Files
claude-mem/scripts/debug-transcript-structure.ts
Alex Newman 68290a9121 Performance improvements: Token reduction and enhanced summaries (#101)
* refactor: Reduce continuation prompt token usage by 95 lines

Removed redundant instructions from continuation prompt that were originally
added to mitigate a session continuity issue. That issue has since been
resolved, making these detailed instructions unnecessary on every continuation.

Changes:
- Reduced continuation prompt from ~106 lines to ~11 lines (~95 line reduction)
- Changed "User's Goal:" to "Next Prompt in Session:" (more accurate framing)
- Removed redundant WHAT TO RECORD, WHEN TO SKIP, and OUTPUT FORMAT sections
- Kept concise reminder: "Continue generating observations and progress summaries..."
- Initial prompt still contains all detailed instructions

Impact:
- Significant token savings on every continuation prompt
- Faster context injection with no loss of functionality
- Instructions remain comprehensive in initial prompt

Files modified:
- src/sdk/prompts.ts (buildContinuationPrompt function)
- plugin/scripts/worker-service.cjs (compiled output)

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

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

* refactor: Enhance observation and summary prompts for clarity and token efficiency

* Enhance prompt clarity and instructions in prompts.ts

- Added a reminder to think about instructions before starting work.
- Simplified the continuation prompt instruction by removing "for this ongoing session."

* feat: Enhance settings.json with permissions and deny access to sensitive files

refactor: Remove PLAN-full-observation-display.md and PR_SUMMARY.md as they are no longer needed

chore: Delete SECURITY_SUMMARY.md since it is redundant after recent changes

fix: Update worker-service.cjs to streamline observation generation instructions

cleanup: Remove src-analysis.md and src-tree.md for a cleaner codebase

refactor: Modify prompts.ts to clarify instructions for memory processing

* refactor: Remove legacy worker service implementation

* feat: Enhance summary hook to extract last assistant message and improve logging

- Added function to extract the last assistant message from the transcript.
- Updated summary hook to include last assistant message in the summary request.
- Modified SDKSession interface to store last assistant message.
- Adjusted buildSummaryPrompt to utilize last assistant message for generating summaries.
- Updated worker service and session manager to handle last assistant message in summarize requests.
- Introduced silentDebug utility for improved logging and diagnostics throughout the summary process.

* docs: Add comprehensive implementation plan for ROI metrics feature

Added detailed implementation plan covering:
- Token usage capture from Agent SDK
- Database schema changes (migration #8)
- Discovery cost tracking per observation
- Context hook display with ROI metrics
- Testing and rollout strategy

Timeline: ~20 hours over 4 days
Goal: Empirical data for YC application amendment

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

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

* feat: Add transcript processing scripts for analysis and formatting

- Implemented `dump-transcript-readable.ts` to generate a readable markdown dump of transcripts, excluding certain entry types.
- Created `extract-rich-context-examples.ts` to extract and showcase rich context examples from transcripts, highlighting user requests and assistant reasoning.
- Developed `format-transcript-context.ts` to format transcript context into a structured markdown format for improved observation generation.
- Added `test-transcript-parser.ts` for validating data extraction from transcript JSONL files, including statistics and error reporting.
- Introduced `transcript-to-markdown.ts` for a complete representation of transcript data in markdown format, showing all context data.
- Enhanced type definitions in `transcript.ts` to support new features and ensure type safety.
- Built `transcript-parser.ts` to handle parsing of transcript JSONL files, including error handling and data extraction methods.

* Refactor hooks and SDKAgent for improved observation handling

- Updated `new-hook.ts` to clean user prompts by stripping leading slashes for better semantic clarity.
- Enhanced `save-hook.ts` to include additional tools in the SKIP_TOOLS set, preventing unnecessary observations from certain command invocations.
- Modified `prompts.ts` to change the structure of observation prompts, emphasizing the observational role and providing a detailed XML output format for observations.
- Adjusted `SDKAgent.ts` to enforce stricter tool usage restrictions, ensuring the memory agent operates solely as an observer without any tool access.

* feat: Enhance session initialization to accept user prompts and prompt numbers

- Updated `handleSessionInit` in `worker-service.ts` to extract `userPrompt` and `promptNumber` from the request body and pass them to `initializeSession`.
- Modified `initializeSession` in `SessionManager.ts` to handle optional `currentUserPrompt` and `promptNumber` parameters.
- Added logic to update the existing session's `userPrompt` and `lastPromptNumber` if a `currentUserPrompt` is provided.
- Implemented debug logging for session initialization and updates to track user prompts and prompt numbers.

---------

Co-authored-by: Claude <noreply@anthropic.com>
2025-11-13 18:22:44 -05:00

114 lines
3.8 KiB
TypeScript

#!/usr/bin/env tsx
/**
* Debug Transcript Structure
* Examines the first few entries to understand the conversation flow
*/
import { TranscriptParser } from '../src/utils/transcript-parser.js';
const transcriptPath = process.argv[2];
if (!transcriptPath) {
console.error('Usage: tsx scripts/debug-transcript-structure.ts <path-to-transcript.jsonl>');
process.exit(1);
}
const parser = new TranscriptParser(transcriptPath);
const entries = parser.getAllEntries();
console.log(`Total entries: ${entries.length}\n`);
// Count entry types
const typeCounts: Record<string, number> = {};
for (const entry of entries) {
typeCounts[entry.type] = (typeCounts[entry.type] || 0) + 1;
}
console.log('Entry types:');
for (const [type, count] of Object.entries(typeCounts)) {
console.log(` ${type}: ${count}`);
}
// Find first user and assistant entries
const firstUser = entries.find(e => e.type === 'user');
const firstAssistant = entries.find(e => e.type === 'assistant');
if (firstUser) {
const userIndex = entries.indexOf(firstUser);
console.log(`\n\n=== First User Entry (index ${userIndex}) ===`);
console.log(`Timestamp: ${firstUser.timestamp}`);
if (typeof firstUser.content === 'string') {
console.log(`Content (string): ${firstUser.content.substring(0, 200)}...`);
} else if (Array.isArray(firstUser.content)) {
console.log(`Content blocks: ${firstUser.content.length}`);
for (const block of firstUser.content) {
if (block.type === 'text') {
console.log(` - text: ${(block as any).text?.substring(0, 200)}...`);
} else {
console.log(` - ${block.type}`);
}
}
}
}
if (firstAssistant) {
const assistantIndex = entries.indexOf(firstAssistant);
console.log(`\n\n=== First Assistant Entry (index ${assistantIndex}) ===`);
console.log(`Timestamp: ${firstAssistant.timestamp}`);
if (Array.isArray(firstAssistant.content)) {
console.log(`Content blocks: ${firstAssistant.content.length}`);
for (const block of firstAssistant.content) {
if (block.type === 'text') {
console.log(` - text: ${(block as any).text?.substring(0, 200)}...`);
} else if (block.type === 'thinking') {
console.log(` - thinking: ${(block as any).thinking?.substring(0, 200)}...`);
} else if (block.type === 'tool_use') {
console.log(` - tool_use: ${(block as any).name}`);
}
}
}
}
// Find a few more user/assistant pairs
console.log('\n\n=== First 3 Conversation Exchanges ===\n');
let userCount = 0;
let assistantCount = 0;
let exchangeNum = 0;
for (const entry of entries) {
if (entry.type === 'user') {
userCount++;
if (userCount <= 3) {
exchangeNum++;
console.log(`\n--- Exchange ${exchangeNum}: USER ---`);
if (typeof entry.content === 'string') {
console.log(entry.content.substring(0, 150) + (entry.content.length > 150 ? '...' : ''));
} else if (Array.isArray(entry.content)) {
const textBlock = entry.content.find((b: any) => b.type === 'text');
if (textBlock) {
const text = (textBlock as any).text || '';
console.log(text.substring(0, 150) + (text.length > 150 ? '...' : ''));
}
}
}
} else if (entry.type === 'assistant' && userCount <= 3) {
assistantCount++;
if (Array.isArray(entry.content)) {
const textBlock = entry.content.find((b: any) => b.type === 'text');
const toolUses = entry.content.filter((b: any) => b.type === 'tool_use');
console.log(`\n--- Exchange ${exchangeNum}: ASSISTANT ---`);
if (textBlock) {
const text = (textBlock as any).text || '';
console.log(text.substring(0, 150) + (text.length > 150 ? '...' : ''));
}
if (toolUses.length > 0) {
console.log(`\nTools used: ${toolUses.map((t: any) => t.name).join(', ')}`);
}
}
}
if (userCount >= 3 && assistantCount >= 3) break;
}