102 lines
5.0 KiB
JSON
102 lines
5.0 KiB
JSON
{
|
|
"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"
|
|
}
|