Enforce bounded operation guardrails

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

tests/rules/test_executor.py

@@ -263,7 +263,7 @@ def test_execute_instruction_with_audit_returns_metadata():
     assert len(result.prompt_hash) == 64
     assert result.model == "test-model"
     assert result.output_validated is True
-    assert result.review_required is True
+    assert result.review_advisory is True
 
 
 def test_execute_instruction_forwards_llm_connect_run_config():
@@ -443,7 +443,7 @@ def test_resilient_report_recovers_valid_prefix_and_quarantines_truncated_tail()
     result = execute_instruction_with_audit(instr, _Event(), {}, llm)
 
     assert result.output_validated is True
-    assert result.review_required is True
+    assert result.review_advisory is True
     assert result.report is not None
     assert result.report["partial"] is True
     assert len(result.report["recommendations"]) == 7
@@ -593,7 +593,7 @@ class _MetadataBadLLM:
         return ("x" * 9000) + "{"
 
 
-def test_invalid_report_preserves_response_metadata_and_long_preview():
+def test_invalid_report_keeps_metadata_but_discards_provider_output():
     llm = _MetadataBadLLM()
     instr = _instr(
         id="daily-triage-report",
@@ -611,10 +611,11 @@ def test_invalid_report_preserves_response_metadata_and_long_preview():
         "usage": {"input_tokens": 1100, "output_tokens": 1200},
     }
     assert result.report["llm_response_metadata"] == result.llm_response_metadata
-    assert len(result.report["raw_output_preview"]) > 4000
+    assert "raw_output_preview" not in result.report
+    assert "partial_report" not in result.report
 
 
-def test_execute_instruction_with_audit_preserves_invalid_report_with_sinks(
+def test_execute_instruction_with_audit_discards_invalid_report_body(
     tmp_path,
     monkeypatch,
 ):
@@ -657,12 +658,13 @@ def test_execute_instruction_with_audit_preserves_invalid_report_with_sinks(
 
     assert result.tasks == []
     assert result.output_validated is False
-    assert result.review_required is True
+    assert result.review_advisory is True
     assert result.validation_error == "$.recommendations[0]: missing required property 'action'"
     assert result.report is not None
     assert result.report["status"] == "validation_failed"
-    assert result.report["partial_summary"] == "Generated partial triage."
-    assert result.report["partial_report"] == report_data
+    assert "partial_summary" not in result.report
+    assert "partial_report" not in result.report
+    assert "Generated partial triage." not in str(result.report)
     assert llm.call_count == 2
 
 
@@ -678,7 +680,7 @@ def test_execute_instruction_with_audit_preserves_execution_failure_with_sinks()
 
     assert result.tasks == []
     assert result.output_validated is False
-    assert result.review_required is True
+    assert result.review_advisory is True
     assert result.validation_error == "LLM_CONNECT_URL is not configured"
     assert result.report == {
         "summary": (
@@ -726,8 +728,7 @@ def test_condition_true_calls_llm():
 
 # ── review_required field ─────────────────────────────────────────────────────
 
-def test_review_required_field_on_instruction_def():
-    """review_required is a declared field on InstructionDef."""
+def test_legacy_review_required_maps_to_advisory():
     defn = InstructionDef(
         id="test",
         trusted_fields=["event.attributes.x"],
@@ -737,6 +738,7 @@ def test_review_required_field_on_instruction_def():
         review_required=True,
     )
     assert defn.review_required is True
+    assert defn.review_advisory is True
 
 
 def test_instruction_def_accepts_llm_connect_depth_config():
@@ -755,7 +757,7 @@ def test_instruction_def_accepts_llm_connect_depth_config():
     assert defn.model_params == {"reasoning_effort": "medium"}
 
 
-def test_review_required_defaults_to_false():
+def test_review_advisory_defaults_to_false():
     defn = InstructionDef(
         id="test",
         trusted_fields=[],
@@ -763,7 +765,21 @@ def test_review_required_defaults_to_false():
         prompt="p",
         output_schema="schema.json",
     )
-    assert defn.review_required is False
+    assert defn.review_required is None
+    assert defn.review_advisory is False
+
+
+def test_conflicting_review_names_are_rejected():
+    with pytest.raises(ValueError, match="review_required conflicts"):
+        InstructionDef(
+            id="test",
+            trusted_fields=[],
+            model="claude-sonnet-4-6",
+            prompt="p",
+            output_schema="schema.json",
+            review_required=True,
+            review_advisory=False,
+        )
 
 
 def test_unknown_root_in_field_path_raises():