mirror of
https://github.com/stablyai/orca.git
synced 2026-11-16 02:47:34 +00:00
* fix(opencode2): only treat the question tool's form as a pane blocker OpenCode 2 has one form primitive and several producers, and Orca's setup bridge mapped every `form.created` to `question.asked` — the un-evictable "the pane owner must answer this" blocker. Against opencode v2.0.12 only `metadata.kind === "question"` is the agent's question tool; `websearch.provider` is a provider picker and `mcp-elicitation` is an MCP server prompt raised on sessionID "global", which is not a session and so can never be retired by that session going idle. Admit only the question kind, remember the admitted form ids, and drop `form.replied`/`form.cancelled` for forms that were never admitted so an ignored form's resolution cannot retire a live blocker. Evidence (live v2.0.12 capture, real TUI in a PTY against `opencode serve`) in docs/bug-reproductions/opencode2-form-created-kinds. That capture also shows the reported Subagents/Shell/Terminals dock and the agent picker emit no server event at all, so they were never the `form.created` source. Refs #22371 * refactor(opencode2): drop the unreachable form-resolution guard Review was right that the admitted-form-id set defended against nothing. `clearAttentionForResolution` builds the exact key [factoryID, "AskUserQuestion", form.id, sourceSessionID] and returns null on a miss, with no session-wide fallback, and form ids are unique — so a resolution for a form Orca ignored already matches no live blocker. The guard's comment claimed a collision the key structure rules out, which is worse than no comment. Removes the set, its FIFO eviction helper, and the claim; the kind check on form.created is the whole fix. The end-to-end test stays: it pins the behavior that an MCP form raised and cancelled leaves a live question blocker standing, which is the property worth holding regardless of how it is achieved.
49 lines
2.1 KiB
Plaintext
49 lines
2.1 KiB
Plaintext
• Affirmative response +
|
|
┃ Use the task tool three times in one go to launch three subagents in parallel. Give each one this exact
|
|
┃ instruction: run the bash command `sleep 240` and then report done. Do not wait for them to finish before Affirmative response
|
|
┃ replying to me.
|
|
┃ Context
|
|
8,907 tokens
|
|
✓ General Subagent — Sleep 240 seconds Background 1% used
|
|
$0.04 spent
|
|
✓ General Subagent — Sleep 240 seconds Background
|
|
|
|
✓ General Subagent — Sleep 240 seconds Background
|
|
|
|
I have launched three subagents, each running sleep 240 in the background. You will be notified when they
|
|
complete.
|
|
|
|
Build · Gemini 2.5 Flash · 2.2s · 117.5 tok/s
|
|
|
|
↳ General finished · Sleep 240 seconds
|
|
|
|
One of the subagents has reported "Done." I'm still waiting for the other two subagents to complete their sleep
|
|
240 command.
|
|
|
|
Build · Gemini 2.5 Flash · 1.1s · 58.7 tok/s
|
|
|
|
↳ General finished · Sleep 240 seconds
|
|
|
|
Another subagent has finished. One subagent is still running its sleep 240 command.
|
|
|
|
Build · Gemini 2.5 Flash · 1.9s · 59.3 tok/s
|
|
|
|
↳ General finished · Sleep 240 seconds
|
|
|
|
All three subagents have now completed their tasks.
|
|
|
|
Build · Gemini 2.5 Flash · 478ms · 21.2 tok/s
|
|
|
|
┃
|
|
┃ Subagents Shell Terminals esc
|
|
┃
|
|
┃ No active subagents
|
|
┃
|
|
┃
|
|
┃
|
|
┃
|
|
┃
|
|
┃ show inactive ctrl+a tabs ←/→
|
|
┃ /private/tmp/oc2-evidence
|
|
|