Skip to content

kagan-sh/kagan

v0.18.0 Feature

This release adds 3 notable features for engineering teams evaluating rollout.

Published 1mo MCP Developer Tools
✓ No known CVEs patched
Read the diff → Tool health → What is this tool? →

✓ No known CVEs patched in this version

Topics

ai ai-agents antrophic claude claude-code cli
+11 more
codex gemini kagan kanban mcp openai opencode python textual tui uv

Summary

AI summary

Multi‑dimensional analytics and intelligent backend selection now automatically choose optimal backends based on performance data.

Full changelog

v0.18.0 — Multi-Dimensional Analytics & Intelligent Backend Selection

This release introduces a comprehensive analytics system that tracks agent performance across three dimensions — Backend × AgentRole × TaskType — and uses the collected data to intelligently select the optimal backend for each task.

🎯 Highlights

  • Multi-Dimensional Analytics — Track success rate, duration, and retry rate per backend, broken down by agent role (Worker / Orchestrator / Reviewer) and task type (code implementation, bug fix, refactoring, testing, and 8 more categories)
  • Intelligent Backend Selection — Kagan can now automatically pick the best-performing backend for each task based on historical performance, with confidence scoring (min. 5 sessions for a recommendation)
  • Task Auto-Classification — Every task is automatically classified into one of 12 categories based on title/description keywords
  • 4-Tab Analytics Dashboard — Web UI now includes Backend, By-Role, By-Task-Type, and Combined (3D) views with interactive charts
  • Glossary Popup — Help icon in analytics page explains all metrics and success criteria in plain language

🚀 Getting Started

  1. Install/Upgrade:
    uv tool install kagan==0.18.0
    # or: kagan update --force
    
  2. Database migrates automatically on first boot (adds task_type and agent_role columns)
  3. Enable smart recommendations: Settings → Backend Selection → toggle "Use recommended backend for tasks"
  4. Run a few tasks to build up performance data (minimum 5 sessions per backend for confidence scoring)
  5. View analytics: kagan web → Analytics page, or press i in the TUI kanban board

📦 What's Also Shipped

Features

  • analytics,types: Add backend timeline summary + enforce board dialog type safety (8ebc812)
  • Add intelligent backend recommendation setting (98bbff4)
  • Add multi-dimensional analytics and intelligent backend selection (de7f2b6)
  • analytics: Add smart backend recommendation in settings (b9c855d)
  • analytics: Add terminology glossary popup (1d986ac)

Bug Fixes

  • types: Explicitly use BoardDialog type in closeDialog function (2f3985c)
  • Resolve linting and dead code issues (1c6ca8d)
  • server: Reduce complexity in analytics routes registration (22582c7)
  • vscode: Add format utilities for analytics commands (5139bf5)
  • vscode: Downgrade @types/vscode to match engines.vscode version (ea88d08)

Refactoring

  • analytics: Consolidate multi-dimensional aggregation queries (3043346)
  • analytics,web: Optimize performance and code quality (cd16373)
  • Simplify task card dropdown to limit to open, edit, delete (993d22e)

Documentation

  • Enhance analytics glossary with success/failure definitions (4ab6735)
  • Update analytics guide with multi-dimensional features (fe55a54)

Full diff: v0.17.1-beta.2...v0.18.0

Weekly OSS security release digest.

The CVE patches and breaking changes that affected production tools this week. One email, every Sunday.

No spam, unsubscribe anytime.

Share this release

Track kagan-sh/kagan

Get notified when new releases ship.

Sign up free

About kagan-sh/kagan

AI-powered Kanban TUI and MCP server for autonomous development workflows. Orchestrates 14 coding agents across task tracking, isolated git worktrees, review, and merge.

All releases →

Beta — feedback welcome: [email protected]