Public Access
admin
25e29c714d
Sprint 13 (commit bae9403) set OLLAMA_MODEL=kimi-k2.6:cloud.
kimi-k2.6 is a reasoning model that burns the entire max_tokens=800
budget on internal reasoning and never produces the JSON answer
for the Sprint 13 prompt. Every /api/llm/plan call has returned
picked_count=0 since 2026-06-05. The library fill (Sprint 6+)
silently took over, masking the bug. Every "Ask the LLM" click
paid Ollama costs for nothing.
Discovered while answering the user's "is there anything else to
refine?" question. Added a temp debug log to _ask_llm, saw
raw_response='' with finish_reason: length. Verified on Ollama
Cloud: gpt-oss:20b (OpenAI's open-source 20B non-reasoning
model) returns 21 valid picks in 2074 chars on the same prompt.
finish_reason: stop. Reasoning field is 239 chars vs kimi-k2.6's
8206+ chars.
Two-line fix:
- backend/app/config.py:38 — OLLAMA_MODEL: str = "gpt-oss:20b"
(was "kimi-k2.6:cloud")
- backend/app/api/llm_plan.py:117 — max_tokens: 4000 (was 800).
21 picks × ~100 chars + reasoning + boilerplate ≈ 2100+ chars;
4000 gives 2x headroom.
Plus the host's .env (or docker-compose env) was also set to
OLLAMA_MODEL=gpt-oss:20b — pydantic settings read env first, so
the .env change is what actually fixed the running container. The
config.py default is a backup for new deploys.
Plus frontend/src/api/llm.test.ts (NEW, 4 cases) — Vitest
contract test on the LLM response shape. Locks plan_id (UUID),
picked_count / filled_count / failed_count (non-negative integers
summing to ≤ 21), and reasoning (string|null). Catches
response-shape regressions so a future model swap that breaks
the JSON contract is caught at npm test time. The 4 cases: 8a
(POST to /llm/plan with payload), 8b (response.plan_id is a
valid UUID), 8c (counts are non-negative integers summing to
≤ 21), 8d (reasoning is string or null).
Verified: 11/11 vitest cases pass (4 new from S16 + 7 from S14).
npm run build green. Live API: 5/5 test weeks return picked_count
15-21 (was 0/5 before). Backend env verified:
docker exec mealplanner-backend-1 env | grep OLLAMA_MODEL →
gpt-oss:20b. No new runtime dependencies. No migration. No
schema change. No UI change.
Deploy: git pull + docker compose up -d --build backend frontend.
The .env change should already be in place; verify with
docker exec mealplanner-backend-1 env | grep OLLAMA_MODEL.
Meal Planner
Self-hosted meal planning system that integrates with Lucky California grocery store, sends weekly meal proposals via email to family members, generates shopping lists, and learns from feedback.
Background
This project was born out of frustration with meal kit services (Blue Apron → EveryPlate → HungryRoot → Sunbasket) that:
- Escalate costs to 3x ingredient markup
- Fall into repetitive meal rhythms
- Force users to log into apps to manage selections
- Don't integrate with home pantry items
Features
- Grocery Integration: Scrapes Lucky California weekly ads and sales
- Family Approval Workflow: Email proposals with approve/deny; one denial swaps the meal
- Shopping List Generation: Weekly list grouped by store aisles, highlighting sales, with interactive checkboxes to track purchased items
- Pantry Integration: Specify home items to incorporate into suggestions
- Web UI: Modern interface for the whole family
- Learning: Feedback-based meal recommendations, with weekly auto-discovery of new recipes from external APIs when family preferences are signaled
- Recipe Images: Scraped from public recipe sites, AI fallback available
- Unit Conversion: Converts recipe quantities (cups, tbsp, lb) to grocery units for accurate cost estimates
Architecture
- Backend: Python/FastAPI
- Database: PostgreSQL
- Frontend: React + Tailwind CSS
- Email: SendGrid
- Hosting: Docker Compose with nginx reverse proxy
Documentation
Quick Start
# Clone and start
docker-compose up -d
# View logs
docker-compose logs -f
# Stop
docker-compose down
Family Profile
Household: 2 adults, 2 children
- One adult likes mushrooms, one child OK with them
- Three family members do NOT like mushrooms
- No allergies
- Calorie, budget, and health conscious eating
Approval Workflow
- System generates 7-day meal plan based on sales, dietary constraints, budget, variety
- Email sent to both adults with meal previews
- One denial = meal swapped; no denials = auto-approved
- Shopping list generated after approval
Tech Stack
| Component | Technology |
|---|---|
| Backend | Python 3.11, FastAPI |
| Database | PostgreSQL 15 |
| Frontend | React 18, TypeScript, Tailwind |
| Scraping | Playwright, BeautifulSoup |
| SendGrid | |
| Hosting | Docker Compose, nginx |