homegraph 1.5.0 → 1.5.2

package/scripts/agent-eval/probe-sweep.mjs

@@ -1,119 +0,0 @@
-#!/usr/bin/env node
-// probe-sweep — direct MCP test across N repos × N tools, no claude needed.
-//
-// Measures response characteristics (size, sections present, signals fired)
-// for each (repo, query) pair against the built dist/. Sub-second per probe;
-// the full sweep below runs in ~10-30s vs hours for a real claude audit.
-//
-// Use this to iterate on backend changes rapidly: change tools.ts /
-// context-builder, npm run build, re-run probe-sweep, compare. Once a
-// change looks good on probe metrics, run a focused claude audit for the
-// few repos that matter to confirm end-to-end cost behavior.
-//
-// Usage: node scripts/agent-eval/probe-sweep.mjs [--tool=context|explore|trace] [--repos=a,b,c]
-import { pathToFileURL } from 'node:url';
-import { resolve } from 'node:path';
-
-const args = Object.fromEntries(
-  process.argv.slice(2).map(a => a.startsWith('--') ? a.slice(2).split('=') : [a, true])
-);
-const TOOL = args.tool ?? 'context';
-
-const load = (rel) => import(pathToFileURL(resolve(rel)).href);
-const idx = await load('dist/index.js');
-const tools = await load('dist/mcp/tools.js');
-const HomeGraph = idx.default?.default ?? idx.default ?? idx.HomeGraph;
-const ToolHandler = tools.ToolHandler ?? tools.default?.ToolHandler;
-
-// Each entry: repo, query, optional 2nd arg for trace (from, to).
-// The query is the same prompt used in the real claude audits, so probe
-// output is directly comparable to the agent's would-be input.
-const SWEEP = [
-  // Small realworld template repos (the loss cases from the cross-language sweep)
-  { id: 'gin-rw',        repo: '/tmp/homegraph-corpus/gin-realworld',         q: 'How does this Gin app route a request through its middleware chain to a handler?' },
-  { id: 'go-mux',        repo: '/tmp/homegraph-corpus/go-mux',                q: 'How does this gorilla/mux app route a request to its handler?' },
-  { id: 'fastapi-rw',    repo: '/tmp/homegraph-corpus/fastapi-realworld',     q: 'How does FastAPI route a request through its dependencies to a handler?' },
-  { id: 'spring-pc',     repo: '/tmp/homegraph-corpus/spring-petclinic',      q: 'How does Spring route an HTTP request to a controller method?' },
-  { id: 'axum-rw',       repo: '/tmp/homegraph-corpus/rust-axum-realworld',   q: 'How does Axum route a request to its handler in this app?' },
-  { id: 'express-rw',    repo: '/tmp/homegraph-corpus/express-realworld',     q: 'How does this Express app route a request through middleware to a handler?' },
-  { id: 'kotlin-pc',     repo: '/tmp/homegraph-corpus/kotlin-petclinic',      q: 'How does the Kotlin Spring app route an HTTP request to its handler?' },
-  { id: 'flask-mb',      repo: '/tmp/homegraph-corpus/flask-microblog',       q: 'How does this Flask app route a request to a view function?' },
-  { id: 'vapor-tpl',     repo: '/tmp/homegraph-corpus/vapor-template',        q: 'How does Vapor route an HTTP request to its handler?' },
-  { id: 'cpp-leveldb',   repo: '/tmp/homegraph-corpus/cpp-leveldb',           q: 'How does LevelDB handle a Put operation through to disk?' },
-  { id: 'lualine',       repo: '/tmp/homegraph-corpus/lualine.nvim',          q: 'How does lualine assemble and render the statusline?' },
-  { id: 'drupal-admin',  repo: '/tmp/homegraph-corpus/drupal-admintoolbar',   q: 'How does the Drupal admin toolbar module render its toolbar?' },
-  { id: 'svelte-rw',     repo: '/tmp/homegraph-corpus/svelte-realworld',      q: 'How does this SvelteKit app route a request to a handler?' },
-  { id: 'react-rw',      repo: '/tmp/homegraph-corpus/react-realworld',       q: 'How does this React app fetch and display articles?' },
-  { id: 'rails-rw',      repo: '/tmp/homegraph-corpus/rails-realworld',       q: 'How does Rails route a request to a controller action?' },
-  { id: 'flask-rest',    repo: '/tmp/homegraph-corpus/flask-restful-realworld', q: 'How does Flask-RESTful route a request to a resource method?' },
-  { id: 'laravel-rw',    repo: '/tmp/homegraph-corpus/laravel-realworld',     q: 'How does Laravel route a request to the controller method?' },
-  { id: 'aspnet-rw',     repo: '/tmp/homegraph-corpus/aspnet-realworld',      q: 'How does ASP.NET route a request to the controller action?' },
-  // The iter7 wins/ties (to make sure we don't regress)
-  { id: 'cobra',         repo: '/tmp/homegraph-corpus/cobra',                 q: 'How does cobra parse commands and flags?' },
-  { id: 'sinatra',       repo: '/tmp/homegraph-corpus/sinatra',               q: 'How does sinatra route a request to its handler?' },
-  { id: 'slim',          repo: '/tmp/homegraph-corpus/slim',                  q: 'How does slim route a request and apply middleware?' },
-];
-
-// Detect signals in response text — these are the levers we've added that
-// otherwise only show up via "agent ran X more tool calls" downstream.
-const detect = (text) => ({
-  hasEntryPoints: /^### Entry Points/m.test(text),
-  hasRelatedSymbols: /^### Related Symbols/m.test(text),
-  hasFlowTrace: /^## Inline flow trace/m.test(text),
-  hasRouteManifest: /^## Routing manifest/m.test(text),
-  hasTopHandler: /^### Top handler file/m.test(text),
-  hasSmallRepoTail: /This project is small/.test(text),
-});
-
-const filterRepos = args.repos ? new Set(String(args.repos).split(',')) : null;
-const subjects = SWEEP.filter(s => !filterRepos || filterRepos.has(s.id));
-
-const t0 = Date.now();
-const rows = [];
-for (const s of subjects) {
-  try {
-    const cg = HomeGraph.openSync(s.repo);
-    const handler = new ToolHandler(cg);
-    const t1 = Date.now();
-    const res = await handler.execute('homegraph_' + TOOL,
-      TOOL === 'context' ? { task: s.q } :
-      TOOL === 'explore' ? { query: s.q } : { from: 'main', to: 'main' });
-    const text = res.content?.[0]?.text ?? '';
-    const signals = detect(text);
-    rows.push({
-      id: s.id,
-      ms: Date.now() - t1,
-      chars: text.length,
-      lines: text.split('\n').length,
-      ...signals,
-    });
-    try { cg.close?.(); } catch {}
-  } catch (e) {
-    rows.push({ id: s.id, error: String(e).slice(0, 80) });
-  }
-}
-
-// Pretty-print as a compact table.
-const fmt = (r) =>
-  r.error
-    ? `  ${r.id.padEnd(13)} ERROR: ${r.error}`
-    : `  ${r.id.padEnd(13)} ${String(r.chars).padStart(6)}c ${String(r.lines).padStart(4)}L ${String(r.ms).padStart(4)}ms` +
-      ` ${r.hasEntryPoints ? 'EP ' : '   '}` +
-      `${r.hasFlowTrace ? 'TRC ' : '    '}` +
-      `${r.hasRouteManifest ? 'MAN ' : '    '}` +
-      `${r.hasTopHandler ? 'HND ' : '    '}` +
-      `${r.hasSmallRepoTail ? 'TAIL' : '    '}`;
-console.log(`=== probe-sweep tool=${TOOL} n=${subjects.length} (${Date.now() - t0}ms total) ===`);
-console.log('  id            chars  lines    ms signals');
-console.log('  ' + '-'.repeat(56));
-for (const r of rows) console.log(fmt(r));
-
-// Sum + medians for the size pillar
-const sizes = rows.filter(r => !r.error).map(r => r.chars);
-sizes.sort((a, b) => a - b);
-const median = sizes[Math.floor(sizes.length / 2)];
-const sum = sizes.reduce((a, b) => a + b, 0);
-console.log(`  ${'-'.repeat(64)}`);
-console.log(`  median=${median}c  total=${sum}c  ` +
-  `manifest=${rows.filter(r => r.hasRouteManifest).length}/${rows.filter(r => !r.error).length}  ` +
-  `top-handler=${rows.filter(r => r.hasTopHandler).length}/${rows.filter(r => !r.error).length}`);

package/scripts/agent-eval/probe-trace.mjs

@@ -1,20 +0,0 @@
-#!/usr/bin/env node
-// Probe homegraph_trace against an index using the built dist.
-// Usage: node probe-trace.mjs <repo-with-.homegraph> <from> <to>
-import { pathToFileURL } from 'node:url';
-import { resolve } from 'node:path';
-
-const [, , repo, from, to] = process.argv;
-if (!repo || !from || !to) { console.error('usage: probe-trace.mjs <repo> <from> <to>'); process.exit(1); }
-
-const load = async (rel) => import(pathToFileURL(resolve(rel)).href);
-const idx = await load('dist/index.js');
-const tools = await load('dist/mcp/tools.js');
-const HomeGraph = idx.default?.default ?? idx.default ?? idx.HomeGraph;
-const ToolHandler = tools.ToolHandler ?? tools.default?.ToolHandler;
-
-const cg = HomeGraph.openSync(repo);
-const h = new ToolHandler(cg);
-const res = await h.execute('homegraph_trace', { from, to });
-console.log(res.content?.[0]?.text ?? '(no text)');
-try { cg.close?.(); } catch {}

package/scripts/agent-eval/redirect-read-hook.sh

@@ -1,38 +0,0 @@
-#!/usr/bin/env bash
-# PreToolUse(Read) REDIRECT hook — prototype for A/B (P1: get agents off Read and
-# onto homegraph_node during implementation, not just for Q&A).
-#
-# When the agent Reads a SOURCE file, deny it and steer to homegraph_node's
-# file-view, which (as of the Lever-1 change) returns the WHOLE file verbatim
-# WITH line numbers — imports, top-level code, comments and all — PLUS the file's
-# blast radius, in one call. That output is a strict superset of Read, so the
-# redirect is lossless: the agent loses nothing by taking it, and gains who-
-# depends-on-this for the edit it's about to make.
-#
-# Differs from block-read-hook.sh (which steers to explore/node-by-symbol): this
-# names the FILE-VIEW path explicitly (file:"<base>" + includeCode:true), the
-# 1:1 Read replacement we're trying to get picked during implementation.
-#
-# Non-source files (configs, docs, lockfiles, .env) pass through to a real Read.
-# A redirect to a file homegraph hasn't indexed SELF-CORRECTS: the file-view
-# replies "No indexed file matches … Read it directly", so a just-created file
-# never dead-ends — the agent Reads it on the next turn.
-#
-# Wire via:  claude ... --settings <settings-with-this-as-PreToolUse(Read)>
-# Eval artifact only. The production version is an indexed-aware `homegraph`
-# subcommand (cross-platform — no bash/jq — and queries the index so it never
-# bounces a new/un-indexed file), wired opt-in by the installer.
-set -uo pipefail
-input="$(cat)"
-fp="$(printf '%s' "$input" | jq -r '.tool_input.file_path // empty' 2>/dev/null)"
-[ -n "$fp" ] || exit 0
-base="$(basename "$fp")"
-
-case "$fp" in
-  *.ts|*.tsx|*.js|*.jsx|*.mjs|*.cjs|*.py|*.go|*.rs|*.java|*.rb|*.php|*.swift|*.kt|*.kts|*.scala|*.c|*.cc|*.cpp|*.h|*.hpp|*.cs|*.lua|*.vue|*.svelte|*.m|*.mm)
-    msg="homegraph has this file indexed (kept in sync on every edit). Call homegraph_node with file:\"$base\" and includeCode:true instead of Read — it returns the WHOLE file verbatim WITH line numbers (imports, top-level code and all — safe to base an Edit on) PLUS which files depend on it, in one call. Treat its output as already-Read; do not Read this file. (If it answers that the file isn't indexed — e.g. you just created it — then Read it directly.)"
-    jq -n --arg m "$msg" '{hookSpecificOutput:{hookEventName:"PreToolUse",permissionDecision:"deny",permissionDecisionReason:$m}}'
-    exit 0
-    ;;
-esac
-exit 0

package/scripts/agent-eval/repro-concurrent-explore.mjs

@@ -1,119 +0,0 @@
-#!/usr/bin/env node
-// Reproduction harness A — does the shared daemon serialize concurrent explore?
-//
-// Mirrors the daemon's reality: ONE CodeGraph + ONE ToolHandler (as MCPEngine
-// shares across all sessions), then fires N concurrent codegraph_explore calls
-// and measures:
-//   - each call's wall-clock latency + completion order
-//   - an event-loop HEARTBEAT (setInterval 50ms): the max gap between ticks is a
-//     direct measure of how long synchronous compute blocked the loop. In the
-//     real daemon a blocked loop can't flush a finished response or read the
-//     next request, so this gap is what starves the MCP transport.
-//
-// Usage: node repro-concurrent-explore.mjs <repo-with-.codegraph> <N> [timeoutMs]
-import { pathToFileURL } from 'node:url';
-import { resolve } from 'node:path';
-import { performance } from 'node:perf_hooks';
-
-const [, , repo, nRaw, timeoutRaw] = process.argv;
-if (!repo) {
-  console.error('usage: repro-concurrent-explore.mjs <repo> <N=10> [timeoutMs=60000]');
-  process.exit(1);
-}
-const N = Number(nRaw) || 10;
-const TIMEOUT_MS = Number(timeoutRaw) || 60000; // ~ MCP SDK default request timeout
-
-const load = async (rel) => import(pathToFileURL(resolve(rel)).href);
-const idx = await load('dist/index.js');
-const tools = await load('dist/mcp/tools.js');
-const CodeGraph = idx.default?.default ?? idx.default ?? idx.CodeGraph;
-const ToolHandler = tools.ToolHandler ?? tools.default?.ToolHandler;
-
-// Distinct queries so no two calls are trivially identical. Mix of NL questions
-// (exercise FTS + RWR over the whole graph) — the expensive explore path.
-const QUERIES = [
-  'how does the text model handle edits and undo',
-  'how does the file service watch for changes on disk',
-  'how does the keybinding service resolve a chord to a command',
-  'how does the extension host activate an extension',
-  'how does the editor render decorations in the viewport',
-  'how does the search service stream results to the UI',
-  'how does the terminal process manager spawn a shell',
-  'how does the configuration service merge user and workspace settings',
-  'how does the debug adapter forward breakpoints to the runtime',
-  'how does the quick input widget filter its items',
-  'how does the notification service queue and show toasts',
-  'how does the git extension compute the diff for a file',
-  'how does the language features registry dispatch a hover request',
-  'how does the workbench layout restore editor groups on reload',
-  'how does the storage service persist state between sessions',
-  'how does the menu service build a context menu from contributions',
-];
-
-const cg = CodeGraph.openSync(repo);
-let fileCount = 0;
-try { fileCount = cg.getStats().fileCount; } catch {}
-const handler = new ToolHandler(cg);
-
-// --- event-loop heartbeat ---
-let lastTick = performance.now();
-let maxGap = 0;
-const gaps = [];
-const hb = setInterval(() => {
-  const now = performance.now();
-  const gap = now - lastTick;
-  lastTick = now;
-  if (gap > 60) gaps.push(Math.round(gap)); // expected ~50ms; record stalls
-  if (gap > maxGap) maxGap = gap;
-}, 50);
-
-function runOne(i) {
-  const q = QUERIES[i % QUERIES.length];
-  const startedAt = performance.now();
-  let timer;
-  const timeout = new Promise((res) => {
-    timer = setTimeout(() => res({ timedOut: true }), TIMEOUT_MS);
-  });
-  const work = handler
-    .execute('codegraph_explore', { query: q })
-    .then((r) => ({ ok: !r.isError, chars: r.content?.[0]?.text?.length ?? 0 }))
-    .catch((e) => ({ ok: false, err: String(e?.message ?? e) }));
-  return Promise.race([work, timeout]).then((r) => {
-    clearTimeout(timer);
-    return { i, q, ms: Math.round(performance.now() - startedAt), ...r };
-  });
-}
-
-// Baseline: one warm single call (so the first-call cold paths don't skew N).
-const warmStart = performance.now();
-await runOne(0);
-const warmMs = Math.round(performance.now() - warmStart);
-
-// Reset heartbeat stats for the concurrent run.
-gaps.length = 0; maxGap = 0; lastTick = performance.now();
-
-const batchStart = performance.now();
-const results = await Promise.all(Array.from({ length: N }, (_, i) => runOne(i)));
-const batchMs = Math.round(performance.now() - batchStart);
-clearInterval(hb);
-
-const lat = results.map((r) => r.ms).sort((a, b) => a - b);
-const timeouts = results.filter((r) => r.timedOut).length;
-const p = (q) => lat[Math.min(lat.length - 1, Math.floor(q * lat.length))];
-
-console.log('='.repeat(64));
-console.log(`repo=${repo}`);
-console.log(`fileCount=${fileCount}  N=${N}  perCallTimeout=${TIMEOUT_MS}ms`);
-console.log(`single warm explore: ${warmMs}ms`);
-console.log('-'.repeat(64));
-console.log(`concurrent batch wall-clock: ${batchMs}ms`);
-console.log(`per-call latency  min=${lat[0]}  p50=${p(0.5)}  p90=${p(0.9)}  max=${lat[lat.length - 1]}  (ms)`);
-console.log(`TIMEOUTS (>${TIMEOUT_MS}ms): ${timeouts} / ${N}`);
-console.log(`event-loop max stall: ${Math.round(maxGap)}ms   stalls>60ms: ${gaps.length}`);
-console.log(`  sum of stalls: ${gaps.reduce((a, b) => a + b, 0)}ms   biggest 5: ${gaps.sort((a,b)=>b-a).slice(0,5).join(', ')}`);
-console.log('-'.repeat(64));
-console.log('SERIALIZATION CHECK:');
-console.log(`  if serialized, batch ≈ N×single = ~${N * warmMs}ms;  actual=${batchMs}ms  (ratio ${(batchMs / (N * warmMs)).toFixed(2)})`);
-console.log(`  max latency / single = ${(lat[lat.length - 1] / warmMs).toFixed(1)}× (≈N means last call waited for all others)`);
-console.log('='.repeat(64));
-try { cg.close?.(); } catch {}

package/scripts/agent-eval/repro-daemon-clients.mjs

@@ -1,125 +0,0 @@
-#!/usr/bin/env node
-// Reproduction harness B — the FAITHFUL opencode scenario.
-//
-// Spawns N real `codegraph serve --mcp --path <repo>` processes (each becomes a
-// proxy that attaches to ONE shared daemon — exactly what opencode does with N
-// subagents), drives clean MCP JSON-RPC over each child's stdio, then fires ONE
-// concurrent wave of codegraph_explore tools/call across all N and measures
-// end-to-end latency + timeouts. This captures transport-flush starvation: a
-// daemon event-loop blocked in synchronous explore compute can neither read the
-// next request nor flush a finished response.
-//
-// Usage: node repro-daemon-clients.mjs <repo> <N=10> [perCallTimeoutMs=60000] [warm=1]
-import { spawn } from 'node:child_process';
-import { performance } from 'node:perf_hooks';
-import { resolve } from 'node:path';
-
-const [, , repoRaw, nRaw, timeoutRaw, warmRaw] = process.argv;
-const repo = resolve(repoRaw || '.');
-const N = Number(nRaw) || 10;
-const TIMEOUT_MS = Number(timeoutRaw) || 60000;
-const WARM = warmRaw === undefined ? true : warmRaw !== '0';
-const CLI = resolve('dist/bin/codegraph.js');
-
-const QUERIES = [
-  'how does the text model handle edits and undo',
-  'how does the file service watch for changes on disk',
-  'how does the keybinding service resolve a chord to a command',
-  'how does the extension host activate an extension',
-  'how does the editor render decorations in the viewport',
-  'how does the search service stream results to the UI',
-  'how does the terminal process manager spawn a shell',
-  'how does the configuration service merge user and workspace settings',
-  'how does the debug adapter forward breakpoints to the runtime',
-  'how does the quick input widget filter its items',
-  'how does the notification service queue and show toasts',
-  'how does the git extension compute the diff for a file',
-];
-
-function makeClient(id) {
-  const child = spawn('node', [CLI, 'serve', '--mcp', '--path', repo], {
-    env: { ...process.env, CODEGRAPH_TELEMETRY: '0', DO_NOT_TRACK: '1', CODEGRAPH_MCP_LOG_ATTACH: '0' },
-    stdio: ['pipe', 'pipe', 'inherit'],
-  });
-  let buf = '';
-  const waiters = new Map(); // id -> resolve
-  child.stdout.setEncoding('utf8');
-  child.stdout.on('data', (chunk) => {
-    buf += chunk;
-    let idx;
-    while ((idx = buf.indexOf('\n')) !== -1) {
-      const line = buf.slice(0, idx).trim();
-      buf = buf.slice(idx + 1);
-      if (!line) continue;
-      let msg; try { msg = JSON.parse(line); } catch { continue; }
-      if (msg.id !== undefined && waiters.has(msg.id)) {
-        waiters.get(msg.id)(msg);
-        waiters.delete(msg.id);
-      }
-    }
-  });
-  const send = (obj) => child.stdin.write(JSON.stringify(obj) + '\n');
-  const request = (method, params, rpcId, timeoutMs) =>
-    new Promise((res) => {
-      let timer;
-      if (timeoutMs) timer = setTimeout(() => { waiters.delete(rpcId); res({ __timeout: true }); }, timeoutMs);
-      waiters.set(rpcId, (m) => { if (timer) clearTimeout(timer); res(m); });
-      send({ jsonrpc: '2.0', id: rpcId, method, params });
-    });
-  return { id, child, send, request };
-}
-
-const sleep = (ms) => new Promise((r) => setTimeout(r, ms));
-
-const clients = Array.from({ length: N }, (_, i) => makeClient(i));
-
-// Initialize every client (handshake is answered locally by each proxy, instant).
-await Promise.all(clients.map((c) =>
-  c.request('initialize', { protocolVersion: '2024-11-05', capabilities: {}, clientInfo: { name: 'repro', version: '1' } }, `init-${c.id}`, 10000)
-    .then(() => c.send({ jsonrpc: '2.0', method: 'initialized' }))
-));
-
-// Warm the daemon: one explore through client 0 forces daemon spawn + project
-// open + catch-up gate to complete, so the concurrent wave measures the STEADY
-// state (the user's real scenario after the first call), not cold start.
-if (WARM) {
-  process.stderr.write('[repro] warming daemon (first explore triggers spawn+open+catchup)...\n');
-  const t0 = performance.now();
-  const r = await clients[0].request('tools/call', { name: 'codegraph_explore', arguments: { query: QUERIES[0] } }, 'warm-0', 120000);
-  process.stderr.write(`[repro] warm explore took ${Math.round(performance.now() - t0)}ms (timeout=${!!r.__timeout})\n`);
-  await sleep(500);
-}
-
-// THE WAVE: fire one explore on every client as simultaneously as possible.
-process.stderr.write(`[repro] firing ${N} concurrent explores...\n`);
-const waveStart = performance.now();
-const results = await Promise.all(clients.map((c, i) => {
-  const started = performance.now();
-  return c.request('tools/call', { name: 'codegraph_explore', arguments: { query: QUERIES[i % QUERIES.length] } }, `call-${c.id}`, TIMEOUT_MS)
-    .then((m) => ({
-      id: c.id,
-      ms: Math.round(performance.now() - started),
-      timedOut: !!m.__timeout,
-      ok: !!m.result && !m.result.isError,
-      chars: m.result?.content?.[0]?.text?.length ?? 0,
-    }));
-}));
-const waveMs = Math.round(performance.now() - waveStart);
-
-const lat = results.map((r) => r.ms).sort((a, b) => a - b);
-const timeouts = results.filter((r) => r.timedOut).length;
-const p = (q) => lat[Math.min(lat.length - 1, Math.floor(q * lat.length))];
-
-console.log('='.repeat(64));
-console.log(`HARNESS B (real daemon + ${N} proxies)   repo=${repo}`);
-console.log(`warm=${WARM}  perCallTimeout=${TIMEOUT_MS}ms`);
-console.log('-'.repeat(64));
-console.log(`wave wall-clock: ${waveMs}ms`);
-console.log(`per-call latency  min=${lat[0]}  p50=${p(0.5)}  p90=${p(0.9)}  max=${lat[lat.length - 1]}  (ms)`);
-console.log(`TIMEOUTS (>${TIMEOUT_MS}ms): ${timeouts} / ${N}`);
-console.log(`completion order (id:ms): ${results.slice().sort((a,b)=>a.ms-b.ms).map(r=>`${r.id}:${r.ms}`).join('  ')}`);
-console.log('='.repeat(64));
-
-for (const c of clients) { try { c.child.stdin.end(); c.child.kill('SIGTERM'); } catch {} }
-await sleep(300);
-process.exit(0);

package/scripts/agent-eval/run-agent.sh

@@ -1,34 +0,0 @@
-#!/usr/bin/env bash
-# Headless Claude Code run against a repo with homegraph MCP, capturing the
-# full stream-json so we can see tool calls + token usage. Complements the
-# interactive itrun.sh: headless gives a clean per-tool breakdown + exact
-# tokens/cost, but defaults to the general-purpose subagent (not Explore).
-# To force the Explore path, ask for it in the prompt.
-#
-# Usage: run-agent.sh <repo-path> <label> "<prompt>"
-# Env: AGENT_EVAL_OUT (default /tmp/agent-eval), CG_BIN (homegraph dist binary)
-set -uo pipefail
-
-REPO="$1"; LABEL="$2"; PROMPT="$3"
-CG_BIN="${CG_BIN:-$(command -v homegraph || echo /usr/local/bin/homegraph)}"
-OUT_DIR="${AGENT_EVAL_OUT:-/tmp/agent-eval}"; mkdir -p "$OUT_DIR"
-OUT="$OUT_DIR/run-${LABEL}.jsonl"
-
-MCP_CONFIG=$(cat <<JSON
-{"mcpServers":{"homegraph":{"command":"${CG_BIN}","args":["serve","--mcp","--path","${REPO}"]}}}
-JSON
-)
-
-echo "→ running [$LABEL] in $REPO"
-cd "$REPO" || exit 1
-
-claude -p "$PROMPT" \
-  --output-format stream-json --verbose \
-  --permission-mode bypassPermissions \
-  --model "${MODEL:-sonnet}" --effort "${EFFORT:-high}" \
-  --max-budget-usd 2 \
-  --strict-mcp-config --mcp-config "$MCP_CONFIG" \
-  > "$OUT" 2>"$OUT_DIR/run-${LABEL}.err"
-
-echo "exit: $? | wrote $OUT ($(wc -l < "$OUT") lines)"
-node "$(cd "$(dirname "$0")" && pwd)/parse-run.mjs" "$OUT" 2>/dev/null || true

package/scripts/agent-eval/run-all.sh

@@ -1,75 +0,0 @@
-#!/usr/bin/env bash
-# With/without A/B (and optional interactive) eval for a homegraph version on a
-# repo. Codegraph is the ONLY variable: both arms launch claude with
-# --strict-mcp-config — with = homegraph-only MCP (pointed at $CG_BIN),
-# without = empty MCP. Built-in Read/Grep/Bash stay available in both arms.
-#
-# Usage: run-all.sh <repo-path> "<question>" [headless|tmux|all]
-# Env:   CG_BIN          homegraph binary (default: command -v homegraph)
-#        AGENT_EVAL_OUT  output dir (default: /tmp/agent-eval)
-#        MODEL / EFFORT  claude model/effort (default: sonnet / high — the
-#                        standing A/B policy; see CLAUDE.md, don't raise)
-set -uo pipefail
-
-REPO="${1:?usage: run-all.sh <repo-path> \"<question>\" [headless|tmux|all]}"
-Q="${2:?question required}"
-MODE="${3:-headless}"
-CG_BIN="${CG_BIN:-$(command -v homegraph)}"
-OUT="${AGENT_EVAL_OUT:-/tmp/agent-eval}"
-HARNESS="$(cd "$(dirname "$0")" && pwd)"
-mkdir -p "$OUT"
-
-# Neutralize any ambient HomeGraph prompt-hook (~/.claude) in BOTH arms:
-# the hook injects homegraph context into every prompt, which contaminates
-# the without-arm (free structural context) and double-counts the with-arm.
-# The A/B's only variable must be the MCP server wired below.
-export HOMEGRAPH_NO_PROMPT_HOOK=1
-
-[ -n "$CG_BIN" ] || { echo "no homegraph binary on PATH (set CG_BIN)"; exit 1; }
-[ -d "$REPO/.homegraph" ] || { echo "no .homegraph index at $REPO — index it first"; exit 1; }
-case "$MODE" in headless|tmux|all) ;; *) echo "mode must be headless|tmux|all (got '$MODE')"; exit 1;; esac
-
-# MCP config files (path form avoids inline-JSON quoting through tmux).
-cat > "$OUT/mcp-homegraph.json" <<JSON
-{"mcpServers":{"homegraph":{"command":"$CG_BIN","args":["serve","--mcp","--path","$REPO"]}}}
-JSON
-echo '{"mcpServers":{}}' > "$OUT/mcp-empty.json"
-
-echo "###### homegraph: $CG_BIN"
-echo "###### repo:      $REPO"
-echo "###### question:  $Q"
-echo
-
-# Headless arm: claude -p with stream-json -> exact tool sequence + tokens/cost.
-headless() {
-  local label="$1" cfg="$2"
-  echo "############################## HEADLESS [$label] ##############################"
-  ( cd "$REPO" && claude -p "$Q" \
-      --output-format stream-json --verbose \
-      --permission-mode bypassPermissions \
-      --model "${MODEL:-sonnet}" --effort "${EFFORT:-high}" \
-      --max-budget-usd 4 \
-      --strict-mcp-config --mcp-config "$cfg" \
-      > "$OUT/run-$label.jsonl" 2>"$OUT/run-$label.err" )
-  echo "exit $? -> $OUT/run-$label.jsonl ($(wc -l < "$OUT/run-$label.jsonl" | tr -d ' ') lines)"
-  tail -2 "$OUT/run-$label.err" 2>/dev/null
-  node "$HARNESS/parse-run.mjs" "$OUT/run-$label.jsonl" 2>&1 || true
-  echo
-}
-
-if [ "$MODE" = headless ] || [ "$MODE" = all ]; then
-  headless "headless-with"    "$OUT/mcp-homegraph.json"
-  headless "headless-without" "$OUT/mcp-empty.json"
-fi
-
-if [ "$MODE" = tmux ] || [ "$MODE" = all ]; then
-  echo "############################## INTERACTIVE [with] ##############################"
-  CLAUDE_EXTRA_ARGS="--model ${MODEL:-sonnet} --effort ${EFFORT:-high} --strict-mcp-config --mcp-config $OUT/mcp-homegraph.json" \
-    bash "$HARNESS/itrun.sh" "$REPO" "int-with" "$Q" 2>&1 || echo "[itrun WITH failed]"
-  echo
-  echo "############################## INTERACTIVE [without] ##############################"
-  CLAUDE_EXTRA_ARGS="--model ${MODEL:-sonnet} --effort ${EFFORT:-high} --strict-mcp-config --mcp-config $OUT/mcp-empty.json" \
-    bash "$HARNESS/itrun.sh" "$REPO" "int-without" "$Q" 2>&1 || echo "[itrun WITHOUT failed]"
-  echo
-fi
-echo "############################## RUN-ALL COMPLETE ##############################"

package/scripts/agent-eval/run-arms.sh

@@ -1,56 +0,0 @@
-#!/usr/bin/env bash
-# Tool-surface ablation — run ONE repo+question under ONE arm.
-#
-# Arms vary (exposed homegraph tools, trace-first steering). Tools are trimmed
-# SERVER-SIDE via HOMEGRAPH_MCP_TOOLS in the MCP config's `env` block, so an
-# ablated tool is genuinely absent from ListTools — no deferred-ToolSearch or
-# denied-call confound (which --disallowedTools would introduce). Steering is
-# injected with --append-system-prompt, so no rebuild of the shipped
-# server-instructions is needed to A/B it.
-#
-#   A control       all tools            no steering
-#   B steer         all tools            trace-first
-#   C no-explore    hide explore         trace-first
-#   D trace-centric hide explore+context trace-first
-#   E control-probe hide explore+context trace-first  (caller passes a NON-flow Q)
-#
-# Usage: run-arms.sh <repo-path> "<question>" <A|B|C|D|E> [run-id]
-set -uo pipefail
-REPO="${1:?repo path}"; Q="${2:?question}"; ARM="${3:?arm A-E}"; RID="${4:-1}"
-CG_BIN="${CG_BIN:-$(command -v homegraph)}"
-OUT="${ARMS_OUT:-/tmp/arms}/$(basename "$REPO")"
-mkdir -p "$OUT"
-[ -n "$CG_BIN" ] || { echo "no homegraph binary (set CG_BIN)"; exit 1; }
-[ -d "$REPO/.homegraph" ] || { echo "no .homegraph index at $REPO"; exit 1; }
-
-STEER='Flow questions ("how does X reach/become Y", "trace the flow", request to handler, state to render): call homegraph_trace(from,to) FIRST — one call returns the whole path. Use homegraph_context/search only to locate the two endpoint symbols if you do not know them. Do NOT reconstruct the path with repeated search/callers/explore.'
-KEEP_NO_EXPLORE="trace,search,node,context,callers,callees,impact,files,status"
-KEEP_TRACE_CENTRIC="trace,search,node,callers,callees,impact,files,status"
-
-case "$ARM" in
-  A|G|H|I) TOOLS="";            STEERING="" ;;  # no steering; H = body-trace, I = body-trace + destination callees (sufficiency)
-  B|F) TOOLS="";                STEERING="$STEER" ;;  # F = B's surface, run on the body-inlining trace build
-  C) TOOLS="$KEEP_NO_EXPLORE";  STEERING="$STEER" ;;
-  D|E) TOOLS="$KEEP_TRACE_CENTRIC"; STEERING="$STEER" ;;
-  *) echo "bad arm '$ARM' (want A|B|C|D|E)"; exit 1 ;;
-esac
-
-CFG="$OUT/mcp-$ARM.json"
-if [ -n "$TOOLS" ]; then
-  cat > "$CFG" <<JSON
-{"mcpServers":{"homegraph":{"command":"$CG_BIN","args":["serve","--mcp","--path","$REPO"],"env":{"HOMEGRAPH_MCP_TOOLS":"$TOOLS"}}}}
-JSON
-else
-  cat > "$CFG" <<JSON
-{"mcpServers":{"homegraph":{"command":"$CG_BIN","args":["serve","--mcp","--path","$REPO"]}}}
-JSON
-fi
-
-LOG="$OUT/$ARM-r$RID.jsonl"; ERR="$OUT/$ARM-r$RID.err"
-ARGS=( -p "$Q" --output-format stream-json --verbose
-       --permission-mode bypassPermissions --model "${MODEL:-sonnet}" --effort "${EFFORT:-high}" --max-budget-usd 4
-       --strict-mcp-config --mcp-config "$CFG" )
-[ -n "$STEERING" ] && ARGS+=( --append-system-prompt "$STEERING" )
-
-( cd "$REPO" && claude "${ARGS[@]}" > "$LOG" 2>"$ERR" )
-echo "[$(basename "$REPO") $ARM r$RID] exit $? -> $LOG ($(wc -l < "$LOG" | tr -d ' ') lines)"