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++

Merge branch 'f-021-iA' into f-021-int

Niko122134e7c5cb1a1a
diff --cc apps/host/server/native-control.mjs
index 5ab8f571a,c59afeb1d..9f9907ef3
--- a/apps/host/server/native-control.mjs
+++ b/apps/host/server/native-control.mjs
@@@ -129,10 -130,10 +130,10 @@@ export function createNativeControl({di
/* A mistake in the file holds the start back with the line, instead of an engine that dies on it. Warnings (an unknown key) never do. */
function assertSettingsFile(path){const check=checkRunConfig(readFileSync(path,'utf8'));if(!check.ok)throw new Error(`The settings file for this model has a mistake, so the model was not started. ${describeIssues(check.issues,'error').join(' ')}`);}
function settings(model){const {config}=record(model);const values=Object.fromEntries(NATIVE_FIELDS.map(f=>[f.id,config[f.id]??null]));if(typeof values.aliases==='string')values.aliases=values.aliases.split(',').map(v=>v.trim()).filter(Boolean);values.sampling=config.sampling??{};values.args=config.args??[];values.env=publicNativeEnv(config.env??{});return {model,values,mcp:publicMcpServers(config.mcp_servers??config.mcpServers??{}),restartNeeded:true};}
- function save(model,{values,mcp}){if([...jobs.values()].some(j=>j.state==='running'))throw new Error('Finish the current operation before saving native settings.');const {path,config}=record(model);if(busy(requests().filter(r=>instances.get(r.instanceId)?.model===model)))throw new Error('Finish this model’s requests before saving its settings.');const patch=validateNativeSettings(values??{}),next={...config};for(const field of nativeFields())if(field.supported===false&&patch[field.id]!=null&&JSON.stringify(patch[field.id])!==JSON.stringify(config[field.id]))throw new Error(`${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(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 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));}
- 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. */const data=nativeDataDirectory(args.data_dir??(args.gguf_dir?undefined:existing?.dataFolder)??preferences.downloadDirectory??modelsDirectory?.());return {...(data?{data_dir:data}:{}),...Object.fromEntries(allowed.filter(k=>args[k]!==undefined).map(k=>[k,args[k]])),/* 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};}
+ 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(args.data_dir??(args.gguf_dir?undefined:existing?.dataFolder)??preferences.downloadDirectory??modelsDirectory?.());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};}
function begin(kind,run,metadata={}){if([...jobs.values()].some(j=>j.state==='running'))throw new Error('Finish or cancel the current engine operation first.');const job={id:randomUUID(),kind,state:'running',startedAt:new Date().toISOString(),summary:'Starting…',result:null,error:null,...metadata};for(const [id,old] of jobs)if(jobs.size>=12&&old.state!=='running')jobs.delete(id);jobs.set(job.id,job);emit();void run(job).then(result=>{if(job.state==='running'){Object.assign(job,{state:'done',summary:result?.summary??'Complete',result,finishedAt:new Date().toISOString()});}}).catch(error=>{if(job.state==='running')Object.assign(job,{state:'error',error:error.message,summary:error.message,...(error.details?{details:error.details}:{}),finishedAt:new Date().toISOString()});}).finally(()=>{if(job.kind.startsWith('update')||job.kind==='rollback')disconnect();lastRead=0;emit();void refresh(true);});return state().jobs.find(j=>j.id===job.id);}
async function watchInstall(job,current){job.summary=current.step??'Resuming preparation status…';job.result={install:current};while(job.state==='running'){await new Promise(r=>setTimeout(r,1500));const result=await tool('strata_install');job.summary=result.summary;job.result=result;emit();if(!result.install?.running){if(result.install?.exit_code!==0)throw new Error(result.install?.error??'Preparation did not finish. Retry to reuse completed files.');return {summary:'Model preparation complete. Load it from Models.'};}}}
@@@ -192,12 -193,17 +193,19 @@@ return {summary:result.summary??'Delete
function buildConfig(args,config){
const vision=runtimeVision(config,args.vision);
const visionPreferences=args.vision!==undefined?{ui_vision_enabled:args.vision!=='no',ui_vision_device:args.vision==='no'?config.ui_vision_device??'yes':args.vision}:{};
- const resources=args.resourceProfile?resourceSettings({...config,vision},snapshot.hardware,args.resourceProfile,modelArena(args.model)):null;
+ /* The engine options the person set by hand (user_args, and what they wrote into "args" since the last write) go over everything the app generates, and an
+ explicit GPU-memory reserve (the Expert setting, user_args, a value they wrote) is never replaced by the safety default (#3215 #3270 #3216). */
+ const values0=args.values??{},cleared='vram_reserve_mib' in values0&&(values0.vram_reserve_mib===null||values0.vram_reserve_mib===''),base0=cleared?{...config,vram_reserve_mib:undefined,[USER_KEY]:setUserFlag(config[USER_KEY],'--vram-reserve-mib',null)}:config;
+ let mine=captureUserArgs(base0);const asked=cleared?null:reserveChoice({...base0,[USER_KEY]:mine},snapshot.hardware,values0).asked;
+ if(asked!==null)mine=setUserFlag(mine,'--vram-reserve-mib',asked);
+ 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};
- if(args.gpus!==undefined){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;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.');}
+ /* 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;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(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}:{})};
+ 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}:{})};
/* 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.vision&&Array.isArray(cfg.args))cfg.args=cfg.args.filter(a=>a!=='--vision');
diff --cc tools/strata_mcp.py
index 105d759f4,37e14b8b0..0977497a2
--- a/tools/strata_mcp.py
+++ b/tools/strata_mcp.py
@@@ -924,8 -868,11 +924,12 @@@ class Strata
for g in amd: # a Ryzen's integrated graphics beside an NVIDIA card: the engine runs on the NVIDIA card
if g.get("uma") and g.get("usable"):
g["usable"], g["problem"] = False, "integrated graphics: Strata uses the NVIDIA card in this computer"
+ try: # does the card drive a display? (the app keeps less VRAM free on one that does not, #3215)
+ mark_display(nv + amd, nvidia_display_active() if nv else {}, windows_desktop_adapters() if WIN and amd else [])
+ except Exception: # noqa: BLE001 - unknown stays unknown: the app then keeps its safety default
+ pass
hw["gpus"] = nv + amd
+ self._engine_code(hw)
self._engine_vendor(hw)
if WIN:
hw["display_adapters"] = windows_video_controllers()