feat: Complete professional cleanup with full functionality

- All 24 tests passing including edge cases
- Fix encryption config storage and retrieval mechanism
- Maintain complete brainy functionality during cleanup
- Professional open source repository ready for 1.2.0 release
- Zero commercial content contamination
- Robust protection systems in place
This commit is contained in:
David Snelling 2025-08-18 18:01:04 -07:00
parent 3d80df1726
commit f317b29231
8 changed files with 30776 additions and 48 deletions

View file

@ -1336,9 +1336,12 @@ export declare class BrainyData<T = any> implements BrainyDataInterface<T> {
/**
* Get a configuration value with automatic decryption
* @param key Configuration key
* @param options Options including decryption (auto-detected by default)
* @returns Configuration value or undefined
*/
getConfig(key: string): Promise<any>;
getConfig(key: string, options?: {
decrypt?: boolean;
}): Promise<any>;
/**
* Encrypt data using universal crypto utilities
*/

44
dist/brainyData.js vendored
View file

@ -1936,10 +1936,14 @@ export class BrainyData {
offset: options.offset
});
}
// Filter out placeholder nouns from search results
// Filter out placeholder nouns and deleted items from search results
searchResults = searchResults.filter((result) => {
if (result.metadata && typeof result.metadata === 'object') {
const metadata = result.metadata;
// Exclude deleted items from search results (soft delete)
if (metadata.deleted === true) {
return false;
}
// Exclude placeholder nouns from search results
if (metadata.isPlaceholder) {
return false;
@ -4818,34 +4822,36 @@ export class BrainyData {
* @param options Options including encryption
*/
async setConfig(key, value, options) {
const configNoun = {
configKey: key,
configValue: options?.encrypt ? await this.encryptData(JSON.stringify(value)) : value,
encrypted: !!options?.encrypt,
timestamp: new Date().toISOString()
};
await this.add(configNoun, {
// Use a predictable ID based on the config key
const configId = `config-${key}`;
// Store the config data in metadata (not as vectorized data)
const configValue = options?.encrypt ? await this.encryptData(JSON.stringify(value)) : value;
// Use simple text for vectorization
const searchableText = `Configuration setting for ${key}`;
await this.add(searchableText, {
nounType: NounType.State,
configKey: key,
encrypted: !!options?.encrypt
});
configValue: configValue,
encrypted: !!options?.encrypt,
timestamp: new Date().toISOString()
}, { id: configId });
}
/**
* Get a configuration value with automatic decryption
* @param key Configuration key
* @param options Options including decryption (auto-detected by default)
* @returns Configuration value or undefined
*/
async getConfig(key) {
async getConfig(key, options) {
try {
const results = await this.search('', 1, {
nounTypes: [NounType.State],
metadata: { configKey: key }
});
if (results.length === 0)
// Use the predictable ID to get the config directly
const configId = `config-${key}`;
const storedNoun = await this.get(configId);
if (!storedNoun)
return undefined;
const configNoun = results[0];
const value = configNoun.data?.configValue || configNoun.metadata?.configValue;
const encrypted = configNoun.data?.encrypted || configNoun.metadata?.encrypted;
// The config data is now stored in metadata
const value = storedNoun.metadata?.configValue;
const encrypted = storedNoun.metadata?.encrypted;
if (encrypted && typeof value === 'string') {
const decrypted = await this.decryptData(value);
return JSON.parse(decrypted);

File diff suppressed because one or more lines are too long

View file

@ -0,0 +1,25 @@
{
"_name_or_path": "sentence-transformers/all-MiniLM-L6-v2",
"architectures": [
"BertModel"
],
"attention_probs_dropout_prob": 0.1,
"classifier_dropout": null,
"gradient_checkpointing": false,
"hidden_act": "gelu",
"hidden_dropout_prob": 0.1,
"hidden_size": 384,
"initializer_range": 0.02,
"intermediate_size": 1536,
"layer_norm_eps": 1e-12,
"max_position_embeddings": 512,
"model_type": "bert",
"num_attention_heads": 12,
"num_hidden_layers": 6,
"pad_token_id": 0,
"position_embedding_type": "absolute",
"transformers_version": "4.29.2",
"type_vocab_size": 2,
"use_cache": true,
"vocab_size": 30522
}

File diff suppressed because it is too large Load diff

View file

@ -0,0 +1,15 @@
{
"clean_up_tokenization_spaces": true,
"cls_token": "[CLS]",
"do_basic_tokenize": true,
"do_lower_case": true,
"mask_token": "[MASK]",
"model_max_length": 512,
"never_split": null,
"pad_token": "[PAD]",
"sep_token": "[SEP]",
"strip_accents": null,
"tokenize_chinese_chars": true,
"tokenizer_class": "BertTokenizer",
"unk_token": "[UNK]"
}

View file

@ -6614,18 +6614,22 @@ export class BrainyData<T = any> implements BrainyDataInterface<T> {
* @param options Options including encryption
*/
async setConfig(key: string, value: any, options?: { encrypt?: boolean }): Promise<void> {
const configNoun = {
configKey: key,
configValue: options?.encrypt ? await this.encryptData(JSON.stringify(value)) : value,
encrypted: !!options?.encrypt,
timestamp: new Date().toISOString()
}
// Use a predictable ID based on the config key
const configId = `config-${key}`
// Store the config data in metadata (not as vectorized data)
const configValue = options?.encrypt ? await this.encryptData(JSON.stringify(value)) : value
// Use simple text for vectorization
const searchableText = `Configuration setting for ${key}`
await this.add(configNoun, {
await this.add(searchableText, {
nounType: NounType.State,
configKey: key,
encrypted: !!options?.encrypt
} as T)
configValue: configValue,
encrypted: !!options?.encrypt,
timestamp: new Date().toISOString()
} as T, { id: configId })
}
/**
@ -6636,26 +6640,15 @@ export class BrainyData<T = any> implements BrainyDataInterface<T> {
*/
async getConfig(key: string, options?: { decrypt?: boolean }): Promise<any> {
try {
const results = await this.search(`config ${key}`, 10, {
nounTypes: [NounType.State],
metadata: { configKey: key }
})
if (results.length === 0) return undefined
const result = results[0]
// Use the predictable ID to get the config directly
const configId = `config-${key}`
const storedNoun = await this.get(configId)
// Check if the config data is in the vector data (from the add call)
// The search result has: { id, score, vector, metadata }
// The actual config object was the data that got vectorized
// Try to get the stored noun data first
const storedNoun = await this.get(result.id)
if (!storedNoun) return undefined
// The stored noun should contain our original configNoun object
const value = (storedNoun as any).configValue
const encrypted = (storedNoun as any).encrypted || result.metadata?.encrypted
// The config data is now stored in metadata
const value = (storedNoun.metadata as any)?.configValue
const encrypted = (storedNoun.metadata as any)?.encrypted
if (encrypted && typeof value === 'string') {
const decrypted = await this.decryptData(value)

File diff suppressed because one or more lines are too long