Files
roboco/.env.example
T
Renn F f6aa590370 feat(grok): close the Claude-parity divergences (reasoning, subagents, web, bash-guard)
Bring the grok CLI to parity with the Claude path on the four deliberate
differences:

- Reasoning: drop the per-role `--effort low` default — Claude sets no per-role
  thinking budget, so grok now uses the model default for every role. The
  fleet-wide ROBOCO_GROK_REASONING_EFFORT override stays as a cost lever. (This
  also un-caps intake-draft quality, the one that actually mattered.)
- Subagents: the intake interviewer may now fan out to subagents (parity with the
  Claude intake's `Task` allowance); every other role still has `Agent` removed.
- Web: `--disable-web-search` for every role — no agent gets direct web (Claude's
  tool set has none either); the roles that get web reach it through the gated
  roboco-search MCP, unaffected.
- Bash command filtering: full parity, split by deny semantics. Verified live that
  a grok PreToolUse hook deny CANCELS the run, while native `--deny` denies
  GRACEFULLY (the agent gets a permission error and recovers). So:
    * git network/branch/history ops -> native `--deny` (operational reflex; the
      agent must recover, not drop the task). Expanded to the full bash-guard set.
    * credential-exfil / identity-forgery / internal-API / env-dump patterns ->
      the SAME bash-guard the Claude path runs, wired as a grok PreToolUse hook
      (ROBOCO_GUARD_SKIP_GIT=1 so it leaves git to `--deny`). A hard cancel is the
      right response there — no legitimate agent reads ~/.netrc or forges an
      X-Agent-ID. One tolerance line (accept grok's camelCase `toolInput`) makes
      the one tested script guard both runtimes; +5 grok cases (50/50 green).

Also cleaned stale internal task-number / smoke labels out of bash-guard-hook.sh.
2026-06-19 05:35:19 +02:00

153 lines
7.0 KiB
Bash

# =============================================================================
# RoboCo Environment Configuration
# =============================================================================
# Copy this file to .env
#
# NOTE: No API keys needed for agents - they use your Claude Code authentication.
# Run `claude` on the host to authenticate before starting RoboCo.
# =============================================================================
# Docker Deployment (NAS/Server)
# =============================================================================
# These are REQUIRED when running via docker compose on a NAS/server.
# They tell the orchestrator container where to find files on the HOST.
# Path to the project on the host (absolute path)
# ROBOCO_HOST_PROJECT_DIR=/volume1/roboco
# Path to Claude Code auth directory on the host
# ROBOCO_HOST_CLAUDE_DIR=/root/.claude
# Claude auth directory to mount into orchestrator
# CLAUDE_AUTH_DIR=~/.claude
# =============================================================================
# Container Images (docker-compose.registry.yml — pre-built deployment)
# =============================================================================
# Only used by docker-compose.registry.yml, which runs the published images
# instead of building from source. Defaults shown.
# Registry namespace: ghcr.io/rennf93 (GHCR) or docker.io/renzof93 (Docker Hub)
# ROBOCO_REGISTRY=ghcr.io/rennf93
# Image tag: latest, or a pinned release such as 0.5.0
# ROBOCO_VERSION=latest
# =============================================================================
# Data Persistence
# =============================================================================
# Set to a path on your NAS RAID array for durability
# Path to data directory on the host (MUST be absolute for Docker-in-Docker)
# ROBOCO_DATA_DIR=/volume1/roboco/data
# =============================================================================
# Application
# =============================================================================
ROBOCO_ENVIRONMENT=development
ROBOCO_DEBUG=true
# =============================================================================
# API Server
# =============================================================================
ROBOCO_HOST=0.0.0.0
ROBOCO_PORT=8000
# =============================================================================
# Database (PostgreSQL)
# =============================================================================
# For docker compose deployment, use container name:
# ROBOCO_DATABASE_HOST=roboco-postgres
# For local development:
ROBOCO_DATABASE_HOST=localhost
ROBOCO_DATABASE_PORT=5432
ROBOCO_DATABASE_USER=roboco
ROBOCO_DATABASE_PASSWORD=roboco
ROBOCO_DATABASE_NAME=roboco
ROBOCO_DATABASE_ECHO=false
# =============================================================================
# Redis
# =============================================================================
# For docker compose deployment, use container name:
# ROBOCO_REDIS_HOST=roboco-redis
# For local development:
ROBOCO_REDIS_HOST=localhost
ROBOCO_REDIS_PORT=6379
ROBOCO_REDIS_DB=0
# ROBOCO_REDIS_PASSWORD=
# =============================================================================
# RAG / Local LLM (Ollama + in-house pgvector engine)
# =============================================================================
# For docker compose use the container name (roboco-ollama); locally, localhost.
ROBOCO_OLLAMA_BASE_URL=http://localhost:11434
ROBOCO_LOCAL_LLM_BASE_URL=http://localhost:11434/v1
ROBOCO_LOCAL_LLM_MODEL=glm-5:cloud
ROBOCO_DEFAULT_EMBEDDING_MODEL=qwen3-embedding:0.6b
# =============================================================================
# Grok (xAI) Provider — optional
# =============================================================================
# RoboCo can run agents on Grok Build (xAI) via xAI's official `grok` CLI on the
# SuperGrok subscription, instead of Claude Code. No metered xAI API key is used:
# the CLI authenticates from a mounted ~/.grok/auth.json — run `grok login` once
# on the host (auth.json auto-refreshes). Every var below is optional.
# Host dir holding the SuperGrok auth. The orchestrator mounts <dir>/auth.json
# read-only into each Grok agent's ~/.grok. GROK_AUTH_DIR is the host source the
# compose mounts into the orchestrator; keep both equal to the host's ~/.grok.
# ROBOCO_HOST_GROK_DIR=/home/youruser/.grok
# GROK_AUTH_DIR=/home/youruser/.grok
# Image the orchestrator spawns for Grok agents, and the CLI model id.
# ROBOCO_GROK_AGENT_IMAGE=roboco-agent-grok:latest
# ROBOCO_GROK_CLI_MODEL=grok-build
# Per-role tool permissions are computed as native grok flags (subagents off
# except intake; edit/shell removed for non-coding roles; git network/branch/
# history mutation + rm -rf denied for coding roles; web search off for all —
# gated web is via the roboco-search MCP). Credential-exfil / identity-forgery /
# internal-API shell patterns are blocked by the same bash-guard the Claude path
# runs, wired as a grok PreToolUse hook. Nothing to set here.
# Reasoning effort for ALL Grok agents: low | medium | high | xhigh | max. Empty
# keeps grok's model default for every role (parity with Claude — no per-role
# cut); set this to trade quality for cost across the whole fleet.
# ROBOCO_GROK_REASONING_EFFORT=
# Hard ceiling on agentic turns per run (loop guard).
# ROBOCO_GROK_MAX_TURNS=200
# Kill a Grok agent container after this many seconds idle (no model call /
# stream) to reclaim a wedged one. Minimum 120.
# ROBOCO_GROK_IDLE_KILL_SECONDS=900
# Per-agent cost ceiling (USD) before the orchestrator kills the container;
# 0 disables. Backstops runaway-loop token burn.
# ROBOCO_GROK_MAX_COST_USD=0.0
# =============================================================================
# Security
# =============================================================================
# Encryption key for git tokens at rest (Fernet). REQUIRED — the orchestrator
# refuses to start without it. Generate with:
# python -c 'from cryptography.fernet import Fernet; print(Fernet.generate_key().decode())'
ROBOCO_ENCRYPTION_KEY=
# Agent auth: HMAC secret that signs X-Agent-Token. REQUIRED for docker compose.
# Generate with: python -c 'import secrets; print(secrets.token_hex(32))'
ROBOCO_AGENT_AUTH_SECRET=
# Secure mode. On a trusted LAN you can leave this false (header-trust mode).
# Set true to require every request to carry a valid token so an agent cannot
# spoof another agent's role. When true you MUST also set ROBOCO_PANEL_AGENT_TOKEN.
ROBOCO_AGENT_AUTH_REQUIRED=false
# The control panel's CEO token, injected by nginx in secure mode so the human
# UI keeps working without the browser holding the signing secret. Generate it
# (after setting ROBOCO_AGENT_AUTH_SECRET above) with: make panel-token
ROBOCO_PANEL_AGENT_TOKEN=
# =============================================================================
# CORS (comma-separated origins)
# =============================================================================
ROBOCO_CORS_ORIGINS=["http://localhost:3000","http://localhost:5173"]