Dabba · kal kitna banana hai

An ops tool for a home tiffin (dabba) kitchen. Paste tonight's WhatsApp messages, get tomorrow's orders as a table and a prep list that says how many of each dish to cook, with a confidence band.

• Order parsing: Qwen3.5-4B LoRA fine-tuned on Tinker reads Hinglish messages like kal 2 veg thali lunch, no onion or parso ka dabba cancel and resolves relative dates against the WhatsApp timestamp.
• Demand forecast: TabPFN (Prior Labs' tabular foundation model) predicts tomorrow's final count per dish from the kitchen's history and the orders already booked by 9 pm.
• Kitchen memory: Backboard remembers each customer's usual dish and prefs, so a bare "1 dabba" from a paneer regular becomes a paneer thali.
• Hosted on Render.

uv venv --python 3.12 && uv pip install -r requirements-train.txt
cp .env.example .env                      # TINKER_API_KEY, BACKBOARD_API_KEY, TABPFN_TOKEN
.venv/bin/python data/simulate.py         # kitchen simulator -> messages_*.jsonl + history.csv
.venv/bin/python train/sft_tinker.py      # LoRA on Tinker -> DABBA_SAMPLER_PATH
.venv/bin/python train/eval.py --systems base,big,lora
.venv/bin/python forecast/forecast.py --mode client
PARSER_BACKEND=tinker .venv/bin/uvicorn app.main:app --reload

Results live in results/ and are reproduced in the DEV post (POST.md).