feat(playground): image & video generation tabs + real chat metrics

The infosave collection now ships media models (Lumina-Image-2.0, MiniMax-H3
Turbo) that cortiq runs via `imagine`/`animate` CLI, not `cortiq serve`. The
gateway grows a media API: local .cmf files are classified by `cortiq info`
(chat/image/video, cached), generations run as tracked jobs with step progress
parsed from stdout, one at a time, cancellable, outputs under <data>/media.

The playground becomes three tabs. Image: width/height/steps/CFG/seed, live
progress, result rendered from P6 PPM to a canvas in the browser (PNG export
via toBlob). Video: frames/steps/quality/seed plus optional first/last
keyframes (rasterized to PPM client-side); the MJPEG+PCM AVI is decoded in JS
and played on a canvas synced to the wav — no ffmpeg on either side (mp4 remux
happens opportunistically when ffmpeg exists). A metrics card shows resolution,
steps, seed, total time, time per step/frame and file size.

Chat metrics: the local cortiq server sends no usage chunk in streams, so
token counts showed 0/0. tap_stream now injects one OpenAI-shaped usage event
ahead of [DONE] with the gateway's ~4-chars/token estimate, flagged
`cortiq_estimated`; the UI renders it as "≈ N / M" and adds tok/s and
time-to-first-token. Registration skips media packs (a `cortiq serve` entry
for a diffusion model would only fail) in both Register and the wizard's
Finish.

36 new UI strings translated across all 7 languages.
This commit is contained in:
infosave2007
2026-08-07 15:55:06 +03:00
parent 32ce2f7ed7
commit a77beeabab
16 changed files with 1814 additions and 30 deletions
+406 -27
View File
@@ -1,17 +1,64 @@
// Playground — send a prompt through the live pipeline, inspect routing decision.
import { h, mount, money, ms } from "../ui.js";
// Playground — three tabs over the live gateway:
// chat → the routing pipeline (with streaming, token counts, tok/s, TTFT)
// image → `cortiq imagine` over a local text-to-image .cmf (Lumina)
// video → `cortiq animate` over a local text-to-video .cmf (MiniMax-H3)
// Media results are decoded in the browser (PPM → canvas, MJPEG AVI → canvas
// player synced to the wav) — the same no-ffmpeg stance as the engine itself.
import { h, mount, toast, money, ms } from "../ui.js";
import { t } from "../i18n.js";
import { api, testStream } from "../api.js";
import { api, testStream, mediaFileUrl, mediaFileBytes } from "../api.js";
import { appState } from "../app.js";
import { ppmToCanvas, fileToPpmB64, aviJpegFrames, mjpegPlayer } from "../media-utils.js";
function fmtBytes(n) {
if (!n && n !== 0) return "—";
if (n >= 1e9) return (n / 1e9).toFixed(2) + " GB";
if (n >= 1e6) return (n / 1e6).toFixed(1) + " MB";
if (n >= 1e3) return Math.round(n / 1e3) + " KB";
return n + " B";
}
function kv(k, v) {
return h("div", { class: "kv" }, h("span", { class: "k" }, k), h("span", { class: "v" }, v));
}
function field(label, control, hint) {
return h("label", { class: "field" }, h("span", {}, label), control, hint ? h("div", { class: "hint" }, hint) : null);
}
export async function renderPlayground() {
const meta = appState.meta || (await api.meta());
const modelsData = await api.listModels();
const ids = (modelsData.models || []).map((m) => m.id);
let mediaModels = [];
try {
mediaModels = (await api.mediaModels()).models || [];
} catch {
/* media API unavailable — tabs will show the hint */
}
const imageModels = mediaModels.filter((m) => m.modality === "image");
const videoModels = mediaModels.filter((m) => m.modality === "video");
let mode = "auto";
const root = h("div");
let tab = "chat";
// ── tabs ──
const tabsSeg = h(
"div",
{ class: "seg" },
h("button", { class: "active", "data-tab": "chat" }, "💬 " + t("pg.tab.chat")),
h("button", { "data-tab": "image" }, "🖼 " + t("pg.tab.image")),
h("button", { "data-tab": "video" }, "🎬 " + t("pg.tab.video"))
);
const panelHost = h("div", {});
tabsSeg.querySelectorAll("button").forEach((b) =>
b.addEventListener("click", () => {
tab = b.dataset.tab;
tabsSeg.querySelectorAll("button").forEach((x) => x.classList.toggle("active", x === b));
mount(panelHost, panels[tab]);
})
);
// ════════════════════════════ chat panel ════════════════════════════
let mode = "auto";
const sysIn = h("textarea", { placeholder: t("pg.systemPlaceholder"), rows: 2 });
const promptIn = h("textarea", { placeholder: t("pg.promptPlaceholder"), rows: 5 });
const tempIn = h("input", { type: "number", step: "0.1", value: 0.7 });
@@ -79,6 +126,7 @@ export async function renderPlayground() {
out.textContent = acc;
});
out.textContent = acc || "—";
const latency = Math.round(performance.now() - started);
renderDecision({
cortiq: {
task_label: info.task_label,
@@ -88,8 +136,10 @@ export async function renderPlayground() {
cost_usd: info.cost_usd,
failover: false,
},
usage: {},
latency_ms: Math.round(performance.now() - started),
usage: info.usage || {},
usage_estimated: info.usage_estimated,
latency_ms: latency,
ttft_ms: info.ttft_ms,
});
} else {
const r = await api.test(body);
@@ -108,12 +158,17 @@ export async function renderPlayground() {
sendBtn.textContent = t("pg.send");
});
function kv(k, v) {
return h("div", { class: "kv" }, h("span", { class: "k" }, k), h("span", { class: "v" }, v));
}
function renderDecision(r) {
const c = r.cortiq || {};
const score = c.complexity?.score ?? 0;
const u = r.usage || {};
const haveUsage = u.completion_tokens != null;
// generation speed over the produce phase (after first token when known)
let tokS = null;
if (haveUsage && r.latency_ms) {
const genMs = r.ttft_ms != null ? Math.max(1, r.latency_ms - r.ttft_ms) : r.latency_ms;
tokS = (u.completion_tokens / (genMs / 1000)).toFixed(1);
}
mount(
decision,
h("div", { class: "card-head" }, h("h3", {}, t("pg.decision"))),
@@ -127,17 +182,188 @@ export async function renderPlayground() {
),
kv(t("pg.selected"), h("span", { class: "mono" }, c.selected_model || "—")),
kv(t("pg.source"), c.route_source || "—"),
kv(t("pg.tokens"), `${r.usage?.prompt_tokens ?? 0}/${r.usage?.completion_tokens ?? 0}`),
kv(t("pg.tokens"), haveUsage ? `${r.usage_estimated ? "≈ " : ""}${u.prompt_tokens ?? 0} / ${u.completion_tokens ?? 0}` : "—"),
kv(t("pg.tokSpeed"), tokS != null ? tokS + " tok/s" : "—"),
kv(t("pg.ttft"), r.ttft_ms != null ? ms(r.ttft_ms) : "—"),
kv(t("pg.cost"), money(c.cost_usd)),
kv(t("pg.latency"), ms(r.latency_ms)),
kv(t("pg.failover"), c.failover ? "yes" : "no")
);
}
mount(
root,
h("div", { class: "page-head" }, h("h2", {}, t("pg.title")), h("p", {}, t("pg.subtitle"))),
const chatPanel = h(
"div",
{ class: "pg" },
h(
"div",
{},
h(
"div",
{ class: "card" },
field(t("pg.system"), sysIn),
field(t("pg.prompt"), promptIn),
field(t("pg.mode"), modeSeg),
modeExtra,
h("div", { class: "row" }, field(t("pg.temp"), tempIn), field(t("pg.maxTokens"), maxTokIn)),
h(
"div",
{ class: "flex", style: "justify-content:space-between" },
h("label", { class: "check", style: "margin:0" }, streamCb, t("pg.stream")),
sendBtn
)
),
h("div", { class: "card" }, h("div", { class: "card-head" }, h("h3", {}, t("pg.answer"))), out)
),
decision
);
// ═══════════════════════ shared media machinery ═══════════════════════
let mediaPoll = null;
function stopMediaPoll() {
if (mediaPoll) clearInterval(mediaPoll);
mediaPoll = null;
}
// one generation at a time server-side → one active job client-side
function watchJob(id, ui, onDone) {
stopMediaPoll();
const started = performance.now();
mediaPoll = setInterval(async () => {
if (!root.isConnected) return stopMediaPoll();
let j;
try {
j = await api.mediaJob(id);
} catch {
return;
}
const secs = ((performance.now() - started) / 1000).toFixed(0);
const pct = j.progress != null ? Math.round(j.progress * 100) : null;
mount(
ui.bar,
h("div", { class: "pbar" },
j.state === "running"
? (pct != null
? h("div", { class: "pbar-fill det", style: `width:${Math.max(pct, 1)}%` })
: h("div", { class: "pbar-fill run" }))
: h("div", { class: "pbar-fill " + (j.state === "done" ? "ok" : "err"), style: "width:100%" })
),
h("div", { class: "muted small" },
(j.phase || j.state) + (pct != null && j.state === "running" ? ` · ${pct}%` : "") + ` · ${secs}s`),
(j.log || []).length ? h("pre", { class: "conv-log", style: "max-height:90px" }, j.log.slice(-5).join("\n")) : null
);
if (j.state !== "running") {
stopMediaPoll();
ui.goBtn.disabled = false;
ui.cancelBtn.style.display = "none";
if (j.state === "done") onDone(j);
else if (j.state === "error") toast(t("pg.genFailed"), "err");
}
}, 1000);
}
function mediaControls(goBtn, onCancelId) {
const cancelBtn = h("button", { class: "btn ghost", style: "display:none" }, "✕ " + t("import.cancel"));
cancelBtn.addEventListener("click", async () => {
try {
await api.mediaCancel(onCancelId.id);
} catch (e) {
toast(e.message, "err");
}
});
return cancelBtn;
}
function noModelsHint(kindLabel) {
return h(
"div",
{ class: "card" },
h("div", { class: "callout" },
t("pg.noMediaModels", { kind: kindLabel }),
" ",
h("a", { href: "#/import" }, t("settings.cmf.importLink") + " ↗"))
);
}
function dice(seedIn) {
const b = h("button", { class: "btn ghost sm", title: t("pg.randomSeed") }, "🎲");
b.addEventListener("click", () => (seedIn.value = Math.floor(Math.random() * 1e9)));
return b;
}
// ════════════════════════════ image panel ════════════════════════════
let imagePanel;
if (!imageModels.length) {
imagePanel = noModelsHint(t("pg.tab.image"));
} else {
const imModel = h("select", {}, ...imageModels.map((m) => h("option", { value: m.name }, `${m.name} · ${fmtBytes(m.size_bytes)}`)));
const imPrompt = h("textarea", { placeholder: t("pg.imagePromptPlaceholder"), rows: 3 });
const imW = h("select", {}, ...[256, 384, 512, 640, 768, 1024].map((v) => h("option", { value: v, selected: v === 512 ? true : null }, v)));
const imH = h("select", {}, ...[256, 384, 512, 640, 768, 1024].map((v) => h("option", { value: v, selected: v === 512 ? true : null }, v)));
const imSteps = h("input", { type: "number", min: 1, max: 100, value: 30 });
const imCfg = h("input", { type: "number", step: "0.5", value: 4 });
const imSeed = h("input", { type: "number", value: 42 });
const imBar = h("div", {});
const imOut = h("div", { class: "media-out" }, h("div", { class: "empty" }, t("pg.imageEmpty")));
const imMetrics = h("div", { class: "card routecard" }, h("div", { class: "card-head" }, h("h3", {}, t("pg.genMetrics"))), h("div", { class: "empty" }, "—"));
const imGo = h("button", { class: "btn primary" }, "🖼 " + t("pg.generate"));
const imCancelRef = { id: null };
const imCancel = mediaControls(imGo, imCancelRef);
imGo.addEventListener("click", async () => {
const prompt = imPrompt.value.trim();
if (!prompt) return;
imGo.disabled = true;
imCancel.style.display = "";
mount(imOut, h("div", { class: "flex" }, h("span", { class: "spinner" }), " ", t("pg.generating")));
const params = {
kind: "image",
model: imModel.value,
prompt,
width: +imW.value,
height: +imH.value,
steps: +imSteps.value || 30,
cfg: parseFloat(imCfg.value) || 4,
seed: +imSeed.value || 42,
};
try {
const r = await api.mediaGenerate(params);
imCancelRef.id = r.job;
const t0 = performance.now();
watchJob(r.job, { bar: imBar, goBtn: imGo, cancelBtn: imCancel }, async (j) => {
mount(imBar);
const secs = (performance.now() - t0) / 1000;
try {
const buf = await mediaFileBytes(j.id, "image");
const canvas = ppmToCanvas(buf);
canvas.className = "media-canvas";
const dl = h("button", { class: "btn sm" }, "⬇ PNG");
dl.addEventListener("click", () =>
canvas.toBlob((b) => {
const a = h("a", { href: URL.createObjectURL(b), download: `cortiq-${j.id}.png` });
a.click();
}, "image/png")
);
mount(imOut, canvas, h("div", { class: "actions" }, dl));
mount(
imMetrics,
h("div", { class: "card-head" }, h("h3", {}, t("pg.genMetrics"))),
kv(t("pg.model"), h("span", { class: "mono" }, j.model)),
kv(t("pg.resolution"), `${j.width}×${j.height}`),
kv(t("pg.steps"), String(j.steps)),
kv("CFG", String(params.cfg)),
kv(t("pg.seed"), String(j.seed)),
kv(t("pg.genTime"), secs.toFixed(1) + " s"),
kv(t("pg.timePerStep"), (secs / j.steps).toFixed(2) + " s"),
kv(t("pg.fileSize"), fmtBytes(j.out_bytes))
);
} catch (e) {
mount(imOut, h("div", { class: "callout" }, String(e.message || e)));
}
});
} catch (e) {
imGo.disabled = false;
imCancel.style.display = "none";
mount(imOut, h("div", { class: "callout" }, String(e.message || e)));
}
});
imagePanel = h(
"div",
{ class: "pg" },
h(
@@ -146,22 +372,175 @@ export async function renderPlayground() {
h(
"div",
{ class: "card" },
h("label", { class: "field" }, h("span", {}, t("pg.system")), sysIn),
h("label", { class: "field" }, h("span", {}, t("pg.prompt")), promptIn),
h("label", { class: "field" }, h("span", {}, t("pg.mode")), modeSeg),
modeExtra,
h("div", { class: "row" }, h("label", { class: "field" }, h("span", {}, t("pg.temp")), tempIn), h("label", { class: "field" }, h("span", {}, t("pg.maxTokens")), maxTokIn)),
h(
"div",
{ class: "flex", style: "justify-content:space-between" },
h("label", { class: "check", style: "margin:0" }, streamCb, t("pg.stream")),
sendBtn
)
field(t("pg.model"), imModel),
field(t("pg.prompt"), imPrompt),
h("div", { class: "row" }, field(t("pg.width"), imW), field(t("pg.height"), imH)),
h("div", { class: "row" },
field(t("pg.steps"), imSteps),
field("CFG", imCfg, t("pg.cfgHint"))),
h("div", { class: "row" },
field(t("pg.seed"), h("div", { class: "flex", style: "gap:6px" }, imSeed, dice(imSeed)))),
h("div", { class: "actions" }, imCancel, imGo),
imBar
),
h("div", { class: "card" }, h("div", { class: "card-head" }, h("h3", {}, t("pg.answer"))), out)
h("div", { class: "card" }, h("div", { class: "card-head" }, h("h3", {}, t("pg.result"))), imOut)
),
decision
)
imMetrics
);
}
// ════════════════════════════ video panel ════════════════════════════
let videoPanel;
if (!videoModels.length) {
videoPanel = noModelsHint(t("pg.tab.video"));
} else {
const vModel = h("select", {}, ...videoModels.map((m) => h("option", { value: m.name }, `${m.name} · ${fmtBytes(m.size_bytes)}`)));
const vPrompt = h("textarea", { placeholder: t("pg.videoPromptPlaceholder"), rows: 3 });
const vW = h("input", { type: "number", step: 32, value: 512 });
const vH = h("input", { type: "number", step: 32, value: 288 });
const vFrames = h("input", { type: "number", value: 39 });
const vSteps = h("input", { type: "number", value: 4 });
const vSeed = h("input", { type: "number", value: 42 });
const vQuality = h("input", { type: "number", min: 10, max: 100, value: 92 });
const vFirst = h("input", { type: "file", accept: "image/*" });
const vLast = h("input", { type: "file", accept: "image/*" });
const vBar = h("div", {});
const vOut = h("div", { class: "media-out" }, h("div", { class: "empty" }, t("pg.videoEmpty")));
const vMetrics = h("div", { class: "card routecard" }, h("div", { class: "card-head" }, h("h3", {}, t("pg.genMetrics"))), h("div", { class: "empty" }, "—"));
const vGo = h("button", { class: "btn primary" }, "🎬 " + t("pg.generate"));
const vCancelRef = { id: null };
const vCancel = mediaControls(vGo, vCancelRef);
vGo.addEventListener("click", async () => {
const prompt = vPrompt.value.trim();
if (!prompt) return;
vGo.disabled = true;
vCancel.style.display = "";
mount(vOut, h("div", { class: "flex" }, h("span", { class: "spinner" }), " ", t("pg.generating")));
const params = {
kind: "video",
model: vModel.value,
prompt,
width: +vW.value || 512,
height: +vH.value || 288,
frames: +vFrames.value || 39,
steps: +vSteps.value || 4,
seed: +vSeed.value || 42,
quality: +vQuality.value || 92,
};
try {
if (vFirst.files[0]) params.first_frame_b64 = await fileToPpmB64(vFirst.files[0], params.width, params.height);
if (vLast.files[0]) params.last_frame_b64 = await fileToPpmB64(vLast.files[0], params.width, params.height);
const r = await api.mediaGenerate(params);
vCancelRef.id = r.job;
const t0 = performance.now();
watchJob(r.job, { bar: vBar, goBtn: vGo, cancelBtn: vCancel }, async (j) => {
mount(vBar);
const secs = (performance.now() - t0) / 1000;
try {
await showVideoResult(j, vOut);
const durS = (j.frames || 0) / 24;
mount(
vMetrics,
h("div", { class: "card-head" }, h("h3", {}, t("pg.genMetrics"))),
kv(t("pg.model"), h("span", { class: "mono" }, j.model)),
kv(t("pg.resolution"), `${j.width}×${j.height}`),
kv(t("pg.frames"), `${j.frames} @ 24 fps`),
kv(t("pg.duration"), durS.toFixed(1) + " s"),
kv(t("pg.steps"), String(j.steps)),
kv(t("pg.seed"), String(j.seed)),
kv(t("pg.genTime"), secs.toFixed(1) + " s"),
kv(t("pg.timePerFrame"), j.frames ? (secs / j.frames).toFixed(2) + " s" : "—"),
kv(t("pg.fileSize"), fmtBytes(j.out_bytes))
);
} catch (e) {
mount(vOut, h("div", { class: "callout" }, String(e.message || e)));
}
});
} catch (e) {
vGo.disabled = false;
vCancel.style.display = "none";
mount(vOut, h("div", { class: "callout" }, String(e.message || e)));
}
});
async function showVideoResult(j, host) {
const downloads = h("div", { class: "actions" });
for (const kind of j.outputs || []) {
const label = { video: "⬇ AVI", audio: "⬇ WAV", mp4: "⬇ MP4" }[kind];
if (!label) continue;
const b = h("button", { class: "btn sm" }, label);
b.addEventListener("click", async () => {
const { url } = await mediaFileUrl(j.id, kind);
const ext = kind === "video" ? "avi" : kind === "audio" ? "wav" : "mp4";
h("a", { href: url, download: `cortiq-${j.id}.${ext}` }).click();
});
downloads.appendChild(b);
}
if ((j.outputs || []).includes("mp4")) {
// ffmpeg was present server-side → native playback
const { url } = await mediaFileUrl(j.id, "mp4");
mount(host, h("video", { src: url, controls: true, class: "media-canvas" }), downloads);
return;
}
// no ffmpeg anywhere: decode the MJPEG AVI ourselves, sync to the wav
const buf = await mediaFileBytes(j.id, "video");
const frames = aviJpegFrames(buf);
let audio = null;
if ((j.outputs || []).includes("audio")) {
const { url } = await mediaFileUrl(j.id, "audio");
audio = h("audio", { src: url });
}
const player = mjpegPlayer(frames, 24, audio);
player.canvas.className = "media-canvas";
await player.seek0();
const playBtn = h("button", { class: "btn primary sm" }, "▶ " + t("pg.play"));
playBtn.addEventListener("click", async () => {
if (player.state.playing) {
player.pause();
playBtn.textContent = "▶ " + t("pg.play");
} else {
playBtn.textContent = "⏸";
await player.play();
}
});
mount(host, player.canvas, h("div", { class: "actions" }, playBtn, ...downloads.childNodes ? [downloads] : []));
}
videoPanel = h(
"div",
{ class: "pg" },
h(
"div",
{},
h(
"div",
{ class: "card" },
field(t("pg.model"), vModel),
field(t("pg.prompt"), vPrompt),
h("div", { class: "row" }, field(t("pg.width"), vW, t("pg.videoSizeHint")), field(t("pg.height"), vH)),
h("div", { class: "row" }, field(t("pg.frames"), vFrames, t("pg.framesHint")), field(t("pg.steps"), vSteps, t("pg.videoStepsHint"))),
h("div", { class: "row" },
field(t("pg.seed"), h("div", { class: "flex", style: "gap:6px" }, vSeed, dice(vSeed))),
field(t("pg.quality"), vQuality)),
h("div", { class: "row" }, field(t("pg.firstFrame"), vFirst, t("pg.keyframeHint")), field(t("pg.lastFrame"), vLast)),
h("div", { class: "actions" }, vCancel, vGo),
vBar
),
h("div", { class: "card" }, h("div", { class: "card-head" }, h("h3", {}, t("pg.result"))), vOut)
),
vMetrics
);
}
const panels = { chat: chatPanel, image: imagePanel, video: videoPanel };
mount(
root,
h("div", { class: "page-head" }, h("h2", {}, t("pg.title")), h("p", {}, t("pg.subtitle"))),
tabsSeg,
panelHost
);
mount(panelHost, panels.chat);
return root;
}