One endpoint in front of every free LLM tier, with automatic failover and no provider key ever leaving the box. Providers are data, not code: adding one is a JSON file plus an env var, never a TypeScript change. Ships 12 providers pre-written; `verify-provider --apply` derives the live model list from your own key. - core: registry, bucketed quota meter (rolling + UTC-calendar windows), key-pool store, 6-step model router with diagnostic rejection reasons - gateway: node:http, failover that commits to a stream only after 200 headers, SSE passthrough with usage sniffing, virtual keys with admin/inference roles - context engine: sqlite sessions and a 5-rung refit ladder, so a 128k thread keeps working when it fails over to an 8k model - cache: exact (sha256, safe-by-default) + opt-in semantic (flat Float32Array) - guard: inbound limits, quota forecasting, limit calibration from upstream headers, key health, secret/PII/injection scanning - dashboard: one self-contained HTML file, live SSE request log, token usage - sdk: zero-dep typed client, drop-in for the OpenAI SDK Zero runtime dependencies. 326 tests, 27-check smoke suite against a scripted mock upstream so routing is testable without spending quota. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
53 lines
1.5 KiB
YAML
53 lines
1.5 KiB
YAML
services:
|
|
freeway:
|
|
build: .
|
|
image: freeway:local
|
|
container_name: freeway
|
|
restart: unless-stopped
|
|
|
|
# Bound to loopback on the host. Freeway itself refuses to serve an open
|
|
# gateway on a public interface, but the port mapping is the outer gate.
|
|
ports:
|
|
- "127.0.0.1:8787:8787"
|
|
|
|
env_file:
|
|
- .env
|
|
|
|
environment:
|
|
HOST: 0.0.0.0
|
|
PORT: 8787
|
|
FREEWAY_ROOT: /app
|
|
FREEWAY_PROVIDERS: /app/providers
|
|
FREEWAY_DATA: /app/data
|
|
FREEWAY_CONFIG: /app/freeway.config.json
|
|
NODE_ENV: production
|
|
|
|
volumes:
|
|
# Read-only: adding a provider is editing a JSON file on the host and
|
|
# hitting POST /api/reload — no rebuild, and the container cannot rewrite
|
|
# its own provider definitions.
|
|
- ./providers:/app/providers:ro
|
|
- ./freeway.config.json:/app/freeway.config.json:ro
|
|
# Read-write: quota counters, conversation history, cache, pasted keys.
|
|
# This is what makes a monthly quota survive a restart.
|
|
- ./data:/app/data
|
|
|
|
healthcheck:
|
|
test: ["CMD", "node", "-e", "fetch('http://127.0.0.1:8787/healthz').then(r=>process.exit(r.ok?0:1)).catch(()=>process.exit(1))"]
|
|
interval: 30s
|
|
timeout: 3s
|
|
start_period: 5s
|
|
retries: 3
|
|
|
|
# Nothing here needs root or any elevated capability.
|
|
security_opt:
|
|
- no-new-privileges:true
|
|
cap_drop:
|
|
- ALL
|
|
|
|
logging:
|
|
driver: json-file
|
|
options:
|
|
max-size: "10m"
|
|
max-file: "3"
|