Normalize Glas execution evidence

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

tests/test_glas_evidence.py

@@ -0,0 +1,115 @@
+"""Normalized Glas evidence boundary (ACTIVITY-WP-0032-T04)."""
+
+from __future__ import annotations
+
+import json
+
+from activity_core.glas_evidence import (
+    normalise_execution_evidence,
+    normalise_ops_result,
+)
+
+
+def _gateway_result() -> dict:
+    return {
+        "ok": True,
+        "evidence": {
+            "request_id": "request-1",
+            "correlation_id": "corr-1",
+            "actor": "agt",
+            "project": "activity-core",
+            "target_repo": "activity-core",
+            "contract_version": "1.0",
+            "profile_ref": "harness.agent-dev@1.0.0",
+            "rein_id": "rein-aharness",
+            "rein_version": "0.1.0",
+            "model_route": "claude-code-cli",
+            "resolved_model": "claude-sonnet-4-6",
+            "sandbox_profile": "profile.bwrap-local",
+            "sandbox_id": "sandbox-1",
+            "tool_profile": "green-commit-only",
+            "outcome": "succeeded",
+            "started_at": "2026-08-22T20:00:00Z",
+            "finished_at": "2026-08-22T20:00:05Z",
+            "duration_s": 5.0,
+            "tokens_spent": 0,
+            "token_budget": 60000,
+            "commit_sha": "deadbeef",
+            "artifacts": ["README.md"],
+            "tool_events_count": 0,
+            "tool_events_completeness": "unavailable",
+            "refs": {
+                "assignment_ref": "assignment:42",
+                "goal_refs": ["goal:42@1", {"credential": "must-drop"}],
+                "api_key": "must-drop",
+            },
+            "raw_prompt": "must-drop",
+            "provider_response": {"must": "drop"},
+        },
+        "tool_output": "sensitive direct model output",
+        "tool_error": "sensitive provider exception",
+        "provider_blob": {"credential": "must-drop"},
+    }
+
+
+def test_normalises_gateway_result_and_drops_direct_output() -> None:
+    result = normalise_ops_result(_gateway_result())
+
+    assert result["ok"] is True
+    evidence = result["execution_evidence"]
+    assert evidence["profile_ref"] == "harness.agent-dev@1.0.0"
+    assert evidence["rein_id"] == "rein-aharness"
+    assert evidence["tokens_spent"] == 0
+    assert evidence["tool_events_count"] == 0
+    assert evidence["tool_events_completeness"] == "unavailable"
+    assert evidence["refs"] == {
+        "assignment_ref": "assignment:42",
+        "goal_refs": ["goal:42@1"],
+    }
+
+    serialized = json.dumps(result)
+    for forbidden in (
+        "tool_output",
+        "tool_error",
+        "provider_blob",
+        "raw_prompt",
+        "provider_response",
+        "credential",
+    ):
+        assert forbidden not in serialized
+
+
+def test_rejects_invalid_enums_and_non_finite_measurements() -> None:
+    evidence = normalise_execution_evidence(
+        {
+            "outcome": "maybe",
+            "failure_stage": "provider-internal",
+            "duration_s": float("nan"),
+            "tokens_spent": -1,
+            "tool_events_completeness": "unknown-ish",
+        }
+    )
+
+    assert evidence == {}
+
+
+def test_keeps_legacy_artifact_fields_but_not_unknown_blobs() -> None:
+    result = normalise_ops_result(
+        {
+            "ok": True,
+            "path": "briefs/report.md",
+            "head_after": "deadbeef",
+            "target_repo": "activity-core",
+            "artifact_urls": [
+                {"kind": "report", "label": "Report", "url": "https://example.test/a"},
+                {"kind": "unsafe", "label": "Unsafe", "url": "file:///tmp/key"},
+            ],
+            "messages": [{"role": "user", "content": "secret"}],
+        }
+    )
+
+    assert result["path"] == "briefs/report.md"
+    assert result["artifact_urls"] == [
+        {"kind": "report", "label": "Report", "url": "https://example.test/a"}
+    ]
+    assert "messages" not in result

tests/test_glas_profile_selection.py

@@ -148,6 +148,13 @@ class TestExecutionRefs:
 
         assert refs == {"resource_envelope_refs": ["ok"]}
 
+    def test_drops_non_string_items_in_reference_lists(self) -> None:
+        refs = normalise_execution_refs(
+            {"goal_refs": ["goal:1@1", {"credential": "must-drop"}, 17]}
+        )
+
+        assert refs == {"goal_refs": ["goal:1@1"]}
+
     @pytest.mark.parametrize("bad", [None, "refs", ["a"], 5])
     def test_non_dict_becomes_empty(self, bad) -> None:
         assert normalise_execution_refs(bad) == {}

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"}

tests/test_run_artifacts.py

@@ -7,6 +7,7 @@ from datetime import datetime, timedelta, timezone
 from unittest.mock import MagicMock
 
 from activity_core.run_artifacts import (
+    _ops_summary,
     artifacts_from_ops_result,
     build_forgejo_blob_url,
     match_ops_runs_to_activity_run,
@@ -88,3 +89,42 @@ def test_match_ops_runs_window_fallback() -> None:
     matched = match_ops_runs_to_activity_run(ar, [far, near])
     assert near in matched
     assert far not in matched
+
+
+def test_ops_summary_exposes_compact_execution_constellation() -> None:
+    now = datetime(2026, 8, 22, 20, 0, tzinfo=timezone.utc)
+    row = MagicMock()
+    row.id = uuid.uuid4()
+    row.state = "succeeded"
+    row.title = "Profiled run"
+    row.target_repo = "activity-core"
+    row.claim_owner = "glas-worker@railiance01"
+    row.attempt = 1
+    row.triggering_event_id = "event-1"
+    row.source_id = "profiled"
+    row.approach_hint = "legacy-only"
+    row.harness_profile_ref = "harness.agent-dev@1.0.0"
+    row.execution_refs = {"goal_refs": ["goal:42@1"]}
+    row.created_at = now
+    row.updated_at = now
+    row.result = {
+        "ok": True,
+        "execution_evidence": {
+            "profile_ref": "harness.agent-dev@1.0.0",
+            "rein_id": "rein-aharness",
+            "rein_version": "0.1.0",
+            "resolved_model": "claude-sonnet-4-6",
+            "sandbox_profile": "profile.bwrap-local",
+            "outcome": "succeeded",
+            "duration_s": 5.2,
+        },
+        "raw_output": "must-drop-even-for-historic-rows",
+    }
+
+    summary = _ops_summary(row)
+
+    assert summary["execution_evidence"]["rein_id"] == "rein-aharness"
+    assert summary["result"]["execution_evidence"]["profile_ref"] == (
+        "harness.agent-dev@1.0.0"
+    )
+    assert "raw_output" not in str(summary)