docs: record thinking-switch findings and capability design (issue #5, #6)

Findings: live-API measurements across MiniMax M3/M2.7/M2.5, qwen and
deepseek, plus a survey of how nine unified gateways model per-model
parameter divergence. Key facts: reasoning_effort is MiniMax's real
switch, M2.x reasoning is mandatory and cannot be disabled, and the
relay's local token-count fallback silently drops reasoning_tokens.

Design: keep the parameter shape at provider level, push capability
down to model level, split "unknown" / "unsupported" / "no opinion"
into three distinct values, and fail at assembly time when a model
cannot honour enable_thinking=False.

This commit is contained in:

iomgaa

2026-08-02 05:42:05 -04:00

parent ce630a37ef

commit 781579bf36

6 changed files with 455 additions and 4 deletions

									
										research-wiki/query_pack.md
									
		+1
		-1
	
												View File
												
				@@ -1,3 +1,3 @@

				# Query Pack

				> 尚无数据。运行 research-lit 或 idea-creator 后自动生成。

				> 自动生成，请勿手动编辑。