docs: register the design and plan in the wiki, with what got rejected

The entity pages carry the rejected alternatives and why, so the next
reader does not have to reconstruct the argument: minimal patch cannot
fill a tier that does not exist, cherry's wire DSL buys four endpoint
protocols we do not have, and default_effort lost its only consumer the
moment enable_thinking=True became Effort.AUTO.
This commit is contained in:
2026-09-05 00:12:55 -04:00
parent abeb09f588
commit e01420178f
5 changed files with 59 additions and 3 deletions
+15
View File
@@ -0,0 +1,15 @@
---
type: plan
node_id: plan:reasoning-effort
title: "实现计划: 推理档位一等化"
date: 2026-09-05
---
# 实现计划: 推理档位一等化
正文: `2026-09-04-reasoning-effort.md`(378 行,10 任务)。实现 `design:reasoning-effort`
- **拆分逻辑**: T1(`Effort` 词汇 + 能力表)与 T2(`ThinkingWire` + 8 段 provider 表)可并行 → T3(五道关卡 + nearest 映射)→ T4(源级 env 入口)→ T5(请求级入口与优先级)→ T6(缓存 key 两处)/T7(遥测第 26 列)→ T8(transport 接线与告警节流)→ T9(CHANGELOG/wiki/1.4.0)→ T10(经 new-api 逐模型实测,标 `slow`)。
- **T10 单列的理由**: 人类定「能力表数据统一自己经 new-api 实测」。T1 落的是文档推定值(四方交叉: 官方文档/OpenRouter/cherry-studio/LiteLLM),不实测则整张表都是假设——LiteLLM 里同一个 kimi-k3 在 `moonshot/` 下三档、`perplexity/` 下六档,中转改档位有第三方证据。
- **执行方式**: 直接按计划实现,**不派** `subagent-driven-development`——10 个任务共享 `Effort`/`ThinkingCapability`/`ThinkingWire` 三个类型,独立上下文的 subagent 容易在签名上分叉。
- **保真校验**: 不适用(`thinking.py` 系库自研,非 `reference/` 移植蓝本;且三项目当前不在工作区)。