feat(models): auto-derive id from model name; actionable probe auth errors

- The model id is now auto-filled from the model name as you type, and if left
  blank it's derived on save (slug of the last path segment, e.g.
  "qwen/qwen3.7-max" → "qwen3-7-max") — saving no longer errors on a blank id.
- probe/test auth failures (401 / "User not found" / "No auth") now append a
  hint to check the API key (for OpenRouter: use an inference key, not a
  provisioning/management key).

Cargo.lock

@@ -285,7 +285,7 @@ checksum = "1d07550c9036bf2ae0c684c4297d503f838287c83c53686d05370d0e139ae570"
 
 [[package]]
 name = "cortiq-gateway"
-version = "0.2.6"
+version = "0.2.12"
 dependencies = [
  "anyhow",
  "arc-swap",

Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "cortiq-gateway"
-version = "0.2.6"
+version = "0.2.12"
 edition = "2021"
 rust-version = "1.75"
 license = "Apache-2.0"

src/admin/mod.rs

@@ -169,12 +169,17 @@ pub fn api_routes(admin_token: String) -> Router<SharedState> {
         .route("/admin/api/shadow", get(get_shadow))
         .route("/admin/api/hf/search", get(hf_search))
         .route("/admin/api/import", get(list_imports).post(start_import))
-        .route("/admin/api/import/:job", get(import_status).delete(delete_import))
+        .route(
+            "/admin/api/import/:job",
+            get(import_status).delete(delete_import),
+        )
         .route("/admin/api/import/:job/cancel", post(cancel_import))
         .route("/admin/api/import/:job/register", post(register_import))
         .route("/admin/api/cmf", get(cmf_status))
         .route("/admin/api/cmf/install", post(cmf_install))
         .route("/admin/api/cmf/port", get(cmf_port_check))
+        .route("/admin/api/cmf/files", get(cmf_files))
+        .route("/admin/api/provider/models", post(provider_models))
         .route("/admin/api/requests", get(get_requests))
         .route("/admin/api/test", post(run_test))
         .route("/admin/api/test/stream", post(run_test_stream))
@@ -387,18 +392,105 @@ async fn router_probe(State(state): State<SharedState>) -> ApiResult {
     ok(json!({ "ok": true, "status": "ok", "latency_ms": latency_ms, "usage": usage }))
 }
 
+#[derive(Deserialize)]
+struct ProviderModelsBody {
+    provider: String,
+    base_url: String,
+    /// Key typed into the form (takes priority)…
+    #[serde(default)]
+    api_key: Option<String>,
+    /// …or the name of a stored secret to reuse if no key was typed.
+    #[serde(default)]
+    api_key_env: Option<String>,
+}
+
+/// Concise error line from a provider's JSON error body.
+fn provider_err(body: &str, status: u16) -> String {
+    if let Ok(v) = serde_json::from_str::<Value>(body) {
+        if let Some(m) = v["error"]["message"]
+            .as_str()
+            .or_else(|| v["error"].as_str())
+            .or_else(|| v["message"].as_str())
+        {
+            return format!("{status}: {m}");
+        }
+    }
+    format!("HTTP {status}")
+}
+
+/// Validate a provider API key and list its models by calling the provider's
+/// `/models` endpoint — powers the "Test key & load models" button. The key is
+/// used transiently (from the form) or resolved from a stored secret; it is not
+/// persisted here.
+async fn provider_models(
+    State(state): State<SharedState>,
+    Json(b): Json<ProviderModelsBody>,
+) -> ApiResult {
+    let base = b.base_url.trim_end_matches('/').to_string();
+    if base.is_empty() {
+        return Err(ApiError::bad("base URL is required"));
+    }
+    let key = b.api_key.filter(|k| !k.trim().is_empty()).or_else(|| {
+        b.api_key_env
+            .as_deref()
+            .and_then(|e| state.secrets.resolve(e))
+    });
+    let key = key.as_deref();
+
+    let client = reqwest::Client::builder()
+        .timeout(std::time::Duration::from_secs(15))
+        .build()
+        .map_err(|e| ApiError::bad(e.to_string()))?;
+
+    // Anthropic uses x-api-key + anthropic-version and /v1/models; every other
+    // (OpenAI-compatible) provider uses a Bearer token and /models.
+    let resp = if b.provider == "anthropic" {
+        let mut r = client
+            .get(format!("{base}/v1/models"))
+            .header("anthropic-version", "2023-06-01");
+        if let Some(k) = key {
+            r = r.header("x-api-key", k);
+        }
+        r.send().await
+    } else {
+        let mut r = client.get(format!("{base}/models"));
+        if let Some(k) = key {
+            r = r.header("authorization", format!("Bearer {k}"));
+        }
+        r.send().await
+    };
+    let resp = resp.map_err(|e| ApiError::bad(format!("request failed: {e}")))?;
+    let status = resp.status().as_u16();
+    let body = resp.text().await.unwrap_or_default();
+    if !(200..300).contains(&status) {
+        return ok(json!({ "ok": false, "status": status, "error": provider_err(&body, status) }));
+    }
+    // OpenAI + Anthropic both return { "data": [ { "id": ... } ] }.
+    let v: Value = serde_json::from_str(&body).unwrap_or(json!({}));
+    let mut models: Vec<String> = v["data"]
+        .as_array()
+        .map(|arr| {
+            arr.iter()
+                .filter_map(|m| m["id"].as_str().map(|s| s.to_string()))
+                .collect()
+        })
+        .unwrap_or_default();
+    models.sort();
+    ok(json!({ "ok": true, "count": models.len(), "models": models }))
+}
+
 async fn meta() -> ApiResult {
     ok(json!({
         "version": env!("CARGO_PKG_VERSION"),
-        "providers": ["openai", "anthropic", "ollama", "http"],
-        "provider_impl": { "openai": true, "ollama": true, "http": true, "anthropic": true },
-        "cost_tiers": ["cheap", "mid", "expensive"],
+        "providers": ["openai", "anthropic", "openrouter", "lmstudio", "ollama", "http"],
+        "provider_impl": { "openai": true, "anthropic": true, "openrouter": true, "lmstudio": true, "ollama": true, "http": true },
+        "cost_tiers": ["cheap", "mid", "expensive", "local"],
         "kinds": ["chat", "embedding"],
         "profiles": ["cost-saver", "balanced", "quality-first"],
         "text_strategies": ["last_user", "last_user_plus_system", "concat_all"],
         "policy_modes": ["fixed_table", "cost_aware"],
         "tiers": ["low", "medium", "high"],
-        "caps": ["tools", "vision"],
+        "caps": ["tools", "vision", "audio", "reasoning", "json", "caching"],
         "protocols_impl": {
             "openai_chat": true, "openai_completions": true, "openai_embeddings": true,
             "openai_models": true, "anthropic_messages": true, "mcp": true, "native_passthrough": true
@@ -423,7 +515,7 @@ async fn put_config(State(state): State<SharedState>, Json(cfg): Json<Config>) -
 
 async fn list_models(State(state): State<SharedState>) -> ApiResult {
     let live = state.live();
-    let models: Vec<Value> = live
+    let mut models: Vec<Value> = live
         .cfg
         .models
         .iter()
@@ -437,6 +529,31 @@ async fn list_models(State(state): State<SharedState>) -> ApiResult {
             v
         })
         .collect();
+
+    // Managed local CMF servers are registered in the routing registry from the
+    // [cmf] config, not from [[models]]. Surface each here (marked managed, so
+    // the UI shows it read-only) so the real running models are visible and
+    // pinnable without a hand-maintained static pool entry. A fresh install with
+    // no managed model still returns an empty list.
+    let cmf = &live.cfg.cmf;
+    for s in cmf.effective_servers() {
+        if models.iter().any(|m| m["id"] == json!(s.id)) {
+            continue;
+        }
+        models.push(json!({
+            "id": s.id,
+            "provider": "openai",
+            "base_url": format!("http://{}:{}/v1", cmf.local_host, s.port),
+            "model": "cortiq",
+            "cost_tier": "local",
+            "price_in": 0.0,
+            "price_out": 0.0,
+            "kind": "chat",
+            "caps": [],
+            "key_source": "none",
+            "managed": true,
+        }));
+    }
     ok(json!({ "models": models }))
 }
 
@@ -470,28 +587,132 @@ async fn update_model(
     ok(json!({ "ok": true }))
 }
 
+/// Remove a `.cmf` path — it may be a plain file or a tensor-dir. Returns whether
+/// something was actually removed.
+fn remove_cmf_path(path: &std::path::Path) -> bool {
+    if path.is_dir() {
+        std::fs::remove_dir_all(path).is_ok()
+    } else if path.is_file() {
+        std::fs::remove_file(path).is_ok()
+    } else {
+        false
+    }
+}
+
+/// The local `.cmf` backing a pool model, if it is a local CMF model whose file
+/// lives under `models_dir`. Cloud models (real remote base_url) return None.
+/// Registered imports store `model` = the file stem under models_dir.
+fn cmf_file_for_model(
+    cmf: &crate::config::CmfCfg,
+    m: &crate::config::ModelCfg,
+) -> Option<std::path::PathBuf> {
+    let local = m.base_url == cmf.cortiq_server_url
+        || m.base_url
+            .contains(&format!("{}:{}", cmf.local_host, cmf.local_port));
+    let stem = m.model.trim();
+    if !local || stem.is_empty() || stem.contains('/') || stem.contains("..") {
+        return None; // not local, or an unsafe/underivable path
+    }
+    Some(std::path::Path::new(&cmf.models_dir).join(format!("{stem}.cmf")))
+}
+
+/// Drop a model id from routing (default + every tier) so `validate()` still
+/// passes after the model is gone.
+fn strip_id_from_routing(routing: &mut RoutingCfg, id: &str) {
+    if routing.default == id {
+        routing.default = String::new();
+    }
+    for tt in routing.tiers.values_mut() {
+        match tt {
+            crate::config::TierTargets::List(v) => v.retain(|x| x != id),
+            crate::config::TierTargets::One(s) if s == id => {
+                *tt = crate::config::TierTargets::List(Vec::new());
+            }
+            crate::config::TierTargets::One(_) => {}
+        }
+    }
+}
+
+/// Whether any managed server or static model in `cfg` still uses `path` as its
+/// local `.cmf`. Guards against deleting a file that another model shares.
+fn cmf_path_referenced(cfg: &crate::config::Config, path: &std::path::Path) -> bool {
+    cfg.cmf
+        .effective_servers()
+        .iter()
+        .any(|s| std::path::Path::new(&s.model) == path)
+        || cfg
+            .models
+            .iter()
+            .any(|m| cmf_file_for_model(&cfg.cmf, m).as_deref() == Some(path))
+}
+
 async fn delete_model(State(state): State<SharedState>, Path(id): Path<String>) -> ApiResult {
     let mut cfg = current_cfg(&state);
+
+    // Managed local models live in [cmf], not [[models]]. Deleting one stops its
+    // server, removes it from the managed config, and deletes its file — unless
+    // another model still points at the same file.
+    let managed = cfg.cmf.effective_servers().into_iter().find(|s| s.id == id);
+    if let Some(server) = managed {
+        if !cfg.models.iter().any(|x| x.id == id) {
+            if cfg.cmf.servers.iter().any(|s| s.id == id) {
+                cfg.cmf.servers.retain(|s| s.id != id); // multi-model list entry
+            } else {
+                cfg.cmf.local_model = String::new(); // legacy single model
+                cfg.cmf.manage_server = false;
+            }
+            strip_id_from_routing(&mut cfg.routing, &id);
+            let path = std::path::PathBuf::from(&server.model);
+            let shared = cmf_path_referenced(&cfg, &path);
+            state.cmf.stop_one(&id).await;
+            state.reload(cfg)?;
+            let file_removed = if shared {
+                false
+            } else {
+                remove_cmf_path(&path)
+            };
+            return ok(json!({ "ok": true, "file_removed": file_removed }));
+        }
+    }
+
+    let victim = cfg.models.iter().find(|x| x.id == id).cloned();
     let before = cfg.models.len();
     cfg.models.retain(|x| x.id != id);
     if cfg.models.len() == before {
         return Err(ApiError::not_found(format!("model '{id}' not found")));
     }
+    strip_id_from_routing(&mut cfg.routing, &id);
+    let file = victim
+        .as_ref()
+        .and_then(|m| cmf_file_for_model(&cfg.cmf, m));
+    // Only remove the file if no remaining model still references it.
+    let file = file.filter(|p| !cmf_path_referenced(&cfg, p));
     state.reload(cfg)?;
-    ok(json!({ "ok": true }))
+    let file_removed = file.map(|p| remove_cmf_path(&p)).unwrap_or(false);
+    ok(json!({ "ok": true, "file_removed": file_removed }))
 }
 
 async fn probe_model(State(state): State<SharedState>, Path(id): Path<String>) -> ApiResult {
     let live = state.live();
-    let mcfg = live
+    // Provider string: from the static pool, or "openai" for a managed local
+    // model (which is synthesized into the registry, not [[models]]).
+    let provider_str = live
         .cfg
         .models
         .iter()
         .find(|m| m.id == id)
-        .ok_or_else(|| ApiError::not_found(format!("model '{id}' not found")))?
-        .clone();
+        .map(|m| m.provider.clone())
+        .or_else(|| {
+            live.cfg
+                .cmf
+                .effective_servers()
+                .iter()
+                .find(|s| s.id == id)
+                .map(|_| "openai".to_string())
+        })
+        .ok_or_else(|| ApiError::not_found(format!("model '{id}' not found")))?;
 
-    if mcfg.provider == "anthropic" {
+    if provider_str == "anthropic" {
         return ok(json!({
             "ok": false,
             "error": "anthropic provider not yet implemented (planned v0.2)",
@@ -528,7 +749,21 @@ async fn probe_model(State(state): State<SharedState>, Path(id): Path<String>) -
     let latency_ms = started.elapsed().as_millis() as u64;
     match res {
         Ok(_) => ok(json!({ "ok": true, "latency_ms": latency_ms })),
-        Err(e) => ok(json!({ "ok": false, "latency_ms": latency_ms, "error": e.to_string() })),
+        Err(e) => {
+            let msg = e.to_string();
+            // Make auth failures actionable — a raw "User not found" (OpenRouter's
+            // 401) usually means the API key is wrong or the wrong type.
+            let hint = if msg.contains("401")
+                || msg.contains("Unauthorized")
+                || msg.contains("User not found")
+                || msg.contains("No auth")
+            {
+                " — check the API key (for OpenRouter use an inference key, not a provisioning/management key)"
+            } else {
+                ""
+            };
+            ok(json!({ "ok": false, "latency_ms": latency_ms, "error": format!("{msg}{hint}") }))
+        }
     }
 }
 
@@ -666,6 +901,7 @@ async fn put_settings(State(state): State<SharedState>, Json(b): Json<SettingsBo
             || v.local_model != cfg.cmf.local_model
             || v.threads != cfg.cmf.threads
             || v.gpu != cfg.cmf.gpu
+            || v.servers != cfg.cmf.servers
         {
             needs_restart = true;
         }
@@ -683,19 +919,32 @@ async fn cmf_status(State(state): State<SharedState>) -> ApiResult {
     let cmf = state.live().cfg.cmf.clone();
     let ver = crate::cmf_runtime::installed_version(&cmf.cortiq_bin);
     let st = state.cmf.status();
+    // Each configured managed server, merged with its live runtime status.
+    let servers: Vec<Value> = cmf
+        .effective_servers()
+        .iter()
+        .map(|s| {
+            let live = st.servers.iter().find(|x| x.id == s.id);
+            json!({
+                "id": s.id,
+                "model": s.model,
+                "port": s.port,
+                "threads": s.threads,
+                "gpu": s.gpu,
+                "running": live.map(|l| l.running).unwrap_or(false),
+                "healthy": live.map(|l| l.healthy).unwrap_or(false),
+                "last_error": live.and_then(|l| l.last_error.clone()),
+            })
+        })
+        .collect();
     ok(json!({
         "installed": ver.is_some(),
         "version": ver,
-        "running": st.running,
-        "healthy": st.healthy,
-        "last_error": st.last_error,
-        "log": st.log,
-        // serving info so the card can show "serving <model> on :<port>"
+        "latest": st.latest_version,
         "manage_server": cmf.manage_server,
-        "local_model": cmf.local_model,
-        "model_id": cmf.model_id,
         "local_host": cmf.local_host,
-        "local_port": cmf.local_port,
+        "servers": servers,
+        "log": st.log,
     }))
 }
 
@@ -707,6 +956,36 @@ async fn cmf_install(State(state): State<SharedState>) -> ApiResult {
     ok(json!({ "started": true }))
 }
 
+/// List the `.cmf` model files available under `models_dir` so the UI can offer
+/// them as a dropdown instead of a hand-typed path. Includes tensor-dir `.cmf`.
+async fn cmf_files(State(state): State<SharedState>) -> ApiResult {
+    let dir = state.live().cfg.cmf.models_dir.clone();
+    let mut entries: Vec<(String, String, Option<u64>, bool)> = Vec::new();
+    if let Ok(rd) = std::fs::read_dir(&dir) {
+        for e in rd.flatten() {
+            let name = e.file_name().to_string_lossy().to_string();
+            if !name.ends_with(".cmf") {
+                continue;
+            }
+            let p = e.path();
+            let is_dir = p.is_dir();
+            let size = if is_dir {
+                None
+            } else {
+                std::fs::metadata(&p).ok().map(|m| m.len())
+            };
+            let path = format!("{}/{}", dir.trim_end_matches('/'), name);
+            entries.push((name, path, size, is_dir));
+        }
+    }
+    entries.sort_by(|a, b| a.0.cmp(&b.0));
+    let files: Vec<Value> = entries
+        .into_iter()
+        .map(|(name, path, size, is_dir)| json!({ "name": name, "path": path, "size": size, "is_dir": is_dir }))
+        .collect();
+    ok(json!({ "dir": dir, "files": files }))
+}
+
 #[derive(Deserialize)]
 struct PortQuery {
     port: u16,
@@ -726,7 +1005,7 @@ async fn cmf_port_check(State(state): State<SharedState>, Query(q): Query<PortQu
     };
     let st = state.cmf.status();
     let port = q.port;
-    let running_here = port == cmf.local_port && st.running;
+    let running_here = st.servers.iter().any(|s| s.port == port && s.running);
 
     // The bind+connect probe is blocking std::net; run it off the async runtime.
     let (available, detail, suggested) = tokio::task::spawn_blocking(move || {
@@ -736,7 +1015,11 @@ async fn cmf_port_check(State(state): State<SharedState>, Query(q): Query<PortQu
         if port_is_free(&host, port) {
             (true, "free", None)
         } else {
-            (false, "occupied by another process", next_free_port(&host, port))
+            (
+                false,
+                "occupied by another process",
+                next_free_port(&host, port),
+            )
         }
     })
     .await
@@ -974,10 +1257,7 @@ async fn start_import(
     ok(json!({ "job": id }))
 }
 
-async fn import_status(
-    State(state): State<SharedState>,
-    Path(job): Path<String>,
-) -> ApiResult {
+async fn import_status(State(state): State<SharedState>, Path(job): Path<String>) -> ApiResult {
     match state.imports.get(&job) {
         Some(j) => ok(serde_json::to_value(j).unwrap_or_else(|_| json!({}))),
         None => Err(ApiError::not_found(format!("job '{job}' not found"))),
@@ -985,10 +1265,7 @@ async fn import_status(
 }
 
 /// Cancel a running conversion: kills the converter and removes partial output.
-async fn cancel_import(
-    State(state): State<SharedState>,
-    Path(job): Path<String>,
-) -> ApiResult {
+async fn cancel_import(State(state): State<SharedState>, Path(job): Path<String>) -> ApiResult {
     if state.imports.get(&job).is_none() {
         return Err(ApiError::not_found(format!("job '{job}' not found")));
     }
@@ -997,10 +1274,7 @@ async fn cancel_import(
 }
 
 /// Delete a finished conversion and its converted `.cmf` file(s) from disk.
-async fn delete_import(
-    State(state): State<SharedState>,
-    Path(job): Path<String>,
-) -> ApiResult {
+async fn delete_import(State(state): State<SharedState>, Path(job): Path<String>) -> ApiResult {
     if state.imports.get(&job).is_none() {
         return Err(ApiError::not_found(format!("job '{job}' not found")));
     }
@@ -1009,10 +1283,7 @@ async fn delete_import(
 }
 
 /// Register a finished `.cmf` as a local model (OpenAI provider → cortiq-server).
-async fn register_import(
-    State(state): State<SharedState>,
-    Path(job): Path<String>,
-) -> ApiResult {
+async fn register_import(State(state): State<SharedState>, Path(job): Path<String>) -> ApiResult {
     let j = state
         .imports
         .get(&job)

src/cmf_runtime.rs

@@ -1,51 +1,68 @@
 //! Local CMF model server lifecycle.
 //!
 //! Closes the loop with <https://github.com/infosave2007/cmf>: install the
-//! `cortiq` CLI from crates.io, keep it up to date, and run `cortiq serve` as a
-//! managed child process. The served model exposes an OpenAI-compatible API, so
-//! the registry registers it as an ordinary provider and the gateway routes to
-//! it like any other backend.
+//! `cortiq` CLI from crates.io, keep it up to date, and run one `cortiq serve`
+//! per configured local model as a managed child process. Each served model
+//! exposes an OpenAI-compatible API, so the registry registers it as an ordinary
+//! provider and the gateway routes to it like any other backend.
 
-use crate::config::CmfCfg;
+use crate::config::{CmfCfg, CmfServer};
 use std::process::Stdio;
 use std::sync::{Arc, Mutex};
 use std::time::Duration;
 use tokio::process::{Child, Command};
 
-/// Observable state of the managed local CMF server (surfaced to the admin API).
+/// Observable state of one managed local model server.
+#[derive(Clone, Debug, Default, serde::Serialize)]
+pub struct CmfServerStatus {
+    /// Pool id it is registered under.
+    pub id: String,
+    /// Path of the `.cmf` being served.
+    pub model: String,
+    /// Port the server binds to.
+    pub port: u16,
+    /// OpenAI base URL the local server is registered under.
+    pub base_url: String,
+    /// The child `cortiq serve` process has been spawned.
+    pub running: bool,
+    /// `/healthz` on the local server answered 200.
+    pub healthy: bool,
+    /// Last fatal error for this server, if any.
+    pub last_error: Option<String>,
+}
+
+/// Observable state of the managed local CMF layer (surfaced to the admin API).
 #[derive(Clone, Debug, Default, serde::Serialize)]
 pub struct CmfStatus {
-    /// `manage_server` is on and a `local_model` is configured.
+    /// `manage_server` is on and at least one local model is configured.
     pub enabled: bool,
     /// Version reported by `cortiq --version` (None = not installed).
     pub installed_version: Option<String>,
     /// Newest `cortiq-cli` on crates.io (populated when `auto_update` runs).
     pub latest_version: Option<String>,
-    /// The child `cortiq serve` process has been spawned.
-    pub running: bool,
-    /// `/healthz` on the local server answered 200.
-    pub healthy: bool,
-    /// OpenAI base URL the local server is registered under.
-    pub base_url: String,
-    /// Path of the `.cmf` being served.
-    pub model: String,
-    /// Last fatal error, if any.
-    pub last_error: Option<String>,
+    /// Per-model server status.
+    pub servers: Vec<CmfServerStatus>,
     /// Recent lifecycle log lines (bounded).
     pub log: Vec<String>,
 }
 
-/// Holds the managed child process and its live status.
+/// A spawned server: its pool id and the child process handle.
+struct Managed {
+    id: String,
+    child: Child,
+}
+
+/// Holds the managed child processes and their live status.
 pub struct CmfRuntime {
     status: Mutex<CmfStatus>,
-    child: Mutex<Option<Child>>,
+    children: Mutex<Vec<Managed>>,
 }
 
 impl CmfRuntime {
     pub fn new() -> Arc<Self> {
         Arc::new(Self {
             status: Mutex::new(CmfStatus::default()),
-            child: Mutex::new(None),
+            children: Mutex::new(Vec::new()),
         })
     }
 
@@ -59,32 +76,115 @@ impl CmfRuntime {
         let mut s = self.status.lock().unwrap();
         s.log.push(msg);
         let n = s.log.len();
-        if n > 50 {
-            s.log.drain(0..n - 50);
+        if n > 80 {
+            s.log.drain(0..n - 80);
         }
     }
 
+    /// A global (install/update) failure — not tied to a single server.
     fn fail(&self, msg: impl Into<String>) {
         let msg = msg.into();
         tracing::warn!(target: "cmf", "{msg}");
+        self.status.lock().unwrap().log.push(format!("✗ {msg}"));
+    }
+
+    /// Record a fatal error against a specific server (and the log).
+    fn fail_server(&self, id: &str, msg: impl Into<String>) {
+        let msg = msg.into();
+        tracing::warn!(target: "cmf", "[{id}] {msg}");
         let mut s = self.status.lock().unwrap();
-        s.last_error = Some(msg.clone());
-        s.log.push(format!("✗ {msg}"));
+        if let Some(sv) = s.servers.iter_mut().find(|x| x.id == id) {
+            sv.last_error = Some(msg.clone());
+        }
+        s.log.push(format!("✗ [{id}] {msg}"));
     }
 
-    fn set_child(&self, child: Child) {
-        *self.child.lock().unwrap() = Some(child);
-        self.status.lock().unwrap().running = true;
+    /// Seed the per-server status slots from the effective server list.
+    fn init_servers(&self, servers: &[CmfServer], host: &str) {
+        let mut s = self.status.lock().unwrap();
+        s.enabled = true;
+        s.servers = servers
+            .iter()
+            .map(|sv| CmfServerStatus {
+                id: sv.id.clone(),
+                model: sv.model.clone(),
+                port: sv.port,
+                base_url: format!("http://{host}:{}/v1", sv.port),
+                running: false,
+                healthy: false,
+                last_error: None,
+            })
+            .collect();
     }
 
-    /// Stop the managed server (used on shutdown / reconfigure).
+    fn set_running(&self, id: &str, running: bool) {
+        if let Some(sv) = self
+            .status
+            .lock()
+            .unwrap()
+            .servers
+            .iter_mut()
+            .find(|x| x.id == id)
+        {
+            sv.running = running;
+        }
+    }
+
+    fn set_healthy(&self, id: &str, healthy: bool) {
+        if let Some(sv) = self
+            .status
+            .lock()
+            .unwrap()
+            .servers
+            .iter_mut()
+            .find(|x| x.id == id)
+        {
+            sv.healthy = healthy;
+        }
+    }
+
+    fn add_child(&self, id: String, child: Child) {
+        self.children.lock().unwrap().push(Managed {
+            id: id.clone(),
+            child,
+        });
+        self.set_running(&id, true);
+    }
+
+    fn is_running(&self, id: &str) -> bool {
+        self.status
+            .lock()
+            .unwrap()
+            .servers
+            .iter()
+            .any(|s| s.id == id && s.running)
+    }
+
+    /// Stop all managed servers (used on shutdown / reconfigure).
     pub async fn stop(&self) {
-        if let Some(mut child) = self.child.lock().unwrap().take() {
-            let _ = child.start_kill();
+        let mut kids = std::mem::take(&mut *self.children.lock().unwrap());
+        for m in kids.iter_mut() {
+            let _ = m.child.start_kill();
         }
         let mut s = self.status.lock().unwrap();
-        s.running = false;
-        s.healthy = false;
+        for sv in s.servers.iter_mut() {
+            sv.running = false;
+            sv.healthy = false;
+        }
+    }
+
+    /// Stop and forget a single managed server (used when a model is deleted).
+    pub async fn stop_one(&self, id: &str) {
+        let removed = {
+            let mut kids = self.children.lock().unwrap();
+            kids.iter()
+                .position(|m| m.id == id)
+                .map(|pos| kids.remove(pos))
+        };
+        if let Some(mut m) = removed {
+            let _ = m.child.start_kill();
+        }
+        self.status.lock().unwrap().servers.retain(|sv| sv.id != id);
     }
 }
 
@@ -92,7 +192,7 @@ impl Default for CmfRuntime {
     fn default() -> Self {
         Self {
             status: Mutex::new(CmfStatus::default()),
-            child: Mutex::new(None),
+            children: Mutex::new(Vec::new()),
         }
     }
 }
@@ -113,14 +213,15 @@ async fn latest_crates_version() -> Option<String> {
         .await
         .ok()?;
     let v: serde_json::Value = serde_json::from_str(&body).ok()?;
-    v["crate"]["newest_version"]
-        .as_str()
-        .map(|s| s.to_string())
+    v["crate"]["newest_version"].as_str().map(|s| s.to_string())
 }
 
 /// `<bin> --version` → the trailing version token (e.g. "cortiq 0.1.2" → "0.1.2").
 pub(crate) fn installed_version(bin: &str) -> Option<String> {
-    let out = std::process::Command::new(bin).arg("--version").output().ok()?;
+    let out = std::process::Command::new(bin)
+        .arg("--version")
+        .output()
+        .ok()?;
     if !out.status.success() {
         return None;
     }
@@ -130,7 +231,11 @@ pub(crate) fn installed_version(bin: &str) -> Option<String> {
 
 fn parse_ver(s: &str) -> (u32, u32, u32) {
     let mut it = s.split('.').map(|x| x.trim().parse::<u32>().unwrap_or(0));
-    (it.next().unwrap_or(0), it.next().unwrap_or(0), it.next().unwrap_or(0))
+    (
+        it.next().unwrap_or(0),
+        it.next().unwrap_or(0),
+        it.next().unwrap_or(0),
+    )
 }
 
 fn version_lt(a: &str, b: &str) -> bool {
@@ -161,30 +266,33 @@ pub async fn install_now(rt: Arc<CmfRuntime>, bin: String) {
         Ok(()) => {
             let v = installed_version(&bin);
             rt.status.lock().unwrap().installed_version = v.clone();
-            rt.log(format!("installed cortiq-cli {}", v.as_deref().unwrap_or("?")));
+            rt.log(format!(
+                "installed cortiq-cli {}",
+                v.as_deref().unwrap_or("?")
+            ));
         }
         Err(e) => rt.fail(format!("cargo install cortiq-cli failed: {e}")),
     }
 }
 
-/// Spawn `cortiq serve <model> --host <host> --port <port>`; the child is killed
-/// when its handle is dropped (i.e. when the gateway shuts down).
-fn spawn_serve(cfg: &CmfCfg) -> Result<Child, String> {
+/// Spawn `cortiq serve <model> --host <host> --port <port>` for one server; the
+/// child is killed when its handle is dropped (i.e. when the gateway shuts down).
+fn spawn_serve(server: &CmfServer, cfg: &CmfCfg) -> Result<Child, String> {
     let mut cmd = Command::new(&cfg.cortiq_bin);
     cmd.arg("serve")
-        .arg(&cfg.local_model)
+        .arg(&server.model)
         .arg("--host")
         .arg(&cfg.local_host)
         .arg("--port")
-        .arg(cfg.local_port.to_string());
-    // Parallelise decode matvecs across cores (CMF_THREADS). 0 = leave the
+        .arg(server.port.to_string());
+    // Parallelise decode matvecs across cores (CMF_THREADS). 0/1 = leave the
     // runtime's own default; N>1 gave ~2.8x on a 15B CPU model.
-    if cfg.threads > 1 {
-        cmd.env("CMF_THREADS", cfg.threads.to_string());
+    if server.threads > 1 {
+        cmd.env("CMF_THREADS", server.threads.to_string());
     }
     // Offload large matvecs to the GPU (Metal on macOS). Memory-bandwidth-bound
     // on unified memory, so mostly a prefill win; opt-in.
-    if cfg.gpu {
+    if server.gpu {
         cmd.env("CMF_GPU", "1");
     }
     cmd.stdout(Stdio::null())
@@ -214,24 +322,17 @@ async fn wait_healthy(host: &str, port: u16, tries: u32) -> bool {
     false
 }
 
-/// Orchestrate the whole lifecycle: ensure installed → maybe update → spawn →
-/// wait healthy. Safe to call in a background task; it never panics.
+/// Orchestrate the whole lifecycle: ensure installed → maybe update → spawn each
+/// configured local model → wait healthy. Safe to call in a background task; it
+/// never panics.
 pub async fn manage(rt: Arc<CmfRuntime>, cfg: CmfCfg) {
-    if !cfg.manage_server || cfg.local_model.trim().is_empty() {
-        return;
-    }
-    {
-        let mut s = rt.status.lock().unwrap();
-        s.enabled = true;
-        s.base_url = format!("http://{}:{}/v1", cfg.local_host, cfg.local_port);
-        s.model = cfg.local_model.clone();
-    }
-    if !std::path::Path::new(&cfg.local_model).exists() {
-        rt.fail(format!("local_model not found: {}", cfg.local_model));
+    let servers = cfg.effective_servers();
+    if servers.is_empty() {
         return;
     }
+    rt.init_servers(&servers, &cfg.local_host);
 
-    // 1. Ensure the `cortiq` binary is available.
+    // 1. Ensure the `cortiq` binary is available (once for all servers).
     let mut ver = installed_version(&cfg.cortiq_bin);
     if ver.is_none() {
         if cfg.auto_install {
@@ -245,7 +346,9 @@ pub async fn manage(rt: Arc<CmfRuntime>, cfg: CmfCfg) {
                 rt.log("installed cortiq-cli");
             }
         } else {
-            rt.fail("cortiq binary not found (set [cmf].auto_install = true, or install cortiq-cli)");
+            rt.fail(
+                "cortiq binary not found (set [cmf].auto_install = true, or install cortiq-cli)",
+            );
             return;
         }
     }
@@ -255,8 +358,15 @@ pub async fn manage(rt: Arc<CmfRuntime>, cfg: CmfCfg) {
     if cfg.auto_update {
         if let Some(latest) = latest_crates_version().await {
             rt.status.lock().unwrap().latest_version = Some(latest.clone());
-            if ver.as_deref().map(|c| version_lt(c, &latest)).unwrap_or(false) {
-                rt.log(format!("updating cortiq-cli {} → {latest}…", ver.as_deref().unwrap_or("?")));
+            if ver
+                .as_deref()
+                .map(|c| version_lt(c, &latest))
+                .unwrap_or(false)
+            {
+                rt.log(format!(
+                    "updating cortiq-cli {} → {latest}…",
+                    ver.as_deref().unwrap_or("?")
+                ));
                 if let Err(e) = cargo_install(true).await {
                     rt.log(format!("update failed (keeping current): {e}"));
                 } else {
@@ -268,27 +378,38 @@ pub async fn manage(rt: Arc<CmfRuntime>, cfg: CmfCfg) {
         }
     }
 
-    // 3. Spawn the local server.
-    rt.log(format!(
-        "starting: cortiq serve {} --host {} --port {}",
-        cfg.local_model, cfg.local_host, cfg.local_port
-    ));
-    match spawn_serve(&cfg) {
-        Ok(child) => rt.set_child(child),
-        Err(e) => {
-            rt.fail(format!("failed to spawn cortiq serve: {e}"));
-            return;
+    // 3. Spawn each server (fast).
+    for server in &servers {
+        if !std::path::Path::new(&server.model).exists() {
+            rt.fail_server(
+                &server.id,
+                format!("model file not found: {}", server.model),
+            );
+            continue;
+        }
+        rt.log(format!(
+            "starting: cortiq serve {} --host {} --port {}",
+            server.model, cfg.local_host, server.port
+        ));
+        match spawn_serve(server, &cfg) {
+            Ok(child) => rt.add_child(server.id.clone(), child),
+            Err(e) => rt.fail_server(&server.id, format!("failed to spawn: {e}")),
         }
     }
 
-    // 4. Wait until it is serving (model load can take a while for big models).
-    if wait_healthy(&cfg.local_host, cfg.local_port, 240).await {
-        rt.status.lock().unwrap().healthy = true;
-        rt.log(format!(
-            "local CMF server ready — registered as model '{}' at http://{}:{}/v1",
-            cfg.model_id, cfg.local_host, cfg.local_port
-        ));
-    } else {
-        rt.fail("local CMF server did not become healthy in time");
+    // 4. Wait until each spawned server is serving (model load can be slow).
+    for server in &servers {
+        if !rt.is_running(&server.id) {
+            continue; // failed to spawn / file missing
+        }
+        if wait_healthy(&cfg.local_host, server.port, 240).await {
+            rt.set_healthy(&server.id, true);
+            rt.log(format!(
+                "local CMF server ready — '{}' at http://{}:{}/v1",
+                server.id, cfg.local_host, server.port
+            ));
+        } else {
+            rt.fail_server(&server.id, "did not become healthy in time");
+        }
     }
 }

src/config.rs

@@ -10,10 +10,18 @@ use std::path::PathBuf;
 /// `~/.cortiq-gateway` — so defaults work regardless of the process CWD
 /// (important once the gateway is installed rather than run from its repo).
 pub fn data_dir() -> PathBuf {
-    for (var, sub) in [("CORTIQ_GATEWAY_HOME", ""), ("XDG_DATA_HOME", "cortiq-gateway"), ("HOME", ".cortiq-gateway")] {
+    for (var, sub) in [
+        ("CORTIQ_GATEWAY_HOME", ""),
+        ("XDG_DATA_HOME", "cortiq-gateway"),
+        ("HOME", ".cortiq-gateway"),
+    ] {
         if let Ok(v) = std::env::var(var) {
             if !v.is_empty() {
-                return if sub.is_empty() { PathBuf::from(v) } else { PathBuf::from(v).join(sub) };
+                return if sub.is_empty() {
+                    PathBuf::from(v)
+                } else {
+                    PathBuf::from(v).join(sub)
+                };
             }
         }
     }
@@ -59,6 +67,24 @@ pub struct Config {
     pub cmf: CmfCfg,
 }
 
+/// One managed local model: the gateway runs a dedicated `cortiq serve` for it
+/// on its own port and registers it in the pool under `id`.
+#[derive(Clone, Debug, PartialEq, Serialize, Deserialize)]
+pub struct CmfServer {
+    /// Pool id it is registered under (e.g. "cmf-qwen3-5-2b").
+    pub id: String,
+    /// Path to the `.cmf` to serve.
+    pub model: String,
+    /// TCP port the dedicated `cortiq serve` binds to (must be unique).
+    pub port: u16,
+    /// Worker threads (CMF_THREADS). 0 = runtime default.
+    #[serde(default = "default_cmf_threads")]
+    pub threads: usize,
+    /// Offload matvecs to the GPU (CMF_GPU=1).
+    #[serde(default)]
+    pub gpu: bool,
+}
+
 /// CMF-format model factory: import a HuggingFace model, convert it to a
 /// local `.cmf` (quantized), and serve it via cortiq-server. Points the
 /// gateway at the Python converter + runtime on the host.
@@ -121,6 +147,35 @@ pub struct CmfCfg {
     /// (helps prefill of long prompts). Off by default.
     #[serde(default)]
     pub gpu: bool,
+    /// Managed local models. When non-empty (and `manage_server` is on), the
+    /// gateway spawns and supervises one `cortiq serve` per entry — each on its
+    /// own port — and registers each in the pool. Empty = fall back to the single
+    /// legacy `local_model` / `local_port` / `model_id` below (back-compat).
+    #[serde(default)]
+    pub servers: Vec<CmfServer>,
+}
+impl CmfCfg {
+    /// The managed local models actually in effect: the `servers` list when set,
+    /// otherwise the single legacy `local_model` (as a one-element list). Empty
+    /// when `manage_server` is off or nothing is configured.
+    pub fn effective_servers(&self) -> Vec<CmfServer> {
+        if !self.manage_server {
+            return Vec::new();
+        }
+        if !self.servers.is_empty() {
+            return self.servers.clone();
+        }
+        if !self.local_model.trim().is_empty() {
+            return vec![CmfServer {
+                id: self.model_id.clone(),
+                model: self.local_model.clone(),
+                port: self.local_port,
+                threads: self.threads,
+                gpu: self.gpu,
+            }];
+        }
+        Vec::new()
+    }
 }
 impl Default for CmfCfg {
     fn default() -> Self {
@@ -141,6 +196,7 @@ impl Default for CmfCfg {
             local_only: false,
             threads: default_cmf_threads(),
             gpu: false,
+            servers: Vec::new(),
         }
     }
 }
@@ -597,7 +653,8 @@ impl Config {
         // A managed local CMF model counts as an available model even though it
         // is registered dynamically rather than via a [[models]] entry — this
         // is what lets the gateway run on local models alone (no cloud, no router).
-        let has_local = self.cmf.manage_server && !self.cmf.local_model.trim().is_empty();
+        let servers = self.cmf.effective_servers();
+        let has_local = !servers.is_empty();
         if self.models.is_empty() && !has_local {
             // Fresh install: start with an EMPTY model pool so the admin console
             // comes up — the user adds models in /admin → Models (or points [cmf]
@@ -616,8 +673,15 @@ impl Config {
         // every target in [routing] must exist in the model pool
         let mut ids: std::collections::HashSet<&str> =
             self.models.iter().map(|m| m.id.as_str()).collect();
-        if has_local {
-            ids.insert(self.cmf.model_id.as_str());
+        // managed local servers are known ids too; also enforce unique ports/ids
+        let mut ports = std::collections::HashSet::new();
+        for s in &servers {
+            if !ids.insert(s.id.as_str()) {
+                anyhow::bail!("config: duplicate managed model id '{}'", s.id);
+            }
+            if !ports.insert(s.port) {
+                anyhow::bail!("config: two managed models share port {}", s.port);
+            }
         }
         if !self.routing.default.is_empty() && !ids.contains(self.routing.default.as_str()) {
             anyhow::bail!(

src/import.rs

@@ -31,13 +31,19 @@ fn cleanup_output(path: &str) {
 }
 
 fn now() -> u64 {
-    SystemTime::now().duration_since(UNIX_EPOCH).unwrap_or_default().as_secs()
+    SystemTime::now()
+        .duration_since(UNIX_EPOCH)
+        .unwrap_or_default()
+        .as_secs()
 }
 
 /// Job id from a hash of (repo, nanos) — unique without a uuid dependency.
 fn gen_id(repo: &str) -> String {
     use std::hash::{Hash, Hasher};
-    let nanos = SystemTime::now().duration_since(UNIX_EPOCH).unwrap_or_default().as_nanos();
+    let nanos = SystemTime::now()
+        .duration_since(UNIX_EPOCH)
+        .unwrap_or_default()
+        .as_nanos();
     let mut h = std::collections::hash_map::DefaultHasher::new();
     repo.hash(&mut h);
     nanos.hash(&mut h);
@@ -82,8 +88,8 @@ pub struct Job {
     pub started: u64,
     pub finished: Option<u64>,
     pub size_bytes: Option<u64>,
-    pub progress: Option<f32>,  // 0..1, parsed from converter @PROGRESS
-    pub phase: Option<String>,  // current phase label
+    pub progress: Option<f32>, // 0..1, parsed from converter @PROGRESS
+    pub phase: Option<String>, // current phase label
 }
 
 #[derive(Default)]
@@ -178,16 +184,24 @@ impl JobStore {
     }
     pub fn list(&self) -> Vec<Job> {
         let mut v: Vec<Job> = self.jobs.lock().unwrap().values().cloned().collect();
-        v.sort_by(|a, b| b.started.cmp(&a.started));
+        v.sort_by_key(|x| std::cmp::Reverse(x.started));
         v.truncate(20);
         v
     }
 }
 
 /// Proxy HuggingFace model search (avoids browser CORS + adds our token).
-pub async fn hf_search(query: &str, limit: usize, token: Option<&str>) -> Result<serde_json::Value, String> {
+pub async fn hf_search(
+    query: &str,
+    limit: usize,
+    token: Option<&str>,
+) -> Result<serde_json::Value, String> {
     let q: String = url_escape(query);
-    let sort = if query.trim().is_empty() { "trendingScore" } else { "downloads" };
+    let sort = if query.trim().is_empty() {
+        "trendingScore"
+    } else {
+        "downloads"
+    };
     let url = format!(
         "https://huggingface.co/api/models?search={q}&sort={sort}&direction=-1&limit={limit}&full=false"
     );
@@ -218,7 +232,13 @@ fn url_escape(s: &str) -> String {
 
 fn sanitize(s: &str) -> String {
     s.chars()
-        .map(|c| if c.is_ascii_alphanumeric() || c == '-' || c == '_' { c } else { '-' })
+        .map(|c| {
+            if c.is_ascii_alphanumeric() || c == '-' || c == '_' {
+                c
+            } else {
+                '-'
+            }
+        })
         .collect()
 }
 
@@ -244,7 +264,10 @@ pub fn start_import(store: Arc<JobStore>, cfg: &CmfCfg, p: ImportParams) -> Resu
     // doesn't support yet (linear-attention folding, v-bit shaping).
     let use_python = p.linear_core.is_some() || p.vbit_shape.is_some() || p.mean_bits.is_some();
     if use_python && !std::path::Path::new(&cfg.converter).exists() {
-        return Err(format!("advanced options need the Python converter, not found: {}", cfg.converter));
+        return Err(format!(
+            "advanced options need the Python converter, not found: {}",
+            cfg.converter
+        ));
     }
     let _ = std::fs::create_dir_all(&cfg.models_dir);
     let base = if p.name.trim().is_empty() {
@@ -288,18 +311,43 @@ pub fn start_import(store: Arc<JobStore>, cfg: &CmfCfg, p: ImportParams) -> Resu
     let (program, args, workdir): (String, Vec<String>, std::path::PathBuf) = if use_python {
         let conv = std::path::Path::new(&cfg.converter);
         let mut a = vec![
-            std::fs::canonicalize(conv).map(|p| p.to_string_lossy().to_string()).unwrap_or_else(|_| cfg.converter.clone()),
-            "--model".into(), p.repo.clone(),
-            "--quant".into(), p.quant.clone(),
-            "--output".into(), output_abs.clone(),
+            std::fs::canonicalize(conv)
+                .map(|p| p.to_string_lossy().to_string())
+                .unwrap_or_else(|_| cfg.converter.clone()),
+            "--model".into(),
+            p.repo.clone(),
+            "--quant".into(),
+            p.quant.clone(),
+            "--output".into(),
+            output_abs.clone(),
         ];
-        if let Some(lc) = &p.linear_core { a.push("--linear-core".into()); a.push(lc.clone()); }
-        if let Some(n) = p.nphase { a.push("--nphase".into()); a.push(n.to_string()); }
-        if let Some(vs) = &p.vbit_shape { a.push("--vbit-shape".into()); a.push(vs.clone()); }
-        if let Some(mb) = p.mean_bits { a.push("--mean-bits".into()); a.push(mb.to_string()); }
-        if let Some(g) = p.shard_max_gb { a.push("--shard-max-gb".into()); a.push(g.to_string()); }
-        if p.skip_mtp { a.push("--skip-mtp".into()); }
-        let wd = conv.parent().map(|d| d.to_path_buf()).unwrap_or_else(|| std::path::PathBuf::from("."));
+        if let Some(lc) = &p.linear_core {
+            a.push("--linear-core".into());
+            a.push(lc.clone());
+        }
+        if let Some(n) = p.nphase {
+            a.push("--nphase".into());
+            a.push(n.to_string());
+        }
+        if let Some(vs) = &p.vbit_shape {
+            a.push("--vbit-shape".into());
+            a.push(vs.clone());
+        }
+        if let Some(mb) = p.mean_bits {
+            a.push("--mean-bits".into());
+            a.push(mb.to_string());
+        }
+        if let Some(g) = p.shard_max_gb {
+            a.push("--shard-max-gb".into());
+            a.push(g.to_string());
+        }
+        if p.skip_mtp {
+            a.push("--skip-mtp".into());
+        }
+        let wd = conv
+            .parent()
+            .map(|d| d.to_path_buf())
+            .unwrap_or_else(|| std::path::PathBuf::from("."));
         (cfg.python_bin.clone(), a, wd)
     } else if p.repo.to_ascii_lowercase().contains("gguf") {
         // GGUF repo → native `cortiq import-gguf` (downloads + dequantizes any
@@ -307,21 +355,40 @@ pub fn start_import(store: Arc<JobStore>, cfg: &CmfCfg, p: ImportParams) -> Resu
         let mut a = vec![
             "import-gguf".into(),
             p.repo.clone(),
-            "--quant".into(), map_quant(&p.quant).into(),
-            "--output".into(), output_abs.clone(),
+            "--quant".into(),
+            map_quant(&p.quant).into(),
+            "--output".into(),
+            output_abs.clone(),
         ];
-        if let Some(t) = &hf_token { a.push("--hf-token".into()); a.push(t.clone()); }
-        (cfg.cortiq_bin.clone(), a, std::env::current_dir().unwrap_or_else(|_| std::path::PathBuf::from(".")))
+        if let Some(t) = &hf_token {
+            a.push("--hf-token".into());
+            a.push(t.clone());
+        }
+        (
+            cfg.cortiq_bin.clone(),
+            a,
+            std::env::current_dir().unwrap_or_else(|_| std::path::PathBuf::from(".")),
+        )
     } else {
         // safetensors → native `cortiq convert` (dense / MoE / GatedDeltaNet).
         let mut a = vec![
             "convert".into(),
-            "--model".into(), p.repo.clone(),
-            "--quant".into(), map_quant(&p.quant).into(),
-            "--output".into(), output_abs.clone(),
+            "--model".into(),
+            p.repo.clone(),
+            "--quant".into(),
+            map_quant(&p.quant).into(),
+            "--output".into(),
+            output_abs.clone(),
         ];
-        if let Some(t) = &hf_token { a.push("--hf-token".into()); a.push(t.clone()); }
-        (cfg.cortiq_bin.clone(), a, std::env::current_dir().unwrap_or_else(|_| std::path::PathBuf::from(".")))
+        if let Some(t) = &hf_token {
+            a.push("--hf-token".into());
+            a.push(t.clone());
+        }
+        (
+            cfg.cortiq_bin.clone(),
+            a,
+            std::env::current_dir().unwrap_or_else(|_| std::path::PathBuf::from(".")),
+        )
     };
 
     let ret_id = id.clone();

src/pipeline.rs

@@ -208,15 +208,25 @@ impl Pipeline {
         };
 
         let (decision, route_source, candidates) = if live.cfg.cmf.local_only {
-            (mk("local-only", "local"), "local".to_string(), live.local_candidates())
+            (
+                mk("local-only", "local"),
+                "local".to_string(),
+                live.local_candidates(),
+            )
         } else {
             match &req.routing {
-                RoutingDirective::Pinned { model_id } => {
-                    (mk("pinned", "pinned"), "pinned".to_string(), vec![model_id.clone()])
-                }
+                RoutingDirective::Pinned { model_id } => (
+                    mk("pinned", "pinned"),
+                    "pinned".to_string(),
+                    vec![model_id.clone()],
+                ),
                 RoutingDirective::Auto { profile } => {
                     if !live.cfg.router.enabled {
-                        (mk("router-disabled", "local"), "local".to_string(), live.local_candidates())
+                        (
+                            mk("router-disabled", "local"),
+                            "local".to_string(),
+                            live.local_candidates(),
+                        )
                     } else {
                         let prof = profile.as_deref().unwrap_or(&live.cfg.route.profile);
                         match live.router.route(&text, prof).await {
@@ -229,7 +239,11 @@ impl Pipeline {
                                 tracing::warn!(
                                     "Router is unavailable. Gracefully degrading to the local/default model."
                                 );
-                                (mk("degraded", "fallback"), "fallback".to_string(), live.local_candidates())
+                                (
+                                    mk("degraded", "fallback"),
+                                    "fallback".to_string(),
+                                    live.local_candidates(),
+                                )
                             }
                         }
                     }
@@ -253,9 +267,21 @@ impl Pipeline {
             }
         }
 
-        // Local-first safety net: if routing produced no usable candidate (e.g.
-        // an unknown pinned model while the router is off), fall back to the
-        // managed local model so a configured local backend still answers.
+        // An explicit pin must never silently answer from a different model: if
+        // the pinned id is unknown or was filtered out, fail loudly so the caller
+        // knows their choice was not honoured (instead of getting a stray reply
+        // from the managed local model via the safety net below).
+        if final_candidates.is_empty() {
+            if let RoutingDirective::Pinned { model_id } = &req.routing {
+                return Err(GatewayError::UpstreamUnavailable(format!(
+                    "pinned model '{model_id}' is not available — it is not in the pool (deleted?) or lacks a required capability such as tools"
+                )));
+            }
+        }
+
+        // Local-first safety net: for AUTO/degraded routes only, if routing
+        // produced no usable candidate, fall back to the managed local model so a
+        // configured local backend still answers.
         if final_candidates.is_empty() && live.cfg.cmf.manage_server {
             for id in live.local_candidates() {
                 if let Some(prov) = live.registry.get(&id) {
@@ -289,7 +315,10 @@ impl Pipeline {
             && !sh.local_model_id.is_empty()
             && matches!(req.routing, RoutingDirective::Auto { .. })
             && state.promotion.serves_local(&decision.task_label)
-            && !matches!(decision.complexity_tier.as_str(), "high" | "hard" | "complex")
+            && !matches!(
+                decision.complexity_tier.as_str(),
+                "high" | "hard" | "complex"
+            )
             && !final_candidates.iter().any(|m| m == &sh.local_model_id)
         {
             final_candidates.insert(0, sh.local_model_id.clone());
@@ -713,7 +742,7 @@ fn parse_judge(text: &str) -> (u8, bool) {
     let score = text
         .split("score")
         .nth(1)
-        .and_then(|t| t.chars().skip_while(|c| !c.is_ascii_digit()).next())
+        .and_then(|t| t.chars().find(|c| c.is_ascii_digit()))
         .and_then(|c| c.to_digit(10))
         .map(|d| d.min(4) as u8);
     let hard_fail = text
@@ -747,7 +776,10 @@ async fn shadow_capture(
     };
 
     // 1. Local answer (free, CPU).
-    let a_local = match local.chat(shadow_req(&cfg.local_model_id, clip(&prompt, 4000), 512)).await {
+    let a_local = match local
+        .chat(shadow_req(&cfg.local_model_id, clip(&prompt, 4000), 512))
+        .await
+    {
         Ok(r) => r
             .choices
             .into_iter()

src/promotion.rs

@@ -18,7 +18,10 @@ use std::sync::Mutex;
 use std::time::{SystemTime, UNIX_EPOCH};
 
 fn now_secs() -> u64 {
-    SystemTime::now().duration_since(UNIX_EPOCH).unwrap_or_default().as_secs()
+    SystemTime::now()
+        .duration_since(UNIX_EPOCH)
+        .unwrap_or_default()
+        .as_secs()
 }
 
 /// One judgment of a local answer (JSONL line, replayed on startup).
@@ -62,14 +65,14 @@ pub enum PromotionState {
 #[derive(Clone, Debug)]
 pub struct PromotionCfg {
     pub enabled: bool,
-    pub window: usize,       // rolling judgments per label (W)
-    pub n_min: usize,        // min judgments before promotion is even considered
-    pub promote_lb: f64,     // Wilson-95 LB of pass must clear this
-    pub demote_pass: f64,    // point pass-rate below this → demote a served label
-    pub hardfail_ub_max: f64,// Wilson-95 UPPER bound of hard_fail must stay under this
-    pub soak: usize,         // extra Canary judgments before LocalServed
-    pub z: f64,              // 1.96 = 95%
-    pub file: Option<String>,// judge.jsonl path (append + replay)
+    pub window: usize,        // rolling judgments per label (W)
+    pub n_min: usize,         // min judgments before promotion is even considered
+    pub promote_lb: f64,      // Wilson-95 LB of pass must clear this
+    pub demote_pass: f64,     // point pass-rate below this → demote a served label
+    pub hardfail_ub_max: f64, // Wilson-95 UPPER bound of hard_fail must stay under this
+    pub soak: usize,          // extra Canary judgments before LocalServed
+    pub z: f64,               // 1.96 = 95%
+    pub file: Option<String>, // judge.jsonl path (append + replay)
 }
 
 impl Default for PromotionCfg {
@@ -92,7 +95,7 @@ struct LabelState {
     passes: VecDeque<bool>,     // rolling window of pass/fail
     hard_fails: VecDeque<bool>, // rolling window of hard_fail flags
     state: PromotionState,
-    soaked: usize,              // judgments accumulated while in Canary
+    soaked: usize, // judgments accumulated while in Canary
 }
 
 impl LabelState {
@@ -124,20 +127,29 @@ pub fn wilson_bound(s: usize, n: usize, z: f64, upper: bool) -> f64 {
     let denom = 1.0 + z2 / n;
     let centre = p + z2 / (2.0 * n);
     let margin = z * ((p * (1.0 - p) / n) + z2 / (4.0 * n * n)).sqrt();
-    let v = if upper { centre + margin } else { centre - margin };
+    let v = if upper {
+        centre + margin
+    } else {
+        centre - margin
+    };
     (v / denom).clamp(0.0, 1.0)
 }
 
 impl Promotion {
     pub fn new(cfg: PromotionCfg) -> std::sync::Arc<Self> {
-        let p = std::sync::Arc::new(Self { cfg, labels: Mutex::new(HashMap::new()) });
+        let p = std::sync::Arc::new(Self {
+            cfg,
+            labels: Mutex::new(HashMap::new()),
+        });
         p.replay();
         p
     }
 
     fn replay(&self) {
         let Some(path) = &self.cfg.file else { return };
-        let Ok(content) = std::fs::read_to_string(path) else { return };
+        let Ok(content) = std::fs::read_to_string(path) else {
+            return;
+        };
         for line in content.lines() {
             if let Ok(rec) = serde_json::from_str::<JudgeRecord>(line) {
                 self.apply(&rec);
@@ -151,8 +163,10 @@ impl Promotion {
         let st = self.apply(&rec);
         if let Some(path) = &self.cfg.file {
             if let Ok(line) = serde_json::to_string(&rec) {
-                if let Ok(mut f) =
-                    std::fs::OpenOptions::new().create(true).append(true).open(path)
+                if let Ok(mut f) = std::fs::OpenOptions::new()
+                    .create(true)
+                    .append(true)
+                    .open(path)
                 {
                     let _ = writeln!(f, "{line}");
                 }
@@ -163,7 +177,9 @@ impl Promotion {
 
     fn apply(&self, rec: &JudgeRecord) -> PromotionState {
         let mut map = self.labels.lock().unwrap();
-        let ls = map.entry(rec.task_label.clone()).or_insert_with(LabelState::new);
+        let ls = map
+            .entry(rec.task_label.clone())
+            .or_insert_with(LabelState::new);
         push_cap(&mut ls.passes, rec.pass, self.cfg.window);
         push_cap(&mut ls.hard_fails, rec.hard_fail, self.cfg.window);
         self.advance(ls);
@@ -188,7 +204,12 @@ impl Promotion {
 
         ls.state = match ls.state {
             PromotionState::CloudOnly | PromotionState::ShadowJudged => {
-                if bar { ls.soaked = 0; PromotionState::Canary } else { PromotionState::ShadowJudged }
+                if bar {
+                    ls.soaked = 0;
+                    PromotionState::Canary
+                } else {
+                    PromotionState::ShadowJudged
+                }
             }
             PromotionState::Canary => {
                 if regressed {
@@ -203,7 +224,11 @@ impl Promotion {
                 }
             }
             PromotionState::LocalServed => {
-                if regressed { PromotionState::Demoted } else { PromotionState::LocalServed }
+                if regressed {
+                    PromotionState::Demoted
+                } else {
+                    PromotionState::LocalServed
+                }
             }
             // Demoted goes back to SHADOW to re-earn promotion (skill stays in .cmf).
             PromotionState::Demoted => PromotionState::ShadowJudged,
@@ -223,7 +248,10 @@ impl Promotion {
     /// Should a request of this label be SERVED by the local model?
     /// (Canary/LocalServed; caller still applies the per-request veto.)
     pub fn serves_local(&self, label: &str) -> bool {
-        matches!(self.state(label), PromotionState::Canary | PromotionState::LocalServed)
+        matches!(
+            self.state(label),
+            PromotionState::Canary | PromotionState::LocalServed
+        )
     }
 
     /// Snapshot for /admin: (state, n, pass-rate, Wilson-LB) per label.
@@ -235,10 +263,16 @@ impl Promotion {
                 let n = ls.passes.len();
                 let s = ls.passes.iter().filter(|&&p| p).count();
                 let p = if n > 0 { s as f64 / n as f64 } else { 0.0 };
-                (k.clone(), ls.state, n, p, wilson_bound(s, n, self.cfg.z, false))
+                (
+                    k.clone(),
+                    ls.state,
+                    n,
+                    p,
+                    wilson_bound(s, n, self.cfg.z, false),
+                )
             })
             .collect();
-        out.sort_by(|a, b| b.2.cmp(&a.2));
+        out.sort_by_key(|x| std::cmp::Reverse(x.2));
         out
     }
 
@@ -259,12 +293,24 @@ mod tests {
     use super::*;
 
     fn cfg() -> PromotionCfg {
-        PromotionCfg { enabled: true, n_min: 200, soak: 0, ..Default::default() }
+        PromotionCfg {
+            enabled: true,
+            n_min: 200,
+            soak: 0,
+            ..Default::default()
+        }
     }
     fn rec(label: &str, pass: bool, hard_fail: bool) -> JudgeRecord {
         JudgeRecord {
-            ts: 0, task_label: label.into(), pass, hard_fail, score: if pass { 4 } else { 0 },
-            source: "checker".into(), recon_e: None, born_conf: None, judge_tokens: 0,
+            ts: 0,
+            task_label: label.into(),
+            pass,
+            hard_fail,
+            score: if pass { 4 } else { 0 },
+            source: "checker".into(),
+            recon_e: None,
+            born_conf: None,
+            judge_tokens: 0,
         }
     }
 
@@ -316,7 +362,10 @@ mod tests {
             match row {
                 Some((_, st, n, pr, lb)) => println!(
                     "    {label:<12} {:<13} n={n:<4} pass={:.0}% LB={:.3} serves_local={}",
-                    format!("{st:?}"), pr * 100.0, lb, p.serves_local(label)
+                    format!("{st:?}"),
+                    pr * 100.0,
+                    lb,
+                    p.serves_local(label)
                 ),
                 None => println!("    {label:<12} (cloud-only, no judgments)"),
             }
@@ -324,19 +373,29 @@ mod tests {
 
         println!("\n── self-warming loop, live ──");
         // A mature skill (e.g. ru-tech): local answers pass the judge ~99%.
-        println!("  1) SHADOW→CANARY: судим локаль 'ru_tech' (сильный скилл ~99% pass), 210 судейств:");
+        println!(
+            "  1) SHADOW→CANARY: судим локаль 'ru_tech' (сильный скилл ~99% pass), 210 судейств:"
+        );
         for i in 0..210 {
             p.record(rec("ru_tech", i % 100 != 0, false));
         }
         show("ru_tech");
-        assert_eq!(p.state("ru_tech"), PromotionState::Canary, "n≥200 & LB≥0.95 → CANARY");
+        assert_eq!(
+            p.state("ru_tech"),
+            PromotionState::Canary,
+            "n≥200 & LB≥0.95 → CANARY"
+        );
 
         println!("  2) CANARY soak (ещё 60 судейств держат планку) → LOCAL_SERVED:");
         for i in 0..60 {
             p.record(rec("ru_tech", i % 100 != 0, false));
         }
         show("ru_tech");
-        assert_eq!(p.state("ru_tech"), PromotionState::LocalServed, "soak → LOCAL_SERVED");
+        assert_eq!(
+            p.state("ru_tech"),
+            PromotionState::LocalServed,
+            "soak → LOCAL_SERVED"
+        );
         assert!(p.serves_local("ru_tech"), "теперь обслуживается локально");
 
         // The code dataset: local fails the checker → never promotes.
@@ -345,7 +404,11 @@ mod tests {
             p.record(rec("code", false, false));
         }
         show("code");
-        assert_eq!(p.state("code"), PromotionState::ShadowJudged, "остаётся на облаке — безопасно");
+        assert_eq!(
+            p.state("code"),
+            PromotionState::ShadowJudged,
+            "остаётся на облаке — безопасно"
+        );
         assert!(!p.serves_local("code"));
 
         // Drift on the promoted label → auto-demote back to cloud.
@@ -376,6 +439,9 @@ mod tests {
         for _ in 0..300 {
             p2.record(rec("t", false, false)); // quality collapses
         }
-        assert!(matches!(p2.state("t"), PromotionState::Demoted | PromotionState::ShadowJudged));
+        assert!(matches!(
+            p2.state("t"),
+            PromotionState::Demoted | PromotionState::ShadowJudged
+        ));
     }
 }

src/registry.rs

@@ -21,24 +21,27 @@ impl Registry {
                 .as_ref()
                 .and_then(|name| secrets.resolve(name));
             let provider: Arc<dyn Provider> = match m.provider.as_str() {
-                "openai" | "ollama" | "http" => Arc::new(OpenAiProvider::new(m, api_key)?),
+                // openrouter + lmstudio are OpenAI-compatible (Bearer + /chat/completions)
+                "openai" | "ollama" | "http" | "openrouter" | "lmstudio" => {
+                    Arc::new(OpenAiProvider::new(m, api_key)?)
+                }
                 "anthropic" => Arc::new(AnthropicProvider::new(m, api_key)?),
                 other => anyhow::bail!("unknown provider '{}' for model '{}'", other, m.id),
             };
             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)
-        {
+        // Managed local CMF servers: register each 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.
+        for s in cfg.cmf.effective_servers() {
+            if by_id.contains_key(&s.id) {
+                continue; // a static [[models]] entry with the same id wins
+            }
             let m = ModelCfg {
-                id: cfg.cmf.model_id.clone(),
+                id: s.id.clone(),
                 provider: "openai".into(),
-                base_url: format!("http://{}:{}/v1", cfg.cmf.local_host, cfg.cmf.local_port),
+                base_url: format!("http://{}:{}/v1", cfg.cmf.local_host, s.port),
                 model: "cortiq".into(),
                 cost_tier: "local".into(),
                 price_in: 0.0,

src/state.rs

@@ -49,8 +49,8 @@ impl Live {
     /// (local-only / disabled) or unavailable, so CMF models serve with no router.
     pub fn local_candidates(&self) -> Vec<String> {
         let mut v = Vec::new();
-        if self.cfg.cmf.manage_server && !self.cfg.cmf.local_model.trim().is_empty() {
-            v.push(self.cfg.cmf.model_id.clone());
+        for s in self.cfg.cmf.effective_servers() {
+            v.push(s.id);
         }
         let def = self.routing.default_model().to_string();
         if !def.is_empty() && !v.contains(&def) {
@@ -90,7 +90,11 @@ fn promotion_cfg(s: &crate::config::ShadowCfg) -> crate::promotion::PromotionCfg
         n_min: s.n_min,
         promote_lb: s.promote_lb,
         soak: s.soak,
-        file: if s.file.is_empty() { None } else { Some(s.file.clone()) },
+        file: if s.file.is_empty() {
+            None
+        } else {
+            Some(s.file.clone())
+        },
         ..Default::default()
     }
 }

web/js/api.js

@@ -99,6 +99,8 @@ export const api = {
   cmfStatus: () => j("GET", "/cmf"),
   cmfInstall: () => j("POST", "/cmf/install"),
   cmfPortCheck: (port) => j("GET", "/cmf/port?port=" + encodeURIComponent(port)),
+  cmfFiles: () => j("GET", "/cmf/files"),
+  providerModels: (b) => j("POST", "/provider/models", b),
 
   // CMF model factory (HuggingFace → local .cmf)
   hfSearch: (q, limit = 24) =>

web/js/i18n/en.js

@@ -129,6 +129,20 @@ export default {
   "models.form.secretMissing": "not set",
   "models.form.secretPlaceholder": "set or replace key (write-only)",
   "models.deleteConfirm": "Delete model \"{id}\"?",
+  "models.form.idOrModel": "Enter an id or a model name",
+  "models.form.apiKey": "API Key",
+  "models.form.apiKeyPlaceholder": "paste your API key",
+  "models.form.apiKeyNotNeeded": "not required (local server)",
+  "models.form.apiKeyHint": "Stored securely on the gateway; it is not shown again.",
+  "models.form.keyStored": "A key is saved — leave blank to keep it, or paste a new one.",
+  "models.form.keyFromEnv": "Using a key from an environment variable.",
+  "models.form.testKey": "Test & load models",
+  "models.form.testing": "checking…",
+  "models.form.foundModels": "{n} models loaded",
+  "models.form.modelPlaceholder": "type to search…",
+  "models.form.modelHint": "Click “Test & load models” to pull the list from your key, then pick one.",
+  "models.managed": "managed",
+  "models.managedHint": "Provided by the managed CMF server (Settings → Local models). Configure it there.",
 
   // routing
   "routing.title": "Routing",
@@ -242,6 +256,11 @@ export default {
   "settings.cmf.threads": "Worker threads",
   "settings.cmf.gpu": "Use GPU (Metal / wgpu)",
   "settings.cmf.speedNote": "Threads parallelise the decode matvecs (~3x faster; 0 = runtime default). GPU offload mainly helps prefill of long prompts — decode is memory-bandwidth-bound, so on Apple Silicon it is roughly neutral.",
+  "settings.cmf.pick": "select a model",
+  "settings.cmf.models": "Local models",
+  "settings.cmf.modelsHelp": "Each row is one model the gateway runs (its own cortiq serve on its own port) and registers in the pool. Add as many as you have .cmf files and free ports.",
+  "settings.cmf.rowHint": "id · .cmf file · port · threads · GPU. Changes apply on restart; deleting a row stops that server.",
+  "settings.cmf.addServer": "+ Add local model",
   "settings.cmf.checkPort": "Check port",
   "settings.cmf.portFree": "port is free",
   "settings.cmf.portBusy": "port is in use",

web/js/i18n/ru.js

@@ -128,6 +128,20 @@ export default {
   "models.form.secretMissing": "не задан",
   "models.form.secretPlaceholder": "задать или заменить ключ (только запись)",
   "models.deleteConfirm": "Удалить модель \"{id}\"?",
+  "models.form.idOrModel": "Укажите id или имя модели",
+  "models.form.apiKey": "API-ключ",
+  "models.form.apiKeyPlaceholder": "вставьте API-ключ",
+  "models.form.apiKeyNotNeeded": "не нужен (локальный сервер)",
+  "models.form.apiKeyHint": "Хранится безопасно на шлюзе; больше не показывается.",
+  "models.form.keyStored": "Ключ сохранён — оставьте пустым, чтобы не менять, или вставьте новый.",
+  "models.form.keyFromEnv": "Используется ключ из переменной окружения.",
+  "models.form.testKey": "Проверить и загрузить модели",
+  "models.form.testing": "проверка…",
+  "models.form.foundModels": "загружено моделей: {n}",
+  "models.form.modelPlaceholder": "введите для поиска…",
+  "models.form.modelHint": "Нажмите «Проверить и загрузить модели», чтобы подтянуть список по ключу, затем выберите.",
+  "models.managed": "управляемая",
+  "models.managedHint": "Предоставляется CMF-сервером (Настройки → Локальные модели). Настраивается там.",
 
   // routing
   "routing.title": "Роутинг",
@@ -241,6 +255,11 @@ export default {
   "settings.cmf.threads": "Рабочие потоки",
   "settings.cmf.gpu": "Использовать GPU (Metal / wgpu)",
   "settings.cmf.speedNote": "Потоки распараллеливают декод-матвеки (~×3; 0 = по умолчанию рантайма). GPU-оффлоад помогает в основном на prefill длинных промптов — декод упирается в пропускную способность памяти, поэтому на Apple Silicon почти нейтрален.",
+  "settings.cmf.pick": "выберите модель",
+  "settings.cmf.models": "Локальные модели",
+  "settings.cmf.modelsHelp": "Каждая строка — отдельная модель: шлюз поднимает свой cortiq serve на своём порту и регистрирует её в пуле. Добавляйте столько, сколько есть .cmf-файлов и свободных портов.",
+  "settings.cmf.rowHint": "id · файл .cmf · порт · потоки · GPU. Изменения применяются после перезапуска; удаление строки останавливает сервер.",
+  "settings.cmf.addServer": "+ Добавить модель",
   "settings.cmf.checkPort": "Проверить порт",
   "settings.cmf.portFree": "порт свободен",
   "settings.cmf.portBusy": "порт занят",

web/js/ui.js

@@ -25,7 +25,9 @@ export function clear(node) {
 
 export function mount(node, ...children) {
   clear(node);
-  for (const c of children.flat()) if (c != null && c !== false) node.appendChild(c);
+  for (const c of children.flat())
+    if (c != null && c !== false)
+      node.appendChild(typeof c === "object" ? c : document.createTextNode(String(c)));
   return node;
 }
 

web/js/views/models.js

@@ -16,52 +16,142 @@ function keyBadge(src) {
   return h("span", { class: "badge " + (map[src] ?? "") }, src);
 }
 
+// Verified per-provider defaults (base URL, key env, whether a key is needed).
+const PROVIDER_DEFAULTS = {
+  openai:     { base: "https://api.openai.com/v1",    keyEnv: "OPENAI_API_KEY",     needsKey: true,  tier: "mid",       caps: ["tools", "vision"] },
+  anthropic:  { base: "https://api.anthropic.com",    keyEnv: "ANTHROPIC_API_KEY",  needsKey: true,  tier: "expensive", caps: ["tools", "vision"] },
+  openrouter: { base: "https://openrouter.ai/api/v1", keyEnv: "OPENROUTER_API_KEY", needsKey: true,  tier: "mid",       caps: ["tools", "vision"] },
+  lmstudio:   { base: "http://localhost:1234/v1",     keyEnv: "",                   needsKey: false, tier: "local",     caps: ["tools", "vision"] },
+  ollama:     { base: "http://localhost:11434/v1",    keyEnv: "",                   needsKey: false, tier: "local",     caps: ["tools"] },
+  http:       { base: "",                              keyEnv: "",                   needsKey: false, tier: "cheap",     caps: ["tools"] },
+};
+
+// Derive a clean model id from a model name (last path segment, slugified).
+// e.g. "qwen/qwen3.7-max" → "qwen3-7-max".
+function slugId(name) {
+  const base = (name || "").split("/").pop() || "";
+  return base.toLowerCase().replace(/[^a-z0-9]+/g, "-").replace(/^-+|-+$/g, "");
+}
+
 function modelForm(meta, existing) {
-  const m = existing || { provider: "openai", kind: "chat", cost_tier: "cheap", caps: [], price_in: 0, price_out: 0 };
-  const idIn = h("input", { value: m.id || "", placeholder: "local-qwen", disabled: existing ? true : null });
+  const m = existing || { provider: "openai", kind: "chat", cost_tier: "mid", caps: ["tools"], price_in: 0, price_out: 0 };
+  const idIn = h("input", { value: m.id || "", placeholder: "my-model", disabled: existing ? true : null });
   const providerSel = h("select", {}, ...(meta.providers || ["openai"]).map((p) => opt(p, p, p === m.provider)));
-  const baseUrlIn = h("input", { value: m.base_url || "", placeholder: "http://localhost:8000/v1" });
-  const modelIn = h("input", { value: m.model || "", placeholder: "qwen2.5-7b-instruct" });
+  const baseUrlIn = h("input", { value: m.base_url || "", placeholder: "https://api.openai.com/v1" });
+
+  // API key — typed directly, stored securely as a secret under a provider env name.
+  const keyIn = h("input", { type: "password", placeholder: t("models.form.apiKeyPlaceholder"), autocomplete: "new-password" });
+  const testBtn = h("button", { class: "btn small", type: "button" }, t("models.form.testKey"));
+  const keyStatus = h("span", { class: "small", style: "margin-left:8px" });
+
+  // Model — below the key (some providers list models from the key); searchable datalist.
+  const dlId = "model-opts-" + (m.id || "new");
+  const dl = h("datalist", { id: dlId });
+  if (m.model) dl.appendChild(h("option", { value: m.model }));
+  const modelIn = h("input", { value: m.model || "", placeholder: t("models.form.modelPlaceholder"), list: dlId, autocomplete: "off" });
+
   const kindSel = h("select", {}, ...(meta.kinds || ["chat"]).map((k) => opt(k, k, k === m.kind)));
   const tierSel = h("select", {}, ...(meta.cost_tiers || ["cheap"]).map((c) => opt(c, c, c === m.cost_tier)));
   const priceInIn = h("input", { type: "number", step: "0.01", value: m.price_in ?? 0 });
   const priceOutIn = h("input", { type: "number", step: "0.01", value: m.price_out ?? 0 });
-  const keyEnvIn = h("input", { value: m.api_key_env || "", placeholder: "OPENAI_API_KEY" });
-  const secretIn = h("input", { type: "password", placeholder: t("models.form.secretPlaceholder") });
   const capInputs = (meta.caps || ["tools", "vision"]).map((c) => {
     const cb = h("input", { type: "checkbox", checked: (m.caps || []).includes(c) ? true : null });
     return { c, cb };
   });
 
+  const envFor = () =>
+    (existing && existing.api_key_env) ||
+    (PROVIDER_DEFAULTS[providerSel.value] || {}).keyEnv ||
+    providerSel.value.toUpperCase().replace(/[^A-Z0-9]/g, "_") + "_API_KEY";
+
+  // Fill in a provider's verified defaults when it is selected.
+  function applyDefaults() {
+    const d = PROVIDER_DEFAULTS[providerSel.value];
+    if (!d) return;
+    baseUrlIn.value = d.base;
+    tierSel.value = d.tier;
+    capInputs.forEach(({ c, cb }) => { cb.checked = d.caps.includes(c); });
+    keyIn.placeholder = d.needsKey ? t("models.form.apiKeyPlaceholder") : t("models.form.apiKeyNotNeeded");
+    mount(keyStatus, "");
+  }
+  providerSel.addEventListener("change", applyDefaults);
+  if (!existing) applyDefaults();
+
+  // Auto-fill the id from the model name (until the user edits id by hand).
+  if (!existing) {
+    modelIn.addEventListener("input", () => {
+      if (!idIn.value || idIn._auto) {
+        idIn.value = slugId(modelIn.value);
+        idIn._auto = true;
+      }
+    });
+    idIn.addEventListener("input", () => { idIn._auto = false; });
+  }
+
+  async function testKey() {
+    if (!baseUrlIn.value.trim()) { mount(keyStatus, h("span", { style: "color:var(--bad)" }, t("models.form.baseUrl") + "?")); return; }
+    testBtn.disabled = true;
+    mount(keyStatus, t("models.form.testing"));
+    try {
+      const r = await api.providerModels({
+        provider: providerSel.value,
+        base_url: baseUrlIn.value.trim(),
+        api_key: keyIn.value.trim() || null,
+        api_key_env: envFor(),
+      });
+      if (r.ok) {
+        dl.replaceChildren(...(r.models || []).map((mm) => h("option", { value: mm })));
+        mount(keyStatus, h("span", { style: "color:var(--good)" }, "✓ " + t("models.form.foundModels", { n: r.count })));
+        modelIn.focus();
+      } else {
+        mount(keyStatus, h("span", { style: "color:var(--bad)" }, "✗ " + (r.error || t("common.error"))));
+      }
+    } catch (e) {
+      mount(keyStatus, h("span", { style: "color:var(--bad)" }, "✗ " + String(e.message || e)));
+    }
+    testBtn.disabled = false;
+  }
+  testBtn.addEventListener("click", testKey);
+
+  const keyHint =
+    existing && existing.key_source === "store" ? t("models.form.keyStored")
+    : existing && existing.key_source === "env" ? t("models.form.keyFromEnv")
+    : t("models.form.apiKeyHint");
+
   const node = h(
     "div",
     {},
     h("div", { class: "row" }, field(t("models.form.id"), idIn, existing ? null : t("models.form.idHint")), field(t("models.form.provider"), providerSel)),
     field(t("models.form.baseUrl"), baseUrlIn),
-    field(t("models.form.model"), modelIn),
+    field(t("models.form.apiKey"), h("div", { class: "flex wrap", style: "gap:8px;align-items:center" }, keyIn, testBtn, keyStatus), keyHint),
+    field(t("models.form.model"), modelIn, t("models.form.modelHint")),
+    dl,
     h("div", { class: "row" }, field(t("models.form.kind"), kindSel), field(t("models.form.costTier"), tierSel)),
     h("div", { class: "row" }, field(t("models.form.priceIn"), priceInIn), field(t("models.form.priceOut"), priceOutIn)),
-    field(t("models.form.caps"), h("div", { class: "flex wrap" }, ...capInputs.map(({ c, cb }) => h("label", { class: "check" }, cb, c)))),
-    field(t("models.form.apiKeyEnv"), keyEnvIn, t("models.form.apiKeyEnvHint")),
-    field(t("models.form.secret"), secretIn)
+    field(t("models.form.caps"), h("div", { class: "flex wrap" }, ...capInputs.map(({ c, cb }) => h("label", { class: "check" }, cb, c))))
   );
 
-  const getValue = () => ({
-    model: {
-      id: existing ? m.id : idIn.value.trim(),
-      provider: providerSel.value,
-      base_url: baseUrlIn.value.trim(),
-      model: modelIn.value.trim(),
-      kind: kindSel.value,
-      cost_tier: tierSel.value,
-      price_in: parseFloat(priceInIn.value) || 0,
-      price_out: parseFloat(priceOutIn.value) || 0,
-      api_key_env: keyEnvIn.value.trim() || null,
-      caps: capInputs.filter(({ cb }) => cb.checked).map(({ c }) => c),
-    },
-    secret: secretIn.value,
-    keyEnv: keyEnvIn.value.trim(),
-  });
+  const getValue = () => {
+    const typedKey = keyIn.value.trim();
+    const hasKey = !!typedKey || !!(existing && existing.api_key_env);
+    const keyEnv = envFor();
+    return {
+      model: {
+        id: existing ? m.id : idIn.value.trim(),
+        provider: providerSel.value,
+        base_url: baseUrlIn.value.trim(),
+        model: modelIn.value.trim(),
+        kind: kindSel.value,
+        cost_tier: tierSel.value,
+        price_in: parseFloat(priceInIn.value) || 0,
+        price_out: parseFloat(priceOutIn.value) || 0,
+        api_key_env: hasKey ? keyEnv : null,
+        caps: capInputs.filter(({ cb }) => cb.checked).map(({ c }) => c),
+      },
+      secret: typedKey,
+      keyEnv,
+    };
+  };
 
   return { node, getValue };
 }
@@ -70,12 +160,14 @@ async function openModal(meta, existing, reload) {
   const { node, getValue } = modelForm(meta, existing);
   modal(existing ? t("models.form.editTitle") : t("models.form.addTitle"), node, async () => {
     const { model, secret, keyEnv } = getValue();
+    // Forgot the id? Derive it from the model name so saving never errors on a
+    // blank id.
+    if (!model.id) model.id = slugId(model.model);
     if (!model.id) {
-      toast(t("models.form.id") + "?", "bad");
+      toast(t("models.form.idOrModel"), "bad");
       return false;
     }
-    // strip null api_key_env so serde keeps it optional
-    if (!model.api_key_env) delete model.api_key_env;
+    if (!model.api_key_env) delete model.api_key_env; // keep serde field optional
     try {
       if (existing) await api.updateModel(existing.id, model);
       else await api.createModel(model);
@@ -168,7 +260,8 @@ function row(m, meta, reload) {
   return h(
     "tr",
     {},
-    h("td", { class: "mono" }, m.id),
+    h("td", { class: "mono" }, m.id,
+      m.managed ? h("span", { class: "badge", style: "margin-left:6px", title: t("models.managedHint") }, t("models.managed")) : null),
     h("td", {}, m.provider),
     h("td", { class: "mono" }, m.model),
     h("td", {}, h("span", { class: "badge " + (m.cost_tier || "") }, m.cost_tier || "—")),
@@ -182,7 +275,7 @@ function row(m, meta, reload) {
         "div",
         { class: "flex", style: "justify-content:flex-end" },
         probeBtn,
-        h("button", { class: "btn sm ghost", onClick: () => openModal(meta, m, reload) }, t("common.edit")),
+        m.managed ? null : h("button", { class: "btn sm ghost", onClick: () => openModal(meta, m, reload) }, t("common.edit")),
         h(
           "button",
           {
@@ -192,7 +285,7 @@ function row(m, meta, reload) {
               try {
                 await api.deleteModel(m.id);
                 toast(t("toast.deleted"), "good");
-                reload();
+                await reload();
               } catch (e) {
                 toast(String(e.message || e), "bad");
               }

web/js/views/settings.js

@@ -207,11 +207,63 @@ export async function renderSettings() {
   const cmfManage = check(t("settings.cmf.manage"), s.cmf?.manage_server, t("settings.cmf.manageHelp"));
   const cmfAutoInstall = check(t("settings.cmf.autoInstall"), s.cmf?.auto_install, t("settings.cmf.autoInstallHelp"));
   const cmfAutoUpdate = check(t("settings.cmf.autoUpdate"), s.cmf?.auto_update, t("settings.cmf.autoUpdateHelp"));
-  const cmfModel = h("input", { value: s.cmf?.local_model || "", placeholder: "models/my-model.cmf" });
-  const cmfPort = h("input", { type: "number", value: s.cmf?.local_port ?? 8081 });
-  const cmfThreads = h("input", { type: "number", min: 0, value: s.cmf?.threads ?? 8 });
-  const cmfGpu = check(t("settings.cmf.gpu"), s.cmf?.gpu, t("settings.cmf.gpuHelp"));
-  const cmfModelIdVal = s.cmf?.model_id || "cmf-local"; // auto — no manual "model id" field
+  // ── managed local models: one supervised `cortiq serve` per row ──
+  const serverRows = [];
+  const serversWrap = h("div", {});
+  const legacyServers = s.cmf?.local_model
+    ? [{ id: s.cmf.model_id || "cmf-local", model: s.cmf.local_model, port: s.cmf.local_port ?? 8081, threads: s.cmf.threads ?? 8, gpu: !!s.cmf.gpu }]
+    : [];
+  const initServers = (s.cmf?.servers && s.cmf.servers.length) ? s.cmf.servers : legacyServers;
+  // available .cmf files under models_dir → offer as a dropdown, not a typed path
+  const cmfFiles = ((await api.cmfFiles().catch(() => ({ files: [] }))).files) || [];
+  const fileLabel = (f) => f.name + (f.size ? ` (${(f.size / 1073741824).toFixed(f.size >= 1073741824 ? 1 : 2)} GB)` : f.is_dir ? " (dir)" : "");
+  function autoId(path) {
+    const base = (path || "").split("/").pop().replace(/\.cmf$/i, "");
+    return base ? "cmf-" + base.replace(/[^a-zA-Z0-9_-]/g, "-") : "";
+  }
+  function makeServerRow(sv) {
+    sv = sv || { id: "", model: "", port: 8090, threads: 8, gpu: false };
+    const idIn = h("input", { value: sv.id || "", placeholder: "cmf-id", style: "width:130px" });
+    // pick from existing .cmf files rather than typing a path
+    const modelSel = h("select", { style: "flex:2;min-width:150px" });
+    const seen = new Set();
+    modelSel.appendChild(h("option", { value: "" }, "— " + t("settings.cmf.pick") + " —"));
+    cmfFiles.forEach((f) => { modelSel.appendChild(h("option", { value: f.path }, fileLabel(f))); seen.add(f.path); });
+    if (sv.model && !seen.has(sv.model)) modelSel.appendChild(h("option", { value: sv.model }, sv.model));
+    modelSel.value = sv.model || "";
+    const portIn = h("input", { type: "number", value: sv.port ?? 8090, style: "width:82px" });
+    const threadsIn = h("input", { type: "number", min: 0, value: sv.threads ?? 8, style: "width:60px", title: t("settings.cmf.threadsHelp") });
+    const gpuIn = h("input", { type: "checkbox", checked: sv.gpu ? true : null, title: t("settings.cmf.gpuHelp") });
+    const checkBtn = h("button", { class: "btn small", type: "button" }, t("settings.cmf.checkPort"));
+    const removeBtn = h("button", { class: "btn small danger", type: "button", title: t("common.delete") }, "✕");
+    const st = h("span", { class: "small" });
+    modelSel.addEventListener("change", () => { if (!idIn.value || idIn._auto) { idIn.value = autoId(modelSel.value); idIn._auto = true; } });
+    idIn.addEventListener("input", () => { idIn._auto = false; });
+    checkBtn.addEventListener("click", async () => {
+      const p = parseInt(portIn.value, 10); if (!p) return;
+      checkBtn.disabled = true; mount(st, t("status.checking"));
+      try {
+        const r = await api.cmfPortCheck(p);
+        if (r.available) mount(st, h("span", { style: "color:var(--good)" }, "✓ " + t("settings.cmf.portFree")));
+        else {
+          const kids = [h("span", { style: "color:var(--bad)" }, "✗ " + t("settings.cmf.portBusy"))];
+          if (r.suggested) { const b = h("button", { class: "btn small", type: "button" }, t("settings.cmf.useSuggested", { port: r.suggested })); b.addEventListener("click", () => { portIn.value = r.suggested; mount(st, ""); }); kids.push(b); }
+          mount(st, h("span", {}, ...kids));
+        }
+      } catch (e) { mount(st, String(e.message || e)); }
+      checkBtn.disabled = false;
+    });
+    const row = h("div", { class: "flex wrap", style: "gap:6px;align-items:center;margin:6px 0" },
+      idIn, modelSel, portIn, checkBtn, threadsIn, h("label", { class: "flex", style: "gap:4px" }, gpuIn, "GPU"), removeBtn, st);
+    const entry = { node: row, read: () => ({ id: idIn.value.trim() || autoId(modelSel.value), model: modelSel.value.trim(), port: parseInt(portIn.value) || 8090, threads: parseInt(threadsIn.value) || 0, gpu: gpuIn.checked }) };
+    removeBtn.addEventListener("click", () => { const i = serverRows.indexOf(entry); if (i >= 0) serverRows.splice(i, 1); row.remove(); });
+    serverRows.push(entry);
+    serversWrap.appendChild(row);
+    return entry;
+  }
+  initServers.forEach((sv) => makeServerRow(sv));
+  const addServerBtn = h("button", { class: "btn small", type: "button" }, t("settings.cmf.addServer"));
+  addServerBtn.addEventListener("click", () => makeServerRow());
   // "Install cortiq" — the CLI that RUNS the .cmf format. Must be present before
   // a local model server can start; this is step 1 for a new user.
   const cmfStatusEl = h("span", { class: "muted" }, "…");
@@ -228,14 +280,17 @@ export async function renderSettings() {
           ? h("span", {}, h("span", { class: "badge ok" }, "✓"), " cortiq " + (st.version || ""))
           : h("span", {}, h("span", { class: "badge bad" }, "×"), " " + t("settings.cmf.notInstalled"))
       );
-      // reflect the managed server state under the "run locally" toggle
-      if (st.manage_server && st.running) {
-        mount(cmfServingEl, h("span", { style: "color:var(--good)" },
-          "▶ " + t("settings.cmf.serving", { model: st.model_id || "", port: st.local_port }) + (st.healthy ? "" : " …")));
-      } else if (st.last_error) {
-        mount(cmfServingEl, h("span", { style: "color:var(--bad)" }, "✗ " + st.last_error));
-      } else {
+      // per-server serving indicators
+      const servers = st.servers || [];
+      if (!servers.length) {
         mount(cmfServingEl, "");
+      } else {
+        mount(cmfServingEl, h("div", {}, ...servers.map((sv) => {
+          if (sv.last_error) return h("div", { style: "color:var(--bad)" }, "✗ " + sv.id + ": " + sv.last_error);
+          if (sv.running) return h("div", { style: "color:var(--good)" },
+            "▶ " + t("settings.cmf.serving", { model: sv.id, port: sv.port }) + (sv.healthy ? "" : " …"));
+          return h("div", { class: "muted" }, "• " + sv.id + " :" + sv.port);
+        })));
       }
     } catch (_) {
       mount(cmfStatusEl, "—");
@@ -251,7 +306,6 @@ export async function renderSettings() {
         await new Promise((r) => setTimeout(r, 3000));
         const st = await api.cmfStatus();
         if (st.installed) { toast(t("settings.cmf.installedOk"), "good"); break; }
-        if (st.last_error) { toast(st.last_error, "bad"); break; }
       }
     } catch (e) {
       toast(String(e.message || e), "bad");
@@ -261,36 +315,6 @@ export async function renderSettings() {
   });
   refreshCmfStatus();
 
-  // Port availability check — let the user confirm the chosen port is free
-  // before enabling the managed server (the default 8081 often clashes).
-  const cmfPortStatus = h("span", { class: "small", style: "margin-left:8px" });
-  const cmfPortCheckBtn = h("button", { class: "btn small", type: "button" }, t("settings.cmf.checkPort"));
-  async function checkPort() {
-    const p = parseInt(cmfPort.value, 10);
-    if (!p) { mount(cmfPortStatus, ""); return; }
-    cmfPortCheckBtn.disabled = true;
-    mount(cmfPortStatus, t("status.checking"));
-    try {
-      const r = await api.cmfPortCheck(p);
-      if (r.available) {
-        mount(cmfPortStatus, h("span", { style: "color:var(--good)" }, "✓ " + t("settings.cmf.portFree")));
-      } else {
-        const kids = [h("span", { style: "color:var(--bad)" }, "✗ " + t("settings.cmf.portBusy"))];
-        if (r.suggested) {
-          const useBtn = h("button", { class: "btn small", type: "button", style: "margin-left:8px" },
-            t("settings.cmf.useSuggested", { port: r.suggested }));
-          useBtn.addEventListener("click", () => { cmfPort.value = r.suggested; checkPort(); });
-          kids.push(useBtn);
-        }
-        mount(cmfPortStatus, h("span", {}, ...kids));
-      }
-    } catch (e) {
-      mount(cmfPortStatus, String(e.message || e));
-    }
-    cmfPortCheckBtn.disabled = false;
-  }
-  cmfPortCheckBtn.addEventListener("click", checkPort);
-
   const saveBtn = h("button", { class: "btn primary" }, t("common.save"));
   saveBtn.addEventListener("click", async () => {
     saveBtn.disabled = true;
@@ -335,11 +359,9 @@ export async function renderSettings() {
         manage_server: cmfManage.cb.checked,
         auto_install: cmfAutoInstall.cb.checked,
         auto_update: cmfAutoUpdate.cb.checked,
-        local_model: cmfModel.value.trim(),
-        local_port: parseInt(cmfPort.value) || 8081,
-        model_id: cmfModelIdVal,
-        threads: parseInt(cmfThreads.value) || 0,
-        gpu: cmfGpu.cb.checked,
+        // the managed-models list is the source of truth; clear the legacy single
+        servers: serverRows.map((r) => r.read()).filter((sv) => sv.model && sv.id),
+        local_model: "",
       },
     };
     // serde: drop null optionals
@@ -477,24 +499,21 @@ export async function renderSettings() {
         ),
         h("div", { class: "row" }, cmfAutoInstall.node, cmfAutoUpdate.node),
         h("div", { class: "divider" }),
-        // Step 2 — add a model. Models are imported in the Models/Import tab; here
-        // you just point the local server at the .cmf file it produced.
-        h("div", { class: "field" }, h("span", {}, "2. " + t("settings.cmf.addModel"), " ", help(t("settings.cmf.addModelHelp"))),
+        // Step 2 — managed local models: one supervised cortiq serve per row, each
+        // on its own port. Add as many as you have .cmf files + free ports.
+        h("div", { class: "field" },
+          h("span", {}, "2. " + t("settings.cmf.models"), " ", help(t("settings.cmf.modelsHelp"))),
+          h("div", { class: "hint" }, t("settings.cmf.rowHint")),
           h("div", { class: "hint" }, t("settings.cmf.importNote"),
             " ", h("a", { href: "#/import" }, t("settings.cmf.importLink") + " ↗"))),
-        field(t("settings.cmf.model"), cmfModel, null, t("settings.cmf.modelHelp")),
-        h("div", { class: "divider" }),
-        // Step 3 — run it locally + performance.
-        cmfManage.node,
+        serversWrap,
+        addServerBtn,
         cmfServingEl,
-        h("div", { class: "row" },
-          field(t("settings.cmf.port"),
-            h("div", { class: "flex wrap" }, cmfPort, cmfPortCheckBtn, cmfPortStatus),
-            null, t("settings.cmf.portHelp")),
-          field(t("settings.cmf.threads"), cmfThreads, null, t("settings.cmf.threadsHelp"))),
-        cmfGpu.node,
-        cmfLocalOnly.node,
-        h("div", { class: "hint" }, t("settings.cmf.speedNote"))
+        h("div", { class: "hint" }, t("settings.cmf.speedNote")),
+        h("div", { class: "divider" }),
+        // Step 3 — how the gateway uses them.
+        cmfManage.node,
+        cmfLocalOnly.node
       )
     ),
     h(