Files
claude-mem/src/services/worker/SDKAgent.ts
T
Alex Newman 817b9e8f27 Improve error handling and logging across worker services (#528)
* fix: prevent memory_session_id from equaling content_session_id

The bug: memory_session_id was initialized to contentSessionId as a
"placeholder for FK purposes". This caused the SDK resume logic to
inject memory agent messages into the USER's Claude Code transcript,
corrupting their conversation history.

Root cause:
- SessionStore.createSDKSession initialized memory_session_id = contentSessionId
- SDKAgent checked memorySessionId !== contentSessionId but this check
  only worked if the session was fetched fresh from DB

The fix:
- SessionStore: Initialize memory_session_id as NULL, not contentSessionId
- SDKAgent: Simple truthy check !!session.memorySessionId (NULL = fresh start)
- Database migration: Ran UPDATE to set memory_session_id = NULL for 1807
  existing sessions that had the bug

Also adds [ALIGNMENT] logging across the session lifecycle to help debug
session continuity issues:
- Hook entry: contentSessionId + promptNumber
- DB lookup: contentSessionId → memorySessionId mapping proof
- Resume decision: shows which memorySessionId will be used for resume
- Capture: logs when memorySessionId is captured from first SDK response

UI: Added "Alignment" quick filter button in LogsModal to show only
alignment logs for debugging session continuity.

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

* refactor: improve error handling in worker-service.ts

- Fix GENERIC_CATCH anti-patterns by logging full error objects instead of just messages
- Add [ANTI-PATTERN IGNORED] markers for legitimate cases (cleanup, hot paths)
- Simplify error handling comments to be more concise
- Improve httpShutdown() error discrimination for ECONNREFUSED
- Reduce LARGE_TRY_BLOCK issues in initialization code

Part of anti-pattern cleanup plan (132 total issues)

* refactor: improve error logging in SearchManager.ts

- Pass full error objects to logger instead of just error.message
- Fixes PARTIAL_ERROR_LOGGING anti-patterns (10 instances)
- Better debugging visibility when Chroma queries fail

Part of anti-pattern cleanup (133 remaining)

* refactor: improve error logging across SessionStore and mcp-server

- SessionStore.ts: Fix error logging in column rename utility
- mcp-server.ts: Log full error objects instead of just error.message
- Improve error handling in Worker API calls and tool execution

Part of anti-pattern cleanup (133 remaining)

* Refactor hooks to streamline error handling and loading states

- Simplified error handling in useContextPreview by removing try-catch and directly checking response status.
- Refactored usePagination to eliminate try-catch, improving readability and maintaining error handling through response checks.
- Cleaned up useSSE by removing unnecessary try-catch around JSON parsing, ensuring clarity in message handling.
- Enhanced useSettings by streamlining the saving process, removing try-catch, and directly checking the result for success.

* refactor: add error handling back to SearchManager Chroma calls

- Wrap queryChroma calls in try-catch to prevent generator crashes
- Log Chroma errors as warnings and fall back gracefully
- Fixes generator failures when Chroma has issues
- Part of anti-pattern cleanup recovery

* feat: Add generator failure investigation report and observation duplication regression report

- Created a comprehensive investigation report detailing the root cause of generator failures during anti-pattern cleanup, including the impact, investigation process, and implemented fixes.
- Documented the critical regression causing observation duplication due to race conditions in the SDK agent, outlining symptoms, root cause analysis, and proposed fixes.

* fix: address PR #528 review comments - atomic cleanup and detector improvements

This commit addresses critical review feedback from PR #528:

## 1. Atomic Message Cleanup (Fix Race Condition)

**Problem**: SessionRoutes.ts generator error handler had race condition
- Queried messages then marked failed in loop
- If crash during loop → partial marking → inconsistent state

**Solution**:
- Added `markSessionMessagesFailed()` to PendingMessageStore.ts
- Single atomic UPDATE statement replaces loop
- Follows existing pattern from `resetProcessingToPending()`

**Files**:
- src/services/sqlite/PendingMessageStore.ts (new method)
- src/services/worker/http/routes/SessionRoutes.ts (use new method)

## 2. Anti-Pattern Detector Improvements

**Problem**: Detector didn't recognize logger.failure() method
- Lines 212 & 335 already included "failure"
- Lines 112-113 (PARTIAL_ERROR_LOGGING detection) did not

**Solution**: Updated regex patterns to include "failure" for consistency

**Files**:
- scripts/anti-pattern-test/detect-error-handling-antipatterns.ts

## 3. Documentation

**PR Comment**: Added clarification on memory_session_id fix location
- Points to SessionStore.ts:1155
- Explains why NULL initialization prevents message injection bug

## Review Response

Addresses "Must Address Before Merge" items from review:
 Clarified memory_session_id bug fix location (via PR comment)
 Made generator error handler message cleanup atomic
 Deferred comprehensive test suite to follow-up PR (keeps PR focused)

## Testing

- Build passes with no errors
- Anti-pattern detector runs successfully
- Atomic cleanup follows proven pattern from existing methods

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>

* fix: FOREIGN KEY constraint and missing failed_at_epoch column

Two critical bugs fixed:

1. Missing failed_at_epoch column in pending_messages table
   - Added migration 20 to create the column
   - Fixes error when trying to mark messages as failed

2. FOREIGN KEY constraint failed when storing observations
   - All three agents (SDK, Gemini, OpenRouter) were passing
     session.contentSessionId instead of session.memorySessionId
   - storeObservationsAndMarkComplete expects memorySessionId
   - Added null check and clear error message

However, observations still not saving - see investigation report.

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>

* Refactor hook input parsing to improve error handling

- Added a nested try-catch block in new-hook.ts, save-hook.ts, and summary-hook.ts to handle JSON parsing errors more gracefully.
- Replaced direct error throwing with logging of the error details using logger.error.
- Ensured that the process exits cleanly after handling input in all three hooks.

---------

Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
2026-01-03 18:51:59 -05:00

547 lines
22 KiB
TypeScript

/**
* SDKAgent: SDK query loop handler
*
* Responsibility:
* - Spawn Claude subprocess via Agent SDK
* - Run event-driven query loop (no polling)
* - Process SDK responses (observations, summaries)
* - Sync to database and Chroma
*/
import { execSync } from 'child_process';
import { homedir } from 'os';
import path from 'path';
import { DatabaseManager } from './DatabaseManager.js';
import { SessionManager } from './SessionManager.js';
import { logger } from '../../utils/logger.js';
import { parseObservations, parseSummary } from '../../sdk/parser.js';
import { buildInitPrompt, buildObservationPrompt, buildSummaryPrompt, buildContinuationPrompt } from '../../sdk/prompts.js';
import { SettingsDefaultsManager } from '../../shared/SettingsDefaultsManager.js';
import { USER_SETTINGS_PATH } from '../../shared/paths.js';
import type { ActiveSession, SDKUserMessage, PendingMessage } from '../worker-types.js';
import { ModeManager } from '../domain/ModeManager.js';
import { updateCursorContextForProject } from '../worker-service.js';
import { getWorkerPort } from '../../shared/worker-utils.js';
// Import Agent SDK (assumes it's installed)
// @ts-ignore - Agent SDK types may not be available
import { query } from '@anthropic-ai/claude-agent-sdk';
export class SDKAgent {
private dbManager: DatabaseManager;
private sessionManager: SessionManager;
constructor(dbManager: DatabaseManager, sessionManager: SessionManager) {
this.dbManager = dbManager;
this.sessionManager = sessionManager;
}
/**
* Start SDK agent for a session (event-driven, no polling)
* @param worker WorkerService reference for spinner control (optional)
*/
async startSession(session: ActiveSession, worker?: any): Promise<void> {
// Find Claude executable
const claudePath = this.findClaudeExecutable();
// Get model ID and disallowed tools
const modelId = this.getModelId();
// Memory agent is OBSERVER ONLY - no tools allowed
const disallowedTools = [
'Bash', // Prevent infinite loops
'Read', // No file reading
'Write', // No file writing
'Edit', // No file editing
'Grep', // No code searching
'Glob', // No file pattern matching
'WebFetch', // No web fetching
'WebSearch', // No web searching
'Task', // No spawning sub-agents
'NotebookEdit', // No notebook editing
'AskUserQuestion',// No asking questions
'TodoWrite' // No todo management
];
// Create message generator (event-driven)
const messageGenerator = this.createMessageGenerator(session);
// CRITICAL: Only resume if memorySessionId exists (was captured from a previous SDK response).
// memorySessionId starts as NULL and is captured on first SDK message.
// NEVER use contentSessionId for resume - that would inject messages into the user's transcript!
const hasRealMemorySessionId = !!session.memorySessionId;
logger.info('SDK', 'Starting SDK query', {
sessionDbId: session.sessionDbId,
contentSessionId: session.contentSessionId,
memorySessionId: session.memorySessionId,
hasRealMemorySessionId,
resume_parameter: hasRealMemorySessionId ? session.memorySessionId : '(none - fresh start)',
lastPromptNumber: session.lastPromptNumber
});
// SESSION ALIGNMENT LOG: Resume decision proof - show if we're resuming with correct memorySessionId
if (session.lastPromptNumber > 1) {
logger.info('SDK', `[ALIGNMENT] Resume Decision | contentSessionId=${session.contentSessionId} | memorySessionId=${session.memorySessionId} | prompt#=${session.lastPromptNumber} | hasRealMemorySessionId=${hasRealMemorySessionId} | resumeWith=${hasRealMemorySessionId ? session.memorySessionId : 'NONE (fresh SDK session)'}`);
} else {
logger.info('SDK', `[ALIGNMENT] First Prompt | contentSessionId=${session.contentSessionId} | prompt#=${session.lastPromptNumber} | Will capture memorySessionId from first SDK response`);
}
// Run Agent SDK query loop
// Only resume if we have a captured memory session ID
const queryResult = query({
prompt: messageGenerator,
options: {
model: modelId,
// Resume with captured memorySessionId (null on first prompt, real ID on subsequent)
...(hasRealMemorySessionId && { resume: session.memorySessionId }),
disallowedTools,
abortController: session.abortController,
pathToClaudeCodeExecutable: claudePath
}
});
// Process SDK messages
for await (const message of queryResult) {
// Capture memory session ID from first SDK message (any type has session_id)
// This enables resume for subsequent generator starts within the same user session
if (!session.memorySessionId && message.session_id) {
session.memorySessionId = message.session_id;
// Persist to database for cross-restart recovery
this.dbManager.getSessionStore().updateMemorySessionId(
session.sessionDbId,
message.session_id
);
logger.info('SDK', 'Captured memory session ID', {
sessionDbId: session.sessionDbId,
memorySessionId: message.session_id
});
// SESSION ALIGNMENT LOG: Memory session ID captured - now contentSessionId→memorySessionId mapping is complete
logger.info('SDK', `[ALIGNMENT] Captured | contentSessionId=${session.contentSessionId} → memorySessionId=${message.session_id} | Future prompts will resume with this ID`);
}
// Handle assistant messages
if (message.type === 'assistant') {
const content = message.message.content;
const textContent = Array.isArray(content)
? content.filter((c: any) => c.type === 'text').map((c: any) => c.text).join('\n')
: typeof content === 'string' ? content : '';
const responseSize = textContent.length;
// Capture token state BEFORE updating (for delta calculation)
const tokensBeforeResponse = session.cumulativeInputTokens + session.cumulativeOutputTokens;
// Extract and track token usage
const usage = message.message.usage;
if (usage) {
session.cumulativeInputTokens += usage.input_tokens || 0;
session.cumulativeOutputTokens += usage.output_tokens || 0;
// Cache creation counts as discovery, cache read doesn't
if (usage.cache_creation_input_tokens) {
session.cumulativeInputTokens += usage.cache_creation_input_tokens;
}
logger.debug('SDK', 'Token usage captured', {
sessionId: session.sessionDbId,
inputTokens: usage.input_tokens,
outputTokens: usage.output_tokens,
cacheCreation: usage.cache_creation_input_tokens || 0,
cacheRead: usage.cache_read_input_tokens || 0,
cumulativeInput: session.cumulativeInputTokens,
cumulativeOutput: session.cumulativeOutputTokens
});
}
// Calculate discovery tokens (delta for this response only)
const discoveryTokens = (session.cumulativeInputTokens + session.cumulativeOutputTokens) - tokensBeforeResponse;
// Process response (empty or not) and mark messages as processed
// Capture earliest timestamp BEFORE processing (will be cleared after)
const originalTimestamp = session.earliestPendingTimestamp;
if (responseSize > 0) {
const truncatedResponse = responseSize > 100
? textContent.substring(0, 100) + '...'
: textContent;
logger.dataOut('SDK', `Response received (${responseSize} chars)`, {
sessionId: session.sessionDbId,
promptNumber: session.lastPromptNumber
}, truncatedResponse);
}
// Parse and process response (even if empty) with discovery token delta and original timestamp
// Empty responses will result in empty observations array and null summary
await this.processSDKResponse(session, textContent, worker, discoveryTokens, originalTimestamp);
}
// Log result messages
if (message.type === 'result' && message.subtype === 'success') {
// Usage telemetry is captured at SDK level
}
}
// Mark session complete
const sessionDuration = Date.now() - session.startTime;
logger.success('SDK', 'Agent completed', {
sessionId: session.sessionDbId,
duration: `${(sessionDuration / 1000).toFixed(1)}s`
});
}
/**
* Create event-driven message generator (yields messages from SessionManager)
*
* CRITICAL: CONTINUATION PROMPT LOGIC
* ====================================
* This is where NEW hook's dual-purpose nature comes together:
*
* - Prompt #1 (lastPromptNumber === 1): buildInitPrompt
* - Full initialization prompt with instructions
* - Sets up the SDK agent's context
*
* - Prompt #2+ (lastPromptNumber > 1): buildContinuationPrompt
* - Continuation prompt for same session
* - Includes session context and prompt number
*
* BOTH prompts receive session.contentSessionId:
* - This comes from the hook's session_id (see new-hook.ts)
* - Same session_id used by SAVE hook to store observations
* - This is how everything stays connected in one unified session
*
* NO SESSION EXISTENCE CHECKS NEEDED:
* - SessionManager.initializeSession already fetched this from database
* - Database row was created by new-hook's createSDKSession call
* - We just use the session_id we're given - simple and reliable
*
* SHARED CONVERSATION HISTORY:
* - Each user message is added to session.conversationHistory
* - This allows provider switching (Claude→Gemini) with full context
* - SDK manages its own internal state, but we mirror it for interop
*/
private async *createMessageGenerator(session: ActiveSession): AsyncIterableIterator<SDKUserMessage> {
// Load active mode
const mode = ModeManager.getInstance().getActiveMode();
// Build initial prompt
const isInitPrompt = session.lastPromptNumber === 1;
logger.info('SDK', 'Creating message generator', {
sessionDbId: session.sessionDbId,
contentSessionId: session.contentSessionId,
lastPromptNumber: session.lastPromptNumber,
isInitPrompt,
promptType: isInitPrompt ? 'INIT' : 'CONTINUATION'
});
const initPrompt = isInitPrompt
? buildInitPrompt(session.project, session.contentSessionId, session.userPrompt, mode)
: buildContinuationPrompt(session.userPrompt, session.lastPromptNumber, session.contentSessionId, mode);
// Add to shared conversation history for provider interop
session.conversationHistory.push({ role: 'user', content: initPrompt });
// Yield initial user prompt with context (or continuation if prompt #2+)
// CRITICAL: Both paths use session.contentSessionId from the hook
yield {
type: 'user',
message: {
role: 'user',
content: initPrompt
},
session_id: session.contentSessionId,
parent_tool_use_id: null,
isSynthetic: true
};
// Consume pending messages from SessionManager (event-driven, no polling)
for await (const message of this.sessionManager.getMessageIterator(session.sessionDbId)) {
if (message.type === 'observation') {
// Update last prompt number
if (message.prompt_number !== undefined) {
session.lastPromptNumber = message.prompt_number;
}
const obsPrompt = buildObservationPrompt({
id: 0, // Not used in prompt
tool_name: message.tool_name!,
tool_input: JSON.stringify(message.tool_input),
tool_output: JSON.stringify(message.tool_response),
created_at_epoch: Date.now(),
cwd: message.cwd
});
// Add to shared conversation history for provider interop
session.conversationHistory.push({ role: 'user', content: obsPrompt });
yield {
type: 'user',
message: {
role: 'user',
content: obsPrompt
},
session_id: session.contentSessionId,
parent_tool_use_id: null,
isSynthetic: true
};
} else if (message.type === 'summarize') {
const summaryPrompt = buildSummaryPrompt({
id: session.sessionDbId,
memory_session_id: session.memorySessionId,
project: session.project,
user_prompt: session.userPrompt,
last_assistant_message: message.last_assistant_message || ''
}, mode);
// Add to shared conversation history for provider interop
session.conversationHistory.push({ role: 'user', content: summaryPrompt });
yield {
type: 'user',
message: {
role: 'user',
content: summaryPrompt
},
session_id: session.contentSessionId,
parent_tool_use_id: null,
isSynthetic: true
};
}
}
}
/**
* Process SDK response text (parse XML, save to database, sync to Chroma)
* @param discoveryTokens - Token cost for discovering this response (delta, not cumulative)
* @param originalTimestamp - Original epoch when message was queued (for backlog processing accuracy)
*
* Also captures assistant responses to shared conversation history for provider interop.
* This allows Gemini to see full context if provider is switched mid-session.
*
* CRITICAL: Uses atomic transaction to prevent observation duplication on crash recovery.
*/
private async processSDKResponse(session: ActiveSession, text: string, worker: any | undefined, discoveryTokens: number, originalTimestamp: number | null): Promise<void> {
// Add assistant response to shared conversation history for provider interop
if (text) {
session.conversationHistory.push({ role: 'assistant', content: text });
}
// Parse observations and summary
const observations = parseObservations(text, session.contentSessionId);
const summary = parseSummary(text, session.sessionDbId);
// Get the pending message ID(s) for this response
// In normal operation, this should be ONE message (FIFO processing)
// But we handle multiple for safety (in case SDK batches messages)
const pendingMessageStore = this.sessionManager.getPendingMessageStore();
const sessionStore = this.dbManager.getSessionStore();
if (session.pendingProcessingIds.size > 0) {
// ATOMIC TRANSACTION: Store observations + summary + mark message(s) complete
// This prevents duplicates if the worker crashes after storing but before marking complete
for (const messageId of session.pendingProcessingIds) {
// CRITICAL: Must use memorySessionId (not contentSessionId) for FK constraint
if (!session.memorySessionId) {
throw new Error('Cannot store observations: memorySessionId not yet captured');
}
const result = sessionStore.storeObservationsAndMarkComplete(
session.memorySessionId,
session.project,
observations,
summary || null,
messageId,
pendingMessageStore,
session.lastPromptNumber,
discoveryTokens,
originalTimestamp ?? undefined
);
// Log what was saved
logger.info('SDK', 'Observations and summary saved atomically', {
sessionId: session.sessionDbId,
messageId,
observationCount: result.observationIds.length,
hasSummary: !!result.summaryId,
atomicTransaction: true
});
// AFTER transaction commits - async operations (can fail safely without data loss)
// Sync observations to Chroma
for (let i = 0; i < observations.length; i++) {
const obsId = result.observationIds[i];
const obs = observations[i];
const chromaStart = Date.now();
this.dbManager.getChromaSync().syncObservation(
obsId,
session.contentSessionId,
session.project,
obs,
session.lastPromptNumber,
result.createdAtEpoch,
discoveryTokens
).then(() => {
const chromaDuration = Date.now() - chromaStart;
logger.debug('CHROMA', 'Observation synced', {
obsId,
duration: `${chromaDuration}ms`,
type: obs.type,
title: obs.title || '(untitled)'
});
}).catch((error) => {
logger.warn('CHROMA', 'Observation sync failed, continuing without vector search', {
obsId,
type: obs.type,
title: obs.title || '(untitled)'
}, error);
});
// Broadcast to SSE clients (for web UI)
if (worker && worker.sseBroadcaster) {
worker.sseBroadcaster.broadcast({
type: 'new_observation',
observation: {
id: obsId,
memory_session_id: session.memorySessionId,
session_id: session.contentSessionId,
type: obs.type,
title: obs.title,
subtitle: obs.subtitle,
text: obs.text || null,
narrative: obs.narrative || null,
facts: JSON.stringify(obs.facts || []),
concepts: JSON.stringify(obs.concepts || []),
files_read: JSON.stringify(obs.files || []),
files_modified: JSON.stringify([]),
project: session.project,
prompt_number: session.lastPromptNumber,
created_at_epoch: result.createdAtEpoch
}
});
}
}
// Sync summary to Chroma (if present)
if (summary && result.summaryId) {
const chromaStart = Date.now();
this.dbManager.getChromaSync().syncSummary(
result.summaryId,
session.contentSessionId,
session.project,
summary,
session.lastPromptNumber,
result.createdAtEpoch,
discoveryTokens
).then(() => {
const chromaDuration = Date.now() - chromaStart;
logger.debug('CHROMA', 'Summary synced', {
summaryId: result.summaryId,
duration: `${chromaDuration}ms`,
request: summary.request || '(no request)'
});
}).catch((error) => {
logger.warn('CHROMA', 'Summary sync failed, continuing without vector search', {
summaryId: result.summaryId,
request: summary.request || '(no request)'
}, error);
});
// Broadcast to SSE clients (for web UI)
if (worker && worker.sseBroadcaster) {
worker.sseBroadcaster.broadcast({
type: 'new_summary',
summary: {
id: result.summaryId,
session_id: session.contentSessionId,
request: summary.request,
investigated: summary.investigated,
learned: summary.learned,
completed: summary.completed,
next_steps: summary.next_steps,
notes: summary.notes,
project: session.project,
prompt_number: session.lastPromptNumber,
created_at_epoch: result.createdAtEpoch
}
});
}
// Update Cursor context file for registered projects (fire-and-forget)
updateCursorContextForProject(session.project, getWorkerPort()).catch(error => {
logger.warn('CURSOR', 'Context update failed (non-critical)', { project: session.project }, error as Error);
});
}
}
// Clear the processed message IDs
session.pendingProcessingIds.clear();
session.earliestPendingTimestamp = null;
// Clean up old processed messages (keep last 100 for UI display)
const deletedCount = pendingMessageStore.cleanupProcessed(100);
if (deletedCount > 0) {
logger.debug('SDK', 'Cleaned up old processed messages', { deletedCount });
}
// Broadcast activity status after processing (queue may have changed)
if (worker && typeof worker.broadcastProcessingStatus === 'function') {
worker.broadcastProcessingStatus();
}
}
}
// REMOVED: markMessagesProcessed() - replaced by atomic transaction in processSDKResponse()
// Messages are now marked complete atomically with observation storage to prevent duplicates
// ============================================================================
// Configuration Helpers
// ============================================================================
/**
* Find Claude executable (inline, called once per session)
*/
private findClaudeExecutable(): string {
const settings = SettingsDefaultsManager.loadFromFile(USER_SETTINGS_PATH);
// 1. Check configured path
if (settings.CLAUDE_CODE_PATH) {
// Lazy load fs to keep startup fast
const { existsSync } = require('fs');
if (!existsSync(settings.CLAUDE_CODE_PATH)) {
throw new Error(`CLAUDE_CODE_PATH is set to "${settings.CLAUDE_CODE_PATH}" but the file does not exist.`);
}
return settings.CLAUDE_CODE_PATH;
}
// 2. Try auto-detection
try {
const claudePath = execSync(
process.platform === 'win32' ? 'where claude' : 'which claude',
{ encoding: 'utf8', windowsHide: true, stdio: ['ignore', 'pipe', 'ignore'] }
).trim().split('\n')[0].trim();
if (claudePath) return claudePath;
} catch (error) {
// [ANTI-PATTERN IGNORED]: Fallback behavior - which/where failed, continue to throw clear error
logger.debug('SDK', 'Claude executable auto-detection failed', {}, error as Error);
}
throw new Error('Claude executable not found. Please either:\n1. Add "claude" to your system PATH, or\n2. Set CLAUDE_CODE_PATH in ~/.claude-mem/settings.json');
}
/**
* Get model ID from settings or environment
*/
private getModelId(): string {
const settingsPath = path.join(homedir(), '.claude-mem', 'settings.json');
const settings = SettingsDefaultsManager.loadFromFile(settingsPath);
return settings.CLAUDE_MEM_MODEL;
}
}