mirror of
https://github.com/rohitg00/skillkit.git
synced 2026-11-20 12:23:29 +00:00
eeddd2a8cf13a0c071dfc17f2b76ce27be2f7e83
2
Commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
|
|
4257e8555b |
feat: Memory, Mesh Network with Security, Messaging, MCP Server (#27)
* feat: add persistent memory, mesh network, and agent messaging (v2.0.0)
Add three major features to SkillKit:
@skillkit/memory - CozoDB-backed semantic memory with embeddings
- 384-dim embeddings via @xenova/transformers (all-MiniLM-L6-v2)
- Memory tiers (warm/long) with promotion logic based on access patterns
- HNSW semantic search for context retrieval
- Storage: ~/.skillkit/agents/{agentId}/memory.db
@skillkit/mesh - Peer mesh network for multi-machine agent distribution
- Local LAN discovery via UDP multicast (239.255.255.250)
- Tailscale VPN support for secure remote connections
- Bidirectional peer registration with health checks
- HTTP and WebSocket transports
- Storage: ~/.skillkit/hosts.json
@skillkit/messaging - Inter-agent messaging system
- Inbox/sent/archived storage with JSON persistence
- Message router for local and cross-host delivery
- Priority levels (low/normal/high/urgent)
- Message types (request/response/notification/update)
- Storage: ~/.skillkit/messages/{inbox|sent|archived}/{agentId}/
CLI Commands:
- skillkit mesh: init, add, remove, list, health, discover, status
- skillkit message: send, inbox, read, reply, archive, forward, sent, status
All packages bumped to version 2.0.0
* feat: add advanced learning, automation, and workflow features
Implements comprehensive enhancement plan with 9 phases:
Phase 1: @skillkit/resources Package
- Bundled agents (9): architect, build-error-resolver, code-reviewer,
doc-updater, e2e-runner, planner, refactor-cleaner, security-reviewer, tdd-guide
- Command templates (10): /tdd, /plan, /e2e, /learn, /build-fix, etc.
- Operational profiles (4): dev, review, research, security
- Guidelines (5): security, code-style, testing, git, performance
- Hook templates (12): typescript-check, eslint-check, security-scan, etc.
Phase 2-3: Pattern Learning & Confidence Scoring
- skillkit learn: Extract patterns from git history
- skillkit pattern status|feedback|approve|reject|export|import|cluster
- Confidence evolution: success +0.05, failure -0.10
Phase 4: Session State Persistence
- skillkit session status|start|load|list|note|complete|in-progress
- Cross-session context preservation in ~/.skillkit/sessions/
Phase 5: Workflow Pipelines
- skillkit workflow pipeline list|<name>
- Built-in: feature, bugfix, refactor, security-audit, documentation
Phase 6: Operational Profiles
- skillkit profile list|<name>|create|remove
- Mode switching for different work contexts
Phase 7: Guidelines System
- skillkit guideline list|show|enable|disable|create|remove
- Always-on coding standards
Phase 8: Hook Templates
- skillkit hook template list|apply|show
- Pre-built automation patterns
Phase 9: Slash Command Templates
- skillkit command available|install <id>
- Install bundled command templates
* feat: add MCP memory server for Claude/Cursor integration
Adds @skillkit/mcp-memory package - an MCP (Model Context Protocol) server
that exposes SkillKit's persistent memory system to Claude, Cursor, and
other MCP-compatible AI tools.
Tools:
- memory_store: Store memories with semantic embeddings
- memory_search: Semantic search through memories
- memory_recall: Recall by category/tier/tags
- memory_get: Get memory by ID
- memory_forget: Delete a memory
- memory_link: Create relationships between memories
- memory_reinforce: Strengthen/weaken memories
- memory_stats: Get memory statistics
Resources:
- memory://stats: Current statistics (JSON)
- memory://recent: Recent memories (JSON)
Usage with Claude Desktop:
```json
{
"mcpServers": {
"skillkit-memory": {
"command": "npx",
"args": ["@skillkit/mcp-memory"],
"env": { "SKILLKIT_AGENT_ID": "claude-desktop" }
}
}
}
```
* feat(mesh): add comprehensive security hardening
- Add cryptographic identity layer (Ed25519 keypairs, fingerprints)
- Add message encryption (XChaCha20-Poly1305) and signing
- Add secure keystore with AES-256-GCM at-rest encryption
- Add JWT authentication and challenge-response handshake
- Add secure WebSocket (WSS) and HTTPS transports
- Add signed discovery messages with trust modes (open/signed/trusted-only)
- Add TLS certificate management (self-signed)
- Add CLI commands: mesh security init/status, mesh peer trust/revoke/list
- Add security presets: development, signed, secure, strict
- Align all package versions to 1.7.11
Security stack: @noble/ed25519, @noble/curves, @noble/ciphers, @noble/hashes, jose
* docs(website): add mesh network and security features
- Add Mesh Network feature card with P2P description
- Add Security feature card with Ed25519/TLS details
- Add Mesh command group with security commands
* fix: address CodeRabbit review suggestions
- cli/mesh: validate port input (1-65535 range check)
- memory/cozo-adapter: call db.close() before nullifying reference
- memory/schema: fix primary key definitions (id => columns)
- resources/hooks: guard pre-commit hooks against empty file lists
- mcp-memory: prevent double-initialization with memoized promise
- mcp-memory: don't mask reinforce failures as "not found"
- mcp-memory: guard main() to prevent auto-start on import
- mcp-memory: add js language identifiers to README code blocks
- mesh/test: update MESH_VERSION test expectation to 1.7.11
* fix: address additional CodeRabbit and Devin review suggestions
Memory package:
- encoder: reset initPromise on failure to allow retry
- encoder: call pipeline.dispose() in disposeEncoder to free GPU resources
- schema: fix probe query to use named-column matching for correct arity
Mesh package:
- hosts-config: add file locking to prevent race conditions
- local discovery: reduce multicast TTL to 1 for LAN-only traffic
- local discovery: handle announce errors in setInterval
- local discovery: close socket on membership setup failure
- local discovery: validate inbound packets (type, hostId, port range)
- local discovery: use rinfo.address to prevent spoofing
- health: guard against overlapping health checks with checking flag
- websocket: prevent auto-reconnect on explicit disconnect()
* fix(memory): increase semantic search fetch multiplier for better filter coverage
Increase from 2x to 5x results to reduce likelihood of incomplete
results when agentId/category/tier filters exclude many candidates.
Filters are applied in application code after HNSW vector search.
* feat(cli): add 'add' as alias for 'install' command
* fix(mesh/auth): use asymmetric EdDSA signing for JWT tokens
Tokens are now signed with the sender's Ed25519 private key and
verified using the sender's public key embedded in the token.
This fixes the issue where tokens couldn't be verified across
different AuthManager instances/hosts because each had a random
symmetric secret.
Changes:
- Switch from HS256 (symmetric) to EdDSA (asymmetric) algorithm
- Include sender's publicKey in JWT payload
- Add privateKey/privateKeyHex getters to PeerIdentity
- Verify fingerprint matches publicKey before accepting token
|
||
|
|
1344d65b3d |
feat: implement phases 12-18 - complete agentic development platform (#6)
* feat: implement phases 12-18 - complete agentic development platform This comprehensive update implements 7 major phases (12-18) transforming SkillKit into a universal agentic development platform with methodology packs, hooks, orchestration, planning, and AI capabilities. Phase 12: Methodology Framework - MethodologyManager for pack-based methodology distribution - 5 methodology packs (testing, debugging, planning, collaboration, meta) - 13 curated methodology skills - Pack loader with validation and installation - 56 comprehensive tests Phase 13: Hooks & Automatic Triggering System - HookManager with event-driven skill activation - 10+ event types (session:start, file:open, task:start, etc.) - Pattern-based triggers with glob support - Agent-specific hook generation - 29 comprehensive tests Phase 14: Subagent Orchestration - TeamOrchestrator for multi-agent coordination - TaskManager with cross-agent assignment - Plan approval workflow (submit → approve/reject) - TeamMessageBus for agent communication - Two-stage review system (spec compliance + code quality) - 36 comprehensive tests Phase 15: Structured Plan System - PlanParser for markdown → structured plan conversion - PlanValidator for completeness checking - PlanExecutor with dry-run support - Bite-sized task format (2-5 min atomic tasks) - 36 comprehensive tests Phase 16: Slash Commands & Agent Integration - CommandRegistry for slash command management - Agent-specific command generation (Claude, Cursor, OpenCode) - Command aliases and arguments support - 42 comprehensive tests Phase 17: Enhanced Agent Features - Permission system (allow/deny/ask patterns) - Glob pattern matching for file-scoped skills - Bootstrap files (AGENTS.md, SOUL.md, TOOLS.md) - Multi-mode support (Code/Architect/Debug/Ask) - Agent feature tests Phase 18: Advanced Features (AI & Audit) - AIManager with natural language skill search - Automatic skill generation from examples/code - MockAIProvider for testing without API keys - AuditLogger with complete operation trail - Query, export (JSON/CSV/text), and statistics - 37 comprehensive tests (15 AI + 22 audit) CLI Commands Added: - skillkit methodology list|install|sync - skillkit hook add|remove|list|generate - skillkit plan parse|validate|execute|create - skillkit commands generate|list - skillkit ai search|generate|similar - skillkit audit log|export|stats|clear TUI Enhancements: - Methodology screen (o key) for pack browsing - Plan screen (n key) for plan viewing/execution - Updated navigation and sidebar Test Coverage: - Total: 619 tests passing (582 core + 49 agents + 1 cli + 3 app) - New: 245+ tests for phases 12-18 - Coverage maintained at 80%+ Breaking Changes: None Dependencies: No new external dependencies added * fix: apply CodeRabbit security and quality improvements Security Fixes: - Replace custom glob-to-regex with minimatch to prevent ReDoS vulnerabilities - Fix regex pattern generation in globs.ts using battle-tested library - Eliminate unsafe regex patterns in modes.ts and permissions.ts Code Quality Improvements: - Use shared GlobMatcher utility to eliminate code duplication in modes.ts - Preserve command metadata on updates to prevent data loss - Fix single-file vs directory output path handling in command.ts - Pass --strict flag through to plan validator Race Condition & Concurrency Fixes: - Add Promise-based mutex to prevent race condition in audit logger flush() - Handle both sync and async event listeners to prevent unhandled rejections - Maintain synchronous event emission while safely handling async listeners Data Integrity Fixes: - Fix dependency checking to detect missing dependencies - Rehydrate Date fields when importing tasks from JSON - Fix executePlan to properly detect incomplete tasks State Management: - Add validation for missing step executor (fail fast) - Handle cancellation and reset executor state in finally block - Add 'cancelled' status and event to PlanStatus/PlanEvent types Dependencies: - Add minimatch@^10.0.1 to @skillkit/agents package All 639 tests passing. * docs: update READMEs with Phase 10-18 features - Root README: add minimal "What's New in v1.5.0" section with 5 bullet points - packages/core: add usage examples for Team, Plugin, Methodology, Orchestration, Plan, Hooks - packages/cli: add command sections for team, plugin, methodology, plan, hook, command - packages/tui: add screen descriptions for Marketplace, Workflow, Execute, Team, Plugins, Methodology, Plan, Memory - apps/skillkit: expand with practical usage examples for all new features All updates are clean, user-focused, and avoid AI marketing fluff. * fix: resolve multiple code quality and robustness issues - Fix minimatch dependency: downgrade to ^9.0.0 for Node 18 compatibility - Fix command.ts export: handle directory paths and ensure parent directories exist - Fix command.ts merge: preserve curated examples when merging commands - Fix plan.ts: filter empty entries from comma-separated inputs - Fix audit logger pagination: respect explicit 0 for limit and offset - Fix audit logger: gracefully handle malformed JSON lines without data loss - Fix team orchestrator: prevent task assignment to non-idle agents - Fix plan executor: unblock waitIfPaused() when cancel() is called All 639 tests passing. * fix: additional robustness improvements for plan and executor - Fix plan.ts createPlan: filter empty strings from techStack after split/trim - Fix executor.ts: re-check abort signal after waitIfPaused() in both execute() and executeTask() to prevent running additional tasks/steps after cancellation during pause All 639 tests passing. |