Commit Graph
7 Commits
Author SHA1 Message Date
Yijia-Xiao 19d22b54a9 feat(llm): add MiniMax as a built-in provider
Two regional endpoints (global api.minimax.io, China api.minimaxi.com)
with separate API keys. Models M2.7 / M2.5 plus -highspeed variants,
204K context. Follows the existing provider-preset pattern.

#789 #609 #577 #546 #395 #378
2026-05-11 02:03:27 +00:00
Yijia-Xiao 7e9e7b83c7 feat: DeepSeek V4 thinking-mode round-trip via DeepSeekChatOpenAI subclass
Resolves #599: thinking-mode models require reasoning_content to be
echoed back across turns; multi-turn agent runs failed with HTTP 400.

The fix isolates DeepSeek's quirks (reasoning_content round-trip and
the deepseek-reasoner no-tool_choice limitation) into a subclass so
the general OpenAI-compatible client stays untouched. Adds DeepSeek
V4 Pro/Flash to the catalog. 9 new tests; rationale documented in
the class docstrings.

Design adapted from #600; #611 closed in favour of this approach.
2026-05-01 19:23:23 +00:00
Yijia-Xiao b0f6058299 feat: add DeepSeek, Qwen, GLM, and Azure OpenAI provider support 2026-04-13 07:12:07 +00:00
Yijia-Xiao 4f965bf46a feat: dynamic OpenRouter model selection with search (#482, #337) 2026-04-04 07:56:44 +00:00
Yijia-Xiao e75d17bc51 chore: update model lists and defaults to GPT-5.4 family 2026-03-29 19:45:36 +00:00
CadeYu bd6a5b75b5 fix model catalog typing and known-model helper 2026-03-25 21:46:56 +08:00
CadeYu 8793336dad sync model validation with cli catalog 2026-03-25 21:23:02 +08:00