agent/agent-framework
1
0
Fork 0
mirror of https://github.com/microsoft/agent-framework.git synced 2026-06-16 21:04:09 +08:00
Code Issues Packages Projects Releases Wiki Activity

Python: Add Sequential orchestration builder support. Samples. Tests. (#703)

Browse Source 
* Add support for the Sequential Builder. Add samples. Add tests

* AgentExecutor: always compute full convo during response

* Upgrade azure-ai-agents ToolOutput to FunctionToolOutput

* Explicit notes around allows types for custom agent executors
This commit is contained in:
Evan Mattson
2025-09-16 10:52:34 +09:00
committed by GitHub
Unverified
parent 68b76e6726
commit 5c0b037e2c
11 changed files with 2537 additions and 1936 deletions
Download Patch File Download Diff File Expand all files Collapse all files
python/samples/getting_started/workflow/README.md
+9
View File
@@ -83,6 +83,8 @@ Once comfortable with these, explore the rest of the samples below.
| Concurrent Orchestration (Custom Agent Executors) | [orchestration/concurrent_custom_agent_executors.py](./orchestration/concurrent_custom_agent_executors.py) | Child executors own ChatAgents; concurrent fan-out/fan-in via ConcurrentBuilder |
| Magentic Workflow (Multi-Agent) | [orchestration/magentic.py](./orchestration/magentic.py) | Orchestrate multiple agents with Magentic manager and streaming |
| Magentic + Human Plan Review | [orchestration/magentic_human_plan_update.py](./orchestration/magentic_human_plan_update.py) | Human reviews/updates the plan before execution |
| Sequential Orchestration (Agents) | [orchestration/sequential_agents.py](./orchestration/sequential_agents.py) | Chain agents sequentially with shared conversation context |
| Sequential Orchestration (Custom Executor) | [orchestration/sequential_custom_executors.py](./orchestration/sequential_custom_executors.py) | Mix agents with a summarizer that appends a compact summary |
### parallelism
| Sample | File | Concepts |
@@ -110,6 +112,13 @@ Once comfortable with these, explore the rest of the samples below.
Notes
- Agent-based samples use provider SDKs (Azure/OpenAI, etc.). Ensure credentials are configured, or adapt agents accordingly.
Sequential orchestration uses a few small adapter nodes for plumbing:
- "input-conversation" normalizes input to `list[ChatMessage]`
- "to-conversation:<participant>" converts agent responses into the shared conversation
- "complete" publishes the final `WorkflowCompletedEvent`
These may appear in event streams (ExecutorInvoke/Completed). They’re analogous to
concurrent’s dispatcher and aggregator and can be ignored if you only care about agent activity.
### Environment Variables
- **AzureChatClient**: Set Azure OpenAI environment variables as documented [here](https://github.com/microsoft/agent-framework/blob/main/python/samples/getting_started/chat_client/README.md#environment-variables).