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 +1,100 @@
+"""Tests for deterministic static trajectory evidence extraction."""
+
+from __future__ import annotations
+
+import json
+
+from swe_data_processing.features import extract_patch_files, extract_static_signals
+
+
+def _tool(name: str) -> str:
+    return json.dumps({"type": "function", "function": {"name": name, "parameters": {}}})
+
+
+def test_detects_masked_failing_test_after_edit() -> None:
+    record = {
+        "trajectory_id": "sample-1",
+        "resolved": 0,
+        "tools": [_tool("str_replace_editor"), _tool("execute_bash"), _tool("finish")],
+        "trajectory": [
+            {"role": "system", "content": "system"},
+            {"role": "user", "content": "Do not modify test files."},
+            {
+                "role": "assistant",
+                "content": "",
+                "tool_calls": [
+                    {
+                        "id": "edit-1",
+                        "type": "function",
+                        "function": {
+                            "name": "str_replace_editor",
+                            "arguments": json.dumps(
+                                {"command": "str_replace", "path": "/workspace/src/main.py"}
+                            ),
+                        },
+                    }
+                ],
+            },
+            {"role": "tool", "content": "The file was edited."},
+            {
+                "role": "assistant",
+                "content": "",
+                "tool_calls": [
+                    {
+                        "id": "test-1",
+                        "type": "function",
+                        "function": {
+                            "name": "execute_bash",
+                            "arguments": json.dumps({"command": "pytest tests | tail -20"}),
+                        },
+                    }
+                ],
+            },
+            {
+                "role": "tool",
+                "content": "1 failed, 10 passed\n[Command finished with exit code 0]",
+            },
+        ],
+        "metadata": {
+            "model_patch": {"patch": "diff --git a/src/main.py b/src/main.py\n+++ b/src/main.py\n"},
+            "reference_patch": {"patch": "diff --git a/src/main.py b/src/main.py\n+++ b/src/main.py\n"},
+        },
+    }
+
+    signals = extract_static_signals(record)
+    assert signals["last_stateful_turn"] == 3
+    assert signals["instruction_constraints"] == ["Do not modify test files."]
+    assert signals["test_events"][0]["masked_pipeline"] is True
+    assert signals["test_events"][0]["explicit_failure"] is True
+    assert signals["test_events"][0]["explicit_exit_codes"] == [0]
+
+
+def test_detects_malformed_and_unknown_tool_calls() -> None:
+    record = {
+        "trajectory_id": "sample-2",
+        "tools": [_tool("execute_bash")],
+        "trajectory": [
+            {"role": "system", "content": "system"},
+            {"role": "user", "content": "issue"},
+            {
+                "role": "assistant",
+                "content": "",
+                "tool_calls": [
+                    {
+                        "id": "bad",
+                        "function": {"name": "made_up_tool", "arguments": "{bad json"},
+                    }
+                ],
+            },
+            {"role": "tool", "content": "error"},
+        ],
+        "metadata": {"model_patch": {}, "reference_patch": {}},
+    }
+    signals = extract_static_signals(record)
+    assert signals["malformed_tool_turns"][0]["turn_id"] == 3
+    assert signals["unknown_tool_turns"] == [{"turn_id": 3, "tool_name": "made_up_tool"}]
+
+
+def test_extract_patch_files_is_stable_and_unique() -> None:
+    patch = "+++ b/src/a.py\n+++ b/src/b.py\n+++ b/src/a.py\n+++ /dev/null\n"
+    assert extract_patch_files(patch) == ["src/a.py", "src/b.py"]