Stop appending unverified search citations to synthesized answers

tests/test_search_observation_budget.py

@@ -1,5 +1,54 @@
 from src.clean_agent_preview import preview_tool_result_text
 from src.clean_agent_preview import preserve_requested_web_recency
+import json
+import pytest
+
+
+@pytest.mark.asyncio
+async def test_runtime_does_not_append_unverified_search_result_as_citation(monkeypatch):
+    import src.clean_agent_preview as runtime
+    from src.tool_schemas import FUNCTION_TOOL_SCHEMAS
+    from src.tool_policy import ToolPolicy
+    from src.turn_contract import resolve_full_inventory_contract
+    answer = 'The retrieved page describes an older version; it does not establish the latest release.'
+    packets = iter([
+        {'choices': [{'delta': {'tool_calls': [{'index': 0, 'id': 'lookup', 'function': {
+            'name': 'web_search', 'arguments': '{"query":"latest Python official source"}',
+        }}]}}]},
+        {'choices': [{'delta': {'content': answer}}]},
+    ])
+    class Response:
+        def __init__(self, payload): self.payload = payload
+        async def __aenter__(self): return self
+        async def __aexit__(self, *args): pass
+        def raise_for_status(self): pass
+        async def aiter_lines(self):
+            yield 'data: ' + json.dumps(self.payload)
+            yield 'data: [DONE]'
+    class Client:
+        def __init__(self, **kwargs): pass
+        async def __aenter__(self): return self
+        async def __aexit__(self, *args): pass
+        def stream(self, *args, **kwargs): return Response(next(packets))
+    async def execute(block, **kwargs):
+        return 'web_search', {'output': '[1] Old Python release\n    https://python.org/old-release/',
+                              'exit_code': 0, 'evidence_status': 'available'}
+    monkeypatch.setattr(runtime.httpx, 'AsyncClient', Client)
+    monkeypatch.setattr(runtime, 'execute_tool_block', execute)
+    schemas = [s for s in FUNCTION_TOOL_SCHEMAS if s['function']['name'] == 'web_search']
+    contract = resolve_full_inventory_contract(schemas=schemas, policy=ToolPolicy())
+    raw = [chunk async for chunk in runtime.stream_preview(
+        endpoint_url='http://test', model='test',
+        messages=[{'role': 'user', 'content': 'latest Python version? official source please'}],
+        headers={}, turn_contract=contract, session_id='test', owner='test',
+        disabled_tools=set(), tool_policy=ToolPolicy(), max_rounds=3,
+    )]
+    events = [json.loads(chunk[6:]) for chunk in raw if '[DONE]' not in chunk]
+    final = ''.join(event.get('delta', '') for event in events)
+    assert answer in final
+    assert 'old-release' not in final
+    assert '[Source:' not in final
+    assert not any(event.get('type') == 'error' for event in events)
 
 
 def test_news_intent_survives_query_rewording_without_changing_other_fresh_queries():