fix(e2e): make D10 coding task resilient to context overflow#74
Merged
emal-avala merged 1 commit intomainfrom Apr 6, 2026
Merged
fix(e2e): make D10 coding task resilient to context overflow#74emal-avala merged 1 commit intomainfrom
emal-avala merged 1 commit intomainfrom
Conversation
|
You have reached your Codex usage limits for code reviews. You can see your limits in the Codex usage dashboard. |
D10 consistently fails with code=400 on small models (gpt-5-nano) because the accumulated session context from D1-D9 exceeds limits. Fix: - Restart serve before D10 to get a fresh session with empty context - Retry once on failure with another fresh session restart - Simplify the prompt to be more direct (provide exact script content instead of describing the logic) This was failing on v0.13.0, v0.13.1, and v0.14.0 releases.
emal-avala
force-pushed
the
fix/e2e-d10-flaky
branch
from
01bdf65 to
30d29f3
Compare
Merged
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
code=400on small models (gpt-5-nano) because the accumulated session context from D1-D9 exceeds the model's limitsThis has been failing on v0.13.0, v0.13.1, and v0.14.0 E2E runs.
Test plan
run-e2elabel to trigger E2E suite — D10 should pass🤖 Generated with Claude Code