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>

plugin/scripts/save-hook.js

@@ -400,4 +400,4 @@ ${e.stack}`:e.message;if(Array.isArray(e))return`[${e.length} items]`;let s=Obje
     `;try{let T=this.db.prepare(E).all(p,u,...i),g=this.db.prepare(c).all(p,u,...i),_=this.db.prepare(b).all(p,u,...i);return{observations:T,sessions:g.map(a=>({id:a.id,sdk_session_id:a.sdk_session_id,project:a.project,request:a.request,completed:a.completed,next_steps:a.next_steps,created_at:a.created_at,created_at_epoch:a.created_at_epoch})),prompts:_.map(a=>({id:a.id,claude_session_id:a.claude_session_id,project:a.project,prompt:a.prompt_text,created_at:a.created_at,created_at_epoch:a.created_at_epoch}))}}catch(T){return console.error("[SessionStore] Error querying timeline records:",T.message),{observations:[],sessions:[],prompts:[]}}}close(){this.db.close()}};function H(d,e,s){return d==="PreCompact"?e?{continue:!0,suppressOutput:!0}:{continue:!1,stopReason:s.reason||"Pre-compact operation failed",suppressOutput:!0}:d==="SessionStart"?e&&s.context?{continue:!0,suppressOutput:!0,hookSpecificOutput:{hookEventName:"SessionStart",additionalContext:s.context}}:{continue:!0,suppressOutput:!0}:d==="UserPromptSubmit"||d==="PostToolUse"?{continue:!0,suppressOutput:!0}:d==="Stop"?{continue:!0,suppressOutput:!0}:{continue:e,suppressOutput:!0,...s.reason&&!e?{stopReason:s.reason}:{}}}function f(d,e,s={}){let t=H(d,e,s);return JSON.stringify(t)}import P from"path";import{homedir as B}from"os";import{existsSync as j,readFileSync as $}from"fs";var W=100;function h(){try{let d=P.join(B(),".claude-mem","settings.json");if(j(d)){let e=JSON.parse($(d,"utf-8")),s=parseInt(e.env?.CLAUDE_MEM_WORKER_PORT,10);if(!isNaN(s))return s}}catch{}return parseInt(process.env.CLAUDE_MEM_WORKER_PORT||"37777",10)}async function G(){try{let d=h();return(await fetch(`http://127.0.0.1:${d}/health`,{signal:AbortSignal.timeout(W)})).ok}catch{return!1}}async function y(){if(await G())return;let d=h();throw new Error(`Worker service is not responding on port ${d}.
 
 If you just updated the plugin, PM2's watch mode should restart automatically.
-If the problem persists, run: pm2 restart claude-mem-worker`)}var Y=new Set(["ListMcpResourcesTool"]);async function K(d){if(!d)throw new Error("saveHook requires input");let{session_id:e,cwd:s,tool_name:t,tool_input:r,tool_response:n}=d;if(Y.has(t)){console.log(f("PostToolUse",!0));return}await y();let o=new R,i=o.createSDKSession(e,"",""),p=o.getPromptCounter(i);o.close();let u=S.formatTool(t,r),E=h();S.dataIn("HOOK",`PostToolUse: ${u}`,{sessionId:i,workerPort:E});try{let c=await fetch(`http://127.0.0.1:${E}/sessions/${i}/observations`,{method:"POST",headers:{"Content-Type":"application/json"},body:JSON.stringify({tool_name:t,tool_input:r!==void 0?JSON.stringify(r):"{}",tool_response:n!==void 0?JSON.stringify(n):"{}",prompt_number:p,cwd:s||""}),signal:AbortSignal.timeout(2e3)});if(!c.ok){let b=await c.text();throw S.failure("HOOK","Failed to send observation",{sessionId:i,status:c.status},b),new Error(`Failed to send observation to worker: ${c.status} ${b}`)}S.debug("HOOK","Observation sent successfully",{sessionId:i,toolName:t})}catch(c){throw c.cause?.code==="ECONNREFUSED"||c.name==="TimeoutError"||c.message.includes("fetch failed")?new Error("There's a problem with the worker. If you just updated, type `pm2 restart claude-mem-worker` in your terminal to continue"):c}console.log(f("PostToolUse",!0))}var L="";D.on("data",d=>L+=d);D.on("end",async()=>{let d=L?JSON.parse(L):void 0;await K(d)});
+If the problem persists, run: pm2 restart claude-mem-worker`)}var Y=new Set(["ListMcpResourcesTool","SlashCommand","Skill","TodoWrite","AskUserQuestion"]);async function K(d){if(!d)throw new Error("saveHook requires input");let{session_id:e,cwd:s,tool_name:t,tool_input:r,tool_response:n}=d;if(Y.has(t)){console.log(f("PostToolUse",!0));return}await y();let o=new R,i=o.createSDKSession(e,"",""),p=o.getPromptCounter(i);o.close();let u=S.formatTool(t,r),E=h();S.dataIn("HOOK",`PostToolUse: ${u}`,{sessionId:i,workerPort:E});try{let c=await fetch(`http://127.0.0.1:${E}/sessions/${i}/observations`,{method:"POST",headers:{"Content-Type":"application/json"},body:JSON.stringify({tool_name:t,tool_input:r!==void 0?JSON.stringify(r):"{}",tool_response:n!==void 0?JSON.stringify(n):"{}",prompt_number:p,cwd:s||""}),signal:AbortSignal.timeout(2e3)});if(!c.ok){let b=await c.text();throw S.failure("HOOK","Failed to send observation",{sessionId:i,status:c.status},b),new Error(`Failed to send observation to worker: ${c.status} ${b}`)}S.debug("HOOK","Observation sent successfully",{sessionId:i,toolName:t})}catch(c){throw c.cause?.code==="ECONNREFUSED"||c.name==="TimeoutError"||c.message.includes("fetch failed")?new Error("There's a problem with the worker. If you just updated, type `pm2 restart claude-mem-worker` in your terminal to continue"):c}console.log(f("PostToolUse",!0))}var L="";D.on("data",d=>L+=d);D.on("end",async()=>{let d=L?JSON.parse(L):void 0;await K(d)});