Normalize Glas execution evidence

Assistant: codex
Assistant-Model: gpt-5.6-sol
Assistant-Session: 01a028de-e2c8-7732-8521-46a7fc5db82f

tests/test_ops_run_queue.py

@@ -225,6 +225,47 @@ async def test_claim_and_complete_roundtrip(monkeypatch: pytest.MonkeyPatch) ->
     assert open_run.result["path"] == "briefs/x.md"
 
 
+@pytest.mark.asyncio
+async def test_complete_persists_only_normalized_glas_evidence() -> None:
+    from activity_core import ops_run_queue as oq
+
+    row = MagicMock()
+    row.state = "claimed"
+    row.claim_owner = "worker-1"
+    row.result = {}
+    session = AsyncMock()
+    session.get = AsyncMock(return_value=row)
+
+    done = await oq.complete_ops_run(
+        session,
+        uuid.uuid4(),
+        worker_id="worker-1",
+        result={
+            "ok": True,
+            "evidence": {
+                "request_id": "request-1",
+                "profile_ref": "harness.agent-dev@1.0.0",
+                "rein_id": "rein-aharness",
+                "outcome": "succeeded",
+                "duration_s": 0,
+            },
+            "tool_output": "must not persist",
+        },
+    )
+
+    assert done is row
+    assert row.result == {
+        "ok": True,
+        "execution_evidence": {
+            "request_id": "request-1",
+            "profile_ref": "harness.agent-dev@1.0.0",
+            "rein_id": "rein-aharness",
+            "outcome": "succeeded",
+            "duration_s": 0,
+        },
+    }
+
+
 @pytest.mark.asyncio
 async def test_fail_reopen_under_max_attempts(monkeypatch: pytest.MonkeyPatch) -> None:
     from activity_core import ops_run_queue as oq
@@ -268,6 +309,44 @@ async def test_fail_permanent_at_max_attempts(monkeypatch: pytest.MonkeyPatch) -
     assert row.state == "failed"
 
 
+@pytest.mark.asyncio
+async def test_fail_persists_redacted_failure_evidence() -> None:
+    from activity_core import ops_run_queue as oq
+
+    row = MagicMock()
+    row.state = "claimed"
+    row.claim_owner = "worker-1"
+    row.attempt = 1
+    row.result = {}
+    session = AsyncMock()
+    session.get = AsyncMock(return_value=row)
+
+    failed = await oq.fail_ops_run(
+        session,
+        uuid.uuid4(),
+        worker_id="worker-1",
+        error="execution refused",
+        result={
+            "ok": False,
+            "evidence": {
+                "request_id": "request-failed",
+                "profile_ref": "harness.agent-dev@1.0.0",
+                "rein_id": "rein-aharness",
+                "outcome": "failed",
+                "failure_stage": "execution",
+                "error": "execution failed; inspect direct caller error",
+                "duration_s": 3.5,
+            },
+            "tool_error": "raw provider failure must not persist",
+        },
+    )
+
+    assert failed is row
+    assert row.result["error"] == "execution refused"
+    assert row.result["execution_evidence"]["failure_stage"] == "execution"
+    assert "tool_error" not in row.result
+
+
 def test_label_filter_any_vs_all() -> None:
     """Document labels_mode semantics used by claim_ops_runs."""
     row_labels = {"automated", "research-brief"}