refactor: add DesignIR distillation pipeline

2026-07-27 17:24:04 +08:00
parent 0adaac2b2a
commit 550b339bcc
1128 changed files with 10248 additions and 426666 deletions
@@ -0,0 +1,81 @@
+# Case JSON input contract
+
+Case JSON is private evidence used only during induction. It may contain exact
+parameters, but the inducer never copies those fields into published experience.
+Store source STEP files in `workspace/teacher/inbox` and generated private
+evidence in `workspace/teacher/evidence`.
+
+Do not pass either folder or a case JSON to cad-router or a CAD backend.
+Creation, modification, and reconstruction may consume only the promoted public
+experience library.
+
+Supported fields:
+
+```json
+{
+  "provenance": {"source_sha256": "..."},
+  "design_ir": {
+    "part_family": "flanged_hub_adapter",
+    "features": [{"type": "base_flange"}, {"type": "hollow_sleeve"}],
+    "constraints": [{"id": "coaxial_stack", "type": "coaxial"}],
+    "reconstruction_evidence": {
+      "parameter_roles": ["overall_long_span", "coaxial_diameter_roles"],
+      "datum_roles": ["part_center", "primary_axis"],
+      "feature_roles": ["rotational_body", "coaxial_cylindrical_stack"],
+      "relation_roles": ["coaxial_stack"],
+      "canonical_stages": [
+        {
+          "id": "establish_reference_frame",
+          "operation": "define_datums",
+          "feature_roles": [],
+          "reference_roles": ["part_center", "primary_axis"]
+        }
+      ],
+      "private_cardinality_evidence": {
+        "feature_role_count": 5,
+        "feature_role_count_class": "repeated"
+      },
+      "validation_roles": ["closed_solid", "coaxial_stack"]
+    },
+    "normalized_observations": [
+      {
+        "name": "sleeve_od_to_base_od",
+        "value": 0.35,
+        "numerator_role": "sleeve_outer_diameter",
+        "denominator_role": "base_outer_diameter"
+      }
+    ]
+  },
+  "experience": {
+    "rules": [
+      {
+        "id": "bound_counterbore_to_host",
+        "scope": ["counterbore"],
+        "statement": "Terminate a counterbore at its host boundary.",
+        "repair": "Bind the cutter extent to the host feature."
+      }
+    ],
+    "validation_targets": [
+      {
+        "id": "counterbore_host_boundary",
+        "check": "A counterbore does not cross an unrelated adjacent feature."
+      }
+    ]
+  }
+}
+```
+
+Rules and checks containing numeric literals are rejected because they are
+likely instance answers. Ratios are accepted only through
+`normalized_observations`, with an explicit numerator and denominator role.
+
+Legacy distilled JSON can be used when it contains the fields above. Exact
+`parameters`, `evidence`, centers, axes, and surface references are ignored.
+
+V3 extractor output should also provide several independent semantic signals
+per case: body-aspect class, topology-complexity role, analytic feature
+networks, part family, relationship candidates, and role-named dimensionless
+observations. It additionally provides symbolic reconstruction roles, canonical
+reconstruction stages, and private exact cardinality evidence. Sanitization
+converts exact counts into qualitative classes before LLM review. Do not encode
+an absolute source dimension as a feature token.