mirror of
https://github.com/microsoft/agent-framework.git
synced 2026-06-16 21:04:09 +08:00
Eduard van Valkenburg
a2856d3b92
* restructure: Python samples into progressive 01-05 layout - 01-get-started/: 6 numbered steps (hello agent → hosting) - 02-agents/: all agent concept samples (tools, middleware, providers, etc.) - 03-workflows/: ALL existing workflow samples preserved as-is - 04-hosting/: azure-functions, durabletask, a2a - 05-end-to-end/: demos, evaluation, hosted agents - Old files moved to _to_delete/ for review - Added AGENTS.md with structure documentation - autogen-migration/ and semantic-kernel-migration/ preserved at root * fix: switch to AzureOpenAI Foundry, fix CI failures - Switch all 01-get-started samples to AzureOpenAIResponsesClient with Azure AI Foundry project endpoint (AZURE_AI_PROJECT_ENDPOINT + AZURE_OPENAI_RESPONSES_DEPLOYMENT_NAME + AzureCliCredential) - Add _to_delete/ and 05-end-to-end/ to pyrightconfig.samples.json excludes - Fix test paths in packages/ that referenced old getting_started/ dirs: durabletask conftest + streaming test, azurefunctions conftest, devui conftest + capture_messages + openai_sdk_integration - Fix workflow_as_agent_human_in_the_loop.py import (sibling import) - Update hosting READMEs and tool comment paths - Replace root README.md with new structure overview - Update AGENTS.md to document Azure OpenAI Foundry as default provider * cleanup: remove _to_delete folder, copy resource files to active dirs All files in _to_delete/ were either: - Exact duplicates of files in the new structure (240 files) - Same file with only comment path updates (100 files) - One import-fix diff (workflow_as_agent_human_in_the_loop.py) - One superseded minimal_sample.py Resource files (sample.pdf, countries.json, employees.pdf, weather.json) copied to 02-agents/sample_assets/ and 02-agents/resources/ since active samples reference them. * fix: address PR review comments, centralize resources, remove root duplicates - Fix type annotation in 04_memory.py (string union -> proper types) - Fix old sample paths in observability files - Fix grammar/spelling in observability samples - Move sample_assets/ and resources/ to shared/ folder - Remove 8 duplicate observability files from 02-agents root - Update resource path references in multimodal_input and provider samples * fix: update broken links from old getting_started paths to new structure - Update relative paths in READMEs: getting_started/ → 01-get-started/, 02-agents/, 03-workflows/, 04-hosting/, 05-end-to-end/ - Fix absolute GitHub URLs in package READMEs - Fix broken link in ollama package README * fix: convert absolute GitHub URLs to relative paths for link checker Absolute URLs to python/samples/ on main branch 404 until PR merges. Converted to relative paths that linkspector can verify locally. * fix: update link for handoff sample moved to orchestrations/ * fix: update chatkit-integration README path from demos/ to 05-end-to-end/ * fix: update broken links in orchestrations README to match flat directory structure
70 lines
3.6 KiB
Markdown
70 lines
3.6 KiB
Markdown
# Custom Agent and Chat Client Examples
|
|
|
|
This folder contains examples demonstrating how to implement custom agents and chat clients using the Microsoft Agent Framework.
|
|
|
|
## Examples
|
|
|
|
| File | Description |
|
|
|------|-------------|
|
|
| [`custom_agent.py`](custom_agent.py) | Shows how to create custom agents by extending the `BaseAgent` class. Demonstrates the `EchoAgent` implementation with both streaming and non-streaming responses, proper thread management, and message history handling. |
|
|
| [`custom_chat_client.py`](../../chat_client/custom_chat_client.py) | Demonstrates how to create custom chat clients by extending the `BaseChatClient` class. Shows a `EchoingChatClient` implementation and how to integrate it with `Agent` using the `as_agent()` method. |
|
|
|
|
## Key Takeaways
|
|
|
|
### Custom Agents
|
|
- Custom agents give you complete control over the agent's behavior
|
|
- You must implement both `run()` for both the `stream=True` and `stream=False` cases
|
|
- Use `self._normalize_messages()` to handle different input message formats
|
|
- Use `self._notify_thread_of_new_messages()` to properly manage conversation history
|
|
|
|
### Custom Chat Clients
|
|
- Custom chat clients allow you to integrate any backend service or create new LLM providers
|
|
- You must implement `_inner_get_response()` with a stream parameter to handle both streaming and non-streaming responses
|
|
- Custom chat clients can be used with `Agent` to leverage all agent framework features
|
|
- Use the `as_agent()` method to easily create agents from your custom chat clients
|
|
|
|
Both approaches allow you to extend the framework for your specific use cases while maintaining compatibility with the broader Agent Framework ecosystem.
|
|
|
|
## Understanding Raw Client Classes
|
|
|
|
The framework provides `Raw...Client` classes (e.g., `RawOpenAIChatClient`, `RawOpenAIResponsesClient`, `RawAzureAIClient`) that are intermediate implementations without middleware, telemetry, or function invocation support.
|
|
|
|
### Warning: Raw Clients Should Not Normally Be Used Directly
|
|
|
|
**The `Raw...Client` classes should not normally be used directly.** They do not include the middleware, telemetry, or function invocation support that you most likely need. If you do use them, you should carefully consider which additional layers to apply.
|
|
|
|
### Layer Ordering
|
|
|
|
There is a defined ordering for applying layers that you should follow:
|
|
|
|
1. **ChatMiddlewareLayer** - Should be applied **first** because it also prepares function middleware
|
|
2. **FunctionInvocationLayer** - Handles tool/function calling loop
|
|
3. **ChatTelemetryLayer** - Must be **inside** the function calling loop for correct per-call telemetry
|
|
4. **Raw...Client** - The base implementation (e.g., `RawOpenAIChatClient`)
|
|
|
|
Example of correct layer composition:
|
|
|
|
```python
|
|
class MyCustomClient(
|
|
ChatMiddlewareLayer[TOptions],
|
|
FunctionInvocationLayer[TOptions],
|
|
ChatTelemetryLayer[TOptions],
|
|
RawOpenAIChatClient[TOptions], # or BaseChatClient for custom implementations
|
|
Generic[TOptions],
|
|
):
|
|
"""Custom client with all layers correctly applied."""
|
|
pass
|
|
```
|
|
|
|
### Use Fully-Featured Clients Instead
|
|
|
|
For most use cases, use the fully-featured public client classes which already have all layers correctly composed:
|
|
|
|
- `OpenAIChatClient` - OpenAI Chat completions with all layers
|
|
- `OpenAIResponsesClient` - OpenAI Responses API with all layers
|
|
- `AzureOpenAIChatClient` - Azure OpenAI Chat with all layers
|
|
- `AzureOpenAIResponsesClient` - Azure OpenAI Responses with all layers
|
|
- `AzureAIClient` - Azure AI Project with all layers
|
|
|
|
These clients handle the layer composition correctly and provide the full feature set out of the box.
|