Skip to content

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++

Drafting in the app: "Drafting: Auto (recommended) / MTP / DFlash2 / Off" beside context in the model's settings

Niko1221b7196c23def2
diff --git a/apps/host/server/control-runtime.mjs b/apps/host/server/control-runtime.mjs
index 3e02f8b19..022af1142 100644
--- a/apps/host/server/control-runtime.mjs
+++ b/apps/host/server/control-runtime.mjs
@@ -244,6 +244,22 @@ export function createControl({ control = findControl(), env = process.env, run
if (result.json?.ok) return result.json;
throw Object.assign(failure(result, 'The partial copies could not be removed.'), { code: result.json?.error?.code ?? 'leave_failed', details: result.json?.error?.details ?? '' });
},
+ /**
+ * The DFlash2 drafter for a model's run config and the drafting choice (`strata drafting plan`): { needed, gb, line, note, drafter }. Control decides
+ * (the table of strata_control/drafting.py); the app never reads it. Nothing is downloaded.
+ */
+ async draftingPlan({ configPath = null, mode = null, family = null, dataDir = null } = {}) {
+ const result = await call(['drafting', 'plan', ...(configPath ? ['--config', configPath] : []), ...(mode ? ['--mode', mode] : []), ...(family ? ['--family', family] : []), ...(dataDir ? ['--data-dir', dataDir] : []), '--output', 'json'], { timeoutMs: 30_000 });
+ if (result.json?.ok) return result.json;
+ throw failure(result, 'The drafter could not be checked.');
+ },
+ /** Fetch and pack the drafter when the choice would use it and it is not here (`strata drafting fetch --if-needed`); `onEvent` gets {step, done, total}. */
+ async draftingFetch({ configPath, mode = null, onEvent = null, signal = null } = {}) {
+ const args = ['drafting', 'fetch', '--config', configPath, ...(mode ? ['--mode', mode] : []), '--if-needed', '--output', 'jsonl'];
+ const result = await call(args, { timeoutMs: 3 * 3600_000, acquire: true, onLine: onEvent ?? (() => {}), signal });
+ if (result.json?.ok) return result.json;
+ throw Object.assign(new ControlError(result.json?.error?.message ?? (result.stderr.split(/\r?\n/).filter(Boolean).pop() || 'The DFlash2 drafter could not be downloaded.'), { exitCode: result.code, output: result.json }), { code: 'drafting_failed' });
+ },
async saveProfile(name, configPath) {
const listed = await call(['profile', 'list', '--output', 'json'], { timeoutMs: 20_000 });
const known = (listed.json?.profiles ?? []).some(p => p.id === name);
diff --git a/apps/host/server/native-control.mjs b/apps/host/server/native-control.mjs
index a4380e797..160495a81 100644
--- a/apps/host/server/native-control.mjs
+++ b/apps/host/server/native-control.mjs
@@ -73,7 +73,7 @@ export function createNativeControl({directory,requests=()=>[],changed=()=>{},sp
for(const name of names){const path=join(dir,name),config=readJson(path,null);if(!config||typeof config!=='object')continue;
const next={...config,...(config.cwd!==undefined?{cwd:fix(config.cwd)}:{}),...(Array.isArray(config.args)?{args:config.args.map(fix)}:{})};
if(JSON.stringify(next)!==JSON.stringify(config)){try{writeModelConfig(path,next);}catch{/* read-only folder: the load reports it */}}}}
- function installedInfo(info){if(!info)return info;return {...info,models:(info.models??[]).map(entry=>{const cfg=/^strata-[a-z0-9_-]+\.json$/i.test(entry.config??'')?readJson(entry.configPath??join(repo(),entry.config)):{};const at=cfg.args?.indexOf('--native')??-1,nativeFile=at>=0?cfg.args[at+1]:null;const dataFolder=typeof nativeFile==='string'&&basename(dirname(dirname(nativeFile)))==='models'?dirname(dirname(dirname(nativeFile))):info.data_folder;/* A model the person pointed at their own GGUF folder (not <data>/models/<tag>): remembered, so a later load runs setup with that folder again instead of downloading the files (#3199). */const ownGgufDir=typeof nativeFile==='string'&&basename(dirname(dirname(nativeFile)))!=='models'&&existsSync(nativeFile)?dirname(nativeFile):undefined;return {...entry,ownGgufDir,diskGb:entry.diskGb??entry.disk_gb,diskBytes:entry.diskBytes??entry.disk_bytes,sharedBytes:entry.sharedBytes??entry.shared_bytes,removableGb:entry.removableGb??entry.removable_gb,dataFolder,visionPrepared:!!cfg.vision,/* The picture files are prepared when the run config has a vision section: the Models screen then loads straight away instead of running setup again (it used to read 'off' for every model, which sent every load of a picture-capable model through "Apply settings and load", and setup writes the arguments, the draft layer and the reader back each time). */images:cfg.vision?'yes':'off',draftLayer:cfg.mtp!==false,/* Picture reading is ON unless the person turned it off: no saved choice and not loaded is undefined, not false (owner rule: pictures on by default). */visionEnabled:cfg.ui_vision_enabled??(()=>{const running=[...instances.values()].find(i=>i.model===entry.model&&i.status==='ready');return running?!!running.vision:undefined;})(),visionDevice:cfg.ui_vision_device,resourceProfile:cfg.ui_resource_profile,lowRamMode:cfg.args?.includes('--resident-experts')?'resident':cfg.args?.includes('--mmap-experts')?'mmap':'auto'};})};}
+ function installedInfo(info){if(!info)return info;return {...info,models:(info.models??[]).map(entry=>{const cfg=/^strata-[a-z0-9_-]+\.json$/i.test(entry.config??'')?readJson(entry.configPath??join(repo(),entry.config)):{};const at=cfg.args?.indexOf('--native')??-1,nativeFile=at>=0?cfg.args[at+1]:null;const dataFolder=typeof nativeFile==='string'&&basename(dirname(dirname(nativeFile)))==='models'?dirname(dirname(dirname(nativeFile))):info.data_folder;/* A model the person pointed at their own GGUF folder (not <data>/models/<tag>): remembered, so a later load runs setup with that folder again instead of downloading the files (#3199). */const ownGgufDir=typeof nativeFile==='string'&&basename(dirname(dirname(nativeFile)))!=='models'&&existsSync(nativeFile)?dirname(nativeFile):undefined;return {...entry,ownGgufDir,diskGb:entry.diskGb??entry.disk_gb,diskBytes:entry.diskBytes??entry.disk_bytes,sharedBytes:entry.sharedBytes??entry.shared_bytes,removableGb:entry.removableGb??entry.removable_gb,dataFolder,visionPrepared:!!cfg.vision,/* The picture files are prepared when the run config has a vision section: the Models screen then loads straight away instead of running setup again (it used to read 'off' for every model, which sent every load of a picture-capable model through "Apply settings and load", and setup writes the arguments, the draft layer and the reader back each time). */images:cfg.vision?'yes':'off',draftLayer:cfg.mtp!==false,drafting:cfg.drafting??'auto',/* Picture reading is ON unless the person turned it off: no saved choice and not loaded is undefined, not false (owner rule: pictures on by default). */visionEnabled:cfg.ui_vision_enabled??(()=>{const running=[...instances.values()].find(i=>i.model===entry.model&&i.status==='ready');return running?!!running.vision:undefined;})(),visionDevice:cfg.ui_vision_device,resourceProfile:cfg.ui_resource_profile,lowRamMode:cfg.args?.includes('--resident-experts')?'resident':cfg.args?.includes('--mmap-experts')?'mmap':'auto'};})};}
function installRoot(){const found=[preferences.installDir].find(d=>d&&existsSync(d));if(found)return realpathSync(found);mkdirSync(defaultInstall(),{recursive:true});return realpathSync(defaultInstall());}
/* The settings file Strata Control and the installer read (control-runtime.mjs sets STRATA_SETTINGS_FILE to it): the app's data folder is written there. */
function controlSettingsFile(){return process.env.STRATA_SETTINGS_FILE||join(dirname(componentsDirectory()),'app-settings.json');}
@@ -139,7 +139,10 @@ export function createNativeControl({directory,requests=()=>[],changed=()=>{},sp
function settings(model){const {config}=record(model);const values=Object.fromEntries(NATIVE_FIELDS.map(f=>[f.id,config[f.id]??null]));if(typeof values.aliases==='string')values.aliases=values.aliases.split(',').map(v=>v.trim()).filter(Boolean);values.sampling=config.sampling??{};values.args=config.args??[];values.env=publicNativeEnv(config.env??{});return {model,values,mcp:publicMcpServers(config.mcp_servers??config.mcpServers??{}),restartNeeded:true};}
function save(model,{values,mcp}){if([...jobs.values()].some(j=>j.state==='running'))throw new Error('Finish the current operation before saving native settings.');const {path,config}=record(model);if(busy(requests().filter(r=>instances.get(r.instanceId)?.model===model)))throw new Error('Finish this model’s requests before saving its settings.');const patch=validateNativeSettings(values??{}),next={...config};for(const field of nativeFields())if(field.supported===false&&patch[field.id]!=null&&JSON.stringify(patch[field.id])!==JSON.stringify(config[field.id]))throw new Error(`${field.label} needs a newer native Strata installation. Update it in Settings → About.`);for(const [key,value] of Object.entries(patch)){if(key==='env')next.env=restoreNativeEnv(value,config.env??{});else if(value===null)delete next[key];else next[key]=value;}if('vram_reserve_mib' in patch){const base=captureUserArgs(next);const mine=setUserFlag(base,'--vram-reserve-mib',patch.vram_reserve_mib);if(mine.length)next[USER_KEY]=mine;else delete next[USER_KEY];next.args=mine.length&&patch.vram_reserve_mib!==null?mergeUserArgs(next.args??[],mine):setUserFlag(next.args??[],'--vram-reserve-mib',null);delete next.ui_reserve_applied;if(Array.isArray(next.args_written))next.args_written=[...next.args];}if(mcp!==undefined){next.mcp_servers=validateMcpServers(mcp,config.mcp_servers??config.mcpServers??{});delete next.mcpServers;}copyFileSync(path,path+'.bak');chmodSync(path+'.bak',0o600);const temp=path+'.ui-tmp';writeFileSync(temp,JSON.stringify(next,null,2)+'\n',{mode:0o600});renameSync(temp,path);return settings(model);}
function previousEngine(){if(packaged)return !!snapshot.engine?.previous;try{const data=snapshot.installed?.data_dir??snapshot.installed?.data_folder;return [join(preferences.repo,'engine/.previous'),data&&join(data,'engine/.previous')].filter(Boolean).some(existsSync)&&readFileSync(join(preferences.repo,'setup.py'),'utf8').includes('--rollback-engine');}catch{return false;}}
- async function plan(args){await refresh();if(!snapshot.available)throw new Error(snapshot.error);return tool('strata_install',installArgs(args,false));}
+ async function plan(args){await refresh();if(!snapshot.available)throw new Error(snapshot.error);const result=await tool('strata_install',installArgs(args,false));
+ /* A chosen drafter that is not on this computer yet is part of the download: its size is listed beside the model's (Control decides; nothing is fetched here). */
+ const choice=args.drafting;if(packaged&&typeof choice==='string'&&choice!=='auto'&&typeof control.draftingPlan==='function'){try{const d=await control.draftingPlan({mode:choice,family:args.family??null,dataDir:snapshot.installed?.data_folder??null});if(d.needed)return {...result,drafting:{needed:true,gb:d.gb,line:d.line}};}catch{/* the model plan still stands */}}
+ return result;}
/* The folder the person picked in the first-run chooser can be the one that holds their GGUF files (or a folder inside it). It is theirs, not a Strata data folder: packs are never made in it, and a Strata folder around it (<Strata>/models/<tag>) is used instead (#3507, #3424). */
function ownFilesDataFolder(candidate,args){if(!candidate||args.data_dir!==undefined||!args.gguf_dir)return candidate;const same=(a,b)=>{const x=resolve(a),y=resolve(b);return process.platform==='win32'?x.toLowerCase()===y.toLowerCase():x===y;};const inside=(a,b)=>{const rel=relative(resolve(b),resolve(a));return rel===''||(!!rel&&!rel.startsWith('..')&&!isAbsolute(rel));};if(!same(candidate,args.gguf_dir)&&!inside(candidate,args.gguf_dir))return candidate;const models=dirname(resolve(args.gguf_dir)),top=dirname(models);return basename(models).toLowerCase()==='models'&&/strata/i.test(basename(top))?top:undefined;}
function installArgs(args,confirm){const allowed=['family','model','context','vision','kv','gpu','gpus','backend','low_ram','port','gguf_dir'];const size=snapshot.catalog?.families?.find(f=>f.family===args.family)?.sizes.find(s=>s.model===args.model);const existing=snapshot.installed?.models?.find(m=>m.model===size?.id);/* A model adopted from the person's own GGUF folder reports that folder's parent as its data folder: it is theirs, not Strata's, so a second preparation never uses it for the packs. */if(args.gguf_dir===undefined&&existing?.ownGgufDir)args={...args,gguf_dir:existing.ownGgufDir};const data=nativeDataDirectory(ownFilesDataFolder(args.data_dir??(args.gguf_dir?undefined:existing?.dataFolder)??preferences.downloadDirectory??modelsDirectory?.(),args));if(data&&packaged&&!args.data_dir)rememberDataFolder(controlSettingsFile(),data);return {...(data?{data_dir:data}:{}),...Object.fromEntries(allowed.filter(k=>args[k]!==undefined).map(k=>[k,args[k]])),/* One card is "gpu", never "gpus" (the installer wants two or more there: "Gpus='0' is not valid", #3203). */...(/^\d{1,2}$/.test(String(args.gpus??''))?{gpu:Number(args.gpus),gpus:undefined}:{}),/* Picture reading is only downloaded when it was asked for (Read pictures); the default stays the smaller download. */...(packaged&&args.vision===undefined?{vision:'no'}:{}),confirm};}
@@ -176,7 +179,7 @@ export function createNativeControl({directory,requests=()=>[],changed=()=>{},sp
const note=engineStep?.summaryNote();
const finalResult=engineStep?job.result:result;
if(note)return {...finalResult,summary:note};
- if(args.loadAfter){const model=(result.install.family??args.family??'qwen')==='qwen'?String(args.model).toLowerCase():`${args.family}-${String(args.model).toLowerCase()}`;return loadEngine(job,{model,multiple:!!args.multiple,resourceProfile:args.resourceProfile,vision:args.loadVision});}
+ if(args.loadAfter){const model=(result.install.family??args.family??'qwen')==='qwen'?String(args.model).toLowerCase():`${args.family}-${String(args.model).toLowerCase()}`;return loadEngine(job,{model,multiple:!!args.multiple,resourceProfile:args.resourceProfile,vision:args.loadVision,...(typeof args.drafting==='string'?{values:{drafting:args.drafting}}:{})});}
return finalResult;
}
}
@@ -218,7 +221,7 @@ return {summary:result.summary??'Deleted',removed:result.plan?.gb??null};}
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}:{})};
/* The model's own choices win over what setup wrote into the arguments: "Draft layer (MTP)" off leaves --mtp out of every start, and a picture reading that is off leaves --vision out (setup writes both again whenever it runs; the saved settings are applied here, on every load). */
- if(cfg.mtp===false&&Array.isArray(cfg.args))cfg.args=withoutDraftLayer(cfg.args);
+ if((cfg.mtp===false||cfg.drafting==='off')&&Array.isArray(cfg.args))cfg.args=withoutDraftLayer(cfg.args);
if(!cfg.vision&&Array.isArray(cfg.args))cfg.args=cfg.args.filter(a=>a!=='--vision');
for(const arg of cfg.args??[])if(arg.endsWith('.gguf')&&!existsSync(resolve(repo(),arg)))throw new Error('An engine argument names a missing GGUF. Restore the saved arguments or repair the files.');
/* The app's own choice of request slots (4, fewer where the card has no room) is part of the configuration, so a tune measures the engine a load will start: slots take VRAM from the expert cache. */
@@ -229,12 +232,32 @@ return {summary:result.summary??'Deleted',removed:result.plan?.gb??null};}
if(parallelChoice){const applied=applyParallel(cfg,parallelChoice);for(const k of Object.keys(cfg))if(!(k in applied.cfg))delete cfg[k];Object.assign(cfg,applied.cfg);parallelNote=applied.note;}
return {cfg,resources,visionPreferences,parallelChoice,parallelNote};
}
+ /* The DFlash2 drafter, before a load that uses it: Control says whether the choice needs it (and the file is not here), downloads it pinned and checked, and packs it, with plain progress in the job.
+ Never stops the load: a drafter that cannot be had leaves the MTP running, and the job says so. The choice itself is remembered in the model's settings file. */
+ async function prepareDrafter(job,args,cfg,configFile){
+ const asked=args.values?.drafting;
+ if(asked!==undefined)rememberSetting(configFile,'drafting',asked===null||asked==='auto'?null:asked);
+ if(!packaged||typeof control.draftingFetch!=='function'||!cfg.drafting||cfg.drafting==='auto'||cfg.drafting==='mtp'||cfg.drafting==='off')return;
+ const work=join(directory,'native-instances');mkdirSync(work,{recursive:true});const probe=join(work,'drafting-'+randomUUID()+'.json');
+ try{
+ writeFileSync(probe,JSON.stringify(cfg),{mode:0o600});
+ job.engineAbort??=new AbortController();
+ await control.draftingFetch({configPath:probe,mode:cfg.drafting,signal:job.engineAbort.signal,onEvent:event=>{if(event.event==='progress'&&job.state==='running'){job.summary=event.step;job.details=event.total>1&&event.done<event.total?`${(event.done/1e9).toFixed(2)} of ${(event.total/1e9).toFixed(2)} GB`:undefined;emit();}}});
+ if(job.state==='running'){job.summary='Loading the model…';job.details=undefined;emit();}
+ }catch(error){if(job.state==='running'){job.drafterNote=error.message;job.summary='The DFlash2 drafter could not be downloaded, so the model starts with the MTP. Loading the model…';emit();}}
+ finally{try{rmSync(probe,{force:true});}catch{/* best effort */}}
+ }
+ /* One key of a model's settings file, set or removed (the Drafting choice): written like the Settings screen writes it, to be there for the next load. */
+ function rememberSetting(configFile,key,value){try{const current=readJson(configFile);if(value===null?!(key in current):current[key]===value)return;const next={...current};if(value===null)delete next[key];else next[key]=value;const temp=configFile+'.ui-tmp';writeFileSync(temp,JSON.stringify(next,null,2)+'\n',{mode:0o600});renameSync(temp,configFile);}catch{/* the load goes on with the choice for this start */}}
+ /* Which drafter runs, when it is not the one that was asked for (the engine's own words, "Drafting: MTP (DFlash2 didn't fit)"): under Details of the load. */
+ async function noteDrafting(job,instance,key){let note='';try{const r=await fetcher(`http://127.0.0.1:${instance.port}/metrics`,{headers:{authorization:`Bearer ${key}`},signal:AbortSignal.timeout(2000)});if(r.ok)note=String((await r.json())?.engine?.drafting_note??'');}catch{/* a convenience */}const lines=[job.drafterNote,note].filter(Boolean);if(lines.length)job.details=[job.details,...lines].filter(Boolean).join('\n');}
async function loadEngine(job,args){
await refresh(true);if(job.state!=='running')return;const {config,entry,path:configFile}=record(args.model);assertSettingsFile(configFile);if(packaged){const engine=await control.engine();if(!engine.usable)throw new Error(ENGINE_NOT_RECOGNISED+(engine.notice?` ${engine.notice}`:''));}if(!entry.ready)throw new Error('Some model files are missing. Use Download / repair to restore them.');
if(externalRunning().length)throw new Error('A Strata server is already running outside this UI. Stop it before loading here, or connect its API in Settings → Models.');
if(args.multiple&&instances.size>=8)throw new Error('Unload an instance before adding another. Up to eight native instances can run here.');
const {cfg,resources,visionPreferences,parallelChoice,parallelNote:chosenNote}=buildConfig(args,config);
let parallelNote=chosenNote;
+ await prepareDrafter(job,args,cfg,configFile);if(job.state!=='running')return;
const fingerprint=createHash('sha256').update(JSON.stringify({...cfg,api_key:undefined,port:undefined})).digest('hex');
const placement=Array.isArray(cfg.gpu)?cfg.gpu:cfg.gpu===undefined?[]:[cfg.gpu];const matching=[...instances.values()].find(i=>i.model===args.model&&JSON.stringify(i.gpus)===JSON.stringify(placement));
if(matching?.status==='ready'&&matching.fingerprint===fingerprint&&(args.multiple||instances.size===1))return {summary:`${matching.label} is already ready.`,instanceId:matching.id};
@@ -289,7 +312,7 @@ return {summary:result.summary??'Deleted',removed:result.plan?.gb??null};}
}
const deadline=Date.now()+300000;while(Date.now()<deadline&&job.state==='running'){
if(instance.status==='error')throw new Error(instance.error);
- try{const response=await fetcher(`http://127.0.0.1:${instance.port}/health`,{headers:{authorization:`Bearer ${key}`},signal:AbortSignal.timeout(2000)});if(job.state!=='running'){await unload(id);return;}if(response.ok){instance.status='ready';instance.phase='idle';if(resources||args.vision!==undefined||JSON.stringify(cfg[USER_KEY]??null)!==JSON.stringify(config[USER_KEY]??null))writeModelConfig(record(args.model).path,{...config,...(resources?{...resources,ui_resource_profile:args.resourceProfile}:{}),...visionPreferences,...(cfg[USER_KEY]?{[USER_KEY]:cfg[USER_KEY]}:{})});emit();ensurePoll();instance.parallelNote=parallelNote;return {summary:retried?`${instance.label} is ready, after a second try: ${retried.words}`:`${instance.label} is ready.${parallelNote?' '+parallelNote:''}`,instanceId:id};}}catch{}
+ try{const response=await fetcher(`http://127.0.0.1:${instance.port}/health`,{headers:{authorization:`Bearer ${key}`},signal:AbortSignal.timeout(2000)});if(job.state!=='running'){await unload(id);return;}if(response.ok){instance.status='ready';instance.phase='idle';await noteDrafting(job,instance,key);if(resources||args.vision!==undefined||JSON.stringify(cfg[USER_KEY]??null)!==JSON.stringify(config[USER_KEY]??null))writeModelConfig(record(args.model).path,{...config,...(resources?{...resources,ui_resource_profile:args.resourceProfile}:{}),...visionPreferences,...(cfg[USER_KEY]?{[USER_KEY]:cfg[USER_KEY]}:{})});emit();ensurePoll();instance.parallelNote=parallelNote;return {summary:retried?`${instance.label} is ready, after a second try: ${retried.words}`:`${instance.label} is ready.${parallelNote?' '+parallelNote:''}`,instanceId:id};}}catch{}
await new Promise(resolve=>setTimeout(resolve,1200));
}
if(job.state!=='running'){await unload(id);return;}
diff --git a/apps/host/server/native-settings.mjs b/apps/host/server/native-settings.mjs
index f8b248da3..4413ac553 100644
--- a/apps/host/server/native-settings.mjs
+++ b/apps/host/server/native-settings.mjs
@@ -9,6 +9,7 @@ export const NATIVE_FIELDS=[
{id:'idle_unload_s',label:'Unload after idle seconds',group:'Serving',type:'number',min:0,max:86400,hint:'Zero keeps the model loaded.'},
{id:'lazy_load',label:'Load on first request',group:'Serving',type:'boolean'},
{id:'mtp',label:'Draft layer (MTP)',group:'Serving',type:'boolean',hint:'The draft layer guesses several words ahead, which makes answers faster, and costs about 1 GB of graphics memory and some RAM. Turn it off if the model stops while it starts, or the card is small: the expert cache gets that memory back and answers are slower. Default is on.'},
+ {id:'drafting',label:'Drafting',group:'Serving',type:'enum',choices:['auto','mtp','dflash2','off'],hint:'Which drafter guesses words ahead to make answers faster. Auto (recommended) lets Strata pick from what it measured on cards like yours; today that is the MTP. DFlash2 is for Qwen3.8-Flash-Next only and downloads a 1.2 GB drafter once. If DFlash2 cannot run, the MTP is used and Details says why. Off turns the draft layer off.'},
{id:'batchMtp',label:'MTP per request',group:'Serving',type:'boolean',hint:'Each concurrent request uses the draft layer. Left alone, Strata turns it on for one graphics card with 24 GB or more and several requests at once, and off otherwise; choose on or off here to decide yourself.'},
{id:'parallel',label:'Concurrent requests',group:'Serving',type:'number',min:1,max:8,hint:'More slots need more memory and can slow each response.'},
{id:'engine_silence_s',label:'Engine stall timeout (seconds)',group:'Recovery',type:'number',min:10,max:3600},
@@ -25,7 +26,7 @@ export const NATIVE_FIELDS=[
{id:'mcp_max_result_chars',label:'Maximum tool result characters',group:'Tools',type:'number',min:100,max:1000000},
];
/** Settings the app itself applies when it starts a model (they are not read from the engine's source, so the engine's text never says it supports them). */
-export const APP_OWNED_FIELDS=['mtp','batchMtp'];
+export const APP_OWNED_FIELDS=['mtp','batchMtp','drafting'];
/** The engine arguments without the draft layer: --mtp <folder or count>, --spec-min-p <p> (its confidence threshold) and --batch-mtp. --spec stays: prompt lookup still uses its windows. Same rule as strata_control/draft_layer.py. */
export function withoutDraftLayer(args){
const out=[];const list=(args??[]).map(String);
diff --git a/apps/host/src/components/NativeModels.tsx b/apps/host/src/components/NativeModels.tsx
index 26c760e85..e36962ec1 100644
--- a/apps/host/src/components/NativeModels.tsx
+++ b/apps/host/src/components/NativeModels.tsx
@@ -41,6 +41,7 @@ export function NativeModels({ onOtherModels, onReady, onImport, onConnectEngine
const manual = useStore(s => s.setup?.choices?.onboarding?.manual ?? false);
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 [drafting, setDrafting] = useState('auto');
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', '');
const presetPending = useRef(false);
@@ -99,8 +100,11 @@ export function NativeModels({ onOtherModels, onReady, onImport, onConnectEngine
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]);
+ // Drafting (which drafter guesses ahead): DFlash2 is for Qwen3.8-Flash-Next only (the qwen and gyro families), so no other model is offered it.
+ const draftingChoices = selectedSize ? (['qwen', 'gyro'].includes(String(selectedSize.sourceFamily ?? selectedFamily?.family)) ? ['auto', 'mtp', 'dflash2', 'off'] : ['auto', 'mtp', 'off']) : null;
+ const draftingWords: Record<string, string> = { auto: 'Auto (recommended)', mtp: 'MTP', dflash2: 'DFlash2', off: 'Off' };
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' };
+ const downloadValues = { ...values, ...(draftingChoices ? { drafting } : {}), 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) {
setFamily(f.family);
@@ -117,7 +121,7 @@ export function NativeModels({ onOtherModels, onReady, onImport, onConnectEngine
}
if (!selectedSize)
return;
- const sig = installed ? ['have', installed.model, installed.ready, installed.context, installed.kv, installed.images, installed.visionEnabled, installed.visionDevice, installed.lowRamMode, installed.resourceProfile].join('|') : `new|${selectedSize.id}`;
+ const sig = installed ? ['have', installed.model, installed.ready, installed.context, installed.kv, installed.images, installed.visionEnabled, installed.visionDevice, installed.lowRamMode, installed.drafting, installed.resourceProfile].join('|') : `new|${selectedSize.id}`;
if (sig === appliedSig)
return;
setAppliedSig(sig);
@@ -128,6 +132,7 @@ export function NativeModels({ onOtherModels, onReady, onImport, onConnectEngine
setVision(installed.visionEnabled === false ? 'no' : installed.visionDevice ?? (installed.images && installed.images !== 'off' ? installed.images : 'yes'));
setKv(installed.kv ?? 'int8');
setLowRam(installed.lowRamMode ?? 'auto');
+ setDrafting(installed.drafting ?? 'auto');
// A model never tuned has no saved choice: keep the page's own (Leave 20%) rather than flipping to Full performance.
if (installed.resourceProfile && !loadedSelected?.resourceProfile)
setResourceProfile(installed.resourceProfile);
@@ -151,7 +156,7 @@ 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, ...(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: {} } });
+ const result = await nativeAction<NativeJob>('operations', { kind: 'load', args: { model: selectedSize.id, resourceProfile, vision: selectedSize?.images ? vision : 'no', multiple: expert && multiple, ...(draftingChoices ? { values: { drafting } } : {}), ...(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' } : {}) : {}) } });
setJobId(result.id);
}
else
@@ -179,8 +184,10 @@ export function NativeModels({ onOtherModels, onReady, onImport, onConnectEngine
{tr(noFit ? <p className="small muted native-spill-note"><Icon name="disk" size={16}/>{tr("May run slower \u00B7 Model data can be read from SSD.")}</p> : null)}
<div className="native-choice__row">
<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>
+ {tr(draftingChoices ? <div className="native-choice__col"><span className="native-choice__label">{tr("Drafting")}</span><Select ariaLabel={tr("Drafting")} value={drafting} disabled={!!active} options={draftingChoices.map(v => ({ value: v, label: tr(draftingWords[v]) }))} onChange={v => setDrafting(String(v))}/></div> : null)}
<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(loadedSelected?.metrics?.engine?.drafting_note ? <p className="small muted native-spill-note">{tr(String(loadedSelected.metrics.engine.drafting_note))}</p> : 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)}
@@ -199,7 +206,7 @@ export function NativeModels({ onOtherModels, onReady, onImport, onConnectEngine
<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>
-<Dialog open={!!plan} title={tr(installed?.ready ? "Apply settings and load" : "Download and prepare")} compact onClose={() => !pending && setPlan(null)} actions={<><Btn disabled={pending} onClick={() => setPlan(null)}>{tr("Cancel")}</Btn><Btn variant="primary" disabled={pending || !!plan?.plan?.disk_short} onClick={() => void download()}>{tr(installed?.ready ? "Apply & load" : "Download & load")}</Btn></>}><p><strong>{tr(plan?.plan?.title ?? selectedFamily?.title)}</strong>{tr(installed?.ready ? null : <>{tr(" \u00B7 approximately ")}{tr(plan?.plan?.download_gb ?? selectedSize?.download_gb)}{tr(" GB")}</>)}</p>{tr(installed?.ready ? <p className="small muted">{tr("The model files are already on this computer. Nothing will be downloaded; only the settings you chose are applied.")}</p> : null)}{tr(plan?.plan?.disk_short ? <ErrorNotice message={plan.plan.disk_short}/> : null)}{tr(installed?.ready ? <p className="small muted">{tr("Any currently loaded native models will be unloaded first.")}</p> : <><p className="small muted">{tr("Existing files are checked and reused. Any currently loaded native models will be unloaded before preparing files.")}</p><p className="small muted">{tr("Your computer may feel slower while weights load. You can stop the download and resume later.")}</p></>)}{tr(selectedSize?.images ? <p className="small muted">{tr("Vision encoder files are included. Picture reading loads only when enabled.")}</p> : null)}</Dialog>
+<Dialog open={!!plan} title={tr(installed?.ready ? "Apply settings and load" : "Download and prepare")} compact onClose={() => !pending && setPlan(null)} actions={<><Btn disabled={pending} onClick={() => setPlan(null)}>{tr("Cancel")}</Btn><Btn variant="primary" disabled={pending || !!plan?.plan?.disk_short} onClick={() => void download()}>{tr(installed?.ready ? "Apply & load" : "Download & load")}</Btn></>}><p><strong>{tr(plan?.plan?.title ?? selectedFamily?.title)}</strong>{tr(installed?.ready ? null : <>{tr(" \u00B7 approximately ")}{tr(plan?.plan?.download_gb ?? selectedSize?.download_gb)}{tr(" GB")}</>)}</p>{tr(plan?.drafting?.needed ? <p className="small muted">{tr("Choosing DFlash2 also downloads its drafter: about {0} GB, once. If it does not fit in graphics memory, the model uses the MTP instead.", [plan.drafting.gb])}</p> : null)}{tr(installed?.ready ? <p className="small muted">{tr("The model files are already on this computer. Nothing will be downloaded; only the settings you chose are applied.")}</p> : null)}{tr(plan?.plan?.disk_short ? <ErrorNotice message={plan.plan.disk_short}/> : null)}{tr(installed?.ready ? <p className="small muted">{tr("Any currently loaded native models will be unloaded first.")}</p> : <><p className="small muted">{tr("Existing files are checked and reused. Any currently loaded native models will be unloaded before preparing files.")}</p><p className="small muted">{tr("Your computer may feel slower while weights load. You can stop the download and resume later.")}</p></>)}{tr(selectedSize?.images ? <p className="small muted">{tr("Vision encoder files are included. Picture reading loads only when enabled.")}</p> : null)}</Dialog>
<NativeDeleteDialog id={deleting} onClose={() => setDeleting(null)}/>
<Dialog open={manage} title={tr("Manage models")} onClose={() => setManage(false)} actions={<Btn onClick={() => setManage(false)}>{tr("Done")}</Btn>}><div className="native-manage">
{tr(downloaded.length ? <div className="native-manage-list" role="list">{tr(downloaded.map(m => { const v = allSizes.find(x => x.id === m.model), loaded = native?.instances.some(i => i.model === m.model && i.status === 'ready'); return <div className="native-manage-row" role="listitem" key={m.model} data-selected={selectedSize?.id === m.model || undefined}>
diff --git a/apps/host/src/lib/native.ts b/apps/host/src/lib/native.ts
index b0cd1a1ac..87565a85e 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;/** 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}}
+ 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';/** The Drafting choice saved with the model: auto | mtp | dflash2 | off. */drafting?:string;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.json
index abe35d703..c112ff701 100644
--- a/apps/host/src/locales/de.json
+++ b/apps/host/src/locales/de.json
@@ -3509,5 +3509,19 @@
"s9017": "Neuen Chat beginnen",
"s9018": "Die Nachricht konnte nicht vorbereitet werden. Versuchen Sie es mit einer kürzeren Nachricht.",
"s9019": "Die letzte Strata-Sitzung wird noch beendet.",
- "s9020": "Warten Sie einen Moment und versuchen Sie es erneut. Wenn es wieder passiert, starten Sie den Computer neu."
+ "s9020": "Warten Sie einen Moment und versuchen Sie es erneut. Wenn es wieder passiert, starten Sie den Computer neu.",
+ "s9021": "Vorausraten",
+ "s9022": "Automatisch (empfohlen)",
+ "s9023": "MTP",
+ "s9024": "DFlash2",
+ "s9025": "Vorausraten: MTP (DFlash2 hat nicht hineingepasst)",
+ "s9026": "Vorausraten: MTP (DFlash2 ist in diesem Modus nicht verfügbar)",
+ "s9027": "Vorausraten: MTP (DFlash2 gibt es nur für Qwen3.8-Flash-Next)",
+ "s9028": "Vorausraten: MTP (der DFlash2-Entwurfsbaustein ist noch nicht heruntergeladen)",
+ "s9029": "Wenn Sie DFlash2 wählen, wird auch sein Entwurfsbaustein heruntergeladen: etwa {0} GB, einmalig. Passt er nicht in den Grafikspeicher, nutzt das Modell stattdessen MTP.",
+ "s9030": "DFlash2-Entwurfsbaustein wird heruntergeladen …",
+ "s9031": "DFlash2-Entwurfsbaustein wird für die Engine vorbereitet …",
+ "s9032": "Der DFlash2-Entwurfsbaustein ist bereit.",
+ "s9033": "Der DFlash2-Entwurfsbaustein konnte nicht heruntergeladen werden, deshalb startet das Modell mit MTP. Das Modell wird geladen …",
+ "s9034": "Das Modell wird geladen …"
}
diff --git a/apps/host/src/locales/en.json b/apps/host/src/locales/en.json
index 3304dfa28..bcb917281 100644
--- a/apps/host/src/locales/en.json
+++ b/apps/host/src/locales/en.json
@@ -3509,5 +3509,19 @@
"s9017": "Start a new chat",
"s9018": "The message could not be prepared. Try a shorter message.",
"s9019": "The last Strata session is still closing down.",
- "s9020": "Wait a moment and try again. If it keeps happening, restart the computer."
+ "s9020": "Wait a moment and try again. If it keeps happening, restart the computer.",
+ "s9021": "Drafting",
+ "s9022": "Auto (recommended)",
+ "s9023": "MTP",
+ "s9024": "DFlash2",
+ "s9025": "Drafting: MTP (DFlash2 didn't fit)",
+ "s9026": "Drafting: MTP (DFlash2 isn't available in this mode)",
+ "s9027": "Drafting: MTP (DFlash2 is for Qwen3.8-Flash-Next only)",
+ "s9028": "Drafting: MTP (the DFlash2 drafter isn't downloaded yet)",
+ "s9029": "Choosing DFlash2 also downloads its drafter: about {0} GB, once. If it does not fit in graphics memory, the model uses the MTP instead.",
+ "s9030": "Downloading the DFlash2 drafter…",
+ "s9031": "Packing the DFlash2 drafter for the engine…",
+ "s9032": "The DFlash2 drafter is ready.",
+ "s9033": "The DFlash2 drafter could not be downloaded, so the model starts with the MTP. Loading the model…",
+ "s9034": "Loading the model…"
}
diff --git a/apps/host/src/locales/es.json b/apps/host/src/locales/es.json
index 9dd428b32..94d71dbd8 100644
--- a/apps/host/src/locales/es.json
+++ b/apps/host/src/locales/es.json
@@ -3509,5 +3509,19 @@
"s9017": "Empezar un chat nuevo",
"s9018": "No se pudo preparar el mensaje. Prueba con un mensaje más corto.",
"s9019": "La última sesión de Strata todavía se está cerrando.",
- "s9020": "Espera un momento y vuelve a intentarlo. Si sigue pasando, reinicia el ordenador."
+ "s9020": "Espera un momento y vuelve a intentarlo. Si sigue pasando, reinicia el ordenador.",
+ "s9021": "Predicción",
+ "s9022": "Automático (recomendado)",
+ "s9023": "MTP",
+ "s9024": "DFlash2",
+ "s9025": "Predicción: MTP (DFlash2 no cabía)",
+ "s9026": "Predicción: MTP (DFlash2 no está disponible en este modo)",
+ "s9027": "Predicción: MTP (DFlash2 es solo para Qwen3.8-Flash-Next)",
+ "s9028": "Predicción: MTP (el predictor de DFlash2 aún no está descargado)",
+ "s9029": "Elegir DFlash2 también descarga su predictor: unos {0} GB, una sola vez. Si no cabe en la memoria gráfica, el modelo usa MTP.",
+ "s9030": "Descargando el predictor de DFlash2…",
+ "s9031": "Preparando el predictor de DFlash2 para el motor…",
+ "s9032": "El predictor de DFlash2 está listo.",
+ "s9033": "No se pudo descargar el predictor de DFlash2, así que el modelo arranca con MTP. Cargando el modelo…",
+ "s9034": "Cargando el modelo…"
}
diff --git a/apps/host/src/locales/ja.json b/apps/host/src/locales/ja.json
index 5cdabe14b..a349f95e1 100644
--- a/apps/host/src/locales/ja.json
+++ b/apps/host/src/locales/ja.json
@@ -3509,5 +3509,19 @@
"s9017": "新しいチャットを始める",
"s9018": "メッセージを準備できませんでした。もっと短いメッセージを試してください。",
"s9019": "前回の Strata セッションがまだ終了処理中です。",
- "s9020": "しばらく待ってからもう一度試してください。繰り返し起こる場合はコンピューターを再起動してください。"
+ "s9020": "しばらく待ってからもう一度試してください。繰り返し起こる場合はコンピューターを再起動してください。",
+ "s9021": "先読み",
+ "s9022": "自動(おすすめ)",
+ "s9023": "MTP",
+ "s9024": "DFlash2",
+ "s9025": "先読み:MTP(DFlash2 は収まりませんでした)",
+ "s9026": "先読み:MTP(このモードでは DFlash2 を使えません)",
+ "s9027": "先読み:MTP(DFlash2 は Qwen3.8-Flash-Next 専用です)",
+ "s9028": "先読み:MTP(DFlash2 のドラフトモデルはまだダウンロードされていません)",
+ "s9029": "DFlash2 を選ぶと、そのドラフトモデルも一度だけダウンロードします(約 {0} GB)。グラフィックメモリに収まらない場合は、代わりに MTP を使います。",
+ "s9030": "DFlash2 のドラフトモデルをダウンロードしています…",
+ "s9031": "DFlash2 のドラフトモデルをエンジン用に準備しています…",
+ "s9032": "DFlash2 のドラフトモデルの準備ができました。",
+ "s9033": "DFlash2 のドラフトモデルをダウンロードできなかったため、MTP で起動します。モデルを読み込んでいます…",
+ "s9034": "モデルを読み込んでいます…"
}
diff --git a/apps/host/src/locales/ko.json b/apps/host/src/locales/ko.json
index ae8bb8c5e..92ca56e06 100644
--- a/apps/host/src/locales/ko.json
+++ b/apps/host/src/locales/ko.json
@@ -3509,5 +3509,19 @@
"s9017": "새 채팅 시작",
"s9018": "메시지를 준비하지 못했습니다. 더 짧은 메시지를 시도해 보세요.",
"s9019": "지난 Strata 세션이 아직 종료되는 중입니다.",
- "s9020": "잠시 기다렸다가 다시 시도하세요. 계속 반복되면 컴퓨터를 다시 시작하세요."
+ "s9020": "잠시 기다렸다가 다시 시도하세요. 계속 반복되면 컴퓨터를 다시 시작하세요.",
+ "s9021": "초안 예측",
+ "s9022": "자동(권장)",
+ "s9023": "MTP",
+ "s9024": "DFlash2",
+ "s9025": "초안 예측: MTP(DFlash2가 들어가지 않았습니다)",
+ "s9026": "초안 예측: MTP(이 모드에서는 DFlash2를 쓸 수 없습니다)",
+ "s9027": "초안 예측: MTP(DFlash2는 Qwen3.8-Flash-Next 전용입니다)",
+ "s9028": "초안 예측: MTP(DFlash2 초안 모델이 아직 내려받아지지 않았습니다)",
+ "s9029": "DFlash2를 고르면 초안 모델도 한 번 내려받습니다(약 {0}GB). 그래픽 메모리에 들어가지 않으면 모델은 대신 MTP를 씁니다.",
+ "s9030": "DFlash2 초안 모델을 내려받는 중…",
+ "s9031": "엔진용 DFlash2 초안 모델을 준비하는 중…",
+ "s9032": "DFlash2 초안 모델이 준비되었습니다.",
+ "s9033": "DFlash2 초안 모델을 내려받지 못해 모델을 MTP로 시작합니다. 모델을 불러오는 중…",
+ "s9034": "모델을 불러오는 중…"
}
diff --git a/apps/host/src/locales/pt.json b/apps/host/src/locales/pt.json
index 8d06ebad1..19dd49846 100644
--- a/apps/host/src/locales/pt.json
+++ b/apps/host/src/locales/pt.json
@@ -3509,5 +3509,19 @@
"s9017": "Começar um novo chat",
"s9018": "Não foi possível preparar a mensagem. Tente uma mensagem mais curta.",
"s9019": "A última sessão do Strata ainda está sendo encerrada.",
- "s9020": "Aguarde um momento e tente novamente. Se continuar acontecendo, reinicie o computador."
+ "s9020": "Aguarde um momento e tente novamente. Se continuar acontecendo, reinicie o computador.",
+ "s9021": "Previsão",
+ "s9022": "Automático (recomendado)",
+ "s9023": "MTP",
+ "s9024": "DFlash2",
+ "s9025": "Previsão: MTP (o DFlash2 não coube)",
+ "s9026": "Previsão: MTP (o DFlash2 não está disponível neste modo)",
+ "s9027": "Previsão: MTP (o DFlash2 é só para o Qwen3.8-Flash-Next)",
+ "s9028": "Previsão: MTP (o preditor do DFlash2 ainda não foi baixado)",
+ "s9029": "Escolher o DFlash2 também baixa o preditor dele: cerca de {0} GB, uma vez. Se não couber na memória gráfica, o modelo usa o MTP.",
+ "s9030": "Baixando o preditor do DFlash2…",
+ "s9031": "Preparando o preditor do DFlash2 para o motor…",
+ "s9032": "O preditor do DFlash2 está pronto.",
+ "s9033": "Não foi possível baixar o preditor do DFlash2, então o modelo inicia com o MTP. Carregando o modelo…",
+ "s9034": "Carregando o modelo…"
}
diff --git a/apps/host/src/locales/ru.json b/apps/host/src/locales/ru.json
index 0ed4f38c6..5e62c115e 100644
--- a/apps/host/src/locales/ru.json
+++ b/apps/host/src/locales/ru.json
@@ -3509,5 +3509,19 @@
"s9017": "Начать новый чат",
"s9018": "Не удалось подготовить сообщение. Попробуйте сообщение покороче.",
"s9019": "Прошлый сеанс Strata ещё завершается.",
- "s9020": "Подождите немного и попробуйте снова. Если это повторяется, перезагрузите компьютер."
+ "s9020": "Подождите немного и попробуйте снова. Если это повторяется, перезагрузите компьютер.",
+ "s9021": "Предсказание",
+ "s9022": "Авто (рекомендуется)",
+ "s9023": "MTP",
+ "s9024": "DFlash2",
+ "s9025": "Предсказание: MTP (DFlash2 не поместился)",
+ "s9026": "Предсказание: MTP (DFlash2 недоступен в этом режиме)",
+ "s9027": "Предсказание: MTP (DFlash2 только для Qwen3.8-Flash-Next)",
+ "s9028": "Предсказание: MTP (черновая модель DFlash2 ещё не скачана)",
+ "s9029": "Если выбрать DFlash2, будет также скачана его черновая модель: около {0} ГБ, один раз. Если она не поместится в видеопамять, модель будет работать с MTP.",
+ "s9030": "Скачивается черновая модель DFlash2…",
+ "s9031": "Черновая модель DFlash2 готовится для движка…",
+ "s9032": "Черновая модель DFlash2 готова.",
+ "s9033": "Не удалось скачать черновую модель DFlash2, поэтому модель запускается с MTP. Загружается модель…",
+ "s9034": "Загружается модель…"
}
diff --git a/apps/host/src/locales/zh.json b/apps/host/src/locales/zh.json
index 8c861dec8..99a28629a 100644
--- a/apps/host/src/locales/zh.json
+++ b/apps/host/src/locales/zh.json
@@ -3509,5 +3509,19 @@
"s9017": "开始新的聊天",
"s9018": "无法准备这条消息。请试试更短的消息。",
"s9019": "上一次 Strata 会话仍在关闭中。",
- "s9020": "请稍等片刻再试。如果一直这样,请重启电脑。"
+ "s9020": "请稍等片刻再试。如果一直这样,请重启电脑。",
+ "s9021": "预测草稿",
+ "s9022": "自动(推荐)",
+ "s9023": "MTP",
+ "s9024": "DFlash2",
+ "s9025": "预测草稿:MTP(DFlash2 放不下)",
+ "s9026": "预测草稿:MTP(此模式下无法使用 DFlash2)",
+ "s9027": "预测草稿:MTP(DFlash2 仅适用于 Qwen3.8-Flash-Next)",
+ "s9028": "预测草稿:MTP(DFlash2 草稿模型尚未下载)",
+ "s9029": "选择 DFlash2 还会下载它的草稿模型:约 {0} GB,只下载一次。如果显存放不下,模型会改用 MTP。",
+ "s9030": "正在下载 DFlash2 草稿模型…",
+ "s9031": "正在为引擎准备 DFlash2 草稿模型…",
+ "s9032": "DFlash2 草稿模型已就绪。",
+ "s9033": "无法下载 DFlash2 草稿模型,因此模型将使用 MTP 启动。正在加载模型…",
+ "s9034": "正在加载模型…"
}
diff --git a/apps/host/tests/draft-layer.test.mjs b/apps/host/tests/draft-layer.test.mjs
index 0cfd034dd..5e915d060 100644
--- a/apps/host/tests/draft-layer.test.mjs
+++ b/apps/host/tests/draft-layer.test.mjs
@@ -45,11 +45,11 @@ test('withoutDraftLayer takes out --mtp, --spec-min-p and --batch-mtp and keeps
test('"Draft layer (MTP)" is a setting of the app, not frozen, and "MTP per request" is not frozen either', async () => {
assert.ok(NATIVE_FIELDS.some(f => f.id === 'mtp' && f.type === 'boolean'));
- assert.deepEqual(APP_OWNED_FIELDS.sort(), ['batchMtp', 'mtp']);
+ assert.deepEqual(APP_OWNED_FIELDS.sort(), ['batchMtp', 'drafting', 'mtp']);
const f = fixture();
try {
await f.native.refresh(true);
- for (const id of ['mtp', 'batchMtp']) assert.equal(f.native.state().fields.find(x => x.id === id).supported, true, `${id} must not be disabled`);
+ for (const id of ['mtp', 'batchMtp', 'drafting']) assert.equal(f.native.state().fields.find(x => x.id === id).supported, true, `${id} must not be disabled`);
assert.deepEqual(validateNativeSettings({ mtp: false }), { mtp: false });
assert.equal(checkRunConfig(JSON.stringify({ exe: 'e', tokenizer: 't', args: [], mtp: false })).issues.length, 0, 'the file check knows the key');
} finally { await f.native.close(); f.cleanup(); }
diff --git a/apps/host/tests/drafting.test.mjs b/apps/host/tests/drafting.test.mjs
new file mode 100644
index 000000000..33347e17a
--- /dev/null
+++ b/apps/host/tests/drafting.test.mjs
@@ -0,0 +1,101 @@
+// The Drafting choice in the app (MTP / DFlash2 / Off / Auto): the Models screen row, the setting the host saves, what the host asks Control before
+// a load, the download plan line, and the words in all eight languages. The table of which card gets which drafter lives in Python
+// (strata_control/drafting.py, tests/terminal/test_drafting.py); the app never reads it.
+import test from 'node:test';
+import assert from 'node:assert/strict';
+import { readFileSync } from 'node:fs';
+import { fileURLToPath } from 'node:url';
+import { NATIVE_FIELDS, APP_OWNED_FIELDS, validateNativeSettings, withoutDraftLayer } from '../server/native-settings.mjs';
+import { createControl } from '../server/control-runtime.mjs';
+
+const read = rel => readFileSync(fileURLToPath(new URL(rel, import.meta.url)), 'utf8').replace(/\r\n/g, '\n');
+
+test('Drafting is a setting of the model with four choices, saved by the app itself', () => {
+ const field = NATIVE_FIELDS.find(f => f.id === 'drafting');
+ assert.ok(field);
+ assert.deepEqual(field.choices, ['auto', 'mtp', 'dflash2', 'off']);
+ assert.equal(field.type, 'enum');
+ assert.match(field.hint, /Auto \(recommended\)/);
+ assert.match(field.hint, /Qwen3\.8-Flash-Next only/);
+ assert.ok(APP_OWNED_FIELDS.includes('drafting'), 'the engine\'s own source never lists it: the app applies it');
+ for (const ok of ['auto', 'mtp', 'dflash2', 'off']) assert.deepEqual(validateNativeSettings({ drafting: ok }), { drafting: ok });
+ assert.deepEqual(validateNativeSettings({ drafting: null }), { drafting: null }, 'cleared = Auto');
+ assert.throws(() => validateNativeSettings({ drafting: 'fastest' }), /Drafting: choose a supported option/);
+});
+
+test('Off leaves the draft layer out of every start, the same as "Draft layer (MTP)" off', () => {
+ assert.deepEqual(withoutDraftLayer(['--pack', 'p', '--mtp', '/m', '--spec', '4', '--spec-min-p', '0.5', '--batch-mtp']), ['--pack', 'p', '--spec', '4']);
+ const source = read('../server/native-control.mjs');
+ assert.match(source, /\(cfg\.mtp===false\|\|cfg\.drafting==='off'\)&&Array\.isArray\(cfg\.args\)\)cfg\.args=withoutDraftLayer\(cfg\.args\)/);
+});
+
+test('the Models screen offers the choice next to context, DFlash2 only for Qwen3.8-Flash-Next, and carries it to the plan and the load', () => {
+ const screen = read('../src/components/NativeModels.tsx');
+ assert.match(screen, /\['qwen', 'gyro'\]\.includes\(String\(selectedSize\.sourceFamily \?\? selectedFamily\?\.family\)\) \? \['auto', 'mtp', 'dflash2', 'off'\] : \['auto', 'mtp', 'off'\]/);
+ assert.match(screen, /draftingWords: Record<string, string> = \{ auto: 'Auto \(recommended\)', mtp: 'MTP', dflash2: 'DFlash2', off: 'Off' \}/);
+ const row = screen.slice(screen.indexOf('<div className="native-choice__row">'), screen.indexOf('{roleCards.length > 1 ? <GpuRoles'));
+ assert.ok(row.indexOf('Conversation context') < row.indexOf('tr("Drafting")') && row.indexOf('tr("Drafting")') < row.indexOf('Computer use'), 'in the same row, between context and computer use');
+ assert.match(row, /<Select ariaLabel=\{tr\("Drafting"\)\}/, 'the existing Select, no new component');
+ assert.match(screen, /setDrafting\(installed\.drafting \?\? 'auto'\)/, 'a model shows what it was saved with');
+ assert.match(screen, /const downloadValues = \{ \.\.\.values, \.\.\.\(draftingChoices \? \{ drafting \} : \{\}\)/);
+ assert.match(screen, /\.\.\.\(draftingChoices \? \{ values: \{ drafting \} \} : \{\}\)/);
+ assert.match(screen, /Choosing DFlash2 also downloads its drafter: about \{0\} GB, once\. If it does not fit in graphics memory, the model uses the MTP instead\./);
+ assert.match(screen, /loadedSelected\?\.metrics\?\.engine\?\.drafting_note/, 'what the engine said is shown');
+});
+
+test('the host asks Control before a load, and Control decides (the app never reads the table)', async () => {
+ const calls = [];
+ const control = createControl({ control: { dir: 'C:/c', python: 'py', cli: 'strata.py' }, run: async (args, options) => {
+ calls.push({ args, options });
+ return args[1] === 'plan'
+ ? { code: 0, json: { ok: true, needed: true, gb: 1.2, line: 'Drafting: DFlash2' }, text: '', stderr: '' }
+ : { code: 0, json: { ok: true, event: 'result', pack: 'C:/d/dflash2/x.pack' }, text: '', stderr: '' };
+ } });
+ const plan = await control.draftingPlan({ mode: 'dflash2', family: 'gyro', dataDir: 'C:/d' });
+ assert.deepEqual(calls[0].args, ['drafting', 'plan', '--mode', 'dflash2', '--family', 'gyro', '--data-dir', 'C:/d', '--output', 'json']);
+ assert.equal(plan.needed, true);
+ const events = [];
+ await control.draftingFetch({ configPath: 'C:/w/cfg.json', mode: 'dflash2', onEvent: e => events.push(e) });
+ assert.deepEqual(calls[1].args, ['drafting', 'fetch', '--config', 'C:/w/cfg.json', '--mode', 'dflash2', '--if-needed', '--output', 'jsonl']);
+ assert.equal(calls[1].options.acquire, true, 'only this explicit step may reach the network');
+ assert.equal(calls[0].options.acquire, undefined, 'planning never does');
+ const failing = createControl({ control: { dir: 'C:/c', python: 'py', cli: 'strata.py' }, run: async () => ({ code: 5, json: { ok: false, error: { code: 'drafting_failed', message: 'The DFlash2 download did not finish.' } }, text: '', stderr: '' }) });
+ await assert.rejects(failing.draftingFetch({ configPath: 'x' }), /DFlash2 download did not finish/);
+});
+
+test('a load fetches the drafter first, never stops for it, and says what ran', () => {
+ const source = read('../server/native-control.mjs');
+ const prepare = source.slice(source.indexOf('async function prepareDrafter'), source.indexOf('function rememberSetting'));
+ assert.match(prepare, /rememberSetting\(configFile,'drafting',asked===null\|\|asked==='auto'\?null:asked\)/, 'the choice is kept for the next load');
+ assert.match(prepare, /cfg\.drafting==='auto'\|\|cfg\.drafting==='mtp'\|\|cfg\.drafting==='off'\)return/, 'Auto, MTP and Off never download');
+ assert.match(prepare, /control\.draftingFetch\(/);
+ assert.match(prepare, /catch\(error\)\{if\(job\.state==='running'\)\{job\.drafterNote=error\.message;/, 'a failed download leaves the MTP and the job says so');
+ assert.match(source, /await prepareDrafter\(job,args,cfg,configFile\)/);
+ assert.match(source, /async function noteDrafting\(job,instance,key\)/);
+ assert.match(source, /instance\.status='ready';instance\.phase='idle';await noteDrafting\(job,instance,key\)/);
+ assert.match(source, /choice!=='auto'&&typeof control\.draftingPlan==='function'/, 'the plan lists the drafter only when it is chosen and Control says it is needed');
+ assert.match(source, /drafting:cfg\.drafting\?\?'auto'/, 'the installed model reports its saved choice');
+});
+
+test('every sentence of the Drafting choice is in the catalog in all eight languages, with the same slots', () => {
+ const langs = ['en', 'zh', 'ja', 'de', 'es', 'ru', 'pt', 'ko'];
+ const catalogs = Object.fromEntries(langs.map(l => [l, JSON.parse(read(`../src/locales/${l}.json`))]));
+ const idOf = text => Object.entries(catalogs.en).find(([, v]) => v === text)?.[0];
+ const sentences = ['Drafting', 'Auto (recommended)', 'MTP', 'DFlash2',
+ "Drafting: MTP (DFlash2 didn't fit)", "Drafting: MTP (DFlash2 isn't available in this mode)", 'Drafting: MTP (DFlash2 is for Qwen3.8-Flash-Next only)',
+ "Drafting: MTP (the DFlash2 drafter isn't downloaded yet)",
+ 'Choosing DFlash2 also downloads its drafter: about {0} GB, once. If it does not fit in graphics memory, the model uses the MTP instead.',
+ 'Downloading the DFlash2 drafter…', 'Packing the DFlash2 drafter for the engine…', 'The DFlash2 drafter is ready.',
+ 'The DFlash2 drafter could not be downloaded, so the model starts with the MTP. Loading the model…', 'Loading the model…'];
+ const slots = t => (t.match(/\{\d+\}/g) ?? []).sort().join();
+ for (const text of sentences) {
+ const id = idOf(text);
+ assert.ok(id, `"${text.slice(0, 60)}" is in the English catalog`);
+ for (const l of langs) {
+ const t = catalogs[l][id];
+ assert.ok(typeof t === 'string' && t.trim(), `${id} in ${l}`);
+ assert.equal(slots(t), slots(text), `${id} in ${l} has the same slots`);
+ if (l !== 'en' && text.length > 25) assert.notEqual(t, text, `${id} is translated in ${l}`);
+ }
+ }
+});
diff --git a/strata_cli/drafting_cmd.py b/strata_cli/drafting_cmd.py
index d93ec2a3e..4933c6f4e 100644
--- a/strata_cli/drafting_cmd.py
+++ b/strata_cli/drafting_cmd.py
@@ -1,4 +1,9 @@
-"""``strata drafting plan|fetch``: the DFlash2 drafter file (strata_control/drafting_fetch.py). The app calls it with ``--output jsonl``."""
+"""``strata drafting plan|fetch``: the DFlash2 drafter file (strata_control/drafting_fetch.py). The app calls it with ``--output jsonl``.
+
+With ``--config`` (a model's run config) and ``--mode`` (the choice, default: the config's own ``drafting``) the command decides what this
+model needs: ``needed`` is true only when the choice would use the drafter and its file is not here yet. ``fetch --if-needed`` then downloads
+only in that case, so the app can call it before every load without asking twice.
+"""
from __future__ import annotations
@@ -16,25 +21,60 @@ def add_parser(sp) -> None:
("fetch", "download the drafter (pinned, checked) and pack it for the engine")):
one = d_sp.add_parser(name, help=text)
one.add_argument("--data-dir", metavar="DIR", help="the model data folder (default: the one Strata uses)")
+ one.add_argument("--config", metavar="FILE", help="a model's run config: its data folder, model and drafting choice decide what is needed")
+ one.add_argument("--family", metavar="NAME", help="the model family when there is no run config yet (qwen, gyro, coder, ...)")
+ one.add_argument("--mode", choices=drafting.MODES, help="the choice to decide for (default: the run config's own)")
+ if name == "fetch":
+ one.add_argument("--if-needed", action="store_true", help="download only when the choice would use the drafter and it is not here")
one.add_argument("--output", choices=("human", "json", "jsonl"), default="human")
-def _data_dir(a) -> Path:
+def _card_class() -> str:
+ try:
+ from strata_control import engine_component
+ return drafting.card_class(list(engine_component.cuda_archs_present()) + list(engine_component.hip_archs_present()))
+ except Exception: # noqa: BLE001 - an unknown card is the "other" class
+ return "other"
+
+
+def _inputs(a) -> dict:
+ cfg: dict = {}
+ if a.config:
+ try:
+ cfg = json.loads(Path(a.config).read_text(encoding="utf-8-sig"))
+ except (OSError, ValueError):
+ cfg = {}
if a.data_dir:
- return Path(a.data_dir)
- from strata_cli.launch.catalog import Catalog
- return Catalog().data_dir()
+ data = Path(a.data_dir)
+ else:
+ data = drafting.data_dir_of(cfg.get("args") or [])
+ if data is None:
+ from strata_cli.launch.catalog import Catalog
+ data = Catalog().data_dir()
+ return {"mode": a.mode if a.mode else cfg.get("drafting"), "klass": _card_class(), "model_name": cfg.get("model_name"), "family": a.family, "data_dir": data}
def run(a) -> int:
machine = a.output in ("json", "jsonl")
- folder = _data_dir(a)
+ want = _inputs(a)
+ folder = want["data_dir"]
+ needed = drafting.needs_pack(**want)
if a.drafting_command == "plan":
- result = drafting_fetch.plan(folder)
+ decision = drafting.decide(want["mode"], klass=want["klass"], model_name=want["model_name"], family=want["family"], data_dir=folder)
+ result = {**drafting_fetch.plan(folder), "needed": needed, "drafter": decision.drafter, "note": decision.note,
+ "line": drafting.summary_line(decision)}
+ if (a.config or a.mode) and not needed: # asked about a model: nothing to download unless the choice uses the drafter
+ result["gb"] = 0.0
if machine:
print(json.dumps({"schema_version": 1, "ok": True, **result}, ensure_ascii=False))
else:
- print(result["text"])
+ print(result["text"] if needed or not decision.note else result["line"])
+ return 0
+ if getattr(a, "if_needed", False) and not needed:
+ if machine:
+ print(json.dumps({"schema_version": 1, "ok": True, "event": "result", "pack": None, "skipped": True}, ensure_ascii=False))
+ else:
+ print("Nothing to download.")
return 0
def show(step: str, done: int, total: int) -> None:
diff --git a/strata_control/drafting.py b/strata_control/drafting.py
index 7fd876ea3..0e5bd7672 100644
--- a/strata_control/drafting.py
+++ b/strata_control/drafting.py
@@ -145,9 +145,18 @@ def normalize(value: Any) -> str:
#: else (flags, download, pack, fallback text) is in place and tested with it on.
ENGINE_SERVES_DFLASH2 = False
-NOT_SUPPORTED = "DFlash2 is for Qwen3.8-Flash-Next only; this model uses the MTP."
-NOT_SERVED = "DFlash2 isn't available in this mode yet; this start uses the MTP."
-NOT_DOWNLOADED = "The DFlash2 drafter is not downloaded yet; this start uses the MTP."
+#: Why the MTP runs when something else was asked for: a closed set of short reasons, each one is a sentence in the interface catalog in all eight
+#: languages (the line is "Drafting: MTP (<reason>)").
+DIDNT_FIT = "DFlash2 didn't fit"
+NOT_HERE = "DFlash2 isn't available in this mode"
+NOT_SUPPORTED = "DFlash2 is for Qwen3.8-Flash-Next only"
+NOT_DOWNLOADED = "the DFlash2 drafter isn't downloaded yet"
+NOT_SERVED = NOT_HERE
+REASONS = (DIDNT_FIT, NOT_HERE, NOT_SUPPORTED, NOT_DOWNLOADED)
+
+
+def mtp_line(reason: str) -> str:
+ return f"Drafting: MTP ({reason})"
def decide(mode: Any, *, klass: str, model_name: str | None = None, family: str | None = None, data_dir: str | Path | None = None) -> Decision:
@@ -223,12 +232,8 @@ def apply(cfg: dict[str, Any], *, klass: str, data_dir: str | Path | None = None
# --------------------------------------------------------------------------------------------------- what the engine said
-_FALLBACK = re.compile(r"--draft dflash2(?: is off)?:\s*(?P<why>[^\n]*?)(?:\.\s|;\s|$)")
_ON = re.compile(r"DFlash2 drafter on\b")
-DIDNT_FIT = "DFlash2 didn't fit"
-NOT_HERE = "DFlash2 isn't available in this mode"
-
def fallback_note(log_text: str) -> str:
"""From one engine start's log: ``Drafting: MTP (DFlash2 didn't fit)`` when the engine fell back from DFlash2, else ``""``. The engine
@@ -243,7 +248,7 @@ def fallback_note(log_text: str) -> str:
reason = NOT_HERE
else:
reason = DIDNT_FIT
- return f"Drafting: MTP ({reason})"
+ return mtp_line(reason)
def summary_line(decision: Decision, engine_note: str = "") -> str:
@@ -251,7 +256,7 @@ def summary_line(decision: Decision, engine_note: str = "") -> str:
if engine_note:
return engine_note
if decision.note:
- return f"Drafting: MTP ({decision.note.rstrip('.')})"
+ return mtp_line(decision.note)
return f"Drafting: {LABELS.get(decision.drafter, decision.drafter) if decision.drafter != 'mtp' else 'MTP'}"
@@ -281,5 +286,5 @@ def engine_info(args: list[Any], log_text: str = "", note: str = "") -> dict[str
if asked_dflash2 and not fell_back:
return {"drafting": "dflash2", "drafting_note": ""}
drafter = "mtp" if "--mtp" in items else "off"
- text = fell_back or (f"Drafting: MTP ({note.rstrip('.')})" if note and drafter == "mtp" else "")
+ text = fell_back or (mtp_line(note) if note and drafter == "mtp" else "")
return {"drafting": drafter, "drafting_note": text}
diff --git a/tests/terminal/test_drafting.py b/tests/terminal/test_drafting.py
index c10e97df8..b2ecfa7a1 100644
--- a/tests/terminal/test_drafting.py
+++ b/tests/terminal/test_drafting.py
@@ -223,7 +223,7 @@ class WhatTheEngineSaid(unittest.TestCase):
def test_choices_that_never_reached_the_engine_keep_their_own_words(self):
self.assertEqual(drafting.engine_info(["--mtp", "/m"], "", drafting.NOT_SUPPORTED)["drafting_note"],
- "Drafting: MTP (DFlash2 is for Qwen3.8-Flash-Next only; this model uses the MTP)")
+ "Drafting: MTP (DFlash2 is for Qwen3.8-Flash-Next only)")
self.assertEqual(drafting.engine_info(["--mtp", "/m"]), {"drafting": "mtp", "drafting_note": ""})
self.assertEqual(drafting.engine_info(["--spec", "4"]), {"drafting": "off", "drafting_note": ""})
@@ -232,7 +232,23 @@ class WhatTheEngineSaid(unittest.TestCase):
self.assertEqual(drafting.summary_line(drafting.Decision("dflash2", "dflash2")), "Drafting: DFlash2")
self.assertEqual(drafting.summary_line(drafting.Decision("off", "off")), "Drafting: Off")
self.assertEqual(drafting.summary_line(drafting.Decision("dflash2", "mtp", drafting.NOT_DOWNLOADED)),
- "Drafting: MTP (The DFlash2 drafter is not downloaded yet; this start uses the MTP)")
+ "Drafting: MTP (the DFlash2 drafter isn't downloaded yet)")
+
+
+class WordsMatchTheApp(unittest.TestCase):
+ def test_every_line_the_engine_start_can_say_is_in_the_apps_catalog_in_all_eight_languages(self):
+ folder = ROOT / "apps" / "host" / "src" / "locales"
+ catalogs = {l: json.loads((folder / f"{l}.json").read_text(encoding="utf-8")) for l in ("en", "de", "es", "ja", "ko", "pt", "ru", "zh")}
+ ids = {v: k for k, v in catalogs["en"].items()}
+ self.assertEqual(len(drafting.REASONS), 4)
+ for reason in drafting.REASONS:
+ line = drafting.mtp_line(reason)
+ self.assertIn(line, ids, line)
+ for lang, catalog in catalogs.items():
+ self.assertTrue(catalog[ids[line]].strip(), f"{line} in {lang}")
+ # and what the engine's log makes of them
+ self.assertEqual(drafting.fallback_note("--draft dflash2: out of memory"), drafting.mtp_line(drafting.DIDNT_FIT))
+ self.assertEqual(drafting.fallback_note("--draft dflash2 is off: it is for one card and the CLI run"), drafting.mtp_line(drafting.NOT_HERE))
class TerminalFlag(unittest.TestCase):
@@ -386,6 +402,57 @@ class FetchAndPack(unittest.TestCase):
self.assertEqual(payload["gb"], 1.2)
+class TheAppAsksControl(unittest.TestCase):
+ """The app calls `strata drafting plan|fetch --config <run config> --mode <choice>` before a load; Control decides, the app never reads the table."""
+
+ def setUp(self):
+ self.tmp = tempfile.TemporaryDirectory()
+ self.addCleanup(self.tmp.cleanup)
+ self.data = Path(self.tmp.name) / "data"
+ self.cfg = Path(self.tmp.name) / "strata-gyro.json"
+ self.cfg.write_text(json.dumps({"model_name": GYRO, "args": ["--pack", str(self.data / "packs" / "gyro"), "--mtp", str(self.data / "mtp" / "rt")]}))
+
+ def plan(self, *extra):
+ code, out, err = run_cli(["drafting", "plan", "--config", str(self.cfg), "--output", "json", *extra])
+ self.assertEqual(code, 0, err)
+ return json.loads(out)
+
+ def test_nothing_is_needed_for_auto_mtp_or_off(self):
+ for mode in ("auto", "mtp", "off"):
+ plan = self.plan("--mode", mode)
+ self.assertFalse(plan["needed"], mode)
+ self.assertEqual(plan["gb"], 0.0)
+ self.assertEqual(self.plan("--mode", "off")["drafter"], "off")
+
+ def test_dflash2_is_needed_once_the_engine_can_serve_it_and_not_before(self):
+ before = self.plan("--mode", "dflash2")
+ self.assertFalse(before["needed"], "while the engine cannot serve it nothing is downloaded")
+ self.assertEqual(before["line"], "Drafting: MTP (DFlash2 isn't available in this mode)")
+ with serving_dflash2():
+ plan = self.plan("--mode", "dflash2")
+ self.assertTrue(plan["needed"])
+ self.assertEqual(plan["gb"], 1.2)
+ self.assertEqual(Path(plan["pack"]), drafting.pack_path(self.data), "the data folder comes from the run config's own arguments")
+ self.cfg.write_text(json.dumps({"model_name": "qwen3.8-flash-next-coder-iq3_xxs", "drafting": "dflash2", "args": ["--pack", str(self.data / "packs" / "c")]}))
+ other = self.plan()
+ self.assertFalse(other["needed"])
+ self.assertEqual(other["note"], drafting.NOT_SUPPORTED)
+
+ def test_a_model_that_is_not_installed_yet_is_asked_about_by_its_family(self):
+ with serving_dflash2():
+ for family, needed in (("gyro", True), ("qwen", True), ("coder", False), ("swift", False)):
+ code, out, err = run_cli(["drafting", "plan", "--family", family, "--mode", "dflash2", "--data-dir", str(self.data), "--output", "json"])
+ self.assertEqual(code, 0, err)
+ self.assertEqual(json.loads(out)["needed"], needed, family)
+
+ def test_fetch_if_needed_does_nothing_when_nothing_is_needed(self):
+ code, out, err = run_cli(["drafting", "fetch", "--config", str(self.cfg), "--mode", "auto", "--if-needed", "--output", "jsonl"])
+ self.assertEqual(code, 0, err)
+ last = json.loads(out.strip().splitlines()[-1])
+ self.assertEqual((last["ok"], last["skipped"], last["pack"]), (True, True, None))
+ self.assertFalse(drafting.pack_path(self.data).exists())
+
+
class TheDownloadPlanListsIt(unittest.TestCase):
"""`strata launch --plan --drafting dflash2` adds the drafter to the download when it would be used."""
@@ -395,7 +462,7 @@ class TheDownloadPlanListsIt(unittest.TestCase):
with Home() as home:
runner = Runner(S.LaunchSettings(family="qwen", model="Q2_0", context=32768, vision="off", drafting="dflash2"), catalog=catalog(HW_12))
line = runner.drafting_plan_line()
- self.assertEqual(line, "Drafting: MTP (DFlash2 isn't available in this mode yet; this start uses the MTP)")
+ self.assertEqual(line, "Drafting: MTP (DFlash2 isn't available in this mode)")
self.assertNotIn("dflash2", [p["kind"] for p in runner.download_plan()["parts"]], "nothing to fetch while the engine cannot serve it")
with serving_dflash2():
kinds = {p["kind"]: p for p in runner.download_plan()["parts"]}