5 Commits

Include renames

Author	SHA1	Message	Date
5 people	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	88ad3e4472	fix(llm): use a JSON-serializable per-turn model timeout ... An httpx.Timeout in ModelSettings.extra_args crashes ModelSettings.to_json_dict() (PydanticSerializationError) on the Chat Completions and LiteLLM model paths, which serialize settings for their tracing generation span — failing every model turn on those paths. Pass the timeout as a plain float, which httpx-based clients apply as the read (inactivity) timeout.	2026-07-17 19:45:32 -07:00
Ahmed AllamandAhmed Allam	cf7689e927	fix(llm): use httpx.Timeout read-inactivity for per-turn model timeout	2026-07-17 18:40:23 -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
3 people	b959d528a2	Warn when configured LLM is not frontier-recommended (#586) ... Co-authored-by: Ahmed Allam <ahmed39652003@gmail.com>	2026-07-13 17:41:44 -07:00