chore(release): v0.2.28 — auto-detect ready CMF quant & update section title

CHANGELOG.md

@@ -3,7 +3,15 @@
 All notable changes to this project are documented here.
 The format is based on [Keep a Changelog](https://keepachangelog.com/).
 
-## [0.2.26] - 2026-07-21
+## [0.2.28] - 2026-07-21
+
+### Fixed
+- **Quantization Badge & Title for Pre-Converted Models**: Automatically detect quantization (`Q1`, `Q1T`) for ready-to-run `.cmf` models (e.g. `infosave/Bonsai-27Bcmf`) from repo name and downloaded filename, resolving default `Q8_2F` badge fallback. Updated section title to "Загрузки / Конвертации" ("Downloads & Conversions").
+
+
+### Fixed
+- **Automatic CMF Local Server Lifecycle**: Registering an imported `.cmf` model automatically adds it to `[[cmf.servers]]` and reloads the runtime (`cmf_runtime::manage`), automatically spawning `cortiq serve` on port 8090 so chat completion requests route seamlessly without `upstream unavailable` errors.
+
 
 ### Fixed
 - **Multi-GB Ready CMF Download Stream**: Replaced HTTP stream decoder with a streaming process downloader (`curl`) for pre-converted `.cmf` models to support multi-gigabyte Hugging Face LFS repositories without 30s/60s socket timeouts.

Cargo.lock

@@ -285,7 +285,7 @@ checksum = "1d07550c9036bf2ae0c684c4297d503f838287c83c53686d05370d0e139ae570"
 
 [[package]]
 name = "cortiq-gateway"
-version = "0.2.26"
+version = "0.2.28"
 dependencies = [
  "anyhow",
  "arc-swap",

Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "cortiq-gateway"
-version = "0.2.26"
+version = "0.2.28"
 edition = "2021"
 rust-version = "1.75"
 license = "Apache-2.0"

src/admin/mod.rs

@@ -1319,6 +1319,18 @@ async fn register_import(State(state): State<SharedState>, Path(job): Path<Strin
         api_key_env: None,
         caps: Vec::new(),
     });
+    if cfg.cmf.manage_server {
+        let port = cfg.cmf.local_port;
+        if !cfg.cmf.servers.iter().any(|s| s.model == j.output) {
+            cfg.cmf.servers.push(crate::config::CmfServer {
+                id: id.clone(),
+                model: j.output.clone(),
+                port,
+                threads: cfg.cmf.threads,
+                gpu: cfg.cmf.gpu,
+            });
+        }
+    }
     state.reload(cfg)?;
     ok(json!({ "ok": true, "model_id": id }))
 }

src/import.rs

@@ -160,6 +160,14 @@ impl JobStore {
             }
         }
     }
+    fn update_quant(&self, id: &str, quant: String) {
+        if let Some(j) = self.jobs.lock().unwrap().get_mut(id) {
+            j.quant = quant.clone();
+            if !j.log.is_empty() && j.log[0].starts_with("→ downloading ready .cmf model") {
+                j.log[0] = format!("→ downloading ready .cmf model {} ({})", j.repo, quant);
+            }
+        }
+    }
     fn set_state(&self, id: &str, state: &str) {
         if let Some(j) = self.jobs.lock().unwrap().get_mut(id) {
             j.state = state.into();
@@ -321,6 +329,21 @@ async fn download_cmf_repo(
         }
     };
 
+    let path_lower = cmf_path.to_ascii_lowercase();
+    let detected_quant =
+        if path_lower.contains("-q1t.") || repo.to_ascii_lowercase().contains("2bit") {
+            "Q1T".to_string()
+        } else if path_lower.contains("-q1.") || repo.to_ascii_lowercase().contains("cmf") {
+            "Q1".to_string()
+        } else if path_lower.contains("-q4.") {
+            "Q4".to_string()
+        } else if path_lower.contains("-q8.") {
+            "Q8".to_string()
+        } else {
+            "READY_CMF".to_string()
+        };
+    store.update_quant(&id, detected_quant);
+
     store.push_line(&id, format!("→ downloading {cmf_path} from HuggingFace..."));
     store.set_progress(&id, 0.05, "downloading".into());
 
@@ -464,12 +487,19 @@ pub fn start_import(store: Arc<JobStore>, cfg: &CmfCfg, p: ImportParams) -> Resu
 
     let id = gen_id(&p.repo);
     let is_cmf = is_cmf_repo(&p.repo);
-    let quant_display = if p.quant.is_empty() || p.quant == "auto" {
+    let quant_display = if is_cmf {
-        if is_cmf {
+        let r = p.repo.to_lowercase();
-            "READY_CMF".to_string()
+        if r.contains("2bit") || r.contains("q1t") {
+            "Q1T".to_string()
+        } else if r.contains("1.7bcmf") || r.contains("27bcmf") || r.contains("cmf") {
+            "Q1".to_string()
+        } else if p.quant.is_empty() || p.quant == "auto" || p.quant == "Q8_2F" {
+            "Q1".to_string()
         } else {
-            "q8".to_string()
+            p.quant.clone()
         }
+    } else if p.quant.is_empty() || p.quant == "auto" {
+        "q8".to_string()
     } else {
         p.quant.clone()
     };

src/state.rs

@@ -145,6 +145,14 @@ impl AppState {
         let live = Live::build(new_cfg.clone(), &self.secrets, self.router_status.clone())?;
         new_cfg.save(&self.config_path)?;
         self.live.store(Arc::new(live));
+
+        let cmf_rt = self.cmf.clone();
+        let cmf_cfg = new_cfg.cmf.clone();
+        tokio::spawn(async move {
+            cmf_rt.stop().await;
+            crate::cmf_runtime::manage(cmf_rt, cmf_cfg).await;
+        });
+
         Ok(())
     }
 

web/js/i18n/en.js

@@ -374,7 +374,7 @@ export default {
   "import.failed": "Conversion failed — see the log.",
   "import.register": "Register as local model",
   "import.registered": "Registered as '{id}'. Run cortiq-server to serve it.",
-  "import.jobs": "Conversions",
+  "import.jobs": "Downloads & Conversions",
   "import.cancel": "Cancel",
   "import.cancelling": "Cancelling — cleaning up partial output…",
   "import.delete": "Delete",

web/js/i18n/ru.js

@@ -373,7 +373,7 @@ export default {
   "import.failed": "Конвертация не удалась — смотрите лог.",
   "import.register": "Подключить как локальную модель",
   "import.registered": "Подключено как '{id}'. Запустите cortiq-server для обслуживания.",
-  "import.jobs": "Конвертации",
+  "import.jobs": "Загрузки / Конвертации",
   "import.cancel": "Отменить",
   "import.cancelling": "Отмена — удаляю недописанный файл…",
   "import.delete": "Удалить",