Commit Graph
3 Commits
Author SHA1 Message Date
cd8270c98b Sign in with a ChatGPT subscription for inference (#854)
Co-authored-by: Jonathan Singer <jonathansinger@Jonathans-MacBook-Pro.local>
Co-authored-by: Jonathan Singer <jonathansinger@Mac-3004.lan>
Co-authored-by: Ahmed Allam <ahmed39652003@gmail.com>
2026-07-24 15:41:19 -07:00
Ahmed AllamandAhmed Allam 3bb95ab43d fix(llm): add per-turn model request timeout so stalled streams fail fast and retry 2026-07-17 18:40:23 -07:00
Ahmed AllamandAhmed Allam b9c2592b53 fix(llm): retry statusless mid-stream provider errors (quota/billing)
The SDK's http_status retry policy only retries errors carrying a known
HTTP status code, but quota/billing (and other provider-side) failures
often surface inside a streamed response as a bare error with no status
code, so they were failing on the first attempt. Add a statusless retry
policy to DEFAULT_MODEL_RETRY so they are retried (before any content is
streamed; user aborts are never retried), restoring the pre-SDK engine's
resilience. If the provider is genuinely exhausted, the error still
propagates and fails the scan after retries.
2026-07-17 16:47:14 -07:00