System Configuration

About

Configure the moving parts that aren’t covered by .env alone: provider entries in the LLM gateway’s config.yaml, the PeerDB Postgres → ClickHouse replication mirrors, and Temporal worker concurrency.

LLM gateway

The gateway is a Go LLM proxy that routes all model calls. It ships with config.example.yaml — OpenAI enabled by default.

Setup

# 1. Copy the example
cp futureagi/agentcc-gateway/config.example.yaml \
   futureagi/agentcc-gateway/config.yaml

# 2. Edit config.yaml — uncomment providers, set keys via ${VAR} interpolation
# 3. Set matching keys in .env (OPENAI_API_KEY, ANTHROPIC_API_KEY, etc.)

# 4. Point the gateway volume at your config.yaml (in docker-compose.yml)
#    volumes:
#      - ./futureagi/agentcc-gateway/config.yaml:/app/config.yaml:ro

# 5. Restart
docker compose up -d --force-recreate gateway

config.yaml is gitignored. Treat it as a secret.

Provider config examples

providers:
  openai:
    api_key: "${OPENAI_API_KEY}"
    api_format: "openai"
    models: [gpt-4o, gpt-4o-mini]

  anthropic:
    api_key: "${ANTHROPIC_API_KEY}"
    api_format: "anthropic"
    models: [claude-opus-4-5, claude-sonnet-4-5]

  gemini:
    api_key: "${GOOGLE_API_KEY}"
    api_format: "gemini"
    models: [gemini-2.0-flash, gemini-1.5-pro]

providers:
  bedrock:
    api_key: "${AWS_SECRET_ACCESS_KEY}"
    api_format: "bedrock"
    region: "${AWS_REGION}"
    access_key: "${AWS_ACCESS_KEY_ID}"
    models: [anthropic.claude-3-5-sonnet-20241022-v2:0]

providers:
  vertex:
    base_url: "https://us-central1-aiplatform.googleapis.com"
    api_key: "${GOOGLE_ACCESS_TOKEN}"
    api_format: "gemini"
    headers:
      x-gcp-project: "${GCP_PROJECT_ID}"
      x-gcp-location: "us-central1"
    models: [gemini-2.0-flash-001]

For routing rules, rate limits, caching, and the full config reference — see Agent Command Center → Self-hosted.

PeerDB (Postgres → ClickHouse CDC)

PeerDB continuously replicates Postgres tables into ClickHouse so trace and eval analytics stay fast.

First-boot timing issue: peerdb-init runs immediately on startup, before Django migrations may have completed. If mirrors show “not started” in the PeerDB UI:

# 1. Wait until backend logs "Application startup complete"
docker compose logs -f backend

# 2. Re-run init
docker compose run --rm peerdb-init bash /setup.sh

Verify at http://localhost:3001 — mirrors should show running within seconds.

After upgrades that touch replicated tables, re-run the same init command.

Temporal workers

Default (all-queue) — one worker polls all task queues. Controlled by TEMPORAL_ALL_QUEUES=true in .env. Good for self-hosted deployments.

Per-queue workers (dev mode) — six dedicated workers via the dev overlay:

Tune concurrency in .env via TEMPORAL_MAX_CONCURRENT_ACTIVITIES and TEMPORAL_MAX_CONCURRENT_WORKFLOW_TASKS.

Temporal UI (dev mode): http://localhost:8085

Next Steps