Initial Open-SWE-Traces cleanup pipeline

tests/test_evidence.py

@@ -0,0 +1,38 @@
+"""Tests for prompt-only trajectory compaction."""
+
+from swe_data_processing.evidence import compact_text, compact_trajectory
+
+
+def test_compact_text_preserves_short_values() -> None:
+    """Short evidence must remain byte-for-byte identical."""
+
+    assert compact_text("short evidence", 100) == "short evidence"
+
+
+def test_compact_text_hashes_long_values() -> None:
+    """Long evidence must expose its size and digest for auditability."""
+
+    result = compact_text("a" * 1_000, 200)
+    assert len(result) == 200
+    assert "COMPACTED original_chars=1000 sha256=" in result
+
+
+def test_compact_trajectory_prioritizes_test_observations() -> None:
+    """Important test output receives a larger preview than ordinary output."""
+
+    long_content = "x" * 3_000
+    trajectory = [
+        {"turn_id": 1, "role": "user", "content": "issue"},
+        {"turn_id": 2, "role": "assistant", "content": "", "tool_calls": []},
+        {"turn_id": 3, "role": "tool", "content": long_content},
+        {"turn_id": 4, "role": "assistant", "content": "done"},
+    ]
+    signals = {
+        "stateful_turns": [],
+        "test_events": [{"command_turn": 2, "output_turn": 3}],
+        "malformed_tool_turns": [],
+        "unknown_tool_turns": [],
+    }
+    compacted, metadata = compact_trajectory(trajectory, signals)
+    assert compacted[2]["content"] == long_content
+    assert 3 in metadata["important_turn_ids"]