@claude-flow/cli 3.42.1 → 3.42.3

package/dist/src/memory/rabitq-index.js

@@ -81,11 +81,11 @@ export async function buildRabitqIndex(options) {
             const SQL = await initSqlJs();
             const fileBuffer = fs.readFileSync(dbPath);
             const db = new SQL.Database(fileBuffer);
-            const result = db.exec(`
-        SELECT id, key, namespace, embedding
-        FROM memory_entries
-        WHERE status = 'active' AND embedding IS NOT NULL
-        LIMIT 50000
+            const result = db.exec(`
+        SELECT id, key, namespace, embedding
+        FROM memory_entries
+        WHERE status = 'active' AND embedding IS NOT NULL
+        LIMIT 50000
       `);
             if (result[0]?.values) {
                 for (const row of result[0].values) {

package/dist/src/proxy/verify.js

@@ -15,8 +15,8 @@ import { createHash, createPublicKey, verify as cryptoVerify } from 'node:crypto
  * live 2026-07-16 by verifying a real `SHA256SUMS.sig` from the v0.1.0
  * release against it (crypto.verify -> true).
  */
-export const PROXY_RELEASE_PUBKEY_PEM = `-----BEGIN PUBLIC KEY-----
-MCowBQYDK2VwAyEAjhLDomjIGdcltYC7j+aiESQFD4LWoHaULietG1PuDjw=
+export const PROXY_RELEASE_PUBKEY_PEM = `-----BEGIN PUBLIC KEY-----
+MCowBQYDK2VwAyEAjhLDomjIGdcltYC7j+aiESQFD4LWoHaULietG1PuDjw=
 -----END PUBLIC KEY-----`;
 export class ReleaseVerificationError extends Error {
     constructor(message) {

package/dist/src/runtime/headless.js

@@ -62,34 +62,34 @@ function parseArgs() {
  * Show help message
  */
 function showHelp() {
-    console.log(`
-Headless Runtime for RuFlo V3
-
-Usage:
-  headless --worker <type>    Run a specific worker
-  headless --daemon           Start background daemon
-  headless --benchmark        Run performance benchmarks
-  headless --status           Show system status
-
-Workers: ${HEADLESS_WORKER_TYPES.join(', ')}
-
-Options:
-  -w, --worker <type>   Worker type to run
-  -d, --daemon          Run as daemon
-  -b, --benchmark       Run benchmarks
-  -s, --status          Show status
-  -t, --timeout <ms>    Execution timeout (default: 60000)
-  -v, --verbose         Verbose output
-  -h, --help            Show help
-
-Environment:
-  CLAUDE_FLOW_HEADLESS=true   Enable headless mode
-  CLAUDE_CODE_HEADLESS=true   Enable Claude Code headless
-
-Examples:
-  headless --worker audit --timeout 120000
-  headless --daemon
-  headless --benchmark
+    console.log(`
+Headless Runtime for RuFlo V3
+
+Usage:
+  headless --worker <type>    Run a specific worker
+  headless --daemon           Start background daemon
+  headless --benchmark        Run performance benchmarks
+  headless --status           Show system status
+
+Workers: ${HEADLESS_WORKER_TYPES.join(', ')}
+
+Options:
+  -w, --worker <type>   Worker type to run
+  -d, --daemon          Run as daemon
+  -b, --benchmark       Run benchmarks
+  -s, --status          Show status
+  -t, --timeout <ms>    Execution timeout (default: 60000)
+  -v, --verbose         Verbose output
+  -h, --help            Show help
+
+Environment:
+  CLAUDE_FLOW_HEADLESS=true   Enable headless mode
+  CLAUDE_CODE_HEADLESS=true   Enable Claude Code headless
+
+Examples:
+  headless --worker audit --timeout 120000
+  headless --daemon
+  headless --benchmark
 `);
 }
 /**

package/dist/src/ruvector/diskann-backend.d.ts

@@ -0,0 +1,78 @@
+/**
+ * DiskANN Vector Search Backend
+ *
+ * SSD-friendly approximate nearest neighbor search using Vamana graph.
+ * Falls back gracefully to HNSW (@ruvector/router VectorDb) or
+ * pure-JS cosine similarity when DiskANN is unavailable.
+ *
+ * @module v3/cli/ruvector/diskann-backend
+ */
+export interface DiskAnnConfig {
+    dim: number;
+    maxDegree?: number;
+    buildBeam?: number;
+    searchBeam?: number;
+    alpha?: number;
+    pqSubspaces?: number;
+    storagePath?: string;
+}
+export interface SearchResult {
+    id: string;
+    distance: number;
+    score: number;
+}
+export type VectorBackend = 'diskann' | 'hnsw' | 'cosine-js';
+/**
+ * Check if @ruvector/diskann is available
+ */
+export declare function isDiskAnnAvailable(): Promise<boolean>;
+/**
+ * Create or get a DiskANN index instance
+ */
+export declare function getDiskAnnIndex(config: DiskAnnConfig): Promise<{
+    index: any;
+    backend: VectorBackend;
+}>;
+/**
+ * Get the active backend name
+ */
+export declare function getActiveBackend(): VectorBackend;
+/**
+ * Reset the index (for testing)
+ */
+export declare function resetIndex(): void;
+/**
+ * Insert a vector into the active backend
+ */
+export declare function insertVector(id: string, vector: Float32Array, config?: DiskAnnConfig): Promise<{
+    backend: VectorBackend;
+}>;
+/**
+ * Build the index (required for DiskANN before search)
+ */
+export declare function buildIndex(config?: DiskAnnConfig): Promise<void>;
+/**
+ * Search for k nearest neighbors
+ */
+export declare function searchVectors(query: Float32Array, k: number, config?: DiskAnnConfig): Promise<SearchResult[]>;
+export interface BenchmarkResult {
+    backend: VectorBackend;
+    dim: number;
+    vectorCount: number;
+    insertTimeMs: number;
+    buildTimeMs: number;
+    searchTimeMs: number;
+    searchesPerSecond: number;
+    recall: number;
+    memoryMB: number;
+}
+/**
+ * Run a benchmark comparing available backends
+ */
+export declare function benchmark(opts?: {
+    dim?: number;
+    vectorCount?: number;
+    k?: number;
+    queries?: number;
+}): Promise<BenchmarkResult[]>;
+//# sourceMappingURL=diskann-backend.d.ts.map

package/dist/src/ruvector/diskann-backend.js

@@ -0,0 +1,310 @@
+/**
+ * DiskANN Vector Search Backend
+ *
+ * SSD-friendly approximate nearest neighbor search using Vamana graph.
+ * Falls back gracefully to HNSW (@ruvector/router VectorDb) or
+ * pure-JS cosine similarity when DiskANN is unavailable.
+ *
+ * @module v3/cli/ruvector/diskann-backend
+ */
+// ===== Lazy loading =====
+let diskannInstance = null;
+let diskannAvailable = null;
+let activeBackend = 'cosine-js';
+/**
+ * Check if @ruvector/diskann is available
+ */
+export async function isDiskAnnAvailable() {
+    if (diskannAvailable !== null)
+        return diskannAvailable;
+    try {
+        const { createRequire } = await import('module');
+        const require2 = createRequire(import.meta.url);
+        const mod = require2('@ruvector/diskann');
+        diskannAvailable = typeof mod.DiskAnn === 'function';
+        return diskannAvailable;
+    }
+    catch {
+        diskannAvailable = false;
+        return false;
+    }
+}
+/**
+ * Create or get a DiskANN index instance
+ */
+export async function getDiskAnnIndex(config) {
+    if (diskannInstance)
+        return { index: diskannInstance, backend: activeBackend };
+    // Try DiskANN first
+    if (await isDiskAnnAvailable()) {
+        try {
+            const { createRequire } = await import('module');
+            const require2 = createRequire(import.meta.url);
+            const { DiskAnn } = require2('@ruvector/diskann');
+            const index = new DiskAnn({
+                dim: config.dim,
+                maxDegree: config.maxDegree ?? 64,
+                buildBeam: config.buildBeam ?? 128,
+                searchBeam: config.searchBeam ?? 64,
+                alpha: config.alpha ?? 1.2,
+                pqSubspaces: config.pqSubspaces ?? 0,
+                storagePath: config.storagePath,
+            });
+            diskannInstance = index;
+            activeBackend = 'diskann';
+            return { index, backend: 'diskann' };
+        }
+        catch {
+            // Fall through
+        }
+    }
+    // Try HNSW (@ruvector/router VectorDb) as fallback
+    try {
+        const { createRequire } = await import('module');
+        const require2 = createRequire(import.meta.url);
+        const router = require2('@ruvector/router');
+        if (router.VectorDb && router.DistanceMetric) {
+            const index = new router.VectorDb({
+                dimensions: config.dim,
+                distanceMetric: router.DistanceMetric.Cosine,
+                hnswM: 16,
+                hnswEfConstruction: 200,
+                hnswEfSearch: 100,
+            });
+            diskannInstance = index;
+            activeBackend = 'hnsw';
+            return { index, backend: 'hnsw' };
+        }
+    }
+    catch {
+        // Fall through
+    }
+    // Pure JS fallback
+    const jsIndex = createJsFallbackIndex(config.dim);
+    diskannInstance = jsIndex;
+    activeBackend = 'cosine-js';
+    return { index: jsIndex, backend: 'cosine-js' };
+}
+/**
+ * Get the active backend name
+ */
+export function getActiveBackend() {
+    return activeBackend;
+}
+/**
+ * Reset the index (for testing)
+ */
+export function resetIndex() {
+    diskannInstance = null;
+    diskannAvailable = null;
+    activeBackend = 'cosine-js';
+}
+// ===== Unified search interface =====
+/**
+ * Insert a vector into the active backend
+ */
+export async function insertVector(id, vector, config = { dim: 384 }) {
+    const { index, backend } = await getDiskAnnIndex(config);
+    if (backend === 'diskann') {
+        index.insert(id, vector);
+    }
+    else if (backend === 'hnsw') {
+        index.insert(id, vector);
+    }
+    else {
+        index.insert(id, vector);
+    }
+    return { backend };
+}
+/**
+ * Build the index (required for DiskANN before search)
+ */
+export async function buildIndex(config = { dim: 384 }) {
+    const { index, backend } = await getDiskAnnIndex(config);
+    if (backend === 'diskann' && typeof index.build === 'function') {
+        index.build();
+    }
+    // HNSW and JS fallback don't need explicit build
+}
+/**
+ * Search for k nearest neighbors
+ */
+export async function searchVectors(query, k, config = { dim: 384 }) {
+    const { index, backend } = await getDiskAnnIndex(config);
+    if (backend === 'diskann') {
+        const results = index.search(query, k);
+        return results.map((r) => ({
+            id: r.id,
+            distance: r.distance,
+            score: 1 / (1 + r.distance), // Convert L2 distance to similarity
+        }));
+    }
+    if (backend === 'hnsw') {
+        const results = index.search(query, k);
+        return results.map((r) => ({
+            id: r.id,
+            distance: r.score, // VectorDb returns distance as 'score'
+            score: 1 / (1 + r.score),
+        }));
+    }
+    // JS fallback
+    return index.search(query, k);
+}
+// ===== Pure JS fallback =====
+function createJsFallbackIndex(dim) {
+    const vectors = new Map();
+    return {
+        insert(id, vector) {
+            vectors.set(id, new Float32Array(vector));
+        },
+        search(query, k) {
+            const results = [];
+            for (const [id, vec] of vectors) {
+                let dot = 0, normQ = 0, normV = 0;
+                for (let i = 0; i < dim; i++) {
+                    dot += query[i] * vec[i];
+                    normQ += query[i] * query[i];
+                    normV += vec[i] * vec[i];
+                }
+                const cosine = dot / (Math.sqrt(normQ) * Math.sqrt(normV) || 1);
+                const distance = 1 - cosine;
+                results.push({ id, distance, score: cosine });
+            }
+            return results.sort((a, b) => a.distance - b.distance).slice(0, k);
+        },
+        count() { return vectors.size; },
+        delete(id) { return vectors.delete(id); },
+        build() { },
+    };
+}
+/**
+ * Run a benchmark comparing available backends
+ */
+export async function benchmark(opts = {}) {
+    const dim = opts.dim ?? 384;
+    const n = opts.vectorCount ?? 1000;
+    const k = opts.k ?? 10;
+    const queryCount = opts.queries ?? 100;
+    const results = [];
+    // Generate random vectors
+    const vectors = [];
+    for (let i = 0; i < n; i++) {
+        const v = new Float32Array(dim);
+        for (let j = 0; j < dim; j++)
+            v[j] = Math.random() * 2 - 1;
+        // Normalize
+        let norm = 0;
+        for (let j = 0; j < dim; j++)
+            norm += v[j] * v[j];
+        norm = Math.sqrt(norm);
+        for (let j = 0; j < dim; j++)
+            v[j] /= norm;
+        vectors.push([`vec-${i}`, v]);
+    }
+    // Generate query vectors
+    const queries = [];
+    for (let i = 0; i < queryCount; i++) {
+        const q = new Float32Array(dim);
+        for (let j = 0; j < dim; j++)
+            q[j] = Math.random() * 2 - 1;
+        let norm = 0;
+        for (let j = 0; j < dim; j++)
+            norm += q[j] * q[j];
+        norm = Math.sqrt(norm);
+        for (let j = 0; j < dim; j++)
+            q[j] /= norm;
+        queries.push(q);
+    }
+    // Brute force ground truth
+    function bruteForceSearch(query) {
+        const scores = [];
+        for (const [id, vec] of vectors) {
+            let dist = 0;
+            for (let j = 0; j < dim; j++) {
+                const d = query[j] - vec[j];
+                dist += d * d;
+            }
+            scores.push({ id, dist });
+        }
+        scores.sort((a, b) => a.dist - b.dist);
+        return scores.slice(0, k).map(s => s.id);
+    }
+    const groundTruth = queries.map(q => bruteForceSearch(q));
+    // Test each available backend
+    for (const backendName of ['diskann', 'hnsw', 'cosine-js']) {
+        resetIndex();
+        try {
+            let index;
+            const memBefore = process.memoryUsage().heapUsed;
+            if (backendName === 'diskann') {
+                if (!(await isDiskAnnAvailable()))
+                    continue;
+                const { createRequire } = await import('module');
+                const require2 = createRequire(import.meta.url);
+                const { DiskAnn } = require2('@ruvector/diskann');
+                index = new DiskAnn({ dim, maxDegree: 64, buildBeam: 128, searchBeam: 64 });
+            }
+            else if (backendName === 'hnsw') {
+                try {
+                    const { createRequire } = await import('module');
+                    const require2 = createRequire(import.meta.url);
+                    const router = require2('@ruvector/router');
+                    if (!router.VectorDb)
+                        continue;
+                    index = new router.VectorDb({ dimensions: dim, distanceMetric: router.DistanceMetric.Cosine });
+                }
+                catch {
+                    continue;
+                }
+            }
+            else {
+                index = createJsFallbackIndex(dim);
+            }
+            // Insert
+            const insertStart = performance.now();
+            for (const [id, vec] of vectors) {
+                index.insert(id, vec);
+            }
+            const insertTime = performance.now() - insertStart;
+            // Build
+            const buildStart = performance.now();
+            if (typeof index.build === 'function')
+                index.build();
+            const buildTime = performance.now() - buildStart;
+            // Search
+            const searchStart = performance.now();
+            const searchResults = [];
+            for (const q of queries) {
+                const r = index.search(q, k);
+                searchResults.push(r.map((x) => x.id));
+            }
+            const searchTime = performance.now() - searchStart;
+            // Recall vs ground truth
+            let totalRecall = 0;
+            for (let i = 0; i < queryCount; i++) {
+                const truth = new Set(groundTruth[i]);
+                const found = searchResults[i].filter(id => truth.has(id)).length;
+                totalRecall += found / k;
+            }
+            const recall = totalRecall / queryCount;
+            const memAfter = process.memoryUsage().heapUsed;
+            results.push({
+                backend: backendName,
+                dim,
+                vectorCount: n,
+                insertTimeMs: Math.round(insertTime * 100) / 100,
+                buildTimeMs: Math.round(buildTime * 100) / 100,
+                searchTimeMs: Math.round(searchTime * 100) / 100,
+                searchesPerSecond: Math.round(queryCount / (searchTime / 1000)),
+                recall: Math.round(recall * 1000) / 1000,
+                memoryMB: Math.round((memAfter - memBefore) / 1024 / 1024 * 100) / 100,
+            });
+        }
+        catch {
+            // Backend failed, skip
+        }
+    }
+    resetIndex();
+    return results;
+}
+//# sourceMappingURL=diskann-backend.js.map

package/dist/src/services/distill-tuning.js

@@ -278,9 +278,9 @@ function buildQuerySet(db, opts) {
         return [];
     const placeholders = namespaces.map(() => '?').join(',');
     const hiFinite = Number.isFinite(hiRowid);
-    const sql = `SELECT rowid, id, namespace, content, embedding FROM memory_entries
-    WHERE rowid > ? ${hiFinite ? 'AND rowid <= ?' : ''} AND embedding IS NOT NULL
-      AND COALESCE(namespace,'default') IN (${placeholders})
+    const sql = `SELECT rowid, id, namespace, content, embedding FROM memory_entries
+    WHERE rowid > ? ${hiFinite ? 'AND rowid <= ?' : ''} AND embedding IS NOT NULL
+      AND COALESCE(namespace,'default') IN (${placeholders})
     ORDER BY rowid`;
     const args = hiFinite ? [loRowid, hiRowid, ...namespaces] : [loRowid, ...namespaces];
     const rows = db.prepare(sql).all(...args);
@@ -398,7 +398,7 @@ function resetDistillationState(db) {
     }
 }
 function applyCorroboratedPromotion(db) {
-    db.prepare(`UPDATE reasoning_patterns SET metadata = json_set(metadata, '$.promoted', 1)
+    db.prepare(`UPDATE reasoning_patterns SET metadata = json_set(metadata, '$.promoted', 1)
      WHERE json_extract(metadata, '$.provenance') = 'proxy:structural' AND uses >= ?`).run(CORROBORATION_MIN_USES);
 }
 // ── Scoring (MRR@K / recall@K, shared by candidate + baseline paths) ────
@@ -437,9 +437,9 @@ function isTopicallyCorrect(q, p) {
 // ── pattern_embeddings BLOB → number[] ───────────────────────────────────
 function loadPromotedPatternIndex(db) {
     const rows = db
-        .prepare(`SELECT rp.id AS id, rp.tags AS tags, rp.metadata AS metadata, pe.embedding AS embedding
-       FROM reasoning_patterns rp
-       JOIN pattern_embeddings pe ON pe.pattern_id = rp.id
+        .prepare(`SELECT rp.id AS id, rp.tags AS tags, rp.metadata AS metadata, pe.embedding AS embedding
+       FROM reasoning_patterns rp
+       JOIN pattern_embeddings pe ON pe.pattern_id = rp.id
        WHERE json_extract(rp.metadata, '$.promoted') = 1`)
         .all();
     return rows.map((r) => {