fix(settings): replacing a managed local model no longer breaks save

- put_settings now heals [routing] after the managed-servers list changes: a removed server whose port is taken over by a new one is treated as a replacement (old id → new id in default + every tier); truly vanished ids are stripped; an emptied default falls back to the first managed server / pool model. Previously the stale id failed validation and the save errored. - /admin/api/cmf/port now returns managed:true when the port is held by this gateway's own managed server; the Settings port check shows that as info ("freed on restart, replacing is fine") instead of a red "port busy".
2026-07-14 10:30:39 +03:00
20 changed files with 100 additions and 639 deletions
@@ -3,40 +3,8 @@
 All notable changes to this project are documented here.
 The format is based on [Keep a Changelog](https://keepachangelog.com/).

-## [0.2.30] - 2026-07-22
-
-### Added
- **Per-Model Generation & Reasoning Parameters**: Full support in Web UI and Gateway core for per-model generation defaults: Temperature, Top-P, Max Tokens, Think Budget (Reasoning mode), O(1) Constant-Memory Streaming Attention (`o1`), MTP (Multi-Token Prediction toggle `skip_mtp`), and default System Prompt.
-
-
-### Fixed
- **Duplicate Local Model Registration**: Fixed `duplicate managed model id` conflict in `register_import` by cleanly routing managed CMF models directly into `[[cmf.servers]]` with automatic free port allocation without pushing duplicate entries to `[[models]]`.
-
-
-### 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.
- **Ready CMF Quantization & UI Labels**: Set correct quantization badges (`Q1`, `Q1T`) for featured ready-to-run `.cmf` models and removed misleading "converting" log messages for direct downloads.
-
-
-### Fixed
- **Direct Ready CMF Download**: Importing pre-converted `.cmf` model repositories (e.g. `infosave/Bonsai-8B_2bit_cmf`) directly streams the ready `.cmf` file from Hugging Face instead of attempting a safetensors conversion without `config.json`.
-
-
-### Added
- **New Quantization Schemes**: Added support for `Q4_TILED` (q4t), `Q1T` (1.58-bit ternary), `Q1S` (1-bit sparse), `Q1P` (1-bit PTQ error diffusion), and `Q1` (pure binary) in converter backend and web admin UI.
- **Featured Ready-to-Run .cmf Models**: Added 1-tap download cards for pre-converted `.cmf` models (`infosave/Bonsai-1.7Bcmf`, `infosave/Bonsai-8B_2bit_cmf`, `infosave/Bonsai-27Bcmf`).
-
 ## [Unreleased]

-
 ### Added
 - **Docker Compose** quickstart (`docker-compose.yml` + `config/gateway.compose.toml`):
  gateway + a local Ollama model in one command. GHCR badge in the READMEs.
@@ -285,7 +285,7 @@ checksum = "1d07550c9036bf2ae0c684c4297d503f838287c83c53686d05370d0e139ae570"

 [[package]]
 name = "cortiq-gateway"
-version = "0.2.30"
+version = "0.2.16"
 dependencies = [
 "anyhow",
 "arc-swap",
@@ -1,6 +1,6 @@
 [package]
 name = "cortiq-gateway"
-version = "0.2.30"
+version = "0.2.16"
 edition = "2021"
 rust-version = "1.75"
 license = "Apache-2.0"
@@ -905,12 +905,75 @@ async fn put_settings(State(state): State<SharedState>, Json(b): Json<SettingsBo
        {
            needs_restart = true;
        }
+        let old_servers = cfg.cmf.effective_servers();
        cfg.cmf = v;
+        // Replacing or renaming a managed model must not brick the save: routing
+        // may still reference the old id. Map a vanished id to its replacement
+        // (the new server on the same port), strip ids that are truly gone, and
+        // repair the default so validate() passes.
+        heal_routing_after_cmf_change(&mut cfg, &old_servers);
    }
    state.reload(cfg)?;
    ok(json!({ "ok": true, "needs_restart": needs_restart }))
 }

+/// After the managed-servers list changed, rewrite [routing] so it only
+/// references ids that still exist. A removed server whose port is now held by
+/// a NEW server is treated as a replacement (old id → new id); other vanished
+/// ids are stripped. An emptied default falls back to the first managed server,
+/// then the first pool model.
+fn heal_routing_after_cmf_change(cfg: &mut Config, old_servers: &[crate::config::CmfServer]) {
+    let servers = cfg.cmf.effective_servers();
+    let known: std::collections::HashSet<String> = cfg
+        .models
+        .iter()
+        .map(|m| m.id.clone())
+        .chain(servers.iter().map(|s| s.id.clone()))
+        .collect();
+    let new_by_port: HashMap<u16, String> =
+        servers.iter().map(|s| (s.port, s.id.clone())).collect();
+    let mut rename: HashMap<String, String> = HashMap::new();
+    for old in old_servers {
+        if !known.contains(&old.id) {
+            if let Some(new_id) = new_by_port.get(&old.port) {
+                rename.insert(old.id.clone(), new_id.clone());
+            }
+        }
+    }
+    let fix = |id: &str| -> Option<String> {
+        if known.contains(id) {
+            Some(id.to_string())
+        } else {
+            rename.get(id).cloned()
+        }
+    };
+    if !cfg.routing.default.is_empty() {
+        cfg.routing.default = fix(&cfg.routing.default).unwrap_or_default();
+    }
+    if cfg.routing.default.is_empty() {
+        cfg.routing.default = servers
+            .first()
+            .map(|s| s.id.clone())
+            .or_else(|| cfg.models.first().map(|m| m.id.clone()))
+            .unwrap_or_default();
+    }
+    for tt in cfg.routing.tiers.values_mut() {
+        let list = match tt {
+            TierTargets::List(v) => v.clone(),
+            TierTargets::One(s) => vec![s.clone()],
+        };
+        let mut healed: Vec<String> = Vec::new();
+        for id in &list {
+            if let Some(new_id) = fix(id) {
+                if !healed.contains(&new_id) {
+                    healed.push(new_id);
+                }
+            }
+        }
+        *tt = TierTargets::List(healed);
+    }
+}
+
 // ───────────────────────────── cmf runtime ─────────────────────────────────
 /// Status of the `cortiq` CLI (the CMF format runtime): is it installed, which
 /// version, and whether a managed server is running. Drives the "Install cortiq"
@@ -1028,6 +1091,9 @@ async fn cmf_port_check(State(state): State<SharedState>, Query(q): Query<PortQu
    ok(json!({
        "port": port,
        "available": available,
+        // true = held by this gateway's own managed server (a replaced/edited
+        // row frees it on restart) — the UI shows this as info, not an error
+        "managed": running_here,
        "detail": detail,
        "suggested": suggested,
    }))
@@ -1304,61 +1370,21 @@ async fn register_import(State(state): State<SharedState>, Path(job): Path<Strin
        .unwrap_or_else(|| "cmf-local".into());
    let id = format!("cmf-{base}");
    let mut cfg = current_cfg(&state);
-
-    let is_in_models = cfg.models.iter().any(|m| m.id == id);
-    let is_in_servers = cfg
-        .cmf
-        .servers
-        .iter()
-        .any(|s| s.id == id || s.model == j.output);
-
-    if is_in_models || is_in_servers {
-        return Err(ApiError::bad(format!("model '{id}' is already registered")));
-    }
-
-    if cfg.cmf.manage_server {
-        let host = if cfg.cmf.local_host.trim().is_empty() {
-            "127.0.0.1"
-        } else {
-            &cfg.cmf.local_host
-        };
-        let base_port = cfg.cmf.servers.iter().map(|s| s.port).max().unwrap_or(8089);
-        let port = next_free_port(host, base_port).unwrap_or_else(|| base_port + 1);
-        cfg.cmf.servers.push(crate::config::CmfServer {
-            id: id.clone(),
-            model: j.output.clone(),
-            port,
-            threads: cfg.cmf.threads,
-            gpu: cfg.cmf.gpu,
-            temperature: None,
-            top_p: None,
-            max_tokens: None,
-            think_budget: None,
-            system_prompt: None,
-            o1: None,
-            skip_mtp: false,
-        });
-    } else {
-        cfg.models.push(crate::config::ModelCfg {
-            id: id.clone(),
-            provider: "openai".into(),
-            base_url: cfg.cmf.cortiq_server_url.clone(),
-            model: base,
-            cost_tier: "local".into(),
-            price_in: 0.0,
-            price_out: 0.0,
-            kind: "chat".into(),
-            api_key_env: None,
-            caps: Vec::new(),
-            temperature: None,
-            top_p: None,
-            max_tokens: None,
-            think_budget: None,
-            system_prompt: None,
-            o1: None,
-            skip_mtp: false,
-        });
+    if cfg.models.iter().any(|m| m.id == id) {
+        return Err(ApiError::bad(format!("model '{id}' already registered")));
    }
+    cfg.models.push(crate::config::ModelCfg {
+        id: id.clone(),
+        provider: "openai".into(),
+        base_url: cfg.cmf.cortiq_server_url.clone(),
+        model: base,
+        cost_tier: "local".into(),
+        price_in: 0.0,
+        price_out: 0.0,
+        kind: "chat".into(),
+        api_key_env: None,
+        caps: Vec::new(),
+    });
    state.reload(cfg)?;
    ok(json!({ "ok": true, "model_id": id }))
 }
@@ -290,17 +290,11 @@ fn spawn_serve(server: &CmfServer, cfg: &CmfCfg) -> Result<Child, 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 server.gpu {
        cmd.env("CMF_GPU", "1");
    }
-    if let Some(o1) = &server.o1 {
-        if !o1.trim().is_empty() && o1 != "off" {
-            cmd.arg("--o1").arg(o1);
-        }
-    }
-    if server.skip_mtp {
-        cmd.arg("--skip-mtp");
-    }
    cmd.stdout(Stdio::null())
        .stderr(Stdio::null())
        .kill_on_drop(true)
@@ -83,27 +83,6 @@ pub struct CmfServer {
    /// Offload matvecs to the GPU (CMF_GPU=1).
    #[serde(default)]
    pub gpu: bool,
-    /// Default generation temperature (0.0 .. 2.0).
-    #[serde(default, skip_serializing_if = "Option::is_none")]
-    pub temperature: Option<f32>,
-    /// Default nucleus sampling threshold (0.0 .. 1.0).
-    #[serde(default, skip_serializing_if = "Option::is_none")]
-    pub top_p: Option<f32>,
-    /// Default maximum completion tokens.
-    #[serde(default, skip_serializing_if = "Option::is_none")]
-    pub max_tokens: Option<u32>,
-    /// Reasoning / thinking token budget.
-    #[serde(default, skip_serializing_if = "Option::is_none")]
-    pub think_budget: Option<u32>,
-    /// Default system prompt prepended if request lacks one.
-    #[serde(default, skip_serializing_if = "Option::is_none")]
-    pub system_prompt: Option<String>,
-    /// O(1) constant-memory streaming attention hint (all, deep, custom, off).
-    #[serde(default, skip_serializing_if = "Option::is_none")]
-    pub o1: Option<String>,
-    /// Skip Multi-Token Prediction (MTP) heads.
-    #[serde(default)]
-    pub skip_mtp: bool,
 }

 /// CMF-format model factory: import a HuggingFace model, convert it to a
@@ -193,13 +172,6 @@ impl CmfCfg {
                port: self.local_port,
                threads: self.threads,
                gpu: self.gpu,
-                temperature: None,
-                top_p: None,
-                max_tokens: None,
-                think_budget: None,
-                system_prompt: None,
-                o1: None,
-                skip_mtp: false,
            }];
        }
        Vec::new()
@@ -334,27 +306,6 @@ pub struct ModelCfg {
    pub api_key_env: Option<String>,
    #[serde(default, skip_serializing_if = "Vec::is_empty")]
    pub caps: Vec<String>,
-    /// Default generation temperature (0.0 .. 2.0).
-    #[serde(default, skip_serializing_if = "Option::is_none")]
-    pub temperature: Option<f32>,
-    /// Default nucleus sampling threshold (0.0 .. 1.0).
-    #[serde(default, skip_serializing_if = "Option::is_none")]
-    pub top_p: Option<f32>,
-    /// Default maximum completion tokens.
-    #[serde(default, skip_serializing_if = "Option::is_none")]
-    pub max_tokens: Option<u32>,
-    /// Reasoning / thinking token budget.
-    #[serde(default, skip_serializing_if = "Option::is_none")]
-    pub think_budget: Option<u32>,
-    /// Default system prompt prepended if request lacks one.
-    #[serde(default, skip_serializing_if = "Option::is_none")]
-    pub system_prompt: Option<String>,
-    /// O(1) constant-memory streaming attention hint (all, deep, custom, off).
-    #[serde(default, skip_serializing_if = "Option::is_none")]
-    pub o1: Option<String>,
-    /// Skip Multi-Token Prediction (MTP) heads.
-    #[serde(default)]
-    pub skip_mtp: bool,
 }
 fn default_kind() -> String {
    "chat".into()
@@ -160,14 +160,6 @@ 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();
@@ -268,166 +260,14 @@ fn sanitize(s: &str) -> String {
 /// Map the UI quant label to the native `cortiq` quant flag.
 fn map_quant(q: &str) -> &'static str {
    match q.to_ascii_uppercase().as_str() {
-        s if s.starts_with("Q4T") || s == "Q4_TILED" => "q4t",
        s if s.starts_with("Q4") => "q4",
-        "Q8_2F" | "Q82F" => "q8_2f",
+        "Q8_2F" => "q8_2f",
        "F16" | "FP16" => "f16",
        "VBIT" => "vbit",
-        "Q1" => "q1",
-        "Q1P" | "Q1_PTQ" => "q1p",
-        "Q1S" | "Q1_MASK" => "q1s",
-        "Q1T" | "Q1_TERNARY" => "q1t",
        _ => "q8",
    }
 }

-fn is_cmf_repo(repo: &str) -> bool {
-    let lower = repo.to_ascii_lowercase();
-    lower.contains("cmf") || lower.ends_with(".cmf")
-}
-
-async fn download_cmf_repo(
-    repo: String,
-    output_abs: String,
-    hf_token: Option<String>,
-    store: Arc<JobStore>,
-    id: String,
-    cancel: Arc<Notify>,
-) {
-    store.set_progress(&id, 0.0, "listing files".into());
-
-    let tree_url = format!("https://huggingface.co/api/models/{repo}/tree/main?recursive=true");
-    let client = reqwest::Client::new();
-    let mut req = client.get(&tree_url).header("User-Agent", "cortiq-gateway");
-    if let Some(t) = &hf_token {
-        req = req.bearer_auth(t);
-    }
-
-    let mut cmf_rel_path = None;
-    if let Ok(resp) = req.send().await {
-        if resp.status().is_success() {
-            if let Ok(json) = resp.json::<serde_json::Value>().await {
-                if let Some(arr) = json.as_array() {
-                    for item in arr {
-                        if let Some(path) = item.get("path").and_then(|p| p.as_str()) {
-                            if path.to_ascii_lowercase().ends_with(".cmf") {
-                                cmf_rel_path = Some(path.to_string());
-                                break;
-                            }
-                        }
-                    }
-                }
-            }
-        }
-    }
-
-    let cmf_path = match cmf_rel_path {
-        Some(p) => p,
-        None => {
-            let repo_name = repo.split('/').last().unwrap_or(&repo);
-            format!("{repo_name}.cmf")
-        }
-    };
-
-    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());
-
-    let download_url = format!("https://huggingface.co/{repo}/resolve/main/{cmf_path}");
-
-    let mut cmd = tokio::process::Command::new("curl");
-    cmd.arg("-f").arg("-L").arg("-#").arg("-o").arg(&output_abs);
-
-    if let Some(t) = &hf_token {
-        cmd.arg("-H").arg(format!("Authorization: Bearer {t}"));
-    }
-
-    cmd.arg(&download_url);
-    cmd.stderr(std::process::Stdio::piped());
-    cmd.stdout(std::process::Stdio::null());
-
-    let mut child = match cmd.spawn() {
-        Ok(c) => c,
-        Err(e) => {
-            store.push_line(&id, format!("✗ failed to start curl download: {e}"));
-            store.finish(&id, false);
-            store.drop_cancel(&id);
-            return;
-        }
-    };
-
-    let stderr = child.stderr.take();
-    let mut t_err = None;
-    if let Some(err_stream) = stderr {
-        let store_clone = store.clone();
-        let id_clone = id.clone();
-        t_err = Some(tokio::spawn(async move {
-            use tokio::io::AsyncReadExt;
-            let mut reader = err_stream;
-            let mut buf = [0u8; 256];
-            while let Ok(n) = reader.read(&mut buf).await {
-                if n == 0 {
-                    break;
-                }
-                let text = String::from_utf8_lossy(&buf[..n]);
-                for word in text.split_whitespace() {
-                    if let Some(num_str) = word.strip_suffix('%') {
-                        if let Ok(pct) = num_str.parse::<f32>() {
-                            let frac = (pct / 100.0).clamp(0.0, 1.0);
-                            store_clone.set_progress(&id_clone, frac, "downloading".into());
-                        }
-                    }
-                }
-            }
-        }));
-    }
-
-    tokio::select! {
-        status_res = child.wait() => {
-            if let Some(t) = t_err { t.abort(); }
-            match status_res {
-                Ok(status) if status.success() => {
-                    store.push_line(&id, "✓ done".into());
-                    store.finish(&id, true);
-                }
-                Ok(status) => {
-                    cleanup_output(&output_abs);
-                    store.push_line(&id, format!("✗ download failed: exit code {:?}", status.code()));
-                    store.finish(&id, false);
-                }
-                Err(e) => {
-                    cleanup_output(&output_abs);
-                    store.push_line(&id, format!("✗ download process error: {e}"));
-                    store.finish(&id, false);
-                }
-            }
-        }
-        _ = cancel.notified() => {
-            let _ = child.start_kill();
-            let _ = child.wait().await;
-            if let Some(t) = t_err { t.abort(); }
-            cleanup_output(&output_abs);
-            store.push_line(&id, "✗ cancelled by user — partial output removed".into());
-            store.set_state(&id, "cancelled");
-        }
-    }
-    store.drop_cancel(&id);
-}
-
 /// into the job log. Fails fast if the converter script is missing.
 pub fn start_import(store: Arc<JobStore>, cfg: &CmfCfg, p: ImportParams) -> Result<String, String> {
    if p.repo.trim().is_empty() {
@@ -486,37 +326,13 @@ pub fn start_import(store: Arc<JobStore>, cfg: &CmfCfg, p: ImportParams) -> Resu
        .unwrap_or_else(|_| output.clone());

    let id = gen_id(&p.repo);
-    let is_cmf = is_cmf_repo(&p.repo);
-    let quant_display = if is_cmf {
-        let r = p.repo.to_lowercase();
-        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 {
-            p.quant.clone()
-        }
-    } else if p.quant.is_empty() || p.quant == "auto" {
-        "q8".to_string()
-    } else {
-        p.quant.clone()
-    };
    store.insert(Job {
        id: id.clone(),
        repo: p.repo.clone(),
-        quant: quant_display.clone(),
+        quant: p.quant.clone(),
        output: output_abs.clone(),
        state: "running".into(),
-        log: if is_cmf {
-            vec![format!(
-                "→ downloading ready .cmf model {} ({})",
-                p.repo, quant_display
-            )]
-        } else {
-            vec![format!("→ converting {} to {} ({})", p.repo, base, p.quant)]
-        },
+        log: vec![format!("→ converting {} to {} ({})", p.repo, base, p.quant)],
        started: now(),
        finished: None,
        size_bytes: None,
@@ -532,14 +348,6 @@ pub fn start_import(store: Arc<JobStore>, cfg: &CmfCfg, p: ImportParams) -> Resu
        std::env::var(&cfg.hf_token_env).ok()
    };

-    if is_cmf && !use_python {
-        let ret_id = id.clone();
-        tokio::spawn(async move {
-            download_cmf_repo(p.repo, output_abs, hf_token, store, id, cancel).await;
-        });
-        return Ok(ret_id);
-    }
-
    // Program + args: `cortiq convert` by default, or the Python converter for
    // advanced options. Both stream `@PROGRESS <frac>` markers into the log.
    let (program, args, workdir): (String, Vec<String>, std::path::PathBuf) = if use_python {
@@ -722,32 +530,3 @@ pub fn start_import(store: Arc<JobStore>, cfg: &CmfCfg, p: ImportParams) -> Resu

    Ok(ret_id)
 }
-
-#[cfg(test)]
-mod tests {
-    use super::*;
-
-    #[test]
-    fn test_map_quant_variants() {
-        assert_eq!(map_quant("Q8_2F"), "q8_2f");
-        assert_eq!(map_quant("q82f"), "q8_2f");
-        assert_eq!(map_quant("Q8_ROW"), "q8");
-        assert_eq!(map_quant("Q4_BLOCK"), "q4");
-        assert_eq!(map_quant("Q4_TILED"), "q4t");
-        assert_eq!(map_quant("q4t"), "q4t");
-        assert_eq!(map_quant("vbit"), "vbit");
-        assert_eq!(map_quant("q1"), "q1");
-        assert_eq!(map_quant("Q1P"), "q1p");
-        assert_eq!(map_quant("q1s"), "q1s");
-        assert_eq!(map_quant("Q1T"), "q1t");
-        assert_eq!(map_quant("F16"), "f16");
-    }
-
-    #[test]
-    fn test_is_cmf_repo_check() {
-        assert!(is_cmf_repo("infosave/Bonsai-8B_2bit_cmf"));
-        assert!(is_cmf_repo("infosave/Bonsai-1.7Bcmf"));
-        assert!(is_cmf_repo("user/model.cmf"));
-        assert!(!is_cmf_repo("Qwen/Qwen2.5-0.5B-Instruct"));
-    }
-}
@@ -29,7 +29,6 @@ pub struct GenParams {
    pub temperature: Option<f32>,
    pub max_tokens: Option<u32>,
    pub top_p: Option<f32>,
-    pub think_budget: Option<u32>,
    pub stop: Vec<String>,
    /// Fields we do not interpret but must proxy through to the provider.
    pub passthrough: serde_json::Map<String, serde_json::Value>,
@@ -341,64 +341,7 @@ impl Pipeline {
                route_source
            );

-            let mut req_call = req.clone();
-            if let Some(m_cfg) = live.cfg.models.iter().find(|m| m.id == model_id) {
-                if req_call.params.temperature.is_none() {
-                    req_call.params.temperature = m_cfg.temperature;
-                }
-                if req_call.params.top_p.is_none() {
-                    req_call.params.top_p = m_cfg.top_p;
-                }
-                if req_call.params.max_tokens.is_none() {
-                    req_call.params.max_tokens = m_cfg.max_tokens;
-                }
-                if req_call.params.think_budget.is_none() {
-                    req_call.params.think_budget = m_cfg.think_budget;
-                }
-                if let Some(sys) = &m_cfg.system_prompt {
-                    if !sys.trim().is_empty()
-                        && !req_call.messages.iter().any(|m| m.role == "system")
-                    {
-                        req_call.messages.insert(
-                            0,
-                            Message {
-                                role: "system".into(),
-                                content: sys.clone(),
-                                tool_calls: Vec::new(),
-                            },
-                        );
-                    }
-                }
-            } else if let Some(s_cfg) = live.cfg.cmf.servers.iter().find(|s| s.id == model_id) {
-                if req_call.params.temperature.is_none() {
-                    req_call.params.temperature = s_cfg.temperature;
-                }
-                if req_call.params.top_p.is_none() {
-                    req_call.params.top_p = s_cfg.top_p;
-                }
-                if req_call.params.max_tokens.is_none() {
-                    req_call.params.max_tokens = s_cfg.max_tokens;
-                }
-                if req_call.params.think_budget.is_none() {
-                    req_call.params.think_budget = s_cfg.think_budget;
-                }
-                if let Some(sys) = &s_cfg.system_prompt {
-                    if !sys.trim().is_empty()
-                        && !req_call.messages.iter().any(|m| m.role == "system")
-                    {
-                        req_call.messages.insert(
-                            0,
-                            Message {
-                                role: "system".into(),
-                                content: sys.clone(),
-                                tool_calls: Vec::new(),
-                            },
-                        );
-                    }
-                }
-            }
-
-            match provider.chat(req_call).await {
+            match provider.chat(req.clone()).await {
                Ok(mut resp) => {
                    let cost =
                        provider.price(resp.usage.prompt_tokens, resp.usage.completion_tokens);
@@ -101,7 +101,6 @@ async fn handler(
            temperature: req.temperature,
            max_tokens: req.max_tokens,
            top_p: req.top_p,
-            think_budget: None,
            stop: Vec::new(),
            passthrough: Default::default(),
        },
@@ -49,10 +49,6 @@ struct OpenAiChatRequest {
    #[serde(default)]
    top_p: Option<f32>,
    #[serde(default)]
-    think_budget: Option<u32>,
-    #[serde(default)]
-    reasoning_effort: Option<u32>,
-    #[serde(default)]
    stream: bool,
    #[serde(default)]
    tools: Vec<serde_json::Value>,
@@ -97,7 +93,6 @@ async fn handler(
            temperature: req.temperature,
            max_tokens: req.max_tokens,
            top_p: req.top_p,
-            think_budget: req.think_budget.or(req.reasoning_effort),
            stop: Vec::new(),
            passthrough: req.rest,
        },
@@ -82,7 +82,6 @@ async fn handler(
            temperature: req.temperature,
            max_tokens: req.max_tokens,
            top_p: req.top_p,
-            think_budget: None,
            stop: Vec::new(),
            passthrough: Default::default(),
        },
@@ -42,16 +42,9 @@ impl OpenAiProvider {
        if let Some(t) = req.params.temperature {
            body["temperature"] = t.into();
        }
-        if let Some(p) = req.params.top_p {
-            body["top_p"] = p.into();
-        }
        if let Some(m) = req.params.max_tokens {
            body["max_tokens"] = m.into();
        }
-        if let Some(tb) = req.params.think_budget {
-            body["think_budget"] = tb.into();
-            body["reasoning_effort"] = tb.into();
-        }
        if !req.tools.is_empty() {
            body["tools"] = serde_json::Value::Array(req.tools.clone());
        }
@@ -49,13 +49,6 @@ impl Registry {
                kind: "chat".into(),
                api_key_env: None,
                caps: Vec::new(),
-                temperature: s.temperature,
-                top_p: s.top_p,
-                max_tokens: s.max_tokens,
-                think_budget: s.think_budget,
-                system_prompt: s.system_prompt.clone(),
-                o1: s.o1.clone(),
-                skip_mtp: s.skip_mtp,
            };
            by_id.insert(m.id.clone(), Arc::new(OpenAiProvider::new(&m, None)?));
        }
@@ -145,14 +145,6 @@ 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(())
    }

@@ -139,18 +139,6 @@ export default {
  "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.paramsTitle": "Generation & Thinking Parameters (O(1), MTP, Temperature)",
-  "models.form.temperature": "Temperature",
-  "models.form.temperatureHint": "Generation temperature (0.0 = deterministic, 1.0+ = creative).",
-  "models.form.topP": "Top-P (Nucleus Sampling)",
-  "models.form.topPHint": "Sampling threshold (0.0 .. 1.0).",
-  "models.form.maxTokens": "Max Tokens",
-  "models.form.maxTokensHint": "Maximum completion tokens to generate.",
-  "models.form.thinkBudget": "Thinking Mode / Think Budget",
-  "models.form.thinkBudgetHint": "Reasoning token budget (0 = disabled, N > 0 = max reasoning tokens).",
-  "models.form.systemPrompt": "Default System Prompt",
-  "models.form.systemPromptHint": "Prepend automatically if request lacks a system prompt.",
-  "models.form.systemPromptPlaceholder": "You are a helpful assistant...",
  "models.form.testKey": "Test & load models",
  "models.form.testing": "checking…",
  "models.form.foundModels": "{n} models loaded",
@@ -279,6 +267,7 @@ export default {
  "settings.cmf.checkPort": "Check port",
  "settings.cmf.portFree": "port is free",
  "settings.cmf.portBusy": "port is in use",
+  "settings.cmf.portOwn": "in use by this gateway's current server — freed on restart, replacing is fine",
  "settings.cmf.useSuggested": "use {port}",
  "settings.cmf.serving": "serving {model} on :{port}",
  "settings.cmf.intro": "Run models locally with the cortiq engine — works even offline or when the router is down.",
@@ -386,7 +375,7 @@ 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": "Downloads & Conversions",
+  "import.jobs": "Conversions",
  "import.cancel": "Cancel",
  "import.cancelling": "Cancelling — cleaning up partial output…",
  "import.delete": "Delete",
@@ -396,21 +385,12 @@ export default {
  "import.state.done": "done",
  "import.state.error": "error",
  "import.state.cancelled": "cancelled",
-  "import.featuredTitle": "Featured Ready-to-Run .cmf Models",
-  "import.readyCmfBadge": "Ready .cmf",
-  "import.directDownload": "Download",
  "import.q.q8_2f": "8-bit two-field (𝒲×θ) — recommended: best quality/size.",
  "import.q.q8_row": "8-bit per-row — simple, robust.",
  "import.q.q4": "4-bit block — smallest, lower quality.",
-  "import.q.q4_tiled": "4-bit tiled (Q4_TILED) — 1.66x faster on Metal GPU.",
  "import.q.vbit": "Variable 3–8 bit — per-expert bit budgets.",
-  "import.q.q1t": "1.58-bit ternary (Q1T) — BitNet b1.58 with sparse outliers.",
-  "import.q.q1s": "1-bit sparse (Q1S) — 1-bit base with holographic outliers.",
-  "import.q.q1p": "1-bit PTQ (Q1P) — 1-bit with error diffusion.",
-  "import.q.q1": "1-bit (Q1) — pure binary format.",
  "import.q.f16": "16-bit — no quantization.",
  "import.q.f32": "32-bit — full precision (large file).",
-
  "import.adv.title": "Advanced settings",
  "import.adv.auto": "auto",
  "import.adv.linearCore": "Linear core",
@@ -138,18 +138,6 @@ export default {
  "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.paramsTitle": "Параметры генерации, O(1) и режим размышления",
-  "models.form.temperature": "Температура",
-  "models.form.temperatureHint": "Температура генерации (0.0 — точные факты, 1.0+ — творчество).",
-  "models.form.topP": "Top-P (Nucleus Sampling)",
-  "models.form.topPHint": "Порог сэмплирования токенов (0.0 .. 1.0).",
-  "models.form.maxTokens": "Макс. токенов (Max Tokens)",
-  "models.form.maxTokensHint": "Максимальное количество генерируемых токенов.",
-  "models.form.thinkBudget": "Режим размышления / Think Budget",
-  "models.form.thinkBudgetHint": "Бюджет токенов мыслей (0 = выключен, N > 0 = лимит рассуждений).",
-  "models.form.systemPrompt": "Системный промпт по умолчанию",
-  "models.form.systemPromptHint": "Автоматически подставляется, если запрос не содержит системное сообщение.",
-  "models.form.systemPromptPlaceholder": "Вы — полезный ассистент...",
  "models.form.testKey": "Проверить и загрузить модели",
  "models.form.testing": "проверка…",
  "models.form.foundModels": "загружено моделей: {n}",
@@ -278,6 +266,7 @@ export default {
  "settings.cmf.checkPort": "Проверить порт",
  "settings.cmf.portFree": "порт свободен",
  "settings.cmf.portBusy": "порт занят",
+  "settings.cmf.portOwn": "занят текущим сервером шлюза — освободится после перезапуска, замена допустима",
  "settings.cmf.useSuggested": "занять {port}",
  "settings.cmf.serving": "работает: {model} на :{port}",
  "settings.cmf.intro": "Запускайте модели локально движком cortiq — работает даже офлайн или когда роутер недоступен.",
@@ -385,7 +374,7 @@ 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": "Загрузки / Конвертации",
+  "import.jobs": "Конвертации",
  "import.cancel": "Отменить",
  "import.cancelling": "Отмена — удаляю недописанный файл…",
  "import.delete": "Удалить",
@@ -395,21 +384,12 @@ export default {
  "import.state.done": "готово",
  "import.state.error": "ошибка",
  "import.state.cancelled": "отменено",
-  "import.featuredTitle": "Рекомендуемые готовые .cmf модели",
-  "import.readyCmfBadge": "Готовая .cmf",
-  "import.directDownload": "Скачать",
  "import.q.q8_2f": "8-бит двухполевой (𝒲×θ) — рекомендуется: лучшее качество/размер.",
  "import.q.q8_row": "8-бит построчно — просто, надёжно.",
  "import.q.q4": "4-бит блочно — компактнее, ниже качество.",
-  "import.q.q4_tiled": "4-бит тайловый (Q4_TILED) — х1.66 быстрее на Metal GPU.",
  "import.q.vbit": "Переменная 3–8 бит — per-expert бюджеты.",
-  "import.q.q1t": "1.58-бит тернарный (Q1T) — BitNet b1.58 с оутлайерами.",
-  "import.q.q1s": "1-бит спарс (Q1S) — 1-бит база с голографическими оутлайерами.",
-  "import.q.q1p": "1-бит PTQ (Q1P) — 1-бит с переносом ошибки (error diffusion).",
-  "import.q.q1": "1-бит (Q1) — чистый бинарный формат.",
  "import.q.f16": "16-бит — без квантования.",
  "import.q.f32": "32-бит — полная точность (большой файл).",
-
  "import.adv.title": "Расширенные настройки",
  "import.adv.auto": "авто",
  "import.adv.linearCore": "Линейное ядро",
@@ -10,23 +10,11 @@ const QUANTS = [
  ["Q8_2F", "import.q.q8_2f"],
  ["Q8_ROW", "import.q.q8_row"],
  ["Q4_BLOCK", "import.q.q4"],
-  ["Q4_TILED", "import.q.q4_tiled"],
  ["VBIT", "import.q.vbit"],
-  ["Q1T", "import.q.q1t"],
-  ["Q1S", "import.q.q1s"],
-  ["Q1P", "import.q.q1p"],
-  ["Q1", "import.q.q1"],
  ["F16", "import.q.f16"],
  ["F32", "import.q.f32"],
 ];

-const FEATURED_REPOS = [
-  { id: "infosave/Bonsai-1.7Bcmf", label: "Bonsai 1.7B CMF", badge: "1.7B · Q1", quant: "Q1" },
-  { id: "infosave/Bonsai-8B_2bit_cmf", label: "Bonsai 8B 2-bit CMF", badge: "8B · Q1T", quant: "Q1T" },
-  { id: "infosave/Bonsai-27Bcmf", label: "Bonsai 27B CMF", badge: "27B · Q1", quant: "Q1" },
-];
-
-
 function field(label, control, hint) {
  return h("label", { class: "field" }, h("span", {}, label), control,
    hint ? h("div", { class: "hint" }, hint) : null);
@@ -370,46 +358,6 @@ export function renderImport() {
    );
  }

-  function featuredCard(item) {
-    const card = h(
-      "div",
-      { class: "hf-card featured-card" },
-      h("div", { class: "row", style: "align-items:center; justify-content:space-between;" },
-        h("div", {},
-          h("div", { class: "hf-id" }, item.label),
-          h("div", { class: "hf-meta" },
-            h("span", { class: "badge" }, item.badge),
-            h("span", { class: "muted" }, item.id)
-          )
-        ),
-        h("button", { class: "btn primary sm" }, "⬇ " + t("import.directDownload"))
-      )
-    );
-    card.querySelector("button").addEventListener("click", async (e) => {
-      e.stopPropagation();
-      try {
-        await api.startImport({
-          repo: item.id,
-          quant: item.quant || "READY_CMF",
-          name: item.id.split("/").pop().toLowerCase(),
-        });
-        toast(t("import.started"), "ok");
-        refreshJobs();
-        jobsHost.scrollIntoView({ behavior: "smooth", block: "nearest" });
-      } catch (err) {
-        toast(err.message, "err");
-      }
-    });
-    return card;
-  }
-
-  const featuredHost = h(
-    "div",
-    { class: "card featured-section" },
-    h("div", { class: "card-title" }, "⚡ " + t("import.featuredTitle")),
-    h("div", { class: "hf-grid" }, ...FEATURED_REPOS.map(featuredCard))
-  );
-
  const root = h(
    "div",
    {},
@@ -417,7 +365,6 @@ export function renderImport() {
      h("h2", {}, t("nav.import")),
      h("div", { class: "muted" }, t("import.subtitle"))),
    jobsHost, // progress panel on top, above the search
-    featuredHost, // featured ready-to-run models
    h("div", { class: "card" }, searchIn, results),
    formHost
  );
@@ -425,4 +372,3 @@ export function renderImport() {
  refreshJobs(); // resume: show any running/recent conversions immediately
  return root;
 }
-
@@ -118,36 +118,6 @@ function modelForm(meta, existing) {
    : existing && existing.key_source === "env" ? t("models.form.keyFromEnv")
    : t("models.form.apiKeyHint");

-  // ⚙ Generation & Thinking Parameters
-  const tempIn = h("input", { type: "number", step: "0.05", min: "0", max: "2.0", placeholder: "0.7", value: m.temperature ?? "" });
-  const topPIn = h("input", { type: "number", step: "0.05", min: "0", max: "1.0", placeholder: "0.9", value: m.top_p ?? "" });
-  const maxTokIn = h("input", { type: "number", min: "1", placeholder: "2048", value: m.max_tokens ?? "" });
-  const thinkIn = h("input", { type: "number", min: "0", placeholder: "1024", value: m.think_budget ?? "" });
-  const o1Sel = h("select", {},
-    opt("", t("import.adv.auto")),
-    opt("all", "all — O(1) Attention"),
-    opt("deep", "deep — O(1) Deep"),
-    opt("off", "off — Standard"));
-  if (m.o1) o1Sel.value = m.o1;
-  const skipMtpCb = h("input", { type: "checkbox", checked: m.skip_mtp ? true : null });
-  const sysPromptIn = h("textarea", { rows: 2, placeholder: t("models.form.systemPromptPlaceholder"), value: m.system_prompt || "" });
-
-  const advParams = h(
-    "details",
-    { class: "adv-params", style: "margin-top:12px;padding:10px;border:1px solid var(--border);border-radius:6px;" },
-    h("summary", { style: "font-weight:600;cursor:pointer;" }, "⚙ " + t("models.form.paramsTitle")),
-    h("div", { class: "row", style: "margin-top:8px" },
-      field(t("models.form.temperature"), tempIn, t("models.form.temperatureHint")),
-      field(t("models.form.topP"), topPIn, t("models.form.topPHint"))),
-    h("div", { class: "row" },
-      field(t("models.form.maxTokens"), maxTokIn, t("models.form.maxTokensHint")),
-      field(t("models.form.thinkBudget"), thinkIn, t("models.form.thinkBudgetHint"))),
-    h("div", { class: "row" },
-      field("O(1) Attention", o1Sel, t("import.adv.o1Hint")),
-      field("MTP", h("label", { class: "check" }, skipMtpCb, t("import.adv.skipMtp")))),
-    field(t("models.form.systemPrompt"), sysPromptIn, t("models.form.systemPromptHint"))
-  );
-
  const node = h(
    "div",
    {},
@@ -158,8 +128,7 @@ function modelForm(meta, existing) {
    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)))),
-    advParams
+    field(t("models.form.caps"), h("div", { class: "flex wrap" }, ...capInputs.map(({ c, cb }) => h("label", { class: "check" }, cb, c))))
  );

  const getValue = () => {
@@ -178,13 +147,6 @@ function modelForm(meta, existing) {
        price_out: parseFloat(priceOutIn.value) || 0,
        api_key_env: hasKey ? keyEnv : null,
        caps: capInputs.filter(({ cb }) => cb.checked).map(({ c }) => c),
-        temperature: tempIn.value !== "" ? parseFloat(tempIn.value) : null,
-        top_p: topPIn.value !== "" ? parseFloat(topPIn.value) : null,
-        max_tokens: maxTokIn.value !== "" ? parseInt(maxTokIn.value) : null,
-        think_budget: thinkIn.value !== "" ? parseInt(thinkIn.value) : null,
-        o1: o1Sel.value || null,
-        skip_mtp: skipMtpCb.checked,
-        system_prompt: sysPromptIn.value.trim() || null,
      },
      secret: typedKey,
      keyEnv,
@@ -245,7 +245,11 @@ export async function renderSettings() {
      try {
        const r = await api.cmfPortCheck(p);
        if (r.available) mount(st, h("span", { style: "color:var(--good)" }, "✓ " + t("settings.cmf.portFree")));
-        else {
+        else if (r.managed) {
+          // held by this gateway's own managed server — replacing the model on
+          // this port is fine, it frees up on restart
+          mount(st, h("span", { style: "color:var(--accent)" }, "ℹ " + t("settings.cmf.portOwn")));
+        } 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));
@@ -253,51 +257,9 @@ export async function renderSettings() {
      } catch (e) { mount(st, String(e.message || e)); }
      checkBtn.disabled = false;
    });
-    // ⚙ Model Generation & Thinking Parameters drawer
-    const tempIn = h("input", { type: "number", step: "0.05", min: "0", max: "2.0", placeholder: "0.7", value: sv.temperature ?? "", style: "width:65px" });
-    const topPIn = h("input", { type: "number", step: "0.05", min: "0", max: "1.0", placeholder: "0.9", value: sv.top_p ?? "", style: "width:65px" });
-    const maxTokIn = h("input", { type: "number", min: "1", placeholder: "2048", value: sv.max_tokens ?? "", style: "width:80px" });
-    const thinkIn = h("input", { type: "number", min: "0", placeholder: "1024", value: sv.think_budget ?? "", style: "width:80px" });
-    const o1Sel = h("select", { style: "width:110px" },
-      opt("", "O(1) auto"),
-      opt("all", "O(1) all"),
-      opt("deep", "O(1) deep"),
-      opt("off", "O(1) off"));
-    if (sv.o1) o1Sel.value = sv.o1;
-    const skipMtpCb = h("input", { type: "checkbox", checked: sv.skip_mtp ? true : null });
-    const sysIn = h("input", { placeholder: t("models.form.systemPromptPlaceholder"), value: sv.system_prompt || "", style: "flex:1" });
-
-    const drawer = h("div", { class: "flex wrap gap-sm", style: "display:none;width:100%;margin-top:4px;padding:6px;background:var(--bg-subtle);border-radius:4px;align-items:center" },
-      h("span", { class: "small muted" }, "Temp:"), tempIn,
-      h("span", { class: "small muted" }, "Top-P:"), topPIn,
-      h("span", { class: "small muted" }, "MaxTokens:"), maxTokIn,
-      h("span", { class: "small muted" }, "ThinkBudget:"), thinkIn,
-      o1Sel,
-      h("label", { class: "check small" }, skipMtpCb, "Skip MTP"),
-      h("span", { class: "small muted" }, "System:"), sysIn
-    );
-
-    const gearBtn = h("button", { class: "btn small", type: "button", title: "⚙ " + t("models.form.paramsTitle") }, "⚙");
-    gearBtn.addEventListener("click", () => {
-      drawer.style.display = drawer.style.display === "none" ? "flex" : "none";
-    });
-
    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"), gearBtn, removeBtn, st, drawer);
-    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,
-      temperature: tempIn.value !== "" ? parseFloat(tempIn.value) : null,
-      top_p: topPIn.value !== "" ? parseFloat(topPIn.value) : null,
-      max_tokens: maxTokIn.value !== "" ? parseInt(maxTokIn.value) : null,
-      think_budget: thinkIn.value !== "" ? parseInt(thinkIn.value) : null,
-      o1: o1Sel.value || null,
-      skip_mtp: skipMtpCb.checked,
-      system_prompt: sysIn.value.trim() || null,
-    }) };
+      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);