feat(mcp): share one serve --mcp per project across MCP clients (#411)
One shared, detached daemon per project root: every `codegraph serve --mcp` is a thin stdio<->socket proxy (Unix socket / Windows named pipe) to it, so N agents in one repo share a single file watcher, SQLite connection, and tree-sitter warm-up instead of N copies. The daemon outlives any single session and reaps via client-refcount + idle timeout; `CODEGRAPH_NO_DAEMON=1` opts out. Hardened during review: detached-process lifecycle (preserves the #277 watchdog via the proxy; the daemon no longer orphans on host SIGKILL), atomic lockfile + pid-verified stale-clear (no double-daemon on concurrent startup), realpath root canonicalization. Validated on macOS, Linux (Docker - 3x fewer inotify watches for 3 agents), and Windows (named pipes); A/B confirms byte-identical tool output vs direct mode. Closes #411. Co-Authored-By: Colby McHenry <me@colbymchenry.com> Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This commit is contained in:
co-authored by
Colby McHenry
Claude Opus 4.7
parent
2721165604
commit
995da54430
+332
-467
@@ -13,54 +13,45 @@
|
||||
* const server = new MCPServer('/path/to/project');
|
||||
* await server.start();
|
||||
* ```
|
||||
*
|
||||
* Runtime modes (decided in {@link MCPServer.start}):
|
||||
*
|
||||
* - **Direct** — one process serves one MCP client over stdio. The pre-#411
|
||||
* behavior; used when the user opts out (`CODEGRAPH_NO_DAEMON=1`), no
|
||||
* `.codegraph/` is reachable, or the daemon machinery fails for any reason.
|
||||
* - **Proxy** — what an MCP host actually talks to when sharing is on: a thin
|
||||
* stdio↔socket pipe to the shared daemon. The proxy carries the #277 PPID
|
||||
* watchdog, so a SIGKILL'd host reaps its proxy promptly. See {@link ./proxy.ts}.
|
||||
* - **Daemon** — a *detached* background process (its own session/process
|
||||
* group) that serves N proxies over a Unix-domain socket / named pipe,
|
||||
* sharing one CodeGraph + watcher + SQLite handle. Spawned on demand; never a
|
||||
* child of any host, so it survives individual sessions and is reaped by
|
||||
* client-refcount + idle timeout. See {@link ./daemon.ts} and issue #411.
|
||||
*
|
||||
* The detached-daemon + always-proxy split is the fix for the review finding
|
||||
* that the original in-process daemon (a) was the first host's child, so closing
|
||||
* that terminal severed every other client, and (b) disabled the PPID watchdog,
|
||||
* regressing #277 (orphaned daemons on host SIGKILL).
|
||||
*/
|
||||
|
||||
import * as fs from 'fs';
|
||||
import * as path from 'path';
|
||||
import CodeGraph, { findNearestCodeGraphRoot } from '../index';
|
||||
import { watchDisabledReason } from '../sync';
|
||||
import { StdioTransport, JsonRpcRequest, JsonRpcNotification, ErrorCodes } from './transport';
|
||||
import { tools, ToolHandler } from './tools';
|
||||
import { SERVER_INSTRUCTIONS } from './server-instructions';
|
||||
import { spawn, StdioOptions } from 'child_process';
|
||||
import { findNearestCodeGraphRoot } from '../index';
|
||||
import { getCodeGraphDir } from '../directory';
|
||||
import { StdioTransport } from './transport';
|
||||
import { MCPEngine } from './engine';
|
||||
import { MCPSession } from './session';
|
||||
import {
|
||||
Daemon,
|
||||
clearStaleDaemonLock,
|
||||
isProcessAlive,
|
||||
tryAcquireDaemonLock,
|
||||
} from './daemon';
|
||||
import { runProxy } from './proxy';
|
||||
import { getDaemonSocketPath } from './daemon-paths';
|
||||
import { HOST_PPID_ENV } from '../extraction/wasm-runtime-flags';
|
||||
|
||||
/**
|
||||
* Convert a file:// URI to a filesystem path.
|
||||
* Handles URL encoding and Windows drive letter paths.
|
||||
*/
|
||||
function fileUriToPath(uri: string): string {
|
||||
try {
|
||||
const url = new URL(uri);
|
||||
let filePath = decodeURIComponent(url.pathname);
|
||||
// On Windows, file:///C:/path produces pathname /C:/path — strip leading /
|
||||
if (process.platform === 'win32' && /^\/[a-zA-Z]:/.test(filePath)) {
|
||||
filePath = filePath.slice(1);
|
||||
}
|
||||
return path.resolve(filePath);
|
||||
} catch {
|
||||
// Fallback for non-standard URIs
|
||||
return uri.replace(/^file:\/\/\/?/, '');
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* MCP Server Info
|
||||
*/
|
||||
const SERVER_INFO = {
|
||||
name: 'codegraph',
|
||||
version: '0.1.0',
|
||||
};
|
||||
|
||||
/**
|
||||
* MCP Protocol Version
|
||||
*/
|
||||
const PROTOCOL_VERSION = '2024-11-05';
|
||||
|
||||
/**
|
||||
* How long to wait for the client's `roots/list` response before giving up
|
||||
* and falling back to the process cwd.
|
||||
*/
|
||||
const ROOTS_LIST_TIMEOUT_MS = 5000;
|
||||
|
||||
/**
|
||||
* How often to poll `process.ppid` to detect parent process death (see #277).
|
||||
* 5s is a deliberate trade-off: the failure mode being guarded against is rare
|
||||
@@ -68,6 +59,32 @@ const ROOTS_LIST_TIMEOUT_MS = 5000;
|
||||
*/
|
||||
const DEFAULT_PPID_POLL_MS = 5000;
|
||||
|
||||
/**
|
||||
* Env var that marks a process as the *detached daemon* itself (set by
|
||||
* {@link spawnDetachedDaemon} when it re-invokes the CLI). Without it a
|
||||
* `serve --mcp` invocation is a launcher that connects-or-spawns; with it, the
|
||||
* process IS the daemon and must never try to spawn another (infinite spawn).
|
||||
*/
|
||||
const DAEMON_INTERNAL_ENV = 'CODEGRAPH_DAEMON_INTERNAL';
|
||||
|
||||
/**
|
||||
* Retries for the detached daemon arbitrating the O_EXCL lock against a racing
|
||||
* sibling. Tiny — the lock resolves on the first round in practice; the retries
|
||||
* only cover clearing a genuinely stale (dead-pid) lockfile.
|
||||
*/
|
||||
const TAKEOVER_MAX_RETRIES = 5;
|
||||
const TAKEOVER_RETRY_DELAY_MS = 100;
|
||||
|
||||
/**
|
||||
* How long a launcher waits for a freshly-spawned daemon to bind its socket
|
||||
* before giving up and running in-process. The daemon binds the socket *before*
|
||||
* the (backgrounded) engine/grammar warm-up, so this only needs to cover node
|
||||
* process startup. 60 × 100ms = 6s of headroom for a cold/slow box; on the
|
||||
* common path the socket appears within a few rounds.
|
||||
*/
|
||||
const DAEMON_CONNECT_MAX_RETRIES = 60;
|
||||
const DAEMON_CONNECT_RETRY_DELAY_MS = 100;
|
||||
|
||||
/**
|
||||
* Resolve the PPID watchdog poll interval from an env override. A value of
|
||||
* `0` disables the watchdog entirely (escape hatch for embedded scenarios
|
||||
@@ -96,28 +113,84 @@ function parseHostPpid(raw: string | undefined): number | null {
|
||||
return parsed;
|
||||
}
|
||||
|
||||
/** True if a process with `pid` currently exists (signal-0 probe). */
|
||||
function isProcessAlive(pid: number): boolean {
|
||||
try {
|
||||
process.kill(pid, 0);
|
||||
return true;
|
||||
} catch {
|
||||
return false;
|
||||
}
|
||||
/** Whether `CODEGRAPH_NO_DAEMON` was set to a truthy value. */
|
||||
function daemonOptOutSet(): boolean {
|
||||
const raw = process.env.CODEGRAPH_NO_DAEMON;
|
||||
if (!raw) return false;
|
||||
return raw !== '0' && raw.toLowerCase() !== 'false';
|
||||
}
|
||||
|
||||
/** Whether this process was spawned to BE the detached daemon. */
|
||||
function daemonInternalSet(): boolean {
|
||||
const raw = process.env[DAEMON_INTERNAL_ENV];
|
||||
return !!raw && raw !== '0' && raw.toLowerCase() !== 'false';
|
||||
}
|
||||
|
||||
/**
|
||||
* Extract the first usable filesystem path from a `roots/list` result.
|
||||
* Shape per MCP spec: `{ roots: [{ uri: "file:///path", name?: string }] }`.
|
||||
* Returns null if the result is empty or malformed.
|
||||
* Resolve the project root the daemon machinery should key on. Returns
|
||||
* `null` when no `.codegraph/` is reachable from the candidate path — in
|
||||
* that case the caller must run in direct mode, since the daemon lockfile
|
||||
* and socket both live under `.codegraph/`.
|
||||
*
|
||||
* The result is canonicalized with `realpathSync` so every client converges on
|
||||
* the same socket/lock path regardless of how it expressed the path: a client
|
||||
* launched with cwd under a symlink (e.g. macOS `/var` → `/private/var`, where
|
||||
* spawned `process.cwd()` is already realpath'd) and one that passed a
|
||||
* symlinked `rootUri` would otherwise hash to different sockets and silently
|
||||
* fail to share the daemon.
|
||||
*/
|
||||
function firstRootPath(result: unknown): string | null {
|
||||
if (!result || typeof result !== 'object') return null;
|
||||
const roots = (result as { roots?: unknown }).roots;
|
||||
if (!Array.isArray(roots) || roots.length === 0) return null;
|
||||
const first = roots[0] as { uri?: unknown };
|
||||
if (typeof first?.uri !== 'string') return null;
|
||||
return fileUriToPath(first.uri);
|
||||
function resolveDaemonRoot(explicitPath: string | null): string | null {
|
||||
const candidate = explicitPath ?? process.cwd();
|
||||
const root = findNearestCodeGraphRoot(candidate);
|
||||
if (!root) return null;
|
||||
try { return fs.realpathSync(root); } catch { return root; }
|
||||
}
|
||||
|
||||
/**
|
||||
* Spawn the shared daemon as a fully detached background process: its own
|
||||
* session/process group (so a SIGHUP/SIGINT to the launcher's terminal can't
|
||||
* reach it) with stdio decoupled from the launcher (logs to
|
||||
* `.codegraph/daemon.log`). Re-invokes the *same* CLI faithfully across dev and
|
||||
* bundled launches by reusing `process.argv[0]` (the right node), the current
|
||||
* `process.execArgv` (carries `--liftoff-only`, so the daemon never re-execs)
|
||||
* and `process.argv[1]` (this script). The spawned process self-arbitrates the
|
||||
* O_EXCL lock, so racing launchers may each spawn one — losers exit and every
|
||||
* launcher proxies through the single winner.
|
||||
*/
|
||||
function spawnDetachedDaemon(root: string): void {
|
||||
const scriptPath = process.argv[1];
|
||||
if (!scriptPath) {
|
||||
// No resolvable CLI entry point to re-invoke — let the caller fall back to
|
||||
// direct mode rather than spawn something broken.
|
||||
throw new Error('cannot resolve CLI script path to spawn the daemon');
|
||||
}
|
||||
|
||||
let logFd: number | null = null;
|
||||
let stdio: StdioOptions = 'ignore';
|
||||
try {
|
||||
logFd = fs.openSync(path.join(getCodeGraphDir(root), 'daemon.log'), 'a');
|
||||
stdio = ['ignore', logFd, logFd];
|
||||
} catch {
|
||||
stdio = 'ignore'; // no log file — discard daemon output rather than fail
|
||||
}
|
||||
try {
|
||||
const child = spawn(
|
||||
process.execPath,
|
||||
[...process.execArgv, scriptPath, 'serve', '--mcp', '--path', root],
|
||||
{
|
||||
detached: true,
|
||||
stdio,
|
||||
windowsHide: true,
|
||||
env: { ...process.env, [DAEMON_INTERNAL_ENV]: '1' },
|
||||
},
|
||||
);
|
||||
child.unref();
|
||||
} finally {
|
||||
// The child holds its own dup of the log fd now; the launcher doesn't need it.
|
||||
if (logFd !== null) {
|
||||
try { fs.closeSync(logFd); } catch { /* ignore */ }
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
@@ -125,281 +198,88 @@ function firstRootPath(result: unknown): string | null {
|
||||
*
|
||||
* Implements the Model Context Protocol to expose CodeGraph
|
||||
* functionality as tools that can be called by AI assistants.
|
||||
*
|
||||
* Backwards-compatible constructor and `start()` signature with the
|
||||
* pre-issue-#411 implementation: callers continue to do
|
||||
* `new MCPServer(path).start()`. Internally we now pick from direct / proxy /
|
||||
* daemon at start time.
|
||||
*/
|
||||
export class MCPServer {
|
||||
private transport: StdioTransport;
|
||||
private cg: CodeGraph | null = null;
|
||||
private toolHandler: ToolHandler;
|
||||
private projectPath: string | null;
|
||||
// In-flight background init kicked off from handleInitialize. Tracked so the
|
||||
// sync retry path doesn't race against it (double-opening the SQLite file).
|
||||
private initPromise: Promise<void> | null = null;
|
||||
// Whether the client advertised the MCP `roots` capability during initialize.
|
||||
// If so, and no explicit project path was given, we ask it for the workspace
|
||||
// root via roots/list rather than guessing from the (often wrong) cwd.
|
||||
private clientSupportsRoots = false;
|
||||
// Guards the one-shot deferred resolution (roots/list or cwd) so we don't
|
||||
// re-issue roots/list on every tool call.
|
||||
private rootsAttempted = false;
|
||||
// PPID watchdog — see start(). Captured at construction so we always have a
|
||||
// Direct-mode-only state. In daemon mode the per-connection sessions live
|
||||
// inside the Daemon class; in proxy mode there is no session at all.
|
||||
private session: MCPSession | null = null;
|
||||
private engine: MCPEngine | null = null;
|
||||
private daemon: Daemon | null = null;
|
||||
private ppidWatchdog: ReturnType<typeof setInterval> | null = null;
|
||||
// PPID watchdog baseline — captured at construction so we always have a
|
||||
// baseline, even if start() runs after a fork-style reparent.
|
||||
private originalPpid: number = process.ppid;
|
||||
// The MCP host's PID, propagated across the `--liftoff-only` re-exec (see
|
||||
// HOST_PPID_ENV). When set, the watchdog polls it directly: the re-exec
|
||||
// inserts an intermediate process whose *death* — not just our reparenting —
|
||||
// is what we'd otherwise miss. null on the direct (bundled) launch path.
|
||||
private hostPpid: number | null = parseHostPpid(process.env[HOST_PPID_ENV]);
|
||||
private ppidWatchdog: ReturnType<typeof setInterval> | null = null;
|
||||
// Idempotency guard for stop(). Without it, the watchdog can race with the
|
||||
// stdin `end`/`close` handlers (or SIGTERM/SIGINT) and double-close cg and
|
||||
// the transport before process.exit() lands.
|
||||
// Idempotency guard for stop().
|
||||
private stopped = false;
|
||||
private mode: 'unstarted' | 'direct' | 'proxy' | 'daemon' = 'unstarted';
|
||||
|
||||
constructor(projectPath?: string) {
|
||||
this.projectPath = projectPath || null;
|
||||
this.transport = new StdioTransport();
|
||||
// Create ToolHandler eagerly — cross-project queries work even without a default project
|
||||
this.toolHandler = new ToolHandler(null);
|
||||
}
|
||||
|
||||
/**
|
||||
* Start the MCP server
|
||||
* Start the MCP server.
|
||||
*
|
||||
* Note: CodeGraph initialization is deferred until the initialize request
|
||||
* is received, which includes the rootUri from the client.
|
||||
* Decision order:
|
||||
* 1. `CODEGRAPH_NO_DAEMON=1` → direct mode (unchanged pre-#411 behavior).
|
||||
* 2. `CODEGRAPH_DAEMON_INTERNAL=1` → we ARE the detached daemon; listen.
|
||||
* 3. No `.codegraph/` reachable → direct mode (the daemon's lockfile and
|
||||
* socket both live under `.codegraph/`).
|
||||
* 4. Otherwise connect to (or spawn) the shared daemon and proxy to it.
|
||||
*
|
||||
* On any unexpected failure in step 4 we transparently fall back to direct
|
||||
* mode — a misbehaving daemon must never block a session from starting.
|
||||
*/
|
||||
async start(): Promise<void> {
|
||||
// Start listening for messages immediately - don't check initialization yet
|
||||
// We'll get the project path from the initialize request's rootUri
|
||||
this.transport.start(this.handleMessage.bind(this));
|
||||
|
||||
// Keep the process running
|
||||
process.on('SIGINT', () => this.stop());
|
||||
process.on('SIGTERM', () => this.stop());
|
||||
|
||||
// When the parent process (Claude Code) exits, stdin closes.
|
||||
// Detect this and shut down gracefully to prevent orphaned processes.
|
||||
process.stdin.on('end', () => this.stop());
|
||||
process.stdin.on('close', () => this.stop());
|
||||
|
||||
// PPID watchdog (#277). Linux doesn't propagate parent death to children,
|
||||
// so when the MCP host (Claude Code, opencode, …) is SIGKILL'd by the OOM
|
||||
// killer / a force-quit / a container teardown, the child is reparented to
|
||||
// init/systemd and the stdin `end`/`close` events don't always fire. The
|
||||
// server would then linger indefinitely, holding inotify watches, file
|
||||
// descriptors, and the SQLite WAL. Poll `process.ppid` and shut down the
|
||||
// moment it changes from what we observed at startup. Cross-platform:
|
||||
// reparenting changes ppid on Linux *and* macOS; on Windows the value can
|
||||
// also drop to 0 once the parent is gone. When the CLI re-execs itself for
|
||||
// `--liftoff-only`, an intermediate process sits between us and the host and
|
||||
// outlives it, so our own ppid wouldn't change — in that case we poll the
|
||||
// host PID (propagated via HOST_PPID_ENV) for liveness instead. The watchdog
|
||||
// is `.unref()`'d so it never holds the event loop open on its own.
|
||||
const pollMs = parsePpidPollMs(process.env.CODEGRAPH_PPID_POLL_MS);
|
||||
if (pollMs > 0) {
|
||||
this.ppidWatchdog = setInterval(() => {
|
||||
const current = process.ppid;
|
||||
const ppidChanged = current !== this.originalPpid;
|
||||
const hostGone = this.hostPpid !== null && !isProcessAlive(this.hostPpid);
|
||||
if (ppidChanged || hostGone) {
|
||||
const reason = ppidChanged
|
||||
? `ppid ${this.originalPpid} -> ${current}`
|
||||
: `host pid ${this.hostPpid} exited`;
|
||||
process.stderr.write(
|
||||
`[CodeGraph MCP] Parent process exited (${reason}); shutting down.\n`
|
||||
);
|
||||
this.stop();
|
||||
}
|
||||
}, pollMs);
|
||||
this.ppidWatchdog.unref();
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* Try to initialize CodeGraph for the default project.
|
||||
*
|
||||
* Walks up parent directories to find the nearest .codegraph/ folder,
|
||||
* similar to how git finds .git/ directories.
|
||||
*
|
||||
* If initialization fails, the error is recorded but the server continues
|
||||
* to work — cross-project queries and retries on subsequent tool calls
|
||||
* are still possible.
|
||||
*/
|
||||
private async tryInitializeDefault(projectPath: string): Promise<void> {
|
||||
// Record where we searched so a later "not initialized" error can name it.
|
||||
this.toolHandler.setDefaultProjectHint(projectPath);
|
||||
|
||||
// Walk up parent directories to find nearest .codegraph/
|
||||
const resolvedRoot = findNearestCodeGraphRoot(projectPath);
|
||||
|
||||
if (!resolvedRoot) {
|
||||
this.projectPath = projectPath;
|
||||
return;
|
||||
// The detached daemon process itself. Checked before the opt-out so the
|
||||
// daemon honors the same env it was spawned with (it never sets NO_DAEMON).
|
||||
if (daemonInternalSet()) {
|
||||
return this.startDaemonProcess();
|
||||
}
|
||||
|
||||
this.projectPath = resolvedRoot;
|
||||
// Direct mode if the user opted out. Setting the env var is sufficient to
|
||||
// get the pre-#411 single-process behavior.
|
||||
if (daemonOptOutSet()) {
|
||||
return this.startDirect('CODEGRAPH_NO_DAEMON set');
|
||||
}
|
||||
|
||||
const root = resolveDaemonRoot(this.projectPath);
|
||||
if (!root) {
|
||||
// No initialized project found — daemon mode has nowhere to put its
|
||||
// socket. The fresh-checkout / outside-project case; behave as before.
|
||||
return this.startDirect('no .codegraph/ root found');
|
||||
}
|
||||
|
||||
try {
|
||||
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);
|
||||
process.stderr.write(`[CodeGraph MCP] Failed to open project at ${resolvedRoot}: ${msg}\n`);
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* Retry initialization of the default project if it previously failed.
|
||||
* Called lazily on tool calls that need the default project.
|
||||
* Re-walks parent directories each time so it picks up projects
|
||||
* initialized after the MCP server started.
|
||||
*
|
||||
* Awaits any in-flight background init (kicked off by handleInitialize) so
|
||||
* we never open the SQLite file twice concurrently.
|
||||
*/
|
||||
private async retryInitIfNeeded(): Promise<void> {
|
||||
// Wait for the background init started during handleInitialize, if any.
|
||||
if (this.initPromise) {
|
||||
try { await this.initPromise; } catch { /* errored init falls through to retry */ }
|
||||
}
|
||||
|
||||
// Already initialized successfully
|
||||
if (this.toolHandler.hasDefaultCodeGraph()) return;
|
||||
|
||||
// No explicit path was given at initialize. Resolve it now, exactly once:
|
||||
// ask the client via roots/list (if it advertised roots), else use cwd.
|
||||
// Deferring to here lets a roots answer override the wrong cwd, and the
|
||||
// one-shot guard means we never re-issue roots/list per tool call.
|
||||
if (!this.projectPath && !this.rootsAttempted) {
|
||||
this.rootsAttempted = true;
|
||||
this.initPromise = (
|
||||
this.clientSupportsRoots
|
||||
? this.initFromRoots()
|
||||
: this.tryInitializeDefault(process.cwd())
|
||||
).finally(() => { this.initPromise = null; });
|
||||
try { await this.initPromise; } catch { /* fall through to last-resort below */ }
|
||||
if (this.toolHandler.hasDefaultCodeGraph()) return;
|
||||
}
|
||||
|
||||
// Last resort: re-walk from the best candidate we have. Picks up projects
|
||||
// initialized after the server started, and covers clients that sent no
|
||||
// usable initialize signal at all.
|
||||
const candidate = this.projectPath ?? process.cwd();
|
||||
this.toolHandler.setDefaultProjectHint(candidate);
|
||||
const resolvedRoot = findNearestCodeGraphRoot(candidate);
|
||||
if (!resolvedRoot) return;
|
||||
|
||||
try {
|
||||
// Close any previously failed instance to avoid leaking resources
|
||||
if (this.cg) {
|
||||
try { this.cg.close(); } catch { /* ignore */ }
|
||||
this.cg = null;
|
||||
const mode = await this.connectOrSpawnDaemon(root);
|
||||
if (mode === 'fallback') {
|
||||
return this.startDirect('daemon unavailable; fallback to direct');
|
||||
}
|
||||
this.cg = CodeGraph.openSync(resolvedRoot);
|
||||
this.projectPath = resolvedRoot;
|
||||
this.toolHandler.setDefaultCodeGraph(this.cg);
|
||||
this.startWatching();
|
||||
this.catchUpSync();
|
||||
} catch {
|
||||
// Still failing — will retry on next tool call
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* Resolve the project root via the MCP `roots/list` request and initialize
|
||||
* from the first root the client reports. Falls back to the process cwd if
|
||||
* the client returns no usable root or doesn't answer in time. See issue #196.
|
||||
*/
|
||||
private async initFromRoots(): Promise<void> {
|
||||
let target = process.cwd();
|
||||
try {
|
||||
const result = await this.transport.request('roots/list', undefined, ROOTS_LIST_TIMEOUT_MS);
|
||||
const rootPath = firstRootPath(result);
|
||||
if (rootPath) {
|
||||
target = rootPath;
|
||||
} else {
|
||||
process.stderr.write('[CodeGraph MCP] Client returned no workspace roots; falling back to process cwd.\n');
|
||||
}
|
||||
} catch (err) {
|
||||
const msg = err instanceof Error ? err.message : String(err);
|
||||
process.stderr.write(`[CodeGraph MCP] roots/list request failed (${msg}); falling back to process cwd.\n`);
|
||||
}
|
||||
await this.tryInitializeDefault(target);
|
||||
}
|
||||
|
||||
/**
|
||||
* Start file watching on the active CodeGraph instance.
|
||||
* Logs sync activity to stderr for diagnostics.
|
||||
*/
|
||||
private startWatching(): void {
|
||||
if (!this.cg) return;
|
||||
|
||||
// When the watcher is intentionally disabled (e.g. WSL2 /mnt drives, or
|
||||
// CODEGRAPH_NO_WATCH=1), say so explicitly and tell the user how to keep
|
||||
// the graph fresh — otherwise the silent staleness is hard to diagnose.
|
||||
const disabledReason = watchDisabledReason(this.projectPath ?? process.cwd());
|
||||
if (disabledReason) {
|
||||
process.stderr.write(
|
||||
`[CodeGraph MCP] File watcher disabled — ${disabledReason}. ` +
|
||||
`The graph will not auto-update; run \`codegraph sync\` (or install the git sync hooks via \`codegraph init\`) to refresh.\n`
|
||||
);
|
||||
// 'proxy': connectOrSpawnDaemon ran the stdio↔socket pipe to completion
|
||||
// (it only returns once the host disconnected). The process is now
|
||||
// expected to terminate naturally — the proxy installed its own watchdog.
|
||||
this.mode = 'proxy';
|
||||
return;
|
||||
}
|
||||
|
||||
const started = this.cg.watch({
|
||||
onSyncComplete: (result) => {
|
||||
if (result.filesChanged > 0) {
|
||||
process.stderr.write(
|
||||
`[CodeGraph MCP] Auto-synced ${result.filesChanged} file(s) in ${result.durationMs}ms\n`
|
||||
);
|
||||
}
|
||||
},
|
||||
onSyncError: (err) => {
|
||||
process.stderr.write(`[CodeGraph MCP] Auto-sync error: ${err.message}\n`);
|
||||
},
|
||||
});
|
||||
|
||||
if (started) {
|
||||
process.stderr.write('[CodeGraph MCP] File watcher active — graph will auto-sync on changes\n');
|
||||
} else {
|
||||
// start() can also return false when recursive fs.watch isn't supported.
|
||||
process.stderr.write(
|
||||
'[CodeGraph MCP] File watcher unavailable on this platform — run `codegraph sync` to refresh the graph after changes.\n'
|
||||
);
|
||||
} catch (err) {
|
||||
// Belt-and-braces: if anything throws inside the daemon machinery,
|
||||
// never wedge the user — fall back to a working direct-mode session.
|
||||
const msg = err instanceof Error ? err.message : String(err);
|
||||
process.stderr.write(`[CodeGraph MCP] Daemon path failed (${msg}); falling back to direct mode.\n`);
|
||||
return this.startDirect('daemon path threw');
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* 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
|
||||
* Stop the server. In daemon mode this triggers graceful shutdown of every
|
||||
* connected session; in direct mode it mirrors the pre-#411 behavior (close
|
||||
* cg, exit). Proxy mode never routes through here — the proxy exits itself.
|
||||
*/
|
||||
stop(): void {
|
||||
if (this.stopped) return;
|
||||
@@ -408,181 +288,166 @@ export class MCPServer {
|
||||
clearInterval(this.ppidWatchdog);
|
||||
this.ppidWatchdog = null;
|
||||
}
|
||||
// Close all cached cross-project connections first
|
||||
this.toolHandler.closeAll();
|
||||
// Close the main CodeGraph instance
|
||||
if (this.cg) {
|
||||
this.cg.close();
|
||||
this.cg = null;
|
||||
if (this.daemon) {
|
||||
void this.daemon.stop('stop()');
|
||||
// Daemon.stop calls process.exit; nothing else to do.
|
||||
return;
|
||||
}
|
||||
this.transport.stop();
|
||||
if (this.session) {
|
||||
this.session.stop();
|
||||
this.session = null;
|
||||
}
|
||||
if (this.engine) {
|
||||
this.engine.stop();
|
||||
this.engine = null;
|
||||
}
|
||||
process.exit(0);
|
||||
}
|
||||
|
||||
/** Single-process stdio MCP session — the pre-issue-#411 code path. */
|
||||
private async startDirect(reason: string): Promise<void> {
|
||||
if (reason && process.env.CODEGRAPH_MCP_DEBUG) {
|
||||
process.stderr.write(`[CodeGraph MCP] Direct mode: ${reason}.\n`);
|
||||
}
|
||||
this.engine = new MCPEngine();
|
||||
const transport = new StdioTransport();
|
||||
this.session = new MCPSession(transport, this.engine, {
|
||||
explicitProjectPath: this.projectPath,
|
||||
});
|
||||
|
||||
if (this.projectPath) {
|
||||
// Background init so the initialize response stays fast (#172).
|
||||
void this.engine.ensureInitialized(this.projectPath);
|
||||
}
|
||||
|
||||
this.session.start();
|
||||
|
||||
// Detect parent-process death — same logic as pre-refactor. When stdin
|
||||
// closes we go through StdioTransport's `process.exit(0)` already, but
|
||||
// SIGKILL of the parent doesn't reliably close stdin on Linux (#277).
|
||||
process.stdin.on('end', () => this.stop());
|
||||
process.stdin.on('close', () => this.stop());
|
||||
|
||||
this.mode = 'direct';
|
||||
this.installSignalHandlers();
|
||||
this.installPpidWatchdog();
|
||||
}
|
||||
|
||||
/**
|
||||
* Run as the detached shared daemon (process spawned with
|
||||
* `CODEGRAPH_DAEMON_INTERNAL=1`). Arbitrate the O_EXCL lock, then either
|
||||
* become the daemon (bind the socket, serve forever) or — if a live daemon
|
||||
* already holds the lock — exit so we don't leak a redundant process.
|
||||
*
|
||||
* No PPID watchdog and no stdin handlers: the daemon is detached on purpose
|
||||
* and reaps itself via client-refcount + idle timeout (see {@link Daemon}).
|
||||
*/
|
||||
private async startDaemonProcess(): Promise<void> {
|
||||
const root = resolveDaemonRoot(this.projectPath) ?? this.projectPath ?? process.cwd();
|
||||
for (let attempt = 0; attempt < TAKEOVER_MAX_RETRIES; attempt++) {
|
||||
const lock = tryAcquireDaemonLock(root);
|
||||
|
||||
if (lock.kind === 'acquired') {
|
||||
const daemon = new Daemon(root);
|
||||
await daemon.start();
|
||||
this.daemon = daemon;
|
||||
this.mode = 'daemon';
|
||||
return; // the net.Server keeps the process alive
|
||||
}
|
||||
|
||||
// Taken. If the holder is alive, another daemon already serves (or is
|
||||
// binding) — we're redundant; exit cleanly so the launcher proxies to it.
|
||||
const existing = lock.existing;
|
||||
if (existing && existing.pid > 0 && isProcessAlive(existing.pid)) {
|
||||
process.stderr.write(
|
||||
`[CodeGraph daemon] Another daemon (pid ${existing.pid}) already holds the lock; exiting.\n`
|
||||
);
|
||||
process.exit(0);
|
||||
}
|
||||
|
||||
// Holder is dead (or the record is unreadable) — clear it (pid-verified,
|
||||
// so we never delete a live daemon's lock) and retry the acquire.
|
||||
clearStaleDaemonLock(lock.pidPath, existing?.pid);
|
||||
await sleep(TAKEOVER_RETRY_DELAY_MS);
|
||||
}
|
||||
|
||||
process.stderr.write('[CodeGraph daemon] Could not acquire the daemon lock; exiting.\n');
|
||||
process.exit(0);
|
||||
}
|
||||
|
||||
/**
|
||||
* Handle incoming JSON-RPC messages
|
||||
* Become a proxy to the shared daemon, spawning the daemon first if none is
|
||||
* reachable. Returns 'proxy' once the proxied session has run to completion
|
||||
* (the host disconnected), or 'fallback' if the caller should run in-process.
|
||||
*/
|
||||
private async handleMessage(message: JsonRpcRequest | JsonRpcNotification): Promise<void> {
|
||||
// Check if it's a request (has id) or notification (no id)
|
||||
const isRequest = 'id' in message;
|
||||
private async connectOrSpawnDaemon(root: string): Promise<'proxy' | 'fallback'> {
|
||||
const socketPath = getDaemonSocketPath(root);
|
||||
|
||||
switch (message.method) {
|
||||
case 'initialize':
|
||||
if (isRequest) {
|
||||
await this.handleInitialize(message as JsonRpcRequest);
|
||||
}
|
||||
break;
|
||||
// Fast path: a daemon may already be listening. On success runProxy pipes
|
||||
// stdio until the host disconnects, so a 'proxied' outcome means this
|
||||
// process has finished its entire job.
|
||||
let probe = await runProxy(socketPath);
|
||||
if (probe.outcome === 'proxied') return 'proxy';
|
||||
if (probe.reason === 'version mismatch') return 'fallback';
|
||||
|
||||
case 'initialized':
|
||||
// Notification that client has finished initialization
|
||||
// No action needed - the client is ready
|
||||
break;
|
||||
// No reachable daemon — spawn one (detached) and wait for it to bind.
|
||||
spawnDetachedDaemon(root);
|
||||
|
||||
case 'tools/list':
|
||||
if (isRequest) {
|
||||
await this.handleToolsList(message as JsonRpcRequest);
|
||||
}
|
||||
break;
|
||||
|
||||
case 'tools/call':
|
||||
if (isRequest) {
|
||||
await this.handleToolsCall(message as JsonRpcRequest);
|
||||
}
|
||||
break;
|
||||
|
||||
case 'ping':
|
||||
if (isRequest) {
|
||||
this.transport.sendResult((message as JsonRpcRequest).id, {});
|
||||
}
|
||||
break;
|
||||
|
||||
default:
|
||||
if (isRequest) {
|
||||
this.transport.sendError(
|
||||
(message as JsonRpcRequest).id,
|
||||
ErrorCodes.MethodNotFound,
|
||||
`Method not found: ${message.method}`
|
||||
);
|
||||
}
|
||||
for (let attempt = 0; attempt < DAEMON_CONNECT_MAX_RETRIES; attempt++) {
|
||||
await sleep(DAEMON_CONNECT_RETRY_DELAY_MS);
|
||||
probe = await runProxy(socketPath);
|
||||
if (probe.outcome === 'proxied') return 'proxy';
|
||||
if (probe.reason === 'version mismatch') return 'fallback';
|
||||
}
|
||||
|
||||
// Daemon never came up in time — run in-process so the user is never blocked.
|
||||
return 'fallback';
|
||||
}
|
||||
|
||||
/** Standard SIGINT/SIGTERM handlers that route to our `stop()` (direct mode). */
|
||||
private installSignalHandlers(): void {
|
||||
process.on('SIGINT', () => this.stop());
|
||||
process.on('SIGTERM', () => this.stop());
|
||||
}
|
||||
|
||||
/**
|
||||
* Handle initialize request
|
||||
* PPID watchdog (#277) — direct mode only. Daemon mode is detached on purpose
|
||||
* and reaps via idle timeout; proxy mode installs its own watchdog inside
|
||||
* {@link runProxy}. So this only ever runs for an in-process direct session.
|
||||
*/
|
||||
private async handleInitialize(request: JsonRpcRequest): Promise<void> {
|
||||
const params = request.params as {
|
||||
rootUri?: string;
|
||||
workspaceFolders?: Array<{ uri: string; name: string }>;
|
||||
capabilities?: { roots?: unknown };
|
||||
} | undefined;
|
||||
|
||||
// Does the client support the MCP `roots` protocol? If so, and we have no
|
||||
// explicit path, we ask it for the workspace root after the handshake
|
||||
// instead of falling back to the (frequently wrong) cwd. See issue #196.
|
||||
this.clientSupportsRoots = !!params?.capabilities?.roots;
|
||||
|
||||
// Explicit project signal, strongest first: a client-provided rootUri /
|
||||
// workspaceFolders (LSP-style, non-standard but some clients send it), else
|
||||
// the --path the server was launched with. cwd is NOT used here — we defer
|
||||
// it so a roots/list answer can win over it.
|
||||
let explicitPath: string | null = null;
|
||||
if (params?.rootUri) {
|
||||
explicitPath = fileUriToPath(params.rootUri);
|
||||
} else if (params?.workspaceFolders?.[0]?.uri) {
|
||||
explicitPath = fileUriToPath(params.workspaceFolders[0].uri);
|
||||
} else if (this.projectPath) {
|
||||
explicitPath = this.projectPath;
|
||||
}
|
||||
|
||||
// Respond to the handshake BEFORE doing any heavy initialization. Loading
|
||||
// the SQLite DB and the tree-sitter WASM runtime can take many seconds on
|
||||
// slow filesystems (Docker Desktop VirtioFS on macOS, WSL2). Clients like
|
||||
// Claude Code time out the handshake at ~30s, which manifested as
|
||||
// "MCP tools never appear" — the child was alive and had received the
|
||||
// initialize but was still awaiting initGrammars(). See issue #172.
|
||||
//
|
||||
// We accept the client's protocol version but respond with our supported
|
||||
// version. The `instructions` field is surfaced by MCP clients in the
|
||||
// agent's system prompt automatically — it's the right place for the
|
||||
// universal tool-selection playbook, ahead of individual tool descriptions.
|
||||
this.transport.sendResult(request.id, {
|
||||
protocolVersion: PROTOCOL_VERSION,
|
||||
capabilities: {
|
||||
tools: {},
|
||||
},
|
||||
serverInfo: SERVER_INFO,
|
||||
instructions: SERVER_INSTRUCTIONS,
|
||||
});
|
||||
|
||||
// If we know the project dir, kick off init in the background now. Tool
|
||||
// calls that arrive before it finishes fall through to `retryInitIfNeeded`,
|
||||
// which waits for this promise rather than racing it with a second open.
|
||||
//
|
||||
// If we DON'T know it (no rootUri, no --path), defer: the first tool call
|
||||
// resolves it via roots/list (when the client supports roots) or cwd. This
|
||||
// is the fix for issue #196 — clients that launch the server outside the
|
||||
// project and don't pass a rootUri previously got a misleading "not
|
||||
// initialized" error on every call.
|
||||
if (explicitPath) {
|
||||
this.initPromise = this.tryInitializeDefault(explicitPath).finally(() => {
|
||||
this.initPromise = null;
|
||||
});
|
||||
}
|
||||
private installPpidWatchdog(): void {
|
||||
if (this.mode !== 'direct') return;
|
||||
const pollMs = parsePpidPollMs(process.env.CODEGRAPH_PPID_POLL_MS);
|
||||
if (pollMs <= 0) return;
|
||||
this.ppidWatchdog = setInterval(() => {
|
||||
const current = process.ppid;
|
||||
const ppidChanged = current !== this.originalPpid;
|
||||
const hostGone = this.hostPpid !== null && !isProcessAlive(this.hostPpid);
|
||||
if (ppidChanged || hostGone) {
|
||||
const reason = ppidChanged
|
||||
? `ppid ${this.originalPpid} -> ${current}`
|
||||
: `host pid ${this.hostPpid} exited`;
|
||||
process.stderr.write(
|
||||
`[CodeGraph MCP] Parent process exited (${reason}); shutting down.\n`
|
||||
);
|
||||
this.stop();
|
||||
}
|
||||
}, pollMs);
|
||||
this.ppidWatchdog.unref();
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* Handle tools/list request
|
||||
*/
|
||||
private async handleToolsList(request: JsonRpcRequest): Promise<void> {
|
||||
await this.retryInitIfNeeded();
|
||||
this.transport.sendResult(request.id, {
|
||||
tools: this.toolHandler.getTools(),
|
||||
});
|
||||
}
|
||||
|
||||
/**
|
||||
* Handle tools/call request
|
||||
*/
|
||||
private async handleToolsCall(request: JsonRpcRequest): Promise<void> {
|
||||
const params = request.params as {
|
||||
name: string;
|
||||
arguments?: Record<string, unknown>;
|
||||
};
|
||||
|
||||
if (!params || !params.name) {
|
||||
this.transport.sendError(
|
||||
request.id,
|
||||
ErrorCodes.InvalidParams,
|
||||
'Missing tool name'
|
||||
);
|
||||
return;
|
||||
}
|
||||
|
||||
const toolName = params.name;
|
||||
const toolArgs = params.arguments || {};
|
||||
|
||||
// Validate tool exists
|
||||
const tool = tools.find(t => t.name === toolName);
|
||||
if (!tool) {
|
||||
this.transport.sendError(
|
||||
request.id,
|
||||
ErrorCodes.InvalidParams,
|
||||
`Unknown tool: ${toolName}`
|
||||
);
|
||||
return;
|
||||
}
|
||||
|
||||
// If the default project isn't initialized yet, retry in case it was
|
||||
// initialized after the MCP server started (e.g. user ran codegraph init)
|
||||
await this.retryInitIfNeeded();
|
||||
|
||||
const result = await this.toolHandler.execute(toolName, toolArgs);
|
||||
|
||||
this.transport.sendResult(request.id, result);
|
||||
}
|
||||
function sleep(ms: number): Promise<void> {
|
||||
// Deliberately NOT unref'd. During the daemon connect/takeover retry loop we
|
||||
// may be between processes — no socket bound yet, no transport, no listener
|
||||
// pinning the event loop. An unref'd timer would let Node drain the loop and
|
||||
// exit silently before we get a chance to try again.
|
||||
return new Promise((resolve) => { setTimeout(resolve, ms); });
|
||||
}
|
||||
|
||||
// Export for use in CLI
|
||||
export { StdioTransport } from './transport';
|
||||
export { tools, ToolHandler } from './tools';
|
||||
// Surface a few daemon-mode bits for tests + diagnostics.
|
||||
export { Daemon } from './daemon';
|
||||
export { CodeGraphPackageVersion } from './version';
|
||||
|
||||
Reference in New Issue
Block a user