mirror of
https://github.com/langbot-app/LangBot.git
synced 2026-10-28 19:35:27 +08:00
Martin
12debe2747
Persist the v4 plugin runtime state so recreating the runtime container no longer discards installed plugins' artifacts, dependency environments and installation-private data, and stop a transient Runner registry miss during steering from dropping the message. - docker-compose: bind-mount ./data/plugin-runtime for the plugin runtime alongside ./data/plugins. - kubernetes: add the langbot-plugin-runtime-state claim (5Gi) mounted at /app/data/plugin-runtime, kept separate from the plugin data claim so runtime state does not land inside the plugin directory. - chat handler: treat RunnerNotFoundError while claiming steering as "steering unavailable" and continue with a normal run; every other error keeps propagating. The runner error imports move to module scope, which the new early reference requires. - tests: cover the steering fallback, the claimed-steering interrupt, and the lasting-gap path that still reports runner-not-found. The steering fallback buys one extra uncached registry lookup while a runtime reconnects; it does not recover a gap that outlasts the message.
146 lines
7.7 KiB
YAML
146 lines
7.7 KiB
YAML
# Docker Compose configuration for LangBot
|
|
# For Kubernetes deployment, see kubernetes.yaml and the deployment guide at https://langbot.app/docs
|
|
version: "3"
|
|
|
|
services:
|
|
|
|
langbot_plugin_runtime:
|
|
image: rockchin/langbot:latest
|
|
container_name: langbot_plugin_runtime
|
|
volumes:
|
|
- ./data/plugins:/app/data/plugins
|
|
# Persist the v4 plugin artifact cache, dependency environments, and
|
|
# per-installation data. Without this, recreating the container throws
|
|
# away every installed plugin's environment and private data while
|
|
# data/plugins survives.
|
|
- ./data/plugin-runtime:/app/data/plugin-runtime
|
|
ports:
|
|
- 5401:5401
|
|
restart: on-failure
|
|
environment:
|
|
- TZ=Asia/Shanghai
|
|
# Optional. Leave unset on both OSS services, or set the same value on
|
|
# both to protect the control WebSocket. Generate with: openssl rand -hex 32
|
|
- LANGBOT_PLUGIN_RUNTIME_CONTROL_TOKEN=${LANGBOT_PLUGIN_RUNTIME_CONTROL_TOKEN:-}
|
|
# Process-wide admission for every asyncio.to_thread() call.
|
|
- LANGBOT_BLOCKING_EXECUTOR_MAX_WORKERS=${LANGBOT_BLOCKING_EXECUTOR_MAX_WORKERS:-8}
|
|
- LANGBOT_BLOCKING_EXECUTOR_MAX_PENDING=${LANGBOT_BLOCKING_EXECUTOR_MAX_PENDING:-128}
|
|
- LANGBOT_BLOCKING_EXECUTOR_MAX_INFLIGHT_PER_SCOPE=${LANGBOT_BLOCKING_EXECUTOR_MAX_INFLIGHT_PER_SCOPE:-4}
|
|
command: ["uv", "run", "--no-sync", "-m", "langbot_plugin.cli.__init__", "rt"]
|
|
# The control WebSocket port also serves an unauthenticated GET /healthz
|
|
# (see langbot_plugin runtime/io/controllers/ws/server.py). curl is removed
|
|
# from the image, so probe with the always-present python.
|
|
healthcheck:
|
|
test: ["CMD", "python", "-c", "import urllib.request,sys; sys.exit(0 if urllib.request.urlopen('http://127.0.0.1:5400/healthz', timeout=3).getcode()==200 else 1)"]
|
|
interval: 30s
|
|
timeout: 5s
|
|
retries: 3
|
|
start_period: 30s
|
|
networks:
|
|
- langbot_network
|
|
|
|
# The Box sandbox runtime is optional. It is only started when you run
|
|
# ``docker compose --profile box up`` (or ``docker compose --profile all
|
|
# up``). With Box off, LangBot keeps skill management, activation, and
|
|
# read-only resources available but disables execution tools and stdio MCP —
|
|
# set ``box.enabled: false`` in ``data/config.yaml`` (or
|
|
# ``BOX__ENABLED=false`` in the langbot service env below) to match.
|
|
langbot_box:
|
|
image: rockchin/langbot:latest
|
|
container_name: langbot_box
|
|
profiles: ["box", "all"]
|
|
volumes:
|
|
# Keep the source and target path identical because langbot_box uses the
|
|
# host Docker socket to create sandbox containers. Override
|
|
# LANGBOT_BOX_ROOT with an absolute path if you do not want the default.
|
|
- ${LANGBOT_BOX_ROOT:-${PWD}/data/box}:${LANGBOT_BOX_ROOT:-${PWD}/data/box}
|
|
# Mount container runtime socket for Box sandbox backend.
|
|
# Uncomment the one that matches your container runtime:
|
|
# - /var/run/podman/podman.sock:/var/run/podman/podman.sock # Podman
|
|
- /var/run/docker.sock:/var/run/docker.sock # Docker
|
|
restart: on-failure
|
|
environment:
|
|
- TZ=Asia/Shanghai
|
|
# Optional shared control-plane secret used to authenticate both the RPC
|
|
# socket and managed-process relay. Leave unset on both OSS services, or
|
|
# generate one with ``openssl rand -hex 32`` and set the same value on
|
|
# both ends. Strongly recommended when the deployment is Internet-accessible.
|
|
- LANGBOT_BOX_CONTROL_TOKEN=${LANGBOT_BOX_CONTROL_TOKEN:-}
|
|
# Box has its own process-wide blocking-work budget.
|
|
- LANGBOT_BLOCKING_EXECUTOR_MAX_WORKERS=${LANGBOT_BLOCKING_EXECUTOR_MAX_WORKERS:-8}
|
|
- LANGBOT_BLOCKING_EXECUTOR_MAX_PENDING=${LANGBOT_BLOCKING_EXECUTOR_MAX_PENDING:-128}
|
|
- LANGBOT_BLOCKING_EXECUTOR_MAX_INFLIGHT_PER_SCOPE=${LANGBOT_BLOCKING_EXECUTOR_MAX_INFLIGHT_PER_SCOPE:-4}
|
|
# The Box runtime does NOT read box.local.* from config.yaml or env; it
|
|
# receives its functional configuration from LangBot via the INIT RPC
|
|
# action. Do not add BOX__* here because those would be ignored.
|
|
# Launched through the same CLI entry point as the plugin runtime
|
|
# (`langbot_plugin.cli.__init__ <subcommand>`). WebSocket is the default
|
|
# control transport — mirrors `rt`, which also runs with no flag. Pass
|
|
# `-s` / `--stdio-control` only for the stdio mode LangBot uses outside
|
|
# containers.
|
|
command: ["uv", "run", "--no-sync", "-m", "langbot_plugin.cli.__init__", "box"]
|
|
# Box serves GET /healthz (liveness) and GET /readyz (readiness, 503 until
|
|
# the configured backend and isolation guarantees are ready) on the control
|
|
# port (default 5410). Use /readyz so the container is only reported healthy
|
|
# once it can actually accept sandbox work.
|
|
healthcheck:
|
|
test: ["CMD", "python", "-c", "import urllib.request,sys; sys.exit(0 if urllib.request.urlopen('http://127.0.0.1:5410/readyz', timeout=3).getcode()==200 else 1)"]
|
|
interval: 30s
|
|
timeout: 5s
|
|
retries: 3
|
|
start_period: 20s
|
|
networks:
|
|
- langbot_network
|
|
|
|
langbot:
|
|
image: rockchin/langbot:latest
|
|
container_name: langbot
|
|
volumes:
|
|
- ./data:/app/data
|
|
# Core owns the SkillRepository even when the Box profile is disabled.
|
|
# Keep this path identical to langbot_box so optional execution can
|
|
# consume the same Workspace-scoped package revisions.
|
|
- ${LANGBOT_BOX_ROOT:-${PWD}/data/box}:${LANGBOT_BOX_ROOT:-${PWD}/data/box}
|
|
restart: on-failure
|
|
environment:
|
|
- TZ=Asia/Shanghai
|
|
# Optional. Leave unset on both OSS services, or match plugin Runtime.
|
|
- LANGBOT_PLUGIN_RUNTIME_CONTROL_TOKEN=${LANGBOT_PLUGIN_RUNTIME_CONTROL_TOKEN:-}
|
|
# When set, this must match langbot_box. If both ends leave it unset,
|
|
# OSS permits the connection without token authentication. The token is
|
|
# sent only in WebSocket handshake headers, never in URLs or payloads.
|
|
- LANGBOT_BOX_CONTROL_TOKEN=${LANGBOT_BOX_CONTROL_TOKEN:-}
|
|
# Core process-wide blocking-work admission. These are native config
|
|
# overrides and are persisted with the effective data/config.yaml.
|
|
- SYSTEM__BLOCKING_EXECUTOR__MAX_WORKERS=${LANGBOT_BLOCKING_EXECUTOR_MAX_WORKERS:-8}
|
|
- SYSTEM__BLOCKING_EXECUTOR__MAX_PENDING=${LANGBOT_BLOCKING_EXECUTOR_MAX_PENDING:-128}
|
|
- SYSTEM__BLOCKING_EXECUTOR__MAX_INFLIGHT_PER_SCOPE=${LANGBOT_BLOCKING_EXECUTOR_MAX_INFLIGHT_PER_SCOPE:-4}
|
|
# Unified env-override convention: SECTION__SUBSECTION__KEY overrides the
|
|
# matching config.yaml field (see LoadConfigStage). These map onto
|
|
# box.* and are forwarded to the Box runtime via INIT RPC.
|
|
- BOX__LOCAL__HOST_ROOT=${LANGBOT_BOX_ROOT:-${PWD}/data/box}
|
|
- BOX__LOCAL__DEFAULT_WORKSPACE=default
|
|
# TODO(next-major): default LANGBOT_SKILLS_ROOT to ${PWD}/data/skills
|
|
# after the historical Box storage path no longer needs zero-copy upgrades.
|
|
- SKILLS__ROOT=${LANGBOT_SKILLS_ROOT:-${LANGBOT_BOX_ROOT:-${PWD}/data/box}/skills}
|
|
- BOX__LOCAL__ALLOWED_MOUNT_ROOTS=${LANGBOT_BOX_ROOT:-${PWD}/data/box}
|
|
- BOX__DOCKER__CPU_LIMIT_ENABLED=${LANGBOT_BOX_DOCKER_CPU_LIMIT_ENABLED:-true}
|
|
ports:
|
|
- 5300:5300 # For web ui and webhook callback
|
|
- 2280-2285:2280-2285 # For platform reverse connection
|
|
# The core Quart app exposes an unauthenticated GET /healthz on api.port
|
|
# (see langbot/pkg/api/http/controller/main.py). curl is removed from the
|
|
# image, so probe with the always-present python.
|
|
healthcheck:
|
|
test: ["CMD", "python", "-c", "import urllib.request,sys; sys.exit(0 if urllib.request.urlopen('http://127.0.0.1:5300/healthz', timeout=3).getcode()==200 else 1)"]
|
|
interval: 30s
|
|
timeout: 5s
|
|
retries: 3
|
|
start_period: 60s
|
|
networks:
|
|
- langbot_network
|
|
|
|
networks:
|
|
langbot_network:
|
|
driver: bridge
|