Repository navigation
Let harness see every agent event and stop retrying what fails the same way - #43
Open
alexandre-daubois wants to merge 1 commit into
Open
alexandre-daubois wants to merge 1 commit into
alexandre-daubois wants to merge 1 commit into
Conversation
…me way The agent wrapper only forwarded the session event, so RunSession never saw a lost conversation and never restarted it fresh, and StreamCmd never saw the error events it classifies as account errors. The retry now skips a model account refused for good and a spent budget. Codex gets its effort through Job.Effort, catalogued CWE ids such as cwe-787 are spelled canonically instead of dropped, GitHub reads retry 429, 502, 503 and 504, a test keeps the agent image pins in step, and CI vets the evals.
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
The agent wrapper only forwarded the session event, so RunSession never saw a lost conversation and never restarted it fresh, and StreamCmd never saw the error events it classifies as account errors. The retry now skips a model account refused for good and a spent budget. Codex gets its effort through Job.Effort, catalogued CWE ids such as cwe-787 are spelled canonically instead of dropped, GitHub reads retry 429, 502, 503 and 504, a test keeps the agent image pins in step, and CI vets the evals.