feat(cmf): integrate CMF as a managed local model server
Run models in the CMF (.cmf) format locally, via the native `cortiq` CLI from crates.io — no Python and no external model server. - cmf_runtime: install/update `cortiq-cli` from crates.io, spawn and health-check `cortiq serve` as a managed local backend. - import: model-import jobs shell out to the native `cortiq convert` (HF repo -> .cmf, quant mapped Q8_2F->q8_2f / Q8_ROW->q8 / Q4->q4); the Python converter is used only for advanced/exotic options. - pipeline: local-first routing — serve from the local CMF model when the router is disabled/unreachable, with a "local only" hard switch. - registry/state: register the local CMF server as an OpenAI provider and track local candidates. - config: data-dir resolution + CmfCfg (auto-install/update, managed server, host/port/model) and relaxed validation for the managed model. - admin + settings UI (en/ru): "Local models (CMF)" settings card.
This commit is contained in:
+29
-1
@@ -1,7 +1,7 @@
|
||||
//! Model pool registry: builds providers from `[[models]]` and resolves
|
||||
//! `model_id → Arc<dyn Provider>`.
|
||||
|
||||
use crate::config::Config;
|
||||
use crate::config::{Config, ModelCfg};
|
||||
use crate::providers::{anthropic::AnthropicProvider, openai::OpenAiProvider, Provider};
|
||||
use crate::secrets::SecretStore;
|
||||
use std::collections::HashMap;
|
||||
@@ -27,9 +27,37 @@ impl Registry {
|
||||
};
|
||||
by_id.insert(m.id.clone(), provider);
|
||||
}
|
||||
|
||||
// Managed local CMF server: register it as an OpenAI-compatible provider
|
||||
// so it can be routed to like any other backend — including when the
|
||||
// router is unavailable or the gateway is in local-only mode.
|
||||
if cfg.cmf.manage_server
|
||||
&& !cfg.cmf.local_model.trim().is_empty()
|
||||
&& !by_id.contains_key(&cfg.cmf.model_id)
|
||||
{
|
||||
let m = ModelCfg {
|
||||
id: cfg.cmf.model_id.clone(),
|
||||
provider: "openai".into(),
|
||||
base_url: format!("http://{}:{}/v1", cfg.cmf.local_host, cfg.cmf.local_port),
|
||||
model: "cortiq".into(),
|
||||
cost_tier: "local".into(),
|
||||
price_in: 0.0,
|
||||
price_out: 0.0,
|
||||
kind: "chat".into(),
|
||||
api_key_env: None,
|
||||
caps: Vec::new(),
|
||||
};
|
||||
by_id.insert(m.id.clone(), Arc::new(OpenAiProvider::new(&m, None)?));
|
||||
}
|
||||
Ok(Self { by_id })
|
||||
}
|
||||
|
||||
/// Any model id, preferring a real registered one (used as a local-first
|
||||
/// fallback target when routing cannot pick a specific model).
|
||||
pub fn any_id(&self) -> Option<String> {
|
||||
self.by_id.keys().next().cloned()
|
||||
}
|
||||
|
||||
pub fn get(&self, model_id: &str) -> Option<Arc<dyn Provider>> {
|
||||
self.by_id.get(model_id).cloned()
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user