mirror of
https://github.com/tiennm99/DocsGPT.git
synced 2026-10-05 00:13:01 +00:00
Alex
3b795dbb83
Introduce a pluggable CodeSandbox abstraction with a SandboxManager and a Jupyter Kernel Gateway backend: the app is a client of a single always-on runner that executes code in stateful in-process kernels (no child-container spawning, no docker socket). Sessions bind to a conversation or workflow run with an agent-selectable TTL clamped by a global cap; execution enforces a wall-clock deadline with interrupt-on-timeout and capped output, and file transfer is workspace-contained with size and integrity checks. Adds a docsgpt-sandbox docker-compose service (resource-capped, read-only, internal network) plus settings, with a real local-gateway integration test.
119 lines
3.5 KiB
YAML
119 lines
3.5 KiB
YAML
name: docsgpt-oss
|
|
services:
|
|
frontend:
|
|
build: ../frontend
|
|
volumes:
|
|
- ../frontend/src:/app/src
|
|
environment:
|
|
- VITE_API_HOST=http://localhost:7091
|
|
- VITE_API_STREAMING=$VITE_API_STREAMING
|
|
- VITE_GOOGLE_CLIENT_ID=$VITE_GOOGLE_CLIENT_ID
|
|
ports:
|
|
- "5173:5173"
|
|
depends_on:
|
|
- backend
|
|
|
|
backend:
|
|
user: root
|
|
build: ../application
|
|
env_file:
|
|
- ../.env
|
|
environment:
|
|
# Override URLs to use docker service names
|
|
- CELERY_BROKER_URL=redis://redis:6379/0
|
|
- CELERY_RESULT_BACKEND=redis://redis:6379/1
|
|
- CACHE_REDIS_URL=redis://redis:6379/2
|
|
- POSTGRES_URI=postgresql://docsgpt:docsgpt@postgres:5432/docsgpt
|
|
# Code-execution runner reached over HTTP + WebSocket (no docker socket).
|
|
- SANDBOX_GATEWAY_URL=http://docsgpt-sandbox:8888
|
|
ports:
|
|
- "7091:7091"
|
|
volumes:
|
|
- ../application/indexes:/app/indexes
|
|
- ../application/inputs:/app/inputs
|
|
- ../application/vectors:/app/vectors
|
|
depends_on:
|
|
redis:
|
|
condition: service_started
|
|
postgres:
|
|
condition: service_healthy
|
|
|
|
worker:
|
|
user: root
|
|
build: ../application
|
|
command: celery -A application.app.celery worker -l INFO -B
|
|
env_file:
|
|
- ../.env
|
|
environment:
|
|
# Override URLs to use docker service names
|
|
- CELERY_BROKER_URL=redis://redis:6379/0
|
|
- CELERY_RESULT_BACKEND=redis://redis:6379/1
|
|
- API_URL=http://backend:7091
|
|
- CACHE_REDIS_URL=redis://redis:6379/2
|
|
- POSTGRES_URI=postgresql://docsgpt:docsgpt@postgres:5432/docsgpt
|
|
- SANDBOX_GATEWAY_URL=http://docsgpt-sandbox:8888
|
|
volumes:
|
|
- ../application/indexes:/app/indexes
|
|
- ../application/inputs:/app/inputs
|
|
- ../application/vectors:/app/vectors
|
|
depends_on:
|
|
redis:
|
|
condition: service_started
|
|
postgres:
|
|
condition: service_healthy
|
|
|
|
# Always-on code-execution runner (Jupyter Kernel Gateway). Sessions are
|
|
# in-process kernels, never child containers; the Docker socket is NOT
|
|
# mounted. On an internal-only network — no host port is published, so the
|
|
# runner is reachable only from backend/worker, not from the host/internet.
|
|
# Egress/SSRF blocks, the gVisor `runsc` runtime, and seccomp profile come in
|
|
# the hardening slice.
|
|
docsgpt-sandbox:
|
|
build: ./sandbox
|
|
mem_limit: ${SANDBOX_MEMORY:-1g}
|
|
cpus: ${SANDBOX_CPUS:-1.0}
|
|
pids_limit: 256
|
|
read_only: true
|
|
environment:
|
|
# Keep Jupyter's runtime/connection files on the writable tmpfs.
|
|
- JUPYTER_RUNTIME_DIR=/tmp/jupyter-runtime
|
|
- JUPYTER_DATA_DIR=/tmp/jupyter-data
|
|
tmpfs:
|
|
# Per-session workspaces (/tmp/docsgpt-sandbox/<session_id>) and Jupyter
|
|
# runtime files live on tmpfs; the root FS is read-only everywhere else.
|
|
- /tmp
|
|
networks:
|
|
- sandbox-net
|
|
- default
|
|
|
|
redis:
|
|
image: redis:6-alpine
|
|
ports:
|
|
- 6379:6379
|
|
|
|
postgres:
|
|
image: postgres:16-alpine
|
|
environment:
|
|
- POSTGRES_USER=docsgpt
|
|
- POSTGRES_PASSWORD=docsgpt
|
|
- POSTGRES_DB=docsgpt
|
|
ports:
|
|
- "5432:5432"
|
|
volumes:
|
|
- postgres_data:/var/lib/postgresql/data
|
|
healthcheck:
|
|
test: ["CMD-SHELL", "pg_isready -U docsgpt -d docsgpt"]
|
|
interval: 5s
|
|
timeout: 5s
|
|
retries: 10
|
|
|
|
networks:
|
|
# Internal-only network for the sandbox runner (no external egress route via
|
|
# this network; the runner still reaches the internet via the default bridge).
|
|
sandbox-net:
|
|
internal: true
|
|
|
|
volumes:
|
|
postgres_data:
|
|
|