Compare commits

..
2 Commits
Author SHA1 Message Date
infosave2007 4220bc27c2 feat(models): ask whether to delete the model file from disk
Docker / publish (push) Canceled after 0s
Release / crates-io (push) Canceled after 0s
Release / release (macos-14, aarch64-apple-darwin) (push) Canceled after 0s
Release / release (ubuntu-latest, x86_64-unknown-linux-gnu) (push) Canceled after 0s
Release / release (windows-latest, x86_64-pc-windows-msvc) (push) Canceled after 0s
- The delete button now opens a dialog; for local models it includes an "also
  delete the model file from disk" checkbox (checked by default), so a pool
  entry can be removed while keeping the .cmf for later.
- DELETE /admin/api/models/:id accepts ?delete_file=true|false (default true).
  The shared-file guard still applies: a file referenced by another model is
  never removed.
- cmf_file_for_model now treats any loopback base_url as local (managed servers
  can sit on any port, not just the legacy local_port).
2026-07-14 11:09:44 +03:00
infosave2007 6fdbe0e159 fix(settings): replacing a managed local model no longer breaks save
Docker / publish (push) Canceled after 0s
Release / crates-io (push) Canceled after 0s
Release / release (macos-14, aarch64-apple-darwin) (push) Canceled after 0s
Release / release (ubuntu-latest, x86_64-unknown-linux-gnu) (push) Canceled after 0s
Release / release (windows-latest, x86_64-pc-windows-msvc) (push) Canceled after 0s
- 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
11 changed files with 131 additions and 128 deletions
-7
View File
@@ -3,15 +3,8 @@
All notable changes to this project are documented here.
The format is based on [Keep a Changelog](https://keepachangelog.com/).
## [0.2.24] - 2026-07-21
### 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.
Generated
+1 -1
View File
@@ -285,7 +285,7 @@ checksum = "1d07550c9036bf2ae0c684c4297d503f838287c83c53686d05370d0e139ae570"
[[package]]
name = "cortiq-gateway"
version = "0.2.24"
version = "0.2.17"
dependencies = [
"anyhow",
"arc-swap",
+1 -1
View File
@@ -1,6 +1,6 @@
[package]
name = "cortiq-gateway"
version = "0.2.24"
version = "0.2.17"
edition = "2021"
rust-version = "1.75"
license = "Apache-2.0"
+89 -8
View File
@@ -606,7 +606,10 @@ fn cmf_file_for_model(
cmf: &crate::config::CmfCfg,
m: &crate::config::ModelCfg,
) -> Option<std::path::PathBuf> {
// Any loopback URL counts as local — managed servers may sit on any port.
let local = m.base_url == cmf.cortiq_server_url
|| m.base_url.contains("//127.0.0.1:")
|| m.base_url.contains("//localhost:")
|| m.base_url
.contains(&format!("{}:{}", cmf.local_host, cmf.local_port));
let stem = m.model.trim();
@@ -646,12 +649,24 @@ fn cmf_path_referenced(cfg: &crate::config::Config, path: &std::path::Path) -> b
.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 {
#[derive(Deserialize)]
struct DeleteModelQuery {
/// Also remove the local `.cmf` from disk. Defaults to true (the historical
/// behaviour); the UI asks the user and passes it explicitly.
delete_file: Option<bool>,
}
async fn delete_model(
State(state): State<SharedState>,
Path(id): Path<String>,
Query(q): Query<DeleteModelQuery>,
) -> ApiResult {
let mut cfg = current_cfg(&state);
let delete_file = q.delete_file.unwrap_or(true);
// 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.
// server, removes it from the managed config, and (when asked) 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) {
@@ -666,10 +681,10 @@ async fn delete_model(State(state): State<SharedState>, Path(id): Path<String>)
let shared = cmf_path_referenced(&cfg, &path);
state.cmf.stop_one(&id).await;
state.reload(cfg)?;
let file_removed = if shared {
false
} else {
let file_removed = if delete_file && !shared {
remove_cmf_path(&path)
} else {
false
};
return ok(json!({ "ok": true, "file_removed": file_removed }));
}
@@ -685,8 +700,8 @@ async fn delete_model(State(state): State<SharedState>, Path(id): Path<String>)
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));
// Only remove the file if asked to AND no remaining model still references it.
let file = file.filter(|p| delete_file && !cmf_path_referenced(&cfg, p));
state.reload(cfg)?;
let file_removed = file.map(|p| remove_cmf_path(&p)).unwrap_or(false);
ok(json!({ "ok": true, "file_removed": file_removed }))
@@ -905,12 +920,75 @@ 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 +1106,9 @@ 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,
}))
+1 -27
View File
@@ -260,15 +260,10 @@ 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",
}
}
@@ -535,24 +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");
}
}
+2 -1
View File
@@ -60,7 +60,8 @@ export const api = {
listModels: () => j("GET", "/models"),
createModel: (b) => j("POST", "/models", b),
updateModel: (id, b) => j("PUT", "/models/" + encodeURIComponent(id), b),
deleteModel: (id) => j("DELETE", "/models/" + encodeURIComponent(id)),
deleteModel: (id, deleteFile = true) =>
j("DELETE", "/models/" + encodeURIComponent(id) + "?delete_file=" + (deleteFile ? "true" : "false")),
probeModel: (id) => j("POST", "/models/" + encodeURIComponent(id) + "/probe"),
// routing
+3 -9
View File
@@ -132,6 +132,8 @@ export default {
"models.form.secretMissing": "not set",
"models.form.secretPlaceholder": "set or replace key (write-only)",
"models.deleteConfirm": "Delete model \"{id}\"?",
"models.deleteFile": "also delete the model file from disk",
"models.deletedWithFile": "Deleted (file removed from disk)",
"models.form.idOrModel": "Enter an id or a model name",
"models.form.apiKey": "API Key",
"models.form.apiKeyPlaceholder": "paste your API key",
@@ -267,6 +269,7 @@ 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.",
@@ -384,21 +387,12 @@ 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",
+3 -9
View File
@@ -131,6 +131,8 @@ export default {
"models.form.secretMissing": "не задан",
"models.form.secretPlaceholder": "задать или заменить ключ (только запись)",
"models.deleteConfirm": "Удалить модель \"{id}\"?",
"models.deleteFile": "также удалить файл модели с диска",
"models.deletedWithFile": "Удалено (файл стёрт с диска)",
"models.form.idOrModel": "Укажите id или имя модели",
"models.form.apiKey": "API-ключ",
"models.form.apiKeyPlaceholder": "вставьте API-ключ",
@@ -266,6 +268,7 @@ 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.",
@@ -383,21 +386,12 @@ 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",
-54
View File
@@ -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 · Ready .cmf" },
{ id: "infosave/Bonsai-8B_2bit_cmf", label: "Bonsai 8B 2-bit CMF", badge: "8B · Ready .cmf" },
{ id: "infosave/Bonsai-27Bcmf", label: "Bonsai 27B CMF", badge: "27B · Ready .cmf" },
];
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: "Q8_2F",
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;
}
+26 -10
View File
@@ -1,5 +1,5 @@
// Models — pool table with add/edit modal, probe, and per-model secret entry.
import { h, mount, modal, toast, confirmDialog, money } from "../ui.js";
import { h, mount, modal, toast, money } from "../ui.js";
import { t } from "../i18n.js";
import { api } from "../api.js";
import { appState } from "../app.js";
@@ -280,15 +280,31 @@ function row(m, meta, reload) {
"button",
{
class: "btn sm danger",
onClick: async () => {
if (!(await confirmDialog(t("models.deleteConfirm", { id: m.id })))) return;
try {
await api.deleteModel(m.id);
toast(t("toast.deleted"), "good");
await reload();
} catch (e) {
toast(String(e.message || e), "bad");
}
onClick: () => {
// local models may have a .cmf on disk — let the user decide its fate
const isLocal = m.managed || /127\.0\.0\.1|localhost/.test(m.base_url || "");
const fileCb = h("input", { type: "checkbox", checked: isLocal ? true : null });
const body = h(
"div",
{},
h("p", {}, t("models.deleteConfirm", { id: m.id })),
isLocal
? h("label", { class: "check" }, fileCb, t("models.deleteFile"))
: null
);
modal(t("common.delete") + ": " + m.id, body, async () => {
try {
const r = await api.deleteModel(m.id, isLocal && fileCb.checked);
toast(
r.file_removed ? t("models.deletedWithFile") : t("toast.deleted"),
"good"
);
await reload();
} catch (e) {
toast(String(e.message || e), "bad");
return false;
}
}, t("common.delete"));
},
},
t("common.delete")
+5 -1
View File
@@ -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));