Emphasis on_messages is for new messages only; remove unused file. (#4819)

* Emphasis on_messages is for new messages only

* update

* update uv

* update uv action

* try pin uv version

* pin all uv versions to 0.5.11

* revert uv lock file and remove unwanted file.

python/packages/autogen-agentchat/src/autogen_agentchat/agents/_assistant_agent.py

@@ -72,6 +72,14 @@ class AssistantAgent(BaseChatAgent):
     the inner messages as they are created, and the :class:`~autogen_agentchat.base.Response`
     object as the last item before closing the generator.
 
+
+    .. note::
+
+        The caller must only pass the new messages to the agent on each call
+        to the :meth:`on_messages` or :meth:`on_messages_stream` method.
+        The agent maintains its state between calls to these methods.
+        Do not pass the entire conversation history to the agent on each call.
+
     Tool call behavior:
 
     * If the model returns no tool call, then the response is immediately returned as a :class:`~autogen_agentchat.messages.TextMessage` in :attr:`~autogen_agentchat.base.Response.chat_message`.

python/packages/autogen-agentchat/src/autogen_agentchat/agents/_base_chat_agent.py

@@ -14,7 +14,26 @@ from ..state import BaseState
 
 
 class BaseChatAgent(ChatAgent, ABC):
-    """Base class for a chat agent."""
+    """Base class for a chat agent.
+
+    This abstract class provides a base implementation for a :class:`ChatAgent`.
+    To create a new chat agent, subclass this class and implement the
+    :meth:`on_messages`, :meth:`on_reset`, and :attr:`produced_message_types`.
+    If streaming is required, also implement the :meth:`on_messages_stream` method.
+
+    An agent is considered stateful and maintains its state between calls to
+    the :meth:`on_messages` or :meth:`on_messages_stream` methods.
+    The agent should store its state in the
+    agent instance. The agent should also implement the :meth:`on_reset` method
+    to reset the agent to its initialization state.
+
+    .. note::
+
+        The caller should only pass the new messages to the agent on each call
+        to the :meth:`on_messages` or :meth:`on_messages_stream` method.
+        Do not pass the entire conversation history to the agent on each call.
+        This design principle must be followed when creating a new agent.
+    """
 
     def __init__(self, name: str, description: str) -> None:
         self._name = name

python/packages/autogen-core/docs/src/user-guide/agentchat-user-guide/tutorial/agents.ipynb

@@ -11,7 +11,7 @@
     "\n",
     "- {py:attr}`~autogen_agentchat.agents.BaseChatAgent.name`: The unique name of the agent.\n",
     "- {py:attr}`~autogen_agentchat.agents.BaseChatAgent.description`: The description of the agent in text.\n",
-    "- {py:meth}`~autogen_agentchat.agents.BaseChatAgent.on_messages`: Send the agent a sequence of {py:class}`~autogen_agentchat.messages.ChatMessage` get a {py:class}`~autogen_agentchat.base.Response`.\n",
+    "- {py:meth}`~autogen_agentchat.agents.BaseChatAgent.on_messages`: Send the agent a sequence of {py:class}`~autogen_agentchat.messages.ChatMessage` get a {py:class}`~autogen_agentchat.base.Response`. **It is important to note that agents are expected to be stateful and this method is expected to be called with new messages, not the complete history**.\n",
     "- {py:meth}`~autogen_agentchat.agents.BaseChatAgent.on_messages_stream`: Same as {py:meth}`~autogen_agentchat.agents.BaseChatAgent.on_messages` but returns an iterator of {py:class}`~autogen_agentchat.messages.AgentEvent` or {py:class}`~autogen_agentchat.messages.ChatMessage` followed by a {py:class}`~autogen_agentchat.base.Response` as the last item.\n",
     "- {py:meth}`~autogen_agentchat.agents.BaseChatAgent.on_reset`: Reset the agent to its initial state.\n",
     "\n",
@@ -106,8 +106,13 @@
     "```{note}\n",
     "It is important to note that {py:meth}`~autogen_agentchat.agents.AssistantAgent.on_messages`\n",
     "will update the internal state of the agent -- it will add the messages to the agent's\n",
-    "history. So you should not repeatedly call this method with the same messages if you want to\n",
-    "carry on a conversation with the agent.\n",
+    "history. So you should call this method with new messages.\n",
+    "**You should not repeatedly call this method with the same messages or the complete history.**\n",
+    "```\n",
+    "\n",
+    "```{note}\n",
+    "Unlike in v0.2 AgentChat, the tools are executed by the same agent directly within\n",
+    "the same call to {py:meth}`~autogen_agentchat.agents.AssistantAgent.on_messages`.\n",
     "```\n",
     "\n",
     "## User Proxy Agent\n",
@@ -141,7 +146,8 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "The User Proxy agent is ideally used for on-demand human-in-the-loop interactions for scenarios such as Just In Time approvals, human feedback, alerts, etc. For slower user interactions, consider terminating the session using a termination condition and start another one from run or run_stream with another message.\n",
+    "The User Proxy agent is ideally used for on-demand human-in-the-loop interactions for scenarios such as Just In Time approvals, human feedback, alerts, etc. For slower user interactions, consider terminating a team using a termination condition and start another one from\n",
+    "{py:meth}`~autogen_agentchat.base.TaskRunner.run` or {py:meth}`~autogen_agentchat.base.TaskRunner.run_stream` with another message.\n",
     "\n",
     "## Streaming Messages\n",
     "\n",

python/packages/autogen-ext/test.py

@@ -1,21 +0,0 @@
-from autogen_core.components.models import LLMMessage
-from autogen_core.models import ChatCompletionClient
-from autogen_core.models import UserMessage
-
-client = ChatCompletionClient.load_component(
-    {
-        "provider": "openai_chat_completion_client",
-        "config": {
-            "model": "gpt-4o"
-        }
-    }
-)
-
-# async def main():
-#     print(await client.create([UserMessage(source="user", content="Hello")]))
-
-# import asyncio
-
-# asyncio.run(main())
-
-print(client.dump_component().model_dump_json())