Screen research evidence and record bounded llm-connect refinement

Assistant: codex
Assistant-Model: gpt-6-astra
Assistant-Session: 01a0cffe-206f-7323-89d3-b20ca4cf4bf9

tests/test_research_admission.py

@@ -0,0 +1,57 @@
+import importlib.util
+import json
+from pathlib import Path
+
+REPO = Path(__file__).resolve().parents[1]
+spec = importlib.util.spec_from_file_location('admission', REPO / 'scripts/research_admission.py')
+admission = importlib.util.module_from_spec(spec)
+spec.loader.exec_module(admission)
+
+
+def block(value):
+    return '```json\n' + json.dumps(value) + '\n```'
+
+
+def test_captured_carniato_failure_is_blocked():
+    result = admission.audit(REPO / 'research/bench/infospaces/carniato-authority-03')
+    assert result['structural_status'] == 'blocked'
+    assert any('candidate contract' in f for f in result['findings'])
+    assert any("'C01'" in f for f in result['findings'])
+    assert any("'C02'" in f for f in result['findings'])
+    assert result['admission'] == 'not_granted'
+
+
+def test_missing_known_use_evidence_and_recurrence_are_blocked():
+    candidates = {'candidates': [{'id': 'P01', 'known_uses': [
+        {'implementation': 'generic chat example'}], 'recurrence': 'supported'}]}
+    result = admission.screen(block(candidates), block([]))
+    assert any('known use lacks' in f for f in result['findings'])
+    assert any('recurrence lacks' in f for f in result['findings'])
+
+
+def test_unknown_and_empty_findings_do_not_grant_admission():
+    for candidates in ([], [{'id': 'P01', 'known_uses': [], 'recurrence': 'unknown'}]):
+        result = admission.screen(block({'candidates': candidates}), block([]))
+        assert result['structural_status'] == 'passed'
+        assert result['admission'] == 'not_granted'
+        assert result['semantic_review'] == 'required'
+
+
+def test_duplicates_and_malformed_contracts_fail_closed():
+    item = {'id': 'P01', 'known_uses': [], 'recurrence': 'unknown'}
+    for candidates, edges in [({'candidates': [item, item]}, []),
+                              ({'candidates': [item]}, {}),
+                              ({'candidates': [None]}, []),
+                              ({'candidates': [item]}, [None])]:
+        assert admission.screen(block(candidates), block(edges))['structural_status'] == 'blocked'
+
+
+def test_claim_endpoint_rejected_even_with_valid_candidate_ledger():
+    candidate = {'id': 'P01', 'known_uses': [], 'recurrence': 'unknown'}
+    edge = {'subject_candidate_id': 'P01', 'object_candidate_id': 'C01',
+            'relation': 'requires', 'rationale': 'context',
+            'source_claim_and_locator': 'C01 Passage A',
+            'counterexample': 'local authority', 'observation_versus_hypothesis': 'hypothesis'}
+    result = admission.screen(block({'candidates': [candidate]}), block([edge]))
+    assert len(result['findings']) == 1
+    assert 'invalid object_candidate_id' in result['findings'][0]

tests/test_research_bench.py

@@ -182,7 +182,7 @@ def test_llm_connect_service_contract(tmp_path, finish, content, complete):
     server.start()
     root = initialize(tmp_path)
     try:
-        live = bench.LLMConnectAdapter(f'http://127.0.0.1:{server.port}', 'requested/model')
+        live = bench.LLMConnectAdapter(f'http://127.0.0.1:{server.port}', 'requested/model', reasoning_effort='low')
         if complete:
             assert bench.execute(root, live)['status'] == 'completed'
             assert len(calls) == 4
@@ -195,9 +195,12 @@ def test_llm_connect_service_contract(tmp_path, finish, content, complete):
         assert receipt['responses'][0]['model'] == 'resolved/model'
         assert receipt['responses'][0]['usage']['total_tokens'] == 42
         assert receipt['responses'][0]['finish_reason'] == finish
+        assert receipt['responses'][0]['content_characters'] == len(content)
+        assert receipt['responses'][0]['content_sha256'] is not None
         assert receipt['service_requests_attempted'] == len(calls)
         assert calls[0][1].model_name == 'requested/model'
         assert calls[0][1].max_tokens == 4000
+        assert calls[0][1].model_params['reasoning_effort'] == 'low'
         assert 'DO-NOT-PERSIST' not in receipt_text
     finally:
         server.stop()