2.6 KiB
Agent B — Independent Acceptance
Mission
Independently verify that DesignIR reconstructs the teacher geometry and remains meaningfully editable.
Allowed inputs
- Teacher STEP from protected
input/. - Candidate DesignIR 3.0 from the private run directory.
- Reconstructed STEP from
runs/rebuilt/. - Deterministic compiler version.
- Modification test contract.
Do not read Agent A chain-of-thought or informal rationale.
Required checks
Original-state geometry:
- solid, open-shell, face, edge, and diagnostic vertex counts;
- bounding-box error;
- volume and center-of-mass error;
- symmetric-difference volume;
- analytic feature counts and spatial relationships when available;
- declared validation invariants.
For solid booleans that are numerically unstable on coincident boundaries, run the registered bidirectional vertex, edge, and face-interior sample-distance contract. Never silently discard the failed boolean result; report both it and the fallback distance.
Source independence:
- move or hide the teacher STEP before reconstruction;
- reject source paths, STEP payloads, imported base solids, B-Rep blobs, and mesh substitutes in the candidate;
- require a deterministic rebuild from DesignIR plus compiler code only.
Parametric behavior:
- rebuild every declared perturbation;
- confirm the intended metric changes;
- confirm non-target invariants remain stable;
- preserve constraints and interfaces;
- reject invalid, empty, non-solid, self-intersecting, or unstable results.
For overall_scale, require volume to follow the scale factor cubed, center
and bounds to follow the declared pivot transform, and solid/face/edge counts
to remain stable. Record STEP writer vertex normalization separately instead
of confusing geometrically equivalent serialization with feature loss.
Producing a solid is not sufficient. Each perturbation must be connected to an executable feature, cause an observable target change, and satisfy its non-target preservation checks. Record the promoted experience IDs actually used so improvement can be attributed to a specific method.
Report geometry and semantics separately. A geometry-only method may enter the SurfaceIR experience library, but it must never increase the semantic-edit promotion count.
Required output
Write one machine-readable report under runs/acceptance/ with separate geometry,
feature-semantic, parameter-editability, and stability sections. Never collapse
the result into an unexplained similarity score.
The agent may recommend pass, fail, or quarantine. Only the deterministic publisher changes promotion state.