suna/backend
sharath 8255c507a5
fix(backend): enhance trace logging levels for error handling and execution status
2025-05-22 08:36:58 +00:00
..
.github/workflows fe reference wip 2025-03-29 23:48:57 -07:00
agent fix(backend): enhance trace logging levels for error handling and execution status 2025-05-22 08:36:58 +00:00
agentpress fix(backend): enhance trace logging levels for error handling and execution status 2025-05-22 08:36:58 +00:00
sandbox wip 2025-05-19 03:39:02 +02:00
services feat(backend): langfuse traces 2025-05-21 00:39:28 +00:00
supabase fix: policy and share page api error 2025-05-04 15:49:26 +02:00
utils feat(backend): langfuse traces 2025-05-21 00:39:28 +00:00
.env.example feat(backend): langfuse traces 2025-05-21 00:39:28 +00:00
.gitignore delete user sandboxes script 2025-05-02 15:50:33 +02:00
Dockerfile unlimited requests per worker, deactivate restore_running_agent_runs 2025-05-14 00:15:46 +02:00
MANIFEST.in fe reference wip 2025-03-29 23:48:57 -07:00
README.md :Merge branch 'main' into pr/ravisojitra/301 2025-05-17 21:11:53 +00:00
api.py unlimited requests per worker, deactivate restore_running_agent_runs 2025-05-14 00:15:46 +02:00
docker-compose.yml Merge pull request #373 from kortix-ai/fix/sandbox-browser 2025-05-19 04:24:46 +02:00
fly.production.toml logger, docker, wip 2025-04-24 23:04:59 +01:00
fly.staging.toml logger, docker, wip 2025-04-24 23:04:59 +01:00
poetry.lock feat(backend): langfuse traces 2025-05-21 00:39:28 +00:00
pyproject.toml feat(backend): langfuse traces 2025-05-21 00:39:28 +00:00
requirements.txt feat(backend): langfuse traces 2025-05-21 00:39:28 +00:00
run_agent_background.py fix(backend): enhance trace logging levels for error handling and execution status 2025-05-22 08:36:58 +00:00

README.md

Suna Backend

Running the backend

Within the backend directory, run the following command to stop and start the backend:

docker compose down && docker compose up --build

Running Individual Services

You can run individual services from the docker-compose file. This is particularly useful during development:

Running only Redis and RabbitMQ

docker compose up redis rabbitmq

Running only the API and Worker

docker compose up api worker

Development Setup

For local development, you might only need to run Redis and RabbitMQ, while working on the API locally. This is useful when:

  • You're making changes to the API code and want to test them directly
  • You want to avoid rebuilding the API container on every change
  • You're running the API service directly on your machine

To run just Redis and RabbitMQ for development:```bash docker compose up redis rabbitmq

Then you can run your API service locally with the following commands

# On one terminal
cd backend
poetry run python3.11 api.py

# On another terminal
cd frontend
poetry run python3.11 -m dramatiq run_agent_background

Environment Configuration

When running services individually, make sure to:

  1. Check your .env file and adjust any necessary environment variables
  2. Ensure Redis connection settings match your local setup (default: localhost:6379)
  3. Ensure RabbitMQ connection settings match your local setup (default: localhost:5672)
  4. Update any service-specific environment variables if needed

Important: Redis Host Configuration

When running the API locally with Redis in Docker, you need to set the correct Redis host in your .env file:

  • For Docker-to-Docker communication (when running both services in Docker): use REDIS_HOST=redis
  • For local-to-Docker communication (when running API locally): use REDIS_HOST=localhost

Important: RabbitMQ Host Configuration

When running the API locally with Redis in Docker, you need to set the correct RabbitMQ host in your .env file:

  • For Docker-to-Docker communication (when running both services in Docker): use RABBITMQ_HOST=rabbitmq
  • For local-to-Docker communication (when running API locally): use RABBITMQ_HOST=localhost

Example .env configuration for local development:

REDIS_HOST=localhost (instead of 'redis')
REDIS_PORT=6379
REDIS_PASSWORD=

RABBITMQ_HOST=localhost (instead of 'rabbitmq')
RABBITMQ_PORT=5672