Commit Graph
2 Commits
Author SHA1 Message Date
Rohit Ghumare 6d290171b7 feat(memory): add lifecycle hooks, progressive disclosure, and auto-compress memory (#44)
* feat(memory): add lifecycle hooks, progressive disclosure, and auto-CLAUDE.md updates

- Add Claude Code lifecycle hooks (SessionStart, PostToolUse, SessionEnd)
  for automatic memory capture and injection
- Implement 3-layer progressive disclosure for token-optimized retrieval
  (Index ~50 tokens, Timeline ~200 tokens, Details ~600 tokens)
- Add CLAUDE.md auto-updater to populate LEARNED section with learnings
- Add auto-compression threshold trigger in observation store
- Add new CLI commands: `memory sync-claude` and `memory index`
- Update documentation with new memory features
- Remove 139 lines of unnecessary inline comments (code cleanup)

* fix(memory): address Devin review comments

- Fix double execution bug in MemoryHookManager by adding
  generateHookOutputFromResult methods to avoid calling execute() twice
- Add setConfig method to PostToolUseHook for runtime config updates
- Update manager.setConfig() to propagate config to all hooks

* fix(memory): address CodeRabbit review comments

- Fix cross-platform path handling using path.basename() instead of split('/')
  in claude-md-updater.ts, session-start.ts, and session-end.ts
- Fix onSessionEnd to call execute() before generateHookOutput to run
  compression/cleanup side effects
- Add generateHookOutputFromResult() to SessionEndHook to avoid double execution
- Call clearOldPendingErrors() in PostToolUseHook.execute() to prevent
  unbounded pendingErrors map growth
- Handle async checkAutoCompression() errors in observation-store.ts
- Add validation for compression threshold (must be positive integer)
- Fix docs/commands.mdx to use correct CLI flags (--limit, --tags)
- Clarify token accounting in progressive-disclosure smartRetrieve() JSDoc
- Use config.minRelevanceForCapture in session-start.ts instead of hardcoded value

* fix(memory): address additional CodeRabbit review comments

- Use nullish coalescing (??) for maxResults defaults in progressive-disclosure
- Guard against non-positive tokenBudget in smartRetrieve()
- Thread minRelevance option through to findRelevantIds()
- Fix memory index CLI to validate --limit and pass maxResults to getIndex()
2026-02-05 11:26:31 +00:00
Rohit Ghumare 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
2026-01-23 18:12:15 +00:00