utkarsh240799
6b4d2b780e
Addresses #2648. The metadata dict passed by callers was mutated in-place inside _create_memory and _create_procedural_memory (both sync and async), causing unsafe behavior under concurrent/async usage. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
401 lines
18 KiB
Python
401 lines
18 KiB
Python
import logging
|
|
from datetime import datetime, timezone
|
|
from unittest.mock import MagicMock
|
|
|
|
import pytest
|
|
|
|
from mem0.memory.main import AsyncMemory, Memory, _normalize_iso_timestamp_to_utc
|
|
|
|
|
|
def _setup_mocks(mocker):
|
|
"""Helper to setup common mocks for both sync and async fixtures"""
|
|
mock_embedder = mocker.MagicMock()
|
|
mock_embedder.return_value.embed.return_value = [0.1, 0.2, 0.3]
|
|
mocker.patch("mem0.utils.factory.EmbedderFactory.create", mock_embedder)
|
|
|
|
mock_vector_store = mocker.MagicMock()
|
|
mock_vector_store.return_value.search.return_value = []
|
|
mocker.patch(
|
|
"mem0.utils.factory.VectorStoreFactory.create", side_effect=[mock_vector_store.return_value, mocker.MagicMock()]
|
|
)
|
|
|
|
mock_llm = mocker.MagicMock()
|
|
mocker.patch("mem0.utils.factory.LlmFactory.create", mock_llm)
|
|
|
|
mocker.patch("mem0.memory.storage.SQLiteManager", mocker.MagicMock())
|
|
|
|
return mock_llm, mock_vector_store
|
|
|
|
|
|
class TestAddToVectorStoreErrors:
|
|
@pytest.fixture
|
|
def mock_memory(self, mocker):
|
|
"""Fixture that returns a Memory instance with mocker-based mocks"""
|
|
mock_llm, _ = _setup_mocks(mocker)
|
|
|
|
memory = Memory()
|
|
memory.config = mocker.MagicMock()
|
|
memory.config.custom_fact_extraction_prompt = None
|
|
memory.config.custom_update_memory_prompt = None
|
|
memory.api_version = "v1.1"
|
|
|
|
return memory
|
|
|
|
def test_empty_llm_response_fact_extraction(self, mocker, mock_memory, caplog):
|
|
"""Test empty response from LLM during fact extraction"""
|
|
# Setup
|
|
mock_memory.llm.generate_response.return_value = "invalid json" # This will trigger a JSON decode error
|
|
mock_capture_event = mocker.MagicMock()
|
|
mocker.patch("mem0.memory.main.capture_event", mock_capture_event)
|
|
|
|
# Execute
|
|
with caplog.at_level(logging.ERROR):
|
|
result = mock_memory._add_to_vector_store(
|
|
messages=[{"role": "user", "content": "test"}], metadata={}, filters={}, infer=True
|
|
)
|
|
|
|
# Verify
|
|
assert mock_memory.llm.generate_response.call_count == 1
|
|
assert result == [] # Should return empty list when no memories processed
|
|
# Check for error message in any of the log records
|
|
assert any("Error in new_retrieved_facts" in record.msg for record in caplog.records), "Expected error message not found in logs"
|
|
assert mock_capture_event.call_count == 1
|
|
|
|
def test_empty_llm_response_memory_actions(self, mock_memory, caplog):
|
|
"""Test empty response from LLM during memory actions"""
|
|
# Setup
|
|
# First call returns valid JSON, second call returns empty string
|
|
mock_memory.llm.generate_response.side_effect = ['{"facts": ["test fact"]}', ""]
|
|
|
|
# Execute
|
|
with caplog.at_level(logging.WARNING):
|
|
result = mock_memory._add_to_vector_store(
|
|
messages=[{"role": "user", "content": "test"}], metadata={}, filters={}, infer=True
|
|
)
|
|
|
|
# Verify
|
|
assert mock_memory.llm.generate_response.call_count == 2
|
|
assert result == [] # Should return empty list when no memories processed
|
|
assert "Empty response from LLM, no memories to extract" in caplog.text
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
class TestAsyncAddToVectorStoreErrors:
|
|
@pytest.fixture
|
|
def mock_async_memory(self, mocker):
|
|
"""Fixture for AsyncMemory with mocker-based mocks"""
|
|
mock_llm, _ = _setup_mocks(mocker)
|
|
|
|
memory = AsyncMemory()
|
|
memory.config = mocker.MagicMock()
|
|
memory.config.custom_fact_extraction_prompt = None
|
|
memory.config.custom_update_memory_prompt = None
|
|
memory.api_version = "v1.1"
|
|
|
|
return memory
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_async_empty_llm_response_fact_extraction(self, mock_async_memory, caplog, mocker):
|
|
"""Test empty response in AsyncMemory._add_to_vector_store"""
|
|
mocker.patch("mem0.utils.factory.EmbedderFactory.create", return_value=MagicMock())
|
|
mock_async_memory.llm.generate_response.return_value = "invalid json" # This will trigger a JSON decode error
|
|
mock_capture_event = mocker.MagicMock()
|
|
mocker.patch("mem0.memory.main.capture_event", mock_capture_event)
|
|
|
|
with caplog.at_level(logging.ERROR):
|
|
result = await mock_async_memory._add_to_vector_store(
|
|
messages=[{"role": "user", "content": "test"}], metadata={}, effective_filters={}, infer=True
|
|
)
|
|
assert mock_async_memory.llm.generate_response.call_count == 1
|
|
assert result == []
|
|
# Check for error message in any of the log records
|
|
assert any("Error in new_retrieved_facts" in record.msg for record in caplog.records), "Expected error message not found in logs"
|
|
assert mock_capture_event.call_count == 1
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_async_empty_llm_response_memory_actions(self, mock_async_memory, caplog, mocker):
|
|
"""Test empty response in AsyncMemory._add_to_vector_store"""
|
|
mocker.patch("mem0.utils.factory.EmbedderFactory.create", return_value=MagicMock())
|
|
mock_async_memory.llm.generate_response.side_effect = ['{"facts": ["test fact"]}', ""]
|
|
mock_capture_event = mocker.MagicMock()
|
|
mocker.patch("mem0.memory.main.capture_event", mock_capture_event)
|
|
|
|
with caplog.at_level(logging.WARNING):
|
|
result = await mock_async_memory._add_to_vector_store(
|
|
messages=[{"role": "user", "content": "test"}], metadata={}, effective_filters={}, infer=True
|
|
)
|
|
|
|
assert result == []
|
|
assert "Empty response from LLM, no memories to extract" in caplog.text
|
|
assert mock_capture_event.call_count == 1
|
|
|
|
|
|
def _build_memory_instance(mocker, memory_cls):
|
|
_setup_mocks(mocker)
|
|
mocker.patch("mem0.memory.main.SQLiteManager", mocker.MagicMock())
|
|
mocker.patch("mem0.memory.main.MEM0_TELEMETRY", False)
|
|
memory = memory_cls()
|
|
memory.config = mocker.MagicMock()
|
|
memory.config.custom_fact_extraction_prompt = None
|
|
memory.config.custom_update_memory_prompt = None
|
|
memory.api_version = "v1.1"
|
|
memory.vector_store = mocker.MagicMock()
|
|
memory.db = mocker.MagicMock()
|
|
return memory
|
|
|
|
|
|
def _assert_utc_timestamp(timestamp: str):
|
|
parsed = datetime.fromisoformat(timestamp)
|
|
assert parsed.tzinfo == timezone.utc
|
|
assert parsed.utcoffset().total_seconds() == 0
|
|
|
|
|
|
def test_create_memory_uses_utc_timestamps(mocker):
|
|
memory = _build_memory_instance(mocker, Memory)
|
|
memory._create_memory("new memory", {"new memory": [0.1, 0.2, 0.3]}, metadata={})
|
|
payload = memory.vector_store.insert.call_args.kwargs["payloads"][0]
|
|
_assert_utc_timestamp(payload["created_at"])
|
|
|
|
|
|
def test_update_memory_uses_utc_timestamps(mocker):
|
|
memory = _build_memory_instance(mocker, Memory)
|
|
memory.vector_store.get.return_value = MagicMock(
|
|
payload={"data": "old memory", "created_at": "2026-03-17T17:00:00-07:00"}
|
|
)
|
|
memory._update_memory("memory-id", "new memory", {"new memory": [0.1, 0.2, 0.3]}, metadata={})
|
|
payload = memory.vector_store.update.call_args.kwargs["payload"]
|
|
assert payload["created_at"] == "2026-03-18T00:00:00+00:00"
|
|
_assert_utc_timestamp(payload["updated_at"])
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_async_create_memory_uses_utc_timestamps(mocker):
|
|
memory = _build_memory_instance(mocker, AsyncMemory)
|
|
await memory._create_memory("new memory", {"new memory": [0.1, 0.2, 0.3]}, metadata={})
|
|
payload = memory.vector_store.insert.call_args.kwargs["payloads"][0]
|
|
_assert_utc_timestamp(payload["created_at"])
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_async_update_memory_uses_utc_timestamps(mocker):
|
|
memory = _build_memory_instance(mocker, AsyncMemory)
|
|
memory.vector_store.get.return_value = MagicMock(
|
|
payload={"data": "old memory", "created_at": "2026-03-17T17:00:00-07:00"}
|
|
)
|
|
await memory._update_memory("memory-id", "new memory", {"new memory": [0.1, 0.2, 0.3]}, metadata={})
|
|
payload = memory.vector_store.update.call_args.kwargs["payload"]
|
|
assert payload["created_at"] == "2026-03-18T00:00:00+00:00"
|
|
_assert_utc_timestamp(payload["updated_at"])
|
|
|
|
|
|
class TestMetadataNotMutated:
|
|
"""Tests that metadata dicts passed to memory methods are not mutated in-place (issue #2648)."""
|
|
|
|
def test_create_memory_does_not_mutate_metadata(self, mocker):
|
|
memory = _build_memory_instance(mocker, Memory)
|
|
original_metadata = {"user_id": "test_user", "category": "sports"}
|
|
metadata_copy = original_metadata.copy()
|
|
|
|
memory._create_memory("test data", {"test data": [0.1, 0.2, 0.3]}, metadata=original_metadata)
|
|
|
|
assert original_metadata == metadata_copy, (
|
|
f"_create_memory mutated the caller's metadata dict: {original_metadata} != {metadata_copy}"
|
|
)
|
|
|
|
def test_create_memory_stores_correct_payload(self, mocker):
|
|
memory = _build_memory_instance(mocker, Memory)
|
|
metadata = {"user_id": "test_user", "category": "sports"}
|
|
|
|
memory._create_memory("test data", {"test data": [0.1, 0.2, 0.3]}, metadata=metadata)
|
|
|
|
payload = memory.vector_store.insert.call_args.kwargs["payloads"][0]
|
|
assert payload["data"] == "test data"
|
|
assert payload["user_id"] == "test_user"
|
|
assert payload["category"] == "sports"
|
|
assert "hash" in payload
|
|
assert "created_at" in payload
|
|
|
|
def test_create_memory_with_none_metadata(self, mocker):
|
|
memory = _build_memory_instance(mocker, Memory)
|
|
|
|
memory._create_memory("test data", {"test data": [0.1, 0.2, 0.3]}, metadata=None)
|
|
|
|
payload = memory.vector_store.insert.call_args.kwargs["payloads"][0]
|
|
assert payload["data"] == "test data"
|
|
assert "hash" in payload
|
|
|
|
def test_create_memory_shared_metadata_across_calls(self, mocker):
|
|
"""Verify that sharing a metadata dict between multiple _create_memory calls is safe."""
|
|
memory = _build_memory_instance(mocker, Memory)
|
|
shared_metadata = {"user_id": "test_user"}
|
|
|
|
memory._create_memory("first memory", {"first memory": [0.1, 0.2, 0.3]}, metadata=shared_metadata)
|
|
memory._create_memory("second memory", {"second memory": [0.4, 0.5, 0.6]}, metadata=shared_metadata)
|
|
|
|
assert shared_metadata == {"user_id": "test_user"}, "shared metadata was mutated across calls"
|
|
|
|
# Verify each call got the correct data
|
|
first_payload = memory.vector_store.insert.call_args_list[0].kwargs["payloads"][0]
|
|
second_payload = memory.vector_store.insert.call_args_list[1].kwargs["payloads"][0]
|
|
assert first_payload["data"] == "first memory"
|
|
assert second_payload["data"] == "second memory"
|
|
|
|
def test_create_memory_preserves_role_and_actor_id_in_history(self, mocker):
|
|
"""Verify that role and actor_id from metadata flow through to add_history after deepcopy."""
|
|
memory = _build_memory_instance(mocker, Memory)
|
|
metadata = {"user_id": "test_user", "role": "assistant", "actor_id": "bot-1"}
|
|
|
|
memory._create_memory("test data", {"test data": [0.1, 0.2, 0.3]}, metadata=metadata)
|
|
|
|
# Verify the payload stored in vector store has all fields
|
|
payload = memory.vector_store.insert.call_args.kwargs["payloads"][0]
|
|
assert payload["role"] == "assistant"
|
|
assert payload["actor_id"] == "bot-1"
|
|
assert payload["user_id"] == "test_user"
|
|
assert payload["data"] == "test data"
|
|
|
|
# Verify add_history received the correct role and actor_id
|
|
history_call = memory.db.add_history.call_args
|
|
assert history_call.kwargs["role"] == "assistant"
|
|
assert history_call.kwargs["actor_id"] == "bot-1"
|
|
|
|
# And the original metadata is still untouched
|
|
assert metadata == {"user_id": "test_user", "role": "assistant", "actor_id": "bot-1"}
|
|
|
|
def test_create_memory_with_nested_metadata_not_mutated(self, mocker):
|
|
"""Verify deepcopy protects nested structures in metadata."""
|
|
memory = _build_memory_instance(mocker, Memory)
|
|
metadata = {"user_id": "test_user", "tags": ["important", "urgent"], "config": {"key": "val"}}
|
|
import copy
|
|
metadata_snapshot = copy.deepcopy(metadata)
|
|
|
|
memory._create_memory("test data", {"test data": [0.1, 0.2, 0.3]}, metadata=metadata)
|
|
|
|
assert metadata == metadata_snapshot, "Nested metadata structures were mutated"
|
|
|
|
def test_update_memory_does_not_mutate_metadata(self, mocker):
|
|
memory = _build_memory_instance(mocker, Memory)
|
|
memory.vector_store.get.return_value = MagicMock(
|
|
payload={"data": "old data", "user_id": "test_user", "created_at": "2026-01-01T00:00:00+00:00"}
|
|
)
|
|
original_metadata = {"category": "updated"}
|
|
metadata_copy = original_metadata.copy()
|
|
|
|
memory._update_memory("mem-id", "new data", {"new data": [0.1, 0.2, 0.3]}, metadata=original_metadata)
|
|
|
|
assert original_metadata == metadata_copy, (
|
|
f"_update_memory mutated the caller's metadata dict: {original_metadata} != {metadata_copy}"
|
|
)
|
|
|
|
def test_add_to_vector_store_no_infer_does_not_mutate_metadata(self, mocker):
|
|
"""Verify _add_to_vector_store with infer=False doesn't leak metadata between messages."""
|
|
memory = _build_memory_instance(mocker, Memory)
|
|
memory.embedding_model.embed.return_value = [0.1, 0.2, 0.3]
|
|
|
|
original_metadata = {"user_id": "test_user"}
|
|
metadata_copy = original_metadata.copy()
|
|
|
|
messages = [
|
|
{"role": "user", "content": "Hello"},
|
|
{"role": "assistant", "content": "Hi there", "name": "bot-1"},
|
|
]
|
|
|
|
result = memory._add_to_vector_store(messages, original_metadata, filters={}, infer=False)
|
|
|
|
# Metadata should not be mutated
|
|
assert original_metadata == metadata_copy, (
|
|
f"_add_to_vector_store mutated the caller's metadata: {original_metadata}"
|
|
)
|
|
|
|
# Should have created 2 memories
|
|
assert len(result) == 2
|
|
assert result[0]["role"] == "user"
|
|
assert result[1]["role"] == "assistant"
|
|
assert result[1]["actor_id"] == "bot-1"
|
|
|
|
# Verify each insert got distinct payloads with correct roles
|
|
insert_calls = memory.vector_store.insert.call_args_list
|
|
first_payload = insert_calls[0].kwargs["payloads"][0]
|
|
second_payload = insert_calls[1].kwargs["payloads"][0]
|
|
assert first_payload["role"] == "user"
|
|
assert "actor_id" not in first_payload # user message has no name
|
|
assert second_payload["role"] == "assistant"
|
|
assert second_payload["actor_id"] == "bot-1"
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_async_create_memory_does_not_mutate_metadata(self, mocker):
|
|
memory = _build_memory_instance(mocker, AsyncMemory)
|
|
original_metadata = {"user_id": "test_user", "category": "sports"}
|
|
metadata_copy = original_metadata.copy()
|
|
|
|
await memory._create_memory("test data", {"test data": [0.1, 0.2, 0.3]}, metadata=original_metadata)
|
|
|
|
assert original_metadata == metadata_copy, (
|
|
f"async _create_memory mutated the caller's metadata dict: {original_metadata} != {metadata_copy}"
|
|
)
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_async_create_memory_shared_metadata_across_calls(self, mocker):
|
|
memory = _build_memory_instance(mocker, AsyncMemory)
|
|
shared_metadata = {"user_id": "test_user"}
|
|
|
|
await memory._create_memory("first memory", {"first memory": [0.1, 0.2, 0.3]}, metadata=shared_metadata)
|
|
await memory._create_memory("second memory", {"second memory": [0.4, 0.5, 0.6]}, metadata=shared_metadata)
|
|
|
|
assert shared_metadata == {"user_id": "test_user"}, "shared metadata was mutated across async calls"
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_async_add_to_vector_store_no_infer_does_not_mutate_metadata(self, mocker):
|
|
"""Verify async _add_to_vector_store with infer=False doesn't leak metadata between messages."""
|
|
memory = _build_memory_instance(mocker, AsyncMemory)
|
|
memory.embedding_model.embed.return_value = [0.1, 0.2, 0.3]
|
|
|
|
original_metadata = {"user_id": "test_user"}
|
|
metadata_copy = original_metadata.copy()
|
|
|
|
messages = [
|
|
{"role": "user", "content": "Hello"},
|
|
{"role": "assistant", "content": "Hi there", "name": "bot-1"},
|
|
]
|
|
|
|
result = await memory._add_to_vector_store(messages, original_metadata, effective_filters={}, infer=False)
|
|
|
|
assert original_metadata == metadata_copy, (
|
|
f"async _add_to_vector_store mutated the caller's metadata: {original_metadata}"
|
|
)
|
|
assert len(result) == 2
|
|
assert result[0]["role"] == "user"
|
|
assert result[1]["role"] == "assistant"
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_async_update_memory_does_not_mutate_metadata(self, mocker):
|
|
memory = _build_memory_instance(mocker, AsyncMemory)
|
|
memory.vector_store.get.return_value = MagicMock(
|
|
payload={"data": "old data", "user_id": "test_user", "created_at": "2026-01-01T00:00:00+00:00"}
|
|
)
|
|
original_metadata = {"category": "updated"}
|
|
metadata_copy = original_metadata.copy()
|
|
|
|
await memory._update_memory("mem-id", "new data", {"new data": [0.1, 0.2, 0.3]}, metadata=original_metadata)
|
|
|
|
assert original_metadata == metadata_copy, (
|
|
f"async _update_memory mutated the caller's metadata dict: {original_metadata} != {metadata_copy}"
|
|
)
|
|
|
|
|
|
def test_normalize_iso_timestamp_to_utc_preserves_naive_values():
|
|
assert _normalize_iso_timestamp_to_utc("2026-03-18T00:00:00") == "2026-03-18T00:00:00"
|
|
|
|
|
|
def test_normalize_iso_timestamp_to_utc_converts_pacific():
|
|
result = _normalize_iso_timestamp_to_utc("2026-03-17T17:00:00-07:00")
|
|
assert result == "2026-03-18T00:00:00+00:00"
|
|
|
|
|
|
def test_normalize_iso_timestamp_to_utc_handles_none():
|
|
assert _normalize_iso_timestamp_to_utc(None) is None
|
|
|
|
|
|
def test_normalize_iso_timestamp_to_utc_handles_empty():
|
|
assert _normalize_iso_timestamp_to_utc("") == ""
|