mirror of https://github.com/microsoft/agent-framework.git synced 2026-06-16 21:04:09 +08:00

Files

T

westey 626b418622 .NET: Harness Feature branch (#5310 )

* .NET: Add a TODO AIContextProvider (#5233)

* Add a TODO AIContextProvider

* Add unit tests

* Address PR comments

* Address PR comments

* Fix test after removing one tool

* .NET: Add a ModeProvider for managing agent modes (#5247)

* Add a ModeProvider for managing agent modes

* Fix typo

* Fix typo

* Fix typo

* Address PR comments

* .NET: Add sample to show how to build a harness (#5268)

* Add sample to show how to build a harness

* Improve sample

* Sample max output tokens and model

* Fix encoding

* Fix model name in readme

* Address PR comments

* .NET: Add context window size compaction strategy for harness (#5304)

* Add context window size compaction strategy for harness

* Apply suggestions from code review

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

* Address PR comments

---------

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

* .NET: Add a file memory provider (#5315)

* Add a file memory provider

* Address PR comments

* Fix review comments.

* Add additional unit tests

* Addressing PR comments.

* .NET:  Harness: Improve prompts and add FileSystem store (#5365)

* Harness: Improve prompts and add FileSystem store

* Address PR comments

* .NET: Harness: Improve path validation (#5404)

* Harness: Improve path validation

* Address PR comments

* .NET: Add always approve helpers, improve sample and fix bug (#5451)

* Add always approve helpers, improve sample and fix bug

* Address PR comments

* .NET: Make Todo, Mode and FileMemory providers more configurable (#5477)

* Make Todo, Mode and FileMemory providers more configurable

* Address PR comments.

* .NET: Add subagents provider and sample (#5518)

* Add subagents provider and sample

* Addressing PR comments.

* .NET: Harness filememory index plus instructions consistency (#5540)

* Add FileMemoryProvider index and improve instruction consistency

* Address PR comments.

* Address PR comments

* Address PR comments.

* Apply suggestion from @rogerbarreto

Co-authored-by: Roger Barreto <19890735+rogerbarreto@users.noreply.github.com>

---------

Co-authored-by: Roger Barreto <19890735+rogerbarreto@users.noreply.github.com>

* .NET: Refactor harness console to be more extensible and easy to understand with better UX (#5573)

* Refactor harness console to be more extensible and easy to understand with better UX.

* Fix formatting issues.

* Allow multiple clarifications in one response

* Address PR comments

* .NET: Add FileAccessProvdider and concurrency fix for FileMemoryProvider (#5583)

* Add FileAccessProvdider and concurrency fix for FileMemoryProvider

* Address PR comments

---------

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
Co-authored-by: Roger Barreto <19890735+rogerbarreto@users.noreply.github.com>

626b418622 · 2026-05-01 10:52:38 +00:00

History

Harness_Step01_Research.csproj

.NET: Harness Feature branch (#5310 )

2026-05-01 10:52:38 +00:00

Program.cs

.NET: Harness Feature branch (#5310 )

2026-05-01 10:52:38 +00:00

README.md

.NET: Harness Feature branch (#5310 )

2026-05-01 10:52:38 +00:00

WebBrowsingTool.cs

.NET: Harness Feature branch (#5310 )

2026-05-01 10:52:38 +00:00

README.md

What this sample demonstrates

This sample demonstrates how to use a ChatClientAgent with the Harness AIContextProviders (TodoProvider and AgentModeProvider) for interactive research tasks with web search capabilities powered by Azure AI Foundry.

Key features showcased:

ChatClientAgent — configured directly with Harness providers for planning and task management
Web Search — the agent can search the web for current information via ResponseTool.CreateWebSearchTool()
TodoProvider — the agent creates and manages a todo list to track research questions
AgentModeProvider — the agent switches between "plan" mode (breaking down the topic) and "execute" mode (answering each research question)
Interactive conversation — you can review the agent's plan, provide feedback, and approve before execution begins
Streaming output — responses are streamed token-by-token for a natural experience
/todos command — view the current todo list at any time without invoking the agent
Mode-based coloring — console output is colored based on the agent's current mode (cyan for plan, green for execute)

Prerequisites

Before running this sample, ensure you have:

An Azure AI Foundry project with a deployed model (e.g., gpt-5.4)
Azure CLI installed and authenticated (az login)

Environment Variables

Set the following environment variables:

# Required: Your Azure AI Foundry OpenAI endpoint
export AZURE_FOUNDRY_OPENAI_ENDPOINT="https://your-project.services.ai.azure.com/openai/v1/"

# Optional: Model deployment name (defaults to gpt-5.4)
export AZURE_AI_MODEL_DEPLOYMENT_NAME="gpt-5.4"

Running the Sample

cd dotnet
dotnet run --project samples/02-agents/Harness/Harness_Step01_Research

What to Expect

The sample starts an interactive conversation loop. You can:

Enter a research topic — the agent will analyze it and create a plan with todos
Review and adjust — provide feedback on the plan, ask for changes, or approve it
Type /todos — to see the current todo list at any time
Watch execution — once approved, tell the agent to proceed and it will work through each todo
Type exit — to end the session

The prompt and agent output are colored by the current mode: cyan during planning, green during execution.