Repository navigation
feat(server): optionally retry Codex capacity errors with backoff - #47
Merged
Merged
Conversation
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Codex turns currently stop when the selected model is at capacity, requiring a manual continuation. Add an opt-in server setting that retries these failures up to five times with exponential backoff and jitter. Each thread retries independently, keeps its original prompt in history, and remains cancellable with Stop.
The setting is available in web/desktop General settings and mobile Agent behavior settings. It defaults to off; authentication and usage-limit errors are not retried.
Validation: 405 focused tests passed, including recovery, retry exhaustion, cancellation, unrelated errors, disabled settings, and parallel threads. Server, web, and mobile typechecks passed. Targeted lint passed with existing warnings. After integrating current main, the affected 326 tests and server typecheck passed again. The existing settings symlink-watch timeout passed when rerun in isolation. Browser/device visual verification and before/after screenshots were not performed.
Merge for the next release; no separate release is requested.
Model: gpt-6.1-sol. Harness: Codex.