Qwen3.8-Flash-Next on any consumer hardware: one-click install for Windows / Linux. Strata inference engine, OpenAI/Anthropic API on localhost, optional image input.
C++
App: GPU roles section (Main / Helper / Off per card) replaces the card option list and the expert Run on picker; host writes roles plus the legacy mirror; 46 strings in 8 locales
Niko1221ed61ad2a9cd4
diff --git a/apps/host/server/native-control.mjs b/apps/host/server/native-control.mjsindex 3445a1380..b0aca1308 100644--- a/apps/host/server/native-control.mjs+++ b/apps/host/server/native-control.mjs@@ -21,6 +21,7 @@ import { checkRunConfig, describeIssues } from './run-config-check.mjs';import { openTextFile } from './open-text-file.mjs';import { markEngine, engineRefusal } from './engine-version.mjs';import { friendlyModelName } from './model-names.mjs';+import { parseSaved as parseRoles, mirror as mirrorRoles } from './gpu-roles.mjs';const ROOT=resolve(dirname(fileURLToPath(import.meta.url)),'..');const safeId=value=>typeof value==='string'&&/^[a-z0-9_-]{1,80}$/i.test(value);@@ -207,8 +208,10 @@ return {summary:result.summary??'Deleted',removed:result.plan?.gb??null};}const resources=args.resourceProfile?resourceSettings({...base0,[USER_KEY]:mine,vision},snapshot.hardware,args.resourceProfile,modelArena(args.model),values0):null;const cfg={...config,...visionPreferences,...(resources?{...resources,ui_resource_profile:args.resourceProfile}:{}),host:'127.0.0.1',open_browser:false,...validateNativeSettings(args.values??{}),vision};/* The app's suggested cards only fill a gap: a model whose settings file already names its GPUs ("gpu": [1, 0], with "gpu_order": "as_given") keeps them (#3256). A card the person picked in the screen always wins. */- const namedInFile=Array.isArray(config.gpu)?config.gpu.length>0:config.gpu!==undefined&&config.gpu!==null&&config.gpu!=='';- if(args.gpus!==undefined&&!(args.gpusFromRecommendation&&namedInFile)){const detected=new Set((snapshot.hardware?.gpus??[]).map(g=>g.index));if(!Array.isArray(args.gpus)||!args.gpus.length||new Set(args.gpus).size!==args.gpus.length||args.gpus.some(g=>!Number.isInteger(g)||!detected.has(g)))throw new Error('Choose distinct detected GPUs. CPU-only text inference is not supported by this native adapter.');cfg.gpu=args.gpus.length===1?args.gpus[0]:args.gpus;delete cfg.hip_ordinal;cfg.layer_split=args.gpus.length>1?validateNativeSettings({layer_split:args.layerSplit??'auto'}).layer_split:'auto';if(cfg.layer_split!=='auto'&&cfg.layer_split.split(',').length!==args.gpus.length-1)throw new Error('Choose one layer split point between each pair of GPUs.');}+ const namedInFile=(Array.isArray(config.gpu)?config.gpu.length>0:config.gpu!==undefined&&config.gpu!==null&&config.gpu!=='')||!!config.gpu_roles;+ /* Roles chosen in the screen (Main / Helper / Off per card, gpu-roles.mjs): the card list is the roles' mirror - Helpers first, the Main card LAST, Off cards left out - with "gpu_roles" beside it. Every card Off is allowed: the server says plainly what the engine can do. */+ if(args.gpuRoles!==undefined){const make=snapshot.hardware?.engine_vendor,cards=(snapshot.hardware?.gpus??[]).filter(g=>!make||!g.vendor||g.vendor===make),named=parseRoles(args.gpuRoles);if(!named)throw new Error('Choose Main, Helper or Off for each graphics card, with one Main.');const known=new Set(cards.map(g=>g.index));if(Object.keys(named).some(k=>!known.has(Number(k))))throw new Error('Choose detected graphics cards.');const roles=Object.fromEntries(cards.map(g=>[g.index,named[g.index]??'off'])),m=mirrorRoles(roles,cards);for(const k of ['gpu','gpu_order','gpu_none','gpu_roles','gpu_cards','hip_ordinal'])delete cfg[k];Object.assign(cfg,m);const count=Array.isArray(m.gpu)?m.gpu.length:m.gpu_none?0:1;cfg.layer_split=count>1?validateNativeSettings({layer_split:args.layerSplit??'auto'}).layer_split:'auto';if(cfg.layer_split!=='auto'&&cfg.layer_split.split(',').length!==count-1)throw new Error('Choose one layer split point between each pair of GPUs.');}+ else if(args.gpus!==undefined&&!(args.gpusFromRecommendation&&namedInFile)){const detected=new Set((snapshot.hardware?.gpus??[]).map(g=>g.index));if(!Array.isArray(args.gpus)||!args.gpus.length||new Set(args.gpus).size!==args.gpus.length||args.gpus.some(g=>!Number.isInteger(g)||!detected.has(g)))throw new Error('Choose distinct detected GPUs. CPU-only text inference is not supported by this native adapter.');cfg.gpu=args.gpus.length===1?args.gpus[0]:args.gpus;for(const k of ['gpu_roles','gpu_cards','gpu_none'])delete cfg[k];delete cfg.hip_ordinal;cfg.layer_split=args.gpus.length>1?validateNativeSettings({layer_split:args.layerSplit??'auto'}).layer_split:'auto';if(cfg.layer_split!=='auto'&&cfg.layer_split.split(',').length!==args.gpus.length-1)throw new Error('Choose one layer split point between each pair of GPUs.');}if(cfg.vram_reserve_mib!==undefined&&cfg.vram_reserve_mib!==null){cfg.args=[...(cfg.args??[])];const at=cfg.args.indexOf('--vram-reserve-mib');if(at>=0)cfg.args.splice(at,2);cfg.args.push('--vram-reserve-mib',String(cfg.vram_reserve_mib));}if(mine.length){cfg.args=mergeUserArgs(cfg.args??[],mine);cfg[USER_KEY]=mine;}else delete cfg[USER_KEY];if(cfg.vision){if(cfg.vision_tokens!=null)cfg.vision={...cfg.vision,max_tokens:cfg.vision_tokens};if(cfg.vision_min_tokens!=null)cfg.vision={...cfg.vision,min_tokens:cfg.vision_min_tokens};}cfg.mcp={...(cfg.mcp??{}),...(cfg.mcp_timeout_s!=null?{timeout_s:cfg.mcp_timeout_s}:{}),...(cfg.mcp_max_rounds!=null?{max_rounds:cfg.mcp_max_rounds}:{}),...(cfg.mcp_max_result_chars!=null?{max_result_chars:cfg.mcp_max_result_chars}:{})};diff --git a/apps/host/src/components/GpuRoles.tsx b/apps/host/src/components/GpuRoles.tsxnew file mode 100644index 000000000..b2aa282e4--- /dev/null+++ b/apps/host/src/components/GpuRoles.tsx@@ -0,0 +1,136 @@+import { tr } from '../lib/i18n';+import { useId, useState } from 'react';+import { Btn, Icon } from './ui';+import {+ CPU_ONLY_LINE, NO_CARD_LINE, OFF_AT_OR_BELOW_GB, gpuLabel, noteText, order, recommend, setRole, shortName, vramOn, warnings,+ type Role, type RoleCard, type Roles, type RoleWarning,+} from '../lib/gpu-roles';++const ROLE_WORD: Record<Role, string> = { main: 'Main', helper: 'Helper', off: 'Off' };+const HINT: Record<Role, string> = { main: 'Does the main work', helper: 'Holds part of the model', off: 'Not used' };++/** The one plain line above the cards, built from translated pieces. */+export function recommendationLine(cards: RoleCard[], vendor?: string | null): string {+ const rec = recommend(cards, vendor);+ if (rec.main === null) return tr('No graphics card that Strata can use was found.');+ const byi = new Map(cards.map(c => [c.index, c]));+ const m = byi.get(rec.main)!;+ if (cards.length === 1) return tr('Strata will use your {0}.', [shortName(m)]);+ const why = { same: 'the cards are alike, so the lower number is Main', memory: 'it has more memory', faster: 'it is faster', only: 'it is the only card', none: '' }[rec.why];+ let s = tr('{0} is Main: {1}.', [shortName(m), tr(why)]);+ const helpers = Object.keys(rec.roles).map(Number).filter(i => rec.roles[i] === 'helper').map(i => shortName(byi.get(i)!));+ if (helpers.length) s += ' ' + tr(helpers.length > 1 ? '{0} help.' : '{0} helps.', [helpers.join(', ')]);+ for (const i of Object.keys(rec.roles).map(Number)) if (rec.roles[i] === 'off') {+ const code = rec.reasons[i], c = byi.get(i)!;+ s += ' ' + tr('{0} starts Off: {1}', [shortName(c), code === 'cannot_run' ? tr('Strata cannot run it.') : code === 'igpu' ? tr('built-in graphics.') : tr('{0} GB or less.', [OFF_AT_OR_BELOW_GB])]);+ }+ return s;+}++function warningText(w: RoleWarning, cards: RoleCard[]): string {+ const c = w.card !== null ? cards.find(x => x.index === w.card) : undefined;+ if (w.code === 'cannot_run') return tr('{0} cannot run Strata.', [c ? shortName(c) : '']);+ if (w.code === 'igpu_main') return tr('{0} is built-in graphics; it is slow as Main.', [c ? shortName(c) : '']);+ if (w.code === 'cpu_only') return tr(w.text === CPU_ONLY_LINE ? CPU_ONLY_LINE : NO_CARD_LINE);+ return tr('Not enough memory for this setup: about {0} GB is read from the drive.', [w.text.match(/about (\d+) GB/)?.[1] ?? '']);+}++export function noteLine(code: string | null, cards: RoleCard[]): string {+ if (!code) return '';+ const kind = code.split(':')[0], c = cards.find(x => x.index === Number(code.split(':')[1]));+ if (kind === 'old_main_helper') return tr('{0} is now a Helper.', [c ? shortName(c) : '']);+ if (kind === 'promoted') return tr('{0} is now Main.', [c ? shortName(c) : '']);+ if (kind === 'only_main') return tr('The only card that is on has to be Main.');+ return noteText(code, cards);+}++/**+ * Main / Helper / Off for every graphics card (the mockup GpuRoles-mockup.html). One click changes a role; "Back to recommended" restores the+ * recommendation. Warnings are short and never block Load. `roles` are the roles in force (the recommendation until the person changes one).+ */+export function GpuRoles({ cards, roles, custom, recommendedRoles, vendor, onChange, onBack, memoryGb, ramGb, spillGb = 0, engineRunsCpuOnly = false, disabled = false, usedBy }: {+ cards: RoleCard[];+ roles: Roles;+ /** The person changed a role: "Your choice", and "Back to recommended" is offered. */+ custom: boolean;+ /** The roles Strata recommends (the tags and "Back to recommended" use them); the pure recommendation when not given. */+ recommendedRoles?: Roles;+ vendor?: string | null;+ onChange: (next: Roles) => void;+ onBack: () => void;+ memoryGb?: number | null;+ ramGb?: number | null;+ /** About how many GB of the model are read from the drive with these cards (0 when everything fits or it is unknown). */+ spillGb?: number;+ engineRunsCpuOnly?: boolean;+ disabled?: boolean;+ /** Names of the loaded models that already use a card ("In use by ..."). */+ usedBy?: (card: number) => string[];+}) {+ const titleId = useId();+ const [note, setNote] = useState('');+ const rec = { ...recommend(cards, vendor), ...(recommendedRoles ? { roles: recommendedRoles } : {}) };+ const single = cards.length === 1;+ const warns = warnings(roles, cards, { spillGb, engineRunsCpuOnly });+ const cardWarn = (i: number) => warns.filter(w => w.card === i);+ const globalWarn = warns.filter(w => w.card === null);+ const lst = order(roles, cards);+ const change = (idx: number, role: Role) => {+ const out = setRole(roles, cards, idx, role);+ setNote(noteLine(out.note, cards));+ onChange(out.roles);+ };+ const back = () => { setNote(''); onBack(); };+ const fix = (w: RoleWarning) => w.fix && change(w.fix.card, w.fix.role);+ const fixLabel = (w: RoleWarning) => {+ if (!w.fix) return '';+ const target = cards.find(c => c.index === w.fix!.card);+ return w.fix.role === 'off' ? tr('Turn it off') : tr('Make {0} Main', [target ? shortName(target) : '']);+ };+ const have = vramOn(roles, cards) + Math.max(0, (ramGb ?? 0) - 10);+ return <div className="gpuroles" aria-labelledby={titleId} data-custom={custom}>+ <div className="gpuroles__head">+ <span className="native-choice__label" id={titleId}>{tr('Graphics cards')}</span>+ {custom ? <button type="button" className="gpuroles__link" disabled={disabled} onClick={back}>{tr('Back to recommended')}</button> : null}+ </div>+ <div className="gpuroles__reco" data-custom={custom}>+ <Icon name="bolt" size={18}/>+ <p><strong>{tr(custom ? 'Your choice.' : 'Recommended.')}</strong> {custom ? tr('You changed the roles. Strata will use exactly these.') : recommendationLine(cards, vendor)}</p>+ </div>+ <div className="gpuroles__rows" role="list">+ {cards.map(c => {+ const role = roles[c.index] ?? 'off', isRec = rec.roles[c.index] === role, w = cardWarn(c.index), other = usedBy?.(c.index) ?? [];+ const shared = !!(c.integrated || c.uma || c.unified_gb);+ const options: Role[] = single ? ['main', 'off'] : ['main', 'helper', 'off'];+ return <div className="gpuroles__row" role="listitem" data-role={role} key={c.index}>+ <div className="gpuroles__top">+ <span className="gpuroles__ico"><Icon name="gpu" size={20}/></span>+ <span className="gpuroles__name">+ <strong>{gpuLabel(c)} · {c.name}{isRec ? <span className="gpuroles__tag">{tr('Recommended')}</span> : <span className="gpuroles__tag gpuroles__tag--neutral">{tr('Recommended: {0}', [tr(ROLE_WORD[rec.roles[c.index] ?? 'off'])])}</span>}</strong>+ <small>{shared ? tr("Uses your computer's memory (built-in graphics)") : tr('{0} GB memory', [Math.round(c.vram_gb)])} · {tr(HINT[role])}</small>+ </span>+ <span className="gpuroles__roles" role="radiogroup" aria-label={tr('Role of {0}', [gpuLabel(c)])}>+ {options.map(r => <button type="button" role="radio" key={r} data-r={r} aria-checked={role === r} disabled={disabled} onClick={() => change(c.index, r)}>{tr(ROLE_WORD[r])}</button>)}+ </span>+ </div>+ {other.length ? <div className="gpuroles__note gpuroles__note--info"><Icon name="info" size={16}/><p>{tr('In use by {0}', [other.join(', ')])}</p></div> : null}+ {w.map(x => <div className="gpuroles__note gpuroles__note--warn" key={x.code}><Icon name="warning" size={16}/><p>{warningText(x, cards)}</p>{x.fix ? <Btn size="sm" disabled={disabled} onClick={() => fix(x)}>{fixLabel(x)}</Btn> : null}</div>)}+ </div>;+ })}+ </div>+ <div className="gpuroles__toast" role="status" aria-live="polite">{note ? <div className="gpuroles__note gpuroles__note--info"><Icon name="info" size={16}/><p>{note}</p></div> : null}</div>+ {globalWarn.map(x => <div className="gpuroles__note gpuroles__note--warn" key={x.code}><Icon name="warning" size={16}/><p>{warningText(x, cards)}</p>{x.code === 'cpu_only' && custom ? <Btn size="sm" disabled={disabled} onClick={back}>{tr('Back to recommended')}</Btn> : null}</div>)}+ <details className="gpuroles__details">+ <summary>{tr('Details')}</summary>+ <div className="gpuroles__body">+ <dl>+ <dt>{tr('Main')}</dt><dd>{tr('The card that does the final steps of every answer: it writes the next words, runs the draft-ahead step and checks it, and keeps your conversation. Pick your fastest card with plenty of memory. There is only ever one.')}</dd>+ <dt>{tr('Helper')}</dt><dd>{tr('Holds a share of the model and its fast memory, so more of it fits on graphics cards instead of being read from your drive. Prompts are read about 20% faster.')}</dd>+ <dt>{tr('Off')}</dt><dd>{tr('Strata does not touch this card. Good for a card you use for something else, such as a game or your screen.')}</dd>+ </dl>+ {memoryGb ? <div className="gpuroles__fit" data-state={lst.length ? (spillGb >= 1 ? 'bad' : 'ok') : 'bad'}><span className="gpuroles__dot" aria-hidden="true"/><span>{lst.length ? (spillGb >= 1 ? tr('The model needs about {0} GB. These cards and your memory give about {1} GB, so about {2} GB would be read from your drive.', [Math.round(memoryGb), Math.round(have), Math.round(spillGb)]) : tr('The model needs about {0} GB. These cards and your memory give about {1} GB. It fits.', [Math.round(memoryGb), Math.round(have)])) : tr('Only your processor and memory are used.')}</span></div> : null}+ <div className="gpuroles__expert xs muted">{lst.length ? tr('For experts: the engine starts on cards {0} (Main last).', [lst.join(',')]) : null} {custom ? '' : tr('Not saved while you keep the recommendation: Strata picks again if you add or remove a card.')}</div>+ </div>+ </details>+ </div>;+}diff --git a/apps/host/src/components/NativeModels.tsx b/apps/host/src/components/NativeModels.tsxindex 9be9d933c..26c760e85 100644--- a/apps/host/src/components/NativeModels.tsx+++ b/apps/host/src/components/NativeModels.tsx@@ -4,7 +4,9 @@ import { Screen } from './layout';import { VersionPicker } from './VersionPicker';import { FamilySwitch } from './FamilySwitch';import { PcFitCard } from './PcFitCard';-import { fitOn, runCards } from '../lib/native-fit';+import { fitOn, memoryNeeded } from '../lib/native-fit';+import { GpuRoles } from './GpuRoles';+import { fromLegacy, normalize as normalizeRoles, order as roleOrder, recommend as recommendRoles, rows as roleRows, sameRoles, vramOn, type RoleCard, type Roles } from '../lib/gpu-roles';import { Btn, Dialog, ErrorNotice, Icon, Select } from './ui';import { installProgress, installStage, stageText, useDownloadEta } from '../lib/download-eta';import { useKept } from '../lib/kept-state';@@ -37,8 +39,7 @@ export function NativeModels({ onOtherModels, onReady, onImport, onConnectEngine// The choices are kept while the page is closed (Models -> Monitor -> Models used to start them over and a person lost track of what was downloading).const [family, setFamily] = useKept('models.family', ''), [size, setSize] = useKept('models.size', ''), [context, setContext] = useKept('models.context', 32768), [vision, setVision] = useKept('models.vision', 'yes');const manual = useStore(s => s.setup?.choices?.onboarding?.manual ?? false);- const [expert, setExpert] = useKept('models.expert', manual), [multiple, setMultiple] = useKept('models.multiple', false), [gpus, setGpus] = useKept<number[]>('models.gpus', []), [kv, setKv] = useKept('models.kv', 'int8'), [lowRam, setLowRam] = useKept('models.lowRam', 'auto'), [split, setSplit] = useKept('models.split', 'auto'), [deviceChoice, setDeviceChoice] = useKept('models.device', 'auto');- const [cardsKey, setCardsKey] = useKept<string | null>('models.cards', null);+ const [expert, setExpert] = useKept('models.expert', manual), [multiple, setMultiple] = useKept('models.multiple', false), [roles, setRoles] = useKept<Roles | null>('models.roles', null), [kv, setKv] = useKept('models.kv', 'int8'), [lowRam, setLowRam] = useKept('models.lowRam', 'auto'), [split, setSplit] = useKept('models.split', 'auto');const [resourceProfile, setResourceProfile] = useKept<'work' | 'performance'>('models.profile', 'work');const [pending, setPending] = useState(false), [error, setError] = useState(''), [plan, setPlan] = useState<Record<string, any> | null>(null), [loadedError, setLoadedError] = useState(''), [tuneOpen, setTuneOpen] = useState(false), [jobId, setJobId] = useKept('models.job', ''), [manage, setManage] = useState(false);const [toastedJob, setToastedJob] = useKept('models.toasted', ''), [appliedSig, setAppliedSig] = useKept('models.applied', '');@@ -53,7 +54,7 @@ export function NativeModels({ onOtherModels, onReady, onImport, onConnectEngine// The model that is running is shown as running, with Unload: not offered for loading again.const downloaded = native?.installed?.models ?? [], allSizes = families.flatMap(f => f.sizes);// This computer for the fit figures: the biggest usable graphics card, or the ones chosen under Expert settings.- const runGpus = runCards(native?.hardware?.gpus, native?.hardware?.engine_vendor);+ const engineVendor = native?.hardware?.engine_vendor ?? null, roleCards: RoleCard[] = roleRows(native?.hardware?.gpus as RoleCard[] | undefined, engineVendor);const pcGpus = (native?.hardware?.gpus ?? []).filter(g => g.usable !== false), pcGpu = [...pcGpus].sort((x, y) => y.vram_gb - x.vram_gb)[0] ?? null;const pcRam = native?.hardware?.ram_gb || hardware?.memory.totalGb || null, pcVram = pcGpu?.vram_gb ?? 0;// What the models that stay loaded (Run multiple models) already take: the fit figures are for what is left.@@ -85,19 +86,20 @@ export function NativeModels({ onOtherModels, onReady, onImport, onConnectEngine// Graphics cards (strata_control/gpu_fit.py: the one rule of the app, the Terminal and setup): the recommended option is pre-selected, the person may pick another// A card a loaded model already uses (a second model on it usually does not fit): said on its row, and not the pre-selected one while another is free.const usedBy = (cards: number[]) => (native?.instances ?? []).filter(i => i.status !== 'error' && i.model !== selectedSize?.id && i.gpus.some(g => cards.includes(g))).map(i => i.label);- const cardOptions = selectedSize?.gpu_options && selectedSize.gpu_options.options.length >= 2 ? selectedSize.gpu_options : null;- const loadedCards = loadedSelected ? cardOptions?.options.find(o => o.cards.length === loadedSelected.gpus.length && o.cards.every(c => loadedSelected.gpus.includes(c))) : undefined;- const activeCards = cardOptions ? (cardOptions.options.find(o => o.key === cardsKey) ?? loadedCards ?? (multiple ? cardOptions.options.find(o => o.recommended && !usedBy(o.cards).length) ?? cardOptions.options.find(o => !usedBy(o.cards).length) : undefined) ?? cardOptions.options.find(o => o.recommended) ?? cardOptions.options[0]) : null;- const cardsGpus: number[] = activeCards?.cards ?? [];- const chosenCards = expert && gpus.length ? gpus : cardsGpus;- const fitHardware = { ram_gb: pcRam ? Math.max(0, pcRam - keptRam) : pcRam, vram_gb: Math.max(0, pcVram - keptVramOn(chosenCards)) };- // "(card 1)" in a card name is the number the screens call GPU 2 (Monitor, the model picker, the loaded list): one numbering everywhere.- const gpuNumbers = (text: string) => text.replace(/\(card (\d+)\)/g, (_m, n) => `(GPU ${Number(n) + 1})`);- // The fit sentence for a card choice, less what the kept models take of RAM and of that card's memory.- const lessKept = (words: string, cards: number[]) => { const gone = Math.round(keptRam + keptVramOn(cards)); return gone > 0 ? words.replace(/of the (\d+) GB available/, (_m, n) => `of the ${Math.max(0, Number(n) - gone)} GB available`) : words; };- const shownSize = useRef(selectedSize?.id);- useEffect(() => { if (shownSize.current !== selectedSize?.id) { shownSize.current = selectedSize?.id; setCardsKey(null); } }, [selectedSize?.id]);- const values = useMemo(() => ({ family: selectedSize?.sourceFamily, model: selectedSize?.model, context, vision: selectedSize?.images ? vision : 'no', kv, low_ram: lowRam, resourceProfile, ...(expert && gpus.length === 1 ? { gpu: gpus[0] } : expert && gpus.length ? { gpus: gpus.join(',') } : cardsGpus.length > 1 ? { gpus: cardsGpus.join(',') } : cardsGpus.length === 1 ? { gpu: cardsGpus[0] } : {}), loadAfter: true, multiple: expert && multiple }), [selectedSize?.sourceFamily, selectedSize?.model, context, vision, kv, lowRam, resourceProfile, gpus.join(','), cardsGpus.join(','), expert, multiple]);+ // Main / Helper / Off per card (src/lib/gpu-roles.ts, strata_control/gpu_roles.py): the recommendation until the person changes a role; a loaded model shows what it was started with.+ // With Run multiple models, a card another loaded model already uses starts Off for this one (while a free card exists).+ const busy = (i: number) => expert && multiple && usedBy([i]).length > 0, freeCards = roleCards.filter(c => !busy(c.index));+ const recommended = freeCards.length && freeCards.length < roleCards.length ? { ...recommendRoles(freeCards, engineVendor), roles: { ...Object.fromEntries(roleCards.map(c => [c.index, 'off'])), ...recommendRoles(freeCards, engineVendor).roles } as Roles } : recommendRoles(roleCards, engineVendor);+ const loadedRoles = loadedSelected && roleCards.length > 1 ? fromLegacy(loadedSelected.gpus, roleCards, 'as_given') : null;+ const effectiveRoles: Roles = roleCards.length > 1 ? (roles ? normalizeRoles(roles, roleCards) : loadedRoles ?? recommended.roles) : recommended.roles;+ const customRoles = !sameRoles(effectiveRoles, recommended.roles);+ const changeRoles = (next: Roles) => setRoles(sameRoles(next, recommended.roles) ? null : next);+ const cardsGpus: number[] = roleCards.length > 1 ? roleOrder(effectiveRoles, roleCards) : [];+ const chosenCards = cardsGpus;+ const fitHardware = { ram_gb: pcRam ? Math.max(0, pcRam - keptRam) : pcRam, vram_gb: Math.max(0, (roleCards.length > 1 ? vramOn(effectiveRoles, roleCards) : pcVram) - keptVramOn(chosenCards)) };+ // A layer split written for another number of cards no longer fits: back to automatic.+ useEffect(() => { if (cardsGpus.length <= 1 && split !== 'auto') setSplit('auto'); }, [cardsGpus.length]);+ const values = useMemo(() => ({ family: selectedSize?.sourceFamily, model: selectedSize?.model, context, vision: selectedSize?.images ? vision : 'no', kv, low_ram: lowRam, resourceProfile, ...(cardsGpus.length > 1 ? { gpus: cardsGpus.join(',') } : cardsGpus.length === 1 ? { gpu: cardsGpus[0] } : {}), loadAfter: true, multiple: expert && multiple }), [selectedSize?.sourceFamily, selectedSize?.model, context, vision, kv, lowRam, resourceProfile, cardsGpus.join(','), expert, multiple]);const downloadValues = { ...values, vision: selectedSize?.images && vision !== 'no' ? 'yes' : 'no', loadVision: selectedSize?.images ? vision : 'no' };useEffect(() => { if (!native?.catalog || family)return; const current = native.instances.find(i => i.id === native.defaultId); const rec = native.catalog.recommendation ?? { family: null, model: null }; const loadedFamily = families.find(f => f.sizes.some(s => s.id === current?.model)); const have = new Set((native.installed?.models ?? []).filter(m => m.ready).map(m => m.model)); const installedFamily = families.find(f => f.sizes.some(s => have.has(s.id))); const f = loadedFamily ?? installedFamily ?? families.find(f => f.family === rec.family || f.sizes.some(s => s.sourceFamily === rec.family)) ?? families[0]; if (f) {@@ -149,7 +151,7 @@ export function NativeModels({ onOtherModels, onReady, onImport, onConnectEngine} }async function load() { if (!selectedSize)return; await perform(async () => { if (installed?.ready && context === installed.context && (!selectedSize?.images || vision === 'no' || installed.images && installed.images !== 'off') && (!installed.kv || kv === installed.kv || kv === tunedNow?.fields.kv) && (lowRam === (installed.lowRamMode ?? 'auto') || lowRam === tunedNow?.fields.lowRam)) {- const result = await nativeAction<NativeJob>('operations', { kind: 'load', args: { model: selectedSize.id, resourceProfile, vision: selectedSize?.images ? vision : 'no', multiple: expert && multiple, ...(expert && gpus.length ? { gpus, layerSplit: split } : cardsGpus.length ? { gpus: cardsGpus, gpusFromRecommendation: !cardsKey } : {}), values: {} } });+ const result = await nativeAction<NativeJob>('operations', { kind: 'load', args: { model: selectedSize.id, resourceProfile, vision: selectedSize?.images ? vision : 'no', multiple: expert && multiple, ...(roleCards.length > 1 ? (roles && customRoles ? { gpuRoles: effectiveRoles, layerSplit: expert && cardsGpus.length > 1 ? split : 'auto' } : cardsGpus.length ? { gpus: cardsGpus, gpusFromRecommendation: true, layerSplit: expert && cardsGpus.length > 1 ? split : 'auto' } : {}) : {}), values: {} } });setJobId(result.id);}else@@ -165,10 +167,10 @@ export function NativeModels({ onOtherModels, onReady, onImport, onConnectEnginesetPending(false);} }async function download() { await perform(async () => { const result = await nativeAction<NativeJob>('operations', { kind: 'install', args: downloadValues }); setJobId(result.id); setPlan(null); }); }- return <Screen plainHeader title={<span className="sr-only">{tr("Models")}</span>} titleDetail={<FamilySwitch families={families} selected={selectedFamily?.family} onPick={f => { setFamily(f.family); setSize((f.sizes.find(s => native?.installed?.models.some(m => m.model === s.id && m.ready)) ?? f.sizes[0])?.id ?? ''); setVision('yes'); setError(''); }}/>} actions={<Btn icon="sliders" aria-pressed={expert} aria-expanded={expert} aria-controls="native-expert-settings" onClick={() => { setExpert(v => !v); setMultiple(false); setGpus([]); setDeviceChoice('auto'); }}>{tr(expert ? 'Close expert mode' : 'Expert mode')}</Btn>}>+ return <Screen plainHeader title={<span className="sr-only">{tr("Models")}</span>} titleDetail={<FamilySwitch families={families} selected={selectedFamily?.family} onPick={f => { setFamily(f.family); setSize((f.sizes.find(s => native?.installed?.models.some(m => m.model === s.id && m.ready)) ?? f.sizes[0])?.id ?? ''); setVision('yes'); setError(''); }}/>} actions={<Btn icon="sliders" aria-pressed={expert} aria-expanded={expert} aria-controls="native-expert-settings" onClick={() => { setExpert(v => !v); setMultiple(false); }}>{tr(expert ? 'Close expert mode' : 'Expert mode')}</Btn>}><div className="native-model-layout native-model-layout--fit"><div className="stack">- {tr(native?.instances.length && expert ? <section className="st-card native-running"><h2 className="h4">{tr(native.instances.length === 1 ? 'Loaded model' : 'Loaded models')}</h2>{tr(native.instances.map(i => <div key={i.id}><span><strong>{tr(i.label)}</strong><small>{tr(i.gpus.length ? i.gpus.map(g => `GPU ${g + 1}`).join(' + ') : 'Automatic GPU')} · {tr(i.status === 'ready' ? i.phase : i.status)}{tr(native.defaultId === i.id ? ' · Chat default' : '')}</small>{tr(i.error ? <small className="inline-error">{tr(plainFailureText(i.error).message)}</small> : null)}</span>{tr(expert && multiple && native.defaultId !== i.id ? <Btn size="sm" variant="ghost" onClick={() => void loadedAction(`instances/${i.id}/default`)}>{tr("Use in chat")}</Btn> : null)}<Btn size="sm" disabled={pending || !!active} onClick={() => void loadedAction(`instances/${i.id}/unload`)}>{tr("Unload")}</Btn></div>))}{tr(loadedError ? <ErrorNotice message={loadedError} next={tr("Stop or answer the chat that is still using this model, then try again.")}/> : null)}</section> : null)}+ {tr(native?.instances.length && expert ? <section className="st-card native-running"><h2 className="h4">{tr(native.instances.length === 1 ? 'Loaded model' : 'Loaded models')}</h2>{tr(native.instances.map(i => <div key={i.id}><span><strong>{tr(i.label)}</strong><small>{tr(i.gpus.length ? i.gpus.map((g, n) => `GPU ${g + 1}${i.gpus.length > 1 && n === i.gpus.length - 1 ? ' (Main)' : ''}`).join(' + ') : 'Automatic GPU')} · {tr(i.status === 'ready' ? i.phase : i.status)}{tr(native.defaultId === i.id ? ' · Chat default' : '')}</small>{tr(i.error ? <small className="inline-error">{tr(plainFailureText(i.error).message)}</small> : null)}</span>{tr(expert && multiple && native.defaultId !== i.id ? <Btn size="sm" variant="ghost" onClick={() => void loadedAction(`instances/${i.id}/default`)}>{tr("Use in chat")}</Btn> : null)}<Btn size="sm" disabled={pending || !!active} onClick={() => void loadedAction(`instances/${i.id}/unload`)}>{tr("Unload")}</Btn></div>))}{tr(loadedError ? <ErrorNotice message={loadedError} next={tr("Stop or answer the chat that is still using this model, then try again.")}/> : null)}</section> : null)}<section className="st-card native-choice">{tr(selectedFamily && (!selectedSize || selectedSize.needsNewerEngine) ? <><h2 className="h3">{tr("This model needs a newer engine.")}</h2><p className="small muted">{tr("Update your engine or import a local GGUF for this model.")}</p><Btn onClick={() => { setSettingsSection('Engine'); go('settings'); }}>{tr("Update engine")}</Btn><Btn variant="ghost" onClick={onImport ?? onOtherModels}>{tr("Use a local GGUF\u2026")}</Btn></> : null)}{tr(!selectedFamily ? <><h2 className="h3">{tr("Set up Strata")}</h2><p className="small muted">{tr("Connect your local installation to choose an optimized model.")}</p><Btn variant="primary" onClick={onConnectEngine ?? (() => { setSettingsSection('Engine'); go('settings'); })}>{tr("Connect engine")}</Btn>{tr(native?.error ? <p className="small inline-error">{tr(native.error)}</p> : null)}<Btn variant="ghost" onClick={onOtherModels}>{tr("Other local models")}</Btn></> : null)}{tr(selectedSize ? <><div className="native-choice__head"><span className="native-choice__label">{tr("Version")}</span><span className="native-choice__tools"><NativePresets values={values} onApply={v => { const f = families.find(f => f.family === v.family || f.sizes.some(s => s.sourceFamily === v.family)); if (!f)@@ -179,7 +181,8 @@ export function NativeModels({ onOtherModels, onReady, onImport, onConnectEngine<div className="native-choice__col"><span className="native-choice__label">{tr("Conversation context")}</span><Select ariaLabel={tr("Conversation context")} value={String(context)} options={contextChoices(native?.catalog?.contexts ?? [8192, 32768, 65536, 131072, 262144], context).map(n => ({ value: String(n), label: n % 1024 === 0 ? `${n / 1024}K` : `${n.toLocaleString()} tokens` }))} onChange={n => setContext(Number(n))}/></div><div className="native-choice__col"><span className="native-choice__label">{tr("Computer use")}</span><div className="native-resource-choice"><button aria-pressed={resourceProfile === 'work'} data-selected={resourceProfile === 'work'} onClick={() => setResourceProfile('work')}><Icon name="computer" size={20}/><span><strong>{tr("Leave 20% for my work")}</strong><small>{tr("Headroom for your other apps")}</small></span>{tr(resourceProfile === 'work' ? <Icon name="check" size={15}/> : null)}</button><button aria-pressed={resourceProfile === 'performance'} data-selected={resourceProfile === 'performance'} onClick={() => setResourceProfile('performance')}><Icon name="bolt" size={20}/><span><strong>{tr("Full performance")}</strong><small>{tr("Give Strata priority")}</small></span>{tr(resourceProfile === 'performance' ? <Icon name="check" size={15}/> : null)}</button></div></div></div>- {tr(cardOptions ? <div className="native-cards"><span className="native-choice__label">{tr("Graphics cards")}</span><div className="native-cards__list" role="radiogroup" aria-label={tr("Graphics cards")}>{cardOptions.options.map(o => { const on = activeCards?.key === o.key; return <button key={o.key} type="button" role="radio" aria-checked={on} data-selected={on} disabled={!!active} className="native-cards__opt" onClick={() => setCardsKey(o.key)}><span className="native-cards__dot" aria-hidden="true"/><span><strong>{gpuNumbers(o.label)}</strong><small data-warn={o.verdict === 'spills' || o.verdict === 'tight' || usedBy(o.cards).length > 0}>{[lessKept(o.words, o.cards), ...o.notes, ...(usedBy(o.cards).length ? [tr('Already used by {0}', [usedBy(o.cards).join(', ')])] : [])].join('. ')}.</small></span></button>; })}{cardOptions.ignored.length ? <p className="small muted native-cards__note">{`Not used: ${cardOptions.ignored.map(g => `${g.name ?? 'a card'} (${g.why_ignored})`).join('; ')}.`}</p> : null}</div></div> : null)}+ {roleCards.length > 1 ? <GpuRoles cards={roleCards} roles={effectiveRoles} custom={customRoles} recommendedRoles={recommended.roles} vendor={engineVendor} disabled={!!active} onChange={changeRoles} onBack={() => setRoles(null)} memoryGb={selectedSize ? memoryNeeded(selectedSize) || null : null} ramGb={pcRam} spillGb={selectedSize ? fitOn(selectedSize, fitHardware).spillGb : 0} usedBy={i => usedBy([i])}/> : null}+ {tr(roleCards.length > 1 && (native?.hardware?.gpus ?? []).length > roleCards.length ? <p className="small muted native-cards__note">{tr('Not used: {0} (another make of graphics card than this engine drives).', [(native?.hardware?.gpus ?? []).filter(g => !roleCards.some(r => r.index === g.index && r.vendor === g.vendor)).map(g => g.name).join(', ')])}</p> : null)}{tr(selectedSize?.imagesCapable && !selectedSize.images ? <p className="small muted native-spill-note">{tr("This model can read pictures, but the engine installed here does not include the picture reader yet, so Read pictures is off. Update the engine in Settings → About to turn it on.")}</p> : null)}{tr(selectedSize?.images ? <><div className="native-image-reading"><label><input type="checkbox" checked={vision !== 'no'} disabled={!selectedSize?.images || !!active} onChange={e => setVision(e.target.checked ? 'yes' : 'no')}/><span><strong>{tr("Read pictures ")}<small>{tr("On by default")}</small></strong><small>{tr("Understand photos, screenshots and charts. The picture files download automatically. Turn it off to save memory.")}</small></span></label>{tr(expert && vision !== 'no' ? <Select ariaLabel={tr("Image encoder device")} value={vision === 'yes' ? 'yes' : vision} options={[{ value: 'yes', label: 'Automatic' }, { value: 'gpu', label: 'GPU' }, { value: 'cpu', label: 'CPU' }]} onChange={setVision}/> : null)}</div>{tr(vision !== 'no' && installed?.ready && installed.visionPrepared === false ? <div className="native-vision-missing" role="status"><span>{tr("Picture reading needs a few more files that are not on this computer yet.")}</span><Btn size="sm" disabled={pending || !!active} onClick={() => void download()}>{tr("Download picture-reading files")}</Btn></div> : null)}</> : null)}</> : null)}@@ -188,10 +191,10 @@ export function NativeModels({ onOtherModels, onReady, onImport, onConnectEngine{tr(job?.state === 'error' ? <ErrorNotice message={job.error ?? job.summary} action={tr("Retry")} onRetry={() => void load()}/> : null)}{tr(error ? <ErrorNotice message={error}/> : null)}{selectedSize && installed?.ready ? <NativeTuneBadge model={selectedSize.id} resourceProfile={resourceProfile} vision={selectedSize.images ? vision : 'no'}/> : null}- <div className="native-model-actions">{tr(loadedSelected ? <><Btn disabled={pending || !!active} onClick={() => void perform(() => nativeAction(`instances/${loadedSelected.id}/unload`))}>{tr("Unload")}</Btn>{tr(onReady ? <Btn variant="primary" onClick={onReady}>{tr("Start chatting")}</Btn> : <span className="native-ready">{tr("Ready")}</span>)}</> : onReady && native?.instances.some(i => i.status === 'ready') ? <Btn variant="primary" onClick={onReady}>{tr("Start chatting")}</Btn> : <><Btn icon="gauge" disabled={!installed?.ready || !native?.available || !!active || !selectedSize || selectedSize.needsNewerEngine} onClick={() => setTuneOpen(true)}>{tr("Tune model")}</Btn><Btn variant="primary" icon="models" disabled={pending || !native?.available || !!active || !selectedSize || !!selectedSize.needsNewerEngine || expert && deviceChoice === 'split' && gpus.length < 2} onClick={() => void load()}>{tr(pending ? 'Checking…' : installed?.ready ? 'Load model' : 'Download & load')}</Btn></>)}</div>+ <div className="native-model-actions">{tr(loadedSelected ? <><Btn disabled={pending || !!active} onClick={() => void perform(() => nativeAction(`instances/${loadedSelected.id}/unload`))}>{tr("Unload")}</Btn>{tr(onReady ? <Btn variant="primary" onClick={onReady}>{tr("Start chatting")}</Btn> : <span className="native-ready">{tr("Ready")}</span>)}</> : onReady && native?.instances.some(i => i.status === 'ready') ? <Btn variant="primary" onClick={onReady}>{tr("Start chatting")}</Btn> : <><Btn icon="gauge" disabled={!installed?.ready || !native?.available || !!active || !selectedSize || selectedSize.needsNewerEngine} onClick={() => setTuneOpen(true)}>{tr("Tune model")}</Btn><Btn variant="primary" icon="models" disabled={pending || !native?.available || !!active || !selectedSize || !!selectedSize.needsNewerEngine} onClick={() => void load()}>{tr(pending ? 'Checking…' : installed?.ready ? 'Load model' : 'Download & load')}</Btn></>)}</div></section>{tr(expert && IMAGE_GENERATION_VISIBLE ? <><details className="native-generation"><summary>{tr("Image generation ")}<span className="muted">{tr("Optional")}</span></summary><RunImageModel library={imageLibrary} disabled={pending || !!active} onChange={() => { }}/></details></> : null)}- {tr(expert ? <section id="native-expert-settings" ref={expertSection} className="st-card native-execution"><h2 className="h4">{tr("Expert settings")}</h2>{tr(tunedNow ? <p className="small muted native-tuned-note">{tr("Showing the values of your tuning '{0}'.", [tunedNow.name])}</p> : null)}<label className="native-toggle"><span><strong>{tr("Run multiple models")}</strong><small>{tr("Loading another model keeps the others loaded.")}</small></span><button className="st-toggle" role="switch" aria-label={tr("Run multiple models")} aria-checked={multiple} onClick={() => setMultiple(v => !v)}/></label><h3 className="small strong">{tr("Run on")}</h3><p className="small muted">{tr("Automatic uses the installation\u2019s GPU placement. Choose a GPU, or split this model across several GPUs.")}</p><Select ariaLabel={tr("Run on")} value={deviceChoice} options={[{ value: 'auto', label: 'Automatic' }, ...runGpus.map(g => ({ value: String(g.index), label: `GPU ${g.index + 1} · ${g.name}` })), ...(runGpus.length > 1 ? [{ value: 'split', label: 'Split across GPUs…' }] : [])]} onChange={value => { setDeviceChoice(value); setGpus(value === 'auto' ? [] : value === 'split' ? runGpus.map(g => g.index) : [Number(value)]); }}/>{tr(deviceChoice === 'split' ? <div className="native-gpu-options">{tr(runGpus.map(g => <label key={g.index}><input type="checkbox" checked={gpus.includes(g.index)} onChange={e => setGpus(old => e.target.checked ? [...old, g.index] : old.filter(i => i !== g.index))}/><span>{tr("GPU ")}{tr(g.index + 1)} · {tr(g.name)}<small>{tr(g.vram_gb)}{tr(" GB VRAM")}</small></span></label>))}</div> : null)}{tr(gpus.length > 1 ? <label className="input-field"><span>{tr("Layer split")}</span><input className="st-input" value={split} placeholder={tr("auto or 16,32")} onChange={e => setSplit(e.target.value)}/></label> : null)}<div className="native-field-grid"><label className="input-field"><span>{tr("Context memory")}</span><Select ariaLabel={tr("Native KV format")} value={kv} options={[{ value: 'int8', label: 'INT8' }, { value: 'q4_0', label: 'Q4' }, { value: 'k8v4', label: 'K8 / V4' }]} onChange={setKv}/></label><label className="input-field"><span>{tr("Low-RAM mode")}</span><Select ariaLabel={tr("Native low RAM mode")} value={lowRam} options={['auto', 'resident', 'mmap'].map(v => ({ value: v, label: v === 'auto' ? 'Automatic' : v === 'resident' ? 'Keep experts in RAM' : 'Read experts from disk' }))} onChange={setLowRam}/></label></div>{tr(installed ? <><NativeSettingsFile model={installed.model}/><NativeSettings model={installed.model}/></> : <p className="small muted">{tr("More engine parameters become available after preparing this version.")}</p>)}</section> : null)}+ {tr(expert ? <section id="native-expert-settings" ref={expertSection} className="st-card native-execution"><h2 className="h4">{tr("Expert settings")}</h2>{tr(tunedNow ? <p className="small muted native-tuned-note">{tr("Showing the values of your tuning '{0}'.", [tunedNow.name])}</p> : null)}<label className="native-toggle"><span><strong>{tr("Run multiple models")}</strong><small>{tr("Loading another model keeps the others loaded.")}</small></span><button className="st-toggle" role="switch" aria-label={tr("Run multiple models")} aria-checked={multiple} onClick={() => setMultiple(v => !v)}/></label>{tr(cardsGpus.length > 1 ? <label className="input-field"><span>{tr("Layer split")}</span><input className="st-input" value={split} placeholder={tr("auto or 16,32")} onChange={e => setSplit(e.target.value)}/></label> : null)}<div className="native-field-grid"><label className="input-field"><span>{tr("Context memory")}</span><Select ariaLabel={tr("Native KV format")} value={kv} options={[{ value: 'int8', label: 'INT8' }, { value: 'q4_0', label: 'Q4' }, { value: 'k8v4', label: 'K8 / V4' }]} onChange={setKv}/></label><label className="input-field"><span>{tr("Low-RAM mode")}</span><Select ariaLabel={tr("Native low RAM mode")} value={lowRam} options={['auto', 'resident', 'mmap'].map(v => ({ value: v, label: v === 'auto' ? 'Automatic' : v === 'resident' ? 'Keep experts in RAM' : 'Read experts from disk' }))} onChange={setLowRam}/></label></div>{tr(installed ? <><NativeSettingsFile model={installed.model}/><NativeSettings model={installed.model}/></> : <p className="small muted">{tr("More engine parameters become available after preparing this version.")}</p>)}</section> : null)}</div><aside className="stack stack--lg"><PcFitCard gpuName={pcGpu?.name} ramGb={pcRam} vramGb={pcVram} inUse={keptModels.length ? { ramGb: Math.round(keptRam), vramGb: Math.round(keptVramOn(chosenCards)) } : null} fit={selectedSize ? fitOn(selectedSize, fitHardware) : null}/><section className="st-card"><h2 className="h4">{tr("Model files")}</h2><p className="small muted">{tr("Strata prepares all shards, the draft layer and shared files. Completed downloads are reused.")}</p><code className="native-path">{installed?.dataFolder ?? native?.downloadDirectory ?? native?.installed?.data_folder ?? 'Choose an installation'}</code><Btn size="sm" variant="ghost" onClick={() => { setSettingsSection('Storage'); go('settings'); }}>{tr("Storage settings")}</Btn></section><Btn size="sm" variant="ghost" onClick={onOtherModels}>{tr("Other local models\u2026")}</Btn></aside></div>diff --git a/apps/host/src/lib/native.ts b/apps/host/src/lib/native.tsindex cc8906235..b0cd1a1ac 100644--- a/apps/host/src/lib/native.ts+++ b/apps/host/src/lib/native.ts@@ -12,7 +12,7 @@ export interface NativeState {/** The picture reader (strata-vision) is installed with the engine, so models marked for pictures can read them here. *//** Strata Control's view of the engine for this computer (the app): usable false = none found or recognised; `notice` says why in plain words. */engine?:{usable:boolean;notice?:string|null;wrongMake?:boolean;version?:string|null};- visionReader?: boolean;available:boolean;repo:string;downloadDirectory?:string;/** Free bytes on the drive that holds the models folder. */downloadFreeBytes?:number|null;downloadTotalBytes?:number|null;version?:string|null;summary:string;error:string|null;catalog:{families:NativeFamily[];contexts:number[];recommendation:{family:string|null;model:string|null;context?:number;why?:string};context_note:string}|null;installed:{models:{model:string;config:string;model_name:string;ready:boolean;/** The picture-reading files are on this computer (notes-split-agent8.md, item 8). */visionPrepared?:boolean;context?:number;kv?:string;images?:string;visionEnabled?:boolean;visionDevice?:string;lowRamMode?:string;resourceProfile?:'work'|'performance';dataFolder?:string;diskGb?:number;diskBytes?:number;/** Files this model shares with another (the picture reader, the draft layer): counted once, in `usage`. */sharedBytes?:number;/** What Delete frees: files in Strata's own folders that no other model uses. */removableGb?:number;missing_files?:string[]}[];/** What all models take on disk, from their real files, shared files counted once. */usage?:{total_bytes:number;total_gb:number;shared_bytes:number;shared_gb:number;models:Record<string,{bytes:number;gb:number}>}|null;data_folder:string;engine:{version:string|null}}|null;hardware:{ram_gb:number;engine_vendor?:string;gpus:{index:number;name:string;vram_gb:number;usable:boolean;vendor?:string;uma?:boolean;integrated?:boolean;unified_gb?:number;problem?:string|null}[]}|null;fields:NativeField[];instances:NativeInstance[];defaultId:string|null;jobs:NativeJob[];capabilities:{responses?:boolean;updates:boolean;rollback:boolean;calibration:boolean;componentUpdates?:boolean}}+ visionReader?: boolean;available:boolean;repo:string;downloadDirectory?:string;/** Free bytes on the drive that holds the models folder. */downloadFreeBytes?:number|null;downloadTotalBytes?:number|null;version?:string|null;summary:string;error:string|null;catalog:{families:NativeFamily[];contexts:number[];recommendation:{family:string|null;model:string|null;context?:number;why?:string};context_note:string}|null;installed:{models:{model:string;config:string;model_name:string;ready:boolean;/** The picture-reading files are on this computer (notes-split-agent8.md, item 8). */visionPrepared?:boolean;context?:number;kv?:string;images?:string;visionEnabled?:boolean;visionDevice?:string;lowRamMode?:string;resourceProfile?:'work'|'performance';dataFolder?:string;diskGb?:number;diskBytes?:number;/** Files this model shares with another (the picture reader, the draft layer): counted once, in `usage`. */sharedBytes?:number;/** What Delete frees: files in Strata's own folders that no other model uses. */removableGb?:number;missing_files?:string[]}[];/** What all models take on disk, from their real files, shared files counted once. */usage?:{total_bytes:number;total_gb:number;shared_bytes:number;shared_gb:number;models:Record<string,{bytes:number;gb:number}>}|null;data_folder:string;engine:{version:string|null}}|null;hardware:{ram_gb:number;engine_vendor?:string;gpus:{index:number;name:string;vram_gb:number;usable:boolean;/** SMs x clock: only the order between cards matters (strata_control/gpu_roles.py). */speed?:number;vendor?:string;uma?:boolean;integrated?:boolean;unified_gb?:number;problem?:string|null}[]}|null;fields:NativeField[];instances:NativeInstance[];defaultId:string|null;jobs:NativeJob[];capabilities:{responses?:boolean;updates:boolean;rollback:boolean;calibration:boolean;componentUpdates?:boolean}}let state:NativeState|null=null;const listeners=new Set<()=>void>();function put(value:NativeState){if(state&&JSON.stringify(state)===JSON.stringify(value))return;state=value;listeners.forEach(fn=>fn());}diff --git a/apps/host/src/locales/de.json b/apps/host/src/locales/de.jsonindex 8b0b25ca2..fa6c50540 100644--- a/apps/host/src/locales/de.json+++ b/apps/host/src/locales/de.json@@ -3443,5 +3443,51 @@"s8419": "Verschieben beenden","s8420": "Belassen","s8421": "Beenden legt alle Ihre Modelle in {1} ab. Belassen lässt sie in {0} und entfernt die unvollständigen Kopien aus {1}.",- "s8422": "Die unvollständigen Kopien wurden entfernt. Ihre Modelle liegen in {0}."+ "s8422": "Die unvollständigen Kopien wurden entfernt. Ihre Modelle liegen in {0}.",+ "s8601": "Grafikkarten",+ "s8602": "Haupt",+ "s8603": "Helfer",+ "s8604": "Ihre Wahl.",+ "s8605": "Empfohlen.",+ "s8606": "Sie haben die Rollen geändert. Strata verwendet genau diese.",+ "s8607": "Empfohlen: {0}",+ "s8608": "Rolle von {0}",+ "s8609": "{0} GB Speicher",+ "s8610": "Nutzt den Arbeitsspeicher Ihres Computers (integrierte Grafik)",+ "s8611": "Macht die Hauptarbeit",+ "s8612": "Hält einen Teil des Modells",+ "s8613": "Nicht genutzt",+ "s8614": "Wird von {0} verwendet",+ "s8615": "Ausschalten",+ "s8616": "{0} zur Hauptkarte machen",+ "s8617": "{0} kann Strata nicht ausführen.",+ "s8618": "{0} ist integrierte Grafik; als Hauptkarte ist sie langsam.",+ "s8619": "Nur mit der CPU ist die Leistung eingeschränkt.",+ "s8620": "Diese Engine braucht zum Start eine Grafikkarte. Schalten Sie eine ein.",+ "s8621": "Nicht genug Speicher für diese Einstellung: etwa {0} GB werden vom Laufwerk gelesen.",+ "s8622": "{0} ist jetzt ein Helfer.",+ "s8623": "{0} ist jetzt die Hauptkarte.",+ "s8624": "Die einzige eingeschaltete Karte muss die Hauptkarte sein.",+ "s8625": "Es wurde keine Grafikkarte gefunden, die Strata nutzen kann.",+ "s8626": "Strata verwendet Ihre {0}.",+ "s8627": "{0} ist die Hauptkarte: {1}.",+ "s8628": "die Karten sind gleich, daher ist die niedrigere Nummer die Hauptkarte",+ "s8629": "sie hat mehr Speicher",+ "s8630": "sie ist schneller",+ "s8631": "sie ist die einzige Karte",+ "s8632": "{0} helfen.",+ "s8633": "{0} hilft.",+ "s8634": "{0} startet ausgeschaltet: {1}",+ "s8635": "Strata kann sie nicht ausführen.",+ "s8636": "integrierte Grafik.",+ "s8637": "{0} GB oder weniger.",+ "s8638": "Die Karte, die die letzten Schritte jeder Antwort übernimmt: Sie schreibt die nächsten Wörter, führt den Vorausschau-Schritt aus, prüft ihn und hält Ihr Gespräch. Wählen Sie Ihre schnellste Karte mit viel Speicher. Es gibt immer nur eine.",+ "s8639": "Hält einen Teil des Modells und seines schnellen Speichers, sodass mehr davon auf den Grafikkarten Platz findet statt vom Laufwerk gelesen zu werden. Prompts werden etwa 20 % schneller gelesen.",+ "s8640": "Strata rührt diese Karte nicht an. Gut für eine Karte, die Sie anderweitig nutzen, etwa für ein Spiel oder Ihren Bildschirm.",+ "s8641": "Das Modell braucht etwa {0} GB. Diese Karten und Ihr Arbeitsspeicher bieten etwa {1} GB. Es passt.",+ "s8642": "Das Modell braucht etwa {0} GB. Diese Karten und Ihr Arbeitsspeicher bieten etwa {1} GB, daher würden etwa {2} GB vom Laufwerk gelesen.",+ "s8643": "Nur Ihr Prozessor und Arbeitsspeicher werden verwendet.",+ "s8644": "Für Experten: Die Engine startet auf den Karten {0} (Hauptkarte zuletzt).",+ "s8645": "Wird nicht gespeichert, solange Sie die Empfehlung behalten: Strata wählt neu, wenn Sie eine Karte hinzufügen oder entfernen.",+ "s8646": "Nicht genutzt: {0} (anderer Grafikkarten-Hersteller als der, den diese Engine ansteuert)."}diff --git a/apps/host/src/locales/en.json b/apps/host/src/locales/en.jsonindex 2f0c9903b..2609d43d4 100644--- a/apps/host/src/locales/en.json+++ b/apps/host/src/locales/en.json@@ -3443,5 +3443,51 @@"s8419": "Finish the move","s8420": "Leave it","s8421": "Finishing puts all your models in {1}. Leaving it keeps them in {0} and removes the partial copies from {1}.",- "s8422": "The partial copies were removed. Your models are in {0}."+ "s8422": "The partial copies were removed. Your models are in {0}.",+ "s8601": "Graphics cards",+ "s8602": "Main",+ "s8603": "Helper",+ "s8604": "Your choice.",+ "s8605": "Recommended.",+ "s8606": "You changed the roles. Strata will use exactly these.",+ "s8607": "Recommended: {0}",+ "s8608": "Role of {0}",+ "s8609": "{0} GB memory",+ "s8610": "Uses your computer's memory (built-in graphics)",+ "s8611": "Does the main work",+ "s8612": "Holds part of the model",+ "s8613": "Not used",+ "s8614": "In use by {0}",+ "s8615": "Turn it off",+ "s8616": "Make {0} Main",+ "s8617": "{0} cannot run Strata.",+ "s8618": "{0} is built-in graphics; it is slow as Main.",+ "s8619": "Performance is degraded on CPU only.",+ "s8620": "This engine needs a graphics card to start. Turn one on.",+ "s8621": "Not enough memory for this setup: about {0} GB is read from the drive.",+ "s8622": "{0} is now a Helper.",+ "s8623": "{0} is now Main.",+ "s8624": "The only card that is on has to be Main.",+ "s8625": "No graphics card that Strata can use was found.",+ "s8626": "Strata will use your {0}.",+ "s8627": "{0} is Main: {1}.",+ "s8628": "the cards are alike, so the lower number is Main",+ "s8629": "it has more memory",+ "s8630": "it is faster",+ "s8631": "it is the only card",+ "s8632": "{0} help.",+ "s8633": "{0} helps.",+ "s8634": "{0} starts Off: {1}",+ "s8635": "Strata cannot run it.",+ "s8636": "built-in graphics.",+ "s8637": "{0} GB or less.",+ "s8638": "The card that does the final steps of every answer: it writes the next words, runs the draft-ahead step and checks it, and keeps your conversation. Pick your fastest card with plenty of memory. There is only ever one.",+ "s8639": "Holds a share of the model and its fast memory, so more of it fits on graphics cards instead of being read from your drive. Prompts are read about 20% faster.",+ "s8640": "Strata does not touch this card. Good for a card you use for something else, such as a game or your screen.",+ "s8641": "The model needs about {0} GB. These cards and your memory give about {1} GB. It fits.",+ "s8642": "The model needs about {0} GB. These cards and your memory give about {1} GB, so about {2} GB would be read from your drive.",+ "s8643": "Only your processor and memory are used.",+ "s8644": "For experts: the engine starts on cards {0} (Main last).",+ "s8645": "Not saved while you keep the recommendation: Strata picks again if you add or remove a card.",+ "s8646": "Not used: {0} (another make of graphics card than this engine drives)."}diff --git a/apps/host/src/locales/es.json b/apps/host/src/locales/es.jsonindex af4f2cd7f..37158a49e 100644--- a/apps/host/src/locales/es.json+++ b/apps/host/src/locales/es.json@@ -3443,5 +3443,51 @@"s8419": "Terminar el traslado","s8420": "Dejarlo","s8421": "Terminar pone todos sus modelos en {1}. Dejarlo los mantiene en {0} y elimina las copias parciales de {1}.",- "s8422": "Se eliminaron las copias parciales. Sus modelos están en {0}."+ "s8422": "Se eliminaron las copias parciales. Sus modelos están en {0}.",+ "s8601": "Tarjetas gráficas",+ "s8602": "Principal",+ "s8603": "Ayudante",+ "s8604": "Tu elección.",+ "s8605": "Recomendado.",+ "s8606": "Cambiaste los roles. Strata usará exactamente estos.",+ "s8607": "Recomendado: {0}",+ "s8608": "Rol de {0}",+ "s8609": "{0} GB de memoria",+ "s8610": "Usa la memoria de tu equipo (gráficos integrados)",+ "s8611": "Hace el trabajo principal",+ "s8612": "Guarda parte del modelo",+ "s8613": "No se usa",+ "s8614": "En uso por {0}",+ "s8615": "Apagarla",+ "s8616": "Hacer principal a {0}",+ "s8617": "{0} no puede ejecutar Strata.",+ "s8618": "{0} son gráficos integrados; como principal es lenta.",+ "s8619": "El rendimiento se reduce al usar solo la CPU.",+ "s8620": "Este motor necesita una tarjeta gráfica para arrancar. Activa una.",+ "s8621": "Memoria insuficiente para esta configuración: unos {0} GB se leen del disco.",+ "s8622": "{0} ahora es ayudante.",+ "s8623": "{0} ahora es la principal.",+ "s8624": "La única tarjeta activada tiene que ser la principal.",+ "s8625": "No se encontró ninguna tarjeta gráfica que Strata pueda usar.",+ "s8626": "Strata usará tu {0}.",+ "s8627": "{0} es la principal: {1}.",+ "s8628": "las tarjetas son iguales, así que la de menor número es la principal",+ "s8629": "tiene más memoria",+ "s8630": "es más rápida",+ "s8631": "es la única tarjeta",+ "s8632": "{0} ayudan.",+ "s8633": "{0} ayuda.",+ "s8634": "{0} empieza apagada: {1}",+ "s8635": "Strata no puede ejecutarla.",+ "s8636": "gráficos integrados.",+ "s8637": "{0} GB o menos.",+ "s8638": "La tarjeta que hace los pasos finales de cada respuesta: escribe las siguientes palabras, ejecuta el paso de adelanto y lo comprueba, y guarda tu conversación. Elige tu tarjeta más rápida con mucha memoria. Solo hay una.",+ "s8639": "Guarda una parte del modelo y de su memoria rápida, así cabe más en las tarjetas gráficas en lugar de leerse del disco. Los prompts se leen un 20 % más rápido.",+ "s8640": "Strata no toca esta tarjeta. Útil para una tarjeta que usas para otra cosa, como un juego o tu pantalla.",+ "s8641": "El modelo necesita unos {0} GB. Estas tarjetas y tu memoria suman unos {1} GB. Cabe.",+ "s8642": "El modelo necesita unos {0} GB. Estas tarjetas y tu memoria suman unos {1} GB, así que unos {2} GB se leerían del disco.",+ "s8643": "Solo se usan tu procesador y tu memoria.",+ "s8644": "Para expertos: el motor arranca en las tarjetas {0} (la principal al final).",+ "s8645": "No se guarda mientras mantengas la recomendación: Strata elige de nuevo si añades o quitas una tarjeta.",+ "s8646": "No se usa: {0} (otra marca de tarjeta gráfica distinta de la que maneja este motor)."}diff --git a/apps/host/src/locales/ja.json b/apps/host/src/locales/ja.jsonindex 1b29a58bc..d5d0caac1 100644--- a/apps/host/src/locales/ja.json+++ b/apps/host/src/locales/ja.json@@ -3443,5 +3443,51 @@"s8419": "移動を完了する","s8420": "中止する","s8421": "完了すると、すべてのモデルが {1} に入ります。中止すると、モデルは {0} に残り、{1} の不完全なコピーが削除されます。",- "s8422": "不完全なコピーを削除しました。モデルは {0} にあります。"+ "s8422": "不完全なコピーを削除しました。モデルは {0} にあります。",+ "s8601": "グラフィックカード",+ "s8602": "メイン",+ "s8603": "ヘルパー",+ "s8604": "あなたの選択です。",+ "s8605": "おすすめです。",+ "s8606": "役割を変更しました。Strata はこのとおりに使います。",+ "s8607": "おすすめ:{0}",+ "s8608": "{0} の役割",+ "s8609": "メモリ {0} GB",+ "s8610": "コンピューター本体のメモリを使います(内蔵グラフィックス)",+ "s8611": "主な処理を担当",+ "s8612": "モデルの一部を保持",+ "s8613": "使用しません",+ "s8614": "{0} が使用中",+ "s8615": "オフにする",+ "s8616": "{0} をメインにする",+ "s8617": "{0} では Strata を実行できません。",+ "s8618": "{0} は内蔵グラフィックスで、メインにすると遅くなります。",+ "s8619": "CPU のみの場合、性能が低下します。",+ "s8620": "このエンジンの起動にはグラフィックカードが必要です。1 枚オンにしてください。",+ "s8621": "この設定ではメモリが足りません。約 {0} GB をドライブから読み込みます。",+ "s8622": "{0} はヘルパーになりました。",+ "s8623": "{0} がメインになりました。",+ "s8624": "オンになっている唯一のカードはメインでなければなりません。",+ "s8625": "Strata が使えるグラフィックカードが見つかりません。",+ "s8626": "Strata は {0} を使います。",+ "s8627": "{0} がメインです:{1}。",+ "s8628": "カードが同じなので番号の小さい方がメインです",+ "s8629": "メモリが多いため",+ "s8630": "より高速なため",+ "s8631": "唯一のカードのため",+ "s8632": "{0} がサポートします。",+ "s8633": "{0} がサポートします。",+ "s8634": "{0} は最初オフです:{1}",+ "s8635": "Strata では実行できません。",+ "s8636": "内蔵グラフィックスです。",+ "s8637": "{0} GB 以下です。",+ "s8638": "回答の最後の工程を担当するカードです。次の単語を書き、先読みの工程を実行して確認し、会話を保持します。メモリに余裕のある一番速いカードを選んでください。常に 1 枚だけです。",+ "s8639": "モデルの一部と高速メモリを保持し、ドライブから読み込む代わりにより多くをグラフィックカード上に置けます。プロンプトの読み込みが約 20% 速くなります。",+ "s8640": "Strata はこのカードに触れません。ゲームや画面表示など、別の用途に使うカードに向いています。",+ "s8641": "モデルには約 {0} GB が必要です。これらのカードとメモリで約 {1} GB あり、収まります。",+ "s8642": "モデルには約 {0} GB が必要です。これらのカードとメモリは約 {1} GB のため、約 {2} GB がドライブから読み込まれます。",+ "s8643": "プロセッサとメモリのみを使います。",+ "s8644": "上級者向け:エンジンはカード {0} で起動します(メインが最後)。",+ "s8645": "おすすめのままの間は保存されません。カードを追加・取り外すと Strata が選び直します。",+ "s8646": "未使用:{0}(このエンジンが対応するのとは別メーカーのカードです)。"}diff --git a/apps/host/src/locales/ko.json b/apps/host/src/locales/ko.jsonindex 4d6f84108..b103fa278 100644--- a/apps/host/src/locales/ko.json+++ b/apps/host/src/locales/ko.json@@ -3443,5 +3443,51 @@"s8419": "이동 마무리","s8420": "그대로 두기","s8421": "마무리하면 모든 모델이 {1}에 들어갑니다. 그대로 두면 모델은 {0}에 남고 {1}의 불완전한 복사본이 삭제됩니다.",- "s8422": "불완전한 복사본을 삭제했습니다. 모델은 {0}에 있습니다."+ "s8422": "불완전한 복사본을 삭제했습니다. 모델은 {0}에 있습니다.",+ "s8601": "그래픽 카드",+ "s8602": "메인",+ "s8603": "헬퍼",+ "s8604": "직접 고른 설정입니다.",+ "s8605": "추천 설정입니다.",+ "s8606": "역할을 변경했습니다. Strata는 이 설정을 그대로 사용합니다.",+ "s8607": "추천: {0}",+ "s8608": "{0}의 역할",+ "s8609": "메모리 {0} GB",+ "s8610": "컴퓨터 본체 메모리를 사용합니다 (내장 그래픽)",+ "s8611": "주요 작업을 처리합니다",+ "s8612": "모델의 일부를 담당합니다",+ "s8613": "사용 안 함",+ "s8614": "{0}에서 사용 중",+ "s8615": "끄기",+ "s8616": "{0}을(를) 메인으로 지정",+ "s8617": "{0}에서는 Strata를 실행할 수 없습니다.",+ "s8618": "{0}은(는) 내장 그래픽이라 메인으로 쓰면 느립니다.",+ "s8619": "CPU만 사용하면 성능이 떨어집니다.",+ "s8620": "이 엔진은 시작하려면 그래픽 카드가 필요합니다. 하나를 켜세요.",+ "s8621": "이 설정에는 메모리가 부족합니다. 약 {0} GB를 드라이브에서 읽습니다.",+ "s8622": "{0}이(가) 이제 헬퍼입니다.",+ "s8623": "{0}이(가) 이제 메인입니다.",+ "s8624": "켜져 있는 유일한 카드는 메인이어야 합니다.",+ "s8625": "Strata가 사용할 수 있는 그래픽 카드를 찾지 못했습니다.",+ "s8626": "Strata가 {0}을(를) 사용합니다.",+ "s8627": "{0}이(가) 메인입니다: {1}.",+ "s8628": "카드가 같아서 번호가 낮은 쪽이 메인입니다",+ "s8629": "메모리가 더 많습니다",+ "s8630": "더 빠릅니다",+ "s8631": "유일한 카드입니다",+ "s8632": "{0}이(가) 돕습니다.",+ "s8633": "{0}이(가) 돕습니다.",+ "s8634": "{0}은(는) 기본적으로 꺼집니다: {1}",+ "s8635": "Strata에서 실행할 수 없습니다.",+ "s8636": "내장 그래픽입니다.",+ "s8637": "{0} GB 이하입니다.",+ "s8638": "모든 답변의 마지막 단계를 맡는 카드입니다. 다음 단어를 쓰고, 미리 계산하는 단계를 실행해 확인하며, 대화를 보관합니다. 메모리가 넉넉한 가장 빠른 카드를 고르세요. 항상 하나뿐입니다.",+ "s8639": "모델의 일부와 빠른 메모리를 담당해, 더 많은 부분이 드라이브가 아니라 그래픽 카드에 올라갑니다. 프롬프트를 약 20% 더 빠르게 읽습니다.",+ "s8640": "Strata가 이 카드를 건드리지 않습니다. 게임이나 화면 출력 등 다른 용도로 쓰는 카드에 알맞습니다.",+ "s8641": "모델에는 약 {0} GB가 필요합니다. 이 카드들과 메모리는 약 {1} GB를 제공하므로 충분합니다.",+ "s8642": "모델에는 약 {0} GB가 필요합니다. 이 카드들과 메모리는 약 {1} GB를 제공하므로 약 {2} GB를 드라이브에서 읽게 됩니다.",+ "s8643": "프로세서와 메모리만 사용합니다.",+ "s8644": "전문가용: 엔진은 카드 {0}에서 시작합니다 (메인이 마지막).",+ "s8645": "추천 설정을 유지하는 동안은 저장되지 않습니다. 카드를 추가하거나 빼면 Strata가 다시 고릅니다.",+ "s8646": "사용 안 함: {0} (이 엔진이 다루는 것과 다른 제조사의 그래픽 카드입니다)."}diff --git a/apps/host/src/locales/pt.json b/apps/host/src/locales/pt.jsonindex 181b64944..4af869165 100644--- a/apps/host/src/locales/pt.json+++ b/apps/host/src/locales/pt.json@@ -3443,5 +3443,51 @@"s8419": "Terminar a mudança","s8420": "Deixar como está","s8421": "Terminar coloca todos os seus modelos em {1}. Deixar como está mantém os modelos em {0} e remove as cópias parciais de {1}.",- "s8422": "As cópias parciais foram removidas. Seus modelos estão em {0}."+ "s8422": "As cópias parciais foram removidas. Seus modelos estão em {0}.",+ "s8601": "Placas de vídeo",+ "s8602": "Principal",+ "s8603": "Auxiliar",+ "s8604": "Sua escolha.",+ "s8605": "Recomendado.",+ "s8606": "Você mudou as funções. O Strata usará exatamente estas.",+ "s8607": "Recomendado: {0}",+ "s8608": "Função de {0}",+ "s8609": "{0} GB de memória",+ "s8610": "Usa a memória do seu computador (gráficos integrados)",+ "s8611": "Faz o trabalho principal",+ "s8612": "Guarda parte do modelo",+ "s8613": "Não usada",+ "s8614": "Em uso por {0}",+ "s8615": "Desligar",+ "s8616": "Tornar {0} a principal",+ "s8617": "{0} não consegue executar o Strata.",+ "s8618": "{0} é um gráfico integrado; como principal é lenta.",+ "s8619": "O desempenho fica reduzido usando apenas a CPU.",+ "s8620": "Este motor precisa de uma placa de vídeo para iniciar. Ative uma.",+ "s8621": "Memória insuficiente para esta configuração: cerca de {0} GB são lidos do disco.",+ "s8622": "{0} agora é auxiliar.",+ "s8623": "{0} agora é a principal.",+ "s8624": "A única placa ligada tem de ser a principal.",+ "s8625": "Nenhuma placa de vídeo que o Strata possa usar foi encontrada.",+ "s8626": "O Strata usará a sua {0}.",+ "s8627": "{0} é a principal: {1}.",+ "s8628": "as placas são iguais, por isso a de menor número é a principal",+ "s8629": "tem mais memória",+ "s8630": "é mais rápida",+ "s8631": "é a única placa",+ "s8632": "{0} ajudam.",+ "s8633": "{0} ajuda.",+ "s8634": "{0} começa desligada: {1}",+ "s8635": "O Strata não consegue executá-la.",+ "s8636": "gráficos integrados.",+ "s8637": "{0} GB ou menos.",+ "s8638": "A placa que faz os passos finais de cada resposta: escreve as próximas palavras, executa o passo de antecipação e o verifica, e guarda a sua conversa. Escolha a placa mais rápida com bastante memória. Há sempre só uma.",+ "s8639": "Guarda uma parte do modelo e da sua memória rápida, para que mais caiba nas placas de vídeo em vez de ser lido do disco. Os prompts são lidos cerca de 20% mais rápido.",+ "s8640": "O Strata não mexe nesta placa. Bom para uma placa que você usa para outra coisa, como um jogo ou a tela.",+ "s8641": "O modelo precisa de cerca de {0} GB. Estas placas e a sua memória dão cerca de {1} GB. Cabe.",+ "s8642": "O modelo precisa de cerca de {0} GB. Estas placas e a sua memória dão cerca de {1} GB, por isso cerca de {2} GB seriam lidos do disco.",+ "s8643": "Apenas o processador e a memória são usados.",+ "s8644": "Para especialistas: o motor inicia nas placas {0} (a principal por último).",+ "s8645": "Não é guardado enquanto mantiver a recomendação: o Strata escolhe de novo se adicionar ou remover uma placa.",+ "s8646": "Não usada: {0} (outra marca de placa de vídeo diferente da que este motor controla)."}diff --git a/apps/host/src/locales/ru.json b/apps/host/src/locales/ru.jsonindex e8a597f77..621a867cf 100644--- a/apps/host/src/locales/ru.json+++ b/apps/host/src/locales/ru.json@@ -3443,5 +3443,51 @@"s8419": "Завершить перенос","s8420": "Оставить как есть","s8421": "Если завершить, все модели окажутся в {1}. Если оставить, модели останутся в {0}, а неполные копии в {1} будут удалены.",- "s8422": "Неполные копии удалены. Ваши модели находятся в {0}."+ "s8422": "Неполные копии удалены. Ваши модели находятся в {0}.",+ "s8601": "Видеокарты",+ "s8602": "Основная",+ "s8603": "Помощник",+ "s8604": "Ваш выбор.",+ "s8605": "Рекомендуется.",+ "s8606": "Вы изменили роли. Strata будет использовать именно их.",+ "s8607": "Рекомендуется: {0}",+ "s8608": "Роль {0}",+ "s8609": "{0} ГБ памяти",+ "s8610": "Использует память компьютера (встроенная графика)",+ "s8611": "Выполняет основную работу",+ "s8612": "Хранит часть модели",+ "s8613": "Не используется",+ "s8614": "Используется: {0}",+ "s8615": "Выключить",+ "s8616": "Сделать {0} основной",+ "s8617": "{0} не может запускать Strata.",+ "s8618": "{0} — встроенная графика; в роли основной она медленная.",+ "s8619": "Только на процессоре производительность снижена.",+ "s8620": "Для запуска этому движку нужна видеокарта. Включите одну.",+ "s8621": "Для этой настройки не хватает памяти: около {0} ГБ читается с диска.",+ "s8622": "{0} теперь помощник.",+ "s8623": "{0} теперь основная.",+ "s8624": "Единственная включённая карта должна быть основной.",+ "s8625": "Не найдено видеокарт, которые может использовать Strata.",+ "s8626": "Strata будет использовать ваш {0}.",+ "s8627": "{0} — основная: {1}.",+ "s8628": "карты одинаковые, поэтому основной считается карта с меньшим номером",+ "s8629": "у неё больше памяти",+ "s8630": "она быстрее",+ "s8631": "это единственная карта",+ "s8632": "{0} помогают.",+ "s8633": "{0} помогает.",+ "s8634": "{0} по умолчанию выключена: {1}",+ "s8635": "Strata не может её запустить.",+ "s8636": "встроенная графика.",+ "s8637": "{0} ГБ или меньше.",+ "s8638": "Карта, выполняющая последние шаги каждого ответа: пишет следующие слова, запускает шаг опережающего черновика и проверяет его, а также хранит вашу беседу. Выберите самую быструю карту с большим объёмом памяти. Основная карта всегда одна.",+ "s8639": "Хранит часть модели и её быстрой памяти, поэтому больше помещается на видеокартах и меньше читается с диска. Запросы читаются примерно на 20 % быстрее.",+ "s8640": "Strata не трогает эту карту. Подходит для карты, занятой другим, например игрой или выводом на экран.",+ "s8641": "Модели нужно около {0} ГБ. Эти карты и ваша память дают около {1} ГБ. Помещается.",+ "s8642": "Модели нужно около {0} ГБ. Эти карты и ваша память дают около {1} ГБ, поэтому около {2} ГБ придётся читать с диска.",+ "s8643": "Используются только процессор и память.",+ "s8644": "Для опытных: движок запускается на картах {0} (основная — последняя).",+ "s8645": "Не сохраняется, пока вы оставляете рекомендацию: Strata выберет заново, если вы добавите или уберёте карту.",+ "s8646": "Не используется: {0} (другой производитель видеокарт, чем тот, с которым работает этот движок)."}diff --git a/apps/host/src/locales/zh.json b/apps/host/src/locales/zh.jsonindex 8cb479656..bef3dc374 100644--- a/apps/host/src/locales/zh.json+++ b/apps/host/src/locales/zh.json@@ -3443,5 +3443,51 @@"s8419": "完成移动","s8420": "保持原样","s8421": "完成后,所有模型都会放到 {1}。保持原样则模型留在 {0},并删除 {1} 中不完整的副本。",- "s8422": "已删除不完整的副本。你的模型在 {0}。"+ "s8422": "已删除不完整的副本。你的模型在 {0}。",+ "s8601": "显卡",+ "s8602": "主卡",+ "s8603": "辅助",+ "s8604": "你的选择。",+ "s8605": "推荐。",+ "s8606": "你更改了分工。Strata 将完全按此使用。",+ "s8607": "推荐:{0}",+ "s8608": "{0} 的分工",+ "s8609": "{0} GB 显存",+ "s8610": "使用电脑自身的内存(集成显卡)",+ "s8611": "承担主要工作",+ "s8612": "存放模型的一部分",+ "s8613": "不使用",+ "s8614": "正被 {0} 使用",+ "s8615": "关闭它",+ "s8616": "将 {0} 设为主卡",+ "s8617": "{0} 无法运行 Strata。",+ "s8618": "{0} 是集成显卡,作主卡会很慢。",+ "s8619": "仅使用 CPU 时性能会下降。",+ "s8620": "此引擎需要一张显卡才能启动。请开启一张。",+ "s8621": "此配置的内存不足:约 {0} GB 将从硬盘读取。",+ "s8622": "{0} 现在是辅助卡。",+ "s8623": "{0} 现在是主卡。",+ "s8624": "唯一开启的显卡必须是主卡。",+ "s8625": "未找到 Strata 可用的显卡。",+ "s8626": "Strata 将使用你的 {0}。",+ "s8627": "{0} 是主卡:{1}。",+ "s8628": "两张卡相同,所以编号较小的是主卡",+ "s8629": "它的显存更大",+ "s8630": "它更快",+ "s8631": "它是唯一的显卡",+ "s8632": "{0} 提供辅助。",+ "s8633": "{0} 提供辅助。",+ "s8634": "{0} 默认关闭:{1}",+ "s8635": "Strata 无法运行它。",+ "s8636": "集成显卡。",+ "s8637": "{0} GB 或更少。",+ "s8638": "负责每次回答最后步骤的显卡:写出下一个词,运行预测步骤并校验,同时保存你的对话。请选最快且显存充足的显卡。始终只有一张。",+ "s8639": "存放模型的一部分及其高速缓存,让更多内容放在显卡上而不是从硬盘读取。读取提示词约快 20%。",+ "s8640": "Strata 不会使用这张显卡。适合用于其他用途的显卡,例如游戏或显示器。",+ "s8641": "模型约需 {0} GB。这些显卡加上内存共约 {1} GB,可以容纳。",+ "s8642": "模型约需 {0} GB。这些显卡加上内存共约 {1} GB,因此约 {2} GB 将从硬盘读取。",+ "s8643": "只使用处理器和内存。",+ "s8644": "专家信息:引擎在显卡 {0} 上启动(主卡在最后)。",+ "s8645": "沿用推荐设置时不会保存:增减显卡后 Strata 会重新选择。",+ "s8646": "未使用:{0}(与此引擎驱动的显卡品牌不同)。"}diff --git a/apps/host/src/main.tsx b/apps/host/src/main.tsxindex 7162366c1..446e060a5 100644--- a/apps/host/src/main.tsx+++ b/apps/host/src/main.tsx@@ -26,3 +26,5 @@ import './styles/model-run.css';import './styles/onboarding.css';import './styles/board.css';++import './styles/gpu-roles.css';diff --git a/apps/host/src/styles/gpu-roles.css b/apps/host/src/styles/gpu-roles.cssnew file mode 100644index 000000000..111f872fb--- /dev/null+++ b/apps/host/src/styles/gpu-roles.css@@ -0,0 +1,50 @@+/* Main / Helper / Off for every graphics card (GpuRoles.tsx). Tokens are the app's (styles/kit/tokens.css). */+.gpuroles { display:flex; flex-direction:column; gap:10px; margin-top:14px; }+.gpuroles__head { display:flex; align-items:baseline; justify-content:space-between; gap:12px; flex-wrap:wrap; }+.gpuroles__link { background:none; border:0; padding:0; color:var(--st-accent-text); font:600 var(--st-fs-sm)/1.4 var(--st-font); cursor:pointer; text-decoration:underline; text-underline-offset:2px; }+.gpuroles__link:disabled { opacity:.5; cursor:default; }+.gpuroles__reco { display:flex; gap:10px; align-items:flex-start; padding:12px 14px; border-radius:var(--st-r-md); background:var(--st-accent-tint); color:var(--st-ink); }+.gpuroles__reco svg { flex:none; margin-top:2px; color:var(--st-accent-text); }+.gpuroles__reco[data-custom="true"] { background:var(--st-surface-2); }+.gpuroles__reco[data-custom="true"] svg { color:var(--st-ink-muted); }+.gpuroles__reco p { margin:0; }+.gpuroles__rows { display:grid; gap:10px; }+.gpuroles__row { border:1px solid var(--st-line); border-radius:var(--st-r-md); padding:14px 16px; background:var(--st-surface); }+.gpuroles__row[data-role="main"] { border-color:var(--st-accent); background:var(--st-accent-tint); }+.gpuroles__row[data-role="off"] { background:var(--st-surface-2); }+.gpuroles__top { display:flex; gap:14px; align-items:center; flex-wrap:wrap; }+.gpuroles__ico { flex:none; width:38px; height:38px; border-radius:10px; background:var(--st-surface-2); display:grid; place-items:center; color:var(--st-icon); }+.gpuroles__row[data-role="main"] .gpuroles__ico { background:var(--st-surface); }+.gpuroles__name { flex:1 1 200px; min-width:0; }+.gpuroles__name strong { display:block; overflow-wrap:anywhere; }+.gpuroles__name small { display:block; color:var(--st-ink-muted); font-size:var(--st-fs-sm); }+.gpuroles__tag { display:inline-block; margin-left:6px; padding:1px 8px; border-radius:var(--st-r-pill); font-size:11px; font-weight:700; vertical-align:1px; background:var(--st-accent-tint); color:var(--st-accent-text); border:1px solid var(--st-accent); }+.gpuroles__row[data-role="main"] .gpuroles__tag { background:var(--st-surface); }+.gpuroles__tag--neutral { background:var(--st-surface-2) !important; border-color:var(--st-line); color:var(--st-ink-muted); }+.gpuroles__roles { display:inline-flex; padding:3px; border-radius:12px; background:var(--st-surface-2); border:1px solid var(--st-line); gap:2px; flex:none; }+.gpuroles__row[data-role="main"] .gpuroles__roles { background:var(--st-surface); }+.gpuroles__roles button { height:34px; min-width:76px; padding:0 14px; border-radius:9px; border:0; background:transparent; cursor:pointer; font:500 var(--st-fs-md)/1 var(--st-font); color:var(--st-ink-soft); }+.gpuroles__roles button:hover:not([aria-checked="true"]):not(:disabled) { background:var(--st-line-soft); }+.gpuroles__roles button[aria-checked="true"] { background:var(--st-accent); color:var(--st-accent-ink); font-weight:700; }+.gpuroles__roles button[aria-checked="true"][data-r="helper"] { background:var(--st-info); color:#fff; }+.gpuroles__roles button[aria-checked="true"][data-r="off"] { background:var(--st-ink-muted); color:var(--st-surface); }+.gpuroles__roles button:disabled { opacity:.4; cursor:not-allowed; }+.gpuroles__roles button:focus-visible, .gpuroles__link:focus-visible, .gpuroles__details summary:focus-visible { outline:2px solid var(--st-focus); outline-offset:2px; }+.gpuroles__note { margin-top:10px; display:flex; gap:10px; align-items:flex-start; padding:10px 12px; border-radius:10px; font-size:var(--st-fs-sm); line-height:1.5; }+.gpuroles__note svg { flex:none; margin-top:2px; }+.gpuroles__note p { margin:0; flex:1; }+.gpuroles__note--warn { background:var(--st-warn-tint); color:var(--st-warn-text); }+.gpuroles__note--info { background:var(--st-info-tint); color:var(--st-info-text); }+.gpuroles__note .st-btn { flex:none; align-self:center; }+.gpuroles__toast:empty { display:none; }+.gpuroles__toast { margin-top:2px; }+.gpuroles__details { margin-top:4px; border-top:1px solid var(--st-line-soft); padding-top:12px; }+.gpuroles__details summary { cursor:pointer; color:var(--st-accent-text); font-weight:600; font-size:var(--st-fs-sm); }+.gpuroles__body { margin-top:10px; font-size:var(--st-fs-sm); color:var(--st-ink-soft); display:grid; gap:8px; }+.gpuroles__body dl { margin:0; display:grid; grid-template-columns:auto 1fr; gap:6px 14px; }+.gpuroles__body dt { font-weight:700; }+.gpuroles__body dd { margin:0; }+.gpuroles__fit { display:flex; gap:8px; align-items:center; }+.gpuroles__dot { width:9px; height:9px; border-radius:50%; background:var(--st-accent); flex:none; }+.gpuroles__fit[data-state="bad"] .gpuroles__dot { background:var(--st-danger); }+@media (max-width:560px) { .gpuroles__roles { width:100%; } .gpuroles__roles button { flex:1; min-width:0; } }diff --git a/apps/host/tests/engine-version.test.mjs b/apps/host/tests/engine-version.test.mjsindex 43d243642..f1638fa59 100644--- a/apps/host/tests/engine-version.test.mjs+++ b/apps/host/tests/engine-version.test.mjs@@ -55,7 +55,7 @@ test('with an older engine installed the app refuses to download or load Gyro, wtest('the screens use the existing "needs a newer engine" notice for a size, and the buttons are held back', async () => {const models = await readFile(new URL('../src/components/NativeModels.tsx', import.meta.url), 'utf8');assert.match(models, /selectedFamily && \(!selectedSize \|\| selectedSize\.needsNewerEngine\) \? <><h2 className="h3">\{tr\("This model needs a newer engine\."\)\}/);- assert.match(models, /!!selectedSize\.needsNewerEngine \|\| expert && deviceChoice === 'split'/);+ assert.match(models, /!!selectedSize\.needsNewerEngine\}/);const guided = await readFile(new URL('../src/components/GuidedSetup.tsx', import.meta.url), 'utf8');assert.equal((guided.match(/needsNewerEngine/g) ?? []).length, 3);});diff --git a/apps/host/tests/native-fb5.test.mjs b/apps/host/tests/native-fb5.test.mjsindex 26032a1bc..f73a0008a 100644--- a/apps/host/tests/native-fb5.test.mjs+++ b/apps/host/tests/native-fb5.test.mjs@@ -4,10 +4,9 @@ import { readFile } from 'node:fs/promises';test('the card list preselects the card the loaded model runs on, and the sidebar card says the version and the card', async () => {const models = await readFile(new URL('../src/components/NativeModels.tsx', import.meta.url), 'utf8');- assert.ok(models.indexOf('const loadedSelected = ') < models.indexOf('const loadedCards = '));- assert.ok(models.indexOf('const loadedCards = ') < models.indexOf('const activeCards = '));- assert.match(models, /cardOptions\.options\.find\(o => o\.key === cardsKey\) \?\? loadedCards \?\?/);- assert.match(models, /o\.cards\.every\(c => loadedSelected\.gpus\.includes\(c\)\)/);+ assert.ok(models.indexOf('const loadedSelected = ') < models.indexOf('const loadedRoles = '));+ assert.match(models, /fromLegacy\(loadedSelected\.gpus, roleCards, 'as_given'\)/);+ assert.match(models, /roles \? normalizeRoles\(roles, roleCards\) : loadedRoles \?\? recommended\.roles/);const side = await readFile(new URL('../src/app/Sidebar.tsx', import.meta.url), 'utf8');assert.match(side, /nativeSize\?\.model \?\? nativeCurrent\.model\.toUpperCase\(\)/);assert.match(side, /`GPU \$\{g \+ 1\}`/);diff --git a/apps/host/tests/native-gpu-roles.test.mjs b/apps/host/tests/native-gpu-roles.test.mjsnew file mode 100644index 000000000..569b4e953--- /dev/null+++ b/apps/host/tests/native-gpu-roles.test.mjs@@ -0,0 +1,76 @@+/** GPU roles in the host: a load writes the roles and the legacy mirror (Main last), a file that names roles keeps them, every card Off is allowed. */+import test from 'node:test';+import assert from 'node:assert/strict';+import { readFileSync, writeFileSync } from 'node:fs';+import { join } from 'node:path';+import { nativeFixture, finishJob } from './helpers/native-fixture.mjs';++const load = async (f, args) => { const done = await finishJob(f.control, f.control.operation('load', { model: 'iq2_xs', ...args }).id); return done; };+const written = (f, done) => JSON.parse(readFileSync(f.control.resolveInstance(done.result.instanceId).configPath, 'utf8'));++test('roles chosen in the screen: Helpers first, Main LAST, Off left out, and "gpu_roles" beside the mirror', async () => {+ const f = nativeFixture();+ try {+ await f.control.refresh(true);+ const done = await load(f, { gpuRoles: { 0: 'main', 1: 'helper' } });+ assert.equal(done.state, 'done', done.error);+ const cfg = written(f, done);+ assert.deepEqual(cfg.gpu, [1, 0], 'card 0 is Main, so it is the last stage');+ assert.equal(cfg.gpu_order, 'as_given');+ assert.deepEqual(cfg.gpu_roles, { 0: 'main', 1: 'helper' });+ assert.equal(cfg.layer_split, 'auto');+ assert.deepEqual(f.control.resolveInstance(done.result.instanceId).gpus, [1, 0]);+ await f.control.unload(done.result.instanceId);+ const one = await load(f, { gpuRoles: { 0: 'off', 1: 'main' } });+ assert.equal(one.state, 'done', one.error);+ const c1 = written(f, one);+ assert.equal(c1.gpu, 1, 'one card is a number, never a list');+ assert.deepEqual(c1.gpu_roles, { 0: 'off', 1: 'main' });+ } finally { await f.cleanup(); }+});++test('every card Off is allowed: no card in the list, "gpu_none" says it was meant', async () => {+ const f = nativeFixture();+ try {+ await f.control.refresh(true);+ const done = await load(f, { gpuRoles: { 0: 'off', 1: 'off' } });+ assert.equal(done.state, 'done', done.error);+ const cfg = written(f, done);+ assert.deepEqual(cfg.gpu, []);+ assert.equal(cfg.gpu_none, true);+ } finally { await f.cleanup(); }+});++test('a settings file that names roles keeps them when the screen only suggests cards; a plain card list replaces them', async () => {+ const f = nativeFixture();+ try {+ await f.control.refresh(true);+ const path = join(f.repo, 'strata-iq2_xs.json');+ const config = JSON.parse(readFileSync(path, 'utf8'));+ Object.assign(config, { gpu: [0, 1], gpu_order: 'as_given', gpu_roles: { 0: 'helper', 1: 'main' } });+ writeFileSync(path, JSON.stringify(config));+ await f.control.refresh(true);+ const kept = await load(f, { gpus: [1, 0], gpusFromRecommendation: true });+ assert.equal(kept.state, 'done', kept.error);+ assert.deepEqual(written(f, kept).gpu, [0, 1]);+ await f.control.unload(kept.result.instanceId);+ const picked = await load(f, { gpus: [1] });+ assert.equal(picked.state, 'done', picked.error);+ const cfg = written(f, picked);+ assert.equal(cfg.gpu, 1);+ assert.equal('gpu_roles' in cfg, false, 'a card list picked by hand replaces the roles');+ } finally { await f.cleanup(); }+});++test('roles that make no sense are refused with a plain line', async () => {+ const f = nativeFixture();+ try {+ await f.control.refresh(true);+ const two = await load(f, { gpuRoles: { 0: 'main', 1: 'main' } });+ assert.equal(two.state, 'error');+ assert.match(two.error, /Main, Helper or Off/);+ const nope = await load(f, { gpuRoles: { 5: 'main' } });+ assert.equal(nope.state, 'error');+ assert.match(nope.error, /detected graphics cards/);+ } finally { await f.cleanup(); }+});diff --git a/apps/host/tests/native-two-models.test.mjs b/apps/host/tests/native-two-models.test.mjsindex 1f3f8c8da..ab428585d 100644--- a/apps/host/tests/native-two-models.test.mjs+++ b/apps/host/tests/native-two-models.test.mjs@@ -18,8 +18,10 @@ test('a second model on a card another model uses still loads (recommend, nevertest('the screens say which card a loaded model uses, prefer a free card for a second model, and show an unload refusal beside its button', async () => {const models = await readFile(new URL('../src/components/NativeModels.tsx', import.meta.url), 'utf8');- assert.match(models, /tr\('Already used by \{0\}', \[usedBy\(o\.cards\)\.join\(', '\)\]\)/);- assert.match(models, /multiple \? cardOptions\.options\.find\(o => o\.recommended && !usedBy\(o\.cards\)\.length\)/);+ assert.match(models, /usedBy=\{i => usedBy\(\[i\]\)\}/);+ assert.match(models, /const busy = \(i: number\) => expert && multiple && usedBy\(\[i\]\)\.length > 0/); // a card another loaded model uses starts Off+ const roles = await readFile(new URL('../src/components/GpuRoles.tsx', import.meta.url), 'utf8');+ assert.match(roles, /tr\('In use by \{0\}', \[other\.join\(', '\)\]\)/);assert.match(models, /loadedAction\(`instances\/\$\{i\.id\}\/unload`\)/);assert.match(models, /loadedError \? <ErrorNotice message=\{loadedError\}/);const control = await readFile(new URL('../server/native-control.mjs', import.meta.url), 'utf8');@@ -28,7 +30,7 @@ test('the screens say which card a loaded model uses, prefer a free card for a stest('usedBy is declared before the card choice that calls it (a const used earlier broke the Models page when Run multiple models was on)', async () => {const models = await readFile(new URL('../src/components/NativeModels.tsx', import.meta.url), 'utf8');- assert.ok(models.indexOf('const usedBy = ') > 0 && models.indexOf('const usedBy = ') < models.indexOf('const activeCards = '));+ assert.ok(models.indexOf('const usedBy = ') > 0 && models.indexOf('const usedBy = ') < models.indexOf('const recommended = '));});test('a model that failed to start is not offered in the chat model picker', async () => {@@ -54,8 +56,9 @@ test('a loaded model is named from the catalog (family and version), the file idtest('card names use the GPU numbering of the other screens, and the fit figures subtract the models that stay loaded', async () => {const models = await readFile(new URL('../src/components/NativeModels.tsx', import.meta.url), 'utf8');- assert.ok(models.includes('(GPU ${Number(n) + 1})') && models.includes('text.replace(/\\(card (\\d+)\\)/g'));- assert.match(models, /<strong>\{gpuNumbers\(o\.label\)\}<\/strong>/);+ const roles = await readFile(new URL('../src/lib/gpu-roles.ts', import.meta.url), 'utf8');+ assert.ok(roles.includes('`GPU ${c.index + 1}`')); // GPU 1 is card 0, as on every other screen+ assert.match(await readFile(new URL('../src/components/GpuRoles.tsx', import.meta.url), 'utf8'), /\{gpuLabel\(c\)\} · \{c\.name\}/);assert.match(models, /const keptModels = expert && multiple/);assert.match(models, /inUse=\{keptModels\.length \?/);const card = await readFile(new URL('../src/components/PcFitCard.tsx', import.meta.url), 'utf8');