowed_sandbox_implementations` permits MXC regardless of the listed implementations. Managed requirements need a separate way to block both explicit MXC configuration and automatic selection through `prefer_mxc`.
## What changed
Add the optional managed requirement `windows.allow_mxc`. Setting it to `false` disables automatic MXC selection and rejects explicit `windows.sandbox = "mxc"` configuration with an error identifying the requirement. Leaving it unset or setting it to `true` preserves existing behavior.
## Testing
Add coverage for the requirement alongside allowed sandbox implementations, preference resolution, and cloud-managed opt-out behavior for implicit, elevated, and explicit MXC configurations.
GitOrigin-RevId: a458a7b4c92cf17e687dbbad8208884d1c097da5
## Why
Session commands with `--remote` should use the selected server's authentication and execution environment, even when the caller has workload identity configured and cannot read its identity token.
## What changed
Connect `queue`, `archive`, `unarchive`, and `delete` directly to the explicit remote app server after validating configuration. Skip caller credential and runtime initialization, use remote thread parameters, and preserve the caller's working-directory override.
## Testing
Add end-to-end coverage with an unreadable caller identity token to verify queued turns use the server's API key and remote archive, unarchive, and deletion operate on the selected server. Add configuration-validation coverage for all four commands and `--no-daemon` rejection coverage for remote unarchive and delete.
GitOrigin-RevId: 5da7abbb40506cd754a8863e1a9d8fad9b1f09a9
## Why
Resuming a thread rereads persisted history even when a preloaded snapshot is unchanged. Reusing that snapshot must still account for writes committed before writer ownership is acquired.
## What changed
- Carry optional, non-serialized revisions from stored history and model context through thread and agent resume paths.
- Validate the revision under writer ownership and reuse the shared snapshot when it matches. Reload stored history when the revision is missing or changed, while preserving explicit history overrides.
- Resolve the selected rollout before loading context, validate compressed snapshots before materialization, and enforce archived-thread restrictions on canonical paths.
## Testing
Extend coverage for snapshot reuse and late-write refresh in legacy and paginated histories, compressed rollout reuse, archived rollout symlinks, and cold child restoration that includes edits made after preloading history.
GitOrigin-RevId: e1fd7aee6ef2b30f41951e6b7e6b01c3e1420cab
## Why
A stored history snapshot can become stale before a resumed thread acquires writer ownership. Resume must include writes committed before that acquisition.
## What changed
Make `ThreadStore::resume_thread` return the replay context and use it for session restoration and metadata initialization. The local store refreshes stored snapshots while holding writer ownership, reads through the installed writer to honor explicit rollout paths, and releases the writer if loading context fails. Explicit histories without a canonical session header retain their override semantics.
## Testing
Extend resume tests to cover edits made after the initial snapshot in both legacy and paginated history modes, stale SQLite rollout paths, and preservation of explicitly supplied history.
GitOrigin-RevId: 2361f524d324c859f5dfcf2863320e2045736c2e
## Why
User goal edits and clears need to reach the model as user instructions, including when a thread is unloaded or history is being compacted. Automatic goal lifecycle updates must not supply user authorization.
## What changed
- Add optional `origin` values of `user` and `automatic` to `thread/goal/set` and `thread/goal/clear`, and mark TUI goal requests as user actions. Omitted origins do not supply user authorization.
- Persist explicit user objective, status, and clear instructions before changing goal state. Recording failures leave goal state unchanged.
- Coordinate goal edits with thread resume, reload stored history under writer ownership, and preserve edits accepted after the compaction input snapshot.
- Update generated protocol schemas and TypeScript and Python bindings.
## Testing
Add coverage for user edits and clears on loaded and unloaded threads, concurrent path-based resume, exclusion of automatic goals from user instructions, preservation of edits during compaction, and recording failures that leave goal state unchanged.
GitOrigin-RevId: d779d7c678a0c32a6ef76975dbe5b1400d1df245
## Why
Guardian and parent requests can arrive in either order after a command yields. A shared response sequence can let parent requests consume Guardian review decisions.
## What changed
Match Guardian responses separately and drive parent responses from the latest tool output in the strict automatic network review test. Poll running sessions with `write_stdin` until the process exits, and assert that the command and network request each receive Guardian review.
GitOrigin-RevId: 21300abd65a3b2d439e8c1ea04e4429d5bd528dd
## Why
Guardian does not consume skills, but host skill discovery can block its startup or turn creation when the primary executor is offline.
## What changed
Skip plugin and skill warmup during Guardian session initialization, and use an empty host skills snapshot when building Guardian turn contexts.
## Testing
Add a regression test that discovers skills for the parent session, disconnects its primary executor, and verifies that Guardian still reviews and denies a network permission request.
GitOrigin-RevId: 3c12129721c82cb78a3fa618d6b05faea631966a
## Why
Copying a rendered local file target such as `repo/foo_bar!` should preserve the selected path without adding Markdown escapes.
## What changed
Treat selections contained within rendered file targets as plain text, including partial selections and targets in tables. Coalesce adjacent file targets and inline code into literal ranges while preserving Markdown escaping when the selection includes surrounding content.
## Testing
Add regression coverage for partial paths, adjacent literal spans, styled links, table cells, special characters, and mixed selections at narrow and wide rendering widths.
GitOrigin-RevId: 94bcdacf14b013f9198cb84adfdb237eb644dd48
## Why
Refreshing available model descriptions changes the `spawn_agent` tool schema. Keep model choices current while preserving tool definitions and earlier conversation input.
## What changed
- Add the disabled-by-default `model_catalog_in_context` feature for multi-agent V1 and V2. When enabled and model overrides are available, move model listings from tool descriptions into developer `<model_catalog>` messages.
- Include picker-visible, compatible models with descriptions, reasoning efforts, and service tiers in a listing bounded to 1,000 bytes. Point `spawn_agent` guidance to the latest catalog.
- Append updated listings only when their rendered content changes, restore missing listings, and invalidate retained catalogs when they no longer apply.
## Testing
Extend integration coverage for V1 and V2 with the feature enabled and disabled. Verify that catalog refreshes preserve tool definitions and prior input when enabled, append the updated listing once, and retain the existing tool-description behavior when disabled. Add a request-history snapshot for the V1 opt-in path.
GitOrigin-RevId: 67b11b4ad6c35f00d0e29edf6343bb0b4804d797
## What changed
- Fork the selected conversation and open the new session with `f`, configurable through `agents.fork` in the TUI keymap.
- Move the default search shortcuts to `F3` and `/`, preserving unshadowed defaults when custom bindings conflict.
- Keep queued input on the source conversation while attaching and forking, and require closing an open side conversation before forking another task.
- Expose the fork action in command-center help and the keymap picker.
## Testing
Add regression coverage for queued-input preservation, side-conversation protection, configurable fork shortcuts, metadata editing, disconnected actions, and search fallback bindings. Update help and keymap snapshots.
GitOrigin-RevId: b11ae21ef6a2053609b31ce97c646104f18806a3
## What changed
Add a debug-only analytics test that switches accounts after the first isolated event request. Assert that only the first request reaches the server and carries the original account's credentials, so subsequent batches do not send stale credentials after the switch.
Remove an unused `ToolCallSource` import.
GitOrigin-RevId: e66904c7a7176f1eaa37662b836132586328884a
## What changed
Define `thread/prediction/request` with `threadId` and `sourceTurnId`, and `thread/prediction/updated` with a `completed` result containing optional text or a `failed` result.
Update generated JSON schemas, TypeScript types, and Python notification models. Route prediction notifications to their thread in the TUI and ignore them in the chat widget.
The request remains unimplemented and returns a method-not-found error.
GitOrigin-RevId: 09922f583d5c56f808d018121c651dcd92734515
## What changed
Add `exchange_ema_auth_token` to discover and validate the MCP resource's authorization server before resolving enterprise identity credentials and performing the ID-JAG token exchange. Keep the lower-level exchange primitive private.
- Probe `server/discover` with the enterprise-managed authorization extension, support recognized legacy discovery rejections, and follow protected-resource metadata challenges or well-known fallbacks.
- Match configured resource and issuer constraints, require advertised public-client JWT bearer support, and validate token endpoint metadata without requiring an authorization endpoint.
- Bound discovery with a shared timeout, redirect and authorization-server limits, reject cross-origin metadata redirects, and restrict private authorization-server destinations while allowing local loopback discovery.
## Testing
Add tests covering resource and issuer mismatches before identity access, metadata capability validation, query preservation, modern challenges, JSON and SSE legacy fallback behavior, cross-origin redirect rejection, and private or malformed issuer destinations.
GitOrigin-RevId: 9a55233a20ff42c293f9bd8175e01141ac2d8576
## Why
`TurnAborted` could be emitted before extension abort callbacks finished, allowing consumers to observe a terminal event while lifecycle cleanup was still pending.
## What changed
Await `on_turn_abort` within task abort handling before emitting `TurnAborted`, retaining callback delivery for already-cancelled tasks. Document that `on_turn_stop` and `on_turn_abort` complete before their corresponding terminal events, if emitted.
## Testing
Add regression coverage for interrupt, conditional interrupt, and shutdown. Hold the abort callback open to verify that `TurnAborted` waits for completion, then verify that the callback runs exactly once with the expected turn ID and abort reason.
GitOrigin-RevId: f34d7e94d04c02544178dc445b85abc65a6ce499
## What changed
Upgrade `rmcp` to a pinned Git revision of version `3.3.0` and enable `auth-enterprise-managed`. Delegate the two-stage ID-JAG exchange and token validation to the SDK, replacing the local implementation while retaining Codex HTTP routing and credential lifecycle policy.
Map SDK errors by exchange stage so `invalid_grant` distinguishes enterprise identity failures from resource authorization failures, and preserve handling of `insufficient_user_authentication`.
## Testing
Update exchange tests to verify rejection of unsupported `authorization_details` and malformed signed scopes. Exercise errors from both token endpoints to check credential policy, prevent credential reflection in diagnostics, and ensure rejected grants are not retried.
GitOrigin-RevId: a56034aa3fd70002754ea552fd2da70bdcd85b31
## Why
Client permission definitions and constraints can differ from those on the connected app server. Accepted permission changes also need to survive task transitions before their settings notifications arrive.
## What changed
- Discover permission profiles and availability from the connected server and apply selections through `thread/settings/update`, including custom profiles.
- Adopt the server's effective permission settings instead of reapplying local definitions or constraints.
- Retain accepted selections and effective approval settings across new tasks, forks, side conversations, directory changes, reconnects, and safety retries without blocking navigation on a settings notification.
- Recognize the current built-in permission preset when the server supplies an unnamed profile.
## Testing
Add regression coverage for conflicting client/server profile definitions, rejected and unchanged selections, consecutive requests with omitted approval settings, and permission carryover before confirmation. Extend discovery and menu tests to verify server-provided availability and unnamed-profile highlighting.
GitOrigin-RevId: bcd767b58dc92dc4f945189078e51e6e5fce6d24
## Why
Login shell startup can reset `PATH`, preventing commands and their children from finding bundled tools such as `rg` in executor-reported directories.
## What changed
When `login_shell_package_path` is enabled, prepend missing executor-reported directories to `PATH` inside the POSIX login shell before running the requested command. Preserve existing entries and the order of newly added directories, and export `PATH` for child commands.
Respect explicit `PATH` overrides and preserve the requested login mode when directories are unusable or `PATH` is read-only. Keep shell diagnostics and `$LINENO` aligned with the original script, including when directory names contain newlines. The feature remains disabled by default.
## Testing
Add shell tests for nested tool lookup, existing entries, quoting, line numbers, and read-only `PATH`. Extend remote execution tests to cover feature gating, explicit overrides, unusable directories, and preservation of the original command in execution events.
GitOrigin-RevId: 301aa34e72cc6292293693250e190c19903f390a
Replace the byte-by-byte reverse newline search with `memchr::memrchr` and add `memchr` as a dependency of `codex-rollout`.
GitOrigin-RevId: b07e42e15efb0d63d7b00ee9a2ee29c446f4cf59
## Why
Responses overload and exhausted-request errors could terminate despite server retry advice, and WebSocket-to-HTTP fallback could issue a request before the advised deadline.
## What changed
- Allow `ServerOverloaded` and `RetryLimit` errors to retry when server advice is present, within the configured retry budgets.
- Preserve `Retry-After` headers from rejected WebSocket upgrades and wait for the server deadline before falling back to HTTP.
- Keep quota, usage-limit, and policy failures terminal even when they include retry advice.
## Testing
Add coverage for HTTP overload and rate-limit recovery, WebSocket upgrade rejection and fallback timing, retry deadline preservation through error mapping, and retry limits for sampling and manual and automatic compaction.
GitOrigin-RevId: 72d30a9f078652664754dfa971fd7dc7a78f20e8
## Why
Voice conversations previously opened the system-default microphone and speaker. Users need to choose which local devices to use, including when connected to a remote app server.
## What changed
- Add input and output device pickers alongside voice selection, with back navigation and a System default option.
- Persist selections as `audio.microphone` and `audio.speaker` on the TUI's machine, excluding project configuration layers. Apply them to the next voice conversation.
- Enumerate devices without opening audio streams and pass the selected names to the voice helper at startup.
- Disable ambiguous device names in the picker and use the same eligibility filtering for discovery and named-device startup.
## Testing
Add tests for device preference persistence across project and remote transitions, picker navigation and duplicate names, discovery without capture, and forwarding selected devices to the helper.
GitOrigin-RevId: d48fb3a09fa9b982a408f5a7c96bdd81776af21d
## Why
Embedded app-server configuration discovery must remain available after login and workspace changes, while content access granted to the previous account must be revoked.
## What changed
Give `AuthRouteConfig` a separate application network policy and bind embedded bootstrap authentication to the effective application policy. Use that policy for account-owned content clients and invalidate it when the authenticated owner changes, preserving the local, endpoint-restricted bootstrap policy.
## Testing
Add a regression test covering bootstrap discovery across login, workspace changes, and sign-out; revocation of previous account clients and permits; and continued enforcement of bootstrap endpoint restrictions and local requirements.
GitOrigin-RevId: 083933e69508224f8232349ba3750c02329af06a
## Why
Daemon-launched app servers should use the same analytics default as first-party clients while honoring explicit user opt-outs.
## What changed
Pass `--analytics-default-enabled` when the PID backend launches an app server, with or without remote control. Users can still disable analytics with `analytics.enabled = false` in `config.toml`.
## Testing
Update argument assertions for both remote-control modes and the daemon start/restart test to expect the analytics flag alongside launch feature overrides.
GitOrigin-RevId: 8a222a00fc56737f5fe2b0385abf59466d1a6671
## Why
Startup-only cleanup leaves expired logs in long-running sessions, and age-based retention alone does not limit database usage.
## What changed
Run cleanup in the background immediately after initialization and every 30 minutes. Start with the existing 10-day retention window, then halve it until occupied SQLite pages fit within a 64 MiB budget or the window reaches one second. Preserve logs within that final second even when they exceed the budget.
Exclude free pages from the budget so SQLite can reuse them, and retain the passive checkpoint after the first sweep. Stop the task when the runtime is dropped or the log pool is closed.
## Testing
Add tests for the 10-day boundary, repeated retention-window halving, free-page accounting, the one-second retention floor, immediate startup cleanup, and periodic cleanup without new writes or a restart. Update existing log tests to use current timestamps so background retention does not remove their fixtures.
GitOrigin-RevId: c6eeb5ec13006d4a03354e08322827429be53ce8
## Why
`LegacyAppPathString` treated `//server/share/project` as POSIX, losing its UNC interpretation when inferring a `PathUri`.
## What changed
Infer Windows syntax whenever an API path starts with two separators, including forward and mixed slashes, independently of the host. For example, `//server/share/project` now converts to `file://server/share/project`. Double-slash POSIX paths require an explicit `PathConvention::Posix`; inferred paths still undergo validation.
## Testing
Add regression tests for UNC and namespace paths, mixed separators, URI serialization round trips, explicit POSIX conversion, convention mismatches, and malformed UNC paths.
GitOrigin-RevId: 720893de517addb7a938e6784d1ed0f05df3ec0d
## Why
`ansi_escape_line` logged the rendered contents of every line when given multiline input, allowing large payloads to inflate warning logs.
## What changed
Replace line contents in the warning with structured `input_bytes` and `line_count` fields. Preserve the existing behavior of returning the styled first line.
## Testing
Enable unit tests for `codex-ansi-escape` and add coverage with small and 128 KiB tails, asserting the exact warning fields and preservation of first-line styling.
GitOrigin-RevId: 4be985b4442eaa12f7fdee8a583d6e9714c618d8
## What changed
Use `derive_more::Debug` for `ContentItem` and `UserInput` to limit debug formatting of `ContentItem::InputText` and `UserInput::Text` to a prefix of at most 512 bytes, ending at a UTF-8 character boundary. Append the full text length in bytes to each preview.
GitOrigin-RevId: ca711dde8f0e3ba7047103415dbc1836f6401e61
## What changed
Set the default SQLite log filter to `DEBUG` for `tokio_graceful::guard` and `tokio_graceful::trigger`, dropping their `TRACE` events while retaining debug and higher-level diagnostics.
## Testing
Extend the SQLite sink filter test to verify that guard and trigger traces are dropped, their debug events are retained, and `tokio_graceful::shutdown` trace events remain available.
GitOrigin-RevId: c98495c834db35f3d8799ab4f0a1f7a82a53c8ef
## What changed
Update the replay assertion in the recorder refresh test to compare `executed_tool_call_metadata()` instead of entire response items. This keeps the assertion focused on preserving recorded tool call metadata across a configuration refresh.
GitOrigin-RevId: 763173a918f4e0bc79c3c04466453cafb9629775
## Why
A stuck transport can fill the outbound queue, leaving an `environment/info` request blocked while sending. The timeout must cover sending as well as waiting for a response.
## What changed
Wrap the live metadata RPC in a 30-second timeout. On timeout, close the probed connection and request session recovery, returning the timeout error without retrying the failed request. Document the experimental `environment/info` endpoint and its timeout behavior.
## Testing
Extend the WebSocket session recovery test to cover an unanswered `environment/info` request, checking that it times out, closes the connection, and resumes the same session while retaining the client instance.
GitOrigin-RevId: 9035d2edab3626e780d8bd40ebcdf0ca327bfddb
## What changed
Forward explicit `cyberAccessProgram` selections for the built-in OpenAI provider when both `api_key_cyber_access_programs` and `api_key_model_discovery` are enabled. The new feature defaults to disabled and can be toggled through the app server's experimental feature enablement API.
Reject explicit selections in OpenAI API-key sessions when either feature is disabled, instead of silently omitting the program. Leave entitlement and model restrictions to the server, and preserve the requested program when a server rejection triggers transport retries.
## Testing
Add app-server coverage for both feature gates, forwarding all three program values, and server rejection without fallback. Update core coverage for API-key resumes with disabled features and custom-provider omission.
GitOrigin-RevId: aa639afb841aa651b28f6f3f61198299372baa2d
## What changed
Register `login_shell_package_path` as a disabled-by-default experimental feature and add it to the configuration schema. Expose it in `/experimental` as “Bundled tools in login shells,” with a description explaining its intended use when login shell startup resets `PATH`.
## Testing
Extend the experimental feature metadata snapshot test to cover the new feature's label, description, and unchecked default state.
GitOrigin-RevId: dc110486ccd8d2d76ac788ba5a413a1374699ff8
## Why
Persistence and aggregate metadata budgets can omit tool-call observations that are still relevant to the current request, including tool result metadata needed during compaction.
## What changed
- Retain live direct-call observations separately from bounded persisted outputs, keyed by response item ID so reused call IDs cannot mix results.
- Restore those observations for sampling and compaction, pruning them only when sampling confirms they have left the history window. Preserve observations across shortened compaction retries.
- Remove aggregate prompt metadata caps while retaining per-call argument limits and the outgoing message size limit. Invalidate cell completeness when argument normalization truncates a recorded call.
## Testing
Add regression coverage for exhausted persistence budgets, reused call IDs and reversed completion order, shortened compaction retries, and completeness after argument truncation. Extend integration coverage for large Code Mode metadata, provider metadata support, and fork/resume behavior.
GitOrigin-RevId: 004082b69bff9cc8b05f36d1052057f163c67f07
## What changed
Remove startup greeting phrases and the shared greeting state from startup drafts, session headers, and the empty-state animation. Raw session headers now consistently include `model:` and `directory:` fields.
## Testing
Update startup and fresh-thread snapshots to omit greetings, and adjust raw-header assertions to check model and directory fields.
GitOrigin-RevId: 531b5ba42d7a88f86b1c7f69030f3560abc25198
## What changed
- Instrument MCP OAuth loads, saves, deletes, fallback cleanup, and refresh persistence with credential-free storage metrics, distinguishing configured policy from operations on a pinned store.
- Retain the originating client across background tasks, blocking storage operations, and session recovery, including recovery after startup found no credentials.
- Preserve typed keyring and lock error categories for metrics and remove raw error details from storage warnings.
## Testing
Add tests for policy and pinned-store outcomes, best-effort cleanup failures, wrapped lock errors, and successful or failed refresh persistence without duplicate observations. Add recovery tests that verify client attribution after anonymous startup and across threads with different originators.
GitOrigin-RevId: 5ea4528bcdcf500c8ffdf1d9c7008ea52112c726
## Why
Elevated sandbox tests share machine-local Windows accounts. Concurrent setup can rotate account passwords between another test's setup and logon.
## What changed
- Add a shared file-lock guard for elevated sandbox tests in `codex-core`, `codex-exec-server`, and `codex-windows-sandbox`, held through sandbox commands and cleanup.
- Queue these tests in a single-threaded Nextest group before their timeouts start, while retaining the file lock to coordinate other test processes.
- Limit account locking to tests that use elevated accounts and remove the sandbox crate's blanket Bazel `exclusive-if-local` tag.
GitOrigin-RevId: 26d4606cb1fdcac65926d29835bed4eac04c19c0
## Why
Opaque Windows paths encoded as UTF-16LE could be mistaken for POSIX paths when they began with `/`, or fail Windows convention inference when their leading separators mixed `/` and `\`. This prevented them from retaining the Windows path convention across URI serialization.
## What changed
Distinguish a UTF-16LE slash from a POSIX root and recognize either Windows separator in both positions of an opaque UNC prefix.
## Testing
Add round-trip coverage for Windows drive, UNC, device, and namespace paths, including forward and mixed separators. Cover JSON serialization, absolute-path joins, relative-path separator handling, and Windows-only host-native conversions.
GitOrigin-RevId: d4e8a40a314cfc030c30fa8c124bfdd1e565076d
## Why
Successful file fallback can hide a secure-store failure. Storage diagnostics need to distinguish that fallback from explicit file storage while keeping credential values out of error output.
## What changed
- Record credential load, save, delete, and fallback-file cleanup outcomes, including secure-store failures and fallback reasons.
- Preserve the initiating client's attribution across app-server requests, login tasks, sessions, turns, and blocking token persistence.
- Preserve storage error context and typed causes while redacting credential JSON data errors and payload-bearing keyring errors.
- Include sanitized fallback completion warnings in the default `codex login` file logs.
## Testing
Add coverage for storage policy and metric attribution, credential redaction, login diagnostics, concurrent app-server clients, device-code login, and token refresh during a turn.
GitOrigin-RevId: 6d5651c1718d184016fa77befa02aa528750b2ae
## Why
Hook dispatch recompiles regex matchers for each input even though discovery already validates them.
## What changed
Store compiled `HookMatcher` values on configured handlers and reuse them during dispatch. Preserve match-all, exact-name, pipe-alternative, and regex matching semantics, along with the original pattern spelling for configuration equality. Invalid regexes continue to be rejected during discovery.
GitOrigin-RevId: 117a8a19c7bc0e55ccbedcd5940b806a17ebba10
Update the runtime catalog test expectations for `global.openai.gpt-6-sol`
and `us.openai.gpt-6-sol` from `MultiAgentVersion::V1` to
`MultiAgentVersion::V2`.
GitOrigin-RevId: 1b038ab988cae221a641ee54002bffc25109f45c
## Why
Credentials can use a keyring backend, so describing all login and logout operations as reads or writes to `auth.json` is misleading.
## What changed
- Remove the API-key onboarding claim that keys are stored in `auth.json`.
- Describe authentication storage and credential-removal errors in terms of stored credentials and the selected backend.
- Label the doctor output's auth-file path as the file backend or fallback, and document why startup checks also consider `config.toml` when credentials may be in a keyring.
## Testing
Add API-key entry snapshots for terminal widths of 80 and 40 columns.
GitOrigin-RevId: 87189f422448b88721ea2d7448930ece63102803
## What changed
- Carry the selected shell and login mode through unified exec using `ShellInvocation`. Use this metadata for shell snapshots and credential brokerage instead of inferring it from command arguments.
- Add `prependPathDirs` to exec-server environment metadata, populated from the executor's package PATH directory. Default to an empty list for older servers and omit empty lists from serialized output.
## Testing
Extend environment metadata round-trip coverage for `prependPathDirs` and the remote exec-server integration test to verify the packaged `codex-path` directory is reported.
GitOrigin-RevId: c571c068effcb305d196a701ad9a335ec7a3f5a2
## Why
Pasting multiple lines into a blockquote previously left subsequent lines unquoted.
## What changed
- Continue the current line's `> ` prefix across pasted lines, including blank and trailing lines, in the TUI composer and embedded answer fields.
- Append two unquoted newlines so typing resumes in the next Markdown block. Preserve quoting when large paste placeholders expand on submission.
- Use a shared edit target for paste context and insertion so selection replacement uses the prefix at the replacement start.
- Keep shell input and provisional startup pastes literal.
## Testing
Add unit tests and rendering snapshots for blockquote pastes, embedded answers, cursor placement, selection replacement, and large-paste expansion. Add textarea tests for forward and backward selections, adjacent elements, and Vim Replace backspace recovery.
GitOrigin-RevId: 525a7951aa16a25d49cc3be98822d0dd0709de97
## Why
Denied-read policies previously kept explicitly approved commands within their original filesystem restrictions, preventing operations that need broader write access, such as updating Git metadata.
## What changed
- Apply broader filesystem permissions after approval of explicit escalation while retaining the sandbox, denied reads, and network policy. Command allow rules alone do not widen filesystem access.
- Reject escalation when the required local sandbox is unavailable or a remote exec server lacks support for preserving the restrictions.
- Track escalated terminal access so subsequent `write_stdin` calls still require review when stdin approval is enabled.
## Testing
Add coverage for approved and denied escalation, allow rules, remote server compatibility, and stdin approval before input delivery. Add a Windows integration test verifying that an approved `git pull` updates Git metadata while exact-path and glob-based read denials remain enforced. Serialize Windows sandbox integration tests across processes to protect shared test account credentials.
GitOrigin-RevId: 5dce6d41487ee4d39bd795c8d086398ab9794d5b
## What changed
Preserve catalog `multi_agent_version` values instead of forcing V1, allowing models that declare V2 to use it by default. Retain Ultra in supported reasoning levels so it appears in the Astra advanced reasoning picker for Bedrock Mantle and Runtime.
## Testing
Add coverage for preserving configured multi-agent versions, selecting V2 and exposing `collaboration.spawn_agent` and `collaboration.followup_task` without the V2 feature flag, and displaying and selecting Ultra in both Bedrock reasoning pickers.
GitOrigin-RevId: 4fb1336c79b3f86ce12fa5ea81fe2237a300840d
## What changed
Add `openai.gpt-6.1-sol` to the Bedrock Mantle catalog and its `global.` and `us.` variants to the Bedrock Runtime catalog. Make GPT-6.1 Sol the default and provider fallback model, preferring the global variant for Runtime. Keep existing models available.
## Testing
Update catalog and provider assertions, thread-start fallback tests, and TUI model-picker snapshots to cover GPT-6.1 Sol and the new defaults.
GitOrigin-RevId: ec65744ff9409980474cc1faf516beed0b2430da
## Why
Canceled RPC calls could leave entries in the pending request map until further traffic or disconnect. Cleanup should happen when the call is dropped, even if no response arrives.
## What changed
Use a `PendingRequestGuard` to remove each registration when its call completes or is canceled. Protect the pending map with a synchronous mutex so cleanup can run in `Drop`, replacing opportunistic pruning and explicit error-path removals.
## Testing
Add a regression test that drops an in-flight call and verifies that the pending request count immediately reaches zero without further traffic.
GitOrigin-RevId: 82c0629f37a2f4bb89b8d10e167e2a09765b26eb
## Why
Reaching the reconnect backoff cap reset the attempt counter, restarting fast retries during sustained failures such as HTTP 409 responses indicating that the remote app server is already online.
## What changed
Keep the reconnect delay at the 30-second cap and stop advancing the backoff exponent once capped. Successful connections and auth changes still reset backoff. Remove logging for the obsolete reset-at-cap behavior.
## Testing
Add regression tests for long failure streaks and repeated HTTP 409 handshakes, with and without a subscribe cursor. Verify capped retry intervals, recovery after a successful handshake, backoff reset on success, and preservation of enrollment and cursor state.
GitOrigin-RevId: 56e3f10ec5ceeced5a71397a99ca22b75dd5ef52
## Why
`CreateProcessWithLogonW` failures with `ERROR_SERVICE_ALREADY_RUNNING` (1056) previously aborted sandbox startup without retrying. At this stage, neither the runner nor the user command has started, so retrying does not replay the command.
## What changed
Retry runner creation once with the same sandbox credentials when logon returns error 1056. Propagate a second failure without refreshing credentials, and keep child startup errors with the same code ineligible for this retry.
## Testing
Add regression tests for recovery, the two-attempt limit, and exclusion of child startup failures. Add a unified exec test that injects a logon failure, verifies that the retry preserves the original request and credentials, and checks that the command runs exactly once.
GitOrigin-RevId: 78def6cdb93bf32f9b4a3e398cd16de83286fec4
Add `gpt-6.1-sol` to the bundled model catalog with its capabilities,
reasoning levels, and availability message. Give it the highest catalog
priority and update older Sol descriptions to reflect their generations.
Update startup, model picker, and tool catalog snapshots to reflect the
new default and catalog contents.
GitOrigin-RevId: 1092a0524c6d1813ddd600c31c4fd0e708294ae9
## Why
A subagent stopped by repeated Guardian denials remained interrupted without notifying its parent. The parent needs guidance to report the stop and wait for explicit user confirmation before continuing the blocked work.
## What changed
Forward `TooManyDenials` interruptions from `MultiAgentV2` children to their parents with Guardian-specific guidance to inform the user and avoid resuming or retrying until the user explicitly confirms. Preserve the child's `Interrupted` status and keep ordinary interruptions silent.
## Testing
Add integration coverage for parent notifications under `CircuitBreakAction::Strict`, silence under `CircuitBreakAction::Default`, and preservation of the child's interrupted status. Add a unit test ensuring long denial messages stay within the notification token limit while retaining the guidance.
GitOrigin-RevId: c9bb90827393068d9c92edaf0443a52e6ff57f9f
## What changed
Use `ConsoleMode::NoWindow` for legacy Windows sandbox capture and non-TTY unified execution, enabling `CREATE_NO_WINDOW` for these piped processes.
## Testing
Extend the PowerShell interrupt and capture tests to assert that `GetConsoleWindow()` returns null before checking process termination and descendant survival.
GitOrigin-RevId: dcc3b5554986ab0280748e5fa7080d36ded3d673
## Why
Thread name resolution performs a separate SQLite metadata lookup for each thread. Batch these reads to reduce database queries for large result sets.
## What changed
Add `StateRuntime::get_threads` and use it in `resolve_thread_names`. Fetch metadata in batches of at most 999 IDs to stay within SQLite's bind limit, skipping missing or invalid records independently so valid metadata remains available.
## Testing
Add regression coverage for reads spanning multiple batches, invalid and missing records, duplicate IDs, and empty input.
GitOrigin-RevId: a403416f1da5adea56705c70839850760d3eb550
## Why
Parsing multiple tag delimiters in a chunk repeatedly drained the pending
buffer, shifting its remaining contents after each delimiter.
## What changed
Track a consumed offset in `InlineHiddenTagParser::push_str` and drain the
buffer once after processing the chunk, preserving partial delimiters for
the next chunk.
## Testing
Add a regression test comparing visible text and extracted tags against
single-chunk parsing at every UTF-8 character boundary. The input covers
non-ASCII text and delimiters, adjacent tags, an empty tag, and an unfinished
tag at end of input.
GitOrigin-RevId: 18bfbfdb81060ffda30901d5cb82ee5804878b09
## Why
Batch thread name lookups read the entire append-only session index even when all requested names could be found near the end.
## What changed
Use `ReverseJsonlScanner` in `spawn_blocking` for `find_thread_names_by_ids`, stopping once every requested ID has a usable name. Preserve the latest nonempty, trimmed name for each ID while skipping malformed entries.
## Testing
Add regression coverage for renamed threads, whitespace-only names, Unicode, reads across chunk boundaries, malformed entries, a partial final write, and missing IDs.
GitOrigin-RevId: 2ab9254ba8b718fe3e02c47fc9b0de20c09fd10f
## What changed
Replace the custom recursive JSON canonicalizer with `serde_json::Value::sort_all_objects()` before hashing configuration values, preserving existing fingerprints.
## Testing
Add a regression test that checks reordered keys in nested tables and tables inside arrays produce the same existing fingerprint.
GitOrigin-RevId: 890e79865a1d690adea3b35f19fcc6c30dbd17ce
## Why
Guardian review and classification telemetry lacks the context mode needed to distinguish `legacy`, `independent`, and `thread_owned` reviews.
## What changed
- Add `guardian_context_mode` to review and classification analytics and `context_mode` to their metrics.
- Capture the mode from the conversation history snapshot before review preparation or classification setup so failure metrics retain it, including when review preparation or reviewer startup fails.
- Use `unknown` for review metric tags when no context mode is available.
## Testing
Update metric assertions to cover `thread_owned` classification tags and the `unknown` review fallback.
GitOrigin-RevId: 79f7d11b3e4ccfc53681890d75fbc7c54e1ce7de
## What changed
Allow users with an active session to start MCP OAuth sign-in through `/mcp login <name>`. Request login through the app server, open the authorization URL in the browser, and display success or failure in the originating thread.
Guard overlapping start requests and track login attempts per server so stale retry completions do not overwrite current results. Skip opening the browser when the attempt has already completed, and retain results across thread switches and session refreshes.
## Testing
Add command dispatch coverage and regression tests for overlapping starts, stale retry completions, rejected starts, independent server logins, and result retention across thread switches and session refreshes.
GitOrigin-RevId: aeec2dbee566660f9aa26ef23039196ef3ca49d6
Replace the three optional fields in `AttachmentState` with `Attached` and
`Detached` variants, making inconsistent field combinations unrepresentable.
Keep the connection ID in both variants and the expiration deadline only in
`Detached`, and update attachment and expiration checks to match on the state.
GitOrigin-RevId: 6a5f05f0ce2f064acc8f5cacd00bc374c4f47986
## Why
Stale thread capability roots can reconnect executors that are not selected for the current turn and shadow selected roots with the same ID.
## What changed
Filter out roots whose environments are absent from the turn snapshot before deduplication and readiness resolution. Update app-server capability tests to explicitly select the executor environments used by each turn, including after resume.
## Testing
Add regression coverage for full-access and workspace-write permissions, verifying that stale roots never connect an unselected executor, selected roots with matching IDs remain available, and turns with no environments expose no roots.
GitOrigin-RevId: afe375047cc5e8aad06df83334149510460dcdcc
## Why
`TurnComplete` can arrive before the previous turn finishes teardown, making `start_turn_if_idle` race with cleanup in the encrypted parent reply scenario.
## What changed
Submit the reply through `Op::InterAgentCommunication` so it queues through the same mailbox path as real agent messages. The scenario continues to verify that the encrypted parent reply appears exactly once in each incremental Guardian review.
GitOrigin-RevId: 3d356c274442aa839324b9425490feafacd47313
## Why
The app server previously rejected OAuth login for enterprise-managed MCP servers. These servers need an explicit sign-in flow that ties saved authorization to the active Codex user and workspace and prevents canceled or superseded attempts from saving credentials.
## What changed
- Enable enterprise sign-in through `mcpServer/oauth/login` for configured servers with a connected thread, trusted IdP registration, and `features.use_xaa` enabled. Scope shared enterprise credentials by user, workspace, issuer, and client ID.
- Add `loginId` to MCP OAuth login responses and completion notifications, preserving compatibility with older servers that omit it.
- Support enterprise login replacement and `account/login/cancel`, wait for callback listener shutdown before replacement, and recheck account and configuration before saving grants. Fence stale attempts across processes and account changes.
- Remove shared enterprise authorization during account logout and `codex mcp logout`, including when the feature is disabled. Continue account logout if enterprise cleanup fails, and invalidate MCP runtimes on account changes.
Start a fresh session after successful enterprise sign-in to use the saved grant.
## Testing
Add regression coverage for login replacement and cancellation, callback port reuse, account changes during setup, cross-process logout invalidation, persisted workspace policy selection, cleanup failures, and responses from older servers without `loginId`.
GitOrigin-RevId: 7ed4caaab4659ed1e67064262cf5cee48e3a26ac
## Why
Responses prewarm can reconnect and consume scripted WebSocket replies intended for realtime conversations when both share a test server.
## What changed
- Give realtime conversations a separate scripted server in tests for runtime replacement, prompts, and voice selection.
- Disable Responses WebSocket prewarm in the audio/text round-trip test while preserving coverage of the default realtime endpoint.
- Update connection counts and request assertions to address only realtime connections.
GitOrigin-RevId: 8e3b5ac86ee80777cf94063db468c80203966999
## Why
Reloads can reject a valid thread configuration when the host configuration references a missing model provider that thread overrides replace. Concurrent cloud refreshes can also leave older policy snapshots or staged cache writes eligible for publication.
## What changed
- Compose preserved session layers before materializing refreshed configuration, retaining source-aware validation errors.
- Carry cloud policy revision bindings through config loading and role overrides. Reject stale MCP refreshes and disable enterprise MCP authorization when the policy is suspended. Retire the old policy when replacing or clearing its loader.
- Stage cloud cache writes in temporary files and publish them atomically only while their policy revision remains current.
- Route file reloads through the shared runtime refresh path, resolve paths relative to each config file, and preserve session settings. Restore host defaults for `secret_auth_storage` and `mcp_oauth_refresh_coordination` when explicit overrides are removed.
## Testing
Add regressions for thread-provided model providers, managed plugin and feature requirement refreshes, stale and suspended policy snapshots, superseded and retired cache writes, and file reloads preserving runtime settings and restoring feature defaults.
GitOrigin-RevId: 3280a2445eeb7074a142f720690bb0e4f01d174b
## What changed
Add `features.multi_agent_v2.message_board_remote` with a board URL and a bearer token supplied directly or through an environment variable. When configured, use the remote board in preference to local or in-memory storage, including in ephemeral sessions, while preserving the existing board tools and session identity.
Ignore remote board settings in project-local configuration and use the runtime HTTP client and clock for remote requests.
## Testing
Add a mock-server integration test and snapshot covering an ephemeral session posting through the existing tool, with the expected bearer authentication, session identity, timestamp, and returned post.
GitOrigin-RevId: 263413d90a1ee4c0bdba8c1b08ba9f68bdd7a986
## Why
Steering and recovery requests can have different traces from the turn they join. Sampling can also finish while tools remain in flight. Tracing needs to preserve that correlation and distinguish sampling time from time spent waiting for tools.
## What changed
- Add `codex.turn_input` spans with `conversation.id` and the accepted `turn.id` for started, steered, and recovered turns.
- Add sampling, tool-blocking, and automatic and manual compaction spans with `codex.turn.phase` and conversation and turn IDs. End the sampling span before draining outstanding tools.
- Emit a `codex.mailbox_preemption` event when pending mailbox input preempts sampling.
## Testing
Add integration coverage for cross-trace steering and recovery, sampling and tool-blocking boundaries through a blocked dynamic tool, and completion or interruption. Extend mailbox preemption tests to check event emission with preemption enabled or deferred.
GitOrigin-RevId: 59893c2d463c02cbd05f5c332e5afc2351cc8b62
## Why
Restoring the error mode with `SetErrorMode` can overwrite the failure code from `CreateProcessWithLogonW`, causing `RunnerLogonError` to report the wrong error.
## What changed
Capture `GetLastError()` immediately after a failed runner launch, before restoring the previous error mode, and use the saved code for `RunnerLogonError`.
GitOrigin-RevId: c0f4267232306be4d06e7e8accd60f7b77b8d6f3
## Why
Configuration reloads must honor current managed restrictions without granting new enterprise MCP authority to existing sessions or overwriting newer configuration with stale snapshots.
## What changed
- Allow enterprise managed authentication only for configured MCP servers. Remove plugin `ema_auth` overlays from the schema and disable servers that still use them.
- Refresh ordinary MCP settings while preserving session settings and initially admitted enterprise registrations. Disable enterprise MCP when its registration changes, policy revokes access, or configuration loading or resolution fails; require a new session to restore enterprise authority.
- Publish refreshes only when their captured configuration is still current, with bounded retries in app-server reloads. Preserve updated managed restrictions even when a refresh is rejected.
- Finish processing other thread refreshes before `config/mcpServer/reload` reports a rejection, and document that an error can accompany partially applied changes.
## Testing
Add regression coverage for stale refreshes, bounded retries, managed-policy revocation, persistent enterprise disablement, ordinary MCP transport changes, and rejection of plugin enterprise authentication. Verify that denied enterprise servers receive no requests.
GitOrigin-RevId: 34429cd339c1ec152a2ee8697cb29f0cff5d9e5f
## Why
Missing retained root instructions could indefinitely block a worker's matching low-risk cached score from approving an action.
## What changed
Require complete retained local context for cached approvals, while allowing incomplete root context when the cached score matches the current authorization. Root omissions remain visible to the classifier.
## Testing
Extend the cached-delivery regression test to verify that a worker with complete local context and an `IncompleteRootInstructions` marker can approve using a matching low-risk cached score.
GitOrigin-RevId: 06feda47fe47feb933c67239d32bf154b2032615
## Why
Copying executable fixtures in the test process can expose writable file descriptors to sibling spawns. The shared `copy_executable` helper completes copies in a separate process on Linux before launching the fixtures.
## What changed
Use `copy_executable` for both `codex-linux-sandbox` and `bwrap` in `bazel_build_rejects_tampered_bundled_bwrap`, and add `codex-utils-cargo-bin` as a Linux test dependency.
GitOrigin-RevId: 05fb1381eeefb64568b525925c9e81863acc2b54
Read `model_provider` from the effective configuration's nested `config`
field in `history_model_provider`, retaining the `openai` fallback.
GitOrigin-RevId: 06a8b3da1b499e673f80b8827951020c469c3970
## Why
Background helpers launched from a detached Windows process can allocate console windows. Job Object launches and containment fallbacks need to preserve console suppression as well.
## What changed
- Add `codex_utils_process::background_command` to set `CREATE_NO_WINDOW` on Windows, and use it across background subprocess launches, including Git, plugins, authentication, diagnostics, and sandbox helpers.
- Centralize console suppression in Job Object launches. Keep `CREATE_NO_WINDOW` when retrying without containment, and clear `CREATE_SUSPENDED` so the fallback child can run.
- Preserve console inheritance for interactive shell launches and interactive AWS authentication refreshes.
## Testing
Add Windows regression tests covering console-free launches from detached parents through standard and Tokio commands, stdout/stderr capture, successful containment, Job Object creation and assignment failures, and sandbox setup refresh helpers.
GitOrigin-RevId: b2c238fa7d4f9fbd868e5adf7d4be9958ff01e6c
## Why
Client provider defaults can override the app server's configured provider and hide its sessions from resume and fork history.
## What changed
- Omit implicit provider overrides from thread start, resume, and fork requests so the server can resolve its defaults.
- Use the server's effective provider for named history lookup, `--last`, and resume and fork pickers, while honoring explicit CLI and selected-profile choices.
- Respect managed provider requirements when resolving history filters and preserve the active session's provider when forking it.
## Testing
Add app-server regression tests for provider defaults, explicit choices, configuration changes, selected profiles, and managed requirements. Add CLI coverage for resume and fork pickers and `--last` with local daemon and embedded servers, plus a picker rendering snapshot.
GitOrigin-RevId: a077758b13a5e55552b52e5532ad4bebe86dce7e
## What changed
- Skip folder trust prompts for locally discovered projectless directories without a saved trust decision. Apply workspace-write permissions and granular approval defaults only when local execution, configuration, and managed policy allow them.
- Prompt for Windows sandbox setup when needed before enabling implicit workspace-write permissions.
- Restore saved task permissions on resume unless explicitly overridden, and keep ordinary turns from overwriting the server's saved permission profile. Track explicit approval reviewer choices separately from restored permissions.
- Let `/cd` request folder trust with a “Keep current directory” option. Recheck task activity and background terminals before switching, and enforce destination permission requirements.
## Testing
Add regression coverage for projectless defaults and session transitions, explicit permission overrides, saved profile preservation, trust discovery, destination policy conflicts, and the directory consent and Windows sandbox prompts.
GitOrigin-RevId: cf74f5a90245f2aee96caa80d76de64da6ec1ebd
## Why
Copying text selected within a blockquote adds Markdown quote markers that are not part of the selected content.
## What changed
Return plain text for selections containing only quoted content, preserving literal `>` characters and selected whitespace. For quoted tables and task lists, remove quote prefixes while retaining table reconstruction and checkbox states. Selections spanning quoted and unquoted content continue to preserve Markdown structure.
Preserve the existing logical source when marking list separator lines as omitted from Markdown copying.
## Testing
Add coverage for partial and nested blockquote selections, quoted tables and task lists at narrow and wide widths and after rewrapping, and copying a mouse-selected blockquote.
GitOrigin-RevId: 5ac0c8c47a77937e5a35c376d8908065217ad2dc
Replace the trailing-slash removal loop in `normalize_base_url` with
`trim_end_matches('/')`, preserving existing behavior.
Add regression coverage for unchanged URLs, single and repeated trailing
slashes, empty and slash-only inputs, and ChatGPT URLs with and without
`/backend-api`.
GitOrigin-RevId: db71e80c4dcaac33b308a45684b14e7edbd71528
## What changed
Omit the reasoning summaries setting from the model details when connected to a remote server or local background server. Continue displaying it when no server connection is present.
## Testing
Expand status snapshots to cover no server connection, a remote server, and a local background server, including the reasoning summary setting visibility in each case.
GitOrigin-RevId: f7213e7ad7439107705461ccf4e070501729113b
## Why
Forwarding local defaults as request overrides can replace server defaults or saved thread settings for reasoning summaries and verbosity.
## What changed
Only forward `model_reasoning_summary` and `model_verbosity` as shared thread request overrides when their winning configuration layer is a session flag or an explicitly selected user profile. Use the effective values from that layer, and omit values whose winning source is ordinary user or project configuration. Preserve the existing reasoning-summary defaults for new embedded threads.
## Testing
Add coverage for profile, project, and CLI precedence. Extend outbound model request tests to verify that remote-mode thread start and resume preserve server reasoning summary and verbosity settings despite conflicting local values.
GitOrigin-RevId: 5e14254a51ed7506118a46847bb7466ab58908ef
## Why
Turn error hooks receive only a `CodexErrorInfo` category, which omits backend metadata such as usage-limit reset times and rate-limit snapshots.
## What changed
Add borrowed `CodexErrorDetails` to `TurnErrorInput` and pass the original details through turn and compaction error notifications, alongside the existing error category.
## Testing
Add coverage for usage-limit metadata during sampling, manual compaction, and post-turn compaction, including preservation of completed answers and existing error events. Extend lifecycle tests to verify that an `InvalidImageRequest` retains its details when surfaced as `BadRequest`.
GitOrigin-RevId: 6f2058992126da0f69508ef51998e7581557deea
## What changed
Render macOS Option shortcuts as `⌥t` and `ctrl+⌥t` instead of `⌥+t` and `ctrl+⌥+t`. Keep `+` separators after text modifier labels such as `ctrl`, `shift`, and `alt`.
## Testing
Update key-label and chord assertions and UI snapshots to expect the compact labels across shortcut help, navigation hints, and tooltips.
GitOrigin-RevId: 7d52088ebce3dfa3f8bdad65eb159ca0fead8a31
## Why
Providers with `model_catalog_url` could advertise bundled models absent from their catalog or reuse stale models after a failed refresh. Model metadata could also match by prefix or namespaced suffix instead of the provider's exact model ID.
## What changed
- Suppress bundled model fallback and merging for explicit provider catalogs, including when discovery is disabled.
- Require unique, non-empty catalog slugs and match metadata by exact model ID.
- Serialize explicit catalog refreshes and invalidate in-memory and persisted catalog entries after fetch failures, preventing stale cache reuse.
- Report a clear configuration error when startup has no available model, while allowing an explicitly configured `model`.
## Testing
Add regression coverage for exact model matching, hidden catalog entries, cache invalidation across restart and recovery, invalid slugs, and empty-catalog startup with and without an explicit model. Update app-server model-list expectations and verify the TUI configuration error.
GitOrigin-RevId: ac323a94178e3c48df8d4a159a86fdbac20b03a2
## What changed
Move content-filter guidance recording from the sampling loop into
`handle_response_stream_error`. Pass `StepContext` so the handler can resolve
model-specific guidance and record it before retry decisions for sampling
requests. Keep remote compaction excluded from guidance recording and update
callers and the existing retry-deadline test to use the new signature.
GitOrigin-RevId: 030bde1d4f1597fc4f3971ad837478e5304c5aa9
## Why
Skills available from both cloud and executor providers consume duplicate catalog space, leaving less room for descriptions of unique skills.
## What changed
- Prefer model-visible cloud skills over executor listings with the same `plugin:skill` name before allocating the metadata budget.
- Preserve aliases from the full visible executor inventory so filtering duplicates does not renumber remaining packages. Continue choosing full locators when they fit the budget better.
- Keep executor packages available through `skills.list` and `skills.read`, and retain executor listings when cloud skills are disabled.
## Testing
Add regression tests and a model-request snapshot covering description retention, stable aliases across turns, executor availability changes, package reads, and full-locator selection after deduplication.
GitOrigin-RevId: 477e4cf16b8968dbe61438dd5af1eca9cbfa78c8
## Why
Responses stopped by `content_filter` previously followed generic stream-error retry handling without guidance about the block. Retried requests need instructions to explain the limitation and offer a permitted alternative.
## What changed
- Recognize content-filter failures as a distinct error while preserving retryability and the existing public error representation.
- Append developer guidance to the conversation after each sampling block, retaining delivered output and using the existing retry handling.
- Support a model catalog override through `model_messages.content_filter_guidance`. Missing, null, blank, or values exceeding 512 UTF-8 bytes fall back to bundled guidance.
- The bundled guidance tells the model to avoid reproducing or working around blocked content, briefly explain the limitation, offer a permitted alternative, and continue unrelated authorized work.
## Testing
Add a scenario and request-history snapshot covering repeated blocks, catalog guidance on each retry, retained partial output, and eventual completion. Add error-mapping assertions for retryability, public error classification, and error text.
GitOrigin-RevId: ba0c201b3a5a3acf5cfa971332027240e0690225
Clarify in the `requires_openai_auth` field documentation and configuration schema that credentials use the backend selected by `cli_auth_credentials_store`, rather than always being stored in `auth.json`. Also clarify that `env_key` specifies the environment variable containing the API key.
GitOrigin-RevId: e65753a72258e43b24c4e40b51ff26830c5b3756
## Why
Sessions can share an analytics client while using different product SKUs. Analytics requests need per-thread attribution to reflect each session's configuration.
## What changed
- Register each thread's `apps_mcp_product_sku` and send `X-OpenAI-Product-Sku` on analytics requests grouped by product, without changing authentication.
- Send product groups concurrently while preserving event order within each group.
- Flush buffered tool events before changing or evicting their product attribution, and clear attribution when a session disables analytics.
- Bound retained thread registrations and concurrent product groups. Drop attribution when registration cannot be queued or a batch exceeds the product-group limit.
## Testing
Add tests for shared-session attribution, clearing attribution on resume with analytics disabled, buffered events across product changes, queue overflow recovery, registry limits, and concurrent delivery with preserved event order.
GitOrigin-RevId: 25a98788cd44d4a85f97ee87aadf3a6909607f6a
## What changed
- Publish released mouse selections from both transcript views to X11 `PRIMARY` as plain text, even when copy-on-select is disabled. Preserve configured `CLIPBOARD` copying when it is enabled.
- Paste `PRIMARY` into the editable fullscreen composer on middle-click, including while a transcript selection remains active.
- Limit support to local Linux X11 sessions, excluding Wayland, SSH, tmux, WSL, and VS Code terminals.
- Retain the latest deferred selection publication and order it before a pending `PRIMARY` read, while giving explicit copies priority. Cancel stale deferred work when its selection or paste target is invalidated.
- Clarify that scrollback mode uses native terminal copy, paste, and scrollback.
## Testing
Add regression tests for selection publication with copy-on-select enabled and disabled, publication-before-read ordering, explicit-copy priority, cancellation of deferred work, and middle-click paste invalidation.
GitOrigin-RevId: 6ba7bddffda60183b7f9ad5cd69a97da8a4a8dcd
## Why
The command center seeded only ten recent sessions, with no way to browse older history from the task list.
## What changed
- Add a keyboard-selectable “Show more” row that discovers up to ten more tasks, with loading and retry states that remain accessible during search.
- Retain per-source cursors and buffered rows across requests, merging interactive and non-interactive history by recency without discarding existing tasks on failure.
- Refill vacancies after tasks are archived or deleted, and prevent stale refreshes from restoring removed tasks.
- Limit routine detail refreshes to recent and loaded tasks, plus explicitly targeted threads, as retained history grows.
## Testing
Add regression coverage for pagination across mixed sources, cursor retries without row loss, automatic refill, queued pagination, and “Show more” navigation, loading, search, and retry rendering.
GitOrigin-RevId: 0bfcc970c9adf0c8d509b275a92ecf01c29595ad
## Why
Reconnecting paused all recovered input, including queued messages that had never been sent. Those messages can resume automatically once any uncertain submissions are resolved.
## What changed
- Track unsent and unconfirmed messages separately. Reconcile submitted prompts and steers using exact client message IDs from restored history, buffered events, and later receipts.
- Remove confirmed submissions from the recovered queue and resume unsent input after replay. Keep uncertain submissions paused without resending them, and show a notice identifying the message whose delivery could not be confirmed.
- Preserve pauses for unavailable conversations, pending compact/review requests, and existing input recovery failures.
- Simplify reconnect status text and remove blanket disconnect/reconnect transcript notices.
## Testing
Update reconnect integration tests and snapshots for automatic queue resumption. Add coverage for matching and unrelated receipts, missing history, late confirmations across navigation, pending compaction, and preservation of image-failure recovery pauses.
GitOrigin-RevId: d0b9aa43c4019d472985d12bbce8ba9bbfb9253b
## Why
Hash-based sharding does not account for differences in test duration. Use estimated test time to balance the Windows Bazel workload across shards.
## What changed
- Add checked-in duration weights and a deterministic selector that assigns the longest targets first to the least-loaded shard.
- Assign every queried target exactly once, default missing weights to one second, and ignore stale weights.
- Run queries and selection in the foreground so failures stop the job before tests run with a partial target list.
- Emit LF-delimited target labels for Git Bash and report estimated shard loads on stderr.
## Testing
Add seven passing selector tests covering deterministic coverage and balancing, missing and stale weights, invalid inputs, duration-file overrides, and CLI output. Run them on the first Windows CI shard.
GitOrigin-RevId: d415ae093bfe57794ee53a2eb9d712022202dad8
## Why
Changing an existing database from `FULL` to `INCREMENTAL` auto-vacuum requires a writer lock and can block pool initialization. SQLx also retries connection initialization failures, masking the original error as `PoolTimedOut`.
## What changed
Preserve existing auto-vacuum modes when opening writable pools, while continuing to initialize empty databases with incremental auto-vacuum. Return the first connection initialization error directly to the caller, retaining SQLx's normal error handling for later lazy connections.
## Testing
Add regression tests for fresh database settings, opening an existing `FULL` auto-vacuum database under a write lock, and preserving the WAL conversion lock error while allowing a subsequent open to succeed after the lock is released.
GitOrigin-RevId: b586c68e43a5a0d3b47268378716919d01b749cf
## Why
Each call to `PluginsConfigInput::remote_plugin_service_config` created a new HTTP client pool, preventing connection reuse across service configurations.
## What changed
Share one lazily initialized, route-aware pool across a `PluginsConfigInput` and its clones. Newly constructed inputs retain separate pools, while service configurations continue to use the current endpoint and product SKU and requests use the supplied authentication.
## Testing
Add tests for lazy initialization, pool sharing across repeated calls and early clones, isolation between new inputs, and requests using updated endpoints, product SKUs, and authentication with the shared pool.
GitOrigin-RevId: 3e929c34052798779a4f153e4db03b3f75b6f87d
## Why
Repeated plugin discovery and loading reparse unchanged manifests and repeat warnings for invalid fields.
## What changed
- Share a manifest cache through `PluginStore` across marketplace listing, plugin loading, capability inspection, and tool suggestion metadata.
- Reuse successful parses by plugin root, manifest path, and content digests, including the Codex overlay. Reread files on each load so manifest edits and overlay changes or removal remain visible.
- Bound the cache to 128 entries and bypass caching for inputs larger than 64 KiB. Retry failed parses and share entries across store clones while keeping independent stores isolated.
- Reuse loaded manifest data when loading apps and MCP metadata.
## Testing
Add unit coverage for parse reuse, warning deduplication, revision invalidation, repair after parse failures, equivalent Windows paths, store isolation, and oversized inputs. Add an app-server regression test that verifies repeated `plugin/list` requests observe manifest and overlay revisions in one running server.
GitOrigin-RevId: ed082cd7d198015cd8ed35db7f2af74e13f49915
## Why
Remote controllers cannot resolve a sandbox-compatible PowerShell executable on the execution host.
## What changed
Apply the existing PowerShell fallback during exec-server request preparation for the `Elevated` and `Mxc` Windows sandbox backends. Match `pwsh` and `powershell` executable names case-insensitively and replace inaccessible Store PowerShell paths when a compatible executable is available.
## Testing
Add Windows RPC regression tests for lowercase and mixed-case PowerShell aliases with a restricted server `PATH`, verifying successful command execution in the `Mxc` sandbox.
GitOrigin-RevId: 365541af2f026a662b1988429f5d182c98e4a236
## Why
Usage-limit failures during manual or post-turn compaction did not notify turn lifecycle extensions, leaving them unable to react to these errors.
## What changed
Emit the turn error lifecycle notification for `UsageLimitExceeded` in both compaction paths. Preserve the completed answer after post-turn compaction fails, and avoid duplicating the error already emitted by manual compaction.
GitOrigin-RevId: f31155e5991d762a0779030921aedbd1f818cfbb
## What changed
- Replace plan-specific and Fast-mode promotions with the desktop app tip for the current platform, while preserving announcement priority and random-tip fallback.
- Share desktop app tips between the preferred slot and random tip pool, including Windows. Keep Linux app tips limited to graphical sessions outside WSL.
- Clarify installation and launch instructions for macOS, Windows, and Linux, and format launcher commands as code.
- Remove the Fast-mode status plumbing used by tooltip selection.
## Testing
Add snapshots for all three platform tips at a narrow terminal width. Update tests to cover plan-independent tip selection and platform availability.
GitOrigin-RevId: 34bbc95c47c83618f9ac1691a1b69ca4690b8665
## Why
Follow-up directives contain display labels and prompt attributes. Show the labels without exposing directive syntax or prompt text in rendered responses and streaming previews.
## What changed
- Render `:codex-followup[label]{prompt="..."}` as its label, preserving inline Markdown styling and source offsets.
- Replace recognized follow-up directives with their labels when copying whole responses, while retaining the original source.
- Withhold unfinished directives in rich streaming previews and avoid cropping into prompt attributes when the preview window advances.
- Preserve literal code, escaped directives, and malformed source when rendering completed messages or copying responses.
## Testing
Add regression coverage for label formatting, nested brackets and backticks, literal and malformed directives, whole-response copying, and streaming holdback across long prompts and preview window boundaries.
GitOrigin-RevId: dce61d1164de0a576fe95fb2c67b177a1ed414e8
## Why
Every thread state mutation scanned all tracked runtimes to recount running turns while holding the state lock. This count supports graceful restart draining introduced in https://github.com/openai/codex/pull/12517.
## What changed
Maintain `running_turn_count` in `ThreadWatchState`, adjusting it when a runtime's `running` flag changes or a running thread is removed. Publish the cached count while preserving notifications only when the count changes.
## Testing
Extend the running-turn watch test to cover duplicate starts, two simultaneous running threads, and removal of a running thread, with counts checked against the runtime map.
GitOrigin-RevId: e7d7ebb33b9ff4d24dc70d8f01ae981378fed5f8
## Why
An offline secondary executor can stall Guardian approval revalidation while diff display setup searches for Git roots, even when the review concerns another executor.
## What changed
Use each environment's working directory as the diff display root for Guardian sessions, regardless of `CwdRelativeTurnDiffs`, so this setup does not wait for remote Git discovery.
## Testing
Add a regression test that withdraws authorization during a pending approval and disconnects an unrelated secondary executor. Verify that Guardian retries with the updated authorization and denies the request.
GitOrigin-RevId: 3661759119935c68539e9eab8df2e862987d0d92
## What changed
Use a shared subscription label mapping for status and analytics views. Rename
`Pro Extra` to `Pro 200`, `Pro Standard` to `Pro 100`, and `Pro Max` to `Pro 500`,
while preserving the existing differences between status and analytics labels
for other plans.
## Testing
Update the status plan-label test expectations for the three Pro tiers.
GitOrigin-RevId: 47af1e7d56ef9f7701caff8af315f530087920b8
## Why
Skill invocation analytics only needs the repository's origin URL, but
`collect_git_info` also checks the repository and reads its commit and branch.
## What changed
Extract and export `get_git_origin_url` and use it directly in skill analytics
to skip the extra Git commands. Reuse the helper in `collect_git_info`,
preserving URL sanitization and command timeouts.
GitOrigin-RevId: f878936937d0ff8c6313bb8168448e0b25ba1a39
## Why
Spawning a subagent before an environment was ready dropped the starting environment from the child's selections. The child needs to retain that environment and receive its configuration or failure when preparation finishes.
## What changed
- Pass the spawning step's environment snapshot to children, preserving ready and starting environments and configuration ownership.
- Propagate the original owner's first configuration result through descendants, applying each session's validation and leaving independently configured children unchanged.
- Preserve pending configuration waits across executor retries. Later owner updates do not overwrite the child's inherited configuration.
## Testing
Add regression coverage for fresh and forked subagents, readiness through turn-settings updates, failure propagation to children and grandchildren, child configuration precedence, and executor retries. Add a request snapshot showing a child using `wait_for_environment` before execution tools become available.
GitOrigin-RevId: a2afed740391f88d195596cfe28e418332b60d43
## What changed
Expose resolved Cargo package versions in `rules_rs` workspace `DEP_DATA` and pass them through `codex_rust_crate` to build scripts, libraries, binaries, and tests. This replaces the hardcoded `0.0.0` build-script version and supplies explicit versions to the other Rust targets.
GitOrigin-RevId: a3555beec3c5ecfc38d69c352b43696986352c49
## Why
Failed `thread/realtime/listVoices` requests silently fell back to the built-in catalog, allowing voice selection and conversation startup to proceed without the server's voice catalog.
## What changed
- Propagate catalog errors and show an error instead of opening the voice picker or starting a realtime conversation.
- If the catalog lookup fails after saving a preference, report that the preference was saved but the effective voice could not be confirmed. Leave the in-memory voice settings unchanged.
## Testing
Extend remote voice tests and snapshots to cover catalog failures when opening the picker, saving a preference, and starting a conversation. Verify that the preference is persisted, in-memory settings stay unchanged, and failed startup clears realtime state without sending `thread/realtime/start`.
GitOrigin-RevId: ba40800d6f9002e02e2b33de8dc858188c3cddd7
## Why
Deleting logs leaves free SQLite pages available for reuse without shrinking the database file. Reclaim excess free space while preserving a reserve for future writes.
## What changed
- Start a background incremental-vacuum worker with `StateRuntime`, enabling reclamation only for the logs database. Use a per-home file lock to select one worker and wait for it to finish during shutdown.
- Reclaim pages when at least 64 MiB and 25% of the database are free, preserving a reserve of at least 16 MiB or 10% of the database.
- Use short transactions with page and cooperative time budgets, defer work on contention, and reduce batch sizes with exponential backoff when interrupted passes make no progress.
- Record reclamation counts, durations, and reclaimed pages in telemetry.
## Testing
Add a regression test that interrupts a vacuum commit, verifies foreground writes can resume without data loss, then confirms a resumed pass shrinks the database and passes `PRAGMA integrity_check`.
GitOrigin-RevId: 8421f87b0aeef6540eda5690c84216906673c72e
## Why
Configuration parser errors can include entire configuration lines containing credentials. Persistent policy-rejection events must avoid recording those values.
## What changed
Replace free-form error text in Windows sandbox provisioning policy-rejection events with known stage labels and typed cloud, HTTP, I/O, and Win32 error codes. Use fixed fallback labels when the stage or cause is unrecognized.
## Testing
Add regression coverage using malformed requirements and cloud configuration fragments containing a synthetic secret. Verify that diagnostics exclude parser values while retaining safe error codes, and that unknown errors produce fixed fallback text.
GitOrigin-RevId: 4f2fa5f6f602c34451776ec31381a102213660b8
## What changed
Update the `guardian_handoff_delegation` snapshot to include three separate `agent_message` items interleaved with user transcript messages, with corresponding transcript numbering and message counts.
GitOrigin-RevId: cae688e00f96d9545eccd7891426cfb4948a6dbf
Refresh the Code Mode messaging snapshot to include a native `agent_message`
entry between transcript segments, with updated message and action numbering.
Adjust retained-instruction spacing in the encrypted parent reply snapshot and
refresh assertion-line metadata in both snapshots.
GitOrigin-RevId: 1ee003cfb9df89faabd2f35e9d656423f16e0501
## Why
Runtime ACL repair needs to handle nested files and directories beyond the legacy Windows path limit.
## What changed
Use Rust's `OpenOptions` for ACL reads and handle-based `SetSecurityInfo` for updates to support extended-length paths. Request ACL-write access only when grants need updating, and share allocation cleanup across success and error paths.
## Testing
Add a regression test covering long directory and file paths alongside a short-path control. Verify repeated repairs grant read/execute access without granting write, delete, or ACL-management rights, and that already-correct grants remain no-ops.
GitOrigin-RevId: 325c17085fa4379eebe982d49175dd2151b0681e
## What changed
Add the disabled-by-default `guardian_root_handoff_context` feature to select worker-specific root evidence for Guardian reviews. Use recorded `spawn_agent`, `send_message`, and `followup_task` calls targeting a worker or its ancestors to select the three preceding root messages per handoff, plus the three latest root messages so recent cancellations remain visible before another handoff.
Preserve verified tool answers and evidence without known ordering, and retain the existing shared message cap. Fall back to the existing root context when no usable handoff window remains or the latest authorization message is a heartbeat. Update the review context revision when the selection changes.
## Testing
Add a delegation scenario and Guardian request snapshot covering ancestor handoffs, separate worker branches, cancellation visibility, and fallback after compaction removes handoff calls. Extend heartbeat coverage to exercise the new feature and verify that the latest turn's trusted skills are retained.
GitOrigin-RevId: 87dc39158f78b2b7e9f4f2e4afc653257ea12025
## What changed
Update plan labels in the analytics views and status display:
- `PlanType::Pro`: `Pro (More)` → `Pro Extra`
- `PlanType::ProLite`: `Pro` → `Pro Standard`
- `PlanType::ProMax`: `Pro (Max)` → `Pro Max`
## Testing
Update the status display-name test expectations for all three Pro tiers.
GitOrigin-RevId: 9bd9f1cd8a701019fd40047cd8131e6193f66cb9
## Why
Copying text selected entirely within inline code added Markdown backticks that were not part of the selected content.
## What changed
Return only the selected content as plain text when the selection is contained within one inline code span, including in a single table cell. Preserve Markdown formatting for selections that also include surrounding content, and continue filtering control characters from table copies.
## Testing
Add regression coverage for full and partial inline code selections, embedded backticks, Unicode, whitespace, wrapping and resizing, and table selections with mixed content or control characters.
GitOrigin-RevId: c63e13cb781f9fca28ae53500cb4f9ae08b72c96
## Why
Guardian transcripts omitted encrypted agent messages, leaving reviews without evidence such as encrypted parent replies.
## What changed
- Carry encrypted `agent_message` items through synchronous reviews and asynchronous scoring, preserving their order, author, recipient, and ciphertext.
- Account for native messages in context budgets and omit them whole with an explicit notice when limits require it.
- Support mixed text and native messages during review admission while retaining user-content annotations.
## Testing
Add coverage for transcript ordering and budget eviction in both reviewer profiles, plus a mocked scenario verifying that an encrypted parent reply appears exactly once in each of two incremental Guardian reviews.
GitOrigin-RevId: abc2f1ce5accd83beb06f799ef9ed9d7fa2cd90a
## Why
The fullscreen status line showed Plan mode without explaining how to leave it.
## What changed
Show `Plan mode (shift+tab to cycle)` when the composer is idle and accepts input, and the hint fits alongside the status text. Fall back to the mode label when space is limited, and hide the shortcut during tasks, popups, interactive footer use, or other non-composer modes.
## Testing
Add a rendering snapshot and regression assertions for wide and narrow layouts, running tasks, interactive search, empty status text, disabled input, and parent-owned threads.
GitOrigin-RevId: a1cf2762b33f5442ab0611a15205f2e36c84b075
## Why
The transcript supplied to Guardian may omit earlier user instructions, restrictions, or revoked permissions. History retrieval lets the reviewer check relevant authorization before approving actions with side effects.
## What changed
- Add the disabled-by-default `guardian_conversation_history_tools` feature. With Apps enabled, expose `user_message.search_messages` and `user_message.read_messages` through the parent's live Apps connection and conversation identity.
- Recheck the parent's current app and tool policy on each call, rejecting disabled tools and calls requiring approval.
- Add retrieval instructions that distinguish user authorization from assistant context and account for later revocations and incomplete results. Allow overrides through `auto_review.experimental_conversation_history_prompt`.
- Limit history responses to an estimated 4,000 tokens by default, configurable through `auto_review.conversation_history_max_output_tokens`, while preserving stricter parent and reviewer limits.
- Allow explicit extension registries for isolated sessions and prevent those sessions from inheriting the implicit Apps connection.
## Testing
Add scenarios covering history tool exposure, parent connection and identity reuse, custom prompts, output truncation, stricter reviewer budgets, and live permission changes on a reused reviewer. Extend configuration coverage for blank prompt overrides.
GitOrigin-RevId: 055a69b113c8548bd58e7d5618ea026ba6d1ffb1
## Why
Setting `auto_vacuum` on every connection can wait for a writer lock even when the mode is unchanged. Logging every span entry and exit can also block SQLx workers on undrained stderr while they hold a write transaction.
## What changed
- Set incremental vacuum only for empty databases or databases using full auto-vacuum, before enabling WAL. Preserve existing nonempty databases with auto-vacuum disabled.
- Emit span creation and closure events in app-server text and JSON stderr logs, preserving busy/idle timings and explicit events while omitting span entry and exit records.
## Testing
Add regression tests for opening and expanding writable pools while another connection holds a writer lock, and for transaction completion with undrained stderr in both log formats. Verify vacuum modes and retained log diagnostics.
GitOrigin-RevId: 40d4ef32c7efc49f4240b987277ba45551259335
Describe permissions and approvals explicitly in the Codex docs link text,
and clarify that the user's ChatGPT plan rate limits and training data
preferences apply. Remove the “Before you start” preamble to shorten the
success screen.
Update the rendering snapshot and hyperlink styling assertions for the
revised copy and layout.
GitOrigin-RevId: 5166ddade6a433191fa86c960899c4da5092b9f5
Older macOS policy compilers do not define the `TIOCSTI` symbol. Generate the sandbox CLI's Seatbelt deny rule with the numeric value from `libc::TIOCSTI` so it remains compatible while blocking terminal input injection.
GitOrigin-RevId: de8113fbab92bb399f37b9a22762c5c649f25972
## Why
Microsoft Store PowerShell cannot run under MXC. The existing fallback to an unpackaged PowerShell executable only applied to the elevated Windows sandbox.
## What changed
Extend local PowerShell fallback discovery to MXC in `unified_exec`, using the executor's Windows sandbox selection. Keep discovery local and automatic `-NoProfile` insertion specific to the elevated sandbox. Skip this preparation for non-Windows target paths.
## Testing
Extend command-preparation tests to cover MXC and add a Windows integration test that replaces a Store PowerShell path before launch, writes a file successfully, and verifies `windows_mxc` sandbox metadata.
GitOrigin-RevId: 6c581396525a8fec7e1fb538b3e63b0de2ddb926
## Why
Best-effort workspace enrichment can time out independently of the detached
request metadata checked by the memory startup test.
## What changed
Keep the phase-one service-tier and detached-metadata test fixture outside Git
and assert that `workspaces` is absent. Update the header assertion message to
refer to turn metadata.
GitOrigin-RevId: 9541668fc62a28d1ff3131d7f71b351149b6e152
## Why
Updates that only change `updated_at` should not rewrite unrelated thread metadata or its indexes.
## What changed
Use `touch_thread_updated_at` for timestamp-only patches when the SQLite row exists and the rollout path is unchanged. Preserve the full update path for missing rows, changed rollout paths, and patches containing other metadata, including staged changes.
## Testing
Add regression coverage for legacy and paginated histories that verifies missing-row reconstruction, timestamp-only writes using SQLite triggers, preservation of other metadata, and application and removal of staged metadata.
GitOrigin-RevId: d5bc70d57e591e3eb8e9521f0c31a7ef75f244d3
## Why
Message-board notifications delivered as ordinary injected input could cause an agent to sample again after its final answer.
## What changed
Route notifications through the current turn's mailbox as `InterAgentCommunication`, checking atomically that the turn is running and still accepts mailbox delivery. Skip notifications when delivery is closed. Accepted notifications may remain in conversation history for a later turn without reopening the finalized answer or starting a new turn.
Report pending inter-agent communications as mailbox activity, while preserving priority for steering input.
## Testing
Add regression scenarios for notifications arriving before and after finalization, asserting no extra sampling and the expected notification presence in the next turn. Extend input-queue coverage to recognize already-pending mailbox activity.
GitOrigin-RevId: 41d786041b4eccc5ccf926f2f190473676a3ac2f
## Why
Startup prewarm can reconnect after its empty WebSocket connection closes,
consuming the scripted realtime session reply in the environment-key fallback
test with ChatGPT authentication.
## What changed
Use separate WebSocket servers for startup and realtime traffic, configuring
`experimental_realtime_ws_base_url` to point to the realtime server. Assert that
it receives exactly one handshake and that the handshake uses the environment
key for authorization.
GitOrigin-RevId: 0e8ba4bdd66ef8aa3c619e36454dded9dcf55444
## What changed
- Default `flowchart` and `graph` to top-down layout when no direction is specified.
- Support solid and dashed edges with directed, undirected, or bidirectional endpoints: `-->`, `---`, `<-->`, `-.->`, `-.-`, and `<-.->`.
- Accept pipe labels on these edges and spaced directed infix labels such as `A -- send --> B` and `A -. retry .-> B`.
- Expand `&` groups into all source-to-target edges, including in chains. For example, `A & B --> C & D` creates four edges. Enforce the 24-edge limit after expansion and cap each group at 24 node references.
## Testing
Add coverage for equivalent syntax, edge styles and endpoints, malformed input, and expansion limits. Extend rendering snapshots across all four directions and the TUI native-renderer test with the new syntax.
GitOrigin-RevId: 6e51653ebf6b8b7e7e1edec0c2e09a5d9c8dec74
## What changed
Render interrupted turns with secondary text styling and shorter wording,
removing the suggestion to tell the model what to do differently.
## Testing
Update interruption snapshots and assert that the notice uses secondary text
styling.
GitOrigin-RevId: 7cb042ed9e6781d107a93d5677fa193f082c764d
## Why
Allow the provisioning service time to start without holding up desktop readiness checks for the full provisioning timeout.
## What changed
- Poll service status while startup is pending, waiting up to five seconds within the caller's deadline. Treat absent, deletion-pending, or other non-running service states as unavailable.
- Preserve the original provisioning deadline for pipe availability and request processing, and reject requests whose deadline expires during server authentication.
- Recheck service status when the pipe disappears while waiting for an available instance.
GitOrigin-RevId: ea89175cb41749b9768ac5915083bbfd8ad32713
## Why
Fresh threads have no rollout until their first turn, so archiving them previously failed with a missing-rollout error.
## What changed
Persist loaded, non-ephemeral threads before looking them up for archival. This lets a newly started thread be archived without creating a user turn.
## Testing
Update the archive regression test to cover threads with no turns in both legacy and paginated history modes. Verify the archive notification, empty turn history, `NotLoaded` status, and archived rollout path.
GitOrigin-RevId: 507351c6238ad96f5e3ffbd2ed7f432058e3d52c
## What changed
- Show a hand pointer over actionable transcript links while Codex captures mouse input in Ghostty and Kitty, excluding sessions inside terminal multiplexers.
- Share link hit testing between hover and click activation, and refresh hover after rendering so scrolling and live output cannot leave a stale hand pointer.
- Suppress link hover during mouse presses and drags, overlays, and popups, and clear remembered mouse coordinates on focus loss, resize, and resume.
- Restore the terminal's pointer policy when releasing mouse capture, releasing Kitty's override and using a text pointer in Ghostty. Deduplicate pointer updates and preserve cleanup after write failures.
## Testing
Add tests for wrapped links containing wide characters, hover/click target agreement, scrolling, pointer transitions and restoration, write-failure retries, and hover invalidation.
GitOrigin-RevId: 1cf52e039a229e12260fa334879784c9bc1c8c87
## Why
Capture jitter and mute transitions can shift RTP timestamps off the 20 ms source grid, causing receivers that assemble fixed-duration frames to reject subsequent audio.
## What changed
Advance elapsed gaps in whole 20 ms packets and keep the track clock on that grid. Bias empty gap durations by 1 ns to avoid losing an RTP tick to floating-point truncation.
## Testing
Update jitter and mute tests to assert exact clock advancement, including a 580 ms gap, and verify that resumed RTP timestamps stay aligned to 960-sample packets.
GitOrigin-RevId: 1511c739b77ee5871f72723fd34cb67aa9a48c95
## What changed
- Give tool fragment sizes and namespace counts logarithmic boundaries through 32,768.
- Give enabled and kept skill counts integer boundaries from 0 through 512, removed description characters logarithmic boundaries through 131,072, and skill truncation flags boundaries at 0 and 1.
- Record these metrics with explicit boundaries, separating zero values and retaining overflow buckets above each range.
## Testing
Extend tool and skill metric tests to assert explicit boundaries. Add an export test covering zero, one, the upper boundary, and overflow, including bucket counts, ordering, and sample totals.
GitOrigin-RevId: 9fbf3acbe352d7c74f3ad11f0b690148c083a6ef
## Why
Splitting every statement at semicolons and rejecting label punctuation prevents rendering labels such as `A["Go []; &"]`, sequence messages containing `data[0] = {x: 1}`, and class members containing semicolons.
## What changed
- Split statements using diagram-specific rules, preserving semicolons inside flowchart labels, quoted tokens, and class member lines. Sequence quotes remain literal text.
- Respect quoted flowchart label delimiters and allow printable label punctuation, including literal ampersands and comparison operators.
- Reject unsupported entity escapes before statement splitting can truncate them, while retaining rejection of HTML markup and malformed labels.
- Document the supported syntax and require newlines between class members.
## Testing
Add parser assertions and update rendering snapshots for punctuation, quoted delimiters, and semicolons. Extend rejection coverage for entity escapes across diagram families, malformed quotes, and invalid class bodies.
GitOrigin-RevId: da94007a66c7c58444e6f0d6a1b409c8c7251941
## What changed
- Add `CodexThread::prewarm_with_history()` to prepare a WebSocket response with existing conversation history and executed-tool metadata using `generate: false`. The next turn can reuse the prepared response when its prompt extends that history and request settings match.
- Keep startup prewarming and `prewarm()` on the existing empty-input path, and skip preparation when the cached WebSocket is ready.
- Label prewarm telemetry by input mode and WebSocket continuation metrics with `after_prewarm`.
- Rename `persistent_mode_enabled` to `persistent_execution_enabled` without changing its behavior.
## Testing
Extend WebSocket coverage to check history preservation during reconnect prewarming, reuse of the prepared response on the next turn, and omission of `previous_response_id` for a non-prefix prompt.
GitOrigin-RevId: c7731541b11b2e6668027a47f37f696213268c66
## Why
Completion footers hid known durations unless they exceeded 60 seconds, leaving short turns without elapsed-time information.
## What changed
Show all known durations for live and restored turns, rendering sub-second durations as `Worked for <1s`. Separate completion metadata with `•` instead of `·`.
## Testing
Update live completion, history replay, and separator tests to cover short durations, missing timestamps, and the revised footer format. Refresh affected TUI snapshots.
GitOrigin-RevId: 666e765db5426c5f9cc00d73f71cab649ad34947
## Why
The “Implement this plan?” prompt blocked transcript scrolling, preventing users from reviewing earlier steps in a long plan while deciding how to proceed.
## What changed
Allow mouse-wheel scrolling over the visible transcript while a modal is active. Keep keyboard input with the modal and preserve restrictions on transcript selection, scrolling outside the transcript, and scrolling with completion popups open.
## Testing
Add input tests and a snapshot covering plan-prompt scrolling, keyboard navigation, dismissal and submission, pointer boundaries, and completion-popup behavior.
GitOrigin-RevId: ac5227c877ce34324a0d3830d5383495241ddbc3
## What changed
Render ordered list markers in the TUI with the terminal's `LightBlue` color instead of `accent_color()`.
## Testing
Add a snapshot covering ordered list markers alongside links and inline code. Update rendering expectations and nested-list streaming tests to assert `LightBlue`, including the incremental rendering snapshot.
GitOrigin-RevId: dea0081737a5bbe8652c761582fb82b20964431a
## Why
Some Windows terminals send legacy mouse reports as key records. Requesting SGR reports lets ConPTY translate them into mouse records.
## What changed
Write and flush the SGR encoding request separately from `EnablePointerCapture`, so it also reaches terminals when capture uses the Windows console API. Explicitly reset SGR encoding during Windows mouse cleanup, even if restoring the console mode fails.
## Testing
Add regression tests for cleanup after SGR setup fails and an isolated Windows console test that checks mouse input activation, SGR encoding, and restoration of the original console mode and default encoding.
GitOrigin-RevId: c1a48d641cda4e770dbbe9fdf805a27e036d35c3
## Why
Guardian denial-limit interruptions lack a structured error identifying the cause. Make this opt-in because older clients may not recognize the new error in shared history.
## What changed
- Add `auto_review.circuit_break_action = "strict"` to attach `TooManyDenials` to the interrupted turn. The default leaves the error unset.
- Expose `turn.error.codexErrorInfo = "tooManyDenials"` in app-server notifications and saved history, and update protocol schemas and generated types.
- Preserve the warning, denial limit, and interrupted status without emitting a separate error notification.
## Testing
Add an integration test covering omitted, `default`, and `strict` settings, checking warnings, live turn errors, the absence of separate error notifications, and persisted turn errors after restart.
GitOrigin-RevId: cb5d379e64728d4d7b9daf834c13756e4a70db31
## Why
Inspecting one MCP server should not require full-inventory discovery or a separate connection when a thread already has one.
## What changed
- Add optional `serverName` to `mcpServerStatus/list` and update generated schemas and bindings.
- With `threadId`, apply any pending runtime refresh and reuse the thread's current connection and tool catalog, waiting only for the selected server during discovery.
- Without `threadId`, create a discovery connection for only the selected server. Unknown names return an empty page; omitting `serverName` preserves full-inventory discovery.
## Testing
Add a regression test covering both status detail modes, checking that tool metadata is preserved and that status reads do not repeat `initialize` or `tools/list` requests.
GitOrigin-RevId: 1b361b67a993ab45cae493e88c146f50cfaf753a
## Why
Guardian reviews need to retain original evidence across parent compaction when checkpoint reuse is disabled, including after resume and rollback.
## What changed
- Make disabling `guardian_reuse_parent_compaction` select a bounded, independent review transcript while preserving thread-owned authorization.
- Keep synchronous reviews and asynchronous scoring independent of parent checkpoints, and allow reviewer sessions to continue using transcript deltas across parent compaction.
- Persist transcript entries with rollback provenance while remaining compatible with older checkpoint readers and metadata-free checkpoints.
- Exclude compaction output from the transcript and synthetic summaries from rollback turn boundaries. Use acceptance ordering to remove rolled-back evidence even when persistence order differs.
## Testing
Add regression coverage for reviewer continuity, evidence retention across compaction and resume, rollback after local and remote compaction, and checkpoint serialization compatibility.
GitOrigin-RevId: fea0852cc5537372854f4a34bacb6bfda6d13e88
Let task titles use the space previously reserved for the `current` badge
in the agents overview. Update the overview assertion and rendering
snapshots to match.
GitOrigin-RevId: 6a007d4f8b1a3a77459895725e2db8ef4a4d584d
## What changed
Add the `› ` prefix to pinned prompt headers, using bold red for spoken prompts and bold dim styling for other prompts. Reserve one column when truncating the header.
## Testing
Add a rendering test comparing pinned headers with the original prompt rows for both regular and spoken prompts. Update snapshots for the prefix and display-width truncation.
GitOrigin-RevId: 89c2d9267374ef8f6504058c12c078025f302fef
## Why
An advertised control socket path can exceed the Unix socket path limit even when its symlink target is short enough to connect to.
## What changed
On Unix, resolve the socket path and retry the connection when the initial attempt returns `InvalidInput`.
## Testing
Add a regression test that creates control sockets under two long home paths, checks that their symlink targets are distinct, and verifies that clients can connect through both advertised paths.
GitOrigin-RevId: 2541f0a9b02d85035fa89fe26bbcd36d5cd0cc1e
## Why
Defaulting missing or unsupported display preferences to `inline` prevents clients from applying resource display defaults.
## What changed
Populate `mcpAppUi` only when a tool descriptor has a resource URI and an explicit `inline` or `fullscreen` preference. Preserve `mcpAppResourceUri` independently in tool-call events, including when `mcpAppUi` is unset, and document the behavior.
## Testing
Update integration coverage for explicit display modes, missing and unsupported preferences, and legacy resource URIs, checking tool-call events and resumed history.
GitOrigin-RevId: 4876cced068d8e464adeb265abd053d8abe667ce
## What changed
Replace generic output disclosure labels with counts such as `+ 5 lines (ctrl+t to expand)` for compact command activity, both live and in history. Count retained output lines hidden or clipped by the preview, excluding output discarded by storage limits.
Use the configured `open_transcript` shortcut and omit the hint when it does not fit or the action is unbound. Invalidate cached layouts when keybindings change. Keep generic `Show details` labels for other hidden details and keep disclosure controls outside copyable and searchable text.
## Testing
Add regression tests for live/history consistency, remapped and disabled shortcuts, and exclusion of hints from source text. Add snapshot coverage for fully visible output, hidden and clipped lines, command-only details, and storage-truncated output.
GitOrigin-RevId: c468be9b88b69dc3ca1abdb6b7be023244d32a57
## What changed
Replace the continuous two-second shimmer with a 600 ms initial delay and a one-second sweep every four seconds, matching the desktop app's thinking and reasoning header timings.
## Testing
Update snapshots for short, long, and Unicode labels in both themes to cover the initial delay, sweep, gap, and next sweep. Sample smoothness across two sweeps at 32 ms intervals and adjust the brightness-change bound for the faster sweep.
GitOrigin-RevId: d7a6a81db99bf0e8a73eee0c67eb7e44d4d76f42
## Why
The status card truncates values in narrow terminals, hiding parts of paths, session IDs, and other details.
## What changed
- Remove the status border and wrap values with continuation lines aligned beneath the value column, falling back to less indentation at very narrow widths.
- Preserve full directory paths and session IDs in displayed and copied status output.
- Allow history updates with no previous rows to append new details while preserving existing history rows.
## Testing
Add regression coverage for long Unicode paths and session IDs across terminal widths, copied text, usage links, and appending late thread-usage details. Update status snapshots for the borderless layout and wrapped values.
GitOrigin-RevId: e059fed5b45e15b76250b684f1760797442eabce
## Why
Concurrent tests can inherit writable descriptors for executable fixtures, causing `ETXTBSY` when those fixtures launch on Linux.
## What changed
Expose shared `write_executable` and `copy_executable` helpers from `codex_utils_cargo_bin` and adopt them in CLI, exec-server, and MCP tests. On Linux, writes and copies complete in separate processes so sibling test spawns cannot inherit the writable descriptors. Script fixtures receive mode `0o755`, and copied executables retain their source permissions.
Remove the executable-busy retry loop from the program resolver test now that its script uses the shared helper.
GitOrigin-RevId: 61624158190bb1e75c27d9eb9c87a2defc147fb7
## Why
Guardian needs the assistant's delivered question to interpret a user's reply. Messages sent through nested Code Mode tools must remain available as review context, and approvals based on earlier context must become stale when a new delivery is confirmed. Assistant messages do not themselves grant authorization.
## What changed
- Capture successful hosted User Messaging sends after input rewriting and before result callbacks or post-tool hooks.
- Retain bounded delivery text in acceptance order, persist it through cancellation and shutdown, and preserve it across compaction and resume with an older-client-compatible rollout encoding.
- Track assistant review context separately from user authorization, invalidating pending and cached approvals for both local and worker reviews when that context changes.
- Associate retained deliveries with the correct instruction or communication boundary during rollback.
## Testing
Add coverage for nested messaging review context, fast replies and communication ordering, shutdown persistence, stale local and worker approvals, rollout compatibility, and rollback retention.
GitOrigin-RevId: 1bc1ec9e8947560b99f4b39a42ddb9f2099f519b
## Why
Concurrent test spawns can inherit a writable descriptor for the MCP server
wrapper, causing `ETXTBSY` when launching it on Linux.
## What changed
Write the wrapper through a separate `/bin/sh` process on Linux so its writable
descriptor stays out of the test process. Check the writer's exit status and
include stderr on failure. Retain direct file writes on other Unix platforms.
GitOrigin-RevId: f99952ec000ba7317243e87fd664dc0e31bb7b24
Stop logging response headers on successful WebSocket connections and payload
previews for tool calls. Keep the connection URL, tool name, and thread ID in
their respective log entries.
GitOrigin-RevId: 1d410b6aef8f12153da9bfc60c515b8e797a9de0
Replace the stale `start_fresh_session_with_summary_hint` call with
`start_fresh_session` in the test for restoring blank drafts and built-in
permissions.
GitOrigin-RevId: a1f1f75dc173a732af712511cf8f6a16f2e3c0fa
Set `CFBundleName` to `ChatGPT` and add `CFBundleDisplayName` with the same
value in the generated `Info.plist`.
GitOrigin-RevId: e40a0b10895227148d6fdc199b1c4166b5c59372
## Why
Untouched threads have no rollout for `thread/resume` yet. Switching away from a blank startup or fresh session needs to preserve its live subscription, draft, and settings so it can be reopened.
## What changed
- Retain blank startup and fresh sessions for non-ephemeral connections to an external app server, and save their input state before navigating away.
- Restore the current thread name and apply background settings updates after restoring drafts, so saved model choices do not overwrite newer server settings.
## Testing
Extend the task-switching regression test to cover blank startup and fresh sessions, preserved drafts and model choices, updated thread names, and restoration without `thread/resume` or `thread/unsubscribe`. Verify that background model, permission, and approval-policy updates are used for the first submitted turn.
GitOrigin-RevId: 958b0cb48a5a873d8d8f5858ac334fecbfad60c7
## What changed
Remove the previous session's token usage and resume hint from the history
shown when starting a fresh session or resuming another thread. Remove the
unused summary helpers and their tests, and rename the fresh-session helper
to `start_fresh_session`.
GitOrigin-RevId: d808bdf355831d1c7b937b6a101ffbb33a805234
## Why
Empty list items can lose their markers, and a bare marker received during streaming can still acquire content in a later chunk.
## What changed
- Render pending markers when an empty item ends or a nested list starts on a new line, including inside blockquotes.
- Keep trailing bare list markers mutable during streaming so later content and terminal resizing preserve the item correctly.
## Testing
Add snapshot coverage for empty ordered, nested, and blockquoted list items, plus regression tests for streamed continuations, finalization, and resizing with a held marker.
GitOrigin-RevId: d9116bddc49670ad66d71dbddc66b2ab347cb6b7
## What changed
Remove automatic next-message generation after successful turns, suggestion rendering in the composer, and the associated Tab acceptance and Escape dismissal handling. Remove the `tui.prompt_suggestions` configuration option and its schema entry, along with suggestion-specific tests and snapshots.
GitOrigin-RevId: 63bf6f2ca85da6ece502c86e2a805d000bf34210
## What changed
Add `Features::persistent_mode_enabled` and use it for persistent instructions and current-time reminder defaults. Enablement still requires `ReasoningEffort::Persistent`.
Change `PersistentModeState::new` to accept an explicit enablement boolean, separating instruction rendering from reasoning-effort selection.
## Testing
Update persistent-context tests to use boolean enablement while preserving coverage for instruction replacement, removal, deduplication, and retained history without a snapshot.
GitOrigin-RevId: f412b90d783438d1526956a56c11b9e66385ee0e
## What changed
- Delete the `plugin-creator` skill, its assets, reference docs, helper scripts, and associated Python tests.
- Update the app-server skills context budget warning test to expect six omitted skills instead of seven.
GitOrigin-RevId: 005b1ab7f2f7c2933e6c297d01541746cc489f68
## Why
A provisioned executor can still be resuming after readiness is reported. Initial connection attempts can exhaust the ordinary registry retry limits before the executor comes online.
## What changed
Retry `environment_offline` registry responses during initial Noise rendezvous connections for provisioned environments until a fixed five-minute deadline, starting after provisioning succeeds. Keep the existing retry limits for other registry errors and stop on permanent failures.
## Testing
Add tests covering the five-minute deadline, ordinary limits for other errors and stalled requests, and termination on a later permanent error. Verify that readiness and info requests remain pending through an extended offline period and succeed using the same environment handle once the executor comes online.
GitOrigin-RevId: e22211499d9ec2f3590e75224eb39e2e4bf3538d
## Why
Long descriptions could exhaust the 4 KiB tool summary budget and hide later namespace names, limiting their visibility for tool discovery.
## What changed
- Reserve space for all namespace names before sharing the remaining budget across descriptions, including added and removed groups.
- Truncate descriptions at UTF-8 boundaries with `...`, including at the existing 250-character cap. Omit whole namespaces only when names alone exceed the budget, reserving omission notices only in that case.
- Render namespace names and descriptions without XML escaping.
## Testing
Add unit and snapshot coverage for description allocation, Unicode boundaries, namespace omissions, and empty-state notices. Add a scenario verifying that a crowded catalog retains every namespace name, allows discovery of a late namespace with its full description, and keeps the summary unchanged on follow-up.
GitOrigin-RevId: 9743cda5aa14190db22c788c9e91e1785a32682b
## Why
Private IP destinations always bypassed inherited upstream proxies, preventing their use for private networks reachable through an upstream VPN proxy.
## What changed
- Add `codex exec-server --proxy-private-ips-via-upstream`, also configurable with `CODEX_EXEC_SERVER_PROXY_PRIVATE_IPS_VIA_UPSTREAM=true`. The setting defaults to disabled.
- Allow permitted RFC 1918, carrier-grade NAT, and IPv6 unique-local destinations to use an applicable upstream proxy. Loopback and link-local destinations retain direct routing, and destination access policy still applies.
- Keep connections direct when no valid upstream proxy applies or `allow_upstream_proxy=false`. Errors after selecting an upstream proxy do not trigger a direct retry.
- Rename `ExecServerRuntimePaths` to `ExecServerRuntimeOptions` and carry the routing setting from executor startup into the managed network proxy.
## Testing
Add routing coverage for private address ranges, special-use addresses, and public targets with the option enabled and disabled. Verify that HTTP and CONNECT requests still enforce destination allowlists and denylists, and update the CLI help snapshot.
GitOrigin-RevId: b7c9cc7da0e0f545694a6521b74c9b36b7b92769
## Why
System libcurl needs access to `com.apple.TrustEvaluationAgent` for TLS, but Seatbelt network profiles did not allow lookup of this service.
## What changed
Allow `mach-lookup` for this service when unrestricted networking is enabled or a restricted profile permits proxy ports or local binding. Keep access denied for network-disabled, Unix-socket-only, and managed profiles without usable endpoints.
## Testing
Add macOS regression tests that apply Seatbelt policies and check trust-service access and loopback connections without external network dependencies. Cover managed-network overrides and verify that unrelated service lookups and connections to unapproved ports remain denied.
GitOrigin-RevId: 8b190d6181fe1321186837557caa379275abfaee
## What changed
- Use the compact title, version, and directory layout for all session headers, including resume, fork, and clear-screen flows. Remove the boxed model row and retain the optional greeting and YOLO permissions indicator.
- Share title styling with the status card and honor the active render mode and wrapping policy when inserting a fresh header after clearing the screen.
## Testing
Update header and startup snapshots for the borderless layout, narrow widths, and halfwidth directory characters. Add assertions that clearing history preserves the raw header in raw output mode.
GitOrigin-RevId: 0b91c1ce6646f9d9d1954b1442936abe93bdcd3c
## Why
Hiding an already-visible working tip during mouse selection shifts the transcript layout and disrupts selection.
## What changed
Keep displayed working tips visible while interacting with the transcript or scrolling away from the latest output. Initial tip display and completion tips still require an idle viewport following the latest output.
Check usage notices directly when suppressing tips so a tip cannot appear merely because interaction temporarily hides the composer warning.
## Testing
Add a mouse-selection regression test and snapshot covering deferred initial display, stable transcript rows through mouse down, drag, and release, correct selected text, and continued tip suppression when a usage warning is hidden during interaction.
GitOrigin-RevId: 3cee527f3a7daaccecbeedbdf083c61075dfa32f
## Why
Inline `$0$` was left unrendered, and expressions containing `\bigwedge`, `\bigl`, or `\bigr` fell back to raw LaTeX.
## What changed
- Allow `$0$` through the inline math detection heuristic.
- Render `\bigwedge` as `⋀`, with limits stacked above and below in display math.
- Handle `\bigl` and `\bigr` like `\left` and `\right`.
## Testing
Add a regression snapshot covering inline zero, inline big wedge, and a multiline display expression with stacked limits and delimiters.
GitOrigin-RevId: 89f596ea5f38070274505cfa7ea757595d7ae137
## Why
Copied table selections became code blocks containing the rendered grid, losing table structure. Stripping trailing whitespace from completed responses also removed Markdown hard breaks and spaces in code.
## What changed
- Reconstruct Markdown tables from selected cells across grid and record layouts, preserving alignment, inline formatting, and list or blockquote nesting.
- Copy a single selected cell as inline content and leave unselected cells empty without adding their text. Escape literal pipes in table code spans and link destinations.
- Preserve trailing whitespace on lines unchanged by assistant directive removal.
- Keep blank rows in copied text without painting newline selection highlights on empty rows.
## Testing
Add regression coverage for wrapped and rewrapped tables, partial selections, empty cells, literal pipes, and separate table and code blocks. Update snapshots for nested tables and selection highlights, and verify completed-response copying preserves hard breaks and code whitespace.
GitOrigin-RevId: 661e4c8331f2737bedff286548f9343bac44e0cb
## Why
Clicking the welcome blossom replays its animation, but completion abruptly switches from full color to the dim idle frame.
## What changed
Fade the blossom back to idle opacity over 400 ms after the replay finishes spinning. Keep scheduling redraws until the fade completes, then clear the replay state.
## Testing
Extend the replay test with color snapshots at the start, midpoint, and end of the fade, and assertions that redraws stop and the original idle frame is restored.
GitOrigin-RevId: ec3fafb6766533d9c221913e8a3be03b8a8036f7
## Why
When browser sign-in does not open automatically, users need to copy the login URL. Onboarding should also allow terminal selection of login URLs and device codes in fullscreen mode.
## What changed
- Add a `c` shortcut to copy the browser sign-in URL, with status messages for pending, successful, unconfirmed, busy, and failed clipboard requests.
- Apply asynchronous clipboard results only to the matching login attempt.
- Disable mouse capture during onboarding so the terminal can select text, and restore the previous input policy afterward.
## Testing
Update the narrow-screen login snapshot to show the copy shortcut and extend mouse-policy coverage to verify onboarding leaves mouse capture disabled.
GitOrigin-RevId: 01676b737efb192d900da306cd2c6b32f791ceb9
Identify the failing setup step when starting, completing, or verifying managed runtime package registration, granting metadata permissions, or persisting the completed registration. Preserve the underlying errors with `anyhow::Context`.
GitOrigin-RevId: 85f712faf2519e95704d7e8cea15d2deeed0d51e
## What changed
- Show a compact session header with a randomly selected greeting, preserving the greeting and blossom state from startup into the live session.
- Center a settled blossom in unused fullscreen space and replay its animation on click. Hide it while typing or when space is insufficient, and respect `tui.animations` and `tui.effects.welcome`.
- Hide startup tips in the fullscreen transcript while retaining them in terminal scrollback, and prevent hidden entries from shifting the first visible header.
- Keep the composer visible and responsive during daemon startup, routing startup diagnostics through tracing while direct lifecycle commands retain stderr output.
## Testing
Add regression tests and update snapshots for blossom placement and click replay, welcome opt-outs, greeting stability, startup transitions, tip visibility, and transcript spacing.
GitOrigin-RevId: ec7b082fbe25ced1180cad3348f5c76e48c0e92b
## Why
Steering an active WebSocket response previously dropped the connection and
resent the full history. Draining the response preserves the connection and
allows the follow-up request to continue with `previous_response_id`.
## What changed
- Drain WebSocket responses when steering. For models using
`use_responses_lite`, first send `response.interrupt` with
`mode: "discard_partial_items"` once the response ID is available.
- Treat `response.incomplete` with reason `interrupted` as completion with
`end_turn: false`, preserving token usage and allowing the turn to continue.
Other incomplete reasons remain errors.
## Testing
Update the steering integration test to cover completed and discarded reasoning
items, asserting connection reuse, incremental follow-up input, and token usage
from the interrupted response.
GitOrigin-RevId: bc714b713e797cf1a67e3b26ffbf7664cb92eb33
## Why
Local daemons use a remote request handle even though their login callback is local, so the TUI skipped opening the browser. Login completion could also arrive while the browser was opening, before the TUI had recorded the active login.
## What changed
- Use `AppServerTarget` to open the login URL for embedded servers and local daemons, while continuing to skip automatic browser opening for remote workspaces.
- Set the pending login state and schedule a frame before opening the browser so completion notifications can match the active login.
## Testing
Add regression tests for browser opening across embedded, local daemon, and remote targets, and for login completion during browser opening.
GitOrigin-RevId: 3feceb877e6131bfd0671c3556314c6c7fd4a677
## Why
Windows launchers such as `cargo run` can prevent background processes from outliving them, causing automatic daemon startup to fail and blocking the CLI from opening.
## What changed
- Classify detached launch restrictions by retrying an access-denied launch probe without the job breakaway flag. Keep both probes suspended and terminate and reap successful probes.
- Use the embedded server with a visible warning when automatic startup encounters this restriction. Preserve errors for other launch failures, including inaccessible executables and elevated startup.
- Keep explicit daemon lifecycle operations failing on the restriction, with guidance to build and run `codex.exe` directly.
## Testing
Add Windows coverage for restriction classification and executable access failures, plus a CLI integration test and warning snapshot for embedded fallback under a restrictive job. The integration test also checks that elevated startup still fails and no daemon PID file is created.
GitOrigin-RevId: fc7c46e0f5f07ca0aba12b535a0e372021bdf46a
## What changed
- Reject unsupported flowchart shapes and Markdown strings so the terminal renderer preserves the source with an unsupported-feature notice instead of misrendering it. Keep ordinary quoted labels containing shape-like punctuation valid.
- Preserve class relationship targets beginning with `o`, such as `A --orange`, instead of consuming the first letter as an aggregation marker.
- Accumulate state aliases and descriptions in source order: use the first as the title and subsequent entries as body rows, preserving state identity and limiting body rows to 16.
## Testing
Add parser regressions for these cases and description limits, update class and state snapshots, and extend TUI snapshots to verify source preservation for unsupported flowchart syntax.
GitOrigin-RevId: c44d954312c77229a3752a0d9ada14e34a43a376
## Why
Piped child processes launched from a detached Windows process should not allocate a console window.
## What changed
Set `CREATE_NO_WINDOW` by default for `codex-rs/utils/pty` child commands. Preserve it alongside `CREATE_SUSPENDED` when preparing a child for Job Object containment, since Tokio's `creation_flags` replaces existing flags.
## Testing
Add a Windows regression test that runs from a detached process and verifies that children have no console window and retain working piped stdin and stdout, both with and without Job Object containment.
GitOrigin-RevId: 990386032d74fa783a66bb20faff769539ea41c1
## What changed
Make `tui.copy_on_select = "auto"` copy on mouse release unless a direct terminal is known to forward its native copy shortcut: Ghostty with a parsed version at least `1.2.0`, Kitty on macOS, Windows Terminal, or VS Code on Windows.
Unknown terminals and Ghostty with older, missing, or unrecognized versions now default to copying. Keep copying enabled under tmux/Zellij and preserve explicit `always` and `never` overrides. Update the configuration documentation and schema to describe these defaults.
## Testing
Expand the existing configuration test matrix to cover more terminals, Ghostty versions (including `1.2.0-dev`), platform-specific defaults, and multiplexer behavior alongside configuration and launch overrides.
GitOrigin-RevId: 410abfa580156454b0f88e0bf4ed977fb8c81b1e
## Why
Changes in executor availability can alter cloud skill catalog rendering under a shared budget and repeat an unchanged executor catalog when it reconnects.
## What changed
- Cap cloud skills at three quarters of the metadata budget initially, leaving the remaining budget and unused cloud allowance for filesystem skills. Reduce the cloud cap only when doing so allows all skill entries to fit; description truncation alone does not trigger rebalancing.
- Persist the allocation across disconnects, compaction, and thread resume. Recompute it when the cloud inventory or total budget changes.
- Emit a short availability update when an unchanged selected-environment catalog returns and its full text remains in history. Reinject the full catalog when that text is missing.
## Testing
Add coverage for allocation stability, catalog and budget changes, omission handling, and full catalog reinjection after compaction and resume. Extend the selected capability stack test to verify reconnection avoids repeating the catalog.
GitOrigin-RevId: 839fe98024e00c4082a46e6a40675e15fd2c16c6
## What changed
- Show a random tip beneath the working status after 30 seconds, using the existing tooltip catalog and current key bindings.
- Show completion tips only after successful turns with a final answer, starting with the third turn and spacing displayed tips by at least three turn starts. Limit completion tips to two per app session, and skip them when a working tip was already shown for that turn.
- Respect `tui.show_tooltips`, hide tips during composer or transcript interactions, and omit tips when space is insufficient. Count exposure only when a tip is rendered.
- Anchor completion tips after queued history updates, keep them outside transcript selection and search, and dismiss them on history replay or transcript clearing.
## Testing
Add lifecycle tests for timing, completion cadence, duplicate notifications, failed and interrupted turns, and hidden tips. Add rendering snapshots and assertions for completion ordering, resizing, limited terminal space, and exclusion from transcript selection and search.
GitOrigin-RevId: 9e956f5b0377e3be71f9574639c3c6ef11ad1168
## What changed
Print `To reconnect, run:` followed by the indented resume command on its own line in disconnect exit summaries. Update CLI expectations and TUI snapshots for the new layout, and adjust the remote reconnect test to parse the command from its new line.
GitOrigin-RevId: 46f05084482063cf4f196b3b49471f331bc91384
## Why
Destination-only filtering stripped raw tool result metadata and MCP attribution when the built-in OpenAI provider used a custom endpoint.
## What changed
Add a runtime-only `include_internal_metadata` grant to `ModelProviderInfo` and enable it for the built-in OpenAI provider. Apply the provider grant or the existing first-party HTTPS destination check to both HTTP and WebSocket Responses requests.
Keep the grant out of serialized configuration and schemas, and default it to false for providers received through remote configuration. Providers without the grant retain the existing destination filtering.
## Testing
Update HTTP and WebSocket tests to expect metadata at overridden OpenAI endpoints. Cover provider grants, destination filtering, MCP attribution on requests, and the grant's exclusion from TOML serialization and configuration.
GitOrigin-RevId: 53aad6fb4d52cdfa9c79c6d92fe87383e1d0d1ef
## Why
The five-attempt limit could stop reconnection before the existing 120-second budget expired, preventing recovery from longer temporary failures.
## What changed
Continue retrying with an eight-second delay after the initial backoff until reconnection succeeds or the shared deadline expires.
## Testing
Update the exhaustion test to require the full 120-second budget. Extend the integration test to recover after five failed `thread/resume` attempts and verify draft preservation and notification delivery.
GitOrigin-RevId: 321d4ad100dbec1254bfe8aafd67ff63fb9a6e93
## Why
Detached Windows daemons can inherit the launcher's output pipes, leaving callers waiting for EOF after the launcher exits.
## What changed
Clear inheritance flags on the launcher's standard handles before spawning managed Windows processes. Leave the flags cleared to protect concurrent launches while preserving the child's configured stdio, and tolerate missing or already-closed handles.
## Testing
- Add a Windows regression test verifying that captured launcher output closes while the detached child remains alive and writes to its configured log.
- Give optional MCP startup grace tests more time to complete on slow runners while keeping the pending server's startup timeout longer than the turn timeout.
GitOrigin-RevId: 053e0417793db3c961e738476a05c7467978f339
## What changed
Expose Windows process creation flags on the shared command wrapper and use
`CREATE_NO_WINDOW` when launching local stdio MCP servers, including fallback
launches without Job Object containment. Preserve `CREATE_SUSPENDED` when
assigning the server to a Job Object before execution.
## Testing
Add a Windows regression test covering direct launches and launches through
`cmd.exe`. Verify that the server has no console, initializes successfully,
returns tools, and exits after shutdown.
GitOrigin-RevId: 84475e82999d91a431e09327d4f5639b59c01427
## What changed
Move `response.failed` classification and rate-limit retry-delay parsing into `responses_error.rs`, preserving existing error mappings, fallback messages, and malformed-payload behavior. Replace the inline classification logic in the SSE event handler with `parse_failed_response`.
## Testing
Add regression coverage for missing or malformed failed-response payloads, including invalid values in unused error fields. Move the existing retry-delay parsing tests alongside the extracted parser.
GitOrigin-RevId: 6faa09b3fb312f1990509eef7088c8a086724615
## Why
Compaction using the previous model can inherit the current turn's access program, producing a model/program pair that the server rejects.
## What changed
- Persist `cyber_access_program` in previous-turn settings and restore it during rollout reconstruction.
- Use the previous turn's access program when compacting with its model, preserving an absent program instead of inheriting the current selection.
- Pass the selected access program into local compaction prompts.
## Testing
Add regression coverage for local and remote compaction after model switches, including resume, fork, rollback, and compaction checkpoints. Verify fallback and subsequent sampling use the current model/program pair, and API-key sessions do not inherit access-program authorization.
GitOrigin-RevId: eaa7162e8711446dc9eb1bfff194e711abd54d7e
## Why
When a nested code-mode call's recorded arguments were truncated and attached to an output before its result arrived, the recorder could no longer attach the result metadata to that call.
## What changed
Retain validated call bindings so late result metadata updates the original output across retries and subsequent waits. Keep truncated arguments and incomplete call inventories intact, and apply existing metadata budgets.
Invalidate late metadata bindings when duplicate IDs, reused cells, conflicting outputs, or changed call inventories make attribution ambiguous. Clear stale pending calls when a cell ID is reused, and avoid counting duplicate pending IDs against capacity more than once.
## Testing
Add recorder regression tests for late metadata across retries, compaction, waits, and cell closure, plus ambiguous bindings and budget limits. Add a code-mode integration test that delays a tool result until its truncated call has been recorded and verifies metadata remains attached to the original output across later waits.
GitOrigin-RevId: 7398beaaa1a513147deebdea7aa841513a79d06b
## Why
Sibling tests can spawn children while an executable fixture is open for
writing, allowing inherited writable descriptors to cause `ETXTBSY` when
launching the fixture.
## What changed
Add a shared `copy_executable` helper for the daemon, doctor path safety, and
exec-server tests. On Linux, run `/bin/cp` in a separate process and wait for
it to exit before launching the fixture, then restore the source permissions
to account for restrictive umasks. Keep `std::fs::copy` on other platforms.
GitOrigin-RevId: 88f36826bbc6ab4e16e28ff02d5e7d6bd8dbf793
## Why
Opening a separate-window editor from the fullscreen TUI leaves the alternate screen, hiding the draft and the instruction to save and close the editor.
## What changed
Preserve and repaint the last Codex frame when handing the terminal to an external editor, while releasing keyboard and mouse input modes. Track whether the alternate screen's keyboard mode is active so cleanup does not pop it twice if the editor switches screens. Restore TUI modes and the alternate screen when the editor returns.
## Testing
Add terminal integration coverage for separate-window editors, terminal editors that switch or reuse screens, and inline mode. Verify the visible draft and handoff hint, disabled mouse reporting, edited draft recovery, and continued typing. Add a unit test for balanced keyboard stacks whether or not the editor leaves the alternate screen.
GitOrigin-RevId: c2ff1046a933f5f9e3168663e2c326999845c578
## Why
Yield signals and queued runtime events can detach an observer during termination, before the remaining output has been drained.
## What changed
Track the active yield signal separately from the observer so termination can disable yielding while keeping the observer attached. Ignore `Started`, `Pending`, and `YieldRequested` events during termination, allowing queued output to reach the observer in `CellEvent::Terminated`.
## Testing
Extend the termination regression test with an immediate yield timeout, a canceled yield signal, and queued start, yield, output, and completion events. Assert that both the termination caller and the initial observer receive the queued output in the terminated event.
GitOrigin-RevId: 1c08bdec06838123aaa102268da2f50b63ddea3f
## Why
Closing the warnings viewer dismisses warnings whose pages were displayed. Allow users to keep a warning available for later review while moving through the remaining warnings.
## What changed
- Press `k` to keep the current warning and advance, closing the viewer after the last warning.
- Preserve kept warnings when applying queued dismissal updates, so a later keep decision takes precedence for the same warning details.
- Reserve `k` in the viewer, update footer hints, and suppress key repeats so holding it does not skip warnings or modify the restored draft.
## Testing
Add coverage for keeping warnings, leaving unvisited warnings undismissed, conflicting key bindings, repeated key events, draft preservation, and queued dismissal updates. Update warning footer snapshots.
GitOrigin-RevId: da267b9142ddda78086418192970db2aec370d3a
## Why
Closing the warnings viewer left reviewed diagnostics in the warning badge and subsequent visits, with no way to dismiss them.
## What changed
- Dismiss only warning pages actually rendered when closing with `Esc`, `F2`, or `Ctrl+C`, and update the footer hint to “dismiss & close”. Unviewed warnings remain available.
- Hide dismissed diagnostics from the badge and viewer while their details are unchanged. Updated details make a warning visible again.
- Reset dismissals when clearing the transcript and ignore queued dismissals from an earlier transcript.
- Cache warning counts until transcript cell identities or dismissal decisions change.
## Testing
Add regression coverage for partial dismissal, navigation that skips rendering a page, changed warning details, and transcript resets with queued dismissals. Update snapshots for the close hint and remaining warning count.
GitOrigin-RevId: 3ce88c62a7f0ff9de34062165051e22168d3db25
Move JSON-to-HTTP header conversion from `responses_websocket` into the
crate-wide `responses_headers` module and update the WebSocket code to use it.
Preserve conversion of string, number, and boolean values, while continuing to
ignore invalid header names and unsupported or invalid values.
GitOrigin-RevId: f179de214cf763549b5b8a898dc4bcda3ce07ebd
## Why
Archived threads without previews were filtered out of thread listings, even though they had valid session metadata.
## What changed
- Include archived threads with empty previews in both SQLite and rollout-file listings.
- Add archive-specific indexes for creation, update, and recency ordering so these listings can use indexed pagination.
## Testing
Add regression coverage for paginated archive listings with and without SQLite, archive query plans that avoid temporary sorting, and metadata reads that preserve source and file timestamps for empty archived threads.
GitOrigin-RevId: e29d0257b2e029bea5fdf94eed6dab1006d2a8f2
## Why
An execution environment's enabled proxy configuration was reduced to traffic restrictions, leaving restricted commands offline without a controller proxy or an approved network grant.
## What changed
Carry `NetworkProxyConfig.enabled` into `EnvironmentNetworkPolicy.requires_proxy` and honor it when activating managed networking. This lets environment owners require filtered proxy access while direct network access remains restricted. Policies without an explicit proxy requirement retain the existing activation behavior.
## Testing
Extend remote command coverage to check allowed and denied proxy requests without a controller proxy, and verify that direct network access remains blocked.
GitOrigin-RevId: 7cc0063a0d1118de56b1bd30036338cf14360f6a
Daemon tests repeatedly hash large CLI binaries, even in `fastbuild` mode.
Set `blake3`'s build-script `OPT_LEVEL` to `3` and Rust compiler flag to
`-Copt-level=3` so both the native backends and Rust implementation are optimized.
GitOrigin-RevId: ebf9b96255e68ba775443077ebf3fd897282795d
## Why
Checking notification data size after SSE parsing leaves oversized fields and unterminated frames free to accumulate in the parser. Malformed UTF-8 can also be retained indefinitely by the decoder.
## What changed
Enforce `MAX_BODY` on incoming frame bytes before SSE parsing and reject malformed UTF-8 incrementally. Reset the byte count at blank lines, supporting LF, CR, and CRLF across chunks, so the limit applies per frame rather than per connection. Stop reading the source stream after an error.
## Testing
Extend the remote board contract test to cover oversized readiness fields, unterminated fields, and multiline data frames. Verify that a long sequence of heartbeat frames with all three line endings still permits notification delivery.
GitOrigin-RevId: c3a95ead88f53e7acfb28c5ba23141bc11d25532
## Why
Sourced snapshots parse options and aliases as a group before restored options take effect. Aliases serialized with `RC_QUOTES` enabled can therefore be misinterpreted by the replay shell.
## What changed
Serialize zsh aliases for sourced snapshots with `NO_RC_QUOTES` in a subshell, preserving the captured shell options and avoiding a dependency on the optional `zsh/parameter` module.
## Testing
Extend regression coverage to execute restored aliases with `RC_QUOTES` enabled and disabled across source and eval replay. Expand macOS zsh concurrent replay tests to cover quoted aliases, preserved options, and blocked descriptor paths with and without a TTY.
GitOrigin-RevId: 48086f380c21318bece9226dfe6486c179c2a440
## Why
AWS profiles can select credential helpers that the application executes. Granting write access to a containing directory should therefore keep `.aws` protected by default.
## What changed
Add `.aws` to the protected metadata paths alongside `.git`, `.agents`, and `.codex`, including workspace roots and additional writable roots. Preserve explicit user rules that override the default protection.
## Testing
Extend policy and sandbox tests to cover `.aws` protection. Add macOS coverage for existing and absent `.aws` directories, deletion and replacement attempts, and symlink targets. Verify that Linux sandbox writes to protected configuration files fail while sibling files remain writable.
GitOrigin-RevId: 31ea287bd0dd9b13aff893783fba9ca3aed0c89d
## Why
Usage limit errors discarded the server-selected window responsible for the limit, leaving turn and compaction analytics unable to distinguish five-hour limits from weekly limits.
## What changed
Preserve optional `limit_window_minutes` from usage limit error responses in `UsageLimitReachedError` and report it as `usage_limit_window_minutes` in turn and compaction events. Accept unsigned integers that fit in `u16`; treat missing, null, malformed, or out-of-range values as unknown. Events for other error kinds report `null`.
## Testing
Add coverage for HTTP and wrapped WebSocket error mapping, analytics serialization and reduction, and app-server propagation to turn and local/remote compaction events. Cases include five-hour and weekly windows, missing or invalid values, and unrelated errors.
GitOrigin-RevId: a32066a007559d91a3c868a756bfd0f976777176
## Why
Threads sharing an executor and sandbox retries can reuse a public process handle while the executor still retains the previous process.
## What changed
Always append a fresh UUID to the exec-server process ID, including requests without sandbox or shell snapshot settings, to avoid collisions when handles are reused.
## Testing
Update the request-parameter test to check the UUID-suffixed format and verify that repeated calls with the same handle produce distinct process IDs.
GitOrigin-RevId: bd1fc9af3e7d5ea99fdf88382df09afa7dc9f72b
## Why
Complete assistant messages with empty text can produce misleading omitted-context notices in Guardian reviews.
## What changed
- Skip complete, empty assistant messages when recording and rendering retained context, while preserving omission notices for incomplete messages.
- Separate retained instruction fragments with blank lines and keep blank lines free of role prefixes, while labeling every nonempty line with its original role.
- Update source-order guidance detection and empty-section deduplication for the added spacing.
## Testing
Extend retained-context tests to cover empty completed messages across resume, restored empty messages, incomplete-message notices, blank-line spacing, and role labeling. Update Guardian prompt snapshots.
GitOrigin-RevId: e945717b18689fa4538d9b617b89a644858ab1c8
## Why
A Windows breakaway launch can leave an outer Job Object attached after escaping an inner job. Job membership alone does not establish whether the daemon will be terminated, so rejecting all remaining membership can block valid launches.
## What changed
Remove the job-membership checks from the launch preflight and the spawned daemon. Keep the suspended breakaway probe to verify that launch is permitted before stopping an existing daemon, and terminate and reap the probe afterward.
## Testing
Add a Windows regression test with nested jobs that verifies the probe and daemon leave the inner job while retaining the outer job, and that daemon startup succeeds.
GitOrigin-RevId: 4c6aafd158300fa428ec398d72dc5d3411c0d8b8
## Why
Approved commands need broader write access while retaining explicit read denials. On Linux, binding the filesystem root writable can shadow standard devices, and additional root-metadata mounts can reopen denied symlink targets.
## What changed
- Add `FileSystemSandboxPolicy::for_approved_command` to grant root and root-metadata writes while retaining path and glob denials. Keep the original policy when denials cannot be resolved or deny the root.
- Restore standard devices after Linux writable root binds, then apply explicit deny masks. Avoid redundant root-alias binds and inherit root-metadata writes from the root mount so denied targets stay masked.
- Preserve literal deny paths alongside resolved targets so Linux can reject denials that cross writable symlinks.
- Advertise Linux device and approved-root restriction support through two opt-in exec-server capabilities, omitted from serialization when false.
## Testing
Add regression coverage for approval policy materialization across Unix, Windows drive, and UNC paths; Windows volume expansion; Linux device access and metadata symlink restrictions; and capability serialization compatibility.
GitOrigin-RevId: 40584473da98a15e606bb1a8934308f69528850f
## What changed
Allow `cursor` to accept an item anchor such as `{"type":"item","itemId":"item-123"}` with a non-empty `turnId`. Ascending pagination returns items after the anchor; descending pagination returns items before it. The anchor itself is excluded, and subsequent pages use the returned opaque string cursor.
Resolve anchors within the requested turn's visible history, including inherited fork history. Reject missing turn IDs and empty, unknown, or out-of-scope item IDs with invalid params (`-32602`). Preserve existing string and null cursor behavior, and update the protocol schemas, TypeScript and Python types, and API documentation.
## Testing
Add protocol round-trip and invalid-shape tests, app-server coverage for anchored pagination and errors, and thread-store coverage for growing turns, reverse pagination, page boundaries, fork visibility, and anchor scope validation.
GitOrigin-RevId: a74cea190d3ff1b44865429f8b0650b793eb688d
## Why
Cached executor MCP declarations must not gain access to host environment credentials when reconnecting to an executor that lacks environment credential resolution.
## What changed
- Retain credential policy through MCP registration, catalog materialization, and runtime setup. Derive selected HTTP plugin policy from the plugin's source environment.
- Reject host bearer-token fallback and transports requiring host environment headers or helpers for executor-owned declarations. Preserve host-configured credential resolution.
- Include credential policy in connection and tool catalog cache identities, and avoid reading host environment values for executor-only identities.
## Testing
Add regression coverage for legacy executors, cached declarations after a capability downgrade, policy preservation through catalog rebuilds, and connection and tool cache isolation.
GitOrigin-RevId: 2d5b85e4e98668c637c538cbe528914c936bd831
## Why
With `instant_interrupt` enabled, new user input should reach the model without waiting for an unfinished response or stream retry backoff.
## What changed
- Interrupt request setup, response streaming, and retry backoff when user input arrives, then continue the turn with the queued input.
- Reset the WebSocket connection and continuation state after preemption so the next request sends full history.
- Drain pending input after a preempted step even when compaction leaves the estimated context above the token limit.
## Testing
Add regression coverage for WebSocket reconnection with full history, interrupted retry backoff, input queued during compaction, and yielding running code-mode calls. Add a streaming scenario that preserves completed commentary while excluding unfinished assistant text from the replacement request.
GitOrigin-RevId: b7e42b6afffbf87da15af05e0850af8579d1353f
Set `CREATE_NO_WINDOW` when launching the code-mode host on Windows so the
child process does not create a console window.
GitOrigin-RevId: ce0d04d7f516d137bcaf5206140aaeaa23334022
## Why
User input queued during a long-running code-mode `exec` or `wait` can remain pending until the call returns. Allow these calls to yield early so Codex can receive the new input while the cell continues running.
## What changed
- Add the `instant_interrupt` feature flag, disabled by default.
- Watch queued user input for each sampling request and pass a shared preemption signal to code-mode `exec` and `wait` calls, including calls received later in the same response.
- Yield running cell IDs without stopping the cells, allowing subsequent `wait` calls to collect their results.
## Testing
Add integration coverage for enabled and disabled behavior, repeated steering during `exec` and `wait`, input deferred during compaction, and later calls in the same response. Verify that direct tool results and queued user messages are preserved, and add a scenario snapshot showing continuation after a cell yields.
GitOrigin-RevId: e33466a980d98e113bfb6c6a45c59de0cc7b3c1d
## What changed
- Let `Left` return to the command center from a conversation open in another app, including while disconnected, without discarding the retained draft.
- Respect editor and Vim keymaps, conflicting shortcuts, and chord prefixes before enabling this navigation.
- Show `←/esc` in the command center hint when `Left` is available; otherwise keep `esc`.
## Testing
Add regression coverage for connected and disconnected navigation, draft preservation, and remapped `Left` with Vim enabled or disabled. Extend attach-conflict coverage to verify that both `Left` and `Esc` preserve the command center selection, and update footer snapshots.
GitOrigin-RevId: 80ef004b548176443ebee03c2a143e723e54c44a
## What changed
Update `each_loader_owns_refresh_until_its_last_clone_is_dropped` to use
`SequenceBundleClient` request notifications and Tokio timeouts instead of
request-count polling with wall-clock deadlines. Await refresh requests from
both loader owners together while retaining the assertions that each refresh
task stops when its last loader clone is dropped.
GitOrigin-RevId: 5fea595fa67d5348a23f59033502e012406a2bd1
## What changed
Add an optional `preempt` signal to `CodeModeSession::execute` and `CodeModeSession::wait` so callers can end an observation early while the cell continues running and remains available for later waits.
Support the signal in the in-process runtime and across both remote transports: `operation/yield` with the negotiated `yield-observation` capability for stdio, and `YieldObservation` for gRPC. Preserve signals received before gRPC observation registration, and retain normal timeout behavior for older hosts that lack support.
## Testing
Add runtime and transport tests covering early execute and wait yields followed by successful cell completion, yields before observation registration, and suppression of yield frames for older stdio hosts.
GitOrigin-RevId: 3f8049d8f0582be6b8f0832cc03f2d974a0b8f18
## Why
Starting a new session from the command center could clear the startup composer or replace it with `Loading task` before the attached chat was ready to render.
## What changed
Show the startup draft immediately and skip loading frames while it is present. Reset transcript state without clearing the visible draft, deferring the terminal clear until the next synchronized draw. Preserve this behavior during resize reflow as well.
## Testing
Add a regression test and snapshot covering inline and owned-screen modes. Verify that draft text survives the handoff, queued events leave the startup frame intact, and the attached composer retains the draft.
GitOrigin-RevId: 26a7ba2929a3b46537da960cbb7201b21b5dc61f
## Why
The worker's completion notice can interrupt the root's one-shot question response before the messaging call reaches its cancellation point in `guardian_subagent_review_preserves_late_root_user_authorization`.
## What changed
Gate the worker's initial response with a `oneshot` channel and a streaming SSE server. Release it after the root's question turn completes or its cancellation is observed, then wait for worker completion and shut down the server.
GitOrigin-RevId: d7f287557a7c27f1054c7ae90ba331ff26bba8ef
## What changed
- Add `tui.right_click_paste` with `auto`, `on`, and `off` modes. The default `auto` enables the fallback on Windows and Linux, including WSL when terminal detection is conclusive. `on` also enables macOS. Both modes skip SSH sessions and recognized VS Code terminals.
- Paste clipboard text through the normal composer input path when no selection, search, or blocking view takes precedence. Discard pending results after intervening input, focus loss, or changes to the target thread, draft, or cursor.
- Read text asynchronously through the shared clipboard worker, with a five-second deadline and the message size limit. Read the Windows clipboard through PowerShell on WSL and reject overlapping clipboard operations.
## Testing
Add coverage for platform and terminal policy, normal paste delivery, stale reads, overlapping clipboard operations, read timeouts, oversized text, and large command output.
GitOrigin-RevId: 0a7b6d445c09928da6c5335841ba2a9a66cc7e4b
## Why
Reasoning shortcuts stopped before Max even when the active model supported it, requiring users to open the advanced-reasoning picker.
## What changed
Allow `Alt+.` and `Shift+Up` to raise reasoning to Max in default and Plan modes. Keep Ultra behind the explicit picker and update the guidance to mention only Ultra.
## Testing
Add coverage for both shortcuts reaching Max in both modes, with footer snapshots. Update the Ultra boundary test to verify that raising from Max shows picker guidance without changing reasoning effort.
GitOrigin-RevId: 4e5ef2866f118a1f59313d494a2383db43293da9
## Why
Local compaction flattened retained user messages into a single text part, losing their original content boundaries and per-part annotations.
## What changed
Preserve the original content parts and annotations for text-only user messages that fit within the token budget. Borrow the original messages until selected history entries are materialized, and rebuild only the text fallback for truncated messages or messages containing media.
## Testing
Extend unit coverage for text boundaries, empty parts, omitted media, and retained metadata. Update the compaction integration test to verify that a multipart user message survives unchanged in the next request and retains its content parts and annotations in persisted replacement history.
GitOrigin-RevId: 39d9df9ae5360506c2a4bdeac76d89198dbbd39c
## Why
Async Guardian requests include retained user instructions even when complete copies are already present in the same request's transcript.
## What changed
- Include retained source metadata and order labels in async user transcript entries.
- Omit retained instructions when the current transcript contains the same complete source revision. Keep ordering guidance in every async sample and never rely on previous samples for deduplication.
- Preserve retained originals when transcript copies are incomplete or lack source metadata.
## Testing
Extend retained-instruction tests to cover async deduplication, preservation of originals without complete source proof, and budget protection. Update async scorer expectations for source order labels and deduplicated instructions.
GitOrigin-RevId: 7029731b296d2342eea4ad74ffa9d3447578d83e
## Why
Synchronous Guardian reviews can include the same user instruction in both the retained instructions section and the conversation transcript. Avoid this duplication while preserving complete authorization evidence and its original acceptance order.
## What changed
- Carry retained source metadata into transcript rendering. Omit a retained instruction when the transcript delivers its complete matching source revision.
- Label qualifying transcript entries with retained source order and protect them from budget truncation. Keep separate retained instructions when source metadata is missing or incomplete.
- Track delivery of source-order guidance so it remains available even when all retained instructions are delivered through the transcript. Invalidate that delivery proof when messages are shortened.
## Testing
Add coverage for complete-source deduplication, missing or incomplete metadata, budget protection, guidance redelivery, and source metadata preservation across resume. Update Guardian review assertions and snapshots to verify instructions are delivered once.
GitOrigin-RevId: 20ad0304501fa49f1596c4cfaf3ef89d64815753
## Why
`/ps` previously showed only the first line of each background command, hiding useful details when a command began with an opening parenthesis.
## What changed
Render LF and CRLF line breaks as `↵` in command previews. Include subsequent lines within the existing 80-grapheme limit, and show the truncation marker only when the command exceeds that limit.
## Testing
Update snapshot coverage for multiline commands, including parenthesized commands and CRLF line endings, and add a snapshot for a multiline command exceeding the preview limit.
GitOrigin-RevId: 92544e5636821fc94bc1ca4af389c3c646127c0e
## What changed
Add `codex-agent-message-board-client` with a `RemoteAgentMessageBoard` implementation of the existing `AgentMessageBoard` interface over a versioned HTTP API. Use the shared HTTP client for authenticated board creation, deletion, member registration, and board operations.
Validate endpoints and credentials, bound request and response sizes, and support a caller-supplied clock. Allow post retries without a fresh timestamp so the service can replay an already committed result.
Provide live SSE receivers that wait for readiness and reject notifications for another agent or turn, as well as previews exceeding 150 characters.
## Testing
Add a mock HTTP integration test covering endpoint and returned-credential validation, bearer authentication, post retries when the clock is unavailable, Unicode post reads, SSE readiness and notification validation, and service error handling.
GitOrigin-RevId: 844f63ee14dc216a9d61767115892c4783fe9d44
## Why
Legacy shell snapshots could retain exports excluded by `shell_environment_policy` and restore captured values over explicit overrides when replayed.
## What changed
- Build snapshots with the resolved environment's policy and omit filtered exports and original values for variables overridden by `set`.
- Skip eager snapshot creation when configuration is unavailable, and reject snapshots whose policy differs from the current turn's policy.
## Testing
Add a regression test covering default and custom exclusions, `include_only`, preservation of multiline values, and `set` overrides that survive snapshot replay. Verify excluded and overridden captured values are absent from the snapshot file.
GitOrigin-RevId: 4b785130f6c5a4d268ab86fd36ab9d77d8c4a3b9
## Why
User messages could fill the root context limit before assistant questions were considered, while commentary could displace relevant conversational context. Guardian needs that context to interpret user authorization when reviewing subagent actions.
## What changed
- Select recent user and assistant evidence together under a shared message limit, discarding assistants with unknown ordering first.
- Exclude explicit assistant commentary and retain message phases across compaction. For older retained records, check available source messages for commentary phases.
- Mark missing instructions or assistant context when the shared limit removes corresponding evidence, and use remaining space for legacy instructions.
## Testing
Update Guardian authorization tests to cover shared message limits, commentary filtering across compaction and resume, and preservation of ordered replies when legacy assistant context has unknown ordering.
GitOrigin-RevId: c369a2760917cba9d7dfca37fb5e85a7ec49012f
## Why
Large shell snapshots need a replay path that does not add their state to the child process environment.
## What changed
- Keep captured state cached in memory and give each Bash or Zsh launch an independent, read-only file descriptor to source. Unlink the file before writing shell state, create it under the sandbox-protected daemon directory, and close the carrier descriptor before restoring functions.
- Probe descriptor-path access inside the capture sandbox. Retain environment replay for `sh` and when descriptor paths are unavailable; use normal shell startup if preparing the replay file fails.
- Group options and aliases during capture so sourcing preserves their parsing behavior.
## Testing
Add coverage for concurrent replays with 480 KiB payloads, pipe and TTY execution, stdin preservation, descriptor cleanup, sandbox protection, blocked descriptor-path fallback, and alias/option parsing equivalence.
GitOrigin-RevId: 8103d5c37ce4d1885628a4efba3551549f12bea8
Derive `Serialize` and `Deserialize` for `CreateChannelRequest`,
`ReadPostRequest`, and `SubscriptionRequest`.
GitOrigin-RevId: 7da638c029f7d57b59e865a3a45ae80924780fba
## Why
Runtime filesystem grants, such as those used for plugin metrics, could trigger unnecessary approval for `write_stdin` and prevent input when sandbox approval was disabled.
## What changed
Include retained runtime grants in the baseline permission comparison for stdin review. Continue requiring review for additional agent permissions, sandbox bypasses, and policy changes. Update the approval description to report current permissions when only runtime grants are present.
## Testing
Extend unit coverage to ensure runtime grants do not require review or mask agent filesystem and network grants, and that sandbox bypasses still require review. Add local and remote plugin regression cases that send stdin and verify metric emission with sandbox approval disabled.
GitOrigin-RevId: 989098bdc7fbf839786c01f11cbf02999bae1cc1
## What changed
Return post metadata from the in-memory message board after updating board state when no notification recipients remain. This avoids constructing an unused notification preview, including when the author is the only requested recipient.
## Testing
Run the existing post-and-search model-context scenario against both disk and in-memory message boards, checking that post metadata and search results reach the model without self-notifications.
GitOrigin-RevId: dcf07a5fd55738fbcd6edd3dce3f6fb8fc910eaf
## Why
The network command can yield before its request reaches Guardian, allowing a parent request to consume the mock response intended for Guardian.
## What changed
Update `guardian_receives_exact_trigger_for_single_network_request` to match parent and Guardian requests separately. Have the parent poll running processes with `write_stdin` until they exit, and bound the wait for turn completion to 30 seconds. Preserve the assertion that Guardian receives exactly the original call ID and command.
GitOrigin-RevId: f39e9461c3628fbab00ba241f828d318b17975b5
## Why
Reused Guardian sessions already contain previously delivered instructions. Follow-up reviews can avoid repeating that evidence, but must deliver it again if it changes or compaction removes it.
## What changed
- Track retained source identity, revision, and completeness in host-owned history metadata, preserving revisions during replay.
- Omit retained instructions from synchronous review inputs only when the same complete revision remains in reviewer history.
- Restore missing evidence after reviewer compaction, enforcing the request budget before persisting additions. Classify restored evidence as context rather than new user authorization.
- Keep source-order labels stable across eviction and retain full delivery for legacy records without reliable provenance.
## Testing
Add coverage for consecutive-review deduplication, changed revisions, missing or incomplete metadata, and restoring compacted evidence exactly once. Extend compaction and resume coverage to verify retained revisions.
GitOrigin-RevId: e90fca16cde0a0970da36dd873af2ca1dbaaf4d3
## What changed
- Stop sending `includeExtensions=true` when fetching installed plugins and remove extension metadata from remote plugin models.
- Remove `PluginSummary.extensions` and the associated extension declaration types from the app-server protocol.
- Update generated JSON schemas, TypeScript and Python bindings, and precomputed protocol exports to match.
GitOrigin-RevId: 56509437b6bdf58d99badff68e86bcf7f09fe036
## What changed
Add app-server integration coverage for awaiting `request_permissions` and then running `exec_command` in the same code-mode cell:
- Verify that turn- and session-scoped write grants allow the command to create a file, including grant propagation to Windows command approval requests.
- Verify that `strictAutoReview` immediately triggers review for a command needing no additional access and returns the reviewer's denial rationale.
GitOrigin-RevId: 02c958071db4e9ba667be9ba95fbb3a506ae1572
## Why
Tool suggestions could pass unchecked `install_url` values to the app link view for opening in a browser.
## What changed
Reuse the external URL validator to require HTTPS URLs with a host and no embedded credentials. Decline suggestions with invalid URLs on the requesting thread without showing a popup.
## Testing
Add a regression test covering malformed URLs, unsupported schemes, embedded credentials, and a valid HTTPS URL. Verify that rejected suggestions leave the popup unchanged and resolve on the requesting thread, while the valid URL opens on confirmation.
GitOrigin-RevId: e47bf09868ec81aeaf1ffed8330039b69c60e093
## Why
The sample hardcoded file-based credential storage and omitted configured auth routing and login restrictions. It should use the configured credentials, including secure storage in `cargo run` builds.
## What changed
- Load authentication settings through the shared bootstrap path and re-export the required helpers and types from `codex-core-api`.
- Honor CLI and MCP credential stores, `features.secret_auth_storage`, auth routing, the ChatGPT base URL, and system proxy settings.
- Preserve managed login-method and ChatGPT workspace restrictions while keeping the sample's built-in execution settings.
- Document the sample's authentication configuration behavior.
GitOrigin-RevId: b49883537acbebf9266b3970d2709e8e7d1bf217
## Why
When a container denies fresh `/proc` mounts, the existing sandbox fallback retains the caller's `/proc` while creating a new PID namespace. Process IDs inside the sandbox can then differ from those exposed by `/proc`, breaking process lookups.
## What changed
- Add `codex exec-server --linux-sandbox-pid-namespace=inherit` to reuse the caller's PID namespace and `/proc` for both process and filesystem helpers. Repository config and command environment variables cannot enable it.
- Keep `isolate` as the default, preserving the existing mount fallback and compatibility with older helpers. Inheritance requires an updated helper and omits `--unshare-pid` and `--as-pid-1`.
- Preserve other sandbox restrictions. With `:minimal`, bind the inherited `/proc` read-only with its container masks and apply explicit filesystem denials afterward.
Inheritance is intended for dedicated environments: it allows sandboxed commands to signal other same-UID processes, including the executor.
## Testing
Add unit and integration coverage for namespace flags, denied proc mounts, consistent process IDs, retained sandbox restrictions, and startup-only selection across process and filesystem helpers.
GitOrigin-RevId: dd13f2b9286d7edcf366b3a42a455f4d78daaf27
## Why
Refreshing the MCP catalog with unchanged tool metadata recreated handlers and forced the tool search index to rebuild.
## What changed
Cache handlers by canonical tool name and reuse them when tool metadata, agent plugin status, and the input schema size limit are unchanged. Replace handlers when those inputs change and evict tools removed from the catalog, preserving search index reuse across equivalent bindings.
## Testing
Extend the deferred tool world state test to verify that an unchanged catalog refresh captures a new binding without rebuilding the search index, and that removing all deferred tools stops advertising `tool_search`.
GitOrigin-RevId: 150866f635e9ee817d7ca44fb76e724a3f7608a5
## What changed
- Record successful spawn phase durations in `codex.multi_agent.spawn.phase.duration_ms`, covering residency reservation and fork context when applicable, child creation, durability waits, input admission, and total latency.
- Count spawn failures from the V1 and V2 tool handlers in `codex.multi_agent.spawn.failure`, grouped by bounded error categories.
- Use bounded labels for fork mode, multi-agent version, product SKU, and successful-spawn history mode. Emit phase timings only after a successful spawn.
## Testing
Add in-memory metrics tests for phase durations and labels, plus a tool-handler test verifying that a thread-limit failure emits one counter increment with the expected labels.
GitOrigin-RevId: 04cba9042b9b34acdf57376ace5288c3f741f3b2
## What changed
Prepare each MCP call from the selected server's current client and catalog instead of building a full runtime binding. Match the advertised tool by server, tool name, and connector ID, and enforce current tool filters and model visibility.
Preserve the advertised `callable_namespace` and `callable_name` while using current schema, annotations, approval metadata, timeout, and permission authority for execution.
GitOrigin-RevId: 703a90926fc72bd446d83ac974162aee6439f363
## Why
Queued voice answers could reappear as text under a newer question when speech failed, the pending queue overflowed, or voice stopped, including answers already spoken as paraphrases.
## What changed
Filter recovered and replayed speech by the current input generation, preserving that generation across conversation resets. Keep text fallbacks for answers still awaiting turn completion so delayed user transcripts do not discard unspoken answers.
## Testing
Add regression coverage for paraphrased answers, queue overflow, stop and replay, failed delivery for current versus superseded input, and delayed transcripts.
GitOrigin-RevId: b7b230910bf4fdb4ae93f7de8ca2222a19c55d7f
## Why
A `.git` pointer can resolve to a Git directory inside another writable root. Broader Seatbelt grants or later bubblewrap mounts can leave that directory writable despite its metadata protections.
## What changed
Include resolved Git directories in read-only exclusions for broader writable roots on Linux and macOS. Resolve symlink aliases when locating exclusion targets and retain explicit policy overrides.
## Testing
Add regression tests for Git directories reached directly or through symlink aliases in another writable root, and for linked worktree metadata under the macOS temporary directory. Verify that metadata writes are denied while ordinary files in the surrounding writable root remain writable.
GitOrigin-RevId: 6971f1cf35008d23eaeb0d02a9c61bee7cf83b12
## What changed
- Recognize `promax` in authentication, account responses, and backend rate limits; update generated schemas and client types.
- Display `prolite` as “Pro”, `pro` as “Pro (More)”, and `promax` as “Pro (Max)” in account labels, status, and analytics.
- Include Pro Max in experimental context eligibility, paid-plan tooltips, and usage-limit guidance for purchasing credits.
## Testing
Extend coverage for Pro Max plan parsing, account and rate-limit responses, experimental context eligibility, and plan display names. Update the login token test to expect “Pro (More)”.
GitOrigin-RevId: 197e00fa7a99cbce125c8f1d43a451ec1ed5c1fb
## Why
`active_turn_environment_selections()` returns the selections captured at turn start, so it does not reflect later environment settings updates.
## What changed
Add `CodexThread::current_turn_environment_selections(expected_turn_id)` to read the running turn's current selections, including environments that are still starting or have failed. Return `None` when the requested turn is no longer active or has been cancelled.
## Testing
Add a regression test covering selection updates, mismatched turn IDs, and completed turns, while verifying that the initial selection snapshot remains unchanged.
GitOrigin-RevId: bb526a686d549209142150ffde99ad1444add205
## Why
Btrfs subvolumes can report an `st_dev` that differs from the device in `/proc/self/mountinfo`, causing daemon socket mount validation to reject valid mounts.
## What changed
Allow the mismatch only when the opened directory and its uniquely identified mount are both verified as Btrfs. Discover socket directory aliases using both device identities while retaining checks that reject unsafe directory and socket bind mounts.
## Testing
Add regression tests for aliases under both device numbers, unverified or inconsistent filesystems, unavailable or missing mount IDs, duplicate mount IDs, and unsafe bind mounts.
GitOrigin-RevId: 921d6465b7a97022573a42412606a26560cc086a
## What changed
- Recognize `flex_unavailable` in HTTP 429 responses and streamed `error` and `response.failed` events. End normal turns without retries and report `Flex capacity unavailable.`
- Expose `flexUnavailable` through the core and app-server protocols and generated schemas and SDK types.
- Keep Flex capacity failures eligible for Guardian review and sampler retries, with a distinct telemetry classification.
- Map unexpected HTTP responses to `HttpConnectionFailed`, preserving their status codes.
## Testing
Add regression coverage for terminal Flex failures over HTTP, SSE, and WebSocket, HTTP 504 status preservation after a stream retry, and protocol serialization. Update Guardian retry and sampler recovery tests to cover Flex failures.
GitOrigin-RevId: f2e03a6d2d36a6d9748c35952e40397f8670d121
## What changed
Keep `x-amzn-mantle-client-agent: codex` in the Amazon Bedrock Runtime provider instead of clearing the headers inherited from the Amazon Bedrock provider.
## Testing
Update provider construction expectations and extend the API provider header test to cover both Amazon Bedrock providers.
GitOrigin-RevId: eab07f347b53f0a6ba2e224a39590f49f181363e
## What changed
- Default `MALLOC_CONF` to `thp:always` for Cargo child processes, including tests and `cargo run`, while preserving an explicitly set value, even if empty.
- Patch `rules_rust` to request transparent huge pages for `codex-rs/` compilation with Linux GNU `rustc` on x86_64 and aarch64. Check policy on the execution worker and enable the setting only when seccomp is disabled, transparent huge pages are permitted, and no allocator, preload, or sanitizer configuration conflicts are detected. Leave the environment unchanged when policy cannot be determined.
GitOrigin-RevId: 3a9b2572ec9e1f30e2f719f30c885914c165eccd
## Why
Removing tool-result metadata alone can leave requests above the 15 MiB message budget when recorded tool calls and arguments occupy the remaining space. If trimming loses calls or arguments from a Code Mode cell, later waits must not report its call inventory as complete.
## What changed
- Bound all optional tool-call observations against the serialized HTTP or WebSocket message size, preserving ordinary tool outputs and continuation history.
- Shed generic result metadata, sources, and recorded arguments before resource-access evidence, retaining tool names and smaller metadata where possible.
- Invalidate completeness across affected cell outputs and later waits when the outgoing copy loses calls or arguments.
- Preserve size-limit omission markers for direct tool-result metadata when they fit, while continuing to exclude that metadata from custom providers.
## Testing
Add regression coverage for HTTP and WebSocket message budgets, unchanged tool results and history, resource-evidence retention, direct-call omission markers, and Code Mode waits after argument truncation.
GitOrigin-RevId: 538dc9d8c11b0830ec70327422f98a1803122e85
## Why
Editing recent conversation images failed when the selected images included a file reference from a message or tool output.
## What changed
Use `ImageReference` in `ImageEditRequest` to accept both `image_url` and `file_id` inputs. Pass file references from conversation history through to image edit requests while preserving image selection order.
## Testing
Update tests to cover file references from messages and tool outputs, and serialization of mixed inline and file references in image edit requests.
GitOrigin-RevId: 2764bf36a81a62ddd25cf9df27346a434a10c449
## What changed
Show the startup tip beneath the session header in the fullscreen transcript, with wrapping on narrow terminals. Remove rotating tips and startup announcements from above the composer, leaving that area for usage warnings.
## Testing
Add startup transcript snapshots at 80 and 32 columns and assert that compact tooltip rendering preserves styled links. Update usage-warning tests to verify composer geometry and recovery without rotating tips.
GitOrigin-RevId: b5e79a46147d112cd50802b0702537deb9b87001
## Why
Dropping the last board handle releases its state but leaves a stale entry in
`InMemoryMessageBoards`, allowing registry entries to accumulate across sessions.
## What changed
Prune entries whose state has no remaining strong references whenever a board is
opened, while preserving shared state for live boards.
## Testing
Add a regression test that repeatedly opens and drops boards, checks that expired
entries are removed, and verifies that reopening a live board shares its state.
GitOrigin-RevId: c3f1c27b42ee17915f0ece01b85a22d0fdf632ce
## What changed
Select checksum-pinned `rusty_v8` 150.4.0 release archives and matching Rust bindings for x64 and arm64 macOS and GNU Linux when pointer compression and the V8 sandbox are enabled.
Add `--//:rusty_v8_from_source=true` to select source-built archives and bindings together for custom V8 C++ flags or instrumentation. Fall back to the existing source path when the sandbox or pointer compression settings differ from the published artifacts, and retain source builds for musl Linux and Windows GNU.
On GNU Linux, weaken the ten shared `std::logic_error` and `std::runtime_error` constructor and assignment symbols in the Bazel output so toolchain libc++ definitions take precedence. Preserve the checksum-verified inputs and constructors accepting `std::__Cr::string`.
Document artifact selection, source overrides, and checksum maintenance.
GitOrigin-RevId: cedd474c739ae16e07a78f35459d2c383e5781d8
## What changed
Increase `MAX_ROOT_MESSAGES` from 8 to 16 so Guardian subagent authorization reviews can include more root conversation context.
## Testing
Update authorization integration tests to exercise the larger message limit, preserve late user authorization and question context, and expect incomplete root instructions when retained user messages exceed the cap.
GitOrigin-RevId: facc55f424a4d7e29626f4161ecfe031021b30c2
## Why
Ephemeral sessions cannot use the SQLite-backed agent message board. An in-memory backend lets agents share discussions without creating durable board storage.
## What changed
- Add the opt-in `message_board_in_memory` setting to the multi-agent v2 configuration, allowing the board to run in ephemeral sessions when both required features are enabled.
- Share board state across agents in the same tree and release it when the last handle is dropped.
- Implement channels, posts, subscriptions, notifications, search, and paginated reads through the existing `AgentMessageBoard` interface, including request deduplication.
## Testing
Add coverage for shared handles, concurrent request deduplication, tree isolation, and state release. Run existing query and tool test cases against both backends, and extend the parent/child scenario to verify ephemeral board sharing without creating a board database.
GitOrigin-RevId: d0b2083f8ea5b1c5a3a70f258ef738b87ea74cef
## What changed
Remove the Windows sandbox audit module and its exported scan-and-deny helper, including the associated tests. Remove the config edit variant and builder method for acknowledging `hide_world_writable_warning`.
GitOrigin-RevId: c9cfc9b276d46c45d5788fe8d29b2bc4e422001c
## Why
Plugin identity and skill ownership need to be available independently of MCP data, including for plugins without servers or connectors. Hosted plugins have no executor root and should not own executor skills.
## What changed
- Add `McpServerContributor::selected_plugins` to declare executor plugin identities with deferred MCP data. Let the host assign server attribution and precedence across contributors.
- Represent hosted connectors with `HostedPluginConnectors` and make `SelectedPluginIdentity::selected_root_id` optional instead of assigning synthetic roots to hosted plugins.
- Resolve executor contributions before reading hosted connectors, and clear stale hosted state on account changes before executor loading can wait.
- Preserve connector declarations from disabled plugins so Apps can hide those connectors.
## Testing
Add coverage for account changes while executor loading is pending. Update tests to verify hosted identities have no executor root and disabled plugins hide their connectors even when plugin IDs differ from root IDs.
GitOrigin-RevId: e7f511264c5874c1b56d5f3e4a46820724046db0
## Why
Callers need to await acceptance or rejection of thread settings without consuming the thread event stream. Acceptance must precede event delivery because the caller may hold a lock needed by the event consumer.
## What changed
- Add `CodexThread::update_thread_settings` and re-export `ThreadSettingsOverrides` from `core-api`.
- Add an optional reply channel to `Op::ThreadSettings`. Return validation failures as `InvalidRequest` through that channel, retaining error events for callers without a reply channel.
- Reply to successful updates before emitting `ThreadSettingsApplied`, while holding the settings persistence lock through notification.
## Testing
Extend settings constraint coverage to direct replies, including rejection without an error event and successful notification. Verify that acceptance and continuation invalidation precede blocked event delivery, while checkpointing waits for notification.
GitOrigin-RevId: e09b0d3cc4b6750709c173371632f19619e5c250
## Why
Fixed schema budgets can strip parameter descriptions from large MCP tools or render their Code Mode input types as `unknown`. Allow larger budgets to preserve that guidance.
## What changed
- Add `mcp_servers.<name>.tool_input_schema_max_bytes` to configure the UTF-8 byte threshold for best-effort input schema compaction, retaining the 5,000-byte default.
- Add `features.code_mode.tool_input_schema_max_bytes` for rendered input types. Use the largest of the 16,000-byte default, the Code Mode setting, and the ordinary MCP server's explicit setting.
- Apply rendering budgets to prompt declarations and the runtime tool catalog, and avoid reusing cached declarations after the Code Mode budget changes.
## Testing
Add coverage for UTF-8 compaction thresholds, budget precedence, configuration round trips, and preservation of parameter guidance in both the Code Mode prompt and `ALL_TOOLS`.
GitOrigin-RevId: 0ef2823a614d4794e636f518b09c0b03a5239b45
## Why
Required MCP servers can block startup while establishing a live connection even when a usable tool catalog is already cached.
## What changed
- Add per-server `startup_readiness = "catalog"` to expose cached tools while the connection starts, retaining `"connection"` as the default.
- Allow an eligible cached catalog to satisfy required-server startup validation and model binding capture. Explicit server or plugin requirements still wait for a live connection, and tool execution still requires the current connection.
- Check tool filters and model visibility when accepting cached catalogs, and preserve cached catalog revisions for binding reuse.
- Serialize the new setting, expose it in the configuration schema, and trace startup readiness at validation and model binding gates.
GitOrigin-RevId: a1cbdf1757ebb5824cffe2cc56408be49711c422
Remove the basic-session restriction from the early return in
`maybe_run_previous_model_inline_compact`. When the model is unchanged and
no compaction compatibility hash change is detected, all session sources now
skip rebuilding the previous model's turn context and checking its limits.
GitOrigin-RevId: 75044856609603859b12e6668c7bae488ce0f7f5
## Why
Saved model selections can outlive their catalog entries. Removing GPT-5.4 needs to preserve a migration path without applying it to other providers that may still support the same model slug.
## What changed
- Remove `gpt-5.4` from the bundled catalog and `openai.gpt-5.4` from the Bedrock catalogs, including GovCloud.
- Add fallback migration prompts to GPT-6 Sol for saved GPT-5.4 selections on OpenAI and Amazon Bedrock. Scope fallback migrations, including the existing GPT-5.4 Mini migration, to their owning providers while honoring catalog metadata.
- Update tests that depend on bundled GPT-5.4 metadata to use GPT-5.5 or explicit model overrides.
## Testing
Extend migration tests to cover catalog metadata precedence, acknowledged targets, missing or hidden replacements, and preserving the provider while saving the replacement model and its default reasoning effort. Update Bedrock catalog assertions and picker snapshots.
GitOrigin-RevId: f739795da423b9622db2a416be6c52b01b8e7a71
## What changed
Connect the existing composer suggestion UI to generation when `tui.prompt_suggestions` is enabled. Request suggestions after successful live turns with known reasoning-summary settings, skipping replayed or duplicate completions and turns with queued follow-ups.
Generate suggestions in hidden, ephemeral forks of the completed turn, preserving conversation context and exposed live settings. Keep fork events out of the visible conversation and reject requests for user interaction. Cancel generation after 30 seconds, interrupt unsuccessful requests, and unsubscribe temporary threads.
Clear suggestions on new submissions, thread changes, reconnects, and feature disablement. Let Escape dismiss suggestions before entering backtrack mode.
## Testing
Add tests for live-turn eligibility and deduplication, preserved request prefixes and settings, hidden fork behavior, startup cancellation, and timeout cleanup.
GitOrigin-RevId: 92ddf3b06448adcc6f4330914cbd8102bff98046
## What changed
Use `127.0.0.1` instead of `localhost` in the OAuth callback URI and local login success URL.
## Testing
Update login and app-server tests to check the callback address, verify that the success redirect shares the callback origin, and assert that the token exchange uses the same `redirect_uri` as the authorization request.
GitOrigin-RevId: a27dd63dca34b9de81fb937da47c753d5dd1ac90
## Why
File blob uploads previously failed immediately on HTTP 502 and 504 responses, even though these transient gateway errors can recover on retry.
## What changed
Treat HTTP 502 and 504 as retryable alongside 503, using the existing attempt limit, upload deadline, and server-provided retry delays.
## Testing
Expand upload retry tests to cover recovery from 502 and 504, mixed transient responses, exhausted attempts, and retry delays exceeding the remaining budget. Verify that 403, 409, and 500 responses are not retried, including responses without an Azure error code.
GitOrigin-RevId: a8e2f6bcf69338fb6d24f4c2d1ee333fb77bdbc0
## What changed
- Export `ProjectTrustPath` and make `ProjectTrustLookup::from_paths` accept an explicit working directory and optional repository root instead of an arbitrary sequence of path pairs.
- Defer repository-root canonicalization until neither working-directory key matches, avoiding unnecessary filesystem access while preserving lookup precedence.
## Testing
Extend the active-project regression test to cover repository-root fallback and ensure a working-directory entry without a trust level takes precedence over a trusted root. Adapt the existing POSIX and Windows lookup tests to the new API.
GitOrigin-RevId: ba5dc0df1ef9d5109933df00c055eef04434601f
## Why
Elevated Windows sandbox setup rejected `danger-full-access` as an incompatible permission profile before registered Core could reach the provisioning service.
## What changed
Allow `PermissionProfile::Disabled` to reach service provisioning when registered Core is requested. Keep legacy full-access setup on the shared setup path and retain permission validation before provisioning for restricted profiles.
## Testing
Add Windows-only regression cases covering full-access and supported restricted profiles reaching the service, unsupported restricted permissions failing before provisioning, and legacy full-access setup skipping the service. Each case checks the completion error and verifies that the configuration file remains unchanged.
GitOrigin-RevId: 5ba190da6f8b1c6ef665015acdb9428718a724dc
## Why
Global deny globs such as `/**/.env` unnecessarily block directory renames and removals on macOS. Moving an ancestor does not let a matching basename escape these rules.
## What changed
Skip ancestor unlink restrictions for root-anchored recursive globs with a literal basename. Keep matching files protected and extend the deny to descendants of matching directories. Preserve ancestor protection for scoped, multi-component, and nonliteral patterns.
## Testing
Add Seatbelt tests covering directory moves and removals, continued protection after moves, symlink access, matching directory descendants, and files created after policy generation. Verify that scoped and nonliteral deny patterns still block ancestor moves.
GitOrigin-RevId: 4e8ea601e8ea98c4da5e3a3fe0d8ce2c63013bc5
## Why
Expanded recursive deny lists can exceed the Windows command-line limit, preventing sandbox wrappers and setup helpers from launching.
## What changed
- Use chunked environment transport for wrapper and non-elevating setup payloads above 24,000 UTF-16 code units, preserving the existing argument protocol for smaller requests.
- Share the transport with the MXC launcher, supporting payloads up to 16 MiB with Unicode-safe chunking and validation.
- Keep transport variables out of the workload environment and remove inherited chunks before launching setup helpers.
## Testing
Add coverage for transport boundaries, Unicode round trips, malformed payload rejection, environment cleanup, and large payloads crossing Windows process creation. Extend the elevated sandbox integration test with 1,000 nested denied files to verify read restrictions and `AGENTS.md` discovery with a payload exceeding the command-line limit.
GitOrigin-RevId: 8ef92fdc7d534143f0eac76036a2173a6f585d08
Accept `service_name` and the expected originator as test parameters, passing
`service_name` through `ThreadStartParams`. Retain the existing case that
expects `TEST_ORIGINATOR` when no service name is provided.
GitOrigin-RevId: 71097dcfe45496216cf3e765999ed0abd0a0cd71
## Why
V8 artifact fetching always downloaded the checksum manifest, requiring network access even when all cached files were valid.
## What changed
Reuse a cached manifest when it is not a symlink and matches the checkout's trusted SHA-256 pin. Continue verifying both the archive and bindings against that manifest, downloading replacements when needed.
Refresh missing, invalid, or symlinked manifests. Preserve existing cache contents if the refresh is interrupted, and reject downloaded manifests that do not match the current pin.
## Testing
Add regression coverage for network-free cache reuse, manifest refresh, corrupt artifact repair, changed pins, symlink replacement, interrupted downloads, and source or paired artifact overrides. All 12 tests in `scripts/codex_package/test_v8.py` pass.
GitOrigin-RevId: d3bdb1ae5f6bc48dd6d081df33dec8db9d3257a8
## Why
Agent messages arriving during a response can interrupt sampling at reasoning or commentary boundaries, cutting off remaining tool calls.
## What changed
Add the disabled-by-default `defer_mailbox_preemption` feature flag. When enabled, sampling continues past these boundaries and queued agent messages reach the next model request alongside completed tool results.
## Testing
Add streaming scenarios and snapshots for reasoning and commentary boundaries with deferral enabled and disabled. Verify that deferral preserves the planned tool call and that both queued messages arrive in order in the next request.
GitOrigin-RevId: d6846dd73b3afb47e7293f3b1aa2abcd04e37853
## Why
Thread startup can prewarm the Responses WebSocket before the creating client is registered with the thread, leaving the handshake unable to request attestation from that client.
## What changed
Reserve a thread ID and register the creating connection before starting the thread, including for ephemeral threads. Remove the thread state if startup fails.
## Testing
Extend the attestation round-trip test to cover persistent and ephemeral threads. Handle attestation requests while awaiting `thread/start` and `turn/start` responses, and verify the WebSocket handshake includes the expected `x-oai-attestation` header.
GitOrigin-RevId: 1bdb38bac641253eed58a2431658ab54d93819c5
## What changed
Add `tui.prompt_suggestions`, defaulting to `false`, along with suggestion request state, a generation prompt, and strict parsing of single-line suggestions up to 240 characters. Suggestion generation is not connected yet.
Keep suggestions outside the draft and render them dimly in an empty, focused composer. `Tab` accepts a suggestion for editing, a separate `Enter` submits, and `Escape` cancels pending suggestions. Respect active key bindings, popups, attachments, paste bursts, and interactive transcript footers; ignore stale results and cancel suggestions when a task starts.
## Testing
Add parser tests, composer interaction tests, and snapshots covering acceptance, dismissal, stale results, input precedence, wrapping, and transcript search layout.
GitOrigin-RevId: 868001a0fc3e6fd8c11ef1650aabc477fa36e03d
Normalize the legacy setting so existing `tui.whimsy` values control the
starfield effect. If both keys appear in the same config layer, the explicit
`tui.effects.starfield` value takes precedence.
GitOrigin-RevId: 2884dbd643690d500ed8d1493ce47950d93d6ab3
## What changed
Represent legacy and canonical config keys as full paths, allowing aliases to target nested tables within the legacy key's containing table. Create missing destination tables, preserve existing canonical values, and skip insertion when an intermediate value is not a table.
Keep the existing `memories` and `agents` alias mappings unchanged.
GitOrigin-RevId: 9ef17e9d1b6adf6299777ed0051cb301fd245073
## Why
Sparse config edits must preserve aliases in unrelated base tables so the returned config version remains consistent with the file on disk.
## What changed
Normalize the full overlay before merging and normalize base aliases only in tables reached by the overlay. Reuse the root-level normalization helper when reporting config origins.
## Testing
Add a regression test showing that an `agents` overlay normalizes `max_threads` while leaving the unrelated `memories` alias untouched.
GitOrigin-RevId: 25cc95b0969979c49c43b766824fa0bd019465a4
## Why
Recursive config merging clones overlay tables at each nesting level, repeatedly copying their descendants.
## What changed
Clone the overlay at the `merge_toml_values` entry point and pass owned values through recursive merges. Normalize overlay tables in place, preserving the public API and existing merge semantics.
GitOrigin-RevId: 05e66648e37d571566b3d119bd3aab3924fb0c74
## What changed
- Add `StorageTelemetry` to record operation counts, durations, secure-store outcomes, and file fallback reasons using bounded labels. Emit fallback warnings without credential payloads or error text.
- Add task-local client attribution with explicit propagation across task boundaries.
- Preserve typed keyring error causes through `std::io::Error` and the local secrets backend, classifying supported native failures without parsing error messages.
- Remove service names, account names, value lengths, and error text from keyring trace logs.
## Testing
Add tests for buffered metric emission, fallback outcomes, exclusion of sensitive error contents, client attribution isolation, and typed native error classification.
GitOrigin-RevId: 18e7201566a3b09061a6014fd6bd90eae96e3fc2
## What changed
- Make `LocalThreadStore` default to paginated history while retaining explicit legacy mode.
- Explicitly use paginated history for Guardian review sessions and allow in-memory stores to create paginated threads.
- Rename full-history resume, fork, and subagent helpers to identify them as legacy APIs, and document the paginated alternatives.
- Reject `thread/revert` for ephemeral threads and prevent the TUI from replaying or attaching to ephemeral agent threads.
## Testing
Add coverage for preserving the default and explicitly selected history modes and conversation context across restart, and for retaining context after rejected ephemeral reverts. Extend Guardian checkpoint coverage across both history modes and verify that saved reviews use paginated history.
GitOrigin-RevId: 870239eb3757018159ee4f230a009c97d38ac5b7
## Why
The `attribution_error` status does not explain why MCP attribution is incomplete. Preserve a diagnostic reason so callers can distinguish history and recorder errors from request serialization failures.
## What changed
- Add optional `error_reason` diagnostics to `McpAttribution`, retaining the first recorder error through checkpoints, compaction, resume, and fork.
- Identify missing or invalid checkpoints, conflicting sources, invalid sources, and poisoned recorder state. Use `restored_error_unknown` for older error checkpoints without a reason.
- Distinguish `payload_too_large` from `serialization_failed` in request metadata fallbacks.
- Tolerate missing, unknown, or malformed diagnostic reasons when reading history, without letting diagnostics determine attribution status.
## Testing
Add coverage for reason preservation, recorder poisoning, backward-compatible checkpoint decoding, resume and cold-fork restoration, and request metadata serialization, including oversized payloads.
GitOrigin-RevId: 389b9446fae119f793978f3e7e4a926677e84d8c
## Why
Treating an omitted `allow_local_binding` setting as `false` prevents environment policies from inheriting local-binding permissions.
## What changed
Keep `allow_local_binding` optional when composing controller and environment policies. Preserve explicit denials from either policy and resolve executor defaults after composition. Without a controller, default to denying local binding unless the environment explicitly allows it.
## Testing
Add coverage for omitted, allowed, and denied settings, managed constraints, executor defaults, and remote launch rejection when local-binding restrictions cannot be enforced. Extend remote network approval tests with loopback requests to verify controller and environment policy composition.
GitOrigin-RevId: aa0d15e8be87a2741255cd3a5a2cabffa03214ac
## Why
Transcript selections were copied as plain text, losing the formatting of rendered Markdown when pasted.
## What changed
- Retain semantic Markdown annotations through rendering, wrapping, and streaming, then serialize selected text with balanced markup.
- Preserve inline formatting, web links, headings, lists, blockquotes, and hard breaks in Markdown clipboard payloads.
- Keep code-only and other literal-only selections as plain text. In mixed selections, escape user prose and fence code, tables, and tool output to preserve their literal content.
## Testing
Add unit tests and Markdown/HTML snapshots covering partial selections, nested containers, escaping, links, resize stability, and streaming boundaries.
GitOrigin-RevId: f0476334a6bf8ad0fb57626627bd258443540852
## Why
TUI test helpers used `TempDir::keep()`, leaving temporary Codex homes on disk after fixtures were dropped.
## What changed
Retain `TempDir` ownership in widget and app fixtures so their homes are removed on drop. Transfer ownership to app fixtures to keep the home alive across widget replacement, and retain directory guards in tests that use configs directly.
## Testing
Add regression tests for recursive cleanup, isolation between widget homes, and app home survival across widget replacement followed by cleanup on app drop.
GitOrigin-RevId: fe80f982cc467ede4c3e1edbac8012ec3066dfb3
## Why
MCP OAuth configuration supported a pre-registered client ID but could not supply a client secret for token exchange or refresh.
## What changed
- Add `oauth.client_secret` and `codex mcp add --oauth-client-secret`, requiring a nonempty secret and client ID. Persist the secret in server configuration and accept `clientSecret` in plugin configuration.
- Pass configured credentials through CLI, app-server, and plugin login flows and token refresh. Require a new login when a configured confidential client's ID differs from stored credentials.
- Redact secrets in debug output and keep them out of authorization URLs and persisted OAuth token records.
- Invalidate cached OAuth connections when the configured client ID or secret changes.
## Testing
Add coverage for configuration validation and round trips, CLI argument redaction and subsequent login, app-server login, connection invalidation, and refresh with `client_secret_basic` and `client_secret_post` in both refresh modes. Verify secret exclusion from token records and reject mismatched client IDs before contacting the provider.
GitOrigin-RevId: 85bb0e410e9e68e6cd68eb6359badfc7eac78147
## Why
Diagnostic uploads through the app server do not include the TUI client's diagnostic buffer. Attach those diagnostics when users consent to uploading logs.
## What changed
- Stage the most recent 1 MiB of client logs as `client-logs.txt` on the app-server host and append it to `extra_log_files`.
- Skip staging without log consent and list the optional attachment in the consent dialog.
- Continue uploading the report if staging fails, noting the omitted logs in the report reason. Attempt to remove the staging directory after both successful and failed uploads.
- Make app-server filesystem helpers usable by background requests.
## Testing
Extend submission tests to cover log truncation, preservation of existing attachments, consent gating, staging failures, cleanup after upload failure, and error display. Update consent dialog snapshots to include the client log attachment.
GitOrigin-RevId: 9790834d52772c08a147ee7c176cbbc2aa029d5f
## Why
Failed SQLite writes leave diagnostic logs incomplete. Notify users before they close Codex so they can submit logs or run `codex doctor`.
## What changed
- Add a best-effort warning on the first log write failure in standalone and in-process app servers, while continuing to retain failure diagnostics in memory.
- Handle failures that occurred before the in-process warning reporter was attached.
- Tailor the warning's guidance to whether submitting logs is enabled.
## Testing
Add coverage for warning deduplication, both guidance variants, retained diagnostics after the notification sender is dropped, and SQLite flush failures before and after reporter attachment. Extend log upload integration coverage and add a TUI warnings snapshot.
GitOrigin-RevId: 12a74126d13c3568430e539a180cca47fa931fa9
## Why
SQLite write failures can leave persisted logs incomplete, while log snapshots taken before collection miss errors raised during that collection.
## What changed
- Report SQLite flush failures directly to the in-memory log buffer without re-entering tracing, using an error category and batch size instead of raw error details.
- Track whether the log writer has lost a batch and make app-server diagnostic uploads use the memory buffer when SQLite logs are incomplete.
- Refresh log bytes after flushing and querying SQLite so the same submission includes collection failures, while preserving captured metadata and thread identity.
## Testing
Add regression tests for failure reporting without recursion, subsequent write recovery, metadata preservation, and healthy and failing SQLite collection. Add an upload integration test that captures attachments locally and checks failure diagnostics, memory-buffer fallback, and omission of raw SQLite error details.
GitOrigin-RevId: 51b0c4b69c977d9f4e74f2f245a9fd90fdb13761
## Why
Paste input classification and asynchronous flush deadlines need to share a clock, including when Tokio time is paused in tests.
## What changed
Use Tokio's clock for chat composer paste timing and startup draft newline tracking, converting to `std::time::Instant` where existing composer helpers require it.
## Testing
Run the existing startup draft multiline paste test with `start_paused = true`. It checks that non-bracketed pastes preserve newlines without submitting the draft.
GitOrigin-RevId: 73bac963204473d85e7395781e0df966ecc92801
## Why
Local `apply_patch` permission checks can treat a macOS system alias and its canonical spelling as different locations, sending writes covered by temporary-directory grants for unnecessary approval.
## What changed
- Normalize trusted top-level aliases in local policy roots and patch targets, reusing a prepared matcher for permission requests and patch safety checks.
- Share alias normalization with Seatbelt and the macOS executor sandbox while preserving mutable symlinks and missing descendants.
- Preserve read-only and deny precedence, protected metadata restrictions, and remote URI matching. Propagate normalization failures from fallible permission checks.
## Testing
Add macOS regressions for multi-file patches with missing parent directories through both direct `apply_patch` calls and shell interception, asserting automatic approval and file contents. Add unit coverage for alias restriction precedence, mutable symlink preservation, missing descendants, and remote permission isolation.
GitOrigin-RevId: 0822ff951eaab728cb1ad91281745fa1b8809f15
## What changed
Record `codex.thread.tools.namespaces_total` and `codex.thread.tools.fragment_bytes` histograms through session telemetry. Tag samples by `stage` (`before` or `after` the 4 KiB cap) and `kind` (`snapshot` or `delta`). Measure bytes after description normalization and XML escaping, including the `<tools>` wrapper, with explicit fragment-size buckets.
Delta counts include only changed entries, and unchanged state emits no samples.
## Testing
Extend rendering tests to verify snapshot and delta metrics, omission counts, byte sizes with Unicode and XML escaping, and no samples for unchanged state.
GitOrigin-RevId: 26543585e2bea54bff6d63263faa9a6ca5dca379
## Why
The PID reservation test could race with the backend's read on Windows by deleting the PID file from its cleanup task. The guardian heartbeat snapshot and environment normalization also needed to match the current permission-context wording.
## What changed
- Release the reservation lock and let `stop()` remove the stale PID file, then assert that the file is gone.
- Update the guardian heartbeat snapshot and normalization pattern to use `The active permission profile for environment`.
GitOrigin-RevId: d9cadae0e5d36cb2e1ab0517e2d7121cf2d0715d
## What changed
Add `otel.log_guardian_assessments`, disabled by default and requiring an OTLP HTTP or gRPC log exporter. Emit `codex.guardian_assessment` when a synchronous Guardian review finishes, including review identifiers, status, risk level, user authorization, and rationale. Include `allow` or `deny` outcomes only for completed model assessments, not review errors, timeouts, or cancellations.
Cap exported rationales at 64 KiB on a UTF-8 character boundary and record their original byte length and truncation status. Use the log-only route to exclude assessment payloads from trace export, local state logs, and bug-report log buffers. Cached V2 approvals are not included.
## Testing
Add coverage for configuration gating, enabled and disabled denial logging, terminal statuses and outcomes, UTF-8 rationale truncation, export routing, and bug-report log buffer exclusion.
GitOrigin-RevId: dcbb5b429c8726a5a5c80ff82f9d625e81796ede
## What changed
- Resolve remote sandbox modes, writable roots, and denied read paths/globs using the executor's filesystem context, displaying paths in its native format. Preserve local filesystem resolution for local environments.
- Resolve remote read denials individually so missing executor facts omit only the unresolved entries.
- Apply a shared 32 KiB budget to displayed permission paths/globs, omitting whole entries and warning that all restrictions still apply, including omitted read denials.
## Testing
Add coverage for remote Windows writable roots and read denials, missing executor path facts, and whole-entry omission with multibyte paths under the shared budget.
GitOrigin-RevId: c61e7ddc8fa569dbc25e9990d90357c42315188f
## Why
`render_ref` already holds a read lock on `sign_in_state`. Acquiring another read lock in `render_continue_in_browser` can deadlock when a writer is waiting.
## What changed
Pass the borrowed `ContinueInBrowserState` from `render_ref` into the browser sign-in renderer instead of reading the lock again.
## Testing
Update the existing narrow-width browser sign-in test to exercise `render_ref`, retaining checks for the full OSC 8 authentication link, device-code guidance, and cancellation footer.
GitOrigin-RevId: ba83e212d510627be9dfd068c8d7318da32a1749
## Why
Checking installed plugin roots performs filesystem work while holding the loaded plugins cache mutex, blocking lookups for other cache keys.
## What changed
Store cache entries in `Arc`s and release the mutex before validating installation paths. After reacquiring the lock, check the cache generation and entry identity to reject entries invalidated or replaced during validation. Preserve stale-entry eviction and most-recently-used ordering.
GitOrigin-RevId: cb5a5f7ec52cba852e6bb9da03a8e214cc19727d
## Why
Image and audio estimate cache misses computed values while holding the cache mutex, blocking access to unrelated keys during initialization.
## What changed
Add `BlockingLruCache::get_or_init` using `Arc<OnceLock<V>>` and migrate the image and audio estimate caches to it. Initialization and same-key waits run in a Tokio blocking region after releasing the cache mutex. Callers share initialization while an entry remains cached; eviction can allow another initialization, so factories must be deterministic.
## Testing
Add a concurrency test covering access to other keys during initialization, eviction of an in-flight entry, and successful completion of both the evicted initializer and its replacement.
GitOrigin-RevId: 079226a58828b854eddc2b501079527bcbe5e603
## Why
Platform proxy resolution holds the system proxy cache mutex, so checking the cache could block a Tokio worker while another lookup was in progress.
## What changed
Use `try_lock` for cache reads, treating contention as a cache miss so async callers on Windows and macOS wait through the existing asynchronous resolver path.
## Testing
Add a Windows/macOS regression test that verifies resolution yields while the cache is locked and completes after release. Adapt the cached-route test to tolerate concurrent cache writers, and isolate the unavailable-decision cache test from shared cache contention.
GitOrigin-RevId: d61da8d37f81b84637e51bf30e4b26091d5fde24
## Why
Unchanged scheduled heartbeat instructions should not become fresh authorization evidence that supersedes a later human override or floods Guardian review context.
## What changed
- Capture heartbeat provenance per input, including when steering an active turn, and persist it in history and retained context.
- Coalesce unchanged instructions for each automation at their original acceptance order. Preserve changed instruction versions and ordinary human messages.
- Represent repeated heartbeats as references to earlier instructions in Guardian transcripts, while tracking the latest input turn separately for trusted skill selection.
- Limit coalescing to recognized, bounded heartbeat envelopes with host-provided provenance.
## Testing
Add regression coverage for human overrides across repeated and steered heartbeats, instruction changes, checkpoint restoration, transcript references, envelope parsing, and latest-turn trusted skills in delegated reviews.
GitOrigin-RevId: 31e444ddb685a1a618be26d3cc32fb562296946b
## Why
Native clipboard setup and writes can block, preventing the TUI from processing input or closing overlays while a copy is in progress.
## What changed
- Route clipboard copies through one session worker that retains native clipboard ownership. Keep terminal escape output on the UI thread.
- Show pending and busy status messages, reject additional copies without queuing them, and ask users to retry image paste after an active copy finishes.
- Abandon setup after five seconds and prevent late delivery. Keep the worker busy until the blocked call returns, and bound shutdown waiting for clipboard handoff.
- Match completions to their originating requests so stale results cannot clear newer selections or unexpectedly resume transcript following. Retain selections on automatic copies, failures, and unconfirmed delivery.
## Testing
Add regression tests for blocked backends, overlay exit, copy and paste ordering, setup expiry, bounded shutdown, completion status messages, and preservation of replaced or moved selections.
GitOrigin-RevId: 4ba1f8da258b9d0700b0edec9ac0ba699f536785
## Why
Cold Rosetta translation and cache invalidation from hard-linked executables can interfere with timed CLI tests. Sampling the clock twice also makes local retry telemetry report a delay shorter than the selected backoff.
## What changed
- Warm CLI fixtures with `--version` on macOS x86_64 before timed checks, and use copies or Unix symlinks to avoid invalidating the shared executable's Rosetta cache.
- Use one clock sample to calculate the response retry deadline and recorded delay.
- Include the retry telemetry event in delay-range assertion failures for the headerless rate-limit stream test.
GitOrigin-RevId: fc573bfff912e999cf74b94a1c6e7ae1be07974b
## Why
Asynchronous Guardian scoring omitted the target environment's denied-read restrictions, and cached score authorization did not include that permission context. A score from one environment could therefore be reused for an action in another environment with different restrictions.
## What changed
- Share permission resolution between synchronous review and asynchronous scoring, including resolving `write_stdin` targets from the owning terminal session.
- Include environment identity and denied-read paths/globs in async scoring context and cached score authorization.
- Fall back to synchronous review when permission evidence cannot be resolved or exceeds the async limit of 3,000 bytes, rather than omitting restrictions.
## Testing
Add regression coverage for rejecting cached scores with different environments or denied paths, passing the target environment's restrictions to the classifier, and rejecting oversized async permission evidence.
GitOrigin-RevId: 14b6f3454bbea458be037560eb1da47d22874df1
## Why
Login clears the recommendation cache after its RPC response, allowing thread startup to race with cache invalidation in the external login tests.
## What changed
Wait for `account/login/completed` and assert a successful notification before starting the thread. This keeps thread startup and the background refresh on the same cache generation in both variants of the recommended plugin test, with `tool_suggest` enabled and disabled.
GitOrigin-RevId: 7be46dacd947b30a28c83176dc2e3b5f730005f1
Raise `max_concurrent_threads_per_session` from 3 to 4 in the test
configuration so the root, worker, grandchild, and sibling can all remain
resident until explicit shutdown.
GitOrigin-RevId: 564fd7bd64d2a91c160437f7346c7e17a30a5f2a
## What changed
Add a `TestCodexBuilder::with_thread_manager` hook for configuring the thread manager before test threads start, and register an integration suite using a test `AgentControl` implementation.
The tests verify:
- Controller factory calls for new roots, forks, and cold resumes, with reuse for warm resumes and shared session identity for internal sessions.
- Child session identity, persisted parent lineage, message-board authorship, and routing of child reloads through the host controller.
- Preservation of the controller's service tier when child threads start or root starts are rejected.
- Dispatch of `spawn_agent`, `send_message`, and `list_agents` to the host controller, including propagation of its errors to tool results.
GitOrigin-RevId: bc6a6c6dbcde9ecc3ce15456aaf7a0610a14eceb
## Why
New user input during a Guardian review invalidated an in-flight approval and aborted the pending action, even when the input was only a status inquiry. Review the action again against the latest authorization evidence so it can proceed or be denied based on the updated instructions.
## What changed
- Treat stale authorization as a retryable review error within the existing attempt budget and shared deadline.
- Refresh authorization evidence for each attempt while keeping the pending action fixed, and record evidence from the completed attempt.
- Preserve cancellation and history-reset aborts, and deny approval if stale authorization exhausts the retry budget.
## Testing
Add and update coverage for parent status updates, authorization revocation, repeated updates, cancellation, history resets, and retry deadlines. Verify that refreshed reviews see the latest input and that the pending action executes exactly once only after approval.
GitOrigin-RevId: c683e2efb6f07840b99d0d34acf0d38c9ddfe9bd
Wait for an assistant item to start before resuming a running paginated
thread, ensuring the user message has reached live history. Emit the initial
response events before the gate and keep completion gated during resume.
Increase the memory dual-write test's consolidation timeout from 10 to 60
seconds to allow Git workspace and agent process startup under contention
on Windows CI runners.
GitOrigin-RevId: 4d74d04955c88a9c208a809f639fe14fdb2ebf37
Use `notify_one()` instead of `notify_waiters()` in
`terminating_initial_exec_command_rechecks_initial_response_state` to retain
the release notification if the termination waiter has not registered yet.
This prevents the test from timing out due to a missed notification.
GitOrigin-RevId: d233ffc50e016eb75752fd360a4d846de0063683
## Why
The list-voices barrier can consume the sleep completion event that `any_new_input_interrupts_sleep` needs to observe.
## What changed
Enqueue agent mail directly in the test so the subsequent wait can observe sleep completion. Keep the `TestCodex` fixture alive for the duration of the test by cloning its `codex` handle instead of moving it out.
GitOrigin-RevId: 957165c2f20cc4d76df763cd41fd99816b477be3
## Why
Explicit user goal edits can restrict permitted actions, such as “Inspect only; do not publish.” Guardian needs these edits as authorization evidence even though they are recorded as contextual messages.
## What changed
- Add `UserGoalUpdate` and a recording API for objective, status, and clear updates without scheduling a model response.
- Use host annotations to retain goal updates in Guardian review history and root authorization evidence, and invalidate cached authorization when updates are recorded.
- Omit oversized objectives whole and mark their evidence incomplete so truncation cannot turn a restriction into a grant.
- Keep item injection from updating shared model and multi-agent metadata.
## Testing
Extend authorization, retained-context, and review snapshot tests to cover goal-edit cache invalidation, root goal visibility from child threads, and restrictive goals reaching Guardian alongside managed policies.
GitOrigin-RevId: 17b99d9fa8c1620840d6f408d79b405a78a778f8
## What changed
- Add `ThreadManager::with_agent_control_factory` to select a host-owned controller asynchronously using the final thread ID for new and cold-resumed threads. Keep local control as the default, reuse live controllers on warm resume, and preserve parent controllers for internal sessions.
- Fail startup on factory errors or when a provided controller's identity does not match the session identity.
- Defer root service-tier updates to host controllers until thread registration succeeds, preventing failed starts from changing settings on a shared controller.
GitOrigin-RevId: 095afbecfee5d47329038d2a97d0cc0081f181df
## What changed
Promote `write_stdin_approval` to stable and enable it by default.
## Testing
Update the stdin approval suite to rely on the default feature setting. Adjust the background network approval test to account for terminal input review before network access and explicitly wait for the network assessment.
GitOrigin-RevId: 1bb449f6d9ecf4ee451e84f95f839a6744877e8b
## Why
Passing extra descriptors to a PTY previously selected behavior intended for inherited escalation sockets: no EOF on stdin close, different signal exit statuses, and no default `SHELL`. Launch attachments need ordinary PTY behavior and must survive execution even when marked `FD_CLOEXEC`.
## What changed
- Add `ChildFds::Attached` alongside `ChildFds::Inherited` to distinguish launch attachments from legacy inherited descriptors.
- Preserve ordinary EOF, default `SHELL`, and signal exit status behavior for PTY attachments.
- Allow explicitly supplied close-on-exec descriptors through pipe and PTY launches without changing the parent's descriptor flags, using child-side flag updates and macOS spawn inheritance actions.
- Update existing callers to use `ChildFds::Inherited`.
## Testing
Add Unix coverage for attachment accessibility, unchanged parent descriptor flags, default `SHELL`, and signal exit statuses. Extend the PTY stdin-draining test to cover attachments and EOF delivery.
GitOrigin-RevId: 864aedc6c5717d8b43c9d71057c9f54409834509
## What changed
Use the model catalog's `send_user_message_async.parameters` override for the `request_user_input_async` tool schema. Fall back to the bundled schema when the override is absent or invalid, logging a warning for invalid overrides while preserving the catalog description.
## Testing
Extend integration coverage for catalog schemas, empty and invalid overrides, and schema updates during mid-turn model changes. Update the asynchronous question-and-answer scenario to verify that requests carry the catalog schema while work continues and the user's answer arrives.
GitOrigin-RevId: c51a90d3266daaba1e7001aa4026964f84dfb206
## Why
The 32 KiB per-result cap and 128 KiB aggregate budget discard tool metadata even when the outgoing request has room to retain it.
## What changed
- Remove the per-result capture cap and raise the aggregate executed-tool metadata budget to 2 MiB.
- Apply a 15 MiB soft budget to serialized HTTP requests and WebSocket messages, using the actual WebSocket delta. Trim optional result metadata on the wire copy while preserving ordinary content and logical history.
- Prioritize `openai/resource_access` metadata during trimming, and include `overage_bytes` in omission markers.
- Record bytes removed by metadata budgets in `codex.tool_metadata.shed_bytes`, tagged by stage.
## Testing
Add coverage for HTTP and WebSocket message boundaries, resource preservation, residual marker removal, unchanged history, and shedding metrics. Update direct-tool and code-mode tests to verify metadata survives beyond the previous limits.
GitOrigin-RevId: ed00996b77945300f60db1e52eff22b4de2707c1
## What changed
Use `KNOWN_PRODUCT_SKUS` in `SessionTelemetry::with_product_sku`, preserving the existing mapping: `codex` stays `codex`, missing or empty values omit the label, and all other values become `other`.
Remove the registry test `dispatch_uses_the_invoking_turn_product_sku` and its unused imports.
GitOrigin-RevId: b4ad6cbc6205aa35fb2866d72f7205814f5b3566
## What changed
Share response decoding and typed error mapping across in-process and remote clients and request handles. Route enum wrappers through `request`, and drop the completed transport future before invoking caller-provided deserialization.
## Testing
Add coverage for dropping typed requests while waiting to send or receive a reply. Exercise the remote typed round trip through `AppServerClient::Remote`.
GitOrigin-RevId: 573c6c45859a96cab69888c3a90c29caa93368b1
## Why
RPC sending and waiting do not depend on request or response types, and Markdown layout does not depend on the parser iterator. Share these implementations across typed calls and parser variants.
## What changed
- Extract `RpcClient::send_request_and_wait` into a non-generic async method, preserving registration before serialization and disconnected-client error precedence.
- Remove the iterator type parameter from `Writer` and pass iterators to event traversal methods, retaining static dispatch and dropping the parser before rendering state, including on unwind.
- Update streaming rendering and existing rendering tests to use the separate parser.
GitOrigin-RevId: 4cc07223111b7c08211028948d13fe04598f8fc7
## Why
Keep source locations available without full debug information in ordinary builds, and retain symbols until release packaging. macOS targets also need to avoid invoking `dsymutil` in Linux remote Rust actions where it is unavailable.
## What changed
- Set Cargo's `dev` profile to `line-tables-only` and let `ci-test` inherit it through `test`. Document environment overrides for full debug information.
- Patch `rules_rs` to use line tables for `fastbuild` and `opt`, full debug information for `dbg`, and no stripping in all three modes.
- Disable split debug information for macOS toolchains, matching Cargo's release policy.
GitOrigin-RevId: 9e92b28f9647cea7dd73084febd84726b1cee279
## Why
Repeated prewarm calls still prepared instructions, tools, and a prompt even when an existing WebSocket connection was already warm.
## What changed
Check for a previous request and a connection that is not known to be closed before startup prewarm preparation. Reuse this readiness check in `prewarm_websocket`, and record `ready` or `needs_prewarm` in the `codex.startup_prewarm.websocket_check` counter before preparation can fail.
## Testing
Extend the WebSocket resume test to verify that repeated prewarm calls skip instruction loading on a healthy connection, while a closed connection triggers preparation again.
GitOrigin-RevId: 6a1b361b36b4e7f16fb283e48a8ce4d4fb996ceb
## Why
History notes and image generation requests used default HTTP clients that did not carry the configured application network policy.
## What changed
Pass `Config::http_client_factory()` into both extension backends and create transports with `ClientRouteClass::Api`, so their requests honor application network restrictions and configured proxy behavior.
## Testing
Add regression coverage verifying that denied image requests never reach the server and that history notes context requests stop after the network policy becomes restrictive. Retain coverage for image file access restrictions.
GitOrigin-RevId: 7ba61fdc60fa1afe1842d869da9ccd744ab7d82f
## Why
Tool telemetry needs to distinguish product SKUs without turning arbitrary configuration values into metric labels.
## What changed
- Read `apps_mcp_product_sku` from the invoking turn when dispatching tools, replacing any stale SKU in the telemetry metadata.
- Add `product_sku` to tool call count and duration metrics and tool result log and trace events.
- Preserve `codex`, map other nonempty values to `other`, and omit the attribute for empty or missing values.
## Testing
Add coverage for SKU separation on a shared metrics client, normalization, and successful and failing dispatches with stale telemetry metadata. Extend export routing tests to check SKU attributes in logs and matching traces.
GitOrigin-RevId: 3fc58c9f7245fd5b65f7cba122e08d7ea838b2d6
## Why
Confirming an Astra model selection recursively polled the large event dispatcher on the TUI thread's stack.
## What changed
Unwrap `AstraSelectedFromModelPicker` before dispatching its model update, then trigger the sparkle afterward when eligible. Keep the eligibility check and model update in the same event so queued backend updates cannot turn a no-op confirmation into a sparkle.
## Testing
Add a regression test that confirms `gpt-6-astra` with `XHigh` reasoning on a thread with a 4 MiB stack and checks the resulting model and reasoning effort.
GitOrigin-RevId: 89df8b417a9fd0107ebb918edeb2d240b53d42bd
## Why
Exceeding the aggregate metadata budget previously replaced all tool result metadata with omission markers, discarding small results unnecessarily. Oversized results also lost resource-access evidence even when that evidence alone would fit.
## What changed
- Raise the executed-tool-call metadata budget per request from 32 KiB to 128 KiB while retaining the 32 KiB per-result limit.
- Reduce the largest result metadata first and stop once the request fits, preserving smaller results.
- Retain `openai/resource_access` when full metadata exceeds capture, request, or direct-call retained-history limits. Keep resource lists intact, and discard optional result metadata before sacrificing call records, source evidence, or completion markers.
## Testing
Add regression coverage for selective reduction, resource-access retention, serialized request size, and direct-call and Code Mode behavior. Update compaction and truncation tests for the larger request budget.
GitOrigin-RevId: 698e47dcbdd3351e9a031e45ea39053608a5a0e4
## What changed
- Move `Provider` and `RetryConfig` into `codex-client`, retaining re-exports from `codex-api`, and switch `codex-model-provider-info` to depend on `codex-client`.
- Move feature-state metric emission into `codex-core`, preserving its behavior while removing the `codex-features` dependency on `codex-otel`.
- Explicitly enable TLS features for `tonic` in `codex-config` and `reqwest` in `codex-http-client`.
- Enable `png`'s `zlib-rs` feature directly in `codex-utils-image` to keep encoded PNG bytes stable when WebSocket dependencies are absent.
GitOrigin-RevId: 91fd63ab01b55d516b3e80e3644d06af8d5a01f6
## Why
Appending output to the completion transcript and pending polling buffer under separate locks allows cancellation to interrupt a chunk update between the two buffers.
## What changed
Store both buffers in `OutputBuffers` behind a shared mutex and append each chunk to both while holding that lock. Polling drains only the pending buffer, while completion events read the retained transcript. Apply this to both local and exec-server output handling.
## Testing
Extend the repeated-drain test to verify that the completion transcript preserves the expected bounded output after polling drains the pending buffer.
GitOrigin-RevId: ef8519582937b0d8c42e46375226501338df4a01
## What changed
Return completed startup prewarm sessions to the client cache and schedule resume prewarm through the normal session setup path. Keep in-flight warmups shared, remove the separate nonblocking prewarmed checks, and simplify the prewarm handle to own a single task.
## Testing
Update the resume prewarm integration test to assert `User-Agent` and `x-codex-window-id` handshake headers while retaining coverage for connection reuse, response continuation, and reconnection after closure. Remove the assertion that healthy resumes skip instruction preparation.
GitOrigin-RevId: a9b6d4810aca9aba2e6e41df181b7d9d90474230
## What changed
- Cast `POSIX_SPAWN_SETSID` to the inferred flag type in the `ProcessMode::NewSession` branch.
- Use `LoaderOverrides::without_managed_config_for_tests()` for both cases in `project_layers_disabled_when_untrusted_or_unknown` so host-managed configuration does not affect the test.
GitOrigin-RevId: 1b27ac3ea139507d3f9402f4c2e3e63933c4d05c
## Why
ChatGPT backend requests could bypass the configured network policy by using a default HTTP client. Requests using captured credentials must also retain the corresponding account policy so revocation continues to block them.
## What changed
- Use the configured HTTP client factory for ChatGPT GET and POST requests, enforcing managed network policy while retaining cookies.
- Capture authentication and network policy together for app reads and plugin reads and installs, preserving that policy across the post-install configuration reload.
- Bind GET requests to the current account policy before loading credentials.
## Testing
Add regression tests for revoked account policies, blocked connector destinations, and network policy enforcement after configuration reload with a cached app client.
GitOrigin-RevId: 5298842eec9664af49df70e89624653d1452fb33
## Why
A previously used WebSocket can close while a thread is idle. Hosts need a way to prepare the connection before the next turn without repeating warmup on a healthy connection.
## What changed
- Expose `CodexThread::prewarm()` using the existing startup warmup and next-turn handoff.
- Reuse healthy connections and pending warmups, retry failed warmups, and repair closed connections. Treat a finished WebSocket reader task as a closed connection.
- Skip scheduling during an active turn or shutdown, and stop warmup admission before shutdown takes the pending task.
- Expose `active_turn_environment_selections()` so hosts can inspect the environments captured by the active turn, including those still starting or failed, when authorizing steering.
## Testing
Add regression coverage for repeated idle prewarm calls, healthy connection reuse with preserved response continuation, reconnection with `generate: false`, and warmup rejection after shutdown. Update delayed MCP discovery coverage to verify prewarm repairs an eagerly closed socket and the first turn reuses it.
GitOrigin-RevId: aa164b91a399de2375eda3bf28397725439fce93
Use `tokio::select!` to listen for shutdown alongside `ws_stream.next()`
in the test server's request loop, allowing the server task to exit when
shutdown is requested while waiting for the next client message.
GitOrigin-RevId: ef77ae64322ab3bdf9b624645a9062a2a9f827cc
Drop the unused command receiver immediately in
`next_event_surfaces_lagged_markers`. Keeping it alive lets `shutdown()`
enqueue a command that nobody handles, causing it to wait for the response
timeout before completing.
GitOrigin-RevId: ce9e13b6f097d4545517ed465c1d3e2343c3d4da
## Why
Registered Windows sandbox setup could appear complete even when Windows rejected the stored account passwords. Checking account flags alone did not detect these failures before runtime logon.
## What changed
- Check stored credentials for both offline and online accounts before reusing completed setup during non-refresh provisioning.
- Classify logon failure, expired-password, and password-change-required errors as `SandboxAccountCredentialMismatch`, preserving the underlying Windows error.
- Trigger full setup to rotate credentials only after verifying that recorded account SIDs still match. Propagate credential-file and policy errors without triggering password repair, and skip credential checks for refresh-only requests.
## Testing
Add tests for native error classification, missing credential files, healthy credentials, password failures on either account, policy failures, and rejection of repair when account ownership validation fails.
GitOrigin-RevId: b3aa02f82841dd2605b0c3585ec93144727721e6
Create a temporary `.curlrc` containing `retry-all-errors` and set
`CURL_HOME` for the DotSlash installer in the shared CI setup action.
GitOrigin-RevId: 920a71c1d1e42016e46c3dd01baa97e082cb4045
## What changed
Call `ensure_rollout_materialized` after recording pending inter-agent communication, using the supplied persistence context. This also triggers the first execution checkpoint when an agent message starts the first turn.
## Testing
Extend the first-input persistence test to cover inter-agent communication, checking that the checkpoint is requested and sampling proceeds while durable metadata is blocked. Verify that prepared context precedes the agent message and that its author and recipient reach the model.
GitOrigin-RevId: 55779edb1a38fcf4d1c1cff24c09f5a810460c3d
## What changed
Remove the session-level capture mode and make thread-owned retained context the default throughout history management. Simplify input ordering, compaction identity preservation, fork handling, and approval freshness checks by removing legacy capture branches.
Keep checkpoint compatibility review separate: unknown or incompatible checkpoints can still use legacy review while retaining user evidence. Set the already-removed `guardianv2.thread_context` feature's default to false and remove redundant opt-out test variants.
## Testing
Update checkpoint tests to exercise legacy review through restored checkpoint data. Adapt existing compaction, resume, rollback, and fork tests to use unconditional context capture.
GitOrigin-RevId: ab23a0d7aca71d5a103458cff8b0c68137dd9708
## What changed
Always use `GuardianContextMode::ThreadOwned` for session capture and subagent history forks, regardless of `guardianv2.thread_context`. Continue selecting reviewer policy from saved checkpoints, preserving legacy review for incompatible checkpoints and removing the feature gate from reviewer compaction compatibility checks.
## Testing
Update coverage for unconditional retained context across compaction, resume, and subagent forks. Exercise legacy review with saved checkpoints, and verify that local and managed opt-outs do not disable sender context capture or checkpoint migration.
GitOrigin-RevId: cd74e2029c83f12bc655b6563242d06f29dd46af
## What changed
Use retained root context for subagent authorization reviews, removing the separate legacy history path. Remove the runtime `request_user_input` answer buffer and its response counter; authorization versions now track the user-message revision and retained-context completeness.
## Testing
Update authorization and input-handler tests to exercise retained context, and add coverage for the `user_messaging` connector in subagent reviews.
GitOrigin-RevId: 00ad151cf71b843af0e82ae90cbcf559d0c65f89
## What changed
- Deprecate and ignore `features.guardianv2.thread_context`, including profile overrides, with a migration notice. Ignore managed requirements for the removed flag with a warning.
- Preserve surviving legacy root instructions across compaction and resume when retained instructions are incomplete. Include unmatched instructions in worker authorization context with an explicit unknown-ordering notice, without replacing newer retained facts or expanding the reviewer's model window.
- Use surviving source calls to roll back verified answers from older checkpoints that lack acceptance-order metadata.
## Testing
Add regression coverage for legacy instruction recovery, compaction and resume, source matching, and answer rollback around same-turn user input. Update configuration and Guardian review tests to verify that the deprecated opt-out still uses thread-owned context and rejects incompatible compaction evidence.
GitOrigin-RevId: a65936c9e0b912e7667d1385a2ec53df726565de
## What changed
- Define `capabilities/discoverV2` request and inventory types and advertise `capabilityDiscoveryV2` in executor metadata.
- Prewarm installed plugin and global skill locations at server startup, with nonfatal scan failures.
- Add sandbox-scoped discovery caching with file watcher invalidation and request-time reloads when watching is unavailable.
- Batch metadata reads through the filesystem sandbox helper and bound discovery responses to 4 MiB and 2,048 capabilities.
- Share plugin identity and installed-version selection in `codex-core-plugin-common`, and fall back to `.app.json` when a plugin does not declare an apps configuration.
The V2 discovery manager is not yet wired into RPC request dispatch.
## Testing
Add coverage for inventory metadata, sandbox cache isolation, watcher invalidation, startup scan failures, response limits, and compatibility with older executor metadata.
GitOrigin-RevId: a223a5bc15fdf251023c0c71f468fd92c3b2d847
## Why
Detached work can keep request spans open beyond response enqueueing. Record explicit phase timings to distinguish request handling from the full span lifetime.
## What changed
- Record server dispatch and response enqueue offsets from request receipt, plus a response enqueue event for HTTP responses that bypass the dispatcher.
- Emit client request enqueue and response receipt events, including success or server-error outcomes and reader-to-caller delay. Carry completion timestamps to the awaiting task so receipt events retain its tracing context.
- Add spans for process startup, sandbox preparation, shell snapshot preparation and capture, and process spawning. Record process identifiers only when nonempty and at most 64 bytes long.
GitOrigin-RevId: 237db898b3284fe8a6a36cb0055b3c7991d8e8a4
## What changed
Add `ModelRequestContributor` and `ModelResponseInterceptor` to the extension API. Contributors can add filtered `client_metadata` without overwriting existing or reserved fields and create interceptors for individual requests.
Wire contributors into HTTP and WebSocket requests, distinguishing generation from warmup. Apply response interceptors in registration order before tracing and response bookkeeping so transformed output is recorded consistently. Interceptors can inspect, buffer, or transform events, with stream ownership carrying request state and cancellation.
## Testing
Add tests for metadata protection, incremental event transformation, interceptor ordering, upstream cancellation, and consistency between delivered output, traces, and WebSocket bookkeeping. Integration tests cover output gating and interruption over HTTP and WebSocket, including a contributor that bypasses gating for warmup requests.
GitOrigin-RevId: d4bc1745d2cacf8636728dbc0a58ab9f250e9392
## Why
Flowcharts with labels such as `A["Review & confirm"]` fell back to source display instead of rendering a diagram.
## What changed
Accept double-quoted node and edge labels, strip the surrounding quotes, and allow literal ampersands in flowchart labels. Keep other diagram families' label restrictions and continue rejecting HTML, entity escapes, and malformed quotes.
## Testing
Add parser and renderer regression tests for quoted labels, literal ampersands, statement separators, and unsupported text, plus TUI coverage for rendered labels and entity source fallback.
GitOrigin-RevId: 9e61a04665f0266d369fa3595411c9a72f10cb9d
## Why
MCP resource helpers use fixed descriptions and parameter schemas, preventing the model catalog from supplying model-specific guidance.
## What changed
Add `model_messages.tools.mcp_resources` entries for `list_mcp_resources`, `list_mcp_resource_templates`, and `read_mcp_resource`. Resolve these entries for the current model when constructing tool specs for direct calls and Code Mode.
Descriptions and parameter schemas override independently. Preserve bundled defaults for missing fields and fall back to bundled parameters with a warning when a supplied schema is invalid. MCP resource execution remains unchanged.
## Testing
Add unit coverage for independent overrides, literal descriptions, and invalid-schema fallback. Add integration coverage for resource discovery and reading through direct calls and Code Mode, plus assertions that resource tool specs follow model changes between steps.
GitOrigin-RevId: 40b5beddb38b2b61c19dc9cd6013d6ba5d756dbc
## Why
Incomplete setup for the installed app reported the same error as an owner mismatch or removal in progress, obscuring the need to retry sandbox setup.
## What changed
- Distinguish owner mismatch, Codex home mismatch, removal in progress, and incomplete setup when authorizing the registered runner receipt.
- Tell users to retry sandbox setup when the receipt is not ready for the installed app.
- Add operation and account context to provisioning failures, including account logon, profile preparation, package queries, alias resolution, and registration persistence.
## Testing
Add a unit test covering distinct authorization errors and their precedence, acceptance of a ready receipt, and rejection after the app package changes.
GitOrigin-RevId: 4e7620c4670e8b02a411a176cc89bd72dcd6e478
## Why
Windows 10 rejects the Object Manager drive-letter link when opening a directory with `OBJ_DONT_REPARSE`, preventing ordinary local-drive paths from opening successfully.
## What changed
Resolve drive-letter aliases with `QueryDosDeviceW` before calling `NtCreateFile`. Accept only direct disk-volume mappings, rejecting other devices and volume subpaths. Leave filesystem components unresolved so `OBJ_DONT_REPARSE` continues to reject filesystem reparse points.
## Testing
Add tests for drive-root opens and NT path construction using ordinary and verbatim drive paths, plus validation of accepted disk-volume mappings and rejected device or subpath mappings.
GitOrigin-RevId: 2fe81913a7ac8d0122ec423db5750e80241def56
## Why
Channel tools use bundled descriptions even when the model catalog supplies tool messages. Let their descriptions follow the active model, including model changes within a turn.
## What changed
- Add channel tool entries to `MultiAgentToolMessages` and pass them to the message board extension for each step.
- Apply catalog descriptions while retaining bundled text for missing or null values and honoring empty strings. Ignore parameter overrides with a warning and keep bundled schemas.
- Clarify bundled descriptions for channel discovery, thread reading, posting, and subscription notifications.
## Testing
Add coverage for full and partial overrides in namespaced and Code Mode tools, preserving Code Mode declarations and parameter schemas. Extend the mid-turn model-change test to verify that the `post` description follows the active model.
GitOrigin-RevId: fca20bed1203d5214713f82cb16a91eeebb38f56
## Why
Output produced before the streaming subscriber attaches can be missing from command completion events, even when it was returned to the model.
## What changed
Record the bounded completion transcript directly in `UnifiedExecProcess` as local and exec-server output arrives. Keep it independent of output polling and streaming delta delivery, and use it for completion events.
## Testing
Add regression coverage for output collected before subscription, both with and without later output. Strengthen the lifecycle test to assert that `aggregated_output` includes both early and late output.
GitOrigin-RevId: 9825acbd706dc4845837c8b4ab1347d8267ce0af
## Why
The default transport fallback bypassed managed application network policy when using `ReqwestDefault` proxy handling or running inside the Codex sandbox.
## What changed
Use a `RouteAwareClientPool` whenever application network policy is managed, retaining policy enforcement for requests and redirects while preserving legacy proxy behavior and custom CA fallback.
## Testing
Add code mode web search regression cases for denied initial requests and denied redirect destinations, verifying that policy errors reach tool output and no requests reach the denied destination.
GitOrigin-RevId: 74ba0e6e4dcad03f3e83c0450b8b17bcefcc267c
## Why
Tool lifecycle observers need visibility into calls rejected before execution starts and timing that remains available on cancellation, independently of tracing settings.
## What changed
- Add `on_tool_dispatch` and `on_tool_timing` callbacks to `ToolLifecycleContributor`, with thread, turn, and call IDs for correlation.
- Report direct calls before readiness, dispatch waiting, and hooks. Report handler duration when dispatch completes or is dropped, excluding readiness and gate waiting and returning zero if the call never passes the gate.
- Expose code-mode host durations as a separate `HostOperation` timing boundary. Exclude nested code-mode calls from dispatch and handler timing observations to avoid double counting.
## Testing
Add tests for callback ordering on completed and rejected calls, timing on cancellation, zero handler duration before gate admission without tracing, and code-mode host timing without nested dispatch or handler timing observations.
GitOrigin-RevId: 97998b5094564c13cb2cfad089bb0a9d6615eb5c
## What changed
Use a dedicated default catalog for Bedrock Mantle endpoints whose host starts with `bedrock-mantle.us-gov-` and ends with `.api.aws`. Include only GPT-5.6 Terra, GPT-5.6 Luna, and GPT-5.4, with GPT-5.6 Terra as the default.
## Testing
Add model picker snapshot coverage for `us-gov-west-1` and `us-gov-east-1`. Update the configured-catalog test to use a GovCloud endpoint, verifying that a custom catalog is preserved while service tiers remain normalized.
GitOrigin-RevId: 5f22ba6983bd60be52d8845c9709112a4766839d
Update the Bazel release archive version and checksum from `0.153.1` to
`0.156.1`, and point `exec-server-stable-release-test` at the new archive.
GitOrigin-RevId: 1d28566d2447c027a67c4197b213458a0838fde0
## Why
Linux descriptor cleanup used allocating directory enumeration after `fork`. The child needs allocation-free cleanup while preserving Rust's spawn-error channel until `exec` succeeds.
## What changed
- Mark unrelated descriptors close-on-exec with `close_range(CLOSE_RANGE_CLOEXEC)`, leaving stdio and explicitly preserved descriptors' flags untouched.
- Fall back to stack-backed `getdents64` enumeration of the child's descriptor table when `close_range` fails.
- Document best-effort cleanup: failures allow launch to proceed and may leave unrelated descriptors inherited.
## Testing
Add Linux tests for descriptor inheritance, unsorted and duplicate allowlists, unchanged parent descriptors, fallback cleanup above a lowered descriptor limit, preserved exec-error reporting, and successful launch when both cleanup paths fail. Retain MCP coverage for descriptor exclusion in servers and descendants.
GitOrigin-RevId: 13abb95f82557324c7b40feb36bd6f806d60674e
## Why
Selected rollouts can reference history stored in ancestor rollouts through `history_base`. Attaching only the selected files leaves that inherited history out of diagnostic reports.
## What changed
When `include_logs` is enabled, follow nested `history_base` references and attach ancestor prefixes up to the recorded byte offsets. Deduplicate ancestors, retain the largest requested prefix, and skip rollouts already selected for upload.
Bound discovery to 64 ancestors and five seconds, and enforce attachment size limits. Missing, unreadable, or incomplete ancestor prefixes are best effort and do not prevent the report upload.
## Testing
Add a unit test verifying that nested parent and grandparent history bases are attached with the expected filenames and contents.
GitOrigin-RevId: d9bba3e50573d25843d2eaedeae775946223ed0e
## What changed
Add `otel.log_agent_responses`, disabled by default and requiring an OTLP HTTP or gRPC log exporter. Emit `codex.agent_response` for completed `final_answer` messages from main agents and spawned task agents, with session, turn, item, and available parent/root attribution.
Strip memory citations from exported text, preserve the stored answer, and cap responses at 64 KiB on a UTF-8 character boundary. Include the original byte length and a truncation flag, and suppress duplicate item completions within each turn. Exclude commentary and non-task agents.
## Testing
Extend configuration tests for default-off and explicit opt-in behavior, the agent execution test for main/subagent response attribution, and the log-buffer test for response-event exclusion.
GitOrigin-RevId: eacda1150de2e6bac2c667d71b57214b0a086f1a
## Why
App-server clients need a way to connect to executors that require bearer authentication through `environment/add` and `environments.toml`.
## What changed
- Add optional `authBearerToken` to `environment/add` and `auth_bearer_token` to URL entries in `environments.toml`.
- Send the token as an `Authorization: Bearer` header on initial connections and reconnects, without automatic refresh. Require `wss://` or a loopback destination when a token is supplied.
- Redact tokens in debug output, mark connection headers sensitive, and omit source text from TOML parse errors.
- Preserve unauthenticated behavior when tokens are omitted, including requests with a null `authBearerToken`.
## Testing
Add integration coverage for authenticated and unauthenticated executors through both RPC and TOML configuration, including missing, null, incorrect, and malformed RPC tokens. Extend tests for reconnect authorization headers, token redaction, URL-only token configuration, and timeout preservation.
GitOrigin-RevId: 2a5d48a1846df1720e4a9b295968348378c287c6
## Why
The Browser connector on `codex_apps` needs the computer-use policies and review handling already applied to `node_repl` and `cua_repl`.
## What changed
- Classify `connector_openai_browser` using registered tool metadata and preserve its computer-use scope through Guardian review.
- Extend confirmation-policy forwarding, review evidence capture, JavaScript execution tracking, and initial-call approval handling to the Browser connector.
- Correlate Browser elicitations with live invocations so nested actions retain their own review identity while assessments are attributed to the originating call. Require verified Browser identity for strict nested review.
- Include the Browser connector in computer-use policy prompts and bundled model messages.
## Testing
Add integration coverage for ordinary and strict Browser nested reviews, including policy injection and action attribution. Verify strict review declines requests with missing or unknown invocation correlation or a non-Browser registration.
GitOrigin-RevId: b04af6fb9db1bac2203dc4265913d210746df90b
## What changed
Add `model_messages.tools.indirect_description_prefixes` with selectors for exact namespaces and configured MCP server names. Apply the selected model's guidance to namespace documentation embedded in `CodeModeOnly` prompts, `ALL_TOOLS` descriptions, and namespaces returned by tool search.
Trim prefix values, treat empty values as no prefix, and reject conflicting selectors for the same namespace. Apply prefixes during rendering so model changes take effect without altering direct tool specifications, search ranking, or tool dispatch.
## Testing
Add unit tests for prefix normalization, namespace grouping, MCP server mapping, and conflicts. Add scenarios covering both Code Mode variants, clearing prefixes on model changes, unchanged tool dispatch, and conflict rejection before a model request.
GitOrigin-RevId: 0c7ce6d418c775945c2ccfdab3c605fa4d431b55
## Why
HTTP retries used local backoff even when the server supplied `Retry-After`. Relative retry delays also failed to account for time spent propagating errors or reporting retries.
## What changed
- Parse `Retry-After` delay seconds and HTTP dates into a monotonic deadline captured when response headers arrive.
- Honor that deadline for HTTP retries, falling back to local backoff when valid advice is absent.
- Preserve deadlines through API and Bedrock error mapping, stream retries, and exhausted retry state. Expired advice remains a zero delay instead of triggering local backoff.
## Testing
Add coverage for header parsing, deadline countdown and expiry, error mapping after exhausted HTTP retries, and delayed stream retry notifications. Update Responses and remote compaction tests to verify that HTTP retries honor `Retry-After`.
GitOrigin-RevId: a2eff02946e5524f29e06f7ba1431e3d339261a4
## What changed
- Add `tui.copy_on_select` with `auto` (default), `always`, and `never` modes, and apply it to the fullscreen transcript, transcript overlay, and resume/fork previews.
- Enable `auto` in tmux and Zellij, and in direct macOS terminals except Ghostty and Kitty. On other platforms, enable it in direct terminals identified as iTerm2 or Terminal.app.
- Copy nonempty mouse selections on release, including word and line selections, while retaining their highlight. Preserve link activation and ignore empty selections.
- Clear composer selections after confirmed keyboard copies, matching right-click copies, while preserving the draft and cursor. Keep selections when copying fails or delivery is unconfirmed.
## Testing
Add coverage for terminal defaults and configuration overrides, copying on release, retained highlights, repeated clicks, link activation, and empty drags. Extend composer coverage to verify selection clearing for `Cmd-C`, `Ctrl-C`, and right-click across clipboard outcomes.
GitOrigin-RevId: 24e6f9e267ef3ab249c5356db736e094127f68b8
## Why
Transient connection and registry failures can reach remote filesystem callers as generic `io::ErrorKind::Other` errors. Callers need a typed signal to identify failures that read-only preparation can retry.
## What changed
- Add `ExecServerError::is_retryable_preparation_error()` to classify transient registry, connection, handshake, timeout, and session-attachment failures, including errors wrapped in `ConnectionAttempt`.
- Map these failures to `io::ErrorKind::BrokenPipe` in the remote filesystem adapter.
- Keep authentication, TLS, and malformed protocol failures outside the retryable classification; error text alone does not trigger it.
## Testing
Add a regression test showing that a wrapped registry service-unavailable error maps to `BrokenPipe`, while a protocol error containing transport-closed text remains `Other`.
GitOrigin-RevId: c3e1bbab8f977a0b421eba5d6d3071ada72c09ff
## Why
Startup prewarm waited for tool discovery before opening its WebSocket connection. Slow MCP startup therefore delayed connection setup even though the handshake could proceed independently.
## What changed
- Run the WebSocket handshake concurrently with tool capture, then send `generate=false` with the discovered tools and finalized request metadata.
- Include model and effective service-tier routing hints in preconnect, including the inherited tier for spawned subagents. Omit routing hints for guardian reviewer requests.
- Recover authentication failures during preconnect and switch to HTTP fallback on `426 Upgrade Required`.
## Testing
Add and extend regression coverage for handshake overlap with delayed MCP discovery, cancellation before warmup, finalized Responses Lite tool metadata, socket reuse and reconnection, service-tier changes and inheritance, and authentication recovery during preconnect.
GitOrigin-RevId: ecb53540765df8227e55e79910a13a05260a4c8d
## What changed
Use `agent_control.resolve` for message board agent lookups and path validation instead of accessing `local_agent_runtime` directly. Derive paths from the session source, with a root fallback, and verify that each path resolves to the agent that owns it.
Validate the requested caller's thread for path and clock queries, and apply the same path ownership check to notification recipients.
GitOrigin-RevId: 92632a31b493b6519d2154f49e9d1d4a1019b394
## Why
Actions targeting a secondary environment could be reviewed with the primary environment's denied-read restrictions. Each review needs the permission context of the environment that owns the action, including when a Guardian session is reused across environments.
## What changed
- Carry `environment_id` through environment-scoped approval requests and their planned-action JSON.
- Select and label permission context using the target environment, explicitly stating when it has no denied-read paths or globs.
- Reject reviews for unavailable target environments and reject environment IDs longer than 256 bytes before Guardian inference, while preserving manual approval routing for oversized IDs.
## Testing
Add coverage for `exec_command`, `apply_patch`, and `request_permissions` reviews switching environments while preserving the existing review prefix. Extend tests for environment-specific restrictions, unavailable environments, action serialization, and the 256-byte ID boundary.
GitOrigin-RevId: ad3292edddb1c6f5b180142c6857cba6f1308328
## What changed
Add `AgentControl::ensure_child_loaded` and use the parent's configured agent control in `ThreadManager` to reload recorded V2 children. The local implementation delegates to the existing loader using the live parent's current configuration, preserving parent-controlled restoration without sending input.
GitOrigin-RevId: 67cadf79cbc034eb271c5ae13145f1a42722fe69
## Why
Enabling `features.token_budget.use_history_notes_extension`, explicitly or through model defaults, rejected session startup when the model lacked `supports_experimental_context`, even with experimental mode disabled.
## What changed
Remove that startup restriction so token-budget history and notes can be used independently of the model's experimental context capability.
## Testing
Extend core tests to cover explicit configuration and model defaults on startup and cold resume, checking `new_context`, token-budget contexts, and `history_ingest_requested` metadata. Add app-server coverage for native history and notes tools and context-window hints without experimental context capability.
GitOrigin-RevId: 6157479aeb75ffd785b8d4b2f48b11c6f46e8f35
## Why
Messages sent through the singular `user_message` connector were omitted from Guardian's delivered assistant message evidence because only `user_messaging` tool names were recognized.
## What changed
Accept both namespaced and flat `user_message` forms of `send_message` alongside the existing `user_messaging` forms.
## Testing
Extend Guardian subagent authorization tests to cover the singular connector and flat tool names, including blocked post-tool hooks and cancellation before confirmation. Add a negative case ensuring `send_message_to_thread` is not treated as delivered message evidence.
GitOrigin-RevId: 68495642ef4b78eec71df4fee2bacfda407adc47
## Why
Nested writable roots must allow the Linux sandbox to start while preserving read-only metadata protections, including when a writable directory sits beneath a read-only `.codex` directory.
## What changed
Defer read-only subpath mounts shared with a deeper writable root until that root is bound. Keep symlink target remapping and writable-symlink validation for deferred paths so mount ordering does not bypass those checks.
## Testing
Add regression coverage for mounting `.git`, `.agents`, and `.codex` metadata exactly once after the nested writable bind. Add sandbox integration cases for ordinary and symlinked roots, using both parent and nested working directories, to verify startup, allowed writes, metadata protection, and temporary mountpoint cleanup.
GitOrigin-RevId: 45e439eaf537e10bfa8b839bad816b0401fb65aa
## What changed
Add `resolve_root_git_project_uri_for_trust` to resolve repository trust roots through `ExecutorFileSystem` using executor path conventions. Share repository and linked-worktree validation with native lookup while preserving native ancestry for paths with opaque URI representations.
Extract `ProjectTrustLookup` to match merged project settings using supplied path spellings and an explicit path convention. Preserve canonical-before-original and cwd-before-repository-root precedence, including cwd entries without a trust level, with ASCII case-insensitive matching for Windows.
## Testing
Add coverage for POSIX, Windows drive and UNC trust roots, project-key precedence and case handling, and native/URI lookup parity. Extend environment-config coverage to verify returned `projects` entries include entries without a trust level.
GitOrigin-RevId: 315434802e86cceee85b14bc1c3767a45e3139f5
## What changed
Add `record_global_operation` to record an operation count and duration in milliseconds, buffering up to 256 pairs until a metrics provider is installed. Validate both metric names and tags before accepting a pair, limit each operation to 16 tags and 1024 bytes of metadata, and drop whole pairs when the buffer is full.
Drain pending operations on installation and serialize recording with provider lifecycle changes so a pair stays with one installation. Resume buffering when the active provider shuts down without disturbing a newer installation. Disabling metrics discards pending operations and suppresses recording until metrics are enabled again.
## Testing
Add unit and integration coverage for buffer limits, validation, concurrent installation and replacement, redirected global handles, shutdown buffering, and accepted or rejected opt-out configuration changes.
GitOrigin-RevId: 3b094e69bf975016ff1fb8f99b3611c2ccddccf3
## Why
Queued-message edit hints could vary by terminal instead of showing the first configured shortcut. Use the keymap consistently for queued messages and async question navigation.
## What changed
- Make `Shift+Left` the primary shortcut for advancing through questions and editing the last queued message, and `Shift+Right` for navigating back toward the composer. Keep `Alt+Up` and `Alt+Down` as alternatives.
- Remove terminal-specific hint selection and derive hints from the configured keymap, including custom chords and unbound actions.
- Update question footers, queued-input previews, and keymap picker snapshots to reflect the preferred shortcuts.
## Testing
Extend tests to cover both default shortcut pairs, configured shortcut ordering, custom chord hints, and hiding the queued-message edit hint when the action is unbound.
GitOrigin-RevId: e0f60860ef1e81c71ca0fc32369b8cbd12582b47
## Why
PTY launches need to establish a controlling terminal and reset signal state. Extend the Linux process setup helper to perform this work in a fresh, single-threaded process image without forking the application when the native helper is available.
## What changed
- Add a PTY setup mode and support caller-owned stdout and stderr descriptors so all three standard streams use the PTY slave.
- Use the helper for eligible Linux PTY launches, including launches with explicitly preserved descriptors, and wait for child exit asynchronously.
- Preserve portable PTY behavior for `PATH` lookup, custom `argv[0]`, missing working directories, default `SHELL`, stdin EOF, and signal exit status.
- Retain compatibility fallbacks and release the initial PTY descriptors before allocating a portable replacement.
## Testing
Add regression tests for controlling-terminal setup without forking, portable signal exit status, and successful fallback under file-descriptor pressure. Resolve the Python test executable to an absolute path to exercise the helper path.
GitOrigin-RevId: 4b07ce68aa33c5b79548581e221caf5953b0eda1
## What changed
Add real-child tests for parent-death signaling, large environment transfers, explicit file descriptor inheritance, and fallback when the helper exits before acknowledgement.
Introduce test-only pause points during environment transfer, reporting, and exec to verify that cancelling startup kills and reaps the helper. Cover cancellation after runtime shutdown and verify that the fallback reaper can reap an exited child while an earlier child remains alive.
Probe an actual helper launch before asserting native-helper behavior, and skip fixtures when their required procfs or pidfd support is unavailable.
GitOrigin-RevId: 5136dc242a91efd0596171266965f29903c6c970
## Why
Linux pipe launches need session, parent-death signal, and descriptor setup. Move this work into a fresh, single-threaded executable image to avoid forking the app-server for child setup.
## What changed
- Register an early setup helper and launch it through `posix_spawn` for Linux pipe processes.
- Start the helper with an empty environment, then transfer the target environment over a control socket so loader settings cannot interfere with helper startup.
- Await target execution asynchronously, propagate setup and execution errors, and kill incomplete launches on cancellation.
- Preserve direct spawning as a fallback when the helper is unavailable or fails before target execution.
## Testing
Add coverage for launch semantics, avoiding fork, loader environment isolation, early argument dispatch, closed standard descriptors, and fallback under bootstrap failure or descriptor pressure. Add an app-server regression test that reuses a process handle after an execution failure.
GitOrigin-RevId: 079c673f0f22ebd531f8c57e5338095cc98acfdc
## What changed
Launch Unix shell snapshot commands through `codex_utils_pty::Command` with `ProcessMode::NewSession`, replacing the custom `pre_exec` hook. Pass the complete, scrubbed child environment and preserve the original command arguments so NUL bytes are rejected before execution.
## Testing
Add a Unix regression test asserting that a snapshot script containing a NUL byte returns `InvalidInput` without creating the file it would otherwise write.
GitOrigin-RevId: ef68a6c9f64d7a541498d3ecc4113fad8ff7ed14
## Why
Unix command hooks use a `pre_exec` callback to detach from the controlling terminal, forcing the launcher to fork. Native spawn attributes can create the detached session without that callback.
## What changed
- Route Unix hooks through `codex_utils_pty::Command` with `ProcessMode::NewSession`.
- Extend the native `posix_spawn` launcher to detached Linux sessions, retaining compatibility fallbacks for unsupported libc features and executable handling.
- Preserve the session environment snapshot, hook overrides, and restricted-variable filtering.
## Testing
Add regression coverage for launches without parent forks, terminal detachment, environment and argument handling, Linux `PATH` lookup, and executable compatibility. Cover process-group cleanup on cancellation and timeout, including descendants holding output pipes open, and preservation of background descendants after completed hooks.
GitOrigin-RevId: dbe2cf12d84aa79868cfb55ace40c7d5b5282703
## Why
Pipe spawning installs Unix `pre_exec` hooks, forcing a fork on macOS even though the shared child launcher supports native spawning.
## What changed
- Use the shared `Command` for pipe processes, enabling native macOS spawning while preserving session isolation, explicit descriptor inheritance, and Linux parent-death handling.
- Select `ReapOnly` so the pipe adapter retains ownership of process-tree termination.
- Track embedded NUL bytes in original Unix command inputs and reject them before spawning, including when invalid `current_dir` or `arg0` values are later replaced.
## Testing
Add macOS integration coverage verifying fork avoidance, executable path lookup, pipe I/O, session isolation, and descriptor inheritance. Add Unix regression tests for pipe and PTY fallback under descriptor pressure and for rejecting NUL inputs without running the child.
GitOrigin-RevId: f4fa2c1d3c1aee2c4ffa1dc2ff946f9f0b08eb20
## What changed
- Add `ProcessMode::NewSession`, null stdin, and opt-in Linux parent-death termination to the shared child command API.
- Replace `DescriptorPolicy::StdioOnly` with `Explicit` and add `preserve_fds` to allow selected inheritable Unix descriptors alongside stdio. Preserve descriptor numbers without duplicating or closing the parent's descriptors, keeping POSIX record locks intact.
- Support session creation and preserved descriptors in the native macOS backend, with a compatible fallback for high descriptor numbers rejected by native file actions.
## Testing
Add regression coverage for process groups and sessions, descriptor preservation across native and executable-text launches, the last descriptor slot below the file limit, and retention of parent record locks.
GitOrigin-RevId: 29ecd859d3b673da6ae6412cc06a32fa10d11346
## What changed
Add a crate-private `ChildDropPolicy` to choose whether dropping a child kills it or only reaps it after exit. Keep `KillAndReap` as the default.
For `ReapOnly` on Unix, transfer dropped children to a shared reaper thread that operates independently of the Tokio runtime. Support both Tokio children and native macOS children, without blocking drop or letting a live child delay reaping others.
## Testing
Add an isolated regression test verifying that reap-only children survive handle drop after runtime shutdown, are reaped after exit, and do not prevent other exited children from being reaped.
GitOrigin-RevId: 5ec639597dba7f3b61694d6d465991e054ae3397
## What changed
Expose the shared `--ws-auth` options on `codex exec-server` for direct WebSocket listeners. Support capability tokens configured by token file or SHA-256 digest, and signed JWT bearer tokens. Validate `Authorization: Bearer TOKEN` before each WebSocket upgrade, rejecting missing or invalid credentials with HTTP 401 when authentication is enabled.
Reject listener authentication with stdio, `--remote`, or `forward`. Document the options and connection-time authentication behavior.
## Testing
Add CLI integration tests for all three credential configurations, unauthorized upgrade rejection, authenticated RPC initialization and reconnects, invalid configuration, and incompatible transports.
GitOrigin-RevId: 941fbd3d43e732c910d29b6f8137077b7c332835
## Why
Publishing a hotfix for an older release line or alpha can replace a newer prerelease pointer. Release pointers should advance according to version order.
## What changed
- Share release version validation and numeric comparison across publishing scripts, including alpha hotfix suffixes and alpha, beta, and stable ordering.
- Read the prerelease pointer directly from R2 and update it only for a newer version or missing or invalid version metadata.
- Restrict `latest-alpha-cli` updates to alpha releases with successful R2 and npm publishing, and compare against the branch's Cargo version before advancing it. Allow replacement when the manifest version cannot be parsed or validated.
## Testing
Add 15 passing unit tests covering version validation, older release lines and alphas, numeric hotfix ordering, prerelease precedence, equal versions, and missing or invalid versions.
GitOrigin-RevId: 6bee3906a47f613b662ef2b2224cfcbd1b56650c
## Why
A realtime call can start or end while a text turn is still running. Using call activity captured at turn creation leaves subsequent model requests with stale realtime context.
## What changed
Capture realtime activity and mode instructions together in a `StepContext` snapshot for each model request. Use that snapshot to build realtime instructions and persist `realtime_active` in the request's turn context. Store the conversation and mode instructions under one mutex so they are installed together when a call starts.
## Testing
Extend the realtime handoff integration test to start and close a call during one text turn, verifying that successive requests include the appropriate start and end instructions.
GitOrigin-RevId: 4c5c2b47b7c0c06ae28167013218dc2e3cd72c42
## Why
Debug executables can be hundreds of megabytes. Computing their identity previously loaded the entire file into memory and hashed it on an async runtime thread.
## What changed
Stream executable contents into the BLAKE3 hasher using `tokio::task::spawn_blocking`, preserving the existing digest format while avoiding whole-file allocation and moving hashing off the async runtime.
## Testing
Expand the executable identity test to verify compatibility with whole-file hashing for a file spanning multiple reads with a partial final buffer and for an empty file, and to confirm that changing a byte changes the identity.
GitOrigin-RevId: 528103397395313d170ec720fefc8c5ab3676956
## What changed
Serialize custom reasoning effort values that parse as `u64` as JSON numbers in API requests. For example, `model_reasoning_effort = "64"` now sends `reasoning.effort` as `64`. Keep named values and custom values that cannot parse as `u64` as strings.
## Testing
Expand the request integration test to cover configured named effort, zero, a positive integer, an unknown name, a negative value, and an integer exceeding `u64`.
GitOrigin-RevId: 18ad03a1cd97dfa3f1a3cc49a43b3f7ca7d9b657
## Why
An unfinished Markdown link can display its destination across multiple preview rows, then collapse when the closing parenthesis arrives.
## What changed
Keep the link label visible while withholding the opening parenthesis and destination until the link closes. Scan incoming text incrementally, accounting for nested parentheses, escapes, angle-bracket destinations, titles, and inline code. Apply this holdback only to rich prose previews; newline commitment and finalization still render the original source.
## Testing
Add regression tests for character-by-character input, long Unicode destinations, resizing, raw-mode switching, and flushing unfinished links on newline or completion, plus a snapshot of the label-only preview.
GitOrigin-RevId: 9cea680a93dfcd0aea21f0fc12006b27400d4dab
## Why
Guardian authorization reviews need the assistant message that prompted a user’s approval, even when a post-tool hook blocks the messaging result or compaction removes the original tool call.
## What changed
Retain confirmed delivered assistant text from tool-output metadata at the original call’s position in thread-owned Guardian context. Recover these messages when restoring checkpoints and respect the call’s inherited-context status.
## Testing
Extend authorization coverage to verify that a delivered message remains in the Guardian root snapshot after a blocked tool result, compaction, and resume, and update checkpoint expectations to preserve assistant/approval ordering.
GitOrigin-RevId: df30ec8a3ef21443210a937ab6db119de8a5fd51
## Why
A user can reply to a streamed question before its completed message is recorded. Assigning the assistant message's order at completion can place the reply before the question in retained context.
## What changed
Reserve an assistant message's order when its source stream starts in thread-owned Guardian context, then reuse that reservation when recording the message. Reserve completion-only messages before publishing their text, and give text and plan output from the same source message a single order.
## Testing
Add streaming regression coverage that accepts a reply before the question completes and verifies question-before-reply ordering both live and after resume. Cover server-provided and generated message IDs, plan output, and text combined with a plan.
GitOrigin-RevId: cb67e7459c804df7beb0841908244202448c655a
## Why
Ordinary user replies can depend on preceding assistant messages. Losing those messages during compaction can leave Guardian without the context needed to interpret a reply's scope.
## What changed
- Retain original assistant messages, including commentary, with their recorded order across checkpoints and resume. Exclude compaction output from this evidence.
- Include assistant context in local and delegated reviews as untrusted context, with separate storage limits and lower budget priority than user instructions.
- Prefer assistant context preceding ordinary replies when selecting bounded root evidence, and report unavailable context without inferring what a reply refers to.
- Preserve inherited context scope and remove assistant evidence beyond rollback boundaries, including during rollout migration.
## Testing
Extend coverage for compaction and resume, checkpoint migration, queued-input ordering and rollback, role labeling, and evidence budgets that preserve user restrictions while dropping assistant context.
GitOrigin-RevId: 886189b0be29ffc3d324b56f5d0b673d6b8d84da
## Why
Mermaid diagrams that cannot be rendered currently fall back to source without
explaining why the preview is unavailable.
## What changed
Show a dimmed notice above the preserved source when a completed Mermaid block
uses unsupported syntax, exceeds renderer size limits, or does not fit the
terminal width. Wrap the notice to the available width and preserve indentation
inside lists and blockquotes. Leave unfinished fences and disabled Mermaid
rendering without notices.
## Testing
Add coverage for fallback reasons, dimmed styling, source preservation, nested
indentation, and suppression of notices for unfinished fences and disabled
rendering. Update the streaming resize snapshot to include the width notice.
GitOrigin-RevId: 6ac7914b398c855e7aed3775ee0de70fb4484b78
## Why
Turn completion precedes active-turn cleanup, so the remote compaction test must wait for the thread to become idle before injecting its history fixture.
## What changed
Register the `ThreadIdle` lifecycle contributor and wait after the initial turn in `remote_compact_v2_rewrites_multiple_trailing_function_call_outputs`, covering both manual and automatic compaction cases.
GitOrigin-RevId: 1593b212db0e07b1457f090b5ac7ba2313a28360
## Why
Command execution analytics lack the observed sandbox backend. Older execution servers may omit this information, so an unknown backend must remain distinguishable from an explicitly unsandboxed process.
## What changed
- Carry optional `sandbox_type` metadata through command execution items and emit its metric tag as `sandbox_backend` in analytics.
- Propagate the observed backend through unified execution completion and failure events, including asynchronous exits.
- Preserve missing backend information as `None` and mark executed user shell commands as `Some(SandboxType::None)`.
- Exclude the metadata from serialized command items and generated schemas and TypeScript types.
## Testing
Extend tests for missing and explicit executor backends, backend propagation on failed execution, and analytics payloads, including platform-specific backend tags in app-server integration coverage.
GitOrigin-RevId: 178fe46824a6194910802ec02168ed40ee0b2019
## Why
Rollout read metrics record the failure stage and I/O error kind, but these do not distinguish specific zstd failures, task join failures, or a busy reader, nor indicate whether any line was read before failure.
## What changed
Add bounded `reason` and `read_progress` labels to rollout read counters and duration metrics, captured at the first failure. Distinguish OS errors, reader-busy and task-join failures, and known zstd error categories, with `stream_error` as the fallback.
Record whether the failure occurred before or after the first line. Classify blocking-task join failures during both open and read. Keep error messages, file paths, and rollout contents out of metric labels.
GitOrigin-RevId: 6db302900f504bc2860504d81c18017adcef3efc
## What changed
Add `features.multi_agent_v2.disable_direct_message`, defaulting to `false`. When enabled, omit `send_message` and `followup_task` while preserving spawning, automatic child results, and the remaining agent management tools.
Require an available message-board `post` tool when this option is enabled for sessions using multi-agent v2 collaboration tools, exempting internal worker sessions.
## Testing
Extend configuration parsing tests and run the message-board subscription/resume scenario with direct messaging both enabled and disabled. Verify post search, subscription behavior, and which collaboration tools are exposed.
GitOrigin-RevId: 72ec22ef0b92fa81e02cdeb058d8b4f93aca3be6
Add a regression test that fails `exec_command` with a missing working directory, pauses command completion, and interrupts the turn before releasing completion.
Verify that the command emits exactly one start and completion, retains its failure status and launch diagnostic, and persists the completion in the rollout. Check that reconstructed history includes the failed command in the interrupted turn.
GitOrigin-RevId: 5962f0791b298ebb05e752138d02b0e0b3af4c63
## Why
V2 tools and model context need to use the controller's agent tree even when the session's local runtime has no registry entries.
## What changed
- Add target resolution and direct-child path lookup to `AgentControl`.
- Move lazy root registration into the controller's resolution and listing methods.
- Build V2 subagent context from controller-provided paths, keeping formatting and size limits in the session layer and preserving loaded-first ordering.
## Testing
Extend the V2 spawn and messaging test with an empty session-local registry to cover relative-path resolution, message delivery, and subagent environment context through the controller.
GitOrigin-RevId: c935b34a6d3314e968ba451ff981cf2a223bbfa8
## Why
When unified exec cannot create a process, command lifecycle events are missing, leaving clients without a command failure notification.
## What changed
Emit start and failure events for terminal process-creation errors in both regular and zsh-fork execution. Report no process ID, an exit code of `-1`, zero duration, and the launch diagnostic, while retaining plugin attribution. Once event publication starts, let it finish even if the caller is cancelled.
Preserve approval rejection handling and retryable sandbox denials.
## Testing
Extend app-server tests to cover pipe and PTY launch failures, plugin attribution on failed launches, and zsh-fork launch failures after approval. Assert failure metadata and check for duplicate lifecycle notifications while retaining approval-decline coverage.
GitOrigin-RevId: 26ed191fc69b903ea4710dd1a6c3b031e8caa4eb
## What changed
- Store `Arc<dyn AgentControl>` in session services and route agent tools, turn admission, usage accounting, completion notifications, and shared settings through the trait.
- Add `AgentControlInit` so delegated and guardian sessions inherit the parent's controller and local runtime.
- Move local registry and context helpers to `LocalAgentRuntime`, keep resume, close, inspection, and status subscriptions on the local controller, and simplify synchronous and infallible trait methods.
GitOrigin-RevId: ad3f213eb483ac524bde56d769f20a78f20989a0
## What changed
Add the boolean `transparent_background` argument to `image_gen.imagegen` for generation and editing. Map `true` to `transparent` and `false` or omission to `opaque`, replacing the previous `auto` background setting.
Update tool guidance to request transparency for background removal and cutouts, and to preserve existing transparency during edits unless the user asks to change it.
## Testing
Add integration coverage for transparent, opaque, and omitted background arguments across generation, editing, and code-mode generation. Verify that `null`, string, and numeric values return a validation error without dispatching an image request.
GitOrigin-RevId: b10ac200a619c72cc1787da41b49d65d0cde05dd
## What changed
Run `AGENTS.md` and thread-instruction refresh concurrently with capability discovery, MCP setup, and tool construction. Box both preparation futures to keep them off caller stacks while they are live together.
Finish delivering returned instruction warnings even when tool preparation fails or is cancelled. Preserve instruction-error precedence and publish the selected-plugin snapshot only after both branches succeed and cancellation is checked.
## Testing
Add tests covering concurrent preparation, warning delivery on tool failure and cancellation, instruction-error precedence, and plugin snapshot publication. Verify that cancellation does not repeat consumed warnings on the next capture.
GitOrigin-RevId: 6b2d7b091aae2dba67ad154a19bdb0ed0f96f6f7
## What changed
Move WebSocket authentication arguments, settings, credential loading, and upgrade authorization into a shared crate using `http` types. Update the app server, transport, and CLI to consume it directly, and remove the `AppServer` prefix from the shared types.
Hide token digests and JWT verification secrets from authentication policy `Debug` output.
## Testing
Move the existing argument validation, capability-token authorization, and signed bearer-token verification tests into the new crate.
GitOrigin-RevId: 1dd20043a3f8efbca55af7eda338b62a62e8fd68
Apply `secondary_text_style()` to the shortcut hint separator and label
so they use a readable foreground color instead of terminal-dependent dimming.
GitOrigin-RevId: 6cd9ced75deca9353c1224d3e5fefc6c4ad6ae8f
## Why
Retry timing assertions can fail if the test is descheduled before retry telemetry is emitted, and parallel tests can leave shared tracing callsites disabled for the test subscriber.
## What changed
- Measure retry intervals from the failed request, filter HTTP observations to `/responses`, and track WebSocket stream requests as well as connections.
- Keep a tracing interest-cache guard alive and rebuild callsite interest when installing the telemetry capture.
- Reserve the connection-failure test's port with a bound socket until the recovery server starts listening.
- Wait for the WebSocket warmup request and assert `generate: false` before submitting user input in connection-limit, rate-limit, and overload tests.
GitOrigin-RevId: bba39ea2ac29ac8553ae6184139382f1e6cdc7ac
## What changed
- Add `environments` to `TurnSettingsUpdate` to replace the selection for subsequent steps without changing future turns.
- Capture model settings and environments together so combined updates apply or reject atomically, while existing steps retain their captured selection.
- Validate environment IDs, working directories, configuration ownership, and permission requirements against the running turn's selections.
- Preserve executor startup behavior when switching environments and use the step's local working directory for tool hooks.
## Testing
Add coverage for workspace switching and restoration on the next turn, atomic model and environment updates, permission validation, executor connection waits, and replacement of pending environment selections.
GitOrigin-RevId: 02b5c57a78fd594b2aed84fc09d9e99eb97be28c
## Why
Thread permission updates could affect later steps of a running turn. Keep inherited environment settings consistent throughout the turn and apply saved updates when the next turn starts.
## What changed
Store active thread defaults alongside selected environments and refresh them when activating a new turn, even when its environment selections are unchanged. Resolve new selections from those active defaults while preserving owner-provided configuration, selection workspace roots, and the local Windows sandbox type.
## Testing
Add a regression test that changes permissions during a paused turn and verifies that both steps retain restricted filesystem access while the next turn receives unrestricted access. Update session and MCP elicitation tests to check that permission changes take effect on the next turn.
GitOrigin-RevId: 37ee44198fa40c138d140974dc90c4177d8c1f4c
## Why
An async question notification can outlive its unanswered question and suppress the lower-priority turn completion notification.
## What changed
Clear pending `AsyncQuestion` notifications when collecting question drafts on completion, interruption, or failure, including the error-handling path. Completed turns can then queue their completion notification.
## Testing
Add regression coverage for all three turn outcomes and assertions for error handling and completion after dropped message deltas.
GitOrigin-RevId: 647b2b37acced431fc98fd4f5334c8973a0be241
## Why
Recovering question answers or interrupted input can cancel an active `Ctrl+R` search or overwrite its preview. Recovery should preserve the search while keeping the recovered input available on cancellation.
## What changed
- Apply background updates to the saved draft without changing the search query or visible preview, including when a query has no match.
- Restore the updated draft on `Esc` or `Ctrl+C`; discard it when accepting a history match. Keep search open when `Enter` has no match to accept.
- Capture the saved draft rather than the preview in draft snapshots, preserving attachments, mention bindings, and pending pastes.
- End search on an explicit fresh draft replacement so cancellation cannot resurrect discarded input.
## Testing
Add regression coverage for recovery on turn completion, failure, and interruption; accepting and canceling search after recovery; Vim undo/redo; pending paste preservation; and clearing drafts after a misalignment policy failure.
GitOrigin-RevId: d3de19bbbcdab2e461c19d47b2b7dca0b28f6ff3
## What changed
Clear pending asynchronous questions when a live turn completes, is interrupted, or fails, and append nonblank typed answers to the main composer in question order without submitting them. Preserve existing composer content and input restored after interruption, and retain large answers as paste placeholders.
Cancel history previews and pending Vim commands during recovery while preserving undo grouping and dot-repeat behavior. Skip recovery during replay and keep input cleared after a misalignment policy violation.
## Testing
Add regression tests and snapshots for open and collapsed drafts, buffered typing, answer ordering, repeated completion notifications, large pastes, interrupted queued input, and Vim undo/redo behavior. Update coverage for terminal errors and realtime question expiration.
GitOrigin-RevId: fec109fe8aecb0735a3a5410fbb063b5c5c6e9a1
## What changed
- Detect Terminal.app from primary and secondary device attributes during startup on Unix SSH sessions without a detected multiplexer. Ignore signatures inside bracketed paste and leave incomplete replies unknown.
- Use inline mode when Terminal.app is detected and `tui.alternate_screen` is `auto`. Apply the decision before the first startup frame and retain it for later configuration loads. Preserve explicit `always`, `never`, and `--no-alt-screen` overrides.
- Update the `crossterm` dependency revision and lockfiles.
## Testing
Add coverage for terminal signatures, fragmented and pasted replies, probe completion and timeout behavior, screen-mode overrides, and an inline startup snapshot.
GitOrigin-RevId: 9b937824b080f9bd6de29df1d9e84f42a698af46
## What changed
Extend an existing transcript selection with Shift-click while preserving its original anchor and selection unit. Allow continued dragging and repeated extension in either direction, including whole-word selections made by double-clicking. An ordinary click still starts a fresh selection.
## Testing
Add tests for extension in both directions, preservation of selection units, continued dragging, and ordinary-click reset, plus a snapshot of word-selection highlighting.
GitOrigin-RevId: e6208c1bc6260ac26e7cd1f81c752b2c0b375f36
## Why
Repeated gateway OAuth credential reads decrypt and deserialize the same unchanged secrets file each time.
## What changed
Add a single-entry cache shared by clones of `LocalSecretsBackend` for `GatewayOAuth`. Reuse decrypted secrets only when the file path, ciphertext hash, and keyring passphrase hash match, and invalidate the cache after writes. Omit cached credentials from the backend's `Debug` output.
GitOrigin-RevId: 91fa03655f5e233d1649f4c2571c5465dfe57f35
## Why
Application network restrictions need to cover clients created by the TUI and `codex exec` before embedded app-server startup, and remain effective when configuration is rebuilt.
## What changed
- Introduce `EmbeddedNetworkPolicy` to share live policy between caller-owned transports and the embedded app-server.
- Apply loaded requirements before creating telemetry, background HTTP clients, and executor connections. Limit authentication and cloud configuration bootstrap requests to exact endpoints under local policy.
- Preserve the shared policy across TUI session changes, permission-profile rebuilds, and worktree cloud loaders so existing clients observe policy reloads and failures.
- Document application network policy behavior and transport coverage.
## Testing
Add regression coverage for policy activation, reload failure and recovery, retained policy across TUI rebuilds, rejected OAuth and cloud-policy redirects, and workspace network restrictions with `CODEX_API_KEY`. Also cover retaining the caller-selected project during embedded startup.
GitOrigin-RevId: 629009f087b8cb21fc34a1ee7ea6fe95d9e0f2b5
## What changed
- Route remote-control enrollment, pairing, client management, and WebSocket connections through the authenticated HTTP client factory. Keep policy denials distinct from authentication failures and wait for policy changes before reconnecting.
- Preserve policy denials through exec-server connection failures so later connection attempts and capability discovery can recover. Keep direct executors running through temporary policy outages while rejecting permanent policy failures.
- Build cached HTTP transports on blocking workers, serialize construction, and retain successful builds after callers time out so request deadlines cover queued construction.
## Testing
Add regression coverage for policy recovery during remote startup, direct registration, accepted WebSocket reconnection, and capability discovery; queued transport construction timeouts; and remote-control WebSocket fallback with invalid custom CA files.
GitOrigin-RevId: c81db18e83de957175bb213d165281ac701089dd
## Why
AWS credential discovery, analytics, and telemetry used clients that did not share the application's network policy. These requests need to honor destination restrictions and permission revocation.
## What changed
- Route AWS credential and region HTTP requests through the shared HTTP client, and check the signing destination before loading credentials. Skip discovery for static access keys with an explicit region.
- Apply account-scoped policy to Bedrock authentication. Require unrestricted policy for credential exporters and reauthentication commands, and cancel active work when permission is revoked. Document that AWS profile `credential_process` network traffic remains outside the application's HTTP policy.
- Send analytics through the authenticated account's HTTP client factory.
- Guard OTLP log, trace, and metric exports with revocable permits, disable them under destination restrictions, and make managed HTTP exports cancellable. Suppress global Statsig settings while managed policy is active.
## Testing
Add coverage for metadata credential request cancellation, allowed and denied SigV4 destinations, AWS credential precedence and endpoint configuration, and blocked credential exporter recovery. Update telemetry tests for account transitions and managed-policy Statsig suppression.
GitOrigin-RevId: d8a2018bfbbe971ec430699b0d3f86a7a9e1e072
## What changed
- Load `application.network` requirements at startup and explicit config/account reloads, applying local policy before authentication and cloud configuration bootstrap.
- Block traffic when policy loading fails, cancel requests that a new policy no longer permits, and reject configuration loads based on superseded policy snapshots. Local requirements edits take effect on the next explicit reload or restart.
- Bind authenticated clients to the current account and revoke them when account ownership changes. Carry policy enforcement through backend requests, realtime connections, workload identity exchanges, and code-mode gRPC streams while preserving gRPC trailers.
- Treat denied credential refreshes as policy errors without retrying them or invalidating stored credentials.
## Testing
Add regression coverage for startup restrictions, reload ordering, cancellation after restrictive or malformed requirements edits, account revocation, gRPC destination denial, workload identity cancellation, and credential preservation after denied OAuth refresh.
GitOrigin-RevId: 0cb4c720a906397e9df06675f01ecf60d741101f
## Why
Codex could enable mouse capture even when the containing tmux session had mouse support turned off.
## What changed
- Probe tmux's `mouse` and `extended-keys-format` settings together, targeting `TMUX_PANE` when available.
- Suppress mouse capture when tmux explicitly reports `0` or `off`, and apply that policy across fullscreen and overlay input changes. Refresh the policy when entering or restoring the alternate screen.
- Preserve normal mouse behavior when the probe fails or the setting is unknown, and retain the keyboard-format fallback for older tmux versions.
## Testing
Add tests for pane targeting, explicit and unknown mouse settings, probe failures, keyboard fallback, and mouse-policy changes across fullscreen and overlays.
GitOrigin-RevId: 7bdd2759207b30a3877e983b489462de7c96e692
## What changed
- Switch the GPT-6, GPT-5.6, GPT-5.5, and auto-review catalog entries to `shell_command` and expand their plan availability.
- Mark `gpt-6-astra` as supporting reasoning-effort updates and disable its experimental-context flag. Add explicit capability and instruction defaults to other entries.
- Update Astra's messaging guidance to recognize authorization from explicitly invoked skills or plugins, with attribution in the final response, and simplify its Default-mode clarification instructions.
- Revise auto-review guidance on autonomy, assumptions, and actions within the user's requested scope.
- Refresh seven scenario snapshots to reflect the updated prompts.
GitOrigin-RevId: b7ed8c413f6451008c982024506009b170e6311e
## Why
A single blob upload failure previously aborted the file upload, even for a temporary `503` response or an interrupted stream.
## What changed
- Retry `503` responses and timeout, connection, body, or request errors, with at most five attempts within a shared five-minute deadline.
- Honor `x-ms-retry-after-ms` and `Retry-After`, falling back to backoff when no valid server delay is available.
- Reopen the contents for each retry while reusing the same file record and upload URL. Preserve the initial read permission check and reopen MCP file streams under the same sandbox policy.
- Record retry, recovery, and terminal failure events with a fresh client request ID for each attempt.
## Testing
Add coverage for recovery after `503` responses and interrupted streams, attempt and deadline limits, non-retryable responses, retry delay parsing, and unique request IDs. Extend the restricted-read MCP upload test to verify that both attempts send the complete file contents.
GitOrigin-RevId: 78089ecfd5076313f5784cbbc864df12d082e3b1
## Why
Destination restrictions and policy revocation must remain effective during redirects, response body reads, and established WebSocket traffic. Policy denials must also survive error handling so callers do not retry them or report a revoked operation as successful.
## What changed
- Route managed HTTP clients through a shared `RequestBuilder` and policy-aware execution, checking each redirect destination before route resolution and retaining a network permit while consuming response bodies.
- Guard WebSocket connection setup, reads, and writes with revocable permits, including independent wakeups for split readers and writers.
- Preserve `TransportError::Policy` through HTTP, SSE, and realtime error handling, and treat policy denials as non-retryable.
- Keep the supplied network policy in plugin startup HTTP requests and propagate response body failures from backend and plugin requests.
## Testing
Add regression coverage for rejection before connecting, revocation during redirect routing and streamed body reads, split WebSocket revocation, realtime writer error propagation, and revoked plugin upload responses.
GitOrigin-RevId: fba36700444c98a8364c09b4dc5452c4d78a90fb
## Why
Selecting text can pause following while the final transcript row remains visible. Clearing that selection could leave an unnecessary `esc latest` hint in place of the composer hints.
## What changed
Only show the return-to-latest footer for paused navigation when the transcript tail is out of view. At the bottom, show selection shortcuts without the earlier-history status, then restore composer hints when the selection is cleared, even if following remains paused. Preserve loading and retry hints.
## Testing
Add regression coverage for selection, clicking away, and scrolling at the bottom with partial and complete history, plus selection above the bottom. Verify retry hints with selected text and update activity expectations and the composer-gap snapshot.
GitOrigin-RevId: aeb2109244d6c3214c945abb51cf469087d03074
## What changed
Display a `voice` badge on the task whose session owns the running voice conversation, including when a child thread owns it. Refresh the overview after voice controls and realtime conversation resets so the badge clears when background voice closes asynchronously.
## Testing
Add snapshot coverage for a child thread owning voice and a regression test for clearing the badge after an asynchronous background voice close.
GitOrigin-RevId: 815dfad4ce1a31945d2dd0d3f9cecc5abfa419d6
## Why
Switching threads stopped the active voice conversation. Users should be able to view another task while continuing the call on its original thread.
## What changed
- Retain the voice owner's live widget and subscription in the background, routing voice controls, speech, and connection callbacks to that owner.
- Restore the live call and transcript when returning to its thread, without duplicating captions or letting background UI events affect the visible task.
- Preserve undelivered speech and defer background errors until the owning thread is shown.
- Stop background voice on shutdown, disconnect, or removal of the owning session.
## Testing
Extend regression and end-to-end coverage for thread switching during delegated speech, voice control routing, transcript restoration, caption deduplication, and cleanup on disconnect or archive/delete.
GitOrigin-RevId: ce010dce6fa8cd6fa44949a131f3f16e8cb80c4d
## What changed
- Handle voice toggle and mute shortcuts in `App`, and route `/voice`, `/voice stop`, and `/voice mute` through thread-scoped events that ignore requests for a different current thread.
- Allow function-key voice toggle bindings and chords beyond chat, including transcript browsing and search, while preserving existing surface bindings and raw key capture.
- Exit transcript browsing when toggling voice, avoid matching completed chords again, and preserve startup submission handling before dispatch.
## Testing
Add regression coverage for voice chords outside chat, binding conflicts, key capture, transcript browsing, mute dispatch, and startup submission cancellation with draft preservation.
GitOrigin-RevId: c4d110ca8a2e1840247a7fe84cd69c6b7cdb36d7
## What changed
Add `backend_reasoning_status`, disabled by default, to relay public reasoning summaries during active, server-managed realtime V3 delegations.
Use the last non-empty summary from each completed reasoning item, truncate it to 256 bytes at a character boundary, and append it as `[STATUS]` context on the `commentary` channel. Discard queued updates if their delegation is no longer active.
## Testing
Add an integration test covering enabled and disabled behavior, selection of the latest non-empty summary, exclusion of raw reasoning and partial summaries, and delivery without triggering `response.create` or changing the model's reasoning-summary setting.
GitOrigin-RevId: 75ce87dbbbab15a6d9d0ad0b23737738837192fd
## What changed
Add the default-off `features.prefer_mxc` flag to select MXC for local Windows execution when native support is available and effective network settings do not explicitly forbid local binding. Otherwise, retain the configured backend and legacy setup behavior.
Resolve the preference during config loading and use the effective local backend for execution, network proxy setup, sandbox diagnostics, and `windowsSandbox/readiness`. Preserve the configured backend for remote executors and `config/read`. Explicit `windows.sandbox = "mxc"` remains strict, and command failures do not trigger backend fallback.
## Testing
Add coverage for preference resolution, startup readiness without rewriting configuration, local and remote backend selection across environment updates and child threads, and workspace-write permission context in an agent turn.
GitOrigin-RevId: b51178f0371d38ebb58e41af54a068fca67fa316
## Why
Restoring persisted V2 agent identities reads descendant metadata serially, making each storage read wait for the previous one.
## What changed
Read up to eight descendants concurrently while registering identities in graph order, preserving path and nickname reservation order. Skip identities already registered and continue restoring after individual read failures.
## Testing
Add a cold-resume regression test that gates child metadata reads to verify overlap, completes reads out of order to check deterministic path reservation, and injects a read failure. It also verifies that child runtimes remain unloaded until requested.
GitOrigin-RevId: ae90f24875966be83208884937621a6a9eb0d848
## Why
Resuming a compacted thread should use the compaction and its newer records without depending on older turn contexts or restoring stale state from before the compaction.
## What changed
- Stop paginated model-context scans at the newest compaction with `replacement_history` and `window_number`. Fall back to full replay if the newest compaction lacks either field.
- Align reconstruction with that boundary and restore `last_started_turn_id`, previous turn settings, and the multi-agent version from compaction resume metadata. Allow newer completed turns to override the saved settings.
- Keep canonical session metadata alongside the bounded replay and use the same scan boundary for subagent rollout migration.
## Testing
Add coverage for cold resume after mid-turn compaction, bounded/full replay equivalence, missing companion state, settings precedence, and incomplete-compaction fallback.
GitOrigin-RevId: f836464bb5cadd9be4a4e05b5d1679223713fc87
## What changed
- Enforce an 8 KiB encoded-message limit for requests, unrecognized notifications, and malformed messages received by exec-server clients over stdio, WebSocket, relay, and Noise relay transports.
- Allow process output, exit, close, and HTTP request body notifications up to 2 MiB. Keep responses and errors subject to existing transport limits, and preserve executor-side request limits.
- Read stdio stderr in chunks of at most 8 KiB.
- Drop outgoing server-request `tracestate` values larger than 512 bytes while preserving `traceparent`.
## Testing
Add regression coverage for oversized requests across transports, malformed messages, requests wrapped in `RawValue`, fragmented Noise messages, large responses, streamed notifications, and trace-context preservation.
GitOrigin-RevId: 3fb87b6dc334296985ef40983d7276acfe9b9796
## Why
Shared filesystem capabilities must not grant access to another logon session's processes, threads, or IPC objects. A shared account's implicit owner rights can also allow another logon to rewrite an object's DACL.
## What changed
- Grant full access in the token's default DACL only to the runner's logon SID, removing grants to Everyone and capability SIDs.
- Add an `OWNER RIGHTS` entry granting only `READ_CONTROL` to suppress the owner's implicit `WRITE_DAC` access.
- Close the new token handle if default DACL or privilege setup fails.
## Testing
Add a Windows `AccessCheck` regression test verifying that process memory, thread creation, termination, query, and DACL modification rights remain available to the creating logon but are denied to a simulated other logon sharing the same owner and capability.
GitOrigin-RevId: 94608466ee1b461fe10db1866e80b3988119bdfc
## Why
User prompt URLs only received explicit hyperlink destinations when they required forced wrapping, leaving other URLs without those annotations.
## What changed
Annotate web URLs before wrapping user messages so their full destinations survive both adaptive wrapping and forced splitting of oversized URLs.
## Testing
Add a regression test and snapshot at widths of 120, 60, and 24 columns, checking URL destinations, line width limits, and matching display and transcript output, including a prompt with an image placeholder and a parenthesized URL.
GitOrigin-RevId: fccae7b76a3613776d7a663c41e699ebad7eebc1
## What changed
Highlight recognized paths and URLs in check descriptions and details in red for failed checks and cyan otherwise. Extend path recognition on Windows to drive-absolute, UNC, Win32, and NT DOS paths.
## Testing
Add Windows and non-Windows color snapshots covering successful, warning, and failed checks, punctuation, and backtick-quoted paths with spaces. Assert that descriptions and details remain unchanged when color is disabled.
GitOrigin-RevId: e8f9982505aa155fd312b12f91a71271effeb35e
## What changed
Reserve a blank row below a trailing recap when the transcript viewport has room. Keep this spacing in layout rather than selectable content, and omit it when a completed or live message follows the recap.
## Testing
Add snapshots covering recap tail spacing across terminal sizes, with and without a next action, and with completed or streaming follow-up messages. Verify that reflowed history retains a single separator between a recap and the following message.
GitOrigin-RevId: f9552931fac4eabd7d72c2b312ffba717257e9e1
## Why
`invalid_prompt` responses were classified as generic invalid requests, losing the server's specific error classification.
## What changed
Add `InvalidPrompt` variants to the API and core error types and serialize the core protocol classification as `invalid_prompt`. Recognize the code in HTTP 400 responses, wrapped WebSocket errors, and SSE `response.failed` events while preserving server messages and keeping the error non-retryable. Map it to `other` in the app-server v2 protocol.
## Testing
Extend coverage for typed error mapping, missing and blank messages, protocol conversion, and guardian retry handling. Exercise HTTP and SSE failures in core integration tests, asserting the error message, serialized classification, and a single request without retry.
GitOrigin-RevId: 5d9a299a013b06158a4dc27a4054f3dbc5fd0f4d
## Why
Cloud skill discovery ran on every turn, even when the Apps resource generation and authentication scope were unchanged.
## What changed
- Reuse warning-free catalogs, including empty catalogs, while their authentication scope and Apps resource cache key remain current.
- Refresh after invalidation and retry failed or partial discovery on the next turn.
- Reject discovery results if the Apps resource cache key changes during discovery.
## Testing
Update lifecycle tests to verify cached turns avoid catalog listings and skill reads, while connection and authentication changes trigger refreshes. Update the referenced-resource test to verify partial discovery retries on the next turn without an explicit MCP refresh.
GitOrigin-RevId: ac47d5202d76703c4946afef3b1a48eaf05b54c2
## What changed
Emit `<recommended_plugins>` with the `developer` role and append it to the shared developer message after other context. Retain recognition of legacy user-role recommendations in existing rollouts.
## Testing
Add a startup context snapshot and assertions that recommendations share the developer message with permissions instructions. Update core and app-server tests to check developer-role recommendations, including across successive model requests.
GitOrigin-RevId: 0326ff347e86ec38b948f93e39e90e6a88a8730c
## Why
Forked subagent startup serializes history persistence and spawn-edge writes. Cancellation during startup can also leave a provisional child behind.
## What changed
- Defer copied-history durability so it can run alongside spawn-edge persistence, while still awaiting both before submitting the child's initial input.
- Commit agent and residency reservations and notify clients only after initial input is accepted.
- Guard provisional children so cancellation or startup failure removes and shuts them down, discards their stored state, and closes their spawn edge after any pending edge write finishes.
## Testing
Add coverage for cancellation at the child-history durability barrier, checking child termination, removal, and edge closure. Extend fork-context tests in legacy and paginated history modes to verify inherited context can be read from storage after spawn acknowledgment without flushing the live child first.
GitOrigin-RevId: e02dda57efc32b7237bb7af0ce5e5844922890c3
## What changed
Add `openai.gpt-6-sol` and `openai.gpt-6-luna` to the Bedrock catalog, including `global.` and `us.` variants for Bedrock Runtime. Make GPT-6 Sol the default and provider fallback model, preferring its global variant for Runtime. Retain the existing models and update model picker ordering.
## Testing
Extend catalog and provider tests to cover the new models, metadata, ordering, and default selection. Update thread-start tests for supported model preservation and fallback behavior, and refresh Mantle and Runtime model picker snapshots.
GitOrigin-RevId: 5ce646e384353ae26cdfc4ea4e7c049ac61e698c
## What changed
Skip the thread store title lookup when initializing an ephemeral fork, leaving its thread name unset.
## Testing
Add a regression test that forks an ephemeral thread from history and verifies that the in-memory thread store's `read_thread` count does not increase.
GitOrigin-RevId: 81180c4a836c932584d2cb94c0816eae33b04af3
## Why
Callers need to interrupt a specific active turn without discarding queued input. Tool callbacks must be able to await the interruption decision without blocking task cancellation.
## What changed
- Add `CodexThread::interrupt_if_no_pending_input` and `Op::InterruptIfNoPendingInput`.
- Check the turn identity and pending user input or mailbox items before taking the active task. Leave the turn running for stale or abandoned requests.
- Acknowledge the decision before joining cancellation, and unblock pending submissions when the active task is cancelled.
## Testing
Add regression coverage for successful interruption, stale turns, preservation of queued user input and agent mail, abandoned requests, and cancellation while the submission queue is full.
GitOrigin-RevId: 42e31c09369fb070ba1b4b3c64ef45334dd872d8
## What changed
- Add “Inspect activity” to the shortcut help’s Session section, using the runtime `focus_activity` binding (`F4` by default) and hiding it when unbound.
- Remove the passive activity footer hint so composer hints remain available. Keep previous, next, details, and back controls while activity is focused, shortening them to fit the available width.
## Testing
Add snapshot coverage for default, remapped, and disabled activity shortcuts. Update footer coverage to verify the absence of passive hints and interactive controls at 20, 32, and 80 columns.
GitOrigin-RevId: 52ca6f4992778cd3cf3eebe163d533e69a8dabeb
## What changed
- Add `gpt-6-sol` and `gpt-6-luna` catalog entries and refresh model descriptions.
- Offer migrations from `gpt-5.5`, `gpt-5.6-sol`, and `gpt-5.6-terra` to `gpt-6-sol`, and from `gpt-5.6-luna` to `gpt-6-luna`.
- Retarget retired `gpt-5.4` and `gpt-5.4-mini` selections to GPT-6 Sol and Luna, respectively.
- Recommend `gpt-6-luna` in the rate-limit switch prompt.
## Testing
Extend migration tests to cover the new targets, their default reasoning effort, and prompting again after a previously acknowledged migration to an older target. Update model-picker and rate-limit prompt snapshots.
GitOrigin-RevId: d3a093d18ce44a903383504ab8f5cbbc911d602d
## Why
An empty composer hint row already separates activity from the input. Adding another separator wastes transcript space, especially in short terminals.
## What changed
Reserve the extra separator only when copy status text, a follow control, or a fitting hint occupies the shared row and the viewport has room. Recalculate the transcript layout in the same frame when adding that separator, and use a shared timestamp for copy status visibility and expiry.
## Testing
Extend snapshots for running turns with no hint, follow controls in short terminals, and copy status text at narrow widths and limited heights. Update resize assertions to check that the draft and caret remain stable relative to the terminal bottom.
GitOrigin-RevId: a73894063b759ec6b9a25f720e0e8007516109c8
## Why
The generic state integrity failure message does not identify which database needs attention.
## What changed
- Include the paths of all databases that fail integrity checks in a structured issue, shown in text summaries and JSON output, with the existing recovery guidance.
- Redact sensitive details using `: ` as the field-label separator so Windows drive letters are not mistaken for labels and unlabeled sensitive paths are fully redacted.
## Testing
Add coverage for single and multiple failed databases, summary and detailed text output, JSON output, preservation of damaged database contents, and sensitive path redaction on Unix and Windows.
GitOrigin-RevId: ac5fec9473d22b6b137a9fc8a751aba8605d940f
## What changed
Remove trailing periods from concise built-in option descriptions and disabled-option explanations, and simplify wording across TUI menus. Share the built-in permission preset descriptions between permission pickers.
Document the convention in `codex-rs/tui/styles.md`, including normal punctuation for descriptions with multiple sentences and preservation of externally supplied descriptions.
## Testing
Update menu assertions and rendering snapshots for the revised copy and line wrapping.
GitOrigin-RevId: 3231d25484178452ab001af5ddc982460d14f94a
## Why
Failed image requests discarded the `x-codex-imagegen-request-id` header, leaving failure analytics without the request ID.
## What changed
Carry the request ID through `ImageRequestError` and backend errors for image generation and editing. Preserve it on failed image generation items for HTTP errors, response decoding errors, and responses with no image data.
## Testing
Extend the app-server failure test to verify that a request ID returned with an HTTP 500 response reaches `codex_image_generation_event` analytics.
GitOrigin-RevId: 57cddacc0221e5b58877ac375d5eca0afb99d853
## What changed
Reject authorization endpoints with schemes other than `http` or `https` before client registration or authorization URL return. Document this constraint for `mcpServer/oauth/login`.
## Testing
Make existing asynchronous tests wait for cleanup: wait for `ThreadIdle` before injecting user input in the guardian cached-score test, and poll for queue consumption before asserting that dispatched items are gone.
GitOrigin-RevId: e5f6b4c5556234c3cc2aa56910486e892c011116
## Why
Sentry tags cannot contain newlines or exceed 200 characters, but report comments can contain both.
## What changed
Limit the `reason` tag to the first 200 Unicode characters and replace each carriage return or newline with a space. Preserve the full, unchanged comment in the exception body.
## Testing
Add coverage for line endings, the 200-character boundary, and multibyte Unicode comments. A mock upload test checks that the compressed Sentry envelope contains the bounded tag preview and full comment, even when caller tags attempt to override `reason`.
GitOrigin-RevId: e0f0db6a9797a817da2f868727077c948ad82bfb
## Why
Compaction companion records do not represent all resume state, including the last started turn and previous turn settings. The selected multi-agent runtime also needs a persisted value when no companion turn context is present.
## What changed
- Add optional `resume_metadata` to `CompactedItem`, recording the multi-agent version, last started turn ID, and previous turn settings. Preserve the distinction between absent metadata and explicitly empty values while retaining compatibility with older records.
- Capture this metadata under the settings persistence lock alongside the compaction checkpoint.
- Rewrite inherited metadata to use the child agent's runtime, and clear previous turn settings when the child must rebuild context.
- Clear pending continuation state before delivering acceptance of standalone settings updates, while holding the persistence lock.
## Testing
Add coverage for metadata round trips with empty values, legacy reader compatibility, checkpoint companion records, inherited fork metadata, and continuation invalidation while settings event delivery is blocked.
GitOrigin-RevId: f30b7feaa7e2fdb5b65fc3c53b37fd7a7fe27903
## What changed
Render unordered bullets as `•` and task markers as `☐` or `☑`, preserving ordered numbering and continuation indentation in streaming and completed Markdown. Add `tui.rendering.lists`, enabled by default; setting it to `false` retains hyphen bullets and textual task markers.
## Testing
Add snapshot coverage for nested, ordered, quoted, and wrapped task lists, plus code and escaped markers. Add character-by-character streaming tests that compare incremental and emitted output with full rendering, with list rendering enabled and disabled.
GitOrigin-RevId: df9209d8c42f277dd2a2d7073ea19a6feb7dd706
## Why
Several TUI views hard-code 24-hour timestamps even when the detected system preference is 12-hour time.
## What changed
Use the existing `ClockFormat` preference for rate-limit and spend-control reset times, usage notices, backend banners, reset-credit expiration times, analytics timestamps, and expanded session details in the resume picker. Capture the preference when constructing views and preserve existing timezone handling, including analytics' UTC labels.
## Testing
Add coverage for midnight, noon, and next-day reset labels in both clock formats, plus 12-hour analytics rendering with UTC labels. Update snapshots for status, banners, usage notices, reset-credit details, and expanded sessions, including narrow-width layouts. Pin test fixtures to explicit clock formats for deterministic output.
GitOrigin-RevId: 73c36d603ddc4eb7800614650a14c6f2961f8b70
## Why
In read-only sessions with an external writer, `Esc` could enter prompt backtracking or be consumed by a scrolled transcript instead of returning to the agent command center.
## What changed
- Exclude external-writer views from prompt backtracking and let `Esc` navigate away from scrolled transcripts. Active search and selection still consume `Esc` first.
- Close the legacy transcript overlay without starting a backtrack preview or changing the retained draft.
- Allow `Esc` to open the agent command center while disconnected, showing a stale-list notice with reconnect status instead of requesting a refresh.
## Testing
Add regression coverage for normal, scrolled, detailed, and offline read-only views, command-center snapshots, and retained-draft preservation when closing the legacy transcript overlay.
GitOrigin-RevId: e2623d25dd4b4beea13b6f517932280168113dce
## Why
Status symbols in the agents overview retained their status color when selected, making their styling inconsistent with the rest of the selected row.
## What changed
Apply the row's selection style to its status symbol while preserving status colors for unselected rows.
## Testing
Extend rendering tests to assert and snapshot selected status symbol styles across status variants, and verify that an unselected idle symbol retains its cyan color.
GitOrigin-RevId: a5163841bed80d6d43e7c62a7596c6e48b9dc886
## Why
Automatic daemon launches could silently fall back to embedded mode when shared feature settings differed from the session's requirements. Changing those settings affects other clients, and restarting the server may interrupt active or queued work.
## What changed
- Offer interactive choices to run without the daemon, restart with the required settings, or cancel. Default to cancel and require explicit confirmation for restart.
- Allow restart only for managed daemons with a feature mismatch, then recheck compatibility once. Noninteractive required-daemon failures return an error with `--no-daemon` guidance; optional attachment retains its fallback behavior.
- Preserve saved feature overrides on startup and require confirmation before applying requested shared-feature disables, including on fresh starts.
- Merge confirmed settings under the lifecycle lock, persist changes after the old process stops, and avoid restarting when the saved overrides already match.
## Testing
Add recovery-menu snapshots and confirmation tests, compatibility tests for required and optional attachment, daemon ownership and settings-preservation tests, and CLI terminal tests for cancellation, embedded fallback, confirmed restart, and disabling shared features.
GitOrigin-RevId: d50a6cf7e476b9647237431e8fc0fc6041ed17db
## Why
`/import` was unavailable in remote sessions and when connected to the local app-server daemon. Shared servers also broadcast import completions from other clients, which must not clear this client's pending import or report its completion.
## What changed
- Allow external setup migration through the connected app server in both session types.
- Detect setup using the active thread's working directory, or the remote working-directory override before a thread starts. Use home-only detection when no remote directory is available.
- Track the returned `import_id` and only clear the pending import and report completion for a matching notification.
- Skip refreshing configuration from local disk after import completion in remote workspaces.
## Testing
Add shared-transport coverage in embedded and remote modes for detection with and without a working directory, retrying failed imports, rejecting overlapping imports, and matching interleaved completion notifications queued before the import response.
GitOrigin-RevId: 864ed9fe87e5c554da79907ed80a01f0c9948392
## Why
Guardian prompts are synthetic review context, but legacy thread metadata can duplicate them in titles, previews, and first messages. Keep SQLite metadata small while retaining rollout JSONL as the canonical record.
## What changed
Add a migration for Guardian threads that:
- Replaces blank or prompt-derived titles with `Guardian review`.
- Preserves nonblank names and distinct nonblank titles, using the title as the name when no name exists.
- Sets `preview` to `Approval review` and clears `first_user_message`.
## Testing
Add a migration test covering prompt-derived and blank titles, custom titles and names, and unchanged metadata for a non-Guardian worker thread.
GitOrigin-RevId: 65b5ff5200a39a19fb11f494de6dca7710ff6cc6
## Why
Guardian review threads use synthetic approval prompts as user messages. Deriving thread titles and previews from those prompts exposes large, unhelpful summaries in thread listings.
## What changed
- Default Guardian threads to the title "Guardian review" and preview "Approval review" across metadata creation, rollout reads, and resume.
- Skip synthetic user messages and goal updates when deriving Guardian display metadata, leaving `first_user_message` unset for new threads.
- Preserve custom names, including legacy indexed names, when listing, reading, resuming, and migrating threads to paginated history.
## Testing
Add regression coverage for compact metadata, resume without session metadata, custom names before and after migration, and app-server persistence, listing, and rename/resume behavior.
GitOrigin-RevId: 42aa707db20c3e57ffa5fd4c91ee313710be10d7
## What changed
Extract `LocalAgentRuntime` from `LocalAgentControl` to hold the shared registry, residency state, execution limiter, rollout budget, service tier, instruction provider, and thread-manager bindings. Keep session identity on the controller handle.
Store the runtime in `SessionServices` and use it to bind controllers for child startup, resume, delegation, and guardian reviews. Route ownership checks and residency handling through the shared runtime, preserving registry identity across handles. Update existing test fixtures to keep the controller and runtime paired.
GitOrigin-RevId: 846094657cbdf736da3149f0a1c96b4e01423dfe
## What changed
Move `spawn`, `send`, and `inspect` into the `AgentControl` implementation for `LocalAgentControl`, removing the forwarding methods and the `spawn_request` module. Update tool handlers and existing tests to use the trait methods, and remove redundant boxing at spawn call sites.
Preserve spawn validation, message attribution, runtime loading, and queue-only delivery semantics.
GitOrigin-RevId: 6027d4d97d0dfb6763dc97ef92a2d7ef58de945d
## What changed
Update `extra_policy_reaches_guardian_review` to expect a retained user
instructions section before the transcript, including the source-order notice
and the original user request. Adjust the subsequent snapshot item numbers.
GitOrigin-RevId: 9e57f9bb7cdc9318787d083bf4350143a1353287
Verify that unsubscribing from a message board thread remains effective
after posting to that thread and resuming the session. The runtime test
checks that replies from a child agent produce no `CHANNEL_POST` notices
while unsubscribed and that explicit resubscription restores delivery.
Use gated streaming responses to keep the recipient active during each
reply and drain worker completion messages before checking notices.
GitOrigin-RevId: fe2695a46722a94e6fca86a3d3bd49c0b8bb7ee7
## What changed
Mark `guardianv2.thread_context` as stable and enable it by default for synchronous and asynchronous Guardian reviews. Keep it independent of the Guardian v2 `enabled` toggle and preserve explicit configuration and profile overrides. Update the configuration schema documentation to match.
## Testing
Update coverage for default configuration and sender user messages, review prompt snapshots, history retention across compaction, and checkpoint provenance. Assert that later user input invalidates an in-flight review's authorization. Keep legacy transcript budgeting coverage by explicitly disabling thread context in that test.
GitOrigin-RevId: 19afd34d7bfc0ee36bbf878089c68b732a21bc6a
## Why
Thread-owned Guardian review rejected usable parent compaction checkpoints when the reviewer's `comp_hash` differed or was unknown, even though the synchronous reviewer can consume those checkpoints.
## What changed
Remove the synchronous reviewer's compaction hash compatibility check and the associated hash plumbing. Pass usable checkpoints to the backend for payload validation, while continuing to fail closed on unusable checkpoints and review errors.
## Testing
Update compaction and resume tests to expect retained evidence with different, missing, or empty reviewer hashes, while preserving rejection of empty checkpoint content.
GitOrigin-RevId: bbc4f5a2e697f832f815dcf8bda4d4a652f06b8a
## What changed
Add an adapter that delegates the shared controller interface to existing local agent operations, including lifecycle management, message delivery, status observation, budget accounting, and shared settings.
Align the trait signatures and documentation with local behavior: separate advisory capacity checks from execution tracking, preserve best-effort completion reporting, and return optional guardian evidence. Use `SessionId` for controller identity and replace paginated queries with loaded-agent listing by path prefix, removing the obsolete types and exports.
GitOrigin-RevId: 15bb7135e0f180d207390f6f2e75f63b9058816a
## What changed
- Return `StatusSubscription` streams of `AgentInfo` snapshots from local status subscriptions, including agent metadata and configuration.
- Emit the initial snapshot before subsequent coalesced updates. Use a weak thread reference and retain the last observed configuration so published final updates remain available after the runtime is dropped.
- Update completion notifications and `wait_agent` to consume snapshot streams, propagate subscription errors from `wait_agent`, and fall back to the latest status when a stream ends.
## Testing
Update the shutdown subscription test to verify that shutdown before the first poll preserves the initial `PendingInit` snapshot followed by `Shutdown`.
GitOrigin-RevId: beb46952cbcc9bddf65a4d6603fea939d5ace8b9
## What changed
- Request installed-plugin metadata with `includeExtensions=true` and carry optional `extensions` through the cache into `PluginSummary`.
- Add typed declarations for global, settings, thread, and file entrypoints, quick actions, settings tools, icons, and search mention providers. Update JSON schemas and TypeScript and Python bindings.
- Accept supported snake_case aliases and emit camelCase fields. Discard incompatible extension declarations without invalidating the installed-plugin inventory.
## Testing
Add an integration test covering extension metadata preservation, field normalization, and unknown entrypoint and quick-action types across live and cached `plugin/installed` reads. Update pagination assertions to require `includeExtensions=true`.
GitOrigin-RevId: b73b0d13c151a30dc1fb9cda70b5cd6d7e3e2441
## Why
Posting to a new channel subscribed its author to replies on that post, but not to new discussion roots in the channel. The creator could therefore miss notifications for subsequent discussions.
## What changed
Subscribe the author to the channel in the same transaction that creates the channel and its first post. Document this behavior in the API and the `new_channel_name` tool parameter.
## Testing
Update coverage to verify that channel creators receive notifications without explicit targeting and that posting to an existing channel preserves an explicit unsubscribe. Adjust thread-deletion test expectations for the additional persisted subscription.
GitOrigin-RevId: 5553ebc9f9b51456ab48886e9871733e93370a2b
## What changed
Add a V1 spawn regression test that removes the child from the thread manager during startup, before spawn reports its settings. Verify that the completed spawn event retains the role-configured model and reasoning effort, nickname, and role even when the child can no longer be looked up.
Also verify that the child receives its initial input with the effective settings and the parent receives a successful spawn result.
GitOrigin-RevId: 5e94e3ddb0feda0eaaa86e7539ef8c6720176f88
## Why
Posting to a discussion automatically subscribed its author, undoing an explicit unsubscribe and restoring unwanted reply notifications.
## What changed
Persist explicit opt-outs so posting follows a discussion by default but leaves unsubscribed agents opted out until explicitly subscribed again. Keep active subscriptions in the existing table for compatibility with older readers, and remove opt-outs when deleting a board. Update the API and tool descriptions to explain the behavior.
## Testing
Extend the local board test to cover reopening an older database, preserving opt-outs across reopen and subsequent posts, legacy subscription queries, explicit notifications without resubscribing, explicit resubscription, and board cleanup.
GitOrigin-RevId: 8b8f7f50cea5041541b8d93067c52db18cdde85c
## What changed
Return an `AgentInfo` snapshot captured before shutdown, including metadata for known unloaded agents. Use the snapshot's status and metadata in the tool's completion event and its status in `previous_status`, replacing the separate status subscription.
Preserve the pre-close status for error reporting when shutdown removes the target before a descendant fails to close. Propagate unexpected thread lookup errors before attempting shutdown.
GitOrigin-RevId: bdbd877aaf0389e830d6a7e84a5e14bb7d47277a
## Why
Remote compaction v2 excluded descendant progress messages from retained history but kept `CHANNEL_POST` messages from those same agents.
## What changed
Treat descendant `CHANNEL_POST` messages like `MESSAGE` progress updates when selecting history to retain after remote compaction v2.
## Testing
Extend the remote compaction test to verify that a child channel post is included in the compaction input and omitted from the follow-up request.
GitOrigin-RevId: 204bf44b8cddf1e6dc1e48234f51d4ac2aaf2e9f
## What changed
Allow `mcpServer/resource/read` to specify `target: {connectorId, linkId}` for direct hosted app reads without tool discovery, when supported by the backend. Require an explicit `linkId`: a string selects an account, while `null` requests no-auth access subject to backend policy.
Restrict direct targets to `codex_apps` and reject empty connector IDs, empty link IDs, and synthetic link IDs. Preserve originating app/account scope when `originCallId` and `threadId` are supplied, and retain discovery when `target` is omitted.
Update protocol schemas and TypeScript and Python models, preserving required-but-nullable `linkId` semantics in Python code generation.
## Testing
Extend resource-read tests to check target metadata with and without a thread, including explicit no-auth targets and omitted targets. Add Python model tests for string and null `linkId` values and rejection of a missing `linkId`.
GitOrigin-RevId: 8cf5595fbdd937193aeb529901fc95299f6e18ad
## What changed
Add `LocalAgentControl::resume_agent` to reuse an existing thread or restore it from its rollout when lookup returns `ThreadNotFound`. Return the agent's current status, metadata, and configuration snapshot.
Route the `resume_agent` tool through this method, replacing its status-based resume check and separate restoration helper.
GitOrigin-RevId: 2ae0572a030f169eca1760ba0aff1fb9e2ab6651
## Why
Accepted inter-agent messages can still be waiting in the submission queue when a worker appears idle. Evicting that worker can lose the queued work, while cancelling an eviction caller can leave shutdown unfinished and allow delivery to a closing runtime.
## What changed
- Pin V2 recipients until queued submissions are handled or dropped, and verify that delivery targets the registered runtime.
- Move `Submission` into core so it can carry the residency guard through queue handoffs.
- Give eviction exclusive access to each runtime and keep it counted against capacity until removal. Run teardown in a separate task so it completes even if its caller is cancelled, and remove registry and residency entries together.
## Testing
Add a regression test covering queued follow-up delivery, eviction refusal while mail is pending, cancelled eviction completing teardown, rejection of late delivery, and capacity reuse after removal.
GitOrigin-RevId: d6de3d68cb6b911942e9ddfc05c65b3741b796b2
## Why
Channel and thread subscriptions, or explicit `agents_to_notify`, could cause agents to receive notifications for their own posts.
## What changed
Exclude the author from notification recipients, even when explicitly targeted. Preserve the author's subscriptions so replies from other agents still reach them, and document this requirement in the board API.
## Testing
Update board tests to cover explicit self-targeting, subscribed authors, and delivery of other agents' replies. Update the model-context scenario and snapshot to verify posts remain searchable without a `CHANNEL_POST` self-notification.
GitOrigin-RevId: 0b2558e7df79122a6da06ad592f9735ba260cce1
## What changed
- Route both multi-agent spawn handlers through `LocalAgentControl::spawn`, accepting user input or an agent message.
- Centralize spawn message attribution and canonical path validation, and require message input to use `TriggerTurn`.
- Return the child's configuration snapshot alongside `LiveAgent`, so handlers obtain effective settings directly from spawning without a separate lookup.
- Update child test fixtures to use the shared spawn entry point.
GitOrigin-RevId: 9f9278df08041a62215f9ec3d38688c78fc5e0e2
## Why
MCP requests pass through background transport queues, so HTTP requests need the caller's trace context carried explicitly to preserve trace ancestry.
## What changed
- Capture W3C trace context in request metadata for tool and resource operations, custom requests, and event streams.
- Restore that context in an `mcp.http.request` span around HTTP POSTs, linking outgoing HTTP traces to the originating request.
- Preserve application metadata while replacing trace fields with the current caller's context and removing stale `tracestate`. Read the SDK's merged metadata so extension fields retain precedence over parameter metadata.
## Testing
Add a unit test for metadata merge precedence and an integration test covering concurrent paginated requests, tool calls, custom requests, and tool-call continuations across legacy and `2026-07-28` protocol modes. Verify HTTP trace ancestry, metadata preservation, and removal of stale `tracestate`.
GitOrigin-RevId: 0b22cd75f31f9fcb855b27fa8d34ecdffd6e3549
## Why
Clients with a gateway sign-in UI need to control when browser authorization starts and inspect credential readiness before making authenticated requests.
## What changed
- Add `initialize.capabilities.explicitGatewayOauth` to require explicit login while allowing existing credentials to refresh. Preserve automatic authorization for clients that omit the capability, and prevent later connections from undoing explicit opt-in.
- Add `account/gatewayOAuth/read`, `account/gatewayOAuth/login`, and `account/gatewayOAuth/cancel`, plus `account/gatewayOAuth/changed` notifications. Send the authorization URL only to the initiating connection and cancel its login on disconnect.
- Check gateway authentication before returning cached results from `model/list`, with restart guidance when provider settings have changed.
- Update protocol schemas, TypeScript and Python bindings, and document capability probing and the sign-in lifecycle.
## Testing
Add tests for passive readiness reads, credential reuse after login, token exchange failures, cancellation and immediate retry, connection ownership, legacy versus explicit login, and model-list authentication checks.
GitOrigin-RevId: a26e116a62c9f3db84dc238a40b7f4e816eb1594
## Why
Standalone web search selected a proxy route only for the initial endpoint. Redirect destinations can require a different system proxy route.
## What changed
- Add `RouteAwareClientPool` support to `ReqwestTransport` for both buffered and streaming requests, and use it for standalone web search.
- Preserve default Codex headers and Cloudflare cookie handling across routes, while retaining the default client behavior when route-aware handling is disabled or Codex is sandboxed.
- Share request construction so URL authentication and header precedence follow `reqwest` semantics, applying them once before redirects and TLS retries.
- Map route-aware failures to transport errors and remove request URLs from those errors.
## Testing
Add regression coverage for redirects through distinct proxies, preservation of POST bodies and default headers, URL authentication and header precedence, and transport error classification without URL leakage.
GitOrigin-RevId: 19a10a62118846db09dd95265dc277e54aac09ef
## Why
Injecting context before the first turn currently forces a full flush. Stores need a preparation checkpoint that can leave disposable context in memory, while local storage must keep prepared context durable before the first user input.
## What changed
- Add `PersistContext::ThreadPreparation` and `CodexThread::checkpoint_preparation()`, and use the checkpoint in `inject_response_items()`.
- Allow stores to defer rollout-derived metadata writes through `record_thread_metadata()`, including during preparation and execution checkpoints. Keep standard metadata updates synchronous.
- Flush local storage at preparation checkpoints so injected context survives restart.
## Testing
Add tests showing that preparation and first sampling can proceed without waiting for durable metadata. Cover prepared context in first and follow-up requests, plus durability before first input and restoration after restart, in both legacy and paginated history modes.
GitOrigin-RevId: 74f6bb1a5f8d47192364b8bba6afd703a3b7d688
## Why
Aligned equations and common optimization notation previously fell back to TeX source. Scripts without Unicode equivalents also prevented otherwise supported expressions from rendering.
## What changed
- Add display layouts for `aligned` and `\boxed`, preserving fraction geometry and alignment with surrounding math.
- Stack sum limits and `\underset`/`\overset` annotations in display math, with compact forms for inline math and nested arguments.
- Support `\substack`, uppercase `\mathcal`, and single-grapheme `\widehat`.
- Preserve scripts without Unicode equivalents using explicit grouping, such as `x_{gpt}` and `x^{q+1}`.
- Keep layouts bounded and retain source fallback for unsupported input or expressions that do not fit.
## Testing
Add snapshots and regression tests for optimization models, display limits, grouped scripts, fraction alignment, narrow-width fallback, malformed input, and layout bounds. Add streaming coverage comparing character-by-character output with complete rendering at wide and narrow widths in rich and raw modes.
GitOrigin-RevId: 83937880a309375f472228368ebe885d4f50bf9c
## Why
Conversations open in another app disable the composer. Let users continue in an editable fork while the original conversation remains owned by that app.
## What changed
- Add an `f`/`F` shortcut and footer hint to the locked conversation view, preserving local drafts and queued prompts in the fork.
- Show “Forking conversation…” while a fork is pending, block additional key input, and discard buffered input after forking from the locked view.
- Replace the previous session summary after a fork with “Fork created. You can continue here.”
- Keep the locked view and draft intact if the fork request fails.
## Testing
Add tests for shortcut ownership and modifiers, repeated input, editable forks that preserve drafts and queued prompts without taking the source lease, and failure recovery. Add snapshots for fork progress, completion, and the updated footer.
GitOrigin-RevId: 2ecdb0b7fc7e82d8295097faa567995d7a2f7d92
## What changed
Promote `daemon_auto_start` to stable and enable it by default for eligible interactive launches. Remove its entry from `/experimental`.
## Testing
Update daemon startup, `--no-daemon`, and startup failure tests to exercise the default without explicitly enabling the feature. Disable daemon startup in unrelated TUI and path-safety test fixtures.
GitOrigin-RevId: 107d71108b96d09431148d7d61f10c6381929e05
## What changed
Default `tui.fullscreen_transcript` to `true`, including when the `[tui]`
section is absent, and apply the same default to the first frame. Update the
configuration schema to match. Alternate-screen restrictions still take
precedence, and `tui.fullscreen_transcript=false` restores terminal scrollback.
## Testing
Update configuration and startup tests for the new default, including an empty
`[tui]` section and `--no-alt-screen`. Adjust PTY tests to cover default fullscreen
entry and explicit opt-out to terminal scrollback.
GitOrigin-RevId: e460dcd058d52c50da2abc5113bbb678e845d5fc
## Why
Reaching the pending tool-call limit could evict finished empty cells even though removing them frees no pending-call capacity. This loses the metadata needed to certify an empty tool-call inventory on a later `wait`.
## What changed
Only evict cells with pending calls when reclaiming pending-call capacity. Keep empty cells eligible for eviction when a cell slot is needed.
## Testing
Extend recorder coverage to check empty inventories under pending-call pressure in fresh and resumed sessions. Add a code-mode integration test verifying that `wait` serializes an empty inventory with `tool_calls_complete: true` while another cell has filled the pending-call budget.
GitOrigin-RevId: 559d0b4fdc9864c42a90b7d087eb2a3327272d5c
## What changed
- Add `GatewayLoginControl` so hosts can require caller-initiated browser authorization while retaining automatic login by default.
- Expose passive readiness checks, scoped status subscriptions, and cancellable browser login that reports success after credentials are persisted.
- Return non-retryable request errors for `LoginRequired` and `LoginInProgress`, while preserving retries for transient authentication failures.
- Keep rejected credentials unready until replaced, and prevent slow readiness reads from blocking cached requests or overwriting newer credentials.
## Testing
Add coverage for login cancellation, status notifications, external credential recovery, concurrent credential I/O, legacy automatic login, and request retry behavior.
GitOrigin-RevId: e236d203998ceb6eeaca9704cc05d20ad45f2931
## Why
Classifier requests need to preserve their owning thread's workspace routing and account binding, including when reusing pooled connections or retrying after authentication changes.
## What changed
- Share the thread's `WorkspaceRoutingContext` with Guardian v2 and resolve routing before leasing HTTP or pooled WebSocket connections.
- Reuse WebSockets only when their connection key and authentication state still match. Cache HTTP transports by URL and redirect policy, rejecting redirects when routing requires it.
- Stop classification requests and retries when the account owner changes while allowing token refreshes for the same user and workspace.
## Testing
Add regression coverage for routing failures with prewarmed sockets, shared thread routing state, account switches during HTTP and WebSocket requests, same-account token refreshes, and HTTP redirect-policy cache changes.
GitOrigin-RevId: 7b3efcadb4797b6a2de2e28e7506b297b0728d69
## What changed
Add nullable `httpOrigin` to `McpServerStatus`, derived from the effective configured endpoint for both configured and plugin-provided servers. Return only the HTTP(S) origin, excluding credentials, path, query, and fragment; return `null` for stdio transports, invalid URLs, and non-HTTP(S) schemes. Update the generated protocol schemas and TypeScript and Python types.
## Testing
Extend status integration tests to cover configured and plugin-provided HTTP servers, verify that endpoint paths and query parameters are omitted, and assert `null` for a stdio server. Update protocol tests to check null serialization and compatibility with older inventory responses.
GitOrigin-RevId: 033ebdeefe829e3a48b2d4ab7d8866dac4cda5c5
## Why
Credential I/O can block async workers, and canceled browser logins must not release the credential store lock while a write is still running. Provider errors can also echo secrets from authorization URL query parameters.
## What changed
- Move credential reads and writes to `spawn_blocking`, retaining the cross-process lock until encryption and the atomic write finish, even if the caller is canceled.
- Clear pending rotated credentials during browser login only when stored credentials have changed, preserving recovery after a failed login without overwriting an external login.
- Omit provider response details and request IDs when the authorization URL contains query parameters, matching the existing protection for token and resource URLs.
## Testing
Extend regression coverage for authorization URL query-secret redaction and failed browser login after a failed credential save, including retry, expiration, and external-login recovery.
GitOrigin-RevId: 4a63702a260fd7f3e2ad2314b0124c0d647d4f12
## Why
A queued close notification from an old runtime can arrive after the same thread has been resumed. Because thread IDs survive reloads, handling that notification can incorrectly exit the TUI or switch away from the displayed thread.
## What changed
Confirm the displayed thread's status with `thread/read` before handling its close notification. Ignore the notification if the thread is still loaded. Bound verification to five seconds and retry an internal server error once.
If verification fails, reconnect remote sessions. Preserve close handling for embedded sessions, unreadable unpersisted threads, and servers that do not support the request.
## Testing
Add regression tests for stale and genuine close notifications, plus disconnects, timeouts, transient and persistent server errors, embedded-session fallback, and unsupported requests.
GitOrigin-RevId: 783433b11ed268aed521f3b2cc4d0aa3a36a3836
Refresh the collaboration namespace hash and aggregate tools hash in the
`code_mode_catalog_messages` snapshot.
GitOrigin-RevId: bcfb793ba379760219cb4214d39f9c8bcd01e40c
## What changed
Move `codex exec-server` argument definitions, transport validation, configuration loading, authentication, and shutdown orchestration from `codex-rs/cli/src/main.rs` into `codex-rs/cli/src/exec_server_command.rs`.
Expose startup through `ExecServerCommand::run`, merge the root `--strict-config` flag into the command before dispatch, and update existing argument tests to use the new entry point.
GitOrigin-RevId: 4bcc59db2bd6e1d153a366142bd0b93ad03c6951
## Why
Standalone web search used a default HTTP client, bypassing the configured system proxy route when `respect_system_proxy` was enabled.
## What changed
Pass the configured `HttpClientFactory` to the web search tool and create its client asynchronously for the provider's search URL using the API route policy. Export and reuse `SEARCH_ENDPOINT` so route selection and search requests use the same endpoint.
## Testing
Add an isolated regression test with environment proxies removed and a mock system proxy. Verify that standalone web search reaches the proxy and returns its result in the follow-up model request.
GitOrigin-RevId: 3b64803a777b9d1eb0ccf694e06658b0fd562129
## Why
Dragging horizontally along the top or bottom transcript row could trigger autoscroll, moving the text under the pointer while selecting it.
## What changed
Require vertical pointer movement from the initial press row before selection autoscroll can begin. Remember that movement so a vertical drag can return to its starting edge and still autoscroll, and preserve the original pointer row across wheel scrolling.
## Testing
Extend regression tests and snapshots for horizontal selection at both edges, stable selected text across repeated ticks, wheel scrolling before the first drag, and autoscroll after a vertical drag returns to its starting edge.
GitOrigin-RevId: e13f3a80adbead1eecbeb281301667c8e12e1541
## What changed
- Add optional `network.mitm_ca` configuration with `certificate_file` and
`private_key_file` for trusted proxy configuration. Require MITM to be enabled
and retain the generated CA when no external CA is configured.
- Validate absolute paths, regular files, file sizes, certificate/key matching,
and Unix private-key permissions. Reject symlinks on Unix, private keys embedded
in certificate files, and external private keys on non-Unix platforms.
- Store derived external-CA trust bundles in the proxy artifact directory,
include only certificates, and skip inherited generated bundles to avoid
retaining stale roots.
- Preserve MITM for external CAs when disabling credential brokerage. Reject
external CA configuration for remote execution, even when the proxy is disabled,
and reject unknown fields in `NetworkProxyConfig`.
- Default the upstream request version adapter to HTTP/1.1 and remove the request
URI from upstream request failure context.
## Testing
Add regression coverage for external CA configuration, mismatched keys, embedded
private keys, non-Unix rejection, trust-bundle placement and contents, stale-root
exclusion, credential-broker toggling, and remote configuration rejection.
GitOrigin-RevId: cb209295c19fbe53a9fa0194f11ff06acccabef6
## What changed
Remove `ultrafast` from the bundled `gpt-5.6-sol` model's `service_tiers`, leaving `priority` (Fast) as its only advertised service tier. Update scenario snapshots for the affected multi-agent tool definitions.
GitOrigin-RevId: 9a235d8f7ea8a72e71152708d2d602194256d420
## Why
Extension calls omitted environments whose working directories could not be converted to host-native paths, preventing extensions from receiving those environments.
## What changed
Store `ToolEnvironment.cwd` as `PathUri` and pass all turn environments to extension tools without requiring host-native path conversion. Keep image generation's existing path requirements by selecting the first environment with a convertible working directory when reading referenced images or saving generated images.
GitOrigin-RevId: b4320c6e07d27ef59885cd0013e5d1c535f69659
## What changed
- Add `auto_review.extra_policy` and the managed `guardian_extra_policy` requirement to supply policy text alongside the resolved tenant policy. Nonblank managed values take precedence; blank values are ignored.
- Render the additional text through `{{ extra_policy }}` in Guardian reviewer templates and append it to the tenant policy for Guardian v2 classification before truncation.
- Preserve placeholder-like text inside supplied policies literally.
## Testing
Add coverage for configuration precedence, blank values, template substitution, and classifier prompts, plus a scenario verifying that managed tenant and extra policies reach the Guardian reviewer together.
GitOrigin-RevId: 180d8d716c63fe96a92ec5bfbd22db4ddccd4f1f
## Why
Attachment stores need the receiving thread ID to support thread-based placement.
## What changed
Add `thread_id` to `UploadRequest` and pass the session's thread ID through image preparation for messages and tool outputs. Include the ID in debug output while continuing to redact attachment bytes.
## Testing
Extend the image rollout test to assert that a new image uploaded after resume carries the resumed session's thread ID. Update the debug-output test for the new field.
GitOrigin-RevId: f81e3bd761dca704064287177b8ecd7175662f07
## What changed
- Add `tools.code_mode` catalog messages for `exec`, `wait`, deferred-tool guidance, and shared MCP TypeScript definitions.
- Render `{{ default_exec_yield_time_ms }}` and `{{ image_helper }}` in `exec` descriptions while preserving runtime tool declarations and the freeform grammar.
- Resolve `wait` descriptions and parameter schemas independently, falling back to bundled parameters for invalid or unsupported schemas.
- Use the active model's Code Mode messages, including after mid-turn model changes. Missing overrides retain bundled defaults; empty text overrides suppress the corresponding text.
## Testing
Add coverage for literal template substitution, runtime section preservation, independent `wait` overrides and fallback behavior, mid-turn model changes, and a yielded cell completing through `wait` with catalog messages.
GitOrigin-RevId: e542a0cd47a7138a414871192cee47790ed1214e
## Why
Remote plugin requests always sent `OAI-Product-Sku: codex`, ignoring the existing `apps_mcp_product_sku` setting.
## What changed
Pass `apps_mcp_product_sku` through plugin configuration and use it for authenticated remote plugin requests, including discovery, search, installation, and sharing. Keep `codex` as the default and include the SKU when comparing remote service configurations.
## Testing
Extend app-server plugin listing and core agent-turn tests to check default and configured SKU headers. Update the CLI worktree test to wait for the user prompt's model request, skipping background title generation requests.
GitOrigin-RevId: 508c9ef9aa3e41b87c92383c3088eb1eb9227fd8
## What changed
- Persist producer-recorded item start and completion times in thread history, preserving existing non-null values on updates.
- Return nullable `startedAtMs` and `completedAtMs` Unix millisecond timestamps from `thread/items/list`, and update the generated schemas and TypeScript and Python types.
- Leave timestamps unknown for existing rows and older writers.
## Testing
Add coverage for exact timestamp persistence, protocol round trips with present and missing timestamps, paginated item responses, and compatibility with older database writers.
GitOrigin-RevId: 894853481085782ff54db1704799e41446d15e51
## What changed
- Capture optional `creator_user_id` and `creator_account_id` from authentication when creating a thread, including forks.
- Carry these fields through thread storage, rollout metadata, and a SQLite migration. Leave them absent when unavailable or when reading older threads.
- Preserve recorded creator values across resume and metadata updates. On revert, recover missing rollout values from SQLite before writing replacement metadata.
## Testing
Add coverage for ChatGPT and API-key sessions, resume under another account, forks using current authentication, metadata extraction and upserts, and repeated reverts after creator fields are removed from a rollout.
GitOrigin-RevId: 9839fa42f9392f12226002e2c27d05d5656f5695
Change `R to Retry` to `r to retry` in the TUI notice and update the
corresponding rendering snapshots.
GitOrigin-RevId: f7971ba0f76ac446a5fea53b44390f65aa965be4
## Why
On Windows, MXC needs `SystemDrive` to resolve platform directories and
`LOCALAPPDATA` to create the sandboxed helper process. The helper environment
filter previously dropped both variables.
## What changed
Allow `SystemDrive` and `LOCALAPPDATA` alongside `PATH` in the Windows helper
environment, using case-insensitive name matching.
## Testing
Extend the Windows environment-filtering test to verify that mixed-case runtime
variable names are preserved while `PATH_INJECTION` and `OPENAI_API_KEY` remain
excluded.
GitOrigin-RevId: bab242dd59da59ac6e7f428436e1c139aadadfdd
## Why
Code Mode callbacks can retain skill tools after another turn becomes active. Looking up the active turn when a delayed skill invocation completes can lose access to the originating turn's metrics and metadata.
## What changed
- Capture and retain the originating `SkillTurnMetrics` when constructing skill analytics.
- Expose turn analytics metadata through the turn extension store and carry it into skill telemetry.
- Add optional turn metadata to `TrackEventsContext` and pass it from app, skill, and plugin usage call sites.
## Testing
Add a regression test that yields a Code Mode cell, starts another turn, and releases both skill reads through a shared barrier. Assert that each `skill_invocation` event retains its originating `turn_id`.
GitOrigin-RevId: aa629dd5f84563d558aa6a86bfbdfc356f1b98e4
## Why
Realtime WebSockets connected directly, bypassing the configured proxy policy for Voice's WebRTC sideband.
## What changed
Pass the configured `HttpClientFactory` into `RealtimeWebsocketClient` and connect through the shared `WebSocketConnector`. Add support for supplying an existing Rustls configuration to preserve custom CA handling and Windows platform trust.
## Testing
Add an integration test that enables `respect_system_proxy`, starts a WebRTC conversation, and verifies that the sideband establishes its session through an HTTP `CONNECT` proxy and closes successfully.
GitOrigin-RevId: d974c9275d7fe29f388d56a9d5d8ce0c483eb8d0
## Why
The 999-byte response budget and blanket string truncation could discard assistant answers alongside supporting history. Thread lists could also lose entries when shortened to fit the budget.
## What changed
- Raise the response budget to 8,000 bytes and remove the separate 2,000-character cap on assistant messages in `read_thread` and `wait_threads`.
- Compact oversized read responses around each turn's latest assistant message, and retain every wait target and returned list entry with pagination cursors intact.
- Shorten only content fields when further reduction is needed, preserving valid JSON and protocol values such as IDs, cursors, phases, and statuses. Mark compacted responses and shortened content with `truncated`.
- Request archived thread pages at the requested limit without retrying with smaller pages to meet the response budget.
## Testing
Add regression coverage for oversized wait responses with Unicode and escaped text, list entry and cursor preservation, and an oversized read whose assistant answer survives into the next model request. Extend read and wait tests to verify assistant messages longer than 2,000 characters are retained when they fit.
GitOrigin-RevId: 459fa522d02fbe4cd877b9afe8e66c9358b7bbce
## Why
Activity indicators and queued input previews could separate usage notices and
reading controls from the composer.
## What changed
- Reserve the shared hint row below activity and previews in the owned transcript
layout, and use its rendered position for hints and reading controls.
- Clip spacing and hints before activity and previews when vertical space is tight.
- Fit usage notice details within half the row, allowing the shortest complete
warning to use more space on narrow terminals.
## Testing
Expand regression tests and snapshots for running turns, queued inputs, multiline
drafts, short terminals, follow-control clicks, and hidden actionable banners.
Cover five-hour and weekly usage notice width thresholds.
GitOrigin-RevId: e73b3614839ce35c5b0a009901514627a77d4190
Delete the workflow that refreshed `codex-rs/models-manager/models.json`
and opened update pull requests every four hours or on manual dispatch.
GitOrigin-RevId: 0179d8af57b17fd69e9b7e94b7f7ed7b0c6dcc24
## Why
Local MCP servers communicate over stdio, so unrelated parent file descriptors should not propagate into the server or its descendants.
## What changed
Apply `DescriptorPolicy::StdioOnly` when launching local stdio MCP servers on Unix, preserving their explicit transport stdio.
## Testing
Add Unix integration tests that check inheritable pipe, socket, and file descriptors are absent from servers and descendants across absolute, relative, and shell-fallback launches. Verify MCP communication, arguments, environment, working directory, parent descriptor ownership, and exec failure reporting remain intact.
GitOrigin-RevId: 37409a5673dbaafa851fd1f78e3a2443eda5f7c6
## What changed
Serialize `ClientResponse` JSON-RPC results through the untagged
`ClientResponsePayload` enum, and serialize payloads directly instead of matching
on each variant. Preserve existing result shapes and request IDs.
## Testing
Add regression tests covering v1 and v2 payloads with integer and string request
IDs, legacy interrupt responses, and serialization errors from non-UTF-8 paths
on Unix across typed, borrowed, and owned response conversions.
GitOrigin-RevId: d46403b02f910a0d3e41a48a5bc6faa2581873e1
## What changed
- Disable default features for `sentry`.
- Disable default features for `syntect`, explicitly enable `parsing`, `plist-load`, and `regex-onig`, and switch `two-face` to `syntect-onig` in `codex-rs/tui`.
- Remove the resulting unused dependencies from the Cargo and Bazel lockfiles, including Actix, Sentry integrations, `ureq`, and `yaml-rust`.
GitOrigin-RevId: b3ca6610fdc60ab99909660f56099fbb4093b9c5
## Why
Chat analytics displayed raw credit strings, exposing values such as `0E-10` for plan-covered tasks and unnecessary trailing decimal zeros.
## What changed
Format ordinary credit amounts with two decimal places and thousands separators. Round directly from decimal digits to avoid floating-point rounding errors, so `1.005` becomes `1.01`. Normalize zero to `0.00`, while preserving the original strings for nonzero sub-cent amounts and values outside the safe conversion range.
## Testing
Add assertions for decimal and scientific notation, signed zero, rounding boundaries, tiny adjustments, and large values. Update the chat analytics snapshot to cover a plan-covered task showing `0.00` credits.
GitOrigin-RevId: f946cb408c2c37291447f90de02ebbb557fbc662
## What changed
- Describe GPT-5.6-Sol as a reliable agentic workhorse for everyday tasks and change its catalog `priority` from `6` to `4`.
- Describe GPT-5.5 as a proven previous-generation model for coding and general work.
- Refresh model picker, migration prompt, and agent tool snapshots to reflect the catalog updates.
GitOrigin-RevId: b39f51c22862b8cef585ed76f3973c9f4b670c27
## Why
Row derives and migration embedding do not need query macros or a host SQLite driver.
## What changed
- Remove the `macros` feature from `sqlx` and depend directly on `sqlx-macros` with only `derive` and `migrate` enabled.
- Update state and thread-store derives and migration embedding to use `sqlx_macros`.
- Enable `sqlx-sqlite`'s `offline` feature directly to preserve query-description support in the target driver.
- Pin `sqlx`, `sqlx-macros`, and `sqlx-sqlite` to `=0.9.0` to keep their versions aligned.
GitOrigin-RevId: 8a8ef691ff2862a7dad978a578c5206b52dfc0b6
Move status resolution, live settings, and subagent input eligibility into
`enrich_loaded_thread`. Keep `enrich_loaded_threads` responsible for fetching
watched statuses and enriching threads concurrently with `join_all`, preserving
existing behavior.
GitOrigin-RevId: 54f7b61b7cc6dcdfb4a63c1906080858b18df378
## What changed
Add a Voice entry using the configured `toggle_voice` binding (`F8` by default). Show it only when voice commands are enabled and no side conversation is active.
## Testing
Update footer and shortcut overlay snapshots to include the Voice entry.
GitOrigin-RevId: ba92f5af1ce1a06d9700d31dcc90e5acb1613803
## What changed
- Record each MCP source and its first turn, including connector and plugin identifiers when available. Cover direct and Code Mode calls, including returned errors and results that are not printed.
- Persist cumulative attribution checkpoints and restore them across compaction, resume, and forks, including forks limited to recent turns.
- Attach fresh attribution to Responses API `client_metadata` under `mcp_attribution`, outside model-visible content. Restrict transmission to allowed OpenAI HTTPS destinations for both HTTP and WebSocket requests.
- Report `attribution_error` for legacy history without checkpoints, malformed or conflicting attribution, and serialized attribution exceeding 16 KiB.
## Testing
Add coverage for source deduplication, checkpoint persistence and restoration, recent-turn forks, direct and Code Mode calls, destination filtering, and the serialized size limit.
GitOrigin-RevId: fd285e152ca9e24bfa000debb20013709d67a86e
## Why
The Linux sandbox rejected bind mounts of ancestors of the app-server socket directory, even when the exposed socket paths could be masked. This prevented sandbox startup with otherwise usable temporary-directory mount layouts.
## What changed
- Collect the socket directory and its exposed ancestor-mount aliases, then mask each path after filesystem binds, including read-only subpaths and the synthetic-mount registry.
- Continue rejecting direct directory or socket aliases and nested mounts that cannot preserve socket isolation.
- Reject non-UTF-8 mask destinations to avoid masking a different path through lossy conversion.
## Testing
Extend mount-analysis tests for ancestor aliases, private temporary directories, and WSLg masks. Extend socket-isolation coverage to verify that ancestor and registry aliases hide daemon sockets while unrelated sockets remain reachable. Add a regression test for non-UTF-8 mask paths.
GitOrigin-RevId: 49a9a764fbe1fddacd99c3a78099fbffff53b944
## Why
Concurrent credential refreshes could restore a removed environment by overwriting the selection list with stale state. Unpolled snapshot futures could also keep pending configuration alive after an environment was removed.
## What changed
- Protect environment selections with a mutex and update them in place to serialize selection changes, configuration refreshes, and connection listener setup.
- Capture only selection metadata and resolution futures in snapshots so they do not retain pending configuration senders.
## Testing
Add regression tests for removal during credential refresh and cancellation while an unpolled snapshot is held. Strengthen the pending attachment integration test to check that `wait_for_environment` returns the expected environment ID and `ready` status.
GitOrigin-RevId: c6f933e8d3031b05335ddcfed00ab400aa5bad2a
## Why
Message board notifications exposed only post and thread IDs, requiring a read to see any post content.
## What changed
Deliver notifications as `agent_message` items with author and recipient attribution. Include a `CHANNEL_POST` payload with the sender, channel, message and thread IDs, and up to 150 characters of post text. Direct agents to `read_post` when the preview is truncated, and retain recognition of legacy user-role notices.
## Testing
Update the model-context scenario to assert the notification's author, recipient, and preview payload, and update the idle-agent scenario to check for the new notification format.
GitOrigin-RevId: e0e2794be82e38bba47f41fb4fc8128eb5e47619
## What changed
- Replace the built-in orchestrator skill provider with a host-supplied cloud provider, using `cloud` authority and `c` root aliases in skill tools and prompts.
- Add `cloud.skills.enabled`, defaulting to true but requiring a supplied provider. Keep `orchestrator.skills` accepted as a legacy no-op setting, and remove the app server's automatic orchestrator provider registration.
- Discover cloud skills once per turn during cancellable startup. Serve catalog snapshots to prompts and tools without triggering discovery or retries.
- Scope cached catalogs and resources to authentication state. Preserve them on refresh failures within the same scope, invalidate them when that scope changes, and reject late discovery or read results from replaced cache generations.
- Reuse executor discovery catalogs only when successful discovery inputs and bundled-skill settings match.
## Testing
Add coverage for per-turn refresh, skill removal, same-account failures and reconnects, authentication changes, and stale in-flight results. Update configuration and tool tests for cloud authority, provider gating, and resource reads without an executor.
GitOrigin-RevId: c57e38ec7dcc880c0d4c8a2995adfd3e28301079
## Why
`TurnComplete` precedes active-turn cleanup, so injecting follow-up history immediately afterward can race with cleanup.
## What changed
Register the `ThreadIdle` lifecycle contributor in `review_preserves_user_instructions_until_request_budgeting` and wait for the thread to become idle after the initial and follow-up turns.
GitOrigin-RevId: 1ae6c80593a71d331c5c6ddf85bbe10822a68afe
## Why
Transcript selections could include a newline without showing it in the highlight, making `code` and `code\n` look identical.
## What changed
Highlight one trailing cell for selected hard line breaks when space permits, including newline separators between transcript entries. Track logical line endings so soft wraps and synthetic rows do not receive newline highlights.
## Testing
Add selection snapshots for hard breaks within and between entries, plus layout coverage for empty lines, wrapping, trailing whitespace, and synthetic rows. Update the app selection test to assert the leading newline highlight.
GitOrigin-RevId: d6f332c472598a3f79557b7ebb41730c6acc7820
## Why
Global deprecation notices can be delivered again by hidden threads, creating duplicate transcript entries.
## What changed
Skip incoming deprecation notices whose summary and details match a notice already in retained history. Preserve notices with different summaries or details, and allow notices to appear again after clearing history or rebuilding the transcript during a thread switch.
## Testing
Add a regression test and transcript snapshot covering repeated live and replayed notifications, an open transcript overlay, distinct notice content, and delivery after clearing history or switching threads.
GitOrigin-RevId: 9c0512f588dfb54f7934380119211b57b0df0ee4
## Why
When result metadata exceeds the output budget, message-board tools keep retrying identical reads after all limits reach one.
## What changed
Stop shrinking reads once every page and character limit reaches one, returning the existing metadata-budget error if the result still does not fit. Use the largest effective limit to keep retrying while either the page size or preview length can still shrink.
## Testing
Add regression assertions for all five read tools with an impossible output budget, checking the error and exact read counts. Cover unequal page and preview limits and limits that are not powers of two.
GitOrigin-RevId: f00ddbcf0372c8f9318fa178259868caae55e68b
Create `posts_roots_created` on `(board, channel, timestamp, seq)` for
posts where `id = root` in the local SQLite schema.
GitOrigin-RevId: 4c40e0d853deaa3ab6b6303525870e3b7bfc3b14
2026-09-21 16:16:40 +00:00
4489 changed files with 317485 additions and 83315 deletions