fix: address completion verdict review findings

- fidelity cacheability also requires a non-empty projected body, so
  think-tag-only answers are no longer cached
- a no-argument tool sent with arguments null only is a deterministic
  dialect: ResultInvalid tool_arguments_null instead of retried
- text mode treats choice index null as 0 and no longer lets False pose
  as 0
- null-only tool_calls elements no longer produce an empty tool_calls
  list; non-stream fidelity checks role before the verdict; warning
  paths are length-bounded
- docs: ARCHITECTURE 7.8 field counts, README cache/watchdog wording,
  CHANGELOG notes, review record in the design, hook note in the plan

Red: 8 new tests failed before this change (e.g.
test_openai_cacheable_requires_projected_body,
test_null_arguments_tool_is_result_invalid_stream,
test_text_mode_choice_index_null_is_zero[None-True]).
This commit is contained in:
2026-10-15 00:22:07 -04:00
parent 31942f55f1
commit abcdf6930e
12 changed files with 179 additions and 27 deletions
@@ -17,7 +17,7 @@ date: 2026-10-14
## 0. 执行纪律
- 分支 `fix/issue30-31-completion-verdict`。每个任务一次提交,经 `commit` skill;pre-commit 钩子会跑全套件 + ruff + "改动触及函数复杂度 < C",故**每个提交点必须全绿**,改到的既有高复杂度函数(`add_chunk` F42、`_complete_stream`/`_complete_once` C、`_rehydrate` C、`OpenAIChatCompletion.__post_init__` D)须在同一提交内拆到 B 及以下;钩子按 radon 全部块判定,**类块**(`ChatCompletionAccumulator` C16、`OpenAIChatCompletion` D24)同样须降到 B 及以下。不改 `OpenAICompatTransport.complete()`(C14),新增逻辑一律放在拆出的 helper 中。
- 分支 `fix/issue30-31-completion-verdict`。每个任务一次提交,经 `commit` skill;pre-commit 钩子会跑全套件 + ruff + "改动触及函数复杂度 < C",故**每个提交点必须全绿**,改到的既有高复杂度函数(`add_chunk` F42、`_complete_stream`/`_complete_once` C、`_rehydrate` C、`OpenAIChatCompletion.__post_init__` D)须在同一提交内拆到 B 及以下;钩子(2026-10-14 经人类同意改为只拦"本次改动触及"的块,存量 ≥C 降为告警,提交 5d2ad40)按 radon 块判定,**类块**(`ChatCompletionAccumulator` C16、`OpenAIChatCompletion` D24)同样须降到 B 及以下。不改 `OpenAICompatTransport.complete()`(C14),新增逻辑一律放在拆出的 helper 中。
- 每个任务的统一验证(与钩子一致): `conda run -n PolyGateway pytest tests/ -q`(含 integration,本地有 Redis/PG 时真跑)+ `conda run -n PolyGateway ruff check src` + `conda run -n PolyGateway radon cc -n C <本任务改动文件>`(输出必须为空,或仅含本任务未触及的存量块)。各任务列出的子集命令只作开发期快速回路。
- 测试结果门: 每个任务的新增/改写测试先在未改实现的代码上运行并记录**失败**输出(粘贴进提交说明正文的"Red:"一行,写明失败用例名与断言),再实现至通过。
- 后台长跑命令末尾禁止接管道(CLAUDE.md §3)。