Files
aetherbound-guild/.agent-taskgraph/queue/failed/ABG-P9.1-FOUNDATION-REVIEW-R2/goal.md
T

82 lines
5.7 KiB
Markdown
Raw Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
# Goal: Independently re-review the repaired P9.1 runtime foundation
> Stage: foundation-independent-rereview
> Started: 2026-08-13T04:46:39+00:00
> Task ID: `ABG-P9.1-FOUNDATION-REVIEW-R2`
> Baseline: `bd505d6188556b5d407bebe9769d1c99e74dc9c1; branch=review/abg-p91-foundation-r2; 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-r2`
> Legal terminal: **ABG-P9.1-FOUNDATION-REVIEW-R2 PASS** 或 **ABG-P9.1-FOUNDATION-REVIEW-R2 FAIL: <最早产品/合同失败边界>** 或 **ABG-P9.1-FOUNDATION-REVIEW-R2 INVALID: <最早 reviewer 环境/工具边界>**
## Objective
Review immutable repaired source bd505d6 from zero. First prove the R1 exact-ID defect is closed with new domain accepting/storing/emitting only retain_loan/add_recruit and rejecting legacy IDs while the facade alone translates legacy P9.0 callers. Then complete the full Foundation 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 terminal, p9.1-contract-r2, RUNTIME_ARCHITECTURE_SPEC, 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-r2`
- 角色职责:Independently review the repaired immutable Foundation candidate from zero and report PASS, FAIL or INVALID
- 角色生命周期:task-scoped
- 派给:p91-foundation-reviewer-r2
- 分配理由:职责匹配
- 连续性:fresh replacement after R1 FAIL; fixed bd505d6; no prior reviewer session or execution evidence reuse
- 工作区:`/Users/wusumac/Documents/game/tmp/aetherbound-guild-worktrees/p91-foundation-review-r2`(分支:`review/abg-p91-foundation-r2`)
- 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 40cfa34a-169a-4480-9df3-1ca5591ed553; zero-message watermark`
- Session evidence:`HAPI 8eab2016-87ac-45ce-bc6d-2a7f9b06331d; PID 42841; runtime-evidence.json`
- Dispatch bootstrap:`dispatch.md`
- Dispatch message:`SENT: dispatch:ABG-P9.1-FOUNDATION-REVIEW-R2:attempt-1 via HAPI 8eab2016 after pre-dispatch verification 40cfa34a`
- Identity ACK:`VERIFIED: IDENTITY_READY dispatch_id=dispatch:ABG-P9.1-FOUNDATION-REVIEW-R2:attempt-1 role=role:p91-foundation-reviewer-r2 team_revision=rev-p9.1-1 goal=task:ABG-P9.1-FOUNDATION-REVIEW-R2 context_revision=p91-foundation-review-r2`
- 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 candidate exactly bd505d6; candidate lineage includes c33c304 plus only the four-file exact-ID repair; worktrees clean
- [ ] Independently prove frozen IDs accepted/stored/emitted, legacy IDs rejected by service/state/contracts, and legacy strings exist only inside compatibility facade translation/UI behavior
- [ ] Review all c33c304 Foundation changes plus bd505d6 repair for composition root, thin facade, one mutable owner, atomic results, exactly-once impacts, domain purity and no downstream gameplay implementation
- [ ] From fresh isolated imported source rerun exactly the accepted 22 scripts with one marker each and strict diagnostics zero
- [ ] Independently regenerate and compare the four named 844x390 groups totaling 30 frames; do not reuse developer or R1 captures
- [ ] 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 logs or captures as R2 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
exact-ID and diff audit 30m; full 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
## Review Terminal
- `ABG-P9.1-FOUNDATION-REVIEW-R2 INVALID: reviewer exact-ID probe import/parse boundary`
- Fixed candidate: `bd505d6188556b5d407bebe9769d1c99e74dc9c1`.
- Reviewer-owned out-of-tree probe used an unresolved `FirstSessionState` type annotation and failed before every product assertion.
- Product conclusion: none. Structural, 22-script and 30-frame gates were not run.
- Evidence: `/private/tmp/abg-p91-foundation-review-r2.qFXJjd/evidence/terminal.txt`, SHA-256 `21fc819c58dc3a4441cc15301fef46add68ae0322b97d684700769717125b55f`.
- Source/refs remained immutable, worktrees clean, temporary source/cache removed and no owned process remained.