github/codegraph
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix(resolution): stop "Resolving refs" wedge on theme-vendoring repos; add exclude config + index watchdogs (#999) (#1009)

Browse Source 
Three fixes for a repo that commits a large JS/TS theme/SDK (Metronic under
static/, ~1,600 tracked files):

1. A SECOND "Resolving refs" quadratic that #915 didn't cover. #915 capped
   import-name collisions; this caps method-name collisions (init/update/render
   re-declared on every widget), which flow through matchMethodCall Strategy 3
   and findBestMatch instead. New AMBIGUOUS_NAME_CEILING (default 500, env
   CODEGRAPH_AMBIGUOUS_NAME_CEILING): above it the fuzzy strategies decline
   rather than score K candidates — no proximity score can pick the one true
   target among thousands anyway. Resolving drops from O(K^2) to linear in refs
   (e.g. 900-file synthetic: 28.7s -> 3.4s), edge counts unchanged, and the cap
   never fires on normal repos (max real method-collision ~40).

2. A new `exclude` array in codegraph.json keeps git-TRACKED paths out of the
   index, which .gitignore can't do (enumeration is `git ls-files`). Mirrors the
   existing includeIgnored plumbing across the git, sync, and non-git-walk
   paths.

3. `index`/`init` now install the #850 liveness + #277 ppid watchdogs (which
   were serve-only), so a wedged or orphaned indexer self-terminates instead of
   pinning a core. The --liftoff-only relaunch's spawnSync can't forward
   signals, so killing the parent shim used to orphan the worker.

Tests: ubiquitous-name ceiling, exclude (incl. tracked-file exclusion on git +
non-git), orphan self-termination (POSIX), and ppid-parser units. Shared the
ppid parsers out of mcp/index.ts into mcp/ppid-watchdog.ts.

Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
This commit is contained in:
Colby Mchenry
2026-06-26 20:25:47 -05:00
committed by GitHub
co-authored by Claude Opus 4.8
parent d3179f5004
commit 45d3293c6a
12 changed files with 805 additions and 100 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/extraction/index.ts
+46 -7
View File
@@ -19,7 +19,7 @@ import {
import { QueryBuilder } from '../db/queries';
import { extractFromSource } from './tree-sitter';
import { detectLanguage, isSourceFile, isLanguageSupported, isFileLevelOnlyLanguage, initGrammars, loadGrammarsForLanguages } from './grammars';
import { loadExtensionOverrides, loadIncludeIgnoredPatterns } from '../project-config';
import { loadExtensionOverrides, loadIncludeIgnoredPatterns, loadExcludePatterns } from '../project-config';
import { isCodeGraphDataDir } from '../directory';
import { logDebug, logWarn } from '../errors';
import { validatePathWithinRoot, normalizePath } from '../utils';
@@ -283,6 +283,20 @@ function loadIncludeIgnoredMatcher(rootDir: string): Ignore | null {
return patterns.length > 0 ? ignore().add(patterns) : null;
}
/**
* Matcher for the project's `codegraph.json` `exclude` patterns — paths to keep
* OUT of the index even when git-tracked, which `.gitignore` cannot do (#999).
* The escape hatch for a committed vendor/theme/SDK directory. Returns `null`
* when nothing is excluded (the zero-config default → no overhead). Matched
* against project-root-relative paths, so it applies uniformly across the whole
* workspace, including inside embedded repos (excluding `static/` means gone
* everywhere). Built once per scan/sync/scope operation from the scan root.
*/
function loadExcludeMatcher(rootDir: string): Ignore | null {
const patterns = loadExcludePatterns(rootDir);
return patterns.length > 0 ? ignore().add(patterns) : null;
}
/**
* `git ls-files --directory` collapses a wholly-untracked/ignored directory into
* one entry — and when the command's own cwd is such a directory (the indexed
@@ -421,12 +435,25 @@ function findNestedGitRepos(absDir: string, relPrefix: string): string[] {
export class ScopeIgnore {
private embedded: Array<{ root: string; matcher: Ignore }>;
private defaults: Ignore = defaultsOnlyIgnore();
constructor(private rootMatcher: Ignore, embedded: Array<{ root: string; matcher: Ignore }>) {
constructor(
private rootMatcher: Ignore,
embedded: Array<{ root: string; matcher: Ignore }>,
/**
* Project `codegraph.json` `exclude` patterns (#999), matched against the
* full root-relative path. Wins over everything else — an explicit user
* exclude applies even to tracked files and even inside embedded repos.
*/
private exclude: Ignore | null = null,
) {
// Longest root first so paths in nested embedded repos hit the innermost matcher.
this.embedded = [...embedded].sort((a, b) => b.root.length - a.root.length);
}
ignores(rel: string): boolean {
// User `exclude` (#999) is checked first and against the full root-relative
// path: it must drop git-TRACKED paths (which `.gitignore` can't) and apply
// everywhere, including ancestors of embedded repos.
if (this.exclude && this.exclude.ignores(rel)) return true;
for (const { root, matcher } of this.embedded) {
if (rel.startsWith(root)) {
const inner = rel.slice(root.length);
@@ -455,6 +482,7 @@ export function buildScopeIgnore(rootDir: string, embeddedRoots?: Iterable<strin
return new ScopeIgnore(
buildDefaultIgnore(rootDir),
roots.map((root) => ({ root, matcher: buildDefaultIgnore(path.join(rootDir, root)) })),
loadExcludeMatcher(rootDir),
);
}
@@ -678,14 +706,14 @@ function getGitChangedFiles(rootDir: string): GitChanges | null {
// Custom extension → language overrides from the project's codegraph.json,
// so change detection sees the same custom-extension files the full index does.
const overrides = loadExtensionOverrides(rootDir);
collectGitStatus(rootDir, '', changes, overrides, loadIncludeIgnoredMatcher(rootDir));
collectGitStatus(rootDir, '', changes, overrides, loadIncludeIgnoredMatcher(rootDir), loadExcludeMatcher(rootDir));
return changes;
} catch {
return null;
}
}
function collectGitStatus(repoDir: string, prefix: string, out: GitChanges, overrides?: Record<string, Language>, includeIgnored: Ignore | null = null): void {
function collectGitStatus(repoDir: string, prefix: string, out: GitChanges, overrides?: Record<string, Language>, includeIgnored: Ignore | null = null, exclude: Ignore | null = null): void {
const output = execFileSync(
'git',
['status', '--porcelain', '--no-renames'],
@@ -732,6 +760,11 @@ function collectGitStatus(repoDir: string, prefix: string, out: GitChanges, over
// Added (`??`) / modified files inside an excluded dir must not enter the
// index — match against the repo-relative path, same as the full scan. (#766)
if (ig.ignores(rel)) continue;
// User `codegraph.json` `exclude` (#999) is project-root-relative, so it's
// matched against the full path — sync must not re-add a tracked file the
// full index now keeps out. Deletions above stay unfiltered so a file that
// WAS indexed before an exclude was added still cleans itself out.
if (exclude && exclude.ignores(filePath)) continue;
if (statusCode === '??') {
out.added.push(filePath);
@@ -747,11 +780,11 @@ function collectGitStatus(repoDir: string, prefix: string, out: GitChanges, over
// and they are left alone (#970, #976), mirroring the full-index scan.
for (const rel of untrackedDirs) {
for (const repoRel of findNestedGitRepos(path.join(repoDir, rel), rel)) {
collectGitStatus(path.join(repoDir, repoRel), prefix + repoRel, out, overrides, includeIgnored);
collectGitStatus(path.join(repoDir, repoRel), prefix + repoRel, out, overrides, includeIgnored, exclude);
}
}
for (const rel of findIgnoredEmbeddedRepos(repoDir, includeIgnored, prefix)) {
collectGitStatus(path.join(repoDir, rel), prefix + rel, out, overrides, includeIgnored);
collectGitStatus(path.join(repoDir, rel), prefix + rel, out, overrides, includeIgnored, exclude);
}
}
@@ -936,7 +969,13 @@ function scanDirectoryWalk(
// Seed a base matcher with the built-in default ignores (merged with the root
// .gitignore so a negation can override). Nested .gitignores still layer per-dir.
walk(rootDir, [{ dir: rootDir, ig: buildDefaultIgnore(rootDir) }]);
const baseMatchers: ScopedIgnore[] = [{ dir: rootDir, ig: buildDefaultIgnore(rootDir) }];
// Project `codegraph.json` `exclude` patterns (#999), rooted at the project so
// `isIgnored` matches them against root-relative paths — same coverage the
// git path gets via ScopeIgnore, for non-git projects.
const exclude = loadExcludeMatcher(rootDir);
if (exclude) baseMatchers.push({ dir: rootDir, ig: exclude });
walk(rootDir, baseMatchers);
return files;
}