- Moved augmentation refactor plan from REFACTOR-2.0-AUGMENTATIONS.md to PLAN.md
- Added documentation cleanup accomplishments to PLAN.md
- Removed separate refactor document to keep all planning in one place
- PLAN.md now contains all current and upcoming work (not checked in)
- Renamed augmentationFactory.ts to .deprecated (not compiled)
- This file used the old augmentation type system incompatible with 2.0
- Remaining work documented in REFACTOR-2.0-AUGMENTATIONS.md
Note: augmentationPipeline.ts still needs refactoring to use new system
- Removed factory function exports from index.ts
- Removed unused augmentationFactory imports
- Added deprecated type definitions temporarily to maintain compilation
- Created REFACTOR-2.0-AUGMENTATIONS.md documenting cleanup plan
- All old types marked as @deprecated for removal before final 2.0
This is an intermediate state - full refactor documented in REFACTOR-2.0-AUGMENTATIONS.md
- Added deprecated augmentation type exports for compatibility
- Added WebRTCConduitAugmentation stub (deprecated)
- Fixed createConduitAugmentation export
- Maintained backwards compatibility while using new unified system
- Archived 13 API design iterations to docs/api-design-archive/
- Consolidated augmentation docs to docs/augmentations-archive/
- Maintained ONE definitive API doc at docs/api/README.md
- Cleaned up documentation structure for 2.0 release
- Preserved all historical documents for reference
Key findings from audit:
- Code implementation is CORRECT (uses greaterThan, lessThan, etc.)
- Only documentation showed wrong MongoDB-style operators
- Neural API is complete and functional
- All features preserved, just better organized
This commit establishes the final, correct API documentation.
- Moved API design docs to docs/api-design/
- Moved planning docs to docs/planning/
- Root now only contains standard repo files (README, LICENSE, etc.)
- Keeps CLAUDE.md and PLAN.md uncommitted for privacy
Clean root directory for better project organization.
Current state:
- Unified augmentation system to BrainyAugmentation interface
- Changed methods to specific noun/verb naming (addNoun, getNoun, etc)
- Made old methods private
- Combined getNouns into single unified method
- Neural API exists and is complete
- Triple Intelligence uses correct Brainy operators (not MongoDB)
Issues identified:
- Documentation incorrectly shows MongoDB operators (code is correct)
- Need to ensure all features are properly exposed
- Need to verify nothing was lost in simplification
This commit serves as a rollback point before applying fixes.
