homegraph 1.1.2 → 1.2.0

package/scripts/add-lang/dump-ast.mjs

@@ -1,103 +1,103 @@
-#!/usr/bin/env node
-// Dump the tree-sitter AST for a sample file so you can write a LanguageExtractor
-// mapping. Loads a grammar .wasm directly via web-tree-sitter (the same runtime
-// homegraph uses) — you do NOT need to register the language first.
-//
-// Usage:
-//   node scripts/add-lang/dump-ast.mjs <lang|wasm-path> <sample-file> [--depth=N] [--full]
-// Examples:
-//   node scripts/add-lang/dump-ast.mjs lua sample.lua
-//   node scripts/add-lang/dump-ast.mjs src/extraction/wasm/tree-sitter-zig.wasm a.zig --depth=4
-//
-// Output: an indented AST (named nodes, with field names) followed by a
-// node-type FREQUENCY table. The frequency table is the payoff — it tells you
-// which node types to map to functionTypes / classTypes / importTypes / etc.
-
-import { readFileSync, existsSync } from 'node:fs';
-import { createRequire } from 'node:module';
-import { Parser, Language } from 'web-tree-sitter';
-
-const require = createRequire(import.meta.url);
-const fail = (msg) => { console.error(`[dump-ast] ${msg}`); process.exit(1); };
-
-const argv = process.argv.slice(2);
-const positional = argv.filter((a) => !a.startsWith('--'));
-const [langOrWasm, sampleFile] = positional;
-const depthFlag = argv.find((a) => a.startsWith('--depth='));
-const showAll = argv.includes('--full'); // also print anonymous (token) nodes
-const maxDepth = depthFlag ? parseInt(depthFlag.split('=')[1], 10) : (showAll ? Infinity : 8);
-
-if (!langOrWasm || !sampleFile) {
-  fail('usage: dump-ast.mjs <lang|wasm-path> <sample-file> [--depth=N] [--full]');
-}
-if (!existsSync(sampleFile)) fail(`sample file not found: ${sampleFile}`);
-
-// Language tokens whose tree-sitter-wasms filename differs from the token.
-const WASM_SPECIAL = { csharp: 'c_sharp', 'c#': 'c_sharp' };
-
-function resolveWasm(token) {
-  if (token.endsWith('.wasm')) {
-    if (!existsSync(token)) fail(`wasm not found: ${token}`);
-    return token;
-  }
-  const base = WASM_SPECIAL[token.toLowerCase()] ?? token.toLowerCase();
-  try {
-    return require.resolve(`tree-sitter-wasms/out/tree-sitter-${base}.wasm`);
-  } catch {
-    /* not in tree-sitter-wasms — try a vendored copy */
-  }
-  const vendored = `src/extraction/wasm/tree-sitter-${base}.wasm`;
-  if (existsSync(vendored)) return vendored;
-  fail(
-    `no grammar for "${token}" — not in tree-sitter-wasms and not vendored at ` +
-      `${vendored}. Pass an explicit .wasm path, or vendor one (see SKILL.md "Find a grammar").`
-  );
-}
-
-const wasmPath = resolveWasm(langOrWasm);
-const source = readFileSync(sampleFile, 'utf8');
-
-try {
-  await Parser.init();
-} catch {
-  await Parser.init({ locateFile: () => require.resolve('web-tree-sitter/tree-sitter.wasm') });
-}
-
-let language;
-try {
-  language = await Language.load(wasmPath);
-} catch (e) {
-  fail(`failed to load grammar ${wasmPath}: ${e.message}`);
-}
-
-const parser = new Parser();
-parser.setLanguage(language);
-const tree = parser.parse(source);
-
-const freq = new Map();
-const snippet = (node) => {
-  const t = node.text.replace(/\s+/g, ' ').trim();
-  return t.length > 48 ? `${t.slice(0, 48)}…` : t;
-};
-
-function walk(node, depth, fieldName) {
-  if (node.isNamed) freq.set(node.type, (freq.get(node.type) || 0) + 1);
-  if ((node.isNamed || showAll) && depth <= maxDepth) {
-    const field = fieldName ? `${fieldName}: ` : '';
-    const leaf = node.childCount === 0 ? `  "${snippet(node)}"` : '';
-    console.log(`${'  '.repeat(depth)}${field}${node.type}  @${node.startPosition.row + 1}:${node.startPosition.column}${leaf}`);
-  }
-  for (let i = 0; i < node.childCount; i++) {
-    const child = node.child(i);
-    if (child) walk(child, depth + 1, node.fieldNameForChild(i));
-  }
-}
-
-console.log(`\n# AST for ${sampleFile}  (grammar: ${wasmPath.split('/').pop()})\n`);
-walk(tree.rootNode, 0, null);
-
-console.log('\n# Node-type frequency (named nodes) — map the relevant ones in your extractor:\n');
-[...freq.entries()]
-  .sort((a, b) => b[1] - a[1])
-  .forEach(([type, n]) => console.log(`  ${String(n).padStart(5)}  ${type}`));
-console.log();
+#!/usr/bin/env node
+// Dump the tree-sitter AST for a sample file so you can write a LanguageExtractor
+// mapping. Loads a grammar .wasm directly via web-tree-sitter (the same runtime
+// homegraph uses) — you do NOT need to register the language first.
+//
+// Usage:
+//   node scripts/add-lang/dump-ast.mjs <lang|wasm-path> <sample-file> [--depth=N] [--full]
+// Examples:
+//   node scripts/add-lang/dump-ast.mjs lua sample.lua
+//   node scripts/add-lang/dump-ast.mjs src/extraction/wasm/tree-sitter-zig.wasm a.zig --depth=4
+//
+// Output: an indented AST (named nodes, with field names) followed by a
+// node-type FREQUENCY table. The frequency table is the payoff — it tells you
+// which node types to map to functionTypes / classTypes / importTypes / etc.
+
+import { readFileSync, existsSync } from 'node:fs';
+import { createRequire } from 'node:module';
+import { Parser, Language } from 'web-tree-sitter';
+
+const require = createRequire(import.meta.url);
+const fail = (msg) => { console.error(`[dump-ast] ${msg}`); process.exit(1); };
+
+const argv = process.argv.slice(2);
+const positional = argv.filter((a) => !a.startsWith('--'));
+const [langOrWasm, sampleFile] = positional;
+const depthFlag = argv.find((a) => a.startsWith('--depth='));
+const showAll = argv.includes('--full'); // also print anonymous (token) nodes
+const maxDepth = depthFlag ? parseInt(depthFlag.split('=')[1], 10) : (showAll ? Infinity : 8);
+
+if (!langOrWasm || !sampleFile) {
+  fail('usage: dump-ast.mjs <lang|wasm-path> <sample-file> [--depth=N] [--full]');
+}
+if (!existsSync(sampleFile)) fail(`sample file not found: ${sampleFile}`);
+
+// Language tokens whose tree-sitter-wasms filename differs from the token.
+const WASM_SPECIAL = { csharp: 'c_sharp', 'c#': 'c_sharp' };
+
+function resolveWasm(token) {
+  if (token.endsWith('.wasm')) {
+    if (!existsSync(token)) fail(`wasm not found: ${token}`);
+    return token;
+  }
+  const base = WASM_SPECIAL[token.toLowerCase()] ?? token.toLowerCase();
+  try {
+    return require.resolve(`tree-sitter-wasms/out/tree-sitter-${base}.wasm`);
+  } catch {
+    /* not in tree-sitter-wasms — try a vendored copy */
+  }
+  const vendored = `src/extraction/wasm/tree-sitter-${base}.wasm`;
+  if (existsSync(vendored)) return vendored;
+  fail(
+    `no grammar for "${token}" — not in tree-sitter-wasms and not vendored at ` +
+      `${vendored}. Pass an explicit .wasm path, or vendor one (see SKILL.md "Find a grammar").`
+  );
+}
+
+const wasmPath = resolveWasm(langOrWasm);
+const source = readFileSync(sampleFile, 'utf8');
+
+try {
+  await Parser.init();
+} catch {
+  await Parser.init({ locateFile: () => require.resolve('web-tree-sitter/tree-sitter.wasm') });
+}
+
+let language;
+try {
+  language = await Language.load(wasmPath);
+} catch (e) {
+  fail(`failed to load grammar ${wasmPath}: ${e.message}`);
+}
+
+const parser = new Parser();
+parser.setLanguage(language);
+const tree = parser.parse(source);
+
+const freq = new Map();
+const snippet = (node) => {
+  const t = node.text.replace(/\s+/g, ' ').trim();
+  return t.length > 48 ? `${t.slice(0, 48)}…` : t;
+};
+
+function walk(node, depth, fieldName) {
+  if (node.isNamed) freq.set(node.type, (freq.get(node.type) || 0) + 1);
+  if ((node.isNamed || showAll) && depth <= maxDepth) {
+    const field = fieldName ? `${fieldName}: ` : '';
+    const leaf = node.childCount === 0 ? `  "${snippet(node)}"` : '';
+    console.log(`${'  '.repeat(depth)}${field}${node.type}  @${node.startPosition.row + 1}:${node.startPosition.column}${leaf}`);
+  }
+  for (let i = 0; i < node.childCount; i++) {
+    const child = node.child(i);
+    if (child) walk(child, depth + 1, node.fieldNameForChild(i));
+  }
+}
+
+console.log(`\n# AST for ${sampleFile}  (grammar: ${wasmPath.split('/').pop()})\n`);
+walk(tree.rootNode, 0, null);
+
+console.log('\n# Node-type frequency (named nodes) — map the relevant ones in your extractor:\n');
+[...freq.entries()]
+  .sort((a, b) => b[1] - a[1])
+  .forEach(([type, n]) => console.log(`  ${String(n).padStart(5)}  ${type}`));
+console.log();

package/scripts/add-lang/verify-extraction.mjs

@@ -1,70 +1,70 @@
-#!/usr/bin/env node
-// Sanity-check that homegraph extracted REAL symbols (not just file/import nodes)
-// from a repo for a given language. Exits non-zero on a critical failure so it
-// can drive a write-extractor -> build -> re-check loop.
-//
-// Usage: node scripts/add-lang/verify-extraction.mjs <repo-path> <lang>
-// Reads `homegraph status <repo> --json` using whatever homegraph is on PATH,
-// so it reflects the binary that built the index.
-//
-// Exit codes: 0 = pass or soft-warn, 1 = critical fail, 2 = could not run.
-
-import { execFileSync } from 'node:child_process';
-
-const [repo, lang] = process.argv.slice(2);
-if (!repo || !lang) {
-  console.error('usage: verify-extraction.mjs <repo-path> <lang>');
-  process.exit(2);
-}
-
-let status;
-try {
-  const out = execFileSync('homegraph', ['status', repo, '--json'], { encoding: 'utf8' });
-  status = JSON.parse(out);
-} catch (e) {
-  console.error(`[verify] could not read homegraph status for ${repo}: ${e.message}`);
-  process.exit(2);
-}
-
-// Kinds that prove the extractor mapped AST node types (everything except
-// 'file' and 'import', which homegraph creates structurally for any language).
-const SYMBOL_KINDS = new Set([
-  'module', 'class', 'struct', 'interface', 'trait', 'protocol', 'function',
-  'method', 'property', 'field', 'variable', 'constant', 'enum', 'enum_member',
-  'type_alias', 'namespace', 'route', 'component',
-]);
-
-const byKind = status.nodesByKind || {};
-const langs = status.languages || [];
-const files = status.fileCount || 0;
-const edges = status.edgeCount || 0;
-const symbolKinds = Object.keys(byKind).filter((k) => SYMBOL_KINDS.has(k));
-const symbolCount = symbolKinds.reduce((s, k) => s + byKind[k], 0);
-
-const checks = [];
-const add = (severity, ok, label, detail) => checks.push({ severity, ok, label, detail });
-
-add('critical', status.initialized === true, 'index initialized', `initialized=${status.initialized}`);
-add('critical', langs.includes(lang), `language "${lang}" detected`, `languages=[${langs.join(', ')}]`);
-add('critical', symbolCount > 0, 'structural symbols extracted', `${symbolCount} symbols (${symbolKinds.join(', ') || 'NONE — only file/import nodes!'})`);
-add('soft', symbolCount >= files, 'symbol density >= 1/file', `${symbolCount} symbols across ${files} files`);
-add('soft', edges > files, 'edges resolved', `${edges} edges across ${files} files`);
-
-console.log(`\n# Extraction check — ${repo}  (lang=${lang}, backend=${status.backend})`);
-console.log(`  files=${files} nodes=${status.nodeCount} edges=${edges}`);
-console.log(`  nodesByKind: ${JSON.stringify(byKind)}\n`);
-for (const c of checks) console.log(`  ${c.ok ? '✓' : '✗'} ${c.label} — ${c.detail}`);
-
-const critical = checks.filter((c) => !c.ok && c.severity === 'critical');
-const soft = checks.filter((c) => !c.ok && c.severity === 'soft');
-console.log();
-if (critical.length) {
-  console.log(`RESULT: FAIL (${critical.length} critical) — extractor or grammar wiring is broken. Re-run dump-ast.mjs and fix the node-type mappings.`);
-  process.exit(1);
-}
-if (soft.length) {
-  console.log(`RESULT: WARN (${soft.length} soft) — extraction works but looks thin; inspect the counts above.`);
-  process.exit(0);
-}
-console.log('RESULT: PASS — extraction looks healthy.');
-process.exit(0);
+#!/usr/bin/env node
+// Sanity-check that homegraph extracted REAL symbols (not just file/import nodes)
+// from a repo for a given language. Exits non-zero on a critical failure so it
+// can drive a write-extractor -> build -> re-check loop.
+//
+// Usage: node scripts/add-lang/verify-extraction.mjs <repo-path> <lang>
+// Reads `homegraph status <repo> --json` using whatever homegraph is on PATH,
+// so it reflects the binary that built the index.
+//
+// Exit codes: 0 = pass or soft-warn, 1 = critical fail, 2 = could not run.
+
+import { execFileSync } from 'node:child_process';
+
+const [repo, lang] = process.argv.slice(2);
+if (!repo || !lang) {
+  console.error('usage: verify-extraction.mjs <repo-path> <lang>');
+  process.exit(2);
+}
+
+let status;
+try {
+  const out = execFileSync('homegraph', ['status', repo, '--json'], { encoding: 'utf8' });
+  status = JSON.parse(out);
+} catch (e) {
+  console.error(`[verify] could not read homegraph status for ${repo}: ${e.message}`);
+  process.exit(2);
+}
+
+// Kinds that prove the extractor mapped AST node types (everything except
+// 'file' and 'import', which homegraph creates structurally for any language).
+const SYMBOL_KINDS = new Set([
+  'module', 'class', 'struct', 'interface', 'trait', 'protocol', 'function',
+  'method', 'property', 'field', 'variable', 'constant', 'enum', 'enum_member',
+  'type_alias', 'namespace', 'route', 'component',
+]);
+
+const byKind = status.nodesByKind || {};
+const langs = status.languages || [];
+const files = status.fileCount || 0;
+const edges = status.edgeCount || 0;
+const symbolKinds = Object.keys(byKind).filter((k) => SYMBOL_KINDS.has(k));
+const symbolCount = symbolKinds.reduce((s, k) => s + byKind[k], 0);
+
+const checks = [];
+const add = (severity, ok, label, detail) => checks.push({ severity, ok, label, detail });
+
+add('critical', status.initialized === true, 'index initialized', `initialized=${status.initialized}`);
+add('critical', langs.includes(lang), `language "${lang}" detected`, `languages=[${langs.join(', ')}]`);
+add('critical', symbolCount > 0, 'structural symbols extracted', `${symbolCount} symbols (${symbolKinds.join(', ') || 'NONE — only file/import nodes!'})`);
+add('soft', symbolCount >= files, 'symbol density >= 1/file', `${symbolCount} symbols across ${files} files`);
+add('soft', edges > files, 'edges resolved', `${edges} edges across ${files} files`);
+
+console.log(`\n# Extraction check — ${repo}  (lang=${lang}, backend=${status.backend})`);
+console.log(`  files=${files} nodes=${status.nodeCount} edges=${edges}`);
+console.log(`  nodesByKind: ${JSON.stringify(byKind)}\n`);
+for (const c of checks) console.log(`  ${c.ok ? '✓' : '✗'} ${c.label} — ${c.detail}`);
+
+const critical = checks.filter((c) => !c.ok && c.severity === 'critical');
+const soft = checks.filter((c) => !c.ok && c.severity === 'soft');
+console.log();
+if (critical.length) {
+  console.log(`RESULT: FAIL (${critical.length} critical) — extractor or grammar wiring is broken. Re-run dump-ast.mjs and fix the node-type mappings.`);
+  process.exit(1);
+}
+if (soft.length) {
+  console.log(`RESULT: WARN (${soft.length} soft) — extraction works but looks thin; inspect the counts above.`);
+  process.exit(0);
+}
+console.log('RESULT: PASS — extraction looks healthy.');
+process.exit(0);

package/scripts/agent-eval/ab-adoption.sh

@@ -1,91 +1,91 @@
-#!/usr/bin/env bash
-# Does the agent PICK homegraph_node to read a file, vs the built-in Read tool?
-# Build A/B: NEW build (HEAD, homegraph_node has Read parity) vs BASELINE build
-# (a ref where it doesn't), BOTH homegraph-attached + pre-warmed, same task. The
-# metric is tool CHOICE: Read calls vs homegraph_node[file] calls per run.
-#
-# Usage: ab-adoption.sh <indexed-repo> "<task>" [runs-per-arm] [baseline-ref]
-# Env: AGENT_EVAL_OUT (default: /tmp/ab-adoption)
-set -uo pipefail
-TARGET="${1:?usage: ab-adoption.sh <indexed-repo> \"<task>\" [runs] [baseline-ref]}"
-TASK="${2:?task required}"
-RUNS="${3:-2}"
-BASE_REF="${4:-HEAD~1}"
-ENGINE="$(cd "$(dirname "$0")/../.." && pwd)"
-BIN="$ENGINE/dist/bin/homegraph.js"
-OUT="${AGENT_EVAL_OUT:-/tmp/ab-adoption}"
-
-command -v claude >/dev/null || { echo "claude CLI not on PATH"; exit 1; }
-[ -d "$TARGET/.homegraph" ] || { echo "target not indexed: run 'homegraph init $TARGET' first"; exit 1; }
-git -C "$ENGINE" diff --quiet && git -C "$ENGINE" diff --cached --quiet || { echo "engine has uncommitted changes — commit/stash first"; exit 1; }
-CHANGED=$(git -C "$ENGINE" diff --name-only "$BASE_REF" HEAD -- src 2>/dev/null)
-[ -n "$CHANGED" ] || { echo "no src/ changes between $BASE_REF and HEAD"; exit 1; }
-
-cleanup() {
-  pkill -9 -f "serve --mcp --path $OUT/" 2>/dev/null
-  git -C "$ENGINE" checkout HEAD -- $CHANGED 2>/dev/null
-  ( cd "$ENGINE" && npm run build >/dev/null 2>&1 )
-}
-trap cleanup EXIT
-mkdir -p "$OUT"
-echo "###### target=$TARGET  runs/arm=$RUNS  baseline=$BASE_REF"
-echo "###### changed: $(echo "$CHANGED" | tr '\n' ' ')"
-echo "###### task=$TASK"; echo
-
-prewarm() {
-  pkill -9 -f "serve --mcp --path $1" 2>/dev/null
-  HOMEGRAPH_DAEMON_IDLE_TIMEOUT_MS=1800000 node "$BIN" serve --mcp --path "$1" </dev/null >/dev/null 2>&1 &
-  node -e 'const fs=require("fs");let n=0;const t=setInterval(()=>{if(fs.existsSync(process.argv[1]+"/.homegraph/daemon.sock")){clearInterval(t);process.exit(0)}if(n++>150){clearInterval(t);process.exit(1)}},100)' "$1" >/dev/null 2>&1
-}
-
-# Per-run tool-choice counts: Read vs homegraph_node[file] vs [symbol].
-count() {
-  node -e '
-    const fs=require("fs");
-    const lines=fs.readFileSync(process.argv[1],"utf8").split("\n").filter(Boolean);
-    let read=0,cgFile=0,cgSym=0,cgOther=0,exposed="?";
-    for(const l of lines){try{const o=JSON.parse(l);
-      if(o.type==="system"&&o.subtype==="init"){exposed=(o.tools||[]).filter(t=>/homegraph/.test(t)).length;}
-      const blocks=o.message?.content||[];
-      for(const b of (Array.isArray(blocks)?blocks:[])){
-        if(b.type!=="tool_use")continue;
-        if(b.name==="Read")read++;
-        else if(b.name==="mcp__homegraph__homegraph_node"){ if(b.input&&b.input.symbol)cgSym++; else cgFile++; }
-        else if(/mcp__homegraph__/.test(b.name))cgOther++;
-      }
-    }catch{}}
-    console.log(`    Read=${read}  homegraph_node[file]=${cgFile}  homegraph_node[symbol]=${cgSym}  other_cg=${cgOther}  (cg exposed=${exposed})`);
-  ' "$1"
-}
-
-run_arm() { # label, N
-  local label="$1" n="$2"
-  local c="$OUT/mcp-$label.json"
-  for i in $(seq 1 "$n"); do
-    local tgt="$OUT/t-$label-$i"
-    rm -rf "$tgt"
-    rsync -a --exclude node_modules --exclude .git --exclude dist --exclude .homegraph "$TARGET/" "$tgt/"
-    node "$BIN" init "$tgt" >/dev/null 2>&1
-    printf '{"mcpServers":{"homegraph":{"command":"env","args":["HOMEGRAPH_WASM_RELAUNCHED=1","node","%s","serve","--mcp","--path","%s"]}}}' "$BIN" "$tgt" > "$c"
-    prewarm "$tgt"
-    echo "----- [$label] run $i -----"
-    ( cd "$tgt" && claude -p "$TASK" \
-        --output-format stream-json --verbose --permission-mode bypassPermissions \
-        --model "${MODEL:-sonnet}" --effort "${EFFORT:-high}" --max-budget-usd 4 --strict-mcp-config --mcp-config "$c" \
-        </dev/null > "$OUT/run-$label-$i.jsonl" 2>"$OUT/run-$label-$i.err" )
-    count "$OUT/run-$label-$i.jsonl"
-    pkill -9 -f "serve --mcp --path $tgt" 2>/dev/null
-  done
-  echo
-}
-
-echo "== NEW build (HEAD: homegraph_node has Read parity) =="
-( cd "$ENGINE" && npm run build >/dev/null 2>&1 ) && echo "built"
-run_arm new "$RUNS"
-
-echo "== BASELINE build ($BASE_REF) =="
-git -C "$ENGINE" checkout "$BASE_REF" -- $CHANGED
-( cd "$ENGINE" && npm run build >/dev/null 2>&1 ) && echo "built"
-run_arm baseline "$RUNS"
-
-echo "###### DONE — compare [new] vs [baseline]: does homegraph_node[file] rise / Read fall? Logs: $OUT"
+#!/usr/bin/env bash
+# Does the agent PICK homegraph_node to read a file, vs the built-in Read tool?
+# Build A/B: NEW build (HEAD, homegraph_node has Read parity) vs BASELINE build
+# (a ref where it doesn't), BOTH homegraph-attached + pre-warmed, same task. The
+# metric is tool CHOICE: Read calls vs homegraph_node[file] calls per run.
+#
+# Usage: ab-adoption.sh <indexed-repo> "<task>" [runs-per-arm] [baseline-ref]
+# Env: AGENT_EVAL_OUT (default: /tmp/ab-adoption)
+set -uo pipefail
+TARGET="${1:?usage: ab-adoption.sh <indexed-repo> \"<task>\" [runs] [baseline-ref]}"
+TASK="${2:?task required}"
+RUNS="${3:-2}"
+BASE_REF="${4:-HEAD~1}"
+ENGINE="$(cd "$(dirname "$0")/../.." && pwd)"
+BIN="$ENGINE/dist/bin/homegraph.js"
+OUT="${AGENT_EVAL_OUT:-/tmp/ab-adoption}"
+
+command -v claude >/dev/null || { echo "claude CLI not on PATH"; exit 1; }
+[ -d "$TARGET/.homegraph" ] || { echo "target not indexed: run 'homegraph init $TARGET' first"; exit 1; }
+git -C "$ENGINE" diff --quiet && git -C "$ENGINE" diff --cached --quiet || { echo "engine has uncommitted changes — commit/stash first"; exit 1; }
+CHANGED=$(git -C "$ENGINE" diff --name-only "$BASE_REF" HEAD -- src 2>/dev/null)
+[ -n "$CHANGED" ] || { echo "no src/ changes between $BASE_REF and HEAD"; exit 1; }
+
+cleanup() {
+  pkill -9 -f "serve --mcp --path $OUT/" 2>/dev/null
+  git -C "$ENGINE" checkout HEAD -- $CHANGED 2>/dev/null
+  ( cd "$ENGINE" && npm run build >/dev/null 2>&1 )
+}
+trap cleanup EXIT
+mkdir -p "$OUT"
+echo "###### target=$TARGET  runs/arm=$RUNS  baseline=$BASE_REF"
+echo "###### changed: $(echo "$CHANGED" | tr '\n' ' ')"
+echo "###### task=$TASK"; echo
+
+prewarm() {
+  pkill -9 -f "serve --mcp --path $1" 2>/dev/null
+  HOMEGRAPH_DAEMON_IDLE_TIMEOUT_MS=1800000 node "$BIN" serve --mcp --path "$1" </dev/null >/dev/null 2>&1 &
+  node -e 'const fs=require("fs");let n=0;const t=setInterval(()=>{if(fs.existsSync(process.argv[1]+"/.homegraph/daemon.sock")){clearInterval(t);process.exit(0)}if(n++>150){clearInterval(t);process.exit(1)}},100)' "$1" >/dev/null 2>&1
+}
+
+# Per-run tool-choice counts: Read vs homegraph_node[file] vs [symbol].
+count() {
+  node -e '
+    const fs=require("fs");
+    const lines=fs.readFileSync(process.argv[1],"utf8").split("\n").filter(Boolean);
+    let read=0,cgFile=0,cgSym=0,cgOther=0,exposed="?";
+    for(const l of lines){try{const o=JSON.parse(l);
+      if(o.type==="system"&&o.subtype==="init"){exposed=(o.tools||[]).filter(t=>/homegraph/.test(t)).length;}
+      const blocks=o.message?.content||[];
+      for(const b of (Array.isArray(blocks)?blocks:[])){
+        if(b.type!=="tool_use")continue;
+        if(b.name==="Read")read++;
+        else if(b.name==="mcp__homegraph__homegraph_node"){ if(b.input&&b.input.symbol)cgSym++; else cgFile++; }
+        else if(/mcp__homegraph__/.test(b.name))cgOther++;
+      }
+    }catch{}}
+    console.log(`    Read=${read}  homegraph_node[file]=${cgFile}  homegraph_node[symbol]=${cgSym}  other_cg=${cgOther}  (cg exposed=${exposed})`);
+  ' "$1"
+}
+
+run_arm() { # label, N
+  local label="$1" n="$2"
+  local c="$OUT/mcp-$label.json"
+  for i in $(seq 1 "$n"); do
+    local tgt="$OUT/t-$label-$i"
+    rm -rf "$tgt"
+    rsync -a --exclude node_modules --exclude .git --exclude dist --exclude .homegraph "$TARGET/" "$tgt/"
+    node "$BIN" init "$tgt" >/dev/null 2>&1
+    printf '{"mcpServers":{"homegraph":{"command":"env","args":["HOMEGRAPH_WASM_RELAUNCHED=1","node","%s","serve","--mcp","--path","%s"]}}}' "$BIN" "$tgt" > "$c"
+    prewarm "$tgt"
+    echo "----- [$label] run $i -----"
+    ( cd "$tgt" && claude -p "$TASK" \
+        --output-format stream-json --verbose --permission-mode bypassPermissions \
+        --model "${MODEL:-sonnet}" --effort "${EFFORT:-high}" --max-budget-usd 4 --strict-mcp-config --mcp-config "$c" \
+        </dev/null > "$OUT/run-$label-$i.jsonl" 2>"$OUT/run-$label-$i.err" )
+    count "$OUT/run-$label-$i.jsonl"
+    pkill -9 -f "serve --mcp --path $tgt" 2>/dev/null
+  done
+  echo
+}
+
+echo "== NEW build (HEAD: homegraph_node has Read parity) =="
+( cd "$ENGINE" && npm run build >/dev/null 2>&1 ) && echo "built"
+run_arm new "$RUNS"
+
+echo "== BASELINE build ($BASE_REF) =="
+git -C "$ENGINE" checkout "$BASE_REF" -- $CHANGED
+( cd "$ENGINE" && npm run build >/dev/null 2>&1 ) && echo "built"
+run_arm baseline "$RUNS"
+
+echo "###### DONE — compare [new] vs [baseline]: does homegraph_node[file] rise / Read fall? Logs: $OUT"