fix(sync): filesystem-based change detection (catch git pull & non-git edits) (#414)

* fix(sync): detect changes via filesystem, not git status

Incremental sync detected changes with `git status --porcelain`, which only sees uncommitted working-tree changes — so committed changes from git pull/checkout/merge/rebase (clean tree afterward) were never reconciled, and non-git projects leaned on a slow full rescan. Change detection is now filesystem-based and git-independent: a (size, mtime) stat pre-filter skips unchanged files, then a content hash confirms the rest; removals are checked against the filesystem (git ls-files still lists deleted-but-unstaged files). Also adds a non-blocking catch-up sync on MCP connect so changes made while the server was down (e.g. a terminal git pull) are reconciled on connect.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

* docs(changelog): add 0.9.5 entry for filesystem-based sync fix

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This commit is contained in:
Colby Mchenry
2026-05-25 17:36:09 -05:00
committed by GitHub
co-authored by Claude Opus 4.7
parent 1be8e7830f
commit 4a94696e44
3 changed files with 108 additions and 77 deletions
+17
View File
@@ -7,6 +7,22 @@ a [GitHub Release](https://github.com/colbymchenry/codegraph/releases) tagged
This project follows [Keep a Changelog](https://keepachangelog.com/en/1.1.0/)
and adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
## [0.9.5] - 2026-05-25
### Fixed
- **The index now stays in sync after `git pull`, branch switches, and edits made
outside your editor.** Incremental sync detected changes via `git status`, which
only sees *uncommitted* edits — so code pulled or checked out (which leaves a
clean working tree) was silently missed until a full `codegraph index -f`.
Change detection is now filesystem-based and git-independent: a `(size, mtime)`
stat pre-filter skips unchanged files, then a content hash confirms the rest. It
reconciles committed changes from `pull`/`checkout`/`merge`/`rebase`, plain edits
in non-git projects, and deletions alike.
- **The MCP server catches up on connect.** When your editor connects, codegraph
reconciles anything that changed while it wasn't running (e.g. a `git pull` from
the terminal), so the first query reflects the current code instead of a stale
snapshot — rather than waiting for the next live edit.
## [0.9.4] - 2026-05-24
### Added
@@ -228,6 +244,7 @@ and adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
find its bundle. The release pipeline now verifies every package reached the
registry (and is idempotent), so a release can't pass green-but-broken again.
[0.9.5]: https://github.com/colbymchenry/codegraph/releases/tag/v0.9.5
[0.9.4]: https://github.com/colbymchenry/codegraph/releases/tag/v0.9.4
[0.9.3]: https://github.com/colbymchenry/codegraph/releases/tag/v0.9.3
[0.9.2]: https://github.com/colbymchenry/codegraph/releases/tag/v0.9.2
+43 -57
View File
@@ -1202,8 +1202,12 @@ export class ExtractionOrchestrator {
}
/**
* Sync with current file state.
* Uses git status as a fast path when available, falling back to full scan.
* Sync the index with the current file state.
*
* Change detection is filesystem-based, never git: a (size, mtime) stat
* pre-filter skips unchanged files, then a content-hash compare confirms real
* changes. This works in non-git projects and catches committed changes from
* `git pull`/`checkout`/`merge`/`rebase` that `git status` cannot see.
*/
async sync(onProgress?: (progress: IndexProgress) => void): Promise<SyncResult> {
await initGrammars(); // Initialize WASM runtime (grammars loaded lazily below)
@@ -1222,73 +1226,58 @@ export class ExtractionOrchestrator {
});
const filesToIndex: string[] = [];
const gitChanges = getGitChangedFiles(this.rootDir);
// === Filesystem reconcile (git-independent) ===
// The source of truth for "what changed" is the filesystem vs the indexed
// state — never git. We enumerate the current source files and reconcile
// each against the DB. A cheap (size, mtime) stat pre-filter skips unchanged
// files without reading or hashing them, so the expensive read+hash+parse
// only runs for files that actually changed. This catches edits/adds/deletes
// whether or not the project uses git, and crucially also catches committed
// changes from `git pull`/`checkout`/`merge`/`rebase` — which `git status`
// cannot see, because the working tree is clean afterward.
const currentFiles = scanDirectory(this.rootDir);
filesChecked = currentFiles.length;
const currentSet = new Set(currentFiles);
if (gitChanges) {
// === Git fast path ===
// Only inspect the files git reports as changed instead of scanning everything.
filesChecked = gitChanges.modified.length + gitChanges.added.length + gitChanges.deleted.length;
// Handle deleted files
for (const filePath of gitChanges.deleted) {
const tracked = this.queries.getFileByPath(filePath);
if (tracked) {
this.queries.deleteFile(filePath);
filesRemoved++;
}
}
// Handle modified + added files — read + hash only these. Untracked
// (`??`) files stay untracked in git even after we index them, so they
// can't be trusted as "new": re-hash and compare against the DB exactly
// like modified files. Otherwise every sync re-indexes them and status
// reports them as pending forever. (See issue #206.)
for (const filePath of [...gitChanges.modified, ...gitChanges.added]) {
const fullPath = path.join(this.rootDir, filePath);
let content: string;
try {
content = fs.readFileSync(fullPath, 'utf-8');
} catch (error) {
logDebug('Skipping unreadable file during sync', { filePath, error: String(error) });
continue;
}
const contentHash = hashContent(content);
const tracked = this.queries.getFileByPath(filePath);
if (!tracked) {
filesToIndex.push(filePath);
changedFilePaths.push(filePath);
filesAdded++;
} else if (tracked.contentHash !== contentHash) {
filesToIndex.push(filePath);
changedFilePaths.push(filePath);
filesModified++;
}
}
} else {
// === Fallback: full scan (non-git project or git failure) ===
const currentFiles = new Set(scanDirectory(this.rootDir));
filesChecked = currentFiles.size;
// Build Map for O(1) lookups instead of .find() per file
const trackedFiles = this.queries.getAllFiles();
const trackedMap = new Map<string, FileRecord>();
for (const f of trackedFiles) {
trackedMap.set(f.path, f);
}
// Find files to remove (in DB but not on disk)
// Removals: tracked in the DB but no longer a present source file. Check the
// filesystem directly — `scanDirectory` (via `git ls-files`) still lists a
// file deleted from disk but not yet staged, so set membership alone misses it.
for (const tracked of trackedFiles) {
if (!currentFiles.has(tracked.path)) {
if (!currentSet.has(tracked.path) || !fs.existsSync(path.join(this.rootDir, tracked.path))) {
this.queries.deleteFile(tracked.path);
filesRemoved++;
}
}
// Find files to add or update
// Adds / modifications.
for (const filePath of currentFiles) {
const fullPath = path.join(this.rootDir, filePath);
const tracked = trackedMap.get(filePath);
// Cheap pre-filter: an already-indexed file whose size AND mtime both match
// the DB is unchanged — skip it without reading or hashing. (A content
// change that preserves both exactly is the blind spot every mtime-based
// incremental tool accepts; `index --force` is the escape hatch. Git bumps
// mtime on every file it writes during checkout/merge, so pulls are caught.)
if (tracked) {
try {
const stat = fs.statSync(fullPath);
if (stat.size === tracked.size && Math.floor(stat.mtimeMs) === Math.floor(tracked.modifiedAt)) {
continue;
}
} catch (error) {
logDebug('Skipping unstattable file during sync', { filePath, error: String(error) });
continue;
}
}
// New, or size/mtime changed — read + hash to confirm a real content change.
let content: string;
try {
content = fs.readFileSync(fullPath, 'utf-8');
@@ -1296,9 +1285,7 @@ export class ExtractionOrchestrator {
logDebug('Skipping unreadable file during sync', { filePath, error: String(error) });
continue;
}
const contentHash = hashContent(content);
const tracked = trackedMap.get(filePath);
if (!tracked) {
filesToIndex.push(filePath);
@@ -1310,7 +1297,6 @@ export class ExtractionOrchestrator {
filesModified++;
}
}
}
// Load only grammars needed for changed files
if (filesToIndex.length > 0) {
+28
View File
@@ -243,6 +243,7 @@ export class MCPServer {
this.cg = await CodeGraph.open(resolvedRoot);
this.toolHandler.setDefaultCodeGraph(this.cg);
this.startWatching();
this.catchUpSync();
} catch (err) {
// Log the error so transient failures are diagnosable (see issue #47)
const msg = err instanceof Error ? err.message : String(err);
@@ -301,6 +302,7 @@ export class MCPServer {
this.projectPath = resolvedRoot;
this.toolHandler.setDefaultCodeGraph(this.cg);
this.startWatching();
this.catchUpSync();
} catch {
// Still failing — will retry on next tool call
}
@@ -370,6 +372,32 @@ export class MCPServer {
}
}
/**
* Reconcile the index with the current filesystem once, right after connect —
* catches edits, adds, deletes, and `git pull`/`checkout` changes made while
* no watcher was running. Runs in the background so it never delays the
* `initialize` response; `sync()` is incremental (a stat pre-filter skips
* unchanged files) and mutex-guarded, so it can't collide with the live
* watcher or a git-hook sync. Runs even when the watcher is unavailable
* (e.g. WSL2 /mnt drives), where catch-up matters most.
*/
private catchUpSync(): void {
const cg = this.cg;
if (!cg) return;
void cg
.sync()
.then((result) => {
const changed = result.filesAdded + result.filesModified + result.filesRemoved;
if (changed > 0) {
process.stderr.write(`[CodeGraph MCP] Caught up ${changed} file(s) changed since last run\n`);
}
})
.catch((err) => {
const msg = err instanceof Error ? err.message : String(err);
process.stderr.write(`[CodeGraph MCP] Catch-up sync failed: ${msg}\n`);
});
}
/**
* Stop the server
*/