Skip to content

feat(server): optionally retry Codex capacity errors with backoff - #47

Merged
r4iju merged 2 commits into
mainfrom
feat/server-capacity-auto-retry
Oct 12, 2026
Merged

r4iju merged 2 commits into
mainfrom
feat/server-capacity-auto-retry

Conversation

@r4iju

@r4iju r4iju commented Oct 12, 2026

Copy link
Copy Markdown
Owner

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.

@github-actions github-actions Bot added the vouch:trusted PR author is trusted by repo permissions or the VOUCHED list. label Oct 12, 2026
@r4iju
r4iju merged commit 2318649 into main Oct 12, 2026
7 of 22 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

size:L vouch:trusted PR author is trusted by repo permissions or the VOUCHED list.

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant