diff --git a/CLAUDE.md b/CLAUDE.md index 74290d7..5a4960b 100644 --- a/CLAUDE.md +++ b/CLAUDE.md @@ -1,122 +1,99 @@ - -Default to using Bun instead of Node.js. - -- Use `bun ` instead of `node ` or `ts-node ` -- Use `bun test` instead of `jest` or `vitest` -- Use `bun build ` instead of `webpack` or `esbuild` -- Use `bun install` instead of `npm install` or `yarn install` or `pnpm install` -- Use `bun run - - -``` - -With the following `frontend.tsx`: - -```tsx#frontend.tsx -import React from "react"; -import { createRoot } from "react-dom/client"; - -// import .css files directly and it works -import './index.css'; - -const root = createRoot(document.body); - -export default function Frontend() { - return

Hello, world!

; -} - -root.render(); -``` - -Then, run index.ts - -```sh -bun --hot ./index.ts -``` - -For more information, read the Bun API docs in `node_modules/bun-types/docs/**.mdx`. -## asin-check Project Notes +## Architecture -- Keep the existing ASIN lead-list and category flows compatible with their current LLM-based FBA/FBM/SKIP analysis. -- The supplier UPC workflow is deterministic and runs through `bun run upc-file --input input/supplier.xlsx --out output/supplier_ranked.xlsx`. -- Keep supplier spreadsheets in `input/`, generated workbooks in `output/`, and SQLite files in `db/`; folder contents are ignored by git. -- Supplier UPC files should resolve UPC/EAN values through SP-API catalog lookup first, with Keepa UPC lookup only as fallback for no-match or request-failure cases. -- The supplier pipeline should not call LM Studio. It should enrich with Keepa + SP-API sellability/fees, score BUY/WATCH/SKIP numerically, write an Excel workbook, and persist rows to SQLite. -- Supplier workbook output should keep the `Ranked Leads`, `Skipped`, and `Summary` sheets. +Two distinct analysis pipelines share infrastructure (Keepa, SP-API, Redis, SQLite) but diverge in how they produce verdicts. + +### ASIN Lead-list Pipeline (`src/index.ts` → `src/analysis-pipeline.ts`) + +For spreadsheets containing known ASINs. Verdict is LLM-based (FBA/FBM/SKIP via LM Studio). + +Flow: `reader.ts` parse → Redis cache check → `sp-api.ts` sellability gate (5 concurrent workers) → `keepa.ts` batch enrichment → `sp-api.ts` pricing + FBA fees (5 concurrent workers) → `llm.ts` batched analysis (5 products/batch) → `writer.ts` XLSX + SQLite. + +### Supplier UPC Pipeline (`src/upc-file-analysis.ts`) + +For supplier price lists containing UPC/EAN values. Verdict is deterministic (BUY/WATCH/SKIP); never calls LM Studio. + +Flow: `upc-file-reader.ts` streaming parse (`.xlsx`) or row-window parse (`.xls`) → SP-API catalog UPC lookup first, Keepa UPC lookup as fallback → `keepa.ts` demand enrichment → `sp-api.ts` sellability + FBA fees → `supplier-scoring.ts` deterministic score → `supplier-export.ts` Excel workbook (`Ranked Leads`, `Skipped`, `Summary` sheets) + SQLite. + +UPC resolution priority: SP-API catalog lookup → Keepa fallback (for no-match or request failure only). + +### Category Pipelines + +`bestsellers-by-category.ts`, `top-monthly-sold-by-category.ts`, `mid-range-sellers-by-category.ts` — Keepa category browsing → SP-API sellability gate → LLM verdict. Each saves results to SQLite. Mid-range applies configurable filters (monthly sold, price, seller count, Amazon buy box share). + +### Shared Infrastructure + +| Module | Role | +|--------|------| +| `src/types.ts` | All shared interfaces (`ProductRecord`, `KeepaData`, `SpApiData`, `SupplierScore`, etc.) | +| `src/config.ts` | Env var loading via `Bun.env` | +| `src/keepa.ts` | Keepa API: batch ASIN fetch, UPC lookup, auto rate-limiting on token exhaustion | +| `src/sp-api.ts` | SP-API: sellability (`getListingsRestrictions`), pricing+fees, UPC catalog lookup | +| `src/cache.ts` | Redis caching (24h TTL for lead-list; 12h for mid-range) | +| `src/database.ts` | SQLite `runs` + `results` tables; auto-creates `db/results.db` | +| `src/server.ts` | Bun HTTP server exposing REST endpoints for both pipelines | + +### File Layout + +- `input/` — source spreadsheets (git-ignored) +- `output/` — generated workbooks (git-ignored) +- `db/` — SQLite files (git-ignored) +- `src/` — all source and test files + +## Project Rules + +- Keep the ASIN lead-list and category flows compatible with their current LLM-based FBA/FBM/SKIP analysis. +- The supplier UPC pipeline must not call LM Studio. +- Supplier UPC files resolve UPC/EAN through SP-API catalog lookup first; Keepa UPC lookup is fallback only (no-match or request-failure cases). +- Supplier workbook output must keep `Ranked Leads`, `Skipped`, and `Summary` sheets. - When changing UPC supplier behavior, cover SP-API UPC parsing, deterministic scoring, and workbook export with `bun test`.