chore: v2.2.73 — ASTRA-DEBUG 로그 레벨 + webview CSP font-src 보강
- ASTRA-DEBUG 정상 흐름 로그를 console.error → logInfo/console.log 로 강등 (chatHandlers, extension, slashRouter): DevTools에 ERR로 찍히던 오탐 제거 - sidebar webview에 명시적 CSP meta 추가 + font-src에 data: 허용 (sidebar.html, sidebarProvider._getHtml): VS Code outer iframe이 codicon.ttf를 data:font/ttf 로 inject하면서 기본 CSP에 막혀 매 prompt 마다 violation 경고가 찍히던 문제 해소 - 누적된 LM Studio / agent / 컨텍스트 매니저 / 테스트 갱신 동반 Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
This commit is contained in:
g1nation
+94
-7
@@ -1,8 +1,20 @@
|
||||
import { LMStudioClient as SDKClient, LLM } from '@lmstudio/sdk';
|
||||
import { LMStudioClient as SDKClient, LLM, type LLMLoadModelConfig } from '@lmstudio/sdk';
|
||||
import { logError, logInfo } from '../utils';
|
||||
|
||||
/** Load-time options forwarded to LM Studio's `llm.load()`. Subset of `LLMLoadModelConfig`. */
|
||||
export interface LMStudioLoadConfig {
|
||||
flashAttention?: boolean;
|
||||
/** "max" | "off" | number 0-1 */
|
||||
gpuOffloadRatio?: 'max' | 'off' | number;
|
||||
offloadKVCacheToGpu?: boolean;
|
||||
keepModelInMemory?: boolean;
|
||||
useFp16ForKVCache?: boolean;
|
||||
/** 0 / undefined = engine default */
|
||||
evalBatchSize?: number;
|
||||
}
|
||||
|
||||
export interface ILMStudioClient {
|
||||
load(modelKey: string, signal?: AbortSignal): Promise<void>;
|
||||
load(modelKey: string, signal?: AbortSignal, loadConfig?: LMStudioLoadConfig): Promise<void>;
|
||||
unload(modelKey: string): Promise<void>;
|
||||
listLoaded(): Promise<string[]>;
|
||||
/** Like listLoaded() but caches the result for `ttlMs` to avoid hammering the SDK. */
|
||||
@@ -15,6 +27,10 @@ export interface ILMStudioClient {
|
||||
* only returns loaded models when JIT is off).
|
||||
*/
|
||||
listDownloaded(): Promise<string[]>;
|
||||
/** Cached variant; the downloaded list only changes when the user installs/removes a model. */
|
||||
listDownloadedCached(ttlMs?: number): Promise<string[]>;
|
||||
/** Pre-warm a draft model for speculative decoding. Idempotent + best-effort. */
|
||||
preloadDraftModel?(draftModelKey: string): Promise<void>;
|
||||
/**
|
||||
* Resolve a chat-ready handle for an already-loaded (or just-loaded) model.
|
||||
*
|
||||
@@ -42,8 +58,20 @@ export function httpToWebSocketUrl(httpBaseUrl: string): string | undefined {
|
||||
if (url.protocol === 'http:') url.protocol = 'ws:';
|
||||
else if (url.protocol === 'https:') url.protocol = 'wss:';
|
||||
else if (url.protocol !== 'ws:' && url.protocol !== 'wss:') return undefined;
|
||||
if (url.pathname.endsWith('/v1')) url.pathname = url.pathname.slice(0, -3);
|
||||
if (url.pathname.endsWith('/api')) url.pathname = url.pathname.slice(0, -4);
|
||||
// Strip every REST-only path suffix LM Studio ships with so the SDK lands on the
|
||||
// WebSocket root. Loop because /api/v0 → /api → '' should fully unwind.
|
||||
const REST_SUFFIXES = ['/api/v0', '/api/v1', '/v1', '/api'];
|
||||
let changed = true;
|
||||
while (changed) {
|
||||
changed = false;
|
||||
for (const suffix of REST_SUFFIXES) {
|
||||
if (url.pathname.endsWith(suffix)) {
|
||||
url.pathname = url.pathname.slice(0, -suffix.length);
|
||||
changed = true;
|
||||
break;
|
||||
}
|
||||
}
|
||||
}
|
||||
const out = url.toString().replace(/\/+$/, '');
|
||||
return out;
|
||||
} catch {
|
||||
@@ -55,7 +83,9 @@ export class LMStudioClient implements ILMStudioClient {
|
||||
private _sdk: SDKClient | undefined;
|
||||
private _wsUrl: string | undefined;
|
||||
private _loadedCache: { value: string[]; expiresAt: number } | undefined;
|
||||
private _downloadedCache: { value: string[]; expiresAt: number } | undefined;
|
||||
private static readonly DEFAULT_LOADED_CACHE_TTL_MS = 5000;
|
||||
private static readonly DEFAULT_DOWNLOADED_CACHE_TTL_MS = 60_000;
|
||||
|
||||
constructor(httpBaseUrl: string) {
|
||||
this.setBaseUrl(httpBaseUrl);
|
||||
@@ -67,6 +97,7 @@ export class LMStudioClient implements ILMStudioClient {
|
||||
this._wsUrl = ws;
|
||||
this._sdk = undefined;
|
||||
this._loadedCache = undefined;
|
||||
this._downloadedCache = undefined;
|
||||
}
|
||||
}
|
||||
|
||||
@@ -77,17 +108,53 @@ export class LMStudioClient implements ILMStudioClient {
|
||||
return this._sdk;
|
||||
}
|
||||
|
||||
async load(modelKey: string, signal?: AbortSignal): Promise<void> {
|
||||
async load(modelKey: string, signal?: AbortSignal, loadConfig?: LMStudioLoadConfig): Promise<void> {
|
||||
try {
|
||||
await this.getSdk().llm.load(modelKey, signal ? { signal } : undefined);
|
||||
const opts: { signal?: AbortSignal; config?: LLMLoadModelConfig } = {};
|
||||
if (signal) opts.signal = signal;
|
||||
const config = this._buildLoadConfig(loadConfig);
|
||||
if (Object.keys(config).length > 0) opts.config = config;
|
||||
await this.getSdk().llm.load(modelKey, Object.keys(opts).length > 0 ? opts : undefined);
|
||||
this._loadedCache = undefined;
|
||||
logInfo('LM Studio model loaded.', { modelKey });
|
||||
// Loading does not change the downloaded-models set; leave _downloadedCache alone.
|
||||
logInfo('LM Studio model loaded.', { modelKey, configKeys: Object.keys(config) });
|
||||
} catch (e: any) {
|
||||
const msg = e?.message ?? String(e);
|
||||
throw new LMStudioLifecycleError(`Failed to load LM Studio model "${modelKey}": ${msg}`, e);
|
||||
}
|
||||
}
|
||||
|
||||
/** Translate our flat LMStudioLoadConfig into LM Studio's nested LLMLoadModelConfig shape. */
|
||||
private _buildLoadConfig(lc: LMStudioLoadConfig | undefined): LLMLoadModelConfig {
|
||||
const out: LLMLoadModelConfig = {};
|
||||
if (!lc) return out;
|
||||
if (typeof lc.flashAttention === 'boolean') out.flashAttention = lc.flashAttention;
|
||||
if (typeof lc.offloadKVCacheToGpu === 'boolean') out.offloadKVCacheToGpu = lc.offloadKVCacheToGpu;
|
||||
if (typeof lc.keepModelInMemory === 'boolean') out.keepModelInMemory = lc.keepModelInMemory;
|
||||
if (typeof lc.useFp16ForKVCache === 'boolean') out.useFp16ForKVCache = lc.useFp16ForKVCache;
|
||||
if (typeof lc.evalBatchSize === 'number' && lc.evalBatchSize > 0) out.evalBatchSize = lc.evalBatchSize;
|
||||
if (lc.gpuOffloadRatio !== undefined) {
|
||||
// GPUSetting is deprecated but still accepted — wraps a single `ratio`.
|
||||
out.gpu = { ratio: lc.gpuOffloadRatio as any };
|
||||
}
|
||||
return out;
|
||||
}
|
||||
|
||||
async preloadDraftModel(draftModelKey: string): Promise<void> {
|
||||
const key = (draftModelKey || '').trim();
|
||||
if (!key) return;
|
||||
try {
|
||||
const llm: any = this.getSdk().llm;
|
||||
if (typeof llm.unstable_preloadDraftModel === 'function') {
|
||||
await llm.unstable_preloadDraftModel(key);
|
||||
logInfo('LM Studio draft model preloaded.', { draftModelKey: key });
|
||||
}
|
||||
} catch (e: any) {
|
||||
// Best-effort — the main model's respond({draftModel}) will still load it lazily.
|
||||
logError('LM Studio draft model preload failed.', { draftModelKey: key, error: e?.message ?? String(e) });
|
||||
}
|
||||
}
|
||||
|
||||
async unload(modelKey: string): Promise<void> {
|
||||
try {
|
||||
await this.getSdk().llm.unload(modelKey);
|
||||
@@ -99,6 +166,12 @@ export class LMStudioClient implements ILMStudioClient {
|
||||
}
|
||||
}
|
||||
|
||||
/** Force the next downloaded/loaded-models call to re-fetch (use after install / remove). */
|
||||
invalidateCaches(): void {
|
||||
this._loadedCache = undefined;
|
||||
this._downloadedCache = undefined;
|
||||
}
|
||||
|
||||
async listLoaded(): Promise<string[]> {
|
||||
try {
|
||||
const items: any[] = await this.getSdk().llm.listLoaded();
|
||||
@@ -138,6 +211,20 @@ export class LMStudioClient implements ILMStudioClient {
|
||||
}
|
||||
}
|
||||
|
||||
async listDownloadedCached(ttlMs: number = LMStudioClient.DEFAULT_DOWNLOADED_CACHE_TTL_MS): Promise<string[]> {
|
||||
const now = Date.now();
|
||||
if (this._downloadedCache && this._downloadedCache.expiresAt > now) {
|
||||
return this._downloadedCache.value.slice();
|
||||
}
|
||||
const value = await this.listDownloaded();
|
||||
// Only cache non-empty results — an empty array often signals a transient SDK error,
|
||||
// and caching that for 60s would hide a freshly-started LM Studio process.
|
||||
if (value.length > 0) {
|
||||
this._downloadedCache = { value, expiresAt: now + ttlMs };
|
||||
}
|
||||
return value.slice();
|
||||
}
|
||||
|
||||
async getModelHandle(modelKey: string, options?: { refresh?: boolean }): Promise<LLM> {
|
||||
try {
|
||||
if (options?.refresh) {
|
||||
|
||||
Reference in New Issue
Block a user