E3 evidence gate: estimate marking + second fact-check round (pin bd687d2) #311

Merged
weichen merged 6 commits from feature/agent-e3-evidence-gate into main 2026-10-10 16:38:09 +00:00
Owner

E3 增量(提案 §5,Backend #130):标注感知豁免(分句判定)+ 两轮修正(变化才二拦)+ base.deliverables v6 数字溯源规则 + 子代理引用格式 + eval 新增 unmarked 口径。

Evidence: make test 全绿(收据);eval/live 前后对照:未核实数字 12→5(未标注仅 3)、工具调用 93→63、时长 916s→787s;报告 .task/e3-eval/after-e3.json;Backend CI success(GATE)。

任务卡:feature/agent-e3-evidence-gate

E3 增量(提案 §5,Backend #130):标注感知豁免(分句判定)+ 两轮修正(变化才二拦)+ base.deliverables v6 数字溯源规则 + 子代理引用格式 + eval 新增 unmarked 口径。 Evidence: make test 全绿(收据);eval/live 前后对照:未核实数字 12→5(未标注仅 3)、工具调用 93→63、时长 916s→787s;报告 .task/e3-eval/after-e3.json;Backend CI success(GATE)。 任务卡:feature/agent-e3-evidence-gate
weichen added 5 commits 2026-10-10 16:28:42 +00:00
Why: establish the authorized task workspace and its initial baseline.

Evidence: preserved precheck receipt in .task/feature-agent-e3-evidence-gate.md; R0=104a4142c918f7325d3a78e3e6e270e46739baea.

Impact: task metadata only; the feature workspace starts at 104a4142c9.

Refs: .task/feature-agent-e3-evidence-gate.md
Record the sync checkpoint
ci / test (pull_request) Successful in 3m27s
f6ec1fed96
Why: bind the task validation checkpoint to the latest integration baseline.

Evidence: SELF recursive component checks; sync_base=104a4142c918f7325d3a78e3e6e270e46739baea; candidate=c87a14e9e4c033ba1f689090a4475c43fdd2b62f.

Impact: task metadata only.

Refs: .task/feature-agent-e3-evidence-gate.md
weichen added 1 commit 2026-10-10 16:28:51 +00:00
Fill the task record PR link
ci / test (pull_request) Successful in 5m46s
73a07959af
weichen merged commit 90c44fc149 into main 2026-10-10 16:38:09 +00:00
Sign in to join this conversation.
No Reviewers
No labels
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: weichen/Agent-System-Dev#311