feat(subagent-tool-call): report coherent agent and command updates#284
Open
duclvz wants to merge 1 commit into
Open
feat(subagent-tool-call): report coherent agent and command updates#284duclvz wants to merge 1 commit into
duclvz wants to merge 1 commit into
Conversation
Present each sub-agent run as one activity and expose internal command output through portable ACP content.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Improve how Codex app-server command execution and sub-agent activity are represented through ACP.
This change:
wait,sendInput, andcloseAgentcontrol actions into updates on that activity._meta.codex.toolName: "Agent"for deterministic client classification.Motivation
The previous mapping exposed Codex orchestration details too literally.
A delegated agent could appear as a foreground command followed by separate
waittool calls, even though those waits were control-plane operations for the same unit of work. This made ACP clients display several unrelated tool cards instead of one sub-agent activity.Internal command executions also used ACP terminal content with a Codex item ID that was never created through ACP
terminal/create. That behavior was not portable to clients without codex-acp-specific terminal handling.The new mapping presents semantic work to the client while retaining the underlying Codex action details in structured output.
Sub-agent lifecycle
Agenttool callwaitsendInputcloseAgentAgenttool callEvery synthesized sub-agent event includes:
{ "_meta": { "codex": { "toolName": "Agent", "subAgent": { "agentThreadId": "<child-thread-id>", "runId": "<activity-tool-call-id>" } } } }