Files
dify/api
L1nSn0w 3bf92323b2 refactor(llm): measure first-token timeout via httpx read timeout
The thread-based FirstTokenWatchdog could never fire in production: the
plugin daemon withholds the SSE response headers until the model's first
token, so the whole time-to-first-token is spent inside httpx
Client.stream() waiting for headers -- before the watchdog is armed. It
only ever measured headers->first-frame (~0s) and was disarmed by the
first frame.

Replace the watchdog with httpx's per-request read timeout set to the
first-token budget. httpcore applies read to both the header wait and each
body read, and the daemon sends no heartbeat before the first token, so it
measures time-to-first-token directly. A pre-first-token ReadTimeout with
the gate enabled becomes FirstTokenTimeoutError; anything else (inter-token
stall, gate off, other transport errors) stays a normal transport error.

Deletes the entire watchdog subsystem (timer, lock, socket-abort,
content-detection); the ContextVar plumbing and producer side are unchanged.
2026-07-10 13:58:48 +08:00
..
2026-04-16 02:21:04 +00:00
2026-04-16 02:21:04 +00:00
2026-04-16 08:50:02 +00:00

Dify Backend API

Setup and Run

Important

In the v1.3.0 release, poetry has been replaced with uv as the package manager for Dify API backend service.

uv and pnpm are required to run the setup and development commands below.

The scripts resolve paths relative to their location, so you can run them from anywhere.

  1. Run setup (copies env files and installs dependencies).

    ./dev/setup
    
  2. Review api/.env, web/.env.local, and docker/middleware.env values (see the SECRET_KEY note below).

  3. Start middleware (PostgreSQL/Redis/Weaviate).

    ./dev/start-docker-compose
    
  4. Start backend (runs migrations first).

    ./dev/start-api
    
  5. Start Dify web service.

    ./dev/start-web
    

    ./dev/setup and ./dev/start-web install JavaScript dependencies through the repository root workspace, so you do not need a separate cd web && pnpm install step.

  6. Set up your application by visiting http://localhost:3000.

  7. Start the worker service (async and scheduler tasks, runs from api).

    ./dev/start-worker
    
  8. Optional: start Celery Beat (scheduled tasks).

    ./dev/start-beat
    

Environment notes

Important

When the frontend and backend run on different subdomains, set COOKIE_DOMAIN to the sites top-level domain (e.g., example.com). The frontend and backend must be under the same top-level domain in order to share authentication cookies.

  • Generate a SECRET_KEY in the .env file.

    bash for Linux

    sed -i "/^SECRET_KEY=/c\\SECRET_KEY=$(openssl rand -base64 42)" .env
    

    bash for Mac

    secret_key=$(openssl rand -base64 42)
    sed -i '' "/^SECRET_KEY=/c\\
    SECRET_KEY=${secret_key}" .env
    

Testing

  1. Install dependencies for both the backend and the test environment

    cd api
    uv sync --group dev
    
  2. Run the tests locally with mocked system environment variables in tool.pytest_env section in pyproject.toml, more can check Claude.md

    cd api
    uv run pytest                           # Run all tests
    uv run pytest tests/unit_tests/         # Unit tests only
    uv run pytest tests/integration_tests/  # Integration tests
    
    # Code quality
    ./dev/reformat               # Run all formatters and linters
    uv run ruff check --fix ./   # Fix linting issues
    uv run ruff format ./        # Format code
    uv run pyrefly check         # Type checking
    

Generate TS stub

uv run dev/generate_swagger_specs.py --output-dir openapi

use https://jsontotable.org/openapi-to-typescript to convert to typescript