Closes the cleanup gaps found in review (latent today; bites under load/crashes).
Sandbox containers (cm-sandbox / cm-runtime):
- label every sandbox `clawmates.sandbox={agent|browser}` at create
- SandboxDriver::list_managed(kind) (Docker label filter + K8s label selector)
- SandboxManager::reconcile_orphans(ttl) + spawn_reaper: removes engine
containers no live handle owns (ZERO = all)
- boot reconciliation (every pre-existing sandbox is an orphan from a dead
process) + periodic reaper (5m interval / 10m TTL)
- SIGTERM graceful drain: serve().with_graceful_shutdown → shutdown() both
managers so a redeploy can't leak; destroy errors now logged not swallowed
DB expiry/retention (cm-db cleanup.rs + cm-api cleanup_sweeper, hourly):
- expire auth_sessions + oauth_states past expires_at (security)
- prune sent outbox(7d), run_events(14d), routine_runs(30d), terminal
topology_runs(90d), consumed execution_grants(7d)
Compose: volume-init restart "no" → on-failure:5 (retry instead of wedging boot).
Co-Authored-By: Claude Opus 4.8 <[email protected]>
143 lines
4.5 KiB
YAML
143 lines
4.5 KiB
YAML
# Air-gapped single-node topology. The network segmentation IS the security
|
|
# model (spec §15):
|
|
# edge — host-published entry points only (frontend, server API)
|
|
# core — internal: server <-> postgres
|
|
# sandbox_net — internal, NO egress: agent sandboxes (joined in P2)
|
|
# secrets_net — internal: secret broker + server only (joined in P2)
|
|
# Images are preloaded from the signed offline bundle; nothing pulls at
|
|
# install time.
|
|
|
|
name: clawmates
|
|
|
|
networks:
|
|
edge: {}
|
|
core:
|
|
internal: true
|
|
sandbox_net:
|
|
internal: true
|
|
secrets_net:
|
|
internal: true
|
|
# Server <-> socket proxy only; the raw Docker socket never reaches the
|
|
# server container.
|
|
engine_net:
|
|
internal: true
|
|
|
|
volumes:
|
|
pgdata: {}
|
|
# Unix socket + master key shared ONLY between server and broker —
|
|
# the unix-socket equivalent of the K8s sidecar topology.
|
|
broker_run: {}
|
|
broker_key: {}
|
|
|
|
services:
|
|
postgres:
|
|
image: postgres:16-alpine
|
|
restart: unless-stopped
|
|
environment:
|
|
POSTGRES_DB: clawmates
|
|
POSTGRES_PASSWORD: ${POSTGRES_PASSWORD:?set in .env}
|
|
volumes:
|
|
- pgdata:/var/lib/postgresql/data
|
|
networks: [core]
|
|
healthcheck:
|
|
test: ["CMD-SHELL", "pg_isready -U postgres -d clawmates"]
|
|
interval: 5s
|
|
timeout: 3s
|
|
retries: 12
|
|
|
|
# Named volumes mount root-owned, but the broker runs as uid 10001 from
|
|
# a scratch image (no shell to chown itself). This one-shot prepares the
|
|
# socket + key volumes, then exits. `on-failure` so a transient chown error
|
|
# retries instead of wedging boot (broker/server depend on it completing).
|
|
volume-init:
|
|
image: busybox:1.36
|
|
command: ["sh", "-c", "chown -R 10001:10001 /run/clawmates /etc/clawmates-broker"]
|
|
user: "0:0"
|
|
volumes:
|
|
- broker_run:/run/clawmates
|
|
- broker_key:/etc/clawmates-broker
|
|
restart: on-failure:5
|
|
|
|
# The secret broker: separate process, separate image; credentials
|
|
# never leave it. Reachable only via the shared unix socket volume.
|
|
broker:
|
|
image: clawmates/broker:${CLAWMATES_VERSION:-latest}
|
|
build:
|
|
context: ../..
|
|
dockerfile: images/broker.Dockerfile
|
|
restart: unless-stopped
|
|
environment:
|
|
CLAWMATES_BROKER_SOCKET: /run/clawmates/broker.sock
|
|
CLAWMATES_BROKER_KEY_FILE: /etc/clawmates-broker/broker.key
|
|
CLAWMATES_DATABASE__URL: postgres://postgres:${POSTGRES_PASSWORD:?set in .env}@postgres:5432/clawmates
|
|
volumes:
|
|
- broker_run:/run/clawmates
|
|
- broker_key:/etc/clawmates-broker
|
|
networks: [core]
|
|
depends_on:
|
|
postgres:
|
|
condition: service_healthy
|
|
volume-init:
|
|
condition: service_completed_successfully
|
|
|
|
# Allow-listed Docker API (§15 blast-radius cap): the server can
|
|
# create/exec/stop/remove sandbox containers and NOTHING else — no
|
|
# image builds, no networks, no secrets, no volumes. Proven by
|
|
# crates/cm-sandbox/tests/socket_proxy.rs against this exact allowlist.
|
|
socket-proxy:
|
|
image: tecnativa/docker-socket-proxy:0.3
|
|
restart: unless-stopped
|
|
environment:
|
|
CONTAINERS: 1
|
|
POST: 1
|
|
EXEC: 1
|
|
DELETE: 1
|
|
VERSION: 1
|
|
volumes:
|
|
- /var/run/docker.sock:/var/run/docker.sock:ro
|
|
networks: [engine_net]
|
|
|
|
server:
|
|
image: clawmates/server:${CLAWMATES_VERSION:-latest}
|
|
build:
|
|
context: ../..
|
|
dockerfile: images/server.Dockerfile
|
|
restart: unless-stopped
|
|
# Operator knobs (bootstrap owner, LLM provider/key overrides, OTLP) come
|
|
# from .env — only the keys you actually set are injected, so unset
|
|
# options stay absent rather than overriding clawmates.toml with "".
|
|
env_file:
|
|
- path: .env
|
|
required: false
|
|
environment:
|
|
CLAWMATES_CONFIG: /etc/clawmates/clawmates.toml
|
|
CLAWMATES_DATABASE__URL: postgres://postgres:${POSTGRES_PASSWORD:?set in .env}@postgres:5432/clawmates
|
|
DOCKER_HOST: tcp://socket-proxy:2375
|
|
volumes:
|
|
- ./clawmates.toml:/etc/clawmates/clawmates.toml:ro
|
|
- broker_run:/run/clawmates
|
|
networks: [edge, core, engine_net]
|
|
ports:
|
|
- "8080:8080"
|
|
depends_on:
|
|
postgres:
|
|
condition: service_healthy
|
|
|
|
frontend:
|
|
image: clawmates/frontend:${CLAWMATES_VERSION:-latest}
|
|
build:
|
|
context: ../..
|
|
dockerfile: images/frontend.Dockerfile
|
|
restart: unless-stopped
|
|
# AUTH_MODE + CLERK_* (when running Clerk) come from .env; see docs/clerk.md.
|
|
env_file:
|
|
- path: .env
|
|
required: false
|
|
environment:
|
|
API_ORIGIN: http://server:8080
|
|
networks: [edge]
|
|
ports:
|
|
- "3000:3000"
|
|
depends_on:
|
|
- server
|