Pin backend to the final-turn result checks #138

Merged
weichen merged 7 commits from feature/agent-harness-p2 into main 2026-10-01 14:00:59 +00:00
Owner

feature/agent-harness-p2 任务卡

任务主记录:https://git-home.u1680832.nyat.app:30319/weichen/Agent-System-Dev/pulls/138 ;状态:进行中;owner:weichen

基线与授权

  • 权威仓:ssh://git@git-ssh.u1680832.nyat.app:31411/weichen/Agent-System-Dev.git;目标分支:main;R0(initial_base_sha)= d02fa9c20a
  • 工作区:/home/weichen/projects/Agent-System-Dev-wt-feature-agent-harness-p2(worktree);分支:feature/agent-harness-p2
  • 授权与交付终点:实现 P2 结果把控。允许改 Agent-System-Backend,并在 feature/agent-harness-p2 上提 PR;Dev 仓只推进 modules/backend 并提 PR。未授权:合入 main、改 agent-native 内核、改小队路径、改 SubLLMRunner、做工作流执行器。
  • 启动自检(2026-10-01T13:44Z):make precheck verdict READY。head=d02fa9c20a,origin/main 同步,树干净,linked worktrees=0。必读 core/baseline.md、workflows/delivery.md §1 已读。

目标与非目标

  • 目标:直连终轮在 deliverableGate 之后做确定性检查(工件存在且非空;md/txt/docx 走 quality,lint error 或评分不过即不通过),再由不带工具的验证器输出 {passed, reason, nextAction}。出错或无法解析判不通过并给 Notice。计划和待办连续 3 个工具轮未更新时提醒一次,每 run 最多 3 次,不落库。
  • 非目标:不改 agent-native;不改小队路径和 SubLLMRunner;不做工作流执行器。runtime.verify 缺省读取为 false,生产默认 true。

同步记录

节点 sync_base_sha tested_head_sha checked_at
启动 d02fa9c20a d02fa9c20a 2026-10-01T13:45:07Z
同步前验收 d02fa9c20a f9d7bbe9f2 2026-10-01T13:54:53Z

结果与验证

  • 结果:直连终轮在 deliverableGate 之后检查本轮工件(存在、非空;md/txt/docx 走 quality.ScoreBytes),再由不带工具的验证器给出 {passed, reason, nextAction}。验证器出错或无法解析时不再续跑主模型,并附 Notice「本轮回复未通过独立验证(验证器不可用)」。计划和待办连续 3 个工具轮未更新提醒一次,每 run 最多 3 次,不落库。Backend a3ae1b9。Dev 只推进 modules/backend 到该提交。三处 agent-native 仍为 a34689c(Dev deps/agent-native、backend deps/agent-native、agent-squad deps/agent-native)。
  • 验证:见下方三段输出。make test 退出码 0(boundaries、core、backend、frontend vitest 51、ui vitest 71、agent-command)。
  • 影响与剩余项:runtime.verify 默认开启,每个终轮多一次轻量模型调用,可用该设置关闭。普通问答也会被「拿不准判不通过」,最多续跑 3 次。Backend PR https://git-home.u1680832.nyat.app:30319/weichen/Agent-System-Backend/pulls/44 与 Dev PR https://git-home.u1680832.nyat.app:30319/weichen/Agent-System-Dev/pulls/138 均未合入。小队路径与 SubLLMRunner 未改。

precheck

[repo]   branch=main head=d02fa9c20a
[remote] origin/main=d02fa9c20a ahead=0 behind=0
[tree]   clean submodules_drift=0 uninit=0
[worktrees] linked=0
[recycle] merged un-recycled branches: feature/card-close-20261001-124542Z feature/card-close-20261001-134217Z feature/card-close-base-extension-roadmap
[required-reading] core/baseline.md, workflows/delivery.md §1
[R0] d02fa9c20a(完整:d02fa9c20a594da287983d8edd47156ddbd49e01)
[verdict] READY — 可建任务工作区:make task-start NAME=feature/your-branch

task-sync

Already up to date.
[synced] sync_base=d02fa9c20a tested_head=f9d7bbe9f2 checked_at=2026-10-01T13:54:53Z
[next] 跑正式验收(make test 等),证据写入任务卡

make test

bash scripts/lint-boundaries.sh
boundaries ok
cd modules/core && go test ./...
ok  	agent-system-core	0.002s
cd modules/backend && go test ./...
(各包 ok,含 internal/runtime、internal/quality、internal/server)
cd modules/frontend && npm ci && npx vitest run
 Test Files  9 passed (9)
      Tests  51 passed (51)
cd modules/ui && npm ci && npx tsc --noEmit && npx vitest run
 Test Files  11 passed (11)
      Tests  71 passed (71)
cd deps/agent-command && go vet ./... && go test -count=1 ./...
ok  	agent-command	0.002s
ok  	agent-command/conformance	0.002s
# feature/agent-harness-p2 任务卡 任务主记录:https://git-home.u1680832.nyat.app:30319/weichen/Agent-System-Dev/pulls/138 ;状态:进行中;owner:weichen ## 基线与授权 - 权威仓:ssh://git@git-ssh.u1680832.nyat.app:31411/weichen/Agent-System-Dev.git;目标分支:main;R0(initial_base_sha)= d02fa9c20a594da287983d8edd47156ddbd49e01 - 工作区:/home/weichen/projects/Agent-System-Dev-wt-feature-agent-harness-p2(worktree);分支:feature/agent-harness-p2 - 授权与交付终点:实现 P2 结果把控。允许改 Agent-System-Backend,并在 `feature/agent-harness-p2` 上提 PR;Dev 仓只推进 `modules/backend` 并提 PR。未授权:合入 main、改 agent-native 内核、改小队路径、改 SubLLMRunner、做工作流执行器。 - 启动自检(2026-10-01T13:44Z):`make precheck` verdict READY。head=d02fa9c20a,origin/main 同步,树干净,linked worktrees=0。必读 core/baseline.md、workflows/delivery.md §1 已读。 ## 目标与非目标 - 目标:直连终轮在 `deliverableGate` 之后做确定性检查(工件存在且非空;md/txt/docx 走 quality,lint error 或评分不过即不通过),再由不带工具的验证器输出 `{passed, reason, nextAction}`。出错或无法解析判不通过并给 Notice。计划和待办连续 3 个工具轮未更新时提醒一次,每 run 最多 3 次,不落库。 - 非目标:不改 agent-native;不改小队路径和 SubLLMRunner;不做工作流执行器。`runtime.verify` 缺省读取为 false,生产默认 true。 ## 同步记录 | 节点 | sync_base_sha | tested_head_sha | checked_at | |---|---|---|---| | 启动 | d02fa9c20a594da287983d8edd47156ddbd49e01 | d02fa9c20a594da287983d8edd47156ddbd49e01 | 2026-10-01T13:45:07Z | | 同步前验收 | d02fa9c20a594da287983d8edd47156ddbd49e01 | f9d7bbe9f2cb4ccc3966faf3d3d7c2949dffcbc6 | 2026-10-01T13:54:53Z | ## 结果与验证 - 结果:直连终轮在 `deliverableGate` 之后检查本轮工件(存在、非空;md/txt/docx 走 `quality.ScoreBytes`),再由不带工具的验证器给出 `{passed, reason, nextAction}`。验证器出错或无法解析时不再续跑主模型,并附 Notice「本轮回复未通过独立验证(验证器不可用)」。计划和待办连续 3 个工具轮未更新提醒一次,每 run 最多 3 次,不落库。Backend `a3ae1b9`。Dev 只推进 `modules/backend` 到该提交。三处 agent-native 仍为 `a34689c`(Dev `deps/agent-native`、backend `deps/agent-native`、agent-squad `deps/agent-native`)。 - 验证:见下方三段输出。`make test` 退出码 0(boundaries、core、backend、frontend vitest 51、ui vitest 71、agent-command)。 - 影响与剩余项:`runtime.verify` 默认开启,每个终轮多一次轻量模型调用,可用该设置关闭。普通问答也会被「拿不准判不通过」,最多续跑 3 次。Backend PR https://git-home.u1680832.nyat.app:30319/weichen/Agent-System-Backend/pulls/44 与 Dev PR https://git-home.u1680832.nyat.app:30319/weichen/Agent-System-Dev/pulls/138 均未合入。小队路径与 SubLLMRunner 未改。 ### precheck ``` [repo] branch=main head=d02fa9c20a [remote] origin/main=d02fa9c20a ahead=0 behind=0 [tree] clean submodules_drift=0 uninit=0 [worktrees] linked=0 [recycle] merged un-recycled branches: feature/card-close-20261001-124542Z feature/card-close-20261001-134217Z feature/card-close-base-extension-roadmap [required-reading] core/baseline.md, workflows/delivery.md §1 [R0] d02fa9c20a(完整:d02fa9c20a594da287983d8edd47156ddbd49e01) [verdict] READY — 可建任务工作区:make task-start NAME=feature/your-branch ``` ### task-sync ``` Already up to date. [synced] sync_base=d02fa9c20a tested_head=f9d7bbe9f2 checked_at=2026-10-01T13:54:53Z [next] 跑正式验收(make test 等),证据写入任务卡 ``` ### make test ``` bash scripts/lint-boundaries.sh boundaries ok cd modules/core && go test ./... ok agent-system-core 0.002s cd modules/backend && go test ./... (各包 ok,含 internal/runtime、internal/quality、internal/server) cd modules/frontend && npm ci && npx vitest run Test Files 9 passed (9) Tests 51 passed (51) cd modules/ui && npm ci && npx tsc --noEmit && npx vitest run Test Files 11 passed (11) Tests 71 passed (71) cd deps/agent-command && go vet ./... && go test -count=1 ./... ok agent-command 0.002s ok agent-command/conformance 0.002s ```
weichen added 5 commits 2026-10-01 13:55:33 +00:00
Why: The harness P2 task needs an explicit write scope before backend edits: direct-path checks and a fail-closed verifier, with PRs as the endpoint.
Evidence: make precheck verdict READY at d02fa9c20a; required reading baseline.md and delivery.md section 1.
Impact: No code change. Backend, squad, and kernel behavior stay as on main until the implementation commits.
Refs: feature/agent-harness-p2
Co-authored-by: Cursor <cursoragent@cursor.com>
Why: Direct runs now check artifacts and run a fail-closed verifier before they stop. The Dev checkout has to build that backend.
Evidence: Backend a3ae1b9; go test ./... passed in that checkout. agent-native gitlinks stay a34689c.
Impact: Only modules/backend moves. Squad and the three agent-native pins stay put.
Refs: feature/agent-harness-p2
Co-authored-by: Cursor <cursoragent@cursor.com>
Record the harness P2 verification on the task card
ci / test (pull_request) Failing after 1m57s
2af7e07164
Why: Acceptance needs the precheck, task-sync, and make test output on the task card before the pull requests.
Evidence: task-sync sync_base=d02fa9c20a tested_head=f9d7bbe9f2. make test exited 0.
Impact: Documentation only. No further code change.
Refs: feature/agent-harness-p2
Co-authored-by: Cursor <cursoragent@cursor.com>
weichen added 1 commit 2026-10-01 13:55:48 +00:00
Record the harness pull requests on the task card
ci / test (pull_request) Failing after 1m58s
9df951323a
Why: The task card is the PR description, and it needs the Backend and Dev pull request links.
Evidence: Backend pull request 44 and Dev pull request 138 are open. Neither is merged.
Impact: Documentation only.
Refs: feature/agent-harness-p2
Co-authored-by: Cursor <cursoragent@cursor.com>
weichen added 1 commit 2026-10-01 14:00:52 +00:00
Record the sync checkpoint
ci / test (pull_request) Failing after 1m30s
7244f8c730
weichen merged commit 1939d50a7f into main 2026-10-01 14:00:59 +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#138