chore: import upstream snapshot with attribution

2026-07-13 13:39:25 +08:00
commit db620d33df
5151 changed files with 925932 additions and 0 deletions
@@ -0,0 +1,7 @@
+.venv
+__pycache__
+*.pyc
+*.pyo
+*.pyd
+.Python
+.env
@@ -0,0 +1,2 @@
+FOUNDRY_PROJECT_ENDPOINT="..."
+AZURE_AI_MODEL_DEPLOYMENT_NAME="..."
@@ -0,0 +1,16 @@
+FROM python:3.12-slim
+
+WORKDIR /app
+
+COPY . user_agent/
+WORKDIR /app/user_agent
+
+RUN if [ -f requirements.txt ]; then \
+        pip install -r requirements.txt; \
+    else \
+        echo "No requirements.txt found"; \
+    fi
+
+EXPOSE 8088
+
+CMD ["python", "main.py"]
@@ -0,0 +1,43 @@
+# What this sample demonstrates
+
+An [Agent Framework](https://github.com/microsoft/agent-framework) workflow demonstrating **multi-agent chaining** and hosted using the **Responses protocol**. It shows how to use the Agent Framework's `WorkflowBuilder` to compose a pipeline of specialized agents — a slogan writer, a legal reviewer, and a formatter — that process a request sequentially. Each agent receives only the output of the previous agent, and only the final formatted result is returned to the caller.
+
+> The workflow will be used as an agent. Read more about Agent Framework workflows in the [Agent Framework documentation](https://learn.microsoft.com/en-us/agent-framework/workflows/) and workflow as an agent in the [Workflow as an Agent documentation](https://learn.microsoft.com/en-us/agent-framework/workflows/as-agents?pivots=programming-language-python).
+
+> This sample requires a more advanced model because the model needs to continue the conversation from an assistant message. Not all models perform well in this scenario. Tested with OpenAI's model `gpt-5.4`.
+
+## How It Works
+
+### Model Integration
+
+The agent creates three specialized `Agent` instances sharing the same `FoundryChatClient`: a **writer** that generates slogans, a **legal reviewer** that ensures compliance, and a **formatter** that styles the output. Each agent is wrapped in an `AgentExecutor` with `context_mode="last_agent"` so it only sees the previous agent's output. The `WorkflowBuilder` wires them into a linear pipeline and limits the output to the formatter's result.
+
+See [main.py](main.py) for the full implementation.
+
+### Agent Hosting
+
+The workflow is exposed as a single agent via `.as_agent()` and hosted using the [Agent Framework](https://github.com/microsoft/agent-framework) with the `ResponsesHostServer`, which provisions a REST API endpoint compatible with the OpenAI Responses protocol.
+
+## Running the Agent Host
+
+Follow the instructions in the [Running the Agent Host Locally](../../README.md#running-the-agent-host-locally) section of the README in the parent directory to run the agent host.
+
+## Interacting with the agent
+
+> Depending on how you run the agent host, you can invoke the agent using `curl` (`Invoke-WebRequest` in PowerShell) or `azd`. Please refer to the [parent README](../../README.md) for more details. Use this README for sample queries you can send to the agent.
+
+Send a POST request to the server with a JSON body containing an `"input"` field to interact with the agent. For example:
+
+```bash
+curl -X POST http://localhost:8088/responses -H "Content-Type: application/json" -d '{"input": "Create a slogan for a new electric SUV that is affordable and fun to drive."}'
+```
+
+Invoke with `azd`:
+
+```bash
+azd ai agent invoke --local "Create a slogan for a new electric SUV that is affordable and fun to drive."
+```
+
+## Deploying the Agent to Foundry
+
+To host the agent on Foundry, follow the instructions in the [Deploying the Agent to Foundry](../../README.md#deploying-the-agent-to-foundry) section of the README in the parent directory.
@@ -0,0 +1,23 @@
+name: agent-framework-workflows-responses
+description: >
+  An Agent Framework workflow hosted by Foundry.
+metadata:
+  tags:
+    - Agent Framework
+    - AI Agent Hosting
+    - Azure AI AgentServer
+    - Responses Protocol
+    - Streaming
+template:
+  name: agent-framework-workflows-responses
+  kind: hosted
+  protocols:
+    - protocol: responses
+      version: 2.0.0
+  environment_variables:
+    - name: AZURE_AI_MODEL_DEPLOYMENT_NAME
+      value: "{{AZURE_AI_MODEL_DEPLOYMENT_NAME}}"
+resources:
+  - kind: model
+    id: gpt-5.4
+    name: AZURE_AI_MODEL_DEPLOYMENT_NAME
@@ -0,0 +1,11 @@
+kind: hosted
+name: agent-framework-workflows-responses
+protocols:
+  - protocol: responses
+    version: 2.0.0
+resources:
+  cpu: "0.25"
+  memory: 0.5Gi
+environment_variables:
+  - name: AZURE_AI_MODEL_DEPLOYMENT_NAME
+    value: ${AZURE_AI_MODEL_DEPLOYMENT_NAME}
@@ -0,0 +1,70 @@
+# Copyright (c) Microsoft. All rights reserved.
+
+import os
+
+from agent_framework import Agent, AgentExecutor, WorkflowBuilder
+from agent_framework.foundry import FoundryChatClient
+from agent_framework_foundry_hosting import ResponsesHostServer
+from azure.identity import DefaultAzureCredential
+from dotenv import load_dotenv
+
+# Load environment variables from .env file
+load_dotenv()
+
+
+def main():
+    client = FoundryChatClient(
+        project_endpoint=os.environ["FOUNDRY_PROJECT_ENDPOINT"],
+        model=os.environ["AZURE_AI_MODEL_DEPLOYMENT_NAME"],
+        credential=DefaultAzureCredential(),
+    )
+
+    writer_agent = Agent(
+        client=client,
+        instructions=("You are an excellent slogan writer. You create new slogans based on the given topic."),
+        name="writer",
+    )
+
+    legal_agent = Agent(
+        client=client,
+        instructions=(
+            "You are an excellent legal reviewer. "
+            "Make necessary corrections to the slogan so that it is legally compliant."
+        ),
+        name="legal_reviewer",
+    )
+
+    format_agent = Agent(
+        client=client,
+        instructions=(
+            "You are an excellent content formatter. "
+            "You take the slogan and format it in a cool retro style when printing to a terminal."
+        ),
+        name="formatter",
+    )
+
+    # Set the context mode to `last_agent` so that each agent only sees the output of the
+    # previous agent instead of the full conversation history
+    writer_executor = AgentExecutor(writer_agent, context_mode="last_agent")
+    legal_executor = AgentExecutor(legal_agent, context_mode="last_agent")
+    format_executor = AgentExecutor(format_agent, context_mode="last_agent")
+
+    workflow_agent = (
+        WorkflowBuilder(
+            start_executor=writer_executor,
+            # Select only the formatted result as Workflow Output.
+            # Unselected executor payloads are hidden unless selected as Intermediate Output.
+            output_from=[format_executor],
+        )
+        .add_edge(writer_executor, legal_executor)
+        .add_edge(legal_executor, format_executor)
+        .build()
+        .as_agent()
+    )
+
+    server = ResponsesHostServer(workflow_agent)
+    server.run()
+
+
+if __name__ == "__main__":
+    main()
@@ -0,0 +1,2 @@
+agent-framework-foundry
+agent-framework-foundry-hosting>=1.0.0a260630