3 Commits

Include renames

Author	SHA1	Message	Date
Yijia-Xiao	9df071b25b	fix(google): give a Gemini call the same 600-second timeout as the other providers (#1417) ... - GoogleClient sets timeout=600 unless one is passed, as the OpenAI and Anthropic SDKs do by default, so a stalled call no longer hangs the run	2026-10-03 21:27:43 +00:00
Yijia-Xiao	9b4c741d33	fix(llm): forward reasoning effort to GPT-6 and gate minimal thinking ... - reasoning_effort was forwarded only to IDs matching gpt-5 or the o-series, so GPT-6 models silently dropped the configured effort; match GPT-5 and later, with a version boundary so unrelated IDs do not match - Gemini Pro, 3.8+ and the -latest aliases reject thinking_level "minimal" with a 400; send it only to numbered Flash models before 3.8 and map it to "low" elsewhere, since aliases move between generations	2026-09-14 18:09:33 +00:00
Yijia-Xiao	7bb16c5daa	chore(models): retire deprecated models, simplify thinking config ... Trim each provider to current-generation models and drop the special-casing they required: - OpenAI: remove gpt-4.1 (deprecated; the only non-reasoning model). - Anthropic: remove Claude Sonnet 4.5 (legacy; the only Sonnet that 400s on effort). - Google: remove the Gemini 2.5 line (superseded by 3.x). - Gemini client: drop the integer thinking_budget mapping; 3.x takes the string thinking_level directly. Effort/reasoning gates stay as defense in depth for custom model IDs. All kept IDs verified against live APIs.	2026-06-21 21:03:05 +00:00