feat: add steps_json-backed RunLog wrapper

tests/unit/test_baseline_run_log.py

@@ -0,0 +1,33 @@
+import json
+
+import pytest
+
+from app.harness.baseline_run_log import StepsJsonRunLog
+
+
+class _FakeInner:
+    def __init__(self, preds, traces):
+        self._preds, self._traces = preds, traces
+
+    async def get_predictions(self, run_id, *, question_ids=None):
+        return [p for p in self._preds if not question_ids or p["question_id"] in question_ids]
+
+    async def get_traces(self, run_id, *, question_ids=None):
+        return list(self._traces)
+
+
+@pytest.mark.asyncio
+async def test_get_traces_falls_back_to_steps_json_when_table_empty():
+    steps = [{"thought": "t", "tool_call": {"tool": "view_node", "args": {}}, "tool_output": "o"}]
+    preds = [{"video_id": "v1", "question_id": "q1", "steps_json": json.dumps(steps)}]
+    log = StepsJsonRunLog(_FakeInner(preds, traces=[]))
+    rows = await log.get_traces("r", question_ids=["q1"])
+    assert rows[0]["tool_name"] == "view_node" and rows[0]["question_id"] == "q1"
+
+
+@pytest.mark.asyncio
+async def test_get_traces_prefers_nonempty_inner_table():
+    inner_traces = [{"video_id": "v1", "question_id": "q1", "step": 0, "tool_name": "x"}]
+    log = StepsJsonRunLog(_FakeInner([], inner_traces))
+    rows = await log.get_traces("r")
+    assert rows == inner_traces