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file with only comment path updates (100 files) - One import-fix diff (workflow_as_agent_human_in_the_loop.py) - One superseded minimal_sample.py Resource files (sample.pdf, countries.json, employees.pdf, weather.json) copied to 02-agents/sample_assets/ and 02-agents/resources/ since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
117 lines
4.8 KiB
Markdown
117 lines
4.8 KiB
Markdown
# Samples Structure & Design Choices — Python
|
||
|
||
> This file documents the structure and conventions of the Python samples so that
|
||
> agents (AI or human) can maintain them without rediscovering decisions.
|
||
|
||
## Directory layout
|
||
|
||
```
|
||
python/samples/
|
||
├── 01-get-started/ # Progressive tutorial (steps 01–06)
|
||
├── 02-agents/ # Deep-dive concept samples
|
||
│ ├── tools/ # Tool patterns (function, approval, schema, etc.)
|
||
│ ├── middleware/ # One file per middleware concept
|
||
│ ├── conversations/ # Thread, storage, suspend/resume
|
||
│ ├── providers/ # One sub-folder per provider (azure_ai/, openai/, etc.)
|
||
│ ├── context_providers/ # Memory & context injection
|
||
│ ├── orchestrations/ # Multi-agent orchestration patterns
|
||
│ ├── observability/ # Tracing, telemetry
|
||
│ ├── declarative/ # Declarative agent definitions
|
||
│ ├── chat_client/ # Raw chat client usage
|
||
│ ├── mcp/ # MCP server/client patterns
|
||
│ ├── multimodal_input/ # Image, audio inputs
|
||
│ └── devui/ # DevUI agent/workflow samples
|
||
├── 03-workflows/ # Workflow samples (preserved from upstream)
|
||
│ ├── _start-here/ # Introductory workflow samples
|
||
│ ├── agents/ # Agents in workflows
|
||
│ ├── checkpoint/ # Checkpointing & resume
|
||
│ ├── composition/ # Sub-workflows
|
||
│ ├── control-flow/ # Edges, conditions, loops
|
||
│ ├── declarative/ # YAML-based workflows
|
||
│ ├── human-in-the-loop/ # HITL patterns
|
||
│ ├── observability/ # Workflow telemetry
|
||
│ ├── parallelism/ # Fan-out, map-reduce
|
||
│ ├── state-management/ # State isolation, kwargs
|
||
│ ├── tool-approval/ # Tool approval in workflows
|
||
│ └── visualization/ # Workflow visualization
|
||
├── 04-hosting/ # Deployment & hosting
|
||
│ ├── a2a/ # Agent-to-Agent protocol
|
||
│ ├── azure-functions/ # Azure Functions samples
|
||
│ └── durabletask/ # Durable task framework
|
||
├── 05-end-to-end/ # Complete applications
|
||
│ ├── chatkit-integration/
|
||
│ ├── evaluation/
|
||
│ ├── hosted_agents/
|
||
│ ├── m365-agent/
|
||
│ ├── purview_agent/
|
||
│ └── workflow_evaluation/
|
||
├── autogen-migration/ # Migration guides (do not restructure)
|
||
├── semantic-kernel-migration/
|
||
└── _to_delete/ # Old samples awaiting review
|
||
```
|
||
|
||
## Design principles
|
||
|
||
1. **Progressive complexity**: Sections 01→05 build from "hello world" to
|
||
production. Within 01-get-started, files are numbered 01–06 and each step
|
||
adds exactly one concept.
|
||
|
||
2. **One concept per file** in 01-get-started and flat files in 02-agents/.
|
||
|
||
3. **Workflows preserved**: 03-workflows/ keeps the upstream folder names
|
||
and file names intact. Do not rename or restructure workflow samples.
|
||
|
||
4. **Single-file for 01-03**: Only 04-hosting and 05-end-to-end use multi-file
|
||
projects with their own README.
|
||
|
||
## Default provider
|
||
|
||
All canonical samples (01-get-started) use **Azure OpenAI Responses** via `AzureOpenAIResponsesClient`
|
||
with an Azure AI Foundry project endpoint:
|
||
|
||
```python
|
||
import os
|
||
from agent_framework.azure import AzureOpenAIResponsesClient
|
||
from azure.identity import AzureCliCredential
|
||
|
||
credential = AzureCliCredential()
|
||
client = AzureOpenAIResponsesClient(
|
||
project_endpoint=os.environ["AZURE_AI_PROJECT_ENDPOINT"],
|
||
deployment_name=os.environ["AZURE_OPENAI_RESPONSES_DEPLOYMENT_NAME"],
|
||
credential=credential,
|
||
)
|
||
agent = client.as_agent(name="...", instructions="...")
|
||
```
|
||
|
||
Environment variables:
|
||
- `AZURE_AI_PROJECT_ENDPOINT` — Your Azure AI Foundry project endpoint
|
||
- `AZURE_OPENAI_RESPONSES_DEPLOYMENT_NAME` — Model deployment name (e.g. gpt-4o)
|
||
|
||
For authentication, run `az login` before running samples.
|
||
|
||
## Snippet tags for docs integration
|
||
|
||
Samples embed named snippet regions for future `:::code` integration:
|
||
|
||
```python
|
||
# <snippet_name>
|
||
code here
|
||
# </snippet_name>
|
||
```
|
||
|
||
## Package install
|
||
|
||
```bash
|
||
pip install agent-framework --pre
|
||
```
|
||
|
||
The `--pre` flag is needed during preview. `openai` is a core dependency.
|
||
|
||
## Current API notes
|
||
|
||
- `Agent` class renamed from `ChatAgent` (use `from agent_framework import Agent`)
|
||
- `Message` class renamed from `ChatMessage` (use `from agent_framework import Message`)
|
||
- `call_next` in middleware takes NO arguments: `await call_next()` (not `await call_next(context)`)
|
||
- Prefer `client.as_agent(...)` over `Agent(client=client, ...)`
|
||
- Tool methods on hosted tools are now functions, not classes (e.g. `hosted_mcp_tool(...)` not `HostedMCPTool(...)`)
|