.NET: Python: Azure Functions feature branch (#1916)

* Python: Add Scaffolding for Durable AzureFunctions package to Agent Framework (#1823)

* Add scafolding

* update readme

* add code owners and label

* update owners

* .NET: Durable extension: initial src and unit tests (#1900)

* Python: Add Durable Agent Wrapper code (#1913)

* add initial changes

* Move code and add single sample

* Update logger

* Remove unused code

* address PR comments

* cleanup code and address comments

---------

Co-authored-by: Dmytro Struk <13853051+dmytrostruk@users.noreply.github.com>

* Azure Functions .NET samples (#1939)

* Python: Add Unit tests for Azurefunctions package (#1976)

* Add Unit tests for Azurefunctions

* remove duplicate import

* .NET: [Feature Branch] Migrate state schema updates and support for agents as MCP tools (#1979)

* Python: Add more samples for Azure Functions (#1980)

* Move all samples

* fix comments

* remove dead lines

* Make samples simpler

* .NET: [Feature Branch] Durable Task extension integration tests (#2017)

* .NET: [Feature Branch] Update OpenAI config for integration tests (#2063)

* Python: Add Integration tests for AzureFunctions  (#2020)

* Add Integration tests

* Remove DTS extension

* Apply suggestions from code review

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

* Apply suggestions from code review

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

* Add pyi file for type safety

* Add samples in readme

* Updated all readme instructions

* Address comments

* Update readmes

* Fix requirements

* Address comments

---------

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

* .NET: [Feature Branch] Update dotnet-build-and-test.yml to support integration tests (#2070)

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

* Fix DTS startup issue and improve logging (#2103)

* .NET: [Feature Branch] Introduce Azure OpenAI config for .NET pipeline (#2106)

Also fixes an issue where we were trying to start docker containers for integration tests on Windows, which doesn't work.

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

* Fix uv.lock after merge

* Python: Add README for Azure Functions samples setup (#2100)

* Add README for Azure Functions samples setup

Added setup instructions for Azure Functions samples, including environment setup, virtual environment creation, and running samples.

* Update python/samples/getting_started/azure_functions/README.md

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

* Apply suggestions from code review

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

* Apply suggestion from @Copilot

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

* Apply suggestions from code review

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

---------

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
Co-authored-by: Laveesh Rohra <larohra@microsoft.com>

* Fix or remove broken markdown file links (#2115)

* .NET: [Feature Branch] Update HTTP API to be consistent across languages (#2118)

* Python: Fix AzureFunctions Integration Tests (#2116)

* Add Identity Auth to samples

* Update python/samples/getting_started/azure_functions/README.md

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

* Update python/samples/getting_started/azure_functions/01_single_agent/function_app.py

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

* Update python/samples/getting_started/azure_functions/02_multi_agent/function_app.py

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

* Update python/samples/getting_started/azure_functions/06_multi_agent_orchestration_conditionals/README.md

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

---------

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

* Python: Fix Http Schema (#2112)

* Rename to threadid

* Respond in plain text

* Make snake-case

* Add http prefix

* rename to wait-for-response

* Add query param check

* address comments

* .NET: Remove IsPackable=false in preparation for nuget release (#2142)

* Python: Move `azurefunctions` to `azure` for import (#2141)

* Move import to Azure

* fix mypy

* Update python/packages/azurefunctions/README.md

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

* Add missing types

* Address comments

---------

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

* Update python/packages/azurefunctions/pyproject.toml

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

* Update python/packages/azurefunctions/agent_framework_azurefunctions/__init__.py

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

* Fix imports

* Address PR feedback from westey-m (#2150)

- Adds a link from the /dotnet/samples/README.md to /dotnet/samples/AzureFunctions
- Make DurableAgentThread deserialization internal for future-proofing
- Update JSON serialization logic to address recently discovered issues with source generator serialization

* Address comments (#2160)

---------

Co-authored-by: Laveesh Rohra <larohra@microsoft.com>
Co-authored-by: Chris Gillum <cgillum@microsoft.com>
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
Co-authored-by: Anirudh Garg <anirudhg@microsoft.com>
This commit is contained in:
Dmytro Struk
2025-11-12 18:00:53 -08:00
committed by GitHub
Unverified
parent 5537b1da79
commit 67a8147151
216 changed files with 18178 additions and 2 deletions
@@ -0,0 +1,82 @@
# Callback Telemetry Sample
This sample demonstrates how to use the Durable Extension for Agent Framework's response callbacks to observe
streaming updates and final agent responses in real time. The `ConversationAuditTrail` callback
records each chunk received from the Azure OpenAI agent and exposes the collected events through
an HTTP API that can be polled by a web client or dashboard.
## Highlights
- Registers a default `AgentResponseCallbackProtocol` implementation that logs streaming and final
responses.
- Persists callback events in an in-memory store and exposes them via
`GET /api/agents/{agentName}/callbacks/{thread_id}`.
- Shows how to reset stored callback events with `DELETE /api/agents/{agentName}/callbacks/{thread_id}`.
- Works alongside the standard `/api/agents/{agentName}/run` endpoint so you can correlate callback
telemetry with agent responses.
## Prerequisites
Complete the shared environment setup steps in `../README.md`, including creating a virtual environment, installing dependencies, and configuring Azure OpenAI credentials and storage settings.
> **Note:** The sample stores callback events in memory for simplicity. For production scenarios you
> should persist events to Application Insights, Azure Storage, Cosmos DB, or another durable store.
## Running the Sample
Send a prompt to the agent:
```bash
curl -X POST http://localhost:7071/api/agents/CallbackAgent/run \
-H "Content-Type: application/json" \
-d '{"message": "Tell me a short joke"}'
```
> **Note:** The run endpoint waits for the agent response by default. To return immediately, set the `x-ms-wait-for-response` header or include `"wait_for_response": false` in the request body.
Poll callback telemetry (replace `<conversationId>` with the value from the POST response):
```bash
curl http://localhost:7071/api/agents/CallbackAgent/callbacks/<conversationId>
```
Reset stored events:
```bash
curl -X DELETE http://localhost:7071/api/agents/CallbackAgent/callbacks/<conversationId>
```
## Expected Output
When you call `GET /api/agents/CallbackAgent/callbacks/{thread_id}` after sending a request to the agent,
the API returns a list of streaming and final callback events similar to the following:
```json
[
{
"timestamp": "2024-01-01T00:00:00Z",
"agent_name": "CallbackAgent",
"thread_id": "<thread_id>",
"correlation_id": "<guid>",
"request_message": "Tell me a short joke",
"event_type": "stream",
"update_kind": "text",
"text": "Sure, here's a joke..."
},
{
"timestamp": "2024-01-01T00:00:01Z",
"agent_name": "CallbackAgent",
"thread_id": "<thread_id>",
"correlation_id": "<guid>",
"request_message": "Tell me a short joke",
"event_type": "final",
"response_text": "Why did the cloud...",
"usage": {
"type": "usage_details",
"input_token_count": 159,
"output_token_count": 29,
"total_token_count": 188
}
}
]
```
@@ -0,0 +1,30 @@
### Callback Sample - API Tests
### Use with VS Code REST Client or another HTTP testing tool.
###
### Endpoints introduced in this sample:
### - POST /api/agents/{agentName}/run : send a message to the agent
### - GET /api/agents/{agentName}/callbacks/{thread_id} : retrieve callback telemetry
### - DELETE /api/agents/{agentName}/callbacks/{thread_id} : clear stored callback events
@baseUrl = http://localhost:7071
@agentName = CallbackAgent
@agentRoute = {{baseUrl}}/api/agents/{{agentName}}
@thread_id = test-thread-00
### Health Check
GET {{baseUrl}}/api/health
### Send message (callbacks will capture streaming + final response)
POST {{agentRoute}}/run
Content-Type: application/json
{
"message": "Generate a short weather update for Paris and mention streaming callbacks.",
"thread_id": "{{thread_id}}"
}
### Inspect callback telemetry
GET {{agentRoute}}/callbacks/{{thread_id}}
### Clear stored callback telemetry for the thread
DELETE {{agentRoute}}/callbacks/{{thread_id}}
@@ -0,0 +1,183 @@
"""Capture agent response callbacks inside Azure Functions.
Components used in this sample:
- AzureOpenAIChatClient to build an agent that streams interim updates.
- AgentFunctionApp with a default AgentResponseCallbackProtocol implementation.
- Azure Functions HTTP triggers that expose callback telemetry via REST.
Prerequisites: set `AZURE_OPENAI_ENDPOINT`, `AZURE_OPENAI_CHAT_DEPLOYMENT_NAME`, and either
`AZURE_OPENAI_API_KEY` or authenticate with Azure CLI before starting the Functions host."""
import json
import logging
from collections import defaultdict
from datetime import datetime, timezone
from typing import Any, DefaultDict
import azure.functions as func
from agent_framework import AgentRunResponseUpdate
from agent_framework.azure import (
AgentCallbackContext,
AgentFunctionApp,
AgentResponseCallbackProtocol,
AzureOpenAIChatClient,
)
from azure.identity import AzureCliCredential
logger = logging.getLogger(__name__)
# 1. Maintain an in-memory store for callback events keyed by thread ID (replace with durable storage in production).
CallbackStore = DefaultDict[str, list[dict[str, Any]]]
callback_events: CallbackStore = defaultdict(list)
def _serialize_usage(usage: Any) -> Any:
"""Best-effort serialization for agent usage metadata."""
if usage is None:
return None
model_dump = getattr(usage, "model_dump", None)
if callable(model_dump):
return model_dump()
to_dict = getattr(usage, "to_dict", None)
if callable(to_dict):
return to_dict()
return str(usage)
class ConversationAuditTrail(AgentResponseCallbackProtocol):
"""Callback that records streaming chunks and final responses for later inspection."""
def __init__(self) -> None:
self._logger = logging.getLogger("durableagent.samples.callbacks.audit")
async def on_streaming_response_update(
self,
update: AgentRunResponseUpdate,
context: AgentCallbackContext,
) -> None:
event = self._build_base_event(context)
event.update(
{
"event_type": "stream",
"update_kind": getattr(update, "kind", "text"),
"text": getattr(update, "text", None),
}
)
thread_id = context.thread_id or ""
callback_events[thread_id].append(event)
preview = event.get("text") or event.get("update_kind")
self._logger.info(
"[%s][%s] streaming chunk: %s",
context.agent_name,
context.correlation_id,
preview,
)
async def on_agent_response(self, response, context: AgentCallbackContext) -> None:
event = self._build_base_event(context)
event.update(
{
"event_type": "final",
"response_text": getattr(response, "text", None),
"usage": _serialize_usage(getattr(response, "usage_details", None)),
}
)
thread_id = context.thread_id or ""
callback_events[thread_id].append(event)
self._logger.info(
"[%s][%s] final response recorded",
context.agent_name,
context.correlation_id,
)
@staticmethod
def _build_base_event(context: AgentCallbackContext) -> dict[str, Any]:
thread_id = context.thread_id
return {
"timestamp": datetime.now(timezone.utc).isoformat(),
"agent_name": context.agent_name,
"thread_id": thread_id,
"correlation_id": context.correlation_id,
"request_message": context.request_message,
}
# 2. Create the agent that will emit streaming updates and final responses.
callback_agent = AzureOpenAIChatClient(credential=AzureCliCredential()).create_agent(
name="CallbackAgent",
instructions=(
"You are a friendly assistant that narrates actions while responding. "
"Keep answers concise and acknowledge when callbacks capture streaming updates."
),
)
# 3. Register the agent inside AgentFunctionApp with a default callback instance.
audit_callback = ConversationAuditTrail()
app = AgentFunctionApp(enable_health_check=True, default_callback=audit_callback)
app.add_agent(callback_agent)
@app.function_name("get_callback_events")
@app.route(route="agents/{agent_name}/callbacks/{thread_id}", methods=["GET"])
async def get_callback_events(req: func.HttpRequest) -> func.HttpResponse:
"""Return all callback events collected for a thread."""
thread_id = req.route_params.get("thread_id", "")
events = callback_events.get(thread_id, [])
return func.HttpResponse(
json.dumps(events, indent=2),
status_code=200,
mimetype="application/json",
)
@app.function_name("reset_callback_events")
@app.route(route="agents/{agent_name}/callbacks/{thread_id}", methods=["DELETE"])
async def reset_callback_events(req: func.HttpRequest) -> func.HttpResponse:
"""Clear the stored callback events for a thread."""
thread_id = req.route_params.get("thread_id", "")
callback_events.pop(thread_id, None)
return func.HttpResponse(status_code=204)
"""
Expected output when querying `GET /api/agents/CallbackAgent/callbacks/{thread_id}`:
HTTP/1.1 200 OK
[
{
"timestamp": "2024-01-01T00:00:00Z",
"agent_name": "CallbackAgent",
"thread_id": "<thread_id>",
"correlation_id": "<guid>",
"request_message": "Tell me a short joke",
"event_type": "stream",
"update_kind": "text",
"text": "Sure, here's a joke..."
},
{
"timestamp": "2024-01-01T00:00:01Z",
"agent_name": "CallbackAgent",
"thread_id": "<thread_id>",
"correlation_id": "<guid>",
"request_message": "Tell me a short joke",
"event_type": "final",
"response_text": "Why did the cloud...",
"usage": {
"type": "usage_details",
"input_token_count": 159,
"output_token_count": 29,
"total_token_count": 188
}
}
]
"""
@@ -0,0 +1,20 @@
{
"version": "2.0",
"logging": {
"applicationInsights": {
"samplingSettings": {
"isEnabled": true,
"maxTelemetryItemsPerSecond": 20
}
}
},
"extensionBundle": {
"id": "Microsoft.Azure.Functions.ExtensionBundle",
"version": "[4.*, 5.0.0)"
},
"extensions": {
"durableTask": {
"hubName": "%TASKHUB_NAME%"
}
}
}
@@ -0,0 +1,12 @@
{
"IsEncrypted": false,
"Values": {
"FUNCTIONS_WORKER_RUNTIME": "python",
"AzureWebJobsStorage": "UseDevelopmentStorage=true",
"DURABLE_TASK_SCHEDULER_CONNECTION_STRING": "Endpoint=http://localhost:8080;TaskHub=default;Authentication=None",
"TASKHUB_NAME": "default",
"AZURE_OPENAI_ENDPOINT": "<AZURE_OPENAI_ENDPOINT>",
"AZURE_OPENAI_CHAT_DEPLOYMENT_NAME": "<AZURE_OPENAI_CHAT_DEPLOYMENT_NAME>",
"AZURE_OPENAI_API_KEY": "<AZURE_OPENAI_API_KEY>"
}
}
@@ -0,0 +1,2 @@
agent-framework-azurefunctions
azure-identity