@claude-flow/cli 3.10.24 → 3.10.25

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@claude-flow/cli",
-  "version": "3.10.24",
+  "version": "3.10.25",
   "type": "module",
   "description": "Ruflo CLI - Enterprise AI agent orchestration with 60+ specialized agents, swarm coordination, MCP server, self-learning hooks, and vector memory for Claude Code",
   "main": "dist/src/index.js",

package/scripts/run-beir-bge.mjs

@@ -0,0 +1,292 @@
+#!/usr/bin/env node
+// run-beir-bge.mjs — NFCorpus retrieval using real BGE-base-en-v1.5
+// embeddings (bypasses neural-tools' broken agentic-flow path that hash-fell-
+// back on darwin-arm64 without sharp/libvips).
+//
+// Stores doc embeddings in a single .f32 binary file (3633 * 768 * 4 = ~11MB)
+// for fast bench iteration without re-embedding.
+//
+// Usage:
+//   cd /tmp/beir-nfcorpus
+//   node /path/to/scripts/run-beir-bge.mjs                          # full ingest + bench
+//   SKIP_INGEST=1 node /path/to/scripts/run-beir-bge.mjs            # reuse cached embeds
+//   BGE_MODEL=Xenova/bge-small-en-v1.5 node ...                     # faster, lower-quality
+//   BGE_MODEL=Xenova/bge-large-en-v1.5 node ...                     # slower, higher-quality
+//
+// ADR-086.
+
+import { readFileSync, writeFileSync, existsSync, mkdirSync } from 'node:fs';
+import { fileURLToPath } from 'node:url';
+import { dirname, join, resolve } from 'node:path';
+import { performance } from 'node:perf_hooks';
+
+const SCRIPT_DIR = dirname(fileURLToPath(import.meta.url));
+const CLI_ROOT = resolve(SCRIPT_DIR, '..');
+const RUFLO_ROOT = resolve(SCRIPT_DIR, '../../../..');
+const RUNS_DIR = join(RUFLO_ROOT, 'docs', 'benchmarks', 'runs');
+
+const DATA_DIR = process.env.BEIR_DATA_DIR || '/tmp/beir-nfcorpus/nfcorpus';
+const CACHE_DIR = join('/tmp/beir-nfcorpus', 'bge-cache');
+const BGE_MODEL = process.env.BGE_MODEL || 'Xenova/bge-base-en-v1.5';
+const SKIP_INGEST = process.env.SKIP_INGEST === '1';
+const MAX_QUERIES = Number(process.env.MAX_QUERIES) || 0;
+
+// Published BEIR baselines per dataset (nDCG@10).
+// Sources: Thakur et al. 2021 (BEIR paper), BGE paper (BAAI 2024),
+// SPLADE++ paper, papers-with-code BEIR leaderboards.
+const BASELINES_BY_DATASET = {
+  nfcorpus: {
+    'BM25 (Lucene)':        0.325,
+    'DocT5query':           0.328,
+    'TAS-B':                0.319,
+    'GenQ':                 0.319,
+    'ColBERT':              0.305,
+    'Contriever':           0.328,
+    'GTR-XL':               0.343,
+    'SPLADE++':             0.347,
+    'BGE-large-v1.5 (pub)': 0.380,
+    'SBERT msmarco':        0.272,
+  },
+  scifact: {
+    'BM25 (Lucene)':        0.679,
+    'DocT5query':           0.675,
+    'TAS-B':                0.643,
+    'GenQ':                 0.644,
+    'ColBERT':              0.671,
+    'Contriever':           0.677,
+    'GTR-XL':               0.662,
+    'SPLADE++':             0.704,
+    'BGE-large-v1.5 (pub)': 0.722,
+    'SBERT msmarco':        0.555,
+  },
+};
+
+// Auto-detect dataset from DATA_DIR path; default to nfcorpus baselines.
+function detectDataset(path) {
+  const p = path.toLowerCase();
+  for (const ds of Object.keys(BASELINES_BY_DATASET)) {
+    if (p.includes(ds)) return ds;
+  }
+  return 'nfcorpus';
+}
+
+// ---------------------------------------------------------------------------
+// nDCG (graded)
+// ---------------------------------------------------------------------------
+
+function dcg(rels, k) {
+  let s = 0;
+  for (let i = 0; i < Math.min(rels.length, k); i++) {
+    s += (Math.pow(2, rels[i]) - 1) / Math.log2(i + 2);
+  }
+  return s;
+}
+function ndcg(retrieved, qrels, k) {
+  const rels = retrieved.slice(0, k).map((id) => qrels.get(id) ?? 0);
+  const ideal = [...qrels.values()].sort((a, b) => b - a).slice(0, k);
+  const idcg = dcg(ideal, k);
+  return idcg > 0 ? dcg(rels, k) / idcg : 0;
+}
+function mrr(retrieved, qrels, k) {
+  for (let i = 0; i < Math.min(retrieved.length, k); i++) {
+    if ((qrels.get(retrieved[i]) ?? 0) > 0) return 1 / (i + 1);
+  }
+  return 0;
+}
+function recall(retrieved, qrels, k) {
+  const tot = [...qrels.values()].filter((v) => v > 0).length;
+  if (tot === 0) return 0;
+  let h = 0;
+  for (let i = 0; i < Math.min(retrieved.length, k); i++) {
+    if ((qrels.get(retrieved[i]) ?? 0) > 0) h++;
+  }
+  return h / tot;
+}
+
+function cosine(a, b) {
+  let s = 0;
+  for (let i = 0; i < a.length; i++) s += a[i] * b[i];
+  return s; // already L2-normalised in BGE
+}
+
+// ---------------------------------------------------------------------------
+// Loaders
+// ---------------------------------------------------------------------------
+
+function loadJsonl(path) {
+  return readFileSync(path, 'utf-8').split('\n').filter(Boolean).map((l) => JSON.parse(l));
+}
+function loadQrels(path) {
+  const qrels = new Map();
+  const lines = readFileSync(path, 'utf-8').split('\n');
+  for (let i = 1; i < lines.length; i++) {
+    if (!lines[i].trim()) continue;
+    const [qid, did, score] = lines[i].split('\t');
+    if (!qrels.has(qid)) qrels.set(qid, new Map());
+    qrels.get(qid).set(did, Number(score));
+  }
+  return qrels;
+}
+
+// ---------------------------------------------------------------------------
+// Embedding cache I/O — single .f32 file + .ids file
+// ---------------------------------------------------------------------------
+
+function cachePath(suffix) {
+  const safe = BGE_MODEL.replace(/\//g, '_');
+  return join(CACHE_DIR, `${safe}.${suffix}`);
+}
+
+function saveEmbeddings(ids, embeddings, dim) {
+  mkdirSync(CACHE_DIR, { recursive: true });
+  // ids: one per line
+  writeFileSync(cachePath('ids'), ids.join('\n') + '\n');
+  // embeddings: concatenated Float32Array
+  const buf = new Float32Array(ids.length * dim);
+  for (let i = 0; i < ids.length; i++) buf.set(embeddings[i], i * dim);
+  writeFileSync(cachePath('f32'), Buffer.from(buf.buffer));
+}
+
+function loadEmbeddings(dim) {
+  if (!existsSync(cachePath('ids')) || !existsSync(cachePath('f32'))) return null;
+  const ids = readFileSync(cachePath('ids'), 'utf-8').split('\n').filter(Boolean);
+  const raw = readFileSync(cachePath('f32'));
+  const buf = new Float32Array(raw.buffer, raw.byteOffset, raw.length / 4);
+  const embeds = [];
+  for (let i = 0; i < ids.length; i++) embeds.push(buf.slice(i * dim, (i + 1) * dim));
+  return { ids, embeds };
+}
+
+// ---------------------------------------------------------------------------
+// Main
+// ---------------------------------------------------------------------------
+
+async function main() {
+  const dataset = detectDataset(DATA_DIR);
+  const BASELINES_NDCG10 = BASELINES_BY_DATASET[dataset];
+  console.log(`# BEIR ${dataset} — BGE embedder (ADR-085/086)`);
+  console.log(`Model: ${BGE_MODEL}`);
+  console.log(`Data:  ${DATA_DIR}`);
+
+  const corpus = loadJsonl(join(DATA_DIR, 'corpus.jsonl'));
+  const queries = loadJsonl(join(DATA_DIR, 'queries.jsonl'));
+  const qrels = loadQrels(join(DATA_DIR, 'qrels/test.tsv'));
+  console.log(`Corpus: ${corpus.length} docs · Queries: ${queries.length} · Test qrels: ${qrels.size}`);
+
+  const bge = await import(join(CLI_ROOT, 'dist/src/memory/bge-embedder.js'));
+  const emb = await bge.getBgeEmbedder(BGE_MODEL);
+  if (!emb) {
+    console.error('BGE failed to load:', bge.getBgeStatus());
+    process.exit(1);
+  }
+  const dim = emb.dim();
+  console.log(`BGE loaded (dim=${dim})`);
+
+  // Ingest or load cached doc embeddings.
+  let docIds, docEmbeds;
+  const cached = SKIP_INGEST ? loadEmbeddings(dim) : null;
+  if (cached) {
+    docIds = cached.ids;
+    docEmbeds = cached.embeds;
+    console.log(`Loaded ${docIds.length} cached doc embeddings from ${cachePath('f32')}`);
+  } else {
+    console.log(`\nEmbedding ${corpus.length} docs (this is the slow step, ~20 min on M-series CPU)...`);
+    docIds = corpus.map((d) => d._id);
+    docEmbeds = new Array(corpus.length);
+    const tIngest = performance.now();
+    for (let i = 0; i < corpus.length; i++) {
+      const d = corpus[i];
+      const text = `${d.title || ''}\n${d.text || ''}`.slice(0, 4096);
+      docEmbeds[i] = await emb.embed(text);
+      if ((i + 1) % 100 === 0) {
+        const elapsed = (performance.now() - tIngest) / 1000;
+        const rate = (i + 1) / elapsed;
+        const eta = (corpus.length - i - 1) / rate;
+        console.log(`  ${i + 1}/${corpus.length}  ${rate.toFixed(1)} docs/s  ETA ${eta.toFixed(0)}s`);
+      }
+    }
+    console.log(`Embedded ${corpus.length} docs in ${((performance.now() - tIngest) / 1000).toFixed(0)}s`);
+    saveEmbeddings(docIds, docEmbeds, dim);
+    console.log(`Cached to ${cachePath('f32')}`);
+  }
+
+  // Run retrieval per query.
+  const queriesById = new Map(queries.map((q) => [q._id, q.text]));
+  const evalQueryIds = MAX_QUERIES
+    ? [...qrels.keys()].slice(0, MAX_QUERIES)
+    : [...qrels.keys()];
+
+  console.log(`\nRunning ${evalQueryIds.length} queries...`);
+  let nSum = 0, mSum = 0, r10Sum = 0, r100Sum = 0, n = 0;
+  const tQ = performance.now();
+  for (const qid of evalQueryIds) {
+    const qtext = queriesById.get(qid);
+    if (!qtext) continue;
+    // BGE recommends prepending "Represent this sentence for searching relevant passages:" to queries
+    // but only for v1.5 *en-icl* variants. v1.5 (non-icl) works without it.
+    const qEmb = await emb.embed(qtext);
+    // Score every doc, sort.
+    const scores = new Array(docEmbeds.length);
+    for (let i = 0; i < docEmbeds.length; i++) scores[i] = { id: docIds[i], score: cosine(qEmb, docEmbeds[i]) };
+    scores.sort((a, b) => b.score - a.score);
+    const top100 = scores.slice(0, 100).map((s) => s.id);
+
+    const qmap = qrels.get(qid);
+    nSum += ndcg(top100, qmap, 10);
+    mSum += mrr(top100, qmap, 10);
+    r10Sum += recall(top100, qmap, 10);
+    r100Sum += recall(top100, qmap, 100);
+    n++;
+    if (n % 50 === 0) {
+      const elapsed = (performance.now() - tQ) / 1000;
+      console.log(`  ${n}/${evalQueryIds.length} in ${elapsed.toFixed(0)}s  running nDCG@10=${(nSum / n).toFixed(4)}`);
+    }
+  }
+  const queryMs = performance.now() - tQ;
+
+  const ndcg10 = nSum / n;
+  const mrr10 = mSum / n;
+  const recall10 = r10Sum / n;
+  const recall100 = r100Sum / n;
+
+  console.log(`\n=== Results (N=${n}, BGE-base-en-v1.5) ===`);
+  console.log(`  nDCG@10:    ${ndcg10.toFixed(4)}`);
+  console.log(`  MRR@10:     ${mrr10.toFixed(4)}`);
+  console.log(`  Recall@10:  ${recall10.toFixed(4)}`);
+  console.log(`  Recall@100: ${recall100.toFixed(4)}`);
+  console.log(`  Avg query latency: ${(queryMs / n).toFixed(0)}ms`);
+
+  console.log(`\n=== vs published NFCorpus baselines (nDCG@10) ===`);
+  const ourLabel = `ruflo + ${BGE_MODEL.replace('Xenova/', '')}`;
+  const ranking = [
+    ...Object.entries(BASELINES_NDCG10).map(([name, score]) => ({ name, score, ours: false })),
+    { name: ourLabel, score: ndcg10, ours: true },
+  ].sort((a, b) => b.score - a.score);
+  for (const r of ranking) {
+    console.log(`  ${r.score.toFixed(3)}  ${r.name}${r.ours ? ' ← us' : ''}`);
+  }
+  const ourRank = ranking.findIndex((r) => r.ours) + 1;
+  console.log(`\n  Our rank: ${ourRank} / ${ranking.length}`);
+
+  const summary = {
+    runAt: new Date().toISOString(),
+    benchmark: `beir-${dataset}-bge`,
+    dataset,
+    model: BGE_MODEL,
+    queries: n,
+    corpusSize: corpus.length,
+    metrics: { ndcg10, mrr10, recall10, recall100, avgQueryLatencyMs: queryMs / n },
+    baselines: BASELINES_NDCG10,
+    ourRank,
+    leaderboardLength: ranking.length,
+  };
+  mkdirSync(RUNS_DIR, { recursive: true });
+  const stamp = summary.runAt.replace(/[:.]/g, '-');
+  const safe = BGE_MODEL.replace(/\//g, '_');
+  writeFileSync(join(RUNS_DIR, `beir-${dataset}-bge-${safe}-${stamp}.json`), JSON.stringify(summary, null, 2));
+  writeFileSync(join(RUNS_DIR, `beir-${dataset}-bge-latest.json`), JSON.stringify(summary, null, 2));
+  console.log(`\nWrote ${join(RUNS_DIR, `beir-${dataset}-bge-${safe}-${stamp}.json`)}`);
+  process.exit(0);
+}
+
+main().catch((err) => { console.error(err); process.exit(1); });

package/scripts/run-beir-nfcorpus.mjs

@@ -0,0 +1,231 @@
+#!/usr/bin/env node
+// run-beir-nfcorpus.mjs — public benchmark harness for BEIR NFCorpus.
+//
+// Why NFCorpus: smallest BEIR dataset (3.6k docs, 323 test queries) with a
+// well-published BM25 baseline and dense-retriever ceilings — runs end-to-end
+// in <15 min on this hardware.
+//
+// Setup:
+//   mkdir -p /tmp/beir-nfcorpus && cd /tmp/beir-nfcorpus
+//   curl -sL -o nfcorpus.zip 'https://public.ukp.informatik.tu-darmstadt.de/thakur/BEIR/datasets/nfcorpus.zip'
+//   unzip -q nfcorpus.zip
+//
+// Run:
+//   cd /tmp/beir-nfcorpus && rm -rf .claude-flow
+//   node /path/to/scripts/run-beir-nfcorpus.mjs
+//
+// Reports:
+//   - nDCG@10 (graded, BEIR standard)
+//   - MRR@10
+//   - Recall@10, Recall@100
+//   - Published comparisons (BM25, ColBERT, SPLADE, etc.)
+
+import { readFileSync, writeFileSync, mkdirSync, readdirSync, statSync } from 'node:fs';
+import { fileURLToPath } from 'node:url';
+import { dirname, join, resolve } from 'node:path';
+import { performance } from 'node:perf_hooks';
+
+const SCRIPT_DIR = dirname(fileURLToPath(import.meta.url));
+const CLI_ROOT = resolve(SCRIPT_DIR, '..');
+const RUFLO_ROOT = resolve(SCRIPT_DIR, '../../../..');
+const RUNS_DIR = join(RUFLO_ROOT, 'docs', 'benchmarks', 'runs');
+
+const DATA_DIR = process.env.BEIR_DATA_DIR || '/tmp/beir-nfcorpus/nfcorpus';
+const TOP_K = Number(process.env.TOP_K) || 100;     // top-100 for recall@100
+const NDCG_K = 10;
+const MAX_QUERIES = Number(process.env.MAX_QUERIES) || 0;  // 0 = all
+const SKIP_INGEST = process.env.SKIP_INGEST === '1'; // reuse existing store
+
+// Published BEIR NFCorpus baselines (from Thakur et al. 2021 + leaderboard tracker)
+const BASELINES_NDCG10 = {
+  'BM25':            0.325,
+  'DocT5query':      0.328,
+  'SBERT (msmarco)': 0.272,  // dense bi-encoder on MS MARCO
+  'TAS-B':           0.319,
+  'GenQ':            0.319,
+  'ColBERT':         0.305,
+  'SPLADE++':        0.347,  // top dense at time of paper
+  'Contriever':      0.328,
+  'GTR-XL':          0.343,
+  'BGE-large-v1.5':  0.380,  // current ~top-of-class
+};
+
+// ---------------------------------------------------------------------------
+// nDCG with graded relevance (BEIR standard)
+// ---------------------------------------------------------------------------
+
+function dcg(rels, k) {
+  let s = 0;
+  for (let i = 0; i < Math.min(rels.length, k); i++) {
+    s += (Math.pow(2, rels[i]) - 1) / Math.log2(i + 2);
+  }
+  return s;
+}
+
+function ndcg(retrievedDocIds, qrelsMap, k) {
+  const rels = retrievedDocIds.slice(0, k).map((id) => qrelsMap.get(id) ?? 0);
+  const ideal = [...qrelsMap.values()].sort((a, b) => b - a).slice(0, k);
+  const idcg = dcg(ideal, k);
+  return idcg > 0 ? dcg(rels, k) / idcg : 0;
+}
+
+function mrr(retrievedDocIds, qrelsMap, k) {
+  for (let i = 0; i < Math.min(retrievedDocIds.length, k); i++) {
+    if ((qrelsMap.get(retrievedDocIds[i]) ?? 0) > 0) return 1 / (i + 1);
+  }
+  return 0;
+}
+
+function recall(retrievedDocIds, qrelsMap, k) {
+  const totalRelevant = [...qrelsMap.values()].filter((v) => v > 0).length;
+  if (totalRelevant === 0) return 0;
+  let hit = 0;
+  for (let i = 0; i < Math.min(retrievedDocIds.length, k); i++) {
+    if ((qrelsMap.get(retrievedDocIds[i]) ?? 0) > 0) hit++;
+  }
+  return hit / totalRelevant;
+}
+
+// ---------------------------------------------------------------------------
+// Loaders
+// ---------------------------------------------------------------------------
+
+function loadJsonl(path) {
+  const items = [];
+  for (const line of readFileSync(path, 'utf-8').split('\n')) {
+    if (!line.trim()) continue;
+    items.push(JSON.parse(line));
+  }
+  return items;
+}
+
+function loadQrels(path) {
+  // Map<queryId, Map<docId, grade>>
+  const qrels = new Map();
+  const lines = readFileSync(path, 'utf-8').split('\n');
+  for (let i = 1; i < lines.length; i++) {
+    if (!lines[i].trim()) continue;
+    const [qid, did, score] = lines[i].split('\t');
+    if (!qrels.has(qid)) qrels.set(qid, new Map());
+    qrels.get(qid).set(did, Number(score));
+  }
+  return qrels;
+}
+
+// ---------------------------------------------------------------------------
+// Main
+// ---------------------------------------------------------------------------
+
+async function main() {
+  console.log(`# BEIR NFCorpus benchmark (ADR-085)`);
+  console.log(`Data: ${DATA_DIR}`);
+  console.log(`Cwd: ${process.cwd()}`);
+
+  const corpus = loadJsonl(join(DATA_DIR, 'corpus.jsonl'));
+  const queries = loadJsonl(join(DATA_DIR, 'queries.jsonl'));
+  const qrels = loadQrels(join(DATA_DIR, 'qrels/test.tsv'));
+
+  console.log(`Corpus: ${corpus.length} docs, ${queries.length} queries (total), ${qrels.size} eval queries (test split)`);
+
+  const neural = await import(join(CLI_ROOT, 'dist/src/mcp-tools/neural-tools.js'));
+  const tool = neural.neuralTools.find((t) => t.name === 'neural_patterns');
+
+  // §1 — Ingest corpus (id-stable pattern name = doc _id; content = title + text).
+  // Skip if SKIP_INGEST=1 and store already populated.
+  if (!SKIP_INGEST) {
+    console.log(`\nIngesting ${corpus.length} docs...`);
+    const t0 = performance.now();
+    // Batch in chunks to avoid memory pressure.
+    const CHUNK = 200;
+    for (let i = 0; i < corpus.length; i += CHUNK) {
+      const batch = corpus.slice(i, i + CHUNK);
+      await neural.storeNeuralPatterns(batch.map((d) => ({
+        name: d._id,                         // use _id as the stable identifier
+        type: 'beir-nfcorpus',
+        content: `${d.title || ''}\n${d.text || ''}`.slice(0, 4096),
+      })));
+      if ((i + CHUNK) % 1000 === 0 || i + CHUNK >= corpus.length) {
+        const pct = Math.min(100, ((i + CHUNK) / corpus.length * 100)).toFixed(0);
+        const elapsed = (performance.now() - t0) / 1000;
+        console.log(`  ${Math.min(i + CHUNK, corpus.length)}/${corpus.length} (${pct}%) in ${elapsed.toFixed(0)}s`);
+      }
+    }
+    console.log(`Ingest done in ${((performance.now() - t0) / 1000).toFixed(0)}s`);
+  } else {
+    console.log('SKIP_INGEST=1 → reusing existing store');
+  }
+
+  // §2 — Build query lookup (eval queries only).
+  const queriesById = new Map(queries.map((q) => [q._id, q.text]));
+  const evalQueryIds = MAX_QUERIES
+    ? [...qrels.keys()].slice(0, MAX_QUERIES)
+    : [...qrels.keys()];
+
+  // §3 — Run retrieval for each query, compute metrics.
+  console.log(`\nRunning ${evalQueryIds.length} queries...`);
+  let ndcgSum = 0, mrrSum = 0, recall10Sum = 0, recall100Sum = 0;
+  const tQ = performance.now();
+  let queryIdx = 0;
+  for (const qid of evalQueryIds) {
+    const qtext = queriesById.get(qid);
+    if (!qtext) { queryIdx++; continue; }
+    const r = await tool.handler({ action: 'search', query: qtext, mode: 'hybrid', limit: TOP_K, rerank: false });
+    const retrievedIds = (r.results || []).map((m) => m.name);  // we set name = _id
+    const qrelsMap = qrels.get(qid) || new Map();
+    ndcgSum += ndcg(retrievedIds, qrelsMap, NDCG_K);
+    mrrSum += mrr(retrievedIds, qrelsMap, NDCG_K);
+    recall10Sum += recall(retrievedIds, qrelsMap, 10);
+    recall100Sum += recall(retrievedIds, qrelsMap, 100);
+    queryIdx++;
+    if (queryIdx % 50 === 0) {
+      const elapsed = (performance.now() - tQ) / 1000;
+      console.log(`  ${queryIdx}/${evalQueryIds.length} in ${elapsed.toFixed(0)}s — running nDCG@10=${(ndcgSum / queryIdx).toFixed(4)}`);
+    }
+  }
+  const queryMs = performance.now() - tQ;
+  const N = evalQueryIds.length;
+  const ndcg10 = ndcgSum / N;
+  const mrr10 = mrrSum / N;
+  const recall10 = recall10Sum / N;
+  const recall100 = recall100Sum / N;
+
+  console.log(`\n=== Results (N=${N} queries) ===`);
+  console.log(`  nDCG@10:    ${ndcg10.toFixed(4)}`);
+  console.log(`  MRR@10:     ${mrr10.toFixed(4)}`);
+  console.log(`  Recall@10:  ${recall10.toFixed(4)}`);
+  console.log(`  Recall@100: ${recall100.toFixed(4)}`);
+  console.log(`  Avg query latency: ${(queryMs / N).toFixed(0)}ms`);
+
+  console.log(`\n=== vs published NFCorpus nDCG@10 baselines ===`);
+  const ourEntry = { name: 'ruflo hybrid (3.10.25)', score: ndcg10, ours: true };
+  const ranking = [
+    ...Object.entries(BASELINES_NDCG10).map(([name, score]) => ({ name, score, ours: false })),
+    ourEntry,
+  ].sort((a, b) => b.score - a.score);
+  for (const r of ranking) {
+    const marker = r.ours ? ' ← us' : '';
+    console.log(`  ${r.score.toFixed(3)}  ${r.name}${marker}`);
+  }
+  const ourRank = ranking.findIndex((r) => r.ours) + 1;
+  console.log(`\n  Our rank: ${ourRank} / ${ranking.length}`);
+
+  const summary = {
+    runAt: new Date().toISOString(),
+    benchmark: 'beir-nfcorpus',
+    queries: N,
+    corpusSize: corpus.length,
+    metrics: { ndcg10, mrr10, recall10, recall100, avgQueryLatencyMs: queryMs / N },
+    baselines: BASELINES_NDCG10,
+    ourRank,
+    leaderboardLength: ranking.length,
+  };
+  mkdirSync(RUNS_DIR, { recursive: true });
+  const stamp = summary.runAt.replace(/[:.]/g, '-');
+  writeFileSync(join(RUNS_DIR, `beir-nfcorpus-${stamp}.json`), JSON.stringify(summary, null, 2));
+  writeFileSync(join(RUNS_DIR, 'beir-nfcorpus-latest.json'), JSON.stringify(summary, null, 2));
+  console.log(`\nWrote ${join(RUNS_DIR, `beir-nfcorpus-${stamp}.json`)}`);
+
+  process.exit(0);
+}
+
+main().catch((err) => { console.error(err); process.exit(1); });