docs: retire the criterion this version disproved, everywhere it survived

The reasoning_tokens docstring was still teaching downstream to treat
None or 0 as no reasoning. The changelog and the schema page had both
been corrected; the docstring had not, and it is the copy that ships in
the wheel and shows up on hover. Someone writing a report from it would
have counted every real MiniMax reasoning call as not reasoning, which
is issue #16 all over again with the tests green.

The original wording stays, since reading pre-1.3.1 rows still needs
it. What follows it now says when it expired and what to read instead.

Two more places had drifted the same way: the changelog and the
architecture doc described the throttle and the cache fallback as they
were before this review, which is to say as the opposite of what the
code now does.

The claim that the two throttle sets would suppress each other does not
survive checking, as the mutation testing showed: their key spaces do
not overlap. Keeping them apart is still right, but for the honest
reason, which is that the two warnings have unrelated lifetimes.

research-wiki/ROADMAP.md

@@ -28,7 +28,7 @@
 |---|---|---|
 | 1 | `types.py` + `errors.py` + `ports.py` 全量设计与冻结 | 原则 2:公共承诺先行;这是 M1 设计文档(人类门)的主体 |
 | 2a | `streaming.py` 看门狗移植 | 原则 4:纯函数,零依赖,直接移植+补测 |
-| 2b | `providers.py` 注册表 | 叶子模块;transport 的前置(thinking 注入/思考流字段声明) |
+| 2b | `providers.py` 注册表 | 叶子模块;transport 的前置(思考流字段声明;thinking 注入的**决策**已于 issue #16/#17 搬到 `thinking.py`,这里只留形态声明) |
 | 3 | `transports/openai_compat.py`(SSE 解析、非流式快路径、错误翻译 §6.2) | 依赖 1/2a/2b;错误翻译是中间件的语义地基 |
 | 4a | `middleware/retry.py`(D13 自研,单层原则)+ `sources.py`(SourceConfig、round_robin/least_inflight 选源、源冷却备忘) | 依赖错误分类;先于限流接入便于独立测试。**多源完整行为(换源/冷却/多源行为测试)2026-07-20 人类拍板自 M2 提前进 M1**——重试循环每次尝试都要选源,签名与行为一并钉死 |
 | 4b | `backends/memory/`(limiter + breaker)+ 对应中间件 | 语义契约(permit/settle、状态机)在内存版上钉死,契约测试同步交付 |