Files
claude-mem/scripts/dump-transcript-readable.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

100 lines
3.4 KiB
TypeScript

#!/usr/bin/env tsx
/**
* Simple 1:1 transcript dump in readable markdown format
* Shows exactly what's in the transcript, chronologically
*/
import { TranscriptParser } from '../src/utils/transcript-parser.js';
import { writeFileSync } from 'fs';
const transcriptPath = process.argv[2];
if (!transcriptPath) {
console.error('Usage: tsx scripts/dump-transcript-readable.ts <path-to-transcript.jsonl>');
process.exit(1);
}
const parser = new TranscriptParser(transcriptPath);
const entries = parser.getAllEntries();
let output = '# Transcript Dump\n\n';
output += `Total entries: ${entries.length}\n\n`;
output += '---\n\n';
let entryNum = 0;
for (const entry of entries) {
entryNum++;
// Skip file-history-snapshot and summary entries for now
if (entry.type === 'file-history-snapshot' || entry.type === 'summary') continue;
output += `## Entry ${entryNum}: ${entry.type.toUpperCase()}\n`;
output += `**Timestamp:** ${entry.timestamp}\n\n`;
if (entry.type === 'user') {
const content = entry.message.content;
if (typeof content === 'string') {
output += `**Content:**\n\`\`\`\n${content}\n\`\`\`\n\n`;
} else if (Array.isArray(content)) {
for (const block of content) {
if (block.type === 'text') {
output += `**Text:**\n\`\`\`\n${(block as any).text}\n\`\`\`\n\n`;
} else if (block.type === 'tool_result') {
output += `**Tool Result (${(block as any).tool_use_id}):**\n`;
const resultContent = (block as any).content;
if (typeof resultContent === 'string') {
const preview = resultContent.substring(0, 500);
output += `\`\`\`\n${preview}${resultContent.length > 500 ? '\n...(truncated)' : ''}\n\`\`\`\n\n`;
} else {
output += `\`\`\`json\n${JSON.stringify(resultContent, null, 2).substring(0, 500)}\n\`\`\`\n\n`;
}
}
}
}
}
if (entry.type === 'assistant') {
const content = entry.message.content;
if (Array.isArray(content)) {
for (const block of content) {
if (block.type === 'text') {
output += `**Text:**\n\`\`\`\n${(block as any).text}\n\`\`\`\n\n`;
} else if (block.type === 'thinking') {
output += `**Thinking:**\n\`\`\`\n${(block as any).thinking}\n\`\`\`\n\n`;
} else if (block.type === 'tool_use') {
const tool = block as any;
output += `**Tool Use: ${tool.name}**\n`;
output += `\`\`\`json\n${JSON.stringify(tool.input, null, 2)}\n\`\`\`\n\n`;
}
}
}
// Show token usage if available
const usage = entry.message.usage;
if (usage) {
output += `**Usage:**\n`;
output += `- Input: ${usage.input_tokens || 0}\n`;
output += `- Output: ${usage.output_tokens || 0}\n`;
output += `- Cache creation: ${usage.cache_creation_input_tokens || 0}\n`;
output += `- Cache read: ${usage.cache_read_input_tokens || 0}\n\n`;
}
}
output += '---\n\n';
// Limit to first 20 entries to keep file manageable
if (entryNum >= 20) {
output += `\n_Remaining ${entries.length - 20} entries omitted for brevity_\n`;
break;
}
}
const outputPath = '/Users/alexnewman/Scripts/claude-mem/docs/context/transcript-dump.md';
writeFileSync(outputPath, output, 'utf-8');
console.log(`\nTranscript dumped to: ${outputPath}`);
console.log(`Showing first 20 conversation entries (skipped file-history-snapshot and summary types)\n`);