codehere 0.2.2 → 0.3.0-rc.10

package/dist/search.js

@@ -1,163 +0,0 @@
-import { config } from 'dotenv';
-import { join, dirname } from 'path';
-import { fileURLToPath } from 'url';
-// CohereClient is lazy-loaded to avoid hard dependency
-import initSqlJs from 'sql.js';
-import { readFileSync, existsSync } from 'fs';
-import { optimizeContext } from './token-optimizer.js';
-import { optimizeQuery } from './query-optimizer.js';
-// Load .env from agent directory
-try {
-    const __filename = fileURLToPath(import.meta.url);
-    const __dirname = dirname(__filename);
-    const agentDir = join(__dirname, '..');
-    config({ path: join(agentDir, '.env') });
-}
-catch {
-    // Fallback
-}
-config(); // Also try current directory
-function getSearchEmbedding(text) {
-    if (process.env.OPENAI_API_KEY) {
-        return fetch('https://api.openai.com/v1/embeddings', {
-            method: 'POST',
-            headers: {
-                'Authorization': `Bearer ${process.env.OPENAI_API_KEY}`,
-                'Content-Type': 'application/json',
-            },
-            body: JSON.stringify({ input: text, model: 'text-embedding-3-small' }),
-        }).then(async (r) => {
-            if (!r.ok)
-                throw new Error(`OpenAI embedding error: ${r.status}`);
-            const data = await r.json();
-            return data.data?.[0]?.embedding || [];
-        });
-    }
-    if (process.env.COHERE_API_KEY) {
-        const { CohereClient } = require('cohere-ai');
-        const cohere = new CohereClient({ token: process.env.COHERE_API_KEY });
-        return cohere.embed({
-            texts: [text],
-            model: 'embed-english-v3.0',
-            inputType: 'search_query',
-        }).then((response) => {
-            const embeddings = Array.isArray(response.embeddings)
-                ? response.embeddings
-                : response.embeddings.embeddings || [];
-            return embeddings[0] || [];
-        });
-    }
-    throw new Error('No embedding API key found. Set OPENAI_API_KEY or COHERE_API_KEY.');
-}
-/**
- * @deprecated Legacy global DB path - this module is legacy
- * Active CLI flows use per-repo embeddings via SQLiteEmbeddingRepository
- * This search.ts module is kept for backward compatibility only
- */
-function getDbPath() {
-    const __filename = fileURLToPath(import.meta.url);
-    const __dirname = dirname(__filename);
-    const agentDir = join(__dirname, '..');
-    // Check if we're in the agent directory structure
-    if (existsSync(join(agentDir, 'package.json'))) {
-        return join(agentDir, 'data', 'embeddings.sqlite');
-    }
-    // Otherwise use current directory
-    return join(process.cwd(), 'agent', 'data', 'embeddings.sqlite');
-}
-// Legacy DB_PATH - not used in active CLI flows
-const DB_PATH = getDbPath();
-function cosineSimilarity(a, b) {
-    if (a.length !== b.length)
-        return 0;
-    let dotProduct = 0;
-    let normA = 0;
-    let normB = 0;
-    for (let i = 0; i < a.length; i++) {
-        dotProduct += a[i] * b[i];
-        normA += a[i] * a[i];
-        normB += b[i] * b[i];
-    }
-    const denominator = Math.sqrt(normA) * Math.sqrt(normB);
-    if (denominator === 0)
-        return 0;
-    return dotProduct / denominator;
-}
-/**
- * Legacy search - kept for backward compatibility
- * Use getIntelligentContext() for new code
- */
-export async function searchSimilar(query, topK = 15) {
-    // Embed the query using available provider
-    const queryEmbedding = await getSearchEmbedding(query);
-    // Load database
-    if (!existsSync(DB_PATH)) {
-        return [];
-    }
-    const SQL = await initSqlJs();
-    const buffer = readFileSync(DB_PATH);
-    const db = new SQL.Database(buffer);
-    // Query all embeddings
-    const stmt = db.prepare('SELECT * FROM embeddings');
-    const rows = [];
-    while (stmt.step()) {
-        const row = stmt.getAsObject();
-        rows.push({
-            id: row.id,
-            filepath: row.filepath,
-            chunkIndex: row.chunkIndex,
-            content: row.content,
-            embedding: row.embedding,
-        });
-    }
-    stmt.free();
-    // Calculate similarities
-    const results = [];
-    for (const row of rows) {
-        const chunkEmbedding = JSON.parse(row.embedding);
-        const similarity = cosineSimilarity(queryEmbedding, chunkEmbedding);
-        results.push({
-            chunk: {
-                id: row.id,
-                filepath: row.filepath,
-                chunkIndex: row.chunkIndex,
-                content: row.content,
-                embedding: chunkEmbedding,
-            },
-            score: similarity,
-        });
-    }
-    db.close();
-    // Sort by similarity and return top K
-    results.sort((a, b) => b.score - a.score);
-    return results.slice(0, topK).map(result => ({
-        filepath: result.chunk.filepath,
-        content: result.chunk.content,
-        score: result.score,
-    }));
-}
-/**
- * NEW: Intelligent search with AST-based understanding
- * Uses searchSimilar internally to avoid circular dependency
- */
-export async function searchIntelligent(query, options = {}) {
-    // Optimize query first
-    const { optimizedQuery, strategy } = optimizeQuery(query);
-    // Use searchSimilar (no circular dependency)
-    const initialResults = await searchSimilar(optimizedQuery, 30);
-    if (initialResults.length === 0) {
-        return {
-            chunks: [],
-            tokenEstimate: 0,
-            reductionPercent: 0,
-        };
-    }
-    // Optimize context tokens
-    const optimized = optimizeContext(initialResults, optimizedQuery, strategy.maxTokens, strategy.contextStrategy);
-    return {
-        chunks: optimized.chunks,
-        tokenEstimate: optimized.totalTokens,
-        reductionPercent: optimized.reductionPercent,
-    };
-}
-//# sourceMappingURL=search.js.map