feat: ops & UX batch — jobs survive restarts, logs/system in the console, media queue, gallery, chat, exact stream tokens
Fifteen changes aimed at the first day of real use: - Import and media jobs persist to <data>/jobs-*.json and reload on start (running ones settle as errors); the Register button no longer vanishes because the gateway restarted. - Docker ships the cortiq binary (built in the builder stage) — local .cmf chat models and image/video generation now work in containers, where auto-install never could (no cargo in the runtime image). libvulkan1 added for optional GPU offload. - Open admin console on 0.0.0.0 without a token now warns in the log and shows a dismissible banner — the VPS footgun is at least labeled. - "Restart gateway" button in Settings: stops managed model servers, spawns a fresh copy (bind retried while the port frees), Docker relies on the container restart policy instead. - Dashboard "System" panel: CPU sparkline + load, RAM (with the gateway's own RSS), free disk at the models dir — sampled by sysinfo every 2 s. - Featured model cards warn "not enough disk" / "may not fit in RAM" before the download, from the same live snapshot. - Log viewer in the sidebar: a 500-line in-memory ring fed by a second ANSI-free tracing layer; filter, level, pause, copy. - Update check: crates.io polled twice a day, the console shows an "update available" notice. - Media generations queue up (with position shown) instead of being rejected; progress gained an honest ETA from measured throughput. - Generation gallery under the image/video tabs: lazy PPM thumbnails, click to reopen with seed/steps, delete. - Playground chat is a real dialogue now: history is resent, bubbles, Clear, Cmd/Ctrl+Enter. - "Connect your app" snippets (curl / Python / JS) on the keys page, with the real key inlined right after creation. - One-click benchmark on the Models page via `cortiq bench --json`. - Config export now downloads the actual gateway.toml (comments intact); import accepts TOML (validated, hot-reloaded) and the legacy JSON. - Streaming token counts are exact when the model server provides usage (cortiq-server patch, shipped separately); the gateway fallback now counts content chunks (1/token on cortiq) instead of chars/4. Wizard's Finish lands on the Playground. 37 new strings in all 7 languages.
This commit is contained in:
infosave2007
+151
-61
@@ -184,7 +184,7 @@ pub struct MediaParams {
|
||||
}
|
||||
|
||||
/// Live state of one generation.
|
||||
#[derive(Clone, Serialize)]
|
||||
#[derive(Clone, Serialize, serde::Deserialize)]
|
||||
pub struct MediaJob {
|
||||
pub id: String,
|
||||
pub kind: String, // image | video
|
||||
@@ -195,7 +195,7 @@ pub struct MediaJob {
|
||||
pub steps: u32,
|
||||
pub seed: u64,
|
||||
pub frames: Option<u32>,
|
||||
pub state: String, // running | done | error | cancelled
|
||||
pub state: String, // queued | running | done | error | cancelled
|
||||
pub progress: Option<f32>,
|
||||
pub phase: Option<String>,
|
||||
pub log: Vec<String>,
|
||||
@@ -206,18 +206,67 @@ pub struct MediaJob {
|
||||
pub out_bytes: Option<u64>,
|
||||
}
|
||||
|
||||
/// Everything needed to actually launch a queued job when its turn comes.
|
||||
struct Prepared {
|
||||
bin: String,
|
||||
args: Vec<String>,
|
||||
gpu: bool,
|
||||
dir: PathBuf,
|
||||
out_path: PathBuf,
|
||||
kind: String,
|
||||
}
|
||||
|
||||
#[derive(Default)]
|
||||
pub struct MediaStore {
|
||||
jobs: Mutex<HashMap<String, MediaJob>>,
|
||||
cancels: Mutex<HashMap<String, Arc<Notify>>>,
|
||||
/// One generation at a time — these models take the whole GPU/RAM budget.
|
||||
busy: Mutex<Option<String>>,
|
||||
/// One generation runs at a time — these models take the whole GPU/RAM
|
||||
/// budget — but new requests queue up instead of being rejected.
|
||||
queue: Mutex<std::collections::VecDeque<String>>,
|
||||
current: Mutex<Option<String>>,
|
||||
prepared: Mutex<HashMap<String, Prepared>>,
|
||||
persist: Mutex<Option<PathBuf>>,
|
||||
}
|
||||
|
||||
impl MediaStore {
|
||||
pub fn new() -> Arc<Self> {
|
||||
Arc::new(Self::default())
|
||||
}
|
||||
/// Load saved generations (their files are still under media_dir) and start
|
||||
/// persisting. Jobs that were queued/running when the gateway died settle
|
||||
/// as errors — the process is gone.
|
||||
pub fn attach_persistence(&self, path: PathBuf) {
|
||||
if let Ok(text) = std::fs::read_to_string(&path) {
|
||||
if let Ok(mut jobs) = serde_json::from_str::<Vec<MediaJob>>(&text) {
|
||||
let mut g = self.jobs.lock().unwrap();
|
||||
for mut j in jobs.drain(..) {
|
||||
if j.state == "running" || j.state == "queued" {
|
||||
j.state = "error".into();
|
||||
j.log.push("✗ interrupted by a gateway restart".into());
|
||||
j.finished = Some(now());
|
||||
}
|
||||
g.insert(j.id.clone(), j);
|
||||
}
|
||||
}
|
||||
}
|
||||
*self.persist.lock().unwrap() = Some(path);
|
||||
}
|
||||
fn save(&self) {
|
||||
let Some(path) = self.persist.lock().unwrap().clone() else {
|
||||
return;
|
||||
};
|
||||
let jobs: Vec<MediaJob> = self.jobs.lock().unwrap().values().cloned().collect();
|
||||
if let Ok(json) = serde_json::to_vec(&jobs) {
|
||||
let tmp = path.with_extension("json.tmp");
|
||||
if std::fs::write(&tmp, json).is_ok() {
|
||||
let _ = std::fs::rename(&tmp, &path);
|
||||
}
|
||||
}
|
||||
}
|
||||
/// How many jobs sit in the queue ahead of `id` (0 = next up).
|
||||
pub fn queue_position(&self, id: &str) -> Option<usize> {
|
||||
self.queue.lock().unwrap().iter().position(|x| x == id)
|
||||
}
|
||||
pub fn list(&self) -> Vec<MediaJob> {
|
||||
let mut v: Vec<MediaJob> = self.jobs.lock().unwrap().values().cloned().collect();
|
||||
v.sort_by_key(|j| std::cmp::Reverse(j.started));
|
||||
@@ -227,30 +276,43 @@ impl MediaStore {
|
||||
pub fn get(&self, id: &str) -> Option<MediaJob> {
|
||||
self.jobs.lock().unwrap().get(id).cloned()
|
||||
}
|
||||
pub fn cancel(&self, id: &str) -> bool {
|
||||
let running = matches!(
|
||||
self.jobs.lock().unwrap().get(id).map(|j| j.state.as_str()),
|
||||
Some("running")
|
||||
);
|
||||
if !running {
|
||||
return false;
|
||||
}
|
||||
if let Some(n) = self.cancels.lock().unwrap().get(id) {
|
||||
n.notify_one();
|
||||
true
|
||||
} else {
|
||||
false
|
||||
pub fn cancel(self: &Arc<Self>, id: &str, media_dir: &Path) -> bool {
|
||||
let state = self
|
||||
.jobs
|
||||
.lock()
|
||||
.unwrap()
|
||||
.get(id)
|
||||
.map(|j| j.state.clone())
|
||||
.unwrap_or_default();
|
||||
match state.as_str() {
|
||||
"queued" => {
|
||||
self.queue.lock().unwrap().retain(|x| x != id);
|
||||
self.prepared.lock().unwrap().remove(id);
|
||||
let _ = std::fs::remove_dir_all(media_dir.join(id));
|
||||
self.set_cancelled(id);
|
||||
true
|
||||
}
|
||||
"running" => {
|
||||
if let Some(n) = self.cancels.lock().unwrap().get(id) {
|
||||
n.notify_one();
|
||||
true
|
||||
} else {
|
||||
false
|
||||
}
|
||||
}
|
||||
_ => false,
|
||||
}
|
||||
}
|
||||
/// Remove a settled job and its output directory. Err = still running.
|
||||
pub fn delete(&self, id: &str, media_dir: &Path) -> Result<bool, String> {
|
||||
let job = self.jobs.lock().unwrap().get(id).cloned();
|
||||
let Some(job) = job else { return Ok(false) };
|
||||
if job.state == "running" {
|
||||
if job.state == "running" || job.state == "queued" {
|
||||
return Err("cancel the running generation first".into());
|
||||
}
|
||||
let _ = std::fs::remove_dir_all(media_dir.join(id));
|
||||
self.jobs.lock().unwrap().remove(id);
|
||||
self.save();
|
||||
Ok(true)
|
||||
}
|
||||
fn push_line(&self, id: &str, line: String) {
|
||||
@@ -273,10 +335,12 @@ impl MediaStore {
|
||||
}
|
||||
}
|
||||
}
|
||||
fn finish(&self, id: &str, ok: bool, outputs: Vec<String>, out_bytes: u64) {
|
||||
fn finish(self: &Arc<Self>, id: &str, ok: bool, outputs: Vec<String>, out_bytes: u64) {
|
||||
let mut g = self.jobs.lock().unwrap();
|
||||
if let Some(j) = g.get_mut(id) {
|
||||
if j.state == "cancelled" {
|
||||
drop(g);
|
||||
self.after_slot_freed(id);
|
||||
return;
|
||||
}
|
||||
j.finished = Some(now());
|
||||
@@ -288,25 +352,67 @@ impl MediaStore {
|
||||
}
|
||||
}
|
||||
drop(g);
|
||||
self.clear_busy(id);
|
||||
self.cancels.lock().unwrap().remove(id);
|
||||
self.after_slot_freed(id);
|
||||
}
|
||||
fn set_cancelled(&self, id: &str) {
|
||||
fn set_cancelled(self: &Arc<Self>, id: &str) {
|
||||
if let Some(j) = self.jobs.lock().unwrap().get_mut(id) {
|
||||
j.state = "cancelled".into();
|
||||
j.finished = Some(now());
|
||||
}
|
||||
self.clear_busy(id);
|
||||
self.cancels.lock().unwrap().remove(id);
|
||||
self.after_slot_freed(id);
|
||||
}
|
||||
fn clear_busy(&self, id: &str) {
|
||||
let mut b = self.busy.lock().unwrap();
|
||||
if b.as_deref() == Some(id) {
|
||||
*b = None;
|
||||
fn after_slot_freed(self: &Arc<Self>, id: &str) {
|
||||
{
|
||||
let mut cur = self.current.lock().unwrap();
|
||||
if cur.as_deref() == Some(id) {
|
||||
*cur = None;
|
||||
}
|
||||
}
|
||||
self.cancels.lock().unwrap().remove(id);
|
||||
self.save();
|
||||
promote_next(self.clone());
|
||||
}
|
||||
}
|
||||
|
||||
/// Start the next queued generation, if the slot is free.
|
||||
fn promote_next(store: Arc<MediaStore>) {
|
||||
let next = {
|
||||
let mut cur = store.current.lock().unwrap();
|
||||
if cur.is_some() {
|
||||
return;
|
||||
}
|
||||
let Some(id) = store.queue.lock().unwrap().pop_front() else {
|
||||
return;
|
||||
};
|
||||
*cur = Some(id.clone());
|
||||
id
|
||||
};
|
||||
let Some(p) = store.prepared.lock().unwrap().remove(&next) else {
|
||||
// job was cancelled while queued and slipped through — free the slot
|
||||
*store.current.lock().unwrap() = None;
|
||||
return;
|
||||
};
|
||||
if let Some(j) = store.jobs.lock().unwrap().get_mut(&next) {
|
||||
j.state = "running".into();
|
||||
j.phase = Some("starting".into());
|
||||
j.started = now();
|
||||
}
|
||||
store.save();
|
||||
let cancel = Arc::new(Notify::new());
|
||||
store
|
||||
.cancels
|
||||
.lock()
|
||||
.unwrap()
|
||||
.insert(next.clone(), cancel.clone());
|
||||
let s = store.clone();
|
||||
tokio::spawn(async move {
|
||||
run_generation(
|
||||
s, next, p.bin, p.args, p.gpu, p.dir, p.out_path, p.kind, cancel,
|
||||
)
|
||||
.await;
|
||||
});
|
||||
}
|
||||
|
||||
/// Progress markers in `cortiq imagine`/`animate` stdout. The exact wording has
|
||||
/// varied between releases, so accept anything that carries an X/Y pair near a
|
||||
/// step/frame word, a bare percentage, or the converter-style `@PROGRESS`.
|
||||
@@ -432,22 +538,10 @@ pub fn start_generation(
|
||||
if !model_path.exists() {
|
||||
return Err(format!("model file not found: {}", model_path.display()));
|
||||
}
|
||||
{
|
||||
let mut busy = store.busy.lock().unwrap();
|
||||
if let Some(running) = busy.as_ref() {
|
||||
return Err(format!(
|
||||
"a generation is already running (job {running}) — these models need the whole machine; wait or cancel it"
|
||||
));
|
||||
}
|
||||
*busy = Some(String::new()); // reserved; real id set below
|
||||
}
|
||||
|
||||
let id = gen_media_id();
|
||||
*store.busy.lock().unwrap() = Some(id.clone());
|
||||
|
||||
let dir = media_dir().join(&id);
|
||||
if let Err(e) = std::fs::create_dir_all(&dir) {
|
||||
store.clear_busy(&id);
|
||||
return Err(format!("cannot create media dir {}: {e}", dir.display()));
|
||||
}
|
||||
|
||||
@@ -553,9 +647,9 @@ pub fn start_generation(
|
||||
steps,
|
||||
seed,
|
||||
frames: (kind == "video").then_some(frames),
|
||||
state: "running".into(),
|
||||
state: "queued".into(),
|
||||
progress: None,
|
||||
phase: Some("starting".into()),
|
||||
phase: None,
|
||||
log: vec![format!("→ cortiq {}", args.join(" "))],
|
||||
started: now(),
|
||||
finished: None,
|
||||
@@ -563,25 +657,21 @@ pub fn start_generation(
|
||||
out_bytes: None,
|
||||
},
|
||||
);
|
||||
let cancel = Arc::new(Notify::new());
|
||||
store
|
||||
.cancels
|
||||
.lock()
|
||||
.unwrap()
|
||||
.insert(id.clone(), cancel.clone());
|
||||
|
||||
let bin = cmf.cortiq_bin.clone();
|
||||
let gpu = cmf.gpu;
|
||||
let ret = id.clone();
|
||||
let dir_clone = dir.clone();
|
||||
let kind_owned = kind.to_string();
|
||||
tokio::spawn(async move {
|
||||
run_generation(
|
||||
store, id, bin, args, gpu, dir_clone, out_path, kind_owned, cancel,
|
||||
)
|
||||
.await;
|
||||
});
|
||||
Ok(ret)
|
||||
store.prepared.lock().unwrap().insert(
|
||||
id.clone(),
|
||||
Prepared {
|
||||
bin: cmf.cortiq_bin.clone(),
|
||||
args,
|
||||
gpu: cmf.gpu,
|
||||
dir,
|
||||
out_path,
|
||||
kind: kind.to_string(),
|
||||
},
|
||||
);
|
||||
store.queue.lock().unwrap().push_back(id.clone());
|
||||
store.save();
|
||||
promote_next(store.clone());
|
||||
Ok(id)
|
||||
}
|
||||
|
||||
#[allow(clippy::too_many_arguments)]
|
||||
|
||||
Reference in New Issue
Block a user