ag2 0.9.1.post0__tar.gz → 0.9.2__tar.gz

{ag2-0.9.1.post0 → ag2-0.9.2}/.github/PULL_REQUEST_TEMPLATE.md

@@ -12,6 +12,6 @@
 
 ## Checks
 
-- [ ] I've included any doc changes needed for https://docs.ag2.ai/. See https://docs.ag2.ai/docs/contributor-guide/documentation to build and test documentation locally.
+- [ ] I've included any doc changes needed for https://docs.ag2.ai/. See https://docs.ag2.ai/latest/docs/contributor-guide/documentation/ 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.

{ag2-0.9.1.post0 → ag2-0.9.2}/.github/workflows/build-mkdocs.yml

@@ -62,7 +62,7 @@ jobs:
           echo $VERSION
           echo $IS_RC
 
-          if [ "$IS_RC" == "False" ]; then
+          if [ "$IS_RC" == "False" ] || [ "$VERSION" == "0.9.1post0" ]; then
             cd website/mkdocs && mike deploy -F mkdocs.yml --update-aliases $VERSION latest
             mike set-default --push --allow-empty -F mkdocs.yml latest
           else

{ag2-0.9.1.post0 → ag2-0.9.2}/.github/workflows/deploy-website-mintlify.yml

@@ -1,5 +1,12 @@
 name: mintlify docs
 
+
+# WORKFLOW DISABLED
+# This workflow is temporarily disabled via "if: false" at the job level
+# and will be completely removed in a future PR as part of the mintlify
+# cleanup task. It's preserved here temporarily for reference purposes.
+# To re-enable, remove the "if: false" condition from the job.
+
 on:
   push:
     branches: [main]
@@ -17,6 +24,8 @@ permissions:
   contents: write
 jobs:
   mintlify-release:
+    # DISABLED: This workflow will be removed as part of the mintlify cleanup task
+    if: false
     uses: ./.github/workflows/build-docs.yml
     with:
       python-version: "3.10"

{ag2-0.9.1.post0 → ag2-0.9.2}/.gitignore

@@ -197,3 +197,7 @@ client_secret*.json
 *token*.json
 *credentials.json
 notebook/*_server.py
+
+
+notebook/mcp/wikipedia_articles
+notebook/mcp/arxiv_papers

{ag2-0.9.1.post0 → ag2-0.9.2}/MAINTAINERS.md

@@ -23,6 +23,7 @@
 | Alec Solder  | [alecsolder](https://github.com/alecsolder)               | -                | swarms, reasoning, function calling |
 | Marc Willhaus | [willhama](https://github.com/willhama)               | -                | - |
 | George Sideris | [giorgossideris](https://github.com/giorgossideris)               | -                | reasoning, RAG |
+| Beibin Li | [BeibinLi](https://github.com/BeibinLi)               | GenAI, Meta               | multimodal, reasoning, optiguide |
 
 **Pending Maintainers list (Marked with \*, Waiting for explicit approval from the maintainers)**
 | Name            | GitHub Handle                                              | Organization           | Features                                |

{ag2-0.9.1.post0 → ag2-0.9.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: ag2
-Version: 0.9.1.post0
+Version: 0.9.2
 Summary: A programming framework for agentic AI
 Project-URL: Homepage, https://ag2.ai/
 Project-URL: Documentation, https://docs.ag2.ai
@@ -199,6 +199,12 @@ Requires-Dist: sympy; extra == 'mathchat'
 Requires-Dist: wolframalpha; extra == 'mathchat'
 Provides-Extra: mcp
 Requires-Dist: mcp<1.6,>=1.4.0; (python_version >= '3.10') and extra == 'mcp'
+Provides-Extra: mcp-proxy-gen
+Requires-Dist: fastapi-code-generator>=0.5.4; extra == 'mcp-proxy-gen'
+Requires-Dist: fastapi<1,>=0.112; extra == 'mcp-proxy-gen'
+Requires-Dist: pyyaml; extra == 'mcp-proxy-gen'
+Requires-Dist: requests; extra == 'mcp-proxy-gen'
+Requires-Dist: typer; extra == 'mcp-proxy-gen'
 Provides-Extra: mistral
 Requires-Dist: mistralai>=1.0.1; extra == 'mistral'
 Provides-Extra: neo4j
@@ -613,7 +619,7 @@ teacher.initiate_chat(
 
 When executed, this code creates a collaborative system where the teacher initiates the conversation, and the lesson planner and reviewer agents work together to create and refine a lesson plan. The GroupChatManager orchestrates the conversation, selecting the next agent to respond based on the context of the discussion.
 
-For workflows requiring more structured processes, explore the Swarm pattern in the detailed [documentation](https://docs.ag2.ai/latest/docs/user-guide/advanced-concepts/conversation-patterns-deep-dive).
+For workflows requiring more structured processes, explore the Group Chat pattern in the detailed [documentation](https://docs.ag2.ai/latest/docs/user-guide/advanced-concepts/orchestration/group-chat/introduction).
 
 ### Tools
 
@@ -674,7 +680,7 @@ AG2 supports more advanced concepts to help you build your AI agent workflows. Y
 - [Ending a conversation](https://docs.ag2.ai/latest/docs/user-guide/advanced-concepts/orchestration/ending-a-chat/)
 - [Retrieval Augmented Generation (RAG)](https://docs.ag2.ai/docs/user-guide/advanced-concepts/rag)
 - [Code Execution](https://docs.ag2.ai/latest/docs/user-guide/advanced-concepts/code-execution)
-- [Tools with Secrets](https://docs.ag2.ai/latest/docs/user-guide/basic-concepts/introducing-tools/tools-with-secrets)
+- [Tools with Secrets](https://docs.ag2.ai/latest/docs/user-guide/advanced-concepts/tools/tools-with-secrets/)
 
 ## Announcements
 

{ag2-0.9.1.post0 → ag2-0.9.2}/README.md

@@ -292,7 +292,7 @@ teacher.initiate_chat(
 
 When executed, this code creates a collaborative system where the teacher initiates the conversation, and the lesson planner and reviewer agents work together to create and refine a lesson plan. The GroupChatManager orchestrates the conversation, selecting the next agent to respond based on the context of the discussion.
 
-For workflows requiring more structured processes, explore the Swarm pattern in the detailed [documentation](https://docs.ag2.ai/latest/docs/user-guide/advanced-concepts/conversation-patterns-deep-dive).
+For workflows requiring more structured processes, explore the Group Chat pattern in the detailed [documentation](https://docs.ag2.ai/latest/docs/user-guide/advanced-concepts/orchestration/group-chat/introduction).
 
 ### Tools
 
@@ -353,7 +353,7 @@ AG2 supports more advanced concepts to help you build your AI agent workflows. Y
 - [Ending a conversation](https://docs.ag2.ai/latest/docs/user-guide/advanced-concepts/orchestration/ending-a-chat/)
 - [Retrieval Augmented Generation (RAG)](https://docs.ag2.ai/docs/user-guide/advanced-concepts/rag)
 - [Code Execution](https://docs.ag2.ai/latest/docs/user-guide/advanced-concepts/code-execution)
-- [Tools with Secrets](https://docs.ag2.ai/latest/docs/user-guide/basic-concepts/introducing-tools/tools-with-secrets)
+- [Tools with Secrets](https://docs.ag2.ai/latest/docs/user-guide/advanced-concepts/tools/tools-with-secrets/)
 
 ## Announcements
 

{ag2-0.9.1.post0 → ag2-0.9.2}/announcements.md

@@ -24,7 +24,7 @@ We adopt the Apache 2.0 license from v0.3. This enhances our commitment to open-
 
 🎉 Dec 31, 2023: [AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation Framework](https://arxiv.org/abs/2308.08155) is selected by [TheSequence: My Five Favorite AI Papers of 2023](https://thesequence.substack.com/p/my-five-favorite-ai-papers-of-2023).
 
-🔥 Nov 24: pyautogen [v0.2](https://github.com/ag2ai/ag2/releases/tag/v0.2.0) is released with many updates and new features compared to v0.1.1. It switches to using openai-python v1. Please read the [migration guide](https://docs.ag2.ai/docs/installation/Installation).
+🔥 Nov 24: pyautogen [v0.2](https://github.com/ag2ai/ag2/releases/tag/v0.2.0) is released with many updates and new features compared to v0.1.1. It switches to using openai-python v1. Please read the [migration guide](https://docs.ag2.ai/latest/docs/user-guide/basic-concepts/installing-ag2/).
 
 🔥 Nov 11: OpenAI's Assistants are available in AutoGen and interoperatable with other AutoGen agents! Checkout our [blogpost](https://docs.ag2.ai/latest/docs/blog/2023/11/13/OAI-assistants/) for details and examples.
 

{ag2-0.9.1.post0 → ag2-0.9.2}/autogen/agentchat/conversable_agent.py

@@ -2321,6 +2321,21 @@ class ConversableAgent(LLMAgent):
 
         return False, None
 
+    def _run_async_in_thread(self, coro):
+        """Run an async coroutine in a separate thread with its own event loop."""
+        result = {}
+
+        def runner():
+            loop = asyncio.new_event_loop()
+            asyncio.set_event_loop(loop)
+            result["value"] = loop.run_until_complete(coro)
+            loop.close()
+
+        t = threading.Thread(target=runner)
+        t.start()
+        t.join()
+        return result["value"]
+
     def generate_function_call_reply(
         self,
         messages: Optional[list[dict[str, Any]]] = None,
@@ -2342,18 +2357,8 @@ class ConversableAgent(LLMAgent):
             func_call = message["function_call"]
             func = self._function_map.get(func_call.get("name", None), None)
             if inspect.iscoroutinefunction(func):
-                try:
-                    # get the running loop if it was already created
-                    loop = asyncio.get_running_loop()
-                    close_loop = False
-                except RuntimeError:
-                    # create a loop if there is no running loop
-                    loop = asyncio.new_event_loop()
-                    close_loop = True
-
-                _, func_return = loop.run_until_complete(self.a_execute_function(func_call, call_id=call_id))
-                if close_loop:
-                    loop.close()
+                coro = self.a_execute_function(func_call, call_id=call_id)
+                _, func_return = self._run_async_in_thread(coro)
             else:
                 _, func_return = self.execute_function(message["function_call"], call_id=call_id)
             return True, func_return
@@ -2409,18 +2414,8 @@ class ConversableAgent(LLMAgent):
             tool_call_id = tool_call.get("id", None)
             func = self._function_map.get(function_call.get("name", None), None)
             if inspect.iscoroutinefunction(func):
-                try:
-                    # get the running loop if it was already created
-                    loop = asyncio.get_running_loop()
-                    close_loop = False
-                except RuntimeError:
-                    # create a loop if there is no running loop
-                    loop = asyncio.new_event_loop()
-                    close_loop = True
-
-                _, func_return = loop.run_until_complete(self.a_execute_function(function_call, call_id=tool_call_id))
-                if close_loop:
-                    loop.close()
+                coro = self.a_execute_function(function_call, call_id=tool_call_id)
+                _, func_return = self._run_async_in_thread(coro)
             else:
                 _, func_return = self.execute_function(function_call, call_id=tool_call_id)
             content = func_return.get("content", "")
@@ -3130,12 +3125,16 @@ class ConversableAgent(LLMAgent):
             arguments = {}
             content = f"Error: Function {func_name} not found."
 
-        if verbose:
-            iostream.send(
-                ExecutedFunctionEvent(
-                    func_name=func_name, call_id=call_id, arguments=arguments, content=content, recipient=self
-                )
+        iostream.send(
+            ExecutedFunctionEvent(
+                func_name=func_name,
+                call_id=call_id,
+                arguments=arguments,
+                content=content,
+                recipient=self,
+                is_exec_success=is_exec_success,
             )
+        )
 
         return is_exec_success, {
             "name": func_name,
@@ -3198,12 +3197,16 @@ class ConversableAgent(LLMAgent):
             arguments = {}
             content = f"Error: Function {func_name} not found."
 
-        if verbose:
-            iostream.send(
-                ExecutedFunctionEvent(
-                    func_name=func_name, call_id=call_id, arguments=arguments, content=content, recipient=self
-                )
+        iostream.send(
+            ExecutedFunctionEvent(
+                func_name=func_name,
+                call_id=call_id,
+                arguments=arguments,
+                content=content,
+                recipient=self,
+                is_exec_success=is_exec_success,
             )
+        )
 
         return is_exec_success, {
             "name": func_name,

{ag2-0.9.1.post0 → ag2-0.9.2}/autogen/events/agent_events.py

@@ -763,9 +763,10 @@ class ExecuteFunctionEvent(BaseEvent):
 class ExecutedFunctionEvent(BaseEvent):
     func_name: str
     call_id: Optional[str] = None
-    arguments: dict[str, Any]
-    content: str
+    arguments: Optional[dict[str, Any]]
+    content: Any
     recipient: str
+    is_exec_success: bool = True
 
     def __init__(
         self,
@@ -773,9 +774,10 @@ class ExecutedFunctionEvent(BaseEvent):
         uuid: Optional[UUID] = None,
         func_name: str,
         call_id: Optional[str] = None,
-        arguments: dict[str, Any],
-        content: str,
+        arguments: Optional[dict[str, Any]],
+        content: Any,
         recipient: Union["Agent", str],
+        is_exec_success: bool = True,
     ):
         super().__init__(
             uuid=uuid,
@@ -785,6 +787,7 @@ class ExecutedFunctionEvent(BaseEvent):
             content=content,
             recipient=recipient.name if hasattr(recipient, "name") else recipient,
         )
+        self.is_exec_success = is_exec_success
 
     def print(self, f: Optional[Callable[..., Any]] = None) -> None:
         f = f or print

{ag2-0.9.1.post0 → ag2-0.9.2}/autogen/interop/litellm/litellm_config_factory.py

@@ -4,7 +4,7 @@
 
 import os
 from abc import ABC, abstractmethod
-from typing import Any, Callable, TypeVar, Union
+from typing import Any, Callable, Optional, TypeVar, Union
 
 from ...doc_utils import export_module
 from ...llm_config import LLMConfig
@@ -15,19 +15,85 @@ __all__ = ["LiteLLmConfigFactory"]
 T = TypeVar("T", bound="LiteLLmConfigFactory")
 
 
+def get_crawl4ai_version() -> Optional[str]:
+    """Get the installed crawl4ai version."""
+    try:
+        import crawl4ai
+
+        version = getattr(crawl4ai, "__version__", None)
+        return version if isinstance(version, str) else None
+    except (ImportError, AttributeError):
+        return None
+
+
+def is_crawl4ai_v05_or_higher() -> bool:
+    """Check if crawl4ai version is 0.5 or higher."""
+    version = get_crawl4ai_version()
+    if version is None:
+        return False
+
+    # Parse version string (e.g., "0.5.0" -> [0, 5, 0])
+    try:
+        version_parts = [int(x) for x in version.split(".")]
+        # Check if version >= 0.5.0
+        return version_parts >= [0, 5, 0]
+    except (ValueError, IndexError):
+        return False
+
+
 @export_module("autogen.interop")
 class LiteLLmConfigFactory(ABC):
     _factories: set["LiteLLmConfigFactory"] = set()
 
     @classmethod
     def create_lite_llm_config(cls, llm_config: Union[LLMConfig, dict[str, Any]]) -> dict[str, Any]:
+        """
+        Create a lite LLM config compatible with the installed crawl4ai version.
+
+        For crawl4ai >=0.5: Returns config with llmConfig parameter
+        For crawl4ai <0.5: Returns config with provider parameter (legacy)
+        """
         first_llm_config = get_first_llm_config(llm_config)
         for factory in LiteLLmConfigFactory._factories:
             if factory.accepts(first_llm_config):
-                return factory.create(first_llm_config)
+                base_config = factory.create(first_llm_config)
+
+                # Check crawl4ai version and adapt config accordingly
+                if is_crawl4ai_v05_or_higher():
+                    return cls._adapt_for_crawl4ai_v05(base_config)
+                else:
+                    return base_config  # Use legacy format
 
         raise ValueError("Could not find a factory for the given config.")
 
+    @classmethod
+    def _adapt_for_crawl4ai_v05(cls, base_config: dict[str, Any]) -> dict[str, Any]:
+        """
+        Adapt the config for crawl4ai >=0.5 by moving deprecated parameters
+        into an llmConfig object.
+        """
+        adapted_config = base_config.copy()
+
+        # Extract deprecated parameters
+        llm_config_params = {}
+
+        if "provider" in adapted_config:
+            llm_config_params["provider"] = adapted_config.pop("provider")
+
+        if "api_token" in adapted_config:
+            llm_config_params["api_token"] = adapted_config.pop("api_token")
+
+        # Add other parameters that should be in llmConfig
+        for param in ["base_url", "api_base", "api_version"]:
+            if param in adapted_config:
+                llm_config_params[param] = adapted_config.pop(param)
+
+        # Create the llmConfig object if we have parameters for it
+        if llm_config_params:
+            adapted_config["llmConfig"] = llm_config_params
+
+        return adapted_config
+
     @classmethod
     def register_factory(cls) -> Callable[[type[T]], type[T]]:
         def decorator(factory: type[T]) -> type[T]:

{ag2-0.9.1.post0 → ag2-0.9.2}/autogen/llm_config.py

@@ -138,7 +138,10 @@ class LLMConfig(metaclass=MetaLLMConfig):
         if len(filtered_config_list) == 0:
             raise ValueError(f"No config found that satisfies the filter criteria: {kwargs}")
 
-        return LLMConfig(config_list=filtered_config_list)
+        kwargs = self.model_dump()
+        kwargs["config_list"] = filtered_config_list
+
+        return LLMConfig(**kwargs)
 
     # @functools.wraps(BaseModel.model_dump)
     def model_dump(self, *args: Any, exclude_none: bool = True, **kwargs: Any) -> dict[str, Any]:

ag2-0.9.2/autogen/mcp/__main__.py

@@ -0,0 +1,78 @@
+# Copyright (c) 2023 - 2025, AG2ai, Inc., AG2ai open-source projects maintainers and core contributors
+#
+# SPDX-License-Identifier: Apache-2.0
+import logging
+from typing import Annotated, Literal, Optional
+
+from .. import __version__
+from ..import_utils import optional_import_block, require_optional_import
+from .mcp_proxy import MCPProxy
+
+logger = logging.getLogger(__name__)
+
+with optional_import_block():
+    import typer
+
+
+@require_optional_import(["typer"], "mcp-proxy-gen")
+def create_typer_app() -> "typer.Typer":
+    """Create a Typer app for the mcp proxy CLI."""
+    app = typer.Typer(rich_markup_mode="rich")
+
+    def version_callback(value: bool) -> None:
+        if value:
+            typer.echo(f"{__version__}")
+            raise typer.Exit()
+
+    @app.callback()
+    def callback(
+        version: Annotated[
+            Optional[bool],
+            typer.Option("--version", help="Show the version and exit.", callback=version_callback),
+        ] = None,
+    ) -> None:
+        """AG2 mcp proxy CLI - The [bold]mcp proxy[/bold] command line app. 😎
+
+        Generate mcp proxy for your [bold]AG2[/bold] projects.
+
+        Read more in the docs: ...
+        """  # noqa: D415
+
+    @app.command()
+    def create(
+        openapi_specification: Annotated[
+            Optional[str],
+            "Specification of the OpenAPI to use for the proxy generation.",
+        ] = None,
+        openapi_url: Annotated[
+            Optional[str],
+            "URL to the OpenAPI specification to use for the proxy generation.",
+        ] = None,
+        client_source_path: Annotated[
+            Optional[str],
+            "Path to the generated proxy client source code.",
+        ] = None,
+        server_url: Annotated[
+            Optional[str],
+            "Comma-separated list of server URLs to use for the proxy generation.",
+        ] = None,
+        configuration_type: Annotated[
+            Literal["json", "yaml"],
+            "Configuration type of the specification. Can be 'json' or 'yaml'.",
+        ] = "json",
+    ) -> None:
+        """Generate mcp proxy for your AG2 projects."""
+        MCPProxy.create(
+            openapi_specification=openapi_specification,
+            openapi_url=openapi_url,
+            client_source_path=client_source_path,
+            servers=[{"url": server_url}],
+            configuration_type=configuration_type,
+        )
+
+    return app
+
+
+if __name__ == "__main__":
+    app = create_typer_app()
+    app(prog_name="mcp_proxy")

ag2-0.9.2/autogen/mcp/mcp_proxy/__init__.py

@@ -0,0 +1,19 @@
+# Copyright (c) 2023 - 2025, AG2ai, Inc., AG2ai open-source projects maintainers and core contributors
+#
+# SPDX-License-Identifier: Apache-2.0
+
+from autogen.import_utils import optional_import_block
+
+from .patch_fastapi_code_generator import (  # noqa: E402
+    SUCCESFUL_IMPORT,
+    patch_function_name_parsing,
+    patch_generate_code,
+)
+
+if SUCCESFUL_IMPORT:
+    patch_function_name_parsing()
+    patch_generate_code()
+
+from .mcp_proxy import MCPProxy  # noqa: E402
+
+__all__ = ["MCPProxy", "optional_import_block"]

ag2-0.9.2/autogen/mcp/mcp_proxy/fastapi_code_generator_helpers.py

@@ -0,0 +1,63 @@
+# Copyright (c) 2023 - 2025, AG2ai, Inc., AG2ai open-source projects maintainers and core contributors
+#
+# SPDX-License-Identifier: Apache-2.0
+from collections.abc import Iterator
+from contextlib import contextmanager
+from functools import cached_property
+from typing import Optional, Union
+
+from ...import_utils import optional_import_block
+
+with optional_import_block() as result:
+    from fastapi_code_generator.parser import (
+        Argument,
+        OpenAPIParser,
+        ParameterObject,
+        ReferenceObject,
+    )
+
+SUCCESFUL_IMPORT = result.is_successful
+
+__all__ = ["SUCCESFUL_IMPORT", "patch_get_parameter_type"]
+
+
+@contextmanager
+def patch_get_parameter_type() -> Iterator[None]:
+    class ArgumentWithDescription(Argument):  # type: ignore[misc]
+        description: Optional[str] = None
+
+        @cached_property
+        def argument(self) -> str:
+            if self.description:
+                description = self.description.replace('"""', '"""')
+                type_hint = f'Annotated[{self.type_hint}, """{description}"""]'
+            else:
+                type_hint = self.type_hint
+
+            if self.default is None and self.required:
+                return f"{self.name}: {type_hint}"
+
+            return f"{self.name}: {type_hint} = {self.default}"
+
+    original_get_parameter_type = OpenAPIParser.get_parameter_type
+
+    def get_parameter_type(
+        self: OpenAPIParser,
+        parameters: Union[ReferenceObject, ParameterObject],
+        snake_case: bool,
+        path: list[str],
+    ) -> Optional[Argument]:
+        # get the original argument
+        argument = original_get_parameter_type(self, parameters, snake_case, path)
+
+        # add description to the argument
+        parameters = self.resolve_object(parameters, ParameterObject)
+        argument_with_description = ArgumentWithDescription(description=parameters.description, **argument.model_dump())
+        return argument_with_description
+
+    OpenAPIParser.get_parameter_type = get_parameter_type
+
+    try:
+        yield
+    finally:
+        OpenAPIParser.get_parameter_type = original_get_parameter_type