Kevin 78b61c076e feat(eval): Playground GLM 评分落库并可恢复 ...

在 conversations 表增加 playground_conversation_judge_json，流式/非流式对话评审结束后写入最近一次快照（整体分、逐轮分、对比文案、错误与基线文件名等）。新增只读 GET 供前端按会话拉取；评测台 Playground 切换会话时自动恢复，并提示基线是否和当时一致。

2026-04-08 16:51:08 +08:00

..

importers

feat/ eval

2026-04-06 23:19:20 +08:00

rubrics

feat: 回忆录证据血缘与内部评测可追溯，顺带对齐本地评测台与 CI

2026-04-08 15:37:09 +08:00

__init__.py

feat/ 导出开发容器内的数据用于评估

2026-04-03 14:44:46 +08:00

admin_service.py

feat(evaluation): session catalog, user export import, and eval web UI

2026-04-06 13:49:28 +08:00

candidate_runner.py

feat/ 导出开发容器内的数据用于评估

2026-04-03 14:44:46 +08:00

deps.py

feat(evaluation): memoir readiness, judge/replay updates, eval web playground

2026-04-08 09:43:34 +08:00

errors.py

feat/ 导出开发容器内的数据用于评估

2026-04-03 14:44:46 +08:00

eval_trace_format.py

feat: 回忆录证据血缘与内部评测可追溯，顺带对齐本地评测台与 CI

2026-04-08 15:37:09 +08:00

eval_trace_repo.py

feat: 回忆录证据血缘与内部评测可追溯，顺带对齐本地评测台与 CI

2026-04-08 15:37:09 +08:00

eval_trace_schemas.py

feat: 回忆录证据血缘与内部评测可追溯，顺带对齐本地评测台与 CI

2026-04-08 15:37:09 +08:00

eval_trace_service.py

feat: 回忆录证据血缘与内部评测可追溯，顺带对齐本地评测台与 CI

2026-04-08 15:37:09 +08:00

execution_service.py

feat: 回忆录证据血缘与内部评测可追溯，顺带对齐本地评测台与 CI

2026-04-08 15:37:09 +08:00

gate_report_service.py

feat/ 导出开发容器内的数据用于评估

2026-04-03 14:44:46 +08:00

gating_service.py

feat/ 导出开发容器内的数据用于评估

2026-04-03 14:44:46 +08:00

internal_auth.py

feat/ 导出开发容器内的数据用于评估

2026-04-03 14:44:46 +08:00

judge_manual_service.py

feat(eval): Playground GLM 评分落库并可恢复

2026-04-08 16:51:08 +08:00

judge_schemas.py

feat(evaluation): memoir readiness, judge/replay updates, eval web playground

2026-04-08 09:43:34 +08:00

judge_service.py

feat: 回忆录证据血缘与内部评测可追溯，顺带对齐本地评测台与 CI

2026-04-08 15:37:09 +08:00

memoir_readiness_service.py

feat(evaluation): memoir readiness, judge/replay updates, eval web playground

2026-04-08 09:43:34 +08:00

models.py

feat/ 导出开发容器内的数据用于评估

2026-04-03 14:44:46 +08:00

presenters.py

feat(evaluation): session catalog, user export import, and eval web UI

2026-04-06 13:49:28 +08:00

replay_service.py

feat(evaluation): memoir readiness, judge/replay updates, eval web playground

2026-04-08 09:43:34 +08:00

repo.py

feat: 回忆录证据血缘与内部评测可追溯，顺带对齐本地评测台与 CI

2026-04-08 15:37:09 +08:00

router.py

feat(eval): Playground GLM 评分落库并可恢复

2026-04-08 16:51:08 +08:00

schemas.py

feat(eval): Playground GLM 评分落库并可恢复

2026-04-08 16:51:08 +08:00

session_catalog_repo.py

feat(evaluation): session catalog, user export import, and eval web UI

2026-04-06 13:49:28 +08:00

session_catalog_service.py

feat(eval): Playground GLM 评分落库并可恢复

2026-04-08 16:51:08 +08:00

stream_router.py

feat/ 导出开发容器内的数据用于评估

2026-04-03 14:44:46 +08:00

transcript_for_judge.py

feat(eval): internal-eval stack, judge fixes, and eval web overhaul

2026-04-07 17:18:47 +08:00

user_export_fixtures.py

feat(evaluation): session catalog, user export import, and eval web UI

2026-04-06 13:49:28 +08:00