Commit graph

199 commits

Author SHA1 Message Date
rUv
f3717b7b28 chore: bump versions for SONA@0.1.5 and graph-node@0.1.26
- SONA: 0.1.4 → 0.1.5 (includes JSON format fix #78)
- graph-node: 0.1.25 → 0.1.26 (includes persistence fix #64)

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2026-01-02 20:30:22 +00:00
rUv
43427b661d feat(edge-net): add self-hosted TURN server and deploy dashboard
- Deploy TURN server (coturn) on GCE at 34.72.154.225:3478
- Update webrtc.js with self-hosted TURN as primary
- Add Edge-Net STUN server as primary option
- Update signaling to use Cloud Run Genesis as default
- Deploy dashboard to Cloud Run at edge-net-dashboard
- Bump to v0.4.5

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2026-01-02 20:20:39 +00:00
rUv
4d306e68a7 fix(ruvllm): sync NativeStats types with Rust bindings
- Update NativeStats interface to match actual native module exports
- Map training_steps to patternsLearned for API compatibility
- Fix stats() returning undefined values
- Bump version to 0.2.4

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2026-01-02 20:08:07 +00:00
rUv
1b74b91323 fix(embedding): resolve ONNX/WASM loading issues (closes #102)
- Add CommonJS-compatible WASM loader to avoid --experimental-wasm-modules
- Add embedText() that returns number[] directly (simple API)
- Add embedTexts() for fast batch processing with batchSize option
- Maintain backwards compatibility with original embed()/embedBatch()
- Bump version to 0.1.95

Fixes:
- Bug 1: WASM now loads without experimental flags
- Bug 2: embedText() returns array directly, not wrapped object
- Bug 3: embedTexts() enables fast bulk KB ingestion

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2026-01-02 19:15:08 +00:00
github-actions[bot]
8f44a67d9c chore: Update NAPI-RS binaries for all platforms
Built from commit 282273a759

  Platforms updated:
  - linux-x64-gnu
  - linux-arm64-gnu
  - darwin-x64
  - darwin-arm64
  - win32-x64-msvc

  🤖 Generated by GitHub Actions
2026-01-02 14:47:47 +00:00
rUv
282273a759
Merge pull request #97 from ruvnet/feature/dashboard
feat(dashboard): Edge-Net Time Crystal Dashboard
2026-01-02 09:44:04 -05:00
rUv
5ac51a84de feat: comprehensive ruvector updates - analysis, workers, dashboard enhancements
Analysis module:
- Add complexity analysis (cyclomatic, cognitive, Halstead metrics)
- Add security scanning (SQL injection, XSS, command injection detection)
- Add pattern detection (code smells, design patterns)

Workers module:
- Add native worker implementation for parallel processing
- Add benchmark worker for performance testing
- Add worker type definitions

Core improvements:
- Add adaptive embedder with dynamic model selection
- Add ONNX optimized embeddings with caching
- Update intelligence engine with enhanced learning
- Update parallel workers with better concurrency

Dashboard enhancements:
- Add relay client service for Edge-Net communication
- Update network stats and specialized networks components
- Update network store with improved state management
- Update type definitions

Configuration:
- Add custom workers skill
- Add agentic-flow and ruvector fast scripts
- Update settings and gitignore

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2026-01-02 14:43:06 +00:00
rUv
9b615dbed6 feat(neural): add security hardening + 17x perf optimizations
Security improvements (v0.1.86-87):
- Add NEURAL_CONSTANTS with 27 named constants replacing magic numbers
- Add NeuralLogger interface with configurable logging (no more console.warn)
- Add readonly modifiers to interface properties for immutability
- Add input validation: ID length, content length, embedding dimensions
- Add resource limits: MAX_MEMORIES=10000, MAX_AGENTS=1000, MAX_DRIFT_EVENTS=1000
- Add stale agent cleanup in EmbeddingStateMachine (1hr timeout)
- Add cluster detection limits to prevent O(n²) DoS (MAX_CLUSTER_AGENTS=500)
- Add zero-vector handling in cosine similarity
- Fix reflex error handling with graceful degradation

Performance optimizations (v0.1.88):
- LRUCache: O(1) get/set/evict with doubly-linked list + hash map (2x faster)
- Float32BufferPool: Pre-allocated buffer reuse (17x faster, 100% reuse)
- TensorBufferManager: Named working buffers for intermediate computations
- VectorOps: 8x loop unrolling for dot/distance (1.3-1.5x faster)
- VectorOps: 4x unrolling + local vars for cosine (1.6x faster)
- ParallelBatchProcessor: Chunked concurrent processing
- OptimizedMemoryStore: Combined LRU cache + buffer pool

Benchmark results:
- Buffer Pool: 0.06 µs vs 1.03 µs (17x improvement)
- LRU Cache eviction: O(1) vs O(n)
- Cosine similarity: 0.39 µs vs 0.61 µs (1.6x improvement)
- Memory store search: 703 µs vs 1301 µs (2x improvement)

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2026-01-02 14:41:37 +00:00
github-actions[bot]
dde19d3708 chore: Update NAPI-RS binaries for all platforms
Built from commit 74ba07f511

  Platforms updated:
  - linux-x64-gnu
  - linux-arm64-gnu
  - darwin-x64
  - darwin-arm64
  - win32-x64-msvc

  🤖 Generated by GitHub Actions
2026-01-01 21:26:02 +00:00
github-actions[bot]
eb0bb1a679 chore: Update NAPI-RS binaries for all platforms
Built from commit 27cd7ae0af

  Platforms updated:
  - linux-x64-gnu
  - linux-arm64-gnu
  - darwin-x64
  - darwin-arm64
  - win32-x64-msvc

  🤖 Generated by GitHub Actions
2026-01-01 15:30:03 +00:00
github-actions[bot]
3ccad2b141 chore: Update NAPI-RS binaries for all platforms
Built from commit 71907b2774

  Platforms updated:
  - linux-x64-gnu
  - linux-arm64-gnu
  - darwin-x64
  - darwin-arm64
  - win32-x64-msvc

  🤖 Generated by GitHub Actions
2026-01-01 07:28:19 +00:00
github-actions[bot]
f60482bde8 chore: Update NAPI-RS binaries for all platforms
Built from commit 3e1ee3942a

  Platforms updated:
  - linux-x64-gnu
  - linux-arm64-gnu
  - darwin-x64
  - darwin-arm64
  - win32-x64-msvc

  🤖 Generated by GitHub Actions
2025-12-31 22:30:22 +00:00
github-actions[bot]
5a0f2e2e35 chore: Update NAPI-RS binaries for all platforms
Built from commit 03fcbd45e5

  Platforms updated:
  - linux-x64-gnu
  - linux-arm64-gnu
  - darwin-x64
  - darwin-arm64
  - win32-x64-msvc

  🤖 Generated by GitHub Actions
2025-12-31 22:11:01 +00:00
github-actions[bot]
ed13fd2939 chore: Update NAPI-RS binaries for all platforms
Built from commit 2e49f288e3

  Platforms updated:
  - linux-x64-gnu
  - linux-arm64-gnu
  - darwin-x64
  - darwin-arm64
  - win32-x64-msvc

  🤖 Generated by GitHub Actions
2025-12-31 21:31:36 +00:00
rUv
2e49f288e3
Merge pull request #93 from ruvnet/feature/mcp-server
feat: RuVector Intelligence v2.1 - Multi-Algorithm Learning, TensorCompress, Edge Swarm
2025-12-31 16:28:06 -05:00
rUv
8f416aa6ae chore: update intelligence data and version bump to v0.1.71 2025-12-31 17:40:37 +00:00
rUv
39018db65a feat: add batch learning and real-time subscriptions
New CLI Commands:
- batch-learn: Process multiple learning experiences at once
- subscribe: Stream real-time learning updates (polling)
- watch: Auto-learn from file changes in real-time

New MCP Tools (49 total):
- hooks_batch_learn: Batch process experiences array
- hooks_subscribe_snapshot: Get state deltas for subscriptions
- hooks_watch_status: Get current watch/learning status

Features:
- Batch learning processes multiple experiences efficiently
- Subscribe streams events: learn, route, memory, compress
- Watch monitors file changes and auto-learns patterns
- Co-edit detection in watch mode (files edited within 1 min)

Published as v0.1.71
2025-12-31 16:02:29 +00:00
rUv
dd137ae3f8 fix: defensive checks for Q-learning patterns and data loading
- Add null checks in getQ() method for patterns object
- Add null checks in updateQ() and learn() methods
- Improve load() to merge file data with defaults
- Ensures all required fields exist even with partial data
- Fixes 'Cannot read properties of undefined' errors

Published as v0.1.70
2025-12-31 15:40:29 +00:00
rUv
e38d3a9c9e feat: Full v2.1 upgrade with multi-algorithm learning and TensorCompress (v0.1.69)
## Multi-Algorithm Learning Engine
- 9 algorithms: q-learning, sarsa, double-q, actor-critic, ppo, decision-transformer, monte-carlo, td-lambda, dqn
- Task-specific configuration:
  - agent-routing: double-q (reduces bias)
  - error-avoidance: sarsa (conservative)
  - confidence-scoring: actor-critic (continuous)
  - trajectory-learning: decision-transformer (sequence)
  - context-ranking: ppo (stable)
  - memory-recall: td-lambda (traces)

## TensorCompress (10x Memory Savings)
- 5 compression levels based on access frequency:
  - none (hot >0.8): 0% savings
  - half (warm >0.4): 50% savings
  - pq8 (cool >0.1): 87.5% savings
  - pq4 (cold >0.01): 93.75% savings
  - binary (archive ≤0.01): 96.9% savings
- Auto-compression on session-end

## Pretrain Phases (11 total)
- Phase 10: Multi-algorithm learning bootstrap
- Phase 11: TensorCompress initialization

## Environment Variables (v2.1)
- RUVECTOR_MULTI_ALGORITHM=true
- RUVECTOR_DEFAULT_ALGORITHM=double-q
- RUVECTOR_TENSOR_COMPRESS=true
- RUVECTOR_AUTO_COMPRESS=true

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2025-12-31 15:24:30 +00:00
rUv
5154c468a3 fix: robust sessionEnd with full data structure validation (v0.1.68)
- Check this.data exists before accessing properties
- Initialize trajectories array if missing
- Add try/catch around engine and save operations
- Null-check trajectory objects in filter

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2025-12-31 15:17:35 +00:00
rUv
eff6c4a7b7 fix: handle undefined stats in sessionEnd (v0.1.67)
- Add defensive check for this.data.stats
- Initialize with defaults if missing
- Fixes "Cannot read properties of undefined (reading 'last_session')"

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2025-12-31 15:15:45 +00:00
rUv
bbbb4f253e feat: add TensorCompress and multi-algorithm LearningEngine (v0.1.66)
TensorCompress:
- Adaptive tensor compression with 5 levels (none, half, pq8, pq4, binary)
- Access-frequency based auto-compression
- Up to 10x memory savings for pattern storage
- CLI: compress, compress-stats, compress-store, compress-get
- MCP: hooks_compress, hooks_compress_stats, hooks_compress_store, hooks_compress_get

LearningEngine (9 algorithms):
- Q-Learning: Simple off-policy (default)
- SARSA: On-policy, conservative (error-avoidance)
- Double Q-Learning: Reduces overestimation (precise routing)
- Actor-Critic: Policy gradient + value (confidence scoring)
- PPO: Stable policy updates (preference learning)
- Decision Transformer: Sequence modeling (trajectory patterns)
- Monte Carlo: Full episode learning (unbiased estimates)
- TD(λ): Eligibility traces (credit assignment)
- DQN: Experience replay (high-dim states)

CLI Commands:
- learning-config: Configure algorithms per task
- learning-stats: View algorithm performance
- learning-update: Record experiences
- learn: Combined action + recommendation

MCP Tools:
- hooks_learning_config, hooks_learning_stats
- hooks_learning_update, hooks_learn
- hooks_algorithms_list

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2025-12-31 15:13:13 +00:00
rUv
76480df271 docs: update README with v2.0 features
- Add Claude Code Intelligence v2.0 section with MCP tools
- Add ONNX WASM embeddings documentation
- Add Windows installation with --ignore-scripts
- Add new CLI commands (AST, Diff, Coverage, Graph, Security, RAG)
- Update hooks configuration with new env variables
- Add performance comparison table (40,000x cache speedup)

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2025-12-31 06:13:35 +00:00
rUv
4b52df2712 feat: add comprehensive intelligence layer with ONNX, AST, Graph, and Coverage modules
Core Modules Added:
- ast-parser.ts: Full AST parsing with symbol extraction, complexity analysis
- onnx-embedder.ts: ONNX WASM embeddings with SIMD acceleration
- diff-embeddings.ts: Semantic diff analysis with risk scoring
- coverage-router.ts: Test coverage-aware agent routing
- graph-algorithms.ts: MinCut, Spectral clustering, Louvain communities
- graph-wrapper.ts: Code dependency graph builder
- cluster-wrapper.ts: RuVector cluster management
- router-wrapper.ts: Semantic routing wrapper
- parallel-intelligence.ts: Parallel processing orchestration
- parallel-workers.ts: Worker pool with work stealing

CLI Hooks (13 new commands):
- ast-analyze, ast-complexity
- diff-analyze, diff-classify, diff-similar
- coverage-route, coverage-suggest
- graph-mincut, graph-cluster
- security-scan, rag-context, git-churn, route-enhanced

MCP Server (16 new tools):
- hooks_ast_*, hooks_diff_*, hooks_coverage_*
- hooks_graph_*, hooks_security_*, hooks_rag_*
- hooks_attention_info, hooks_gnn_info

Enhanced Features:
- 10 attention mechanisms (Flash, Hyperbolic, MoE, GraphRoPe, etc.)
- 9-phase pretrain with neural capabilities
- ONNX WASM runtime (7.4MB) with all-MiniLM-L6-v2 support
- hooks init generates v2.0 templates with full documentation

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2025-12-31 06:05:38 +00:00
rUv
f915196918 chore: bump version to 0.1.65
New features in this release:
- 13 new CLI hooks commands (AST, Diff, Coverage, Graph, Security, RAG)
- 16 new MCP tools for Claude Code integration
- Enhanced hooks init with v2.0 templates
- 9-phase pretrain with attention/GNN capabilities
- Comprehensive CLAUDE.md documentation generation

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2025-12-31 06:04:06 +00:00
rUv
ad94b8f411 fix(hooks): add --silent flag to remember command
Fixes PreToolUse:Read hook error by supporting --silent flag
for Read/Glob/Task hooks that should not produce output.

Published ruvector@0.1.54

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2025-12-31 04:08:04 +00:00
github-actions[bot]
a35eb202c9 chore: Update NAPI-RS binaries for all platforms
Built from commit 23fc7839cd

  Platforms updated:
  - linux-x64-gnu
  - linux-arm64-gnu
  - darwin-x64
  - darwin-arm64
  - win32-x64-msvc

  🤖 Generated by GitHub Actions
2025-12-31 01:52:50 +00:00
rUv
23fc7839cd
Merge pull request #92 from ruvnet/feature/mcp-server
feat(hooks): Full IntelligenceEngine with MCP tools, trajectory tracking, and attention
2025-12-30 20:49:04 -05:00
rUv
e6ab31a38e feat(hooks): add full IntelligenceEngine with trajectory, co-edit, and attention
- Add IntelligenceEngine class integrating VectorDB, SONA, and Attention
- Add 11 new MCP tools (22 total): trajectory tracking, co-edit patterns,
  error suggestions, swarm recommendations, force learning
- Add 8 new CLI commands: trajectory-begin/step/end, coedit-record/suggest,
  error-record/suggest, force-learn
- Integrate Flash/MultiHead attention for embeddings with fallbacks
- Add Read/Glob/Task hooks to settings.json for pattern learning
- Fix @ruvector/attention-linux-x64-gnu (publish v0.1.3)
- Published ruvector@0.1.53

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2025-12-31 00:28:19 +00:00
rUv
738571ff61 feat(mcp): add MCP server for Claude Code integration
Add Model Context Protocol (MCP) server with stdio transport for
seamless Claude Code integration. Provides 10 self-learning
intelligence tools via JSON-RPC protocol.

New commands:
- `npx ruvector mcp start` - Start MCP server
- `npx ruvector mcp info` - Show setup instructions

MCP Tools:
- hooks_stats - Get intelligence statistics
- hooks_route - Route task to best agent
- hooks_remember - Store context in vector memory
- hooks_recall - Search vector memory semantically
- hooks_init - Initialize hooks in project
- hooks_pretrain - Pretrain from repository
- hooks_build_agents - Generate agent configs
- hooks_verify - Verify hooks configuration
- hooks_doctor - Diagnose setup issues
- hooks_export - Export intelligence data

MCP Resources:
- ruvector://intelligence/stats
- ruvector://intelligence/patterns
- ruvector://intelligence/memories

Setup: claude mcp add ruvector npx ruvector mcp start

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2025-12-30 22:22:49 +00:00
rUv
a761924bde docs: add Claude Code hooks section to README and create HOOKS.md
- Added hooks feature summary near top of README.md
- Created comprehensive HOOKS.md documentation
- Links to detailed docs for pretrain, build-agents, verify, etc.
2025-12-30 21:51:37 +00:00
rUv
1a5d62e20a fix(hooks): use project-local storage for intelligence data
- Intelligence now saves to .ruvector/intelligence.json in project dir
- Falls back to ~/.ruvector/ only if no project context found
- Prefers project-local when .ruvector/ or .claude/ exists
- Fixes verify showing 'will be created' after pretrain
2025-12-30 21:40:23 +00:00
rUv
e6ef464df0 feat(hooks): add build-agents command and integrate pretrain/agents into init
New command:
- hooks build-agents: Generate optimized agent configs based on repo analysis
  - Focus modes: quality, speed, security, testing, fullstack
  - Detects languages (Rust, TypeScript, Python, Go) and frameworks (React, Vue)
  - Generates YAML/JSON/MD agent definitions with system prompts
  - Creates coordinator agent with routing rules
  - Outputs to .claude/agents/

Init enhancements:
- --pretrain: Bootstrap intelligence after init
- --build-agents [focus]: Generate agents after init

Example: npx ruvector hooks init --pretrain --build-agents security
2025-12-30 21:28:15 +00:00
rUv
2933eb2c6e feat(hooks): add pretrain command + fix permissions deny pattern
New command:
- hooks pretrain: Bootstrap intelligence by analyzing repository
  - Phase 1: Analyze file structure → agent routing patterns
  - Phase 2: Analyze git history → co-edit patterns
  - Phase 3: Create vector memories from key files
  - Phase 4: Build directory-agent mappings

Options:
  --depth <n>: Git history depth (default: 100)
  --workers <n>: Parallel workers (default: 4)
  --skip-git: Skip git history analysis
  --skip-files: Skip file structure analysis
  --verbose: Show detailed progress

Fix:
- Removed fork bomb pattern from deny list (caused validation error)
2025-12-30 21:22:29 +00:00
rUv
6246d5801e feat(hooks): add verify, doctor, export, import commands and enhanced init
New commands:
- hooks verify: Check if hooks are working correctly
- hooks doctor: Diagnose and fix setup issues (with --fix)
- hooks export: Export intelligence data for backup
- hooks import: Import intelligence data (with --merge, --dry-run)

Enhanced init:
- Auto-detect project type (Rust, Node, Python, Go, Ruby, Java)
- Project-specific permissions (cargo for Rust, npm for Node, etc.)
- StatusLine configuration with .claude/statusline.sh
- MCP server configuration (claude-flow)
- .gitignore update (adds .ruvector/)
- Creates .ruvector/ directory

New options for init:
- --no-gitignore: Skip .gitignore update
- --no-mcp: Skip MCP server configuration
- --no-statusline: Skip statusLine configuration
2025-12-30 21:18:29 +00:00
rUv
345e8a45b9 feat(hooks): enhanced init with full configuration
- Add environment variables (RUVECTOR_INTELLIGENCE_ENABLED, LEARNING_RATE, etc.)
- Add permissions configuration (allow/deny lists)
- Add UserPromptSubmit hook for context suggestions
- Add PreCompact hook for preserving context before compaction
- Add Notification hook for event tracking
- Add --minimal flag for basic hooks only
- Add --no-env and --no-permissions flags
- Updated CLAUDE.md template with complete documentation
2025-12-30 21:11:48 +00:00
github-actions[bot]
7de5414cee chore: Update NAPI-RS binaries for all platforms
Built from commit 598e2a184c

  Platforms updated:
  - linux-x64-gnu
  - linux-arm64-gnu
  - darwin-x64
  - darwin-arm64
  - win32-x64-msvc

  🤖 Generated by GitHub Actions
2025-12-30 19:35:33 +00:00
rUv
598e2a184c
Merge pull request #91 from ruvnet/cleanup/remove-duplicate-npm-ruvector
chore: remove duplicate npm/ruvector directory
2025-12-30 14:29:28 -05:00
rUv
c961cbc50e feat(hooks): init command now creates CLAUDE.md with RuVector documentation
- Added CLAUDE.md creation to 'hooks init' command
- Includes complete hooks documentation and CLI commands
- Added --no-claude-md flag to skip CLAUDE.md creation
- Respects existing CLAUDE.md unless --force is used
2025-12-30 19:25:59 +00:00
rUv
5effc17c43 fix(hooks): init command now fixes invalid schema and hook names
- Fixes $schema to correct URL
- Removes invalid Start/End hooks (renamed to SessionStart/Stop)
- Preserves other existing settings when merging

Bumps to v0.1.43

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2025-12-30 19:22:00 +00:00
rUv
bde2de7ce6 chore: remove duplicate npm/ruvector directory
Removed legacy /npm/ruvector/ (v0.1.38) in favor of
/npm/packages/ruvector/ (v0.1.42) which is actively maintained
and published to npm.

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2025-12-30 19:15:03 +00:00
github-actions[bot]
70dc24d503 chore: Update NAPI-RS binaries for all platforms
Built from commit c46bec45db

  Platforms updated:
  - linux-x64-gnu
  - linux-arm64-gnu
  - darwin-x64
  - darwin-arm64
  - win32-x64-msvc

  🤖 Generated by GitHub Actions
2025-12-30 18:33:05 +00:00
rUv
f3d691a82a chore: sync settings and dependencies
🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2025-12-30 18:26:41 +00:00
rUv
b0c1f2cdd3 fix(hooks): correct hooks format - string matcher, hooks wrapper
Format fixes based on Claude Code validation:
- matcher: string regex (e.g., "Edit|Write|MultiEdit") not object
- SessionStart/Stop: require { hooks: [...] } wrapper

Bumps to v0.1.42

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2025-12-30 17:23:37 +00:00
rUv
be70b06184 fix(hooks): update to new Claude Code hooks format
Updates hooks to use new object-based format:
- matcher: { tools: [...] } instead of string
- hooks: [{ type: "command", command: "..." }] instead of string array

Required by Claude Code's updated hooks schema.
Bumps to v0.1.41

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2025-12-30 17:20:48 +00:00
rUv
96692c78a1 fix(npm): hooks init now generates npx ruvector commands
The hooks init command now generates settings.json with
npx ruvector hooks instead of ruvector hooks, ensuring
commands work without global installation.

Bumps to v0.1.40

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2025-12-30 17:11:27 +00:00
rUv
9e2a24b98a feat(npm): add hooks support to ruvector package
Adds Intelligence class with self-learning capabilities:
- Q-learning for agent routing
- Vector embeddings for semantic memory
- Command classification and risk analysis
- File sequence prediction

Hooks commands added:
- init, stats, session-start, session-end
- pre-edit, post-edit, pre-command, post-command
- route, suggest-context, remember, recall
- pre-compact, swarm-recommend, async-agent
- lsp-diagnostic, track-notification

Bumps version to 0.1.39

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2025-12-30 16:58:53 +00:00
rUv
bd3c56966d docs(ruvector): add Self-Learning Hooks section to README
Comprehensive documentation for hooks including:
- init, session-start, session-end
- pre-edit, post-edit with success/error recording
- pre-command, post-command with risk analysis
- route for agent recommendations
- remember/recall for vector memory
- suggest-context for relevant context
- stats for intelligence statistics
- swarm-recommend for task routing
- Configuration example for .claude/settings.json
- Explanation of how self-learning works

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2025-12-30 16:51:58 +00:00
rUv
415f08a0c6 chore(rudag): add .npmkeep to preserve WASM directories
Prevents wasm-pack from regenerating .gitignore files that block npm

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2025-12-30 16:42:33 +00:00
rUv
437fa6dd6f fix(rudag): include WASM binaries in npm package
Remove wasm-pack generated .gitignore files that were blocking
npm from including the pkg/ and pkg-node/ WASM binaries.

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2025-12-30 16:41:03 +00:00