chore(pmo): activate foundation review r3

2026-08-13 13:18:19 +08:00
parent 19e7dd405b
commit b5936346a6
9 changed files with 18 additions and 17 deletions
@@ -0,0 +1,29 @@
+# Context Manifest: ABG-P9.1-FOUNDATION-REVIEW-R3
+
+> Task ID: `ABG-P9.1-FOUNDATION-REVIEW-R3`
+> Revision: `p91-foundation-review-r3`
+> Mode: `deep`
+> Budget exception: `none`
+
+## 必须读取（默认不超过 8 项）
+
+| 路径或稳定引用 | Revision / 范围 | 为什么本 Goal 必须读 |
+|---|---|---|
+| `AGENTS.md` | bd505d6 | fixed-tester and evidence boundaries |
+| `.agent-taskgraph/PROJECT.md` | p9.1 profile | visible HAPI reviewer runtime and environment recovery |
+| `.agent-taskgraph/spec.md` | p9.1-spec-r2 | frozen P9.1 stage scope |
+| `docs/runtime/PHASE9_1_ARBITRARY_PARTY_FIRST_SESSION_CONTRACT.md` | p9.1-contract-r2 | exact IDs, API and accepted 22-script authority |
+| `docs/runtime/p9_1/RUNTIME_ARCHITECTURE_SPEC.md` | 7bc871d | foundation structure and ownership requirements |
+| `candidate bd505d6188556b5d407bebe9769d1c99e74dc9c1` | fixed repaired product source | immutable candidate under review |
+| `.agent-taskgraph/queue/failed/ABG-P9.1-FOUNDATION-REVIEW-R1/report.md and ABG-P9.1-FOUNDATION-REVIEW-R2/report.md` | R1 FAIL + R2 INVALID | defect to retest and reviewer harness failure not to repeat |
+| `/private/tmp/abg-p9-0r10-regression-r2.4fxrTu/summary.txt` | sha256 3de791bb6da14be19d97c194368cd14bc8bfb906013470e81b6e12da83736bf7 | exact accepted R10 22-script authority |
+
+## 按需检索（先搜索，再局部读取）
+
+| 路径/范围 | 触发条件 | 检索提示 |
+|---|---|---|
+| source tree | Goal 需要实现细节时 | 先 rg，再局部读取 |
+
+## 最近 Delta
+
+- 2026-08-13T05:12:44+00:00: structured pre-dispatch manifest created.
@@ -0,0 +1,21 @@
+# Dispatch Bootstrap: ABG-P9.1-FOUNDATION-REVIEW-R3
+
+| Field | Value |
+|---|---|
+| Task ID | ABG-P9.1-FOUNDATION-REVIEW-R3 |
+| Dispatch ID | dispatch:ABG-P9.1-FOUNDATION-REVIEW-R3:attempt-1 |
+| Role ref | role:p91-foundation-reviewer-r3 |
+| Role profile | roles/p91-foundation-reviewer-r3/ROLE.md |
+| Role lifecycle | task-scoped |
+| Team revision | rev-p9.1-1 |
+| Goal ref | task:ABG-P9.1-FOUNDATION-REVIEW-R3 |
+| Context manifest | context.md |
+| Context revision | p91-foundation-review-r3 |
+| Continuity | fresh environment recovery after R2 harness INVALID; fixed bd505d6; no R1/R2 execution evidence reuse |
+| Session ID | a96709b9-9139-435d-83bf-40c05835f028 |
+| Expected identity ACK | IDENTITY_READY dispatch_id=dispatch:ABG-P9.1-FOUNDATION-REVIEW-R3:attempt-1 role=role:p91-foundation-reviewer-r3 team_revision=rev-p9.1-1 goal=task:ABG-P9.1-FOUNDATION-REVIEW-R3 context_revision=p91-foundation-review-r3 |
+| Delivery | SENT: dispatch:ABG-P9.1-FOUNDATION-REVIEW-R3:attempt-1 via HAPI a96709b9 after pre-dispatch verification 78ec87d1 |
+| Identity ACK | VERIFIED: IDENTITY_READY dispatch_id=dispatch:ABG-P9.1-FOUNDATION-REVIEW-R3:attempt-1 role=role:p91-foundation-reviewer-r3 team_revision=rev-p9.1-1 goal=task:ABG-P9.1-FOUNDATION-REVIEW-R3 context_revision=p91-foundation-review-r3 |
+| ACK evidence | exact standalone identity line observed in fresh HAPI a96709b9-9139-435d-83bf-40c05835f028 before any review command; worktree clean at binding commit 19e7dd4 |
+
+Read Role, PROJECT, context, Goal and direct evidence in that order. Return the exact identity ACK before executing the Goal.
@@ -0,0 +1,72 @@
+# Goal: Independently review P9.1 Foundation with corrected environment
+
+> Stage: foundation-independent-rereview-r3
+> Started: 2026-08-13T05:12:44+00:00
+> Task ID: `ABG-P9.1-FOUNDATION-REVIEW-R3`
+> Baseline: `bd505d6188556b5d407bebe9769d1c99e74dc9c1; branch=review/abg-p91-foundation-r3; clean`
+> Frozen spec: `.agent-taskgraph/spec.md revision p9.1-spec-r2; docs/runtime/PHASE9_1_ARBITRARY_PARTY_FIRST_SESSION_CONTRACT.md revision p9.1-contract-r2`
+> Graph node: `.agent-taskgraph/graph.yaml#p91_runtime_foundation`
+> Independent contract: 不适用
+> Context manifest: `context.md`
+> Context revision: `p91-foundation-review-r3`
+> Legal terminal: **ABG-P9.1-FOUNDATION-REVIEW-R3 PASS** 或 **ABG-P9.1-FOUNDATION-REVIEW-R3 FAIL: <最早产品/合同失败边界>** 或 **ABG-P9.1-FOUNDATION-REVIEW-R3 INVALID: <最早 reviewer 环境/工具边界>**
+
+## Objective
+
+Review immutable bd505d6 from zero. Create a fresh archive, run an isolated Godot editor import first, and retest exact IDs with an annotation-free external probe so R2's harness defect cannot recur. Then complete the full structural, pure-domain, exact 22-script and independent four-group/30-frame gates. Report PASS, product FAIL, or environment/harness INVALID at the earliest boundary and never repair.
+
+## 图输入、输出与写入范围
+
+- 直接依赖（needs）：p91_runtime_foundation repaired candidate bd505d6
+- 必须读取（consumes）：bd505d6 fixed source, R1 FAIL, R2 INVALID harness lesson, p9.1-contract-r2, accepted exact 22-script authority
+- 必须产出（produces）：fresh read-only PASS, FAIL or INVALID terminal with reviewer-owned evidence
+- 唯一写入范围（writes）：none in repository; reviewer-owned isolated temporary evidence only
+- 路由：PASS -> p91_domain_implementation；FAIL -> failed；最大尝试 1
+
+## 分配记录
+
+- Role ref：`role:p91-foundation-reviewer-r3`
+- 角色职责：Independently review immutable bd505d6 from zero using a corrected isolated import/probe environment
+- 角色生命周期：task-scoped
+- 派给：p91-foundation-reviewer-r3
+- 分配理由：职责匹配
+- 连续性：fresh environment recovery after R2 harness INVALID; fixed bd505d6; no R1/R2 execution evidence reuse
+- 工作区：`/Users/wusumac/Documents/game/tmp/aetherbound-guild-worktrees/p91-foundation-review-r3`（分支：`review/abg-p91-foundation-r3`）
+- Runtime requested：`runtime=hapi; flavor=codex; model=gpt-5.6-sol; effort=xhigh; permission=yolo; visibility=visible`
+- Runtime observed：`runtime=hapi; flavor=codex; model=gpt-5.6-sol; effort=xhigh; permission=yolo; visibility=visible`
+- Runtime verification：`VERIFIED pre-dispatch; verification 78ec87d1-cd67-4888-9791-d3afcc946cf4; zero-message watermark`
+- Session evidence：`HAPI a96709b9-9139-435d-83bf-40c05835f028; PID 65647; runtime-evidence.json`
+- Dispatch bootstrap：`dispatch.md`
+- Dispatch message：`SENT: dispatch:ABG-P9.1-FOUNDATION-REVIEW-R3:attempt-1 via HAPI a96709b9 after pre-dispatch verification 78ec87d1`
+- Identity ACK：`VERIFIED: IDENTITY_READY dispatch_id=dispatch:ABG-P9.1-FOUNDATION-REVIEW-R3:attempt-1 role=role:p91-foundation-reviewer-r3 team_revision=rev-p9.1-1 goal=task:ABG-P9.1-FOUNDATION-REVIEW-R3 context_revision=p91-foundation-review-r3`
+- 完整启动方式：派发预览批准后由所选 runtime 控制面生成
+
+## 报告协议
+
+- 完成、失败或阻塞时通知 PMO，并引用任务号、legal terminal 和证据路径。
+- worker 不修改 PMO 管理的 queue ledger、STATUS 或角色注册表。
+
+## 验收标准（证据门）
+
+- [ ] Prove fixed product source exactly bd505d6 and clean worktrees; later PMO commits excluded
+- [ ] Fresh archive + isolated HOME/cache/TMP editor import passes; annotation-free exact-ID probe proves frozen IDs accepted/stored/emitted and legacy IDs rejected/leaks zero
+- [ ] Review all Foundation and repair changes for composition root, thin facade, one mutable owner, atomic results, exactly-once impacts, domain purity and no downstream gameplay implementation
+- [ ] From the same fresh imported archive run exactly the accepted 22 scripts serially with one marker each and strict diagnostics zero
+- [ ] Independently regenerate and compare four named 844x390 groups totaling 30 frames; no developer/R1/R2 capture reuse
+- [ ] Verify immutable source, sanitized evidence inventory, clean worktrees and owned-process/temp cleanup before terminal
+
+## Frozen（禁止触碰，明确列出）
+
+- Do not edit, repair, stage, commit, push, merge or modify repository files or Git refs
+- Do not reuse developer/R1/R2 logs or captures as R3 execution evidence and do not read later product changes
+- Do not implement Domain/UI/Tests, generate media, package, sign, upload, publish or cross a Human Gate
+- Classify harness/input/import/recording/timeout/concurrent-load/cleanup failures as INVALID
+
+## Estimate
+
+environment preflight 15m; exact-ID/structure audit 30m; 22 scripts 30-60m; 30-frame comparison 45-90m; confidence high
+
+## 完成时交付
+
+- graph 节点约定的 produces
+- 验收证据与残余风险
@@ -0,0 +1,47 @@
+# 台账记录：ABG-P9.1-FOUNDATION-REVIEW-R3
+
+| 字段 | 值 |
+|---|---|
+| 任务 ID | ABG-P9.1-FOUNDATION-REVIEW-R3 |
+| Goal ref | task:ABG-P9.1-FOUNDATION-REVIEW-R3 |
+| Goal current path | queue/active/ABG-P9.1-FOUNDATION-REVIEW-R3/goal.md |
+| Context manifest | context.md |
+| Context revision | p91-foundation-review-r3 |
+| Role ref | role:p91-foundation-reviewer-r3 |
+| Role lifecycle | task-scoped |
+| Role profile | roles/p91-foundation-reviewer-r3/ROLE.md |
+| Role continuity | fresh environment recovery after R2 harness INVALID; fixed bd505d6; no R1/R2 execution evidence reuse |
+| Reviewer Role ref | role:p91-foundation-reviewer-r3 |
+| Reviewer Role profile | roles/p91-foundation-reviewer-r3/ROLE.md |
+| Frozen spec | .agent-taskgraph/spec.md revision p9.1-spec-r2; docs/runtime/PHASE9_1_ARBITRARY_PARTY_FIRST_SESSION_CONTRACT.md revision p9.1-contract-r2 |
+| Graph node | .agent-taskgraph/graph.yaml#p91_runtime_foundation |
+| 依赖/路由 | needs: p91_runtime_foundation repaired candidate bd505d6; PASS -> p91_domain_implementation; FAIL -> failed; max_attempts=1 |
+| 状态 | active |
+| 负责人 | p91-foundation-reviewer-r3 |
+| 分配理由 | 职责匹配 |
+| 轮次 | 1 |
+| 开始时间 | 2026-08-13T05:12:44+00:00 |
+| 最后更新 | 2026-08-13T05:17:12+00:00 |
+| 验收结果 | PENDING |
+| 日志指针 | PENDING |
+| Runtime requested | runtime=hapi; flavor=codex; model=gpt-5.6-sol; effort=xhigh; permission=yolo; visibility=visible |
+| Runtime observed | runtime=hapi; flavor=codex; model=gpt-5.6-sol; effort=xhigh; permission=yolo; visibility=visible |
+| Runtime verification | VERIFIED |
+| Session ID | a96709b9-9139-435d-83bf-40c05835f028 |
+| Runtime evidence | runtime-evidence.json |
+| Dispatch bootstrap | dispatch.md |
+| Dispatch message | SENT: dispatch:ABG-P9.1-FOUNDATION-REVIEW-R3:attempt-1 via HAPI a96709b9 after pre-dispatch verification 78ec87d1 |
+| Identity ACK | VERIFIED: IDENTITY_READY dispatch_id=dispatch:ABG-P9.1-FOUNDATION-REVIEW-R3:attempt-1 role=role:p91-foundation-reviewer-r3 team_revision=rev-p9.1-1 goal=task:ABG-P9.1-FOUNDATION-REVIEW-R3 context_revision=p91-foundation-review-r3 |
+| 等待归属 | 在等谁：p91-foundation-reviewer-r3；等什么：fixed bd505d6 PASS/FAIL/INVALID；PMO 600s HAPI timer/observe |
+
+## 备注
+
+Prepared from task-manifest.json. Do not hand-edit field names.
+
+## 状态转换历史（追加式）
+
+| 时间 | from -> to | 操作者 | 依据/证据 | 唯一下一步 |
+|---|---|---|---|---|
+| 2026-08-13T05:12:44+00:00 | created -> inbox | PMO | structured manifest | run pre-dispatch validation |
+| 2026-08-13T05:14:10+00:00 | inbox -> inbox | PMO | fresh R3 HAPI runtime VERIFIED at correct cwd/model/effort/yolo with zero-message watermark | commit binding, fast-forward worktree, send identity bootstrap |
+| 2026-08-13T05:17:12+00:00 | inbox -> active | PMO | exact standalone R3 identity ACK observed before review commands | fast-forward activation and execute corrected-environment fixed bd505d6 review |
@@ -0,0 +1,39 @@
+{
+  "status": "VERIFIED",
+  "phase": "pre-dispatch",
+  "verification_id": "78ec87d1-cd67-4888-9791-d3afcc946cf4",
+  "goal_ref": "task:ABG-P9.1-FOUNDATION-REVIEW-R3",
+  "session_id": "a96709b9-9139-435d-83bf-40c05835f028",
+  "machine_id": "a15888ad-d405-4884-a407-c28ddd8b397c",
+  "machine_name": "小吴家",
+  "machine_host": "wusumacdeMac-mini.local",
+  "pid": "65647",
+  "flavor": "codex",
+  "cwd": "/Users/wusumac/Documents/game/tmp/aetherbound-guild-worktrees/p91-foundation-review-r3",
+  "model": "gpt-5.6-sol",
+  "effort": "xhigh",
+  "permission": "yolo",
+  "messages_received": 0,
+  "message_watermark": {
+    "latest_page_count": 0,
+    "latest_message_id": "",
+    "snapshot_head_seq": null,
+    "snapshot_head_at": null,
+    "epoch": 0,
+    "captured_at": "2026-08-13T05:14:10.705812+00:00"
+  },
+  "active": true,
+  "thinking": false,
+  "lifecycle": "running",
+  "catalog": {
+    "status": "VERIFIED",
+    "source": "/api/machines/:id/codex-models",
+    "checked_at": "2026-08-13T05:14:07.800312+00:00",
+    "model": "gpt-5.6-sol",
+    "effort": "xhigh",
+    "model_supported": true,
+    "effort_supported": true
+  },
+  "evidence": "HAPI Hub session metadata, model catalog, and message watermark",
+  "verified_at": "2026-08-13T05:14:10.706038+00:00"
+}
@@ -0,0 +1,101 @@
+{
+  "task_id": "ABG-P9.1-FOUNDATION-REVIEW-R3",
+  "title": "Independently review P9.1 Foundation with corrected environment",
+  "stage": "foundation-independent-rereview-r3",
+  "baseline": "bd505d6188556b5d407bebe9769d1c99e74dc9c1",
+  "branch": "review/abg-p91-foundation-r3",
+  "worktree": "/Users/wusumac/Documents/game/tmp/aetherbound-guild-worktrees/p91-foundation-review-r3",
+  "frozen_spec": ".agent-taskgraph/spec.md revision p9.1-spec-r2; docs/runtime/PHASE9_1_ARBITRARY_PARTY_FIRST_SESSION_CONTRACT.md revision p9.1-contract-r2",
+  "graph_node": ".agent-taskgraph/graph.yaml#p91_runtime_foundation",
+  "context_revision": "p91-foundation-review-r3",
+  "context_mode": "deep",
+  "context_items": [
+    {
+      "path": "AGENTS.md",
+      "revision": "bd505d6",
+      "reason": "fixed-tester and evidence boundaries"
+    },
+    {
+      "path": ".agent-taskgraph/PROJECT.md",
+      "revision": "p9.1 profile",
+      "reason": "visible HAPI reviewer runtime and environment recovery"
+    },
+    {
+      "path": ".agent-taskgraph/spec.md",
+      "revision": "p9.1-spec-r2",
+      "reason": "frozen P9.1 stage scope"
+    },
+    {
+      "path": "docs/runtime/PHASE9_1_ARBITRARY_PARTY_FIRST_SESSION_CONTRACT.md",
+      "revision": "p9.1-contract-r2",
+      "reason": "exact IDs, API and accepted 22-script authority"
+    },
+    {
+      "path": "docs/runtime/p9_1/RUNTIME_ARCHITECTURE_SPEC.md",
+      "revision": "7bc871d",
+      "reason": "foundation structure and ownership requirements"
+    },
+    {
+      "path": "candidate bd505d6188556b5d407bebe9769d1c99e74dc9c1",
+      "revision": "fixed repaired product source",
+      "reason": "immutable candidate under review"
+    },
+    {
+      "path": ".agent-taskgraph/queue/failed/ABG-P9.1-FOUNDATION-REVIEW-R1/report.md and ABG-P9.1-FOUNDATION-REVIEW-R2/report.md",
+      "revision": "R1 FAIL + R2 INVALID",
+      "reason": "defect to retest and reviewer harness failure not to repeat"
+    },
+    {
+      "path": "/private/tmp/abg-p9-0r10-regression-r2.4fxrTu/summary.txt",
+      "revision": "sha256 3de791bb6da14be19d97c194368cd14bc8bfb906013470e81b6e12da83736bf7",
+      "reason": "exact accepted R10 22-script authority"
+    }
+  ],
+  "role_id": "p91-foundation-reviewer-r3",
+  "role_lifecycle": "task-scoped",
+  "role_responsibility": "Independently review immutable bd505d6 from zero using a corrected isolated import/probe environment",
+  "role_continuity": "fresh environment recovery after R2 harness INVALID; fixed bd505d6; no R1/R2 execution evidence reuse",
+  "runtime_requested": {
+    "runtime": "hapi",
+    "flavor": "codex",
+    "model": "gpt-5.6-sol",
+    "effort": "xhigh",
+    "permission": "yolo",
+    "visibility": "visible"
+  },
+  "objective": "Review immutable bd505d6 from zero. Create a fresh archive, run an isolated Godot editor import first, and retest exact IDs with an annotation-free external probe so R2's harness defect cannot recur. Then complete the full structural, pure-domain, exact 22-script and independent four-group/30-frame gates. Report PASS, product FAIL, or environment/harness INVALID at the earliest boundary and never repair.",
+  "needs": [
+    "p91_runtime_foundation repaired candidate bd505d6"
+  ],
+  "consumes": [
+    "bd505d6 fixed source",
+    "R1 FAIL",
+    "R2 INVALID harness lesson",
+    "p9.1-contract-r2",
+    "accepted exact 22-script authority"
+  ],
+  "produces": [
+    "fresh read-only PASS, FAIL or INVALID terminal with reviewer-owned evidence"
+  ],
+  "writes": [
+    "none in repository; reviewer-owned isolated temporary evidence only"
+  ],
+  "pass_route": "p91_domain_implementation",
+  "fail_route": "failed",
+  "max_attempts": 1,
+  "acceptance": [
+    "[ ] Prove fixed product source exactly bd505d6 and clean worktrees; later PMO commits excluded",
+    "[ ] Fresh archive + isolated HOME/cache/TMP editor import passes; annotation-free exact-ID probe proves frozen IDs accepted/stored/emitted and legacy IDs rejected/leaks zero",
+    "[ ] Review all Foundation and repair changes for composition root, thin facade, one mutable owner, atomic results, exactly-once impacts, domain purity and no downstream gameplay implementation",
+    "[ ] From the same fresh imported archive run exactly the accepted 22 scripts serially with one marker each and strict diagnostics zero",
+    "[ ] Independently regenerate and compare four named 844x390 groups totaling 30 frames; no developer/R1/R2 capture reuse",
+    "[ ] Verify immutable source, sanitized evidence inventory, clean worktrees and owned-process/temp cleanup before terminal"
+  ],
+  "frozen": [
+    "Do not edit, repair, stage, commit, push, merge or modify repository files or Git refs",
+    "Do not reuse developer/R1/R2 logs or captures as R3 execution evidence and do not read later product changes",
+    "Do not implement Domain/UI/Tests, generate media, package, sign, upload, publish or cross a Human Gate",
+    "Classify harness/input/import/recording/timeout/concurrent-load/cleanup failures as INVALID"
+  ],
+  "estimate": "environment preflight 15m; exact-ID/structure audit 30m; 22 scripts 30-60m; 30-frame comparison 45-90m; confidence high"
+}