SPEC: Cut toolkit — eyes / hands / prove (BlenderRun)

Status: DRAFT
Repo: the-shit/kit
Slug: cut-toolkit
Depends on: kit#10 factory-seats (Cut receipt stays "one slice queued" until this lands)
Related: kit#6 ImageToMesh (TRELLIS/Hunyuan) — blockout only, not the edit loop

Lie: Kit "does 3D modeling." Today Cut cannot see or touch meshes (ImagineStill only; factory-seats locks Cut against Blender). This SPEC makes the lie true for one closed loop: see → act → measure → retry.

Seat: Cut agent (smart brain: Astra via OpenRouter for now; swappable). Look stays honesty. Ship stays PR/CI, never merge. No LLM on /api/assign.

Number (done-when): For a single catalog asset job, LookCompare score ≥ agreed threshold on the four views (front/side/back/3-quarter) AND ValidateGLB green, within N Cut turns (default 5). Pitcher owns the threshold when the job is assigned.

Locked

Eyes (sense)

• RenderViews — render orthographic/perspective stills from current GLB for front|side|back|ride (match ImagineStill view names). Output paths under factory tree only.
• Vision critique — Cut brain receives those stills + brief + prior fail notes. SHALL NOT invent what a mesh looks like from filenames alone.
• LookCompare — score candidate vs reference per region/check. Reuse Look honesty rules: fail ⇒ message contains fail, never visual_ok.

Hands (act)

• BlenderRun — bounded bpy only (allowlisted ops: load/save GLB, transform, boolean, remesh/decimate, weld, simple material assign). No free shell, no network from bpy, no arbitrary Python import outside allowlist.
• ImageToMesh — optional blockout when starting from zero; implementation may call kit#6 backends. Receipt is a GLB path + catalog id.
• MeshOps — non-Blender repairs when cheaper. Prefer BlenderRun when topology must change.

Prove (scoreboard)

• ValidateGLB — manifold, poly budget, units, required LODs/catalog schema. Hard fail blocks Ship.
• Turn cap — Cut SHALL stop and report honest fail when N turns exhausted without number met.
• Ship — only after ValidateGLB + LookCompare pass; hallway still does not merge.

Brain / routing

• Cut is one of the 1–3 smart house seats. Brain is config (KIT_CUT_MODEL, default OpenRouter Astra-class when available; fallback documented).
• Look and Ship stay cheap/local — do not promote them to frontier models for this SPEC.
• Assign still has no LLM.

Host / GPU

• Blender execution host is Loki (creative default) with Thor borrow when idle. This SPEC SHALL NOT hardcode cloud burst.
• PEM/secrets stay off shared Cursor VM.

Files (proposed)

Acceptance

• SPEC file lands at specs/cut-toolkit/spec.md with spec: on this issue
• Cut job can run one fake loop in CI (mocked RenderViews/BlenderRun) and emit a receipt with turn count + pass/fail
• Real BlenderRun path documented; CI does not require Loki GPU
• factory-seats Cut lock updated: "SHALL NOT spawn Blender" becomes "SHALL only spawn via BlenderRun allowlist after cut-toolkit APPROVE"
• Look honesty unchanged: fail/missing never visual_ok
• Ship still never merges
• php artisan test --filter=CutToolkit green without GPU
• Pint green on touched PHP

Non-goals

• Unreal/editor driving
• Free-form bash or unrestricted bpy
• Merging PRs / restack babysit beyond today's Ship hallway
• Multitenancy (kit#11)
• Replacing Feel/Bench identities
• Making Look or Ship into frontier agents
• Full TRELLIS training stack (belongs to kit#6)

After APPROVE

1. Land specs/cut-toolkit/spec.md on the-shit/kit; comment spec: specs/cut-toolkit/spec.md here.
2. Implement tools + CutLoop behind feature flag; dogfood one catalog asset on Loki.
3. Only then point Cut brain at Astra (or successor) — tools before brain.
4. Do not label night-ready until SPEC is on GitHub and Jordan wants pickup.