test(tools): gated live test — agent chains write_file → run_shell - #28
Merged
Conversation
Reproduces the "wrote the script but didn't run it" failure and verifies the
fix: with a persistence-oriented system prompt ("keep going until FULLY done;
after writing a script, RUN it"), glm-5.2:cloud chains write_file -> run_shell
and reports the real output. Passed 3/3.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
|
Caution The consumer version of Gemini Code Assist on GitHub has been sunset. All code review activity has officially ceased. |
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Reproduces the observed "wrote the script but didn't run it" failure and pins the fix.
With a persistence-oriented system prompt ("keep going until FULLY done; do not stop after one step; after writing a script, RUN it and report the output"),
glm-5.2:cloudreliably chainswrite_file→run_shell→ reports the real output and the file exists. Passed 3/3 locally. Gated onSAK_LIVE_TESTS=1.The corresponding app fix (Naseem's default system prompt) lives in the app repo; this pins the framework-level behavior it depends on.
🤖 Generated with Claude Code