Repository navigation
fix(muse-proxy): surface runs that fail after partial output as errors (#672) - #673
Merged
Merged
Conversation
#672) The failed predicate gated both clauses on empty content, so a run that emitted any assistant text before failing — terminal state 'failed', or a non-zero exit with no terminal event — was returned as a successful finish_reason 'stop' carrying the truncated text. Judge failure by the authoritative terminal state when one was emitted, otherwise by the exit code; partial content no longer masks the failure. Stream mode keeps the #670 surfacing (error frame + [DONE], no 'stop' chunk). When stderr is empty and the terminal state is the evidence, the error detail names the terminal state instead of a misleading 'exited with code 0'.
Codex Review SummaryThis comment shows the latest Codex review activity on this pull request.
ℹ️ About Codex in GitHubYour team has set up Codex to review pull requests in this repo. Reviews are triggered when you
Codex reacts with 👀 while any review is running, comments if it has suggestions, and reacts with 👍 once all reviews finish with no findings. |
|
Note Currently processing new changes in this PR. This may take a few minutes, please wait... ⚙️ Run configuration
📒 Files selected for processing: 2
✨ Finishing Touches
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
This was referenced Oct 23, 2026
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Fixes #672
Problem
bin/muse-proxy.mjs's failure predicate gated both clauses onfullContent.length === 0, so any run that emitted assistant text before failing was returned as a successfulfinish_reason: 'stop'carrying the truncated text — verified pre-fix with a stubmusefor both arun.terminal.failed(exit 0) and a crash (exit 3, no terminal event), in stream and non-stream modes.Fix
terminalState !== 'completed'), otherwise by the exit code. Partial content no longer masks a failure.completedterminal event (terminal is authoritative), the muse-proxy (PR #479): streaming responses silently drop the terminal text tail that non-streaming returns #484 tail reconciliation, and usage accounting.[DONE], and no'stop'chunk is emitted. Non-stream gets the 500 error body.muse exec exited with code 0.Tests
partial output then failure: masked success becomes an error in both modes (#672)with stub markers FAILPARTIAL / CRASHPARTIAL covering both failure shapes × both modes.node --test bin/muse-proxy.test.mjs: 4/4 pass. Ablation: with onlybin/muse-proxy.mjsreverted, exactly the new test fails and the other three pass.Need help on this PR? Tag
@codesmith-botwith what you need.