Verified each provider's hard-coded list against current official docs:
- MiniMax: add MiniMax-M3 (1M ctx, multimodal) as the default; keep M2.7 line.
- Qwen: use the live qwen{3.7,3.6}-{plus,max} IDs.
- GLM: add glm-5.2 as the latest flagship.
- xAI: drop deprecated grok-4-fast-* / grok-4-0709 builds.
- DeepSeek: migrate to deepseek-v4-pro / deepseek-v4-flash (the chat/reasoner
aliases are deprecated 2026-07-24 and now map to V4 Flash).
OpenAI, Anthropic, and Gemini were already current and are unchanged.
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.
MinimaxChatOpenAI unconditionally set reasoning_split=True, but the
kwarg is only valid on M2.x reasoning models. The openai SDK's strict
kwarg validation raised TypeError for Coding Plan and any other non-
reasoning MiniMax model.
Adds requires_reasoning_split to ModelCapabilities, gates the payload
injection on it, and only sets True for _MINIMAX_THINKING (M2.x exact
IDs and the ^MiniMax-M\d forward-compat pattern). Same shape as the
existing supports_tool_choice gate.
Regression tests cover both halves: M2.x models still receive the flag,
non-reasoning MiniMax models do not.
M2.x tool_choice is enum-only (none/auto), so route through the
no-tool_choice dispatch. MinimaxChatOpenAI injects reasoning_split
so <think> blocks stay out of content. Catalog rounded out to the
full official M2.x lineup plus forward-compat regex.
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
