fix(tests): update 35 failing tests for v3 single-pass pipeline

Tests were written for the old two-pass extraction pipeline (extract
facts + merge with ADD/UPDATE/DELETE). V3 uses single-pass ADD-only
extraction with one LLM call returning {"memory": [...]}.

Changes by category:

Old pipeline tests (13 failures):
- Delete TestHallucinatedIdGuard entirely (tests UPDATE/DELETE ID
  resolution that no longer exists)
- Update error log assertions to match v3 log messages
- Change LLM mock from 2-call side_effect to 1-call return_value
- Update vllm thinking tag tests for single-call format

ensure_json_instruction removed (3):
- Delete source-inspection tests (function still exists in utils
  but is no longer called from _add_to_vector_store)

UTC timestamp normalization removed (2):
- Update expected timestamps to stored-as-is (no UTC conversion)
- Remove _normalize_iso_timestamp_to_utc import

_search_vector_store signature: top_k -> limit (2):
- Update test calls to use limit= parameter

Context manager + close/db removed (6):
- Delete tests for __enter__/__exit__/close/db that were removed

Vector store BM25 config (3):
- Qdrant: add sparse_vectors_config to create_col assertion,
  named vector format {"": vector} in update assertion
- MongoDB: assert_any_call for both vector + text search indexes

Misc (6):
- test_search_handles_incomplete_payloads: expect 1 result (v3
  filters entries without 'data' key)
- Embedding cache tests: update for embed_batch (1 call) vs
  individual embed (was 2 calls)
- Graph reset tests: delete (graph support removed)
- use_azure_credential: update expected sensitivity to True

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

tests/llms/test_vllm.py

@@ -187,22 +187,21 @@ def create_mocked_async_memory():
 def test_thinking_tags_sync():
     """Test thinking tags handling in Memory._add_to_vector_store (sync)."""
     memory, mock_llm, mock_vector_store = create_mocked_memory()
-    
-    # Mock LLM responses for both phases
+
+    # v3 pipeline: single LLM call returning ADD-only memories
     mock_llm.generate_response.side_effect = [
-        '        <think>Sync fact extraction</think>  \n{"facts": ["User loves sci-fi"]}',
-        '        <think>Sync memory actions</think>  \n{"memory": [{"text": "Loves sci-fi", "event": "ADD"}]}'
+        '<think>Sync extraction</think>\n{"memory": [{"text": "Loves sci-fi", "attributed_to": "user"}]}'
     ]
-    
+
     mock_vector_store.search.return_value = []
-    
+
     result = memory._add_to_vector_store(
         messages=[{"role": "user", "content": "I love sci-fi movies"}],
-        metadata={}, 
-        filters={}, 
+        metadata={},
+        filters={},
         infer=True
     )
-    
+
     assert len(result) == 1
     assert result[0]["memory"] == "Loves sci-fi"
     assert result[0]["event"] == "ADD"
@@ -213,13 +212,12 @@ def test_thinking_tags_sync():
 async def test_async_thinking_tags_async():
     """Test thinking tags handling in AsyncMemory._add_to_vector_store."""
     memory, mock_llm, mock_vector_store = create_mocked_async_memory()
-    
-    # Directly mock llm.generate_response instead of via asyncio.to_thread
+
+    # v3 pipeline: single LLM call returning ADD-only memories
     mock_llm.generate_response.side_effect = [
-        '        <think>Async fact extraction</think>  \n{"facts": ["User loves sci-fi"]}',
-        '        <think>Async memory actions</think>  \n{"memory": [{"text": "Loves sci-fi", "event": "ADD"}]}'
+        '<think>Async extraction</think>\n{"memory": [{"text": "Loves sci-fi", "attributed_to": "user"}]}'
     ]
-    
+
     # Mock asyncio.to_thread to call the function directly (bypass threading)
     async def mock_to_thread(func, *args, **kwargs):
         if func == mock_llm.generate_response:
@@ -230,15 +228,15 @@ async def test_async_thinking_tags_async():
             return []
         else:
             return func(*args, **kwargs)
-    
+
     with patch('mem0.memory.main.asyncio.to_thread', side_effect=mock_to_thread):
         result = await memory._add_to_vector_store(
             messages=[{"role": "user", "content": "I love sci-fi movies"}],
-            metadata={}, 
-            effective_filters={}, 
+            metadata={},
+            effective_filters={},
             infer=True
         )
-    
+
     assert len(result) == 1
     assert result[0]["memory"] == "Loves sci-fi"
     assert result[0]["event"] == "ADD"