Repository navigation
feat(ux): show resolved model/effort in the /codex:rescue launch line (closes #34) - #35
Merged
Merged
Conversation
…closes #34) The launch line for the codex:codex-rescue subagent showed only the topic (codex:codex-rescue(<topic>)) and never the model/effort Codex actually uses — painful in background runs where the companion's stderr announce is swallowed. The Agent-tool `description` is free-form text composed by the caller before the subagent selects the model, so instruct the caller (commands/rescue.md) to include the resolved model/effort there: `<topic> model=<…> effort=<…>`. Aliases resolve to full ids (spark→gpt-5.3-codex-spark, sol→gpt-5.6-sol, terra→gpt-5.6-terra, luna→gpt-5.6-luna); unset → `default`. No desync risk because codex-rescue selects the model only from explicit user flags. Companion unchanged — announceRun (#24) stays for foreground-stderr; the launch line is covered by the skill layer. Co-Authored-By: Claude <[email protected]>
Owner
Author
📋 Review summary — all cycles
Totals: 0 FIX, 0 SKIP, 0 UNVERIFIED. |
axisrow
added a commit
that referenced
this pull request
Jul 21, 2026
Ships accumulated fixes since fork.4: - #29 broker-busy hang (PR #30): bound broker handshake - #31 spawned-app-server handshake (PR #32): bound request() primitive - openai#508 config-driven sandbox + --read-only (PR #33) + resume-sandbox fail-closed - #34 model/effort in /codex:rescue launch line (PR #35) - #28 turn-timeout gaps (already in fork.4 base) Co-Authored-By: Claude <[email protected]>
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
What
The launch line for the
codex:codex-rescuesubagent shows only the topic:The model/effort Codex actually uses is nowhere visible — especially painful in background runs where the companion's stderr announce is swallowed. This PR makes the launch line show the resolved model/effort:
How
The Agent-tool
descriptionis free-form text the caller composes before the subagent selects the model.commands/rescue.mdnow instructs the caller to appendmodel=<…> effort=<…>(resolved to full ids;defaultwhen unset). No desync risk —codex-rescue.mdselects the model only from explicit user flags, so the caller resolves the same value deterministically.Companion unchanged:
announceRun(#24) stays for foreground-stderr; the launch line is covered by the skill layer.Verification
Docs/skill-layer change (no runtime code). Manual check after install:
/codex:rescue --model sol --effort xhigh <prompt>→model=gpt-5.6-sol effort=xhigh/codex:rescue <prompt>(no flags) →model=default effort=default🤖 Generated with Claude Code