chore: recovery checkpoint - v3.0 API successfully recovered
CRITICAL CHECKPOINT - DO NOT PUSH TO GITHUB Recovery Status: - Successfully recovered brainy.ts from compiled JavaScript - All core v3.0 API methods functional (add, get, update, delete, relate, find, etc.) - Neural subsystem intact (562KB embedded patterns, NLP working) - Augmentation pipeline operational (20+ augmentations) - HNSW clustering system complete - Triple Intelligence compiled (needs constructor fix) - Test suite validates functionality Changes preserved: - 898 files with changes from last 3 days - 144,475 insertions - All augmentation improvements - All test coverage enhancements - Complete v3.0 feature set This is a LOCAL checkpoint only - contains recovered work after corruption incident. Created backup in .backups/brainy-full-20250910-151314.tar.gz Branch: recovery-checkpoint-20250910-151433 Date: Wed Sep 10 03:18:04 PM PDT 2025
This commit is contained in:
parent
f65455fb22
commit
8ff382ca3b
895 changed files with 143654 additions and 28268 deletions
60
.recovery-workspace/dist-backup-20250910-141917/critical/model-guardian.d.ts
vendored
Normal file
60
.recovery-workspace/dist-backup-20250910-141917/critical/model-guardian.d.ts
vendored
Normal file
|
|
@ -0,0 +1,60 @@
|
|||
/**
|
||||
* MODEL GUARDIAN - CRITICAL PATH
|
||||
*
|
||||
* THIS IS THE MOST CRITICAL COMPONENT OF BRAINY
|
||||
* Without the exact model, users CANNOT access their data
|
||||
*
|
||||
* Requirements:
|
||||
* 1. Model MUST be Xenova/all-MiniLM-L6-v2 (never changes)
|
||||
* 2. Model MUST be available at runtime
|
||||
* 3. Model MUST produce consistent 384-dim embeddings
|
||||
* 4. System MUST fail fast if model unavailable in production
|
||||
*/
|
||||
export declare class ModelGuardian {
|
||||
private static instance;
|
||||
private isVerified;
|
||||
private modelPath;
|
||||
private lastVerification;
|
||||
private constructor();
|
||||
static getInstance(): ModelGuardian;
|
||||
/**
|
||||
* CRITICAL: Verify model availability and integrity
|
||||
* This MUST be called before any embedding operations
|
||||
*/
|
||||
ensureCriticalModel(): Promise<void>;
|
||||
/**
|
||||
* Verify the local model files exist and are correct
|
||||
*/
|
||||
private verifyLocalModel;
|
||||
/**
|
||||
* Compute SHA256 hash of a file
|
||||
*/
|
||||
private computeFileHash;
|
||||
/**
|
||||
* Download model from a fallback source
|
||||
*/
|
||||
private downloadFromSource;
|
||||
/**
|
||||
* Configure transformers.js to use verified local model
|
||||
*/
|
||||
private configureTransformers;
|
||||
/**
|
||||
* Detect where models should be stored
|
||||
*/
|
||||
private detectModelPath;
|
||||
/**
|
||||
* Get model status for diagnostics
|
||||
*/
|
||||
getStatus(): Promise<{
|
||||
verified: boolean;
|
||||
path: string;
|
||||
lastVerification: Date | null;
|
||||
modelName: string;
|
||||
dimensions: number;
|
||||
}>;
|
||||
/**
|
||||
* Force re-verification (for testing)
|
||||
*/
|
||||
forceReverify(): Promise<void>;
|
||||
}
|
||||
export declare const modelGuardian: ModelGuardian;
|
||||
|
|
@ -0,0 +1,264 @@
|
|||
/**
|
||||
* MODEL GUARDIAN - CRITICAL PATH
|
||||
*
|
||||
* THIS IS THE MOST CRITICAL COMPONENT OF BRAINY
|
||||
* Without the exact model, users CANNOT access their data
|
||||
*
|
||||
* Requirements:
|
||||
* 1. Model MUST be Xenova/all-MiniLM-L6-v2 (never changes)
|
||||
* 2. Model MUST be available at runtime
|
||||
* 3. Model MUST produce consistent 384-dim embeddings
|
||||
* 4. System MUST fail fast if model unavailable in production
|
||||
*/
|
||||
import { existsSync } from 'fs';
|
||||
import { stat } from 'fs/promises';
|
||||
import { join } from 'path';
|
||||
import { env } from '@huggingface/transformers';
|
||||
// CRITICAL: These values MUST NEVER CHANGE
|
||||
const CRITICAL_MODEL_CONFIG = {
|
||||
modelName: 'Xenova/all-MiniLM-L6-v2',
|
||||
modelHash: {
|
||||
// SHA256 of model.onnx - computed from actual model
|
||||
'onnx/model.onnx': 'add_actual_hash_here',
|
||||
'tokenizer.json': 'add_actual_hash_here'
|
||||
},
|
||||
modelSize: {
|
||||
'onnx/model.onnx': 90387606, // Exact size in bytes (updated to match actual file)
|
||||
'tokenizer.json': 711661
|
||||
},
|
||||
embeddingDimensions: 384,
|
||||
fallbackSources: [
|
||||
// Primary: Our Google Cloud Storage CDN (we control this, fastest)
|
||||
{
|
||||
name: 'Soulcraft CDN (Primary)',
|
||||
url: 'https://models.soulcraft.com/models/all-MiniLM-L6-v2.tar.gz',
|
||||
type: 'tarball'
|
||||
},
|
||||
// Secondary: GitHub releases backup
|
||||
{
|
||||
name: 'GitHub Backup',
|
||||
url: 'https://github.com/soulcraftlabs/brainy-models/releases/download/v1.0.0/all-MiniLM-L6-v2.tar.gz',
|
||||
type: 'tarball'
|
||||
},
|
||||
// Tertiary: Hugging Face (original source)
|
||||
{
|
||||
name: 'Hugging Face',
|
||||
url: 'huggingface',
|
||||
type: 'transformers'
|
||||
}
|
||||
]
|
||||
};
|
||||
export class ModelGuardian {
|
||||
constructor() {
|
||||
this.isVerified = false;
|
||||
this.lastVerification = null;
|
||||
this.modelPath = this.detectModelPath();
|
||||
}
|
||||
static getInstance() {
|
||||
if (!ModelGuardian.instance) {
|
||||
ModelGuardian.instance = new ModelGuardian();
|
||||
}
|
||||
return ModelGuardian.instance;
|
||||
}
|
||||
/**
|
||||
* CRITICAL: Verify model availability and integrity
|
||||
* This MUST be called before any embedding operations
|
||||
*/
|
||||
async ensureCriticalModel() {
|
||||
console.log('DEBUG: ensureCriticalModel called');
|
||||
console.log('🛡️ MODEL GUARDIAN: Verifying critical model availability...');
|
||||
console.log(`🚀 Debug: Model path: ${this.modelPath}`);
|
||||
console.log(`🚀 Debug: Already verified: ${this.isVerified}`);
|
||||
// Check if already verified in this session
|
||||
if (this.isVerified && this.lastVerification) {
|
||||
const hoursSinceVerification = (Date.now() - this.lastVerification.getTime()) / (1000 * 60 * 60);
|
||||
if (hoursSinceVerification < 24) {
|
||||
console.log('✅ Model previously verified in this session');
|
||||
return;
|
||||
}
|
||||
}
|
||||
// Step 1: Check if model exists locally
|
||||
console.log('🔍 Debug: Calling verifyLocalModel()');
|
||||
const modelExists = await this.verifyLocalModel();
|
||||
if (modelExists) {
|
||||
console.log('✅ Critical model verified locally');
|
||||
this.isVerified = true;
|
||||
this.lastVerification = new Date();
|
||||
this.configureTransformers();
|
||||
return;
|
||||
}
|
||||
// Step 2: In production, FAIL FAST
|
||||
if (process.env.NODE_ENV === 'production' && !process.env.BRAINY_ALLOW_RUNTIME_DOWNLOAD) {
|
||||
throw new Error('🚨 CRITICAL FAILURE: Transformer model not found in production!\n' +
|
||||
'The model is REQUIRED for Brainy to function.\n' +
|
||||
'Users CANNOT access their data without it.\n' +
|
||||
'Solution: Run "npm run download-models" during build stage.');
|
||||
}
|
||||
// Step 3: Attempt to download from fallback sources
|
||||
console.warn('⚠️ Model not found locally, attempting download...');
|
||||
for (const source of CRITICAL_MODEL_CONFIG.fallbackSources) {
|
||||
try {
|
||||
console.log(`📥 Trying ${source.name}...`);
|
||||
await this.downloadFromSource(source);
|
||||
// Verify the download
|
||||
if (await this.verifyLocalModel()) {
|
||||
console.log(`✅ Successfully downloaded from ${source.name}`);
|
||||
this.isVerified = true;
|
||||
this.lastVerification = new Date();
|
||||
this.configureTransformers();
|
||||
return;
|
||||
}
|
||||
}
|
||||
catch (error) {
|
||||
console.warn(`❌ ${source.name} failed:`, error.message);
|
||||
}
|
||||
}
|
||||
// Step 4: CRITICAL FAILURE
|
||||
throw new Error('🚨 CRITICAL FAILURE: Cannot obtain transformer model!\n' +
|
||||
'Tried all fallback sources.\n' +
|
||||
'Brainy CANNOT function without the model.\n' +
|
||||
'Users CANNOT access their data.\n' +
|
||||
'Please check network connectivity or pre-download models.');
|
||||
}
|
||||
/**
|
||||
* Verify the local model files exist and are correct
|
||||
*/
|
||||
async verifyLocalModel() {
|
||||
const modelBasePath = join(this.modelPath, ...CRITICAL_MODEL_CONFIG.modelName.split('/'));
|
||||
console.log(`🔍 Debug: Checking model at path: ${modelBasePath}`);
|
||||
console.log(`🔍 Debug: Model path components: ${this.modelPath} + ${CRITICAL_MODEL_CONFIG.modelName.split('/')}`);
|
||||
// Check critical files
|
||||
const criticalFiles = [
|
||||
'onnx/model.onnx',
|
||||
'tokenizer.json',
|
||||
'config.json'
|
||||
];
|
||||
for (const file of criticalFiles) {
|
||||
const filePath = join(modelBasePath, file);
|
||||
console.log(`🔍 Debug: Checking file: ${filePath}`);
|
||||
if (!existsSync(filePath)) {
|
||||
console.log(`❌ Missing critical file: ${file} at ${filePath}`);
|
||||
return false;
|
||||
}
|
||||
// Verify size for critical files
|
||||
if (CRITICAL_MODEL_CONFIG.modelSize[file]) {
|
||||
const stats = await stat(filePath);
|
||||
const expectedSize = CRITICAL_MODEL_CONFIG.modelSize[file];
|
||||
if (Math.abs(stats.size - expectedSize) > 1000) { // Allow 1KB variance
|
||||
console.error(`❌ CRITICAL: Model file size mismatch!\n` +
|
||||
`File: ${file}\n` +
|
||||
`Expected: ${expectedSize} bytes\n` +
|
||||
`Actual: ${stats.size} bytes\n` +
|
||||
`This indicates model corruption or version mismatch!`);
|
||||
return false;
|
||||
}
|
||||
}
|
||||
// SHA256 verification for ultimate security
|
||||
if (CRITICAL_MODEL_CONFIG.modelHash && CRITICAL_MODEL_CONFIG.modelHash[file]) {
|
||||
const hash = await this.computeFileHash(filePath);
|
||||
if (hash !== CRITICAL_MODEL_CONFIG.modelHash[file]) {
|
||||
console.error(`❌ CRITICAL: Model hash mismatch for ${file}!\n` +
|
||||
`Expected: ${CRITICAL_MODEL_CONFIG.modelHash[file]}\n` +
|
||||
`Got: ${hash}\n` +
|
||||
`This indicates model tampering or corruption!`);
|
||||
return false;
|
||||
}
|
||||
}
|
||||
}
|
||||
return true;
|
||||
}
|
||||
/**
|
||||
* Compute SHA256 hash of a file
|
||||
*/
|
||||
async computeFileHash(filePath) {
|
||||
try {
|
||||
const { readFile } = await import('fs/promises');
|
||||
const { createHash } = await import('crypto');
|
||||
const fileBuffer = await readFile(filePath);
|
||||
const hash = createHash('sha256').update(fileBuffer).digest('hex');
|
||||
return hash;
|
||||
}
|
||||
catch (error) {
|
||||
console.error(`Failed to compute hash for ${filePath}:`, error);
|
||||
return '';
|
||||
}
|
||||
}
|
||||
/**
|
||||
* Download model from a fallback source
|
||||
*/
|
||||
async downloadFromSource(source) {
|
||||
if (source.type === 'transformers') {
|
||||
// Use transformers.js native download
|
||||
const { pipeline } = await import('@huggingface/transformers');
|
||||
env.cacheDir = this.modelPath;
|
||||
env.allowRemoteModels = true;
|
||||
const extractor = await pipeline('feature-extraction', CRITICAL_MODEL_CONFIG.modelName);
|
||||
// Test the model
|
||||
const test = await extractor('test', { pooling: 'mean', normalize: true });
|
||||
if (test.data.length !== CRITICAL_MODEL_CONFIG.embeddingDimensions) {
|
||||
throw new Error(`CRITICAL: Model dimension mismatch! ` +
|
||||
`Expected ${CRITICAL_MODEL_CONFIG.embeddingDimensions}, ` +
|
||||
`got ${test.data.length}`);
|
||||
}
|
||||
}
|
||||
else if (source.type === 'tarball') {
|
||||
// Download and extract tarball
|
||||
// This would require implementation with proper tar extraction
|
||||
throw new Error('Tarball extraction not yet implemented');
|
||||
}
|
||||
}
|
||||
/**
|
||||
* Configure transformers.js to use verified local model
|
||||
*/
|
||||
configureTransformers() {
|
||||
env.localModelPath = this.modelPath;
|
||||
env.allowRemoteModels = false; // Force local only after verification
|
||||
console.log('🔒 Transformers configured to use verified local model');
|
||||
}
|
||||
/**
|
||||
* Detect where models should be stored
|
||||
*/
|
||||
detectModelPath() {
|
||||
const candidates = [
|
||||
process.env.BRAINY_MODELS_PATH,
|
||||
'./models',
|
||||
join(process.cwd(), 'models'),
|
||||
join(process.env.HOME || '', '.brainy', 'models'),
|
||||
'/opt/models', // Lambda/container path
|
||||
env.cacheDir
|
||||
];
|
||||
for (const path of candidates) {
|
||||
if (path && existsSync(path)) {
|
||||
const modelPath = join(path, ...CRITICAL_MODEL_CONFIG.modelName.split('/'));
|
||||
if (existsSync(join(modelPath, 'onnx', 'model.onnx'))) {
|
||||
return path; // Return the models directory, not its parent
|
||||
}
|
||||
}
|
||||
}
|
||||
// Default
|
||||
return './models';
|
||||
}
|
||||
/**
|
||||
* Get model status for diagnostics
|
||||
*/
|
||||
async getStatus() {
|
||||
return {
|
||||
verified: this.isVerified,
|
||||
path: this.modelPath,
|
||||
lastVerification: this.lastVerification,
|
||||
modelName: CRITICAL_MODEL_CONFIG.modelName,
|
||||
dimensions: CRITICAL_MODEL_CONFIG.embeddingDimensions
|
||||
};
|
||||
}
|
||||
/**
|
||||
* Force re-verification (for testing)
|
||||
*/
|
||||
async forceReverify() {
|
||||
this.isVerified = false;
|
||||
this.lastVerification = null;
|
||||
await this.ensureCriticalModel();
|
||||
}
|
||||
}
|
||||
// Export singleton instance
|
||||
export const modelGuardian = ModelGuardian.getInstance();
|
||||
//# sourceMappingURL=model-guardian.js.map
|
||||
File diff suppressed because one or more lines are too long
Loading…
Add table
Add a link
Reference in a new issue