superlocalmemory 2.3.6 → 2.4.0

package/CHANGELOG.md

@@ -16,6 +16,71 @@ SuperLocalMemory V2 - Intelligent local memory system for AI coding assistants.
 
 ---
 
+## [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
+- **--full flag**: Show complete memory content without truncation in search/list/recent/cluster commands
+- **Smart truncation**: Memories <5000 chars shown in full, ≥5000 chars truncated to 2000 chars (previously always truncated at 200 chars)
+- **Help text**: Added --full flag documentation to CLI help output
+
+### Fixed
+- **CLI bug**: Fixed `get` command error - `get_memory()` → `get_by_id()` method call
+- **Content display**: Recall now shows full content for short/medium memories instead of always truncating at 200 chars
+- **User experience**: Agents and users can now see complete memory content by default for most memories
+
+### Changed
+- **Truncation logic**: 200 char limit → 2000 char preview for memories ≥5000 chars
+- **Node.js wrappers**: memory-recall-skill.js and memory-list-skill.js updated to pass --full flag through
+
+### Technical Details
+- Added `format_content()` helper function in memory_store_v2.py (line 918)
+- Updated search/list/recent/cluster commands to use smart truncation
+- Backward compatible: same output structure, MCP/API calls unaffected
+- All 74+ existing memories tested: short memories show full, long memories truncate intelligently
+
+---
+
 ## [2.3.5] - 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@2.3.7
+```
+
+**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

package/hooks/memory-list-skill.js

@@ -34,6 +34,7 @@ Options:
                          • recent: Latest created first (default)
                          • accessed: Most recently accessed
                          • importance: Highest importance first
+  --full                 Show complete content without truncation
 
 Examples:
   memory-list
@@ -42,17 +43,17 @@ Examples:
 
   memory-list --sort importance
 
-  memory-list --limit 10 --sort accessed
+  memory-list --limit 10 --sort accessed --full
 
 Output Format:
-  • ID, Content (truncated), Tags, Importance
+  • ID, Content (smart truncated), Tags, Importance
   • Creation timestamp
   • Access count and last accessed time
 
 Notes:
   • Default shows last 20 memories
-  • Content is truncated to 100 chars for readability
-  • Use ID with memory-recall to see full content
+  • Smart truncation: full content if <5000 chars, preview if ≥5000 chars
+  • Use --full flag to always show complete content
   • Sort by 'accessed' to find frequently used memories
 `);
     return;
@@ -61,6 +62,7 @@ Notes:
   // Parse options
   let limit = 20;
   let sortBy = 'recent';
+  let showFull = false;
 
   for (let i = 0; i < args.length; i++) {
     const arg = args[i];
@@ -83,6 +85,8 @@ Notes:
         return;
       }
       i++;
+    } else if (arg === '--full') {
+      showFull = true;
     }
   }
 
@@ -97,6 +101,11 @@ Notes:
     pythonArgs = ['list', limit.toString()];
   }
 
+  // Add --full flag if requested
+  if (showFull) {
+    pythonArgs.push('--full');
+  }
+
   try {
     const { stdout, stderr } = await execFileAsync('python3', [memoryScript, ...pythonArgs]);
 

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/hooks/memory-recall-skill.js

@@ -33,13 +33,14 @@ Arguments:
 
 Options:
   --limit <n>            Maximum results to return (default: 10)
+  --full                 Show complete content without truncation
 
 Examples:
   memory-recall "authentication bug"
 
   memory-recall "API configuration" --limit 5
 
-  memory-recall "security best practices"
+  memory-recall "security best practices" --full
 
   memory-recall "user preferences"
 
@@ -47,6 +48,8 @@ Output Format:
   • Ranked by relevance (TF-IDF cosine similarity)
   • Shows: ID, Content, Tags, Importance, Timestamp
   • Higher scores = better matches
+  • Smart truncation: full content if <5000 chars, preview if ≥5000 chars
+  • Use --full flag to always show complete content
 
 Notes:
   • Uses local TF-IDF search (no external APIs)
@@ -67,6 +70,8 @@ Notes:
     if (arg === '--limit' && i + 1 < args.length) {
       // Note: V1 store doesn't support --limit in search, will truncate output instead
       i++; // Skip but don't add to pythonArgs
+    } else if (arg === '--full') {
+      pythonArgs.push('--full');
     } else if (!arg.startsWith('--') && query === null) {
       query = arg;
     }

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": "2.3.6",
+  "version": "2.4.0",
   "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",