lili 87777975c7 feat(w-axis): R1 生成可信闸代码收口(actor/judge闭合+W-GOLD-LIVE+full_gate+三批闸门) ...

actor/judge prompt eval 闭合: actor 3.0.5 正文强化+baseline(7轮); judge 3.0.14 正文强化+anyTerms同义词补全+baseline(judge-a 13轮/judge-b 33轮); registry/checker 版本对齐+顺序锚点 fail-closed 双保险
W-GOLD-LIVE live_prompt: play-loop 契约开口(request/3+provenance/3+ReferenceAssetRecord/1+Registry/1+迁移清单15条); cheap_verify 切v3+消费对账六闸(只消费active)+生成prompt注入接线(0 active不注入); Node runner playtest-v3.cdp.cjs 升/3+绊线恢复; 真模型回归验向后兼容
full_gate+三批基线: full_gate.py 集成runner串六子门+降级+22测; baseline_gates.py fresh25阈值+historical11预期表(2 needs_human交创始人定标)+shadow20框架+38测
注: registry cheap-system 登记 1.8.0→1.8.1 同步此前在途 cheap-system.md frontmatter 升版(修 pre-commit 版本漂移); cheap_verify/cheap_studio/validate/test_acceptance_v3/test_cheap_service_driver 为在途M含本会话叠加+此前W-AXIS在途(同一线无法hunk分离); 3红测试根因与raw审计未入本提交

2026-07-25 18:47:47 -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(cheap-gen): W-AXIS-V2 波1——测试 agent 生产化+三路统一验收编排器+字段迁移

2026-07-10 07:07:08 -07:00

test_a11_m4_regenerate.py

feat(cheap-gen): W-AXIS-V2 波1——测试 agent 生产化+三路统一验收编排器+字段迁移

2026-07-10 07:07:08 -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_acceptance_v2.py

feat(cheap-gen): W-AXIS-V2 波1——测试 agent 生产化+三路统一验收编排器+字段迁移

2026-07-10 07:07:08 -07:00

test_acceptance_v3.py

feat(w-axis): R1 生成可信闸代码收口(actor/judge闭合+W-GOLD-LIVE+full_gate+三批闸门)

2026-07-25 18:47:47 -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

fix(cheap): 收口采集重复打印幂等(工单 f)+ bake_off brief 全缺 fail-fast(工单 i)

2026-07-04 00:41:56 -07:00

test_baseline_gates.py

feat(w-axis): R1 生成可信闸代码收口(actor/judge闭合+W-GOLD-LIVE+full_gate+三批闸门)

2026-07-25 18:47:47 -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_brief_forensics.py

fix(cheap-gen): 死圈修复 fix③ brief 落 evidence/brief.json 供根因取证

2026-07-08 02:23:36 -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_budget_two_stage.py

feat(budget): T3 预算两段式统一(软停线 ¥10/¥50 只许收尾+RMB 硬地板 ×1.5 fail-closed 封上界+CLI/Service 同源工厂) (W-ARCH②,创始人 2026-07-03 裁决)

2026-07-03 14:15:59 -07:00

test_cheap_failure_layer.py

feat(cheap-gen): W-AXIS 波1 真相层——turns 全文落盘+per-run 归档+evidence 清单化+failureLayer

2026-07-10 04:27:17 -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_otlp_sink.py

feat(obs): 阶段四观测面二 Python 侧 token metric——llm_tokens{kind} + llm_cache_hit_rate

2026-07-05 23:57:40 -07:00

test_cheap_run_archive.py

feat(cheap-gen): W-AXIS 波1 真相层——turns 全文落盘+per-run 归档+evidence 清单化+failureLayer

2026-07-10 04:27:17 -07:00

test_cheap_service_app.py

feat(cheap-gen): W-AXIS 波1 真相层——turns 全文落盘+per-run 归档+evidence 清单化+failureLayer

2026-07-10 04:27:17 -07:00

test_cheap_service_driver.py

feat(w-axis): R1 生成可信闸代码收口(actor/judge闭合+W-GOLD-LIVE+full_gate+三批闸门)

2026-07-25 18:47:47 -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_turns_sink.py

feat(cheap-gen): W-AXIS 波1 真相层——turns 全文落盘+per-run 归档+evidence 清单化+failureLayer

2026-07-10 04:27:17 -07:00

test_cheap_verify.py

feat(quality): ⑨升通用底座第12条「核心操作非无脑」落 RICHNESS_CHECKLIST(L2 6→7,前11条一字不动,prompt 计数改动态 len 同源防漂)+ 测试分母随升;图说预算两段式「待实施/CLI仍hard」翻已落实态(cheap_budget 同源工厂+真M3实证) (质量SoT §4 规范一 12条口径,ba55508e 配套;金标复验=C波)

2026-07-03 14:51:36 -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_ctx_compress_patch.py

feat(cheap): T5 Service 壳合成终结事件(run 崩快失败,封 600s 慢失败出口)+ 压缩崩根因坐实与 fail-open 补丁

2026-07-03 14:21:34 -07:00

test_deadloop_fix_loop.py

test(cheap-gen): 死圈修复外科修复回路确定性集成测试(fix①-A × fix②-check 成环)

2026-07-08 02:28:51 -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_edit_file_toolkit.py

feat(cheap-gen): W-AXIS 波2 判定语义重置——独立模型玩法判定阻断+拆残笼+判定档切 M3

2026-07-10 04:27:18 -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_full_gate.py

feat(w-axis): R1 生成可信闸代码收口(actor/judge闭合+W-GOLD-LIVE+full_gate+三批闸门)

2026-07-25 18:47:47 -07:00

test_gameplay_judge.py

feat(cheap-gen): W-AXIS 波2 判定语义重置——独立模型玩法判定阻断+拆残笼+判定档切 M3

2026-07-10 04:27:18 -07:00

test_genre_puzzle_assets.py

feat(cheap-gen): W-AXIS-V2 波2——取证契约退役+提示全加载链清洗,四门∧测试员为唯一验收链

2026-07-10 09:21:04 -07:00

test_genre_route.py

feat(cheap): T4 生产 create 路 genre 最小路由(brief→五类确定性词表·先验序=特异性降序·无命中回退通用) (M3 cutover 放行检查单增补)

2026-07-03 14:17:54 -07:00

test_golden_specs.py

merge: W-GENRE 解谜品类四件套(skill puzzle-game-design + _template-puzzle 9/9 + _fewshot-puzzle 正例 + rubric fixture/金标 spec + 范例签名机器门)——品类路由并集 v1.4.0(剧情6/TRPG7/非遗8/解谜9)

2026-07-02 23:48:41 -07:00

test_kb_externalize.py

feat(cfg): W-CFG-KB K3 知识包治理接线——knowledge 配置块+激活发布 Nacos+worker 订阅热物化(复用阶段二三·默认关)

2026-07-05 22:50:10 -07:00

test_m3_stream_patch.py

fix(cheap): 封死 M3 400 流式 tool_calls 聚合炸弹——parallel_tool_calls=False 主防线 + 同 index 异 id 按 id 分桶兜底补丁 (fix400 A/B/C)

2026-07-02 21:09:44 -07:00

test_planning_team_tools_patch.py

feat(cheap): 便宜档 Service 收窄工具面——关 Planning/Team/Schedule 三组框架工具(工单 h)

2026-07-04 00:46:09 -07:00

test_play_spec_contract.py

feat(cheap): T1 驱动器约定收敛·C5 考卷契约接线(startRitual 起局仪式+driver 显式化+sourceHash 陈旧重生·金标 held-constant 不误杀) (W-S1 修复三单·单①)

2026-07-03 14:02:53 -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

fix(cheap-gen): new-api 额度耗尽真机探测揪出误判——401+「额度已用尽」修为 quota_exhausted

2026-07-08 07:52:57 -07:00

test_roles.py

feat(cheap-gen): W-AXIS-V2 波2——取证契约退役+提示全加载链清洗,四门∧测试员为唯一验收链

2026-07-10 09:21:04 -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_service_synthetic_reply_end.py

feat(cheap): T5 Service 壳合成终结事件(run 崩快失败,封 600s 慢失败出口)+ 压缩崩根因坐实与 fail-open 补丁

2026-07-03 14:21:34 -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_propagation.py

feat(cheap): 面四 Python 三跳 traceparent 打通——便宜档生成串成单条 trace 树(观测阶段四)

2026-07-05 20:30:04 -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): 面四 Python 三跳 traceparent 打通——便宜档生成串成单条 trace 树(观测阶段四)

2026-07-05 20:30:04 -07:00

test_ws_builtin_tools_patch.py

fix(cheap): Service 关 workspace 内建工具(Bash/Edit/Glob/Grep/Read/Write)——内建 Write/Bash 旁路六工具写白名单(护城河击穿)+ M3 12+工具面语义重叠混乱税(80009 死圈/80011 失败目录:Bash CWD 混乱/read_file 被串 Read 参数/Edit 连败,签名富化观测实证) (cutover S2 工具面封口)

2026-07-03 19:12:35 -07:00