lili 2f51439c55 feat(genre): 品类 rubric 喂 LLM 验证 agent 接线 + 解谜金标 play-spec(W-GENRE 品类件④) ...

cheap_verify 品类扩展接线(全 additive):load_genre_checklist 读 fixtures/genre-rubrics/<genre>.json(缺失/坏 JSON 退化为空,best-effort 绝不抛);同一次 judge 调用并入品类条目(规范四:每款一次评分),输出独立 genreHits/genreGroups 分组小计(规范二:分母与通用底座分开、不混合平均);genre=None 时 judge prompt 与解析输出与既有版本逐字节/逐键一致(锚定纪律,单测锁死)。run_studio 加 genre 透传(缺省 None=原行为);rubric 仍纯 LLM 非阻塞、不进 verdict/九门/达标判定;service driver 路不动(genre 路由进服务请求时再接)。

解谜金标 play-spec fixtures/golden-specs/puzzle.play-spec.json:tap-targets occupied 反应族 + score 递增断言 + expectLatch,只依赖 forensics 契约不绑定坐标(formalize p11b-tmpl 已验证过的 occupied spec);test_golden_specs 品类集同步加 puzzle(金标机器门)。

验证:test_genre_puzzle_assets 6 项全过(含 prompt 逐字节恒等/分组小计分母/漏答 genreChecks 兜底)、test_golden_specs 6/6、test_cheap_verify 14/14 零回归;test_roles 10/12 与 test_studio_smoke 0/4 为基线既有失败(主仓同状态,与本改动无关)。

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

2026-07-02 22:36:15 -07:00

..

test_a11_m1.py

feat(studio): A11 切片三 M1 前置基座 + M2 worker 判意图

2026-06-29 01:04:55 -07:00

test_a11_m2_classify.py

feat(studio): A11 切片三 M1 前置基座 + M2 worker 判意图

2026-06-29 01:04:55 -07:00

test_a11_m3_deterministic.py

feat(studio): A11 切片三 M5 三结构断言机器门(改对了没/有没有误伤/血缘可查)

2026-06-29 02:34:06 -07:00

test_a11_m4_regenerate.py

feat(studio): A11 切片三 M5 三结构断言机器门(改对了没/有没有误伤/血缘可查)

2026-06-29 02:34:06 -07:00

test_a11_m5_assertions.py

feat(studio): A11 切片三 M5 三结构断言机器门(改对了没/有没有误伤/血缘可查)

2026-06-29 02:34:06 -07:00

test_auto_vs_golden.py

feat(cheap-worker): 同游戏双驱动 play 编排 + auto-vs-golden 批跑(M2 U2)

2026-06-27 08:47:13 -07:00

test_bake_off.py

feat(cheap-worker): 便宜档生成丰富度 + M1 达标门富化重验(切片一 A/B)

2026-06-30 01:39:06 -07:00

test_bootstrap.py

feat(cheap-worker): 便宜档 Node→Python 重写进 AgentScope spike — 范式可移植坐实

2026-06-26 02:42:14 -07:00

test_budget_gate.py

feat(cheap-worker): 便宜档预算闸 <¥10 fail-closed 接线 + 成本落盘(M1 U4)

2026-06-27 02:01:20 -07:00

test_cheap_gates.py

fix(cheap): 阶段一② 终审 merge-before(红线③ unlink×2 防陈旧 verdict 假绿 + setup fail-fast + acquire_ports to_thread + 死码/ReplyEndEvent canary/restricted fail-closed) (切片一 阶段一②/终审fix)

2026-07-02 13:34:57 -07:00

test_cheap_service_app.py

fix(cheap): 阶段一② 终审 merge-before(红线③ unlink×2 防陈旧 verdict 假绿 + setup fail-fast + acquire_ports to_thread + 死码/ReplyEndEvent canary/restricted fail-closed) (切片一 阶段一②/终审fix)

2026-07-02 13:34:57 -07:00

test_cheap_service_driver.py

fix(cheap): 阶段一② 终审 merge-before(红线③ unlink×2 防陈旧 verdict 假绿 + setup fail-fast + acquire_ports to_thread + 死码/ReplyEndEvent canary/restricted fail-closed) (切片一 阶段一②/终审fix)

2026-07-02 13:34:57 -07:00

test_cheap_trace.py

feat(cheap-worker): 便宜档生成丰富度 + M1 达标门富化重验(切片一 A/B)

2026-06-30 01:39:06 -07:00

test_cheap_verify.py

feat(cheap): rubric v2 评分尺 8→11 条 + L2/L3/L4 三分组小计落库(质量模型 §3.3 计分制·前置小工单)

2026-07-02 19:58:20 -07:00

test_compare_multi.py

feat(cheap-worker): compare_node 加有界并发(端口池+线程,可选)

2026-06-26 11:00:00 -07:00

test_compare.py

feat(cheap-worker): 便宜档 Node→Python 重写进 AgentScope spike — 范式可移植坐实

2026-06-26 02:42:14 -07:00

test_dedup.py

feat(cheap-worker): M3b 本机 U1-U3 — 9d trace parity 救活 D11 + D9 vendored + 跨语言反假绿门(切片一 M3b)

2026-06-28 02:17:41 -07:00

test_ensure_play_spec.py

fix(WU-C 5.4): tap-targets harness 认单数/可空 target — 解 M2 Node 退役阻塞

2026-06-27 10:41:16 -07:00

test_genre_puzzle_assets.py

feat(genre): 品类 rubric 喂 LLM 验证 agent 接线 + 解谜金标 play-spec(W-GENRE 品类件④)

2026-07-02 22:36:15 -07:00

test_golden_specs.py

feat(genre): 品类 rubric 喂 LLM 验证 agent 接线 + 解谜金标 play-spec(W-GENRE 品类件④)

2026-07-02 22:36:15 -07:00

test_repair_middleware_spike.py

feat(cheap-worker): 续修 middleware 机制 spike 坐实(拦 finish+注入+续跑)(切片一 阶段一前置)

2026-07-01 05:22:49 -07:00

test_result_out.py

feat(cheap-worker): M3b 本机 U1-U3 — 9d trace parity 救活 D11 + D9 vendored + 跨语言反假绿门(切片一 M3b)

2026-06-28 02:17:41 -07:00

test_roles.py

feat(cheap-worker): 便宜档生成丰富度 + M1 达标门富化重验(切片一 A/B)

2026-06-30 01:39:06 -07:00

test_run.py

feat(cheap-worker): 便宜档 Node→Python 重写进 AgentScope spike — 范式可移植坐实

2026-06-26 02:42:14 -07:00

test_studio_smoke.py

feat(cheap-worker): 便宜档 Node→Python 重写进 AgentScope spike — 范式可移植坐实

2026-06-26 02:42:14 -07:00

test_toolkit.py

feat(cheap-gen): 阶段一B #5 drawButton 改返命中矩形(黄金首件·治 #1 翻车点根因)

2026-06-30 01:39:05 -07:00

test_trace_source.py

feat(cheap-worker): M3b 本机 U1-U3 — 9d trace parity 救活 D11 + D9 vendored + 跨语言反假绿门(切片一 M3b)

2026-06-28 02:17:41 -07:00

test_worker_service.py

feat(cheap-worker): M3b 本机 U1-U3 — 9d trace parity 救活 D11 + D9 vendored + 跨语言反假绿门(切片一 M3b)

2026-06-28 02:17:41 -07:00