Initial Open-SWE-Traces cleanup pipeline

2026-08-06 22:53:47 +08:00
commit 044bd03f0e
35 changed files with 3638 additions and 0 deletions
@@ -0,0 +1,43 @@
+{
+  "$schema": "https://json-schema.org/draft/2020-12/schema",
+  "type": "object",
+  "additionalProperties": false,
+  "required": [
+    "sample_id", "approved", "maximum_training_use", "invariant_violations",
+    "unsupported_changes", "evidence", "summary"
+  ],
+  "properties": {
+    "sample_id": {"type": "string", "minLength": 1},
+    "approved": {"type": "boolean"},
+    "maximum_training_use": {
+      "enum": ["SFT_FULL", "SFT_STEP_ONLY", "DPO_REJECTED", "ERROR_ANALYSIS", "HOLD", "DROP"]
+    },
+    "invariant_violations": {
+      "type": "array", "uniqueItems": true,
+      "items": {
+        "enum": [
+          "RESOLVED_CHANGED", "TOOL_OUTPUT_CHANGED", "MODEL_PATCH_CHANGED", "REFERENCE_PATCH_CHANGED",
+          "SYNTHETIC_EXECUTION_RESULT_ADDED", "STATEFUL_TURN_REMOVED", "DANGLING_TOOL_PAIR",
+          "SEMANTIC_TOOL_CALL_CHANGED_WITHOUT_EXECUTION", "TRAINING_USE_UPGRADED_WITHOUT_EVIDENCE"
+        ]
+      }
+    },
+    "unsupported_changes": {
+      "type": "array",
+      "items": {"type": "string", "minLength": 1, "maxLength": 400}
+    },
+    "evidence": {
+      "type": "array", "minItems": 1, "maxItems": 20,
+      "items": {
+        "type": "object", "additionalProperties": false,
+        "required": ["turn_id", "quote", "assessment"],
+        "properties": {
+          "turn_id": {"type": ["integer", "null"], "minimum": 1},
+          "quote": {"type": "string", "minLength": 1, "maxLength": 240},
+          "assessment": {"type": "string", "minLength": 1, "maxLength": 400}
+        }
+      }
+    },
+    "summary": {"type": "string", "minLength": 1, "maxLength": 1000}
+  }
+}