promptgraph-mcp 1.5.9 → 1.5.11

package/ann.js

@@ -23,14 +23,24 @@ export async function buildAnnIndex() {
   const db = getDb();
   const chunks = db.prepare('SELECT skill_id, chunk_index, embedding FROM chunks').all();
 
-  for (const chunk of chunks) {
-    const vec = JSON.parse(chunk.embedding);
-    await index.insertItem({
-      vector: vec,
-      metadata: { skill_id: chunk.skill_id, chunk_index: chunk.chunk_index },
-    });
+  // Batch ALL inserts into a single disk write — vectra otherwise
+  // persists the whole index on every insertItem (O(N^2) I/O).
+  await index.beginUpdate();
+  try {
+    for (const chunk of chunks) {
+      const vec = JSON.parse(chunk.embedding);
+      await index.insertItem({
+        vector: vec,
+        metadata: { skill_id: chunk.skill_id, chunk_index: chunk.chunk_index },
+      });
+    }
+    await index.endUpdate();
+  } catch (e) {
+    try { index.cancelUpdate(); } catch {}
+    throw e;
   }
 
+  _index = null; // force reload so queries see fresh index
   console.error(`[PromptGraph] ANN index built: ${chunks.length} chunks`);
 }
 
@@ -38,6 +48,8 @@ export async function annSearch(queryVec, topK = 20) {
   try {
     const index = await getIndex();
     if (!await index.isIndexCreated()) return null;
+    const items = await index.listItems();
+    if (!items || items.length === 0) return null;
 
     const results = await index.queryItems(queryVec, topK);
     return results.map(r => ({

package/config.js

@@ -37,7 +37,7 @@ export async function promptConfig() {
   const extra = await ask('\nAdd extra skill directories? (comma-separated paths, or press Enter to skip): ');
   rl.close();
 
-  const config = { ...DEFAULTS };
+  const config = structuredClone(DEFAULTS);
 
   if (extra.trim()) {
     const extraDirs = extra.split(',').map(d => d.trim()).filter(Boolean);

package/doctor.js

@@ -0,0 +1,48 @@
+import { getDb } from './db.js';
+
+export function runDoctor() {
+  const db = getDb();
+  const report = {};
+
+  // orphaned chunks (skill_id not in skills)
+  const orphanChunks = db.prepare(`
+    DELETE FROM chunks WHERE skill_id NOT IN (SELECT id FROM skills)
+  `).run();
+  report.orphanChunks = orphanChunks.changes;
+
+  // orphaned ratings
+  const orphanRatings = db.prepare(`
+    DELETE FROM ratings WHERE skill_id NOT IN (SELECT id FROM skills)
+  `).run();
+  report.orphanRatings = orphanRatings.changes;
+
+  // orphaned edges where from_skill no longer exists
+  const orphanFromEdges = db.prepare(`
+    DELETE FROM edges WHERE from_skill NOT IN (SELECT id FROM skills)
+  `).run();
+  report.orphanFromEdges = orphanFromEdges.changes;
+
+  // dangling edges where to_skill is a bare name that never resolved to a real skill
+  // (keep edges that point to real ids OR bare names that match a skill name)
+  const danglingEdges = db.prepare(`
+    DELETE FROM edges
+    WHERE to_skill NOT IN (SELECT id FROM skills)
+      AND to_skill NOT IN (SELECT name FROM skills)
+  `).run();
+  report.danglingEdges = danglingEdges.changes;
+
+  // duplicate skills by path (should not happen, but check)
+  const dupPaths = db.prepare(`
+    SELECT path, COUNT(*) as c FROM skills GROUP BY path HAVING c > 1
+  `).all();
+  report.duplicatePaths = dupPaths.length;
+
+  db.pragma('wal_checkpoint(TRUNCATE)');
+  db.exec('VACUUM');
+
+  report.totalSkills = db.prepare('SELECT COUNT(*) as c FROM skills').get().c;
+  report.totalChunks = db.prepare('SELECT COUNT(*) as c FROM chunks').get().c;
+  report.totalEdges = db.prepare('SELECT COUNT(*) as c FROM edges').get().c;
+
+  return report;
+}

package/index.js

@@ -20,7 +20,7 @@ const args = process.argv.slice(2);
 const rawBin = process.argv[1]?.split(/[\\/]/).pop()?.replace(/\.js$/, '');
 const bin = (rawBin && rawBin !== 'index') ? rawBin : 'pg';
 
-const KNOWN_COMMANDS = new Set(['init', 'reindex', 'import', 'setup', 'validate', 'marketplace', 'help', '--help', '-h']);
+const KNOWN_COMMANDS = new Set(['init', 'reindex', 'import', 'setup', 'validate', 'marketplace', 'doctor', 'help', '--help', '-h']);
 
 function showHelp() {
   console.log(
@@ -37,6 +37,7 @@ function showHelp() {
     ['import <owner/repo>', 'Import skills from GitHub'],
     ['marketplace [page]',  'Browse the community skill registry'],
     ['validate <file.md>',  'Validate a skill before publishing'],
+    ['doctor',              'Clean orphaned chunks/edges/ratings'],
     ['setup <platform>',    'Register MCP in platform config'],
     ['help',                'Show this help'],
   ];
@@ -58,6 +59,19 @@ if (!KNOWN_COMMANDS.has(args[0])) {
   process.exit(1);
 }
 
+if (args[0] === 'doctor') {
+  const { runDoctor } = await import('./doctor.js');
+  const spin = (await import('./cli.js')).spinner('Checking database...');
+  spin.start();
+  const r = runDoctor();
+  spin.stop();
+  success('Database checked');
+  info(`Removed: ${r.orphanChunks} chunks, ${r.orphanRatings} ratings, ${r.orphanFromEdges + r.danglingEdges} edges`);
+  if (r.duplicatePaths > 0) info(chalk.yellow(`Warning: ${r.duplicatePaths} duplicate paths`));
+  info(chalk.gray(`Now: ${r.totalSkills} skills, ${r.totalChunks} chunks, ${r.totalEdges} edges`));
+  process.exit(0);
+}
+
 if (args[0] === 'marketplace') {
   const { browseMarketplace } = await import('./marketplace.js');
   const PER_PAGE = 10;

package/indexer.js

@@ -58,11 +58,15 @@ async function indexBatch(db, skills) {
   })();
 
   // pass 2: resolve edges after all skills in batch are committed
+  const resolveSameSource = db.prepare("SELECT id FROM skills WHERE name = ? AND source = ? LIMIT 1");
+  const resolveAny = db.prepare("SELECT id FROM skills WHERE name = ? ORDER BY id LIMIT 1");
   db.transaction(() => {
     for (const skill of skills) {
       const id = skillId(skill.source, skill.name);
       for (const calledName of skill.calls) {
-        const resolved = db.prepare("SELECT id FROM skills WHERE name = ? ORDER BY id LIMIT 1").get(calledName);
+        // prefer a skill in the same source, fall back to any, then bare name
+        const same = resolveSameSource.get(calledName, skill.source);
+        const resolved = same || resolveAny.get(calledName);
         upsertEdge.run(id, resolved ? resolved.id : calledName);
       }
     }

package/marketplace.js

@@ -1,6 +1,7 @@
 import fs from 'fs';
 import path from 'path';
 import os from 'os';
+import https from 'https';
 import { spawnSync } from 'child_process';
 import { getDb } from './db.js';
 import { validateSkill } from './validator.js';
@@ -8,11 +9,39 @@ import { validateSkill } from './validator.js';
 const REGISTRY_URL = 'https://raw.githubusercontent.com/NeiP4n/promptgraph-registry/main/registry.json';
 const SKILLS_DIR = path.join(os.homedir(), '.claude', 'skills-store', 'marketplace');
 
+// Robust fetch: try undici fetch, fall back to node:https (works where undici fails on Windows)
+function httpGet(url) {
+  return new Promise((resolve, reject) => {
+    https.get(url, { headers: { 'User-Agent': 'promptgraph-mcp' } }, (res) => {
+      if (res.statusCode >= 300 && res.statusCode < 400 && res.headers.location) {
+        return httpGet(res.headers.location).then(resolve, reject);
+      }
+      if (res.statusCode !== 200) {
+        res.resume();
+        return reject(new Error(`HTTP ${res.statusCode}`));
+      }
+      let data = '';
+      res.setEncoding('utf8');
+      res.on('data', c => data += c);
+      res.on('end', () => resolve(data));
+    }).on('error', reject);
+  });
+}
+
+async function fetchText(url) {
+  try {
+    const res = await fetch(url, { headers: { 'User-Agent': 'promptgraph-mcp' } });
+    if (!res.ok) throw new Error(`HTTP ${res.status}`);
+    return await res.text();
+  } catch {
+    return await httpGet(url);
+  }
+}
+
 export async function browseMarketplace(topK = 20) {
   try {
-    const res = await fetch(REGISTRY_URL);
-    if (!res.ok) return { error: `Registry returned ${res.status}. Check https://github.com/NeiP4n/promptgraph-registry` };
-    const registry = await res.json();
+    const text = await fetchText(REGISTRY_URL);
+    const registry = JSON.parse(text);
     if (!Array.isArray(registry.skills)) return { error: 'Invalid registry format' };
     return registry.skills
       .sort((a, b) => (b.stars || 0) - (a.stars || 0))
@@ -24,9 +53,8 @@ export async function browseMarketplace(topK = 20) {
 
 export async function installSkill(skillId) {
   try {
-    const res = await fetch(REGISTRY_URL);
-    if (!res.ok) return { error: `Registry returned ${res.status}` };
-    const registry = await res.json();
+    const text = await fetchText(REGISTRY_URL);
+    const registry = JSON.parse(text);
     const skill = registry.skills?.find(s => s.id === skillId);
     if (!skill) return { error: `Skill "${skillId}" not found in registry` };
     if (!skill.raw_url) return { error: `Skill "${skillId}" has no download URL` };
@@ -34,10 +62,8 @@ export async function installSkill(skillId) {
     fs.mkdirSync(SKILLS_DIR, { recursive: true });
     const dest = path.join(SKILLS_DIR, `${skillId}.md`);
 
-    const content = await fetch(skill.raw_url);
-    if (!content.ok) return { error: `Failed to download skill: ${content.status}` };
-    const text = await content.text();
-    fs.writeFileSync(dest, text);
+    const content = await fetchText(skill.raw_url);
+    fs.writeFileSync(dest, content);
 
     return { success: true, path: dest, name: skill.name };
   } catch (e) {

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "promptgraph-mcp",
-  "version": "1.5.9",
+  "version": "1.5.11",
   "main": "index.js",
   "type": "module",
   "bin": {
@@ -11,7 +11,8 @@
   "scripts": {
     "start": "node index.js",
     "init": "node index.js init",
-    "reindex": "node index.js reindex"
+    "reindex": "node index.js reindex",
+    "test": "vitest run"
   },
   "keywords": [
     "claude",
@@ -43,5 +44,8 @@
     "gray-matter": "^4.0.3",
     "ora": "^9.4.0",
     "vectra": "^0.15.0"
+  },
+  "devDependencies": {
+    "vitest": "^4.1.8"
   }
 }