chore: Bump version to 6.2.1

fix: Refresh in-memory session project when updated in database
**Problem:** - Summaries created with empty project names even after database fix - 13 summaries had empty project, couldn't appear in context-hook - In-memory sessions cached stale empty project value **Root Cause:** SessionManager caches ActiveSession objects in memory. When reusing an existing session, it never refreshed the project field from the database. Even though createSDKSession() now updates the DB with the correct project, the in-memory session.project remained empty, causing summaries to be stored with empty project. **Flow:** 1. Session created with empty project (cached in memory) 2. new-hook UPDATE fixes project in database 3. SessionManager reuses cached session (stale project="") 4. Summary stored with session.project (empty) 5. Context-hook can't find summary (WHERE project = 'claude-mem') **Solution:** When SessionManager.initializeSession() reuses an existing session, refresh the project field from the database. This ensures summaries and observations always use the latest project value. **Impact:** - Future summaries will have correct project name - Backfilled 13 historical summaries with project='claude-mem' - Context injection will now show recent summaries - Both observations AND summaries fixed 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>
2025-11-23 16:18:58 -05:00 · 2025-11-23 16:14:53 -05:00 · 2025-11-23 16:06:46 -05:00 · 2025-11-22 00:29:25 -05:00 · 2025-11-22 00:27:34 -05:00 · 2025-11-22 04:44:20 +00:00
64 changed files with 3374 additions and 909 deletions
@@ -10,7 +10,7 @@
  "plugins": [
    {
      "name": "claude-mem",
-      "version": "6.0.7",
+      "version": "6.2.1",
      "source": "./plugin",
      "description": "Persistent memory system for Claude Code - context compression across sessions"
    }
@@ -4,6 +4,188 @@ All notable changes to this project will be documented in this file.

 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/).

+## [6.2.0] - 2025-11-22
+
+## Major Features
+
+### Unified Search API (#145, #133)
+- **Vector-first search architecture**: All text queries now use ChromaDB semantic search
+- **Unified /api/search endpoint**: Single endpoint with filter parameters (type, concepts, files)
+- **ID-based fetch endpoints**: New GET /api/observation/:id, /api/session/:id, /api/prompt/:id
+- **90-day recency filter**: Automatic relevance filtering for search results
+- **Backward compatibility**: Legacy endpoints still functional, routing through unified infrastructure
+
+### Search Architecture Cleanup
+- **Removed FTS5 fallback code**: Eliminated ~300 lines of deprecated full-text search code
+- **Removed experimental contextualize endpoint**: Will be reimplemented as LLM-powered skill (see #132)
+- **Simplified mem-search skill**: Streamlined to prescriptive 3-step workflow (Search → Review IDs → Fetch by ID)
+- **Better error messages**: Clear guidance when ChromaDB/UVX unavailable
+
+## Bug Fixes
+
+### Search Improvements
+- Fixed parameter handling in searchUserPrompts method
+- Improved dual-path logic for filter-only vs text queries
+- Corrected missing debug output in search API
+
+## Documentation
+
+- Updated CLAUDE.md to reflect vector-first architecture
+- Clarified FTS5 tables maintained for backward compatibility only (removal planned for v7.0.0)
+- Enhanced mem-search skill documentation with clearer usage patterns
+- Added comprehensive test results for search functionality
+
+## Breaking Changes
+
+None - all changes maintain backward compatibility.
+
+## Installation
+
+Users with auto-update enabled will receive this update automatically. To manually update:
+
+\`\`\`bash
+# Restart Claude Code or run:
+npm run sync-marketplace
+\`\`\`
+
+## [6.1.1] - 2025-11-21
+
+## Bug Fixes
+
+### Dynamic Project Name Detection (#142)
+- Fixed hardcoded "claude-mem" project name in ChromaSync and search-server
+- Now uses `getCurrentProjectName()` to dynamically detect the project based on working directory
+- Resolves #140 where all observations were incorrectly tagged with "claude-mem"
+
+### Viewer UI Scrolling
+- Simplified overflow CSS to enable proper scrolling in viewer UI
+- Removed overcomplicated nested overflow containers
+- Fixed issue where feed content wouldn't scroll
+
+## Installation
+
+Users with auto-update enabled will receive this patch automatically. To manually update:
+
+\`\`\`bash
+# Restart Claude Code or run:
+npm run sync-marketplace
+\`\`\`
+
+## [6.1.0] - 2025-11-19
+
+## Viewer UI: Responsive Layout Improvements
+
+The viewer UI now handles narrow screens better with responsive breakpoints:
+
+- Community button relocates to sidebar below 600px width
+- Projects dropdown relocates to sidebar below 480px width
+- Sidebar constrained to 400px max width
+
+Makes the viewer usable on phones and narrow browser windows.
+
+## [6.0.9] - 2025-11-17
+
+## Queue Depth Indicator Feature
+
+Added a real-time queue depth indicator to the viewer UI that displays the count of active work items (queued + currently processing).
+
+### Features
+- Visual badge next to claude-mem logo
+- Shows count of pending messages + active SDK generators
+- Only displays when queueDepth > 0
+- Subtle pulse animation for visual feedback
+- Theme-aware styling
+- Real-time updates via SSE
+
+### Implementation
+- Backend: Added `getTotalActiveWork()` method to SessionManager
+- Backend: Updated worker-service to broadcast queueDepth via SSE
+- Frontend: Enhanced Header component to display queue bubble
+- Frontend: Updated useSSE hook to track queueDepth state
+- Frontend: Added CSS styling with pulse animation
+
+### Closes
+- #122 - Implement queue depth indicator feature
+- #96 - Add real-time queue depth indicator to viewer UI
+- #97 - Fix inconsistent queue depth calculation
+
+### Credit
+Original implementation by @thedotmack in PR #96
+Bug fix by @copilot-swe-agent in PR #97
+
+## [6.0.8] - 2025-11-17
+
+## Critical Fix
+
+This patch release fixes a critical bug where the PM2 worker process would start from the wrong directory (development folder instead of marketplace folder), causing the plugin to malfunction when installed via the marketplace.
+
+### What's Fixed
+
+- **Worker Startup Path Resolution** (`src/shared/worker-utils.ts:61`)  
+  Added `cwd: pluginRoot` option to `execSync` when starting PM2
+  
+  This ensures the worker always starts from the correct marketplace directory (`~/.claude/plugins/marketplaces/thedotmack/`), regardless of where the hook is invoked from.
+
+### Impact
+
+Users will no longer experience issues with the worker starting from the wrong location. The plugin now works correctly when installed via marketplace without manual intervention.
+
+### Verification
+
+Run `pm2 info claude-mem-worker` to verify:
+- **exec cwd** should be: `/Users/[username]/.claude/plugins/marketplaces/thedotmack`
+- **script path** should be: `/Users/[username]/.claude/plugins/marketplaces/thedotmack/plugin/scripts/worker-service.cjs`
+
+## [6.0.7] - 2025-11-17
+
+## Critical Hotfix: Database Migration Issue (#121)
+
+This is an emergency hotfix addressing a critical database migration bug that prevented claude-mem from loading for some users.
+
+### What was fixed
+
+**Issue**: Users were seeing `SqliteError: no such column: discovery_tokens` when starting Claude Code.
+
+**Root Cause**: The `ensureDiscoveryTokensColumn` migration was using version number 7, which was already taken by another migration (`removeSessionSummariesUniqueConstraint`). This duplicate version number caused migration tracking issues in databases that were upgraded through multiple versions.
+
+**Fix**: 
+- Changed migration version from 7 to 11 (next available)
+- Added explicit schema_versions check to prevent unnecessary re-runs
+- Improved error propagation and documentation
+
+### Upgrade Instructions
+
+**If you're experiencing the error:**
+
+Option 1 - Manual fix (preserves history):
+```bash
+sqlite3 ~/.claude-mem/claude-mem.db "ALTER TABLE observations ADD COLUMN discovery_tokens INTEGER DEFAULT 0; ALTER TABLE session_summaries ADD COLUMN discovery_tokens INTEGER DEFAULT 0;"
+```
+
+Option 2 - Delete and recreate (loses history):
+```bash
+rm ~/.claude-mem/claude-mem.db
+# Restart Claude Code - database will recreate with correct schema
+```
+
+Option 3 - Fresh install:
+Just upgrade to v6.0.7 and the migration will work correctly.
+
+### Changes
+
+- **Fixed**: Database migration version conflict (migration 7 → 11) (#121)
+- **Improved**: Migration error handling and schema_versions tracking
+
+### Full Changelog
+
+See [CHANGELOG.md](https://github.com/thedotmack/claude-mem/blob/main/CHANGELOG.md) for complete version history.
+
+---
+
+**Affected Users**: @liadtigloo @notmyself - this release fixes your reported issue. Please try one of the upgrade options above and let me know if the issue persists.
+
+Thanks to everyone who reported this issue with detailed error logs! 🙏
+
 ## [6.0.6] - 2025-11-17

 ## Critical Bugfix Release
@@ -1,178 +1,38 @@
+/* To @claude: be vigilant about only leaving evergreen context in this file, claude-mem handles working context separately. */
+
 # Claude-Mem: AI Development Instructions

 ## What This Project Is

 Claude-mem is a Claude Code plugin providing persistent memory across sessions. It captures tool usage, compresses observations using the Claude Agent SDK, and injects relevant context into future sessions.

-**Your Role**: You are working on the plugin itself. When users interact with Claude Code with this plugin installed, your observations get captured and become their persistent memory.
+**Current Version**: 6.2.1

-**Current Version**: 6.0.7
+## Architecture

-## IMPORTANT: Skills Are Auto-Invoked
+**5 Lifecycle Hooks**: SessionStart → UserPromptSubmit → PostToolUse → Summary → SessionEnd

-**There is no `/skill` command.** Skills auto-invoke based on description metadata matching user queries. Don't document manual invocation (e.g., "Run `/skill troubleshoot`"). Instead: "The troubleshoot skill auto-activates when issues are detected."
+**Hooks** (`src/hooks/*.ts`) - TypeScript → ESM, built to `plugin/scripts/*-hook.js`

-## Critical Architecture Knowledge
+**Worker Service** (`src/services/worker-service.ts`) - Express API on port 37777, PM2-managed, handles AI processing asynchronously

-### The Lifecycle Flow
+**Database** (`src/services/sqlite/`) - SQLite3 at `~/.claude-mem/claude-mem.db` with FTS5 full-text search

-1. **SessionStart** → smart-install.js runs first (pre-hook), then `context-hook.ts` runs
-   - Smart installer checks dependencies (cached, only runs on version changes)
-   - Starts PM2 worker if not healthy
-   - Injects context from previous sessions (configurable observation count)
+**Search Skill** (`plugin/skills/mem-search/SKILL.md`) - HTTP API for searching past work, auto-invoked when users ask about history

-2. **UserPromptSubmit** → `new-hook.ts` runs
-   - Creates session record in SQLite
-   - Saves raw user prompt for FTS5 search
+**Chroma** (`src/services/sync/ChromaSync.ts`) - Vector embeddings for semantic search

-3. **PostToolUse** → `save-hook.ts` runs
-   - Captures your tool executions
-   - Sends to worker service for AI compression
+**Viewer UI** (`src/ui/viewer/`) - React interface at http://localhost:37777, built to `plugin/ui/viewer.html`

-4. **Summary** → Summary hook generates session summaries
+## Build Commands

-5. **SessionEnd** → `cleanup-hook.ts` runs
-   - Marks session complete (graceful, not DELETE)
-   - Skips on `/clear` to preserve ongoing sessions
+**Hooks only**: `npm run build && npm run sync-marketplace`

-**Note**: smart-install.js is a pre-hook script (not a lifecycle hook). It's called before context-hook via command chaining in hooks.json and only runs when dependencies need updating.
+**Worker changes**: `npm run build && npm run sync-marketplace && npm run worker:restart`

-### Key Components
+**Skills only**: `npm run sync-marketplace`

-**Hooks** (`src/hooks/*.ts`)
- Built to `plugin/scripts/*-hook.js` (ESM format)
- Must output valid JSON to `hookSpecificOutput` field
- Called by Claude Code lifecycle events
-
-**Worker Service** (`src/services/worker-service.ts`)
- Express.js API on port 37777 (configurable via `CLAUDE_MEM_WORKER_PORT`)
- Managed by PM2 (auto-started by hooks)
- Built to `plugin/worker-service.cjs` (CJS format)
- Handles AI processing asynchronously to avoid hook timeouts
-
-**Database** (`src/services/sqlite/`)
- SQLite3 with better-sqlite3 (NOT bun:sqlite - that's legacy)
- Location: `~/.claude-mem/claude-mem.db`
- FTS5 virtual tables for full-text search
- `SessionStore` = CRUD, `SessionSearch` = FTS5 queries
-
-**Search Skill** (`plugin/skills/mem-search/SKILL.md`)
- Provides access to all search functionality via HTTP API + skill
- Auto-invoked when users ask about past work, decisions, or history
- Uses HTTP endpoints instead of MCP tools (~2,250 token savings per session)
- 10 search operations: observations, sessions, prompts, by-type, by-file, by-concept, timelines, etc.
-
-**Chroma Vector Database** (`src/services/sync/ChromaSync.ts`)
- Hybrid semantic + keyword search architecture
- Automatic vector embedding synchronization
- 90-day recency filtering for relevant results
- Combined with SQLite FTS5 for optimal search performance
-
-**Viewer UI** (`src/ui/viewer/`)
- React + TypeScript web interface accessible at http://localhost:37777
- Real-time memory stream visualization via Server-Sent Events (SSE)
- Infinite scroll pagination for observations, sessions, and user prompts
- Project filtering and settings persistence
- Built to `plugin/ui/viewer.html` (self-contained bundle via esbuild)
- Auto-reconnection and error recovery
-
-## How to Make Changes
-
-### When You Modify Hooks
-```bash
-npm run build
-npm run sync-marketplace
-```
-Changes take effect on next Claude Code session. No worker restart needed.
-
-### When You Modify Worker Service
-```bash
-npm run build
-npm run sync-marketplace
-npm run worker:restart
-```
-Must restart PM2 worker for changes to take effect.
-
-### When You Modify Search Skill
-```bash
-npm run sync-marketplace
-```
-Skill changes take effect immediately on next Claude Code session. No build or restart needed (skills are markdown).
-
-### When You Modify Viewer UI
-```bash
-npm run build
-npm run sync-marketplace
-npm run worker:restart
-```
-Changes to React components, styles, or viewer logic require rebuilding and restarting the worker. Refresh browser to see changes.
-
-### Build Pipeline
-1. `npm run build` → Compiles TypeScript, outputs to `plugin/`
-2. `npm run sync-marketplace` → Syncs to `~/.claude/plugins/marketplaces/thedotmack/`
-3. Changes are live for next session (hooks/skills) or after restart (worker)
-
-## Coding Standards
-
-**Philosophy**: Write the dumb, obvious thing first. Add complexity only when you hit the problem.
-
-**Key Principles:**
-1. **YAGNI**: Don't build it until you need it
-2. **DRY**: Extract patterns after second duplication, not before
-3. **Fail Fast**: Explicit errors beat silent failures
-4. **Simple First**: Write the obvious solution, optimize only if needed
-5. **Delete Aggressively**: Less code = fewer bugs
-
-**Common anti-patterns to avoid:**
- Ceremonial wrapper functions for constants (just export the constant)
- Unused default parameters (remove if never used)
- Magic numbers without named constants
- Silent failures instead of explicit errors
- Fragile string parsing (use structured JSON output)
- Copy-pasted promise wrappers (extract helper functions)
- Overengineered "defensive" code for problems you don't have
-
-## Common Tasks
-
-### Adding a New Hook
-1. Create `src/hooks/new-hook.ts`
-2. Add to `scripts/build-hooks.js` build list
-3. Add configuration to `plugin/hooks/hooks.json`
-4. Build and sync: `npm run build && npm run sync-marketplace`
-
-**Note**: smart-install.js is not a hook - it's a pre-hook dependency checker that runs before context-hook via command chaining.
-
-### Modifying Database Schema
-1. Update schema in `src/services/sqlite/schema.ts`
-2. Update SessionStore/SessionSearch classes
-3. Migration strategy: The plugin currently recreates on schema changes (acceptable for alpha)
-4. TODO: Add proper migrations for production
-
-### Debugging Worker Issues
-```bash
-pm2 list                    # Check worker status
-npm run worker:logs         # View logs
-npm run worker:restart      # Restart if needed
-pm2 delete claude-mem-worker # Force clean start
-```
-
-### Testing Changes Locally
-1. Make changes in `src/`
-2. `npm run build && npm run sync-marketplace`
-3. Start new Claude Code session (hooks) or restart worker (worker changes)
-4. Check `~/.claude-mem/claude-mem.db` for database state
-5. Use mem-search skill to verify behavior (auto-invoked when asking about past work)
-
-### Version Bumps
-Use the `version-bump` skill (auto-invokes when requesting version updates). It handles:
- Semantic version increments (patch/minor/major)
- Updates all version references (package.json, plugin.json, CLAUDE.md, marketplace.json)
- Creates git tags and GitHub releases
- Auto-generates CHANGELOG.md from releases
-
-## Investigation Best Practices
-
-When investigations fail persistently, use Task agents for comprehensive file analysis instead of repeated grep/search. Deploy agents to read full files and answer specific questions - more efficient than multiple rounds of searching.
+**Viewer UI**: `npm run build && npm run sync-marketplace && npm run worker:restart`

 ## Environment Variables

@@ -180,37 +40,24 @@ When investigations fail persistently, use Task agents for comprehensive file an
 - `CLAUDE_MEM_CONTEXT_OBSERVATIONS` - Observations injected at SessionStart (default: 50)
 - `CLAUDE_MEM_WORKER_PORT` - Worker service port (default: 37777)

-## Key Design Decisions
-
-### Why PM2 Instead of Direct Process
-Hooks have strict timeout limits. PM2 manages a persistent background worker, allowing AI processing to continue after hooks complete.
-
-### Why SQLite FTS5
-Enables instant full-text search across thousands of observations without external dependencies. Automatic sync triggers keep FTS5 tables synchronized.
-
-### Why Graceful Cleanup
-Changed from aggressive DELETE requests to marking sessions complete. Prevents interrupting summary generation and other async operations.
-
-### Why Smart Install Caching
-npm install is expensive (2-5s). Caching version state and only installing on changes makes SessionStart nearly instant (10ms).
-
-### Why Web-Based Viewer UI
-Real-time visibility into memory stream helps users understand what's being captured and how context is being built. SSE provides instant updates without polling. Self-contained HTML bundle (esbuild) eliminates deployment complexity - everything served from a single file.
-
 ## File Locations

-**Source**: `<project-root>/src/` - TypeScript source files
-**Built Plugin**: `<project-root>/plugin/` - Compiled JavaScript outputs
-**Installed Plugin**: `~/.claude/plugins/marketplaces/thedotmack/` - User's installed plugin location
-**Database**: `~/.claude-mem/claude-mem.db` - SQLite database with observations, sessions, summaries
-**Chroma Database**: `~/.claude-mem/chroma/` - Vector embeddings for semantic search
-**Usage Logs**: `~/.claude-mem/usage-logs/usage-YYYY-MM-DD.jsonl` - Daily API usage tracking
+- **Source**: `<project-root>/src/`
+- **Built Plugin**: `<project-root>/plugin/`
+- **Installed Plugin**: `~/.claude/plugins/marketplaces/thedotmack/`
+- **Database**: `~/.claude-mem/claude-mem.db`
+- **Chroma**: `~/.claude-mem/chroma/`
+- **Usage Logs**: `~/.claude-mem/usage-logs/usage-YYYY-MM-DD.jsonl`

 ## Quick Reference

-**Build**: `npm run build`
-**Sync**: `npm run sync-marketplace`
-**Worker Restart**: `npm run worker:restart`
-**Worker Logs**: `npm run worker:logs`
-**Usage Analysis**: `npm run usage:today`
-**Viewer UI**: http://localhost:37777 (auto-starts with worker)
+```bash
+npm run build                 # Compile TypeScript
+npm run sync-marketplace      # Copy to ~/.claude/plugins
+npm run worker:restart        # Restart PM2 worker
+npm run worker:logs           # View worker logs
+pm2 list                      # Check worker status
+pm2 delete claude-mem-worker  # Force clean start
+```
+
+**Viewer UI**: http://localhost:37777
@@ -31,16 +31,8 @@ module.exports = {
        '*.log',
        '*.db',
        '*.db-*',
-        '.git',
-        'vector-db',  // Ignore Chroma vector DB files
-        '.claude-mem' // Ignore data directory
-      ],
-      // Allow extra time for graceful shutdown (cleanup of child processes)
-      kill_timeout: 5000,
-      // Wait before restarting to allow full cleanup
-      wait_ready: true,
-      // Shutdown signal (SIGTERM for graceful shutdown)
-      kill_signal: 'SIGTERM'
+        '.git'
+      ]
    }
  ]
 };
@@ -1,12 +1,12 @@
 {
  "name": "claude-mem",
-  "version": "6.0.3",
+  "version": "6.0.9",
  "lockfileVersion": 3,
  "requires": true,
  "packages": {
    "": {
      "name": "claude-mem",
-      "version": "6.0.3",
+      "version": "6.0.9",
      "license": "AGPL-3.0",
      "dependencies": {
        "@anthropic-ai/claude-agent-sdk": "^0.1.27",
@@ -1,6 +1,6 @@
 {
  "name": "claude-mem",
-  "version": "6.0.7",
+  "version": "6.2.1",
  "description": "Memory compression system for Claude Code - persist context across sessions",
  "keywords": [
    "claude",
@@ -39,7 +39,8 @@
    "worker:start": "pm2 start ecosystem.config.cjs",
    "worker:stop": "pm2 stop claude-mem-worker",
    "worker:restart": "pm2 restart claude-mem-worker",
-    "worker:logs": "pm2 logs claude-mem-worker",
+    "worker:logs": "pm2 flush claude-mem-worker && pm2 logs claude-mem-worker --lines 100 --nostream",
+    "worker:logs:no-flush": "pm2 logs claude-mem-worker --lines 100 --nostream",
    "changelog:generate": "node scripts/generate-changelog.js",
    "usage:analyze": "node scripts/analyze-usage.js",
    "usage:today": "node scripts/analyze-usage.js $(date +%Y-%m-%d)"
@@ -1,6 +1,6 @@
 {
  "name": "claude-mem",
-  "version": "6.0.7",
+  "version": "6.2.1",
  "description": "Persistent memory system for Claude Code - seamlessly preserve context across sessions",
  "author": {
    "name": "Alex Newman"
@@ -1,7 +1,7 @@
 #!/usr/bin/env node
-import{stdin as I}from"process";import w from"better-sqlite3";import{join as E,dirname as k,basename as G}from"path";import{homedir as O}from"os";import{existsSync as K,mkdirSync as x}from"fs";import{fileURLToPath as U}from"url";function M(){return typeof __dirname<"u"?__dirname:k(U(import.meta.url))}var q=M(),m=process.env.CLAUDE_MEM_DATA_DIR||E(O(),".claude-mem"),R=process.env.CLAUDE_CONFIG_DIR||E(O(),".claude"),J=E(m,"archives"),Q=E(m,"logs"),z=E(m,"trash"),Z=E(m,"backups"),ee=E(m,"settings.json"),f=E(m,"claude-mem.db"),se=E(m,"vector-db"),te=E(R,"settings.json"),re=E(R,"commands"),ne=E(R,"CLAUDE.md");function L(c){x(c,{recursive:!0})}var h=(n=>(n[n.DEBUG=0]="DEBUG",n[n.INFO=1]="INFO",n[n.WARN=2]="WARN",n[n.ERROR=3]="ERROR",n[n.SILENT=4]="SILENT",n))(h||{}),N=class{level;useColor;constructor(){let e=process.env.CLAUDE_MEM_LOG_LEVEL?.toUpperCase()||"INFO";this.level=h[e]??1,this.useColor=process.stdout.isTTY??!1}correlationId(e,s){return`obs-${e}-${s}`}sessionId(e){return`session-${e}`}formatData(e){if(e==null)return"";if(typeof e=="string")return e;if(typeof e=="number"||typeof e=="boolean")return e.toString();if(typeof e=="object"){if(e instanceof Error)return this.level===0?`${e.message}
+import{stdin as I}from"process";import w from"better-sqlite3";import{join as m,dirname as k,basename as W}from"path";import{homedir as O}from"os";import{existsSync as K,mkdirSync as x}from"fs";import{fileURLToPath as U}from"url";function M(){return typeof __dirname<"u"?__dirname:k(U(import.meta.url))}var q=M(),E=process.env.CLAUDE_MEM_DATA_DIR||m(O(),".claude-mem"),R=process.env.CLAUDE_CONFIG_DIR||m(O(),".claude"),J=m(E,"archives"),Q=m(E,"logs"),z=m(E,"trash"),Z=m(E,"backups"),ee=m(E,"settings.json"),f=m(E,"claude-mem.db"),se=m(E,"vector-db"),te=m(R,"settings.json"),re=m(R,"commands"),ne=m(R,"CLAUDE.md");function A(c){x(c,{recursive:!0})}var h=(n=>(n[n.DEBUG=0]="DEBUG",n[n.INFO=1]="INFO",n[n.WARN=2]="WARN",n[n.ERROR=3]="ERROR",n[n.SILENT=4]="SILENT",n))(h||{}),N=class{level;useColor;constructor(){let e=process.env.CLAUDE_MEM_LOG_LEVEL?.toUpperCase()||"INFO";this.level=h[e]??1,this.useColor=process.stdout.isTTY??!1}correlationId(e,s){return`obs-${e}-${s}`}sessionId(e){return`session-${e}`}formatData(e){if(e==null)return"";if(typeof e=="string")return e;if(typeof e=="number"||typeof e=="boolean")return e.toString();if(typeof e=="object"){if(e instanceof Error)return this.level===0?`${e.message}
 ${e.stack}`:e.message;if(Array.isArray(e))return`[${e.length} items]`;let s=Object.keys(e);return s.length===0?"{}":s.length<=3?JSON.stringify(e):`{${s.length} keys: ${s.slice(0,3).join(", ")}...}`}return String(e)}formatTool(e,s){if(!s)return e;try{let t=typeof s=="string"?JSON.parse(s):s;if(e==="Bash"&&t.command){let r=t.command.length>50?t.command.substring(0,50)+"...":t.command;return`${e}(${r})`}if(e==="Read"&&t.file_path){let r=t.file_path.split("/").pop()||t.file_path;return`${e}(${r})`}if(e==="Edit"&&t.file_path){let r=t.file_path.split("/").pop()||t.file_path;return`${e}(${r})`}if(e==="Write"&&t.file_path){let r=t.file_path.split("/").pop()||t.file_path;return`${e}(${r})`}return e}catch{return e}}log(e,s,t,r,n){if(e<this.level)return;let o=new Date().toISOString().replace("T"," ").substring(0,23),i=h[e].padEnd(5),d=s.padEnd(6),_="";r?.correlationId?_=`[${r.correlationId}] `:r?.sessionId&&(_=`[session-${r.sessionId}] `);let T="";n!=null&&(this.level===0&&typeof n=="object"?T=`
-`+JSON.stringify(n,null,2):T=" "+this.formatData(n));let u="";if(r){let{sessionId:l,sdkSessionId:S,correlationId:p,...a}=r;Object.keys(a).length>0&&(u=` {${Object.entries(a).map(([y,D])=>`${y}=${D}`).join(", ")}}`)}let b=`[${o}] [${i}] [${d}] ${_}${t}${u}${T}`;e===3?console.error(b):console.log(b)}debug(e,s,t,r){this.log(0,e,s,t,r)}info(e,s,t,r){this.log(1,e,s,t,r)}warn(e,s,t,r){this.log(2,e,s,t,r)}error(e,s,t,r){this.log(3,e,s,t,r)}dataIn(e,s,t,r){this.info(e,`\u2192 ${s}`,t,r)}dataOut(e,s,t,r){this.info(e,`\u2190 ${s}`,t,r)}success(e,s,t,r){this.info(e,`\u2713 ${s}`,t,r)}failure(e,s,t,r){this.error(e,`\u2717 ${s}`,t,r)}timing(e,s,t,r){this.info(e,`\u23F1 ${s}`,r,{duration:`${t}ms`})}},A=new N;var g=class{db;constructor(){L(m),this.db=new w(f),this.db.pragma("journal_mode = WAL"),this.db.pragma("synchronous = NORMAL"),this.db.pragma("foreign_keys = ON"),this.initializeSchema(),this.ensureWorkerPortColumn(),this.ensurePromptTrackingColumns(),this.removeSessionSummariesUniqueConstraint(),this.addObservationHierarchicalFields(),this.makeObservationsTextNullable(),this.createUserPromptsTable(),this.ensureDiscoveryTokensColumn()}initializeSchema(){try{this.db.exec(`
+`+JSON.stringify(n,null,2):T=" "+this.formatData(n));let u="";if(r){let{sessionId:l,sdkSessionId:S,correlationId:p,...a}=r;Object.keys(a).length>0&&(u=` {${Object.entries(a).map(([y,D])=>`${y}=${D}`).join(", ")}}`)}let b=`[${o}] [${i}] [${d}] ${_}${t}${u}${T}`;e===3?console.error(b):console.log(b)}debug(e,s,t,r){this.log(0,e,s,t,r)}info(e,s,t,r){this.log(1,e,s,t,r)}warn(e,s,t,r){this.log(2,e,s,t,r)}error(e,s,t,r){this.log(3,e,s,t,r)}dataIn(e,s,t,r){this.info(e,`\u2192 ${s}`,t,r)}dataOut(e,s,t,r){this.info(e,`\u2190 ${s}`,t,r)}success(e,s,t,r){this.info(e,`\u2713 ${s}`,t,r)}failure(e,s,t,r){this.error(e,`\u2717 ${s}`,t,r)}timing(e,s,t,r){this.info(e,`\u23F1 ${s}`,r,{duration:`${t}ms`})}},L=new N;var g=class{db;constructor(){A(E),this.db=new w(f),this.db.pragma("journal_mode = WAL"),this.db.pragma("synchronous = NORMAL"),this.db.pragma("foreign_keys = ON"),this.initializeSchema(),this.ensureWorkerPortColumn(),this.ensurePromptTrackingColumns(),this.removeSessionSummariesUniqueConstraint(),this.addObservationHierarchicalFields(),this.makeObservationsTextNullable(),this.createUserPromptsTable(),this.ensureDiscoveryTokensColumn()}initializeSchema(){try{this.db.exec(`
        CREATE TABLE IF NOT EXISTS schema_versions (
          id INTEGER PRIMARY KEY,
          version INTEGER UNIQUE NOT NULL,
@@ -293,13 +293,17 @@ ${e.stack}`:e.message;if(Array.isArray(e))return`[${e.length} items]`;let s=Obje
      INSERT OR IGNORE INTO sdk_sessions
      (claude_session_id, sdk_session_id, project, user_prompt, started_at, started_at_epoch, status)
      VALUES (?, ?, ?, ?, ?, ?, 'active')
-    `).run(e,e,s,t,r.toISOString(),n);return i.lastInsertRowid===0||i.changes===0?this.db.prepare(`
+    `).run(e,e,s,t,r.toISOString(),n);return i.lastInsertRowid===0||i.changes===0?(s&&s.trim()!==""&&this.db.prepare(`
+          UPDATE sdk_sessions
+          SET project = ?, user_prompt = ?
+          WHERE claude_session_id = ?
+        `).run(s,t,e),this.db.prepare(`
        SELECT id FROM sdk_sessions WHERE claude_session_id = ? LIMIT 1
-      `).get(e).id:i.lastInsertRowid}updateSDKSessionId(e,s){return this.db.prepare(`
+      `).get(e).id):i.lastInsertRowid}updateSDKSessionId(e,s){return this.db.prepare(`
      UPDATE sdk_sessions
      SET sdk_session_id = ?
      WHERE id = ? AND sdk_session_id IS NULL
-    `).run(s,e).changes===0?(A.debug("DB","sdk_session_id already set, skipping update",{sessionId:e,sdkSessionId:s}),!1):!0}setWorkerPort(e,s){this.db.prepare(`
+    `).run(s,e).changes===0?(L.debug("DB","sdk_session_id already set, skipping update",{sessionId:e,sdkSessionId:s}),!1):!0}setWorkerPort(e,s){this.db.prepare(`
      UPDATE sdk_sessions
      SET worker_port = ?
      WHERE id = ?
@@ -1,7 +1,7 @@
 #!/usr/bin/env node
-import Y from"path";import{stdin as D}from"process";import X from"better-sqlite3";import{join as m,dirname as U,basename as J}from"path";import{homedir as f}from"os";import{existsSync as ee,mkdirSync as M}from"fs";import{fileURLToPath as w}from"url";function F(){return typeof __dirname<"u"?__dirname:U(w(import.meta.url))}var te=F(),l=process.env.CLAUDE_MEM_DATA_DIR||m(f(),".claude-mem"),h=process.env.CLAUDE_CONFIG_DIR||m(f(),".claude"),re=m(l,"archives"),ne=m(l,"logs"),oe=m(l,"trash"),ie=m(l,"backups"),ae=m(l,"settings.json"),L=m(l,"claude-mem.db"),de=m(l,"vector-db"),pe=m(h,"settings.json"),ce=m(h,"commands"),_e=m(h,"CLAUDE.md");function A(d){M(d,{recursive:!0})}var N=(n=>(n[n.DEBUG=0]="DEBUG",n[n.INFO=1]="INFO",n[n.WARN=2]="WARN",n[n.ERROR=3]="ERROR",n[n.SILENT=4]="SILENT",n))(N||{}),O=class{level;useColor;constructor(){let e=process.env.CLAUDE_MEM_LOG_LEVEL?.toUpperCase()||"INFO";this.level=N[e]??1,this.useColor=process.stdout.isTTY??!1}correlationId(e,s){return`obs-${e}-${s}`}sessionId(e){return`session-${e}`}formatData(e){if(e==null)return"";if(typeof e=="string")return e;if(typeof e=="number"||typeof e=="boolean")return e.toString();if(typeof e=="object"){if(e instanceof Error)return this.level===0?`${e.message}
-${e.stack}`:e.message;if(Array.isArray(e))return`[${e.length} items]`;let s=Object.keys(e);return s.length===0?"{}":s.length<=3?JSON.stringify(e):`{${s.length} keys: ${s.slice(0,3).join(", ")}...}`}return String(e)}formatTool(e,s){if(!s)return e;try{let t=typeof s=="string"?JSON.parse(s):s;if(e==="Bash"&&t.command){let r=t.command.length>50?t.command.substring(0,50)+"...":t.command;return`${e}(${r})`}if(e==="Read"&&t.file_path){let r=t.file_path.split("/").pop()||t.file_path;return`${e}(${r})`}if(e==="Edit"&&t.file_path){let r=t.file_path.split("/").pop()||t.file_path;return`${e}(${r})`}if(e==="Write"&&t.file_path){let r=t.file_path.split("/").pop()||t.file_path;return`${e}(${r})`}return e}catch{return e}}log(e,s,t,r,n){if(e<this.level)return;let o=new Date().toISOString().replace("T"," ").substring(0,23),i=N[e].padEnd(5),p=s.padEnd(6),u="";r?.correlationId?u=`[${r.correlationId}] `:r?.sessionId&&(u=`[session-${r.sessionId}] `);let c="";n!=null&&(this.level===0&&typeof n=="object"?c=`
-`+JSON.stringify(n,null,2):c=" "+this.formatData(n));let E="";if(r){let{sessionId:T,sdkSessionId:S,correlationId:_,...a}=r;Object.keys(a).length>0&&(E=` {${Object.entries(a).map(([k,x])=>`${k}=${x}`).join(", ")}}`)}let b=`[${o}] [${i}] [${p}] ${u}${t}${E}${c}`;e===3?console.error(b):console.log(b)}debug(e,s,t,r){this.log(0,e,s,t,r)}info(e,s,t,r){this.log(1,e,s,t,r)}warn(e,s,t,r){this.log(2,e,s,t,r)}error(e,s,t,r){this.log(3,e,s,t,r)}dataIn(e,s,t,r){this.info(e,`\u2192 ${s}`,t,r)}dataOut(e,s,t,r){this.info(e,`\u2190 ${s}`,t,r)}success(e,s,t,r){this.info(e,`\u2713 ${s}`,t,r)}failure(e,s,t,r){this.error(e,`\u2717 ${s}`,t,r)}timing(e,s,t,r){this.info(e,`\u23F1 ${s}`,r,{duration:`${t}ms`})}},v=new O;var R=class{db;constructor(){A(l),this.db=new X(L),this.db.pragma("journal_mode = WAL"),this.db.pragma("synchronous = NORMAL"),this.db.pragma("foreign_keys = ON"),this.initializeSchema(),this.ensureWorkerPortColumn(),this.ensurePromptTrackingColumns(),this.removeSessionSummariesUniqueConstraint(),this.addObservationHierarchicalFields(),this.makeObservationsTextNullable(),this.createUserPromptsTable(),this.ensureDiscoveryTokensColumn()}initializeSchema(){try{this.db.exec(`
+import re from"path";import{stdin as M}from"process";import W from"better-sqlite3";import{join as m,dirname as P,basename as ae}from"path";import{homedir as L}from"os";import{existsSync as _e,mkdirSync as H}from"fs";import{fileURLToPath as B}from"url";function $(){return typeof __dirname<"u"?__dirname:P(B(import.meta.url))}var j=$(),l=process.env.CLAUDE_MEM_DATA_DIR||m(L(),".claude-mem"),h=process.env.CLAUDE_CONFIG_DIR||m(L(),".claude"),me=m(l,"archives"),Ee=m(l,"logs"),le=m(l,"trash"),Te=m(l,"backups"),be=m(l,"settings.json"),A=m(l,"claude-mem.db"),Se=m(l,"vector-db"),ge=m(h,"settings.json"),Re=m(h,"commands"),he=m(h,"CLAUDE.md");function y(a){H(a,{recursive:!0})}function v(){return m(j,"..","..")}var N=(n=>(n[n.DEBUG=0]="DEBUG",n[n.INFO=1]="INFO",n[n.WARN=2]="WARN",n[n.ERROR=3]="ERROR",n[n.SILENT=4]="SILENT",n))(N||{}),f=class{level;useColor;constructor(){let e=process.env.CLAUDE_MEM_LOG_LEVEL?.toUpperCase()||"INFO";this.level=N[e]??1,this.useColor=process.stdout.isTTY??!1}correlationId(e,s){return`obs-${e}-${s}`}sessionId(e){return`session-${e}`}formatData(e){if(e==null)return"";if(typeof e=="string")return e;if(typeof e=="number"||typeof e=="boolean")return e.toString();if(typeof e=="object"){if(e instanceof Error)return this.level===0?`${e.message}
+${e.stack}`:e.message;if(Array.isArray(e))return`[${e.length} items]`;let s=Object.keys(e);return s.length===0?"{}":s.length<=3?JSON.stringify(e):`{${s.length} keys: ${s.slice(0,3).join(", ")}...}`}return String(e)}formatTool(e,s){if(!s)return e;try{let t=typeof s=="string"?JSON.parse(s):s;if(e==="Bash"&&t.command){let r=t.command.length>50?t.command.substring(0,50)+"...":t.command;return`${e}(${r})`}if(e==="Read"&&t.file_path){let r=t.file_path.split("/").pop()||t.file_path;return`${e}(${r})`}if(e==="Edit"&&t.file_path){let r=t.file_path.split("/").pop()||t.file_path;return`${e}(${r})`}if(e==="Write"&&t.file_path){let r=t.file_path.split("/").pop()||t.file_path;return`${e}(${r})`}return e}catch{return e}}log(e,s,t,r,n){if(e<this.level)return;let i=new Date().toISOString().replace("T"," ").substring(0,23),o=N[e].padEnd(5),p=s.padEnd(6),_="";r?.correlationId?_=`[${r.correlationId}] `:r?.sessionId&&(_=`[session-${r.sessionId}] `);let c="";n!=null&&(this.level===0&&typeof n=="object"?c=`
+`+JSON.stringify(n,null,2):c=" "+this.formatData(n));let E="";if(r){let{sessionId:T,sdkSessionId:S,correlationId:u,...d}=r;Object.keys(d).length>0&&(E=` {${Object.entries(d).map(([F,X])=>`${F}=${X}`).join(", ")}}`)}let b=`[${i}] [${o}] [${p}] ${_}${t}${E}${c}`;e===3?console.error(b):console.log(b)}debug(e,s,t,r){this.log(0,e,s,t,r)}info(e,s,t,r){this.log(1,e,s,t,r)}warn(e,s,t,r){this.log(2,e,s,t,r)}error(e,s,t,r){this.log(3,e,s,t,r)}dataIn(e,s,t,r){this.info(e,`\u2192 ${s}`,t,r)}dataOut(e,s,t,r){this.info(e,`\u2190 ${s}`,t,r)}success(e,s,t,r){this.info(e,`\u2713 ${s}`,t,r)}failure(e,s,t,r){this.error(e,`\u2717 ${s}`,t,r)}timing(e,s,t,r){this.info(e,`\u23F1 ${s}`,r,{duration:`${t}ms`})}},C=new f;var g=class{db;constructor(){y(l),this.db=new W(A),this.db.pragma("journal_mode = WAL"),this.db.pragma("synchronous = NORMAL"),this.db.pragma("foreign_keys = ON"),this.initializeSchema(),this.ensureWorkerPortColumn(),this.ensurePromptTrackingColumns(),this.removeSessionSummariesUniqueConstraint(),this.addObservationHierarchicalFields(),this.makeObservationsTextNullable(),this.createUserPromptsTable(),this.ensureDiscoveryTokensColumn()}initializeSchema(){try{this.db.exec(`
        CREATE TABLE IF NOT EXISTS schema_versions (
          id INTEGER PRIMARY KEY,
          version INTEGER UNIQUE NOT NULL,
@@ -166,7 +166,7 @@ ${e.stack}`:e.message;if(Array.isArray(e))return`[${e.length} items]`;let s=Obje
            INSERT INTO user_prompts_fts(rowid, prompt_text)
            VALUES (new.id, new.prompt_text);
          END;
-        `),this.db.exec("COMMIT"),this.db.prepare("INSERT OR IGNORE INTO schema_versions (version, applied_at) VALUES (?, ?)").run(10,new Date().toISOString()),console.error("[SessionStore] Successfully created user_prompts table with FTS5 support")}catch(t){throw this.db.exec("ROLLBACK"),t}}catch(e){console.error("[SessionStore] Migration error (create user_prompts table):",e.message)}}ensureDiscoveryTokensColumn(){try{if(this.db.prepare("SELECT version FROM schema_versions WHERE version = ?").get(11))return;this.db.pragma("table_info(observations)").some(o=>o.name==="discovery_tokens")||(this.db.exec("ALTER TABLE observations ADD COLUMN discovery_tokens INTEGER DEFAULT 0"),console.error("[SessionStore] Added discovery_tokens column to observations table")),this.db.pragma("table_info(session_summaries)").some(o=>o.name==="discovery_tokens")||(this.db.exec("ALTER TABLE session_summaries ADD COLUMN discovery_tokens INTEGER DEFAULT 0"),console.error("[SessionStore] Added discovery_tokens column to session_summaries table")),this.db.prepare("INSERT OR IGNORE INTO schema_versions (version, applied_at) VALUES (?, ?)").run(11,new Date().toISOString())}catch(e){throw console.error("[SessionStore] Discovery tokens migration error:",e.message),e}}getRecentSummaries(e,s=10){return this.db.prepare(`
+        `),this.db.exec("COMMIT"),this.db.prepare("INSERT OR IGNORE INTO schema_versions (version, applied_at) VALUES (?, ?)").run(10,new Date().toISOString()),console.error("[SessionStore] Successfully created user_prompts table with FTS5 support")}catch(t){throw this.db.exec("ROLLBACK"),t}}catch(e){console.error("[SessionStore] Migration error (create user_prompts table):",e.message)}}ensureDiscoveryTokensColumn(){try{if(this.db.prepare("SELECT version FROM schema_versions WHERE version = ?").get(11))return;this.db.pragma("table_info(observations)").some(i=>i.name==="discovery_tokens")||(this.db.exec("ALTER TABLE observations ADD COLUMN discovery_tokens INTEGER DEFAULT 0"),console.error("[SessionStore] Added discovery_tokens column to observations table")),this.db.pragma("table_info(session_summaries)").some(i=>i.name==="discovery_tokens")||(this.db.exec("ALTER TABLE session_summaries ADD COLUMN discovery_tokens INTEGER DEFAULT 0"),console.error("[SessionStore] Added discovery_tokens column to session_summaries table")),this.db.prepare("INSERT OR IGNORE INTO schema_versions (version, applied_at) VALUES (?, ?)").run(11,new Date().toISOString())}catch(e){throw console.error("[SessionStore] Discovery tokens migration error:",e.message),e}}getRecentSummaries(e,s=10){return this.db.prepare(`
      SELECT
        request, investigated, learned, completed, next_steps,
        files_read, files_edited, notes, prompt_number, created_at
@@ -244,12 +244,12 @@ ${e.stack}`:e.message;if(Array.isArray(e))return`[${e.length} items]`;let s=Obje
      SELECT *
      FROM observations
      WHERE id = ?
-    `).get(e)||null}getObservationsByIds(e,s={}){if(e.length===0)return[];let{orderBy:t="date_desc",limit:r}=s,n=t==="date_asc"?"ASC":"DESC",o=r?`LIMIT ${r}`:"",i=e.map(()=>"?").join(",");return this.db.prepare(`
+    `).get(e)||null}getObservationsByIds(e,s={}){if(e.length===0)return[];let{orderBy:t="date_desc",limit:r}=s,n=t==="date_asc"?"ASC":"DESC",i=r?`LIMIT ${r}`:"",o=e.map(()=>"?").join(",");return this.db.prepare(`
      SELECT *
      FROM observations
-      WHERE id IN (${i})
+      WHERE id IN (${o})
      ORDER BY created_at_epoch ${n}
-      ${o}
+      ${i}
    `).all(...e)}getSummaryForSession(e){return this.db.prepare(`
      SELECT
        request, investigated, learned, completed, next_steps,
@@ -262,7 +262,7 @@ ${e.stack}`:e.message;if(Array.isArray(e))return`[${e.length} items]`;let s=Obje
      SELECT files_read, files_modified
      FROM observations
      WHERE sdk_session_id = ?
-    `).all(e),r=new Set,n=new Set;for(let o of t){if(o.files_read)try{let i=JSON.parse(o.files_read);Array.isArray(i)&&i.forEach(p=>r.add(p))}catch{}if(o.files_modified)try{let i=JSON.parse(o.files_modified);Array.isArray(i)&&i.forEach(p=>n.add(p))}catch{}}return{filesRead:Array.from(r),filesModified:Array.from(n)}}getSessionById(e){return this.db.prepare(`
+    `).all(e),r=new Set,n=new Set;for(let i of t){if(i.files_read)try{let o=JSON.parse(i.files_read);Array.isArray(o)&&o.forEach(p=>r.add(p))}catch{}if(i.files_modified)try{let o=JSON.parse(i.files_modified);Array.isArray(o)&&o.forEach(p=>n.add(p))}catch{}}return{filesRead:Array.from(r),filesModified:Array.from(n)}}getSessionById(e){return this.db.prepare(`
      SELECT id, claude_session_id, sdk_session_id, project, user_prompt
      FROM sdk_sessions
      WHERE id = ?
@@ -289,17 +289,21 @@ ${e.stack}`:e.message;if(Array.isArray(e))return`[${e.length} items]`;let s=Obje
      SELECT prompt_counter FROM sdk_sessions WHERE id = ?
    `).get(e)?.prompt_counter||1}getPromptCounter(e){return this.db.prepare(`
      SELECT prompt_counter FROM sdk_sessions WHERE id = ?
-    `).get(e)?.prompt_counter||0}createSDKSession(e,s,t){let r=new Date,n=r.getTime(),i=this.db.prepare(`
+    `).get(e)?.prompt_counter||0}createSDKSession(e,s,t){let r=new Date,n=r.getTime(),o=this.db.prepare(`
      INSERT OR IGNORE INTO sdk_sessions
      (claude_session_id, sdk_session_id, project, user_prompt, started_at, started_at_epoch, status)
      VALUES (?, ?, ?, ?, ?, ?, 'active')
-    `).run(e,e,s,t,r.toISOString(),n);return i.lastInsertRowid===0||i.changes===0?this.db.prepare(`
+    `).run(e,e,s,t,r.toISOString(),n);return o.lastInsertRowid===0||o.changes===0?(s&&s.trim()!==""&&this.db.prepare(`
+          UPDATE sdk_sessions
+          SET project = ?, user_prompt = ?
+          WHERE claude_session_id = ?
+        `).run(s,t,e),this.db.prepare(`
        SELECT id FROM sdk_sessions WHERE claude_session_id = ? LIMIT 1
-      `).get(e).id:i.lastInsertRowid}updateSDKSessionId(e,s){return this.db.prepare(`
+      `).get(e).id):o.lastInsertRowid}updateSDKSessionId(e,s){return this.db.prepare(`
      UPDATE sdk_sessions
      SET sdk_session_id = ?
      WHERE id = ? AND sdk_session_id IS NULL
-    `).run(s,e).changes===0?(v.debug("DB","sdk_session_id already set, skipping update",{sessionId:e,sdkSessionId:s}),!1):!0}setWorkerPort(e,s){this.db.prepare(`
+    `).run(s,e).changes===0?(C.debug("DB","sdk_session_id already set, skipping update",{sessionId:e,sdkSessionId:s}),!1):!0}setWorkerPort(e,s){this.db.prepare(`
      UPDATE sdk_sessions
      SET worker_port = ?
      WHERE id = ?
@@ -312,29 +316,29 @@ ${e.stack}`:e.message;if(Array.isArray(e))return`[${e.length} items]`;let s=Obje
      INSERT INTO user_prompts
      (claude_session_id, prompt_number, prompt_text, created_at, created_at_epoch)
      VALUES (?, ?, ?, ?, ?)
-    `).run(e,s,t,r.toISOString(),n).lastInsertRowid}storeObservation(e,s,t,r,n=0){let o=new Date,i=o.getTime();this.db.prepare(`
+    `).run(e,s,t,r.toISOString(),n).lastInsertRowid}storeObservation(e,s,t,r,n=0){let i=new Date,o=i.getTime();this.db.prepare(`
      SELECT id FROM sdk_sessions WHERE sdk_session_id = ?
    `).get(e)||(this.db.prepare(`
        INSERT INTO sdk_sessions
        (claude_session_id, sdk_session_id, project, started_at, started_at_epoch, status)
        VALUES (?, ?, ?, ?, ?, 'active')
-      `).run(e,e,s,o.toISOString(),i),console.error(`[SessionStore] Auto-created session record for session_id: ${e}`));let E=this.db.prepare(`
+      `).run(e,e,s,i.toISOString(),o),console.error(`[SessionStore] Auto-created session record for session_id: ${e}`));let E=this.db.prepare(`
      INSERT INTO observations
      (sdk_session_id, project, type, title, subtitle, facts, narrative, concepts,
       files_read, files_modified, prompt_number, discovery_tokens, created_at, created_at_epoch)
      VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?)
-    `).run(e,s,t.type,t.title,t.subtitle,JSON.stringify(t.facts),t.narrative,JSON.stringify(t.concepts),JSON.stringify(t.files_read),JSON.stringify(t.files_modified),r||null,n,o.toISOString(),i);return{id:Number(E.lastInsertRowid),createdAtEpoch:i}}storeSummary(e,s,t,r,n=0){let o=new Date,i=o.getTime();this.db.prepare(`
+    `).run(e,s,t.type,t.title,t.subtitle,JSON.stringify(t.facts),t.narrative,JSON.stringify(t.concepts),JSON.stringify(t.files_read),JSON.stringify(t.files_modified),r||null,n,i.toISOString(),o);return{id:Number(E.lastInsertRowid),createdAtEpoch:o}}storeSummary(e,s,t,r,n=0){let i=new Date,o=i.getTime();this.db.prepare(`
      SELECT id FROM sdk_sessions WHERE sdk_session_id = ?
    `).get(e)||(this.db.prepare(`
        INSERT INTO sdk_sessions
        (claude_session_id, sdk_session_id, project, started_at, started_at_epoch, status)
        VALUES (?, ?, ?, ?, ?, 'active')
-      `).run(e,e,s,o.toISOString(),i),console.error(`[SessionStore] Auto-created session record for session_id: ${e}`));let E=this.db.prepare(`
+      `).run(e,e,s,i.toISOString(),o),console.error(`[SessionStore] Auto-created session record for session_id: ${e}`));let E=this.db.prepare(`
      INSERT INTO session_summaries
      (sdk_session_id, project, request, investigated, learned, completed,
       next_steps, notes, prompt_number, discovery_tokens, created_at, created_at_epoch)
      VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?)
-    `).run(e,s,t.request,t.investigated,t.learned,t.completed,t.next_steps,t.notes,r||null,n,o.toISOString(),i);return{id:Number(E.lastInsertRowid),createdAtEpoch:i}}markSessionCompleted(e){let s=new Date,t=s.getTime();this.db.prepare(`
+    `).run(e,s,t.request,t.investigated,t.learned,t.completed,t.next_steps,t.notes,r||null,n,i.toISOString(),o);return{id:Number(E.lastInsertRowid),createdAtEpoch:o}}markSessionCompleted(e){let s=new Date,t=s.getTime();this.db.prepare(`
      UPDATE sdk_sessions
      SET status = 'completed', completed_at = ?, completed_at_epoch = ?
      WHERE id = ?
@@ -342,62 +346,64 @@ ${e.stack}`:e.message;if(Array.isArray(e))return`[${e.length} items]`;let s=Obje
      UPDATE sdk_sessions
      SET status = 'failed', completed_at = ?, completed_at_epoch = ?
      WHERE id = ?
-    `).run(s.toISOString(),t,e)}getSessionSummariesByIds(e,s={}){if(e.length===0)return[];let{orderBy:t="date_desc",limit:r}=s,n=t==="date_asc"?"ASC":"DESC",o=r?`LIMIT ${r}`:"",i=e.map(()=>"?").join(",");return this.db.prepare(`
+    `).run(s.toISOString(),t,e)}getSessionSummariesByIds(e,s={}){if(e.length===0)return[];let{orderBy:t="date_desc",limit:r}=s,n=t==="date_asc"?"ASC":"DESC",i=r?`LIMIT ${r}`:"",o=e.map(()=>"?").join(",");return this.db.prepare(`
      SELECT * FROM session_summaries
-      WHERE id IN (${i})
+      WHERE id IN (${o})
      ORDER BY created_at_epoch ${n}
-      ${o}
-    `).all(...e)}getUserPromptsByIds(e,s={}){if(e.length===0)return[];let{orderBy:t="date_desc",limit:r}=s,n=t==="date_asc"?"ASC":"DESC",o=r?`LIMIT ${r}`:"",i=e.map(()=>"?").join(",");return this.db.prepare(`
+      ${i}
+    `).all(...e)}getUserPromptsByIds(e,s={}){if(e.length===0)return[];let{orderBy:t="date_desc",limit:r}=s,n=t==="date_asc"?"ASC":"DESC",i=r?`LIMIT ${r}`:"",o=e.map(()=>"?").join(",");return this.db.prepare(`
      SELECT
        up.*,
        s.project,
        s.sdk_session_id
      FROM user_prompts up
      JOIN sdk_sessions s ON up.claude_session_id = s.claude_session_id
-      WHERE up.id IN (${i})
+      WHERE up.id IN (${o})
      ORDER BY up.created_at_epoch ${n}
-      ${o}
-    `).all(...e)}getTimelineAroundTimestamp(e,s=10,t=10,r){return this.getTimelineAroundObservation(null,e,s,t,r)}getTimelineAroundObservation(e,s,t=10,r=10,n){let o=n?"AND project = ?":"",i=n?[n]:[],p,u;if(e!==null){let T=`
+      ${i}
+    `).all(...e)}getTimelineAroundTimestamp(e,s=10,t=10,r){return this.getTimelineAroundObservation(null,e,s,t,r)}getTimelineAroundObservation(e,s,t=10,r=10,n){let i=n?"AND project = ?":"",o=n?[n]:[],p,_;if(e!==null){let T=`
        SELECT id, created_at_epoch
        FROM observations
-        WHERE id <= ? ${o}
+        WHERE id <= ? ${i}
        ORDER BY id DESC
        LIMIT ?
      `,S=`
        SELECT id, created_at_epoch
        FROM observations
-        WHERE id >= ? ${o}
+        WHERE id >= ? ${i}
        ORDER BY id ASC
        LIMIT ?
-      `;try{let _=this.db.prepare(T).all(e,...i,t+1),a=this.db.prepare(S).all(e,...i,r+1);if(_.length===0&&a.length===0)return{observations:[],sessions:[],prompts:[]};p=_.length>0?_[_.length-1].created_at_epoch:s,u=a.length>0?a[a.length-1].created_at_epoch:s}catch(_){return console.error("[SessionStore] Error getting boundary observations:",_.message),{observations:[],sessions:[],prompts:[]}}}else{let T=`
+      `;try{let u=this.db.prepare(T).all(e,...o,t+1),d=this.db.prepare(S).all(e,...o,r+1);if(u.length===0&&d.length===0)return{observations:[],sessions:[],prompts:[]};p=u.length>0?u[u.length-1].created_at_epoch:s,_=d.length>0?d[d.length-1].created_at_epoch:s}catch(u){return console.error("[SessionStore] Error getting boundary observations:",u.message),{observations:[],sessions:[],prompts:[]}}}else{let T=`
        SELECT created_at_epoch
        FROM observations
-        WHERE created_at_epoch <= ? ${o}
+        WHERE created_at_epoch <= ? ${i}
        ORDER BY created_at_epoch DESC
        LIMIT ?
      `,S=`
        SELECT created_at_epoch
        FROM observations
-        WHERE created_at_epoch >= ? ${o}
+        WHERE created_at_epoch >= ? ${i}
        ORDER BY created_at_epoch ASC
        LIMIT ?
-      `;try{let _=this.db.prepare(T).all(s,...i,t),a=this.db.prepare(S).all(s,...i,r+1);if(_.length===0&&a.length===0)return{observations:[],sessions:[],prompts:[]};p=_.length>0?_[_.length-1].created_at_epoch:s,u=a.length>0?a[a.length-1].created_at_epoch:s}catch(_){return console.error("[SessionStore] Error getting boundary timestamps:",_.message),{observations:[],sessions:[],prompts:[]}}}let c=`
+      `;try{let u=this.db.prepare(T).all(s,...o,t),d=this.db.prepare(S).all(s,...o,r+1);if(u.length===0&&d.length===0)return{observations:[],sessions:[],prompts:[]};p=u.length>0?u[u.length-1].created_at_epoch:s,_=d.length>0?d[d.length-1].created_at_epoch:s}catch(u){return console.error("[SessionStore] Error getting boundary timestamps:",u.message),{observations:[],sessions:[],prompts:[]}}}let c=`
      SELECT *
      FROM observations
-      WHERE created_at_epoch >= ? AND created_at_epoch <= ? ${o}
+      WHERE created_at_epoch >= ? AND created_at_epoch <= ? ${i}
      ORDER BY created_at_epoch ASC
    `,E=`
      SELECT *
      FROM session_summaries
-      WHERE created_at_epoch >= ? AND created_at_epoch <= ? ${o}
+      WHERE created_at_epoch >= ? AND created_at_epoch <= ? ${i}
      ORDER BY created_at_epoch ASC
    `,b=`
      SELECT up.*, s.project, s.sdk_session_id
      FROM user_prompts up
      JOIN sdk_sessions s ON up.claude_session_id = s.claude_session_id
-      WHERE up.created_at_epoch >= ? AND up.created_at_epoch <= ? ${o.replace("project","s.project")}
+      WHERE up.created_at_epoch >= ? AND up.created_at_epoch <= ? ${i.replace("project","s.project")}
      ORDER BY up.created_at_epoch ASC
-    `;try{let T=this.db.prepare(c).all(p,u,...i),S=this.db.prepare(E).all(p,u,...i),_=this.db.prepare(b).all(p,u,...i);return{observations:T,sessions:S.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 C(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 $}from"fs";var G=100;function g(){try{let d=P.join(B(),".claude-mem","settings.json");if(j(d)){let e=JSON.parse($(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 W(){try{let d=g();return(await fetch(`http://127.0.0.1:${d}/health`,{signal:AbortSignal.timeout(G)})).ok}catch{return!1}}async function y(){if(await W())return;let d=g();throw new Error(`Worker service is not responding on port ${d}.
+    `;try{let T=this.db.prepare(c).all(p,_,...o),S=this.db.prepare(E).all(p,_,...o),u=this.db.prepare(b).all(p,_,...o);return{observations:T,sessions:S.map(d=>({id:d.id,sdk_session_id:d.sdk_session_id,project:d.project,request:d.request,completed:d.completed,next_steps:d.next_steps,created_at:d.created_at,created_at_epoch:d.created_at_epoch})),prompts:u.map(d=>({id:d.id,claude_session_id:d.claude_session_id,project:d.project,prompt:d.prompt_text,created_at:d.created_at,created_at_epoch:d.created_at_epoch}))}}catch(T){return console.error("[SessionStore] Error querying timeline records:",T.message),{observations:[],sessions:[],prompts:[]}}}close(){this.db.close()}};function G(a,e,s){return a==="PreCompact"?e?{continue:!0,suppressOutput:!0}:{continue:!1,stopReason:s.reason||"Pre-compact operation failed",suppressOutput:!0}:a==="SessionStart"?e&&s.context?{continue:!0,suppressOutput:!0,hookSpecificOutput:{hookEventName:"SessionStart",additionalContext:s.context}}:{continue:!0,suppressOutput:!0}:a==="UserPromptSubmit"||a==="PostToolUse"?{continue:!0,suppressOutput:!0}:a==="Stop"?{continue:!0,suppressOutput:!0}:{continue:e,suppressOutput:!0,...s.reason&&!e?{stopReason:s.reason}:{}}}function D(a,e,s={}){let t=G(a,e,s);return JSON.stringify(t)}import k from"path";import{homedir as Y}from"os";import{existsSync as x,readFileSync as K}from"fs";import{execSync as V}from"child_process";var q=100,J=500,Q=10;function R(){try{let a=k.join(Y(),".claude-mem","settings.json");if(x(a)){let e=JSON.parse(K(a,"utf-8")),s=parseInt(e.env?.CLAUDE_MEM_WORKER_PORT,10);if(!isNaN(s))return s}}catch{}return parseInt(process.env.CLAUDE_MEM_WORKER_PORT||"37777",10)}async function U(){try{let a=R();return(await fetch(`http://127.0.0.1:${a}/health`,{signal:AbortSignal.timeout(q)})).ok}catch{return!1}}async function z(){try{let a=v(),e=k.join(a,"ecosystem.config.cjs");if(!x(e))throw new Error(`Ecosystem config not found at ${e}`);V(`pm2 start "${e}"`,{cwd:a,stdio:"pipe",encoding:"utf-8"});for(let s=0;s<Q;s++)if(await new Promise(t=>setTimeout(t,J)),await U())return!0;return!1}catch{return!1}}async function w(){if(await U())return;if(!await z()){let e=R();throw new Error(`Worker service failed to start on port ${e}.

-If you just updated the plugin, PM2's watch mode should restart automatically.
-If the problem persists, run: pm2 restart claude-mem-worker`)}async function K(d){if(!d)throw new Error("newHook requires input");let{session_id:e,cwd:s,prompt:t}=d,r=Y.basename(s);await y();let n=new R,o=n.createSDKSession(e,r,t),i=n.incrementPromptCounter(o);n.saveUserPrompt(e,i,t),console.error(`[new-hook] Session ${o}, prompt #${i}`),n.close();let p=g(),u=t.startsWith("/")?t.substring(1):t;try{let c=await fetch(`http://127.0.0.1:${p}/sessions/${o}/init`,{method:"POST",headers:{"Content-Type":"application/json"},body:JSON.stringify({project:r,userPrompt:u,promptNumber:i}),signal:AbortSignal.timeout(5e3)});if(!c.ok){let E=await c.text();throw new Error(`Failed to initialize session: ${c.status} ${E}`)}}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(C("UserPromptSubmit",!0))}var I="";D.on("data",d=>I+=d);D.on("end",async()=>{let d=I?JSON.parse(I):void 0;await K(d)});
+Try manually running: pm2 start ecosystem.config.cjs
+Or restart: pm2 restart claude-mem-worker`)}}import{appendFileSync as Z}from"fs";import{homedir as ee}from"os";import{join as se}from"path";var te=se(ee(),".claude-mem","silent.log");function O(a,e,s=""){let t=new Date().toISOString(),o=((new Error().stack||"").split(`
+`)[2]||"").match(/at\s+(?:.*\s+)?\(?([^:]+):(\d+):(\d+)\)?/),p=o?`${o[1].split("/").pop()}:${o[2]}`:"unknown",_=`[${t}] [${p}] ${a}`;if(e!==void 0)try{_+=` ${JSON.stringify(e)}`}catch(c){_+=` [stringify error: ${c}]`}_+=`
+`;try{Z(te,_)}catch(c){console.error("[silent-debug] Failed to write to log:",c)}return s}async function ne(a){if(!a)throw new Error("newHook requires input");let{session_id:e,cwd:s,prompt:t}=a;O("[new-hook] Input received",{session_id:e,cwd:s,cwd_type:typeof s,cwd_length:s?.length,has_cwd:!!s,prompt_length:t?.length});let r=re.basename(s);O("[new-hook] Project extracted",{project:r,project_type:typeof r,project_length:r?.length,is_empty:r==="",cwd_was:s}),await w();let n=new g,i=n.createSDKSession(e,r,t),o=n.incrementPromptCounter(i);n.saveUserPrompt(e,o,t),console.error(`[new-hook] Session ${i}, prompt #${o}`),n.close();let p=R(),_=t.startsWith("/")?t.substring(1):t;try{let c=await fetch(`http://127.0.0.1:${p}/sessions/${i}/init`,{method:"POST",headers:{"Content-Type":"application/json"},body:JSON.stringify({project:r,userPrompt:_,promptNumber:o}),signal:AbortSignal.timeout(5e3)});if(!c.ok){let E=await c.text();throw new Error(`Failed to initialize session: ${c.status} ${E}`)}}catch(c){throw c.cause?.code==="ECONNREFUSED"||c.name==="TimeoutError"||c.message.includes("fetch failed")?new Error("There's a problem with the worker. If you just updated, type `pm2 restart claude-mem-worker` in your terminal to continue"):c}console.log(D("UserPromptSubmit",!0))}var I="";M.on("data",a=>I+=a);M.on("end",async()=>{let a=I?JSON.parse(I):void 0;await ne(a)});
@@ -1,7 +1,7 @@
 #!/usr/bin/env node
-import{stdin as D}from"process";import X from"better-sqlite3";import{join as m,dirname as U,basename as J}from"path";import{homedir as A}from"os";import{existsSync as ee,mkdirSync as M}from"fs";import{fileURLToPath as w}from"url";function F(){return typeof __dirname<"u"?__dirname:U(w(import.meta.url))}var te=F(),T=process.env.CLAUDE_MEM_DATA_DIR||m(A(),".claude-mem"),N=process.env.CLAUDE_CONFIG_DIR||m(A(),".claude"),re=m(T,"archives"),oe=m(T,"logs"),ne=m(T,"trash"),ie=m(T,"backups"),ae=m(T,"settings.json"),v=m(T,"claude-mem.db"),de=m(T,"vector-db"),pe=m(N,"settings.json"),ce=m(N,"commands"),_e=m(N,"CLAUDE.md");function C(d){M(d,{recursive:!0})}var O=(o=>(o[o.DEBUG=0]="DEBUG",o[o.INFO=1]="INFO",o[o.WARN=2]="WARN",o[o.ERROR=3]="ERROR",o[o.SILENT=4]="SILENT",o))(O||{}),I=class{level;useColor;constructor(){let e=process.env.CLAUDE_MEM_LOG_LEVEL?.toUpperCase()||"INFO";this.level=O[e]??1,this.useColor=process.stdout.isTTY??!1}correlationId(e,s){return`obs-${e}-${s}`}sessionId(e){return`session-${e}`}formatData(e){if(e==null)return"";if(typeof e=="string")return e;if(typeof e=="number"||typeof e=="boolean")return e.toString();if(typeof e=="object"){if(e instanceof Error)return this.level===0?`${e.message}
+import{stdin as M}from"process";import W from"better-sqlite3";import{join as m,dirname as X,basename as te}from"path";import{homedir as A}from"os";import{existsSync as ie,mkdirSync as H}from"fs";import{fileURLToPath as P}from"url";function B(){return typeof __dirname<"u"?__dirname:X(P(import.meta.url))}var j=B(),T=process.env.CLAUDE_MEM_DATA_DIR||m(A(),".claude-mem"),N=process.env.CLAUDE_CONFIG_DIR||m(A(),".claude"),de=m(T,"archives"),pe=m(T,"logs"),ce=m(T,"trash"),_e=m(T,"backups"),ue=m(T,"settings.json"),v=m(T,"claude-mem.db"),me=m(T,"vector-db"),Ee=m(N,"settings.json"),le=m(N,"commands"),Te=m(N,"CLAUDE.md");function y(a){H(a,{recursive:!0})}function C(){return m(j,"..","..")}var O=(o=>(o[o.DEBUG=0]="DEBUG",o[o.INFO=1]="INFO",o[o.WARN=2]="WARN",o[o.ERROR=3]="ERROR",o[o.SILENT=4]="SILENT",o))(O||{}),f=class{level;useColor;constructor(){let e=process.env.CLAUDE_MEM_LOG_LEVEL?.toUpperCase()||"INFO";this.level=O[e]??1,this.useColor=process.stdout.isTTY??!1}correlationId(e,s){return`obs-${e}-${s}`}sessionId(e){return`session-${e}`}formatData(e){if(e==null)return"";if(typeof e=="string")return e;if(typeof e=="number"||typeof e=="boolean")return e.toString();if(typeof e=="object"){if(e instanceof Error)return this.level===0?`${e.message}
 ${e.stack}`:e.message;if(Array.isArray(e))return`[${e.length} items]`;let s=Object.keys(e);return s.length===0?"{}":s.length<=3?JSON.stringify(e):`{${s.length} keys: ${s.slice(0,3).join(", ")}...}`}return String(e)}formatTool(e,s){if(!s)return e;try{let t=typeof s=="string"?JSON.parse(s):s;if(e==="Bash"&&t.command){let r=t.command.length>50?t.command.substring(0,50)+"...":t.command;return`${e}(${r})`}if(e==="Read"&&t.file_path){let r=t.file_path.split("/").pop()||t.file_path;return`${e}(${r})`}if(e==="Edit"&&t.file_path){let r=t.file_path.split("/").pop()||t.file_path;return`${e}(${r})`}if(e==="Write"&&t.file_path){let r=t.file_path.split("/").pop()||t.file_path;return`${e}(${r})`}return e}catch{return e}}log(e,s,t,r,o){if(e<this.level)return;let i=new Date().toISOString().replace("T"," ").substring(0,23),n=O[e].padEnd(5),p=s.padEnd(6),u="";r?.correlationId?u=`[${r.correlationId}] `:r?.sessionId&&(u=`[session-${r.sessionId}] `);let E="";o!=null&&(this.level===0&&typeof o=="object"?E=`
-`+JSON.stringify(o,null,2):E=" "+this.formatData(o));let c="";if(r){let{sessionId:b,sdkSessionId:g,correlationId:_,...a}=r;Object.keys(a).length>0&&(c=` {${Object.entries(a).map(([k,x])=>`${k}=${x}`).join(", ")}}`)}let l=`[${i}] [${n}] [${p}] ${u}${t}${c}${E}`;e===3?console.error(l):console.log(l)}debug(e,s,t,r){this.log(0,e,s,t,r)}info(e,s,t,r){this.log(1,e,s,t,r)}warn(e,s,t,r){this.log(2,e,s,t,r)}error(e,s,t,r){this.log(3,e,s,t,r)}dataIn(e,s,t,r){this.info(e,`\u2192 ${s}`,t,r)}dataOut(e,s,t,r){this.info(e,`\u2190 ${s}`,t,r)}success(e,s,t,r){this.info(e,`\u2713 ${s}`,t,r)}failure(e,s,t,r){this.error(e,`\u2717 ${s}`,t,r)}timing(e,s,t,r){this.info(e,`\u23F1 ${s}`,r,{duration:`${t}ms`})}},S=new I;var R=class{db;constructor(){C(T),this.db=new X(v),this.db.pragma("journal_mode = WAL"),this.db.pragma("synchronous = NORMAL"),this.db.pragma("foreign_keys = ON"),this.initializeSchema(),this.ensureWorkerPortColumn(),this.ensurePromptTrackingColumns(),this.removeSessionSummariesUniqueConstraint(),this.addObservationHierarchicalFields(),this.makeObservationsTextNullable(),this.createUserPromptsTable(),this.ensureDiscoveryTokensColumn()}initializeSchema(){try{this.db.exec(`
+`+JSON.stringify(o,null,2):E=" "+this.formatData(o));let c="";if(r){let{sessionId:b,sdkSessionId:R,correlationId:_,...d}=r;Object.keys(d).length>0&&(c=` {${Object.entries(d).map(([w,F])=>`${w}=${F}`).join(", ")}}`)}let l=`[${i}] [${n}] [${p}] ${u}${t}${c}${E}`;e===3?console.error(l):console.log(l)}debug(e,s,t,r){this.log(0,e,s,t,r)}info(e,s,t,r){this.log(1,e,s,t,r)}warn(e,s,t,r){this.log(2,e,s,t,r)}error(e,s,t,r){this.log(3,e,s,t,r)}dataIn(e,s,t,r){this.info(e,`\u2192 ${s}`,t,r)}dataOut(e,s,t,r){this.info(e,`\u2190 ${s}`,t,r)}success(e,s,t,r){this.info(e,`\u2713 ${s}`,t,r)}failure(e,s,t,r){this.error(e,`\u2717 ${s}`,t,r)}timing(e,s,t,r){this.info(e,`\u23F1 ${s}`,r,{duration:`${t}ms`})}},S=new f;var g=class{db;constructor(){y(T),this.db=new W(v),this.db.pragma("journal_mode = WAL"),this.db.pragma("synchronous = NORMAL"),this.db.pragma("foreign_keys = ON"),this.initializeSchema(),this.ensureWorkerPortColumn(),this.ensurePromptTrackingColumns(),this.removeSessionSummariesUniqueConstraint(),this.addObservationHierarchicalFields(),this.makeObservationsTextNullable(),this.createUserPromptsTable(),this.ensureDiscoveryTokensColumn()}initializeSchema(){try{this.db.exec(`
        CREATE TABLE IF NOT EXISTS schema_versions (
          id INTEGER PRIMARY KEY,
          version INTEGER UNIQUE NOT NULL,
@@ -293,9 +293,13 @@ ${e.stack}`:e.message;if(Array.isArray(e))return`[${e.length} items]`;let s=Obje
      INSERT OR IGNORE INTO sdk_sessions
      (claude_session_id, sdk_session_id, project, user_prompt, started_at, started_at_epoch, status)
      VALUES (?, ?, ?, ?, ?, ?, 'active')
-    `).run(e,e,s,t,r.toISOString(),o);return n.lastInsertRowid===0||n.changes===0?this.db.prepare(`
+    `).run(e,e,s,t,r.toISOString(),o);return n.lastInsertRowid===0||n.changes===0?(s&&s.trim()!==""&&this.db.prepare(`
+          UPDATE sdk_sessions
+          SET project = ?, user_prompt = ?
+          WHERE claude_session_id = ?
+        `).run(s,t,e),this.db.prepare(`
        SELECT id FROM sdk_sessions WHERE claude_session_id = ? LIMIT 1
-      `).get(e).id:n.lastInsertRowid}updateSDKSessionId(e,s){return this.db.prepare(`
+      `).get(e).id):n.lastInsertRowid}updateSDKSessionId(e,s){return this.db.prepare(`
      UPDATE sdk_sessions
      SET sdk_session_id = ?
      WHERE id = ? AND sdk_session_id IS NULL
@@ -363,25 +367,25 @@ ${e.stack}`:e.message;if(Array.isArray(e))return`[${e.length} items]`;let s=Obje
        WHERE id <= ? ${i}
        ORDER BY id DESC
        LIMIT ?
-      `,g=`
+      `,R=`
        SELECT id, created_at_epoch
        FROM observations
        WHERE id >= ? ${i}
        ORDER BY id ASC
        LIMIT ?
-      `;try{let _=this.db.prepare(b).all(e,...n,t+1),a=this.db.prepare(g).all(e,...n,r+1);if(_.length===0&&a.length===0)return{observations:[],sessions:[],prompts:[]};p=_.length>0?_[_.length-1].created_at_epoch:s,u=a.length>0?a[a.length-1].created_at_epoch:s}catch(_){return console.error("[SessionStore] Error getting boundary observations:",_.message),{observations:[],sessions:[],prompts:[]}}}else{let b=`
+      `;try{let _=this.db.prepare(b).all(e,...n,t+1),d=this.db.prepare(R).all(e,...n,r+1);if(_.length===0&&d.length===0)return{observations:[],sessions:[],prompts:[]};p=_.length>0?_[_.length-1].created_at_epoch:s,u=d.length>0?d[d.length-1].created_at_epoch:s}catch(_){return console.error("[SessionStore] Error getting boundary observations:",_.message),{observations:[],sessions:[],prompts:[]}}}else{let b=`
        SELECT created_at_epoch
        FROM observations
        WHERE created_at_epoch <= ? ${i}
        ORDER BY created_at_epoch DESC
        LIMIT ?
-      `,g=`
+      `,R=`
        SELECT created_at_epoch
        FROM observations
        WHERE created_at_epoch >= ? ${i}
        ORDER BY created_at_epoch ASC
        LIMIT ?
-      `;try{let _=this.db.prepare(b).all(s,...n,t),a=this.db.prepare(g).all(s,...n,r+1);if(_.length===0&&a.length===0)return{observations:[],sessions:[],prompts:[]};p=_.length>0?_[_.length-1].created_at_epoch:s,u=a.length>0?a[a.length-1].created_at_epoch:s}catch(_){return console.error("[SessionStore] Error getting boundary timestamps:",_.message),{observations:[],sessions:[],prompts:[]}}}let E=`
+      `;try{let _=this.db.prepare(b).all(s,...n,t),d=this.db.prepare(R).all(s,...n,r+1);if(_.length===0&&d.length===0)return{observations:[],sessions:[],prompts:[]};p=_.length>0?_[_.length-1].created_at_epoch:s,u=d.length>0?d[d.length-1].created_at_epoch:s}catch(_){return console.error("[SessionStore] Error getting boundary timestamps:",_.message),{observations:[],sessions:[],prompts:[]}}}let E=`
      SELECT *
      FROM observations
      WHERE created_at_epoch >= ? AND created_at_epoch <= ? ${i}
@@ -397,7 +401,7 @@ ${e.stack}`:e.message;if(Array.isArray(e))return`[${e.length} items]`;let s=Obje
      JOIN sdk_sessions s ON up.claude_session_id = s.claude_session_id
      WHERE up.created_at_epoch >= ? AND up.created_at_epoch <= ? ${i.replace("project","s.project")}
      ORDER BY up.created_at_epoch ASC
-    `;try{let b=this.db.prepare(E).all(p,u,...n),g=this.db.prepare(c).all(p,u,...n),_=this.db.prepare(l).all(p,u,...n);return{observations:b,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(b){return console.error("[SessionStore] Error querying timeline records:",b.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 G}from"fs";var W=100;function h(){try{let d=P.join(B(),".claude-mem","settings.json");if(j(d)){let e=JSON.parse(G(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 $(){try{let d=h();return(await fetch(`http://127.0.0.1:${d}/health`,{signal:AbortSignal.timeout(W)})).ok}catch{return!1}}async function y(){if(await $())return;let d=h();throw new Error(`Worker service is not responding on port ${d}.
+    `;try{let b=this.db.prepare(E).all(p,u,...n),R=this.db.prepare(c).all(p,u,...n),_=this.db.prepare(l).all(p,u,...n);return{observations:b,sessions:R.map(d=>({id:d.id,sdk_session_id:d.sdk_session_id,project:d.project,request:d.request,completed:d.completed,next_steps:d.next_steps,created_at:d.created_at,created_at_epoch:d.created_at_epoch})),prompts:_.map(d=>({id:d.id,claude_session_id:d.claude_session_id,project:d.project,prompt:d.prompt_text,created_at:d.created_at,created_at_epoch:d.created_at_epoch}))}}catch(b){return console.error("[SessionStore] Error querying timeline records:",b.message),{observations:[],sessions:[],prompts:[]}}}close(){this.db.close()}};function $(a,e,s){return a==="PreCompact"?e?{continue:!0,suppressOutput:!0}:{continue:!1,stopReason:s.reason||"Pre-compact operation failed",suppressOutput:!0}:a==="SessionStart"?e&&s.context?{continue:!0,suppressOutput:!0,hookSpecificOutput:{hookEventName:"SessionStart",additionalContext:s.context}}:{continue:!0,suppressOutput:!0}:a==="UserPromptSubmit"||a==="PostToolUse"?{continue:!0,suppressOutput:!0}:a==="Stop"?{continue:!0,suppressOutput:!0}:{continue:e,suppressOutput:!0,...s.reason&&!e?{stopReason:s.reason}:{}}}function I(a,e,s={}){let t=$(a,e,s);return JSON.stringify(t)}import D from"path";import{homedir as G}from"os";import{existsSync as k,readFileSync as Y}from"fs";import{execSync as K}from"child_process";var V=100,q=500,J=10;function h(){try{let a=D.join(G(),".claude-mem","settings.json");if(k(a)){let e=JSON.parse(Y(a,"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 x(){try{let a=h();return(await fetch(`http://127.0.0.1:${a}/health`,{signal:AbortSignal.timeout(V)})).ok}catch{return!1}}async function Q(){try{let a=C(),e=D.join(a,"ecosystem.config.cjs");if(!k(e))throw new Error(`Ecosystem config not found at ${e}`);K(`pm2 start "${e}"`,{cwd:a,stdio:"pipe",encoding:"utf-8"});for(let s=0;s<J;s++)if(await new Promise(t=>setTimeout(t,q)),await x())return!0;return!1}catch{return!1}}async function U(){if(await x())return;if(!await Q()){let e=h();throw new Error(`Worker service failed to start on port ${e}.

-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","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:o}=d;if(Y.has(t)){console.log(f("PostToolUse",!0));return}await y();let i=new R,n=i.createSDKSession(e,"",""),p=i.getPromptCounter(n);i.close();let u=S.formatTool(t,r),E=h();S.dataIn("HOOK",`PostToolUse: ${u}`,{sessionId:n,workerPort:E});try{let c=await fetch(`http://127.0.0.1:${E}/sessions/${n}/observations`,{method:"POST",headers:{"Content-Type":"application/json"},body:JSON.stringify({tool_name:t,tool_input:r!==void 0?JSON.stringify(r):"{}",tool_response:o!==void 0?JSON.stringify(o):"{}",prompt_number:p,cwd:s||""}),signal:AbortSignal.timeout(2e3)});if(!c.ok){let l=await c.text();throw S.failure("HOOK","Failed to send observation",{sessionId:n,status:c.status},l),new Error(`Failed to send observation to worker: ${c.status} ${l}`)}S.debug("HOOK","Observation sent successfully",{sessionId:n,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)});
+Try manually running: pm2 start ecosystem.config.cjs
+Or restart: pm2 restart claude-mem-worker`)}}var z=new Set(["ListMcpResourcesTool","SlashCommand","Skill","TodoWrite","AskUserQuestion"]);async function Z(a){if(!a)throw new Error("saveHook requires input");let{session_id:e,cwd:s,tool_name:t,tool_input:r,tool_response:o}=a;if(z.has(t)){console.log(I("PostToolUse",!0));return}await U();let i=new g,n=i.createSDKSession(e,"",""),p=i.getPromptCounter(n);i.close();let u=S.formatTool(t,r),E=h();S.dataIn("HOOK",`PostToolUse: ${u}`,{sessionId:n,workerPort:E});try{let c=await fetch(`http://127.0.0.1:${E}/sessions/${n}/observations`,{method:"POST",headers:{"Content-Type":"application/json"},body:JSON.stringify({tool_name:t,tool_input:r!==void 0?JSON.stringify(r):"{}",tool_response:o!==void 0?JSON.stringify(o):"{}",prompt_number:p,cwd:s||""}),signal:AbortSignal.timeout(2e3)});if(!c.ok){let l=await c.text();throw S.failure("HOOK","Failed to send observation",{sessionId:n,status:c.status},l),new Error(`Failed to send observation to worker: ${c.status} ${l}`)}S.debug("HOOK","Observation sent successfully",{sessionId:n,toolName:t})}catch(c){throw c.cause?.code==="ECONNREFUSED"||c.name==="TimeoutError"||c.message.includes("fetch failed")?new Error("There's a problem with the worker. If you just updated, type `pm2 restart claude-mem-worker` in your terminal to continue"):c}console.log(I("PostToolUse",!0))}var L="";M.on("data",a=>L+=a);M.on("end",async()=>{let a=L?JSON.parse(L):void 0;await Z(a)});
@@ -1,7 +1,7 @@
 #!/usr/bin/env node
-import{stdin as k}from"process";import{readFileSync as x,existsSync as U}from"fs";import j from"better-sqlite3";import{join as m,dirname as F,basename as ne}from"path";import{homedir as y}from"os";import{existsSync as de,mkdirSync as X}from"fs";import{fileURLToPath as H}from"url";function B(){return typeof __dirname<"u"?__dirname:F(H(import.meta.url))}var ce=B(),l=process.env.CLAUDE_MEM_DATA_DIR||m(y(),".claude-mem"),f=process.env.CLAUDE_CONFIG_DIR||m(y(),".claude"),ue=m(l,"archives"),_e=m(l,"logs"),me=m(l,"trash"),Ee=m(l,"backups"),le=m(l,"settings.json"),A=m(l,"claude-mem.db"),Te=m(l,"vector-db"),ge=m(f,"settings.json"),be=m(f,"commands"),Se=m(f,"CLAUDE.md");function v(a){X(a,{recursive:!0})}var O=(n=>(n[n.DEBUG=0]="DEBUG",n[n.INFO=1]="INFO",n[n.WARN=2]="WARN",n[n.ERROR=3]="ERROR",n[n.SILENT=4]="SILENT",n))(O||{}),N=class{level;useColor;constructor(){let e=process.env.CLAUDE_MEM_LOG_LEVEL?.toUpperCase()||"INFO";this.level=O[e]??1,this.useColor=process.stdout.isTTY??!1}correlationId(e,s){return`obs-${e}-${s}`}sessionId(e){return`session-${e}`}formatData(e){if(e==null)return"";if(typeof e=="string")return e;if(typeof e=="number"||typeof e=="boolean")return e.toString();if(typeof e=="object"){if(e instanceof Error)return this.level===0?`${e.message}
-${e.stack}`:e.message;if(Array.isArray(e))return`[${e.length} items]`;let s=Object.keys(e);return s.length===0?"{}":s.length<=3?JSON.stringify(e):`{${s.length} keys: ${s.slice(0,3).join(", ")}...}`}return String(e)}formatTool(e,s){if(!s)return e;try{let t=typeof s=="string"?JSON.parse(s):s;if(e==="Bash"&&t.command){let r=t.command.length>50?t.command.substring(0,50)+"...":t.command;return`${e}(${r})`}if(e==="Read"&&t.file_path){let r=t.file_path.split("/").pop()||t.file_path;return`${e}(${r})`}if(e==="Edit"&&t.file_path){let r=t.file_path.split("/").pop()||t.file_path;return`${e}(${r})`}if(e==="Write"&&t.file_path){let r=t.file_path.split("/").pop()||t.file_path;return`${e}(${r})`}return e}catch{return e}}log(e,s,t,r,n){if(e<this.level)return;let i=new Date().toISOString().replace("T"," ").substring(0,23),o=O[e].padEnd(5),d=s.padEnd(6),c="";r?.correlationId?c=`[${r.correlationId}] `:r?.sessionId&&(c=`[session-${r.sessionId}] `);let u="";n!=null&&(this.level===0&&typeof n=="object"?u=`
-`+JSON.stringify(n,null,2):u=" "+this.formatData(n));let E="";if(r){let{sessionId:T,sdkSessionId:S,correlationId:_,...p}=r;Object.keys(p).length>0&&(E=` {${Object.entries(p).map(([M,w])=>`${M}=${w}`).join(", ")}}`)}let b=`[${i}] [${o}] [${d}] ${c}${t}${E}${u}`;e===3?console.error(b):console.log(b)}debug(e,s,t,r){this.log(0,e,s,t,r)}info(e,s,t,r){this.log(1,e,s,t,r)}warn(e,s,t,r){this.log(2,e,s,t,r)}error(e,s,t,r){this.log(3,e,s,t,r)}dataIn(e,s,t,r){this.info(e,`\u2192 ${s}`,t,r)}dataOut(e,s,t,r){this.info(e,`\u2190 ${s}`,t,r)}success(e,s,t,r){this.info(e,`\u2713 ${s}`,t,r)}failure(e,s,t,r){this.error(e,`\u2717 ${s}`,t,r)}timing(e,s,t,r){this.info(e,`\u23F1 ${s}`,r,{duration:`${t}ms`})}},g=new N;var R=class{db;constructor(){v(l),this.db=new j(A),this.db.pragma("journal_mode = WAL"),this.db.pragma("synchronous = NORMAL"),this.db.pragma("foreign_keys = ON"),this.initializeSchema(),this.ensureWorkerPortColumn(),this.ensurePromptTrackingColumns(),this.removeSessionSummariesUniqueConstraint(),this.addObservationHierarchicalFields(),this.makeObservationsTextNullable(),this.createUserPromptsTable(),this.ensureDiscoveryTokensColumn()}initializeSchema(){try{this.db.exec(`
+import{stdin as w}from"process";import{readFileSync as F,existsSync as X}from"fs";import Y from"better-sqlite3";import{join as m,dirname as B,basename as pe}from"path";import{homedir as y}from"os";import{existsSync as Ee,mkdirSync as j}from"fs";import{fileURLToPath as $}from"url";function W(){return typeof __dirname<"u"?__dirname:B($(import.meta.url))}var G=W(),l=process.env.CLAUDE_MEM_DATA_DIR||m(y(),".claude-mem"),f=process.env.CLAUDE_CONFIG_DIR||m(y(),".claude"),Te=m(l,"archives"),ge=m(l,"logs"),Se=m(l,"trash"),be=m(l,"backups"),Re=m(l,"settings.json"),A=m(l,"claude-mem.db"),he=m(l,"vector-db"),fe=m(f,"settings.json"),Oe=m(f,"commands"),Ne=m(f,"CLAUDE.md");function v(a){j(a,{recursive:!0})}function C(){return m(G,"..","..")}var O=(n=>(n[n.DEBUG=0]="DEBUG",n[n.INFO=1]="INFO",n[n.WARN=2]="WARN",n[n.ERROR=3]="ERROR",n[n.SILENT=4]="SILENT",n))(O||{}),N=class{level;useColor;constructor(){let e=process.env.CLAUDE_MEM_LOG_LEVEL?.toUpperCase()||"INFO";this.level=O[e]??1,this.useColor=process.stdout.isTTY??!1}correlationId(e,s){return`obs-${e}-${s}`}sessionId(e){return`session-${e}`}formatData(e){if(e==null)return"";if(typeof e=="string")return e;if(typeof e=="number"||typeof e=="boolean")return e.toString();if(typeof e=="object"){if(e instanceof Error)return this.level===0?`${e.message}
+${e.stack}`:e.message;if(Array.isArray(e))return`[${e.length} items]`;let s=Object.keys(e);return s.length===0?"{}":s.length<=3?JSON.stringify(e):`{${s.length} keys: ${s.slice(0,3).join(", ")}...}`}return String(e)}formatTool(e,s){if(!s)return e;try{let t=typeof s=="string"?JSON.parse(s):s;if(e==="Bash"&&t.command){let r=t.command.length>50?t.command.substring(0,50)+"...":t.command;return`${e}(${r})`}if(e==="Read"&&t.file_path){let r=t.file_path.split("/").pop()||t.file_path;return`${e}(${r})`}if(e==="Edit"&&t.file_path){let r=t.file_path.split("/").pop()||t.file_path;return`${e}(${r})`}if(e==="Write"&&t.file_path){let r=t.file_path.split("/").pop()||t.file_path;return`${e}(${r})`}return e}catch{return e}}log(e,s,t,r,n){if(e<this.level)return;let i=new Date().toISOString().replace("T"," ").substring(0,23),o=O[e].padEnd(5),d=s.padEnd(6),p="";r?.correlationId?p=`[${r.correlationId}] `:r?.sessionId&&(p=`[session-${r.sessionId}] `);let u="";n!=null&&(this.level===0&&typeof n=="object"?u=`
+`+JSON.stringify(n,null,2):u=" "+this.formatData(n));let E="";if(r){let{sessionId:T,sdkSessionId:b,correlationId:_,...c}=r;Object.keys(c).length>0&&(E=` {${Object.entries(c).map(([H,P])=>`${H}=${P}`).join(", ")}}`)}let S=`[${i}] [${o}] [${d}] ${p}${t}${E}${u}`;e===3?console.error(S):console.log(S)}debug(e,s,t,r){this.log(0,e,s,t,r)}info(e,s,t,r){this.log(1,e,s,t,r)}warn(e,s,t,r){this.log(2,e,s,t,r)}error(e,s,t,r){this.log(3,e,s,t,r)}dataIn(e,s,t,r){this.info(e,`\u2192 ${s}`,t,r)}dataOut(e,s,t,r){this.info(e,`\u2190 ${s}`,t,r)}success(e,s,t,r){this.info(e,`\u2713 ${s}`,t,r)}failure(e,s,t,r){this.error(e,`\u2717 ${s}`,t,r)}timing(e,s,t,r){this.info(e,`\u23F1 ${s}`,r,{duration:`${t}ms`})}},g=new N;var R=class{db;constructor(){v(l),this.db=new Y(A),this.db.pragma("journal_mode = WAL"),this.db.pragma("synchronous = NORMAL"),this.db.pragma("foreign_keys = ON"),this.initializeSchema(),this.ensureWorkerPortColumn(),this.ensurePromptTrackingColumns(),this.removeSessionSummariesUniqueConstraint(),this.addObservationHierarchicalFields(),this.makeObservationsTextNullable(),this.createUserPromptsTable(),this.ensureDiscoveryTokensColumn()}initializeSchema(){try{this.db.exec(`
        CREATE TABLE IF NOT EXISTS schema_versions (
          id INTEGER PRIMARY KEY,
          version INTEGER UNIQUE NOT NULL,
@@ -293,9 +293,13 @@ ${e.stack}`:e.message;if(Array.isArray(e))return`[${e.length} items]`;let s=Obje
      INSERT OR IGNORE INTO sdk_sessions
      (claude_session_id, sdk_session_id, project, user_prompt, started_at, started_at_epoch, status)
      VALUES (?, ?, ?, ?, ?, ?, 'active')
-    `).run(e,e,s,t,r.toISOString(),n);return o.lastInsertRowid===0||o.changes===0?this.db.prepare(`
+    `).run(e,e,s,t,r.toISOString(),n);return o.lastInsertRowid===0||o.changes===0?(s&&s.trim()!==""&&this.db.prepare(`
+          UPDATE sdk_sessions
+          SET project = ?, user_prompt = ?
+          WHERE claude_session_id = ?
+        `).run(s,t,e),this.db.prepare(`
        SELECT id FROM sdk_sessions WHERE claude_session_id = ? LIMIT 1
-      `).get(e).id:o.lastInsertRowid}updateSDKSessionId(e,s){return this.db.prepare(`
+      `).get(e).id):o.lastInsertRowid}updateSDKSessionId(e,s){return this.db.prepare(`
      UPDATE sdk_sessions
      SET sdk_session_id = ?
      WHERE id = ? AND sdk_session_id IS NULL
@@ -357,31 +361,31 @@ ${e.stack}`:e.message;if(Array.isArray(e))return`[${e.length} items]`;let s=Obje
      WHERE up.id IN (${o})
      ORDER BY up.created_at_epoch ${n}
      ${i}
-    `).all(...e)}getTimelineAroundTimestamp(e,s=10,t=10,r){return this.getTimelineAroundObservation(null,e,s,t,r)}getTimelineAroundObservation(e,s,t=10,r=10,n){let i=n?"AND project = ?":"",o=n?[n]:[],d,c;if(e!==null){let T=`
+    `).all(...e)}getTimelineAroundTimestamp(e,s=10,t=10,r){return this.getTimelineAroundObservation(null,e,s,t,r)}getTimelineAroundObservation(e,s,t=10,r=10,n){let i=n?"AND project = ?":"",o=n?[n]:[],d,p;if(e!==null){let T=`
        SELECT id, created_at_epoch
        FROM observations
        WHERE id <= ? ${i}
        ORDER BY id DESC
        LIMIT ?
-      `,S=`
+      `,b=`
        SELECT id, created_at_epoch
        FROM observations
        WHERE id >= ? ${i}
        ORDER BY id ASC
        LIMIT ?
-      `;try{let _=this.db.prepare(T).all(e,...o,t+1),p=this.db.prepare(S).all(e,...o,r+1);if(_.length===0&&p.length===0)return{observations:[],sessions:[],prompts:[]};d=_.length>0?_[_.length-1].created_at_epoch:s,c=p.length>0?p[p.length-1].created_at_epoch:s}catch(_){return console.error("[SessionStore] Error getting boundary observations:",_.message),{observations:[],sessions:[],prompts:[]}}}else{let T=`
+      `;try{let _=this.db.prepare(T).all(e,...o,t+1),c=this.db.prepare(b).all(e,...o,r+1);if(_.length===0&&c.length===0)return{observations:[],sessions:[],prompts:[]};d=_.length>0?_[_.length-1].created_at_epoch:s,p=c.length>0?c[c.length-1].created_at_epoch:s}catch(_){return console.error("[SessionStore] Error getting boundary observations:",_.message),{observations:[],sessions:[],prompts:[]}}}else{let T=`
        SELECT created_at_epoch
        FROM observations
        WHERE created_at_epoch <= ? ${i}
        ORDER BY created_at_epoch DESC
        LIMIT ?
-      `,S=`
+      `,b=`
        SELECT created_at_epoch
        FROM observations
        WHERE created_at_epoch >= ? ${i}
        ORDER BY created_at_epoch ASC
        LIMIT ?
-      `;try{let _=this.db.prepare(T).all(s,...o,t),p=this.db.prepare(S).all(s,...o,r+1);if(_.length===0&&p.length===0)return{observations:[],sessions:[],prompts:[]};d=_.length>0?_[_.length-1].created_at_epoch:s,c=p.length>0?p[p.length-1].created_at_epoch:s}catch(_){return console.error("[SessionStore] Error getting boundary timestamps:",_.message),{observations:[],sessions:[],prompts:[]}}}let u=`
+      `;try{let _=this.db.prepare(T).all(s,...o,t),c=this.db.prepare(b).all(s,...o,r+1);if(_.length===0&&c.length===0)return{observations:[],sessions:[],prompts:[]};d=_.length>0?_[_.length-1].created_at_epoch:s,p=c.length>0?c[c.length-1].created_at_epoch:s}catch(_){return console.error("[SessionStore] Error getting boundary timestamps:",_.message),{observations:[],sessions:[],prompts:[]}}}let u=`
      SELECT *
      FROM observations
      WHERE created_at_epoch >= ? AND created_at_epoch <= ? ${i}
@@ -391,28 +395,28 @@ ${e.stack}`:e.message;if(Array.isArray(e))return`[${e.length} items]`;let s=Obje
      FROM session_summaries
      WHERE created_at_epoch >= ? AND created_at_epoch <= ? ${i}
      ORDER BY created_at_epoch ASC
-    `,b=`
+    `,S=`
      SELECT up.*, s.project, s.sdk_session_id
      FROM user_prompts up
      JOIN sdk_sessions s ON up.claude_session_id = s.claude_session_id
      WHERE up.created_at_epoch >= ? AND up.created_at_epoch <= ? ${i.replace("project","s.project")}
      ORDER BY up.created_at_epoch ASC
-    `;try{let T=this.db.prepare(u).all(d,c,...o),S=this.db.prepare(E).all(d,c,...o),_=this.db.prepare(b).all(d,c,...o);return{observations:T,sessions:S.map(p=>({id:p.id,sdk_session_id:p.sdk_session_id,project:p.project,request:p.request,completed:p.completed,next_steps:p.next_steps,created_at:p.created_at,created_at_epoch:p.created_at_epoch})),prompts:_.map(p=>({id:p.id,claude_session_id:p.claude_session_id,project:p.project,prompt:p.prompt_text,created_at:p.created_at,created_at_epoch:p.created_at_epoch}))}}catch(T){return console.error("[SessionStore] Error querying timeline records:",T.message),{observations:[],sessions:[],prompts:[]}}}close(){this.db.close()}};function P(a,e,s){return a==="PreCompact"?e?{continue:!0,suppressOutput:!0}:{continue:!1,stopReason:s.reason||"Pre-compact operation failed",suppressOutput:!0}:a==="SessionStart"?e&&s.context?{continue:!0,suppressOutput:!0,hookSpecificOutput:{hookEventName:"SessionStart",additionalContext:s.context}}:{continue:!0,suppressOutput:!0}:a==="UserPromptSubmit"||a==="PostToolUse"?{continue:!0,suppressOutput:!0}:a==="Stop"?{continue:!0,suppressOutput:!0}:{continue:e,suppressOutput:!0,...s.reason&&!e?{stopReason:s.reason}:{}}}function C(a,e,s={}){let t=P(a,e,s);return JSON.stringify(t)}import $ from"path";import{homedir as G}from"os";import{existsSync as W,readFileSync as Y}from"fs";var K=100;function h(){try{let a=$.join(G(),".claude-mem","settings.json");if(W(a)){let e=JSON.parse(Y(a,"utf-8")),s=parseInt(e.env?.CLAUDE_MEM_WORKER_PORT,10);if(!isNaN(s))return s}}catch{}return parseInt(process.env.CLAUDE_MEM_WORKER_PORT||"37777",10)}async function q(){try{let a=h();return(await fetch(`http://127.0.0.1:${a}/health`,{signal:AbortSignal.timeout(K)})).ok}catch{return!1}}async function D(){if(await q())return;let a=h();throw new Error(`Worker service is not responding on port ${a}.
+    `;try{let T=this.db.prepare(u).all(d,p,...o),b=this.db.prepare(E).all(d,p,...o),_=this.db.prepare(S).all(d,p,...o);return{observations:T,sessions:b.map(c=>({id:c.id,sdk_session_id:c.sdk_session_id,project:c.project,request:c.request,completed:c.completed,next_steps:c.next_steps,created_at:c.created_at,created_at_epoch:c.created_at_epoch})),prompts:_.map(c=>({id:c.id,claude_session_id:c.claude_session_id,project:c.project,prompt:c.prompt_text,created_at:c.created_at,created_at_epoch:c.created_at_epoch}))}}catch(T){return console.error("[SessionStore] Error querying timeline records:",T.message),{observations:[],sessions:[],prompts:[]}}}close(){this.db.close()}};function K(a,e,s){return a==="PreCompact"?e?{continue:!0,suppressOutput:!0}:{continue:!1,stopReason:s.reason||"Pre-compact operation failed",suppressOutput:!0}:a==="SessionStart"?e&&s.context?{continue:!0,suppressOutput:!0,hookSpecificOutput:{hookEventName:"SessionStart",additionalContext:s.context}}:{continue:!0,suppressOutput:!0}:a==="UserPromptSubmit"||a==="PostToolUse"?{continue:!0,suppressOutput:!0}:a==="Stop"?{continue:!0,suppressOutput:!0}:{continue:e,suppressOutput:!0,...s.reason&&!e?{stopReason:s.reason}:{}}}function D(a,e,s={}){let t=K(a,e,s);return JSON.stringify(t)}import k from"path";import{homedir as q}from"os";import{existsSync as x,readFileSync as V}from"fs";import{execSync as J}from"child_process";var Q=100,z=500,Z=10;function h(){try{let a=k.join(q(),".claude-mem","settings.json");if(x(a)){let e=JSON.parse(V(a,"utf-8")),s=parseInt(e.env?.CLAUDE_MEM_WORKER_PORT,10);if(!isNaN(s))return s}}catch{}return parseInt(process.env.CLAUDE_MEM_WORKER_PORT||"37777",10)}async function U(){try{let a=h();return(await fetch(`http://127.0.0.1:${a}/health`,{signal:AbortSignal.timeout(Q)})).ok}catch{return!1}}async function ee(){try{let a=C(),e=k.join(a,"ecosystem.config.cjs");if(!x(e))throw new Error(`Ecosystem config not found at ${e}`);J(`pm2 start "${e}"`,{cwd:a,stdio:"pipe",encoding:"utf-8"});for(let s=0;s<Z;s++)if(await new Promise(t=>setTimeout(t,z)),await U())return!0;return!1}catch{return!1}}async function M(){if(await U())return;if(!await ee()){let e=h();throw new Error(`Worker service failed to start on port ${e}.

-If you just updated the plugin, PM2's watch mode should restart automatically.
-If the problem persists, run: pm2 restart claude-mem-worker`)}import{appendFileSync as V}from"fs";import{homedir as J}from"os";import{join as Q}from"path";var z=Q(J(),".claude-mem","silent.log");function I(a,e,s=""){let t=new Date().toISOString(),o=((new Error().stack||"").split(`
-`)[2]||"").match(/at\s+(?:.*\s+)?\(?([^:]+):(\d+):(\d+)\)?/),d=o?`${o[1].split("/").pop()}:${o[2]}`:"unknown",c=`[${t}] [${d}] ${a}`;if(e!==void 0)try{c+=` ${JSON.stringify(e)}`}catch(u){c+=` [stringify error: ${u}]`}c+=`
-`;try{V(z,c)}catch(u){console.error("[silent-debug] Failed to write to log:",u)}return s}function Z(a){if(!a||!U(a))return"";try{let e=x(a,"utf-8").trim();if(!e)return"";let s=e.split(`
+Try manually running: pm2 start ecosystem.config.cjs
+Or restart: pm2 restart claude-mem-worker`)}}import{appendFileSync as se}from"fs";import{homedir as te}from"os";import{join as re}from"path";var ne=re(te(),".claude-mem","silent.log");function I(a,e,s=""){let t=new Date().toISOString(),o=((new Error().stack||"").split(`
+`)[2]||"").match(/at\s+(?:.*\s+)?\(?([^:]+):(\d+):(\d+)\)?/),d=o?`${o[1].split("/").pop()}:${o[2]}`:"unknown",p=`[${t}] [${d}] ${a}`;if(e!==void 0)try{p+=` ${JSON.stringify(e)}`}catch(u){p+=` [stringify error: ${u}]`}p+=`
+`;try{se(ne,p)}catch(u){console.error("[silent-debug] Failed to write to log:",u)}return s}function oe(a){if(!a||!X(a))return"";try{let e=F(a,"utf-8").trim();if(!e)return"";let s=e.split(`
 `);for(let t=s.length-1;t>=0;t--)try{let r=JSON.parse(s[t]);if(r.type==="user"&&r.message?.content){let n=r.message.content;if(typeof n=="string")return n;if(Array.isArray(n))return n.filter(o=>o.type==="text").map(o=>o.text).join(`
-`)}}catch{continue}}catch(e){g.error("HOOK","Failed to read transcript",{transcriptPath:a},e)}return""}function ee(a){if(!a||!U(a))return"";try{let e=x(a,"utf-8").trim();if(!e)return"";let s=e.split(`
+`)}}catch{continue}}catch(e){g.error("HOOK","Failed to read transcript",{transcriptPath:a},e)}return""}function ie(a){if(!a||!X(a))return"";try{let e=F(a,"utf-8").trim();if(!e)return"";let s=e.split(`
 `);for(let t=s.length-1;t>=0;t--)try{let r=JSON.parse(s[t]);if(r.type==="assistant"&&r.message?.content){let n="",i=r.message.content;return typeof i=="string"?n=i:Array.isArray(i)&&(n=i.filter(d=>d.type==="text").map(d=>d.text).join(`
 `)),n=n.replace(/<system-reminder>[\s\S]*?<\/system-reminder>/g,""),n=n.replace(/\n{3,}/g,`

-`).trim(),n}}catch{continue}}catch(e){g.error("HOOK","Failed to read transcript",{transcriptPath:a},e)}return""}async function se(a){if(!a)throw new Error("summaryHook requires input");let{session_id:e}=a;await D();let s=new R,t=s.createSDKSession(e,"",""),r=s.getPromptCounter(t),n=s.db.prepare(`
+`).trim(),n}}catch{continue}}catch(e){g.error("HOOK","Failed to read transcript",{transcriptPath:a},e)}return""}async function ae(a){if(!a)throw new Error("summaryHook requires input");let{session_id:e}=a;await M();let s=new R,t=s.createSDKSession(e,"",""),r=s.getPromptCounter(t),n=s.db.prepare(`
    SELECT id, claude_session_id, sdk_session_id, project
    FROM sdk_sessions WHERE id = ?
  `).get(t),i=s.db.prepare(`
    SELECT COUNT(*) as count
    FROM observations
    WHERE sdk_session_id = ?
-  `).get(n?.sdk_session_id);I("[summary-hook] Session diagnostics",{claudeSessionId:e,sessionDbId:t,sdkSessionId:n?.sdk_session_id,project:n?.project,promptNumber:r,observationCount:i?.count||0,transcriptPath:a.transcript_path}),s.close();let o=h(),d=Z(a.transcript_path||""),c=ee(a.transcript_path||"");I("[summary-hook] Extracted messages",{hasLastUserMessage:!!d,hasLastAssistantMessage:!!c,lastAssistantPreview:c.substring(0,200),lastAssistantLength:c.length}),g.dataIn("HOOK","Stop: Requesting summary",{sessionId:t,workerPort:o,promptNumber:r,hasLastUserMessage:!!d,hasLastAssistantMessage:!!c});try{let u=await fetch(`http://127.0.0.1:${o}/sessions/${t}/summarize`,{method:"POST",headers:{"Content-Type":"application/json"},body:JSON.stringify({prompt_number:r,last_user_message:d,last_assistant_message:c}),signal:AbortSignal.timeout(2e3)});if(!u.ok){let E=await u.text();throw g.failure("HOOK","Failed to generate summary",{sessionId:t,status:u.status},E),new Error(`Failed to request summary from worker: ${u.status} ${E}`)}g.debug("HOOK","Summary request sent successfully",{sessionId:t})}catch(u){throw u.cause?.code==="ECONNREFUSED"||u.name==="TimeoutError"||u.message.includes("fetch failed")?new Error("There's a problem with the worker. If you just updated, type `pm2 restart claude-mem-worker` in your terminal to continue"):u}finally{await fetch(`http://127.0.0.1:${o}/api/processing`,{method:"POST",headers:{"Content-Type":"application/json"},body:JSON.stringify({isProcessing:!1})})}console.log(C("Stop",!0))}var L="";k.on("data",a=>L+=a);k.on("end",async()=>{let a=L?JSON.parse(L):void 0;await se(a)});
+  `).get(n?.sdk_session_id);I("[summary-hook] Session diagnostics",{claudeSessionId:e,sessionDbId:t,sdkSessionId:n?.sdk_session_id,project:n?.project,promptNumber:r,observationCount:i?.count||0,transcriptPath:a.transcript_path}),s.close();let o=h(),d=oe(a.transcript_path||""),p=ie(a.transcript_path||"");I("[summary-hook] Extracted messages",{hasLastUserMessage:!!d,hasLastAssistantMessage:!!p,lastAssistantPreview:p.substring(0,200),lastAssistantLength:p.length}),g.dataIn("HOOK","Stop: Requesting summary",{sessionId:t,workerPort:o,promptNumber:r,hasLastUserMessage:!!d,hasLastAssistantMessage:!!p});try{let u=await fetch(`http://127.0.0.1:${o}/sessions/${t}/summarize`,{method:"POST",headers:{"Content-Type":"application/json"},body:JSON.stringify({prompt_number:r,last_user_message:d,last_assistant_message:p}),signal:AbortSignal.timeout(2e3)});if(!u.ok){let E=await u.text();throw g.failure("HOOK","Failed to generate summary",{sessionId:t,status:u.status},E),new Error(`Failed to request summary from worker: ${u.status} ${E}`)}g.debug("HOOK","Summary request sent successfully",{sessionId:t})}catch(u){throw u.cause?.code==="ECONNREFUSED"||u.name==="TimeoutError"||u.message.includes("fetch failed")?new Error("There's a problem with the worker. If you just updated, type `pm2 restart claude-mem-worker` in your terminal to continue"):u}finally{await fetch(`http://127.0.0.1:${o}/api/processing`,{method:"POST",headers:{"Content-Type":"application/json"},body:JSON.stringify({isProcessing:!1})})}console.log(D("Stop",!0))}var L="";w.on("data",a=>L+=a);w.on("end",async()=>{let a=L?JSON.parse(L):void 0;await ae(a)});
@@ -1,5 +1,5 @@
 #!/usr/bin/env node
-import{execSync as u}from"child_process";import{join as r}from"path";import{homedir as s}from"os";import{existsSync as l}from"fs";import i from"path";import{homedir as a}from"os";import{existsSync as c,readFileSync as p}from"fs";function n(){try{let e=i.join(a(),".claude-mem","settings.json");if(c(e)){let t=JSON.parse(p(e,"utf-8")),o=parseInt(t.env?.CLAUDE_MEM_WORKER_PORT,10);if(!isNaN(o))return o}}catch{}return parseInt(process.env.CLAUDE_MEM_WORKER_PORT||"37777",10)}var m=r(s(),".claude","plugins","marketplaces","thedotmack"),d=r(m,"node_modules");l(d)||(console.error(`
+import{execSync as _}from"child_process";import{join as i}from"path";import{homedir as p}from"os";import{existsSync as x}from"fs";import l from"path";import{homedir as f}from"os";import{existsSync as g,readFileSync as h}from"fs";import{join as t,dirname as m,basename as y}from"path";import{homedir as c}from"os";import{fileURLToPath as u}from"url";function d(){return typeof __dirname<"u"?__dirname:m(u(import.meta.url))}var A=d(),e=process.env.CLAUDE_MEM_DATA_DIR||t(c(),".claude-mem"),s=process.env.CLAUDE_CONFIG_DIR||t(c(),".claude"),P=t(e,"archives"),w=t(e,"logs"),C=t(e,"trash"),I=t(e,"backups"),b=t(e,"settings.json"),v=t(e,"claude-mem.db"),U=t(e,"vector-db"),M=t(s,"settings.json"),O=t(s,"commands"),L=t(s,"CLAUDE.md");function a(){try{let o=l.join(f(),".claude-mem","settings.json");if(g(o)){let n=JSON.parse(h(o,"utf-8")),r=parseInt(n.env?.CLAUDE_MEM_WORKER_PORT,10);if(!isNaN(r))return r}}catch{}return parseInt(process.env.CLAUDE_MEM_WORKER_PORT||"37777",10)}var D=i(p(),".claude","plugins","marketplaces","thedotmack"),k=i(D,"node_modules");x(k)||(console.error(`
 ---
 \u{1F389}  Note: This appears under Plugin Hook Error, but it's not an error. That's the only option for 
   user messages in Claude Code UI until a better method is provided.
@@ -17,15 +17,15 @@ Dependencies have been installed in the background. This only happens once.
 Thank you for installing Claude-Mem!

 This message was not added to your startup context, so you can continue working as normal.
-`),process.exit(3));try{let e=r(s(),".claude","plugins","marketplaces","thedotmack","plugin","scripts","context-hook.js"),t=u(`node "${e}" --colors`,{encoding:"utf8"}),o=n();console.error(`
+`),process.exit(3));try{let o=i(p(),".claude","plugins","marketplaces","thedotmack","plugin","scripts","context-hook.js"),n=_(`node "${o}" --colors`,{encoding:"utf8"}),r=a();console.error(`

 \u{1F4DD} Claude-Mem Context Loaded
   \u2139\uFE0F  Note: This appears as stderr but is informational only

-`+t+`
+`+n+`

 \u{1F4AC} Feedback & Support
 https://github.com/thedotmack/claude-mem/discussions/110

-\u{1F4FA} Watch live in browser http://localhost:${o}/
-`)}catch(e){console.error(`\u274C Failed to load context display: ${e}`)}process.exit(3);
+\u{1F4FA} Watch live in browser http://localhost:${r}/
+`)}catch(o){console.error(`\u274C Failed to load context display: ${o}`)}process.exit(3);
@@ -1,196 +1,123 @@
 ---
 name: mem-search
-description: Search claude-mem's persistent cross-session memory database to find work from previous conversations days, weeks, or months ago. Access past session summaries, bug fixes, feature implementations, and decisions that are NOT in the current conversation context. Use when user asks "did we already solve this?", "how did we do X last time?", "what happened in last week's session?", or needs information from previous sessions stored in the PM2-managed database. Searches observations, session summaries, and user prompts across entire project history.
+description: Search claude-mem's persistent cross-session memory database. Use when user asks "did we already solve this?", "how did we do X last time?", or needs work from previous sessions.
 ---

 # Memory Search

-Access claude-mem's persistent cross-session memory through HTTP API. Find past work, understand context across sessions, and learn from previous decisions.
+Search past work across all sessions. Simple workflow: search → get IDs → fetch details by ID.

-## When to Use This Skill
+## When to Use

-**Use when users ask about work from PREVIOUS sessions** (not current conversation):
+Use when users ask about PREVIOUS sessions (not current conversation):
+- "Did we already fix this?"
+- "How did we solve X last time?"
+- "What happened last week?"

-### Temporal Triggers (Key Indicators)
- "Did we **already** fix this bug?" or "Have we seen this error **before**?"
- "How did we solve X **last time**?" or "What approach did we take **previously**?"
- "What did we do in **yesterday's/last week's/last month's** session?"
- "**When** did we last work on this?" or "What's the **history** of this file?"
+## The Workflow

-### Cross-Session Queries
- "Show me all authentication-related changes **across all sessions**"
- "What features did we add **last month**?" (not "today" or "this session")
- "Why did we choose this approach **before**?" (decisions from past sessions)
- "What files did we modify **when we added X**?" (historical context)
+**ALWAYS follow this exact flow:**

-**Do NOT use** for current session work, future planning, or questions Claude can answer from current conversation context.
+1. **Search** - Get an index of results with IDs
+2. **Review** - Look at titles/dates, pick relevant IDs
+3. **Fetch** - Get full details ONLY for those IDs

-## Common Trigger Phrases
+### Step 1: Search Everything

-This skill activates when detecting phrases about **cross-session history**:
+```bash
+curl "http://localhost:37777/api/search?query=authentication&format=index&limit=5"
+```

- "Did we already solve this?" / "Have we done this before?"
- "How did we implement X last time?"
- "What did we work on yesterday/last week/last month?"
- "Show me the history of [file/feature/decision]"
- "When did we fix/add/change X?"
- "What was happening around [date/time]?"
- "Catch me up on recent sessions" / "What have we been doing?"
- "What changes to [filename] across all sessions?"
+**Required parameters:**
+- `query` - Search term
+- `format=index` - ALWAYS start with index (lightweight)
+- `limit=5` - Start small (3-5 results)

-**Unique identifiers:** claude-mem, persistent memory, cross-session database, session history, PM2-managed database
+**Returns:**
+```
+1. [feature] Added JWT authentication
+   Date: 11/17/2025, 3:48:45 PM
+   ID: 11131

-## Available Operations
+2. [bugfix] Fixed auth token expiration
+   Date: 11/16/2025, 2:15:22 PM
+   ID: 10942
+```

-### Full-Text Search
- **observations** - Search all observations by keyword (bugs, features, decisions, discoveries, changes)
-  - Use when: "How did we implement X?" or "What bugs did we fix?"
-  - Example: Search for "authentication JWT" to find auth-related work
+### Step 2: Pick IDs

- **sessions** - Search session summaries to find what was accomplished when
-  - Use when: "What did we accomplish last time?" or "What was the goal of that session?"
-  - Example: Find sessions where "added login feature"
+Review the index results. Identify which IDs are actually relevant. Discard the rest.

- **prompts** - Find what users have asked about in previous sessions
-  - Use when: "Did I ask about this before?" or "What did I request last week?"
-  - Example: Search for "database migration" in past user prompts
+### Step 3: Fetch by ID

-### Filtered Search
- **by-type** - Filter observations by type (bugfix, feature, refactor, decision, discovery, change)
-  - Use when: "Show me all bug fixes" or "List features we added"
-  - Example: Get all observations with type=bugfix from last month
+For each relevant ID, fetch full details:

- **by-concept** - Find observations tagged with specific concepts (problem-solution, how-it-works, gotcha)
-  - Use when: "What patterns did we discover?" or "Show me gotchas"
-  - Example: Find all observations tagged with concept "gotcha"
+```bash
+# Fetch observation
+curl "http://localhost:37777/api/observation/11131"

- **by-file** - Find all work related to a specific file path across all sessions
-  - Use when: "What changes to auth.ts?" or "History of this file"
-  - Example: Get all work related to "src/auth/login.ts"
+# Fetch session
+curl "http://localhost:37777/api/session/2005"

-### Timeline & Context
- **recent-context** - Get last N sessions with summaries and observations
-  - Use when: "What's been happening?" or "Catch me up on recent work"
-  - Example: Get last 3 sessions with limit=3
+# Fetch prompt
+curl "http://localhost:37777/api/prompt/5421"
+```

- **timeline** - Get chronological context around a specific point in time (before/after window)
-  - Use when: "What was happening around [date]?" or "Show me context from that time"
-  - Example: Timeline around session 123 with depth 5 before and after
+**ID formats:**
+- Observations: Just the number (11131)
+- Sessions: Just the number (2005) from "S2005"
+- Prompts: Just the number (5421)

- **timeline-by-query** - Search first, then get timeline context around best match
-  - Use when: "When did we implement auth?" combined with "show me context around that time"
-  - Example: Search for "OAuth implementation" then get surrounding timeline
+## Search Parameters

-For detailed instructions on any operation, read the corresponding file in [operations/](operations/).
+**Basic:**
+- `query` - What to search for (required)
+- `format` - "index" or "full" (always use "index" first)
+- `limit` - How many results (default 5, max 100)

-## Quick Decision Guide
+**Filters (optional):**
+- `type` - Filter to "observations", "sessions", or "prompts"
+- `project` - Filter by project name
+- `dateRange[start]` - Start date (YYYY-MM-DD)
+- `dateRange[end]` - End date (YYYY-MM-DD)
+- `obs_type` - Filter observations by: bugfix, feature, decision, discovery, change

-**What is the user asking about?**
+## Examples

-1. **Recent work** (last 3-5 sessions) → Use **recent-context** with limit=3-5
-2. **Specific topic/keyword** (bugs, features, decisions) → Use **observations** search
-3. **Specific file history** (changes to a file) → Use **by-file** search
-4. **Timeline/chronology** (what happened when) → Use **timeline** or **timeline-by-query**
-5. **Type-specific** (all bug fixes, all features) → Use **by-type** filter
+**Find recent bug fixes:**
+```bash
+curl "http://localhost:37777/api/search?query=bug&type=observations&obs_type=bugfix&format=index&limit=5"
+```

-**Most common:** Use **observations** search for general "how did we..." questions.
+**Find what happened last week:**
+```bash
+curl "http://localhost:37777/api/search?query=&type=observations&dateRange[start]=2025-11-11&format=index&limit=10"
+```

-## Progressive Disclosure Workflow (Token Efficiency)
+**Search everything:**
+```bash
+curl "http://localhost:37777/api/search?query=database+migration&format=index&limit=5"
+```

-**Core Principle**: Find high-signal items in index format FIRST (~50-100 tokens each), then request full details ONLY for relevant items (~500-1000 tokens each).
+## Why This Workflow?

-**4-Step Workflow:**
+**Token efficiency:**
+- Index format: ~50-100 tokens per result
+- Full format: ~500-1000 tokens per result
+- **10x difference** - only fetch full when you know it's relevant

-1. **Start with Index Format**
-   - Always use `format=index` initially
-   - Set `limit=3-5` (not 10-20)
-   - Review titles and dates to assess relevance
-   - Token cost: ~50-100 per result
-
-2. **Identify Relevant Items**
-   - Scan index results
-   - Discard irrelevant items from list
-   - Keep only 1-3 most relevant
-
-3. **Request Full Details Selectively**
-   - Use `format=full` ONLY for specific relevant items
-   - Token cost: ~500-1000 per result
-   - **10x cost difference** - be selective
-
-4. **Refine with Filters**
-   - Use type, dateRange, concepts, files filters
-   - Paginate with offset if needed
-   - Narrow scope before expanding limits
-
-**DO:**
- ✅ Start with `format=index` and `limit=3-5`
- ✅ Use filters (type, dateRange, concepts, files) to narrow results
- ✅ Request `format=full` ONLY for specific relevant items
- ✅ Use offset for pagination instead of large limits
-
-**DON'T:**
- ❌ Jump straight to `format=full`
- ❌ Request `limit=20` without assessing index results first
- ❌ Load full details for all results upfront
- ❌ Skip index format to "save a step" (costs 10x more tokens)
-
-See [principles/progressive-disclosure.md](principles/progressive-disclosure.md) for complete workflow with examples and token calculations.
-
-## Quick Reference Table
-
-| Need | Operation | Key Parameters |
-|------|-----------|----------------|
-| Recent context | recent-context | limit=3-5 |
-| Search observations | observations | query, format=index, limit=5 |
-| Search sessions | sessions | query, format=index, limit=5 |
-| Find by type | by-type | type=(bugfix\|feature\|decision), format=index |
-| Find by file | by-file | filePath, format=index |
-| Timeline around event | timeline | anchor=(sessionDbId), depth_before=5, depth_after=5 |
-| Search + timeline | timeline-by-query | query, mode=auto |
-
-## Common Workflows
-
-For step-by-step guides on typical user requests, see [operations/common-workflows.md](operations/common-workflows.md):
- Understanding past work from previous sessions
- Finding specific bug fixes from history
- Understanding file history across sessions
- Timeline investigation workflows
- Search composition patterns
-
-## Response Formatting
-
-For guidelines on presenting search results to users, see [operations/formatting.md](operations/formatting.md):
- Index format responses (compact lists with titles/dates)
- Full format responses (complete observation details)
- Timeline responses (chronologically grouped)
- Error handling and user-friendly messages
-
-## Technical Notes
-
- **Port:** Default 37777 (configurable via `CLAUDE_MEM_WORKER_PORT`)
- **Response format:** Always JSON
- **Search engine:** ChromaDB semantic search (primary ranking) + SQLite FTS5 (fallback) + 90-day recency filter + temporal ordering (hybrid architecture)
- **All operations:** HTTP GET with query parameters
- **Worker:** PM2-managed background process
+**Clarity:**
+- See everything first
+- Pick what matters
+- Get details only for what you need

 ## Error Handling

-If HTTP request fails:
-1. Inform user the claude-mem search service isn't available
-2. Suggest checking if worker is running: `pm2 list` or `pm2 status claude-mem-worker`
-3. Offer to help troubleshoot using the troubleshoot skill
-
-## Resources
-
-**Principles:**
- [principles/progressive-disclosure.md](principles/progressive-disclosure.md) - Complete 4-step workflow with token calculations
- [principles/anti-patterns.md](principles/anti-patterns.md) - 5 anti-patterns to avoid with LLM behavior insights
-
-**Operations:**
- [operations/](operations/) - Detailed instructions for each operation (9 operations + help)
- [operations/common-workflows.md](operations/common-workflows.md) - Step-by-step workflow guides
- [operations/formatting.md](operations/formatting.md) - Response formatting templates
+If search fails, tell the user the worker isn't available and suggest:
+```bash
+pm2 list  # Check if worker is running
+```

 ---

-**Remember:** This skill searches **cross-session persistent memory**, NOT current conversation. Start with index format for token efficiency. Use temporal triggers to differentiate from native Claude memory.
+**Remember:** ALWAYS search with format=index first. ALWAYS fetch by ID for details. The IDs are there for a reason - USE THEM.
@@ -17,10 +17,16 @@ curl -s "http://localhost:37777/api/search/observations?query=authentication&for

 ## Parameters

- **query** (required): Natural language search query - uses semantic search (ChromaDB) for ranking with SQLite FTS5 fallback (e.g., "authentication", "bug fix", "database migration")
+- **query** (optional): Natural language search query - uses semantic search (ChromaDB) for ranking with SQLite FTS5 fallback (e.g., "authentication", "bug fix", "database migration"). Can be omitted for filter-only searches.
 - **format**: "index" (summary) or "full" (complete details). Default: "full"
 - **limit**: Number of results (default: 20, max: 100)
 - **project**: Filter by project name (optional)
+- **dateRange**: Filter by date range (optional) - `dateRange[start]` and/or `dateRange[end]`
+- **obs_type**: Filter by observation type: bugfix, feature, refactor, decision, discovery, change (optional)
+- **concepts**: Filter by concept tags (optional)
+- **files**: Filter by file paths (optional)
+
+**Important**: When omitting `query`, you MUST provide at least one filter (project, dateRange, obs_type, concepts, or files)

 ## When to Use Each Format

@@ -76,13 +82,28 @@ Found 5 results for "authentication":

 For complete formatting guidelines, see formatting.md (documentation coming soon).

+## Filter-Only Examples
+
+Search without query text (direct SQLite filtering):
+
+```bash
+# Get all observations from November 2025
+curl -s "http://localhost:37777/api/search?type=observations&dateRange[start]=2025-11-01&format=index"
+
+# Get all bug fixes from a specific project
+curl -s "http://localhost:37777/api/search?type=observations&obs_type=bugfix&project=api-server&format=index"
+
+# Get all observations from last 7 days
+curl -s "http://localhost:37777/api/search?type=observations&dateRange[start]=2025-11-11&format=index"
+```
+
 ## Error Handling

-**Missing query parameter:**
+**Missing query and filters:**
 ```json
-{"error": "Missing required parameter: query"}
+{"error": "Either query or filters required for search"}
 ```
-Fix: Add the query parameter
+Fix: Provide either a query parameter OR at least one filter (project, dateRange, obs_type, concepts, files)

 **No results found:**
 ```json
@@ -376,6 +376,36 @@
      animation: spin 1.5s linear infinite;
    }

+    .queue-bubble {
+      position: absolute;
+      top: -8px;
+      right: -8px;
+      background: var(--color-accent-primary);
+      color: var(--color-text-button);
+      font-size: 10px;
+      font-weight: 600;
+      font-family: 'Monaspace Radon', monospace;
+      min-width: 18px;
+      height: 18px;
+      border-radius: 9px;
+      display: flex;
+      align-items: center;
+      justify-content: center;
+      padding: 0 5px;
+      box-shadow: 0 2px 4px rgba(0, 0, 0, 0.2);
+      animation: pulse 2s ease-in-out infinite;
+      z-index: 10;
+    }
+
+    @keyframes pulse {
+      0%, 100% {
+        transform: scale(1);
+      }
+      50% {
+        transform: scale(1.1);
+      }
+    }
+
    .logo-text {
      font-family: 'Monaspace Radon', monospace;
      font-weight: 100;
@@ -0,0 +1,109 @@
+# Postmortem: Worker Debug Failure - 2025-11-17
+
+## Incident Summary
+Attempted to fix broken worker service. Worker was in crash loop with 225 restarts, failing with "MCP error -32000: Connection closed". Debug attempt failed and changes were reverted.
+
+## What Went Wrong
+
+### 1. **Jumped to Symptoms, Not Root Cause**
+- Saw "MCP connection failed" errors in logs
+- Immediately focused on MCP/Chroma connection code
+- Never asked: "Why is this suddenly broken when it worked before?"
+- Classic symptom chasing instead of root cause analysis
+
+### 2. **Ignored the Build Pipeline**
+- Worker file wasn't in the expected location (`plugin/worker-service.cjs` vs `plugin/scripts/worker-service.cjs`)
+- Build output existed but search server was producing corrupted/error output
+- Never investigated: "Is the build system broken?"
+- Should have compared built artifacts between main and current branch
+
+### 3. **Tried to Fix by Disabling Instead of Understanding**
+- Final approach: comment out Chroma, comment out search server
+- This is the opposite of debugging - it's just making things "work" by removing functionality
+- User called this out as "duct tape around 5 things unrelated to the problem"
+- Violated YAGNI/KISS by adding defensive complexity instead of fixing the actual issue
+
+### 4. **Didn't Compare Working vs Broken State**
+- User specifically said "we fixed this before"
+- Should have immediately: `git diff main src/services/worker-service.ts`
+- Did this eventually but didn't follow through on the findings
+- The diff showed only search-everything additions - the core worker code was UNCHANGED
+- This should have been a huge red flag: "If the code is the same, why is it broken?"
+
+### 5. **Overcomplicated the Investigation**
+- Started reading through ChromaSync implementation
+- Traced through MCP connection code
+- Analyzed startup sequences
+- All of this was unnecessary if the root cause was a build issue
+
+## What Should Have Happened
+
+### Correct Debug Sequence:
+1. ✅ Check worker status (`pm2 list`) - DONE
+2. ✅ Check error logs - DONE
+3. ❌ **Compare current code to main branch** - SKIPPED INITIALLY
+4. ❌ **Check if built files are correct** - SKIPPED
+5. ❌ **Test the build pipeline** - NEVER DONE
+6. ❌ **Verify dependencies are installed** - NEVER CHECKED
+
+### The Real Questions:
+- Is this a code change or a build issue?
+- What changed between working state and broken state?
+- Are the built artifacts corrupted?
+- Is the search server build actually valid?
+- Are there missing dependencies in plugin/scripts/node_modules?
+
+## Likely Root Causes (Untested)
+
+Based on evidence:
+1. **Build artifacts are corrupted** - search-server.mjs threw syntax errors when run
+2. **Node modules missing/outdated** - plugin/scripts/node_modules may be stale
+3. **ESM/CJS bundling issue** - esbuild may have produced invalid output
+4. **search-everything branch has broken build config** - scripts/build-hooks.js may have issues
+
+## Key Lessons
+
+### KISS/DRY/YAGNI Violations
+- Added complexity (disabling features) instead of removing it
+- Tried to work around symptoms instead of fixing root cause
+- Ignored the principle: "If it worked before and code is same, it's environment/build"
+
+### Debugging Anti-Patterns
+1. **Symptom Chasing**: Following error messages down rabbit holes
+2. **Defensive Coding**: Commenting out "broken" features instead of fixing them
+3. **Ignoring History**: Not comparing working vs broken states
+4. **Build Blindness**: Assuming built artifacts are correct without verification
+
+### What Good Debugging Looks Like
+1. Compare working state (main) vs broken state (current branch)
+2. Identify what actually changed (code? deps? build?)
+3. Test the simplest hypothesis first (build issue vs code issue)
+4. Never disable features to "fix" things - that's not fixing
+
+## Action Items for Next Attempt
+
+### Before Writing Any Code:
+- [ ] `git diff main` for all modified files
+- [ ] Check if `plugin/scripts/` artifacts are valid JavaScript
+- [ ] Compare build process: `npm run build` output on main vs current branch
+- [ ] Verify `plugin/scripts/node_modules` exists and is current
+- [ ] Test search-server.mjs in isolation: `node plugin/scripts/search-server.mjs`
+
+### If Build is Broken:
+- [ ] Check scripts/build-hooks.js for recent changes
+- [ ] Verify esbuild configuration
+- [ ] Test build on main branch, then on current branch
+- [ ] Don't modify source code until build is proven working
+
+### If Code is Broken:
+- [ ] Create minimal repro (which specific change broke it?)
+- [ ] Fix the actual bug, don't add workarounds
+- [ ] Test the fix in isolation
+
+## Conclusion
+
+This failure exemplifies "debugging by making changes" instead of "debugging by understanding". The instinct to fix symptoms (MCP errors) instead of investigating root cause (why is it broken now?) led to wasted effort and ultimately no solution.
+
+The user's frustration was justified - I was adding defensive duct tape instead of finding and fixing the real problem. This is exactly what KISS/DRY/YAGNI principles are meant to prevent.
+
+**Next time: Compare, verify, understand, THEN fix. Never disable features to make errors go away.**
@@ -0,0 +1,119 @@
+ Unified Search API Consolidation Plan
+
+ Overview
+
+ Consolidate 10 search endpoints into 6 powerful, semantic endpoints with intelligent aliasing for backward compatibility.
+
+ New Endpoint Structure
+
+ 1. /search - Unified Cross-Type Search
+
+ - Searches all record types (observations + sessions + prompts) via Chroma multi-collection search
+ - Optional type filter to narrow down
+ - Replaces: search_observations, search_sessions, search_user_prompts
+ - Params: query, response=[index|full], type, project, dateRange, limit, offset, orderBy
+
+ 2. /timeline - Unified Timeline Tool
+
+ - Supports both anchor-based and query-based modes via params
+ - If anchor → direct timeline lookup (like get_context_timeline)
+ - If query → search-first then timeline (like get_timeline_by_query)
+ - Params: anchor OR query, depth_before, depth_after, response, mode, project
+
+ 3. /decisions - Decision Observations
+
+ - Metadata-first search for type=decision observations
+ - Uses specialized search logic for precision
+ - Params: response, project, dateRange, limit, offset, orderBy
+
+ 4. /changes - Change Observations
+
+ - Metadata-first search for type=change observations
+ - Same pattern as /decisions
+
+ 5. /how-it-works - How-It-Works Concept
+
+ - Metadata-first search for concept=how-it-works observations
+ - Same pattern as concept endpoints
+
+ 6. /contextualize - Intelligent Context Builder
+
+ - Complex hybrid endpoint:
+   a. Get 7 latest decisions + 7 latest changes + 3 latest how-it-works
+   b. Find newest date across all results
+   c. Get timeline (7 before + 7 after) around that date
+   d. Merge & re-sort into single timeline (newest → oldest)
+   e. Return timeline + narratives of each concept's latest result
+ - Params: query (for contextualization), project
+
+ Implementation Phases
+
+ Phase 1: Core Unified Search (search-server.ts)
+
+ - Create search tool with Chroma multi-collection query
+ - Add type filtering support
+ - Alias old tools: search_observations → search(type=['observations'])
+
+ Phase 2: Unified Timeline (search-server.ts)
+
+ - Merge get_context_timeline + get_timeline_by_query logic
+ - Support both anchor and query params (mutually exclusive)
+ - Alias old timeline tools to new unified implementation
+
+ Phase 3: Specialized Concept Endpoints (search-server.ts)
+
+ - Create decisions, changes, how_it_works tools
+ - Use metadata-first search strategy
+ - Update find_by_type and find_by_concept to call these internally
+
+ Phase 4: Contextualize Endpoint (search-server.ts)
+
+ - Implement parallel fetching (7 decisions, 7 changes, 3 how-it-works)
+ - Find newest date, get timeline around it
+ - Merge, re-sort, extract narratives
+ - Return structured response with timeline + narratives
+
+ Phase 5: HTTP API Routes (worker-service.ts)
+
+ - Add 6 new routes: /api/search, /api/timeline, /api/decisions, /api/changes, /api/how-it-works, /api/contextualize
+ - Update old routes to alias new implementations
+ - Maintain backward compatibility
+
+ Phase 6: Chroma Multi-Collection Search (ChromaSync.ts)
+
+ - Add searchAll() method to query all collections in parallel
+ - Include source collection metadata in results
+ - Merge and rank by similarity score
+
+ Phase 7: SQLite Fallback (SessionSearch.ts)
+
+ - Add searchAll() for FTS5 fallback when Chroma unavailable
+ - Merge results from all three FTS5 tables
+
+ Phase 8: Documentation & Skill Updates
+
+ - Update mem-search skill with new endpoints
+ - Update CLAUDE.md and README.md
+ - Add examples and migration guide
+
+ Phase 9: Testing & Deployment
+
+ - Unit tests for all new tools
+ - Integration tests for aliasing
+ - Manual testing via mem-search skill
+ - Build → sync → worker restart
+
+ Key Design Decisions
+
+ ✅ Aliasing Strategy: Old endpoints call new implementations internally (zero breaking changes)
+ ✅ Unified Search: Chroma multi-collection search for true cross-type queries
+ ✅ Flexible Timeline: Single tool supports both direct and query-based modes
+ ✅ Specialized Shortcuts: /decisions, /changes, /how-it-works for common queries
+ ✅ Intelligent Context: /contextualize auto-builds rich context with narratives
+
+ Migration Impact
+
+ - Users: Zero breaking changes, old endpoints work via aliasing
+ - Codebase: Simplified from 10 conceptual endpoints to 6
+ - Performance: Improved via Chroma multi-collection search
+ - Developer UX: Cleaner, more semantic API
@@ -26,12 +26,10 @@ const WORKER_SERVICE = {
  source: 'src/services/worker-service.ts'
 };

-// DEPRECATED: MCP search server replaced by skill-based search
-// Keeping source file for reference: src/servers/search-server.ts
-// const SEARCH_SERVER = {
-//   name: 'search-server',
-//   source: 'src/servers/search-server.ts'
-// };
+const SEARCH_SERVER = {
+  name: 'search-server',
+  source: 'src/servers/search-server.ts'
+};

 async function buildHooks() {
  console.log('🔨 Building claude-mem hooks and worker service...\n');
@@ -94,6 +92,31 @@ async function buildHooks() {
    const workerStats = fs.statSync(`${hooksDir}/${WORKER_SERVICE.name}.cjs`);
    console.log(`✓ worker-service built (${(workerStats.size / 1024).toFixed(2)} KB)`);

+    // Build search server
+    console.log(`\n🔧 Building search server...`);
+    await build({
+      entryPoints: [SEARCH_SERVER.source],
+      bundle: true,
+      platform: 'node',
+      target: 'node18',
+      format: 'cjs',
+      outfile: `${hooksDir}/${SEARCH_SERVER.name}.cjs`,
+      minify: true,
+      logLevel: 'error',
+      external: ['better-sqlite3'],
+      define: {
+        '__DEFAULT_PACKAGE_VERSION__': `"${version}"`
+      },
+      banner: {
+        js: '#!/usr/bin/env node'
+      }
+    });
+
+    // Make search server executable
+    fs.chmodSync(`${hooksDir}/${SEARCH_SERVER.name}.cjs`, 0o755);
+    const searchServerStats = fs.statSync(`${hooksDir}/${SEARCH_SERVER.name}.cjs`);
+    console.log(`✓ search-server built (${(searchServerStats.size / 1024).toFixed(2)} KB)`);
+
    // Build each hook
    for (const hook of HOOKS) {
      console.log(`\n🔧 Building ${hook.name}...`);
@@ -126,14 +149,11 @@ async function buildHooks() {
      console.log(`✓ ${hook.name} built (${sizeInKB} KB)`);
    }

-    // DEPRECATED: MCP search server no longer built (replaced by skill-based search)
-    // Search functionality now provided via HTTP API + search skill
-    // Source file kept for reference: src/servers/search-server.ts
-
-    console.log('\n✅ All hooks and worker service built successfully!');
+    console.log('\n✅ All hooks, worker service, and search server built successfully!');
    console.log(`   Output: ${hooksDir}/`);
    console.log(`   - Hooks: *-hook.js`);
    console.log(`   - Worker: worker-service.cjs`);
+    console.log(`   - Search Server: search-server.cjs`);
    console.log(`   - Skills: plugin/skills/`);
    console.log('\n💡 Note: Dependencies will be auto-installed on first hook execution');

@@ -0,0 +1,273 @@
+#!/usr/bin/env node
+
+/**
+ * Endless Mode Token Economics Calculator
+ *
+ * Simulates the recursive/cumulative token savings from Endless Mode by
+ * "playing the tape through" with real observation data from SQLite.
+ *
+ * Key Insight:
+ * - Discovery tokens are ALWAYS spent (creating observations)
+ * - But Endless Mode feeds compressed observations as context instead of full tool outputs
+ * - Savings compound recursively - each tool benefits from ALL previous compressions
+ */
+
+const observationsData = [{"id":10136,"type":"decision","title":"Token Accounting Function for Recursive Continuation Pattern","discovery_tokens":4037,"created_at_epoch":1763360747429,"compressed_size":1613},
+{"id":10135,"type":"discovery","title":"Sequential Thinking Analysis of Token Economics Calculator","discovery_tokens":1439,"created_at_epoch":1763360651617,"compressed_size":1812},
+{"id":10134,"type":"discovery","title":"Recent Context Query Execution","discovery_tokens":1273,"created_at_epoch":1763360646273,"compressed_size":1228},
+{"id":10133,"type":"discovery","title":"Token Data Query Execution and Historical Context","discovery_tokens":11878,"created_at_epoch":1763360642485,"compressed_size":1924},
+{"id":10132,"type":"discovery","title":"Token Data Query and Script Validation Request","discovery_tokens":4167,"created_at_epoch":1763360628269,"compressed_size":903},
+{"id":10131,"type":"discovery","title":"Endless Mode Token Economics Analysis Output: Complete Infrastructure Impact","discovery_tokens":2458,"created_at_epoch":1763360553238,"compressed_size":2166},
+{"id":10130,"type":"change","title":"Integration of Actual Compute Savings Analysis into Main Execution Flow","discovery_tokens":11031,"created_at_epoch":1763360545347,"compressed_size":1032},
+{"id":10129,"type":"discovery","title":"Prompt Caching Economics: User Cost vs. Anthropic Compute Cost Divergence","discovery_tokens":20059,"created_at_epoch":1763360540854,"compressed_size":1802},
+{"id":10128,"type":"discovery","title":"Token Caching Cost Analysis Across AI Model Providers","discovery_tokens":3506,"created_at_epoch":1763360478133,"compressed_size":1245},
+{"id":10127,"type":"discovery","title":"Endless Mode Token Economics Calculator Successfully Integrated Prompt Caching Cost Model","discovery_tokens":3481,"created_at_epoch":1763360384055,"compressed_size":2444},
+{"id":10126,"type":"bugfix","title":"Fix Return Statement Variable Names in playTheTapeThrough Function","discovery_tokens":8326,"created_at_epoch":1763360374566,"compressed_size":1250},
+{"id":10125,"type":"change","title":"Redesign Timeline Display to Show Fresh/Cached Token Breakdown and Real Dollar Costs","discovery_tokens":12999,"created_at_epoch":1763360368843,"compressed_size":2004},
+{"id":10124,"type":"change","title":"Replace Estimated Cost Model with Actual Caching-Based Costs in Anthropic Scale Analysis","discovery_tokens":12867,"created_at_epoch":1763360361147,"compressed_size":2064},
+{"id":10123,"type":"change","title":"Pivot Session Length Comparison Table from Token to Cost Metrics","discovery_tokens":9746,"created_at_epoch":1763360352992,"compressed_size":1652},
+{"id":10122,"type":"change","title":"Add Dual Reporting: Token Count vs Actual Cost in Comparison Output","discovery_tokens":9602,"created_at_epoch":1763360346495,"compressed_size":1640},
+{"id":10121,"type":"change","title":"Apply Prompt Caching Cost Model to Endless Mode Calculation Function","discovery_tokens":9963,"created_at_epoch":1763360339238,"compressed_size":2003},
+{"id":10120,"type":"change","title":"Integrate Prompt Caching Cost Calculations into Without-Endless-Mode Function","discovery_tokens":8652,"created_at_epoch":1763360332046,"compressed_size":1701},
+{"id":10119,"type":"change","title":"Display Prompt Caching Pricing in Initial Calculator Output","discovery_tokens":6669,"created_at_epoch":1763360325882,"compressed_size":1188},
+{"id":10118,"type":"change","title":"Add Prompt Caching Pricing Model to Token Economics Calculator","discovery_tokens":10433,"created_at_epoch":1763360320552,"compressed_size":1264},
+{"id":10117,"type":"discovery","title":"Claude API Prompt Caching Cost Optimization Factor","discovery_tokens":3439,"created_at_epoch":1763360210175,"compressed_size":1142},
+{"id":10116,"type":"discovery","title":"Endless Mode Token Economics Verified at Scale","discovery_tokens":2855,"created_at_epoch":1763360144039,"compressed_size":2184},
+{"id":10115,"type":"feature","title":"Token Economics Calculator for Endless Mode Sessions","discovery_tokens":13468,"created_at_epoch":1763360134068,"compressed_size":1858},
+{"id":10114,"type":"decision","title":"Token Accounting for Recursive Session Continuations","discovery_tokens":3550,"created_at_epoch":1763360052317,"compressed_size":1478},
+{"id":10113,"type":"discovery","title":"Performance and Token Optimization Impact Analysis for Endless Mode","discovery_tokens":3464,"created_at_epoch":1763359862175,"compressed_size":1259},
+{"id":10112,"type":"change","title":"Endless Mode Blocking Hooks & Transcript Transformation Plan Document Created","discovery_tokens":17312,"created_at_epoch":1763359465307,"compressed_size":2181},
+{"id":10111,"type":"change","title":"Plan Document Creation for Morning Implementation","discovery_tokens":3652,"created_at_epoch":1763359347166,"compressed_size":843},
+{"id":10110,"type":"decision","title":"Blocking vs Non-Blocking Behavior by Mode","discovery_tokens":3652,"created_at_epoch":1763359347165,"compressed_size":797},
+{"id":10109,"type":"decision","title":"Tool Use and Observation Processing Architecture: Non-Blocking vs Blocking","discovery_tokens":3472,"created_at_epoch":1763359247045,"compressed_size":1349},
+{"id":10108,"type":"feature","title":"SessionManager.getMessageIterator implements event-driven async generator with graceful abort handling","discovery_tokens":2417,"created_at_epoch":1763359189299,"compressed_size":2016},
+{"id":10107,"type":"feature","title":"SessionManager implements event-driven session lifecycle with auto-initialization and zero-latency queue notifications","discovery_tokens":4734,"created_at_epoch":1763359165608,"compressed_size":2781},
+{"id":10106,"type":"discovery","title":"Two distinct uses of transcript data: live data flow vs session initialization","discovery_tokens":2933,"created_at_epoch":1763359156448,"compressed_size":2015},
+{"id":10105,"type":"discovery","title":"Transcript initialization pattern identified for compressed context on session resume","discovery_tokens":2933,"created_at_epoch":1763359156447,"compressed_size":2536},
+{"id":10104,"type":"feature","title":"SDKAgent implements event-driven message generator with continuation prompt logic and Endless Mode integration","discovery_tokens":6148,"created_at_epoch":1763359140399,"compressed_size":3241},
+{"id":10103,"type":"discovery","title":"Endless Mode architecture documented with phased implementation plan and context economics","discovery_tokens":5296,"created_at_epoch":1763359127954,"compressed_size":3145},
+{"id":10102,"type":"feature","title":"Save hook enhanced to extract and forward tool_use_id for Endless Mode linking","discovery_tokens":3294,"created_at_epoch":1763359115848,"compressed_size":2125},
+{"id":10101,"type":"feature","title":"TransformLayer implements Endless Mode context compression via observation substitution","discovery_tokens":4637,"created_at_epoch":1763359108317,"compressed_size":2629},
+{"id":10100,"type":"feature","title":"EndlessModeConfig implemented for loading Endless Mode settings from files and environment","discovery_tokens":2313,"created_at_epoch":1763359099972,"compressed_size":2125},
+{"id":10098,"type":"change","title":"User prompts wrapped with semantic XML structure in buildInitPrompt and buildContinuationPrompt","discovery_tokens":7806,"created_at_epoch":1763359091460,"compressed_size":1585},
+{"id":10099,"type":"discovery","title":"Session persistence mechanism relies on SDK internal state without context reload","discovery_tokens":7806,"created_at_epoch":1763359091460,"compressed_size":1883},
+{"id":10097,"type":"change","title":"Worker service session init now extracts userPrompt and promptNumber from request body","discovery_tokens":7806,"created_at_epoch":1763359091459,"compressed_size":1148},
+{"id":10096,"type":"feature","title":"SessionManager enhanced to accept dynamic userPrompt updates during multi-turn conversations","discovery_tokens":7806,"created_at_epoch":1763359091457,"compressed_size":1528},
+{"id":10095,"type":"discovery","title":"Five lifecycle hooks integrate claude-mem at critical session boundaries","discovery_tokens":6625,"created_at_epoch":1763359074808,"compressed_size":1570},
+{"id":10094,"type":"discovery","title":"PostToolUse hook is real-time observation creation point, not delayed processing","discovery_tokens":6625,"created_at_epoch":1763359074807,"compressed_size":2371},
+{"id":10093,"type":"discovery","title":"PostToolUse hook timing and compression integration options explored","discovery_tokens":1696,"created_at_epoch":1763359062088,"compressed_size":1605},
+{"id":10092,"type":"discovery","title":"Transcript transformation strategy for endless mode identified","discovery_tokens":6112,"created_at_epoch":1763359057563,"compressed_size":1968},
+{"id":10091,"type":"decision","title":"Finalized Transcript Compression Implementation Strategy","discovery_tokens":1419,"created_at_epoch":1763358943803,"compressed_size":1556},
+{"id":10090,"type":"discovery","title":"UserPromptSubmit Hook as Compression Integration Point","discovery_tokens":1546,"created_at_epoch":1763358931936,"compressed_size":1621},
+{"id":10089,"type":"decision","title":"Hypothesis 5 Selected: UserPromptSubmit Hook for Transcript Compression","discovery_tokens":1465,"created_at_epoch":1763358920209,"compressed_size":1918}];
+
+// Estimate original tool output size from discovery tokens
+// Heuristic: discovery_tokens roughly correlates with original content size
+// Assumption: If it took 10k tokens to analyze, original was probably 15-30k tokens
+function estimateOriginalToolOutputSize(discoveryTokens) {
+  // Conservative multiplier: 2x (original content was 2x the discovery cost)
+  // This accounts for: reading the tool output + analyzing it + generating observation
+  return discoveryTokens * 2;
+}
+
+// Convert compressed_size (character count) to approximate token count
+// Rough heuristic: 1 token ≈ 4 characters for English text
+function charsToTokens(chars) {
+  return Math.ceil(chars / 4);
+}
+
+/**
+ * Simulate session WITHOUT Endless Mode (current behavior)
+ * Each continuation carries ALL previous full tool outputs in context
+ */
+function calculateWithoutEndlessMode(observations) {
+  let cumulativeContextTokens = 0;
+  let totalDiscoveryTokens = 0;
+  let totalContinuationTokens = 0;
+  const timeline = [];
+
+  observations.forEach((obs, index) => {
+    const toolNumber = index + 1;
+    const originalToolSize = estimateOriginalToolOutputSize(obs.discovery_tokens);
+
+    // Discovery cost (creating observation from full tool output)
+    const discoveryCost = obs.discovery_tokens;
+    totalDiscoveryTokens += discoveryCost;
+
+    // Continuation cost: Re-process ALL previous tool outputs + current one
+    // This is the key recursive cost
+    cumulativeContextTokens += originalToolSize;
+    const continuationCost = cumulativeContextTokens;
+    totalContinuationTokens += continuationCost;
+
+    timeline.push({
+      tool: toolNumber,
+      obsId: obs.id,
+      title: obs.title.substring(0, 60),
+      originalSize: originalToolSize,
+      discoveryCost,
+      contextSize: cumulativeContextTokens,
+      continuationCost,
+      totalCostSoFar: totalDiscoveryTokens + totalContinuationTokens
+    });
+  });
+
+  return {
+    totalDiscoveryTokens,
+    totalContinuationTokens,
+    totalTokens: totalDiscoveryTokens + totalContinuationTokens,
+    timeline
+  };
+}
+
+/**
+ * Simulate session WITH Endless Mode
+ * Each continuation carries ALL previous COMPRESSED observations in context
+ */
+function calculateWithEndlessMode(observations) {
+  let cumulativeContextTokens = 0;
+  let totalDiscoveryTokens = 0;
+  let totalContinuationTokens = 0;
+  const timeline = [];
+
+  observations.forEach((obs, index) => {
+    const toolNumber = index + 1;
+    const originalToolSize = estimateOriginalToolOutputSize(obs.discovery_tokens);
+    const compressedSize = charsToTokens(obs.compressed_size);
+
+    // Discovery cost (same as without Endless Mode - still need to create observation)
+    const discoveryCost = obs.discovery_tokens;
+    totalDiscoveryTokens += discoveryCost;
+
+    // KEY DIFFERENCE: Add COMPRESSED size to context, not original size
+    cumulativeContextTokens += compressedSize;
+    const continuationCost = cumulativeContextTokens;
+    totalContinuationTokens += continuationCost;
+
+    const compressionRatio = ((originalToolSize - compressedSize) / originalToolSize * 100).toFixed(1);
+
+    timeline.push({
+      tool: toolNumber,
+      obsId: obs.id,
+      title: obs.title.substring(0, 60),
+      originalSize: originalToolSize,
+      compressedSize,
+      compressionRatio: `${compressionRatio}%`,
+      discoveryCost,
+      contextSize: cumulativeContextTokens,
+      continuationCost,
+      totalCostSoFar: totalDiscoveryTokens + totalContinuationTokens
+    });
+  });
+
+  return {
+    totalDiscoveryTokens,
+    totalContinuationTokens,
+    totalTokens: totalDiscoveryTokens + totalContinuationTokens,
+    timeline
+  };
+}
+
+/**
+ * Play the tape through - show token-by-token progression
+ */
+function playTheTapeThrough(observations) {
+  console.log('\n' + '='.repeat(100));
+  console.log('ENDLESS MODE TOKEN ECONOMICS CALCULATOR');
+  console.log('Playing the tape through with REAL observation data');
+  console.log('='.repeat(100) + '\n');
+
+  console.log(`📊 Dataset: ${observations.length} observations from live sessions\n`);
+
+  // Calculate both scenarios
+  const without = calculateWithoutEndlessMode(observations);
+  const withMode = calculateWithEndlessMode(observations);
+
+  // Show first 10 tools from each scenario side by side
+  console.log('🎬 TAPE PLAYBACK: First 10 Tools\n');
+  console.log('WITHOUT Endless Mode (Current) | WITH Endless Mode (Proposed)');
+  console.log('-'.repeat(100));
+
+  for (let i = 0; i < Math.min(10, observations.length); i++) {
+    const w = without.timeline[i];
+    const e = withMode.timeline[i];
+
+    console.log(`\nTool #${w.tool}: ${w.title}`);
+    console.log(`  Original: ${w.originalSize.toLocaleString()}t | Compressed: ${e.compressedSize.toLocaleString()}t (${e.compressionRatio} saved)`);
+    console.log(`  Context:  ${w.contextSize.toLocaleString()}t | Context:    ${e.contextSize.toLocaleString()}t`);
+    console.log(`  Total:    ${w.totalCostSoFar.toLocaleString()}t | Total:      ${e.totalCostSoFar.toLocaleString()}t`);
+  }
+
+  // Summary table
+  console.log('\n' + '='.repeat(100));
+  console.log('📈 FINAL TOTALS\n');
+
+  console.log('WITHOUT Endless Mode (Current):');
+  console.log(`  Discovery tokens:    ${without.totalDiscoveryTokens.toLocaleString()}t (creating observations)`);
+  console.log(`  Continuation tokens: ${without.totalContinuationTokens.toLocaleString()}t (context accumulation)`);
+  console.log(`  TOTAL TOKENS:        ${without.totalTokens.toLocaleString()}t`);
+
+  console.log('\nWITH Endless Mode:');
+  console.log(`  Discovery tokens:    ${withMode.totalDiscoveryTokens.toLocaleString()}t (same - still create observations)`);
+  console.log(`  Continuation tokens: ${withMode.totalContinuationTokens.toLocaleString()}t (COMPRESSED context)`);
+  console.log(`  TOTAL TOKENS:        ${withMode.totalTokens.toLocaleString()}t`);
+
+  const tokensSaved = without.totalTokens - withMode.totalTokens;
+  const percentSaved = (tokensSaved / without.totalTokens * 100).toFixed(1);
+
+  console.log('\n💰 SAVINGS:');
+  console.log(`  Tokens saved:        ${tokensSaved.toLocaleString()}t`);
+  console.log(`  Percentage saved:    ${percentSaved}%`);
+  console.log(`  Efficiency gain:     ${(without.totalTokens / withMode.totalTokens).toFixed(2)}x`);
+
+  // Anthropic scale calculation
+  console.log('\n' + '='.repeat(100));
+  console.log('🌍 ANTHROPIC SCALE IMPACT\n');
+
+  // Conservative assumptions
+  const activeUsers = 100000; // Claude Code users
+  const sessionsPerWeek = 10; // Per user
+  const toolsPerSession = observations.length; // Use our actual data
+  const weeklyToolUses = activeUsers * sessionsPerWeek * toolsPerSession;
+
+  const avgTokensPerToolWithout = without.totalTokens / observations.length;
+  const avgTokensPerToolWith = withMode.totalTokens / observations.length;
+
+  const weeklyTokensWithout = weeklyToolUses * avgTokensPerToolWithout;
+  const weeklyTokensWith = weeklyToolUses * avgTokensPerToolWith;
+  const weeklyTokensSaved = weeklyTokensWithout - weeklyTokensWith;
+
+  console.log('Assumptions:');
+  console.log(`  Active Claude Code users:  ${activeUsers.toLocaleString()}`);
+  console.log(`  Sessions per user/week:    ${sessionsPerWeek}`);
+  console.log(`  Tools per session:         ${toolsPerSession}`);
+  console.log(`  Weekly tool uses:          ${weeklyToolUses.toLocaleString()}`);
+
+  console.log('\nWeekly Compute:');
+  console.log(`  Without Endless Mode:      ${(weeklyTokensWithout / 1e9).toFixed(2)} billion tokens`);
+  console.log(`  With Endless Mode:         ${(weeklyTokensWith / 1e9).toFixed(2)} billion tokens`);
+  console.log(`  Weekly savings:            ${(weeklyTokensSaved / 1e9).toFixed(2)} billion tokens (${percentSaved}%)`);
+
+  const annualTokensSaved = weeklyTokensSaved * 52;
+  console.log(`  Annual savings:            ${(annualTokensSaved / 1e12).toFixed(2)} TRILLION tokens`);
+
+  console.log('\n💡 What this means:');
+  console.log(`  • ${percentSaved}% reduction in Claude Code inference costs`);
+  console.log(`  • ${(without.totalTokens / withMode.totalTokens).toFixed(1)}x more users served with same infrastructure`);
+  console.log(`  • Massive energy/compute savings at scale`);
+  console.log(`  • Longer sessions = better UX without economic penalty`);
+
+  console.log('\n' + '='.repeat(100) + '\n');
+
+  return {
+    without,
+    withMode,
+    tokensSaved,
+    percentSaved,
+    weeklyTokensSaved,
+    annualTokensSaved
+  };
+}
+
+// Run the calculation
+playTheTapeThrough(observationsData);
@@ -38,6 +38,7 @@ import { stdin } from 'process';
 import { SessionStore } from '../services/sqlite/SessionStore.js';
 import { createHookResponse } from './hook-response.js';
 import { ensureWorkerRunning, getWorkerPort } from '../shared/worker-utils.js';
+import { silentDebug } from '../utils/silent-debug.js';

 export interface UserPromptSubmitInput {
  session_id: string;
@@ -55,8 +56,27 @@ async function newHook(input?: UserPromptSubmitInput): Promise<void> {
  }

  const { session_id, cwd, prompt } = input;
+
+  // Debug: Log what we received
+  silentDebug('[new-hook] Input received', {
+    session_id,
+    cwd,
+    cwd_type: typeof cwd,
+    cwd_length: cwd?.length,
+    has_cwd: !!cwd,
+    prompt_length: prompt?.length
+  });
+
  const project = path.basename(cwd);

+  silentDebug('[new-hook] Project extracted', {
+    project,
+    project_type: typeof project,
+    project_length: project?.length,
+    is_empty: project === '',
+    cwd_was: cwd
+  });
+
  // Ensure worker is running
  await ensureWorkerRunning();

@@ -13,7 +13,8 @@ import {

 /**
 * Search interface for session-based memory
- * Provides FTS5 full-text search and structured queries for sessions, observations, and summaries
+ * Provides filter-only structured queries for sessions, observations, and user prompts
+ * Vector search is handled by ChromaDB - this class only supports filtering without query text
 */
 export class SessionSearch {
  private db: Database.Database;
@@ -31,7 +32,18 @@ export class SessionSearch {
  }

  /**
-   * Ensure FTS5 tables exist (inline migration)
+   * Ensure FTS5 tables exist (backward compatibility only - no longer used for search)
+   *
+   * FTS5 tables are maintained for backward compatibility but not used for search.
+   * Vector search (Chroma) is now the primary search mechanism.
+   *
+   * Retention Rationale:
+   * - Prevents breaking existing installations with FTS5 tables
+   * - Allows graceful migration path for users
+   * - Tables maintained but search paths removed
+   * - Triggers still fire to keep tables synchronized
+   *
+   * TODO: Remove FTS5 infrastructure in future major version (v7.0.0)
   */
  private ensureFTSTables(): void {
    try {
@@ -134,22 +146,6 @@ export class SessionSearch {
    }
  }

-  /**
-   * Escape FTS5 special characters in user input
-   * 
-   * FTS5 uses double quotes for phrase searches and treats certain characters
-   * as operators (*, AND, OR, NOT, parentheses, etc.). To prevent injection,
-   * we wrap user input in double quotes and escape internal quotes by doubling them.
-   * This converts any user input into a safe phrase search.
-   * 
-   * @param text - User input to escape for FTS5 MATCH queries
-   * @returns Safely escaped FTS5 query string
-   */
-  private escapeFTS5(text: string): string {
-    // Escape internal double quotes by doubling them (FTS5 standard)
-    // Then wrap the entire string in double quotes for phrase search
-    return `"${text.replace(/"/g, '""')}"`;
-  }

  /**
   * Build WHERE clause for structured filters
@@ -243,118 +239,78 @@ export class SessionSearch {
  }

  /**
-   * Search observations using FTS5 full-text search
+   * Search observations using filter-only direct SQLite query.
+   * Vector search is handled by ChromaDB - this only supports filtering without query text.
   */
-  searchObservations(query: string, options: SearchOptions = {}): ObservationSearchResult[] {
+  searchObservations(query: string | undefined, options: SearchOptions = {}): ObservationSearchResult[] {
    const params: any[] = [];
    const { limit = 50, offset = 0, orderBy = 'relevance', ...filters } = options;

-    // Build FTS5 match query
-    const ftsQuery = this.escapeFTS5(query);
-    params.push(ftsQuery);
+    // FILTER-ONLY PATH: When no query text, query table directly
+    // This enables date filtering which Chroma cannot do (requires direct SQLite access)
+    if (!query) {
+      const filterClause = this.buildFilterClause(filters, params, 'o');
+      if (!filterClause) {
+        throw new Error('Either query or filters required for search');
+      }

-    // Build filter conditions
-    const filterClause = this.buildFilterClause(filters, params, 'o');
-    const whereClause = filterClause ? `AND ${filterClause}` : '';
+      const orderClause = this.buildOrderClause(orderBy, false);

-    // Build ORDER BY
-    const orderClause = this.buildOrderClause(orderBy, true);
+      const sql = `
+        SELECT o.*, o.discovery_tokens
+        FROM observations o
+        WHERE ${filterClause}
+        ${orderClause}
+        LIMIT ? OFFSET ?
+      `;

-    // Main query with FTS5
-    const sql = `
-      SELECT
-        o.*,
-        o.discovery_tokens,
-        observations_fts.rank as rank
-      FROM observations o
-      JOIN observations_fts ON o.id = observations_fts.rowid
-      WHERE observations_fts MATCH ?
-      ${whereClause}
-      ${orderClause}
-      LIMIT ? OFFSET ?
-    `;
-
-    params.push(limit, offset);
-
-    const results = this.db.prepare(sql).all(...params) as ObservationSearchResult[];
-
-    // Normalize rank to score (0-1, higher is better)
-    if (results.length > 0) {
-      const minRank = Math.min(...results.map(r => r.rank || 0));
-      const maxRank = Math.max(...results.map(r => r.rank || 0));
-      const range = maxRank - minRank || 1;
-
-      results.forEach(r => {
-        if (r.rank !== undefined) {
-          // Invert rank (lower rank = better match) and normalize to 0-1
-          r.score = 1 - ((r.rank - minRank) / range);
-        }
-      });
+      params.push(limit, offset);
+      return this.db.prepare(sql).all(...params) as ObservationSearchResult[];
    }

-    return results;
+    // Vector search with query text should be handled by ChromaDB
+    // This method only supports filter-only queries (query=undefined)
+    console.warn('[SessionSearch] Text search not supported - use ChromaDB for vector search');
+    return [];
  }

  /**
-   * Search session summaries using FTS5 full-text search
+   * Search session summaries using filter-only direct SQLite query.
+   * Vector search is handled by ChromaDB - this only supports filtering without query text.
   */
-  searchSessions(query: string, options: SearchOptions = {}): SessionSummarySearchResult[] {
+  searchSessions(query: string | undefined, options: SearchOptions = {}): SessionSummarySearchResult[] {
    const params: any[] = [];
    const { limit = 50, offset = 0, orderBy = 'relevance', ...filters } = options;

-    // Build FTS5 match query
-    const ftsQuery = this.escapeFTS5(query);
-    params.push(ftsQuery);
+    // FILTER-ONLY PATH: When no query text, query session_summaries table directly
+    if (!query) {
+      const filterOptions = { ...filters };
+      delete filterOptions.type;
+      const filterClause = this.buildFilterClause(filterOptions, params, 's');
+      if (!filterClause) {
+        throw new Error('Either query or filters required for search');
+      }

-    // Build filter conditions (without type filter - not applicable to summaries)
-    const filterOptions = { ...filters };
-    delete filterOptions.type;
-    const filterClause = this.buildFilterClause(filterOptions, params, 's');
-    const whereClause = filterClause ? `AND ${filterClause}` : '';
+      const orderClause = orderBy === 'date_asc'
+        ? 'ORDER BY s.created_at_epoch ASC'
+        : 'ORDER BY s.created_at_epoch DESC';

-    // Note: session_summaries don't have files_read/files_modified in the same way
-    // We'll need to adjust the filter clause
-    const adjustedWhereClause = whereClause.replace(/files_read/g, 'files_read').replace(/files_modified/g, 'files_edited');
+      const sql = `
+        SELECT s.*, s.discovery_tokens
+        FROM session_summaries s
+        WHERE ${filterClause}
+        ${orderClause}
+        LIMIT ? OFFSET ?
+      `;

-    // Build ORDER BY
-    const orderClause = orderBy === 'relevance'
-      ? 'ORDER BY session_summaries_fts.rank ASC'
-      : orderBy === 'date_asc'
-      ? 'ORDER BY s.created_at_epoch ASC'
-      : 'ORDER BY s.created_at_epoch DESC';
-
-    // Main query with FTS5
-    const sql = `
-      SELECT
-        s.*,
-        s.discovery_tokens,
-        session_summaries_fts.rank as rank
-      FROM session_summaries s
-      JOIN session_summaries_fts ON s.id = session_summaries_fts.rowid
-      WHERE session_summaries_fts MATCH ?
-      ${adjustedWhereClause}
-      ${orderClause}
-      LIMIT ? OFFSET ?
-    `;
-
-    params.push(limit, offset);
-
-    const results = this.db.prepare(sql).all(...params) as SessionSummarySearchResult[];
-
-    // Normalize rank to score
-    if (results.length > 0) {
-      const minRank = Math.min(...results.map(r => r.rank || 0));
-      const maxRank = Math.max(...results.map(r => r.rank || 0));
-      const range = maxRank - minRank || 1;
-
-      results.forEach(r => {
-        if (r.rank !== undefined) {
-          r.score = 1 - ((r.rank - minRank) / range);
-        }
-      });
+      params.push(limit, offset);
+      return this.db.prepare(sql).all(...params) as SessionSummarySearchResult[];
    }

-    return results;
+    // Vector search with query text should be handled by ChromaDB
+    // This method only supports filter-only queries (query=undefined)
+    console.warn('[SessionSearch] Text search not supported - use ChromaDB for vector search');
+    return [];
  }

  /**
@@ -485,16 +441,13 @@ export class SessionSearch {
  }

  /**
-   * Search user prompts with full-text search
+   * Search user prompts using filter-only direct SQLite query.
+   * Vector search is handled by ChromaDB - this only supports filtering without query text.
   */
-  searchUserPrompts(query: string, options: SearchOptions = {}): UserPromptSearchResult[] {
+  searchUserPrompts(query: string | undefined, options: SearchOptions = {}): UserPromptSearchResult[] {
    const params: any[] = [];
    const { limit = 20, offset = 0, orderBy = 'relevance', ...filters } = options;

-    // Build FTS5 match query
-    const ftsQuery = this.escapeFTS5(query);
-    params.push(ftsQuery);
-
    // Build filter conditions (join with sdk_sessions for project filtering)
    const baseConditions: string[] = [];
    if (filters.project) {
@@ -516,47 +469,34 @@ export class SessionSearch {
      }
    }

-    const whereClause = baseConditions.length > 0 ? `AND ${baseConditions.join(' AND ')}` : '';
+    // FILTER-ONLY PATH: When no query text, query user_prompts table directly
+    if (!query) {
+      if (baseConditions.length === 0) {
+        throw new Error('Either query or filters required for search');
+      }

-    // Build ORDER BY
-    const orderClause = orderBy === 'relevance'
-      ? 'ORDER BY user_prompts_fts.rank ASC'
-      : orderBy === 'date_asc'
-      ? 'ORDER BY up.created_at_epoch ASC'
-      : 'ORDER BY up.created_at_epoch DESC';
+      const whereClause = `WHERE ${baseConditions.join(' AND ')}`;
+      const orderClause = orderBy === 'date_asc'
+        ? 'ORDER BY up.created_at_epoch ASC'
+        : 'ORDER BY up.created_at_epoch DESC';

-    // Main query with FTS5 (join sdk_sessions for project filtering)
-    const sql = `
-      SELECT
-        up.*,
-        user_prompts_fts.rank as rank
-      FROM user_prompts up
-      JOIN user_prompts_fts ON up.id = user_prompts_fts.rowid
-      JOIN sdk_sessions s ON up.claude_session_id = s.claude_session_id
-      WHERE user_prompts_fts MATCH ?
-      ${whereClause}
-      ${orderClause}
-      LIMIT ? OFFSET ?
-    `;
+      const sql = `
+        SELECT up.*
+        FROM user_prompts up
+        JOIN sdk_sessions s ON up.claude_session_id = s.claude_session_id
+        ${whereClause}
+        ${orderClause}
+        LIMIT ? OFFSET ?
+      `;

-    params.push(limit, offset);
-
-    const results = this.db.prepare(sql).all(...params) as UserPromptSearchResult[];
-
-    // Normalize rank to score
-    if (results.length > 0) {
-      const minRank = Math.min(...results.map(r => r.rank || 0));
-      const maxRank = Math.max(...results.map(r => r.rank || 0));
-      const range = maxRank - minRank || 1;
-
-      results.forEach(r => {
-        if (r.rank !== undefined) {
-          r.score = 1 - ((r.rank - minRank) / range);
-        }
-      });
+      params.push(limit, offset);
+      return this.db.prepare(sql).all(...params) as UserPromptSearchResult[];
    }

-    return results;
+    // Vector search with query text should be handled by ChromaDB
+    // This method only supports filter-only queries (query=undefined)
+    console.warn('[SessionSearch] Text search not supported - use ChromaDB for vector search');
+    return [];
  }

  /**
@@ -1013,6 +1013,17 @@ export class SessionStore {

    // If lastInsertRowid is 0, insert was ignored (session exists), so fetch existing ID
    if (result.lastInsertRowid === 0 || result.changes === 0) {
+      // Session exists - UPDATE project and user_prompt if we have non-empty values
+      // This fixes the bug where SAVE hook creates session with empty project,
+      // then NEW hook can't update it because INSERT OR IGNORE skips the insert
+      if (project && project.trim() !== '') {
+        this.db.prepare(`
+          UPDATE sdk_sessions
+          SET project = ?, user_prompt = ?
+          WHERE claude_session_id = ?
+        `).run(project, userPrompt, claudeSessionId);
+      }
+
      const selectStmt = this.db.prepare(`
        SELECT id FROM sdk_sessions WHERE claude_session_id = ? LIMIT 1
      `);
@@ -155,6 +155,12 @@ export class WorkerService {
    this.app.get('/api/observations', this.handleGetObservations.bind(this));
    this.app.get('/api/summaries', this.handleGetSummaries.bind(this));
    this.app.get('/api/prompts', this.handleGetPrompts.bind(this));
+
+    // Fetch by ID
+    this.app.get('/api/observation/:id', this.handleGetObservationById.bind(this));
+    this.app.get('/api/session/:id', this.handleGetSessionById.bind(this));
+    this.app.get('/api/prompt/:id', this.handleGetPromptById.bind(this));
+
    this.app.get('/api/stats', this.handleGetStats.bind(this));
    this.app.get('/api/processing-status', this.handleGetProcessingStatus.bind(this));
    this.app.post('/api/processing', this.handleSetProcessing.bind(this));
@@ -168,6 +174,14 @@ export class WorkerService {
    this.app.post('/api/mcp/toggle', this.handleToggleMcp.bind(this));

    // Search API endpoints (for skill-based search)
+    // Unified endpoints (new consolidated API)
+    this.app.get('/api/search', this.handleUnifiedSearch.bind(this));
+    this.app.get('/api/timeline', this.handleUnifiedTimeline.bind(this));
+    this.app.get('/api/decisions', this.handleDecisions.bind(this));
+    this.app.get('/api/changes', this.handleChanges.bind(this));
+    this.app.get('/api/how-it-works', this.handleHowItWorks.bind(this));
+
+    // Backward compatibility endpoints (use /api/search with type param instead)
    this.app.get('/api/search/observations', this.handleSearchObservations.bind(this));
    this.app.get('/api/search/sessions', this.handleSearchSessions.bind(this));
    this.app.get('/api/search/prompts', this.handleSearchPrompts.bind(this));
@@ -223,7 +237,7 @@ export class WorkerService {
    await this.dbManager.initialize();

    // Connect to MCP search server
-    const searchServerPath = path.join(__dirname, '..', '..', 'plugin', 'scripts', 'search-server.mjs');
+    const searchServerPath = path.join(__dirname, '..', '..', 'plugin', 'scripts', 'search-server.cjs');
    const transport = new StdioClientTransport({
      command: 'node',
      args: [searchServerPath],
@@ -322,9 +336,11 @@ export class WorkerService {

    // Send initial processing status (based on queue depth + active generators)
    const isProcessing = this.sessionManager.isAnySessionProcessing();
+    const queueDepth = this.sessionManager.getTotalActiveWork(); // Includes queued + actively processing
    this.sseBroadcaster.broadcast({
      type: 'processing_status',
-      isProcessing
+      isProcessing,
+      queueDepth
    });
  }

@@ -657,6 +673,87 @@ export class WorkerService {
    }
  }

+  /**
+   * Get observation by ID
+   * GET /api/observation/:id
+   */
+  private handleGetObservationById(req: Request, res: Response): void {
+    try {
+      const id = parseInt(req.params.id, 10);
+      if (isNaN(id)) {
+        res.status(400).json({ error: 'Invalid observation ID' });
+        return;
+      }
+
+      const store = this.dbManager.getSessionStore();
+      const observation = store.getObservationById(id);
+
+      if (!observation) {
+        res.status(404).json({ error: `Observation #${id} not found` });
+        return;
+      }
+
+      res.json(observation);
+    } catch (error) {
+      logger.failure('WORKER', 'Get observation by ID failed', {}, error as Error);
+      res.status(500).json({ error: (error as Error).message });
+    }
+  }
+
+  /**
+   * Get session by ID
+   * GET /api/session/:id
+   */
+  private handleGetSessionById(req: Request, res: Response): void {
+    try {
+      const id = parseInt(req.params.id, 10);
+      if (isNaN(id)) {
+        res.status(400).json({ error: 'Invalid session ID' });
+        return;
+      }
+
+      const store = this.dbManager.getSessionStore();
+      const sessions = store.getSessionSummariesByIds([id]);
+
+      if (sessions.length === 0) {
+        res.status(404).json({ error: `Session #${id} not found` });
+        return;
+      }
+
+      res.json(sessions[0]);
+    } catch (error) {
+      logger.failure('WORKER', 'Get session by ID failed', {}, error as Error);
+      res.status(500).json({ error: (error as Error).message });
+    }
+  }
+
+  /**
+   * Get user prompt by ID
+   * GET /api/prompt/:id
+   */
+  private handleGetPromptById(req: Request, res: Response): void {
+    try {
+      const id = parseInt(req.params.id, 10);
+      if (isNaN(id)) {
+        res.status(400).json({ error: 'Invalid prompt ID' });
+        return;
+      }
+
+      const store = this.dbManager.getSessionStore();
+      const prompts = store.getUserPromptsByIds([id]);
+
+      if (prompts.length === 0) {
+        res.status(404).json({ error: `Prompt #${id} not found` });
+        return;
+      }
+
+      res.json(prompts[0]);
+    } catch (error) {
+      logger.failure('WORKER', 'Get prompt by ID failed', {}, error as Error);
+      res.status(500).json({ error: (error as Error).message });
+    }
+  }
+
  /**
   * Get database statistics (with worker metadata)
   */
@@ -806,11 +903,12 @@ export class WorkerService {
  }

  /**
-   * Get processing status (for viewer UI spinner)
+   * Get processing status (for viewer UI spinner and queue indicator)
   */
  private handleGetProcessingStatus(req: Request, res: Response): void {
    const isProcessing = this.sessionManager.isAnySessionProcessing();
-    res.json({ isProcessing });
+    const queueDepth = this.sessionManager.getTotalActiveWork(); // Includes queued + actively processing
+    res.json({ isProcessing, queueDepth });
  }

  // ============================================================================
@@ -823,7 +921,7 @@ export class WorkerService {
   */
  broadcastProcessingStatus(): void {
    const isProcessing = this.sessionManager.isAnySessionProcessing();
-    const queueDepth = this.sessionManager.getTotalQueueDepth();
+    const queueDepth = this.sessionManager.getTotalActiveWork(); // Includes queued + actively processing
    const activeSessions = this.sessionManager.getActiveSessionCount();

    logger.info('WORKER', 'Broadcasting processing status', {
@@ -834,7 +932,8 @@ export class WorkerService {

    this.sseBroadcaster.broadcast({
      type: 'processing_status',
-      isProcessing
+      isProcessing,
+      queueDepth
    });
  }

@@ -940,8 +1039,102 @@ export class WorkerService {
  // Search API Handlers (for skill-based search)
  // ============================================================================

+  // ============================================================================
+  // Unified Search API Handlers (New Consolidated API)
+  // ============================================================================
+
  /**
-   * Search observations
+   * Unified search across all memory types (observations, sessions, prompts)
+   * GET /api/search?query=...&format=index&limit=20
+   */
+  private async handleUnifiedSearch(req: Request, res: Response): Promise<void> {
+    try {
+      const result = await this.mcpClient.callTool({
+        name: 'search',
+        arguments: req.query
+      });
+      res.json(result.content);
+    } catch (error) {
+      logger.failure('WORKER', 'Unified search failed', {}, error as Error);
+      res.status(500).json({ error: (error as Error).message });
+    }
+  }
+
+  /**
+   * Unified timeline (anchor or query-based)
+   * GET /api/timeline?anchor=123 OR GET /api/timeline?query=...
+   */
+  private async handleUnifiedTimeline(req: Request, res: Response): Promise<void> {
+    try {
+      const result = await this.mcpClient.callTool({
+        name: 'timeline',
+        arguments: req.query
+      });
+      res.json(result.content);
+    } catch (error) {
+      logger.failure('WORKER', 'Unified timeline failed', {}, error as Error);
+      res.status(500).json({ error: (error as Error).message });
+    }
+  }
+
+  /**
+   * Semantic shortcut for finding decision observations
+   * GET /api/decisions?format=index&limit=20
+   */
+  private async handleDecisions(req: Request, res: Response): Promise<void> {
+    try {
+      const result = await this.mcpClient.callTool({
+        name: 'decisions',
+        arguments: req.query
+      });
+      res.json(result.content);
+    } catch (error) {
+      logger.failure('WORKER', 'Decisions search failed', {}, error as Error);
+      res.status(500).json({ error: (error as Error).message });
+    }
+  }
+
+  /**
+   * Semantic shortcut for finding change-related observations
+   * GET /api/changes?format=index&limit=20
+   */
+  private async handleChanges(req: Request, res: Response): Promise<void> {
+    try {
+      const result = await this.mcpClient.callTool({
+        name: 'changes',
+        arguments: req.query
+      });
+      res.json(result.content);
+    } catch (error) {
+      logger.failure('WORKER', 'Changes search failed', {}, error as Error);
+      res.status(500).json({ error: (error as Error).message });
+    }
+  }
+
+  /**
+   * Semantic shortcut for finding "how it works" explanations
+   * GET /api/how-it-works?format=index&limit=20
+   */
+  private async handleHowItWorks(req: Request, res: Response): Promise<void> {
+    try {
+      const result = await this.mcpClient.callTool({
+        name: 'how_it_works',
+        arguments: req.query
+      });
+      res.json(result.content);
+    } catch (error) {
+      logger.failure('WORKER', 'How it works search failed', {}, error as Error);
+      res.status(500).json({ error: (error as Error).message });
+    }
+  }
+
+  // ============================================================================
+  // Backward Compatibility API Handlers
+  // All functionality available via /api/search with type/obs_type/concepts/files params
+  // ============================================================================
+
+  /**
+   * Search observations (use /api/search?type=observations instead)
   * GET /api/search/observations?query=...&format=index&limit=20&project=...
   */
  private async handleSearchObservations(req: Request, res: Response): Promise<void> {
@@ -38,6 +38,19 @@ export class SessionManager {
    // Check if already active
    let session = this.sessions.get(sessionDbId);
    if (session) {
+      // Refresh project from database in case it was updated by new-hook
+      // This fixes the bug where sessions created with empty project get updated
+      // in the database but the in-memory session still has the stale empty value
+      const dbSession = this.dbManager.getSessionById(sessionDbId);
+      if (dbSession.project && dbSession.project !== session.project) {
+        silentDebug('[SessionManager] Updating project from database', {
+          sessionDbId,
+          oldProject: session.project,
+          newProject: dbSession.project
+        });
+        session.project = dbSession.project;
+      }
+
      // Update userPrompt for continuation prompts
      if (currentUserPrompt) {
        silentDebug('[SessionManager] Updating userPrompt for continuation', {
@@ -256,6 +269,23 @@ export class SessionManager {
    return total;
  }

+  /**
+   * Get total active work (queued + currently processing)
+   * Counts both pending messages and items actively being processed by SDK agents
+   */
+  getTotalActiveWork(): number {
+    let total = 0;
+    for (const session of this.sessions.values()) {
+      // Count queued messages
+      total += session.pendingMessages.length;
+      // Count currently processing item (1 per active generator)
+      if (session.generatorPromise !== null) {
+        total += 1;
+      }
+    }
+    return total;
+  }
+
  /**
   * Check if any session is actively processing (has pending messages OR active generator)
   * Used for activity indicator to prevent spinner from stopping while SDK is processing
@@ -1,9 +1,13 @@
 import path from "path";
 import { homedir } from "os";
 import { existsSync, readFileSync } from "fs";
+import { execSync } from "child_process";
+import { getPackageRoot } from "./paths.js";

 // Named constants for health checks
 const HEALTH_CHECK_TIMEOUT_MS = 100;
+const WORKER_STARTUP_WAIT_MS = 500;
+const WORKER_STARTUP_RETRIES = 10;

 /**
 * Get the worker port number
@@ -38,20 +42,61 @@ async function isWorkerHealthy(): Promise<boolean> {
  }
 }

+/**
+ * Start the worker using PM2
+ */
+async function startWorker(): Promise<boolean> {
+  try {
+    // Find the ecosystem config file (built version in plugin/)
+    const pluginRoot = getPackageRoot();
+    const ecosystemPath = path.join(pluginRoot, 'ecosystem.config.cjs');
+
+    if (!existsSync(ecosystemPath)) {
+      throw new Error(`Ecosystem config not found at ${ecosystemPath}`);
+    }
+
+    // Start using PM2 with the ecosystem config
+    // CRITICAL: Must set cwd to pluginRoot so PM2 starts from marketplace directory
+    execSync(`pm2 start "${ecosystemPath}"`, {
+      cwd: pluginRoot,
+      stdio: 'pipe',
+      encoding: 'utf-8'
+    });
+
+    // Wait for worker to become healthy
+    for (let i = 0; i < WORKER_STARTUP_RETRIES; i++) {
+      await new Promise(resolve => setTimeout(resolve, WORKER_STARTUP_WAIT_MS));
+      if (await isWorkerHealthy()) {
+        return true;
+      }
+    }
+
+    return false;
+  } catch (error) {
+    // Failed to start worker
+    return false;
+  }
+}
+
 /**
 * Ensure worker service is running
- * Checks health and fails with instructions if not healthy
- * PM2's watch mode handles auto-restarts automatically
+ * Checks health and auto-starts if not running
 */
 export async function ensureWorkerRunning(): Promise<void> {
+  // Check if already healthy
  if (await isWorkerHealthy()) {
    return;
  }

-  const port = getWorkerPort();
-  throw new Error(
-    `Worker service is not responding on port ${port}.\n\n` +
-    `If you just updated the plugin, PM2's watch mode should restart automatically.\n` +
-    `If the problem persists, run: pm2 restart claude-mem-worker`
-  );
+  // Try to start the worker
+  const started = await startWorker();
+
+  if (!started) {
+    const port = getWorkerPort();
+    throw new Error(
+      `Worker service failed to start on port ${port}.\n\n` +
+      `Try manually running: pm2 start ecosystem.config.cjs\n` +
+      `Or restart: pm2 restart claude-mem-worker`
+    );
+  }
 }
@@ -376,6 +376,36 @@
      animation: spin 1.5s linear infinite;
    }

+    .queue-bubble {
+      position: absolute;
+      top: -8px;
+      right: -8px;
+      background: var(--color-accent-primary);
+      color: var(--color-text-button);
+      font-size: 10px;
+      font-weight: 600;
+      font-family: 'Monaspace Radon', monospace;
+      min-width: 18px;
+      height: 18px;
+      border-radius: 9px;
+      display: flex;
+      align-items: center;
+      justify-content: center;
+      padding: 0 5px;
+      box-shadow: 0 2px 4px rgba(0, 0, 0, 0.2);
+      animation: pulse 2s ease-in-out infinite;
+      z-index: 10;
+    }
+
+    @keyframes pulse {
+      0%, 100% {
+        transform: scale(1);
+      }
+      50% {
+        transform: scale(1.1);
+      }
+    }
+
    .logo-text {
      font-family: 'Monaspace Radon', monospace;
      font-weight: 100;
@@ -17,7 +17,7 @@ export function App() {
  const [paginatedSummaries, setPaginatedSummaries] = useState<Summary[]>([]);
  const [paginatedPrompts, setPaginatedPrompts] = useState<UserPrompt[]>([]);

-  const { observations, summaries, prompts, projects, isProcessing, isConnected } = useSSE();
+  const { observations, summaries, prompts, projects, isProcessing, queueDepth, isConnected } = useSSE();
  const { settings, saveSettings, isSaving, saveStatus } = useSettings();
  const { stats, refreshStats } = useStats();
  const { preference, resolvedTheme, setThemePreference } = useTheme();
@@ -96,6 +96,7 @@ export function App() {
          onSettingsToggle={toggleSidebar}
          sidebarOpen={sidebarOpen}
          isProcessing={isProcessing}
+          queueDepth={queueDepth}
          themePreference={preference}
          onThemeChange={setThemePreference}
        />
@@ -10,6 +10,7 @@ interface HeaderProps {
  onSettingsToggle: () => void;
  sidebarOpen: boolean;
  isProcessing: boolean;
+  queueDepth: number;
  themePreference: ThemePreference;
  onThemeChange: (theme: ThemePreference) => void;
 }
@@ -22,13 +23,21 @@ export function Header({
  onSettingsToggle,
  sidebarOpen,
  isProcessing,
+  queueDepth,
  themePreference,
  onThemeChange
 }: HeaderProps) {
  return (
    <div className="header">
      <h1>
-        <img src="claude-mem-logomark.webp" alt="" className={`logomark ${isProcessing ? 'spinning' : ''}`} />
+        <div style={{ position: 'relative', display: 'inline-block' }}>
+          <img src="claude-mem-logomark.webp" alt="" className={`logomark ${isProcessing ? 'spinning' : ''}`} />
+          {queueDepth > 0 && (
+            <div className="queue-bubble">
+              {queueDepth}
+            </div>
+          )}
+        </div>
        <span className="logo-text">claude-mem</span>
      </h1>
      <div className="status">
@@ -10,6 +10,7 @@ export function useSSE() {
  const [projects, setProjects] = useState<string[]>([]);
  const [isConnected, setIsConnected] = useState(false);
  const [isProcessing, setIsProcessing] = useState(false);
+  const [queueDepth, setQueueDepth] = useState(0);
  const eventSourceRef = useRef<EventSource | null>(null);
  const reconnectTimeoutRef = useRef<NodeJS.Timeout>();

@@ -83,8 +84,9 @@ export function useSSE() {

            case 'processing_status':
              if (typeof data.isProcessing === 'boolean') {
-                console.log('[SSE] Processing status:', data.isProcessing);
+                console.log('[SSE] Processing status:', data.isProcessing, 'Queue depth:', data.queueDepth);
                setIsProcessing(data.isProcessing);
+                setQueueDepth(data.queueDepth || 0);
              }
              break;
          }
@@ -107,5 +109,5 @@ export function useSSE() {
    };
  }, []);

-  return { observations, summaries, prompts, projects, isProcessing, isConnected };
+  return { observations, summaries, prompts, projects, isProcessing, queueDepth, isConnected };
 }
@@ -0,0 +1,86 @@
+#!/bin/bash
+
+# Comprehensive Search API Test Suite
+# Tests all endpoints and parameter combinations
+
+API_URL="http://localhost:37777"
+RESULTS_DIR="test-results"
+
+echo "🔍 Starting comprehensive search API tests..."
+echo ""
+
+# SEMANTIC QUERIES - Understanding how things work
+echo "📚 Running semantic queries..."
+curl -s "$API_URL/api/search?type=observations&query=worker%20service%20startup&format=full&limit=5&orderBy=relevance" > "$RESULTS_DIR/test-01-worker-service-startup.json"
+curl -s "$API_URL/api/search?type=observations&query=SQLite%20FTS5%20implementation&format=full&limit=5&orderBy=relevance" > "$RESULTS_DIR/test-02-sqlite-fts5-implementation.json"
+curl -s "$API_URL/api/search?type=observations&query=hook%20lifecycle%20flow&format=full&limit=5&orderBy=relevance" > "$RESULTS_DIR/test-03-hook-lifecycle-flow.json"
+curl -s "$API_URL/api/search?type=observations&query=build%20pipeline%20process&format=full&limit=5&orderBy=relevance" > "$RESULTS_DIR/test-04-build-pipeline-process.json"
+echo "✅ Semantic queries complete (4 tests)"
+
+# DECISION QUERIES - Architectural choices
+echo "⚖️  Running decision queries..."
+curl -s "$API_URL/api/search?type=observations&obs_type=decision&query=PM2%20instead%20of%20direct%20process&format=full&limit=5&orderBy=relevance" > "$RESULTS_DIR/test-05-pm2-decision.json"
+curl -s "$API_URL/api/search?type=observations&obs_type=decision&query=search%20architecture%20guidelines&format=full&limit=5&orderBy=relevance" > "$RESULTS_DIR/test-06-search-architecture-decision.json"
+curl -s "$API_URL/api/search?type=observations&obs_type=decision&query=MCP%20as%20DRY%20source&format=full&limit=5&orderBy=relevance" > "$RESULTS_DIR/test-07-mcp-dry-decision.json"
+echo "✅ Decision queries complete (3 tests)"
+
+# TROUBLESHOOTING QUERIES - Finding bugfixes
+echo "🔴 Running troubleshooting queries..."
+curl -s "$API_URL/api/search?type=observations&obs_type=bugfix&query=worker%20service%20debugging&format=full&limit=5&orderBy=relevance" > "$RESULTS_DIR/test-08-worker-debugging.json"
+curl -s "$API_URL/api/search?type=observations&query=hook%20timeout%20problems&format=full&limit=5&orderBy=relevance" > "$RESULTS_DIR/test-09-hook-timeout.json"
+curl -s "$API_URL/api/search?type=observations&query=database%20migration%20issues&format=full&limit=5&orderBy=relevance" > "$RESULTS_DIR/test-10-database-migration.json"
+echo "✅ Troubleshooting queries complete (3 tests)"
+
+# FILE-SPECIFIC QUERIES - Tracking file changes
+echo "📁 Running file-specific queries..."
+curl -s "$API_URL/api/search?type=observations&files=search-server.ts&format=full&limit=5&orderBy=date_desc" > "$RESULTS_DIR/test-11-search-server-changes.json"
+curl -s "$API_URL/api/search?type=observations&files=context-hook&format=full&limit=5&orderBy=date_desc" > "$RESULTS_DIR/test-12-context-hook-changes.json"
+curl -s "$API_URL/api/search?type=observations&files=worker-service&format=full&limit=5&orderBy=date_desc" > "$RESULTS_DIR/test-13-worker-service-changes.json"
+echo "✅ File-specific queries complete (3 tests)"
+
+# CONCEPT-BASED QUERIES - Patterns, gotchas, discoveries
+echo "🏷️  Running concept-based queries..."
+curl -s "$API_URL/api/search?type=observations&concepts=pattern&format=full&limit=5&orderBy=date_desc" > "$RESULTS_DIR/test-14-patterns.json"
+curl -s "$API_URL/api/search?type=observations&concepts=gotcha&format=full&limit=5&orderBy=date_desc" > "$RESULTS_DIR/test-15-gotchas.json"
+curl -s "$API_URL/api/search?type=observations&concepts=discovery&format=full&limit=5&orderBy=date_desc" > "$RESULTS_DIR/test-16-discoveries.json"
+echo "✅ Concept-based queries complete (3 tests)"
+
+# TYPE-FILTERED QUERIES - Bugfixes, features, decisions
+echo "🔖 Running type-filtered queries..."
+curl -s "$API_URL/api/search?type=observations&obs_type=bugfix&format=full&limit=5&orderBy=date_desc" > "$RESULTS_DIR/test-17-all-bugfixes.json"
+curl -s "$API_URL/api/search?type=observations&obs_type=feature&format=full&limit=5&orderBy=date_desc" > "$RESULTS_DIR/test-18-all-features.json"
+curl -s "$API_URL/api/search?type=observations&obs_type=decision&format=full&limit=5&orderBy=date_desc" > "$RESULTS_DIR/test-19-all-decisions.json"
+echo "✅ Type-filtered queries complete (3 tests)"
+
+# SESSION QUERIES - Testing session search
+echo "📝 Running session queries..."
+curl -s "$API_URL/api/search?type=sessions&query=search%20architecture&format=full&limit=5&orderBy=relevance" > "$RESULTS_DIR/test-20-session-search.json"
+echo "✅ Session queries complete (1 test)"
+
+# USER PROMPT QUERIES - Testing prompt search
+echo "💬 Running user prompt queries..."
+curl -s "$API_URL/api/search?type=prompts&query=build%20and%20deploy&format=full&limit=5&orderBy=relevance" > "$RESULTS_DIR/test-21-prompt-search.json"
+echo "✅ User prompt queries complete (1 test)"
+
+# DEDICATED ENDPOINTS - Timeline and semantic shortcuts
+echo "🎯 Running dedicated endpoint tests..."
+curl -s "$API_URL/api/decisions?format=full&limit=5" > "$RESULTS_DIR/test-22-decisions-endpoint.json"
+curl -s "$API_URL/api/changes?format=full&limit=5" > "$RESULTS_DIR/test-23-changes-endpoint.json"
+curl -s "$API_URL/api/how-it-works?format=full&limit=5" > "$RESULTS_DIR/test-24-how-it-works-endpoint.json"
+curl -s "$API_URL/api/contextualize?format=full" > "$RESULTS_DIR/test-25-contextualize-endpoint.json"
+echo "✅ Dedicated endpoint tests complete (4 tests)"
+
+# TIMELINE QUERY - Get context around a specific observation
+echo "⏱️  Running timeline query..."
+curl -s "$API_URL/api/timeline?anchor=10630&depth_before=3&depth_after=3&format=full" > "$RESULTS_DIR/test-26-timeline-around-observation.json"
+echo "✅ Timeline query complete (1 test)"
+
+# MULTI-PARAMETER COMBO - Test complex query combinations
+echo "🎛️  Running multi-parameter combination tests..."
+curl -s "$API_URL/api/search?type=observations&obs_type=decision&concepts=pattern&query=search&format=full&limit=5&orderBy=relevance" > "$RESULTS_DIR/test-27-multi-param-combo.json"
+curl -s "$API_URL/api/search?type=observations&files=search-server&obs_type=feature&format=full&limit=5&orderBy=date_desc" > "$RESULTS_DIR/test-28-file-type-combo.json"
+echo "✅ Multi-parameter tests complete (2 tests)"
+
+echo ""
+echo "✨ All tests complete! 28 total queries executed."
+echo "📊 Results saved to $RESULTS_DIR/"
@@ -0,0 +1 @@
+[{"type":"text","text":"## User Prompt #5\n*Source: claude-mem://user-prompt/2735*\n\nAre you ok? You seem a little excited and it's hard to do this project. Can you tell me what's going on?\n\n---\nDate: 11/17/2025, 9:38:06 PM\n\n---\n\n## User Prompt #2\n*Source: claude-mem://user-prompt/2719*\n\nedit the build script, we need it to always do this.\n\n---\nDate: 11/17/2025, 7:49:17 PM\n\n---\n\n## User Prompt #3\n*Source: claude-mem://user-prompt/2662*\n\nthose built files, the js, the cjs, if the source files don't have merge issues, then these are just way outdated build files.... is that the case?\n\n---\nDate: 11/17/2025, 3:03:13 PM\n\n---\n\n## User Prompt #12\n*Source: claude-mem://user-prompt/2651*\n\nI FUCKING DID BUILD AND SYNC AND DELETE. I would not have told you to fucking check pm2 info had I not done that\n\n---\nDate: 11/17/2025, 2:25:18 PM\n\n---\n\n## User Prompt #7\n*Source: claude-mem://user-prompt/2646*\n\nCan you fix it so that it runs from the marketplace folder so it doesn't break on EVERYONES SYSTEM WHO DOESNT FUCKING BUILD MANUALLY\n\n---\nDate: 11/17/2025, 2:19:29 PM"}]
@@ -0,0 +1 @@
+[{"type":"text","text":"# Project Context: claude-mem\n\nNo activity found for this project."}]
@@ -0,0 +1 @@
+[{"type":"text","text":"# Timeline around anchor: 10630\n**Window:** 3 records before → 3 records after | **Items:** 3 (3 obs, 0 sessions, 0 prompts)\n\n**Legend:** 🎯 session-request | 🔴 bugfix | 🟣 feature | 🔄 refactor | ✅ change | 🔵 discovery | 🧠 decision\n\n### Nov 17, 2025\n\n**General**\n| ID | Time | T | Title | Tokens |\n|----|------|---|-------|--------|\n| #10756 | 11:50 PM | 🔴 | Fixed Incorrect Parameter Array in searchUserPrompts FTS5 Path | ~213 |\n| #10757 | ″ | 🔵 | Unified search handler implements Chroma-first with FTS5 fallback on zero results | ~224 |\n| #10758 | 11:51 PM | ✅ | Build and sync claude-mem plugin to marketplace location | ~189 |\n"}]
Author	SHA1	Message	Date
Alex Newman	634033b730	chore: Bump version to 6.2.1	2025-11-23 16:18:58 -05:00
Alex Newman	54ef1496d2	fix: Refresh in-memory session project when updated in database Problem: - Summaries created with empty project names even after database fix - 13 summaries had empty project, couldn't appear in context-hook - In-memory sessions cached stale empty project value Root Cause: SessionManager caches ActiveSession objects in memory. When reusing an existing session, it never refreshed the project field from the database. Even though createSDKSession() now updates the DB with the correct project, the in-memory session.project remained empty, causing summaries to be stored with empty project. Flow: 1. Session created with empty project (cached in memory) 2. new-hook UPDATE fixes project in database 3. SessionManager reuses cached session (stale project="") 4. Summary stored with session.project (empty) 5. Context-hook can't find summary (WHERE project = 'claude-mem') Solution: When SessionManager.initializeSession() reuses an existing session, refresh the project field from the database. This ensures summaries and observations always use the latest project value. Impact: - Future summaries will have correct project name - Backfilled 13 historical summaries with project='claude-mem' - Context injection will now show recent summaries - Both observations AND summaries fixed 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>	2025-11-23 16:14:53 -05:00
Alex Newman	5d23c60b76	fix: Update project name when session already exists in createSDKSession Problem: - Sessions created with empty project names couldn't be updated - INSERT OR IGNORE skipped updates when session already existed - Context-hook couldn't find observations (WHERE project = 'claude-mem') - 364 observations had empty project names Root Cause: createSDKSession() used INSERT OR IGNORE for idempotency, but never updated project/prompt fields when session already existed. If SAVE hook created session first (with empty project), NEW hook couldn't fix it. Solution: When INSERT is ignored (session exists), UPDATE project and user_prompt if we have non-empty values. This ensures project name gets set even when session was created by SAVE hook or with incomplete data. Impact: - New sessions will always have correct project name - Backfilled 364 historical observations with project='claude-mem' - Context injection will now work (finds observations by project) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>	2025-11-23 16:06:46 -05:00
Alex Newman	9314ede6e9	docs: Update CHANGELOG.md for v6.2.0	2025-11-22 00:29:25 -05:00
Alex Newman	58f4053a61	chore: Bump version to 6.2.0	2025-11-22 00:27:34 -05:00
claude[bot]	a08e5068c8	fix: Update version to 6.1.1 across package.json and CLAUDE.md Co-authored-by: Alex Newman <thedotmack@users.noreply.github.com>	2025-11-22 04:44:20 +00:00
claude[bot]	9f1b653f2f	fix: Update CLAUDE.md version to match package.json (6.0.9) Co-authored-by: Alex Newman <thedotmack@users.noreply.github.com>	2025-11-22 04:17:31 +00:00
copilot-swe-agent[bot]	c5d89142b9	chore: Update package-lock.json after merge and build Co-authored-by: thedotmack <683968+thedotmack@users.noreply.github.com>	2025-11-22 00:18:14 +00:00
copilot-swe-agent[bot]	b44d4702b1	Merge main branch, prefer this branch's version except simpler CLAUDE.md	2025-11-22 00:17:24 +00:00
copilot-swe-agent[bot]	4988b4b317	Initial plan	2025-11-22 00:12:58 +00:00
Alex Newman	c5e68a17c8	refactor: Clean up search architecture, remove experimental contextualize endpoint (#133 ) * Refactor code structure for improved readability and maintainability * Add test results for search API and related functionalities - Created test result files for various search-related functionalities, including: - test-11-search-server-changes.json - test-12-context-hook-changes.json - test-13-worker-service-changes.json - test-14-patterns.json - test-15-gotchas.json - test-16-discoveries.json - test-17-all-bugfixes.json - test-18-all-features.json - test-19-all-decisions.json - test-20-session-search.json - test-21-prompt-search.json - test-22-decisions-endpoint.json - test-23-changes-endpoint.json - test-24-how-it-works-endpoint.json - test-25-contextualize-endpoint.json - test-26-timeline-around-observation.json - test-27-multi-param-combo.json - test-28-file-type-combo.json - Each test result file captures specific search failures or outcomes, including issues with undefined properties and successful execution of search queries. - Enhanced documentation of search architecture and testing strategies, ensuring compliance with established guidelines and improving overall search functionality. * feat: Enhance unified search API with catch-all parameters and backward compatibility - Implemented a unified search API at /api/search that accepts catch-all parameters for filtering by type, observation type, concepts, and files. - Maintained backward compatibility by keeping granular endpoints functional while routing through the same infrastructure. - Completed comprehensive testing of search capabilities with real-world query scenarios. fix: Address missing debug output in search API query tests - Flushed PM2 logs and executed search queries to verify functionality. - Diagnosed absence of "Raw Chroma" debug messages in worker logs, indicating potential issues with logging or query processing. refactor: Improve build and deployment pipeline for claude-mem plugin - Successfully built and synced all hooks and services to the marketplace directory. - Ensured all dependencies are installed and up-to-date in the deployment location. feat: Implement hybrid search filters with 90-day recency window - Enhanced search server to apply a 90-day recency filter to Chroma results before categorizing by document type. fix: Correct parameter handling in searchUserPrompts method - Added support for filter-only queries and improved dual-path logic for clarity. refactor: Rename FTS5 method to clarify fallback status - Renamed escapeFTS5 to escapeFTS5_fallback_when_chroma_unavailable to indicate its temporary usage. feat: Introduce contextualize tool for comprehensive project overview - Added a new tool to fetch recent observations, sessions, and user prompts, providing a quick project overview. feat: Add semantic shortcut tools for common search patterns - Implemented 'decisions', 'changes', and 'how_it_works' tools for convenient access to frequently searched observation categories. feat: Unified timeline tool supports anchor and query modes - Combined get_context_timeline and get_timeline_by_query into a single interface for timeline exploration. feat: Unified search tool added to MCP server - New tool queries all memory types simultaneously, providing combined chronological results for improved search efficiency. * Refactor search functionality to clarify FTS5 fallback usage - Updated `worker-service.cjs` to replace FTS5 fallback function with a more descriptive name and improved error handling. - Enhanced documentation in `SKILL.md` to specify the unified API endpoint and clarify the behavior of the search engine, including the conditions under which FTS5 is used. - Modified `search-server.ts` to provide clearer logging and descriptions regarding the fallback to FTS5 when UVX/Python is unavailable. - Renamed and updated the `SessionSearch.ts` methods to reflect the conditions for using FTS5, emphasizing the lack of semantic understanding in fallback scenarios. * feat: Add ID-based fetch endpoints and simplify mem-search skill Problem: - Search returns IDs but no way to fetch by ID - Skill documentation was bloated with too many options - Claude wasn't using IDs because we didn't tell it how Solution: 1. Added three new HTTP endpoints: - GET /api/observation/:id - GET /api/session/:id - GET /api/prompt/:id 2. Completely rewrote SKILL.md: - Stripped complexity down to essentials - Clear 3-step prescriptive workflow: Search → Review IDs → Fetch by ID - Emphasized ID usage: "The IDs are there for a reason - USE THEM" - Removed confusing multi-endpoint documentation - Kept only unified search with filters Impact: - Token efficiency: Claude can now fetch full details only for relevant IDs - Clarity: One clear workflow instead of 10+ options to choose from - Usability: IDs are no longer wasted context - they're actionable 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * chore: Move internal docs to private directory Moved POSTMORTEM and planning docs to ./private to exclude from PR reviews. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: Remove experimental contextualize endpoint - Removed contextualize MCP tool from search-server (saves ~4KB) - Disabled FTS5 fallback paths in SessionSearch (now vector-first) - Cleaned up CLAUDE.md documentation - Removed contextualize-rewrite-plan.md doc Rationale: - Contextualize is better suited as a skill (LLM-powered) than an endpoint - Search API already provides vector search with configurable limits - Created issue #132 to track future contextualize skill implementation Changes: - src/servers/search-server.ts: Removed contextualize tool definition - src/services/sqlite/SessionSearch.ts: Disabled FTS5 fallback, added deprecation warnings - CLAUDE.md: Cleaned up outdated skill documentation - docs/: Removed contextualize plan document 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: Complete FTS5 cleanup - remove all deprecated search code This completes the FTS5 cleanup work by removing all commented-out FTS5 search code while preserving database tables for backward compatibility. Changes: - Removed 200+ lines of commented FTS5 search code from SessionSearch.ts - Removed deprecated degraded_search_query__when_uvx_unavailable method - Updated all method documentation to clarify vector-first architecture - Updated class documentation to reflect filter-only query support - Updated CLAUDE.md to remove FTS5 search references - Clarified that FTS5 tables exist for backward compatibility only - Updated "Why SQLite FTS5" section to "Why Vector-First Search" Database impact: NONE - FTS5 tables remain intact for existing installations Search architecture: - ChromaDB: All text-based vector search queries - SQLite: Filter-only queries (date ranges, metadata, no query text) - FTS5 tables: Maintained but unused (backward compatibility) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * refactor: Remove all FTS5 fallback execution code from search-server Completes the FTS5 cleanup by removing all fallback execution paths that attempted to use FTS5 when ChromaDB was unavailable. Changes: - Removed all FTS5 fallback code execution paths - When ChromaDB fails or is unavailable, return empty results with helpful error messages - Updated all deprecated tool descriptions (search_observations, search_sessions, search_user_prompts) - Changed error messages to indicate FTS5 fallback has been removed - Added installation instructions for UVX/Python when vector search is unavailable - Updated comments from "hybrid search" to "vector-first search" - Removed ~100 lines of dead FTS5 fallback code Database impact: NONE - FTS5 tables remain intact (backward compatibility) Search behavior when ChromaDB unavailable: - Text queries: Return empty results with error explaining ChromaDB is required - Filter-only queries (no text): Continue to work via direct SQLite 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * fix: Address PR 133 review feedback Critical fixes: - Remove contextualize endpoint from worker-service (route + handler) - Fix build script logging to show correct .cjs extension (was .mjs) Documentation improvements: - Add comprehensive FTS5 retention rationale documentation - Include v7.0.0 removal TODO for future cleanup Testing: - Build succeeds with correct output logging - Worker restarts successfully (30th restart) - Contextualize endpoint properly removed (404 response) - Search endpoint verified working This addresses all critical review feedback from PR 133. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> --------- Co-authored-by: Claude <noreply@anthropic.com>	2025-11-21 18:59:23 -05:00
Alex Newman	f35764aa14	Update link for AI Memory Economics analysis (#143 )	2025-11-21 00:59:54 -05:00
Alex Newman	601bded789	docs: Update CHANGELOG.md for v6.1.1	2025-11-20 20:40:40 -05:00
Alex Newman	c231e8d076	chore: Bump version to 6.1.1	2025-11-20 20:39:40 -05:00
Alex Newman	b62e93577c	fix: Use dynamic project name detection for ChromaDB collections and observations (#142 ) * fix: Use dynamic project name detection instead of hardcoded values Fixes #140 Previously, the worker process used hardcoded "claude-mem" for: - ChromaSync instantiation in DatabaseManager - ChromaDB collection naming in search-server This caused all observations to be tagged with "claude-mem" regardless of the actual project being worked on. Now both services use getCurrentProjectName() to dynamically detect the project based on the worker's current working directory. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> * fix: Simplify viewer UI overflow CSS to enable scrolling - Remove overcomplicated nested overflow containers - Use explicit 100vh for layout height - Add overflow: hidden to main-col to constrain feed - Keep simple overflow-y: auto on feed element - Fix issue where feed content wouldn't scroll --------- Co-authored-by: Claude <noreply@anthropic.com>	2025-11-20 20:37:57 -05:00
Alex Newman	0787e47b1a	Add AI Memory Economics analysis to README Added a new section for AI Memory Economics analysis with key insights and a link.	2025-11-20 00:47:44 -05:00
Alex Newman	f9843fe593	docs: Compress CLAUDE.md to bare essentials Removed verbose explanations and kept only critical reference info: - What the project is - Architecture overview (hooks, worker, database, skills, chroma, viewer) - Build commands for different scenarios - Environment variables - File locations - Quick reference commands Moved general coding standards to ~/.claude/CLAUDE.md (global config). 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>	2025-11-19 18:12:27 -05:00
Alex Newman	5b772ee768	docs: Fix v6.1.0 release notes accuracy	2025-11-19 17:24:21 -05:00
Alex Newman	baabf14bfa	docs: Update CHANGELOG.md for v6.1.0 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>	2025-11-19 17:14:45 -05:00
Alex Newman	c126a7083f	chore: Bump version to 6.1.0 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>	2025-11-19 17:14:09 -05:00
Alex Newman	f1170512d6	feat: Add responsive mobile navigation with Discord-style sidebar layout (#138 ) Implements a mobile-first navigation reorganization that moves controls into the sidebar at smaller breakpoints: - Community button moves to sidebar at 600px - Projects dropdown moves to sidebar at 480px - Sidebar gains proper width constraints (100% width, 400px max-width) - Full-height layout styling fixes for proper flex behavior - Clean separation between header and sidebar responsibilities This creates a Discord-like mobile experience where the sidebar becomes the primary navigation container on smaller screens. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-authored-by: Claude <noreply@anthropic.com>	2025-11-19 17:13:24 -05:00
Alex Newman	d64939c379	docs: Add semantic naming principle and clean up migration docs Added semantic naming to coding standards emphasizing verbose, self-documenting names for comprehension. Cleaned up database migration section removing TODO in favor of clear evergreen statement. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>	2025-11-17 15:45:33 -05:00
Alex Newman	97d8bd3e62	docs: Update CHANGELOG.md for v6.0.9 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>	2025-11-17 15:18:25 -05:00
Alex Newman	6cd904a81c	chore: Bump version to 6.0.9 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>	2025-11-17 15:17:23 -05:00
Alex Newman	74c8afd0e0	feat: Add real-time queue depth indicator to viewer UI Implements a visual badge that displays the count of active work items (queued + currently processing) in the worker service. The badge appears next to the claude-mem logo and updates in real-time via SSE. Features: - Shows count of pending messages + active SDK generators - Only displays when queueDepth > 0 - Subtle pulse animation for visual feedback - Theme-aware styling Backend changes: - Added getTotalActiveWork() method to SessionManager - Updated worker-service to broadcast queueDepth via SSE - Enhanced processing status API endpoint Frontend changes: - Updated Header component to display queue bubble - Enhanced useSSE hook to track queueDepth state - Added CSS styling with pulse animation Closes #122 Closes #96 Closes #97 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>	2025-11-17 15:11:37 -05:00
Alex Newman	02444392da	docs: Update CHANGELOG.md for v6.0.8 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>	2025-11-17 14:43:39 -05:00
Alex Newman	d175f1759c	chore: Bump version to 6.0.8 Critical hotfix for PM2 worker startup issue. The worker now correctly starts from the marketplace directory automatically. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>	2025-11-17 14:42:16 -05:00
Alex Newman	d55db524f0	Refactor worker scripts to improve logging and error handling - Updated `new-hook.js` and `save-hook.js` to enhance logging functionality, including better error messages and structured logging. - Improved the handling of worker startup in `summary-hook.js` and `worker-utils.ts`, ensuring proper directory context for PM2. - Added checks for worker health and streamlined session management across hooks.	2025-11-17 14:38:47 -05:00
Alex Newman	7d44fdb289	Refactor worker-utils to use getPackageRoot for plugin path resolution	2025-11-17 14:12:50 -05:00
Alex Newman	812de2940d	feat: Implement Endless Mode Token Economics Calculator - Added a new script to simulate token savings from Endless Mode using real observation data. - Introduced functions to calculate token costs with and without Endless Mode, showcasing the differences in context handling. - Enhanced output to display detailed token usage statistics and potential savings at scale. - Integrated assumptions for user activity to estimate weekly and annual token savings. - Updated worker-utils to automatically start the worker using PM2 if not running, improving service reliability.	2025-11-17 14:04:47 -05:00
Alex Newman	95edf31c14	fix: Remove unnecessary ignore entries from ecosystem.config.cjs	2025-11-17 14:01:43 -05:00
Alex Newman	a9ae89a198	docs: Update CHANGELOG.md for v6.0.7 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>	2025-11-17 13:47:38 -05:00
				`@@ -0,0 +1 @@`
				[{"type":"text","text":"## User Prompt #5\nSource: claude-mem://user-prompt/2735\n\nAre you ok? You seem a little excited and it's hard to do this project. Can you tell me what's going on?\n\n---\nDate: 11/17/2025, 9:38:06 PM\n\n---\n\n## User Prompt #2\nSource: claude-mem://user-prompt/2719\n\nedit the build script, we need it to always do this.\n\n---\nDate: 11/17/2025, 7:49:17 PM\n\n---\n\n## User Prompt #3\nSource: claude-mem://user-prompt/2662\n\nthose built files, the js, the cjs, if the source files don't have merge issues, then these are just way outdated build files.... is that the case?\n\n---\nDate: 11/17/2025, 3:03:13 PM\n\n---\n\n## User Prompt #12\nSource: claude-mem://user-prompt/2651\n\nI FUCKING DID BUILD AND SYNC AND DELETE. I would not have told you to fucking check pm2 info had I not done that\n\n---\nDate: 11/17/2025, 2:25:18 PM\n\n---\n\n## User Prompt #7\nSource: claude-mem://user-prompt/2646\n\nCan you fix it so that it runs from the marketplace folder so it doesn't break on EVERYONES SYSTEM WHO DOESNT FUCKING BUILD MANUALLY\n\n---\nDate: 11/17/2025, 2:19:29 PM"}]
				`@@ -0,0 +1 @@`
				`[{"type":"text","text":"# Project Context: claude-mem\n\nNo activity found for this project."}]`
				`@@ -0,0 +1 @@`
				[{"type":"text","text":"# Timeline around anchor: 10630\nWindow: 3 records before → 3 records after \| Items: 3 (3 obs, 0 sessions, 0 prompts)\n\nLegend: 🎯 session-request \| 🔴 bugfix \| 🟣 feature \| 🔄 refactor \| ✅ change \| 🔵 discovery \| 🧠 decision\n\n### Nov 17, 2025\n\nGeneral\n\| ID \| Time \| T \| Title \| Tokens \|\n\|----\|------\|---\|-------\|--------\|\n\| #10756 \| 11:50 PM \| 🔴 \| Fixed Incorrect Parameter Array in searchUserPrompts FTS5 Path \| ~213 \|\n\| #10757 \| ″ \| 🔵 \| Unified search handler implements Chroma-first with FTS5 fallback on zero results \| ~224 \|\n\| #10758 \| 11:51 PM \| ✅ \| Build and sync claude-mem plugin to marketplace location \| ~189 \|\n"}]