mirror of
https://github.com/rohitg00/skillkit.git
synced 2026-11-18 18:04:26 +00:00
feat/eval-system
1
Commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
|
|
d3ffb79512 |
feat: add session memory system for cross-agent learning (#3)
* feat: add session memory system for cross-agent learning
Implements a lightweight, local-first memory system that works across
all 17 AI coding agents. Key features:
- YAML-based storage (no databases or external services)
- Three memory layers: Session, Project, and Global
- AI-powered compression of observations into learnings
- Cross-agent memory injection with relevance matching
- Progressive disclosure for token efficiency
Core modules:
- ObservationStore: Capture raw session observations
- LearningStore: Persist compressed learnings
- MemoryCompressor: AI/rule-based compression engine
- MemoryInjector: Context-aware memory retrieval
- MemoryObserver: Automatic observation capture
CLI commands (skillkit memory):
- status, search, list, show, compress, export
- import, clear, add, rate, config
TUI integration:
- New Memory screen with tabs (Learnings/Observations/Search)
- useMemory hook for state management
- Updated navigation and keybindings
Code quality improvements:
- Replaced nested ternaries with explicit functions
- Added named constants for magic numbers
- Simplified navigation with lookup map
* feat: add marketplace, testing, CI/CD, workflows, and fix dry-run bug
New Features:
- Skill Marketplace: Aggregates skills from GitHub repos with caching
- Skill Testing Framework: 18+ assertion types for skill validation
- CI/CD Integration: Templates for GitHub Actions, GitLab CI, CircleCI
- Workflow Orchestration: Wave-based parallel skill execution
- Session Management: Pause/resume support with state persistence
- Agent Execution: CLI spawning for claude/codex/gemini/opencode/goose
New CLI Commands:
- skillkit marketplace - Browse and install from marketplace
- skillkit test - Run skill tests with assertions
- skillkit run - Execute skills with orchestration
- skillkit status - Show session state
- skillkit pause/resume - Session management
- skillkit workflow - Workflow management
New TUI Screens:
- Marketplace browser with search
- History viewer with session details
- Workflow management screen
Bug Fix:
- Fixed dry-run mode in memory compress command (Devin review)
The --dry-run flag now properly prevents storing learnings
* fix: add missing yaml dependency to @skillkit/cli
* chore: update pnpm-lock.yaml
* fix: address 7 bugs identified by Devin code review
- Fix MemoryIndexStore ignoring isGlobal flag (memory-index.ts)
- Fix ESM runtime crash using require('yaml') in test runner (runner.ts)
- Fix ESM runtime crash using require('node:fs') in MarketplaceAggregator (aggregator.ts)
- Fix ESM runtime crash using require('node:fs') in SessionManager (manager.ts)
- Fix memory rate command parsing rating from --content instead of positional arg (memory.ts)
- Fix SkillExecutionEngine emitting failed status for paused executions (engine.ts)
- Fix run command misclassifying directories as skill markdown files (run.ts)
* fix: address CodeRabbit/Devin review issues (batch 2)
- Fix resume skipping checkpoint handling in engine.ts
- Add paused status guard before completeExecution call
- Fix NaN% progress when totalSteps=0 in Execute.tsx
- Fix effectiveness ?? instead of || to preserve 0% values in compressor.ts
- Clear cache on source change in aggregator.ts addSource/removeSource
* fix: address critical and major CodeRabbit/Devin issues (batch 3)
Security fixes:
- Remove shell: true from spawn to prevent shell injection (agents.ts)
- Add safe regex test with ReDoS protection (engine.ts)
- Add security warning for verification commands (engine.ts)
Bug fixes:
- Fix global memory index path to use ~/.skillkit/ (compressor.ts, memory-index.ts)
- Add task_complete events and verification to resumeExecution (engine.ts)
- Handle absolute URLs in skill entries (aggregator.ts)
- Implement actual port availability check (runner.ts)
- Remove invalid JUnit report format (templates.ts)
- Add crash guard to workflow list command (workflow/list.ts)
* fix: address remaining CodeRabbit/Devin issues (batch 4)
- ReDoS protection: Add pattern validator to reject dangerous regex patterns
(nested quantifiers, overlapping alternations, excessive quantifiers)
- Add missing 'cancelled' status message in execution engine
- Make completedAt/durationMs optional in TaskExecutionResult
- Fix tag filter to skip untagged tests when tags are specified
- Improve error-solution matching: require keyword similarity + solution indicator
- Validate --limit and sanitize --tags in memory/marketplace CLI commands
- Guard against missing arrays when importing YAML learnings
- Escape YAML frontmatter values to prevent invalid output
- Preserve original learning source when merging learnings
- Fix keyword double-counting in memory index search
- Normalize keywords by stripping punctuation for better matching
|