Files
roboco/docker-compose.registry.yml
Renn F 95e7d5df7c fix(kimi): cap concurrent Kimi agents to protect the shared auth chain
Every Kimi container redeems the same rotating refresh-token chain;
Moonshot rotates with a short reuse grace, so two containers refreshing
near-simultaneously fork the chain and a later stale redemption revokes
the whole family - fleet-wide re-login (observed twice in production,
each after paired spawns). With one consumer at a time refreshes are
strictly sequential and the chain stays coherent, so the spawn gate now
skips-and-retries Kimi spawns past ROBOCO_KIMI_MAX_CONCURRENT (default
1), sharing the provider-parked bail path. The compose files also gain
the four Kimi tunables their environment blocks silently dropped -
documented .env overrides never reached the orchestrator container.
2026-07-29 06:14:22 +02:00

611 lines
33 KiB
YAML

# ============================================================================
# RoboCo — pre-built (registry) deployment
# ============================================================================
# This is the "pull and run" compose for USERS: it runs the images the release
# workflow publishes (GHCR + Docker Hub) instead of building from source, so a
# host needs neither the repo's build context nor a build toolchain.
#
# 1. Copy `.env.example` to `.env` and fill in the required secrets.
# 2. docker compose -f docker-compose.registry.yml pull
# 3. docker compose -f docker-compose.registry.yml up -d
#
# Pick the registry + version with two env vars (defaults shown):
# ROBOCO_REGISTRY=ghcr.io/rennf93 # or docker.io/renzof93
# ROBOCO_VERSION=latest # or a pinned release, e.g. 0.5.0
#
# The orchestrator spawns agent containers itself; ROBOCO_AGENT_IMAGE_REGISTRY
# + ROBOCO_AGENT_IMAGE_TAG below tell it to spawn the SAME pre-built agent
# images (it pulls any it doesn't already have). The one-shot agent-*-image
# services exist only so `docker compose pull` fetches every agent image up
# front; they pull then exit.
#
# NOTE: this file is the registry counterpart of docker-compose.yml — when you
# add or change a service there, mirror it here. The infra services
# (postgres/redis/ollama/nginx) are byte-identical to the build compose.
#
# Declared contract — intended deltas from docker-compose.yml (check drift
# against THIS list, not against the build compose directly):
# - Image source: every roboco-built service pulls `image:` from
# ROBOCO_REGISTRY/ROBOCO_VERSION instead of `build:`-ing from source.
# - Agent image pre-pull one-shots + ROBOCO_AGENT_IMAGE_REGISTRY/_TAG exist
# only here — the build compose builds agent images on demand instead.
# - Feature-flag posture: every default-OFF subsystem is carried here at
# its OFF/config default (never omitted — an omitted var can't be armed
# via .env without hand-editing this file) so the published default
# stays conservative; the build compose arms most of them ON for the
# personal NAS deploy. ROBOCO_ROUTING_STRICT and the fastapi-guard trio
# (ROBOCO_GUARD_ENABLED/_PASSIVE_MODE/_FAIL_SECURE) are the exception:
# ROUTING_STRICT is still mid-calibration, and guard is now ACTIVE
# enforcement on the personal deploy (passive calibration reviewed clean).
# Both stay omitted here rather than carried — a third-party deployer
# hasn't run that calibration against their own traffic, so their config
# defaults (graceful-degrade routing, guard off) are the safer posture.
# - Host path defaults differ (/opt/roboco vs /volume1/roboco, ${HOME}
# instead of a hardcoded /home/renzof) — registry targets a generic host.
# - MinIO (object storage for rendered videos) is intentionally omitted —
# NAS default-on, registry default-off (see the comment near the
# orchestrator's MinIO env block below and docs/rag/architecture/
# minio-storage.md). No consumer requires it; the media route falls
# back to local-disk FileResponse when unconfigured.
# - The video-renders bind mount is commented out here (video engine ships
# OFF); uncomment alongside ROBOCO_VIDEO_ENGINE_ENABLED=true.
# ============================================================================
services:
postgres:
image: pgvector/pgvector:pg16
container_name: roboco-postgres
restart: unless-stopped
# data-only network: agent containers (on roboco_default) cannot reach
# the production DB; only the multi-homed orchestrator can. Host port
# publishing (15432) is unaffected — roboco_data is a normal bridge.
networks:
- data
environment:
POSTGRES_USER: roboco
POSTGRES_PASSWORD: roboco
POSTGRES_DB: roboco
ports:
- "15432:5432"
volumes:
- ${ROBOCO_DATA_DIR:-./data}/postgres:/var/lib/postgresql/data
healthcheck:
test: ["CMD-SHELL", "pg_isready -U roboco -d roboco"]
interval: 10s
timeout: 5s
retries: 5
redis:
image: redis:8-alpine
container_name: roboco-redis
restart: unless-stopped
# data-only network — see postgres. Redis has no auth, so network
# membership is its ONLY containment against agent containers.
networks:
- data
command: redis-server --appendonly yes
ports:
- "16379:6379"
volumes:
- ${ROBOCO_DATA_DIR:-./data}/redis:/data
healthcheck:
test: ["CMD", "redis-cli", "ping"]
interval: 10s
timeout: 5s
retries: 5
# --------------------------------------------------------------------------
# Backup - periodic pg_dump of the roboco DB (interim; no PITR/WAL yet)
# --------------------------------------------------------------------------
backup:
image: pgvector/pgvector:pg16
container_name: roboco-backup
restart: unless-stopped
# data-only network — pg_dump reaches postgres by container name, same
# as every other data-network consumer; never exposed to the agent mesh.
networks:
- data
environment:
POSTGRES_HOST: roboco-postgres
POSTGRES_PORT: 5432
POSTGRES_USER: roboco
POSTGRES_PASSWORD: roboco
POSTGRES_DB: roboco
# Armed only when ROBOCO_BACKUP_MIRROR_DIR is set in .env; that host
# path must live on a DIFFERENT disk (external/remote mount) — a
# same-disk mirror protects nothing. Unset → the script skips mirroring.
BACKUP_MIRROR_DIR: ${ROBOCO_BACKUP_MIRROR_DIR:+/backups-mirror}
entrypoint: ["/bin/bash", "/scripts/backup-entrypoint.sh"]
volumes:
- ./docker/scripts/backup-entrypoint.sh:/scripts/backup-entrypoint.sh:ro
- ${ROBOCO_DATA_DIR:-./data}/backups:/backups
# Unarmed default deliberately re-mounts the primary backups dir (it
# already exists, so no stray root-owned dir is auto-created) — the
# script never writes there while BACKUP_MIRROR_DIR is empty.
- ${ROBOCO_BACKUP_MIRROR_DIR:-${ROBOCO_DATA_DIR:-./data}/backups}:/backups-mirror
depends_on:
postgres:
condition: service_healthy
ollama:
image: ollama/ollama:latest
container_name: roboco-ollama
restart: unless-stopped
environment:
OLLAMA_API_KEY: ${OLLAMA_API_KEY:-}
ports:
- "11435:11434"
volumes:
- ${ROBOCO_DATA_DIR:-./data}/ollama:/root/.ollama
healthcheck:
test: ["CMD", "ollama", "list"]
interval: 10s
timeout: 5s
retries: 5
start_period: 10s
ollama-init:
image: curlimages/curl:latest
container_name: roboco-ollama-init
depends_on:
ollama:
condition: service_healthy
restart: "no"
entrypoint: ["/bin/sh", "-c"]
command:
- |
# NO `set -e`: pulls are best-effort. Cached models persist in the ollama
# volume and MUST survive a slow/unreachable ollama registry — a manifest
# re-check failure there must never down a fully-cached deployment (it
# used to: a degraded registry made `ollama pull` fail under set -e, which
# blocked the orchestrator's service_completed_successfully gate). Success
# is gated on the models being PRESENT (verify step), not on the pull.
# Note: $$ escapes $ for docker-compose variable substitution.
echo "=== Pulling embedding model (qwen3-embedding:0.6b) — best-effort ==="
curl -sN http://ollama:11434/api/pull -d '{"name":"qwen3-embedding:0.6b"}' | while read -r line; do
status=$$(echo "$$line" | grep -o '"status":"[^"]*"' | cut -d'"' -f4)
[ -n "$$status" ] && echo " $$status"
done || echo " (pull failed — relying on the cached model)"
echo "=== Pulling LLM model (glm-5.2:cloud) — best-effort ==="
curl -sN http://ollama:11434/api/pull -d '{"name":"glm-5.2:cloud"}' | while read -r line; do
status=$$(echo "$$line" | grep -o '"status":"[^"]*"' | cut -d'"' -f4)
[ -n "$$status" ] && echo " $$status"
done || echo " (pull failed — relying on the cached model)"
echo "=== Verifying models are present (the real success gate) ==="
curl -sf http://ollama:11434/api/tags | grep -q "qwen3-embedding" || { echo "FATAL: qwen3-embedding missing and could not be pulled"; exit 1; }
curl -sf http://ollama:11434/api/tags | grep -q "glm-5.2" || { echo "FATAL: glm-5.2 missing and could not be pulled"; exit 1; }
echo "=== All models ready! ==="
# --------------------------------------------------------------------------
# Video Renderer - sidecar for the video-generation engine (renders
# motion/ compositions to MP4 with HyperFrames). Harmless when idle — it
# only renders when POSTed; the video_engine_* feature flags (off by
# default in this compose) gate whether the orchestrator ever sends it
# work. No DB access, no git, no credentials.
# --------------------------------------------------------------------------
video-renderer:
image: ${ROBOCO_REGISTRY:-ghcr.io/rennf93}/roboco-video-renderer:${ROBOCO_VERSION:-latest}
container_name: roboco-video-renderer
restart: unless-stopped
# Isolated sidecar network: headless Chrome here executes
# agent-authored composition HTML/JS. Only the orchestrator (also
# homed on `render`) can reach it; it can reach nothing else.
networks:
- render
# Chrome headless rendering can crash under Docker's default 64MB
# /dev/shm ("Chrome crashed"); give it real shared memory.
shm_size: "1gb"
mem_limit: "2g"
cpus: 2
healthcheck:
test: ["CMD", "node", "-e", "fetch('http://127.0.0.1:3001/health').then((r) => process.exit(r.ok ? 0 : 1)).catch(() => process.exit(1))"]
interval: 10s
timeout: 5s
retries: 5
start_period: 10s
# --------------------------------------------------------------------------
# Agent image pre-pull (one-shot). Each pulls its published image then exits,
# so `docker compose pull` fetches every agent image up front. The
# orchestrator spawns these same images at runtime.
# --------------------------------------------------------------------------
agent-base-image:
image: ${ROBOCO_REGISTRY:-ghcr.io/rennf93}/roboco-agent-base:${ROBOCO_VERSION:-latest}
entrypoint: ["/bin/sh", "-c", "echo 'agent-base image present'"]
restart: "no"
agent-pm-image:
image: ${ROBOCO_REGISTRY:-ghcr.io/rennf93}/roboco-agent-pm:${ROBOCO_VERSION:-latest}
entrypoint: ["/bin/sh", "-c", "echo 'agent-pm image present'"]
restart: "no"
agent-dev-be-image:
image: ${ROBOCO_REGISTRY:-ghcr.io/rennf93}/roboco-agent-dev-be:${ROBOCO_VERSION:-latest}
entrypoint: ["/bin/sh", "-c", "echo 'agent-dev-be image present'"]
restart: "no"
agent-dev-fe-image:
image: ${ROBOCO_REGISTRY:-ghcr.io/rennf93}/roboco-agent-dev-fe:${ROBOCO_VERSION:-latest}
entrypoint: ["/bin/sh", "-c", "echo 'agent-dev-fe image present'"]
restart: "no"
agent-qa-be-image:
image: ${ROBOCO_REGISTRY:-ghcr.io/rennf93}/roboco-agent-qa-be:${ROBOCO_VERSION:-latest}
entrypoint: ["/bin/sh", "-c", "echo 'agent-qa-be image present'"]
restart: "no"
agent-qa-fe-image:
image: ${ROBOCO_REGISTRY:-ghcr.io/rennf93}/roboco-agent-qa-fe:${ROBOCO_VERSION:-latest}
entrypoint: ["/bin/sh", "-c", "echo 'agent-qa-fe image present'"]
restart: "no"
agent-ux-image:
image: ${ROBOCO_REGISTRY:-ghcr.io/rennf93}/roboco-agent-ux:${ROBOCO_VERSION:-latest}
entrypoint: ["/bin/sh", "-c", "echo 'agent-ux image present'"]
restart: "no"
agent-doc-image:
image: ${ROBOCO_REGISTRY:-ghcr.io/rennf93}/roboco-agent-doc:${ROBOCO_VERSION:-latest}
entrypoint: ["/bin/sh", "-c", "echo 'agent-doc image present'"]
restart: "no"
agent-prompter-image:
image: ${ROBOCO_REGISTRY:-ghcr.io/rennf93}/roboco-agent-prompter:${ROBOCO_VERSION:-latest}
entrypoint: ["/bin/sh", "-c", "echo 'agent-prompter image present'"]
restart: "no"
agent-secretary-image:
image: ${ROBOCO_REGISTRY:-ghcr.io/rennf93}/roboco-agent-secretary:${ROBOCO_VERSION:-latest}
entrypoint: ["/bin/sh", "-c", "echo 'agent-secretary image present'"]
restart: "no"
agent-pr-reviewer-image:
image: ${ROBOCO_REGISTRY:-ghcr.io/rennf93}/roboco-agent-pr-reviewer:${ROBOCO_VERSION:-latest}
entrypoint: ["/bin/sh", "-c", "echo 'agent-pr-reviewer image present'"]
restart: "no"
agent-grok-image:
image: ${ROBOCO_REGISTRY:-ghcr.io/rennf93}/roboco-agent-grok:${ROBOCO_VERSION:-latest}
entrypoint: ["/bin/sh", "-c", "echo 'agent-grok image present'"]
restart: "no"
agent-grok-prompter-image:
image: ${ROBOCO_REGISTRY:-ghcr.io/rennf93}/roboco-agent-grok-prompter:${ROBOCO_VERSION:-latest}
entrypoint: ["/bin/sh", "-c", "echo 'agent-grok-prompter image present'"]
restart: "no"
agent-grok-secretary-image:
image: ${ROBOCO_REGISTRY:-ghcr.io/rennf93}/roboco-agent-grok-secretary:${ROBOCO_VERSION:-latest}
entrypoint: ["/bin/sh", "-c", "echo 'agent-grok-secretary image present'"]
restart: "no"
# Codex (OpenAI, official CLI) — one-shot delivery roles only, no
# interactive prompter/secretary variant in V1.
agent-codex-image:
image: ${ROBOCO_REGISTRY:-ghcr.io/rennf93}/roboco-agent-codex:${ROBOCO_VERSION:-latest}
entrypoint: ["/bin/sh", "-c", "echo 'agent-codex image present'"]
restart: "no"
# Gemini (Google, via the official gemini CLI). One-shot delivery roles
# only (V1) — no interactive prompter/secretary variant, contrast Grok above.
agent-gemini-image:
image: ${ROBOCO_REGISTRY:-ghcr.io/rennf93}/roboco-agent-gemini:${ROBOCO_VERSION:-latest}
entrypoint: ["/bin/sh", "-c", "echo 'agent-gemini image present'"]
restart: "no"
# Kimi (Moonshot AI, via the official kimi CLI). One-shot delivery roles
# only (V1) — no interactive prompter/secretary variant, contrast Grok above.
agent-kimi-image:
image: ${ROBOCO_REGISTRY:-ghcr.io/rennf93}/roboco-agent-kimi:${ROBOCO_VERSION:-latest}
entrypoint: ["/bin/sh", "-c", "echo 'agent-kimi image present'"]
restart: "no"
# Sandbox PG (kitchen-sink) — pulled by the provisioner when a venture opts
# into pg extensions. Bare sandboxes use the upstream postgres image, so this
# is only needed by extension-using projects.
sandbox-pg-image:
image: ${ROBOCO_REGISTRY:-ghcr.io/rennf93}/roboco-sandbox-pg:${ROBOCO_VERSION:-latest}
entrypoint: ["/bin/sh", "-c", "echo 'sandbox-pg image present'"]
restart: "no"
# --------------------------------------------------------------------------
# Orchestrator — API server + agent spawner
# --------------------------------------------------------------------------
orchestrator:
image: ${ROBOCO_REGISTRY:-ghcr.io/rennf93}/roboco-orchestrator:${ROBOCO_VERSION:-latest}
container_name: roboco-orchestrator
restart: unless-stopped
# Multi-homed: the agent mesh (default) for spawned agents / panel /
# ollama, the data network for postgres/redis, plus render to reach the
# isolated video-renderer sidecar.
networks:
- default
- data
- render
ports:
# Loopback-only: the orchestrator API is an unauthenticated control plane
# in header-trust mode. nginx reaches it over the internal network, so it
# never needs a routable host publish; remote access goes via nginx + cloud
# auth. A 0.0.0.0 publish exposed spawn/stop and settings-write with no
# credential to anyone who could reach the host (GHSA-4f7g-w95g-5q2c).
- "127.0.0.1:8000:8000"
environment:
# DB network isolation is LIVE in this file (postgres/redis on the
# data-only network): suppress the legacy prod-creds gate-env
# injection — agents can't reach roboco-postgres anyway. This flag
# must always travel with the networks: topology.
ROBOCO_DB_NETWORK_ISOLATED: ${ROBOCO_DB_NETWORK_ISOLATED:-true}
ROBOCO_DATABASE_HOST: roboco-postgres
ROBOCO_DATABASE_PORT: 5432
ROBOCO_DATABASE_USER: roboco
ROBOCO_DATABASE_PASSWORD: roboco
ROBOCO_DATABASE_NAME: roboco
ROBOCO_REDIS_HOST: roboco-redis
ROBOCO_REDIS_PORT: 6379
ROBOCO_HOST: 0.0.0.0
ROBOCO_PORT: 8000
ROBOCO_ENCRYPTION_KEY: ${ROBOCO_ENCRYPTION_KEY:?ROBOCO_ENCRYPTION_KEY is required}
ROBOCO_AGENT_AUTH_SECRET: ${ROBOCO_AGENT_AUTH_SECRET:?ROBOCO_AGENT_AUTH_SECRET is required}
# Fail closed by default (GHSA-4f7g-w95g-5q2c): this deploy is
# ROBOCO_ENVIRONMENT=production, and header-trust off a network-reachable
# port lets any client claim X-Agent-Role: ceo. nginx injects the CEO
# token below so the panel keeps working. Set false only on a trusted
# private network with no untrusted reach to nginx.
ROBOCO_AGENT_AUTH_REQUIRED: ${ROBOCO_AGENT_AUTH_REQUIRED:-true}
ROBOCO_LOCAL_LLM_BASE_URL: http://roboco-ollama:11434/v1
ROBOCO_LOCAL_LLM_MODEL: glm-5.2:cloud
ROBOCO_DEFAULT_EMBEDDING_MODEL: qwen3-embedding:0.6b
ROBOCO_OLLAMA_BASE_URL: http://roboco-ollama:11434
# Video renderer sidecar (use container name). The video engine
# itself is default-off (video_engine_enabled); this just points the
# client at the sidecar for when it's armed.
ROBOCO_VIDEO_RENDERER_BASE_URL: http://roboco-video-renderer:3001
# Spawn the PRE-BUILT agent images from the same registry instead of
# building them from source (the orchestrator pulls any it lacks).
ROBOCO_AGENT_IMAGE_REGISTRY: ${ROBOCO_REGISTRY:-ghcr.io/rennf93}
ROBOCO_AGENT_IMAGE_TAG: ${ROBOCO_VERSION:-latest}
# Host paths for spawning agent containers (Docker-in-Docker). MUST be
# absolute paths on the host. Default to this compose project's ./data.
ROBOCO_HOST_PROJECT_DIR: ${ROBOCO_HOST_PROJECT_DIR:-/opt/roboco}
ROBOCO_HOST_CLAUDE_DIR: ${ROBOCO_HOST_CLAUDE_DIR:-${HOME}/.claude}
# SuperGrok auth (host ~/.grok) for Grok-CLI agents — the orchestrator
# mounts <dir>/auth.json into each Grok agent. Run `grok login` on the host.
ROBOCO_HOST_GROK_DIR: ${ROBOCO_HOST_GROK_DIR:-${HOME}/.grok}
# ChatGPT-subscription auth (host ~/.codex) for Codex-CLI agents — same
# shape as ROBOCO_HOST_GROK_DIR. Run `codex login` on the host.
ROBOCO_HOST_CODEX_DIR: ${ROBOCO_HOST_CODEX_DIR:-${HOME}/.codex}
# OAuth login (host ~/.gemini) for Gemini-CLI agents — the orchestrator
# mounts <dir>/oauth_creds.json (read-only) into each Gemini agent. Run
# `gemini` interactively once on the host to produce it.
ROBOCO_HOST_GEMINI_DIR: ${ROBOCO_HOST_GEMINI_DIR:-${HOME}/.gemini}
# Kimi subscription auth (host ~/.kimi-code) for Kimi-CLI agents — the
# orchestrator mounts <dir>/credentials/kimi-code.json into each Kimi
# agent. Run `kimi login` on the host. Read-WRITE (see the volumes
# mount below): unlike gemini's reusable refresh token, Kimi's refresh
# is rotation-with-short-reuse-grace, so every container shares this
# ONE host chain via a symlinked-in credentials/+oauth/ mount rather
# than a per-container copy (kimi follows codex's RW mount mode here).
ROBOCO_HOST_KIMI_DIR: ${ROBOCO_HOST_KIMI_DIR:-${HOME}/.kimi-code}
ROBOCO_KIMI_CLI_MODEL: ${ROBOCO_KIMI_CLI_MODEL:-kimi-code/k3}
ROBOCO_KIMI_RATE_LIMIT_RETRY_AFTER_SECONDS: ${ROBOCO_KIMI_RATE_LIMIT_RETRY_AFTER_SECONDS:-60}
ROBOCO_KIMI_AUTH_RETRY_AFTER_SECONDS: ${ROBOCO_KIMI_AUTH_RETRY_AFTER_SECONDS:-60}
ROBOCO_KIMI_MAX_CONCURRENT: ${ROBOCO_KIMI_MAX_CONCURRENT:-1}
ROBOCO_HOST_DATA_DIR: ${ROBOCO_HOST_DATA_DIR:-/opt/roboco/data}
# Reachable base URL for commit-trailer links — set to your host's LAN
# address or domain so the links in commit bodies resolve.
ROBOCO_PUBLIC_BASE_URL: ${ROBOCO_PUBLIC_BASE_URL:-http://localhost:8000}
ROBOCO_ENVIRONMENT: production
ROBOCO_CLAIM_STALE_SECONDS: "1800"
ROBOCO_STALE_CLAIM_REAP_SECONDS: "1800"
# Every optional feature ships OFF in this user-facing compose (the build
# compose arms them for the personal deploy). External-PR review included —
# arm it (and any other subsystem) via .env or Settings → Feature Flags.
ROBOCO_EXTERNAL_PR_ENABLED: ${ROBOCO_EXTERNAL_PR_ENABLED:-false}
ROBOCO_EXTERNAL_PR_REQUIRE_HUMAN_CONFIRM: ${ROBOCO_EXTERNAL_PR_REQUIRE_HUMAN_CONFIRM:-true}
# ROBOCO_EXTERNAL_PR_POLL_INTERVAL_SECONDS: "300"
# ROBOCO_EXTERNAL_PR_AUTHOR_ALLOWLIST: '["corey"]' # empty = every external PR
# Production self-healing ("engine 4"). RoboCo watches its OWN repo CI and,
# when red, notifies the CEO and (with originate on) opens a PENDING fix
# task that STOPS for the CEO's Approve-&-Start — it never self-deploys.
# Both toggles default OFF (arm from Settings -> Feature Flags). Set
# PROJECT_SLUG to the registered project that IS RoboCo; CI_WORKFLOW scopes
# the signal to the real CI workflow (RoboCo has several workflows, so the
# unscoped "latest run" would be unreliable).
ROBOCO_SELF_HEAL_ENABLED: ${ROBOCO_SELF_HEAL_ENABLED:-false}
ROBOCO_OBSIDIAN_VAULT_ENABLED: ${ROBOCO_OBSIDIAN_VAULT_ENABLED:-true}
ROBOCO_VAULT_PATH: ${ROBOCO_VAULT_PATH:-/app/vault}
ROBOCO_VAULT_INTAKE_ENABLED: ${ROBOCO_VAULT_INTAKE_ENABLED:-true}
ROBOCO_VAULT_ARCHIVE_DAYS: ${ROBOCO_VAULT_ARCHIVE_DAYS:-30}
ROBOCO_VAULT_REPORT_ENABLED: ${ROBOCO_VAULT_REPORT_ENABLED:-true}
ROBOCO_VAULT_KB_ENABLED: ${ROBOCO_VAULT_KB_ENABLED:-false}
ROBOCO_VAULT_KB_DIRS: ${ROBOCO_VAULT_KB_DIRS:-RoboCo/Notes}
ROBOCO_VAULT_KB_INTERVAL_SECONDS: ${ROBOCO_VAULT_KB_INTERVAL_SECONDS:-900}
ROBOCO_SELF_HEAL_ORIGINATE_ENABLED: ${ROBOCO_SELF_HEAL_ORIGINATE_ENABLED:-false}
ROBOCO_SELF_HEAL_PROJECT_SLUG: ${ROBOCO_SELF_HEAL_PROJECT_SLUG:-roboco-api}
ROBOCO_SELF_HEAL_CI_WORKFLOW: ${ROBOCO_SELF_HEAL_CI_WORKFLOW:-ci.yml}
# Docs-divergence sync (release -> docs-update task): default OFF in the
# registry compose; arm via .env once the engine is verified.
ROBOCO_DOCS_SYNC_ENABLED: ${ROBOCO_DOCS_SYNC_ENABLED:-false}
# Video engine (HyperFrames): NAS-default-on, OFF in public registry —
# heavier optional feature. Arm via .env + uncomment the video-renders
# bind mount above so renders persist.
ROBOCO_VIDEO_ENGINE_ENABLED: ${ROBOCO_VIDEO_ENGINE_ENABLED:-false}
ROBOCO_VIDEO_ON_RELEASE: ${ROBOCO_VIDEO_ON_RELEASE:-false}
ROBOCO_VIDEO_ON_SPOTLIGHT: ${ROBOCO_VIDEO_ON_SPOTLIGHT:-false}
# Toolchain matching + architectural conventions standard: default OFF
# in config; carried here at OFF (armed in the build compose) so a
# registry deploy can opt in via .env without hand-editing this file.
ROBOCO_TOOLCHAIN_MATCH_ENABLED: ${ROBOCO_TOOLCHAIN_MATCH_ENABLED:-false}
ROBOCO_CONVENTIONS_ENABLED: ${ROBOCO_CONVENTIONS_ENABLED:-false}
# Autonomy engines (CI-watch, dep-update bot, release manager, org-memory
# loop, X account, board roadmap engine) — default OFF, carried at OFF
# so the published default stays conservative; arm any via .env.
ROBOCO_CI_WATCH_ENABLED: ${ROBOCO_CI_WATCH_ENABLED:-false}
ROBOCO_DEP_UPDATE_ENABLED: ${ROBOCO_DEP_UPDATE_ENABLED:-false}
ROBOCO_RELEASE_MANAGER_ENABLED: ${ROBOCO_RELEASE_MANAGER_ENABLED:-false}
ROBOCO_ORG_MEMORY_ENABLED: ${ROBOCO_ORG_MEMORY_ENABLED:-false}
ROBOCO_X_ENGINE_ENABLED: ${ROBOCO_X_ENGINE_ENABLED:-false}
ROBOCO_ROADMAP_ENGINE_ENABLED: ${ROBOCO_ROADMAP_ENGINE_ENABLED:-false}
# Telegram notifications bridge V1/V2/V3 — default OFF; inert without
# stored bot-token + chat-id credentials regardless of these flags.
ROBOCO_TELEGRAM_ENABLED: ${ROBOCO_TELEGRAM_ENABLED:-false}
ROBOCO_TELEGRAM_INBOUND_ENABLED: ${ROBOCO_TELEGRAM_INBOUND_ENABLED:-false}
ROBOCO_TELEGRAM_MINIAPP_ENABLED: ${ROBOCO_TELEGRAM_MINIAPP_ENABLED:-false}
# Fable-mode (behavioral doctrine + turn-discipline hooks) and the
# sandboxed per-agent dev DB/Redis — both default OFF, conservative here.
ROBOCO_FABLE_MODE_ENABLED: ${ROBOCO_FABLE_MODE_ENABLED:-false}
ROBOCO_SANDBOX_DB_ENABLED: ${ROBOCO_SANDBOX_DB_ENABLED:-false}
# Strategy engine + internal PR review — both default OFF.
ROBOCO_STRATEGY_ENGINE_ENABLED: ${ROBOCO_STRATEGY_ENGINE_ENABLED:-false}
ROBOCO_INTERNAL_PR_ENABLED: ${ROBOCO_INTERNAL_PR_ENABLED:-false}
# Web research + pitch auto-provisioning: both master switches default
# ON in config (unset here, so they inherit that default); these are
# the key/token passthrough — without them a real value set in .env
# never reaches the container and both stay inert regardless.
ROBOCO_RESEARCH_API_KEY: ${ROBOCO_RESEARCH_API_KEY:-}
ROBOCO_RESEARCH_PROVIDER: ${ROBOCO_RESEARCH_PROVIDER:-tavily}
ROBOCO_PROVISIONING_TOKEN: ${ROBOCO_PROVISIONING_TOKEN:-}
ROBOCO_PROVISIONING_ORG: ${ROBOCO_PROVISIONING_ORG:-}
# Spawn preflight — inert in practice (every real delivery role is
# gateway-enabled); carried at OFF for parity with the build compose.
ROBOCO_SPAWN_PREFLIGHT_ENABLED: ${ROBOCO_SPAWN_PREFLIGHT_ENABLED:-false}
# fastapi-guard's emergency-lockdown whitelist escape hatch. Carried
# here even though the guard trio itself (ENABLED/PASSIVE_MODE/
# FAIL_SECURE, see the declared-contract note above) is intentionally
# omitted — inert while guard stays off by default, but reaches the
# container the moment an operator arms guard by hand-editing this file.
ROBOCO_GUARD_EMERGENCY_WHITELIST: ${ROBOCO_GUARD_EMERGENCY_WHITELIST:-}
# Trusted local-proxy hop IPs (docker bridge gateway) for the XFF
# real-client resolver — carried here (inert until guard is armed) so a
# gateway-fronted Tailscale Serve deploy can set it via .env rather than
# hand-editing this file. Same reach-the-container rule as above.
ROBOCO_GUARD_TRUSTED_CHAIN_PEERS: ${ROBOCO_GUARD_TRUSTED_CHAIN_PEERS:-}
ROBOCO_AGENT_TOOL_CALL_HALT: ${ROBOCO_AGENT_TOOL_CALL_HALT:-600}
ROBOCO_AGENT_TOOL_CALL_WARN: ${ROBOCO_AGENT_TOOL_CALL_WARN:-200}
# Per-task/project cost budgets (default-off; conservative registry
# posture, unlike the build compose which arms it).
ROBOCO_TASK_BUDGETS_ENABLED: ${ROBOCO_TASK_BUDGETS_ENABLED:-false}
# Cloud auth (FastAPI Users): login-gates the panel/API when exposed
# beyond localhost. OFF by default (matches config default, unlike the
# build compose which arms it for the personal deploy). Set
# ROBOCO_CLOUD_AUTH_EMAIL/_PASSWORD/_SECRET in .env and terminate TLS
# before arming — startup fails loud if enabled without a secret.
ROBOCO_CLOUD_AUTH_ENABLED: ${ROBOCO_CLOUD_AUTH_ENABLED:-false}
ROBOCO_CLOUD_AUTH_EMAIL: ${ROBOCO_CLOUD_AUTH_EMAIL:-}
ROBOCO_CLOUD_AUTH_PASSWORD: ${ROBOCO_CLOUD_AUTH_PASSWORD:-}
ROBOCO_CLOUD_AUTH_SECRET: ${ROBOCO_CLOUD_AUTH_SECRET:-}
ROBOCO_CLOUD_AUTH_COOKIE_MAX_AGE: ${ROBOCO_CLOUD_AUTH_COOKIE_MAX_AGE:-2592000}
# MinIO object storage for rendered videos is intentionally omitted from
# this registry compose (NAS default-on, registry default-off — the
# established pattern). The minio/minio-init services are absent here and
# ROBOCO_MINIO_* is left unset, so minio_endpoint defaults to empty and the
# media route falls back to FileResponse. Arm via a custom override file.
volumes:
- /var/run/docker.sock:/var/run/docker.sock
- ${CLAUDE_AUTH_DIR:-${HOME}/.claude}:/root/.claude
# SuperGrok auth — mount host ~/.grok at the SAME host path the orchestrator
# hands each Grok agent's `-v`, so its auth.json exists() check passes here
# AND the agent bind resolves on the host. Read-WRITE: the orchestrator
# auto-refreshes the ~6h token in place (grok_auth.refresh_if_stale) so
# agents never mount a dead credential; the agent's own mount stays RO.
- ${ROBOCO_HOST_GROK_DIR:-${HOME}/.grok}:${ROBOCO_HOST_GROK_DIR:-${HOME}/.grok}
# Codex CLI auth — same shape as the SuperGrok mount above.
- ${ROBOCO_HOST_CODEX_DIR:-${HOME}/.codex}:${ROBOCO_HOST_CODEX_DIR:-${HOME}/.codex}
# OAuth login for Gemini-CLI agents — mount host ~/.gemini at the SAME
# host path the orchestrator hands each Gemini agent's `-v`, so its
# oauth_creds.json exists() check passes here AND the agent bind
# resolves on the host. Read-ONLY: Google's OAuth refresh token is
# reusable and refreshed IN-PROCESS by each agent container's own CLI —
# never by the orchestrator — unlike grok's read-write mount above.
- ${ROBOCO_HOST_GEMINI_DIR:-${HOME}/.gemini}:${ROBOCO_HOST_GEMINI_DIR:-${HOME}/.gemini}:ro
# Kimi subscription auth — mount the host ~/.kimi-code at the SAME host
# path the orchestrator passes to each Kimi agent's `-v`, so the
# credentials/kimi-code.json exists() check passes here AND the agent
# bind resolves on the host. Read-WRITE (unlike gemini's RO mount
# above): Moonshot's refresh token is rotation-with-short-reuse-grace,
# not truly reusable, so every container symlinks credentials/+oauth/
# from this ONE shared chain instead of refreshing a private copy —
# the CLI's own cross-process lock (oauth/kimi-code.lock) serializes
# redemptions. No orchestrator refresh daemon (the CLI refreshes
# itself); this mount just needs to be writable so the CLI can.
- ${ROBOCO_HOST_KIMI_DIR:-${HOME}/.kimi-code}:${ROBOCO_HOST_KIMI_DIR:-${HOME}/.kimi-code}
- ${ROBOCO_DATA_DIR:-./data}/mcp-configs:/app/mcp-configs
- ${ROBOCO_DATA_DIR:-./data}/vault:/app/vault
- ${ROBOCO_DATA_DIR:-./data}/prompts-generated:/app/prompts-generated
- ${ROBOCO_DATA_DIR:-./data}/agent-settings:/app/agent-settings
- ${ROBOCO_DATA_DIR:-./data}/workspaces:/data/workspaces
# Per-agent GROK usage capture (usage.json -> finalizer).
- ${ROBOCO_DATA_DIR:-./data}/grok-usage:/data/grok-usage
# Per-agent CODEX usage capture — same shape as grok-usage above.
- ${ROBOCO_DATA_DIR:-./data}/codex-usage:/data/codex-usage
# Per-agent GEMINI usage capture (usage.json -> finalizer).
- ${ROBOCO_DATA_DIR:-./data}/gemini-usage:/data/gemini-usage
# Per-agent KIMI usage capture — same shape as grok/codex/gemini-usage.
- ${ROBOCO_DATA_DIR:-./data}/kimi-usage:/data/kimi-usage
- ${ROBOCO_DATA_DIR:-./data}/logs:/data/logs
# video engine: NAS-only bind mount, off by default in public registry.
# Uncomment + set ROBOCO_VIDEO_ENGINE_ENABLED=true in .env to arm.
# - ${ROBOCO_DATA_DIR:-./data}/video-renders:/data/video-renders
- ${ROBOCO_DATA_DIR:-./data}/briefings:/app/briefings
- ${ROBOCO_DATA_DIR:-./data}/manifests:/app/manifests
depends_on:
postgres:
condition: service_healthy
redis:
condition: service_healthy
ollama:
condition: service_healthy
ollama-init:
condition: service_completed_successfully
agent-base-image:
condition: service_completed_successfully
# --------------------------------------------------------------------------
# Next.js control panel (fronted by nginx; not exposed directly)
# --------------------------------------------------------------------------
panel:
image: ${ROBOCO_REGISTRY:-ghcr.io/rennf93}/roboco-panel:${ROBOCO_VERSION:-latest}
container_name: roboco-panel
restart: unless-stopped
expose:
- "3000"
depends_on:
- orchestrator
# --------------------------------------------------------------------------
# Nginx — single entry point on port 3000
# --------------------------------------------------------------------------
nginx:
image: nginx:alpine
container_name: roboco-nginx
restart: unless-stopped
ports:
- "3000:80"
environment:
# Required when cloud auth is off: with auth armed, nginx must inject a
# valid CEO token or the panel is locked out (GHSA-4f7g-w95g-5q2c). Mint
# one with the agent-auth secret; see docs/backend/ops.
ROBOCO_PANEL_AGENT_TOKEN: ${ROBOCO_PANEL_AGENT_TOKEN:?ROBOCO_PANEL_AGENT_TOKEN is required (mint a CEO token from ROBOCO_AGENT_AUTH_SECRET) unless ROBOCO_CLOUD_AUTH_ENABLED=true}
NGINX_ENVSUBST_FILTER: "^ROBOCO_"
volumes:
- ./docker/nginx.conf:/etc/nginx/templates/default.conf.template:ro
depends_on:
- panel
- orchestrator
networks:
default:
name: roboco_default
# DB isolation: postgres/redis live ONLY here; the orchestrator is the
# only service homed on both. Spawned agent containers + sandbox sidecars
# join roboco_default (AGENT_NETWORK) and cannot resolve or reach the
# production DB/Redis. Normal bridge (not internal) so host-published
# ports keep working.
data:
name: roboco_data
# Sidecar isolation: video-renderer executes agent-authored composition
# HTML/JS in headless Chrome. It lives ONLY here, reachable only by the
# orchestrator (multi-homed onto this network too); it can reach nothing
# else on roboco_default or roboco_data.
render:
name: roboco_render