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 +1,54 @@
+"""Tests for deterministic static repair application and evidence preservation."""
+
+from __future__ import annotations
+
+from swe_data_processing.repair import apply_static_repair
+
+
+def _plan() -> dict:
+    return {
+        "sample_id": "sample-1",
+        "repair_decision": "APPLY_STATIC_REPAIR",
+        "maximum_training_use": "ERROR_ANALYSIS",
+        "invariants": {
+            "resolved_unchanged": True,
+            "tool_outputs_unchanged": True,
+            "model_patch_unchanged": True,
+            "reference_patch_unchanged": True,
+            "no_synthetic_execution_result": True,
+        },
+        "operations": [
+            {
+                "op": "REWRITE_FINAL_SUMMARY",
+                "target_turns": [5],
+                "preconditions": ["Turn 5 is an assistant-only summary."],
+                "replacement": "The build passed, but functional behavior remains unverified.",
+                "reason": "Remove an unsupported success claim.",
+            }
+        ],
+        "requires_second_review": True,
+        "summary": "Correct the final claim without changing execution evidence.",
+    }
+
+
+def test_rewrite_summary_preserves_tool_output_and_patch() -> None:
+    record = {
+        "trajectory_id": "sample-1",
+        "resolved": -1,
+        "trajectory": [
+            {"role": "system", "content": "system"},
+            {"role": "user", "content": "issue"},
+            {"role": "assistant", "content": "build", "tool_calls": []},
+            {"role": "tool", "content": "build completed with exit code 0"},
+            {"role": "assistant", "content": "All tests pass.", "tool_calls": []},
+        ],
+        "metadata": {
+            "model_patch": {"patch": "+++ b/src/a.py\n"},
+            "reference_patch": {"patch": "+++ b/src/a.py\n"},
+        },
+    }
+    repaired, diff = apply_static_repair(record, _plan())
+    assert repaired["trajectory"][3] == record["trajectory"][3]
+    assert repaired["trajectory"][4]["content"].startswith("The build passed")
+    assert repaired["metadata"] == record["metadata"]
+    assert diff["replaced_original_turn_ids"] == [5]