Files

T

Benjamin Taylor e1f88ebc12 refactor(examples): split the Channel out of the host, drop its HTTP server

Addresses review feedback that channel-host.mts is doing too much.

Two changes, both scoped to the starters:

1. Channel construction moves to a new `channels.mts` beside `agent.ts` —
   name resolution, `createChannel`, and the `onMessage` handler. That is
   also the file to edit to customise a Channel (commands, reactions,
   onMention), which previously meant editing the host.

   The per-framework agent import moves with it, so `channel-host.mts` is now
   byte-identical in all 15 starters rather than 13 + 2.

2. The host no longer stands up an HTTP server. Its comment claimed the
   server was what "keeps the lifecycle-owning process alive"; that is false.
   An open undici WebSocket holds the event loop on its own — verified with a
   standalone repro where a process with no HTTP server and no timers of its
   own stayed up indefinitely on a single WebSocket connection. The server was
   therefore serving a second, uncalled copy of the runtime API on port 8300
   for no reason.

   With the server gone, `createCopilotNodeListener` was the wrong factory —
   it builds a request listener purely for its activation side effect. The
   host now uses `createCopilotRuntimeHandler` + `ready()`, which is the
   documented long-running-host pattern (see fetch-handler.ts). This also
   drops `node:http`, `basePath`, and the CHANNEL_PORT env var.

Behaviour is unchanged: same Channel, same agent, same status reporting, and
the same non-zero exit on activation failure.

Verified: 14/14 starters with a `typecheck:channel` script pass; mastra has no
such script by design (166dc94691) and its pre-existing Mastra `Memory` type
error is byte-identical before and after. `npm run channel` exercised on both
failure paths — missing channels.json, and missing INTELLIGENCE_API_KEY with a
name supplied — confirming the new `./channels.mjs` specifier resolves under
tsx as well as tsc. `parity:check` output identical to the pre-change baseline.

Refs #6315

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>

2026-08-02 12:41:46 -05:00

6.1 KiB

Raw Permalink Blame History

CopilotKit <> strands Starter

This is a starter template for building AI agents using strands and CopilotKit. It provides a modern Next.js application with an integrated investment analyst agent that can research stocks, analyze market data, and provide investment insights.

Prerequisites

Node.js 20+
Python 3.12+
uv (Python package manager)
OpenAI API Key (for the strands agent)
Any of the following package managers:
- npm (default)
- pnpm
- yarn
- bun

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 install

Note: Installing the package dependencies will also install the agent's python dependencies via the install:agent script.

Set up your OpenAI API key:

export OPENAI_API_KEY="your-openai-api-key-here"

or create a .env file.

echo "OPENAI_API_KEY=your-openai-api-key-here" > .env

Start the development server:

# Using npm (default)
npm run dev

# Using pnpm
pnpm dev

# Using yarn
yarn dev

# Using bun
bun run dev

This will start both the UI and agent servers concurrently.

Running a Channel

channel-host.mts mounts the same agent as an Intelligence Channel (Slack, Teams). It requires INTELLIGENCE_API_KEY and a declared Channel in .copilotkit/channels.json — set both up with copilotkit init or copilotkit channels add, which write that file and the credentials your .env needs, then:

npm run channel

The host reads which Channel to hold from .copilotkit/channels.json. If a project declares more than one, set INTELLIGENCE_CHANNEL_NAME to pick one.

The host holds no provider credentials and exposes no provider endpoint — Intelligence owns the provider edge — so the same file works for every provider.

The Channel itself is declared in channels.mts — that is where to add commands, reactions, or an onMention handler. channel-host.mts only owns the process lifetime, and is byte-identical in every starter.

Once startup finishes, the log reports the truth per Channel:

Channel "<name>" is online. — the session is up and can send.
Channel "<name>" is declared but no provider is attached yet. — a normal waiting state, not a failure. Run copilotkit channels status to see what setup remains.

Neither message proves the provider app is installed, reachable, or that anyone can message it — verify that separately (invite the bot, then message it) before treating the Channel as working.

Available Scripts

The following scripts can also be run using your preferred package manager:

dev - Starts both UI and agent servers in development mode
dev:ui - Starts only the Next.js UI server
dev:agent - Starts only the strands agent server
build - Builds the Next.js application for production
start - Starts the production server
install:agent - Installs Python dependencies for the agent
channel - Holds an Intelligence Channel open (see "Running a Channel" above)
typecheck:channel - Type-checks the channel host on its own tsconfig.channel.json

📚 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

Otherwise, check out the documentation relevant to your task:

Strands Documentation - Learn more about Strands 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 strands agent is running on port 8000
Your OpenAI API key is set correctly
Both servers started successfully

Python Dependencies

If you encounter Python import errors:

cd agent
uv sync

CopilotKit Intelligence & Threads (Optional)

CopilotKit Intelligence adds durable thread history and cross-session memory to your agent. It requires a COPILOTKIT_LICENSE_TOKEN and a running local Intelligence stack (Docker Desktop + a local Intelligence repo checkout).

Prerequisites

Docker Desktop running
A COPILOTKIT_LICENSE_TOKEN (obtain from CopilotKit Cloud)
The Intelligence repo cloned locally. The docker-compose.intelligence.yml defaults to a sibling directory at ../../../Intelligence relative to this starter; override with the INTELLIGENCE_REPO env var if your checkout is elsewhere.

Start the intelligence stack

# From inside this starter directory:
docker compose -f docker-compose.intelligence.yml up -d --wait

First run builds the intelligence image from source (may take several minutes).

Verify the stack is healthy

docker compose -f docker-compose.intelligence.yml ps

All three services (postgres, redis, intelligence) should show healthy.

Set environment variables

Add the following to your .env file:

COPILOTKIT_LICENSE_TOKEN=your-license-token-here
INTELLIGENCE_API_URL=http://localhost:4207
INTELLIGENCE_GATEWAY_WS_URL=ws://localhost:4407

Then start the dev server as usual (npm run dev). Thread history and memory features are activated automatically when COPILOTKIT_LICENSE_TOKEN is set.

Stop / reset

# Stop without removing data:
docker compose -f docker-compose.intelligence.yml down

# Full reset (removes postgres + redis volumes):
docker compose -f docker-compose.intelligence.yml down -v

6.1 KiB Raw Permalink Blame History

CopilotKit <> strands Starter

Prerequisites

Getting Started

Running a Channel

Available Scripts

📚 Documentation

Contributing

License

Troubleshooting

Agent Connection Issues

Python Dependencies

CopilotKit Intelligence & Threads (Optional)

Prerequisites

Start the intelligence stack

Verify the stack is healthy

Set environment variables

Stop / reset

6.1 KiB

Raw Permalink Blame History