chore: import upstream snapshot with attribution

scripts/add-lang/bench.sh

@@ -0,0 +1,60 @@
+#!/usr/bin/env bash
+# Add-lang benchmark for ONE repo:
+#   clone -> wipe+index (with the codegraph on PATH) -> verify extraction ->
+#   with/without retrieval A/B (reuses scripts/agent-eval/run-all.sh).
+#
+# Assumes the codegraph dev build is already built + linked on PATH — the skill
+# runs `npm run build && ./scripts/local-install.sh` ONCE before looping repos.
+# The A/B is skipped if extraction fails its critical checks (don't burn $ on a
+# broken extractor); set FORCE_AB=1 to run it anyway.
+#
+# Usage: bench.sh <lang> <repo-name> <repo-url> "<question>" [headless|tmux|all]
+# Env:   CORPUS   corpus dir (default /tmp/codegraph-corpus, shared with agent-eval)
+set -uo pipefail
+
+LANG_TOKEN="${1:?usage: bench.sh <lang> <repo-name> <repo-url> \"<question>\" [mode]}"
+NAME="${2:?repo-name required}"
+URL="${3:?repo-url required}"
+Q="${4:?question required}"
+MODE="${5:-headless}"
+
+HARNESS="$(cd "$(dirname "$0")" && pwd)"
+AGENT_EVAL="$(cd "$HARNESS/../agent-eval" && pwd)"
+CORPUS="${CORPUS:-/tmp/codegraph-corpus}"
+REPO="$CORPUS/$NAME"
+
+command -v codegraph >/dev/null || { echo "no codegraph on PATH (build + ./scripts/local-install.sh first)"; exit 1; }
+
+echo "==================== add-lang bench: $NAME ($LANG_TOKEN) ===================="
+echo "codegraph: $(command -v codegraph) -> $(codegraph --version 2>/dev/null || echo '?')"
+
+# 1. Ensure the repo (shallow clone, reuse if present).
+mkdir -p "$CORPUS"
+if [ -d "$REPO/.git" ]; then
+  echo "→ reusing checkout: $REPO"
+else
+  echo "→ cloning $URL"
+  git clone --depth 1 "$URL" "$REPO" || { echo "git clone failed"; exit 1; }
+fi
+
+# 2. Wipe + index with the binary under test.
+echo "→ wiping .codegraph and indexing"
+rm -rf "$REPO/.codegraph"
+( cd "$REPO" && codegraph init -i ) || { echo "indexing failed"; exit 1; }
+
+# 3. Verify extraction (cheap guard before the paid A/B).
+echo "→ verifying extraction"
+node "$HARNESS/verify-extraction.mjs" "$REPO" "$LANG_TOKEN"
+VERIFY=$?
+
+# 4. Retrieval A/B (skipped if extraction is broken, unless FORCE_AB=1).
+if [ "$VERIFY" -ne 0 ] && [ "${FORCE_AB:-0}" != "1" ]; then
+  echo "→ SKIPPING A/B — extraction failed critical checks (set FORCE_AB=1 to override)"
+else
+  echo "→ retrieval A/B (mode=$MODE)"
+  bash "$AGENT_EVAL/run-all.sh" "$REPO" "$Q" "$MODE"
+fi
+
+echo "==================== bench complete: $NAME (verify exit=$VERIFY) ===================="
+# Exit reflects extraction: 0 = pass/warn, 1 = critical fail, 2 = couldn't read status.
+exit "$VERIFY"

scripts/add-lang/check-grammar.mjs

@@ -0,0 +1,75 @@
+#!/usr/bin/env node
+// Verify a tree-sitter grammar wasm is HEALTHY under the project's web-tree-sitter
+// runtime BEFORE writing an extractor. Prints the ABI version and parses a valid
+// sample many times in a multi-grammar context, to catch heap-corruption bugs
+// that silently drop nodes on every parse after the first.
+//
+// Why this exists: the tree-sitter-wasms Lua grammar is ABI 13 and corrupts the
+// shared WASM heap under web-tree-sitter 0.25 — Lua extraction degraded on every
+// file after the first (nested calls/imports vanished). The fix was to vendor the
+// upstream ABI-15 wasm. Run this on any new grammar first; if it FAILs, vendor a
+// newer build instead of using the tree-sitter-wasms one.
+//
+// Usage: node scripts/add-lang/check-grammar.mjs <lang|wasm-path> <valid-sample> [iterations]
+// Exit: 0 healthy, 1 corruption / parse errors, 2 could not run.
+// NOTE: the sample must be SYNTACTICALLY VALID — a broken sample fails for the
+//       wrong reason.
+
+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 = (code, msg) => { console.error(`[check-grammar] ${msg}`); process.exit(code); };
+
+const [token, sample, iterArg] = process.argv.slice(2);
+if (!token || !sample) fail(2, 'usage: check-grammar.mjs <lang|wasm-path> <valid-sample> [iterations]');
+if (!existsSync(sample)) fail(2, `sample not found: ${sample}`);
+const iters = iterArg ? parseInt(iterArg, 10) : 20;
+
+const SPECIAL = { csharp: 'c_sharp', 'c#': 'c_sharp' };
+function resolveWasm(t) {
+  if (t.endsWith('.wasm')) return existsSync(t) ? t : fail(2, `wasm not found: ${t}`);
+  const base = SPECIAL[t.toLowerCase()] ?? t.toLowerCase();
+  try { return require.resolve(`tree-sitter-wasms/out/tree-sitter-${base}.wasm`); } catch { /* try vendored */ }
+  const vendored = `src/extraction/wasm/tree-sitter-${base}.wasm`;
+  if (existsSync(vendored)) return vendored;
+  return fail(2, `no grammar for "${t}" — not in tree-sitter-wasms and not vendored`);
+}
+
+const wasmPath = resolveWasm(token);
+const source = readFileSync(sample, 'utf8');
+
+try { await Parser.init(); }
+catch { await Parser.init({ locateFile: () => require.resolve('web-tree-sitter/tree-sitter.wasm') }); }
+
+// Load a second, known-good grammar — the corruption surfaces under the
+// multi-grammar runtime that real indexing uses, not a single grammar in isolation.
+try { await Language.load(require.resolve('tree-sitter-wasms/out/tree-sitter-python.wasm')); } catch { /* ok */ }
+
+let language;
+try { language = await Language.load(wasmPath); }
+catch (e) { fail(2, `failed to load ${wasmPath}: ${e.message}`); }
+
+const parser = new Parser();
+parser.setLanguage(language);
+
+let ok = 0, err = 0;
+for (let i = 0; i < iters; i++) {
+  const tree = parser.parse(source);
+  if (tree.rootNode.hasError) err++; else ok++;
+}
+
+console.log(`grammar: ${wasmPath.split('/').pop()}`);
+console.log(`  ABI version: ${language.abiVersion}`);
+console.log(`  parses: ${ok} clean / ${err} with errors (of ${iters})`);
+if (err > 0) {
+  console.log(
+    `RESULT: FAIL — ${err}/${iters} parses produced ERROR trees on a valid sample. ` +
+    `This grammar corrupts under web-tree-sitter; vendor a newer (ABI 14/15) wasm ` +
+    `(see SKILL.md "Find a grammar"). Confirm your sample is syntactically valid first.`
+  );
+  process.exit(1);
+}
+console.log('RESULT: PASS — grammar parses cleanly and reuses safely.');
+process.exit(0);

scripts/add-lang/dump-ast.mjs

@@ -0,0 +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
+// codegraph 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();

scripts/add-lang/verify-extraction.mjs

@@ -0,0 +1,70 @@
+#!/usr/bin/env node
+// Sanity-check that codegraph 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 `codegraph status <repo> --json` using whatever codegraph 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('codegraph', ['status', repo, '--json'], { encoding: 'utf8' });
+  status = JSON.parse(out);
+} catch (e) {
+  console.error(`[verify] could not read codegraph status for ${repo}: ${e.message}`);
+  process.exit(2);
+}
+
+// Kinds that prove the extractor mapped AST node types (everything except
+// 'file' and 'import', which codegraph creates structurally for any language).
+const SYMBOL_KINDS = new Set([
+  'module', 'class', 'struct', 'interface', 'trait', 'protocol', 'function',
+  'method', 'property', 'field', 'variable', 'constant', 'enum', 'enum_member',
+  'type_alias', 'namespace', 'route', 'component',
+]);
+
+const byKind = status.nodesByKind || {};
+const langs = status.languages || [];
+const files = status.fileCount || 0;
+const edges = status.edgeCount || 0;
+const symbolKinds = Object.keys(byKind).filter((k) => SYMBOL_KINDS.has(k));
+const symbolCount = symbolKinds.reduce((s, k) => s + byKind[k], 0);
+
+const checks = [];
+const add = (severity, ok, label, detail) => checks.push({ severity, ok, label, detail });
+
+add('critical', status.initialized === true, 'index initialized', `initialized=${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);