Python: Fix Mem0Provider.invoking() to support AsyncMemory (OSS) client#3844
Python: Fix Mem0Provider.invoking() to support AsyncMemory (OSS) client#3844
Conversation
Co-authored-by: markwallace-microsoft <127216156+markwallace-microsoft@users.noreply.github.com>
Co-authored-by: markwallace-microsoft <127216156+markwallace-microsoft@users.noreply.github.com>
Co-authored-by: markwallace-microsoft <127216156+markwallace-microsoft@users.noreply.github.com>
Python Test Coverage Report •
Python Unit Test Overview
|
||||||||||||||||||||||||||||||
There was a problem hiding this comment.
Pull request overview
This PR fixes compatibility between Mem0Provider.invoking() and the Mem0 OSS client (AsyncMemory) by passing scoping parameters (user_id, agent_id, run_id) as direct keyword arguments when required, while preserving the existing filters-dict behavior for the Mem0 Platform client (AsyncMemoryClient).
Changes:
- Update
Mem0Provider.invoking()to route scoping parameters differently based on whether the client isAsyncMemory(OSS) vsAsyncMemoryClient(Platform). - Add unit tests validating the OSS client call shape for
search().
Reviewed changes
Copilot reviewed 2 out of 2 changed files in this pull request and generated 2 comments.
| File | Description |
|---|---|
| python/packages/mem0/agent_framework_mem0/_provider.py | Adds OSS-vs-Platform branching to pass scoping parameters in the format expected by each client. |
| python/packages/mem0/tests/test_mem0_context_provider.py | Adds an OSS client mock fixture and tests asserting search() receives scoping params as direct kwargs. |
| async def test_model_invoking_with_oss_client_all_params(self, mock_oss_mem0_client: AsyncMock) -> None: | ||
| """Test invoking with OSS client with all scoping parameters.""" | ||
| provider = Mem0Provider( | ||
| user_id="user123", | ||
| agent_id="agent456", | ||
| thread_id="thread789", | ||
| mem0_client=mock_oss_mem0_client, | ||
| ) | ||
| message = Message(role="user", text="Hello") | ||
|
|
||
| mock_oss_mem0_client.search.return_value = [] | ||
|
|
||
| await provider.invoking(message) | ||
|
|
||
| # Verify search was called with direct kwargs | ||
| call_args = mock_oss_mem0_client.search.call_args | ||
| assert call_args.kwargs["user_id"] == "user123" | ||
| assert call_args.kwargs["agent_id"] == "agent456" | ||
| assert call_args.kwargs["run_id"] == "thread789" | ||
| assert call_args.kwargs.get("filters") is None |
There was a problem hiding this comment.
The new OSS-client tests cover user_id/agent_id/run_id, but don’t cover the application_id path. Since _build_filters() adds app_id, please add a test that sets application_id with an OSS client and asserts the expected search() call shape (to prevent regressions / unexpected-kwarg issues).
| # OSS client: pass scoping parameters as direct kwargs | ||
| search_kwargs.update(filters) | ||
| else: | ||
| # Platform client: pass scoping parameters in filters dict |
There was a problem hiding this comment.
In the OSS branch, search_kwargs.update(filters) moves every filter key (including app_id from application_id) from the prior filters={...} payload into top-level kwargs. This changes behavior vs the Platform path and could break if the OSS AsyncMemory.search() API does not accept app_id as a keyword argument. Consider only unpacking the scoping kwargs the OSS client expects (e.g., user_id/agent_id/run_id) and keep any remaining filter keys in a filters dict (or omit them) to avoid passing unexpected kwargs.
| # OSS client: pass scoping parameters as direct kwargs | |
| search_kwargs.update(filters) | |
| else: | |
| # Platform client: pass scoping parameters in filters dict | |
| # OSS client: only pass supported scoping parameters as direct kwargs | |
| oss_scoping_keys = ("user_id", "agent_id", "run_id") | |
| for key in oss_scoping_keys: | |
| value = filters.get(key) | |
| if value is not None: | |
| search_kwargs[key] = value | |
| else: | |
| # Platform client: pass all scoping parameters in filters dict |
AsyncMemory (OSS) expects user_id/agent_id/run_id as direct kwargs, while AsyncMemoryClient (Platform) expects them in a filters dict. Adds tests for both client types. Port of fix from microsoft#3844 to new Mem0ContextProvider.
AsyncMemory (OSS) expects user_id/agent_id/run_id as direct kwargs, while AsyncMemoryClient (Platform) expects them in a filters dict. Adds tests for both client types. Port of fix from microsoft#3844 to new Mem0ContextProvider.
AsyncMemory (OSS) expects user_id/agent_id/run_id as direct kwargs, while AsyncMemoryClient (Platform) expects them in a filters dict. Adds tests for both client types. Port of fix from microsoft#3844 to new Mem0ContextProvider.
AsyncMemory (OSS) expects user_id/agent_id/run_id as direct kwargs, while AsyncMemoryClient (Platform) expects them in a filters dict. Adds tests for both client types. Port of fix from microsoft#3844 to new Mem0ContextProvider.
…ypes, update all consumers (microsoft#3850) * PR2: Wire context provider pipeline and update all internal consumers - Replace AgentThread with AgentSession across all packages - Replace ContextProvider with BaseContextProvider across all packages - Replace context_provider param with context_providers (Sequence) - Replace thread= with session= in run() signatures - Replace get_new_thread() with create_session() - Add get_session(service_session_id) to agent interface - DurableAgentThread -> DurableAgentSession - Remove _notify_thread_of_new_messages from WorkflowAgent - Wire before_run/after_run context provider pipeline in RawAgent - Auto-inject InMemoryHistoryProvider when no providers configured * fix: update all tests for context provider pipeline, fix lazy-loaders, remove old test files * refactor: update all sample files for context provider pipeline (AgentThread→AgentSession, ContextProvider→BaseContextProvider) * fix: update remaining ag-ui references (client docstring, getting_started sample) * fix: make get_session service_session_id keyword-only to avoid confusion with session_id * refactor: rename _RunContext.thread_messages to session_messages * refactor: remove _threads.py, _memory.py, and old provider files; migrate devui to use plain message lists * rename: remove _new_ prefix from test files * refactor: rewrite SlidingWindowChatMessageStore as SlidingWindowHistoryProvider(InMemoryHistoryProvider) * fix: read full history from session state directly instead of reaching into provider internals * fix: update stale .pyi stubs, sample imports, and README references for new provider types * fix: remove stale message_store, _notify_thread_of_new_messages, and session_id.key references in samples * refactor: merge context_providers and sessions sample folders into sessions, remove aggregate_context_provider * refactor: UserInfoMemory stores state in session.state instead of instance attributes * feat: add Pydantic BaseModel support to session state serialization Pydantic models stored in session.state are now automatically serialized via model_dump() and restored via model_validate() during to_dict()/from_dict() round-trips. Models are auto-registered on first serialization; use register_state_type() for cold-start deserialization. Also export register_state_type as a public API. * fix mem0 * Update sample README links and descriptions for session terminology - Replace 'thread' with 'session' in sample descriptions across all READMEs - Update file links for renamed samples (mem0_sessions, redis_sessions, etc.) - Fix Threads section → Sessions section in main samples/README.md - Update tools, middleware, workflows, durabletask, azure_functions READMEs - Update architecture diagrams in concepts/tools/README.md - Update migration guides (autogen, semantic-kernel) * Fix broken Redis README link to renamed sample * Fix Mem0 OSS client search: pass scoping params as direct kwargs AsyncMemory (OSS) expects user_id/agent_id/run_id as direct kwargs, while AsyncMemoryClient (Platform) expects them in a filters dict. Adds tests for both client types. Port of fix from microsoft#3844 to new Mem0ContextProvider. * Fix rebase issues: restore missing _conversation_state.py and checkpoint decode logic - Add back _conversation_state.py (encode/decode_chat_messages) lost in rebase - Fix on_checkpoint_restore to decode cache/conversation with decode_chat_messages - Fix on_checkpoint_restore to use decode_checkpoint_value for pending requests - Add tests/workflow/__init__.py for relative import support - Fix test_agent_executor checkpoint selection (checkpoints[1] not superstep) * Add STORES_BY_DEFAULT ClassVar to skip redundant InMemoryHistoryProvider injection Chat clients that store history server-side by default (OpenAI Responses API, Azure AI Agent) now declare STORES_BY_DEFAULT = True. The agent checks this during auto-injection and skips InMemoryHistoryProvider unless the user explicitly sets store=False. * Fix broken markdown links in azure_ai and redis READMEs * Fix getting-started samples to use session API instead of removed thread/ContextProvider API * updates to workflow as agent * fix group chat import * Rename Thread→Session throughout, fix service_session_id propagation, remove stale AGUIThread - Fix: Propagate conversation_id from ChatResponse back to session.service_session_id in both streaming and non-streaming paths in _agents.py - Rename AgentThreadException → AgentSessionException - Remove stale AGUIThread from ag_ui lazy-loader - Rename use_service_thread → use_service_session in ag-ui package - Rename test functions from *_thread_* to *_session_* - Rename sample files from *_thread* to *_session* - Update docstrings and comments: thread → session - Update _mcp.py kwargs filter: add 'session' alongside 'thread' - Fix ContinuationToken docstring example: thread=thread → session=session - Fix _clients.py docstring: 'Agent threads' → 'Agent sessions' * Fix broken markdown links after thread→session file renames * fix azure ai test
Pull request was closed
Motivation and Context
Mem0Provider.invoking()passes scoping parameters (user_id,agent_id,run_id) in afiltersdict tosearch(). This works forAsyncMemoryClient(Platform) but breaksAsyncMemory(OSS), which expects these as direct kwargs per its signature:Description
Detect client type with
isinstance()and route parameters accordingly:Changes:
_provider.py: Added client type detection ininvoking()(14 lines modified)test_mem0_context_provider.py: Added OSS client fixture and 2 test cases (59 lines added)Note:
invoked()already passes params as direct kwargs toadd(), which works for both clients. This alignsinvoking()with the same pattern.Contribution Checklist
Warning
Firewall rules blocked me from connecting to one or more addresses (expand for details)
I tried to connect to the following addresses, but was blocked by firewall rules:
astral.sh/usr/bin/curl curl -LsSf REDACTED --show-toplevel(dns block)If you need me to access, download, or install something from one of these locations, you can either:
Original prompt
💡 You can make Copilot smarter by setting up custom instructions, customizing its development environment and configuring Model Context Protocol (MCP) servers. Learn more Copilot coding agent tips in the docs.