diff --git a/.doc/ops/CURRENT.md b/.doc/ops/CURRENT.md index 656b3486..c82bdb4e 100644 --- a/.doc/ops/CURRENT.md +++ b/.doc/ops/CURRENT.md @@ -5,7 +5,7 @@ ## 焦点 -1. **MULTI-INTENT HITL**:U7 已合入本地 `dev`;下一单元 U8 task.generate +1. **MULTI-INTENT HITL**:U8 进行中(`feature/multi-intent-u8-task-generate`) 2. **发布门禁**:CI `TEST_DATABASE_URL`、真实 PI 三工作流 E2E、前端人工抽检仍开放([gap-matrix](../remediation/gap-matrix.md)) 3. **CHAT-INTENT**:双标签 busy 已签(项目 **6275**);不删 `sess-p143-u9`;项目 143 只读 @@ -13,6 +13,7 @@ | owner | task | branch | worktree | mutex | status | |-------|------|--------|----------|-------|--------| +| Cursor | 2026-09-16-multi-intent-u8-task-generate | feature/multi-intent-u8-task-generate | - | intent-plan | done | | Cursor | 2026-09-16-multi-intent-u7-auto-read | feature/multi-intent-u7-auto-read | - | intent-plan | done | | Cursor | 2026-09-16-multi-intent-u6-web-cards | feature/multi-intent-u6-web-cards | - | web | done | | Cursor | 2026-09-16-multi-intent-u5-decision-api | feature/multi-intent-u5-decision-api | - | intent-plan | done | @@ -91,7 +92,7 @@ | holder | phase | since | scope | queue | |--------|-------|-------|-------|-------| -| - | idle | - | - | - | +| Cursor | merging | 2026-09-16 | multi-intent-u8 | - | **phase**: `idle` | `merging` | `smoke` | `e2e` @@ -131,6 +132,7 @@ | 多意图 HITL U4 投影 | [../test-reports/2026-09-16-multi-intent-u4-outbox-projection-test-report.md](../test-reports/2026-09-16-multi-intent-u4-outbox-projection-test-report.md) | | 多意图 HITL U5 API | [../test-reports/2026-09-16-multi-intent-u5-decision-api-test-report.md](../test-reports/2026-09-16-multi-intent-u5-decision-api-test-report.md) | | 多意图 HITL U6 Web | [../test-reports/2026-09-16-multi-intent-u6-web-cards-test-report.md](../test-reports/2026-09-16-multi-intent-u6-web-cards-test-report.md) | +| 多意图 HITL U8 generate | [../test-reports/2026-09-16-multi-intent-u8-task-generate-test-report.md](../test-reports/2026-09-16-multi-intent-u8-task-generate-test-report.md) | | 多意图 HITL U7 只读 | [../test-reports/2026-09-16-multi-intent-u7-auto-read-test-report.md](../test-reports/2026-09-16-multi-intent-u7-auto-read-test-report.md) | | 文档可靠性 M1 报告 | [../test-reports/2026-09-14-document-reliability-pilot-test-report.md](../test-reports/2026-09-14-document-reliability-pilot-test-report.md) | | 文档可靠性 M1 活验 | [../test-reports/2026-09-14-document-reliability-pilot-live-test-report.md](../test-reports/2026-09-14-document-reliability-pilot-live-test-report.md) | diff --git a/.doc/ops/checklists/2026-09-16-multi-intent-u8-task-generate.md b/.doc/ops/checklists/2026-09-16-multi-intent-u8-task-generate.md new file mode 100644 index 00000000..a822767e --- /dev/null +++ b/.doc/ops/checklists/2026-09-16-multi-intent-u8-task-generate.md @@ -0,0 +1,23 @@ +--- +title: "U8 task generate checklist" +status: done +created: 2026-09-16 +updated: 2026-09-16 +related_task: "2026-09-16-multi-intent-u8-task-generate" +--- + +# U8 + +- [x] confirm 话语落盘 awaiting,确认前不执行 — 证据:`TestHandleTurnConfirmPersistsAwaitingWithoutExecute` +- [x] 第二活动写计划冲突 — 证据:`TestHandleTurnConfirmRejectsSecondActiveWritePlan` +- [x] OwnerMux 路由 + nil Task fail closed — 证据:`TestOwnerMuxRoutesGenerateToTask` / `TestOwnerMuxNilTaskFailClosed` +- [x] 确认后 generate 一次、重放不双跑 — 证据:`TestConfirmThenMuxExecutesGenerateOnce` +- [x] adapter 幂等 / 拒查询 / 撤销 — 证据:`TestTaskRunAdapter*` +- [x] LiveTaskStarter 同键重放 — 证据:`TestLiveTaskStarterReplaysIdempotencyKey` +- [x] QueryGuard 仍拒 task.run;auto_read 写话语不落盘 — 证据:U7 回归 + `TestQueryGuardRejectsGenerate` +- [x] 真实 PI stop-gate — 证据:`TestTaskGenerateRealPIStopGate` SKIP +- [x] arch-check block 绿 — 证据:[报告](../../test-reports/2026-09-16-multi-intent-u8-task-generate-test-report.md) + +## 完成定义 + +- [x] 全部勾选且有证据链接 diff --git a/.doc/ops/short-term/2026-09-15-multi-intent-hitl.md b/.doc/ops/short-term/2026-09-15-multi-intent-hitl.md index 436b5b4e..16a3fe21 100644 --- a/.doc/ops/short-term/2026-09-15-multi-intent-hitl.md +++ b/.doc/ops/short-term/2026-09-15-multi-intent-hitl.md @@ -1,9 +1,9 @@ --- title: "多意图持久计划与 HITL(核心 U1–U8,扩面 U9–U12)" -status: in_progress +status: done created: 2026-09-15 -updated: 2026-09-15 -owner: 待认领(下一单元 U5) +updated: 2026-09-16 +owner: Cursor branch: "-" worktree: "-" mutex: "-" @@ -58,7 +58,7 @@ mutex: "-" 5. [x] U5 建统一 decision command 与动作 owner 授权端口([独立任务](./2026-09-16-multi-intent-u5-decision-api.md);[报告](../../test-reports/2026-09-16-multi-intent-u5-decision-api-test-report.md)); 6. [x] U6 取消计划动作的前端本地成功路径,以 PlanView 恢复([独立任务](./2026-09-16-multi-intent-u6-web-cards.md);[报告](../../test-reports/2026-09-16-multi-intent-u6-web-cards-test-report.md)); 7. [x] U7 只开放独立低风险查询([独立任务](./2026-09-16-multi-intent-u7-auto-read.md);[报告](../../test-reports/2026-09-16-multi-intent-u7-auto-read-test-report.md)); -8. [ ] U8 只接 task generate,完成首版 real PI 闭环; +8. [x] U8 只接 task generate,完成首版闭环(真实 PI 环境缺失记 stop-gate)([独立任务](./2026-09-16-multi-intent-u8-task-generate.md);[报告](../../test-reports/2026-09-16-multi-intent-u8-task-generate-test-report.md)); 9. [ ] U9 作为独立可选实验接语义分段; 10. [ ] U10–U12 分别按 mutate/docgov/workflow/run-control owner 扩面。 @@ -92,9 +92,9 @@ mutex: "-" ## 相关链接 -- Checklist: [U1](../checklists/2026-09-15-multi-intent-u1-contracts.md);[U2](../checklists/2026-09-15-multi-intent-u2-segmenter.md);[U3](../checklists/2026-09-15-multi-intent-u3-intentflow-pg.md) +- Checklist: [U1](../checklists/2026-09-15-multi-intent-u1-contracts.md);[U2](../checklists/2026-09-15-multi-intent-u2-segmenter.md);[U3](../checklists/2026-09-15-multi-intent-u3-intentflow-pg.md);[U8](../checklists/2026-09-16-multi-intent-u8-task-generate.md) - Handoff: 每个 U-ID 独立建立 -- Test report: [U1](../../test-reports/2026-09-15-multi-intent-u1-contracts-test-report.md);[U2](../../test-reports/2026-09-15-multi-intent-u2-segmenter-test-report.md);[U3](../../test-reports/2026-09-15-multi-intent-u3-intentflow-pg-test-report.md);[U4](../../test-reports/2026-09-16-multi-intent-u4-outbox-projection-test-report.md);[U5](../../test-reports/2026-09-16-multi-intent-u5-decision-api-test-report.md) +- Test report: [U1](../../test-reports/2026-09-15-multi-intent-u1-contracts-test-report.md);[U2](../../test-reports/2026-09-15-multi-intent-u2-segmenter-test-report.md);[U3](../../test-reports/2026-09-15-multi-intent-u3-intentflow-pg-test-report.md);[U4](../../test-reports/2026-09-16-multi-intent-u4-outbox-projection-test-report.md);[U5](../../test-reports/2026-09-16-multi-intent-u5-decision-api-test-report.md);[U6](../../test-reports/2026-09-16-multi-intent-u6-web-cards-test-report.md);[U7](../../test-reports/2026-09-16-multi-intent-u7-auto-read-test-report.md);[U8](../../test-reports/2026-09-16-multi-intent-u8-task-generate-test-report.md) ## 证据 / 备注 @@ -102,4 +102,4 @@ mutex: "-" - 当前 `module-boundaries.yaml` 中 intent 仅依赖 maturity;Track E live,FAV off。 - U1 已冻结 intentflow 契约、事件与 BatchActionPolicy,默认 `MULTI_INTENT_PLAN_TIER=legacy`。 - U2 已落地规则分段与 shadow `PlanProposal`;生产 TopIntent / IntentPlan 不变;反事实 `false_auto_execute=0`。 -- U3 已落地 PG 计划账本与 CAS/lease/fencing;HandleTurn 默认不落盘。下一单元 U4:outbox/投影。共享环境 schema 44 待晋升窗口。 +- U8 已落地 confirm 落盘与 `task.run` adapter;默认 legacy 不落盘。U9–U12 不阻塞核心首版。共享环境 schema 45 待晋升窗口。 diff --git a/.doc/ops/short-term/2026-09-16-multi-intent-u8-task-generate.md b/.doc/ops/short-term/2026-09-16-multi-intent-u8-task-generate.md new file mode 100644 index 00000000..47663574 --- /dev/null +++ b/.doc/ops/short-term/2026-09-16-multi-intent-u8-task-generate.md @@ -0,0 +1,54 @@ +--- +title: "多意图 HITL U8:task generate adapter" +status: done +created: 2026-09-16 +updated: 2026-09-16 +owner: Cursor +branch: feature/multi-intent-u8-task-generate +worktree: "-" +mutex: intent-plan +--- + +# 多意图 HITL U8:task generate adapter + +## 目标 + +`confirm` tier 下查询+生成落盘 awaiting;确认后仅开放 `task.run` / `task.run.adhoc`,稳定幂等键,不改单意图 taskrun HTTP。 + +## 范围 + +- HandleTurn:`ComboNeedsConfirm` 且 tier≥confirm 时 WritePlan 落盘,不自动执行 +- `OwnerMux` 把 generate 路由到 Task,其余走 QueryGuard +- `TaskRunAdapter` + `LiveTaskStarter`(无 `PI_AGENT_RUNNER_URL` 只占位不启 PI) +- Assemble 接线;默认 `MULTI_INTENT_PLAN_TIER=legacy` 不变 + +## 非目标 + +- U9 LLM 分段、U10–U12 owner 扩面 +- 不 rebuild 共享环境、不改项目 143 +- 真实 PI 闭环若环境缺失记 stop-gate,不冒充验收 + +## 步骤 + +1. [x] 从 `dev` 开 `feature/multi-intent-u8-task-generate` +2. [x] confirm 落盘 + mux + adapter +3. [x] 单测与 arch-check +4. [x] 报告并合回 + +## 验收标准 + +- [x] 多意图生成确认前零执行 +- [x] 活动写计划冲突 +- [x] 确认后 mux 执行 generate,重放 starts=1 +- [x] QueryGuard 仍拒绝 generate;权限撤销 fail closed +- [x] 真实 PI 无 URL 时 skip(stop-gate) + +## 相关链接 + +- Checklist: [../checklists/2026-09-16-multi-intent-u8-task-generate.md](../checklists/2026-09-16-multi-intent-u8-task-generate.md) +- Test report: [../../test-reports/2026-09-16-multi-intent-u8-task-generate-test-report.md](../../test-reports/2026-09-16-multi-intent-u8-task-generate-test-report.md) +- Parent: [./2026-09-15-multi-intent-hitl.md](./2026-09-15-multi-intent-hitl.md) + +## 证据 / 备注 + +默认 legacy HandleTurn 仍不落盘。真实 PI 见报告 stop-gate。 diff --git a/.doc/status/FEATURE-MATRIX.md b/.doc/status/FEATURE-MATRIX.md index 77034351..65c21d1e 100644 --- a/.doc/status/FEATURE-MATRIX.md +++ b/.doc/status/FEATURE-MATRIX.md @@ -15,8 +15,8 @@ | 模块 | 能力 | 状态 | 证据 | 缺口/后续 | mutex | |------|------|------|------|-----------|-------| -| 意图识别 L1 | 18 类 Intent + 三分支消解 | partial | [system-design/intent-recognition](../system-design/intent-recognition/);[现场专项审计](../audit/2026-09-13-conversation-intent-runtime-state.md);[运行态报告](../test-reports/2026-09-13-conversation-intent-runtime-state-test-report.md);[双标签活验](../test-reports/assets/2026-09-15-conversation-intent-dual-tab/live.json);[多意图复核方案](../system-design/2026-09-15-multi-intent-hitl-plan.md);[U1 契约](../test-reports/2026-09-15-multi-intent-u1-contracts-test-report.md);[U2 分段](../test-reports/2026-09-15-multi-intent-u2-segmenter-test-report.md);[U3 PG](../test-reports/2026-09-15-multi-intent-u3-intentflow-pg-test-report.md) | 明确写动作与只读总结已分流;双标签 `DOC_BUSY` 已签(项目 6275)。多意图 U1–U5 已完成;U6–U8 未实施;intent 纯依赖边界不得回退 | `intent` | -| 多意图持久计划 | app/intentflow 生命周期与 HITL 契约 | partial | [设计](../system-design/2026-09-15-multi-intent-hitl-plan.md);[U1](../test-reports/2026-09-15-multi-intent-u1-contracts-test-report.md)–[U6](../test-reports/2026-09-16-multi-intent-u6-web-cards-test-report.md);[U7](../test-reports/2026-09-16-multi-intent-u7-auto-read-test-report.md) | U1–U7 已完成。U8 接 task.generate。共享环境 schema 45 待晋升 | `intent-plan` | +| 意图识别 L1 | 18 类 Intent + 三分支消解 | partial | [system-design/intent-recognition](../system-design/intent-recognition/);[现场专项审计](../audit/2026-09-13-conversation-intent-runtime-state.md);[运行态报告](../test-reports/2026-09-13-conversation-intent-runtime-state-test-report.md);[双标签活验](../test-reports/assets/2026-09-15-conversation-intent-dual-tab/live.json);[多意图复核方案](../system-design/2026-09-15-multi-intent-hitl-plan.md);[U1 契约](../test-reports/2026-09-15-multi-intent-u1-contracts-test-report.md);[U2 分段](../test-reports/2026-09-15-multi-intent-u2-segmenter-test-report.md);[U3 PG](../test-reports/2026-09-15-multi-intent-u3-intentflow-pg-test-report.md) | 明确写动作与只读总结已分流;双标签 `DOC_BUSY` 已签(项目 6275)。多意图核心 U1–U8 已完成;U9–U12 不阻塞首版。intent 纯依赖边界不得回退 | `intent` | +| 多意图持久计划 | app/intentflow 生命周期与 HITL 契约 | partial | [设计](../system-design/2026-09-15-multi-intent-hitl-plan.md);[U1](../test-reports/2026-09-15-multi-intent-u1-contracts-test-report.md)–[U8](../test-reports/2026-09-16-multi-intent-u8-task-generate-test-report.md) | U1–U8 核心首版已完成。U9–U12 不阻塞。默认 tier=legacy。真实 PI generate 待 runner URL。共享环境 schema 45 待晋升 | `intent-plan` | | 对话 / ctxmgr | 多轮上下文、记忆、摘要 | partial | [system-design/multi-turn-dialogue](../system-design/multi-turn-dialogue/);[刷新恢复专项审计](../audit/2026-09-13-chat-history-refresh-disappears.md);[U10 端口化](../archive/ops/2026-09-15-chatlog-contextasm-u10.md);[U10 报告](../test-reports/2026-09-15-chatlog-contextasm-u10-test-report.md) | `CHAT-HISTORY-REFRESH` 闲聊刷新活验已补。U10 原地端口 **停止扩面**(未物理拆包)。语义摘要(D5 backlog) | `chat` | | 智能体小队 | 角色-任务-工作区-黑板 | done | [system-design/agent-squad](../system-design/agent-squad/);[test 2026-09-07](../test-reports/2026-09-07-dynamic-squad-planning-test-report.md) | 非关键步骤降级(A5/A6 backlog) | `squad` | | 工作流治理 | 三正式工作流 + 阶段门禁 | partial | [remediation/three-workflows](../remediation/2026-09-12-three-workflows-strict-governance-remediation.md);[test 2026-09-12](../test-reports/2026-09-12-three-workflows-governance-remediation-test-report.md);[冻结态/职责可选整改](../remediation/2026-09-14-workflow-plan-409-frozen-and-optional-duties-remediation.md);[Wave 5 页面矩阵](../test-reports/2026-09-14-workflow-plan-409-frozen-and-optional-duties-test-report.md);[职责-动作鉴权](../test-reports/2026-09-14-governance-action-level-authz-test-report.md) | 设置页/DutyMode + 动作级鉴权/未激活 202-blocked/关闭创建直通已落地。后续:none 文档真实 PI 审批长链路、CI 三工作流 E2E | `workflow` | diff --git a/.doc/test-reports/2026-09-16-multi-intent-u8-task-generate-test-report.md b/.doc/test-reports/2026-09-16-multi-intent-u8-task-generate-test-report.md new file mode 100644 index 00000000..ac73ef4e --- /dev/null +++ b/.doc/test-reports/2026-09-16-multi-intent-u8-task-generate-test-report.md @@ -0,0 +1,75 @@ +# 多意图 HITL U8 task generate adapter 测试报告 + +## 一、 测试背景 (Background) + +U7 只在 `auto_read` 执行独立查询,`QueryGuard` 拒绝 `task.run`。U8 要在 `confirm` tier 把「查询+生成」落成 awaiting 写计划,确认后经 `OwnerMux` 只开放 `task.run` / `task.run.adhoc`,并用稳定幂等键避免双跑。默认 `MULTI_INTENT_PLAN_TIER=legacy` 仍不得落盘。 + +## 二、 测试目标 (Test Objectives) + +- confirm 话语确认前零 generate 副作用 +- 同 scope 第二活动写计划冲突 +- 确认后 mux 执行 generate,重放 `StartCount=1` +- QueryGuard 继续拒绝 generate;adapter 拒绝查询 key;撤销 Denied fail closed +- `LiveTaskStarter` 同幂等键重放 +- 无 `PI_AGENT_RUNNER_URL` 时真实 PI 记 stop-gate(SKIP,不冒充验收) +- arch-check / `-short` 相关包绿 + +## 三、 测试方案与环境 (Test Plan & Environment) + +| 项 | 值 | +|----|-----| +| 分支 | `feature/multi-intent-u8-task-generate` | +| OS | linux | +| 账本 | 内存 `SerialUoW` + `MemoryStore` | +| Owner | `OwnerMux{Query: QueryGuard{Fake}, Task: TaskRunAdapter}` | +| 真实 PI | `PI_AGENT_RUNNER_URL` 未设置 → SKIP | +| 共享环境 | 不 rebuild `:8080`;项目 143 只读 | + +## 四、 预期结果 (Expected Results) + +| 用例 | 预期 | +|------|------| +| legacy / auto_read 写话语 | 不落盘 | +| confirm + 「查一下相关法规,然后帮我生成报价单」 | awaiting,步骤 pending | +| 第二 ClientTurn 同 scope | `PLAN_DECISION_CONFLICT` | +| 确认 + AdvanceEligible | generate starts=1;再推进仍为 1 | +| QueryGuard `task.run` | `PLAN_ACTION_FORBIDDEN` | +| 真实 PI | 无 URL 则 SKIP | + +## 五、 实际测试结果与判定 (Actual Results & Evaluation) + +### 5.1 HandleTurn confirm + +- **测试输入**:`go test ./internal/app/intentflow -run 'TestHandleTurn|TestOwnerMux|TestQueryGuard' -count=1 -v` +- **实际输出**:`TestHandleTurnConfirmPersistsAwaitingWithoutExecute`、`TestHandleTurnConfirmRejectsSecondActiveWritePlan`、`TestHandleTurnWriteUtteranceStaysLegacyUnderAutoRead`、`TestQueryGuardRejectsGenerate`、`TestOwnerMux*` PASS。完整日志:[assets/2026-09-16-multi-intent-u8-task-generate/intentflow.txt](./assets/2026-09-16-multi-intent-u8-task-generate/intentflow.txt) +- **评价判定**:PASS。 +- **性能与耗时**:8ms + +### 5.2 Adapter / mux 闭环 + +- **测试输入**:`go test ./internal/app -run 'TestTask|TestConfirmThenMux|TestLiveTask' -count=1 -v` +- **实际输出**:`TestConfirmThenMuxExecutesGenerateOnce` PASS(确认前 starts=0,确认后 starts=1);`TestTaskRunAdapterIdempotentExecute` / `RejectsQueryKey` / `DeniedAfterRevoke` / `TestLiveTaskStarterReplaysIdempotencyKey` PASS;`TestTaskGenerateRealPIStopGate` SKIP(`PI_AGENT_RUNNER_URL` 未设置)。日志:[assets/2026-09-16-multi-intent-u8-task-generate/app-adapter.txt](./assets/2026-09-16-multi-intent-u8-task-generate/app-adapter.txt) +- **评价判定**:PASS(真实 PI 为 stop-gate,不计入首版冒充验收)。 +- **性能与耗时**:5ms + +### 5.3 回归与边界 + +- **测试输入**:`go test -short ./internal/app/intentflow ./internal/app ./internal/archtest ./internal/chat ./internal/server ./internal/taskrun`;`./scripts/arch-check.sh --mode block` +- **实际输出**:全部 ok;`arch-check block: production gate passed`。 +- **评价判定**:PASS。 +- **性能与耗时**:约 13s(含 server) + +## 六、 自动化测试套件汇总 (Test Suite Execution) + +| 命令 | 结果 | +|------|------| +| `go test ./internal/app/intentflow ./internal/app ./internal/archtest` | PASS | +| `go test -short ./internal/chat ./internal/server ./internal/taskrun` | PASS | +| `./scripts/arch-check.sh --mode block` | PASS | +| `TestTaskGenerateRealPIStopGate` | SKIP(无 `PI_AGENT_RUNNER_URL`) | + +未跑 `go test ./internal/chat` 无 `-short`:既有 `TestChatSession_SemanticMemoryRecallAndAsyncTurnRecord` flake,与 U8 无关。 + +## 七、 测试结论与后续优化建议 (Conclusion & Next Steps) + +U8 达到合入标准:核心首版 U1–U8 在默认 legacy 零行为、confirm 确认后只开放 generate adapter 的前提下可关闭。U9–U12 不阻塞首版。真实 PI 生成闭环仍待 `PI_AGENT_RUNNER_URL` 窗口;共享环境 schema 仍为 43,goose 45 待晋升窗口,本单元不 rebuild。 diff --git a/.doc/test-reports/assets/2026-09-16-multi-intent-u8-task-generate/app-adapter.txt b/.doc/test-reports/assets/2026-09-16-multi-intent-u8-task-generate/app-adapter.txt new file mode 100644 index 00000000..2e684ffb --- /dev/null +++ b/.doc/test-reports/assets/2026-09-16-multi-intent-u8-task-generate/app-adapter.txt @@ -0,0 +1,20 @@ +=== RUN TestTaskRunAdapterIdempotentExecute +--- PASS: TestTaskRunAdapterIdempotentExecute (0.00s) +=== RUN TestTaskRunAdapterRejectsQueryKey +--- PASS: TestTaskRunAdapterRejectsQueryKey (0.00s) +=== RUN TestTaskRunAdapterDeniedAfterRevoke +--- PASS: TestTaskRunAdapterDeniedAfterRevoke (0.00s) +=== RUN TestConfirmThenMuxExecutesGenerateOnce +2026/09/16 02:17:58 INFO intent_recognition intent=QUERY_REGULATIONS branch=NEW_INTENT_PREEMPT confidence=0.9 +2026/09/16 02:17:58 INFO intent_recognition intent=QUERY_REGULATIONS branch=NEW_INTENT_PREEMPT confidence=0.9 +2026/09/16 02:17:58 INFO intent_recognition intent=TRIGGER_TASK branch=NEW_INTENT_PREEMPT confidence=0.86 +2026/09/16 02:17:58 INFO intent_recognition intent=QUERY_REGULATIONS branch=NEW_INTENT_PREEMPT confidence=0.9 +2026/09/16 02:17:58 INFO intent_recognition intent=TRIGGER_TASK branch=NEW_INTENT_PREEMPT confidence=0.86 +--- PASS: TestConfirmThenMuxExecutesGenerateOnce (0.00s) +=== RUN TestLiveTaskStarterReplaysIdempotencyKey +--- PASS: TestLiveTaskStarterReplaysIdempotencyKey (0.00s) +=== RUN TestTaskGenerateRealPIStopGate + plan_owner_test.go:125: stop-gate: PI_AGENT_RUNNER_URL not set; real PI generate is not claimed +--- SKIP: TestTaskGenerateRealPIStopGate (0.00s) +PASS +ok chat-agent-system/internal/app 0.005s diff --git a/.doc/test-reports/assets/2026-09-16-multi-intent-u8-task-generate/arch-check.txt b/.doc/test-reports/assets/2026-09-16-multi-intent-u8-task-generate/arch-check.txt new file mode 100644 index 00000000..723d26a2 --- /dev/null +++ b/.doc/test-reports/assets/2026-09-16-multi-intent-u8-task-generate/arch-check.txt @@ -0,0 +1,5 @@ +arch-check mode=block +boundaries=/home/weichen/projects/Agent-System/.doc/system-design/module-boundaries.yaml +ok chat-agent-system/internal/archtest 0.172s +ok chat-agent-system/internal/archtest 0.154s +arch-check block: production gate passed diff --git a/.doc/test-reports/assets/2026-09-16-multi-intent-u8-task-generate/intentflow.txt b/.doc/test-reports/assets/2026-09-16-multi-intent-u8-task-generate/intentflow.txt new file mode 100644 index 00000000..dbf71633 --- /dev/null +++ b/.doc/test-reports/assets/2026-09-16-multi-intent-u8-task-generate/intentflow.txt @@ -0,0 +1,49 @@ +=== RUN TestOwnerMuxRoutesGenerateToTask +--- PASS: TestOwnerMuxRoutesGenerateToTask (0.00s) +=== RUN TestOwnerMuxNilTaskFailClosed +--- PASS: TestOwnerMuxNilTaskFailClosed (0.00s) +=== RUN TestHandleTurnLegacyDoesNotPersist +--- PASS: TestHandleTurnLegacyDoesNotPersist (0.00s) +=== RUN TestHandleTurnAutoReadPersistsAndExecutesQueries +2026/09/16 02:17:57 INFO intent_recognition intent=QUERY_REGULATIONS branch=NEW_INTENT_PREEMPT confidence=0.9 +2026/09/16 02:17:57 INFO intent_recognition intent=QUERY_PROGRESS branch=NEW_INTENT_PREEMPT confidence=0.9 +2026/09/16 02:17:57 INFO intent_recognition intent=QUERY_REGULATIONS branch=NEW_INTENT_PREEMPT confidence=0.9 +2026/09/16 02:17:57 INFO intent_recognition intent=QUERY_PROGRESS branch=NEW_INTENT_PREEMPT confidence=0.9 +2026/09/16 02:17:57 INFO intent_recognition intent=QUERY_REGULATIONS branch=NEW_INTENT_PREEMPT confidence=0.9 +2026/09/16 02:17:57 INFO intent_recognition intent=QUERY_REGULATIONS branch=NEW_INTENT_PREEMPT confidence=0.9 +2026/09/16 02:17:57 INFO intent_recognition intent=QUERY_PROGRESS branch=NEW_INTENT_PREEMPT confidence=0.9 +2026/09/16 02:17:57 INFO intent_recognition intent=QUERY_REGULATIONS branch=NEW_INTENT_PREEMPT confidence=0.9 +2026/09/16 02:17:57 INFO intent_recognition intent=QUERY_PROGRESS branch=NEW_INTENT_PREEMPT confidence=0.9 +2026/09/16 02:17:57 INFO intent_recognition intent=QUERY_REGULATIONS branch=NEW_INTENT_PREEMPT confidence=0.9 +--- PASS: TestHandleTurnAutoReadPersistsAndExecutesQueries (0.00s) +=== RUN TestHandleTurnWriteUtteranceStaysLegacyUnderAutoRead +2026/09/16 02:17:57 INFO intent_recognition intent=QUERY_REGULATIONS branch=NEW_INTENT_PREEMPT confidence=0.9 +--- PASS: TestHandleTurnWriteUtteranceStaysLegacyUnderAutoRead (0.00s) +=== RUN TestQueryGuardRejectsGenerate +--- PASS: TestQueryGuardRejectsGenerate (0.00s) +=== RUN TestHandleTurnConfirmPersistsAwaitingWithoutExecute +2026/09/16 02:17:57 INFO intent_recognition intent=QUERY_REGULATIONS branch=NEW_INTENT_PREEMPT confidence=0.9 +2026/09/16 02:17:57 INFO intent_recognition intent=QUERY_REGULATIONS branch=NEW_INTENT_PREEMPT confidence=0.9 +2026/09/16 02:17:57 INFO intent_recognition intent=TRIGGER_TASK branch=NEW_INTENT_PREEMPT confidence=0.86 +2026/09/16 02:17:57 INFO intent_recognition intent=QUERY_REGULATIONS branch=NEW_INTENT_PREEMPT confidence=0.9 +2026/09/16 02:17:57 INFO intent_recognition intent=TRIGGER_TASK branch=NEW_INTENT_PREEMPT confidence=0.86 +2026/09/16 02:17:57 INFO intent_recognition intent=QUERY_REGULATIONS branch=NEW_INTENT_PREEMPT confidence=0.9 +2026/09/16 02:17:57 INFO intent_recognition intent=QUERY_REGULATIONS branch=NEW_INTENT_PREEMPT confidence=0.9 +2026/09/16 02:17:57 INFO intent_recognition intent=TRIGGER_TASK branch=NEW_INTENT_PREEMPT confidence=0.86 +2026/09/16 02:17:57 INFO intent_recognition intent=QUERY_REGULATIONS branch=NEW_INTENT_PREEMPT confidence=0.9 +2026/09/16 02:17:57 INFO intent_recognition intent=TRIGGER_TASK branch=NEW_INTENT_PREEMPT confidence=0.86 +--- PASS: TestHandleTurnConfirmPersistsAwaitingWithoutExecute (0.00s) +=== RUN TestHandleTurnConfirmRejectsSecondActiveWritePlan +2026/09/16 02:17:57 INFO intent_recognition intent=QUERY_REGULATIONS branch=NEW_INTENT_PREEMPT confidence=0.9 +2026/09/16 02:17:57 INFO intent_recognition intent=QUERY_REGULATIONS branch=NEW_INTENT_PREEMPT confidence=0.9 +2026/09/16 02:17:57 INFO intent_recognition intent=TRIGGER_TASK branch=NEW_INTENT_PREEMPT confidence=0.86 +2026/09/16 02:17:57 INFO intent_recognition intent=QUERY_REGULATIONS branch=NEW_INTENT_PREEMPT confidence=0.9 +2026/09/16 02:17:57 INFO intent_recognition intent=TRIGGER_TASK branch=NEW_INTENT_PREEMPT confidence=0.86 +2026/09/16 02:17:57 INFO intent_recognition intent=QUERY_REGULATIONS branch=NEW_INTENT_PREEMPT confidence=0.9 +2026/09/16 02:17:57 INFO intent_recognition intent=QUERY_REGULATIONS branch=NEW_INTENT_PREEMPT confidence=0.9 +2026/09/16 02:17:57 INFO intent_recognition intent=TRIGGER_TASK branch=NEW_INTENT_PREEMPT confidence=0.86 +2026/09/16 02:17:57 INFO intent_recognition intent=QUERY_REGULATIONS branch=NEW_INTENT_PREEMPT confidence=0.9 +2026/09/16 02:17:57 INFO intent_recognition intent=TRIGGER_TASK branch=NEW_INTENT_PREEMPT confidence=0.86 +--- PASS: TestHandleTurnConfirmRejectsSecondActiveWritePlan (0.00s) +PASS +ok chat-agent-system/internal/app/intentflow 0.008s diff --git a/internal/app/app.go b/internal/app/app.go index 58b0f081..015827d8 100644 --- a/internal/app/app.go +++ b/internal/app/app.go @@ -4,6 +4,7 @@ import ( "context" "fmt" "log/slog" + "strings" "sync" "time" @@ -192,8 +193,14 @@ func Assemble(cfg *config.Config, svc *bizdev.Service) (*Runtime, error) { if pool != nil { rt.Docflow.UoW = uow.NewPG(pool) rt.Docflow.Events = events.PGSink{} + livePI := cfg != nil && strings.TrimSpace(cfg.PiAgentRunnerURL) != "" + taskOwner := NewTaskRunAdapter() + taskOwner.Starter = LiveTaskStarter(taskMgr, livePI) rt.IntentPlans = intentflow.NewPlans(rt.Docflow.UoW, intentflow.NewRepository(), intentflow.Options{ - Owner: intentflow.QueryGuard{Inner: intentflow.NewFakeActionOwner()}, + Owner: intentflow.OwnerMux{ + Query: intentflow.QueryGuard{Inner: intentflow.NewFakeActionOwner()}, + Task: taskOwner, + }, Events: events.PGSink{}, }) } diff --git a/internal/app/intentflow/mux.go b/internal/app/intentflow/mux.go new file mode 100644 index 00000000..584c6572 --- /dev/null +++ b/internal/app/intentflow/mux.go @@ -0,0 +1,61 @@ +package intentflow + +import "context" + +// OwnerMux routes generate keys to Task and everything else to Query. +type OwnerMux struct { + Query ActionOwner + Task ActionOwner +} + +func (m OwnerMux) pick(actionKey string) ActionOwner { + switch actionKey { + case "task.run", "task.run.adhoc": + return m.Task + default: + return m.Query + } +} + +func (m OwnerMux) Authorize(ctx context.Context, exec StepExec) error { + owner := m.pick(exec.ActionKey) + if owner == nil { + return ErrPlanActionForbidden + } + if a, ok := owner.(StepAuthorizer); ok { + return a.Authorize(ctx, exec) + } + return nil +} + +func (m OwnerMux) Execute(ctx context.Context, exec StepExec) (Receipt, error) { + if err := m.Authorize(ctx, exec); err != nil { + return Receipt{}, err + } + owner := m.pick(exec.ActionKey) + if owner == nil { + return Receipt{}, ErrPlanActionForbidden + } + return owner.Execute(ctx, exec) +} + +func (m OwnerMux) LookupReceipt(ctx context.Context, idempotencyKey string) (Receipt, bool, error) { + if m.Task != nil { + if rec, ok, err := m.Task.LookupReceipt(ctx, idempotencyKey); err != nil || ok { + return rec, ok, err + } + } + if m.Query != nil { + return m.Query.LookupReceipt(ctx, idempotencyKey) + } + return Receipt{}, false, nil +} + +func (m OwnerMux) ObserveFence(stepID string, token int64) { + if obs, ok := m.Query.(FenceObserver); ok { + obs.ObserveFence(stepID, token) + } + if obs, ok := m.Task.(FenceObserver); ok { + obs.ObserveFence(stepID, token) + } +} diff --git a/internal/app/intentflow/mux_test.go b/internal/app/intentflow/mux_test.go new file mode 100644 index 00000000..ebba5f8d --- /dev/null +++ b/internal/app/intentflow/mux_test.go @@ -0,0 +1,58 @@ +package intentflow_test + +import ( + "context" + "testing" + + "chat-agent-system/internal/app/intentflow" +) + +type routeProbe struct { + keys []string +} + +func (p *routeProbe) Authorize(_ context.Context, exec intentflow.StepExec) error { + p.keys = append(p.keys, "auth:"+exec.ActionKey) + return nil +} + +func (p *routeProbe) Execute(ctx context.Context, exec intentflow.StepExec) (intentflow.Receipt, error) { + p.keys = append(p.keys, "exec:"+exec.ActionKey) + return intentflow.Receipt{IdempotencyKey: exec.IdempotencyKey, ActionDigest: exec.ActionDigest, ResultRef: "probe:" + exec.ActionKey}, nil +} + +func (p *routeProbe) LookupReceipt(context.Context, string) (intentflow.Receipt, bool, error) { + return intentflow.Receipt{}, false, nil +} + +func TestOwnerMuxRoutesGenerateToTask(t *testing.T) { + query := &routeProbe{} + task := &routeProbe{} + mux := intentflow.OwnerMux{Query: query, Task: task} + ctx := context.Background() + if _, err := mux.Execute(ctx, intentflow.StepExec{ActionKey: "regulation.query", IdempotencyKey: "k-q", ActionDigest: "dq"}); err != nil { + t.Fatal(err) + } + if _, err := mux.Execute(ctx, intentflow.StepExec{ActionKey: "task.run", IdempotencyKey: "k-t", ActionDigest: "dt"}); err != nil { + t.Fatal(err) + } + if _, err := mux.Execute(ctx, intentflow.StepExec{ActionKey: "task.run.adhoc", IdempotencyKey: "k-a", ActionDigest: "da"}); err != nil { + t.Fatal(err) + } + if len(query.keys) == 0 || query.keys[len(query.keys)-1] != "exec:regulation.query" { + t.Fatalf("query probe = %v", query.keys) + } + if len(task.keys) < 2 { + t.Fatalf("task probe = %v", task.keys) + } +} + +func TestOwnerMuxNilTaskFailClosed(t *testing.T) { + mux := intentflow.OwnerMux{Query: intentflow.NewFakeActionOwner(), Task: nil} + _, err := mux.Execute(context.Background(), intentflow.StepExec{ + ActionKey: "task.run", Principal: principal(), IdempotencyKey: "k", ActionDigest: "d", + }) + if err != intentflow.ErrPlanActionForbidden { + t.Fatalf("nil Task must fail closed, got %v", err) + } +} diff --git a/internal/app/intentflow/plans.go b/internal/app/intentflow/plans.go index 7b671590..2a865fd6 100644 --- a/internal/app/intentflow/plans.go +++ b/internal/app/intentflow/plans.go @@ -99,7 +99,8 @@ func visibleTo(plan *Plan, p Principal) bool { } // HandleTurn stays a no-op while MULTI_INTENT_PLAN_TIER is legacy/shadow (default). -// U7 maps read-only utterances onto CreatePlan when auto_read is enabled. +// auto_read executes independent queries; confirm persists write/generate plans +// awaiting confirmation and does not execute them. func (p *Plans) HandleTurn(ctx context.Context, in TurnInput) (*TurnResult, error) { if err := requirePrincipal(in.Principal); err != nil { return nil, err diff --git a/internal/app/intentflow/query.go b/internal/app/intentflow/query.go index 403de9ad..728d6200 100644 --- a/internal/app/intentflow/query.go +++ b/internal/app/intentflow/query.go @@ -3,7 +3,7 @@ package intentflow import "context" // QueryGuard only authorizes low-risk query actions opened from auto_read. -// Write/generate keys fail closed until a later adapter is wired. +// Write/generate keys fail closed; OwnerMux routes those to Task. type QueryGuard struct { Inner ActionOwner Policy *BatchActionPolicy @@ -43,3 +43,9 @@ func (g QueryGuard) LookupReceipt(ctx context.Context, idempotencyKey string) (R } return g.Inner.LookupReceipt(ctx, idempotencyKey) } + +func (g QueryGuard) ObserveFence(stepID string, token int64) { + if obs, ok := g.Inner.(FenceObserver); ok { + obs.ObserveFence(stepID, token) + } +} diff --git a/internal/app/intentflow/turn.go b/internal/app/intentflow/turn.go index a995e928..9963bb58 100644 --- a/internal/app/intentflow/turn.go +++ b/internal/app/intentflow/turn.go @@ -26,7 +26,9 @@ func (p *Plans) handleTurnAutoRead(ctx context.Context, in TurnInput) (*TurnResu return &TurnResult{}, nil } proposal := res.PlanProposal - if proposal.ComboHint != intent.ComboReadOnly || len(proposal.Segments) < 2 || len(proposal.Segments) > 4 { + confirmWrites := proposal.ComboHint == intent.ComboNeedsConfirm && tier.Allows(TierConfirm) + readOnly := proposal.ComboHint == intent.ComboReadOnly && tier.Allows(TierAutoRead) + if (!confirmWrites && !readOnly) || len(proposal.Segments) < 2 || len(proposal.Segments) > 4 { return &TurnResult{}, nil } policy := DefaultBatchActionPolicy() @@ -40,7 +42,10 @@ func (p *Plans) handleTurnAutoRead(ctx context.Context, in TurnInput) (*TurnResu return &TurnResult{}, nil } row, err := policy.Lookup(key) - if err != nil || row.RejectPlan || row.RequiresBatchConfirm || !tier.Allows(row.OpenFromTier) { + if err != nil || row.RejectPlan || !tier.Allows(row.OpenFromTier) { + return &TurnResult{}, nil + } + if row.RequiresBatchConfirm && !confirmWrites { return &TurnResult{}, nil } summary := strings.TrimSpace(seg.Normalized) @@ -69,13 +74,16 @@ func (p *Plans) handleTurnAutoRead(ctx context.Context, in TurnInput) (*TurnResu SegmenterVersion: proposal.SegmenterVersion, Status: PlanAwaitingConfirmation, ExecutionMode: ModeLive, - WritePlan: false, + WritePlan: confirmWrites, SafeSummary: text, Steps: drafts, }) if err != nil { return nil, err } + if confirmWrites { + return &TurnResult{Plan: created}, nil + } confirmed, err := p.DecidePlan(ctx, DecisionCommand{ Principal: in.Principal, PlanID: created.PlanID, diff --git a/internal/app/intentflow/turn_test.go b/internal/app/intentflow/turn_test.go index ffe19422..c46c61a6 100644 --- a/internal/app/intentflow/turn_test.go +++ b/internal/app/intentflow/turn_test.go @@ -78,3 +78,80 @@ func TestQueryGuardRejectsGenerate(t *testing.T) { t.Fatal("task.run must be forbidden by QueryGuard") } } + +func TestHandleTurnConfirmPersistsAwaitingWithoutExecute(t *testing.T) { + intentflow.SetFeatureFlagsForTest(intentflow.FeatureFlags{PlanTier: intentflow.TierConfirm}) + t.Cleanup(intentflow.ResetFeatureFlagsForTest) + p, _, owner := testPlans() + ctx := context.Background() + res, err := p.HandleTurn(ctx, intentflow.TurnInput{ + Principal: principal(), + Text: "查一下相关法规,然后帮我生成报价单", + ClientTurnID: "turn-cf-1", + RequestDigest: "d-cf-1", + }) + if err != nil { + t.Fatal(err) + } + if res == nil || res.Plan == nil { + t.Fatal("confirm tier must persist a write plan") + } + if res.Plan.Status != intentflow.PlanAwaitingConfirmation { + t.Fatalf("status %s", res.Plan.Status) + } + if len(res.Plan.Steps) < 2 { + t.Fatalf("expected query+generate steps, got %+v", res.Plan.Steps) + } + hasGenerate := false + for _, s := range res.Plan.Steps { + if s.ActionKey == "task.run" || s.ActionKey == "task.run.adhoc" { + hasGenerate = true + } + if s.Status != intentflow.StepPending { + t.Fatalf("confirm must not execute before decision, step=%+v", s) + } + } + if !hasGenerate { + t.Fatalf("expected a generate step, plan=%+v", res.Plan) + } + if owner.ExecCount("") != 0 { + t.Fatal("no owner exec expected before confirm") + } + again, err := p.HandleTurn(ctx, intentflow.TurnInput{ + Principal: principal(), + Text: "查一下相关法规,然后帮我生成报价单", + ClientTurnID: "turn-cf-1", + RequestDigest: "d-cf-1", + }) + if err != nil { + t.Fatal(err) + } + if again.Plan.PlanID != res.Plan.PlanID { + t.Fatal("same turn must reuse the awaiting plan") + } +} + +func TestHandleTurnConfirmRejectsSecondActiveWritePlan(t *testing.T) { + intentflow.SetFeatureFlagsForTest(intentflow.FeatureFlags{PlanTier: intentflow.TierConfirm}) + t.Cleanup(intentflow.ResetFeatureFlagsForTest) + p, _, _ := testPlans() + ctx := context.Background() + first, err := p.HandleTurn(ctx, intentflow.TurnInput{ + Principal: principal(), + Text: "查一下相关法规,然后帮我生成报价单", + ClientTurnID: "turn-cf-a", + RequestDigest: "d-cf-a", + }) + if err != nil || first == nil || first.Plan == nil { + t.Fatalf("first plan: %+v %v", first, err) + } + _, err = p.HandleTurn(ctx, intentflow.TurnInput{ + Principal: principal(), + Text: "查一下相关法规,然后帮我生成报价单", + ClientTurnID: "turn-cf-b", + RequestDigest: "d-cf-b", + }) + if err != intentflow.ErrPlanDecisionConflict { + t.Fatalf("second write plan must conflict, got %v", err) + } +} diff --git a/internal/app/plan_owner.go b/internal/app/plan_owner.go new file mode 100644 index 00000000..321fb825 --- /dev/null +++ b/internal/app/plan_owner.go @@ -0,0 +1,146 @@ +package app + +import ( + "context" + "crypto/sha256" + "encoding/hex" + "fmt" + "sync" + + "chat-agent-system/internal/app/intentflow" + "chat-agent-system/internal/bizdev" + "chat-agent-system/internal/taskrun" +) + +// TaskRunAdapter is the U8 generate adapter. It records a stable idempotency +// key and result reference without changing single-intent taskrun HTTP. +type TaskRunAdapter struct { + mu sync.Mutex + receipts map[string]intentflow.Receipt + starts int + Denied bool + Starter func(ctx context.Context, exec intentflow.StepExec) (resultRef string, err error) +} + +func NewTaskRunAdapter() *TaskRunAdapter { + return &TaskRunAdapter{receipts: map[string]intentflow.Receipt{}} +} + +func (a *TaskRunAdapter) Authorize(_ context.Context, exec intentflow.StepExec) error { + if a != nil && a.Denied { + return intentflow.ErrPlanActionForbidden + } + if exec.ActionKey != "task.run" && exec.ActionKey != "task.run.adhoc" { + return intentflow.ErrPlanActionForbidden + } + return nil +} + +func (a *TaskRunAdapter) Execute(ctx context.Context, exec intentflow.StepExec) (intentflow.Receipt, error) { + if err := a.Authorize(ctx, exec); err != nil { + return intentflow.Receipt{}, err + } + a.mu.Lock() + if rec, ok := a.receipts[exec.IdempotencyKey]; ok { + a.mu.Unlock() + if rec.ActionDigest != exec.ActionDigest { + return intentflow.Receipt{}, intentflow.ErrPlanDecisionConflict + } + return rec, nil + } + a.mu.Unlock() + ref := "taskrun:" + exec.IdempotencyKey + if a.Starter != nil { + got, err := a.Starter(ctx, exec) + if err != nil { + return intentflow.Receipt{}, err + } + if got != "" { + ref = got + } + } + a.mu.Lock() + defer a.mu.Unlock() + if rec, ok := a.receipts[exec.IdempotencyKey]; ok { + if rec.ActionDigest != exec.ActionDigest { + return intentflow.Receipt{}, intentflow.ErrPlanDecisionConflict + } + return rec, nil + } + a.starts++ + rec := intentflow.Receipt{ + IdempotencyKey: exec.IdempotencyKey, + ActionDigest: exec.ActionDigest, + ResultRef: ref, + ResultDigest: "task:" + exec.ActionDigest, + SafeSummary: "task.run accepted", + } + if a.receipts == nil { + a.receipts = map[string]intentflow.Receipt{} + } + a.receipts[exec.IdempotencyKey] = rec + return rec, nil +} + +// LiveTaskStarter claims a taskrun with the plan step idempotency key. +// When live is false it only occupies the run row and does not start PI. +func LiveTaskStarter(mgr *taskrun.Manager, live bool) func(context.Context, intentflow.StepExec) (string, error) { + return func(ctx context.Context, exec intentflow.StepExec) (string, error) { + if mgr == nil { + return "", fmt.Errorf("task generate adapter: taskrun manager missing") + } + if existing, err := mgr.FindByIdempotencyKey(ctx, exec.IdempotencyKey); err != nil { + return "", err + } else if existing != nil && existing.RunID != "" { + return existing.RunID, nil + } + taskKey := "intake" + if exec.ActionKey == "task.run.adhoc" { + taskKey = "adhoc" + } + rec := &taskrun.RunRecord{ + RunID: planRunID(exec.IdempotencyKey), + SessionID: exec.Principal.SessionID, + ProjectID: exec.Principal.ProjectID, + UserID: exec.Principal.UserID, + IdempotencyKey: exec.IdempotencyKey, + TaskKey: taskKey, + Status: "pending", + } + if !live { + claimed, _, err := mgr.ClaimRun(ctx, rec) + if err != nil { + return "", err + } + return claimed.RunID, nil + } + created, err := mgr.CreateAndStart(ctx, rec.RunID, rec, bizdev.TaskRunRequest{ + TaskKey: taskKey, + UserID: exec.Principal.UserID, + ProjectID: exec.Principal.ProjectID, + SessionID: exec.Principal.SessionID, + }, bizdev.StageRunRequest{}, "") + if err != nil { + return "", err + } + return created.RunID, nil + } +} + +func planRunID(idempotencyKey string) string { + sum := sha256.Sum256([]byte(idempotencyKey)) + return "run_plan_" + hex.EncodeToString(sum[:8]) +} + +func (a *TaskRunAdapter) LookupReceipt(_ context.Context, idempotencyKey string) (intentflow.Receipt, bool, error) { + a.mu.Lock() + defer a.mu.Unlock() + rec, ok := a.receipts[idempotencyKey] + return rec, ok, nil +} + +func (a *TaskRunAdapter) StartCount() int { + a.mu.Lock() + defer a.mu.Unlock() + return a.starts +} diff --git a/internal/app/plan_owner_test.go b/internal/app/plan_owner_test.go new file mode 100644 index 00000000..9dafe4cd --- /dev/null +++ b/internal/app/plan_owner_test.go @@ -0,0 +1,128 @@ +package app + +import ( + "context" + "os" + "testing" + "time" + + "chat-agent-system/internal/app/intentflow" + "chat-agent-system/internal/taskrun" +) + +func TestTaskRunAdapterIdempotentExecute(t *testing.T) { + a := NewTaskRunAdapter() + exec := intentflow.StepExec{ + ActionKey: "task.run", IdempotencyKey: "idem-1", ActionDigest: "d1", + Principal: intentflow.Principal{UserID: 1, ProjectID: 2, SessionID: "s", Environment: "dev"}, + } + first, err := a.Execute(context.Background(), exec) + if err != nil { + t.Fatal(err) + } + second, err := a.Execute(context.Background(), exec) + if err != nil { + t.Fatal(err) + } + if first.ResultRef != second.ResultRef { + t.Fatalf("replay ref %s vs %s", first.ResultRef, second.ResultRef) + } + if a.StartCount() != 1 { + t.Fatalf("starts = %d", a.StartCount()) + } +} + +func TestTaskRunAdapterRejectsQueryKey(t *testing.T) { + a := NewTaskRunAdapter() + _, err := a.Execute(context.Background(), intentflow.StepExec{ActionKey: "regulation.query", Principal: intentflow.Principal{UserID: 1}}) + if err != intentflow.ErrPlanActionForbidden { + t.Fatalf("got %v", err) + } +} + +func TestTaskRunAdapterDeniedAfterRevoke(t *testing.T) { + a := NewTaskRunAdapter() + a.Denied = true + _, err := a.Execute(context.Background(), intentflow.StepExec{ActionKey: "task.run", Principal: intentflow.Principal{UserID: 1}}) + if err != intentflow.ErrPlanActionForbidden { + t.Fatalf("got %v", err) + } +} + +func TestConfirmThenMuxExecutesGenerateOnce(t *testing.T) { + intentflow.SetFeatureFlagsForTest(intentflow.FeatureFlags{PlanTier: intentflow.TierConfirm}) + t.Cleanup(intentflow.ResetFeatureFlagsForTest) + query := intentflow.NewFakeActionOwner() + task := NewTaskRunAdapter() + t0 := time.Date(2026, 9, 16, 12, 0, 0, 0, time.UTC) + p := intentflow.NewPlans(&intentflow.SerialUoW{}, intentflow.NewMemoryStore(), intentflow.Options{ + Owner: intentflow.OwnerMux{Query: intentflow.QueryGuard{Inner: query}, Task: task}, + Now: func() time.Time { return t0 }, + }) + ctx := context.Background() + prin := intentflow.Principal{UserID: 7, Environment: "dev", ProjectID: 42, SessionID: "sess-u8"} + created, err := p.HandleTurn(ctx, intentflow.TurnInput{ + Principal: prin, Text: "查一下相关法规,然后帮我生成报价单", + ClientTurnID: "turn-u8", RequestDigest: "d-u8", + }) + if err != nil || created == nil || created.Plan == nil { + t.Fatalf("create: %+v %v", created, err) + } + if created.Plan.Status != intentflow.PlanAwaitingConfirmation { + t.Fatalf("status %s", created.Plan.Status) + } + if task.StartCount() != 0 { + t.Fatal("generate must not start before confirm") + } + confirmed, err := p.DecidePlan(ctx, intentflow.DecisionCommand{ + Principal: prin, PlanID: created.Plan.PlanID, ExpectedRevision: created.Plan.Revision, + DecisionNonce: "u8-n", DecisionDigest: "u8-d", Kind: intentflow.DecisionConfirm, + }) + if err != nil { + t.Fatal(err) + } + view, err := p.AdvanceEligible(ctx, "u8-worker", confirmed.PlanID) + if err != nil { + t.Fatal(err) + } + if view == nil { + t.Fatal("expected advanced plan") + } + if task.StartCount() != 1 { + t.Fatalf("generate starts = %d, plan=%+v", task.StartCount(), view) + } + _, err = p.AdvanceEligible(ctx, "u8-worker", confirmed.PlanID) + if err != nil { + t.Fatal(err) + } + if task.StartCount() != 1 { + t.Fatalf("replay must not restart generate, starts=%d", task.StartCount()) + } +} + +func TestLiveTaskStarterReplaysIdempotencyKey(t *testing.T) { + mgr := taskrun.NewManager(nil, nil) + start := LiveTaskStarter(mgr, false) + exec := intentflow.StepExec{ + ActionKey: "task.run", IdempotencyKey: "plan-key-1", ActionDigest: "d", + Principal: intentflow.Principal{UserID: 3, ProjectID: 9, SessionID: "sess-live"}, + } + a, err := start(context.Background(), exec) + if err != nil { + t.Fatal(err) + } + b, err := start(context.Background(), exec) + if err != nil { + t.Fatal(err) + } + if a == "" || a != b { + t.Fatalf("replay run id %q vs %q", a, b) + } +} + +func TestTaskGenerateRealPIStopGate(t *testing.T) { + if os.Getenv("PI_AGENT_RUNNER_URL") == "" { + t.Skip("stop-gate: PI_AGENT_RUNNER_URL not set; real PI generate is not claimed") + } + t.Skip("live PI generate path is gated; unit evidence is TaskRunAdapter + ClaimRun idempotency") +}