soroban-abacus-flashcards

History

Thomas Hallock 5a4c751ebe feat: add LLM client package and worksheet parsing infrastructure Part A: @soroban/llm-client package - Multi-provider support (OpenAI, Anthropic) via env vars - Zod schema validation for structured LLM responses - Retry loop with validation error feedback in prompt - Progress indication hooks for UI feedback - Vision support for image analysis Part B: Worksheet parsing feature - Zod schemas for parsed worksheet problems - LLM prompt builder for abacus workbook images - Parser using llm.vision() with retry logic - Session converter to create SlotResults for BKT - Database migration for parsing columns - API routes: /parse, /review, /approve workflow 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>	2026-01-02 08:49:48 -06:00
..
README.json	feat: add LLM client package and worksheet parsing infrastructure	2026-01-02 08:49:48 -06:00

Thomas Hallock 5a4c751ebe feat: add LLM client package and worksheet parsing infrastructure

Part A: @soroban/llm-client package
- Multi-provider support (OpenAI, Anthropic) via env vars
- Zod schema validation for structured LLM responses
- Retry loop with validation error feedback in prompt
- Progress indication hooks for UI feedback
- Vision support for image analysis

Part B: Worksheet parsing feature
- Zod schemas for parsed worksheet problems
- LLM prompt builder for abacus workbook images
- Parser using llm.vision() with retry logic
- Session converter to create SlotResults for BKT
- Database migration for parsing columns
- API routes: /parse, /review, /approve workflow

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

2026-01-02 08:49:48 -06:00

README.json

feat: add LLM client package and worksheet parsing infrastructure

2026-01-02 08:49:48 -06:00

README.json

{
  "note": "Placeholder - model needs to be trained. Run: npx tsx scripts/train-column-classifier/generateTrainingData.ts and then the Python training script."
}