docs: cut 1.3.3 notes for the tier work

CHANGELOG gets all five breaking changes, not the one the draft had:
ThinkingCapability's constructor, two ports that grew a parameter with
no default, resolve_thinking's new return type, and ProviderProfile's
single wire field. Behaviour changes get their own section, including
the one that is easy to miss — the openai fallback segment no longer
refuses an unknown shape, so a downstream that parks a foreign model
there and asks for thinking used to fail at assembly and now sends
nothing at all. minimax is called out as the exception it is: the gateway
proved M3 does not think without a parameter, so that segment keeps its
medium and its downstreams see no change this release.

The capability table is reported as it stands — 17 of 24 rows measured,
7 still on documentation, with the reason each one went unmeasured, so
nobody reads "measured" into a row that is a guess. The auto limitation
and its deliberate MiniMax-M3 inconsistency are written down rather than
left for someone to trip over; issue #21 holds the real fix.

ARCHITECTURE had five claims that measurement showed had gone false:
the cache key formula, the field count, the reconcile predicate and its
throttle key, and two field lists. README's FIELD set was missing the
two new keys it calls exhaustive.

docs-convention still opened by announcing a 17-page site that has not
existed since August. It now says what is actually there — one placeholder
page pointing at .env.example, CHANGELOG and the source docstrings — and
says which four files carry the sync gate while the site is down.

README.md

@@ -16,9 +16,10 @@
 | 熔断 | 双通道(连续失败 + 失败率窗口,健康证据抑制误熔);半开单探针带租约(持有者死亡自动回收);epoch fencing 拒绝迟到写回;开路时长指数递增;**开路时当场失败还是等冷却可配**(`CIRCUIT_OPEN`,单源 scope 应配 `wait`) |
 | 自适应并发 | AIMD:429 削减、成功缓升,防止打爆上游 |
 | 背压与判死 | 配额满与熔断开路**各自**可选等待或快速失败(`QUOTA_FULL` / `CIRCUIT_OPEN`,两键不可互相替代);等待期按双条件判死(本地非生产性等待与全局无进展**同时**超窗)。stall 窗口只计**非生产性**等待(429 退避/配额轮询/熔断冷却),与 `TIMEOUT_S` 无耦合 |
-| 响应缓存 | Redis/内存;key 含 model + messages 摘要 + namespace(缓存隔离单位)+ salt + 采样参数,多模态 content 先摘要再 hash(防毒化);可 per-call 绕过(科研重采样) |
+| 响应缓存 | Redis/内存;key 含 model + messages 摘要 + namespace(缓存隔离单位)+ salt + 采样参数 + 请求级推理档位(同 messages 跑 low 与 max 不互相命中),多模态 content 先摘要再 hash(防毒化);可 per-call 绕过(科研重采样) |
 | 流式看门狗 | TTFT / inter-token / 总超时三层活性;thinking token 刷活性不计结果;截断流(缺 `[DONE]`)判瞬时不入缓存 |
-| 推理可观测性 | "这次到底推理没推理"由多信号裁定(推理正文压倒 usage 明细),三态落在 `LLMResponse.thinking_observation`:`observed` / `absent` / `unknown`——**`unknown` 是"本次判不出",不是"没推理"**;请求方向与实测观测矛盾时按 `(模型, 方向)` 各告警一次(能力表过期、开启未生效、注入了却观测不到);裁定结果随遥测落库 |
+| 推理可观测性 | "这次到底推理没推理"由多信号裁定(推理正文压倒 usage 明细),三态落在 `LLMResponse.thinking_observation`:`observed` / `absent` / `unknown`——**`unknown` 是"本次判不出",不是"没推理"**;本次实发档位与实测观测矛盾时按 `(源, 模型, 生效档位)` 各告警一次(能力表过期、开启未生效、注入了却观测不到;同一模型的 low 与 max 是两个独立的矛盾,不共用节流键);裁定结果随遥测落库 |
+| 推理档位 | 推理是**八档**(`none`/`auto`/`minimal`/`low`/`medium`/`high`/`xhigh`/`max`)而非开关:源级 `REASONING_EFFORT` + 请求级 `chat(reasoning_effort=...)`,`ENABLE_THINKING` 保留为语法糖;库带 24 条能力表(逐条 evidence 自报实测/文档推定),档位打空**默认报错并给出该模型最省的可用档与该配的键**,要静默映射需显式配 `EFFORT_FALLBACK=nearest`;实发档随 `LLMResponse.applied_effort` 与遥测落库 |
 | 遥测与成本 | 每次调用(含缓存命中与失败)必录 26 字段;SQLite / Postgres 后端(表已存在时**不需要** schema 建表权限,最小权限账号可直接用);按价格表折算成本落库(注意 `LLMResponse.cost` 本身恒为 `None`,成本只进遥测);多模态内容摘要落库不存原图 |
 | 遥测的资源与降级 | Postgres 池**闲时占 0 条连接**、忙时上限可配(`PGW_TELEMETRY_PG_POOL_MAX`,缺省 4),每次写入有硬预算(`PGW_TELEMETRY_PG_WRITE_TIMEOUT_S`,缺省 5s);后端不可用是**可恢复的降级**(冷却 60s 后自动重试,DBA 建完表/放开权限即自愈),永久失能只留给 DSN 本身写错;降级状态可编程查询——`client.telemetry_status` 给出 `degraded`/`fatal`/`reason`/`dropped_rows` 等只读快照,不必再靠人工对账。**对账要同时看 `degraded` 与 `dropped_rows`**: 池饱和超预算丢的行走行级丢弃,`degraded` 保持 `False`(后端没挂,是本进程并发超了),只按 `degraded` 告警会看不见这一类丢行——而它恰是 `pool_max` 配小了的唯一信号 |
 | 调用方维度 | 每次调用可带 `tenant_id`(遥测表的真实列,可挂 RLS、可建复合索引)与 `meta`(≤16 个自定义 KV);四个公共方法全覆盖,校验超限即报错;**库只交付列,不启用 RLS、不建索引** |
@@ -402,7 +403,7 @@ SQLite 侧**不建议**对着一个大库文件跑 `DELETE` + `VACUUM`,而应**
 
 | 键形态 | 作用 |
 |---|---|
-| `{SCOPE}__{PROVIDER}__{N}__{FIELD}` | 第 N 个源;FIELD **全集** = BASE_URL/API_KEY/MODEL/TIMEOUT_S/MAX_CONCURRENCY/RPM/TPM/EST_TOKENS/TTFT_TIMEOUT_S/INTER_TOKEN_TIMEOUT_S/ENABLE_THINKING/MISSING_DONE/TRUST_ENV/EXTRA_BODY(表外的 FIELD 直接报错) |
+| `{SCOPE}__{PROVIDER}__{N}__{FIELD}` | 第 N 个源;FIELD **全集** = BASE_URL/API_KEY/MODEL/TIMEOUT_S/MAX_CONCURRENCY/RPM/TPM/EST_TOKENS/TTFT_TIMEOUT_S/INTER_TOKEN_TIMEOUT_S/ENABLE_THINKING/REASONING_EFFORT/EFFORT_FALLBACK/MISSING_DONE/TRUST_ENV/EXTRA_BODY(表外的 FIELD 直接报错) |
 | `{SCOPE}__GLOBAL__*` | scope 级全局限额(跨源并发/RPM/TPM) |
 | `{SCOPE}__RETRY__*` / `BREAKER__*` / `BACKPRESSURE__*` / `SELECTOR` / `QUOTA_FULL` / `CIRCUIT_OPEN` | per-scope 韧性参数;缺省回落平铺键(`LLM_MAX_RETRIES` 等,兼容旧项目习惯) |
 | `{SCOPE}__BATCH_SIZE` / `NORMALIZE` / `EXPECTED_DIM` | 仅 `EmbeddingClient` 消费;`BATCH_SIZE` 必填(分批是行为关键,不设默认) |