3 Commits

Author	SHA1	Message	Date
Yijia-Xiao	e3bc872982	chore(lint): make the repository ruff-clean under the strict select ... Clear the deferred full-repo lint backlog so the whole tree passes the strict ruff select (E,W,F,I,B,UP,C4,SIM). Mechanical fixes dominate: import sorting, pep585/604 annotations, dropped dead imports, and whitespace. The few semantic changes are behavior-preserving: declare __all__ on the agent_utils and alpha_vantage re-export hubs; expand 'from x import *' to explicit names; use immutable tuple defaults instead of mutable list defaults; contextlib.suppress for try/except/pass; and narrow an over-broad assertRaises.	2026-06-14 16:38:36 +00:00
Yijia-Xiao	22bb91bd83	fix(llm): structured output for DeepSeek V4 and reasoner ... DeepSeek V4 and reasoner reject tool_choice but accept tools. Route via a per-model capability table that suppresses tool_choice for thinking-mode models. #678 #689	2026-05-11 01:12:28 +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