agentic-flow 2.0.1-alpha.32 → 2.0.1-alpha.33

package/CHANGELOG.md

@@ -2,617 +2,6 @@
 
 All notable changes to this project will be documented in this file.
 
-## [2.0.1-alpha.29] - 2025-12-31
-
-### Added
-- **E2B Sandbox Integration**: Secure cloud sandboxes for AI code execution
-  - Firecracker-based isolation with Code Interpreter support
-  - Python, JavaScript, and shell execution
-  - File system access and package installation
-  - `E2BSandboxManager`, `runInE2BSandbox()`, `isE2BAvailable()`
-
-- **Query Control System**: Runtime control of active SDK queries
-  - Change model mid-execution (`setModel()`)
-  - Switch permission modes (`setPermissionMode()`)
-  - Interrupt, resume, and abort queries
-  - Query introspection (commands, models, MCP status)
-  - `createQueryController()`, `getActiveQueries()`, `abortAllQueries()`
-
-- **Plugins System**: Flexible plugin loading and management
-  - Load from local filesystem, NPM packages, remote URLs, or inline
-  - Plugin tool execution with typed definitions
-  - Checksum verification for remote plugins
-  - `loadPlugin()`, `getAllPluginTools()`, `executePluginTool()`, `defineTool()`
-
-- **Streaming Input Mode**: Async iterable prompts for SDK
-  - `StreamingPromptBuilder` with fluent API
-  - `InteractivePromptStream` for real-time input
-  - Transform, filter, batch, and rate-limit operations
-  - `streamingPrompt()`, `createInteractiveStream()`, `fromArray()`
-
-- **Security Module**: Comprehensive security hardening
-  - Path sanitization with traversal protection
-  - Command injection detection (20+ patterns)
-  - Secret redaction (API keys, tokens, DB URLs, private keys)
-  - Rate limiting with sliding window
-  - Audit logging with file persistence
-  - `sanitizePath()`, `validateCommand()`, `redactSecrets()`, `checkRateLimit()`, `auditLog()`
-
-### Tests
-- 47 security tests covering all security functions
-- 46 SDK module tests for E2B, query control, plugins, and streaming
-- All 93 tests passing
-
-## [2.0.1-alpha.28] - 2025-12-31
-
-### Added
-- **SDK Structured Outputs**: `outputFormat` with JSON schema support
-- **SDK Sandbox Configuration**: Environment variable control for sandbox mode
-- **Beta Features**: 1M context window support (`SDK_ENABLE_BETAS=true`)
-- **Query Limits**: `maxTurns` and `maxBudgetUsd` controls
-- **File Checkpointing**: Persistent session state (`SDK_FILE_CHECKPOINTING=true`)
-
-### Environment Variables
-- `SDK_OUTPUT_SCHEMA` - JSON schema for structured output
-- `SDK_ENABLE_SANDBOX` - Enable SDK sandbox mode
-- `SDK_ENABLE_BETAS` - Enable beta features (1M context)
-- `SDK_MAX_TURNS` - Maximum conversation turns
-- `SDK_MAX_BUDGET_USD` - Maximum cost limit
-- `SDK_FILE_CHECKPOINTING` - Enable file checkpointing
-
-## [2.0.1-alpha.27] - 2025-12-31
-
-### Fixed
-- **Permission Handler**: Overly broad command substitution blocking
-  - Changed `/\$\(.*\)/` to specific dangerous patterns
-  - Safe patterns like `$(date)` now allowed
-- **Memory Leaks**: Added TTL-based cleanup for Maps
-  - `activeTrajectories`: 5-minute TTL with 2-minute cleanup
-  - `activeSessions`: 30-minute TTL with 5-minute cleanup
-- **Agent Converter**: Added 1-minute cache for converted agents
-  - `invalidateAgentCache()` function for manual cache clearing
-
-### Added
-- New dangerous patterns: `git push --force`, `npm publish`, `cat .env`
-- TTL cleanup intervals for trajectory and session Maps
-- Agent conversion caching for performance
-
-### Tests
-- 20 permission handler tests (all passing)
-- Includes git force push, npm publish, safe command substitution
-
-## [2.0.1-alpha.26] - 2025-12-31
-
-### Added
-- **SDK Integration Module**: Full Claude Agent SDK v0.1.76 support
-  - Hooks bridge with trajectory tracking
-  - Session management with resume/fork
-  - Custom permission handlers
-  - Agent converter for subagent spawning
-  - All 17 SDK tools enabled
-
-### Exports (src/sdk/index.ts)
-- Hooks: `preToolUseHook`, `postToolUseHook`, `sessionStartHook`, etc.
-- Sessions: `captureSessionId`, `getResumeOptions`, `getForkOptions`
-- Permissions: `customPermissionHandler`, `strictPermissionHandler`
-- Agents: `convertAgentToSdkFormat`, `getAgentsForUseCase`
-
-## [2.0.1-alpha.25] - 2025-12-31
-
-### Added
-- **Multi-Algorithm Learning Engine**: 9 specialized RL algorithms for different task types
-
-  | Algorithm            | Task Type           | Why                              |
-  |----------------------|---------------------|----------------------------------|
-  | double-q             | agent-routing       | Reduces overestimation bias      |
-  | sarsa                | error-avoidance     | Conservative, on-policy          |
-  | actor-critic         | confidence-scoring  | Continuous 0-1 scores            |
-  | ppo                  | context-ranking     | Stable preference learning       |
-  | decision-transformer | trajectory-learning | Sequence patterns                |
-  | td-lambda            | memory-recall       | Better credit assignment         |
-  | q-learning           | pattern-matching    | Fast value-based matching        |
-  | reinforce            | exploration         | Policy gradient for novel tasks  |
-  | a2c                  | multi-agent         | Advantage estimation             |
-
-### New Functions (IntelligenceBridge)
-- `getAlgorithmForTask(taskType)` - Get recommended algorithm and reason
-- `learnFromEpisode(taskType, state, action, reward, nextState, done)` - Learn with appropriate algorithm
-- `getActionValue(taskType, state, action)` - Get Q-value or policy probability
-- `getMultiAlgorithmStats()` - Get per-algorithm episode counts and avg rewards
-
-### Updated
-- `ruvector` upgraded to `^0.1.69` with multi-algorithm learning engine
-- `getIntelligenceStats()` now includes `multiAlgorithmStats`
-- Features list now includes `multi-algorithm-rl`
-
-### Usage
-```typescript
-import { getAlgorithmForTask, learnFromEpisode } from 'agentic-flow/hooks';
-
-// Get recommended algorithm for a task
-const { algorithm, reason } = getAlgorithmForTask('agent-routing');
-// => { algorithm: 'double-q', reason: 'Reduces overestimation bias...' }
-
-// Learn from an episode
-const result = await learnFromEpisode(
-  'error-avoidance',  // Uses SARSA (conservative)
-  'state',
-  'action',
-  0.9,  // reward
-  'nextState',
-  true  // done
-);
-```
-
-## [2.0.1-alpha.24] - 2025-12-31
-
-### Added
-- **Tiered TensorCompress**: Dynamic compression based on access frequency
-  - **Hot patterns** (>80% freq): No compression (0% savings) - fastest access
-  - **Warm patterns** (40-80% freq): Half precision (50% savings)
-  - **Cool patterns** (10-40% freq): PQ8 quantization (87.5% savings)
-  - **Cold patterns** (1-10% freq): PQ4 quantization (93.75% savings)
-  - **Archive patterns** (<1% freq): Binary (96.9% savings)
-
-### Improved
-- **Access Frequency Tracking**: Each pattern tracks total accesses, creation time
-- **Dynamic Tier Migration**: Patterns automatically move between tiers based on usage
-- **Periodic Recompression**: Background process migrates patterns every 5 minutes
-- **Memory Efficiency**: Up to 96.9% memory savings for rarely-used patterns
-- **Stats Display**: New compression tier distribution table in `enhanced_booster_stats`
-
-### IntelligenceBridge Integration
-- **TensorCompress in Hooks**: Tiered compression now integrated into hooks intelligence layer
-- **storePattern**: New patterns start as "hot" (no compression), migrate based on access
-- **findSimilarPatterns**: Tracks accesses for automatic tier migration
-- **routeTaskIntelligent**: Pattern results now tracked for compression decisions
-- **getIntelligenceStats**: Now includes `compressionStats` with tier distribution
-- **Backward Compatible**: Existing patterns continue to work without modification
-
-### Technical Details
-- Access frequency = 50% access ratio + 30% recency (24hr decay) + 20% success rate
-- New patterns start as "hot" (no compression) since they're likely to be reused
-- Recompression runs non-blocking in background during apply()
-- Backward-compatible with older pattern files (auto-migrates fields)
-
-### Stats Output
-```
-🗜️ Tiered Compression:
-   ┌─────────────────────────────────────────────────┐
-   │ Tier      │ Count │ Access Freq │ Memory Save  │
-   ├─────────────────────────────────────────────────┤
-   │ 🔥 Hot    │    15 │ >80%        │ 0%           │
-   │ 🌡️ Warm   │     8 │ 40-80%      │ 50%          │
-   │ ❄️ Cool   │    12 │ 10-40%      │ 87.5%        │
-   │ 🧊 Cold   │    25 │ 1-10%       │ 93.75%       │
-   │ 📦 Archive│    40 │ <1%         │ 96.9%        │
-   └─────────────────────────────────────────────────┘
-   Compression Ratio: 4.2:1
-   Memory Savings: 76.2%
-```
-
-## [2.0.1-alpha.23] - 2025-12-31
-
-### Added
-- **Enhanced Agent Booster v2**: Full RuVector intelligence stack upgrade
-  - **Semantic Fuzzy Matching**: Match similar patterns (var x → var y) with 91%+ similarity
-  - **ONNX Embeddings**: Semantic code understanding with async initialization
-  - **Parallel Batch Apply**: 4x faster multi-file edits
-  - **Context-Aware Prefetch**: Pre-warm cache based on file context
-  - **Error Pattern Learning**: Learn what NOT to do from failed edits
-  - **TensorCompress**: 10x more patterns in memory
-  - **Co-Edit Graph**: Track which files are edited together
-
-### New MCP Tools
-- `enhanced_booster_batch` - Apply multiple edits in parallel
-- `enhanced_booster_prefetch` - Pre-warm cache for a file
-- `enhanced_booster_likely_files` - Get files likely to be edited next
-
-### Performance v2
-| Strategy | Latency | Description |
-|----------|---------|-------------|
-| exact_cache | **0ms** | Identical pattern match |
-| fuzzy_match | **0-5ms** | Similar pattern (91%+ similarity) |
-| gnn_match | 1-10ms | GNN differentiable search |
-| agent_booster | ~650ms | Fallback to underlying engine |
-
-### Test Results
-```
-🎯 Step 2: Exact cache hit → 0ms
-🔮 Step 4: Fuzzy match → 0ms (91.9% similarity)
-⚡ Step 5: Batch (4 edits) → 0ms total, 4/4 fuzzy matches
-```
-
-## [2.0.1-alpha.22] - 2025-12-31
-
-### Added
-- **RuVector-Enhanced Agent Booster**: Supercharged code editing with self-learning
-  - **HNSW Pattern Cache**: 0ms cache hits vs 650ms baseline (~infinite speedup)
-  - **SONA Learning**: Continuously improves from edit success/failure
-  - **GNN Matching**: Differentiable search for similar patterns
-  - **Embedding Support**: Hash-based (fast) or ONNX (semantic)
-
-### New Files
-- `src/intelligence/agent-booster-enhanced.ts` - Main enhanced booster module
-- `src/mcp/tools/enhanced-booster-tools.ts` - MCP tools for enhanced booster
-
-### New MCP Tools
-- `enhanced_booster_edit` - Apply edit with RuVector intelligence
-- `enhanced_booster_edit_file` - Edit file with auto-learning
-- `enhanced_booster_stats` - View cache hit rate, patterns learned
-- `enhanced_booster_pretrain` - Pre-cache common patterns
-- `enhanced_booster_benchmark` - Compare enhanced vs baseline
-- `enhanced_booster_record_outcome` - Feedback for learning
-
-### Performance
-| Metric | Baseline | Enhanced |
-|--------|----------|----------|
-| Cache Hit Latency | N/A | **0ms** |
-| Pattern Match | 650ms | 0-5ms |
-| Learning | None | SONA + EWC++ |
-| Pattern Capacity | 0 | 10,000+ |
-
-### Usage
-```typescript
-import { getEnhancedBooster } from 'agentic-flow/intelligence';
-
-const booster = getEnhancedBooster();
-await booster.pretrain(); // Cache common patterns
-
-const result = await booster.apply({
-  code: 'var x = 1;',
-  edit: 'const x = 1;',
-  language: 'javascript'
-});
-// First call: agent_booster (650ms)
-// Second call: cache_hit (0ms)!
-```
-
-## [2.0.1-alpha.21] - 2025-12-31
-
-### Fixed
-- **Windows Agent Booster Error**: Resolved "Cannot find package 'agent-booster'" error
-  - Made all `agent-booster` imports optional with try-catch wrappers
-  - Added null checks for AgentBooster in all MCP tools and handlers
-  - Graceful fallback when agent-booster is not available
-  - Removed `file:` dependency that required local package
-
-### Changed
-- `claudeFlowSdkServer.ts`: Agent Booster tools return helpful error message when unavailable
-- `agent-booster-tools.ts`: All handlers check for booster availability before use
-- `agent-booster-migration.ts`: Engine initialization now optional, fallback to traditional edits
-
-### Notes
-- Agent Booster tools will gracefully degrade on Windows
-- CLI-based agent-booster commands (`npx agent-booster@0.2.2`) still work on all platforms
-- Native import-based agent-booster requires Linux/macOS
-
-## [2.0.1-alpha.20] - 2025-12-31
-
-### Fixed
-- **Windows Compatibility**: Full persistence without native module compilation
-  - `better-sqlite3` moved to optionalDependencies
-  - **sql.js (WASM SQLite)** fallback for Windows persistence
-  - Automatic backend selection: native → WASM → memory
-  - No Visual Studio Build Tools required
-
-### Added
-- **WASM SQLite Cache**: Cross-platform persistence via sql.js
-  - Stores embeddings in `~/.agentic-flow/embedding-cache-wasm.db`
-  - Debounced file writes (1s) for performance
-  - Same 9000x speedup on Windows
-
-### Changed
-- EmbeddingCache auto-selects backend (priority order):
-  1. Native SQLite (better-sqlite3) - Fastest, ~0.045ms
-  2. WASM SQLite (sql.js) - Cross-platform, ~0.1ms
-  3. In-memory LRU - No persistence, ~0.01ms
-- New `getBackendType()` method: returns 'native' | 'wasm' | 'memory'
-
-### Performance
-| Backend | Time | Persistence | Platform |
-|---------|------|-------------|----------|
-| Native SQLite | ~0.045ms | ✓ | Linux/macOS |
-| WASM SQLite | ~0.1ms | ✓ | Windows/All |
-| Memory | ~0.01ms | ✗ | Fallback |
-
-## [2.0.1-alpha.19] - 2025-12-31
-
-### Added
-- **Cache Pretrain**: Pre-populate embedding cache for faster cold starts
-  - `pretrain(sources)` - Pretrain from files, globs, or text arrays
-  - `pretrainCodePatterns()` - 45 common programming patterns (~3ms)
-  - `pretrainFromRepo(path)` - Crawl and cache entire repositories
-
-- **AI-Enhanced Pretrain** (ruvector integration):
-  - `pretrainWithAI()` - Uses attention mechanisms for intelligent caching
-  - `pretrainIntelligent()` - 5-stage analysis (patterns, AST, git, deps, chunks)
-  - `pretrainIncremental()` - Only cache changed files (git diff)
-  - `pretrainSemantic()` - Code-aware chunking (functions, classes, interfaces)
-  - `prefetchForContext()` - Context-aware prefetch based on current task
-
-- **Attention-Guided Caching**:
-  - `HyperbolicAttention` - Hierarchical code structure (AST trees)
-  - `MoEAttention` - Expert routing (frontend/backend/data/test)
-  - `GraphRoPeAttention` - Dependency graph understanding
-  - `FastGRNN` - Pattern prediction for smart prefetch
-
-- **Smart Pretraining Features**:
-  - Semantic chunking by code boundaries (not fixed size)
-  - Priority-based caching of frequently accessed patterns
-  - Background pretraining (non-blocking)
-  - Git history analysis (cache hot files first)
-  - Dependency graph caching
-
-### Performance (pretrain)
-| Operation | Time | Notes |
-|-----------|------|-------|
-| Code patterns | ~3ms | 45 patterns, one-time |
-| Custom texts | ~0.3ms | 5 texts batch |
-| Cached query | ~0.01ms | Memory cache hit |
-| Incremental | ~50ms | Git-based, 20 commits |
-| AI pretrain | ~200ms | Full 5-stage analysis |
-| Context prefetch | ~5ms | Task-aware prediction |
-
-## [2.0.1-alpha.18] - 2025-12-31
-
-### Added
-- **Persistent SQLite Embedding Cache**: Cross-session embedding persistence
-  - New `EmbeddingCache` class with SQLite (better-sqlite3) backend
-  - **9000x faster** cached lookups: ~0.045ms vs ~400ms ONNX inference
-  - Batch writes with transactions: 0.016ms per embedding
-  - Stored at `~/.agentic-flow/embedding-cache.db`
-  - LRU eviction with configurable max entries (default: 10,000)
-  - Automatic cleanup of entries older than 30 days
-  - WAL mode for concurrent access
-
-- **Cache Hierarchy** (checked in order):
-  1. In-memory LRU cache (~0.001ms) - fastest, ephemeral
-  2. Persistent SQLite cache (~0.045ms) - persists across sessions
-  3. ONNX inference (~400ms) - only on complete cache miss
-
-- **EmbeddingService Cache Methods**:
-  - `clearPersistentCache()` - Clear SQLite cache
-  - `clearAllCaches()` - Clear both memory and persistent caches
-  - `getPersistentCacheStats()` - Get cache statistics
-
-- **Environment Variables**:
-  - `AGENTIC_FLOW_PERSISTENT_CACHE=true|false` (default: true)
-
-### Performance (with persistent cache)
-| Operation | Time | Notes |
-|-----------|------|-------|
-| ONNX cold | ~400ms | First inference + cache write |
-| SQLite read | ~0.045ms | Persistent cache lookup |
-| SQLite batch write | 0.016ms/ea | Transactional batch insert |
-| Memory cache | ~0.001ms | In-memory LRU lookup |
-| **Speedup** | **9000x** | SQLite vs ONNX inference |
-
-### Changed
-- EmbeddingService now checks persistent cache before ONNX inference
-- Only semantic (ONNX) embeddings are persisted (simple hash-based are not)
-
-## [2.0.1-alpha.17] - 2025-12-31
-
-### Added
-- **10 Attention Mechanisms** (ruvector@0.1.63):
-  - `MultiHeadAttention` - Pattern matching
-  - `FlashAttention` - Memory-efficient O(n)
-  - `HyperbolicAttention` - Hierarchical data (AST, trees)
-  - `LinearAttention` - O(n) real-time hooks
-  - `LocalGlobalAttention` - Long document summarization
-  - `MoEAttention` - Multi-agent routing
-  - `GraphRoPeAttention` - Code structure analysis
-  - `EdgeFeaturedAttention` - Import/dependency graphs
-  - `DualSpaceAttention` - Euclidean + Hyperbolic
-
-- **Extended Worker Pool Operations**:
-  - `speculativeEmbed(files)` - Pre-embed for post-edit
-  - `analyzeAST(files)` - Multi-file parallel AST
-  - `analyzeComplexity(files)` - Cyclomatic metrics
-  - `buildDependencyGraph(files)` - Import graph
-  - `securityScan(files)` - Parallel SAST
-  - `ragRetrieve(query, chunks)` - Parallel RAG
-  - `rankContext(query, contexts)` - Relevance ranking
-  - `deduplicate(texts)` - Semantic deduplication
-  - `gitBlame(files)` - Parallel blame analysis
-  - `gitChurn(patterns, since)` - Code churn metrics
-
-- **Parallel Attention Compute**:
-  - `parallelAttentionCompute()` - 3-4x faster multi-query
-  - `batchAttentionCompute()` - Batch Q-K-V sets
-  - `computeFlashAttentionAsync()` - Non-blocking flash
-  - `getAttentionForUseCase()` - Auto-select attention type
-
-- **Training Utilities**:
-  - `AdamOptimizer` - Attention parameter training
-  - `infoNceLoss()` - Contrastive learning
-  - `mineHardNegatives()` - Hard negative mining
-  - `benchmarkAttention()` - Performance comparison
-
-### Changed
-- Updated ruvector dependency: 0.1.62 → 0.1.63
-- Intelligence bridge supports all attention mechanisms
-
-## [2.0.1-alpha.16] - 2025-12-31
-
-### Added
-- **Parallel Intelligence** (ruvector@0.1.62): Full parallel worker integration
-  - `queueEpisode()` + `flushEpisodeBatch()` - 3-4x faster batch Q-learning
-  - `matchPatternsParallel(files)` - Multi-file parallel pretrain
-  - `indexMemoriesBackground(memories)` - Non-blocking hook indexing
-  - `searchParallel(query, topK)` - Parallel shard similarity search
-  - `analyzeFilesParallel(files)` - Multi-file AST routing
-  - `analyzeCommitsParallel(commits)` - Faster co-edit detection
-
-- **Auto-detection for parallel mode**:
-  - MCP server (`MCP_SERVER=1`): Workers enabled automatically
-  - CLI hooks (`RUVECTOR_CLI=1`): Fast sequential mode
-  - Manual: `RUVECTOR_PARALLEL=1` to force enable
-
-### Changed
-- Updated ruvector dependency: 0.1.61 → 0.1.62
-- Intelligence bridge now lazy-loads parallel engine
-
-## [2.0.1-alpha.15] - 2025-12-31
-
-### Added
-- **Parallel Worker Embeddings**: 7 worker threads for parallel ONNX processing
-  - Uses ruvector@0.1.61 with parallel worker pool
-  - SIMD128 enabled (6x faster single-threaded, 7x parallel)
-  - Auto-detection: defaults to ONNX when SIMD available
-
-- **Advanced Embedding Features**:
-  - `similarityMatrix(texts)` - NxN pairwise similarity computation
-  - `semanticSearch(query, topK)` - Search against pre-built corpus
-  - `findDuplicates(texts, threshold)` - Near-duplicate detection
-  - `clusterTexts(texts, k)` - K-means semantic clustering
-  - `streamEmbed(texts, batchSize)` - Memory-efficient streaming
-
-- **Parallel Use Cases** (from ruvector@0.1.61):
-  | Use Case           | Current            | With Workers      | Benefit                  |
-  |--------------------|--------------------|-------------------|--------------------------|
-  | Q-learning updates | Sequential         | Parallel batch    | Faster learning          |
-  | Pattern matching   | 1 file at a time   | 4+ files parallel | 3-4x faster pretrain     |
-  | Memory indexing    | Blocking           | Background        | Non-blocking hooks       |
-  | Similarity search  | Sequential scan    | Parallel shards   | Faster recall            |
-  | Code analysis      | Single AST         | Multi-file AST    | Faster routing           |
-  | Git history        | Sequential commits | Parallel commits  | Faster co-edit detection |
-
-### Changed
-- EmbeddingService now uses ruvector@0.1.61 (not ruvector-onnx-embeddings-wasm directly)
-- Default backend changed from 'simple' to 'auto' (auto-detects ONNX/SIMD)
-- Updated dependency: ruvector ^0.1.61
-
-### Performance (7 workers + SIMD)
-- Cold start: ~1.5s (includes model download, worker init)
-- Warm embedding: ~100-200ms per text (parallelized)
-- Batch embedding: Up to 7x faster with parallel workers
-
-## [2.0.1-alpha.14] - 2025-12-31
-
-### Added
-- **ONNX Embeddings with SIMD**: Real semantic embeddings via ruvector-onnx-embeddings-wasm
-  - SIMD128 enabled for 6x faster embedding generation
-  - 100% semantic accuracy (correctly identifies related/unrelated texts)
-  - all-MiniLM-L6-v2 model (384 dimensions)
-  - Configure with `AGENTIC_FLOW_EMBEDDINGS=onnx`
-
-- **EmbeddingService**: Unified embedding interface
-  - Simple backend: ~0.04ms (hash-based, fast but not semantic)
-  - ONNX backend: ~400ms with SIMD (true semantic similarity)
-  - LRU cache for repeated embeddings
-  - Auto-fallback to simple if ONNX fails
-
-- **Embedding Benchmark**: Compare simple vs ONNX embeddings
-  - Run with: `node --experimental-wasm-modules dist/intelligence/embedding-benchmark.js`
-  - Shows latency, accuracy, and semantic similarity comparisons
-
-### Changed
-- Updated intelligence-bridge.ts to use EmbeddingService
-- Added onnxruntime-node and ruvector-onnx-embeddings-wasm dependencies
-
-### Performance (SIMD enabled)
-- Cold start: ~1.5s (includes model download)
-- Warm embedding: ~400ms per text
-- Batch embedding: ~400ms per text (sequential)
-
-## [2.0.1-alpha.13] - 2025-12-31
-
-### Added
-- **SQLite Persistence**: Learning data now persists across npx calls and CLI invocations
-  - New `IntelligenceStore` class with cross-platform SQLite (better-sqlite3)
-  - Stores trajectories, routings, patterns, and operations
-  - Works on Linux, macOS, and Windows
-  - Database stored in `.agentic-flow/intelligence.db`
-
-### Changed
-- **Intelligence Stats**: Now shows persisted data from SQLite
-  - Trajectories count persists across CLI invocations
-  - Routings count persists across CLI invocations
-  - New "Persistence (SQLite)" section in stats output
-
-### Verified
-- Trajectories persist: created in one call, visible in next
-- Routings persist: recorded for each routing decision
-- Cross-platform SQLite with WAL mode for better concurrency
-
-## [2.0.1-alpha.12] - 2025-12-31
-
-### Fixed
-- **HNSW Enabled Status**: Fixed intelligence stats showing "HNSW: Enabled: false"
-  - Reordered initialization to call `getIntelligence()` before `getIntelligenceStats()`
-  - Now correctly shows "HNSW: Enabled: true" with 150x speedup
-
-### Verified
-- All intelligence stats display correctly
-- HNSW enabled and operational
-
-## [2.0.1-alpha.11] - 2025-12-31
-
-### Fixed
-- **AdamOptimizer Constructor**: Fixed "Failed to convert napi value Undefined into rust type `f64`" error
-  - AdamOptimizer now correctly receives all 4 required parameters: learning_rate, beta1, beta2, epsilon
-- **Silent Warnings**: Removed noisy AgentDB controller warnings for v2+ installations
-- **RuVector HNSW**: Verified HNSW indexing works with M=16, efConstruction=200, achieving 1ms search times
-
-### Verified
-- Hooks run without any error messages
-- Intelligence stats display cleanly
-- RuVector backend with HNSW fully operational
-
-## [2.0.1-alpha.10] - 2025-12-31
-
-### Fixed
-- **ruvector VectorDB/VectorDb Case Mismatch**: Fixed critical bug where @ruvector/core exports `VectorDb` but ruvector checks for `VectorDB`
-  - Updated postinstall.js with regex-based patching for whitespace-insensitive matching
-  - Added patch marker (`// AGENTIC-FLOW-PATCHED: VectorDb alias`) for idempotent patching
-  - Hooks now work correctly with `npx agentic-flow hooks init` and `npx agentic-flow hooks metrics`
-
-### Tested
-- Verified postinstall patch applies correctly on fresh install
-- Hooks init creates .claude/settings.json properly
-- Hooks metrics command executes without VectorDB errors
-
-## [2.0.1-alpha.9] - 2025-12-31
-
-### Added
-- **Runtime Patching System**: Added agentdb-runtime-patch.ts for runtime fixes
-  - Automatic AgentDB ESM import resolution patching
-  - Automatic ruvector VectorDB/VectorDb case mismatch fixing
-  - Works with npm install, npm install -g, and npx contexts
-
-### Changed
-- **Hook System Migration**: Updated from ruvector hooks to agentic-flow@alpha hooks
-  - New environment variables: AGENTIC_FLOW_INTELLIGENCE, AGENTIC_FLOW_LEARNING_RATE
-  - Updated CLAUDE.md documentation with new hook commands
-
-## [2.0.1-alpha.8] - 2025-12-31
-
-### Fixed
-- **TypeScript Compilation**: Fixed all 11 TypeScript errors in the core package
-  - Fixed AgentDBConfig property mismatch (`path` → `dbPath`)
-  - Fixed RuvectorLayer constructor signature (added dropout parameter)
-  - Fixed MoEAttention constructor to use config object
-  - Fixed SONAEngine type cast for proper interface compatibility
-  - Fixed ReasoningPattern local interface for type safety
-  - Fixed DebugStream.logConnection argument handling
-  - Added try-catch for optional AttentionService import
-  - Fixed AgentDB import to use named export
-
-### Changed
-- **Type Safety Improvements**:
-  - Local ReasoningPattern interface now includes all required fields (similarity, approach, taskType)
-  - Added proper type casts for cross-module compatibility
-  - GNN initialization now uses RuvectorLayer instead of deprecated GraphNeuralNetwork
-
-### Tested
-- ✅ All TypeScript compilation passes with zero errors
-- ✅ Build completes successfully
-- ✅ Retry and logging tests pass
-
----
-
 ## [2.0.1-alpha.4] - 2025-12-03
 
 ### Added