feat: replace WASM embeddings with persistent chroma-mcp MCP connection (#1176)

* feat: replace WASM embeddings with persistent chroma-mcp MCP connection

Replace ChromaServerManager (npx chroma run + chromadb npm + ONNX/WASM)
with ChromaMcpManager, a singleton stdio MCP client that communicates with
chroma-mcp via uvx. This eliminates native binary issues, segfaults, and
WASM embedding failures that plagued cross-platform installs.

Key changes:
- Add ChromaMcpManager: singleton MCP client with lazy connect, auto-reconnect,
  connection lock, and Zscaler SSL cert support
- Rewrite ChromaSync to use MCP tool calls instead of chromadb npm client
- Handle chroma-mcp's non-JSON responses (plain text success/error messages)
- Treat "collection already exists" as idempotent success
- Wire ChromaMcpManager into GracefulShutdown for clean subprocess teardown
- Delete ChromaServerManager (no longer needed)

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* fix: address PR review — connection guard leak, timer leak, async reset

- Clear connecting guard in finally block to prevent permanent reconnection block
- Clear timeout after successful connection to prevent timer leak
- Make reset() async to await stop() before nullifying instance
- Delete obsolete chroma-server-manager test (imports deleted class)
- Update graceful-shutdown test to use chromaMcpManager property name

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* fix: prevent chroma-mcp spawn storm — zombie cleanup, stale onclose guard, reconnect backoff

Three bugs caused chroma-mcp processes to accumulate (92+ observed):

1. Zombie on timeout: failed connections left subprocess alive because
   only the timer was cleared, not the transport. Now catch block
   explicitly closes transport+client before rethrowing.

2. Stale onclose race: old transport's onclose handler captured `this`
   and overwrote the current connection reference after reconnect,
   orphaning the new subprocess. Now guarded with reference check.

3. No backoff: every failure triggered immediate reconnect. With
   backfill doing hundreds of MCP calls, this created rapid-fire
   spawning. Added 10s backoff on both connection failure and
   unexpected process death.

Also includes ChromaSync fixes from PR review:
- queryChroma deduplication now preserves index-aligned arrays
- SQL injection guard on backfill ID exclusion lists

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>

src/services/worker-service.ts

@@ -18,7 +18,7 @@ import { HOOK_TIMEOUTS } from '../shared/hook-constants.js';
 import { SettingsDefaultsManager } from '../shared/SettingsDefaultsManager.js';
 import { getAuthMethodDescription } from '../shared/EnvManager.js';
 import { logger } from '../utils/logger.js';
-import { ChromaServerManager } from './sync/ChromaServerManager.js';
+import { ChromaMcpManager } from './sync/ChromaMcpManager.js';
 import { ChromaSync } from './sync/ChromaSync.js';
 
 // Windows: avoid repeated spawn popups when startup fails (issue #921)
@@ -166,8 +166,8 @@ export class WorkerService {
   // Route handlers
   private searchRoutes: SearchRoutes | null = null;
 
-  // Chroma server (local mode)
-  private chromaServer: ChromaServerManager | null = null;
+  // Chroma MCP manager (lazy - connects on first use)
+  private chromaMcpManager: ChromaMcpManager | null = null;
 
   // Initialization tracking
   private initializationComplete: Promise<void>;
@@ -373,31 +373,12 @@ export class WorkerService {
       const { ModeManager } = await import('./domain/ModeManager.js');
       const { SettingsDefaultsManager } = await import('../shared/SettingsDefaultsManager.js');
       const { USER_SETTINGS_PATH } = await import('../shared/paths.js');
-      const os = await import('os');
 
       const settings = SettingsDefaultsManager.loadFromFile(USER_SETTINGS_PATH);
 
-      // Start Chroma server if in local mode
-      const chromaMode = settings.CLAUDE_MEM_CHROMA_MODE || 'local';
-      if (chromaMode === 'local') {
-        logger.info('SYSTEM', 'Starting local Chroma server...');
-        this.chromaServer = ChromaServerManager.getInstance({
-          dataDir: path.join(os.homedir(), '.claude-mem', 'vector-db'),
-          host: settings.CLAUDE_MEM_CHROMA_HOST || '127.0.0.1',
-          port: parseInt(settings.CLAUDE_MEM_CHROMA_PORT || '8000', 10)
-        });
-
-        const ready = await this.chromaServer.start(60000);
-
-        if (ready) {
-          logger.success('SYSTEM', 'Chroma server ready');
-        } else {
-          logger.warn('SYSTEM', 'Chroma server failed to start - vector search disabled');
-          this.chromaServer = null;
-        }
-      } else {
-        logger.info('SYSTEM', 'Chroma remote mode - skipping local server');
-      }
+      // Initialize ChromaMcpManager (lazy - connects on first use via ChromaSync)
+      this.chromaMcpManager = ChromaMcpManager.getInstance();
+      logger.info('SYSTEM', 'ChromaMcpManager initialized (lazy - connects on first use)');
 
       const modeId = settings.CLAUDE_MEM_MODE;
       ModeManager.getInstance().loadMode(modeId);
@@ -428,7 +409,7 @@ export class WorkerService {
       logger.info('WORKER', 'SearchManager initialized and search routes registered');
 
       // Auto-backfill Chroma for all projects if out of sync with SQLite (fire-and-forget)
-      if (this.chromaServer !== null || chromaMode !== 'local') {
+      if (this.chromaMcpManager) {
         ChromaSync.backfillAllProjects().then(() => {
           logger.info('CHROMA_SYNC', 'Backfill check complete for all projects');
         }).catch(error => {
@@ -855,7 +836,7 @@ export class WorkerService {
       sessionManager: this.sessionManager,
       mcpClient: this.mcpClient,
       dbManager: this.dbManager,
-      chromaServer: this.chromaServer || undefined
+      chromaMcpManager: this.chromaMcpManager || undefined
     });
   }