Python: [BREAKING] Simplify API: ChatAgent -> Agent, ChatMessage -> Message (#3747)

* [BREAKING] Rename ChatAgent -> Agent, ChatMessage -> Message, ChatClientProtocol -> SupportsChatGetResponse

Simplify the public API by removing redundant 'Chat' prefix from core types:
- ChatAgent -> Agent
- RawChatAgent -> RawAgent
- ChatMessage -> Message
- ChatClientProtocol -> SupportsChatGetResponse

Also renamed internal WorkflowMessage (was Message in _runner_context) to avoid collision.

No backward compatibility aliases - this is a clean breaking change.

* [BREAKING] Rename Agent chat_client parameter to client

* Fix rebase issues: WorkflowMessage references and broken markdown links

* Fix formatting and lint issues from code quality checks

* Fix import ordering in workflow sample files

* fixed rebase

* Fix test failures: use WorkflowMessage and A2AMessage after ChatMessage→Message rename

- Replace Message(data=..., source_id=...) with WorkflowMessage(...) in workflow tests
- Fix isinstance check in A2A agent to use A2AMessage instead of Message
- Fix import in test_workflow_observability.py (Message→WorkflowMessage)

* Fix lint, fmt, and sample errors after ChatMessage→Message rename

- Auto-fix 70+ ruff lint issues across samples (ChatMessage→Message refs)
- Fix HostedVectorStoreContent→Content.from_hosted_vector_store in file search sample
- Fix _normalize_messages→normalize_messages in custom agent sample
- Fix context.terminate→raise MiddlewareTermination in middleware samples
- Fix with_update_hook→with_transform_hook in override middleware sample
- Add TOptions_co import back to custom_chat_client sample
- Add noqa for FastAPI File() default in chatkit sample
- Fix B023 loop variable capture in weather agent sample

* fix: update Agent constructor calls from chat_client to client in declaration-only tool tests

* fix: add register_cleanup to devui lazy-loading proxy and type stub

* fixed tests and updated new pieces

* fix agui typevar

* fix merge errors

* fix merge conflicts

* fiux merge

* Remove unused links

---------

Co-authored-by: Evan Mattson <evan.mattson@microsoft.com>

python/packages/lab/lightning/README.md

@@ -49,8 +49,8 @@ async def math_agent(task: TaskType, llm: LLM) -> float:
     """A function that solves a math problem and returns the evaluation score."""
     async with (
         MCPStdioTool(name="calculator", command="uvx", args=["mcp-server-calculator"]) as mcp_server,
-        ChatAgent(
-            chat_client=OpenAIChatClient(
+        Agent(
+            client=OpenAIChatClient(
                 model_id=llm.model,
                 api_key="your-api-key",
                 base_url=llm.endpoint,

python/packages/lab/lightning/samples/train_math_agent.py

@@ -20,7 +20,7 @@ import string
 from typing import TypedDict, cast
 
 import sympy  # type: ignore[import-untyped,reportMissingImports]
-from agent_framework import AgentResponse, ChatAgent, MCPStdioTool
+from agent_framework import Agent, AgentResponse, MCPStdioTool
 from agent_framework.lab.lightning import AgentFrameworkTracer
 from agent_framework.openai import OpenAIChatClient
 from agentlightning import LLM, Dataset, Trainer, rollout
@@ -166,8 +166,8 @@ async def math_agent(task: MathProblem, llm: LLM) -> float:
     # MCPStdioTool provides calculator functionality via MCP protocol
     async with (
         MCPStdioTool(name="calculator", command="uvx", args=["mcp-server-calculator"]) as mcp_server,
-        ChatAgent(
-            chat_client=OpenAIChatClient(
+        Agent(
+            client=OpenAIChatClient(
                 model_id=llm.model,  # This is the model being trained
                 api_key=os.getenv("OPENAI_API_KEY") or "dummy",  # Can be dummy when connecting to training LLM
                 base_url=llm.endpoint,  # vLLM server endpoint provided by agent-lightning

python/packages/lab/lightning/tests/test_lightning.py

@@ -9,7 +9,7 @@ import pytest
 
 agentlightning = pytest.importorskip("agentlightning")
 
-from agent_framework import AgentExecutor, AgentResponse, ChatAgent, WorkflowBuilder, Workflow
+from agent_framework import AgentExecutor, AgentResponse, Agent, WorkflowBuilder, Workflow
 from agent_framework_lab_lightning import AgentFrameworkTracer
 from agent_framework.openai import OpenAIChatClient
 from agentlightning import TracerTraceToTriplet
@@ -80,14 +80,14 @@ def workflow_two_agents():
             ),
         ):
             # Create the two agents
-            analyzer_agent = ChatAgent(
-                chat_client=first_chat_client,
+            analyzer_agent = Agent(
+                client=first_chat_client,
                 name="DataAnalyzer",
                 instructions="You are a data analyst. Analyze the given data and provide insights.",
             )
 
-            advisor_agent = ChatAgent(
-                chat_client=second_chat_client,
+            advisor_agent = Agent(
+                client=second_chat_client,
                 name="InvestmentAdvisor",
                 instructions="You are an investment advisor. Based on analysis results, provide recommendations.",
             )