infosave2007andClaude Opus 4.8
a67564bc24
- cache.rs: cosine-similarity store (threshold, TTL, ring buffer), partitioned by routing signature; tracks hit rate and model cost saved - pipeline: embed routing text, look up before the model call (route_source=cache on hit), insert successful responses; stats record cache hits - config [cache] + admin settings card; dashboard shows hit-rate and savings - embedding model resolved from the pool (or first kind="embedding") Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
109 lines
3.0 KiB
Rust
109 lines
3.0 KiB
Rust
//! Cortiq Gateway — entry point.
|
|
//!
|
|
//! Loads the config, builds the shared state, assembles routes from protocols and
|
|
//! the admin panel, and starts the HTTP server. See docs/ARCHITECTURE.md.
|
|
|
|
// Part of the canonical model / error API surface (auth, rate-limit, idempotency,
|
|
// traceparent, vision/streaming caps) is intentionally reserved for upcoming phases;
|
|
// allow the unused items until those features land.
|
|
#![allow(dead_code)]
|
|
|
|
mod admin;
|
|
mod cache;
|
|
mod config;
|
|
mod error;
|
|
mod model;
|
|
mod pipeline;
|
|
mod protocols;
|
|
mod providers;
|
|
mod registry;
|
|
mod router_client;
|
|
mod routing;
|
|
mod secrets;
|
|
mod state;
|
|
mod stats;
|
|
|
|
use axum::{routing::get, Router};
|
|
use clap::Parser;
|
|
use config::Config;
|
|
use state::SharedState;
|
|
|
|
#[derive(Parser)]
|
|
#[command(
|
|
name = "cortiq-gateway",
|
|
version,
|
|
about = "Universal LLM gateway with intelligent routing"
|
|
)]
|
|
struct Args {
|
|
/// Path to the TOML config file.
|
|
#[arg(long, default_value = "config/gateway.toml")]
|
|
config: String,
|
|
/// Admin token for the web panel (overrides `[admin].token_env`).
|
|
#[arg(long)]
|
|
admin_token: Option<String>,
|
|
}
|
|
|
|
/// Resolve the admin token: env from `[admin].token_env` → `--admin-token` →
|
|
/// generate a random one. Returns `(token, generated)`.
|
|
fn resolve_admin_token(cfg: &Config, args: &Args) -> (String, bool) {
|
|
if let Some(env) = &cfg.admin.token_env {
|
|
if let Ok(v) = std::env::var(env) {
|
|
if !v.is_empty() {
|
|
return (v, false);
|
|
}
|
|
}
|
|
}
|
|
if let Some(t) = &args.admin_token {
|
|
if !t.is_empty() {
|
|
return (t.clone(), false);
|
|
}
|
|
}
|
|
(admin::random_token(24), true)
|
|
}
|
|
|
|
#[tokio::main]
|
|
async fn main() -> anyhow::Result<()> {
|
|
let args = Args::parse();
|
|
|
|
let cfg = Config::load(&args.config)?;
|
|
tracing_subscriber::fmt()
|
|
.with_env_filter(
|
|
tracing_subscriber::EnvFilter::try_from_default_env()
|
|
.unwrap_or_else(|_| cfg.log.level.clone().into()),
|
|
)
|
|
.init();
|
|
|
|
let listen = cfg.listen.clone();
|
|
let admin_enabled = cfg.admin.enabled;
|
|
let (admin_token, generated) = resolve_admin_token(&cfg, &args);
|
|
|
|
let state = SharedState::build(cfg, args.config.clone())?;
|
|
|
|
let mut app = Router::new()
|
|
.route("/healthz", get(|| async { "ok" }))
|
|
.route("/readyz", get(|| async { "ready" }))
|
|
.route("/metrics", get(admin::metrics))
|
|
.merge(protocols::build_router());
|
|
|
|
if admin_enabled {
|
|
app = app
|
|
.merge(admin::api_routes(admin_token.clone()))
|
|
.fallback(admin::assets::fallback);
|
|
}
|
|
|
|
let app = app.with_state(state);
|
|
|
|
let listener = tokio::net::TcpListener::bind(&listen).await?;
|
|
tracing::info!("cortiq-gateway listening on {listen}");
|
|
if admin_enabled {
|
|
tracing::info!("admin console: http://{listen}/admin");
|
|
if generated {
|
|
tracing::warn!(
|
|
"admin token (auto-generated, set [admin].token_env to persist): {admin_token}"
|
|
);
|
|
}
|
|
}
|
|
axum::serve(listener, app).await?;
|
|
Ok(())
|
|
}
|