Fix Codex provider to detect file edits from patch_apply_end events#148
Merged
Fix Codex provider to detect file edits from patch_apply_end events#148
Conversation
Codex records file modifications as event_msg entries with type patch_apply_end rather than function_call tool invocations. This fix tracks those events and adds Edit to the tools list, enabling proper calculation of edit turns, one-shot rates, and retry rates. Fixes edit detection showing 0 edit turns despite actual file changes.
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
patch_apply_endevents as Edit tool usageProblem
Codex records file modifications as
event_msgentries withtype: patch_apply_endrather thanfunction_calltool invocations likewrite_file. The provider was only looking for tool calls, missing all the actual edits.Solution
Track
patch_apply_endevents and add "Edit" to the tools list when detected.Test plan
codeburn comparewith Codex model to verify metrics