Development Configuration

LangBot is divided into frontend and backend. The frontend is developed using Vite + React Router + shadcn, and the backend is developed using Quart (an asynchronous version of Flask).

Backend

The code is located in the pkg directory and is started by the main.py file in the root directory. Install dependencies, we use uv to manage dependencies.

pip install uv
uv sync --dev

Start the backend

uv run main.py

At this point, the configuration file will be automatically generated in the data/config.yaml file.

Frontend

The code is located in the web directory and requires Node.js and pnpm. Copy .env.example to .env and fill in the values.

Usage in Linux and other environments

cp .env.example .env

Usage in Windows environments

copy .env.example .env

Install dependencies and start the frontend

pnpm install
pnpm dev

# If pnpm is not installed, you can also use npm to solve dependencies and start
npm install
npm run dev

Then according to the output information, visit http://127.0.0.1:3000 to view the standalone frontend page.

In production environments, the frontend will be precompiled into static files and provided by the backend, and the frontend will automatically access the backend address on the same domain.

Code Formatting

The repository contains lint and format check workflows, and your code will be automatically checked when you push it. Please configure pre-commit to check your code locally before submitting.

uv run pre-commit install

API Documentation

We will write API documentation in APIFox before developing each interface. Please refer to API Documentation(Chinese).

Database Migrations

LangBot uses Alembic to manage database migrations, supporting both SQLite and PostgreSQL seamlessly without database-specific branching.

Migration File Location

src/langbot/pkg/persistence/alembic/versions/

Creating a New Migration

The recommended way is to use autogenerate, which compares ORM models against the database schema and generates a migration script:

# Run from the project root (requires data/config.yaml)
uv run python -m langbot.pkg.persistence.alembic_runner autogenerate "describe your changes"

The generated file will appear in src/langbot/pkg/persistence/alembic/versions/. Review and edit the generated script to confirm the changes are correct before committing.

Autogenerate can automatically detect column additions/removals, table changes, type changes, etc. However, for data migrations (e.g., modifying JSON field content), you need to manually add code to the generated script.

You can also create migration files manually, following the naming convention NNNN_description.py:

"""Describe your migration

Revision ID: 0003_add_bot_description
Revises: 0002_sample
Create Date: 2026-04-08
"""
from alembic import op
import sqlalchemy as sa

revision = '0003_add_bot_description'
down_revision = '0002_sample'  # Points to the previous migration's revision
branch_labels = None
depends_on = None


def upgrade() -> None:
    # Schema change (works on both SQLite and PostgreSQL)
    op.add_column('bots', sa.Column('description', sa.String(512), server_default=''))


def downgrade() -> None:
    op.drop_column('bots', 'description')

Migration Patterns

Schema Changes (add/drop columns, create tables)

def upgrade() -> None:
    # Add a column
    op.add_column('table_name', sa.Column('new_col', sa.String(255), server_default=''))
    
    # Create a new table
    op.create_table(
        'new_table',
        sa.Column('id', sa.Integer, primary_key=True, autoincrement=True),
        sa.Column('name', sa.String(255), nullable=False),
    )

env.py sets render_as_batch=True, which makes Alembic automatically handle SQLite’s ALTER TABLE limitations (via temporary table rebuild). No need to branch on database type.

Data Migrations (read and modify data)

import json

def upgrade() -> None:
    conn = op.get_bind()
    rows = conn.execute(sa.text("SELECT uuid, config FROM pipelines")).fetchall()
    for row in rows:
        config = json.loads(row[1]) if isinstance(row[1], str) else row[1]
        config.setdefault('ai', {})['new_key'] = 'default_value'
        conn.execute(
            sa.text("UPDATE pipelines SET config = :cfg WHERE uuid = :uuid"),
            {"cfg": json.dumps(config), "uuid": row[0]}
        )

How It Works

Migrations run automatically when LangBot starts — no manual commands needed:

On first startup, the baseline version is automatically stamped (marking the existing database)
On subsequent startups, all pending migrations are applied (alembic upgrade head)

CI Testing

The repository includes a test-migrations.yml workflow that automatically tests migration scripts on both SQLite and PostgreSQL when persistence/ related files change.

CLI Tool

# Autogenerate migration (compare ORM models against DB)
uv run python -m langbot.pkg.persistence.alembic_runner autogenerate "description"

# Upgrade database
uv run python -m langbot.pkg.persistence.alembic_runner upgrade

# Show current revision
uv run python -m langbot.pkg.persistence.alembic_runner current

# Stamp revision (without running migrations)
uv run python -m langbot.pkg.persistence.alembic_runner stamp head

Plugin Development

Plugin SDK API

Core Development

Development Configuration

Backend

Frontend

Code Formatting

API Documentation

Database Migrations

Migration File Location

Creating a New Migration

Migration Patterns

How It Works

CI Testing

CLI Tool

​Backend

​Frontend

​Code Formatting

​API Documentation

​Database Migrations

​Migration File Location

​Creating a New Migration

​Migration Patterns

​How It Works

​CI Testing

​CLI Tool

Backend

Frontend

Code Formatting

API Documentation

Database Migrations

Migration File Location

Creating a New Migration

Migration Patterns

How It Works

CI Testing

CLI Tool