feat: universal LLM gateway with embedded multilingual admin console
- OpenAI-compatible gateway with intelligent routing via cortiq-router (allaigate) - Embedded build-free admin SPA at /admin: 7 languages (en/ru/de/fr/es/zh/tr), light/dark themes, hot config reload (no restart) - Admin API, per-request statistics + Prometheus /metrics, secret store, playground - English documentation (primary) with Russian translations (*.ru.md) Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
This commit is contained in:
infosave2007
@@ -0,0 +1,17 @@
|
||||
//! Incoming protocol adapters. Each one builds its own axum routes and translates
|
||||
//! its protocol to/from the canonical model. Enabled via flags in `[protocols]`.
|
||||
|
||||
pub mod openai_chat;
|
||||
|
||||
use crate::state::SharedState;
|
||||
use axum::Router;
|
||||
|
||||
/// Build the protocols router. Implemented adapters are **always** mounted;
|
||||
/// each handler checks the live `protocols.*` flag from config itself, so
|
||||
/// toggles in the admin panel take effect without a restart (hot switching).
|
||||
pub fn build_router() -> Router<SharedState> {
|
||||
Router::new().merge(openai_chat::routes())
|
||||
// TODO: openai_completions, openai_embeddings, openai_models,
|
||||
// anthropic_messages, mcp, native_passthrough — add here as well,
|
||||
// with a check of the corresponding flag inside the handler.
|
||||
}
|
||||
@@ -0,0 +1,168 @@
|
||||
//! Incoming adapter for OpenAI Chat Completions: `POST /v1/chat/completions`.
|
||||
//! Translates the OpenAI request body into a canonical [`ChatRequest`], passes it
|
||||
//! to the pipeline, then converts the canonical [`ChatResponse`] back to OpenAI format.
|
||||
|
||||
use crate::error::{GatewayError, Result};
|
||||
use crate::model::{ChatRequest, GenParams, Message, RequestMeta, RoutingDirective};
|
||||
use crate::state::SharedState;
|
||||
use axum::{extract::State, routing::post, Json, Router};
|
||||
use serde::Deserialize;
|
||||
|
||||
pub fn routes() -> Router<SharedState> {
|
||||
Router::new().route("/v1/chat/completions", post(handler))
|
||||
}
|
||||
|
||||
#[derive(Deserialize)]
|
||||
struct OpenAiChatRequest {
|
||||
model: String,
|
||||
messages: Vec<Message>,
|
||||
#[serde(default)]
|
||||
temperature: Option<f32>,
|
||||
#[serde(default)]
|
||||
max_tokens: Option<u32>,
|
||||
#[serde(default)]
|
||||
top_p: Option<f32>,
|
||||
#[serde(default)]
|
||||
stream: bool,
|
||||
#[serde(default)]
|
||||
tools: Vec<serde_json::Value>,
|
||||
#[serde(flatten)]
|
||||
rest: serde_json::Map<String, serde_json::Value>,
|
||||
}
|
||||
|
||||
/// Parse the `model` field value into a routing directive.
|
||||
/// `cortiq-auto[:profile]` → Auto; otherwise → Pinned(real id).
|
||||
fn parse_routing(model: &str) -> RoutingDirective {
|
||||
if let Some(rest) = model.strip_prefix("cortiq-auto") {
|
||||
let profile = rest.strip_prefix(':').map(|p| p.to_string());
|
||||
RoutingDirective::Auto { profile }
|
||||
} else {
|
||||
RoutingDirective::Pinned {
|
||||
model_id: model.to_string(),
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
async fn handler(
|
||||
State(state): State<SharedState>,
|
||||
Json(req): Json<OpenAiChatRequest>,
|
||||
) -> Result<impl axum::response::IntoResponse> {
|
||||
// hot protocol toggle: if the adapter is disabled in config — return 404
|
||||
if !state.live().cfg.protocols.openai_chat {
|
||||
return Err(GatewayError::InvalidRequest(
|
||||
"openai_chat protocol is disabled".into(),
|
||||
));
|
||||
}
|
||||
if req.messages.is_empty() {
|
||||
return Err(GatewayError::InvalidRequest(
|
||||
"messages must not be empty".into(),
|
||||
));
|
||||
}
|
||||
|
||||
let canonical = ChatRequest {
|
||||
routing: parse_routing(&req.model),
|
||||
messages: req.messages,
|
||||
tools: req.tools,
|
||||
params: GenParams {
|
||||
temperature: req.temperature,
|
||||
max_tokens: req.max_tokens,
|
||||
top_p: req.top_p,
|
||||
stop: Vec::new(),
|
||||
passthrough: req.rest,
|
||||
},
|
||||
stream: req.stream,
|
||||
meta: RequestMeta {
|
||||
protocol: "openai_chat".into(),
|
||||
..Default::default()
|
||||
},
|
||||
};
|
||||
|
||||
if req.stream {
|
||||
return Err(GatewayError::InvalidRequest(
|
||||
"Streaming is not yet supported in this version".into(),
|
||||
));
|
||||
}
|
||||
|
||||
let resp = state.pipeline.run(canonical, &state).await?;
|
||||
|
||||
let mut headers = axum::http::HeaderMap::new();
|
||||
headers.insert(
|
||||
"X-Cortiq-Task-Label",
|
||||
axum::http::HeaderValue::from_str(&resp.cortiq.task_label)
|
||||
.unwrap_or(axum::http::HeaderValue::from_static("")),
|
||||
);
|
||||
headers.insert(
|
||||
"X-Cortiq-Complexity-Score",
|
||||
axum::http::HeaderValue::from_str(&resp.cortiq.complexity_score.to_string())
|
||||
.unwrap_or(axum::http::HeaderValue::from_static("0.0")),
|
||||
);
|
||||
headers.insert(
|
||||
"X-Cortiq-Complexity-Tier",
|
||||
axum::http::HeaderValue::from_str(&resp.cortiq.complexity_tier)
|
||||
.unwrap_or(axum::http::HeaderValue::from_static("")),
|
||||
);
|
||||
headers.insert(
|
||||
"X-Cortiq-Selected-Model",
|
||||
axum::http::HeaderValue::from_str(&resp.cortiq.selected_model)
|
||||
.unwrap_or(axum::http::HeaderValue::from_static("")),
|
||||
);
|
||||
headers.insert(
|
||||
"X-Cortiq-Route-Source",
|
||||
axum::http::HeaderValue::from_str(&resp.cortiq.route_source)
|
||||
.unwrap_or(axum::http::HeaderValue::from_static("")),
|
||||
);
|
||||
headers.insert(
|
||||
"X-Cortiq-Cost-Usd",
|
||||
axum::http::HeaderValue::from_str(&resp.cortiq.cost_usd.to_string())
|
||||
.unwrap_or(axum::http::HeaderValue::from_static("0.0")),
|
||||
);
|
||||
if let Some(req_id) = &resp.cortiq.router_request_id {
|
||||
headers.insert(
|
||||
"X-Cortiq-Request-Id",
|
||||
axum::http::HeaderValue::from_str(req_id)
|
||||
.unwrap_or(axum::http::HeaderValue::from_static("")),
|
||||
);
|
||||
}
|
||||
|
||||
let mut body = serde_json::json!({
|
||||
"id": resp.id,
|
||||
"object": "chat.completion",
|
||||
"created": std::time::SystemTime::now()
|
||||
.duration_since(std::time::UNIX_EPOCH)
|
||||
.unwrap_or_default()
|
||||
.as_secs(),
|
||||
"model": resp.model_used,
|
||||
"choices": resp.choices.iter().map(|c| {
|
||||
serde_json::json!({
|
||||
"index": c.index,
|
||||
"message": {
|
||||
"role": c.message.role,
|
||||
"content": c.message.content,
|
||||
"tool_calls": if c.message.tool_calls.is_empty() { serde_json::Value::Null } else { serde_json::Value::Array(c.message.tool_calls.clone()) },
|
||||
},
|
||||
"finish_reason": c.finish_reason,
|
||||
})
|
||||
}).collect::<Vec<_>>(),
|
||||
"usage": {
|
||||
"prompt_tokens": resp.usage.prompt_tokens,
|
||||
"completion_tokens": resp.usage.completion_tokens,
|
||||
"total_tokens": resp.usage.total_tokens,
|
||||
}
|
||||
});
|
||||
|
||||
if state.live().cfg.cortiq.echo {
|
||||
body["cortiq"] = serde_json::json!({
|
||||
"task_label": resp.cortiq.task_label,
|
||||
"complexity": {
|
||||
"score": resp.cortiq.complexity_score,
|
||||
"tier": resp.cortiq.complexity_tier,
|
||||
},
|
||||
"selected_model": resp.cortiq.selected_model,
|
||||
"route_source": resp.cortiq.route_source,
|
||||
"router_request_id": resp.cortiq.router_request_id,
|
||||
"cost_usd": resp.cortiq.cost_usd,
|
||||
});
|
||||
}
|
||||
|
||||
Ok((headers, Json(body)))
|
||||
}
|
||||
Reference in New Issue
Block a user