superlocalmemory 2.3.7 → 2.4.1

package/CHANGELOG.md

@@ -16,6 +16,72 @@ SuperLocalMemory V2 - Intelligent local memory system for AI coding assistants.
 
 ---
 
+## [2.4.1] - 2026-02-11
+
+**Release Type:** Hierarchical Clustering & Documentation Release
+**Backward Compatible:** Yes (additive schema changes only)
+
+### Added
+- **Hierarchical Leiden clustering** (`graph_engine.py`): Recursive community detection — large clusters (≥10 members) are automatically sub-divided up to 3 levels deep. E.g., "Python" → "FastAPI" → "Authentication patterns". New `parent_cluster_id` and `depth` columns in `graph_clusters` table
+- **Community summaries** (`graph_engine.py`): TF-IDF structured reports for every cluster — key topics, projects, categories, hierarchy context. Stored in `graph_clusters.summary` column, surfaced in `/api/clusters` endpoint and web dashboard
+- **CLI commands**: `python3 graph_engine.py hierarchical` and `python3 graph_engine.py summaries` for manual runs
+- **Schema migration**: Safe `ALTER TABLE` additions for `summary`, `parent_cluster_id`, `depth` columns — backward compatible with existing databases
+
+### Changed
+- `build_graph()` now automatically runs hierarchical sub-clustering and summary generation after flat Leiden
+- `/api/clusters` endpoint returns `summary`, `parent_cluster_id`, `depth` fields
+- `get_stats()` includes `max_depth` and per-cluster summary/hierarchy data
+- `setup_validator.py` schema updated to include new columns
+
+### Documentation
+- **README.md**: v2.4.0→v2.4.1, added Hierarchical Leiden, Community Summaries, MACLA, Auto-Backup sections
+- **Wiki**: Updated Roadmap, Pattern-Learning-Explained, Knowledge-Graph-Guide, Configuration, Visualization-Dashboard, Footer
+- **Website**: Updated features.astro, comparison.astro, index.astro for v2.4.1 features
+- **`.npmignore`**: Recursive `__pycache__` exclusion patterns
+
+---
+
+## [2.4.0] - 2026-02-11
+
+**Release Type:** Profile System & Intelligence Release
+**Backward Compatible:** Yes (additive schema changes only)
+
+### Added
+- **Column-based memory profiles**: Single `memory.db` with `profile` column — all memories, clusters, patterns, and graph data are profile-scoped. Switch profiles from any IDE/CLI and it takes effect everywhere instantly via shared `profiles.json`
+- **Auto-backup system** (`src/auto_backup.py`): SQLite backup API with configurable interval (daily/weekly), retention policy, and one-click backup from UI
+- **MACLA confidence scorer**: Research-grounded Beta-Binomial Bayesian posterior (arXiv:2512.18950) replaces ad-hoc log2 formula. Pattern-specific priors: preference(1,4), style(1,5), terminology(2,3). Log-scaled competition prevents over-dilution from sparse signals
+- **UI: Profile Management**: Create, switch, and delete profiles from the web dashboard. "+" button in navbar for quick creation, full management table in Settings tab
+- **UI: Settings tab**: Auto-backup status, configuration (interval, max backups, enable toggle), backup history, profile management — all in one place
+- **UI: Column sorting**: Click any column header in the Memories table to sort asc/desc
+- **UI: Enhanced Patterns view**: DOM-based rendering with confidence bars, color coding, type icons
+- **API: Profile isolation on all endpoints**: `/api/graph`, `/api/clusters`, `/api/patterns`, `/api/timeline` now filter by active profile (previously showed all profiles)
+- **API: `get_active_profile()` helper**: Shared function in `ui_server.py` replaces 4 duplicate inline profile-reading blocks
+- **API: Profile CRUD endpoints**: `POST /api/profiles/create`, `DELETE /api/profiles/{name}` with validation and safety (can't delete default or active profile)
+
+### Fixed
+- **Profile switching ValueError**: Rewrote from directory-based to column-based profiles — no more file copy errors on switch
+- **Pattern learner schema validation**: Safe column addition with try/except for `profile` column on `identity_patterns` table
+- **Graph engine schema validation**: Safe column check before profile-filtered queries
+- **Research references**: PageIndex correctly attributed to VectifyAI (not Meta AI), removed fabricated xMemory/Stanford citation, replaced with MemoryBank (AAAI 2024) across wiki and website
+- **Graph tooltip**: Shows project name or Memory ID instead of "Uncategorized" when category is null
+
+### Changed
+- All 4 core layers (storage, tree, graph, patterns) are now profile-aware
+- `memory_store_v2.py`: Every query filters by `WHERE profile = ?` from `_get_active_profile()`
+- `graph_engine.py`: `build_graph()` and `get_stats()` scoped to active profile
+- `pattern_learner.py`: Pattern learning and retrieval scoped to active profile
+- `ui_server.py`: Refactored profile code into shared helper, eliminated 4 duplicate blocks
+
+### Technical Details
+- Schema: `ALTER TABLE memories ADD COLUMN profile TEXT DEFAULT 'default'`
+- Schema: `ALTER TABLE identity_patterns ADD COLUMN profile TEXT DEFAULT 'default'`
+- MACLA formula: `posterior = (alpha + evidence) / (alpha + beta + evidence + log2(total_memories))`
+- Confidence range: 0.0 to 0.95 (capped), with recency and distribution bonuses
+- Backup: Uses SQLite `backup()` API for safe concurrent backup
+- 17 API endpoint tests, 5 core module tests — all passing
+
+---
+
 ## [2.3.7] - 2026-02-09
 
 ### Added

package/README.md

@@ -119,6 +119,31 @@ superlocalmemoryv2:status
 
 **That's it.** No Docker. No API keys. No cloud accounts. No configuration.
 
+### Updating to Latest Version
+
+**npm users:**
+```bash
+# Update to latest version
+npm update -g superlocalmemory
+
+# Or force latest
+npm install -g superlocalmemory@latest
+
+# Install specific version
+npm install -g superlocalmemory@latest
+```
+
+**Manual install users:**
+```bash
+cd SuperLocalMemoryV2
+git pull origin main
+./install.sh  # Mac/Linux
+# or
+.\install.ps1  # Windows
+```
+
+**Your data is safe:** Updates preserve your database and all memories.
+
 ### Start the Visualization Dashboard
 
 ```bash
@@ -164,6 +189,19 @@ python ~/.claude-memory/ui_server.py
 
 ---
 
+### New in v2.4.1: Hierarchical Clustering, Community Summaries & Auto-Backup
+
+| Feature | Description |
+|---------|-------------|
+| **Hierarchical Leiden** | Recursive community detection — clusters within clusters up to 3 levels. "Python" → "FastAPI" → "Auth patterns" |
+| **Community Summaries** | TF-IDF structured reports per cluster: key topics, projects, categories at a glance |
+| **MACLA Confidence** | Bayesian Beta-Binomial scoring (arXiv:2512.18950) — calibrated confidence, not raw frequency |
+| **Auto-Backup** | Configurable SQLite backups with retention policies, one-click restore from dashboard |
+| **Profile UI** | Create, switch, delete profiles from the web dashboard — full isolation per context |
+| **Profile Isolation** | All API endpoints (graph, clusters, patterns, timeline) scoped to active profile |
+
+---
+
 ## 🔍 Advanced Search
 
 SuperLocalMemory V2.2.0 implements **hybrid search** combining multiple strategies for maximum accuracy.
@@ -408,13 +446,13 @@ Not another simple key-value store. SuperLocalMemory implements **cutting-edge m
 │  6 universal slash-commands for AI assistants               │
 │  Compatible with Claude Code, Continue, Cody                │
 ├─────────────────────────────────────────────────────────────┤
-│  Layer 4: PATTERN LEARNING                                  │
-│  Learns: coding style, preferences, terminology             │
+│  Layer 4: PATTERN LEARNING + MACLA (v2.4.0)                  │
+│  Bayesian Beta-Binomial confidence (arXiv:2512.18950)       │
 │  "You prefer React over Vue" (73% confidence)               │
 ├─────────────────────────────────────────────────────────────┤
-│  Layer 3: KNOWLEDGE GRAPH                                   │
-│  Auto-clusters: "Auth & Tokens", "Performance", "Testing"   │
-│  Discovers relationships you didn't know existed            │
+│  Layer 3: KNOWLEDGE GRAPH + HIERARCHICAL LEIDEN (v2.4.1)    │
+│  Recursive clustering: "Python" → "FastAPI" → "Auth"        │
+│  Community summaries + TF-IDF structured reports            │
 ├─────────────────────────────────────────────────────────────┤
 │  Layer 2: HIERARCHICAL INDEX                                │
 │  Tree structure for fast navigation                         │
@@ -463,6 +501,8 @@ python ~/.claude-memory/pattern_learner.py context 0.5
 
 **Your AI assistant can now match your preferences automatically.**
 
+**MACLA Confidence Scoring (v2.4.0):** Confidence uses a Bayesian Beta-Binomial posterior (Forouzandeh et al., [arXiv:2512.18950](https://arxiv.org/abs/2512.18950)). Pattern-specific priors, log-scaled competition, recency bonus. Range: 0.0–0.95 (hard cap prevents overconfidence).
+
 ### Multi-Profile Support
 
 ```bash
@@ -512,14 +552,21 @@ superlocalmemoryv2:profile create <name>                 # New profile
 superlocalmemoryv2:profile switch <name>                 # Switch context
 
 # Knowledge Graph
-python ~/.claude-memory/graph_engine.py build            # Build graph
+python ~/.claude-memory/graph_engine.py build            # Build graph (+ hierarchical + summaries)
 python ~/.claude-memory/graph_engine.py stats            # View clusters
 python ~/.claude-memory/graph_engine.py related --id 5   # Find related
+python ~/.claude-memory/graph_engine.py hierarchical     # Sub-cluster large communities
+python ~/.claude-memory/graph_engine.py summaries        # Generate cluster summaries
 
 # Pattern Learning
 python ~/.claude-memory/pattern_learner.py update        # Learn patterns
 python ~/.claude-memory/pattern_learner.py context 0.5   # Get identity
 
+# Auto-Backup (v2.4.0)
+python ~/.claude-memory/auto_backup.py backup            # Manual backup
+python ~/.claude-memory/auto_backup.py list              # List backups
+python ~/.claude-memory/auto_backup.py status            # Backup status
+
 # Reset (Use with caution!)
 superlocalmemoryv2:reset soft                            # Clear memories
 superlocalmemoryv2:reset hard --confirm                  # Nuclear option

package/hooks/memory-profile-skill.js

@@ -31,13 +31,13 @@ async function memoryProfileSkill() {
 ║                                                          ║
 ╚══════════════════════════════════════════════════════════╝
 
-Profiles let you maintain separate memory databases for different contexts:
+Profiles let you maintain separate memory contexts in ONE database:
   • Work vs Personal projects
   • Different clients or teams
-  • Different AI personalities
   • Experimentation vs Production
 
-Each profile has isolated: memories, graph, patterns, archives
+All profiles share one database. Switching is instant and safe.
+No data copying, no data loss risk.
 
 Usage: memory-profile <command> [options]
 
@@ -157,18 +157,12 @@ After switching, restart Claude CLI for changes to take effect.
 
     console.log(`
 ╔══════════════════════════════════════════════════════════╗
-║              Profile Switch Confirmation                 ║
+║              Profile Switch                              ║
 ╚══════════════════════════════════════════════════════════╝
 
-This will:
-  ✓ Save current profile state
-  ✓ Load profile "${profileName}"
-  ✓ Update active profile marker
-
-After switching, you MUST restart Claude CLI for the new profile
-to take effect.
-
-Current memories will be preserved in the old profile.
+This will switch the active profile to "${profileName}".
+All profiles share one database — switching is instant and safe.
+Your current memories are always preserved.
 `);
 
     const answer = await question('Proceed with profile switch? (yes/no): ');
@@ -181,11 +175,6 @@ Current memories will be preserved in the old profile.
           profileName
         ]);
         console.log(stdout);
-        console.log(`
-⚠️  IMPORTANT: Restart Claude CLI now for profile switch to complete.
-
-The new profile will not be active until you restart.
-`);
       } catch (error) {
         console.error('❌ Error:', error.message);
         if (error.stdout) console.log(error.stdout);

package/mcp_server.py

@@ -332,7 +332,8 @@ async def switch_profile(name: str) -> dict:
     Switch to a different memory profile.
 
     Profiles allow you to maintain separate memory contexts
-    (e.g., work, personal, client projects).
+    (e.g., work, personal, client projects). All profiles share
+    one database — switching is instant and safe (no data copying).
 
     Args:
         name: Profile name to switch to
@@ -345,25 +346,40 @@ async def switch_profile(name: str) -> dict:
         }
     """
     try:
-        # Profile switching logic (calls existing system)
-        profile_path = MEMORY_DIR / "profiles" / name
-
-        if not profile_path.exists():
+        # Import profile manager (uses column-based profiles)
+        sys.path.insert(0, str(MEMORY_DIR))
+        from importlib import import_module
+        # Use direct JSON config update for speed
+        import json
+        config_file = MEMORY_DIR / "profiles.json"
+
+        if config_file.exists():
+            with open(config_file, 'r') as f:
+                config = json.load(f)
+        else:
+            config = {'profiles': {'default': {'name': 'default', 'description': 'Default memory profile'}}, 'active_profile': 'default'}
+
+        if name not in config.get('profiles', {}):
+            available = ', '.join(config.get('profiles', {}).keys())
             return {
                 "success": False,
-                "message": f"Profile '{name}' does not exist. Use list_profiles() to see available profiles."
+                "message": f"Profile '{name}' not found. Available: {available}"
             }
 
-        # Update current profile symlink
-        current_link = MEMORY_DIR / "current_profile"
-        if current_link.exists() or current_link.is_symlink():
-            current_link.unlink()
-        current_link.symlink_to(profile_path)
+        old_profile = config.get('active_profile', 'default')
+        config['active_profile'] = name
+
+        from datetime import datetime
+        config['profiles'][name]['last_used'] = datetime.now().isoformat()
+
+        with open(config_file, 'w') as f:
+            json.dump(config, f, indent=2)
 
         return {
             "success": True,
             "profile": name,
-            "message": f"Switched to profile '{name}'. Restart IDE to use new profile."
+            "previous_profile": old_profile,
+            "message": f"Switched to profile '{name}'. Memory operations now use this profile."
         }
 
     except Exception as e:
@@ -374,6 +390,51 @@ async def switch_profile(name: str) -> dict:
         }
 
 
+@mcp.tool(annotations=ToolAnnotations(
+    readOnlyHint=True,
+    destructiveHint=False,
+    openWorldHint=False,
+))
+async def backup_status() -> dict:
+    """
+    Get auto-backup system status for SuperLocalMemory.
+
+    Returns backup configuration, last backup time, next scheduled backup,
+    total backup count, and storage used. Useful for monitoring data safety.
+
+    Returns:
+        {
+            "enabled": bool,
+            "interval_display": str,
+            "last_backup": str or null,
+            "next_backup": str or null,
+            "backup_count": int,
+            "total_size_mb": float
+        }
+    """
+    try:
+        from auto_backup import AutoBackup
+        backup = AutoBackup()
+        status = backup.get_status()
+        return {
+            "success": True,
+            **status
+        }
+    except ImportError:
+        return {
+            "success": False,
+            "message": "Auto-backup module not installed. Update SuperLocalMemory to v2.4.0+.",
+            "enabled": False,
+            "backup_count": 0
+        }
+    except Exception as e:
+        return {
+            "success": False,
+            "error": str(e),
+            "message": "Failed to get backup status"
+        }
+
+
 # ============================================================================
 # CHATGPT CONNECTOR TOOLS (search + fetch — required by OpenAI MCP spec)
 # These two tools are required for ChatGPT Connectors and Deep Research.
@@ -673,6 +734,7 @@ if __name__ == "__main__":
     print("  - get_status()", file=sys.stderr)
     print("  - build_graph()", file=sys.stderr)
     print("  - switch_profile(name)", file=sys.stderr)
+    print("  - backup_status()        [Auto-Backup]", file=sys.stderr)
     print("", file=sys.stderr)
     print("MCP Resources Available:", file=sys.stderr)
     print("  - memory://recent/{limit}", file=sys.stderr)

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "superlocalmemory",
-  "version": "2.3.7",
+  "version": "2.4.1",
   "description": "Your AI Finally Remembers You - Local-first intelligent memory system for AI assistants. Works with Claude, Cursor, Windsurf, VS Code/Copilot, Codex, and 16+ AI tools. 100% local, zero cloud dependencies.",
   "keywords": [
     "ai-memory",
@@ -43,6 +43,7 @@
     "superlocalmemory": "./bin/slm-npm"
   },
   "scripts": {
+    "prepack": "find . -type d -name __pycache__ -exec rm -rf {} + 2>/dev/null; find . -name '*.pyc' -delete 2>/dev/null; true",
     "postinstall": "node scripts/postinstall.js",
     "preuninstall": "node scripts/preuninstall.js",
     "test": "echo \"Run: npm install -g . && slm status\" && exit 0"