lili 8038109ce8 feat(cheap-worker): 同游戏双驱动 play 编排 + auto-vs-golden 批跑(M2 U2) ...

run_pair_dual_sync:同一份 staged src/ 上先自动 spec(ensure_play_spec)、后金标
(inject_golden)各 play 一次,取两组逐门 verdict——隔离生成方差、只暴露驱动器差。
编排序 gen-only→smoke→断言 staged 无残留 spec→ensure→play(auto)→inject→play
(golden);auto_gates 在金标注入前捕获。run_batch 端口池+线程前台有界并发(≤15
夹取、复用 bake_off._clamp_conc)、报告 auto-vs-golden-<idx>.json 不覆盖。
mock 编排单测(调用序 + auto 先于 golden + no-spec 守卫)20/20 全绿。

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

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

..

fixtures/golden-specs

feat(cheap-worker): U1 三品类金标 play-spec fixtures

2026-06-26 10:43:39 -07:00

tests

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

_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

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

bake_off.py

feat(cheap-worker): bake-off 达标门改质量口径 + 编排未收敛单列(M1 U3 收口)

2026-06-27 07:30:53 -07:00

cheap_roles.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

cheap_run.py

feat(cheap-worker): 自动 play-spec 加厚到金标同质 + 防自证(M1 U2)

2026-06-27 04:40:04 -07:00

cheap_studio.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

cheap_toolkit.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

compare_node.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

requirements.txt

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