mirror of
https://github.com/microsoft/agent-framework.git
synced 2026-06-16 21:04:09 +08:00
de791fb8a9
* Add 3 new hosted agent samples: AgentWithTools, AgentWithLocalTools, AgentThreadAndHITL - AgentWithTools: Foundry tools (MCP + code interpreter) via UseFoundryTools - AgentWithLocalTools: Local C# function tool (Seattle hotel search) with AIProjectClient - AgentThreadAndHITL: Human-in-the-loop with ApprovalRequiredAIFunction and thread persistence All samples follow agent-framework conventions (net10.0, AzureCliCredential, CPM disabled). AgentWithTools includes comprehensive README with setup guide and troubleshooting. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * Add root HostedAgents README, replace test_requests.py with .http, update sample READMEs - Create root README.md with shared prerequisites, Azure AI Foundry setup, troubleshooting, and samples index - Replace test_requests.py with run-requests.http in AgentThreadAndHITL - Add pointer to root README in all 6 sample READMEs - Trim AgentWithTools README to concise style Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * Fix dotnet format issues in AgentWithLocalTools/Program.cs - Add UTF-8 BOM (CHARSET) - Sort System.ClientModel.Primitives import alphabetically (IMPORTS) - Use target-typed new for AIProjectClient (IDE0090) - Add internal accessibility modifier to Hotel record (IDE0040) Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * Address PR review: align model names and package versions - Change default model from gpt-4.1-mini to gpt-4o-mini in AgentWithLocalTools (Program.cs, agent.yaml, README.md) to match existing samples - Change README example from gpt-5.2 to gpt-4o-mini in AgentWithTools and root README - Align AgentWithLocalTools package versions with other samples: Azure.AI.AgentServer.AgentFramework beta.6 -> beta.8 Azure.AI.OpenAI 2.8.0-beta.1 -> 2.7.0-beta.2 Microsoft.Extensions.AI.OpenAI 10.2.0-preview -> 10.1.1-preview Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * Upgrade new samples to latest package versions - Azure.AI.OpenAI: 2.7.0-beta.2 -> 2.8.0-beta.1 - Microsoft.Extensions.AI.OpenAI: 10.1.1-preview -> 10.3.0 Aligns with AgentWithHostedMCP which uses the latest versions. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * Pin AgentThreadAndHITL to Microsoft.Extensions.AI.OpenAI 10.1.1 Azure.AI.AgentServer.AgentFramework beta.8 was compiled against Microsoft.Extensions.AI.Abstractions with the single-param FunctionApprovalRequestContent.CreateResponse(bool). Version 10.3.0 changed the signature to include an optional reason parameter, causing a binary incompatibility at runtime. Pin to 10.1.1 until the framework is recompiled against the newer abstractions. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> --------- Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
71 lines
1.9 KiB
HTTP
71 lines
1.9 KiB
HTTP
@host = http://localhost:8088
|
|
@endpoint = {{host}}/responses
|
|
|
|
### Health Check
|
|
GET {{host}}/readiness
|
|
|
|
###
|
|
# HITL (Human-in-the-Loop) Flow
|
|
#
|
|
# This sample requires a multi-turn conversation to demonstrate the approval flow:
|
|
# 1. Send a request that triggers a tool call (e.g., asking about the weather)
|
|
# 2. The agent responds with a function_call named "__hosted_agent_adapter_hitl__"
|
|
# containing the call_id and the tool details
|
|
# 3. Send a follow-up request with a function_call_output to approve or reject
|
|
#
|
|
# IMPORTANT: You must use the same conversation.id across all requests in a flow,
|
|
# and update the call_id from step 2 into step 3.
|
|
###
|
|
|
|
### Step 1: Send initial request (triggers HITL approval)
|
|
# @name initialRequest
|
|
POST {{endpoint}}
|
|
Content-Type: application/json
|
|
|
|
{
|
|
"input": "What is the weather like in Vancouver?",
|
|
"stream": false,
|
|
"conversation": {
|
|
"id": "conv_test0000000000000000000000000000000000000000000000"
|
|
}
|
|
}
|
|
|
|
### Step 2: Approve the function call
|
|
# Copy the call_id from the Step 1 response output and replace below.
|
|
# The response will contain: "name": "__hosted_agent_adapter_hitl__" with a "call_id" value.
|
|
POST {{endpoint}}
|
|
Content-Type: application/json
|
|
|
|
{
|
|
"input": [
|
|
{
|
|
"type": "function_call_output",
|
|
"call_id": "REPLACE_WITH_CALL_ID_FROM_STEP_1",
|
|
"output": "approve"
|
|
}
|
|
],
|
|
"stream": false,
|
|
"conversation": {
|
|
"id": "conv_test0000000000000000000000000000000000000000000000"
|
|
}
|
|
}
|
|
|
|
### Step 3 (alternative): Reject the function call
|
|
# Use this instead of Step 2 to deny the tool execution.
|
|
POST {{endpoint}}
|
|
Content-Type: application/json
|
|
|
|
{
|
|
"input": [
|
|
{
|
|
"type": "function_call_output",
|
|
"call_id": "REPLACE_WITH_CALL_ID_FROM_STEP_1",
|
|
"output": "reject"
|
|
}
|
|
],
|
|
"stream": false,
|
|
"conversation": {
|
|
"id": "conv_test0000000000000000000000000000000000000000000000"
|
|
}
|
|
}
|