fix(ai): honor retry-after for OpenAI Codex SSE retries

- honor `retry-after-ms` and `retry-after` for OpenAI Codex SSE retries
- add SSE retry coverage for millisecond, seconds, date, and fallback delays
This commit is contained in:
Ramiz Wachtler
2026-05-13 19:26:08 +02:00
parent 40c05f5539
commit 0ae909316a
3 changed files with 184 additions and 20 deletions

View File

@@ -12,6 +12,7 @@
- Fixed GitHub Copilot Claude test coverage to use the current Claude Sonnet 4.6 model ID.
- Fixed OpenAI Responses requests for models that support disabling reasoning to send `reasoning.effort: "none"` when thinking is off.
- Fixed Inception Mercury 2 tool calling on OpenRouter by marking `off` as unsupported in `thinkingLevelMap`, so the openai-completions provider omits the reasoning param instead of defaulting to `{reasoning:{effort:"none"}}` (which puts Mercury 2 in instant mode, disabling tool calls).
- Fixed OpenAI Codex SSE retries to honor `retry-after-ms` and `retry-after` headers before falling back to exponential backoff.
## [0.74.0] - 2026-05-07