Files
aetherbound-guild/.agent-taskgraph/queue/failed/ABG-V2-EXPERIENCE-REVIEW-R2/goal.md
T

101 lines
5.6 KiB
Markdown

# Goal: ABG-V2 Experience And Production Review R2
> Stage: pre-development fixed-revision review
> Started: 2026-08-11T00:47:43+08:00
> Task ID: `ABG-V2-EXPERIENCE-REVIEW-R2`
> Baseline: `7054fe6` on local `main`, clean, no configured upstream
> Accepted previous stage: integrated product source `ec4863a`; PMO review closure `7054fe6`
> Frozen spec: `.agent-taskgraph/spec.md` revision `design-spec-r3`
> Graph node: `.agent-taskgraph/graph.yaml#v2_experience_review` revision `graph-r5`
> Independent contract: `docs/reviews/PRE_DEVELOPMENT_READINESS_AUDIT.md`
> Context manifest: `context.md`
> Context revision: `1`
> Legal terminal: **ABG-V2-EXPERIENCE-REVIEW-R2 PASS** or **ABG-V2-EXPERIENCE-REVIEW-R2 FAIL: <earliest failed product boundary>** or **ABG-V2-EXPERIENCE-REVIEW-R2 INVALID: <review environment boundary>**
## Objective
Independently audit immutable revision `7054fe6` for a complete, understandable
landscape player experience and a feasible original 2D Japanese hand-drawn art,
animation, VFX and audio production plan. This is a design-authority review,
not runtime, screenshot or human acceptance.
## Graph Input, Output And Write Scope
- Needs: `v2_integration`
- Consumes: immutable `7054fe6`, design-spec-r3, presentation and content
authorities required by the checks below
- Produces: one read-only PASS/FAIL/INVALID terminal with exact file/line and
command evidence
- Writes: none in the repository; reviewer-owned temporary files only
- Route: PASS -> `v2_review_synthesis`; FAIL/INVALID -> `failed`; max attempt 1
## Assignment
- Role ref: `role:experience-production-reviewer-v2`
- Lifecycle: task-scoped
- Assigned to: new isolated visible HAPI session
- Reason: parallel independent experience/production expertise
- Continuity: fresh role; no worker or R1 acceptance is inherited
- Workspace: repository root for discovery, then reviewer-owned
`git archive 7054fe6` for all judgment
- Runtime requested: `runtime=hapi; flavor=codex; model=gpt-5.6-sol; effort=xhigh; permission=bypassPermissions; visibility=visible`
- Runtime observed: `runtime=hapi; flavor=codex; model=gpt-5.6-sol; effort=xhigh; permission=yolo; visibility=visible`
- Runtime verification: `VERIFIED` pre-dispatch at 2026-08-11T00:54:55+08:00
- Session evidence: HAPI `8cfe0437-3a7e-4ac0-8b26-3477ef170654`, PID
`41549`, verification `436c7db8-40cb-43fb-bd38-e9b76147d9bc`,
`runtime-evidence.json`, zero-message watermark
- Dispatch bootstrap: `dispatch.md`
- Dispatch message: `SENT: 2026-08-11T00:56:00+08:00 via HAPI peer 8cfe0437; dispatch:ABG-V2-EXPERIENCE-REVIEW-R2:r1`
- Identity ACK: `VERIFIED: IDENTITY_READY dispatch_id=dispatch:ABG-V2-EXPERIENCE-REVIEW-R2:r1 role=role:experience-production-reviewer-v2 team_revision=rev-4 goal=task:ABG-V2-EXPERIENCE-REVIEW-R2 context_revision=1`
- Full launch method: HAPI Hub helper on machine
`a15888ad-d405-4884-a407-c28ddd8b397c`
## Required Gates
1. Prove the archive is exactly `7054fe6`, contains `ec4863a`, and the
canonical repository is clean. Use no later source for judgment.
2. Run the predevelopment validator self-test/full/JSON audits from the archive.
Require self-test 15, `errors=0`, pages=50, bindings=33 and exact production
counts before semantic review.
3. Map the first-play chain across all relevant pages: inspect offer, recruit or
buy, equip, reorder, risk choice, battle observation, casualty/reward and
next Market. Fail unexplained controls, icon-only critical actions,
prose-dependent comprehension or missing next-action hierarchy.
4. Audit all 50 page/state contracts for landscape phone/tablet layouts,
safe areas, focus, controller and touch, empty/loading/error/locked/disabled/
confirmation/interruption states, EN/zh_CN and 130% text.
5. Check the final-Recruit disabled/rejected state and distinct `OUT-006`
abandonment confirmation are visible, inspectable and cannot route through
an empty Shop. Check casualty, loss and recovery consequences are legible.
6. Check party-order battle readability with up to 10 deployed members:
silhouettes, overlap, targeting, reach, movement, health/status, damage,
healing, death, rewards, speed and pause/inspect without manual skill UI.
7. Audit modular recruit construction, all 42 profession identities, 36 trait
cues, 320 equipment, 60 artifacts, eight regions, 100 ordinary/elite enemies
and 16 bosses for countable asset families, silhouette differentiation,
equipment layering, animation states, VFX limits and production feasibility.
8. Audit 32 music, 76 ambience, 228 SFX and 32 voice-intent authorities for
event bindings, priority/ducking, lifecycle, mute, reduced-motion coupling,
low-power and localization/subtitle behavior. Generated recruits must not
create fixed-cast voice burden.
9. Trace each major content family from mechanics to screen/state, art/VFX and
audio presentation. Reject orphaned rows, placeholder-only assets or a plan
that cannot be reviewed page by page before implementation.
10. Check originality: structural reference lessons must not copy names, prose,
layouts, formulas, characters, commercial art/audio, source or assets.
## Terminal Rules
- PASS only when all ten gates pass.
- FAIL at the earliest defensible design or production contradiction; cite
exact file/line evidence and checks completed before stopping.
- INVALID for archive, parser, command, environment, timeout or reviewer
process failure. Do not retry silently or convert it into product FAIL.
- Never edit, repair, commit, push, generate media, package or release.
- Human understanding/fun/visual/listening, runtime, device and release remain
open after PASS.
## Estimate
- Review: 1.5-3h; hard upper bound 4h; confidence medium.