Jordan Ritter
1900bace89
Re-applies the starter @chat usability fix that was collaterally reverted.
PR #5210 standardized starter agent registry keys to "default", and PR #5151
(ENT-679) had added useSingleEndpoint={false} to the starter <CopilotKit>
layouts. Together those two halves fixed the "@chat: No assistant response"
blocker: without them the client auto-detects single-endpoint transport and
POSTs to a route that 404s instead of the per-agent endpoint keyed "default".
The ENT-679 revert (#5217, commit 3721e7b36) backed out BOTH halves as
collateral, so starters on main are broken again (adk key my_agent, agno
agno_agent, etc., and no useSingleEndpoint={false}).
This re-applies ONLY the usability fix, fully decoupled from the Intelligence
threads feature. No threads-drawer, no _intelligence overlay, no
CopilotKitIntelligence runtime block, no ghcr composite images.
Per affected starter:
- route.ts (or mastra/index.ts): agents registry key -> default
- layout.tsx: add useSingleEndpoint={false}, drop agent= prop (falls back to default)
- page.tsx: useAgent name/agentId literal -> "default"
Affected starters: adk, agno, crewai-crews, llamaindex,
ms-agent-framework-dotnet, ms-agent-framework-python, pydantic-ai, mastra.
Agent semantic names/exports (e.g. mastra weatherAgent) are unchanged; only
the registry KEY and frontend agentId become "default".
Real verification is the smoke-starter @chat matrix legs in CI.
CopilotKit <> Microsoft Agent Framework (Python)
This is a starter template for building CopilotKit experiences using the Microsoft Agent Framework. It ships with a Next.js UI and a FastAPI server that exposes a Microsoft Agent Framework agent over the AG-UI protocol, so you can study and customize both sides of the stack.
Prerequisites
- OpenAI or Azure OpenAI credentials (for the Microsoft Agent Framework agent)
- Python 3.12+
- uv
- Node.js 20+
- Any of the following package managers:
Getting Started
-
Install dependencies using your preferred package manager:
# Using npm (default) npm install # Using pnpm pnpm install # Using yarn yarn install # Using bun bun installNote: This automatically sets up the Python environment as well.
If you have manual issues, you can run:
npm run install:agent -
Set up your agent credentials. The backend automatically uses Azure when the Azure env vars below are present; otherwise it falls back to OpenAI. Create a
.envfile inside theagentfolder with one of the following configurations:OpenAI
OPENAI_API_KEY=sk-...your-openai-key-here... OPENAI_CHAT_MODEL_ID=gpt-4o-miniAzure OpenAI
AZURE_OPENAI_ENDPOINT=https://your-resource.openai.azure.com/ AZURE_OPENAI_CHAT_DEPLOYMENT_NAME=gpt-4o-mini # If you are not relying on az login: # AZURE_OPENAI_API_KEY=... -
Start the development server:
# Using npm (default) npm run dev # Using pnpm pnpm dev # Using yarn yarn dev # Using bun bun run devThis will start both the UI and the Microsoft Agent Framework server concurrently.
Available Scripts
The following scripts can also be run using your preferred package manager:
dev– Starts both UI and agent servers in development modedev:debug– Starts development servers with debug logging enableddev:ui– Starts only the Next.js UI serverdev:agent– Starts only the Microsoft Agent Framework serverbuild– Builds the Next.js application for productionstart– Starts the production serverlint– Runs ESLint for code lintinginstall:agent– Installs Python dependencies for the agent
Documentation
The main UI component is in src/app/page.tsx. You can:
- Modify the theme colors and styling
- Add new frontend actions
- Customize the CopilotKit sidebar appearance
📚 Documentation
- Microsoft Agent Framework – Learn more about Microsoft Agent Framework and its features
- CopilotKit Documentation – Explore CopilotKit’s capabilities
- Next.js Documentation – Learn about Next.js features and API
Contributing
Feel free to submit issues and enhancement requests! This starter is designed to be easily extensible.
License
This project is licensed under the MIT License – see the LICENSE file for details.
Troubleshooting
Agent Connection Issues
If you see "I'm having trouble connecting to my tools", make sure:
- The Microsoft Agent Framework agent is running on port 8000
- Your OpenAI/Azure credentials are set correctly
- Both servers started successfully
Python Dependencies
If you encounter Python import errors:
cd agent
uv sync
uv run src/main.py