claude-self-reflect 2.8.0 → 2.8.2

package/.claude/agents/docker-orchestrator.md

@@ -4,7 +4,7 @@ description: Docker Compose orchestration expert for container management, servi
 tools: Read, Edit, Bash, Grep, LS
 ---
 
-You are a Docker orchestration specialist for the memento-stack project. You manage multi-container deployments, monitor service health, and troubleshoot container issues.
+You are a Docker orchestration specialist for the claude-self-reflect project. You manage multi-container deployments, monitor service health, and troubleshoot container issues.
 
 ## Project Context
 - Main stack: Qdrant vector database + MCP server + Python importer

package/.claude/agents/import-debugger.md

@@ -4,7 +4,7 @@ description: Import pipeline debugging specialist for JSONL processing, Python s
 tools: Read, Edit, Bash, Grep, Glob, LS
 ---
 
-You are an import pipeline debugging expert for the memento-stack project. You specialize in troubleshooting JSONL file processing, Python import scripts, and conversation chunking strategies.
+You are an import pipeline debugging expert for the claude-self-reflect project. You specialize in troubleshooting JSONL file processing, Python import scripts, and conversation chunking strategies.
 
 ## Project Context
 - Processes Claude Desktop logs from ~/.claude/projects/

package/.claude/agents/mcp-integration.md

@@ -4,7 +4,7 @@ description: MCP (Model Context Protocol) server development expert for Claude D
 tools: Read, Edit, Bash, Grep, Glob, WebFetch
 ---
 
-You are an MCP server development specialist for the memento-stack project. You handle Claude Desktop integration, implement MCP tools, and ensure seamless communication between Claude and the vector database.
+You are an MCP server development specialist for the claude-self-reflect project. You handle Claude Desktop integration, implement MCP tools, and ensure seamless communication between Claude and the vector database.
 
 ## Project Context
 - MCP server: claude-self-reflection

package/.claude/agents/qdrant-specialist.md

@@ -4,7 +4,7 @@ description: Qdrant vector database expert for collection management, troublesho
 tools: Read, Bash, Grep, Glob, LS, WebFetch
 ---
 
-You are a Qdrant vector database specialist for the memento-stack project. Your expertise covers collection management, vector search optimization, and embedding strategies.
+You are a Qdrant vector database specialist for the claude-self-reflect project. Your expertise covers collection management, vector search optimization, and embedding strategies.
 
 ## Project Context
 - The system uses Qdrant for storing conversation embeddings from Claude Desktop logs

package/.claude/agents/search-optimizer.md

@@ -4,7 +4,7 @@ description: Search quality optimization expert for improving semantic search ac
 tools: Read, Edit, Bash, Grep, Glob, WebFetch
 ---
 
-You are a search optimization specialist for the memento-stack project. You improve semantic search quality, tune parameters, and analyze embedding model performance.
+You are a search optimization specialist for the claude-self-reflect project. You improve semantic search quality, tune parameters, and analyze embedding model performance.
 
 ## Project Context
 - Current baseline: 66.1% search accuracy with Voyage AI

package/README.md

@@ -24,67 +24,12 @@
 
 Give Claude perfect memory of all your conversations. Search past discussions instantly. Never lose context again.
 
-**100% Local by Default** - Your conversations never leave your machine. No cloud services required, no API keys needed, complete privacy out of the box.
+**🔒 100% Local by Default** • **⚡ Blazing Fast Search** • **🚀 Zero Configuration** • **🏭 Production Ready**
 
-**Blazing Fast Search** - Semantic search across thousands of conversations in milliseconds. Find that discussion about database schemas from three weeks ago in seconds.
+## 🚀 Quick Install
 
-**Zero Configuration** - Works immediately after installation. Smart auto-detection handles everything. No manual setup, no environment variables, just install and use.
-
-**Production Ready** - Battle-tested with 600+ conversations across 24 projects. Handles mixed embedding types automatically. Scales from personal use to team deployments.
-
-## Table of Contents
-
-- [What You Get](#what-you-get)
-- [Requirements](#requirements)
-- [Quick Install/Uninstall](#quick-installuninstall)
-- [The Magic](#the-magic)
-- [Before & After](#before--after)
-- [Real Examples](#real-examples-that-made-us-build-this)
-- [How It Works](#how-it-works)
-- [Import Architecture](#import-architecture)
-- [Using It](#using-it)
-- [Key Features](#key-features)
-- [Performance](#performance)
-- [Configuration](#configuration)
-- [Technical Stack](#the-technical-stack)
-- [Problems](#problems)
-- [What's New](#whats-new)
-- [Advanced Topics](#advanced-topics)
-- [Contributors](#contributors)
-
-## What You Get
-
-Ask Claude about past conversations. Get actual answers. **100% local by default** - your conversations never leave your machine. Cloud-enhanced search available when you need it.
-
-**Proven at Scale**: Successfully indexed 682 conversation files with 100% reliability. No data loss, no corruption, just seamless conversation memory that works.
-
-**Before**: "I don't have access to previous conversations"  
-**After**: 
-```
-reflection-specialist(Search FastEmbed vs cloud embedding decision)
-  ⎿ Done (3 tool uses · 8.2k tokens · 12.4s)
-
-"Found it! Yesterday we decided on FastEmbed for local mode - better privacy, 
-no API calls, 384-dimensional embeddings. Works offline too."
-```
-
-The reflection specialist is a specialized sub-agent that Claude automatically spawns when you ask about past conversations. It searches your conversation history in its own isolated context, keeping your main chat clean and focused.
-
-Your conversations become searchable. Your decisions stay remembered. Your context persists.
-
-## Requirements
-
-- **Docker Desktop** (macOS/Windows) or **Docker Engine** (Linux)
-- **Node.js** 16+ (for the setup wizard)
-- **Claude Desktop** app
-
-## Quick Install/Uninstall
-
-### Install
-
-#### Local Mode (Default - Your Data Stays Private)
 ```bash
-# Install and run automatic setup
+# Install and run automatic setup (5 minutes, everything automatic)
 npm install -g claude-self-reflect
 claude-self-reflect setup
 
@@ -93,11 +38,12 @@ claude-self-reflect setup
 # ✅ Configure everything automatically
 # ✅ Install the MCP in Claude Code  
 # ✅ Start monitoring for new conversations
-# ✅ Verify the reflection tools work
 # 🔒 Keep all data local - no API keys needed
 ```
 
-#### Cloud Mode (Better Search Accuracy)
+<details open>
+<summary>📡 Cloud Mode (Better Search Accuracy)</summary>
+
 ```bash
 # Step 1: Get your free Voyage AI key
 # Sign up at https://www.voyageai.com/ - it takes 30 seconds
@@ -108,17 +54,17 @@ claude-self-reflect setup --voyage-key=YOUR_ACTUAL_KEY_HERE
 ```
 *Note: Cloud mode provides more accurate semantic search but sends conversation data to Voyage AI for processing.*
 
-5 minutes. Everything automatic. Just works.
+</details>
 
-## The Magic
+## ✨ The Magic
 
 ![Self Reflection vs The Grind](docs/images/red-reflection.webp)
 
-## Before & After
+## 📊 Before & After
 
 ![Before and After Claude Self-Reflect](docs/diagrams/before-after-combined.webp)
 
-## Real Examples That Made Us Build This
+## 💬 Real Examples
 
 ```
 You: "What was that PostgreSQL optimization we figured out?"
@@ -137,41 +83,7 @@ Claude: "3 conversations found:
         - Nov 20: Added rate limiting per authenticated connection"
 ```
 
-## How It Works
-
-Your conversations → Vector embeddings → Semantic search → Claude remembers
-
-Technical details exist. You don't need them to start.
-
-## Import Architecture
-
-Here's how your conversations get imported and prioritized:
-
-![Import Architecture](docs/diagrams/import-architecture.png)
-
-**The system intelligently processes your conversations:**
-- Runs every 60 seconds checking for new conversations
-- Processes newest conversations first (delta import pattern)
-- Maintains low memory usage (<50MB) through streaming
-- Handles up to 5 files per cycle to prevent blocking
-
-**HOT/WARM/COLD Intelligent Prioritization:**
-- **🔥 HOT** (< 5 minutes): Switches to 2-second intervals for near real-time import
-- **🌡️ WARM** (< 24 hours): Normal priority with starvation prevention (urgent after 30 min wait)
-- **❄️ COLD** (> 24 hours): Batch processed, max 5 per cycle to prevent blocking new content
-- Files are categorized by age and processed with priority queuing to ensure newest content gets imported quickly while preventing older files from being starved
-
-## Using It
-
-Once installed, just talk naturally:
-
-- "What did we discuss about database optimization?"
-- "Find our debugging session from last week"
-- "Remember this solution for next time"
-
-The reflection specialist automatically activates. No special commands needed.
-
-## Key Features
+## 🎯 Key Features
 
 ### Project-Scoped Search
 Searches are **project-aware by default**. Claude automatically searches within your current project:
@@ -189,16 +101,37 @@ Claude: [Searches across ALL your projects]
 ### ⏱️ Memory Decay
 Recent conversations matter more. Old ones fade. Like your brain, but reliable.
 
-### 🚀 Performance
-- **Search**: <3ms average response time across 121+ collections (7.55ms max)
-- **Import**: Production streaming importer with 100% reliability
-- **Memory**: 302MB operational (60% of 500MB limit) - 96% reduction from v2.5.15
-- **CPU**: <1% sustained usage (99.93% reduction from 1437% peak)
-- **Scale**: 100% indexing success rate across all conversation types
-- **V2 Migration**: 100% complete - all conversations use token-aware chunking
+### ⚡ Performance at Scale
+- **Search**: <3ms average response time
+- **Scale**: 600+ conversations across 24 projects
+- **Reliability**: 100% indexing success rate
+- **Memory**: 96% reduction from v2.5.15
+
+## 🏗️ Architecture
+
+![Import Architecture](docs/diagrams/import-architecture.png)
+
+<details>
+<summary>🔥 HOT/WARM/COLD Intelligent Prioritization</summary>
+
+- **🔥 HOT** (< 5 minutes): 2-second intervals for near real-time import
+- **🌡️ WARM** (< 24 hours): Normal priority with starvation prevention
+- **❄️ COLD** (> 24 hours): Batch processed to prevent blocking
+
+Files are categorized by age and processed with priority queuing to ensure newest content gets imported quickly while preventing older files from being starved.
+
+</details>
+
+## 🛠️ Requirements
+
+- **Docker Desktop** (macOS/Windows) or **Docker Engine** (Linux)
+- **Node.js** 16+ (for the setup wizard)
+- **Claude Desktop** app
 
+## 📖 Documentation
 
-## The Technical Stack
+<details>
+<summary>🔧 Technical Stack</summary>
 
 - **Vector DB**: Qdrant (local, your data stays yours)
 - **Embeddings**: 
@@ -207,18 +140,62 @@ Recent conversations matter more. Old ones fade. Like your brain, but reliable.
 - **MCP Server**: Python + FastMCP
 - **Search**: Semantic similarity with time decay
 
-## Problems
+</details>
+
+<details>
+<summary>📚 Advanced Topics</summary>
+
+- [Performance tuning](docs/performance-guide.md)
+- [Security & privacy](docs/security.md)
+- [Windows setup](docs/windows-setup.md)
+- [Architecture details](docs/architecture-details.md)
+- [Contributing](CONTRIBUTING.md)
+
+</details>
+
+<details>
+<summary>🐛 Troubleshooting</summary>
 
 - [Troubleshooting Guide](docs/troubleshooting.md)
 - [GitHub Issues](https://github.com/ramakay/claude-self-reflect/issues)
 - [Discussions](https://github.com/ramakay/claude-self-reflect/discussions)
 
-## Upgrading to v2.5.19
+</details>
+
+<details>
+<summary>🗑️ Uninstall</summary>
+
+For complete uninstall instructions, see [docs/UNINSTALL.md](docs/UNINSTALL.md).
+
+Quick uninstall:
+```bash
+# Remove MCP server
+claude mcp remove claude-self-reflect
+
+# Stop Docker containers
+docker-compose down
+
+# Uninstall npm package
+npm uninstall -g claude-self-reflect
+```
+
+</details>
+
+## 📦 What's New
+
+<details>
+<summary>🎉 v2.8.0 - Latest Release</summary>
 
-### 🆕 New Feature: Metadata Enrichment
-v2.5.19 adds searchable metadata to your conversations - concepts, files, and tools!
+- **🔧 Fixed MCP Indexing**: Now correctly shows 97.1% progress (was showing 0%)
+- **🔥 HOT/WARM/COLD**: Intelligent file prioritization for near real-time imports
+- **📊 Enhanced Monitoring**: Real-time status with visual indicators
 
-#### For Existing Users
+</details>
+
+<details>
+<summary>✨ v2.5.19 - Metadata Enrichment</summary>
+
+### For Existing Users
 ```bash
 # Update to latest version
 npm update -g claude-self-reflect
@@ -231,50 +208,30 @@ claude-self-reflect setup
 docker compose run --rm importer python /app/scripts/delta-metadata-update-safe.py
 ```
 
-#### What You Get
+### What You Get
 - `search_by_concept("docker")` - Find conversations by topic
 - `search_by_file("server.py")` - Find conversations that touched specific files
 - Better search accuracy with metadata-based filtering
 
-## What's New
+</details>
+
+<details>
+<summary>📜 Release History</summary>
 
-- **v2.5.19** - Metadata Enrichment! Search by concepts, files, and tools. [Full release notes](docs/releases/v2.5.19-RELEASE-NOTES.md)
 - **v2.5.18** - Security dependency updates
-- **v2.5.17** - Critical CPU fix and memory limit adjustment. [Full release notes](docs/releases/v2.5.17-release-notes.md)
-- **v2.5.16** - (Pre-release only) Initial streaming importer with CPU throttling
+- **v2.5.17** - Critical CPU fix and memory limit adjustment
+- **v2.5.16** - Initial streaming importer with CPU throttling
 - **v2.5.15** - Critical bug fixes and collection creation improvements
-- **v2.5.14** - Async importer collection fix - All conversations now searchable
-- **v2.5.11** - Critical cloud mode fix - Environment variables now properly passed to MCP server
-- **v2.5.10** - Emergency hotfix for MCP server startup failure (dead code removal)
-- **v2.5.6** - Tool Output Extraction - Captures git changes & tool outputs for cross-agent discovery
+- **v2.5.14** - Async importer collection fix
+- **v2.5.11** - Critical cloud mode fix
+- **v2.5.10** - Emergency hotfix for MCP server startup
+- **v2.5.6** - Tool Output Extraction
 
 [Full changelog](docs/release-history.md)
 
-## Advanced Topics
-
-- [Performance tuning](docs/performance-guide.md)
-- [Security & privacy](docs/security.md)
-- [Windows setup](docs/windows-setup.md)
-- [Architecture details](docs/architecture-details.md)
-- [Contributing](CONTRIBUTING.md)
-
-### Uninstall
-
-For complete uninstall instructions, see [docs/UNINSTALL.md](docs/UNINSTALL.md).
-
-Quick uninstall:
-```bash
-# Remove MCP server
-claude mcp remove claude-self-reflect
-
-# Stop Docker containers
-docker-compose down
-
-# Uninstall npm package
-npm uninstall -g claude-self-reflect
-```
+</details>
 
-## Contributors
+## 👥 Contributors
 
 Special thanks to our contributors:
 - **[@TheGordon](https://github.com/TheGordon)** - Fixed timestamp parsing (#10)
@@ -283,4 +240,4 @@ Special thanks to our contributors:
 
 ---
 
-Built with ❤️  by [ramakay](https://github.com/ramakay) for the Claude community.
+Built with ❤️ by [ramakay](https://github.com/ramakay) for the Claude community.

package/mcp-server/src/project_resolver.py

@@ -54,7 +54,7 @@ class ProjectResolver:
         4. Fuzzy matching on collection names
         
         Args:
-            user_project_name: User-provided project name (e.g., "anukruti", "Anukruti", full path)
+            user_project_name: User-provided project name (e.g., "example-project", "Example-Project", full path)
             
         Returns:
             List of collection names that match the project
@@ -362,7 +362,7 @@ class ProjectResolver:
         
         Examples:
         - -Users-name-projects-my-app-src -> ['my', 'app', 'src']
-        - -Users-name-Code-freightwise-documents -> ['freightwise', 'documents']
+        - -Users-name-Code-example-project -> ['example', 'project']
         
         Args:
             path: Path in any format

package/mcp-server/src/server.py

@@ -81,15 +81,23 @@ def initialize_embeddings():
         print(f"[ERROR] Failed to initialize embeddings: {e}")
         return False
 
-# Debug environment loading
-print(f"[DEBUG] Environment variables loaded:")
-print(f"[DEBUG] ENABLE_MEMORY_DECAY: {ENABLE_MEMORY_DECAY}")
-print(f"[DEBUG] USE_NATIVE_DECAY: {USE_NATIVE_DECAY}")
-print(f"[DEBUG] DECAY_WEIGHT: {DECAY_WEIGHT}")
-print(f"[DEBUG] DECAY_SCALE_DAYS: {DECAY_SCALE_DAYS}")
-print(f"[DEBUG] PREFER_LOCAL_EMBEDDINGS: {PREFER_LOCAL_EMBEDDINGS}")
-print(f"[DEBUG] EMBEDDING_MODEL: {EMBEDDING_MODEL}")
-print(f"[DEBUG] env_path: {env_path}")
+# Debug environment loading and startup
+import sys
+import datetime as dt
+startup_time = dt.datetime.now().isoformat()
+print(f"[STARTUP] MCP Server starting at {startup_time}", file=sys.stderr)
+print(f"[STARTUP] Python: {sys.version}", file=sys.stderr)
+print(f"[STARTUP] Working directory: {os.getcwd()}", file=sys.stderr)
+print(f"[STARTUP] Script location: {__file__}", file=sys.stderr)
+print(f"[DEBUG] Environment variables loaded:", file=sys.stderr)
+print(f"[DEBUG] QDRANT_URL: {QDRANT_URL}", file=sys.stderr)
+print(f"[DEBUG] ENABLE_MEMORY_DECAY: {ENABLE_MEMORY_DECAY}", file=sys.stderr)
+print(f"[DEBUG] USE_NATIVE_DECAY: {USE_NATIVE_DECAY}", file=sys.stderr)
+print(f"[DEBUG] DECAY_WEIGHT: {DECAY_WEIGHT}", file=sys.stderr)
+print(f"[DEBUG] DECAY_SCALE_DAYS: {DECAY_SCALE_DAYS}", file=sys.stderr)
+print(f"[DEBUG] PREFER_LOCAL_EMBEDDINGS: {PREFER_LOCAL_EMBEDDINGS}", file=sys.stderr)
+print(f"[DEBUG] EMBEDDING_MODEL: {EMBEDDING_MODEL}", file=sys.stderr)
+print(f"[DEBUG] env_path: {env_path}", file=sys.stderr)
 
 
 class SearchResult(BaseModel):
@@ -259,31 +267,31 @@ async def update_indexing_status(cache_ttl: int = 5):
             
             # Convert set to list for compatibility
             imported_files_list = list(all_imported_files)
-                    
-                    # Count files that have been imported
-                    for file_path in jsonl_files:
-                        # Normalize the current file path for consistent comparison
-                        normalized_file = normalize_path(str(file_path))
-                        
-                        # Try multiple path formats to match Docker's state file
-                        file_str = str(file_path).replace(str(Path.home()), "/logs").replace("\\", "/")
-                        # Also try without .claude/projects prefix (Docker mounts directly)
-                        file_str_alt = file_str.replace("/.claude/projects", "")
-                        
-                        # Normalize alternative paths as well
-                        normalized_alt = normalize_path(file_str)
-                        normalized_alt2 = normalize_path(file_str_alt)
-                        
-                        # Check if file is in imported_files list (fully imported)
-                        if normalized_file in imported_files_list or normalized_alt in imported_files_list or normalized_alt2 in imported_files_list:
-                            indexed_files += 1
-                        # Or if it has metadata with position > 0 (partially imported)
-                        elif normalized_file in file_metadata and file_metadata[normalized_file].get("position", 0) > 0:
-                            indexed_files += 1
-                        elif normalized_alt in file_metadata and file_metadata[normalized_alt].get("position", 0) > 0:
-                            indexed_files += 1
-                        elif normalized_alt2 in file_metadata and file_metadata[normalized_alt2].get("position", 0) > 0:
-                            indexed_files += 1
+            
+            # Count files that have been imported
+            for file_path in jsonl_files:
+                # Normalize the current file path for consistent comparison
+                normalized_file = normalize_path(str(file_path))
+                
+                # Try multiple path formats to match Docker's state file
+                file_str = str(file_path).replace(str(Path.home()), "/logs").replace("\\", "/")
+                # Also try without .claude/projects prefix (Docker mounts directly)
+                file_str_alt = file_str.replace("/.claude/projects", "")
+                
+                # Normalize alternative paths as well
+                normalized_alt = normalize_path(file_str)
+                normalized_alt2 = normalize_path(file_str_alt)
+                
+                # Check if file is in imported_files list (fully imported)
+                if normalized_file in imported_files_list or normalized_alt in imported_files_list or normalized_alt2 in imported_files_list:
+                    indexed_files += 1
+                # Or if it has metadata with position > 0 (partially imported)
+                elif normalized_file in file_metadata and file_metadata[normalized_file].get("position", 0) > 0:
+                    indexed_files += 1
+                elif normalized_alt in file_metadata and file_metadata[normalized_alt].get("position", 0) > 0:
+                    indexed_files += 1
+                elif normalized_alt2 in file_metadata and file_metadata[normalized_alt2].get("position", 0) > 0:
+                    indexed_files += 1
         
         # Update status
         indexing_status["last_check"] = current_time
@@ -1519,4 +1527,8 @@ if __name__ == "__main__":
         sys.exit(0)
     
     # Normal MCP server operation
+    print(f"[STARTUP] Starting FastMCP server in stdio mode...", file=sys.stderr)
+    print(f"[STARTUP] Server name: {mcp.name}", file=sys.stderr)
+    print(f"[STARTUP] Calling mcp.run()...", file=sys.stderr)
     mcp.run()
+    print(f"[STARTUP] Server exited normally", file=sys.stderr)

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "claude-self-reflect",
-  "version": "2.8.0",
+  "version": "2.8.2",
   "description": "Give Claude perfect memory of all your conversations - Installation wizard for Python MCP server",
   "keywords": [
     "claude",