Running Workers Locally

The Hatchet CLI provides the hatchet worker commands to run Hatchet workers locally for development and testing purposes.

Setting up a hatchet.yaml file

The hatchet worker commands rely on a hatchet.yaml configuration file to define the worker settings. You can create a hatchet.yaml file in your project directory which resembles the following (you will need to adjust the preCmds and runCmd fields to match your project’s setup):

dev:
  preCmds: ["poetry install"]
  runCmd: "poetry run python src/worker.py"
  files:
    - "**/*.py"
    - "!**/__pycache__/**"
    - "!**/.venv/**"
  reload: true

dev:
  preCmds: ["pnpm install"]
  runCmd: "pnpm start"
  files:
    - "**/*.ts"
    - "!**/node_modules/**"
  reload: true

dev:
  preCmds: ["go mod download"]
  runCmd: "go run ./cmd/worker"
  files:
    - "**/*.go"
  reload: true

Running a worker

Once you have a hatchet.yaml file set up, you can run a worker locally using the following command:

hatchet worker dev

To run a worker with a specific profile, you can run:

hatchet worker dev --profile <profile-name>

Disabling auto-reload

If you want to run the worker without auto-reloading on file changes, you can set the dev.reload field to false in your hatchet.yaml file:

dev:
  reload: false

Or you can pass the --no-reload flag when running the worker:

hatchet worker dev --no-reload

Overriding the run command

You can override the runCmd specified in the hatchet.yaml file by using the --run-cmd flag:

hatchet worker dev --run-cmd "npm run dev"