## Summary
Implements the `tool_choice` parameter for `ChatCompletionClient`
interface as requested in #6696. This allows users to restrict which
tools the model can choose from when multiple tools are available.
## Changes
### Core Interface
- Core Interface: Added `tool_choice: Tool | Literal["auto", "required",
"none"] = "auto"` parameter to `ChatCompletionClient.create()` and
`create_stream()` methods
- Model Implementations: Updated client implementations to support the
new parameter, for now, only the following model clients are supported:
- OpenAI
- Anthropic
- Azure AI
- Ollama
- `LlamaCppChatCompletionClient` currently not supported
Features
- "auto" (default): Let the model choose whether to use tools, when
there is no tool, it has no effect.
- "required": Force the model to use at least one tool
- "none": Disable tool usage completely
- Tool object: Force the model to use a specific tool
---------
Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com>
Co-authored-by: ekzhu <320302+ekzhu@users.noreply.github.com>
Co-authored-by: Eric Zhu <ekzhu@users.noreply.github.com>
<!-- Thank you for your contribution! Please review
https://microsoft.github.io/autogen/docs/Contribute before opening a
pull request. -->
The current `StreamableHttpServerParams` has timedelta values that are
not JSON serializable (config.dump_component.model_dump_json()).
This make is unusable in UIs like AGS that expect configs to be
serializable to json,
```python
class StreamableHttpServerParams(BaseModel):
"""Parameters for connecting to an MCP server over Streamable HTTP."""
type: Literal["StreamableHttpServerParams"] = "StreamableHttpServerParams"
url: str # The endpoint URL.
headers: dict[str, Any] | None = None # Optional headers to include in requests.
timeout: timedelta = timedelta(seconds=30) # HTTP timeout for regular operations.
sse_read_timeout: timedelta = timedelta(seconds=60 * 5) # Timeout for SSE read operations.
terminate_on_close: bool = True
```
This PR uses float for time outs and casts it to timedelta as needed.
```python
class StreamableHttpServerParams(BaseModel):
"""Parameters for connecting to an MCP server over Streamable HTTP."""
type: Literal["StreamableHttpServerParams"] = "StreamableHttpServerParams"
url: str # The endpoint URL.
headers: dict[str, Any] | None = None # Optional headers to include in requests.
timeout: float = 30.0 # HTTP timeout for regular operations in seconds.
sse_read_timeout: float = 300.0 # Timeout for SSE read operations in seconds.
terminate_on_close: bool = True
```
<!-- Please add a reviewer to the assignee section when you create a PR.
If you don't have the access to it, we will shortly find a reviewer and
assign them to your PR. -->
## Why are these changes needed?
<!-- Please give a short summary of the change and the problem this
solves. -->
## Related issue number
<!-- For example: "Closes #1234" -->
## Checks
- [ ] I've included any doc changes needed for
<https://microsoft.github.io/autogen/>. See
<https://github.com/microsoft/autogen/blob/main/CONTRIBUTING.md> to
build and test documentation locally.
- [ ] I've added tests (if relevant) corresponding to the changes
introduced in this PR.
- [ ] I've made sure all auto checks have passed.
<!-- Thank you for your contribution! Please review
https://microsoft.github.io/autogen/docs/Contribute before opening a
pull request. -->
<!-- Please add a reviewer to the assignee section when you create a PR.
If you don't have the access to it, we will shortly find a reviewer and
assign them to your PR. -->
## Why are these changes needed?
These changes are needed to expand AutoGen's memory capabilities with a
robust, production-ready integration with Mem0.ai.
<!-- Please give a short summary of the change and the problem this
solves. -->
This PR adds a new memory component for AutoGen that integrates with
Mem0.ai, providing a robust memory solution that supports both cloud and
local backends. The Mem0Memory class enables agents to store and
retrieve information persistently across conversation sessions.
## Key Features
- Seamless integration with Mem0.ai memory system
- Support for both cloud-based and local storage backends
- Robust error handling with detailed logging
- Full implementation of AutoGen's Memory interface
- Context updating for enhanced agent conversations
- Configurable search parameters for memory retrieval
## Related issue number
<!-- For example: "Closes #1234" -->
## Checks
- [x] I've included any doc changes needed for
<https://microsoft.github.io/autogen/>. See
<https://github.com/microsoft/autogen/blob/main/CONTRIBUTING.md> to
build and test documentation locally.
- [x] I've added tests (if relevant) corresponding to the changes
introduced in this PR.
- [ ] I've made sure all auto checks have passed.
---------
Co-authored-by: Victor Dibia <victordibia@microsoft.com>
Co-authored-by: Eric Zhu <ekzhu@users.noreply.github.com>
Co-authored-by: Ricky Loynd <riloynd@microsoft.com>
## Why are these changes needed?
This PR adds support for configurable embedding functions in
ChromaDBVectorMemory, addressing the need for users to customize how
embeddings are generated for vector similarity search. Currently,
ChromaDB memory is limited to default embedding functions, which
restricts flexibility for different use cases that may require specific
embedding models or custom embedding logic.
The implementation allows users to:
- Use different SentenceTransformer models for domain-specific
embeddings
- Integrate with OpenAI's embedding API for consistent embedding
generation
- Define custom embedding functions for specialized requirements
- Maintain backward compatibility with existing default behavior
## Related issue number
Closes#6267
## Checks
- [x] I've included any doc changes needed for
<https://microsoft.github.io/autogen/>. See
<https://github.com/microsoft/autogen/blob/main/CONTRIBUTING.md> to
build and test documentation locally.
- [x] I've added tests corresponding to the changes introduced in this
PR.
- [x] I've made sure all auto checks have passed.
---------
Co-authored-by: Victor Dibia <victordibia@microsoft.com>
Co-authored-by: Victor Dibia <victor.dibia@gmail.com>
Add OTel GenAI traces:
- `create_agent`
- `invoke_agnet`
- `execute_tool`
Introduces context manager helpers to create these traces. The helpers
also serve as instrumentation points for other instrumentation
libraries.
Resolves#6644
<!-- Thank you for your contribution! Please review
https://microsoft.github.io/autogen/docs/Contribute before opening a
pull request. -->
<!-- Please add a reviewer to the assignee section when you create a PR.
If you don't have the access to it, we will shortly find a reviewer and
assign them to your PR. -->
## Why are these changes needed?
MCP Python-sdk has started to support a new transport protocol named
`Streamble HTTP` since
[v1.8.0](https://github.com/modelcontextprotocol/python-sdk/releases/tag/v1.8.0)
last month. I heard it supersedes the SSE transport. Therefore, AutoGen
have to support it as soon as possible.
## Related issue number
https://github.com/microsoft/autogen/discussions/6517
## Checks
- [x] I've included any doc changes needed for
<https://microsoft.github.io/autogen/>. See
<https://github.com/microsoft/autogen/blob/main/CONTRIBUTING.md> to
build and test documentation locally.
- [x] I've added tests (if relevant) corresponding to the changes
introduced in this PR.
- [x] I've made sure all auto checks have passed.
---------
Co-authored-by: Victor Dibia <victordibia@microsoft.com>
Co-authored-by: Victor Dibia <victor.dibia@gmail.com>
## Why are these changes needed?
This PR introduces a new `OpenAIAgent` implementation that uses the
[OpenAI Response
API](https://platform.openai.com/docs/guides/responses-vs-chat-completions)
as its backend. The OpenAI Assistant API will be deprecated in 2026, and
the Response API is its successor. This change ensures our codebase is
future-proof and aligned with OpenAI’s latest platform direction.
### Motivation
- **Deprecation Notice:** The OpenAI Assistant API will be deprecated in
2026.
- **Future-Proofing:** The Response API is the recommended replacement
and offers improved capabilities for stateful, multi-turn, and
tool-augmented conversations.
- **AgentChat Compatibility:** The new agent is designed to conform to
the behavior and expectations of `AssistantAgent` in AgentChat, but is
implemented directly on top of the OpenAI Response API.
### Key Changes
- **New Agent:** Adds `OpenAIAgent`, a stateful agent that interacts
with the OpenAI Response API.
- **Stateful Design:** The agent maintains conversation state, tool
usage, and other metadata as required by the Response API.
- **AssistantAgent Parity:** The new agent matches the interface and
behavior of `AssistantAgent` in AgentChat, ensuring a smooth migration
path.
- **Direct OpenAI Integration:** Uses the official `openai` Python
library for all API interactions.
- **Extensible:** Designed to support future enhancements, such as
advanced tool use, function calling, and multi-modal capabilities.
### Migration Path
- Existing users of the Assistant API should migrate to the new
`OpenAIAgent` to ensure long-term compatibility.
- Documentation and examples will be updated to reflect the new agent
and its usage patterns.
### References
- [OpenAI: Responses vs. Chat
Completions](https://platform.openai.com/docs/guides/responses-vs-chat-completions)
- [OpenAI Deprecation
Notice](https://platform.openai.com/docs/guides/responses-vs-chat-completions#deprecation-timeline)
---
## Related issue number
Closes#6032
## Checks
- [ ] I've included any doc changes needed for
<https://microsoft.github.io/autogen/>. See
<https://github.com/microsoft/autogen/blob/main/CONTRIBUTING.md> to
build and test documentation locally.
- [X] I've added tests (if relevant) corresponding to the changes
introduced in this PR.
- [X] I've made sure all auto checks have passed.
Co-authored-by: Griffin Bassman <griffinbassman@gmail.com>
## Why are these changes needed?
Enables usage statistics for streaming responses by default.
There is a similar bug in the AzureAI client. Theoretically adding the
parameter
```
model_extras={"stream_options": {"include_usage": True}}
```
should fix the problem, but I'm currently unable to test that workflow
## Related issue number
closes https://github.com/microsoft/autogen/issues/6548
## Checks
- [ ] I've included any doc changes needed for
<https://microsoft.github.io/autogen/>. See
<https://github.com/microsoft/autogen/blob/main/CONTRIBUTING.md> to
build and test documentation locally.
- [ ] I've added tests (if relevant) corresponding to the changes
introduced in this PR.
- [ ] I've made sure all auto checks have passed.
<!-- Thank you for your contribution! Please review
https://microsoft.github.io/autogen/docs/Contribute before opening a
pull request. -->
<!-- Please add a reviewer to the assignee section when you create a PR.
If you don't have the access to it, we will shortly find a reviewer and
assign them to your PR. -->
There have been updates to the azure ai agent foundry sdk
(azure-ai-project). This PR updates the autogen `AzureAIAgent` which
wraps the azure ai agent. A list of some changes
- Update docstring samples to use `endpoint` (instead of connection
string previously)
- Update imports and arguments e.g, from `azure.ai.agents` etc
- Add a guide in ext docs showing Bing Search Grounding tool example.
<img width="1423" alt="image"
src="https://github.com/user-attachments/assets/0b7c8fa6-8aa5-4c20-831b-b525ac8243b7"
/>
## Why are these changes needed?
<!-- Please give a short summary of the change and the problem this
solves. -->
## Related issue number
Closes#6601
<!-- For example: "Closes #1234" -->
## Checks
- [ ] I've included any doc changes needed for
<https://microsoft.github.io/autogen/>. See
<https://github.com/microsoft/autogen/blob/main/CONTRIBUTING.md> to
build and test documentation locally.
- [ ] I've added tests (if relevant) corresponding to the changes
introduced in this PR.
- [ ] I've made sure all auto checks have passed.
<!-- Thank you for your contribution! Please review
https://microsoft.github.io/autogen/docs/Contribute before opening a
pull request. -->
<!-- Please add a reviewer to the assignee section when you create a PR.
If you don't have the access to it, we will shortly find a reviewer and
assign them to your PR. -->
## Why are these changes needed?
<!-- Please give a short summary of the change and the problem this
solves. -->
## Related issue number
resolved https://github.com/microsoft/autogen/issues/6584
## Checks
- [x] I've included any doc changes needed for
<https://microsoft.github.io/autogen/>. See
<https://github.com/microsoft/autogen/blob/main/CONTRIBUTING.md> to
build and test documentation locally.
- [x] I've added tests (if relevant) corresponding to the changes
introduced in this PR.
- [x] I've made sure all auto checks have passed.
## Why are these changes needed?
I added `created_at` to both BaseChatMessage and BaseAgentEvent classes
that store the time these Pydantic model instances are generated. And
then users will be able to use `created_at` to build up a customized
external persisting state management layer for their case.
## Related issue number
https://github.com/microsoft/autogen/discussions/6169#discussioncomment-13151540
## Checks
- [x] I've included any doc changes needed for
<https://microsoft.github.io/autogen/>. See
<https://github.com/microsoft/autogen/blob/main/CONTRIBUTING.md> to
build and test documentation locally.
- [x] I've added tests (if relevant) corresponding to the changes
introduced in this PR.
- [x] I've made sure all auto checks have passed.
---------
Co-authored-by: Jack Gerrits <jackgerrits@users.noreply.github.com>
Co-authored-by: Eric Zhu <ekzhu@users.noreply.github.com>
