mirror of
https://github.com/zeronsh/comet.git
synced 2026-11-16 18:57:19 +00:00
* Claude subagents: count and open only this chat's spawns The ● N badge counted every tagged stream the engine opened a sink for, while the lanes card lists only the chat's spawn chips. Claude Code tags a forked skill's traffic with its Skill call's id, the agents a subagent starts with their own Agent call ids, and a skill passed as `/<name>` with `forked-command-<name>`. None of them is a spawn chip of the chat, so the badge could read 3 over an empty card (#999). A sink (its own doc, one unit on the badge) now opens only for a spawn chip of the chat (`is_chat_spawn`). Traffic tagged with any other id stays in the journal. A forked skill is the chat's own subagent, though. The Claude adapter sets each Skill call aside until its task starts, which comes ahead of all the fork's traffic, and re-decodes it then as a spawn named after the skill (`Agent: /review`). Its traffic then has a card and a tab to feed. An inline skill starts no task, and its result drops it. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> * Claude subagents: forward a foreground subagent's text and thinking Claude Code leaves the text and thinking blocks of a foreground subagent (or a forked skill) out of the stream unless asked, so its tab showed tool calls only (#1000). Runs now set CLAUDE_CODE_FORWARD_SUBAGENT_TEXT=1, which "enables the same behavior" as `--forward-subagent-text` (https://code.claude.com/docs/en/cli-reference). The variable rather than the flag: a CLI older than 2.1.211 ignores it, but refuses an unknown flag. The CLI then forwards subagents "at every nesting depth" (https://code.claude.com/docs/en/headless). The spawn gate keeps the agents a subagent starts in the journal, instead of badging the chat with docs no card lists (#999). The adapter already emitted tagged text blocks. Tagged thinking blocks now become the subagent's reasoning, in block order. A background subagent sends them unasked, so its tab gains its reasoning too. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> * Forward-subagent-text demo media for the PR (live before/after stills) Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> |
History
|
|
|---|---|---|
| .. | ||
| 00-before-after.png | ||
| 01-before-tab.png | ||
| 02-after-tab.png | ||
| 03-before-window.png | ||
| 04-after-window.png | ||
| README.md | ||
Forward subagent text: demo media
Live captures for "Claude subagents: forward a foreground subagent's text and thinking" (#1000).
- The same prompt went to two headless engines on one Mac, each in a fresh chat on Claude Code 2.1.310 with Haiku: Zeron v0.2.121 (before) and this branch (after). It asks for one foreground
Agentcall whose prompt is: write "The sky is blue.", runecho hi, write "The grass is green.". Both runs named the subagent "Sky, echo, grass sequence". - The frames are the production
Shellrendered offscreen by gpui (Window::render_to_image), attached to each engine over IPC, with the subagent's tab opened as its chip opens it. They are not an OS screen recording. - Both tabs show the subagent's prompt twice. That is the separate bug #952 fixes.
00-before-after.pngputs the two tabs side by side.01and02are the tabs at full resolution.03and04are the full windows, at half size.- The session card's device name is blurred.