Files
agent-framework/python/samples/demos/chatkit-integration/app.py
T
Eduard van Valkenburg 3dc59c83b5 Python: [BREAKING] Moved to a single get_response and run API (#3379)
* WIP

* big update to new ResponseStream model

* fixed tests and typing

* fixed tests and typing

* fixed tools typevar import

* fix

* mypy fix

* mypy fixes and some cleanup

* fix missing quoted names

* and client

* fix  imports agui

* fix anthropic override

* fix agui

* fix ag ui

* fix import

* fix anthropic types

* fix mypy

* refactoring

* updated typing

* fix 3.11

* fixes

* redid layering of chat clients and agents

* redid layering of chat clients and agents

* Fix lint, type, and test issues after rebase

- Add @overload decorators to AgentProtocol.run() for type compatibility
- Add missing docstring params (middleware, function_invocation_configuration)
- Fix TODO format (TD002) by adding author tags
- Fix broken observability tests from upstream:
  - Replace non-existent use_instrumentation with direct instantiation
  - Replace non-existent use_agent_instrumentation with AgentTelemetryLayer mixin
  - Fix get_streaming_response to use get_response(stream=True)
  - Add AgentInitializationError import
  - Update streaming exception tests to match actual behavior

* Fix AgentExecutionException import error in test_agents.py

- Replace non-existent AgentExecutionException with AgentRunException

* Fix test import and asyncio deprecation issues

- Add 'tests' to pythonpath in ag-ui pyproject.toml for utils_test_ag_ui import
- Replace deprecated asyncio.get_event_loop().run_until_complete with asyncio.run

* Fix azure-ai test failures

- Update _prepare_options patching to use correct class path
- Fix test_to_azure_ai_agent_tools_web_search_missing_connection to clear env vars

* Convert ag-ui utils_test_ag_ui.py to conftest.py

- Move test utilities to conftest.py for proper pytest discovery
- Update all test imports to use conftest instead of utils_test_ag_ui
- Remove old utils_test_ag_ui.py file
- Revert pythonpath change in pyproject.toml

* fix: use relative imports for ag-ui test utilities

* fix agui

* Rename Bare*Client to Raw*Client and BaseChatClient

- Renamed BareChatClient to BaseChatClient (abstract base class)
- Renamed BareOpenAIChatClient to RawOpenAIChatClient
- Renamed BareOpenAIResponsesClient to RawOpenAIResponsesClient
- Renamed BareAzureAIClient to RawAzureAIClient
- Added warning docstrings to Raw* classes about layer ordering
- Updated README in samples/getting_started/agents/custom with layer docs
- Added test for span ordering with function calling

* Fix layer ordering: FunctionInvocationLayer before ChatTelemetryLayer

This ensures each inner LLM call gets its own telemetry span, resulting in
the correct span sequence: chat -> execute_tool -> chat

Updated all production clients and test mocks to use correct ordering:
- ChatMiddlewareLayer (first)
- FunctionInvocationLayer (second)
- ChatTelemetryLayer (third)
- BaseChatClient/Raw...Client (fourth)

* Remove run_stream usage

* Fix conversation_id propagation

* Python: Add BaseAgent implementation for Claude Agent SDK (#3509)

* Added ClaudeAgent implementation

* Updated streaming logic

* Small updates

* Small update

* Fixes

* Small fix

* Naming improvements

* Updated imports

* Addressed comments

* Updated package versions

* Update Claude agent connector layering

* fix test and plugin

* Store function middleware in invocation layer

* Fix telemetry streaming and ag-ui tests

* Remove legacy ag-ui tests folder

* updates

* Remove terminate flag from FunctionInvocationContext, use MiddlewareTermination instead

- Remove terminate attribute from FunctionInvocationContext
- Add result attribute to MiddlewareTermination to carry function results
- FunctionMiddlewarePipeline.execute() now lets MiddlewareTermination propagate
- _auto_invoke_function captures context.result in exception before re-raising
- _try_execute_function_calls catches MiddlewareTermination and sets should_terminate
- Fix handoff middleware to append to chat_client.function_middleware directly
- Update tests to use raise MiddlewareTermination instead of context.terminate
- Add middleware flow documentation in samples/concepts/tools/README.md
- Fix ag-ui to use FunctionMiddlewarePipeline instead of removed create_function_middleware_pipeline

* fix: remove references to removed terminate flag in purview tests, add type ignore

* fix: move _test_utils.py from package to test folder

* fix: call get_final_response() to trigger context provider notification in streaming test

* fix: correct broken links in tools README

* docs: clarify default middleware behavior in summary table

* fix: ensure inner stream result hooks are called when using map()/from_awaitable()

* Fix mypy type errors

* Address PR review comments on observability.py

- Remove TODO comment about unconsumed streams, add explanatory note instead
- Remove redundant _close_span cleanup hook (already called in _finalize_stream)
- Clarify behavior: cleanup hooks run after stream iteration, if stream is not
  consumed the span remains open until garbage collected

* Remove gen_ai.client.operation.duration from span attributes

Duration is a metrics-only attribute per OpenTelemetry semantic conventions.
It should be recorded to the histogram but not set as a span attribute.

* Remove duration from _get_response_attributes, pass directly to _capture_response

Duration is a metrics-only attribute. It's now passed directly to _capture_response
instead of being included in the attributes dict that gets set on the span.

* Remove redundant _close_span cleanup hook in AgentTelemetryLayer

_finalize_stream already calls _close_span() in its finally block,
so adding it as a separate cleanup hook is redundant.

* Use weakref.finalize to close span when stream is garbage collected

If a user creates a streaming response but never consumes it, the cleanup
hooks won't run. Now we register a weak reference finalizer that will close
the span when the stream object is garbage collected, ensuring spans don't
leak in this scenario.

* Fix _get_finalizers_from_stream to use _result_hooks attribute

Renamed function to _get_result_hooks_from_stream and fixed it to
look for the _result_hooks attribute which is the correct name in
ResponseStream class.

* Add missing asyncio import in test_request_info_mixin.py

* Fix leftover merge conflict marker in image_generation sample

* Update integration tests

* Fix integration tests: increase max_iterations from 1 to 2

Tests with tool_choice options require at least 2 iterations:
1. First iteration to get function call and execute the tool
2. Second iteration to get the final text response

With max_iterations=1, streaming tests would return early with only
the function call/result but no final text content.

* Fix duplicate function call error in conversation-based APIs

When using conversation_id (for Responses/Assistants APIs), the server
already has the function call message from the previous response. We
should only send the new function result message, not all messages
including the function call which would cause a duplicate ID error.

Fix: When conversation_id is set, only send the last message (the tool
result) instead of all response.messages.

* Add regression test for conversation_id propagation between tool iterations

Port test from PR #3664 with updates for new streaming API pattern.
Tests that conversation_id is properly updated in options dict during
function invocation loop iterations.

* Fix tool_choice=required to return after tool execution

When tool_choice is 'required', the user's intent is to force exactly one
tool call. After the tool executes, return immediately with the function
call and result - don't continue to call the model again.

This fixes integration tests that were failing with empty text responses
because with tool_choice=required, the model would keep returning function
calls instead of text.

Also adds regression tests for:
- conversation_id propagation between tool iterations (from PR #3664)
- tool_choice=required returns after tool execution

* Document tool_choice behavior in tools README

- Add table explaining tool_choice values (auto, none, required)
- Explain why tool_choice=required returns immediately after tool execution
- Add code example showing the difference between required and auto
- Update flow diagram to show the early return path for tool_choice=required

* Fix tool_choice=None behavior - don't default to 'auto'

Remove the hardcoded default of 'auto' for tool_choice in ChatAgent init.
When tool_choice is not specified (None), it will now not be sent to the
API, allowing the API's default behavior to be used.

Users who want tool_choice='auto' can still explicitly set it either in
default_options or at runtime.

Fixes #3585

* Fix tool_choice=none should not remove tools

In OpenAI Assistants client, tools were not being sent when
tool_choice='none'. This was incorrect - tool_choice='none' means
the model won't call tools, but tools should still be available
in the request (they may be used later in the conversation).

Fixes #3585

* Add test for tool_choice=none preserving tools

Adds a regression test to ensure that when tool_choice='none' is set but
tools are provided, the tools are still sent to the API. This verifies
the fix for #3585.

* Fix tool_choice=none should not remove tools in all clients

Apply the same fix to OpenAI Responses client and Azure AI client:
- OpenAI Responses: Remove else block that popped tool_choice/parallel_tool_calls
- Azure AI: Remove tool_choice != 'none' check when adding tools

When tool_choice='none', the model won't call tools, but tools should
still be sent to the API so they're available for future turns.

Also update README to clarify tool_choice=required supports multiple tools.

Fixes #3585

* Keep tool_choice even when tools is None

Move tool_choice processing outside of the 'if tools' block in OpenAI
Responses client so tool_choice is sent to the API even when no tools
are provided.

* Update test to match new parallel_tool_calls behavior

Changed test_prepare_options_removes_parallel_tool_calls_when_no_tools to
test_prepare_options_preserves_parallel_tool_calls_when_no_tools to reflect
that parallel_tool_calls is now preserved even when no tools are present,
consistent with the tool_choice behavior.

* Fix ChatMessage API and Role enum usage after rebase

- Update ChatMessage instantiation to use keyword args (role=, text=, contents=)
- Fix Role enum comparisons to use .value for string comparison
- Add created_at to AgentResponse in error handling
- Fix AgentResponse.from_updates -> from_agent_run_response_updates
- Fix DurableAgentStateMessage.from_chat_message to convert Role enum to string
- Add Role import where needed

* Fix additional ChatMessage API and method name changes

- Fix ChatMessage usage in workflow files (use text= instead of contents= for strings)
- Fix AgentResponse.from_updates -> from_agent_run_response_updates in workflow files
- Fix test files for ChatMessage and Role enum usage

* Fix remaining ChatMessage API usage in test files

* Fix more ChatMessage and Role API changes in source and test files

- Fix ChatMessage in _magentic.py replan method
- Fix Role enum comparison in test assertions
- Fix remaining test files with old ChatMessage syntax

* Fix ChatMessage and Role API changes across packages

- Add Role import where missing
- Fix ChatMessage signature: positional args to keyword args (role=, text=, contents=)
- Fix Role enum comparisons: .role.value instead of .role string
- Fix FinishReason enum usage in ag-ui event converters
- Rename AgentResponse.from_updates to from_agent_run_response_updates in ag-ui

Fixes API compatibility after Types API Review improvements merge

* Fix ChatMessage and Role API changes in github_copilot tests

* Fix ChatMessage and Role API changes in redis and github_copilot packages

- Fix redis provider: Role enum comparison using .value
- Fix redis tests: ChatMessage signature and Role comparisons
- Fix github_copilot tests: ChatMessage signature and Role comparisons
- Update docstring examples in redis chat message store

* Fix ChatMessage and Role API changes in devui package

- Fix executor: ChatMessage signature change
- Fix conversations: Role enum to string conversion in two places
- Fix tests: ChatMessage signatures and Role comparisons

* Fix ChatMessage and Role API changes in a2a and lab packages

- Fix a2a tests: Role comparisons and ChatMessage signatures
- Fix lab tau2 source: Role enum comparison in flip_messages, log_messages, sliding_window
- Fix lab tau2 tests: ChatMessage signatures and Role comparisons

* Remove duplicate test files from ag-ui/tests (tests are in ag_ui_tests)

* Fix ChatMessage and Role API changes across packages

After rebasing on upstream/main which merged PR #3647 (Types API Review
improvements), fix all packages to use the new API:

- ChatMessage: Use keyword args (role=, text=, contents=) instead of
  positional args
- Role: Compare using .value attribute since it's now an enum

Packages fixed:
- ag-ui: Fixed Role value extraction bugs in _message_adapters.py
- anthropic: Fixed ChatMessage and Role comparisons in tests
- azure-ai: Fixed Role comparison in _client.py
- azure-ai-search: Fixed ChatMessage and Role in source/tests
- bedrock: Fixed ChatMessage signatures in tests
- chatkit: Fixed ChatMessage and Role in source/tests
- copilotstudio: Fixed ChatMessage and Role in tests
- declarative: Fixed ChatMessage in _executors_agents.py
- mem0: Fixed ChatMessage and Role in source/tests
- purview: Fixed ChatMessage in source/tests

* Fix mypy errors for ChatMessage and Role API changes

- durabletask: Use str() fallback in role value extraction
- core: Fix ChatMessage in _orchestrator_helpers.py to use keyword args
- core: Add type ignore for _conversation_state.py contents deserialization
- ag-ui: Fix type ignore comments (call-overload instead of arg-type)
- azure-ai-search: Fix get_role_value type hint to accept Any
- lab: Move get_role_value to module level with Any type hint

* Improve CI test timeout configuration

- Increase job timeout from 10 to 15 minutes
- Reduce per-test timeout to 60s (was 900s/300s)
- Add --timeout_method thread for better timeout handling
- Add --timeout-verbose to see which tests are slow
- Reduce retries from 3 to 2 and delay from 10s to 5s

This ensures individual test timeouts are shorter than the job
timeout, providing better visibility when tests hang.

With 60s timeout and 2 retries, worst case per test is ~180s.

* Fix ChatMessage API usage in docstrings and source

- Fix ChatMessage positional args in docstrings: _serialization.py, _threads.py, _middleware.py
- Fix ChatMessage in tau2 runner.py
- Fix role comparison in _orchestrator_helpers.py to use .value
- Fix role comparison in _group_chat.py docstring example
- Fix role assertions in test_durable_entities.py to use .value

* Revert tool_choice/parallel_tool_calls changes - must be removed when no tools

OpenAI API requires tool_choice and parallel_tool_calls to only be
present when tools are specified. Restored the logic that removes
these options when there are no tools.

- Restored check in _chat_client.py to remove tool_choice and
  parallel_tool_calls when no tools present
- Restored same logic in _responses_client.py
- Reverted test to expect the correct behavior

* fixed issue in tests

* fix: resolve merge conflict markers in ag-ui tests

* fix: restructure ag-ui tests and fix Role/FinishReason to use string types

* fix: streaming function invocation and middleware termination

- Refactor streaming function invocation to use get_final_response() on inner streams
- Fix MiddlewareTermination to accept result parameter for passing results
- Fix _AutoHandoffMiddleware to use MiddlewareTermination instead of context.terminate
- Fix AgentMiddlewareLayer.run() to properly forward function/chat middleware
- Remove duplicate middleware registration in AgentMiddlewareLayer.__init__
- Fix exception handling in _auto_invoke_function to properly capture termination
- Fix mypy errors in core package
- Update tests to use stream=True parameter for unified run API

* fix all tests command

* Refactor integration tests to use pytest fixtures

- Merge testutils.py into conftest.py for azurefunctions integration tests
- Merge dt_testutils.py into conftest.py for durabletask integration tests
- Convert all integration tests to use fixtures instead of direct imports
  (fixes ModuleNotFoundError with --import-mode=importlib)
- Add sample_helper fixture for azurefunctions tests
- Add agent_client_factory and orchestration_helper fixtures for durabletask
- Integration tests now skip with descriptive messages when services unavailable
- Restructure devui tests into tests/devui/ with proper conftest.py
- Add test organization guidelines to CODING_STANDARD.md
- Remove __init__.py from test directories per pytest best practices

* Fix pytest_collection_modifyitems to only skip integration tests

The hook was skipping all tests in the test session, not just
integration tests. Now it only skips items in the integration_tests
directory.

* Fix mem0 tests failing on Python 3.13

Use patch.object on the imported module instead of @patch with string
path to ensure the mock takes effect regardless of import timing.

* fix mem0

* another attempt for mem0

* fix for mem0

* fix mem0

* Increase worker initialization wait time in durabletask tests

Increase from 2 to 8 seconds to allow time for:
- Python startup and module imports
- Azure OpenAI client creation
- Agent registration with DTS worker
- Worker connection to DTS

This helps prevent test failures in CI where the first tests may run
before the worker is fully ready to process requests.

* Fix streaming test to use ResponseStream with finalizer

The _consume_stream method now expects a ResponseStream that can provide
a final AgentResponse via get_final_response(). Update the test to use
ResponseStream with AgentResponse.from_updates as the finalizer.

* Fix MockToolCallingAgent to use new ResponseStream API and update samples

* small updates to run_stream to run

* fix sub workflow

* temp fix for az func test

---------

Co-authored-by: Dmytro Struk <13853051+dmytrostruk@users.noreply.github.com>
2026-02-05 20:09:58 +00:00

636 lines
25 KiB
Python

# Copyright (c) Microsoft. All rights reserved.
"""
ChatKit Integration Sample with Weather Agent and Image Analysis
This sample demonstrates how to integrate Microsoft Agent Framework with OpenAI ChatKit
using a weather tool with widget visualization, image analysis, and Azure OpenAI. It shows
a complete ChatKit server implementation using Agent Framework agents with proper FastAPI
setup, interactive weather widgets, and vision capabilities for analyzing uploaded images.
"""
import logging
from collections.abc import AsyncIterator, Callable
from datetime import datetime, timezone
from random import randint
from typing import Annotated, Any
import uvicorn
# Agent Framework imports
from agent_framework import AgentResponseUpdate, ChatAgent, ChatMessage, FunctionResultContent, Role, tool
from agent_framework.azure import AzureOpenAIChatClient
# Agent Framework ChatKit integration
from agent_framework_chatkit import ThreadItemConverter, stream_agent_response
# Local imports
from attachment_store import FileBasedAttachmentStore
from azure.identity import AzureCliCredential
# ChatKit imports
from chatkit.actions import Action
from chatkit.server import ChatKitServer
from chatkit.store import StoreItemType, default_generate_id
from chatkit.types import (
ThreadItem,
ThreadItemDoneEvent,
ThreadMetadata,
ThreadStreamEvent,
UserMessageItem,
WidgetItem,
)
from chatkit.widgets import WidgetRoot
from fastapi import FastAPI, File, Request, UploadFile
from fastapi.middleware.cors import CORSMiddleware
from fastapi.responses import FileResponse, JSONResponse, Response, StreamingResponse
from pydantic import Field
from store import SQLiteStore
from weather_widget import (
WeatherData,
city_selector_copy_text,
render_city_selector_widget,
render_weather_widget,
weather_widget_copy_text,
)
# ============================================================================
# Configuration Constants
# ============================================================================
# Server configuration
SERVER_HOST = "127.0.0.1" # Bind to localhost only for security (local dev)
SERVER_PORT = 8001
SERVER_BASE_URL = f"http://localhost:{SERVER_PORT}"
# Database configuration
DATABASE_PATH = "chatkit_demo.db"
# File storage configuration
UPLOADS_DIRECTORY = "./uploads"
# User context
DEFAULT_USER_ID = "demo_user"
# Logging configuration
LOG_LEVEL = logging.INFO
LOG_FORMAT = "%(asctime)s - %(name)s - %(levelname)s - %(message)s"
LOG_DATE_FORMAT = "%Y-%m-%d %H:%M:%S"
# ============================================================================
# Logging Setup
# ============================================================================
logging.basicConfig(
level=LOG_LEVEL,
format=LOG_FORMAT,
datefmt=LOG_DATE_FORMAT,
)
logger = logging.getLogger(__name__)
class WeatherResponse(str):
"""A string response that also carries WeatherData for widget creation."""
def __new__(cls, text: str, weather_data: WeatherData):
instance = super().__new__(cls, text)
instance.weather_data = weather_data # type: ignore
return instance
async def stream_widget(
thread_id: str,
widget: WidgetRoot,
copy_text: str | None = None,
generate_id: Callable[[StoreItemType], str] = default_generate_id,
) -> AsyncIterator[ThreadStreamEvent]:
"""Stream a ChatKit widget as a ThreadStreamEvent.
This helper function creates a ChatKit widget item and yields it as a
ThreadItemDoneEvent that can be consumed by the ChatKit UI.
Args:
thread_id: The ChatKit thread ID for the conversation.
widget: The ChatKit widget to display.
copy_text: Optional text representation of the widget for copy/paste.
generate_id: Optional function to generate IDs for ChatKit items.
Yields:
ThreadStreamEvent: ChatKit event containing the widget.
"""
item_id = generate_id("message")
widget_item = WidgetItem(
id=item_id,
thread_id=thread_id,
created_at=datetime.now(),
widget=widget,
copy_text=copy_text,
)
yield ThreadItemDoneEvent(type="thread.item.done", item=widget_item)
# NOTE: approval_mode="never_require" is for sample brevity. Use "always_require" in production; see samples/getting_started/tools/function_tool_with_approval.py and samples/getting_started/tools/function_tool_with_approval_and_threads.py.
@tool(approval_mode="never_require")
def get_weather(
location: Annotated[str, Field(description="The location to get the weather for.")],
) -> str:
"""Get the weather for a given location.
Returns a string description with embedded WeatherData for widget creation.
"""
logger.info(f"Fetching weather for location: {location}")
conditions = ["sunny", "cloudy", "rainy", "stormy", "snowy", "foggy"]
temperature = randint(-5, 35)
condition = conditions[randint(0, len(conditions) - 1)]
# Add some realistic details
humidity = randint(30, 90)
wind_speed = randint(5, 25)
weather_data = WeatherData(
location=location,
condition=condition,
temperature=temperature,
humidity=humidity,
wind_speed=wind_speed,
)
logger.debug(f"Weather data generated: {condition}, {temperature}°C, {humidity}% humidity, {wind_speed} km/h wind")
# Return a WeatherResponse that is both a string (for the LLM) and carries structured data
text = (
f"Weather in {location}:\n"
f"• Condition: {condition.title()}\n"
f"• Temperature: {temperature}°C\n"
f"• Humidity: {humidity}%\n"
f"• Wind: {wind_speed} km/h"
)
return WeatherResponse(text, weather_data)
@tool(approval_mode="never_require")
def get_time() -> str:
"""Get the current UTC time."""
current_time = datetime.now(timezone.utc)
logger.info("Getting current UTC time")
return f"Current UTC time: {current_time.strftime('%Y-%m-%d %H:%M:%S')} UTC"
@tool(approval_mode="never_require")
def show_city_selector() -> str:
"""Show an interactive city selector widget to the user.
This function triggers the display of a widget that allows users
to select from popular cities to get weather information.
Returns a special marker string that will be detected to show the widget.
"""
logger.info("Activating city selector widget")
return "__SHOW_CITY_SELECTOR__"
class WeatherChatKitServer(ChatKitServer[dict[str, Any]]):
"""ChatKit server implementation using Agent Framework.
This server integrates Agent Framework agents with ChatKit's server protocol,
providing weather information with interactive widgets and time queries through Azure OpenAI.
"""
def __init__(self, data_store: SQLiteStore, attachment_store: FileBasedAttachmentStore):
super().__init__(data_store, attachment_store)
logger.info("Initializing WeatherChatKitServer")
# Create Agent Framework agent with Azure OpenAI
# For authentication, run `az login` command in terminal
try:
self.weather_agent = ChatAgent(
chat_client=AzureOpenAIChatClient(credential=AzureCliCredential()),
instructions=(
"You are a helpful weather assistant with image analysis capabilities. "
"You can provide weather information for any location, tell the current time, "
"and analyze images that users upload. Be friendly and informative in your responses.\n\n"
"If a user asks to see a list of cities or wants to choose from available cities, "
"use the show_city_selector tool to display an interactive city selector.\n\n"
"When users upload images, you will automatically receive them and can analyze their content. "
"Describe what you see in detail and be helpful in answering questions about the images."
),
tools=[get_weather, get_time, show_city_selector],
)
logger.info("Weather agent initialized successfully with Azure OpenAI")
except Exception as e:
logger.error(f"Failed to initialize weather agent: {e}")
raise
# Create ThreadItemConverter with attachment data fetcher
self.converter = ThreadItemConverter(
attachment_data_fetcher=self._fetch_attachment_data,
)
logger.info("WeatherChatKitServer initialized")
async def _fetch_attachment_data(self, attachment_id: str) -> bytes:
"""Fetch attachment binary data for the converter.
Args:
attachment_id: The ID of the attachment to fetch.
Returns:
The binary data of the attachment.
"""
return await attachment_store.read_attachment_bytes(attachment_id)
async def _update_thread_title(
self, thread: ThreadMetadata, thread_items: list[ThreadItem], context: dict[str, Any]
) -> None:
"""Update thread title using LLM to generate a concise summary.
Args:
thread: The thread metadata to update.
thread_items: All items in the thread.
context: The context dictionary.
"""
logger.info(f"Attempting to update thread title for thread: {thread.id}")
if not thread_items:
logger.debug("No thread items available for title generation")
return
# Collect user messages to understand the conversation topic
user_messages: list[str] = []
for item in thread_items:
if isinstance(item, UserMessageItem) and item.content:
for content_part in item.content:
if hasattr(content_part, "text") and isinstance(content_part.text, str):
user_messages.append(content_part.text)
break
if not user_messages:
logger.debug("No user messages found for title generation")
return
logger.debug(f"Found {len(user_messages)} user message(s) for title generation")
try:
# Use the agent's chat client to generate a concise title
# Combine first few messages to capture the conversation topic
conversation_context = "\n".join(user_messages[:3])
title_prompt = [
ChatMessage(
role=Role.USER,
text=(
f"Generate a very short, concise title (max 40 characters) for a conversation "
f"that starts with:\n\n{conversation_context}\n\n"
"Respond with ONLY the title, nothing else."
),
)
]
# Use the chat client directly for a quick, lightweight call
response = await self.weather_agent.chat_client.get_response(
messages=title_prompt,
options={
"temperature": 0.3,
"max_tokens": 20,
},
)
if response.messages and response.messages[-1].text:
title = response.messages[-1].text.strip().strip('"').strip("'")
# Ensure it's not too long
if len(title) > 50:
title = title[:47] + "..."
thread.title = title
await self.store.save_thread(thread, context)
logger.info(f"Updated thread {thread.id} title to: {title}")
except Exception as e:
logger.warning(f"Failed to generate thread title, using fallback: {e}")
# Fallback to simple truncation
first_message: str = user_messages[0]
title: str = first_message[:50].strip()
if len(first_message) > 50:
title += "..."
thread.title = title
await self.store.save_thread(thread, context)
logger.info(f"Updated thread {thread.id} title to (fallback): {title}")
async def respond(
self,
thread: ThreadMetadata,
input_user_message: UserMessageItem | None,
context: dict[str, Any],
) -> AsyncIterator[ThreadStreamEvent]:
"""Handle incoming user messages and generate responses.
This method converts ChatKit messages to Agent Framework format using ThreadItemConverter,
runs the agent, converts the response back to ChatKit events using stream_agent_response,
and creates interactive weather widgets when weather data is queried.
"""
from agent_framework import FunctionResultContent
if input_user_message is None:
logger.debug("Received None user message, skipping")
return
logger.info(f"Processing message for thread: {thread.id}")
try:
# Track weather data and city selector flag for this request
weather_data: WeatherData | None = None
show_city_selector = False
# Load full thread history from the store
thread_items_page = await self.store.load_thread_items(
thread_id=thread.id,
after=None,
limit=1000,
order="asc",
context=context,
)
thread_items = thread_items_page.data
# Convert ALL thread items to Agent Framework ChatMessages using ThreadItemConverter
# This ensures the agent has the full conversation context
agent_messages = await self.converter.to_agent_input(thread_items)
if not agent_messages:
logger.warning("No messages after conversion")
return
logger.info(f"Running agent with {len(agent_messages)} message(s)")
# Run the Agent Framework agent with streaming
agent_stream = self.weather_agent.run(agent_messages, stream=True)
# Create an intercepting stream that extracts function results while passing through updates
async def intercept_stream() -> AsyncIterator[AgentResponseUpdate]:
nonlocal weather_data, show_city_selector
async for update in agent_stream:
# Check for function results in the update
if update.contents:
for content in update.contents:
if isinstance(content, FunctionResultContent):
result = content.result
# Check if it's a WeatherResponse (string subclass with weather_data attribute)
if isinstance(result, str) and hasattr(result, "weather_data"):
extracted_data = getattr(result, "weather_data", None)
if isinstance(extracted_data, WeatherData):
weather_data = extracted_data
logger.info(f"Weather data extracted: {weather_data.location}")
# Check if it's the city selector marker
elif isinstance(result, str) and result == "__SHOW_CITY_SELECTOR__":
show_city_selector = True
logger.info("City selector flag detected")
yield update
# Stream updates as ChatKit events with interception
async for event in stream_agent_response(
intercept_stream(),
thread_id=thread.id,
):
yield event
# If weather data was collected during the tool call, create a widget
if weather_data is not None and isinstance(weather_data, WeatherData):
logger.info(f"Creating weather widget for location: {weather_data.location}")
# Create weather widget
widget = render_weather_widget(weather_data)
copy_text = weather_widget_copy_text(weather_data)
# Stream the widget
async for widget_event in stream_widget(thread_id=thread.id, widget=widget, copy_text=copy_text):
yield widget_event
logger.debug("Weather widget streamed successfully")
# If city selector should be shown, create and stream that widget
if show_city_selector:
logger.info("Creating city selector widget")
# Create city selector widget
selector_widget = render_city_selector_widget()
selector_copy_text = city_selector_copy_text()
# Stream the widget
async for widget_event in stream_widget(
thread_id=thread.id, widget=selector_widget, copy_text=selector_copy_text
):
yield widget_event
logger.debug("City selector widget streamed successfully")
# Update thread title based on first user message if not already set
if not thread.title or thread.title == "New thread":
await self._update_thread_title(thread, thread_items, context)
logger.info(f"Completed processing message for thread: {thread.id}")
except Exception as e:
logger.error(f"Error processing message for thread {thread.id}: {e}", exc_info=True)
async def action(
self,
thread: ThreadMetadata,
action: Action[str, Any],
sender: WidgetItem | None,
context: dict[str, Any],
) -> AsyncIterator[ThreadStreamEvent]:
"""Handle widget actions from the frontend.
This method processes actions triggered by interactive widgets,
such as city selection from the city selector widget.
"""
logger.info(f"Received action: {action.type} for thread: {thread.id}")
if action.type == "city_selected":
# Extract city information from the action payload
city_label = action.payload.get("city_label", "Unknown")
logger.info(f"City selected: {city_label}")
logger.debug(f"Action payload: {action.payload}")
# Track weather data for this request
weather_data: WeatherData | None = None
# Create an agent message asking about the weather
agent_messages = [ChatMessage(role=Role.USER, text=f"What's the weather in {city_label}?")]
logger.debug(f"Processing weather query: {agent_messages[0].text}")
# Run the Agent Framework agent with streaming
agent_stream = self.weather_agent.run(agent_messages, stream=True)
# Create an intercepting stream that extracts function results while passing through updates
async def intercept_stream() -> AsyncIterator[AgentResponseUpdate]:
nonlocal weather_data
async for update in agent_stream:
# Check for function results in the update
if update.contents:
for content in update.contents:
if isinstance(content, FunctionResultContent):
result = content.result
# Check if it's a WeatherResponse (string subclass with weather_data attribute)
if isinstance(result, str) and hasattr(result, "weather_data"):
extracted_data = getattr(result, "weather_data", None)
if isinstance(extracted_data, WeatherData):
weather_data = extracted_data
logger.info(f"Weather data extracted: {weather_data.location}")
yield update
# Stream updates as ChatKit events with interception
async for event in stream_agent_response(
intercept_stream(),
thread_id=thread.id,
):
yield event
# If weather data was collected during the tool call, create a widget
if weather_data is not None and isinstance(weather_data, WeatherData):
logger.info(f"Creating weather widget for: {weather_data.location}")
# Create weather widget
widget = render_weather_widget(weather_data)
copy_text = weather_widget_copy_text(weather_data)
# Stream the widget
async for widget_event in stream_widget(thread_id=thread.id, widget=widget, copy_text=copy_text):
yield widget_event
logger.debug("Weather widget created successfully from action")
else:
logger.warning("No weather data available to create widget after action")
# FastAPI application setup
app = FastAPI(
title="ChatKit Weather & Vision Agent",
description="Weather and image analysis assistant powered by Agent Framework and Azure OpenAI",
version="1.0.0",
)
# Add CORS middleware to allow frontend connections
app.add_middleware(
CORSMiddleware,
allow_origins=["*"], # In production, specify exact origins
allow_credentials=True,
allow_methods=["*"],
allow_headers=["*"],
)
# Initialize data store and ChatKit server
logger.info("Initializing application components")
data_store = SQLiteStore(db_path=DATABASE_PATH)
attachment_store = FileBasedAttachmentStore(
uploads_dir=UPLOADS_DIRECTORY,
base_url=SERVER_BASE_URL,
data_store=data_store,
)
chatkit_server = WeatherChatKitServer(data_store, attachment_store)
logger.info("Application initialization complete")
@app.post("/chatkit")
async def chatkit_endpoint(request: Request):
"""Main ChatKit endpoint that handles all ChatKit requests.
This endpoint follows the ChatKit server protocol and handles both
streaming and non-streaming responses.
"""
logger.debug(f"Received ChatKit request from {request.client}")
request_body = await request.body()
# Create context following the working examples pattern
context = {"request": request}
try:
# Process the request using ChatKit server
result = await chatkit_server.process(request_body, context)
# Return appropriate response type
if hasattr(result, "__aiter__"): # StreamingResult
logger.debug("Returning streaming response")
return StreamingResponse(result, media_type="text/event-stream") # type: ignore[arg-type]
# NonStreamingResult
logger.debug("Returning non-streaming response")
return Response(content=result.json, media_type="application/json") # type: ignore[union-attr]
except Exception as e:
logger.error(f"Error processing ChatKit request: {e}", exc_info=True)
raise
@app.post("/upload/{attachment_id}")
async def upload_file(attachment_id: str, file: UploadFile = File(...)):
"""Handle file upload for two-phase upload.
The client POSTs the file bytes here after creating the attachment
via the ChatKit attachments.create endpoint.
"""
logger.info(f"Receiving file upload for attachment: {attachment_id}")
try:
# Read file contents
contents = await file.read()
# Save to disk
file_path = attachment_store.get_file_path(attachment_id)
file_path.write_bytes(contents)
logger.info(f"Saved {len(contents)} bytes to {file_path}")
# Load the attachment metadata from the data store
attachment = await data_store.load_attachment(attachment_id, {"user_id": DEFAULT_USER_ID})
# Clear the upload_url since upload is complete
attachment.upload_url = None
# Save the updated attachment back to the store
await data_store.save_attachment(attachment, {"user_id": DEFAULT_USER_ID})
# Return the attachment metadata as JSON
return JSONResponse(content=attachment.model_dump(mode="json"))
except Exception as e:
logger.error(f"Error uploading file for attachment {attachment_id}: {e}", exc_info=True)
return JSONResponse(status_code=500, content={"error": "Failed to upload file."})
@app.get("/preview/{attachment_id}")
async def preview_image(attachment_id: str):
"""Serve image preview/thumbnail.
For simplicity, this serves the full image. In production, you should
generate and cache thumbnails.
"""
logger.debug(f"Serving preview for attachment: {attachment_id}")
try:
file_path = attachment_store.get_file_path(attachment_id)
if not file_path.exists():
return JSONResponse(status_code=404, content={"error": "File not found"})
# Determine media type from file extension or attachment metadata
# For simplicity, we'll try to load from the store
try:
attachment = await data_store.load_attachment(attachment_id, {"user_id": DEFAULT_USER_ID})
media_type = attachment.mime_type
except Exception:
# Default to binary if we can't determine
media_type = "application/octet-stream"
return FileResponse(file_path, media_type=media_type)
except Exception as e:
logger.error(f"Error serving preview for attachment {attachment_id}: {e}", exc_info=True)
return JSONResponse(status_code=500, content={"error": "Error serving preview for attachment."})
if __name__ == "__main__":
# Run the server
logger.info(f"Starting ChatKit Weather Agent server on {SERVER_HOST}:{SERVER_PORT}")
uvicorn.run(app, host=SERVER_HOST, port=SERVER_PORT, log_level="info")