Compare commits

..

No commits in common. "main" and "feature/orch-auto-lifecycle" have entirely different histories.

241 changed files with 1078 additions and 36543 deletions

View file

@ -1,44 +0,0 @@
# git-cliff changelog configuration for Kiwi
# See: https://git-cliff.org/docs/configuration
[changelog]
header = """
# Changelog\n
"""
body = """
{% if version %}\
## [{{ version | trim_start_matches(pat="v") }}] - {{ timestamp | date(format="%Y-%m-%d") }}
{% else %}\
## [Unreleased]
{% endif %}\
{% for group, commits in commits | group_by(attribute="group") %}
### {{ group | upper_first }}
{% for commit in commits %}
- {% if commit.scope %}**{{ commit.scope }}:** {% endif %}{{ commit.message | upper_first }}\
{% endfor %}
{% endfor %}\n
"""
trim = true
[git]
conventional_commits = true
filter_unconventional = true
split_commits = false
commit_preprocessors = []
commit_parsers = [
{ message = "^feat", group = "Features" },
{ message = "^fix", group = "Bug Fixes" },
{ message = "^perf", group = "Performance" },
{ message = "^refactor", group = "Refactoring" },
{ message = "^docs", group = "Documentation" },
{ message = "^test", group = "Testing" },
{ message = "^chore", group = "Chores" },
{ message = "^ci", group = "CI/CD" },
{ message = "^revert", group = "Reverts" },
]
filter_commits = false
tag_pattern = "v[0-9].*"
skip_tags = ""
ignore_tags = ""
topo_order = false
sort_commits = "oldest"

View file

@ -21,12 +21,10 @@ DATA_DIR=./data
# IP this machine advertises to the coordinator (must be reachable from coordinator host) # IP this machine advertises to the coordinator (must be reachable from coordinator host)
# CF_ORCH_ADVERTISE_HOST=10.1.10.71 # CF_ORCH_ADVERTISE_HOST=10.1.10.71
# GPU inference server (cf-orch coordinator for recipe scan, LLM generation, etc.) # CF-core hosted coordinator (managed cloud GPU inference — Paid+ tier)
# GPU_SERVER_URL: set to your local cf-orch coordinator (self-hosted rack). # Set CF_ORCH_URL to use a hosted cf-orch coordinator instead of self-hosting.
# CF_ORCH_URL is the backward-compat alias — both are honoured. # CF_LICENSE_KEY is read automatically by CFOrchClient for bearer auth.
# Paid+ default: when CF_LICENSE_KEY is present and neither URL is set, # CF_ORCH_URL=https://orch.circuitforge.tech
# the app automatically points to https://orch.circuitforge.tech.
# GPU_SERVER_URL=http://10.1.10.71:7700
# CF_LICENSE_KEY=CFG-KIWI-xxxx-xxxx-xxxx # CF_LICENSE_KEY=CFG-KIWI-xxxx-xxxx-xxxx
# LLM backend — env-var auto-config (no llm.yaml needed for bare-metal users) # LLM backend — env-var auto-config (no llm.yaml needed for bare-metal users)
@ -53,15 +51,6 @@ ENABLE_OCR=false
DEBUG=false DEBUG=false
CLOUD_MODE=false CLOUD_MODE=false
DEMO_MODE=false DEMO_MODE=false
# Product identifier reported in cf-orch coordinator analytics for per-app breakdown
CF_APP_NAME=kiwi
# USE_ORCH_SCHEDULER: use coordinator-aware multi-GPU scheduler instead of local FIFO.
# Unset = auto-detect: true if CLOUD_MODE or circuitforge_orch is installed (paid+ local).
# Set false to force LocalScheduler even when cf-orch is present.
# USE_ORCH_SCHEDULER=false
# GPU_SERVER_URL: cf-orch coordinator endpoint. Required for recipe scan (cf-docuvision)
# and LLM features on a self-hosted rack. CF_ORCH_URL is the backward-compat alias.
# GPU_SERVER_URL=http://10.1.10.71:7700
# Cloud mode (set in compose.cloud.yml; also set here for reference) # Cloud mode (set in compose.cloud.yml; also set here for reference)
# CLOUD_DATA_ROOT=/devl/kiwi-cloud-data # CLOUD_DATA_ROOT=/devl/kiwi-cloud-data
@ -79,14 +68,9 @@ CF_APP_NAME=kiwi
# HEIMDALL_URL=https://license.circuitforge.tech # HEIMDALL_URL=https://license.circuitforge.tech
# HEIMDALL_ADMIN_TOKEN= # HEIMDALL_ADMIN_TOKEN=
# Directus JWT (must match cf-directus SECRET env var exactly, including base64 == padding) # Directus JWT (must match cf-directus SECRET env var)
# DIRECTUS_JWT_SECRET= # DIRECTUS_JWT_SECRET=
# E2E test account (Directus — free tier, used by automated tests)
# E2E_TEST_EMAIL=e2e@circuitforge.tech
# E2E_TEST_PASSWORD=
# E2E_TEST_USER_ID=
# In-app feedback → Forgejo issue creation # In-app feedback → Forgejo issue creation
# FORGEJO_API_TOKEN= # FORGEJO_API_TOKEN=
# FORGEJO_REPO=Circuit-Forge/kiwi # FORGEJO_REPO=Circuit-Forge/kiwi
@ -99,10 +83,3 @@ CF_APP_NAME=kiwi
# INSTACART_AFFILIATE_ID=circuitforge # INSTACART_AFFILIATE_ID=circuitforge
# Walmart Impact network affiliate ID (inline, path-based redirect) # Walmart Impact network affiliate ID (inline, path-based redirect)
# WALMART_AFFILIATE_ID= # WALMART_AFFILIATE_ID=
# Community PostgreSQL — shared across CF products (cloud only; leave unset for local dev)
# Points at cf-orch's cf-community-postgres container (port 5434 on the orch host).
# When unset, community write paths fail soft with a plain-language message.
# COMMUNITY_DB_URL=postgresql://cf_community:changeme@cf-orch-host:5434/cf_community
# COMMUNITY_PSEUDONYM_SALT=change-this-to-a-random-32-char-string

View file

@ -1,62 +0,0 @@
# Kiwi CI — lint, type-check, test on PR/push
# Full-stack: FastAPI (Python) + Vue 3 SPA (Node)
# Adapted from Circuit-Forge/cf-agents workflows/ci.yml (cf-agents#4 tracks the
# upstream ci-fullstack.yml variant; update this file when that lands).
#
# Note: frontend has no test suite yet — CI runs typecheck only.
# Add `npm run test` when vitest is wired (kiwi#XX).
#
# circuitforge-core is not on PyPI — installed from Forgejo git (public repo).
name: CI
on:
push:
branches: [main, 'feature/**', 'fix/**']
pull_request:
branches: [main]
jobs:
backend:
name: Backend (Python)
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v4
- uses: actions/setup-python@v5
with:
python-version: '3.11'
cache: pip
- name: Install circuitforge-core
run: pip install git+https://git.opensourcesolarpunk.com/Circuit-Forge/circuitforge-core.git@main
- name: Install dependencies
run: pip install -e ".[dev]" || pip install -e . pytest pytest-asyncio httpx ruff
- name: Lint
run: ruff check .
- name: Test
run: pytest tests/ -v --tb=short
frontend:
name: Frontend (Vue)
runs-on: ubuntu-latest
defaults:
run:
working-directory: frontend
steps:
- uses: actions/checkout@v4
- uses: actions/setup-node@v4
with:
node-version: '20'
cache: npm
cache-dependency-path: frontend/package-lock.json
- name: Install dependencies
run: npm ci
- name: Type check
run: npx vue-tsc --noEmit

View file

@ -1,34 +0,0 @@
# Mirror push to GitHub and Codeberg on every push to main or tag.
# Copied from Circuit-Forge/cf-agents workflows/mirror.yml
# Required secrets: GITHUB_MIRROR_TOKEN, CODEBERG_MIRROR_TOKEN
name: Mirror
on:
push:
branches: [main]
tags: ['v*']
jobs:
mirror:
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v4
with:
fetch-depth: 0
- name: Mirror to GitHub
env:
GITHUB_TOKEN: ${{ secrets.GITHUB_MIRROR_TOKEN }}
REPO: ${{ github.event.repository.name }}
run: |
git remote add github "https://x-access-token:${GITHUB_TOKEN}@github.com/CircuitForgeLLC/${REPO}.git"
git push github --mirror
- name: Mirror to Codeberg
env:
CODEBERG_TOKEN: ${{ secrets.CODEBERG_MIRROR_TOKEN }}
REPO: ${{ github.event.repository.name }}
run: |
git remote add codeberg "https://CircuitForge:${CODEBERG_TOKEN}@codeberg.org/CircuitForge/${REPO}.git"
git push codeberg --mirror

View file

@ -1,71 +0,0 @@
# Tag-triggered release workflow.
# Generates changelog and creates Forgejo release on v* tags.
# Copied from Circuit-Forge/cf-agents workflows/release.yml
#
# Docker push is intentionally disabled — BSL 1.1 registry policy not yet resolved.
# Tracked in Circuit-Forge/cf-agents#3. Re-enable the Docker steps when that lands.
#
# Required secrets: FORGEJO_RELEASE_TOKEN
# (GHCR_TOKEN not needed until Docker push is enabled)
name: Release
on:
push:
tags: ['v*']
jobs:
release:
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v4
with:
fetch-depth: 0
# ── Changelog ────────────────────────────────────────────────────────────
- name: Generate changelog
uses: orhun/git-cliff-action@v3
id: cliff
with:
config: .cliff.toml
args: --latest --strip header
env:
OUTPUT: CHANGES.md
# ── Docker (disabled — BSL registry policy pending cf-agents#3) ──────────
# - name: Set up QEMU
# uses: docker/setup-qemu-action@v3
# - name: Set up Buildx
# uses: docker/setup-buildx-action@v3
# - name: Log in to GHCR
# uses: docker/login-action@v3
# with:
# registry: ghcr.io
# username: ${{ github.actor }}
# password: ${{ secrets.GHCR_TOKEN }}
# - name: Build and push Docker image
# uses: docker/build-push-action@v6
# with:
# context: .
# push: true
# platforms: linux/amd64,linux/arm64
# tags: |
# ghcr.io/circuitforgellc/kiwi:${{ github.ref_name }}
# ghcr.io/circuitforgellc/kiwi:latest
# cache-from: type=gha
# cache-to: type=gha,mode=max
# ── Forgejo Release ───────────────────────────────────────────────────────
- name: Create Forgejo release
env:
FORGEJO_TOKEN: ${{ secrets.FORGEJO_RELEASE_TOKEN }}
REPO: ${{ github.event.repository.name }}
TAG: ${{ github.ref_name }}
NOTES: ${{ steps.cliff.outputs.content }}
run: |
curl -sS -X POST \
"https://git.opensourcesolarpunk.com/api/v1/repos/Circuit-Forge/${REPO}/releases" \
-H "Authorization: token ${FORGEJO_TOKEN}" \
-H "Content-Type: application/json" \
-d "$(jq -n --arg tag "$TAG" --arg body "$NOTES" \
'{tag_name: $tag, name: $tag, body: $body}')"

View file

@ -1,59 +0,0 @@
# Kiwi CI — runs on GitHub mirror for public credibility badge.
# Forgejo (.forgejo/workflows/ci.yml) is the canonical CI — keep these in sync.
# No Forgejo-specific secrets used here; circuitforge-core is public on Forgejo.
#
# Note: frontend has no test suite yet — CI runs typecheck only.
# Add 'npm run test' when vitest is wired.
name: CI
on:
push:
branches: [main]
pull_request:
branches: [main]
jobs:
backend:
name: Backend (Python)
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v4
- uses: actions/setup-python@v5
with:
python-version: '3.11'
cache: pip
- name: Install circuitforge-core
run: pip install git+https://git.opensourcesolarpunk.com/Circuit-Forge/circuitforge-core.git@main
- name: Install dependencies
run: pip install -e . pytest pytest-asyncio httpx ruff
- name: Lint
run: ruff check .
- name: Test
run: pytest tests/ -v --tb=short
frontend:
name: Frontend (Vue)
runs-on: ubuntu-latest
defaults:
run:
working-directory: frontend
steps:
- uses: actions/checkout@v4
- uses: actions/setup-node@v4
with:
node-version: '20'
cache: npm
cache-dependency-path: frontend/package-lock.json
- name: Install dependencies
run: npm ci
- name: Type check
run: npx vue-tsc --noEmit

3
.gitignore vendored
View file

@ -23,9 +23,6 @@ dist/
# Data directories # Data directories
data/ data/
# Local dev database
*.db
# Test artifacts (MagicMock sqlite files from pytest) # Test artifacts (MagicMock sqlite files from pytest)
<MagicMock* <MagicMock*

View file

@ -1,34 +0,0 @@
# Kiwi gitleaks config — extends base CircuitForge config with local rules
[extend]
path = "/Library/Development/CircuitForge/circuitforge-hooks/gitleaks.toml"
# ── Global allowlist ──────────────────────────────────────────────────────────
# Amazon grocery department IDs (rh=n:<10-digit>) false-positive as phone
# numbers. locale_config.py is a static lookup table with no secrets.
[allowlist]
# Amazon grocery dept IDs (rh=n:<digits>) false-positive as phone numbers.
regexes = [
'''rh=n:\d{8,12}''',
]
# ── Test fixture allowlists ───────────────────────────────────────────────────
[[rules]]
id = "cf-generic-env-token"
description = "Generic KEY=<token> in env-style assignment — catches FORGEJO_API_TOKEN=hex etc."
regex = '''(?i)(token|secret|key|password|passwd|pwd|api_key)\s*[=:]\s*['"]?[A-Za-z0-9\-_]{20,}['"]?'''
[rules.allowlist]
paths = [
'.*test.*',
]
regexes = [
'api_key:\s*ollama',
'api_key:\s*any',
'your-[a-z\-]+-here',
'replace-with-',
'xxxx',
'test-fixture-',
'CFG-KIWI-TEST-',
]

View file

@ -11,23 +11,13 @@ RUN apt-get update && apt-get install -y --no-install-recommends \
COPY circuitforge-core/ ./circuitforge-core/ COPY circuitforge-core/ ./circuitforge-core/
RUN conda run -n base pip install --no-cache-dir -e ./circuitforge-core RUN conda run -n base pip install --no-cache-dir -e ./circuitforge-core
# Install circuitforge-orch — needed for the cf-orch-agent sidecar (compose.override.yml)
COPY circuitforge-orch/ ./circuitforge-orch/
# Create kiwi conda env and install app # Create kiwi conda env and install app
COPY kiwi/environment.yml . COPY kiwi/environment.yml .
RUN conda env create -f environment.yml RUN conda env create -f environment.yml
COPY kiwi/ ./kiwi/ COPY kiwi/ ./kiwi/
# Install cf-core into the kiwi env BEFORE installing kiwi (kiwi lists it as a dep)
# Remove gitignored config files that may exist locally — defense-in-depth.
# The parent .dockerignore should exclude these, but an explicit rm guarantees
# they never end up in the cloud image regardless of .dockerignore placement.
RUN rm -f /app/kiwi/.env
# Install cf-core and cf-orch into the kiwi env BEFORE installing kiwi
RUN conda run -n kiwi pip install --no-cache-dir -e /app/circuitforge-core RUN conda run -n kiwi pip install --no-cache-dir -e /app/circuitforge-core
RUN conda run -n kiwi pip install --no-cache-dir -e /app/circuitforge-orch
WORKDIR /app/kiwi WORKDIR /app/kiwi
RUN conda run -n kiwi pip install --no-cache-dir -e . RUN conda run -n kiwi pip install --no-cache-dir -e .

136
README.md
View file

@ -1,58 +1,40 @@
<!-- Logo coming soon — replace docs/kiwi-logo.svg when final icon ships --> # 🥝 Kiwi
<div align="center">
<img src="docs/kiwi-logo.svg" alt="Kiwi logo" width="96" height="96" />
# Kiwi > *Part of the CircuitForge LLC "AI for the tasks the system made hard on purpose" suite.*
**Pantry tracking and recipe suggestions — with or without an LLM.** **Pantry tracking and leftover recipe suggestions.**
[![License: MIT/BSL](https://img.shields.io/badge/license-MIT%20%2F%20BSL%201.1-blue)](#license) Scan barcodes, photograph receipts, and get recipe ideas based on what you already have — before it expires.
[![CI](https://git.opensourcesolarpunk.com/Circuit-Forge/kiwi/badges/workflows/ci.yml/badge.svg)](https://git.opensourcesolarpunk.com/Circuit-Forge/kiwi/actions)
[![Version](https://img.shields.io/badge/version-0.6.0-green)](https://git.opensourcesolarpunk.com/Circuit-Forge/kiwi/releases)
[Documentation](https://docs.circuitforge.tech/kiwi) · [Live demo](https://menagerie.circuitforge.tech/kiwi) · [circuitforge.tech](https://circuitforge.tech) **LLM support is optional.** Inventory tracking, barcode scanning, expiry alerts, CSV export, and receipt upload all work without any LLM configured. AI features (receipt OCR, recipe suggestions, meal planning) activate when a backend is available and are BYOK-unlockable at any tier.
*Part of the CircuitForge LLC suite — "AI for the tasks the system made hard on purpose."* **Status:** Beta · CircuitForge LLC
</div>
--- ---
> **The LLM is optional.** Barcode scanning, receipt upload, expiry alerts, the full 200k+ recipe browser, and CSV export all work with zero LLM configured. Recipe suggestions and receipt OCR activate when a backend is available, and are BYOK-unlockable at any tier. You are never forced to send your data anywhere. ## What it does
--- - **Inventory tracking** — add items by barcode scan, receipt upload, or manually
- **Expiry alerts** — know what's about to go bad
- **Recipe browser** — browse the full recipe corpus by cuisine, meal type, dietary preference, or main ingredient; pantry match percentage shown inline (Free)
- **Saved recipes** — bookmark any recipe with notes, a 05 star rating, and free-text style tags (Free); organize into named collections (Paid)
- **Receipt OCR** — extract line items from receipt photos automatically (Paid tier, BYOK-unlockable)
- **Recipe suggestions** — four levels from pantry-match to full LLM generation (Paid tier, BYOK-unlockable)
- **Style auto-classifier** — LLM suggests style tags (comforting, hands-off, quick, etc.) for saved recipes (Paid tier, BYOK-unlockable)
- **Leftover mode** — prioritize nearly-expired items in recipe ranking (Premium tier)
- **LLM backend config** — configure inference via `circuitforge-core` env-var system; BYOK unlocks Paid AI features at any tier
- **Feedback FAB** — in-app feedback button; status probed on load, hidden if CF feedback endpoint unreachable
## What Kiwi does ## Stack
| Feature | Notes | - **Frontend:** Vue 3 SPA (Vite + TypeScript)
|---|---| - **Backend:** FastAPI + SQLite (via `circuitforge-core`)
| **Inventory tracking** | Add items by barcode scan, receipt upload, or manually | - **Auth:** CF session cookie → Directus JWT (cloud mode)
| **Expiry alerts** | Know what is about to go bad before it does | - **Licensing:** Heimdall (free tier auto-provisioned at signup)
| **Recipe browser** | 200k+ recipes — filter by cuisine, meal type, dietary preference, or main ingredient; pantry match percentage shown inline |
| **Leftover mode** | Prioritizes nearly-expired items in recipe ranking (5/day free, unlimited at Paid+) |
| **Recipe suggestions** | Four levels: direct corpus match, substitution/swap, cuisine-style adapter, full LLM generation |
| **Meal planning** | Plan meals for the week; pull from saved recipes or suggestions |
| **Saved recipes** | Bookmark any recipe with notes, 0-5 star rating, and free-text style tags; organize into named collections (Paid) |
| **Receipt OCR** | Extract line items from receipt photos automatically |
| **Dietary profiles** | Vegan, gluten-free, diabetic, and other constraints respected throughout |
| **Style auto-classifier** | LLM suggests style tags (comforting, hands-off, quick, etc.) for saved recipes |
| **Community feed** | Browse and share recipes with other Kiwi users |
| **CSV export** | Full pantry export, always available, no tier gate |
--- ## Running locally
## Quick start
**One-line install (self-hosted, Docker required):**
```bash ```bash
bash <(curl -fsSL https://git.opensourcesolarpunk.com/Circuit-Forge/kiwi/raw/branch/main/install.sh)
```
**Or clone and run manually:**
```bash
git clone https://git.opensourcesolarpunk.com/Circuit-Forge/kiwi.git
cd kiwi
cp .env.example .env cp .env.example .env
./manage.sh build ./manage.sh build
./manage.sh start ./manage.sh start
@ -60,59 +42,37 @@ cp .env.example .env
# API: http://localhost:8512 # API: http://localhost:8512
``` ```
**Live cloud instance** (free account required): ## Cloud instance
[menagerie.circuitforge.tech/kiwi](https://menagerie.circuitforge.tech/kiwi)
Full setup and configuration guide: [docs.circuitforge.tech/kiwi](https://docs.circuitforge.tech/kiwi) ```bash
./manage.sh cloud-build
--- ./manage.sh cloud-start
# Served at menagerie.circuitforge.tech/kiwi (JWT-gated)
```
## Tiers ## Tiers
| Feature | Free | Paid | Premium | | Feature | Free | Paid | Premium |
|---|:---:|:---:|:---:| |---------|------|------|---------|
| Inventory CRUD | Yes | Yes | Yes | | Inventory CRUD | ✓ | ✓ | ✓ |
| Barcode scan | Yes | Yes | Yes | | Barcode scan | ✓ | ✓ | ✓ |
| Receipt upload | Yes | Yes | Yes | | Receipt upload | ✓ | ✓ | ✓ |
| Expiry alerts | Yes | Yes | Yes | | Expiry alerts | ✓ | ✓ | ✓ |
| CSV export | Yes | Yes | Yes | | CSV export | ✓ | ✓ | ✓ |
| Recipe browser (200k+ recipes) | Yes | Yes | Yes | | Recipe browser (domain/category) | ✓ | ✓ | ✓ |
| Save recipes + notes + star rating | Yes | Yes | Yes | | Save recipes + notes + star rating | ✓ | ✓ | ✓ |
| Style tags (manual, free-text) | Yes | Yes | Yes | | Style tags (manual, free-text) | ✓ | ✓ | ✓ |
| Leftover mode (5/day) | Yes | Yes | Yes | | Receipt OCR | BYOK | ✓ | ✓ |
| Receipt OCR | BYOK | Yes | Yes | | Recipe suggestions (L1L4) | BYOK | ✓ | ✓ |
| Recipe suggestions (L1L4) | BYOK | Yes | Yes | | Named recipe collections | — | ✓ | ✓ |
| Named recipe collections | — | Yes | Yes | | LLM style auto-classifier | — | BYOK | ✓ |
| LLM style auto-classifier | — | BYOK | Yes | | Meal planning | — | ✓ | ✓ |
| Meal planning | — | Yes | Yes | | Multi-household | — | — | ✓ |
| Multi-household | — | — | Yes | | Leftover mode | — | — | ✓ |
**BYOK** = bring your own LLM backend. Configure `~/.config/circuitforge/llm.yaml` to unlock AI features at any tier without a paid subscription. BYOK = bring your own LLM backend (configure `~/.config/circuitforge/llm.yaml`)
---
## Stack
- **Frontend:** Vue 3 SPA (Vite + TypeScript), served on port 8511
- **Backend:** FastAPI + SQLite via `circuitforge-core`, API on port 8512
- **Auth:** CircuitForge session cookie (cloud mode); local mode requires no account
- **Licensing:** Heimdall — free tier auto-provisioned at signup
---
## Forgejo-primary
Kiwi is developed and maintained on Forgejo at [git.opensourcesolarpunk.com/Circuit-Forge/kiwi](https://git.opensourcesolarpunk.com/Circuit-Forge/kiwi). GitHub and Codeberg are read-only mirrors. File issues and submit pull requests on Forgejo.
---
## License ## License
Kiwi uses a split license: Discovery/pipeline layer: MIT
AI features: BSL 1.1 (free for personal non-commercial self-hosting)
- **Discovery and inventory pipeline** (barcode scan, expiry tracking, pantry CRUD, CSV export, recipe browser): [MIT](LICENSE-MIT)
- **AI features** (receipt OCR, LLM recipe suggestions, style auto-classifier): [BSL 1.1](LICENSE-BSL) — free for personal non-commercial self-hosting; commercial use or SaaS re-hosting requires a paid license. Converts to MIT after 4 years.
Humans own design, architecture, code review, testing, and verification. LLMs are part of our development workflow. [Our positions on LLM use →](https://circuitforge.tech/positions)
Privacy · Safety · Accessibility — co-equal, non-negotiable across all CircuitForge products.

View file

@ -3,5 +3,5 @@
Kiwi: Pantry tracking and leftover recipe suggestions. Kiwi: Pantry tracking and leftover recipe suggestions.
""" """
__version__ = "0.2.0" __version__ = "0.1.0"
__author__ = "Alan 'pyr0ball' Weinstock" __author__ = "Alan 'pyr0ball' Weinstock"

View file

@ -1,332 +0,0 @@
# app/api/endpoints/activitypub.py
# MIT License
#
# ActivityPub endpoints for Kiwi instances:
# GET /.well-known/webfinger — WebFinger JRD
# GET /ap/actor — Instance actor document
# POST /ap/actor/inbox — Incoming activities
# GET /ap/outbox — Outgoing activities (OrderedCollection)
# GET /ap/posts/{slug} — Individual AP Note
# GET /ap/followers — Followers collection (count only)
# GET /ap/following — Following collection (empty stub)
#
# All endpoints are no-ops / 404 when AP_ENABLED=false or actor not loaded.
# The WebFinger and well-known routes are mounted at the root app level (not
# under /api/v1) — see main.py.
from __future__ import annotations
import asyncio
import json
import logging
from datetime import datetime, timezone
from fastapi import APIRouter, HTTPException, Request, Response
from fastapi.responses import JSONResponse
from app.core.config import settings
from app.services.ap.keys import get_actor
logger = logging.getLogger(__name__)
# ── Two routers: one for well-known (root mount), one for /ap prefix ─────────
webfinger_router = APIRouter(tags=["activitypub"])
ap_router = APIRouter(prefix="/ap", tags=["activitypub"])
_AP_CONTENT_TYPE = "application/activity+json"
_JRD_CONTENT_TYPE = "application/jrd+json"
def _actor_required():
actor = get_actor()
if actor is None:
raise HTTPException(status_code=404, detail="ActivityPub not enabled on this instance.")
return actor
# ── WebFinger ─────────────────────────────────────────────────────────────────
@webfinger_router.get("/.well-known/webfinger")
async def webfinger(resource: str | None = None):
actor = get_actor()
if actor is None:
raise HTTPException(status_code=404, detail="ActivityPub not enabled.")
expected = f"acct:kiwi@{settings.AP_HOST}"
if resource and resource != expected:
raise HTTPException(status_code=404, detail=f"Resource {resource!r} not found.")
jrd = {
"subject": expected,
"links": [
{
"rel": "self",
"type": _AP_CONTENT_TYPE,
"href": actor.actor_id,
}
],
}
return Response(
content=json.dumps(jrd),
media_type=_JRD_CONTENT_TYPE,
)
# ── Actor ─────────────────────────────────────────────────────────────────────
@ap_router.get("/actor")
async def get_actor_doc():
actor = _actor_required()
return Response(
content=json.dumps(actor.to_ap_dict()),
media_type=_AP_CONTENT_TYPE,
)
# ── Inbox (mounted via make_inbox_router below) ───────────────────────────────
async def _on_follow(activity: dict, headers: dict) -> None:
"""Accept Follow: add to ap_followers, send Accept(Follow) back."""
actor_url = activity.get("actor", "")
if not actor_url:
return
from app.db.store import Store
from app.core.config import settings as _settings
db_path = _settings.DB_PATH
inbox_url, shared_inbox = await asyncio.to_thread(_resolve_inbox, actor_url)
if inbox_url is None:
return
import sqlite3
conn = sqlite3.connect(str(db_path))
try:
conn.execute(
"""INSERT OR REPLACE INTO ap_followers
(actor_id, inbox_url, shared_inbox, followed_at, active)
VALUES (?, ?, ?, ?, 1)""",
(actor_url, inbox_url, shared_inbox, datetime.now(timezone.utc).isoformat()),
)
conn.commit()
finally:
conn.close()
actor = get_actor()
if actor is None:
return
accept = {
"@context": "https://www.w3.org/ns/activitystreams",
"id": f"{actor.actor_id}/accepts/{activity.get('id', 'unknown')}",
"type": "Accept",
"actor": actor.actor_id,
"object": activity,
}
from circuitforge_core.activitypub import deliver_activity
await asyncio.to_thread(deliver_activity, accept, inbox_url, actor, 10.0)
async def _on_undo(activity: dict, headers: dict) -> None:
"""Handle Undo(Follow): deactivate the follower row."""
inner = activity.get("object", {})
if isinstance(inner, dict) and inner.get("type") == "Follow":
actor_url = activity.get("actor", "")
if actor_url:
import sqlite3
conn = sqlite3.connect(str(settings.DB_PATH))
try:
conn.execute(
"UPDATE ap_followers SET active = 0 WHERE actor_id = ?", (actor_url,)
)
conn.commit()
finally:
conn.close()
async def _dedup_activity(activity_id: str | None) -> bool:
"""Return True (already seen) if activity_id is in ap_received; otherwise insert it."""
if not activity_id:
return False
import sqlite3
conn = sqlite3.connect(str(settings.DB_PATH))
try:
try:
conn.execute(
"INSERT INTO ap_received (activity_id) VALUES (?)", (activity_id,)
)
conn.commit()
return False
except sqlite3.IntegrityError:
return True
finally:
conn.close()
def _build_inbox_router():
from circuitforge_core.activitypub.inbox import make_inbox_router
async def on_follow(activity: dict, headers: dict) -> None:
if await _dedup_activity(activity.get("id")):
return
await _on_follow(activity, headers)
async def on_undo(activity: dict, headers: dict) -> None:
if await _dedup_activity(activity.get("id")):
return
await _on_undo(activity, headers)
return make_inbox_router(
handlers={"Follow": on_follow, "Undo": on_undo},
verify_key_fetcher=None, # Signature verification enabled in prod when actor is loaded
path="/inbox",
)
# Mount inbox at /ap/actor/inbox (AP spec: inbox is a sub-resource of the actor)
try:
_inbox_sub = _build_inbox_router()
ap_router.include_router(_inbox_sub, prefix="/actor")
except Exception as _e:
logger.warning("AP inbox router not available: %s", _e)
# ── Outbox ────────────────────────────────────────────────────────────────────
@ap_router.get("/outbox")
async def get_outbox(page: int | None = None, request: Request = None):
actor = _actor_required()
from app.api.endpoints.community import _get_community_store
store = _get_community_store()
base = f"https://{settings.AP_HOST}"
if store is None:
collection = {
"@context": "https://www.w3.org/ns/activitystreams",
"id": f"{actor.outbox_url}",
"type": "OrderedCollection",
"totalItems": 0,
"orderedItems": [],
}
return Response(content=json.dumps(collection), media_type=_AP_CONTENT_TYPE)
PAGE_SIZE = 20
offset = ((page or 1) - 1) * PAGE_SIZE
posts = await asyncio.to_thread(store.list_posts, limit=PAGE_SIZE, offset=offset)
items = [_post_to_ap_note(p, actor, base) for p in posts]
collection = {
"@context": "https://www.w3.org/ns/activitystreams",
"id": actor.outbox_url + (f"?page={page}" if page else ""),
"type": "OrderedCollectionPage" if page else "OrderedCollection",
"orderedItems": items,
}
return Response(content=json.dumps(collection), media_type=_AP_CONTENT_TYPE)
# ── Individual post ───────────────────────────────────────────────────────────
@ap_router.get("/posts/{slug}")
async def get_ap_post(slug: str):
actor = _actor_required()
from app.api.endpoints.community import _get_community_store
store = _get_community_store()
if store is None:
raise HTTPException(status_code=404, detail="Community DB not available.")
post = await asyncio.to_thread(store.get_post_by_slug, slug)
if post is None:
raise HTTPException(status_code=404, detail="Post not found.")
base = f"https://{settings.AP_HOST}"
note = _post_to_ap_note(post, actor, base)
return Response(content=json.dumps(note), media_type=_AP_CONTENT_TYPE)
# ── Followers / Following ─────────────────────────────────────────────────────
@ap_router.get("/followers")
async def get_followers():
actor = _actor_required()
import sqlite3
count = 0
try:
conn = sqlite3.connect(str(settings.DB_PATH))
row = conn.execute("SELECT COUNT(*) FROM ap_followers WHERE active = 1").fetchone()
conn.close()
count = row[0] if row else 0
except Exception:
pass
collection = {
"@context": "https://www.w3.org/ns/activitystreams",
"id": f"{actor.actor_id}/followers",
"type": "OrderedCollection",
"totalItems": count,
}
return Response(content=json.dumps(collection), media_type=_AP_CONTENT_TYPE)
@ap_router.get("/following")
async def get_following():
actor = _actor_required()
collection = {
"@context": "https://www.w3.org/ns/activitystreams",
"id": f"{actor.actor_id}/following",
"type": "OrderedCollection",
"totalItems": 0,
"orderedItems": [],
}
return Response(content=json.dumps(collection), media_type=_AP_CONTENT_TYPE)
# ── Helpers ───────────────────────────────────────────────────────────────────
def _post_to_ap_note(post, actor, base_url: str) -> dict:
from circuitforge_core.activitypub import make_note
from app.services.community.ap_compat import _build_content
diet_tags: list[str] = list(getattr(post, "dietary_tags", []) or [])
hashtags = [{"type": "Hashtag", "name": "#Kiwi", "href": f"{base_url}/ap/tags/kiwi"}]
for tag in diet_tags[:4]:
ht = "".join(w.capitalize() for w in tag.replace("-", " ").split())
hashtags.append({"type": "Hashtag", "name": f"#{ht}"})
content = _build_content(
{
"title": post.title,
"description": getattr(post, "description", None),
"outcome_notes": getattr(post, "outcome_notes", None),
"dietary_tags": diet_tags,
}
)
published = post.published
note = make_note(
actor_id=actor.actor_id,
content=content,
tag=hashtags,
published=published if isinstance(published, datetime) else None,
)
note["id"] = f"{base_url}/ap/posts/{post.slug}"
return note
def _resolve_inbox(actor_url: str) -> tuple[str | None, str | None]:
"""Fetch an AP actor document and extract inbox + sharedInbox URLs."""
try:
import httpx
resp = httpx.get(
actor_url,
headers={"Accept": "application/activity+json"},
timeout=8.0,
follow_redirects=True,
)
resp.raise_for_status()
doc = resp.json()
inbox = doc.get("inbox")
shared = doc.get("endpoints", {}).get("sharedInbox")
return inbox, shared
except Exception as exc:
logger.debug("Could not resolve actor %s: %s", actor_url, exc)
return None, None

View file

@ -1,444 +0,0 @@
# app/api/endpoints/community.py
# MIT License
from __future__ import annotations
import asyncio
import logging
import re
import sqlite3
from datetime import datetime, timezone
from fastapi import APIRouter, Depends, HTTPException, Request, Response
from app.cloud_session import CloudUser, get_session
from app.core.config import settings
from app.db.store import Store
from app.services.community.feed import posts_to_rss
logger = logging.getLogger(__name__)
router = APIRouter(prefix="/community", tags=["community"])
_community_store = None
def _get_community_store():
return _community_store
def init_community_store(community_db_url: str | None) -> None:
global _community_store
if not community_db_url:
logger.info(
"COMMUNITY_DB_URL not set — community write features disabled. "
"Browse still works via cloud feed."
)
return
from circuitforge_core.community import CommunityDB
from app.services.community.community_store import KiwiCommunityStore
db = CommunityDB(dsn=community_db_url)
db.run_migrations()
_community_store = KiwiCommunityStore(db)
logger.info("Community store initialized.")
def _visible(post, session=None) -> bool:
"""Return False for premium-tier posts when the session is not paid/premium."""
tier = getattr(post, "tier", None)
if tier == "premium":
if session is None or getattr(session, "tier", None) not in ("paid", "premium"):
return False
return True
@router.get("/posts")
async def list_posts(
post_type: str | None = None,
dietary_tags: str | None = None,
allergen_exclude: str | None = None,
page: int = 1,
page_size: int = 20,
):
store = _get_community_store()
if store is None:
return {
"posts": [],
"total": 0,
"page": page,
"page_size": page_size,
"note": "Community DB not available on this instance.",
}
dietary = [t.strip() for t in dietary_tags.split(",")] if dietary_tags else None
allergen_ex = [t.strip() for t in allergen_exclude.split(",")] if allergen_exclude else None
offset = (page - 1) * min(page_size, 100)
posts = await asyncio.to_thread(
store.list_posts,
limit=min(page_size, 100),
offset=offset,
post_type=post_type,
dietary_tags=dietary,
allergen_exclude=allergen_ex,
)
visible = [_post_to_dict(p) for p in posts if _visible(p)]
return {"posts": visible, "total": len(visible), "page": page, "page_size": page_size}
@router.get("/posts/{slug}")
async def get_post(slug: str, request: Request):
store = _get_community_store()
if store is None:
raise HTTPException(status_code=503, detail="Community DB not available on this instance.")
post = await asyncio.to_thread(store.get_post_by_slug, slug)
if post is None:
raise HTTPException(status_code=404, detail="Post not found.")
accept = request.headers.get("accept", "")
if "application/activity+json" in accept or "application/ld+json" in accept:
from app.services.community.ap_compat import post_to_ap_json_ld
base_url = str(request.base_url).rstrip("/")
return post_to_ap_json_ld(_post_to_dict(post), base_url=base_url)
return _post_to_dict(post)
@router.get("/feed.rss")
async def get_rss_feed(request: Request):
store = _get_community_store()
posts_data: list[dict] = []
if store is not None:
posts = await asyncio.to_thread(store.list_posts, limit=50)
posts_data = [_post_to_dict(p) for p in posts]
base_url = str(request.base_url).rstrip("/")
rss = posts_to_rss(posts_data, base_url=base_url)
return Response(content=rss, media_type="application/rss+xml; charset=utf-8")
@router.get("/local-feed")
async def local_feed():
store = _get_community_store()
if store is None:
return []
posts = await asyncio.to_thread(store.list_posts, limit=50)
return [_post_to_dict(p) for p in posts]
@router.get("/hall-of-chaos")
async def hall_of_chaos():
"""Hidden easter egg endpoint -- returns the 10 most chaotic bloopers."""
store = _get_community_store()
if store is None:
return {"posts": [], "chaos_level": 0}
posts = await asyncio.to_thread(
store.list_posts, limit=10, post_type="recipe_blooper"
)
return {
"posts": [_post_to_dict(p) for p in posts],
"chaos_level": len(posts),
}
_VALID_POST_TYPES = {"plan", "recipe_success", "recipe_blooper"}
_MAX_TITLE_LEN = 200
_MAX_TEXT_LEN = 2000
def _validate_publish_body(body: dict) -> None:
"""Raise HTTPException(422) for any invalid fields in a publish request."""
post_type = body.get("post_type", "plan")
if post_type not in _VALID_POST_TYPES:
raise HTTPException(
status_code=422,
detail=f"post_type must be one of: {', '.join(sorted(_VALID_POST_TYPES))}",
)
title = body.get("title") or ""
if len(title) > _MAX_TITLE_LEN:
raise HTTPException(status_code=422, detail=f"title exceeds {_MAX_TITLE_LEN} character limit.")
for field in ("description", "outcome_notes", "recipe_name"):
value = body.get(field)
if value and len(str(value)) > _MAX_TEXT_LEN:
raise HTTPException(status_code=422, detail=f"{field} exceeds {_MAX_TEXT_LEN} character limit.")
photo_url = body.get("photo_url")
if photo_url and not str(photo_url).startswith("https://"):
raise HTTPException(status_code=422, detail="photo_url must be an https:// URL.")
@router.post("/check-similar")
async def check_similar(body: dict, session: CloudUser = Depends(get_session)):
"""Pre-submission dedup check: return similar existing posts for the given title/recipe_id.
Safe to call with no community store configured returns empty list rather than 503.
"""
store = _get_community_store()
if store is None:
return {"similar_posts": []}
title = (body.get("title") or "").strip()
recipe_id = body.get("recipe_id")
post_type = body.get("post_type")
if not title:
return {"similar_posts": []}
candidates = await asyncio.to_thread(
store.search_similar_posts,
title,
recipe_id,
post_type,
8,
)
if not candidates:
return {"similar_posts": []}
from app.services.community.dedup import build_similar_post_result, fetch_recipe_ingredients
incoming_ingredients = await asyncio.to_thread(
fetch_recipe_ingredients, session.db, recipe_id
)
results = []
for post in candidates:
result = await asyncio.to_thread(
build_similar_post_result,
post,
recipe_id,
incoming_ingredients,
session.db,
)
if result["similarity_tier"] != "different":
results.append(result)
return {"similar_posts": results[:5]}
@router.post("/posts", status_code=201)
async def publish_post(body: dict, session: CloudUser = Depends(get_session)):
from app.tiers import can_use
if not can_use("community_publish", session.tier, session.has_byok):
raise HTTPException(status_code=402, detail="Community publishing requires Paid tier.")
_validate_publish_body(body)
store = _get_community_store()
if store is None:
raise HTTPException(
status_code=503,
detail="This Kiwi instance is not connected to a community database. "
"Publishing is only available on cloud instances.",
)
from app.services.community.community_store import get_or_create_pseudonym
def _get_pseudonym():
s = Store(session.db)
try:
return get_or_create_pseudonym(
store=s,
directus_user_id=session.user_id,
requested_name=body.get("pseudonym_name"),
)
finally:
s.close()
try:
pseudonym = await asyncio.to_thread(_get_pseudonym)
except ValueError as exc:
raise HTTPException(status_code=422, detail=str(exc)) from exc
recipe_ids = [slot["recipe_id"] for slot in body.get("slots", []) if slot.get("recipe_id")]
from app.services.community.element_snapshot import compute_snapshot
def _snapshot():
s = Store(session.db)
try:
return compute_snapshot(recipe_ids=recipe_ids, store=s)
finally:
s.close()
snapshot = await asyncio.to_thread(_snapshot)
post_type = body.get("post_type", "plan")
slug_title = re.sub(r"[^a-z0-9]+", "-", (body.get("title") or "plan").lower()).strip("-")
today = datetime.now(timezone.utc).strftime("%Y-%m-%d")
slug = f"kiwi-{_post_type_prefix(post_type)}-{pseudonym.lower().replace(' ', '')}-{today}-{slug_title}"[:120]
similar_to_ref = body.get("similar_to_ref") or None
from circuitforge_core.community.models import CommunityPost
post = CommunityPost(
slug=slug,
pseudonym=pseudonym,
post_type=post_type,
published=datetime.now(timezone.utc),
title=(body.get("title") or "Untitled")[:_MAX_TITLE_LEN],
description=body.get("description"),
photo_url=body.get("photo_url"),
slots=body.get("slots", []),
recipe_id=body.get("recipe_id"),
recipe_name=body.get("recipe_name"),
level=body.get("level"),
outcome_notes=body.get("outcome_notes"),
seasoning_score=snapshot.seasoning_score,
richness_score=snapshot.richness_score,
brightness_score=snapshot.brightness_score,
depth_score=snapshot.depth_score,
aroma_score=snapshot.aroma_score,
structure_score=snapshot.structure_score,
texture_profile=snapshot.texture_profile,
dietary_tags=list(snapshot.dietary_tags),
allergen_flags=list(snapshot.allergen_flags),
flavor_molecules=list(snapshot.flavor_molecules),
fat_pct=snapshot.fat_pct,
protein_pct=snapshot.protein_pct,
moisture_pct=snapshot.moisture_pct,
similar_to_ref=similar_to_ref,
)
try:
inserted = await asyncio.to_thread(store.insert_post, post)
except sqlite3.IntegrityError as exc:
raise HTTPException(
status_code=409,
detail="A post with this title already exists today. Try a different title.",
) from exc
post_dict = _post_to_dict(inserted)
# AP delivery + Mastodon post (Paid tier, AP_ENABLED, opted-in)
from app.core.config import settings as _settings
if _settings.AP_ENABLED and session.tier in ("paid", "premium", "ultra"):
from circuitforge_core.activitypub import make_create, make_note, PUBLIC
from app.services.ap.keys import get_actor
from app.services.ap.delivery import deliver_to_followers
_ap_actor = get_actor()
if _ap_actor is not None:
base = f"https://{_settings.AP_HOST}"
from app.api.endpoints.activitypub import _post_to_ap_note
_note = _post_to_ap_note(inserted, _ap_actor, base)
_activity = make_create(_ap_actor, _note)
asyncio.create_task(
asyncio.to_thread(
deliver_to_followers, inserted.slug, _activity, session.db
)
)
# Mastodon post if user has connected account and opted in
if body.get("post_to_mastodon"):
from app.services.ap.mastodon import build_post_content, get_token, post_status
_masto = await asyncio.to_thread(
get_token, session.db, session.user_id, _settings.AP_TOKEN_ENCRYPTION_KEY
)
if _masto:
_masto_url, _masto_token = _masto
_content = build_post_content(post_dict)
asyncio.create_task(
asyncio.to_thread(post_status, _masto_url, _masto_token, _content)
)
return post_dict
@router.delete("/posts/{slug}", status_code=204)
async def delete_post(slug: str, session: CloudUser = Depends(get_session)):
store = _get_community_store()
if store is None:
raise HTTPException(status_code=503, detail="Community DB not available.")
def _get_pseudonym():
s = Store(session.db)
try:
return s.get_current_pseudonym(session.user_id)
finally:
s.close()
pseudonym = await asyncio.to_thread(_get_pseudonym)
if not pseudonym:
raise HTTPException(status_code=400, detail="No pseudonym set. Cannot delete posts.")
deleted = await asyncio.to_thread(store.delete_post, slug=slug, pseudonym=pseudonym)
if not deleted:
raise HTTPException(status_code=404, detail="Post not found or you are not the author.")
@router.post("/posts/{slug}/fork", status_code=201)
async def fork_post(slug: str, session: CloudUser = Depends(get_session)):
store = _get_community_store()
if store is None:
raise HTTPException(status_code=503, detail="Community DB not available.")
post = await asyncio.to_thread(store.get_post_by_slug, slug)
if post is None:
raise HTTPException(status_code=404, detail="Post not found.")
if post.post_type != "plan":
raise HTTPException(status_code=400, detail="Only plan posts can be forked as a meal plan.")
required_slot_keys = {"day", "meal_type", "recipe_id"}
if any(not required_slot_keys.issubset(slot) for slot in post.slots):
raise HTTPException(status_code=400, detail="Post contains malformed slots and cannot be forked.")
from datetime import date
week_start = date.today().strftime("%Y-%m-%d")
def _create_plan():
s = Store(session.db)
try:
meal_types = list({slot["meal_type"] for slot in post.slots})
plan = s.create_meal_plan(week_start=week_start, meal_types=meal_types or ["dinner"])
for slot in post.slots:
s.assign_recipe_to_slot(
plan_id=plan["id"],
day_of_week=slot["day"],
meal_type=slot["meal_type"],
recipe_id=slot["recipe_id"],
)
return plan
finally:
s.close()
plan = await asyncio.to_thread(_create_plan)
return {"plan_id": plan["id"], "week_start": plan["week_start"], "forked_from": slug}
@router.post("/posts/{slug}/fork-adapt", status_code=201)
async def fork_adapt_post(slug: str, session: CloudUser = Depends(get_session)):
from app.tiers import can_use
if not can_use("community_fork_adapt", session.tier, session.has_byok):
raise HTTPException(status_code=402, detail="Fork with adaptation requires Paid tier or BYOK.")
# Stub: full LLM adaptation deferred
raise HTTPException(status_code=501, detail="Fork-adapt not yet implemented.")
def _post_to_dict(post) -> dict:
return {
"slug": post.slug,
"pseudonym": post.pseudonym,
"post_type": post.post_type,
"published": post.published.isoformat() if hasattr(post.published, "isoformat") else str(post.published),
"title": post.title,
"description": post.description,
"photo_url": post.photo_url,
"slots": list(post.slots),
"recipe_id": post.recipe_id,
"recipe_name": post.recipe_name,
"level": post.level,
"outcome_notes": post.outcome_notes,
"element_profiles": {
"seasoning_score": post.seasoning_score,
"richness_score": post.richness_score,
"brightness_score": post.brightness_score,
"depth_score": post.depth_score,
"aroma_score": post.aroma_score,
"structure_score": post.structure_score,
"texture_profile": post.texture_profile,
},
"dietary_tags": list(post.dietary_tags),
"allergen_flags": list(post.allergen_flags),
"flavor_molecules": list(post.flavor_molecules),
"fat_pct": post.fat_pct,
"protein_pct": post.protein_pct,
"moisture_pct": post.moisture_pct,
"similar_to_ref": getattr(post, "similar_to_ref", None),
}
def _post_type_prefix(post_type: str) -> str:
return {"plan": "plan", "recipe_success": "success", "recipe_blooper": "blooper"}.get(post_type, "post")

View file

@ -1,5 +0,0 @@
# app/api/endpoints/corrections.py — user corrections to LLM output for SFT training
from circuitforge_core.api import make_corrections_router
from app.db.session import get_db
router = make_corrections_router(get_db=get_db, product="kiwi")

View file

@ -1,11 +1,9 @@
"""Export endpoints — CSV and JSON export of user data.""" """Export endpoints — CSV/Excel of receipt and inventory data."""
from __future__ import annotations from __future__ import annotations
import asyncio import asyncio
import csv import csv
import io import io
import json
from datetime import datetime, timezone
from fastapi import APIRouter, Depends from fastapi import APIRouter, Depends
from fastapi.responses import StreamingResponse from fastapi.responses import StreamingResponse
@ -47,33 +45,3 @@ async def export_inventory_csv(store: Store = Depends(get_store)):
media_type="text/csv", media_type="text/csv",
headers={"Content-Disposition": "attachment; filename=inventory.csv"}, headers={"Content-Disposition": "attachment; filename=inventory.csv"},
) )
@router.get("/json")
async def export_full_json(store: Store = Depends(get_store)):
"""Export full pantry inventory + saved recipes as a single JSON file.
Intended for data portability users can import this into another
Kiwi instance or keep it as an offline backup.
"""
inventory, saved = await asyncio.gather(
asyncio.to_thread(store.list_inventory),
asyncio.to_thread(store.get_saved_recipes),
)
export_doc = {
"kiwi_export": {
"version": "1.0",
"exported_at": datetime.now(timezone.utc).isoformat(),
"inventory": [dict(row) for row in inventory],
"saved_recipes": [dict(row) for row in saved],
}
}
body = json.dumps(export_doc, default=str, indent=2)
filename = f"kiwi-export-{datetime.now(timezone.utc).strftime('%Y%m%d')}.json"
return StreamingResponse(
iter([body]),
media_type="application/json",
headers={"Content-Disposition": f"attachment; filename={filename}"},
)

View file

@ -1,103 +0,0 @@
"""Screenshot attachment endpoint for in-app feedback.
After the cf-core feedback router creates a Forgejo issue, the frontend
can call POST /feedback/attach to upload a screenshot and pin it as a
comment on that issue.
The endpoint is separate from the cf-core router so Kiwi owns it
without modifying shared infrastructure.
"""
from __future__ import annotations
import base64
import os
import requests
from fastapi import APIRouter, HTTPException
from pydantic import BaseModel, Field
router = APIRouter()
_FORGEJO_BASE = os.environ.get(
"FORGEJO_API_URL", "https://git.opensourcesolarpunk.com/api/v1"
)
_REPO = "Circuit-Forge/kiwi"
_MAX_BYTES = 5 * 1024 * 1024 # 5 MB
class AttachRequest(BaseModel):
issue_number: int
filename: str = Field(default="screenshot.png", max_length=80)
image_b64: str # data URI or raw base64
class AttachResponse(BaseModel):
comment_url: str
def _forgejo_headers() -> dict[str, str]:
token = os.environ.get("FORGEJO_API_TOKEN", "")
return {"Authorization": f"token {token}"}
def _decode_image(image_b64: str) -> tuple[bytes, str]:
"""Return (raw_bytes, mime_type) from a base64 string or data URI."""
if image_b64.startswith("data:"):
header, _, data = image_b64.partition(",")
mime = header.split(";")[0].split(":")[1] if ":" in header else "image/png"
else:
data = image_b64
mime = "image/png"
return base64.b64decode(data), mime
@router.post("/attach", response_model=AttachResponse)
def attach_screenshot(payload: AttachRequest) -> AttachResponse:
"""Upload a screenshot to a Forgejo issue as a comment with embedded image.
The image is uploaded as an issue asset, then referenced in a comment
so it is visible inline when the issue is viewed.
"""
token = os.environ.get("FORGEJO_API_TOKEN", "")
if not token:
raise HTTPException(status_code=503, detail="Feedback not configured.")
raw_bytes, mime = _decode_image(payload.image_b64)
if len(raw_bytes) > _MAX_BYTES:
raise HTTPException(
status_code=413,
detail=f"Screenshot exceeds 5 MB limit ({len(raw_bytes) // 1024} KB received).",
)
# Upload image as issue asset
asset_resp = requests.post(
f"{_FORGEJO_BASE}/repos/{_REPO}/issues/{payload.issue_number}/assets",
headers=_forgejo_headers(),
files={"attachment": (payload.filename, raw_bytes, mime)},
timeout=20,
)
if not asset_resp.ok:
raise HTTPException(
status_code=502,
detail=f"Forgejo asset upload failed: {asset_resp.text[:200]}",
)
asset_url = asset_resp.json().get("browser_download_url", "")
# Pin as a comment so the image is visible inline
comment_body = f"**Screenshot attached by reporter:**\n\n![screenshot]({asset_url})"
comment_resp = requests.post(
f"{_FORGEJO_BASE}/repos/{_REPO}/issues/{payload.issue_number}/comments",
headers={**_forgejo_headers(), "Content-Type": "application/json"},
json={"body": comment_body},
timeout=15,
)
if not comment_resp.ok:
raise HTTPException(
status_code=502,
detail=f"Forgejo comment failed: {comment_resp.text[:200]}",
)
comment_url = comment_resp.json().get("html_url", "")
return AttachResponse(comment_url=comment_url)

View file

@ -11,8 +11,7 @@ import sqlite3
import requests import requests
from fastapi import APIRouter, Depends, HTTPException from fastapi import APIRouter, Depends, HTTPException
from app.cloud_session import CloudUser, CLOUD_DATA_ROOT, get_session from app.cloud_session import CloudUser, CLOUD_DATA_ROOT, HEIMDALL_URL, HEIMDALL_ADMIN_TOKEN, get_session
from app.services.heimdall_orch import HEIMDALL_URL, HEIMDALL_ADMIN_TOKEN
from app.db.store import Store from app.db.store import Store
from app.models.schemas.household import ( from app.models.schemas.household import (
HouseholdAcceptRequest, HouseholdAcceptRequest,
@ -129,18 +128,15 @@ async def household_status(session: CloudUser = Depends(_require_premium)):
@router.post("/invite", response_model=HouseholdInviteResponse) @router.post("/invite", response_model=HouseholdInviteResponse)
async def create_invite(session: CloudUser = Depends(_require_household_owner)): async def create_invite(session: CloudUser = Depends(_require_household_owner)):
"""Generate a one-time invite token valid for 7 days.""" """Generate a one-time invite token valid for 7 days."""
store = Store(session.db)
token = secrets.token_hex(32) token = secrets.token_hex(32)
expires_at = (datetime.now(timezone.utc) + timedelta(days=_INVITE_TTL_DAYS)).isoformat() expires_at = (datetime.now(timezone.utc) + timedelta(days=_INVITE_TTL_DAYS)).isoformat()
store = Store(session.db)
try:
store.conn.execute( store.conn.execute(
"""INSERT INTO household_invites (token, household_id, created_by, expires_at) """INSERT INTO household_invites (token, household_id, created_by, expires_at)
VALUES (?, ?, ?, ?)""", VALUES (?, ?, ?, ?)""",
(token, session.household_id, session.user_id, expires_at), (token, session.household_id, session.user_id, expires_at),
) )
store.conn.commit() store.conn.commit()
finally:
store.close()
invite_url = f"{_KIWI_BASE_URL}/#/join?household_id={session.household_id}&token={token}" invite_url = f"{_KIWI_BASE_URL}/#/join?household_id={session.household_id}&token={token}"
return HouseholdInviteResponse(token=token, invite_url=invite_url, expires_at=expires_at) return HouseholdInviteResponse(token=token, invite_url=invite_url, expires_at=expires_at)
@ -156,7 +152,6 @@ async def accept_invite(
hh_store = _household_store(body.household_id) hh_store = _household_store(body.household_id)
now = datetime.now(timezone.utc).isoformat() now = datetime.now(timezone.utc).isoformat()
try:
row = hh_store.conn.execute( row = hh_store.conn.execute(
"""SELECT token, expires_at, used_at FROM household_invites """SELECT token, expires_at, used_at FROM household_invites
WHERE token = ? AND household_id = ?""", WHERE token = ? AND household_id = ?""",
@ -175,8 +170,6 @@ async def accept_invite(
(now, session.user_id, body.token), (now, session.user_id, body.token),
) )
hh_store.conn.commit() hh_store.conn.commit()
finally:
hh_store.close()
_heimdall_post("/admin/household/add-member", { _heimdall_post("/admin/household/add-member", {
"household_id": body.household_id, "household_id": body.household_id,

View file

@ -1,185 +0,0 @@
"""Kiwi — /api/v1/imitate/samples endpoint for Avocet Imitate tab.
Returns the actual assembled prompt Kiwi sends to its LLM for recipe generation,
including the full pantry context (expiry-first ordering), dietary constraints
(from user_settings if present), and the Level 3 format instructions.
"""
from __future__ import annotations
from fastapi import APIRouter, Depends
from app.cloud_session import get_session, CloudUser
from app.db.store import Store
router = APIRouter()
_LEVEL3_FORMAT = [
"",
"Reply using EXACTLY this plain-text format — no markdown, no bold, no extra commentary:",
"Title: <name of the dish>",
"Ingredients: <comma-separated list>",
"Directions:",
"1. <first step>",
"2. <second step>",
"3. <continue for each step>",
"Notes: <optional tips>",
]
_LEVEL4_FORMAT = [
"",
"Reply using EXACTLY this plain-text format — no markdown, no bold:",
"Title: <name of the dish>",
"Ingredients: <comma-separated list>",
"Directions:",
"1. <first step>",
"2. <second step>",
"Notes: <optional tips>",
]
def _read_user_settings(store: Store) -> dict:
"""Read all key/value pairs from user_settings table."""
try:
rows = store.conn.execute("SELECT key, value FROM user_settings").fetchall()
return {r["key"]: r["value"] for r in rows}
except Exception:
return {}
def _build_recipe_prompt(
pantry_names: list[str],
expiring_names: list[str],
constraints: list[str],
allergies: list[str],
level: int = 3,
) -> str:
"""Assemble the recipe generation prompt matching Kiwi's Level 3/4 format."""
# Expiring items first, then remaining pantry items (deduped)
expiring_set = set(expiring_names)
ordered = list(expiring_names) + [n for n in pantry_names if n not in expiring_set]
if not ordered:
ordered = pantry_names
if level == 4:
lines = [
"Surprise me with a creative, unexpected recipe.",
"Only use ingredients that make culinary sense together. "
"Do not force flavoured/sweetened items (vanilla yoghurt, flavoured syrups, jam) into savoury dishes.",
f"Ingredients available: {', '.join(ordered)}",
]
if constraints:
lines.append(f"Constraints: {', '.join(constraints)}")
if allergies:
lines.append(f"Must NOT contain: {', '.join(allergies)}")
lines.append("Treat any mystery ingredient as a wildcard — use your imagination.")
lines += _LEVEL4_FORMAT
else:
lines = [
"You are a creative chef. Generate a recipe using the ingredients below.",
"IMPORTANT: When you use a pantry item, list it in Ingredients using its exact name "
"from the pantry list. Do not add adjectives, quantities, or cooking states "
"(e.g. use 'butter', not 'unsalted butter' or '2 tbsp butter').",
"IMPORTANT: Only use pantry items that make culinary sense for the dish. "
"Do NOT force flavoured/sweetened items (vanilla yoghurt, fruit yoghurt, jam, "
"dessert sauces, flavoured syrups) into savoury dishes.",
"IMPORTANT: Do not default to the same ingredient repeatedly across dishes. "
"If a pantry item does not genuinely improve this specific dish, leave it out.",
"",
f"Pantry items: {', '.join(ordered)}",
]
if expiring_names:
lines.append(
f"Priority — use these soon (expiring): {', '.join(expiring_names)}"
)
if constraints:
lines.append(f"Dietary constraints: {', '.join(constraints)}")
if allergies:
lines.append(f"IMPORTANT — must NOT contain: {', '.join(allergies)}")
lines += _LEVEL3_FORMAT
return "\n".join(lines)
@router.get("/samples")
async def imitate_samples(
limit: int = 5,
level: int = 3,
session: CloudUser = Depends(get_session),
):
"""Return assembled recipe generation prompts for Avocet's Imitate tab.
Each sample includes:
system_prompt empty (Kiwi uses no system context)
input_text full Level 3/4 prompt with pantry items, expiring items,
dietary constraints, and format instructions
output_text empty (no prior LLM output stored per-request)
level: 3 (structured with element biasing context) or 4 (wildcard creative)
limit: max number of distinct prompt variants to return (varies by pantry state)
"""
limit = max(1, min(limit, 10))
store = Store(session.db)
# Full pantry for context
all_items = store.list_inventory()
pantry_names = [r["product_name"] for r in all_items if r.get("product_name")]
# Expiring items as priority ingredients
expiring = store.expiring_soon(days=14)
expiring_names = [r["product_name"] for r in expiring if r.get("product_name")]
# Dietary constraints from user_settings (keys: constraints, allergies)
settings = _read_user_settings(store)
import json as _json
try:
constraints = _json.loads(settings.get("dietary_constraints", "[]")) or []
except Exception:
constraints = []
try:
allergies = _json.loads(settings.get("dietary_allergies", "[]")) or []
except Exception:
allergies = []
if not pantry_names:
return {"samples": [], "total": 0, "type": f"recipe_level{level}"}
# Build prompt variants: one per expiring item as the "anchor" ingredient,
# plus one general pantry prompt. Cap at limit.
samples = []
seen_anchors: set[str] = set()
for item in (expiring[:limit - 1] if expiring else []):
anchor = item.get("product_name", "")
if not anchor or anchor in seen_anchors:
continue
seen_anchors.add(anchor)
# Put this item first in the list for the prompt
ordered_expiring = [anchor] + [n for n in expiring_names if n != anchor]
prompt = _build_recipe_prompt(pantry_names, ordered_expiring, constraints, allergies, level)
samples.append({
"id": item.get("id", 0),
"anchor_item": anchor,
"expiring_count": len(expiring_names),
"pantry_count": len(pantry_names),
"system_prompt": "",
"input_text": prompt,
"output_text": "",
})
# One general prompt using all expiring as priority
if len(samples) < limit:
prompt = _build_recipe_prompt(pantry_names, expiring_names, constraints, allergies, level)
samples.append({
"id": 0,
"anchor_item": "full pantry",
"expiring_count": len(expiring_names),
"pantry_count": len(pantry_names),
"system_prompt": "",
"input_text": prompt,
"output_text": "",
})
return {"samples": samples, "total": len(samples), "type": f"recipe_level{level}"}

View file

@ -3,7 +3,6 @@
from __future__ import annotations from __future__ import annotations
import asyncio import asyncio
import logging
import uuid import uuid
from pathlib import Path from pathlib import Path
from typing import Any, Dict, List, Optional from typing import Any, Dict, List, Optional
@ -12,73 +11,28 @@ import aiofiles
from fastapi import APIRouter, Depends, File, Form, HTTPException, UploadFile, status from fastapi import APIRouter, Depends, File, Form, HTTPException, UploadFile, status
from pydantic import BaseModel from pydantic import BaseModel
from app.cloud_session import CloudUser, _auth_label, get_session from app.cloud_session import CloudUser, get_session
log = logging.getLogger(__name__)
from app.db.session import get_store from app.db.session import get_store
from app.services.expiration_predictor import ExpirationPredictor
_predictor = ExpirationPredictor()
from app.db.store import Store from app.db.store import Store
from app.models.schemas.inventory import ( from app.models.schemas.inventory import (
BarcodeScanResponse, BarcodeScanResponse,
BulkAddByNameRequest, BulkAddByNameRequest,
BulkAddByNameResponse, BulkAddByNameResponse,
BulkAddItemResult, BulkAddItemResult,
DiscardRequest,
InventoryItemCreate, InventoryItemCreate,
InventoryItemResponse, InventoryItemResponse,
InventoryItemUpdate, InventoryItemUpdate,
InventoryStats, InventoryStats,
PartialConsumeRequest,
ProductCreate, ProductCreate,
ProductResponse, ProductResponse,
ProductUpdate, ProductUpdate,
TagCreate, TagCreate,
TagResponse, TagResponse,
) )
from app.models.schemas.label_capture import LabelConfirmRequest
router = APIRouter() router = APIRouter()
# ── Helpers ───────────────────────────────────────────────────────────────────
def _user_constraints(store) -> list[str]:
"""Load active dietary constraints from user settings (comma-separated string)."""
raw = store.get_setting("dietary_constraints") or ""
return [c.strip() for c in raw.split(",") if c.strip()]
def _enrich_item(item: dict, user_constraints: list[str] | None = None) -> dict:
"""Attach computed fields: opened_expiry_date, secondary_state/uses/warning/discard_signs."""
from datetime import date, timedelta
opened = item.get("opened_date")
if opened:
days = _predictor.days_after_opening(item.get("category"))
if days is not None:
try:
opened_expiry = date.fromisoformat(opened) + timedelta(days=days)
item = {**item, "opened_expiry_date": str(opened_expiry)}
except ValueError:
pass
if "opened_expiry_date" not in item:
item = {**item, "opened_expiry_date": None}
# Secondary use window — check sell-by date (not opened expiry).
# Apply dietary constraint filter (e.g. wine suppressed for halal/alcohol-free).
sec = _predictor.secondary_state(item.get("category"), item.get("expiration_date"))
sec = _predictor.filter_secondary_by_constraints(sec, user_constraints or [])
item = {
**item,
"secondary_state": sec["label"] if sec else None,
"secondary_uses": sec["uses"] if sec else None,
"secondary_warning": sec["warning"] if sec else None,
"secondary_discard_signs": sec["discard_signs"] if sec else None,
}
return item
# ── Products ────────────────────────────────────────────────────────────────── # ── Products ──────────────────────────────────────────────────────────────────
@router.post("/products", response_model=ProductResponse, status_code=status.HTTP_201_CREATED) @router.post("/products", response_model=ProductResponse, status_code=status.HTTP_201_CREATED)
@ -163,12 +117,7 @@ async def delete_product(product_id: int, store: Store = Depends(get_store)):
# ── Inventory items ─────────────────────────────────────────────────────────── # ── Inventory items ───────────────────────────────────────────────────────────
@router.post("/items", response_model=InventoryItemResponse, status_code=status.HTTP_201_CREATED) @router.post("/items", response_model=InventoryItemResponse, status_code=status.HTTP_201_CREATED)
async def create_inventory_item( async def create_inventory_item(body: InventoryItemCreate, store: Store = Depends(get_store)):
body: InventoryItemCreate,
store: Store = Depends(get_store),
session: CloudUser = Depends(get_session),
):
log.info("add_item auth=%s tier=%s product_id=%s", _auth_label(session.user_id), session.tier, body.product_id)
item = await asyncio.to_thread( item = await asyncio.to_thread(
store.add_inventory_item, store.add_inventory_item,
body.product_id, body.product_id,
@ -181,10 +130,7 @@ async def create_inventory_item(
notes=body.notes, notes=body.notes,
source=body.source, source=body.source,
) )
# RETURNING * omits joined columns (product_name, barcode, category). return InventoryItemResponse.model_validate(item)
# Re-fetch with the products JOIN so the response is fully populated (#99).
full_item = await asyncio.to_thread(store.get_inventory_item, item["id"])
return InventoryItemResponse.model_validate(full_item)
@router.post("/items/bulk-add-by-name", response_model=BulkAddByNameResponse) @router.post("/items/bulk-add-by-name", response_model=BulkAddByNameResponse)
@ -197,7 +143,7 @@ async def bulk_add_items_by_name(body: BulkAddByNameRequest, store: Store = Depe
for entry in body.items: for entry in body.items:
try: try:
product, _ = await asyncio.to_thread( product, _ = await asyncio.to_thread(
store.get_or_create_product, entry.name, None, source="manual" store.get_or_create_product, entry.name, None, source="shopping"
) )
item = await asyncio.to_thread( item = await asyncio.to_thread(
store.add_inventory_item, store.add_inventory_item,
@ -205,7 +151,7 @@ async def bulk_add_items_by_name(body: BulkAddByNameRequest, store: Store = Depe
entry.location, entry.location,
quantity=entry.quantity, quantity=entry.quantity,
unit=entry.unit, unit=entry.unit,
source="manual", source="shopping",
) )
results.append(BulkAddItemResult(name=entry.name, ok=True, item_id=item["id"])) results.append(BulkAddItemResult(name=entry.name, ok=True, item_id=item["id"]))
except Exception as exc: except Exception as exc:
@ -222,15 +168,13 @@ async def list_inventory_items(
store: Store = Depends(get_store), store: Store = Depends(get_store),
): ):
items = await asyncio.to_thread(store.list_inventory, location, item_status) items = await asyncio.to_thread(store.list_inventory, location, item_status)
constraints = await asyncio.to_thread(_user_constraints, store) return [InventoryItemResponse.model_validate(i) for i in items]
return [InventoryItemResponse.model_validate(_enrich_item(i, constraints)) for i in items]
@router.get("/items/expiring", response_model=List[InventoryItemResponse]) @router.get("/items/expiring", response_model=List[InventoryItemResponse])
async def get_expiring_items(days: int = 7, store: Store = Depends(get_store)): async def get_expiring_items(days: int = 7, store: Store = Depends(get_store)):
items = await asyncio.to_thread(store.expiring_soon, days) items = await asyncio.to_thread(store.expiring_soon, days)
constraints = await asyncio.to_thread(_user_constraints, store) return [InventoryItemResponse.model_validate(i) for i in items]
return [InventoryItemResponse.model_validate(_enrich_item(i, constraints)) for i in items]
@router.get("/items/{item_id}", response_model=InventoryItemResponse) @router.get("/items/{item_id}", response_model=InventoryItemResponse)
@ -238,8 +182,7 @@ async def get_inventory_item(item_id: int, store: Store = Depends(get_store)):
item = await asyncio.to_thread(store.get_inventory_item, item_id) item = await asyncio.to_thread(store.get_inventory_item, item_id)
if not item: if not item:
raise HTTPException(status_code=404, detail="Inventory item not found") raise HTTPException(status_code=404, detail="Inventory item not found")
constraints = await asyncio.to_thread(_user_constraints, store) return InventoryItemResponse.model_validate(item)
return InventoryItemResponse.model_validate(_enrich_item(item, constraints))
@router.patch("/items/{item_id}", response_model=InventoryItemResponse) @router.patch("/items/{item_id}", response_model=InventoryItemResponse)
@ -251,83 +194,24 @@ async def update_inventory_item(
updates["purchase_date"] = str(updates["purchase_date"]) updates["purchase_date"] = str(updates["purchase_date"])
if "expiration_date" in updates and updates["expiration_date"]: if "expiration_date" in updates and updates["expiration_date"]:
updates["expiration_date"] = str(updates["expiration_date"]) updates["expiration_date"] = str(updates["expiration_date"])
if "opened_date" in updates and updates["opened_date"]:
updates["opened_date"] = str(updates["opened_date"])
item = await asyncio.to_thread(store.update_inventory_item, item_id, **updates) item = await asyncio.to_thread(store.update_inventory_item, item_id, **updates)
if not item: if not item:
raise HTTPException(status_code=404, detail="Inventory item not found") raise HTTPException(status_code=404, detail="Inventory item not found")
constraints = await asyncio.to_thread(_user_constraints, store) return InventoryItemResponse.model_validate(item)
return InventoryItemResponse.model_validate(_enrich_item(item, constraints))
@router.post("/items/{item_id}/open", response_model=InventoryItemResponse)
async def mark_item_opened(item_id: int, store: Store = Depends(get_store)):
"""Record that this item was opened today, triggering secondary shelf-life tracking."""
from datetime import date
item = await asyncio.to_thread(
store.update_inventory_item,
item_id,
opened_date=str(date.today()),
)
if not item:
raise HTTPException(status_code=404, detail="Inventory item not found")
constraints = await asyncio.to_thread(_user_constraints, store)
return InventoryItemResponse.model_validate(_enrich_item(item, constraints))
@router.post("/items/{item_id}/consume", response_model=InventoryItemResponse) @router.post("/items/{item_id}/consume", response_model=InventoryItemResponse)
async def consume_item( async def consume_item(item_id: int, store: Store = Depends(get_store)):
item_id: int,
body: Optional[PartialConsumeRequest] = None,
store: Store = Depends(get_store),
):
"""Consume an inventory item fully or partially.
When body.quantity is provided, decrements by that amount and only marks
status=consumed when quantity reaches zero. Omit body to consume all.
"""
from datetime import datetime, timezone from datetime import datetime, timezone
now = datetime.now(timezone.utc).isoformat()
if body is not None:
item = await asyncio.to_thread(
store.partial_consume_item, item_id, body.quantity, now
)
else:
item = await asyncio.to_thread( item = await asyncio.to_thread(
store.update_inventory_item, store.update_inventory_item,
item_id, item_id,
status="consumed", status="consumed",
consumed_at=now,
)
if not item:
raise HTTPException(status_code=404, detail="Inventory item not found")
constraints = await asyncio.to_thread(_user_constraints, store)
return InventoryItemResponse.model_validate(_enrich_item(item, constraints))
@router.post("/items/{item_id}/discard", response_model=InventoryItemResponse)
async def discard_item(
item_id: int,
body: DiscardRequest = DiscardRequest(),
store: Store = Depends(get_store),
):
"""Mark an item as discarded (not used, spoiled, etc).
Optional reason field accepts free text or a preset label
('not used', 'spoiled', 'excess', 'other').
"""
from datetime import datetime, timezone
item = await asyncio.to_thread(
store.update_inventory_item,
item_id,
status="discarded",
consumed_at=datetime.now(timezone.utc).isoformat(), consumed_at=datetime.now(timezone.utc).isoformat(),
disposal_reason=body.reason,
) )
if not item: if not item:
raise HTTPException(status_code=404, detail="Inventory item not found") raise HTTPException(status_code=404, detail="Inventory item not found")
constraints = await asyncio.to_thread(_user_constraints, store) return InventoryItemResponse.model_validate(item)
return InventoryItemResponse.model_validate(_enrich_item(item, constraints))
@router.delete("/items/{item_id}", status_code=status.HTTP_204_NO_CONTENT) @router.delete("/items/{item_id}", status_code=status.HTTP_204_NO_CONTENT)
@ -350,31 +234,6 @@ class BarcodeScanTextRequest(BaseModel):
auto_add_to_inventory: bool = True auto_add_to_inventory: bool = True
def _captured_to_product_info(row: dict) -> dict:
"""Convert a captured_products row to the product_info dict shape used by
the barcode scan flow (mirrors what OpenFoodFactsService returns)."""
macros: dict = {}
for field in ("calories", "fat_g", "saturated_fat_g", "carbs_g", "sugar_g",
"fiber_g", "protein_g", "sodium_mg", "serving_size_g"):
if row.get(field) is not None:
macros[field] = row[field]
return {
"name": row.get("product_name") or row.get("barcode", "Unknown Product"),
"brand": row.get("brand"),
"category": None,
"nutrition_data": macros,
"ingredient_names": row.get("ingredient_names") or [],
"allergens": row.get("allergens") or [],
"source": "visual_capture",
}
def _gap_message(tier: str, has_visual_capture: bool) -> str:
if has_visual_capture:
return "We couldn't find this product. Photograph the nutrition label to add it."
return "Not found in any product database — add manually"
@router.post("/scan/text", response_model=BarcodeScanResponse) @router.post("/scan/text", response_model=BarcodeScanResponse)
async def scan_barcode_text( async def scan_barcode_text(
body: BarcodeScanTextRequest, body: BarcodeScanTextRequest,
@ -382,24 +241,12 @@ async def scan_barcode_text(
session: CloudUser = Depends(get_session), session: CloudUser = Depends(get_session),
): ):
"""Scan a barcode from a text string (e.g. from a hardware scanner or manual entry).""" """Scan a barcode from a text string (e.g. from a hardware scanner or manual entry)."""
log.info("scan auth=%s tier=%s barcode=%r", _auth_label(session.user_id), session.tier, body.barcode)
from app.services.openfoodfacts import OpenFoodFactsService from app.services.openfoodfacts import OpenFoodFactsService
from app.services.expiration_predictor import ExpirationPredictor from app.services.expiration_predictor import ExpirationPredictor
from app.tiers import can_use
predictor = ExpirationPredictor()
has_visual_capture = can_use("visual_label_capture", session.tier, session.has_byok)
# 1. Check local captured-products cache before hitting FDC/OFF
cached = await asyncio.to_thread(store.get_captured_product, body.barcode)
if cached and cached.get("confirmed_by_user"):
product_info: dict | None = _captured_to_product_info(cached)
product_source = "visual_capture"
else:
off = OpenFoodFactsService() off = OpenFoodFactsService()
predictor = ExpirationPredictor()
product_info = await off.lookup_product(body.barcode) product_info = await off.lookup_product(body.barcode)
product_source = "openfoodfacts"
inventory_item = None inventory_item = None
if product_info and body.auto_add_to_inventory: if product_info and body.auto_add_to_inventory:
@ -410,7 +257,7 @@ async def scan_barcode_text(
brand=product_info.get("brand"), brand=product_info.get("brand"),
category=product_info.get("category"), category=product_info.get("category"),
nutrition_data=product_info.get("nutrition_data", {}), nutrition_data=product_info.get("nutrition_data", {}),
source=product_source, source="openfoodfacts",
source_data=product_info, source_data=product_info,
) )
exp = predictor.predict_expiration( exp = predictor.predict_expiration(
@ -420,14 +267,10 @@ async def scan_barcode_text(
tier=session.tier, tier=session.tier,
has_byok=session.has_byok, has_byok=session.has_byok,
) )
# Use OFFs pack size when detected; caller-supplied quantity is a fallback
resolved_qty = product_info.get("pack_quantity") or body.quantity
resolved_unit = product_info.get("pack_unit") or "count"
inventory_item = await asyncio.to_thread( inventory_item = await asyncio.to_thread(
store.add_inventory_item, store.add_inventory_item,
product["id"], body.location, product["id"], body.location,
quantity=resolved_qty, quantity=body.quantity,
unit=resolved_unit,
expiration_date=str(exp) if exp else None, expiration_date=str(exp) if exp else None,
source="barcode_scan", source="barcode_scan",
) )
@ -435,8 +278,6 @@ async def scan_barcode_text(
else: else:
result_product = None result_product = None
product_found = product_info is not None
needs_capture = not product_found and has_visual_capture
return BarcodeScanResponse( return BarcodeScanResponse(
success=True, success=True,
barcodes_found=1, barcodes_found=1,
@ -446,9 +287,7 @@ async def scan_barcode_text(
"product": result_product, "product": result_product,
"inventory_item": InventoryItemResponse.model_validate(inventory_item) if inventory_item else None, "inventory_item": InventoryItemResponse.model_validate(inventory_item) if inventory_item else None,
"added_to_inventory": inventory_item is not None, "added_to_inventory": inventory_item is not None,
"needs_manual_entry": not product_found and not needs_capture, "message": "Added to inventory" if inventory_item else "Product not found in database",
"needs_visual_capture": needs_capture,
"message": "Added to inventory" if inventory_item else _gap_message(session.tier, needs_capture),
}], }],
message="Barcode processed", message="Barcode processed",
) )
@ -464,10 +303,6 @@ async def scan_barcode_image(
session: CloudUser = Depends(get_session), session: CloudUser = Depends(get_session),
): ):
"""Scan a barcode from an uploaded image. Requires Phase 2 scanner integration.""" """Scan a barcode from an uploaded image. Requires Phase 2 scanner integration."""
log.info("scan_image auth=%s tier=%s", _auth_label(session.user_id), session.tier)
from app.tiers import can_use
has_visual_capture = can_use("visual_label_capture", session.tier, session.has_byok)
temp_dir = Path("/tmp/kiwi_barcode_scans") temp_dir = Path("/tmp/kiwi_barcode_scans")
temp_dir.mkdir(parents=True, exist_ok=True) temp_dir.mkdir(parents=True, exist_ok=True)
temp_file = temp_dir / f"{uuid.uuid4()}_{file.filename}" temp_file = temp_dir / f"{uuid.uuid4()}_{file.filename}"
@ -478,8 +313,7 @@ async def scan_barcode_image(
from app.services.openfoodfacts import OpenFoodFactsService from app.services.openfoodfacts import OpenFoodFactsService
from app.services.expiration_predictor import ExpirationPredictor from app.services.expiration_predictor import ExpirationPredictor
image_bytes = temp_file.read_bytes() barcodes = await asyncio.to_thread(BarcodeScanner().scan_image, temp_file)
barcodes = await asyncio.to_thread(BarcodeScanner().scan_from_bytes, image_bytes)
if not barcodes: if not barcodes:
return BarcodeScanResponse( return BarcodeScanResponse(
success=False, barcodes_found=0, results=[], success=False, barcodes_found=0, results=[],
@ -491,30 +325,19 @@ async def scan_barcode_image(
results = [] results = []
for bc in barcodes: for bc in barcodes:
code = bc["data"] code = bc["data"]
# Check local visual-capture cache before hitting FDC/OFF
cached = await asyncio.to_thread(store.get_captured_product, code)
if cached and cached.get("confirmed_by_user"):
product_info: dict | None = _captured_to_product_info(cached)
product_source = "visual_capture"
else:
product_info = await off.lookup_product(code) product_info = await off.lookup_product(code)
product_source = "openfoodfacts"
db_product = None
inventory_item = None inventory_item = None
if product_info: if product_info and auto_add_to_inventory:
db_product, _ = await asyncio.to_thread( product, _ = await asyncio.to_thread(
store.get_or_create_product, store.get_or_create_product,
product_info.get("name", code), product_info.get("name", code),
code, code,
brand=product_info.get("brand"), brand=product_info.get("brand"),
category=product_info.get("category"), category=product_info.get("category"),
nutrition_data=product_info.get("nutrition_data", {}), nutrition_data=product_info.get("nutrition_data", {}),
source=product_source, source="openfoodfacts",
source_data=product_info, source_data=product_info,
) )
if auto_add_to_inventory:
exp = predictor.predict_expiration( exp = predictor.predict_expiration(
product_info.get("category", ""), product_info.get("category", ""),
location, location,
@ -522,27 +345,20 @@ async def scan_barcode_image(
tier=session.tier, tier=session.tier,
has_byok=session.has_byok, has_byok=session.has_byok,
) )
resolved_qty = product_info.get("pack_quantity") or quantity
resolved_unit = product_info.get("pack_unit") or "count"
inventory_item = await asyncio.to_thread( inventory_item = await asyncio.to_thread(
store.add_inventory_item, store.add_inventory_item,
db_product["id"], location, product["id"], location,
quantity=resolved_qty, quantity=quantity,
unit=resolved_unit,
expiration_date=str(exp) if exp else None, expiration_date=str(exp) if exp else None,
source="barcode_scan", source="barcode_scan",
) )
product_found = db_product is not None
needs_capture = not product_found and has_visual_capture
results.append({ results.append({
"barcode": code, "barcode": code,
"barcode_type": bc.get("type", "unknown"), "barcode_type": bc.get("type", "unknown"),
"product": ProductResponse.model_validate(db_product) if db_product else None, "product": ProductResponse.model_validate(product) if product_info else None,
"inventory_item": InventoryItemResponse.model_validate(inventory_item) if inventory_item else None, "inventory_item": InventoryItemResponse.model_validate(inventory_item) if inventory_item else None,
"added_to_inventory": inventory_item is not None, "added_to_inventory": inventory_item is not None,
"needs_manual_entry": not product_found and not needs_capture, "message": "Added to inventory" if inventory_item else "Barcode scanned",
"needs_visual_capture": needs_capture,
"message": "Added to inventory" if inventory_item else _gap_message(session.tier, needs_capture),
}) })
return BarcodeScanResponse( return BarcodeScanResponse(
success=True, barcodes_found=len(barcodes), results=results, success=True, barcodes_found=len(barcodes), results=results,
@ -553,143 +369,6 @@ async def scan_barcode_image(
temp_file.unlink() temp_file.unlink()
# ── Visual label capture (kiwi#79) ────────────────────────────────────────────
@router.post("/scan/label-capture")
async def capture_nutrition_label(
file: UploadFile = File(...),
barcode: str = Form(...),
store: Store = Depends(get_store),
session: CloudUser = Depends(get_session),
):
"""Photograph a nutrition label for an unenriched product (paid tier).
Sends the image to the vision model and returns structured nutrition data
for user review. Fields extracted with confidence < 0.7 should be
highlighted in amber in the UI.
"""
from app.tiers import can_use
from app.models.schemas.label_capture import LabelCaptureResponse
from app.services.label_capture import extract_label, needs_review as _needs_review
if not can_use("visual_label_capture", session.tier, session.has_byok):
raise HTTPException(status_code=403, detail="Visual label capture requires a Paid tier or higher.")
log.info("label_capture tier=%s barcode=%r", session.tier, barcode)
image_bytes = await file.read()
extraction = await asyncio.to_thread(extract_label, image_bytes)
return LabelCaptureResponse(
barcode=barcode,
product_name=extraction.get("product_name"),
brand=extraction.get("brand"),
serving_size_g=extraction.get("serving_size_g"),
calories=extraction.get("calories"),
fat_g=extraction.get("fat_g"),
saturated_fat_g=extraction.get("saturated_fat_g"),
carbs_g=extraction.get("carbs_g"),
sugar_g=extraction.get("sugar_g"),
fiber_g=extraction.get("fiber_g"),
protein_g=extraction.get("protein_g"),
sodium_mg=extraction.get("sodium_mg"),
ingredient_names=extraction.get("ingredient_names") or [],
allergens=extraction.get("allergens") or [],
confidence=extraction.get("confidence", 0.0),
needs_review=_needs_review(extraction),
)
@router.post("/scan/label-confirm")
async def confirm_nutrition_label(
body: LabelConfirmRequest,
store: Store = Depends(get_store),
session: CloudUser = Depends(get_session),
):
"""Confirm and save a user-reviewed label extraction.
Saves the product to the local cache so future scans of the same barcode
resolve instantly without another capture. Optionally adds the item to
the user's inventory.
"""
from app.tiers import can_use
from app.models.schemas.label_capture import LabelConfirmResponse
from app.services.expiration_predictor import ExpirationPredictor
if not can_use("visual_label_capture", session.tier, session.has_byok):
raise HTTPException(status_code=403, detail="Visual label capture requires a Paid tier or higher.")
log.info("label_confirm tier=%s barcode=%r", session.tier, body.barcode)
# Persist to local visual-capture cache
await asyncio.to_thread(
store.save_captured_product,
body.barcode,
product_name=body.product_name,
brand=body.brand,
serving_size_g=body.serving_size_g,
calories=body.calories,
fat_g=body.fat_g,
saturated_fat_g=body.saturated_fat_g,
carbs_g=body.carbs_g,
sugar_g=body.sugar_g,
fiber_g=body.fiber_g,
protein_g=body.protein_g,
sodium_mg=body.sodium_mg,
ingredient_names=body.ingredient_names,
allergens=body.allergens,
confidence=body.confidence,
confirmed_by_user=True,
)
product_id: int | None = None
inventory_item_id: int | None = None
if body.auto_add:
predictor = ExpirationPredictor()
nutrition = {}
for field in ("calories", "fat_g", "saturated_fat_g", "carbs_g", "sugar_g",
"fiber_g", "protein_g", "sodium_mg", "serving_size_g"):
val = getattr(body, field, None)
if val is not None:
nutrition[field] = val
product, _ = await asyncio.to_thread(
store.get_or_create_product,
body.product_name or body.barcode,
body.barcode,
brand=body.brand,
category=None,
nutrition_data=nutrition,
source="visual_capture",
source_data={},
)
product_id = product["id"]
exp = predictor.predict_expiration(
"",
body.location,
product_name=body.product_name or body.barcode,
tier=session.tier,
has_byok=session.has_byok,
)
inv_item = await asyncio.to_thread(
store.add_inventory_item,
product_id, body.location,
quantity=body.quantity,
unit="count",
expiration_date=str(exp) if exp else None,
source="visual_capture",
)
inventory_item_id = inv_item["id"]
return LabelConfirmResponse(
ok=True,
barcode=body.barcode,
product_id=product_id,
inventory_item_id=inventory_item_id,
message="Product saved" + (" and added to inventory" if body.auto_add else ""),
)
# ── Tags ────────────────────────────────────────────────────────────────────── # ── Tags ──────────────────────────────────────────────────────────────────────
@router.post("/tags", response_model=TagResponse, status_code=status.HTTP_201_CREATED) @router.post("/tags", response_model=TagResponse, status_code=status.HTTP_201_CREATED)

View file

@ -1,133 +0,0 @@
# app/api/endpoints/mastodon_oauth.py
# MIT License
#
# Mastodon OAuth flow endpoints:
# POST /social/mastodon/connect — Start OAuth (dynamic app registration)
# GET /social/mastodon/callback — OAuth callback, exchange code for token
# DELETE /social/mastodon/disconnect — Revoke and remove stored token
# GET /social/mastodon/status — Check connection status
from __future__ import annotations
import asyncio
import logging
from urllib.parse import urlencode
from fastapi import APIRouter, Depends, HTTPException
from fastapi.responses import RedirectResponse
from app.cloud_session import CloudUser, get_session
from app.core.config import settings
logger = logging.getLogger(__name__)
router = APIRouter(prefix="/social/mastodon", tags=["mastodon"])
def _redirect_uri() -> str:
host = settings.AP_HOST or "localhost:8512"
return f"https://{host}/api/v1/social/mastodon/callback"
# In-memory pending state: maps state_token → {instance_url, client_id, client_secret, user_id}
# A real deployment would persist this in a short-TTL cache or DB.
_pending: dict[str, dict] = {}
@router.post("/connect")
async def connect_mastodon(body: dict, session: CloudUser = Depends(get_session)):
"""Start the Mastodon OAuth flow.
Body: {"instance_url": "https://mastodon.social"}
Returns: {"authorize_url": "..."}
"""
import secrets
from app.services.ap.mastodon import build_authorize_url, register_app
instance_url = (body.get("instance_url") or "").strip().rstrip("/")
if not instance_url.startswith("https://"):
raise HTTPException(status_code=422, detail="instance_url must be an https:// URL.")
redirect_uri = _redirect_uri()
try:
app_creds = await asyncio.to_thread(register_app, instance_url, redirect_uri)
except Exception as exc:
raise HTTPException(
status_code=502, detail=f"Could not register with Mastodon instance: {exc}"
) from exc
state = secrets.token_urlsafe(24)
_pending[state] = {
"instance_url": instance_url,
"client_id": app_creds["client_id"],
"client_secret": app_creds["client_secret"],
"user_id": session.user_id,
}
authorize_url = build_authorize_url(
instance_url=instance_url,
client_id=app_creds["client_id"],
redirect_uri=redirect_uri + f"?state={state}",
)
return {"authorize_url": authorize_url, "state": state}
@router.get("/callback")
async def mastodon_callback(code: str | None = None, state: str | None = None):
"""OAuth callback. Exchanges auth code for access token and stores it."""
if not code or not state:
raise HTTPException(status_code=400, detail="Missing code or state parameter.")
pending = _pending.pop(state, None)
if pending is None:
raise HTTPException(status_code=400, detail="Unknown or expired OAuth state.")
from app.services.ap.mastodon import exchange_code, store_token
redirect_uri = _redirect_uri() + f"?state={state}"
try:
access_token = await asyncio.to_thread(
exchange_code,
pending["instance_url"],
pending["client_id"],
pending["client_secret"],
code,
redirect_uri,
)
except Exception as exc:
raise HTTPException(status_code=502, detail=f"Token exchange failed: {exc}") from exc
await asyncio.to_thread(
store_token,
settings.DB_PATH,
pending["user_id"],
pending["instance_url"],
access_token,
settings.AP_TOKEN_ENCRYPTION_KEY,
)
# Redirect to frontend settings page after successful connect
return RedirectResponse(url="/#/settings?mastodon=connected", status_code=302)
@router.delete("/disconnect", status_code=204)
async def disconnect_mastodon(session: CloudUser = Depends(get_session)):
"""Remove the stored Mastodon token."""
from app.services.ap.mastodon import delete_token
await asyncio.to_thread(delete_token, settings.DB_PATH, session.user_id)
@router.get("/status")
async def mastodon_status(session: CloudUser = Depends(get_session)):
"""Return connection status and instance URL (no token value)."""
from app.services.ap.mastodon import get_token
result = await asyncio.to_thread(
get_token,
settings.DB_PATH,
session.user_id,
settings.AP_TOKEN_ENCRYPTION_KEY,
)
if result is None:
return {"connected": False, "instance_url": None}
instance_url, _ = result
return {"connected": True, "instance_url": instance_url}

View file

@ -1,325 +0,0 @@
# app/api/endpoints/meal_plans.py
"""Meal plan CRUD, shopping list, and prep session endpoints."""
from __future__ import annotations
import asyncio
import json
from datetime import date
from fastapi import APIRouter, Depends, HTTPException
from app.cloud_session import CloudUser, get_session
from app.db.session import get_store
from app.db.store import Store
from app.models.schemas.meal_plan import (
CreatePlanRequest,
GapItem,
PlanSummary,
PrepSessionSummary,
PrepTaskSummary,
ShoppingListResponse,
SlotSummary,
UpdatePlanRequest,
UpdatePrepTaskRequest,
UpsertSlotRequest,
VALID_MEAL_TYPES,
)
from app.services.meal_plan.affiliates import get_retailer_links
from app.services.meal_plan.prep_scheduler import build_prep_tasks
from app.services.meal_plan.shopping_list import compute_shopping_list
from app.tiers import can_use
router = APIRouter()
# ── helpers ───────────────────────────────────────────────────────────────────
def _slot_summary(row: dict) -> SlotSummary:
return SlotSummary(
id=row["id"],
plan_id=row["plan_id"],
day_of_week=row["day_of_week"],
meal_type=row["meal_type"],
recipe_id=row.get("recipe_id"),
recipe_title=row.get("recipe_title"),
servings=row["servings"],
custom_label=row.get("custom_label"),
)
def _plan_summary(plan: dict, slots: list[dict]) -> PlanSummary:
meal_types = plan.get("meal_types") or ["dinner"]
if isinstance(meal_types, str):
meal_types = json.loads(meal_types)
return PlanSummary(
id=plan["id"],
week_start=plan["week_start"],
meal_types=meal_types,
slots=[_slot_summary(s) for s in slots],
created_at=plan["created_at"],
)
def _prep_task_summary(row: dict) -> PrepTaskSummary:
return PrepTaskSummary(
id=row["id"],
recipe_id=row.get("recipe_id"),
task_label=row["task_label"],
duration_minutes=row.get("duration_minutes"),
sequence_order=row["sequence_order"],
equipment=row.get("equipment"),
is_parallel=bool(row.get("is_parallel", False)),
notes=row.get("notes"),
user_edited=bool(row.get("user_edited", False)),
)
# ── plan CRUD ─────────────────────────────────────────────────────────────────
@router.post("/", response_model=PlanSummary)
async def create_plan(
req: CreatePlanRequest,
session: CloudUser = Depends(get_session),
store: Store = Depends(get_store),
) -> PlanSummary:
import sqlite3
# Free tier is locked to dinner-only; paid+ may configure meal types
if can_use("meal_plan_config", session.tier):
meal_types = [t for t in req.meal_types if t in VALID_MEAL_TYPES] or ["dinner"]
else:
meal_types = ["dinner"]
try:
plan = await asyncio.to_thread(store.create_meal_plan, str(req.week_start), meal_types)
except sqlite3.IntegrityError:
raise HTTPException(
status_code=409,
detail=f"A meal plan for the week of {req.week_start} already exists.",
)
slots = await asyncio.to_thread(store.get_plan_slots, plan["id"])
return _plan_summary(plan, slots)
@router.get("/", response_model=list[PlanSummary])
async def list_plans(
session: CloudUser = Depends(get_session),
store: Store = Depends(get_store),
) -> list[PlanSummary]:
plans = await asyncio.to_thread(store.list_meal_plans)
result = []
for p in plans:
slots = await asyncio.to_thread(store.get_plan_slots, p["id"])
result.append(_plan_summary(p, slots))
return result
@router.patch("/{plan_id}", response_model=PlanSummary)
async def update_plan(
plan_id: int,
req: UpdatePlanRequest,
session: CloudUser = Depends(get_session),
store: Store = Depends(get_store),
) -> PlanSummary:
plan = await asyncio.to_thread(store.get_meal_plan, plan_id)
if plan is None:
raise HTTPException(status_code=404, detail="Plan not found.")
# Free tier stays dinner-only; paid+ may add meal types
if can_use("meal_plan_config", session.tier):
meal_types = [t for t in req.meal_types if t in VALID_MEAL_TYPES] or ["dinner"]
else:
meal_types = ["dinner"]
updated = await asyncio.to_thread(store.update_meal_plan_types, plan_id, meal_types)
if updated is None:
raise HTTPException(status_code=404, detail="Plan not found.")
slots = await asyncio.to_thread(store.get_plan_slots, plan_id)
return _plan_summary(updated, slots)
@router.get("/{plan_id}", response_model=PlanSummary)
async def get_plan(
plan_id: int,
session: CloudUser = Depends(get_session),
store: Store = Depends(get_store),
) -> PlanSummary:
plan = await asyncio.to_thread(store.get_meal_plan, plan_id)
if plan is None:
raise HTTPException(status_code=404, detail="Plan not found.")
slots = await asyncio.to_thread(store.get_plan_slots, plan_id)
return _plan_summary(plan, slots)
# ── slots ─────────────────────────────────────────────────────────────────────
@router.put("/{plan_id}/slots/{day_of_week}/{meal_type}", response_model=SlotSummary)
async def upsert_slot(
plan_id: int,
day_of_week: int,
meal_type: str,
req: UpsertSlotRequest,
session: CloudUser = Depends(get_session),
store: Store = Depends(get_store),
) -> SlotSummary:
if day_of_week < 0 or day_of_week > 6:
raise HTTPException(status_code=422, detail="day_of_week must be 0-6.")
if meal_type not in VALID_MEAL_TYPES:
raise HTTPException(status_code=422, detail=f"Invalid meal_type '{meal_type}'.")
plan = await asyncio.to_thread(store.get_meal_plan, plan_id)
if plan is None:
raise HTTPException(status_code=404, detail="Plan not found.")
row = await asyncio.to_thread(
store.upsert_slot,
plan_id, day_of_week, meal_type,
req.recipe_id, req.servings, req.custom_label,
)
return _slot_summary(row)
@router.delete("/{plan_id}/slots/{slot_id}", status_code=204)
async def delete_slot(
plan_id: int,
slot_id: int,
session: CloudUser = Depends(get_session),
store: Store = Depends(get_store),
) -> None:
plan = await asyncio.to_thread(store.get_meal_plan, plan_id)
if plan is None:
raise HTTPException(status_code=404, detail="Plan not found.")
await asyncio.to_thread(store.delete_slot, slot_id)
# ── shopping list ─────────────────────────────────────────────────────────────
@router.get("/{plan_id}/shopping-list", response_model=ShoppingListResponse)
async def get_shopping_list(
plan_id: int,
session: CloudUser = Depends(get_session),
store: Store = Depends(get_store),
) -> ShoppingListResponse:
plan = await asyncio.to_thread(store.get_meal_plan, plan_id)
if plan is None:
raise HTTPException(status_code=404, detail="Plan not found.")
recipes = await asyncio.to_thread(store.get_plan_recipes, plan_id)
inventory = await asyncio.to_thread(store.list_inventory)
gaps, covered = compute_shopping_list(recipes, inventory)
# Enrich gap items with retailer links
def _to_schema(item, enrich: bool) -> GapItem:
links = get_retailer_links(item.ingredient_name) if enrich else []
return GapItem(
ingredient_name=item.ingredient_name,
needed_raw=item.needed_raw,
have_quantity=item.have_quantity,
have_unit=item.have_unit,
covered=item.covered,
retailer_links=links,
)
gap_items = [_to_schema(g, enrich=True) for g in gaps]
covered_items = [_to_schema(c, enrich=False) for c in covered]
disclosure = (
"Some links may be affiliate links. Purchases through them support Kiwi development."
if gap_items else None
)
return ShoppingListResponse(
plan_id=plan_id,
gap_items=gap_items,
covered_items=covered_items,
disclosure=disclosure,
)
# ── prep session ──────────────────────────────────────────────────────────────
@router.get("/{plan_id}/prep-session", response_model=PrepSessionSummary)
async def get_prep_session(
plan_id: int,
session: CloudUser = Depends(get_session),
store: Store = Depends(get_store),
) -> PrepSessionSummary:
plan = await asyncio.to_thread(store.get_meal_plan, plan_id)
if plan is None:
raise HTTPException(status_code=404, detail="Plan not found.")
prep_session = await asyncio.to_thread(store.get_prep_session_for_plan, plan_id)
if prep_session is None:
raise HTTPException(status_code=404, detail="No prep session for this plan.")
raw_tasks = await asyncio.to_thread(store.get_prep_tasks, prep_session["id"])
return PrepSessionSummary(
id=prep_session["id"],
plan_id=plan_id,
scheduled_date=prep_session["scheduled_date"],
status=prep_session["status"],
tasks=[_prep_task_summary(t) for t in raw_tasks],
)
@router.post("/{plan_id}/prep-session", response_model=PrepSessionSummary)
async def create_prep_session(
plan_id: int,
session: CloudUser = Depends(get_session),
store: Store = Depends(get_store),
) -> PrepSessionSummary:
plan = await asyncio.to_thread(store.get_meal_plan, plan_id)
if plan is None:
raise HTTPException(status_code=404, detail="Plan not found.")
slots = await asyncio.to_thread(store.get_plan_slots, plan_id)
recipes = await asyncio.to_thread(store.get_plan_recipes, plan_id)
prep_tasks = build_prep_tasks(slots=slots, recipes=recipes)
scheduled_date = date.today().isoformat()
prep_session = await asyncio.to_thread(
store.create_prep_session, plan_id, scheduled_date
)
session_id = prep_session["id"]
task_dicts = [
{
"recipe_id": t.recipe_id,
"slot_id": t.slot_id,
"task_label": t.task_label,
"duration_minutes": t.duration_minutes,
"sequence_order": t.sequence_order,
"equipment": t.equipment,
"is_parallel": t.is_parallel,
"notes": t.notes,
}
for t in prep_tasks
]
inserted = await asyncio.to_thread(store.bulk_insert_prep_tasks, session_id, task_dicts)
return PrepSessionSummary(
id=prep_session["id"],
plan_id=prep_session["plan_id"],
scheduled_date=prep_session["scheduled_date"],
status=prep_session["status"],
tasks=[_prep_task_summary(r) for r in inserted],
)
@router.patch(
"/{plan_id}/prep-session/tasks/{task_id}",
response_model=PrepTaskSummary,
)
async def update_prep_task(
plan_id: int,
task_id: int,
req: UpdatePrepTaskRequest,
session: CloudUser = Depends(get_session),
store: Store = Depends(get_store),
) -> PrepTaskSummary:
updated = await asyncio.to_thread(
store.update_prep_task,
task_id,
duration_minutes=req.duration_minutes,
sequence_order=req.sequence_order,
notes=req.notes,
equipment=req.equipment,
)
if updated is None:
raise HTTPException(status_code=404, detail="Task not found.")
return _prep_task_summary(updated)

View file

@ -219,7 +219,7 @@ def _commit_items(
receipt_id=receipt_id, receipt_id=receipt_id,
purchase_date=str(purchase_date) if purchase_date else None, purchase_date=str(purchase_date) if purchase_date else None,
expiration_date=str(exp) if exp else None, expiration_date=str(exp) if exp else None,
source="receipt", source="receipt_ocr",
) )
created.append(ApprovedInventoryItem( created.append(ApprovedInventoryItem(

View file

@ -1,27 +0,0 @@
"""Proxy endpoint: exposes cf-orch call budget to the Kiwi frontend.
Only lifetime/founders users have a license_key subscription and free
users receive null (no budget UI shown).
"""
from __future__ import annotations
from fastapi import APIRouter, Depends
from app.cloud_session import CloudUser, get_session
from app.services.heimdall_orch import get_orch_usage
router = APIRouter()
@router.get("")
async def orch_usage_endpoint(
session: CloudUser = Depends(get_session),
) -> dict | None:
"""Return the current period's orch usage for the authenticated user.
Returns null if the user has no lifetime/founders license key (i.e. they
are on a subscription or free plan no budget cap applies to them).
"""
if session.license_key is None:
return None
return get_orch_usage(session.license_key, "kiwi")

View file

@ -42,11 +42,9 @@ async def upload_receipt(
) )
# Only queue OCR if the feature is enabled server-side AND the user's tier allows it. # Only queue OCR if the feature is enabled server-side AND the user's tier allows it.
# Check tier here, not inside the background task — once dispatched it can't be cancelled. # Check tier here, not inside the background task — once dispatched it can't be cancelled.
# Pass session.db (a Path) rather than store — the store dependency closes before
# background tasks run, so the task opens its own store from the DB path.
ocr_allowed = settings.ENABLE_OCR and can_use("receipt_ocr", session.tier, session.has_byok) ocr_allowed = settings.ENABLE_OCR and can_use("receipt_ocr", session.tier, session.has_byok)
if ocr_allowed: if ocr_allowed:
background_tasks.add_task(_process_receipt_ocr, receipt["id"], saved, session.db) background_tasks.add_task(_process_receipt_ocr, receipt["id"], saved, store)
return ReceiptResponse.model_validate(receipt) return ReceiptResponse.model_validate(receipt)
@ -66,7 +64,7 @@ async def upload_receipts_batch(
store.create_receipt, file.filename, str(saved) store.create_receipt, file.filename, str(saved)
) )
if ocr_allowed: if ocr_allowed:
background_tasks.add_task(_process_receipt_ocr, receipt["id"], saved, session.db) background_tasks.add_task(_process_receipt_ocr, receipt["id"], saved, store)
results.append(ReceiptResponse.model_validate(receipt)) results.append(ReceiptResponse.model_validate(receipt))
return results return results
@ -99,13 +97,8 @@ async def get_receipt_quality(receipt_id: int, store: Store = Depends(get_store)
return QualityAssessment.model_validate(qa) return QualityAssessment.model_validate(qa)
async def _process_receipt_ocr(receipt_id: int, image_path: Path, db_path: Path) -> None: async def _process_receipt_ocr(receipt_id: int, image_path: Path, store: Store) -> None:
"""Background task: run OCR pipeline on an uploaded receipt. """Background task: run OCR pipeline on an uploaded receipt."""
Accepts db_path (not a Store instance) because FastAPI closes the request-scoped
store before background tasks execute. This task owns its store lifecycle.
"""
store = Store(db_path)
try: try:
await asyncio.to_thread(store.update_receipt_status, receipt_id, "processing") await asyncio.to_thread(store.update_receipt_status, receipt_id, "processing")
from app.services.receipt_service import ReceiptService from app.services.receipt_service import ReceiptService
@ -115,5 +108,3 @@ async def _process_receipt_ocr(receipt_id: int, image_path: Path, db_path: Path)
await asyncio.to_thread( await asyncio.to_thread(
store.update_receipt_status, receipt_id, "error", str(exc) store.update_receipt_status, receipt_id, "error", str(exc)
) )
finally:
store.close()

View file

@ -1,371 +0,0 @@
"""Recipe scanner endpoints (kiwi#9).
POST /recipes/scan -- scan photo(s) -> structured recipe JSON (not saved)
POST /recipes/scan/save -- save a confirmed scanned recipe to user_recipes
GET /recipes/user -- list user-created recipes
GET /recipes/user/{id} -- get a single user recipe
DELETE /recipes/user/{id} -- delete a user recipe
BSL 1.1 -- recipe_scan requires Paid tier or BYOK.
"""
from __future__ import annotations
import asyncio
import json as _json
import logging
import uuid
from pathlib import Path
from typing import Annotated
import aiofiles
from fastapi import APIRouter, Depends, File, HTTPException, UploadFile
from fastapi.responses import JSONResponse, StreamingResponse
from app.cloud_session import CloudUser, get_session
from app.core.config import settings
from app.db.session import get_store
from app.db.store import Store
from app.models.schemas.recipe_scan import (
ScannedIngredientSchema,
ScannedRecipeResponse,
ScannedRecipeSaveRequest,
UserRecipeResponse,
)
from app.tiers import can_use
logger = logging.getLogger(__name__)
router = APIRouter()
_ALLOWED_MIME_TYPES = {
"image/jpeg", "image/jpg", "image/png", "image/webp", "image/heic", "image/heif"
}
_MAX_FILE_SIZE_MB = 20
async def _save_upload_temp(file: UploadFile) -> Path:
"""Write upload to a temp path under UPLOAD_DIR. Caller is responsible for cleanup."""
settings.ensure_dirs()
dest = settings.UPLOAD_DIR / f"scan_{uuid.uuid4()}_{file.filename}"
async with aiofiles.open(dest, "wb") as f:
await f.write(await file.read())
return dest
def _result_to_response(result) -> ScannedRecipeResponse:
"""Convert ScannedRecipeResult (dataclass) to Pydantic response schema."""
return ScannedRecipeResponse(
title=result.title,
subtitle=result.subtitle,
servings=result.servings,
cook_time=result.cook_time,
source_note=result.source_note,
ingredients=[
ScannedIngredientSchema(
name=i.name,
qty=i.qty,
unit=i.unit,
raw=i.raw,
in_pantry=i.in_pantry,
)
for i in result.ingredients
],
steps=result.steps,
notes=result.notes,
tags=result.tags,
pantry_match_pct=result.pantry_match_pct,
confidence=result.confidence,
warnings=result.warnings,
)
def _row_to_user_recipe(row: dict) -> UserRecipeResponse:
"""Convert a store row dict to UserRecipeResponse."""
return UserRecipeResponse(
id=row["id"],
title=row["title"],
subtitle=row.get("subtitle"),
servings=row.get("servings"),
cook_time=row.get("cook_time"),
source_note=row.get("source_note"),
ingredients=[
ScannedIngredientSchema(**i) if isinstance(i, dict) else i
for i in (row.get("ingredients") or [])
],
steps=row.get("steps") or [],
notes=row.get("notes"),
tags=row.get("tags") or [],
source=row.get("source", "manual"),
pantry_match_pct=row.get("pantry_match_pct"),
created_at=row["created_at"],
)
# ── Scan endpoint ──────────────────────────────────────────────────────────────
@router.post("/scan", response_model=ScannedRecipeResponse)
async def scan_recipe(
files: Annotated[list[UploadFile], File(...)],
store: Store = Depends(get_store),
session: CloudUser = Depends(get_session),
):
"""Scan one or more recipe photos and return a structured recipe for review.
Accepts 1-4 images. Multi-page recipes (e.g. ingredients on page 1,
directions on page 2) work best when all pages are submitted together.
The response is NOT saved automatically -- the user reviews and edits it,
then calls POST /recipes/scan/save to persist.
Tier: Paid (or BYOK).
"""
if not can_use("recipe_scan", session.tier, session.has_byok):
raise HTTPException(
status_code=403,
detail=(
"Recipe scanning requires Paid tier or a configured vision backend (BYOK). "
"Set ANTHROPIC_API_KEY or connect to a cf-orch vision service."
),
)
if not files:
raise HTTPException(status_code=422, detail="At least one image file is required.")
if len(files) > 4:
raise HTTPException(status_code=422, detail="Maximum 4 images per scan request.")
for f in files:
ct = (f.content_type or "").lower()
if ct and ct not in _ALLOWED_MIME_TYPES:
raise HTTPException(
status_code=422,
detail=f"Unsupported file type: {ct}. Supported: JPEG, PNG, WebP, HEIC.",
)
# Save uploads to temp files
saved_paths: list[Path] = []
try:
for f in files:
saved_paths.append(await _save_upload_temp(f))
# Get pantry item names for cross-reference
inventory = await asyncio.to_thread(store.list_inventory)
pantry_names = [item["product_name"] for item in inventory if item.get("product_name")]
# Run scanner (blocks on VLM -- use to_thread)
from app.services.recipe.recipe_scanner import RecipeScanner
def _run_scan():
scanner = RecipeScanner()
return scanner.scan(saved_paths, pantry_names=pantry_names)
try:
result = await asyncio.to_thread(_run_scan)
except ValueError as exc:
msg = str(exc)
if "not_a_recipe" in msg:
raise HTTPException(
status_code=422,
detail="The image does not appear to contain a recipe. "
"Please photograph a recipe card, cookbook page, or handwritten note.",
)
raise HTTPException(status_code=422, detail=msg)
except RuntimeError as exc:
msg = str(exc)
logger.warning("Recipe scanner unavailable: %s", msg)
raise HTTPException(
status_code=503,
detail=(
"The recipe scanner is temporarily unavailable — "
"no vision backend could be reached. "
"Try again in a few minutes, or contact support if this persists."
),
)
return _result_to_response(result)
finally:
# Clean up temp files
for p in saved_paths:
try:
p.unlink(missing_ok=True)
except Exception:
pass
# ── SSE scan endpoint ─────────────────────────────────────────────────────────
async def _scan_recipe_sse(saved_paths: list[Path], pantry_names: list[str]):
"""Async generator yielding SSE events for a recipe scan.
Emits progress events while the vision service allocates and runs, then a
final "done" event containing the full recipe payload (same shape as the
ScannedRecipeResponse from POST /scan).
Events:
{"status": "allocating", "message": "..."}
{"status": "scanning", "message": "..."}
{"status": "structuring","message": "..."}
{"status": "done", "recipe": {...}}
{"status": "error", "message": "..."}
"""
queue: asyncio.Queue = asyncio.Queue()
loop = asyncio.get_running_loop()
def _run() -> None:
def cb(status: str, message: str) -> None:
loop.call_soon_threadsafe(queue.put_nowait, {"status": status, "message": message})
try:
from app.services.recipe.recipe_scanner import RecipeScanner
result = RecipeScanner().scan(saved_paths, pantry_names=pantry_names, progress_cb=cb)
recipe_dict = _result_to_response(result).model_dump()
loop.call_soon_threadsafe(queue.put_nowait, {"status": "done", "recipe": recipe_dict})
except ValueError as exc:
loop.call_soon_threadsafe(queue.put_nowait, {"status": "error", "message": str(exc)})
except RuntimeError as exc:
loop.call_soon_threadsafe(queue.put_nowait, {"status": "error", "message": str(exc)})
except Exception as exc:
logger.exception("Unexpected error in recipe scan thread")
loop.call_soon_threadsafe(queue.put_nowait, {"status": "error", "message": "Scan failed unexpectedly."})
scan_task = asyncio.ensure_future(asyncio.to_thread(_run))
try:
while True:
try:
event = await asyncio.wait_for(queue.get(), timeout=180.0)
except asyncio.TimeoutError:
yield f"data: {_json.dumps({'status': 'error', 'message': 'Scan timed out after 3 minutes.'})}\n\n"
break
yield f"data: {_json.dumps(event)}\n\n"
if event["status"] in ("done", "error"):
break
finally:
if not scan_task.done():
scan_task.cancel()
@router.post("/scan/stream")
async def scan_recipe_stream(
files: Annotated[list[UploadFile], File(...)],
store: Store = Depends(get_store),
session: CloudUser = Depends(get_session),
):
"""Scan recipe photos and stream SSE progress events during model load.
Use this endpoint instead of POST /scan when you need live feedback during
cold-start model loading (first request after a GPU-idle period can take
30-60 seconds for cf-docuvision to warm up).
Tier: Paid (or BYOK) same gate as POST /scan.
"""
if not can_use("recipe_scan", session.tier, session.has_byok):
raise HTTPException(
status_code=403,
detail=(
"Recipe scanning requires Paid tier or a configured vision backend (BYOK). "
"Set ANTHROPIC_API_KEY or connect to a cf-orch vision service."
),
)
if not files:
raise HTTPException(status_code=422, detail="At least one image file is required.")
if len(files) > 4:
raise HTTPException(status_code=422, detail="Maximum 4 images per scan request.")
for f in files:
ct = (f.content_type or "").lower()
if ct and ct not in _ALLOWED_MIME_TYPES:
raise HTTPException(
status_code=422,
detail=f"Unsupported file type: {ct}. Supported: JPEG, PNG, WebP, HEIC.",
)
saved_paths: list[Path] = []
for f in files:
saved_paths.append(await _save_upload_temp(f))
inventory = await asyncio.to_thread(store.list_inventory)
pantry_names = [item["product_name"] for item in inventory if item.get("product_name")]
async def generate():
try:
async for chunk in _scan_recipe_sse(saved_paths, pantry_names):
yield chunk
finally:
for p in saved_paths:
try:
p.unlink(missing_ok=True)
except Exception:
pass
return StreamingResponse(generate(), media_type="text/event-stream")
# ── Save endpoint ──────────────────────────────────────────────────────────────
@router.post("/scan/save", response_model=UserRecipeResponse, status_code=201)
async def save_scanned_recipe(
body: ScannedRecipeSaveRequest,
store: Store = Depends(get_store),
session: CloudUser = Depends(get_session),
):
"""Save a user-reviewed (possibly edited) scanned recipe.
The body is the ScannedRecipeResponse (or a user-edited version of it).
Returns the persisted UserRecipe with an assigned ID.
Tier: Free (saving your own recipe doesn't require vision access).
"""
def _save():
return store.create_user_recipe(
title=body.title,
subtitle=body.subtitle,
servings=body.servings,
cook_time=body.cook_time,
source_note=body.source_note,
ingredients=[i.model_dump() for i in body.ingredients],
steps=body.steps,
notes=body.notes,
tags=body.tags,
source=body.source,
pantry_match_pct=None,
)
row = await asyncio.to_thread(_save)
return _row_to_user_recipe(row)
# ── User recipe list / get / delete ───────────────────────────────────────────
@router.get("/user", response_model=list[UserRecipeResponse])
async def list_user_recipes(
store: Store = Depends(get_store),
session: CloudUser = Depends(get_session),
):
"""List all user-created recipes (scanned + manually entered), newest first."""
rows = await asyncio.to_thread(store.list_user_recipes)
return [_row_to_user_recipe(r) for r in rows]
@router.get("/user/{recipe_id}", response_model=UserRecipeResponse)
async def get_user_recipe(
recipe_id: int,
store: Store = Depends(get_store),
session: CloudUser = Depends(get_session),
):
"""Get a single user recipe by ID."""
row = await asyncio.to_thread(store.get_user_recipe, recipe_id)
if not row:
raise HTTPException(status_code=404, detail="User recipe not found.")
return _row_to_user_recipe(row)
@router.delete("/user/{recipe_id}", status_code=204)
async def delete_user_recipe(
recipe_id: int,
store: Store = Depends(get_store),
session: CloudUser = Depends(get_session),
):
"""Delete a user recipe by ID."""
deleted = await asyncio.to_thread(store.delete_user_recipe, recipe_id)
if not deleted:
raise HTTPException(status_code=404, detail="User recipe not found.")
return JSONResponse(status_code=204, content=None)

View file

@ -1,166 +0,0 @@
# app/api/endpoints/recipe_tags.py
"""Community subcategory tagging for corpus recipes.
Users can tag a recipe they're viewing with a domain/category/subcategory
from the browse taxonomy. Tags require a community pseudonym and reach
public visibility once two independent users have tagged the same recipe
to the same location (upvotes >= 2).
All tiers may submit and upvote tags community contribution is free.
"""
from __future__ import annotations
import logging
from fastapi import APIRouter, Depends, HTTPException
from pydantic import BaseModel
from app.api.endpoints.community import _get_community_store
from app.api.endpoints.session import get_session
from app.cloud_session import CloudUser
from app.services.recipe.browser_domains import DOMAINS
logger = logging.getLogger(__name__)
router = APIRouter()
ACCEPT_THRESHOLD = 2
# ── Request / response models ──────────────────────────────────────────────────
class TagSubmitBody(BaseModel):
recipe_id: int
domain: str
category: str
subcategory: str | None = None
pseudonym: str
class TagResponse(BaseModel):
id: int
recipe_id: int
domain: str
category: str
subcategory: str | None
pseudonym: str
upvotes: int
accepted: bool
def _to_response(row: dict) -> TagResponse:
return TagResponse(
id=row["id"],
recipe_id=int(row["recipe_ref"]),
domain=row["domain"],
category=row["category"],
subcategory=row.get("subcategory"),
pseudonym=row["pseudonym"],
upvotes=row["upvotes"],
accepted=row["upvotes"] >= ACCEPT_THRESHOLD,
)
def _validate_location(domain: str, category: str, subcategory: str | None) -> None:
"""Raise 422 if (domain, category, subcategory) isn't in the known taxonomy."""
if domain not in DOMAINS:
raise HTTPException(status_code=422, detail=f"Unknown domain '{domain}'.")
cats = DOMAINS[domain].get("categories", {})
if category not in cats:
raise HTTPException(
status_code=422,
detail=f"Unknown category '{category}' in domain '{domain}'.",
)
if subcategory is not None:
subcats = cats[category].get("subcategories", {})
if subcategory not in subcats:
raise HTTPException(
status_code=422,
detail=f"Unknown subcategory '{subcategory}' in '{domain}/{category}'.",
)
# ── Endpoints ──────────────────────────────────────────────────────────────────
@router.get("/recipes/community-tags/{recipe_id}", response_model=list[TagResponse])
async def list_recipe_tags(
recipe_id: int,
session: CloudUser = Depends(get_session),
) -> list[TagResponse]:
"""Return all community tags for a corpus recipe, accepted ones first."""
store = _get_community_store()
if store is None:
return []
tags = store.list_tags_for_recipe(recipe_id)
return [_to_response(r) for r in tags]
@router.post("/recipes/community-tags", response_model=TagResponse, status_code=201)
async def submit_recipe_tag(
body: TagSubmitBody,
session: CloudUser = Depends(get_session),
) -> TagResponse:
"""Tag a corpus recipe with a browse taxonomy location.
Requires the user to have a community pseudonym set. Returns 409 if this
user has already tagged this recipe to this exact location.
"""
store = _get_community_store()
if store is None:
raise HTTPException(
status_code=503,
detail="Community features are not available on this instance.",
)
_validate_location(body.domain, body.category, body.subcategory)
try:
import psycopg2.errors # type: ignore[import]
row = store.submit_recipe_tag(
recipe_id=body.recipe_id,
domain=body.domain,
category=body.category,
subcategory=body.subcategory,
pseudonym=body.pseudonym,
)
return _to_response(row)
except Exception as exc:
if "unique" in str(exc).lower() or "UniqueViolation" in type(exc).__name__:
raise HTTPException(
status_code=409,
detail="You have already tagged this recipe to this location.",
)
logger.error("submit_recipe_tag failed: %s", exc)
raise HTTPException(status_code=500, detail="Failed to submit tag.")
@router.post("/recipes/community-tags/{tag_id}/upvote", response_model=TagResponse)
async def upvote_recipe_tag(
tag_id: int,
pseudonym: str,
session: CloudUser = Depends(get_session),
) -> TagResponse:
"""Upvote an existing community tag.
Returns 409 if this pseudonym has already voted on this tag.
Returns 404 if the tag doesn't exist.
"""
store = _get_community_store()
if store is None:
raise HTTPException(status_code=503, detail="Community features unavailable.")
tag_row = store.get_recipe_tag_by_id(tag_id)
if tag_row is None:
raise HTTPException(status_code=404, detail=f"Tag {tag_id} not found.")
try:
new_upvotes = store.upvote_recipe_tag(tag_id, pseudonym)
except ValueError:
raise HTTPException(status_code=404, detail=f"Tag {tag_id} not found.")
except Exception as exc:
if "unique" in str(exc).lower() or "UniqueViolation" in type(exc).__name__:
raise HTTPException(status_code=409, detail="You have already voted on this tag.")
logger.error("upvote_recipe_tag failed: %s", exc)
raise HTTPException(status_code=500, detail="Failed to upvote tag.")
tag_row["upvotes"] = new_upvotes
return _to_response(tag_row)

View file

@ -2,54 +2,21 @@
from __future__ import annotations from __future__ import annotations
import asyncio import asyncio
import logging
from pathlib import Path from pathlib import Path
from typing import Annotated from typing import Annotated
import json as _json_mod
from fastapi import APIRouter, Depends, HTTPException, Query from fastapi import APIRouter, Depends, HTTPException, Query
from fastapi.responses import StreamingResponse
from app.cloud_session import CloudUser, _auth_label, get_session from app.cloud_session import CloudUser, get_session
log = logging.getLogger(__name__)
from app.db.session import get_store
from app.db.store import Store from app.db.store import Store
from app.models.schemas.recipe import ( from app.models.schemas.recipe import RecipeRequest, RecipeResult
AskRequest,
AskResponse,
AskRecipeHit,
AssemblyTemplateOut,
BuildRequest,
LeftoversResponse,
RecipeJobStatus,
RecipeRequest,
RecipeResult,
RecipeSuggestion,
RoleCandidatesResponse,
StreamTokenRequest,
StreamTokenResponse,
)
from app.services.coordinator_proxy import CoordinatorError, coordinator_authorize
from app.api.endpoints.imitate import _build_recipe_prompt
from app.services.recipe.assembly_recipes import (
build_from_selection,
get_role_candidates,
get_templates_for_api,
)
from app.services.recipe.browser_domains import ( from app.services.recipe.browser_domains import (
DOMAINS, DOMAINS,
category_has_subcategories,
get_category_names, get_category_names,
get_domain_labels, get_domain_labels,
get_keywords_for_category, get_keywords_for_category,
get_keywords_for_subcategory,
get_subcategory_names,
) )
from app.services.recipe.recipe_engine import RecipeEngine from app.services.recipe.recipe_engine import RecipeEngine
from app.services.recipe.time_effort import parse_time_effort
from app.services.recipe.sensory import build_sensory_exclude
from app.services.heimdall_orch import check_orch_budget
from app.tiers import can_use from app.tiers import can_use
router = APIRouter() router = APIRouter()
@ -70,127 +37,13 @@ def _suggest_in_thread(db_path: Path, req: RecipeRequest) -> RecipeResult:
store.close() store.close()
def _build_stream_prompt(db_path: Path, level: int) -> str: @router.post("/suggest", response_model=RecipeResult)
"""Fetch pantry + user settings from DB and build the recipe prompt.
Runs in a thread (called via asyncio.to_thread) so it can use sync Store.
"""
import datetime
store = Store(db_path)
try:
items = store.list_inventory(status="available")
pantry_names = [i["product_name"] for i in items if i.get("product_name")]
today = datetime.date.today()
expiring_names = [
i["product_name"]
for i in items
if i.get("product_name")
and i.get("expiry_date")
and (datetime.date.fromisoformat(i["expiry_date"]) - today).days <= 3
]
settings: dict = {}
try:
rows = store.conn.execute("SELECT key, value FROM user_settings").fetchall()
settings = {r["key"]: r["value"] for r in rows}
except Exception:
pass
constraints_raw = settings.get("dietary_constraints", "")
constraints = [c.strip() for c in constraints_raw.split(",") if c.strip()] if constraints_raw else []
allergies_raw = settings.get("allergies", "")
allergies = [a.strip() for a in allergies_raw.split(",") if a.strip()] if allergies_raw else []
return _build_recipe_prompt(pantry_names, expiring_names, constraints, allergies, level)
finally:
store.close()
async def _stream_recipe_sse(db_path: Path, req: RecipeRequest):
"""Async generator that yields SSE events for a streaming recipe request.
Phase 1 (thread): classify pantry items using a temporary Store.
Phase 2 (async): stream tokens from LLM via LLMRecipeGenerator.stream_generate().
"""
def _prep(db_path: Path) -> tuple[list, list[str]]:
from app.services.recipe.element_classifier import IngredientClassifier
store = Store(db_path)
try:
classifier = IngredientClassifier(store)
profiles = classifier.classify_batch(req.pantry_items)
gaps = classifier.identify_gaps(profiles)
return profiles, gaps
finally:
store.close()
try:
profiles, gaps = await asyncio.to_thread(_prep, db_path)
except Exception as exc:
yield f"data: {_json_mod.dumps({'error': str(exc)})}\n\n"
return
from app.services.recipe.llm_recipe import LLMRecipeGenerator
gen = LLMRecipeGenerator(None)
try:
async for token in gen.stream_generate(req, profiles, gaps):
yield f"data: {_json_mod.dumps({'chunk': token})}\n\n"
yield f"data: {_json_mod.dumps({'done': True})}\n\n"
except Exception as exc:
yield f"data: {_json_mod.dumps({'error': str(exc)})}\n\n"
async def _enqueue_recipe_job(session: CloudUser, req: RecipeRequest):
"""Queue an async recipe_llm job and return 202 with job_id.
Falls back to synchronous generation in CLOUD_MODE (scheduler polls only
the shared settings DB, not per-user DBs see snipe#45 / kiwi backlog).
"""
import json
import uuid
from fastapi.responses import JSONResponse
from app.cloud_session import CLOUD_MODE
from app.tasks.runner import insert_task
if CLOUD_MODE:
log.warning("recipe_llm async jobs not supported in CLOUD_MODE — falling back to sync")
result = await asyncio.to_thread(_suggest_in_thread, session.db, req)
return result
job_id = f"rec_{uuid.uuid4().hex}"
def _create(db_path: Path) -> int:
store = Store(db_path)
try:
row = store.create_recipe_job(job_id, session.user_id, req.model_dump_json())
return row["id"]
finally:
store.close()
int_id = await asyncio.to_thread(_create, session.db)
params_json = json.dumps({"job_id": job_id})
task_id, is_new = insert_task(session.db, "recipe_llm", int_id, params=params_json)
if is_new:
from app.tasks.scheduler import get_scheduler
get_scheduler(session.db).enqueue(task_id, "recipe_llm", int_id, params_json)
return JSONResponse(content={"job_id": job_id, "status": "queued"}, status_code=202)
@router.post("/suggest")
async def suggest_recipes( async def suggest_recipes(
req: RecipeRequest, req: RecipeRequest,
async_mode: bool = Query(default=False, alias="async"),
stream: bool = Query(default=False),
session: CloudUser = Depends(get_session), session: CloudUser = Depends(get_session),
store: Store = Depends(get_store), ) -> RecipeResult:
):
log.info("recipes auth=%s tier=%s level=%s", _auth_label(session.user_id), session.tier, req.level)
# Inject session-authoritative tier/byok immediately — client-supplied values are ignored. # Inject session-authoritative tier/byok immediately — client-supplied values are ignored.
# Also read stored unit_system preference; default to metric if not set. req = req.model_copy(update={"tier": session.tier, "has_byok": session.has_byok})
unit_system = store.get_setting("unit_system") or "metric"
req = req.model_copy(update={"tier": session.tier, "has_byok": session.has_byok, "unit_system": unit_system})
if req.level == 4 and not req.wildcard_confirmed: if req.level == 4 and not req.wildcard_confirmed:
raise HTTPException( raise HTTPException(
status_code=400, status_code=400,
@ -203,105 +56,7 @@ async def suggest_recipes(
) )
if req.style_id and not can_use("style_picker", req.tier): if req.style_id and not can_use("style_picker", req.tier):
raise HTTPException(status_code=403, detail="Style picker requires Paid tier.") raise HTTPException(status_code=403, detail="Style picker requires Paid tier.")
return await asyncio.to_thread(_suggest_in_thread, session.db, req)
# Orch budget check for lifetime/founders keys — downgrade to L2 (local) if exhausted.
# Subscription and local/BYOK users skip this check entirely.
orch_fallback = False
if (
req.level in (3, 4)
and session.license_key is not None
and not session.has_byok
and session.tier != "local"
):
budget = check_orch_budget(session.license_key, "kiwi")
if not budget.get("allowed", True):
req = req.model_copy(update={"level": 2})
orch_fallback = True
if stream and req.level in (3, 4):
return StreamingResponse(
_stream_recipe_sse(session.db, req),
media_type="text/event-stream",
headers={"Cache-Control": "no-cache", "X-Accel-Buffering": "no"},
)
if req.level in (3, 4) and async_mode:
return await _enqueue_recipe_job(session, req)
result = await asyncio.to_thread(_suggest_in_thread, session.db, req)
if orch_fallback:
result = result.model_copy(update={"orch_fallback": True})
return result
@router.post("/stream-token", response_model=StreamTokenResponse)
async def get_stream_token(
req: StreamTokenRequest,
session: CloudUser = Depends(get_session),
) -> StreamTokenResponse:
"""Issue a one-time stream token for LLM recipe generation.
Tier-gated (Paid or BYOK). Builds the prompt from pantry + user settings,
then calls the cf-orch coordinator to obtain a stream URL. Returns
immediately the frontend opens EventSource to the stream URL directly.
"""
if not can_use("recipe_suggestions", session.tier, session.has_byok):
raise HTTPException(
status_code=403,
detail="Streaming recipe generation requires Paid tier or a configured LLM backend.",
)
if req.level == 4 and not req.wildcard_confirmed:
raise HTTPException(
status_code=400,
detail="Level 4 (Wildcard) streaming requires wildcard_confirmed=true.",
)
prompt = await asyncio.to_thread(_build_stream_prompt, session.db, req.level)
try:
result = await coordinator_authorize(prompt=prompt, caller="kiwi-recipe", ttl_s=300)
except CoordinatorError as exc:
raise HTTPException(status_code=exc.status_code, detail=str(exc))
return StreamTokenResponse(
stream_url=result.stream_url,
token=result.token,
expires_in_s=result.expires_in_s,
)
@router.get("/jobs/{job_id}", response_model=RecipeJobStatus)
async def get_recipe_job_status(
job_id: str,
session: CloudUser = Depends(get_session),
) -> RecipeJobStatus:
"""Poll the status of an async recipe generation job.
Returns 404 when job_id is unknown or belongs to a different user.
On status='done' with suggestions=[], the LLM returned empty client
should show a 'no recipe generated, try again' message.
"""
def _get(db_path: Path) -> dict | None:
store = Store(db_path)
try:
return store.get_recipe_job(job_id, session.user_id)
finally:
store.close()
row = await asyncio.to_thread(_get, session.db)
if row is None:
raise HTTPException(status_code=404, detail="Job not found.")
result = None
if row["status"] == "done" and row["result"]:
result = RecipeResult.model_validate_json(row["result"])
return RecipeJobStatus(
job_id=row["job_id"],
status=row["status"],
result=result,
error=row["error"],
)
@router.get("/browse/domains") @router.get("/browse/domains")
@ -321,42 +76,15 @@ async def list_browse_categories(
if domain not in DOMAINS: if domain not in DOMAINS:
raise HTTPException(status_code=404, detail=f"Unknown domain '{domain}'.") raise HTTPException(status_code=404, detail=f"Unknown domain '{domain}'.")
cat_names = get_category_names(domain) keywords_by_category = {
keywords_by_category = {cat: get_keywords_for_category(domain, cat) for cat in cat_names} cat: get_keywords_for_category(domain, cat)
has_subs = {cat: category_has_subcategories(domain, cat) for cat in cat_names} for cat in get_category_names(domain)
def _get(db_path: Path) -> list[dict]:
store = Store(db_path)
try:
return store.get_browser_categories(domain, keywords_by_category, has_subs)
finally:
store.close()
return await asyncio.to_thread(_get, session.db)
@router.get("/browse/{domain}/{category}/subcategories")
async def list_browse_subcategories(
domain: str,
category: str,
session: CloudUser = Depends(get_session),
) -> list[dict]:
"""Return [{subcategory, recipe_count}] for a category that supports subcategories."""
if domain not in DOMAINS:
raise HTTPException(status_code=404, detail=f"Unknown domain '{domain}'.")
if not category_has_subcategories(domain, category):
return []
subcat_names = get_subcategory_names(domain, category)
keywords_by_subcat = {
sub: get_keywords_for_subcategory(domain, category, sub)
for sub in subcat_names
} }
def _get(db_path: Path) -> list[dict]: def _get(db_path: Path) -> list[dict]:
store = Store(db_path) store = Store(db_path)
try: try:
return store.get_browser_subcategories(domain, keywords_by_subcat) return store.get_browser_categories(domain, keywords_by_category)
finally: finally:
store.close() store.close()
@ -370,33 +98,16 @@ async def browse_recipes(
page: Annotated[int, Query(ge=1)] = 1, page: Annotated[int, Query(ge=1)] = 1,
page_size: Annotated[int, Query(ge=1, le=100)] = 20, page_size: Annotated[int, Query(ge=1, le=100)] = 20,
pantry_items: Annotated[str | None, Query()] = None, pantry_items: Annotated[str | None, Query()] = None,
subcategory: Annotated[str | None, Query()] = None,
q: Annotated[str | None, Query(max_length=200)] = None,
sort: Annotated[str, Query(pattern="^(default|alpha|alpha_desc|match)$")] = "default",
required_ingredient: Annotated[str | None, Query(max_length=100)] = None,
session: CloudUser = Depends(get_session), session: CloudUser = Depends(get_session),
) -> dict: ) -> dict:
"""Return a paginated list of recipes for a domain/category. """Return a paginated list of recipes for a domain/category.
Pass pantry_items as a comma-separated string to receive match_pct badges. Pass pantry_items as a comma-separated string to receive match_pct
Pass subcategory to narrow within a category that has subcategories. badges on each result.
Pass q to filter by title substring. Pass sort for ordering (default/alpha/alpha_desc/match).
sort=match orders by pantry coverage DESC; falls back to default when no pantry_items.
Pass required_ingredient to restrict results to recipes that must include that ingredient.
""" """
if domain not in DOMAINS: if domain not in DOMAINS:
raise HTTPException(status_code=404, detail=f"Unknown domain '{domain}'.") raise HTTPException(status_code=404, detail=f"Unknown domain '{domain}'.")
if category == "_all":
keywords = None # unfiltered browse
elif subcategory:
keywords = get_keywords_for_subcategory(domain, category, subcategory)
if not keywords:
raise HTTPException(
status_code=404,
detail=f"Unknown subcategory '{subcategory}' in '{category}'.",
)
else:
keywords = get_keywords_for_category(domain, category) keywords = get_keywords_for_category(domain, category)
if not keywords: if not keywords:
raise HTTPException( raise HTTPException(
@ -413,90 +124,12 @@ async def browse_recipes(
def _browse(db_path: Path) -> dict: def _browse(db_path: Path) -> dict:
store = Store(db_path) store = Store(db_path)
try: try:
# Load sensory preferences
sensory_prefs_json = store.get_setting("sensory_preferences")
sensory_exclude = build_sensory_exclude(sensory_prefs_json)
result = store.browse_recipes( result = store.browse_recipes(
keywords=keywords, keywords=keywords,
page=page, page=page,
page_size=page_size, page_size=page_size,
pantry_items=pantry_list, pantry_items=pantry_list,
q=q or None,
sort=sort,
sensory_exclude=sensory_exclude,
required_ingredient=required_ingredient or None,
) )
# ── Attach time/effort signals to each browse result ────────────────
import json as _json
for recipe_row in result.get("recipes", []):
directions_raw = recipe_row.get("directions") or []
if isinstance(directions_raw, str):
try:
directions_raw = _json.loads(directions_raw)
except Exception:
directions_raw = []
if directions_raw:
_profile = parse_time_effort(
directions_raw,
ingredients=recipe_row.get("ingredients") or [],
ingredient_names=recipe_row.get("ingredient_names") or [],
)
recipe_row["active_min"] = _profile.active_min
recipe_row["passive_min"] = _profile.passive_min
else:
recipe_row["active_min"] = None
recipe_row["passive_min"] = None
# Remove directions from browse payload — not needed by the card UI
recipe_row.pop("directions", None)
# Community tag fallback: if FTS returned nothing for a subcategory,
# check whether accepted community tags exist for this location and
# fetch those corpus recipes directly by ID.
if result["total"] == 0 and subcategory and keywords:
try:
from app.api.endpoints.community import _get_community_store
cs = _get_community_store()
if cs is not None:
community_ids = cs.get_accepted_recipe_ids_for_subcategory(
domain=domain,
category=category,
subcategory=subcategory,
)
if community_ids:
offset = (page - 1) * page_size
paged_ids = community_ids[offset: offset + page_size]
recipes = store.fetch_recipes_by_ids(paged_ids, pantry_list)
import json as _json_c
for recipe_row in recipes:
directions_raw = recipe_row.get("directions") or []
if isinstance(directions_raw, str):
try:
directions_raw = _json_c.loads(directions_raw)
except Exception:
directions_raw = []
if directions_raw:
_profile = parse_time_effort(
directions_raw,
ingredients=recipe_row.get("ingredients") or [],
ingredient_names=recipe_row.get("ingredient_names") or [],
)
recipe_row["active_min"] = _profile.active_min
recipe_row["passive_min"] = _profile.passive_min
else:
recipe_row["active_min"] = None
recipe_row["passive_min"] = None
recipe_row.pop("directions", None)
result = {
"recipes": recipes,
"total": len(community_ids),
"page": page,
"community_tagged": True,
}
except Exception as exc:
logger.warning("community tag fallback failed: %s", exc)
store.log_browser_telemetry( store.log_browser_telemetry(
domain=domain, domain=domain,
category=category, category=category,
@ -510,227 +143,6 @@ async def browse_recipes(
return await asyncio.to_thread(_browse, session.db) return await asyncio.to_thread(_browse, session.db)
@router.get("/templates", response_model=list[AssemblyTemplateOut])
async def list_assembly_templates() -> list[dict]:
"""Return all 13 assembly templates with ordered role sequences.
Cache-friendly: static data, no per-user state.
"""
return get_templates_for_api()
@router.get("/template-candidates", response_model=RoleCandidatesResponse)
async def get_template_role_candidates(
template_id: str = Query(..., description="Template slug, e.g. 'burrito_taco'"),
role: str = Query(..., description="Role display name, e.g. 'protein'"),
prior_picks: str = Query(default="", description="Comma-separated prior selections"),
session: CloudUser = Depends(get_session),
) -> dict:
"""Return pantry-matched candidates for one wizard step."""
def _get(db_path: Path) -> dict:
store = Store(db_path)
try:
items = store.list_inventory(status="available")
pantry_set = {
item["product_name"]
for item in items
if item.get("product_name")
}
pantry_list = list(pantry_set)
prior = [p.strip() for p in prior_picks.split(",") if p.strip()]
profile_index = store.get_element_profiles(pantry_list + prior)
return get_role_candidates(
template_slug=template_id,
role_display=role,
pantry_set=pantry_set,
prior_picks=prior,
profile_index=profile_index,
)
finally:
store.close()
return await asyncio.to_thread(_get, session.db)
@router.post("/build", response_model=RecipeSuggestion)
async def build_recipe(
req: BuildRequest,
session: CloudUser = Depends(get_session),
) -> RecipeSuggestion:
"""Build a recipe from explicit role selections."""
def _build(db_path: Path) -> RecipeSuggestion | None:
store = Store(db_path)
try:
items = store.list_inventory(status="available")
pantry_set = {
item["product_name"]
for item in items
if item.get("product_name")
}
suggestion = build_from_selection(
template_slug=req.template_id,
role_overrides=req.role_overrides,
pantry_set=pantry_set,
)
if suggestion is None:
return None
# Persist to recipes table so the result can be saved/bookmarked.
# external_id encodes template + selections for stable dedup.
import hashlib as _hl, json as _js
sel_hash = _hl.md5(
_js.dumps(req.role_overrides, sort_keys=True).encode()
).hexdigest()[:8]
external_id = f"assembly:{req.template_id}:{sel_hash}"
real_id = store.upsert_built_recipe(
external_id=external_id,
title=suggestion.title,
ingredients=suggestion.matched_ingredients,
directions=suggestion.directions,
)
return suggestion.model_copy(update={"id": real_id})
finally:
store.close()
result = await asyncio.to_thread(_build, session.db)
if result is None:
raise HTTPException(
status_code=404,
detail="Template not found or required ingredient missing.",
)
return result
_ASK_STOPWORDS: frozenset[str] = frozenset({
"what", "can", "make", "with", "have", "some", "the", "and", "for",
"that", "this", "these", "those", "how", "about", "are", "there",
"give", "show", "find", "want", "need", "like", "any", "good",
"quick", "easy", "simple", "fast", "using", "use", "from", "into",
"more", "much", "just", "only", "my", "please", "could", "would",
"should", "something", "anything", "everything", "ideas", "idea",
"suggest", "meal", "food", "dish", "dishes", "today", "tonight",
"tomorrow", "now", "here", "there", "recipes", "recipe", "dinner",
"lunch", "breakfast", "snack", "under", "minutes", "hours", "time",
"left", "over", "also", "some", "make", "cook", "made", "cooked",
})
import re as _re
def _extract_ask_keywords(question: str) -> list[str]:
"""Extract food-relevant keywords from a natural language question."""
tokens = _re.findall(r"[a-zA-Z]+", question.lower())
return [t for t in tokens if len(t) > 3 and t not in _ASK_STOPWORDS]
def _ask_in_thread(db_path: Path, question: str, pantry_items: list[str]) -> AskResponse:
"""Run Ask logic in a worker thread.
Free tier: keyword extraction + FTS ingredient search.
Paid tier path: same search, then LLM synthesis over results.
The caller handles tier gating and LLM synthesis outside this thread
to avoid importing LLMRouter in a sync context.
"""
import json as _json
store = Store(db_path)
try:
keywords = _extract_ask_keywords(question)
ingredient_hits: list[dict] = []
if keywords:
ingredient_hits = store.search_recipes_by_ingredients(keywords, limit=15)
# Also search by title using the full question text as a substring hint.
# browse_recipes q= does title LIKE %q%. Extract the longest keyword
# from the question as the title probe (most likely to appear in a title).
title_hits: list[dict] = []
title_probe = max(keywords, key=len) if keywords else None
if title_probe:
browse_result = store.browse_recipes(
keywords=None,
page=1,
page_size=12,
pantry_items=pantry_items or None,
q=title_probe,
sort="match" if pantry_items else "default",
)
title_hits = browse_result.get("recipes", [])
# Merge by ID; ingredient hits come first (more semantically relevant).
seen: set[int] = set()
merged: list[dict] = []
for row in ingredient_hits + title_hits:
rid = row.get("id")
if rid is not None and rid not in seen:
seen.add(rid)
merged.append(row)
# Compute pantry match_pct if caller sent pantry items.
pantry_set = {p.lower() for p in pantry_items} if pantry_items else set()
hits: list[AskRecipeHit] = []
for row in merged[:12]:
match_pct: float | None = None
if pantry_set:
raw_names = row.get("ingredient_names") or []
if isinstance(raw_names, str):
try:
raw_names = _json.loads(raw_names)
except Exception:
raw_names = []
if raw_names:
covered = sum(
1 for n in raw_names
if any(p in n.lower() for p in pantry_set)
)
match_pct = round(covered / len(raw_names), 2)
hits.append(AskRecipeHit(
id=row["id"],
title=row.get("title", ""),
category=row.get("category"),
match_pct=match_pct,
))
return AskResponse(answer=None, recipes=hits, tier="free")
finally:
store.close()
@router.post("/ask", response_model=AskResponse)
async def ask_recipes(
req: AskRequest,
session: CloudUser = Depends(get_session),
) -> AskResponse:
"""Natural-language recipe search with optional LLM synthesis.
Free tier: keyword extraction from question FTS ingredient + title search.
Paid tier / BYOK: same search, then LLM synthesizes a short conversational answer.
"""
result = await asyncio.to_thread(_ask_in_thread, session.db, req.question, req.pantry_items)
# LLM synthesis: only for paid/premium/ultra tiers, not "local" dev tier.
# Wrapped in wait_for so an unresponsive model degrades gracefully to recipe list only.
paid_tier = session.tier in ("paid", "premium", "ultra")
if (paid_tier or session.has_byok) and result.recipes:
recipe_titles = ", ".join(r.title for r in result.recipes[:6])
prompt = (
f'You are a helpful kitchen assistant. The user asked: "{req.question}"\n\n'
f"Matching recipes: {recipe_titles}\n\n"
f"Write a brief, friendly 12 sentence response suggesting which of these "
f"recipes might best fit the question. Be specific and natural."
)
try:
from circuitforge_core.llm.router import LLMRouter
answer = await asyncio.wait_for(
asyncio.to_thread(LLMRouter().complete, prompt),
timeout=8.0,
)
result = result.model_copy(update={"answer": answer.strip() or None, "tier": "paid"})
except (Exception, asyncio.TimeoutError) as exc:
log.warning("Ask LLM synthesis skipped: %s", exc)
return result
@router.get("/{recipe_id}") @router.get("/{recipe_id}")
async def get_recipe(recipe_id: int, session: CloudUser = Depends(get_session)) -> dict: async def get_recipe(recipe_id: int, session: CloudUser = Depends(get_session)) -> dict:
def _get(db_path: Path, rid: int) -> dict | None: def _get(db_path: Path, rid: int) -> dict | None:
@ -743,111 +155,4 @@ async def get_recipe(recipe_id: int, session: CloudUser = Depends(get_session))
recipe = await asyncio.to_thread(_get, session.db, recipe_id) recipe = await asyncio.to_thread(_get, session.db, recipe_id)
if not recipe: if not recipe:
raise HTTPException(status_code=404, detail="Recipe not found.") raise HTTPException(status_code=404, detail="Recipe not found.")
return recipe
# Normalize corpus record into RecipeSuggestion shape so RecipeDetailPanel
# can render it without knowing it came from a direct DB lookup.
ingredient_names = recipe.get("ingredient_names") or []
if isinstance(ingredient_names, str):
import json as _json
try:
ingredient_names = _json.loads(ingredient_names)
except Exception:
ingredient_names = []
_directions_for_te = recipe.get("directions") or []
if isinstance(_directions_for_te, str):
import json as _json2
try:
_directions_for_te = _json2.loads(_directions_for_te)
except Exception:
_directions_for_te = []
_ingredients_for_te = recipe.get("ingredients") or []
if isinstance(_ingredients_for_te, str):
import json as _json3
try:
_ingredients_for_te = _json3.loads(_ingredients_for_te)
except Exception:
_ingredients_for_te = []
_ingredient_names_for_te = recipe.get("ingredient_names") or []
if isinstance(_ingredient_names_for_te, str):
import json as _json4
try:
_ingredient_names_for_te = _json4.loads(_ingredient_names_for_te)
except Exception:
_ingredient_names_for_te = []
if _directions_for_te:
_te = parse_time_effort(
_directions_for_te,
ingredients=_ingredients_for_te,
ingredient_names=_ingredient_names_for_te,
)
_time_effort_out: dict | None = {
"active_min": _te.active_min,
"passive_min": _te.passive_min,
"total_min": _te.total_min,
"effort_label": _te.effort_label,
"equipment": _te.equipment,
"step_analyses": [
{
"is_passive": sa.is_passive,
"detected_minutes": sa.detected_minutes,
"prep_min": sa.prep_min,
}
for sa in _te.step_analyses
],
}
else:
_time_effort_out = None
return {
"id": recipe.get("id"),
"title": recipe.get("title", ""),
"match_count": 0,
"matched_ingredients": ingredient_names,
"missing_ingredients": [],
"directions": recipe.get("directions") or [],
"prep_notes": [],
"swap_candidates": [],
"element_coverage": {},
"notes": recipe.get("notes") or "",
"level": 1,
"is_wildcard": False,
"nutrition": None,
"source_url": recipe.get("source_url") or None,
"complexity": None,
"estimated_time_min": None,
"time_effort": _time_effort_out,
}
@router.post("/{recipe_id}/leftovers", response_model=LeftoversResponse)
async def get_leftovers_shelf_life(
recipe_id: int,
session: CloudUser = Depends(get_session),
) -> LeftoversResponse:
"""Return cooked-leftover shelf-life estimate for a recipe.
Free tier: deterministic lookup (FDA/USDA table).
Deterministic path always runs; no tier gate needed.
"""
def _get(db_path: Path, rid: int) -> LeftoversResponse:
from app.services.leftovers_predictor import predict_leftovers_from_row
store = Store(db_path)
try:
recipe = store.get_recipe(rid)
finally:
store.close()
if recipe is None:
raise HTTPException(status_code=404, detail="Recipe not found.")
result = predict_leftovers_from_row(recipe)
return LeftoversResponse(
fridge_days=result.fridge_days,
freeze_days=result.freeze_days,
freeze_by_day=result.freeze_by_day,
storage_advice=result.storage_advice,
)
return await asyncio.to_thread(_get, session.db, recipe_id)

View file

@ -5,7 +5,6 @@ import asyncio
from pathlib import Path from pathlib import Path
from fastapi import APIRouter, Depends, HTTPException from fastapi import APIRouter, Depends, HTTPException
from pydantic import BaseModel
from app.cloud_session import CloudUser, get_session from app.cloud_session import CloudUser, get_session
from app.db.store import Store from app.db.store import Store
@ -17,13 +16,8 @@ from app.models.schemas.saved_recipe import (
SaveRecipeRequest, SaveRecipeRequest,
UpdateSavedRecipeRequest, UpdateSavedRecipeRequest,
) )
from app.services.magpie_hook import fire_recipe_signal
from app.tiers import can_use from app.tiers import can_use
class StyleClassifyResponse(BaseModel):
suggested_tags: list[str]
router = APIRouter() router = APIRouter()
@ -41,7 +35,7 @@ def _to_summary(row: dict, store: Store) -> SavedRecipeSummary:
return SavedRecipeSummary( return SavedRecipeSummary(
id=row["id"], id=row["id"],
recipe_id=row["recipe_id"], recipe_id=row["recipe_id"],
title=row.get("title") or "", title=row.get("title", ""),
saved_at=row["saved_at"], saved_at=row["saved_at"],
notes=row.get("notes"), notes=row.get("notes"),
rating=row.get("rating"), rating=row.get("rating"),
@ -61,9 +55,7 @@ async def save_recipe(
row = store.save_recipe(req.recipe_id, req.notes, req.rating) row = store.save_recipe(req.recipe_id, req.notes, req.rating)
return _to_summary(row, store) return _to_summary(row, store)
result = await asyncio.to_thread(_in_thread, session.db, _run) return await asyncio.to_thread(_in_thread, session.db, _run)
asyncio.create_task(fire_recipe_signal(session.db, req.recipe_id, req.rating, []))
return result
@router.delete("/{recipe_id}", status_code=204) @router.delete("/{recipe_id}", status_code=204)
@ -90,11 +82,7 @@ async def update_saved_recipe(
) )
return _to_summary(row, store) return _to_summary(row, store)
result = await asyncio.to_thread(_in_thread, session.db, _run) return await asyncio.to_thread(_in_thread, session.db, _run)
asyncio.create_task(
fire_recipe_signal(session.db, recipe_id, req.rating, req.style_tags or [])
)
return result
@router.get("", response_model=list[SavedRecipeSummary]) @router.get("", response_model=list[SavedRecipeSummary])
@ -110,37 +98,12 @@ async def list_saved_recipes(
return await asyncio.to_thread(_in_thread, session.db, _run) return await asyncio.to_thread(_in_thread, session.db, _run)
# ── style classifier (Paid / BYOK) ───────────────────────────────────────────
@router.post("/{recipe_id}/classify-style", response_model=StyleClassifyResponse)
async def classify_style(
recipe_id: int,
session: CloudUser = Depends(get_session),
) -> StyleClassifyResponse:
if not can_use("style_classifier", session.tier, getattr(session, "has_byok", False)):
raise HTTPException(status_code=403, detail="Style classifier requires Paid tier or BYOK.")
def _run(store: Store) -> StyleClassifyResponse:
recipe = store.get_recipe(recipe_id)
if recipe is None:
raise HTTPException(status_code=404, detail="Recipe not found.")
from app.services.recipe.style_classifier import classify_style as _classify
tags = _classify(recipe)
return StyleClassifyResponse(suggested_tags=tags)
return await asyncio.to_thread(_in_thread, session.db, _run)
# ── collections (Paid) ──────────────────────────────────────────────────────── # ── collections (Paid) ────────────────────────────────────────────────────────
@router.get("/collections", response_model=list[CollectionSummary]) @router.get("/collections", response_model=list[CollectionSummary])
async def list_collections( async def list_collections(
session: CloudUser = Depends(get_session), session: CloudUser = Depends(get_session),
) -> list[CollectionSummary]: ) -> list[CollectionSummary]:
# Free users can list (they'll always have zero — creating requires Paid).
# Returning 403 here breaks savedStore.load() via Promise.all for non-Paid users.
if not can_use("recipe_collections", session.tier):
return []
rows = await asyncio.to_thread( rows = await asyncio.to_thread(
_in_thread, session.db, lambda s: s.get_collections() _in_thread, session.db, lambda s: s.get_collections()
) )

View file

@ -1,37 +0,0 @@
"""Session bootstrap endpoint — called once per app load by the frontend.
Logs auth= + tier= for log-based analytics without client-side tracking.
See Circuit-Forge/kiwi#86.
"""
from __future__ import annotations
import logging
from fastapi import APIRouter, Depends
from app.cloud_session import CloudUser, _auth_label, get_session
from app.core.config import settings
router = APIRouter()
log = logging.getLogger(__name__)
@router.get("/bootstrap")
def session_bootstrap(session: CloudUser = Depends(get_session)) -> dict:
"""Record auth type and tier for log-based analytics.
Expected log output:
INFO:app.api.endpoints.session: session auth=authed tier=paid
INFO:app.api.endpoints.session: session auth=anon tier=free
E2E test sessions (E2E_TEST_USER_ID) are logged at DEBUG so they don't
pollute analytics counts while still being visible when DEBUG=true.
"""
is_test = bool(settings.E2E_TEST_USER_ID and session.user_id == settings.E2E_TEST_USER_ID)
logger = log.debug if is_test else log.info
logger("session auth=%s tier=%s%s", _auth_label(session.user_id), session.tier, " e2e=true" if is_test else "")
return {
"auth": _auth_label(session.user_id),
"tier": session.tier,
"has_byok": session.has_byok,
}

View file

@ -10,7 +10,7 @@ from app.db.store import Store
router = APIRouter() router = APIRouter()
_ALLOWED_KEYS = frozenset({"cooking_equipment", "unit_system", "shopping_locale", "sensory_preferences", "time_first_layout"}) _ALLOWED_KEYS = frozenset({"cooking_equipment"})
class SettingBody(BaseModel): class SettingBody(BaseModel):

View file

@ -1,233 +0,0 @@
"""Shopping list endpoints.
Free tier for all users (anonymous guests included shopping list is the
primary affiliate revenue surface). Confirm-purchase action is also Free:
it moves a checked item into pantry inventory without a tier gate so the
flow works for anyone who signs up or browses without an account.
Routes:
GET /shopping list items (with affiliate links)
POST /shopping add item manually
PATCH /shopping/{id} update (check/uncheck, rename, qty)
DELETE /shopping/{id} remove single item
DELETE /shopping/checked clear all checked items
DELETE /shopping/all clear entire list
POST /shopping/from-recipe bulk add gaps from a recipe
POST /shopping/{id}/confirm confirm purchase add to pantry inventory
"""
from __future__ import annotations
import asyncio
import logging
from fastapi import APIRouter, Depends, HTTPException, status
from app.cloud_session import CloudUser, get_session
from app.db.session import get_store
from app.db.store import Store
from app.models.schemas.shopping import (
BulkAddFromRecipeRequest,
ConfirmPurchaseRequest,
ShoppingItemCreate,
ShoppingItemResponse,
ShoppingItemUpdate,
)
from app.services.recipe.grocery_links import GroceryLinkBuilder
log = logging.getLogger(__name__)
router = APIRouter()
def _enrich(item: dict, builder: GroceryLinkBuilder) -> ShoppingItemResponse:
"""Attach live affiliate links to a raw store row."""
links = builder.build_links(item["name"])
return ShoppingItemResponse(
**{**item, "checked": bool(item.get("checked", 0))},
grocery_links=[{"ingredient": l.ingredient, "retailer": l.retailer, "url": l.url} for l in links],
)
def _in_thread(db_path, fn):
store = Store(db_path)
try:
return fn(store)
finally:
store.close()
# ── List ──────────────────────────────────────────────────────────────────────
def _locale_from_store(store: Store) -> str:
return store.get_setting("shopping_locale") or "us"
@router.get("", response_model=list[ShoppingItemResponse])
async def list_shopping_items(
include_checked: bool = True,
session: CloudUser = Depends(get_session),
store: Store = Depends(get_store),
):
locale = await asyncio.to_thread(_in_thread, session.db, _locale_from_store)
builder = GroceryLinkBuilder(tier=session.tier, has_byok=session.has_byok, locale=locale)
items = await asyncio.to_thread(
_in_thread, session.db, lambda s: s.list_shopping_items(include_checked)
)
return [_enrich(i, builder) for i in items]
# ── Add manually ──────────────────────────────────────────────────────────────
@router.post("", response_model=ShoppingItemResponse, status_code=status.HTTP_201_CREATED)
async def add_shopping_item(
body: ShoppingItemCreate,
session: CloudUser = Depends(get_session),
store: Store = Depends(get_store),
):
builder = GroceryLinkBuilder(tier=session.tier, has_byok=session.has_byok, locale=_locale_from_store(store))
item = await asyncio.to_thread(
_in_thread,
session.db,
lambda s: s.add_shopping_item(
name=body.name,
quantity=body.quantity,
unit=body.unit,
category=body.category,
notes=body.notes,
source=body.source,
recipe_id=body.recipe_id,
sort_order=body.sort_order,
),
)
return _enrich(item, builder)
# ── Bulk add from recipe ───────────────────────────────────────────────────────
@router.post("/from-recipe", response_model=list[ShoppingItemResponse], status_code=status.HTTP_201_CREATED)
async def add_from_recipe(
body: BulkAddFromRecipeRequest,
session: CloudUser = Depends(get_session),
store: Store = Depends(get_store),
):
"""Add missing ingredients from a recipe to the shopping list.
Runs pantry gap analysis and adds only the items the user doesn't have
(unless include_covered=True). Skips duplicates already on the list.
"""
from app.services.meal_plan.shopping_list import compute_shopping_list
def _run(store: Store):
recipe = store.get_recipe(body.recipe_id)
if not recipe:
raise HTTPException(status_code=404, detail="Recipe not found")
inventory = store.list_inventory()
gaps, covered = compute_shopping_list([recipe], inventory)
targets = (gaps + covered) if body.include_covered else gaps
# Avoid duplicates already on the list
existing = {i["name"].lower() for i in store.list_shopping_items()}
added = []
for gap in targets:
if gap.ingredient_name.lower() in existing:
continue
item = store.add_shopping_item(
name=gap.ingredient_name,
quantity=None,
unit=gap.have_unit,
source="recipe",
recipe_id=body.recipe_id,
)
added.append(item)
return added
builder = GroceryLinkBuilder(tier=session.tier, has_byok=session.has_byok, locale=_locale_from_store(store))
items = await asyncio.to_thread(_in_thread, session.db, _run)
return [_enrich(i, builder) for i in items]
# ── Update ────────────────────────────────────────────────────────────────────
@router.patch("/{item_id}", response_model=ShoppingItemResponse)
async def update_shopping_item(
item_id: int,
body: ShoppingItemUpdate,
session: CloudUser = Depends(get_session),
store: Store = Depends(get_store),
):
builder = GroceryLinkBuilder(tier=session.tier, has_byok=session.has_byok, locale=_locale_from_store(store))
item = await asyncio.to_thread(
_in_thread,
session.db,
lambda s: s.update_shopping_item(item_id, **body.model_dump(exclude_none=True)),
)
if not item:
raise HTTPException(status_code=404, detail="Shopping item not found")
return _enrich(item, builder)
# ── Confirm purchase → pantry ─────────────────────────────────────────────────
@router.post("/{item_id}/confirm", status_code=status.HTTP_201_CREATED)
async def confirm_purchase(
item_id: int,
body: ConfirmPurchaseRequest,
session: CloudUser = Depends(get_session),
):
"""Confirm a checked item was purchased and add it to pantry inventory.
Human approval step: the user explicitly confirms what they actually bought
before it lands in their pantry. Returns the new inventory item.
"""
def _run(store: Store):
shopping_item = store.get_shopping_item(item_id)
if not shopping_item:
raise HTTPException(status_code=404, detail="Shopping item not found")
qty = body.quantity if body.quantity is not None else (shopping_item.get("quantity") or 1.0)
unit = body.unit or shopping_item.get("unit") or "count"
category = shopping_item.get("category")
product = store.get_or_create_product(
name=shopping_item["name"],
category=category,
)
inv_item = store.add_inventory_item(
product_id=product["id"],
location=body.location,
quantity=qty,
unit=unit,
source="manual",
)
# Mark the shopping item checked and leave it for the user to clear
store.update_shopping_item(item_id, checked=True)
return inv_item
return await asyncio.to_thread(_in_thread, session.db, _run)
# ── Delete ────────────────────────────────────────────────────────────────────
@router.delete("/{item_id}", status_code=status.HTTP_204_NO_CONTENT)
async def delete_shopping_item(
item_id: int,
session: CloudUser = Depends(get_session),
):
deleted = await asyncio.to_thread(
_in_thread, session.db, lambda s: s.delete_shopping_item(item_id)
)
if not deleted:
raise HTTPException(status_code=404, detail="Shopping item not found")
@router.delete("/checked", status_code=status.HTTP_204_NO_CONTENT)
async def clear_checked(session: CloudUser = Depends(get_session)):
await asyncio.to_thread(
_in_thread, session.db, lambda s: s.clear_checked_shopping_items()
)
@router.delete("/all", status_code=status.HTTP_204_NO_CONTENT)
async def clear_all(session: CloudUser = Depends(get_session)):
await asyncio.to_thread(
_in_thread, session.db, lambda s: s.clear_all_shopping_items()
)

View file

@ -1,34 +1,16 @@
from fastapi import APIRouter from fastapi import APIRouter
from app.api.endpoints import health, receipts, export, inventory, ocr, recipes, settings, staples, feedback, feedback_attach, household, saved_recipes, imitate, meal_plans, orch_usage, session, shopping from app.api.endpoints import health, receipts, export, inventory, ocr, recipes, settings, staples, feedback, household, saved_recipes
from app.api.endpoints.community import router as community_router
from app.api.endpoints.corrections import router as corrections_router
from app.api.endpoints.mastodon_oauth import router as mastodon_router
from app.api.endpoints.recipe_scan import router as recipe_scan_router
from app.api.endpoints.recipe_tags import router as recipe_tags_router
api_router = APIRouter() api_router = APIRouter()
api_router.include_router(session.router, prefix="/session", tags=["session"])
api_router.include_router(health.router, prefix="/health", tags=["health"]) api_router.include_router(health.router, prefix="/health", tags=["health"])
api_router.include_router(receipts.router, prefix="/receipts", tags=["receipts"]) api_router.include_router(receipts.router, prefix="/receipts", tags=["receipts"])
api_router.include_router(ocr.router, prefix="/receipts", tags=["ocr"]) api_router.include_router(ocr.router, prefix="/receipts", tags=["ocr"])
api_router.include_router(export.router, tags=["export"]) api_router.include_router(export.router, tags=["export"])
api_router.include_router(inventory.router, prefix="/inventory", tags=["inventory"]) api_router.include_router(inventory.router, prefix="/inventory", tags=["inventory"])
api_router.include_router(saved_recipes.router, prefix="/recipes/saved", tags=["saved-recipes"])
# recipe_scan_router registered BEFORE recipes.router so /recipes/scan and /recipes/user
# take priority over /recipes/{recipe_id} (which would otherwise match them as int IDs).
api_router.include_router(recipe_scan_router, prefix="/recipes", tags=["recipe-scan"])
api_router.include_router(recipes.router, prefix="/recipes", tags=["recipes"]) api_router.include_router(recipes.router, prefix="/recipes", tags=["recipes"])
api_router.include_router(settings.router, prefix="/settings", tags=["settings"]) api_router.include_router(settings.router, prefix="/settings", tags=["settings"])
api_router.include_router(staples.router, prefix="/staples", tags=["staples"]) api_router.include_router(staples.router, prefix="/staples", tags=["staples"])
api_router.include_router(feedback.router, prefix="/feedback", tags=["feedback"]) api_router.include_router(feedback.router, prefix="/feedback", tags=["feedback"])
api_router.include_router(feedback_attach.router, prefix="/feedback", tags=["feedback"])
api_router.include_router(household.router, prefix="/household", tags=["household"]) api_router.include_router(household.router, prefix="/household", tags=["household"])
api_router.include_router(imitate.router, prefix="/imitate", tags=["imitate"]) api_router.include_router(saved_recipes.router, prefix="/recipes/saved", tags=["saved-recipes"])
api_router.include_router(meal_plans.router, prefix="/meal-plans", tags=["meal-plans"])
api_router.include_router(orch_usage.router, prefix="/orch-usage", tags=["orch-usage"])
api_router.include_router(shopping.router, prefix="/shopping", tags=["shopping"])
api_router.include_router(community_router)
api_router.include_router(recipe_tags_router)
api_router.include_router(corrections_router, prefix="/corrections", tags=["corrections"])
api_router.include_router(mastodon_router)

View file

@ -1,9 +1,11 @@
"""Cloud session resolution for Kiwi FastAPI. """Cloud session resolution for Kiwi FastAPI.
Delegates JWT validation, Heimdall provisioning, tier resolution, and guest Local mode (CLOUD_MODE unset/false): returns a local CloudUser with no auth
session management to circuitforge_core.CloudSessionFactory. Kiwi-specific checks, full tier access, and DB path pointing to settings.DB_PATH.
CloudUser (per-user DB path, household data, BYOK flag) and DB helpers are
kept here. Cloud mode (CLOUD_MODE=true): validates the cf_session JWT injected by Caddy
as X-CF-Session, resolves user_id, auto-provisions a free Heimdall license on
first visit, fetches the tier, and returns a per-user DB path.
FastAPI usage: FastAPI usage:
@app.get("/api/v1/inventory/items") @app.get("/api/v1/inventory/items")
@ -15,11 +17,15 @@ from __future__ import annotations
import logging import logging
import os import os
import re
import time
from dataclasses import dataclass from dataclasses import dataclass
from pathlib import Path from pathlib import Path
from circuitforge_core.cloud_session import CloudSessionFactory as _CoreFactory, detect_byok import jwt as pyjwt
from fastapi import Depends, HTTPException, Request, Response import requests
import yaml
from fastapi import Depends, HTTPException, Request
log = logging.getLogger(__name__) log = logging.getLogger(__name__)
@ -27,22 +33,54 @@ log = logging.getLogger(__name__)
CLOUD_MODE: bool = os.environ.get("CLOUD_MODE", "").lower() in ("1", "true", "yes") CLOUD_MODE: bool = os.environ.get("CLOUD_MODE", "").lower() in ("1", "true", "yes")
CLOUD_DATA_ROOT: Path = Path(os.environ.get("CLOUD_DATA_ROOT", "/devl/kiwi-cloud-data")) CLOUD_DATA_ROOT: Path = Path(os.environ.get("CLOUD_DATA_ROOT", "/devl/kiwi-cloud-data"))
DIRECTUS_JWT_SECRET: str = os.environ.get("DIRECTUS_JWT_SECRET", "")
HEIMDALL_URL: str = os.environ.get("HEIMDALL_URL", "https://license.circuitforge.tech")
HEIMDALL_ADMIN_TOKEN: str = os.environ.get("HEIMDALL_ADMIN_TOKEN", "")
# Dev bypass: comma-separated IPs or CIDR ranges that skip JWT auth.
# NEVER set this in production. Intended only for LAN developer testing when
# the request doesn't pass through Caddy (which normally injects X-CF-Session).
# Example: CLOUD_AUTH_BYPASS_IPS=10.1.10.0/24,127.0.0.1
import ipaddress as _ipaddress
_BYPASS_RAW: list[str] = [
e.strip()
for e in os.environ.get("CLOUD_AUTH_BYPASS_IPS", "").split(",")
if e.strip()
]
_BYPASS_NETS: list[_ipaddress.IPv4Network | _ipaddress.IPv6Network] = []
_BYPASS_IPS: frozenset[str] = frozenset()
if _BYPASS_RAW:
_nets, _ips = [], set()
for entry in _BYPASS_RAW:
try:
_nets.append(_ipaddress.ip_network(entry, strict=False))
except ValueError:
_ips.add(entry) # treat non-parseable entries as bare IPs
_BYPASS_NETS = _nets
_BYPASS_IPS = frozenset(_ips)
def _is_bypass_ip(ip: str) -> bool:
if not ip:
return False
if ip in _BYPASS_IPS:
return True
try:
addr = _ipaddress.ip_address(ip)
return any(addr in net for net in _BYPASS_NETS)
except ValueError:
return False
_LOCAL_KIWI_DB: Path = Path(os.environ.get("KIWI_DB", "data/kiwi.db")) _LOCAL_KIWI_DB: Path = Path(os.environ.get("KIWI_DB", "data/kiwi.db"))
_TIER_CACHE: dict[str, tuple[dict, float]] = {}
_TIER_CACHE_TTL = 300 # 5 minutes
TIERS = ["free", "paid", "premium", "ultra"] TIERS = ["free", "paid", "premium", "ultra"]
_core = _CoreFactory(product="kiwi", byok_detector=detect_byok)
def _auth_label(user_id: str) -> str:
"""Classify a user_id into a short tag for structured log lines. No PII emitted."""
if user_id in ("local", "local-dev"):
return "local"
if user_id.startswith("anon-"):
return "anon"
return "authed"
# ── Domain ──────────────────────────────────────────────────────────────────── # ── Domain ────────────────────────────────────────────────────────────────────
@ -54,10 +92,74 @@ class CloudUser:
has_byok: bool # True if a configured LLM backend is present in llm.yaml has_byok: bool # True if a configured LLM backend is present in llm.yaml
household_id: str | None = None household_id: str | None = None
is_household_owner: bool = False is_household_owner: bool = False
license_key: str | None = None # key_display for lifetime/founders keys; None for subscription/free
# ── DB path helpers ─────────────────────────────────────────────────────────── # ── JWT validation ─────────────────────────────────────────────────────────────
def _extract_session_token(header_value: str) -> str:
m = re.search(r'(?:^|;)\s*cf_session=([^;]+)', header_value)
return m.group(1).strip() if m else header_value.strip()
def validate_session_jwt(token: str) -> str:
"""Validate cf_session JWT and return the Directus user_id."""
try:
payload = pyjwt.decode(
token,
DIRECTUS_JWT_SECRET,
algorithms=["HS256"],
options={"require": ["id", "exp"]},
)
return payload["id"]
except Exception as exc:
log.debug("JWT validation failed: %s", exc)
raise HTTPException(status_code=401, detail="Session invalid or expired")
# ── Heimdall integration ──────────────────────────────────────────────────────
def _ensure_provisioned(user_id: str) -> None:
if not HEIMDALL_ADMIN_TOKEN:
return
try:
requests.post(
f"{HEIMDALL_URL}/admin/provision",
json={"directus_user_id": user_id, "product": "kiwi", "tier": "free"},
headers={"Authorization": f"Bearer {HEIMDALL_ADMIN_TOKEN}"},
timeout=5,
)
except Exception as exc:
log.warning("Heimdall provision failed for user %s: %s", user_id, exc)
def _fetch_cloud_tier(user_id: str) -> tuple[str, str | None, bool]:
"""Returns (tier, household_id | None, is_household_owner)."""
now = time.monotonic()
cached = _TIER_CACHE.get(user_id)
if cached and (now - cached[1]) < _TIER_CACHE_TTL:
entry = cached[0]
return entry["tier"], entry.get("household_id"), entry.get("is_household_owner", False)
if not HEIMDALL_ADMIN_TOKEN:
return "free", None, False
try:
resp = requests.post(
f"{HEIMDALL_URL}/admin/cloud/resolve",
json={"directus_user_id": user_id, "product": "kiwi"},
headers={"Authorization": f"Bearer {HEIMDALL_ADMIN_TOKEN}"},
timeout=5,
)
data = resp.json() if resp.ok else {}
tier = data.get("tier", "free")
household_id = data.get("household_id")
is_owner = data.get("is_household_owner", False)
except Exception as exc:
log.warning("Heimdall tier resolve failed for user %s: %s", user_id, exc)
tier, household_id, is_owner = "free", None, False
_TIER_CACHE[user_id] = ({"tier": tier, "household_id": household_id, "is_household_owner": is_owner}, now)
return tier, household_id, is_owner
def _user_db_path(user_id: str, household_id: str | None = None) -> Path: def _user_db_path(user_id: str, household_id: str | None = None) -> Path:
if household_id: if household_id:
@ -68,57 +170,77 @@ def _user_db_path(user_id: str, household_id: str | None = None) -> Path:
return path return path
def _anon_guest_db_path(guest_id: str) -> Path: # ── BYOK detection ────────────────────────────────────────────────────────────
"""Per-session DB for unauthenticated guest visitors.
Each anonymous visitor gets an isolated SQLite DB keyed by their guest UUID _LLM_CONFIG_PATH = Path.home() / ".config" / "circuitforge" / "llm.yaml"
cookie, so shopping lists and affiliate interactions never bleed across sessions.
def _detect_byok(config_path: Path = _LLM_CONFIG_PATH) -> bool:
"""Return True if at least one enabled non-vision LLM backend is configured.
Reads the same llm.yaml that LLMRouter uses. Local (Ollama, vLLM) and
API-key backends both count the policy is "user is supplying compute",
regardless of where that compute lives.
""" """
path = CLOUD_DATA_ROOT / f"anon-{guest_id}" / "kiwi.db" try:
path.parent.mkdir(parents=True, exist_ok=True) with open(config_path) as f:
return path cfg = yaml.safe_load(f) or {}
return any(
b.get("enabled", True) and b.get("type") != "vision_service"
for b in cfg.get("backends", {}).values()
)
except Exception:
return False
# ── FastAPI dependency ──────────────────────────────────────────────────────── # ── FastAPI dependency ────────────────────────────────────────────────────────
def get_session(request: Request, response: Response) -> CloudUser: def get_session(request: Request) -> CloudUser:
"""FastAPI dependency — resolves the current user from the request. """FastAPI dependency — resolves the current user from the request.
Delegates auth/tier resolution to cf-core CloudSessionFactory, then maps
the result to Kiwi's CloudUser with per-user DB path and household data.
Local mode: fully-privileged "local" user pointing at local DB. Local mode: fully-privileged "local" user pointing at local DB.
Cloud mode: validates X-CF-Session JWT, provisions license, resolves tier. Cloud mode: validates X-CF-Session JWT, provisions license, resolves tier.
Dev bypass: CLOUD_AUTH_BYPASS_IPS match returns a "local-dev" session. Dev bypass: if CLOUD_AUTH_BYPASS_IPS is set and the client IP matches,
Anonymous: per-session UUID cookie (cf_guest_id) isolates each guest's data. returns a "local" session without JWT validation (dev/LAN use only).
""" """
core_user = _core.resolve(request, response) has_byok = _detect_byok()
uid, tier, has_byok = core_user.user_id, core_user.tier, core_user.has_byok
if not CLOUD_MODE or uid in ("local", "local-dev"): if not CLOUD_MODE:
# local-dev gets a writable path under CLOUD_DATA_ROOT; local uses KIWI_DB return CloudUser(user_id="local", tier="local", db=_LOCAL_KIWI_DB, has_byok=has_byok)
db = _user_db_path(uid) if uid == "local-dev" else _LOCAL_KIWI_DB
return CloudUser(user_id=uid, tier=tier, db=db, has_byok=has_byok)
if uid.startswith("anon-"): # Prefer X-Real-IP (set by nginx from the actual client address) over the
guest_id = uid[len("anon-"):] # TCP peer address (which is nginx's container IP when behind the proxy).
return CloudUser( client_ip = (
user_id=uid, tier=tier, request.headers.get("x-real-ip", "")
db=_anon_guest_db_path(guest_id), or (request.client.host if request.client else "")
has_byok=has_byok,
) )
if (_BYPASS_IPS or _BYPASS_NETS) and _is_bypass_ip(client_ip):
log.debug("CLOUD_AUTH_BYPASS_IPS match for %s — returning local session", client_ip)
# Use a dev DB under CLOUD_DATA_ROOT so the container has a writable path.
dev_db = _user_db_path("local-dev")
return CloudUser(user_id="local-dev", tier="local", db=dev_db, has_byok=has_byok)
household_id = core_user.meta.get("household_id") raw_header = (
is_owner = core_user.meta.get("is_household_owner", False) request.headers.get("x-cf-session", "")
license_key = core_user.meta.get("license_key") or request.headers.get("cookie", "")
log.debug("Resolved %s session uid=%s tier=%s household=%s", _auth_label(uid), uid[:8], tier, household_id) )
if not raw_header:
raise HTTPException(status_code=401, detail="Not authenticated")
token = _extract_session_token(raw_header) # gitleaks:allow — function name, not a secret
if not token:
raise HTTPException(status_code=401, detail="Not authenticated")
user_id = validate_session_jwt(token)
_ensure_provisioned(user_id)
tier, household_id, is_household_owner = _fetch_cloud_tier(user_id)
return CloudUser( return CloudUser(
user_id=uid, tier=tier, user_id=user_id,
db=_user_db_path(uid, household_id=household_id), tier=tier,
db=_user_db_path(user_id, household_id=household_id),
has_byok=has_byok, has_byok=has_byok,
household_id=household_id, household_id=household_id,
is_household_owner=is_owner, is_household_owner=is_household_owner,
license_key=license_key,
) )

View file

@ -35,28 +35,6 @@ class Settings:
# Database # Database
DB_PATH: Path = Path(os.environ.get("DB_PATH", str(DATA_DIR / "kiwi.db"))) DB_PATH: Path = Path(os.environ.get("DB_PATH", str(DATA_DIR / "kiwi.db")))
# Pre-computed browse counts cache (small SQLite, separate from corpus).
# Written by the nightly refresh task and by infer_recipe_tags.py.
# Set BROWSE_COUNTS_PATH to a bind-mounted path if you want the host
# pipeline to share counts with the container without re-running FTS.
BROWSE_COUNTS_PATH: Path = Path(
os.environ.get("BROWSE_COUNTS_PATH", str(DATA_DIR / "browse_counts.db"))
)
# Magpie data flywheel — ingest endpoint for anonymized recipe signals
# Set MAGPIE_INGEST_URL to enable; leave unset (or None) to disable silently.
MAGPIE_INGEST_URL: str | None = os.environ.get("MAGPIE_INGEST_URL") or None
# Community feature settings
COMMUNITY_DB_URL: str | None = os.environ.get("COMMUNITY_DB_URL") or None
COMMUNITY_PSEUDONYM_SALT: str = os.environ.get(
"COMMUNITY_PSEUDONYM_SALT", "kiwi-default-salt-change-in-prod"
)
COMMUNITY_CLOUD_FEED_URL: str = os.environ.get(
"COMMUNITY_CLOUD_FEED_URL",
"https://menagerie.circuitforge.tech/kiwi/api/v1/community/posts",
)
# Processing # Processing
MAX_CONCURRENT_JOBS: int = int(os.environ.get("MAX_CONCURRENT_JOBS", "4")) MAX_CONCURRENT_JOBS: int = int(os.environ.get("MAX_CONCURRENT_JOBS", "4"))
USE_GPU: bool = os.environ.get("USE_GPU", "true").lower() in ("1", "true", "yes") USE_GPU: bool = os.environ.get("USE_GPU", "true").lower() in ("1", "true", "yes")
@ -65,52 +43,15 @@ class Settings:
# Quality # Quality
MIN_QUALITY_SCORE: float = float(os.environ.get("MIN_QUALITY_SCORE", "50.0")) MIN_QUALITY_SCORE: float = float(os.environ.get("MIN_QUALITY_SCORE", "50.0"))
# CF-core resource coordinator (VRAM lease management — lease broker, not inference) # CF-core resource coordinator (VRAM lease management)
COORDINATOR_URL: str = os.environ.get("COORDINATOR_URL", "http://localhost:7700") COORDINATOR_URL: str = os.environ.get("COORDINATOR_URL", "http://localhost:7700")
# GPU inference server URL
# Priority: GPU_SERVER_URL env var → CF_ORCH_URL env var (backward compat)
# → https://orch.circuitforge.tech when CF_LICENSE_KEY is present (Paid+)
# Resolved value is written back to os.environ["CF_ORCH_URL"] at startup so
# all service-layer callers that read CF_ORCH_URL directly see the right URL.
GPU_SERVER_URL: str | None = (
os.environ.get("GPU_SERVER_URL")
or os.environ.get("CF_ORCH_URL")
or (
"https://orch.circuitforge.tech"
if os.environ.get("CF_LICENSE_KEY")
else None
)
)
# Hosted cf-orch coordinator — bearer token for managed cloud GPU inference (Paid+) # Hosted cf-orch coordinator — bearer token for managed cloud GPU inference (Paid+)
# CFOrchClient reads CF_LICENSE_KEY automatically; exposed here for startup validation. # CFOrchClient reads CF_LICENSE_KEY automatically; exposed here for startup validation.
CF_LICENSE_KEY: str | None = os.environ.get("CF_LICENSE_KEY") CF_LICENSE_KEY: str | None = os.environ.get("CF_LICENSE_KEY")
# E2E test account — analytics logging is suppressed for this user_id so test
# runs don't pollute session counts. Set to the Directus UUID of the test user.
E2E_TEST_USER_ID: str | None = os.environ.get("E2E_TEST_USER_ID") or None
# ActivityPub federation (optional; disabled by default)
AP_ENABLED: bool = os.environ.get("AP_ENABLED", "false").lower() in ("1", "true", "yes")
AP_HOST: str = os.environ.get("AP_HOST", "") # e.g. kiwi.circuitforge.tech
CLOUD_DATA_ROOT: Path = Path(os.environ.get("CLOUD_DATA_ROOT", "/devl/kiwi-cloud-data"))
AP_KEY_PATH: Path = Path(
os.environ.get("AP_KEY_PATH", str(CLOUD_DATA_ROOT / "ap_keys" / "instance.pem"))
)
# Fernet key for Mastodon access token encryption (base64-urlsafe, 32 bytes)
# Leave unset to skip encryption (dev only)
AP_TOKEN_ENCRYPTION_KEY: str | None = os.environ.get("AP_TOKEN_ENCRYPTION_KEY") or None
# Feature flags # Feature flags
ENABLE_OCR: bool = os.environ.get("ENABLE_OCR", "false").lower() in ("1", "true", "yes") ENABLE_OCR: bool = os.environ.get("ENABLE_OCR", "false").lower() in ("1", "true", "yes")
# Use OrchestratedScheduler (coordinator-aware, multi-GPU fan-out) instead of
# LocalScheduler. Defaults to true in CLOUD_MODE; can be set independently
# for multi-GPU local rigs that don't need full cloud auth.
USE_ORCH_SCHEDULER: bool | None = (
None if os.environ.get("USE_ORCH_SCHEDULER") is None
else os.environ.get("USE_ORCH_SCHEDULER", "").lower() in ("1", "true", "yes")
)
# Runtime # Runtime
DEBUG: bool = os.environ.get("DEBUG", "false").lower() in ("1", "true", "yes") DEBUG: bool = os.environ.get("DEBUG", "false").lower() in ("1", "true", "yes")
@ -123,9 +64,3 @@ class Settings:
settings = Settings() settings = Settings()
# Normalise GPU_SERVER_URL into CF_ORCH_URL so every service-layer caller that
# reads os.environ.get("CF_ORCH_URL") sees the resolved value, including the
# Paid+ cloud default injected above.
if settings.GPU_SERVER_URL:
os.environ["CF_ORCH_URL"] = settings.GPU_SERVER_URL

View file

@ -1,43 +0,0 @@
-- Migration 021: FTS5 inverted index for the recipe browser (category + keywords).
--
-- The browser domain queries were using LIKE '%keyword%' against category and
-- keywords columns — a leading wildcard prevents any B-tree index use, so every
-- query was a full sequential scan of 3.1M rows. This FTS5 index replaces those
-- scans with O(log N) token lookups.
--
-- Content-table backed: stores only the inverted index, no text duplication.
-- The keywords column is a JSON array; FTS5 tokenises it as plain text, stripping
-- the punctuation, which gives correct per-word matching.
--
-- One-time rebuild cost on 3.1M rows: ~20-40 seconds at first startup.
-- Subsequent startups skip this migration (IF NOT EXISTS guard).
CREATE VIRTUAL TABLE IF NOT EXISTS recipe_browser_fts USING fts5(
category,
keywords,
content=recipes,
content_rowid=id,
tokenize="unicode61"
);
INSERT INTO recipe_browser_fts(recipe_browser_fts) VALUES('rebuild');
CREATE TRIGGER IF NOT EXISTS recipe_browser_fts_ai
AFTER INSERT ON recipes BEGIN
INSERT INTO recipe_browser_fts(rowid, category, keywords)
VALUES (new.id, new.category, new.keywords);
END;
CREATE TRIGGER IF NOT EXISTS recipe_browser_fts_ad
AFTER DELETE ON recipes BEGIN
INSERT INTO recipe_browser_fts(recipe_browser_fts, rowid, category, keywords)
VALUES ('delete', old.id, old.category, old.keywords);
END;
CREATE TRIGGER IF NOT EXISTS recipe_browser_fts_au
AFTER UPDATE ON recipes BEGIN
INSERT INTO recipe_browser_fts(recipe_browser_fts, rowid, category, keywords)
VALUES ('delete', old.id, old.category, old.keywords);
INSERT INTO recipe_browser_fts(rowid, category, keywords)
VALUES (new.id, new.category, new.keywords);
END;

View file

@ -1,8 +0,0 @@
-- 022_meal_plans.sql
CREATE TABLE meal_plans (
id INTEGER PRIMARY KEY,
week_start TEXT NOT NULL,
meal_types TEXT NOT NULL DEFAULT '["dinner"]',
created_at TEXT NOT NULL DEFAULT (datetime('now')),
updated_at TEXT NOT NULL DEFAULT (datetime('now'))
);

View file

@ -1,5 +0,0 @@
-- Migration 022: Add is_generic flag to recipes
-- Generic recipes are catch-all/dump recipes with loose ingredient lists
-- that should not appear in Level 1 (deterministic "use what I have") results.
-- Admins can mark recipes via the recipe editor or a bulk backfill script.
ALTER TABLE recipes ADD COLUMN is_generic INTEGER NOT NULL DEFAULT 0;

View file

@ -1,11 +0,0 @@
-- 023_meal_plan_slots.sql
CREATE TABLE meal_plan_slots (
id INTEGER PRIMARY KEY,
plan_id INTEGER NOT NULL REFERENCES meal_plans(id) ON DELETE CASCADE,
day_of_week INTEGER NOT NULL CHECK(day_of_week BETWEEN 0 AND 6),
meal_type TEXT NOT NULL,
recipe_id INTEGER REFERENCES recipes(id),
servings REAL NOT NULL DEFAULT 2.0,
custom_label TEXT,
UNIQUE(plan_id, day_of_week, meal_type)
);

View file

@ -1,10 +0,0 @@
-- 024_prep_sessions.sql
CREATE TABLE prep_sessions (
id INTEGER PRIMARY KEY,
plan_id INTEGER NOT NULL REFERENCES meal_plans(id) ON DELETE CASCADE,
scheduled_date TEXT NOT NULL,
status TEXT NOT NULL DEFAULT 'draft'
CHECK(status IN ('draft','reviewed','done')),
created_at TEXT NOT NULL DEFAULT (datetime('now')),
updated_at TEXT NOT NULL DEFAULT (datetime('now'))
);

View file

@ -1,15 +0,0 @@
-- 025_prep_tasks.sql
CREATE TABLE prep_tasks (
id INTEGER PRIMARY KEY,
session_id INTEGER NOT NULL REFERENCES prep_sessions(id) ON DELETE CASCADE,
recipe_id INTEGER REFERENCES recipes(id),
slot_id INTEGER REFERENCES meal_plan_slots(id),
task_label TEXT NOT NULL,
duration_minutes INTEGER,
sequence_order INTEGER NOT NULL,
equipment TEXT,
is_parallel INTEGER NOT NULL DEFAULT 0,
notes TEXT,
user_edited INTEGER NOT NULL DEFAULT 0,
created_at TEXT NOT NULL DEFAULT (datetime('now'))
);

View file

@ -1,21 +0,0 @@
-- 028_community_pseudonyms.sql
-- Per-user pseudonym store: maps the user's chosen community display name
-- to their Directus user ID. This table lives in per-user kiwi.db only.
-- It is NEVER replicated to the community PostgreSQL — pseudonym isolation is by design.
--
-- A user may have one active pseudonym. Old pseudonyms are retained for reference
-- (posts published under them keep their pseudonym attribution) but only one is
-- flagged as current (is_current = 1).
CREATE TABLE IF NOT EXISTS community_pseudonyms (
id INTEGER PRIMARY KEY AUTOINCREMENT,
pseudonym TEXT NOT NULL,
directus_user_id TEXT NOT NULL,
is_current INTEGER NOT NULL DEFAULT 1 CHECK (is_current IN (0, 1)),
created_at TEXT NOT NULL DEFAULT (datetime('now'))
);
-- Only one pseudonym can be current at a time per user
CREATE UNIQUE INDEX IF NOT EXISTS idx_community_pseudonyms_current
ON community_pseudonyms (directus_user_id)
WHERE is_current = 1;

View file

@ -1,49 +0,0 @@
-- Migration 029: Add inferred_tags column and update FTS index to include it.
--
-- inferred_tags holds a JSON array of normalized tag strings derived by
-- scripts/pipeline/infer_recipe_tags.py (e.g. ["cuisine:Italian",
-- "dietary:Low-Carb", "flavor:Umami", "can_be:Gluten-Free"]).
--
-- The FTS5 browser table is rebuilt to index inferred_tags alongside
-- category and keywords so browse domain queries match against all signals.
-- 1. Add inferred_tags column (empty array default; populated by pipeline run)
ALTER TABLE recipes ADD COLUMN inferred_tags TEXT NOT NULL DEFAULT '[]';
-- 2. Drop old FTS table and triggers that only covered category + keywords
DROP TRIGGER IF EXISTS recipes_ai;
DROP TRIGGER IF EXISTS recipes_ad;
DROP TRIGGER IF EXISTS recipes_au;
DROP TABLE IF EXISTS recipe_browser_fts;
-- 3. Recreate FTS5 table: now indexes category, keywords, AND inferred_tags
CREATE VIRTUAL TABLE recipe_browser_fts USING fts5(
category,
keywords,
inferred_tags,
content=recipes,
content_rowid=id
);
-- 4. Triggers to keep FTS in sync with recipes table changes
CREATE TRIGGER recipes_ai AFTER INSERT ON recipes BEGIN
INSERT INTO recipe_browser_fts(rowid, category, keywords, inferred_tags)
VALUES (new.id, new.category, new.keywords, new.inferred_tags);
END;
CREATE TRIGGER recipes_ad AFTER DELETE ON recipes BEGIN
INSERT INTO recipe_browser_fts(recipe_browser_fts, rowid, category, keywords, inferred_tags)
VALUES ('delete', old.id, old.category, old.keywords, old.inferred_tags);
END;
CREATE TRIGGER recipes_au AFTER UPDATE ON recipes BEGIN
INSERT INTO recipe_browser_fts(recipe_browser_fts, rowid, category, keywords, inferred_tags)
VALUES ('delete', old.id, old.category, old.keywords, old.inferred_tags);
INSERT INTO recipe_browser_fts(rowid, category, keywords, inferred_tags)
VALUES (new.id, new.category, new.keywords, new.inferred_tags);
END;
-- 5. Populate FTS from current table state
-- (inferred_tags is '[]' for all rows at this point; run infer_recipe_tags.py
-- to populate, then the FTS will be rebuilt as part of that script.)
INSERT INTO recipe_browser_fts(recipe_browser_fts) VALUES('rebuild');

View file

@ -1,5 +0,0 @@
-- Migration 030: open-package tracking
-- Adds opened_date to track when a multi-use item was first opened,
-- enabling secondary shelf-life windows (e.g. salsa: 1 year sealed → 2 weeks opened).
ALTER TABLE inventory_items ADD COLUMN opened_date TEXT;

View file

@ -1,4 +0,0 @@
-- Migration 031: add disposal_reason for waste logging (#60)
-- status='discarded' already exists in the CHECK constraint from migration 002.
-- This column stores free-text reason (optional) and calm-framing presets.
ALTER TABLE inventory_items ADD COLUMN disposal_reason TEXT;

View file

@ -1,4 +0,0 @@
-- 032_meal_plan_unique_week.sql
-- Prevent duplicate plans for the same week.
-- Existing duplicates must be resolved before applying (keep MIN(id) per week_start).
CREATE UNIQUE INDEX IF NOT EXISTS idx_meal_plans_week_start ON meal_plans (week_start);

View file

@ -1,21 +0,0 @@
-- Migration 033: standalone shopping list
-- Items can be added manually, from recipe gap analysis, or from the recipe browser.
-- Affiliate links are computed at query time by the API layer (never stored).
CREATE TABLE IF NOT EXISTS shopping_list_items (
id INTEGER PRIMARY KEY AUTOINCREMENT,
name TEXT NOT NULL,
quantity REAL,
unit TEXT,
category TEXT,
checked INTEGER NOT NULL DEFAULT 0, -- 0=want, 1=in-cart/checked off
notes TEXT,
source TEXT NOT NULL DEFAULT 'manual', -- manual | recipe | meal_plan
recipe_id INTEGER REFERENCES recipes(id) ON DELETE SET NULL,
sort_order INTEGER NOT NULL DEFAULT 0,
created_at TEXT NOT NULL DEFAULT (datetime('now')),
updated_at TEXT NOT NULL DEFAULT (datetime('now'))
);
CREATE INDEX IF NOT EXISTS idx_shopping_list_checked
ON shopping_list_items (checked, sort_order);

View file

@ -1,14 +0,0 @@
-- Migration 034: async recipe generation job queue
CREATE TABLE IF NOT EXISTS recipe_jobs (
id INTEGER PRIMARY KEY AUTOINCREMENT,
job_id TEXT NOT NULL UNIQUE,
user_id TEXT NOT NULL,
status TEXT NOT NULL DEFAULT 'queued',
request TEXT NOT NULL,
result TEXT,
error TEXT,
created_at TEXT NOT NULL DEFAULT (datetime('now')),
updated_at TEXT NOT NULL DEFAULT (datetime('now'))
);
CREATE INDEX IF NOT EXISTS idx_recipe_jobs_job_id ON recipe_jobs (job_id);
CREATE INDEX IF NOT EXISTS idx_recipe_jobs_user_id ON recipe_jobs (user_id, created_at DESC);

View file

@ -1,12 +0,0 @@
-- Migration 035: add sensory_tags column for sensory profile filtering
--
-- sensory_tags holds a JSON object with texture, smell, and noise signals:
-- {"textures": ["mushy", "creamy"], "smell": "pungent", "noise": "moderate"}
--
-- Empty object '{}' means untagged — these recipes pass ALL sensory filters
-- (graceful degradation when tag_sensory_profiles.py has not yet been run).
--
-- Populated offline by: python scripts/tag_sensory_profiles.py [path/to/kiwi.db]
-- No FTS rebuild needed — sensory_tags is filtered in Python after candidate fetch.
ALTER TABLE recipes ADD COLUMN sensory_tags TEXT NOT NULL DEFAULT '{}';

View file

@ -1,26 +0,0 @@
-- Migration 036: captured_products local cache
-- Products captured via visual label scanning (kiwi#79).
-- Keyed by barcode; checked before FDC/OFF on future scans so each product
-- is only captured once per device.
CREATE TABLE IF NOT EXISTS captured_products (
id INTEGER PRIMARY KEY AUTOINCREMENT,
barcode TEXT UNIQUE NOT NULL,
product_name TEXT,
brand TEXT,
serving_size_g REAL,
calories REAL,
fat_g REAL,
saturated_fat_g REAL,
carbs_g REAL,
sugar_g REAL,
fiber_g REAL,
protein_g REAL,
sodium_mg REAL,
ingredient_names TEXT NOT NULL DEFAULT '[]', -- JSON array
allergens TEXT NOT NULL DEFAULT '[]', -- JSON array
confidence REAL,
source TEXT NOT NULL DEFAULT 'visual_capture',
captured_at TEXT NOT NULL DEFAULT (datetime('now')),
confirmed_by_user INTEGER NOT NULL DEFAULT 0
);

View file

@ -1,34 +0,0 @@
-- Migration 037: add 'visual_capture' to products.source CHECK constraint
-- SQLite cannot ALTER a CHECK constraint, so we rebuild the table.
PRAGMA foreign_keys = OFF;
BEGIN;
CREATE TABLE products_new (
id INTEGER PRIMARY KEY AUTOINCREMENT,
barcode TEXT UNIQUE,
name TEXT NOT NULL,
brand TEXT,
category TEXT,
description TEXT,
image_url TEXT,
nutrition_data TEXT NOT NULL DEFAULT '{}',
source TEXT NOT NULL DEFAULT 'openfoodfacts'
CHECK (source IN ('openfoodfacts', 'manual', 'receipt_ocr', 'visual_capture')),
source_data TEXT,
created_at TEXT NOT NULL DEFAULT (datetime('now')),
updated_at TEXT NOT NULL DEFAULT (datetime('now'))
);
INSERT INTO products_new
SELECT id, barcode, name, brand, category, description, image_url,
nutrition_data, source, source_data, created_at, updated_at
FROM products;
DROP TABLE products;
ALTER TABLE products_new RENAME TO products;
COMMIT;
PRAGMA foreign_keys = ON;

View file

@ -1,43 +0,0 @@
-- Migration 038: add 'visual_capture' to inventory_items.source CHECK constraint
-- SQLite cannot ALTER a CHECK constraint, so we rebuild the table.
PRAGMA foreign_keys = OFF;
BEGIN;
CREATE TABLE inventory_items_new (
id INTEGER PRIMARY KEY AUTOINCREMENT,
product_id INTEGER NOT NULL
REFERENCES products (id) ON DELETE RESTRICT,
receipt_id INTEGER
REFERENCES receipts (id) ON DELETE SET NULL,
quantity REAL NOT NULL DEFAULT 1 CHECK (quantity > 0),
unit TEXT NOT NULL DEFAULT 'count',
location TEXT NOT NULL,
sublocation TEXT,
purchase_date TEXT,
expiration_date TEXT,
status TEXT NOT NULL DEFAULT 'available'
CHECK (status IN ('available', 'consumed', 'expired', 'discarded')),
consumed_at TEXT,
notes TEXT,
source TEXT NOT NULL DEFAULT 'manual'
CHECK (source IN ('barcode_scan', 'manual', 'receipt', 'visual_capture')),
created_at TEXT NOT NULL DEFAULT (datetime('now')),
updated_at TEXT NOT NULL DEFAULT (datetime('now')),
opened_date TEXT,
disposal_reason TEXT
);
INSERT INTO inventory_items_new
SELECT id, product_id, receipt_id, quantity, unit, location, sublocation,
purchase_date, expiration_date, status, consumed_at, notes, source,
created_at, updated_at, opened_date, disposal_reason
FROM inventory_items;
DROP TABLE inventory_items;
ALTER TABLE inventory_items_new RENAME TO inventory_items;
COMMIT;
PRAGMA foreign_keys = ON;

View file

@ -1,31 +0,0 @@
-- Migration 039: Drop FK constraint on saved_recipes.recipe_id.
--
-- In cloud mode the recipe corpus is ATTACHed as a separate database.
-- SQLite FK constraints only resolve against the `main` schema, so
-- `REFERENCES recipes(id)` was always failing for cloud saves (the
-- main.recipes table is empty; all data lives in corpus.recipes).
-- The corpus is read-only and never modified by the app, so cascade-on-delete
-- is meaningless anyway. Remove the constraint without changing any data.
PRAGMA foreign_keys = OFF;
CREATE TABLE saved_recipes_new (
id INTEGER PRIMARY KEY AUTOINCREMENT,
recipe_id INTEGER NOT NULL,
saved_at TEXT NOT NULL DEFAULT (datetime('now')),
notes TEXT,
rating INTEGER CHECK (rating IS NULL OR (rating >= 0 AND rating <= 5)),
style_tags TEXT NOT NULL DEFAULT '[]',
UNIQUE (recipe_id)
);
INSERT INTO saved_recipes_new SELECT * FROM saved_recipes;
DROP TABLE saved_recipes;
ALTER TABLE saved_recipes_new RENAME TO saved_recipes;
CREATE INDEX IF NOT EXISTS idx_saved_recipes_saved_at ON saved_recipes (saved_at DESC);
CREATE INDEX IF NOT EXISTS idx_saved_recipes_rating ON saved_recipes (rating);
PRAGMA foreign_keys = ON;

View file

@ -1,21 +0,0 @@
-- 040_corrections.sql — corrections table for SFT training data
-- Schema from circuitforge_core.api.corrections.CORRECTIONS_MIGRATION_SQL
CREATE TABLE IF NOT EXISTS corrections (
id INTEGER PRIMARY KEY AUTOINCREMENT,
item_id TEXT NOT NULL DEFAULT '',
product TEXT NOT NULL,
correction_type TEXT NOT NULL,
input_text TEXT NOT NULL,
original_output TEXT NOT NULL,
corrected_output TEXT NOT NULL DEFAULT '',
rating TEXT NOT NULL DEFAULT 'down',
context TEXT NOT NULL DEFAULT '{}',
opted_in INTEGER NOT NULL DEFAULT 0,
created_at TEXT NOT NULL DEFAULT (datetime('now'))
);
CREATE INDEX IF NOT EXISTS idx_corrections_product
ON corrections (product);
CREATE INDEX IF NOT EXISTS idx_corrections_opted_in
ON corrections (opted_in);

View file

@ -1,23 +0,0 @@
-- Migration 041: user_recipes table for user-scanned and manually-entered recipes.
--
-- Separate from the food.com corpus (recipes table) -- user recipes are personal,
-- not curated, and need different fields (servings as string, cook_time as string).
CREATE TABLE IF NOT EXISTS user_recipes (
id INTEGER PRIMARY KEY AUTOINCREMENT,
title TEXT NOT NULL,
subtitle TEXT,
servings TEXT, -- kept as string: "2", "4-6", "serves 8"
cook_time TEXT, -- kept as string: "25 min", "1 hour"
source_note TEXT, -- e.g. "Purple Carrot", "Betty Crocker"
ingredients TEXT NOT NULL DEFAULT '[]', -- JSON: [{name, qty, unit, raw}]
steps TEXT NOT NULL DEFAULT '[]', -- JSON: ["step 1", "step 2", ...]
notes TEXT,
tags TEXT DEFAULT '[]', -- JSON: ["vegan", "quick"]
source TEXT NOT NULL DEFAULT 'manual', -- 'scan' | 'manual'
pantry_match_pct INTEGER, -- 0-100, computed at scan time; null for manual
created_at TEXT NOT NULL DEFAULT (datetime('now')),
updated_at TEXT NOT NULL DEFAULT (datetime('now'))
);
CREATE INDEX IF NOT EXISTS idx_user_recipes_created ON user_recipes (created_at DESC);

View file

@ -1,47 +0,0 @@
-- 042_activitypub.sql
-- ActivityPub federation tables: follower registry, delivery log, dedup, Mastodon tokens.
-- Follower registry: AP actors that Follow this Kiwi instance
CREATE TABLE IF NOT EXISTS ap_followers (
id INTEGER PRIMARY KEY,
actor_id TEXT NOT NULL UNIQUE, -- AP actor URL
inbox_url TEXT NOT NULL,
shared_inbox TEXT,
followed_at TEXT NOT NULL DEFAULT (datetime('now')),
active INTEGER NOT NULL DEFAULT 1
);
CREATE INDEX IF NOT EXISTS idx_ap_followers_active
ON ap_followers (active) WHERE active = 1;
-- Outgoing delivery log: one row per (post_slug, target_inbox) attempt
CREATE TABLE IF NOT EXISTS ap_deliveries (
id INTEGER PRIMARY KEY,
post_slug TEXT NOT NULL,
target_inbox TEXT NOT NULL,
status TEXT NOT NULL DEFAULT 'pending', -- pending | delivered | failed
attempts INTEGER NOT NULL DEFAULT 0,
last_error TEXT,
created_at TEXT NOT NULL DEFAULT (datetime('now')),
delivered_at TEXT
);
CREATE INDEX IF NOT EXISTS idx_ap_deliveries_status
ON ap_deliveries (status) WHERE status != 'delivered';
-- Incoming activity dedup: prevents replay attacks and double-processing
CREATE TABLE IF NOT EXISTS ap_received (
activity_id TEXT PRIMARY KEY,
received_at TEXT NOT NULL DEFAULT (datetime('now'))
);
-- Mastodon OAuth tokens: per-user, encrypted at rest
-- Stored in the user's local kiwi.db (CLOUD_MODE: per-user DB tree)
CREATE TABLE IF NOT EXISTS mastodon_tokens (
id INTEGER PRIMARY KEY,
directus_user_id TEXT NOT NULL UNIQUE,
instance_url TEXT NOT NULL,
access_token TEXT NOT NULL, -- Fernet-encrypted when AP_TOKEN_ENCRYPTION_KEY set
created_at TEXT NOT NULL DEFAULT (datetime('now')),
updated_at TEXT NOT NULL DEFAULT (datetime('now'))
);

View file

@ -6,8 +6,6 @@ Cloud mode: opens a Store at the per-user DB path from the CloudUser session.
""" """
from __future__ import annotations from __future__ import annotations
import sqlite3
from collections.abc import Iterator
from typing import Generator from typing import Generator
from fastapi import Depends from fastapi import Depends
@ -23,16 +21,3 @@ def get_store(session: CloudUser = Depends(get_session)) -> Generator[Store, Non
yield store yield store
finally: finally:
store.close() store.close()
def get_db(session: CloudUser = Depends(get_session)) -> Iterator[sqlite3.Connection]:
"""FastAPI dependency — yields the raw sqlite3.Connection for the current user.
Used by make_corrections_router() from circuitforge-core, which expects a
dependency that yields a sqlite3.Connection directly.
"""
store = Store(session.db)
try:
yield store.conn
finally:
store.close()

File diff suppressed because it is too large Load diff

View file

@ -1,9 +1,7 @@
#!/usr/bin/env python #!/usr/bin/env python
# app/main.py # app/main.py
import asyncio
import logging import logging
import os
from contextlib import asynccontextmanager from contextlib import asynccontextmanager
from fastapi import FastAPI from fastapi import FastAPI
@ -11,83 +9,20 @@ from fastapi.middleware.cors import CORSMiddleware
from app.api.routes import api_router from app.api.routes import api_router
from app.core.config import settings from app.core.config import settings
from app.services.meal_plan.affiliates import register_kiwi_programs
# Structured key=value log lines — grep/awk-friendly for log-based analytics.
# Without basicConfig, app-level INFO logs are silently dropped.
logging.basicConfig(level=logging.INFO, format="%(levelname)s:%(name)s: %(message)s")
logger = logging.getLogger(__name__) logger = logging.getLogger(__name__)
_BROWSE_REFRESH_INTERVAL_H = 24
async def _browse_counts_refresh_loop(corpus_path: str) -> None:
"""Refresh browse counts every 24 h while the container is running."""
from app.db.store import _COUNT_CACHE
from app.services.recipe.browse_counts_cache import load_into_memory, refresh
while True:
await asyncio.sleep(_BROWSE_REFRESH_INTERVAL_H * 3600)
try:
logger.info("browse_counts: starting scheduled refresh...")
computed = await asyncio.to_thread(
refresh, corpus_path, settings.BROWSE_COUNTS_PATH
)
load_into_memory(settings.BROWSE_COUNTS_PATH, _COUNT_CACHE, corpus_path)
logger.info("browse_counts: scheduled refresh complete (%d sets)", computed)
except Exception as exc:
logger.warning("browse_counts: scheduled refresh failed: %s", exc)
@asynccontextmanager @asynccontextmanager
async def lifespan(app: FastAPI): async def lifespan(app: FastAPI):
logger.info("Starting Kiwi API...") logger.info("Starting Kiwi API...")
settings.ensure_dirs() settings.ensure_dirs()
# Run DB migrations at startup (ensures all tables exist before any request)
from app.db.store import Store
_s = Store(settings.DB_PATH)
_s.close()
register_kiwi_programs()
# Start LLM background task scheduler # Start LLM background task scheduler
from app.tasks.scheduler import get_scheduler from app.tasks.scheduler import get_scheduler
get_scheduler(settings.DB_PATH) get_scheduler(settings.DB_PATH)
logger.info("Task scheduler started.") logger.info("Task scheduler started.")
# Initialize community store (no-op if COMMUNITY_DB_URL is not set)
from app.api.endpoints.community import init_community_store
init_community_store(settings.COMMUNITY_DB_URL)
# Initialize ActivityPub instance actor (no-op when AP_ENABLED=false)
if settings.AP_ENABLED and settings.AP_HOST:
try:
from app.services.ap.keys import init_actor
init_actor(host=settings.AP_HOST, key_path=settings.AP_KEY_PATH)
except Exception as _ap_exc:
logger.warning("AP init failed (AP features disabled): %s", _ap_exc)
# Browse counts cache — warm in-memory cache from disk, refresh if stale.
# Uses the corpus path the store will attach to at request time.
corpus_path = os.environ.get("RECIPE_DB_PATH", str(settings.DB_PATH))
try:
from app.db.store import _COUNT_CACHE
from app.services.recipe.browse_counts_cache import (
is_stale, load_into_memory, refresh,
)
if is_stale(settings.BROWSE_COUNTS_PATH):
logger.info("browse_counts: cache stale — refreshing in background...")
asyncio.create_task(
asyncio.to_thread(refresh, corpus_path, settings.BROWSE_COUNTS_PATH)
)
else:
load_into_memory(settings.BROWSE_COUNTS_PATH, _COUNT_CACHE, corpus_path)
except Exception as exc:
logger.warning("browse_counts: startup init failed (live FTS fallback active): %s", exc)
# Nightly background refresh loop
asyncio.create_task(_browse_counts_refresh_loop(corpus_path))
yield yield
# Graceful scheduler shutdown # Graceful scheduler shutdown
@ -100,7 +35,7 @@ async def lifespan(app: FastAPI):
app = FastAPI( app = FastAPI(
title=settings.PROJECT_NAME, title=settings.PROJECT_NAME,
description="Pantry tracking + leftover recipe suggestions", description="Pantry tracking + leftover recipe suggestions",
version="0.2.0", version="0.1.0",
lifespan=lifespan, lifespan=lifespan,
) )
@ -114,11 +49,6 @@ app.add_middleware(
app.include_router(api_router, prefix=settings.API_PREFIX) app.include_router(api_router, prefix=settings.API_PREFIX)
# AP endpoints: WebFinger at root (not under /api/v1), AP objects under /ap
from app.api.endpoints.activitypub import ap_router, webfinger_router
app.include_router(webfinger_router)
app.include_router(ap_router)
@app.get("/") @app.get("/")
async def root(): async def root():

View file

View file

@ -1,306 +0,0 @@
"""Kiwi MCP Server — read-only corpus DB access for tag/keyword audits.
Exposes four tools to Claude:
kiwi_query_corpus run a read-only SQL query against the corpus DB
kiwi_count_fts run an FTS5 MATCH expression and return row count
kiwi_sample_tags return tag frequency distribution by prefix
kiwi_browse_preview call the browse endpoint and return first-page results
Run with:
python -m app.mcp.server
(from /Library/Development/CircuitForge/kiwi with cf conda env active)
Configure in Claude Code ~/.claude/settings.json mcpServers:
"kiwi": {
"command": "/devl/miniconda3/envs/cf/bin/python",
"args": ["-m", "app.mcp.server"],
"cwd": "/Library/Development/CircuitForge/kiwi",
"env": {
"KIWI_DB_PATH": "/Library/Development/CircuitForge/kiwi/data/kiwi.db",
"KIWI_API_URL": "http://localhost:8512"
}
}
"""
from __future__ import annotations
import asyncio
import json
import os
import sqlite3
from pathlib import Path
import httpx
from mcp.server import Server
from mcp.server.stdio import stdio_server
from mcp.types import TextContent, Tool
_DB_PATH = os.environ.get(
"KIWI_DB_PATH",
str(Path(__file__).parents[3] / "data" / "kiwi.db"),
)
_API_URL = os.environ.get("KIWI_API_URL", "http://localhost:8512")
_TIMEOUT = 30.0
_QUERY_ROW_LIMIT = 200
server = Server("kiwi")
def _open_ro() -> sqlite3.Connection:
"""Open the corpus DB in read-only mode."""
uri = f"file:///{Path(_DB_PATH).as_posix()}?mode=ro"
conn = sqlite3.connect(uri, uri=True, check_same_thread=False)
conn.row_factory = sqlite3.Row
return conn
@server.list_tools()
async def list_tools() -> list[Tool]:
return [
Tool(
name="kiwi_query_corpus",
description=(
"Run a read-only SQL SELECT query against the Kiwi corpus DB (kiwi.db). "
"Returns up to 200 rows as a JSON array. "
"Key tables: recipes (id, title, ingredient_names, inferred_tags, source_url), "
"recipes_fts (FTS5 virtual table for full-text search), "
"ingredient_profiles (name, elements, texture_profile). "
"Use for schema exploration, spot-checking tag coverage, and counting results. "
"Read-only — any write statement will be rejected by SQLite."
),
inputSchema={
"type": "object",
"required": ["sql"],
"properties": {
"sql": {
"type": "string",
"description": (
"A SELECT statement. E.g.: "
"SELECT title, inferred_tags FROM recipes WHERE inferred_tags LIKE '%vegan%' LIMIT 10"
),
},
},
},
),
Tool(
name="kiwi_count_fts",
description=(
"Run an FTS5 MATCH expression against the recipes_fts table and return the hit count. "
"Useful for quickly auditing keyword coverage without a full query. "
"Always double-quote all terms in MATCH expressions. "
"E.g. match_expr='\"tofu\" OR \"tempeh\"' returns how many recipes include either."
),
inputSchema={
"type": "object",
"required": ["match_expr"],
"properties": {
"match_expr": {
"type": "string",
"description": (
"FTS5 MATCH expression string (without the MATCH keyword). "
'E.g. \'"lentil" OR "chickpea"\' or \'"pasta" AND "vegetarian"\''
),
},
},
},
),
Tool(
name="kiwi_sample_tags",
description=(
"Return tag frequency distribution from the corpus. "
"Queries inferred_tags column for tags matching the given prefix pattern. "
"Useful for auditing how well a category keyword set covers the corpus, "
"or discovering what tags exist under a domain (cuisine:, meal:, dietary:, texture:)."
),
inputSchema={
"type": "object",
"properties": {
"prefix": {
"type": "string",
"default": "",
"description": (
"Tag prefix to filter by. E.g. 'cuisine:' returns all cuisine tags, "
"'meal:' returns all meal type tags, '' returns all tags. "
"Returns top 50 by frequency."
),
},
"limit": {
"type": "integer",
"default": 50,
"description": "Max number of tag entries to return (default 50, max 200).",
},
},
},
),
Tool(
name="kiwi_browse_preview",
description=(
"Call the Kiwi browse endpoint and return first-page results. "
"Use to verify that a domain/category returns the expected recipes "
"after a keyword or tag change, without opening the browser. "
"Returns recipe titles, match counts, and total result count."
),
inputSchema={
"type": "object",
"required": ["domain", "category"],
"properties": {
"domain": {
"type": "string",
"description": (
"Browse domain slug. "
"Known domains: cuisine, meal_type, dietary, ingredient, occasion, texture."
),
},
"category": {
"type": "string",
"description": "Category slug within the domain, e.g. 'italian', 'breakfast', 'vegan'.",
},
"subcategory": {
"type": "string",
"default": "",
"description": "Optional subcategory slug to narrow further.",
},
"page_size": {
"type": "integer",
"default": 10,
"description": "Results per page (default 10, max 50).",
},
},
},
),
]
@server.call_tool()
async def call_tool(name: str, arguments: dict) -> list[TextContent]:
if name == "kiwi_query_corpus":
return await _query_corpus(arguments)
if name == "kiwi_count_fts":
return await _count_fts(arguments)
if name == "kiwi_sample_tags":
return await _sample_tags(arguments)
if name == "kiwi_browse_preview":
return await _browse_preview(arguments)
return [TextContent(type="text", text=f"Unknown tool: {name}")]
async def _query_corpus(args: dict) -> list[TextContent]:
sql = args.get("sql", "").strip()
if not sql.upper().startswith("SELECT"):
return [TextContent(type="text", text="Error: only SELECT statements are allowed.")]
def _run() -> list[dict]:
conn = _open_ro()
try:
cur = conn.execute(sql)
rows = cur.fetchmany(_QUERY_ROW_LIMIT)
return [dict(r) for r in rows]
finally:
conn.close()
try:
rows = await asyncio.get_event_loop().run_in_executor(None, _run)
return [TextContent(type="text", text=json.dumps(rows, indent=2, default=str))]
except Exception as exc:
return [TextContent(type="text", text=f"Query error: {exc}")]
async def _count_fts(args: dict) -> list[TextContent]:
match_expr = args.get("match_expr", "").strip()
if not match_expr:
return [TextContent(type="text", text="Error: match_expr is required.")]
def _run() -> int:
conn = _open_ro()
try:
cur = conn.execute(
"SELECT COUNT(*) FROM recipes_fts WHERE recipes_fts MATCH ?",
(match_expr,),
)
return cur.fetchone()[0]
finally:
conn.close()
try:
count = await asyncio.get_event_loop().run_in_executor(None, _run)
return [TextContent(type="text", text=json.dumps({"match_expr": match_expr, "count": count}))]
except Exception as exc:
return [TextContent(type="text", text=f"FTS error: {exc}")]
async def _sample_tags(args: dict) -> list[TextContent]:
prefix = args.get("prefix", "")
limit = min(int(args.get("limit", 50)), _QUERY_ROW_LIMIT)
def _run() -> list[dict]:
conn = _open_ro()
try:
# Split inferred_tags (comma or space separated) and count each tag
sql = """
WITH tag_rows AS (
SELECT trim(value) AS tag
FROM recipes, json_each('["' || replace(replace(inferred_tags, ', ', '","'), ',', '","') || '"]')
WHERE inferred_tags IS NOT NULL AND inferred_tags != ''
)
SELECT tag, COUNT(*) AS frequency
FROM tag_rows
WHERE tag LIKE ? AND tag != ''
GROUP BY tag
ORDER BY frequency DESC
LIMIT ?
"""
pattern = f"{prefix}%" if prefix else "%"
cur = conn.execute(sql, (pattern, limit))
return [{"tag": r["tag"], "frequency": r["frequency"]} for r in cur.fetchall()]
finally:
conn.close()
try:
tags = await asyncio.get_event_loop().run_in_executor(None, _run)
return [TextContent(type="text", text=json.dumps({"prefix": prefix, "tags": tags}, indent=2))]
except Exception as exc:
return [TextContent(type="text", text=f"Tag query error: {exc}")]
async def _browse_preview(args: dict) -> list[TextContent]:
domain = args.get("domain", "")
category = args.get("category", "")
subcategory = args.get("subcategory", "")
page_size = min(int(args.get("page_size", 10)), 50)
params: dict = {"page": 1, "page_size": page_size}
if subcategory:
params["subcategory"] = subcategory
async with httpx.AsyncClient(timeout=_TIMEOUT) as client:
try:
resp = await client.get(
f"{_API_URL}/api/v1/recipes/browse/{domain}/{category}",
params=params,
)
resp.raise_for_status()
except Exception as exc:
return [TextContent(type="text", text=f"Browse error: {exc}")]
data = resp.json()
summary = {
"domain": domain,
"category": category,
"subcategory": subcategory or None,
"total": data.get("total", 0),
"page_size": page_size,
"titles": [r.get("title", "") for r in data.get("recipes", [])],
}
return [TextContent(type="text", text=json.dumps(summary, indent=2))]
async def _main() -> None:
async with stdio_server() as (read_stream, write_stream):
await server.run(
read_stream,
write_stream,
server.create_initialization_options(),
)
if __name__ == "__main__":
asyncio.run(_main())

View file

@ -89,20 +89,9 @@ class InventoryItemUpdate(BaseModel):
unit: Optional[str] = None unit: Optional[str] = None
location: Optional[str] = None location: Optional[str] = None
sublocation: Optional[str] = None sublocation: Optional[str] = None
purchase_date: Optional[date] = None
expiration_date: Optional[date] = None expiration_date: Optional[date] = None
opened_date: Optional[date] = None
status: Optional[str] = None status: Optional[str] = None
notes: Optional[str] = None notes: Optional[str] = None
disposal_reason: Optional[str] = None
class PartialConsumeRequest(BaseModel):
quantity: float = Field(..., gt=0, description="Amount to consume from this item")
class DiscardRequest(BaseModel):
reason: Optional[str] = Field(None, max_length=200)
class InventoryItemResponse(BaseModel): class InventoryItemResponse(BaseModel):
@ -117,15 +106,8 @@ class InventoryItemResponse(BaseModel):
sublocation: Optional[str] sublocation: Optional[str]
purchase_date: Optional[str] purchase_date: Optional[str]
expiration_date: Optional[str] expiration_date: Optional[str]
opened_date: Optional[str] = None
opened_expiry_date: Optional[str] = None
secondary_state: Optional[str] = None
secondary_uses: Optional[List[str]] = None
secondary_warning: Optional[str] = None
secondary_discard_signs: Optional[str] = None
status: str status: str
notes: Optional[str] notes: Optional[str]
disposal_reason: Optional[str] = None
source: str source: str
created_at: str created_at: str
updated_at: str updated_at: str
@ -141,8 +123,6 @@ class BarcodeScanResult(BaseModel):
product: Optional[ProductResponse] product: Optional[ProductResponse]
inventory_item: Optional[InventoryItemResponse] inventory_item: Optional[InventoryItemResponse]
added_to_inventory: bool added_to_inventory: bool
needs_manual_entry: bool = False
needs_visual_capture: bool = False # Paid tier offer when no product data found
message: str message: str

View file

@ -1,59 +0,0 @@
"""Pydantic schemas for visual label capture (kiwi#79)."""
from __future__ import annotations
from typing import Any, Dict, List, Optional
from pydantic import BaseModel, Field
class LabelCaptureResponse(BaseModel):
"""Extraction result returned after the user photographs a nutrition label."""
barcode: str
product_name: Optional[str] = None
brand: Optional[str] = None
serving_size_g: Optional[float] = None
calories: Optional[float] = None
fat_g: Optional[float] = None
saturated_fat_g: Optional[float] = None
carbs_g: Optional[float] = None
sugar_g: Optional[float] = None
fiber_g: Optional[float] = None
protein_g: Optional[float] = None
sodium_mg: Optional[float] = None
ingredient_names: List[str] = Field(default_factory=list)
allergens: List[str] = Field(default_factory=list)
confidence: float = 0.0
needs_review: bool = True # True when confidence < REVIEW_THRESHOLD
class LabelConfirmRequest(BaseModel):
"""User-confirmed extraction to save to the local product cache."""
barcode: str
product_name: Optional[str] = None
brand: Optional[str] = None
serving_size_g: Optional[float] = None
calories: Optional[float] = None
fat_g: Optional[float] = None
saturated_fat_g: Optional[float] = None
carbs_g: Optional[float] = None
sugar_g: Optional[float] = None
fiber_g: Optional[float] = None
protein_g: Optional[float] = None
sodium_mg: Optional[float] = None
ingredient_names: List[str] = Field(default_factory=list)
allergens: List[str] = Field(default_factory=list)
confidence: float = 0.0
# When True the confirmed product is also added to inventory
location: str = "pantry"
quantity: float = 1.0
auto_add: bool = True
class LabelConfirmResponse(BaseModel):
"""Result of confirming a captured product."""
ok: bool
barcode: str
product_id: Optional[int] = None
inventory_item_id: Optional[int] = None
message: str

View file

@ -1,100 +0,0 @@
# app/models/schemas/meal_plan.py
"""Pydantic schemas for meal planning endpoints."""
from __future__ import annotations
from datetime import date as _date
from pydantic import BaseModel, Field, field_validator
VALID_MEAL_TYPES = {"breakfast", "lunch", "dinner", "snack"}
class CreatePlanRequest(BaseModel):
week_start: _date
meal_types: list[str] = Field(default_factory=lambda: ["dinner"])
@field_validator("week_start")
@classmethod
def must_be_monday(cls, v: _date) -> _date:
if v.weekday() != 0:
raise ValueError("week_start must be a Monday (weekday 0)")
return v
class UpdatePlanRequest(BaseModel):
meal_types: list[str]
class UpsertSlotRequest(BaseModel):
recipe_id: int | None = None
servings: float = Field(2.0, gt=0)
custom_label: str | None = None
class SlotSummary(BaseModel):
id: int
plan_id: int
day_of_week: int
meal_type: str
recipe_id: int | None
recipe_title: str | None
servings: float
custom_label: str | None
class PlanSummary(BaseModel):
id: int
week_start: str
meal_types: list[str]
slots: list[SlotSummary]
created_at: str
class RetailerLink(BaseModel):
retailer: str
label: str
url: str
class GapItem(BaseModel):
ingredient_name: str
needed_raw: str | None # e.g. "2 cups" from recipe text
have_quantity: float | None # from pantry
have_unit: str | None
covered: bool # True = pantry has it
retailer_links: list[RetailerLink] = Field(default_factory=list)
class ShoppingListResponse(BaseModel):
plan_id: int
gap_items: list[GapItem]
covered_items: list[GapItem]
disclosure: str | None = None # affiliate disclosure text when links present
class PrepTaskSummary(BaseModel):
id: int
recipe_id: int | None
task_label: str
duration_minutes: int | None
sequence_order: int
equipment: str | None
is_parallel: bool
notes: str | None
user_edited: bool
class PrepSessionSummary(BaseModel):
id: int
plan_id: int
scheduled_date: str
status: str
tasks: list[PrepTaskSummary]
class UpdatePrepTaskRequest(BaseModel):
duration_minutes: int | None = None
sequence_order: int | None = None
notes: str | None = None
equipment: str | None = None

View file

@ -4,36 +4,6 @@ from __future__ import annotations
from pydantic import BaseModel, Field from pydantic import BaseModel, Field
class LeftoversResponse(BaseModel):
"""Cooked-leftover shelf-life estimate returned by POST /recipes/{id}/leftovers."""
fridge_days: int
freeze_days: int | None = None # None = not recommended
freeze_by_day: int | None = None # day number from cook date to freeze by
storage_advice: str
class StepAnalysis(BaseModel):
"""Active/passive classification for one direction step."""
is_passive: bool
detected_minutes: int | None = None
prep_min: int | None = None # estimated physical prep time (action detection)
class TimeEffortProfile(BaseModel):
"""Parsed time and effort profile for a recipe.
Mirrors app.services.recipe.time_effort.TimeEffortProfile (dataclass).
Serialised into RecipeSuggestion so the frontend can render the effort
summary without a second round-trip.
"""
active_min: int = 0
passive_min: int = 0
total_min: int = 0
effort_label: str = "moderate" # "quick" | "moderate" | "involved"
equipment: list[str] = Field(default_factory=list)
step_analyses: list[StepAnalysis] = Field(default_factory=list)
class SwapCandidate(BaseModel): class SwapCandidate(BaseModel):
original_name: str original_name: str
substitute_name: str substitute_name: str
@ -71,10 +41,6 @@ class RecipeSuggestion(BaseModel):
is_wildcard: bool = False is_wildcard: bool = False
nutrition: NutritionPanel | None = None nutrition: NutritionPanel | None = None
source_url: str | None = None source_url: str | None = None
complexity: str | None = None # 'easy' | 'moderate' | 'involved'
estimated_time_min: int | None = None # derived from step count + method signals
time_effort: TimeEffortProfile | None = None # full time/effort profile from parse_time_effort
rerank_score: float | None = None # cross-encoder relevance score (paid+ only, None for free tier)
class GroceryLink(BaseModel): class GroceryLink(BaseModel):
@ -90,19 +56,6 @@ class RecipeResult(BaseModel):
grocery_links: list[GroceryLink] = Field(default_factory=list) grocery_links: list[GroceryLink] = Field(default_factory=list)
rate_limited: bool = False rate_limited: bool = False
rate_limit_count: int = 0 rate_limit_count: int = 0
orch_fallback: bool = False # True when orch budget exhausted; fell back to local LLM
class RecipeJobQueued(BaseModel):
job_id: str
status: str = "queued"
class RecipeJobStatus(BaseModel):
job_id: str
status: str
result: RecipeResult | None = None
error: str | None = None
class NutritionFilters(BaseModel): class NutritionFilters(BaseModel):
@ -115,10 +68,6 @@ class NutritionFilters(BaseModel):
class RecipeRequest(BaseModel): class RecipeRequest(BaseModel):
pantry_items: list[str] pantry_items: list[str]
# Maps product name → secondary state label for items past nominal expiry
# but still within their secondary use window (e.g. {"Bread": "stale"}).
# Used by the recipe engine to boost recipes suited to those specific states.
secondary_pantry_items: dict[str, str] = Field(default_factory=dict)
level: int = Field(default=1, ge=1, le=4) level: int = Field(default=1, ge=1, le=4)
constraints: list[str] = Field(default_factory=list) constraints: list[str] = Field(default_factory=list)
expiry_first: bool = False expiry_first: bool = False
@ -132,98 +81,4 @@ class RecipeRequest(BaseModel):
allergies: list[str] = Field(default_factory=list) allergies: list[str] = Field(default_factory=list)
nutrition_filters: NutritionFilters = Field(default_factory=NutritionFilters) nutrition_filters: NutritionFilters = Field(default_factory=NutritionFilters)
excluded_ids: list[int] = Field(default_factory=list) excluded_ids: list[int] = Field(default_factory=list)
exclude_ingredients: list[str] = Field(default_factory=list)
shopping_mode: bool = False shopping_mode: bool = False
pantry_match_only: bool = False # when True, only return recipes with zero missing ingredients
complexity_filter: str | None = None # 'easy' | 'moderate' | 'involved' — None = any
max_time_min: int | None = None # filter by estimated cooking time ceiling
max_total_min: int | None = None # filter by parsed total time (active + passive)
max_active_min: int | None = None # filter by hands-on active time only
unit_system: str = "metric" # "metric" | "imperial"
# ── Build Your Own schemas ──────────────────────────────────────────────────
class AssemblyRoleOut(BaseModel):
"""One role slot in a template, as returned by GET /api/recipes/templates."""
display: str
required: bool
keywords: list[str]
hint: str = ""
class AssemblyTemplateOut(BaseModel):
"""One assembly template, as returned by GET /api/recipes/templates."""
id: str # slug, e.g. "burrito_taco"
title: str
icon: str
descriptor: str
role_sequence: list[AssemblyRoleOut]
class RoleCandidateItem(BaseModel):
"""One candidate ingredient for a wizard picker step."""
name: str
in_pantry: bool
tags: list[str] = Field(default_factory=list)
class RoleCandidatesResponse(BaseModel):
"""Response from GET /api/recipes/template-candidates."""
compatible: list[RoleCandidateItem] = Field(default_factory=list)
other: list[RoleCandidateItem] = Field(default_factory=list)
available_tags: list[str] = Field(default_factory=list)
class BuildRequest(BaseModel):
"""Request body for POST /api/recipes/build."""
template_id: str
role_overrides: dict[str, str] = Field(default_factory=dict)
class StreamTokenRequest(BaseModel):
"""Request body for POST /recipes/stream-token.
Pantry items and dietary constraints are fetched from the DB at request
time the client does not supply them here.
"""
level: int = Field(4, ge=3, le=4, description="Recipe level: 3=styled, 4=wildcard")
wildcard_confirmed: bool = Field(False, description="Required true for level 4")
class StreamTokenResponse(BaseModel):
"""Response from POST /recipes/stream-token.
The frontend opens EventSource at stream_url?token=<token> to receive
SSE chunks directly from the coordinator.
"""
stream_url: str
token: str
expires_in_s: int
class AskRequest(BaseModel):
"""Request body for POST /recipes/ask."""
question: str = Field(min_length=1, max_length=500)
pantry_items: list[str] = Field(default_factory=list)
class AskRecipeHit(BaseModel):
"""A single recipe result from the Ask endpoint."""
id: int
title: str
match_pct: float | None = None
category: str | None = None
class AskResponse(BaseModel):
"""Response from POST /recipes/ask."""
answer: str | None = None # LLM-synthesized response (Paid tier only)
recipes: list[AskRecipeHit]
tier: str

View file

@ -1,74 +0,0 @@
"""Pydantic schemas for the recipe scanner (kiwi#9).
Scan input photo(s).
Scan output ScannedRecipeResponse (for review + editing before save).
Save input ScannedRecipeSaveRequest.
User recipe output UserRecipeResponse (after save).
"""
from __future__ import annotations
from pydantic import BaseModel, Field
# ── Ingredient in a scanned recipe ────────────────────────────────────────────
class ScannedIngredientSchema(BaseModel):
"""One ingredient line extracted from a recipe photo."""
name: str # normalized generic name ("ranch dressing")
qty: str | None = None # quantity as string, preserving fractions ("1/2", "¼")
unit: str | None = None # unit of measure; null for countable items
raw: str | None = None # verbatim original line from the image
in_pantry: bool = False # True if this ingredient matches something in the pantry
# ── Scan response (returned immediately, not persisted) ───────────────────────
class ScannedRecipeResponse(BaseModel):
"""Structured recipe extracted from photo(s). Returned for user review before save."""
title: str | None = None
subtitle: str | None = None # e.g. "with Broccoli & Ranch Dressing"
servings: str | None = None # kept as string: "2", "4-6", "serves 8"
cook_time: str | None = None # kept as string: "25 min", "1 hour"
source_note: str | None = None # e.g. "Purple Carrot", "Betty Crocker"
ingredients: list[ScannedIngredientSchema] = Field(default_factory=list)
steps: list[str] = Field(default_factory=list)
notes: str | None = None
tags: list[str] = Field(default_factory=list)
pantry_match_pct: int = 0 # 0-100: percentage of ingredients found in pantry
confidence: str = "medium" # "high" | "medium" | "low"
warnings: list[str] = Field(default_factory=list)
# ── Save request ──────────────────────────────────────────────────────────────
class ScannedRecipeSaveRequest(BaseModel):
"""User-reviewed (possibly edited) recipe data to persist as a user recipe."""
title: str
subtitle: str | None = None
servings: str | None = None
cook_time: str | None = None
source_note: str | None = None
ingredients: list[ScannedIngredientSchema]
steps: list[str]
notes: str | None = None
tags: list[str] = Field(default_factory=list)
source: str = "scan" # "scan" | "manual"
# ── User recipe (persisted) ───────────────────────────────────────────────────
class UserRecipeResponse(BaseModel):
"""A user-created or user-scanned recipe stored in user_recipes table."""
id: int
title: str
subtitle: str | None = None
servings: str | None = None
cook_time: str | None = None
source_note: str | None = None
ingredients: list[ScannedIngredientSchema]
steps: list[str]
notes: str | None = None
tags: list[str] = Field(default_factory=list)
source: str
pantry_match_pct: int | None = None
created_at: str

View file

@ -1,60 +0,0 @@
"""Pydantic schemas for the shopping list endpoints."""
from __future__ import annotations
from typing import Optional
from pydantic import BaseModel, Field
class ShoppingItemCreate(BaseModel):
name: str = Field(..., min_length=1, max_length=200)
quantity: Optional[float] = None
unit: Optional[str] = None
category: Optional[str] = None
notes: Optional[str] = None
source: str = "manual"
recipe_id: Optional[int] = None
sort_order: int = 0
class ShoppingItemUpdate(BaseModel):
name: Optional[str] = Field(None, min_length=1, max_length=200)
quantity: Optional[float] = None
unit: Optional[str] = None
category: Optional[str] = None
checked: Optional[bool] = None
notes: Optional[str] = None
sort_order: Optional[int] = None
class GroceryLinkOut(BaseModel):
ingredient: str
retailer: str
url: str
class ShoppingItemResponse(BaseModel):
id: int
name: str
quantity: Optional[float]
unit: Optional[str]
category: Optional[str]
checked: bool
notes: Optional[str]
source: str
recipe_id: Optional[int]
sort_order: int
created_at: str
updated_at: str
grocery_links: list[GroceryLinkOut] = []
class BulkAddFromRecipeRequest(BaseModel):
recipe_id: int
include_covered: bool = False # if True, add pantry-covered items too
class ConfirmPurchaseRequest(BaseModel):
"""Move a checked item into pantry inventory."""
location: str = "pantry"
quantity: Optional[float] = None # override the list quantity
unit: Optional[str] = None

View file

@ -3,11 +3,6 @@
Business logic services for Kiwi. Business logic services for Kiwi.
""" """
from app.services.receipt_service import ReceiptService
__all__ = ["ReceiptService"] __all__ = ["ReceiptService"]
def __getattr__(name: str):
if name == "ReceiptService":
from app.services.receipt_service import ReceiptService
return ReceiptService
raise AttributeError(f"module {__name__!r} has no attribute {name!r}")

View file

@ -1,115 +0,0 @@
# app/services/ap/delivery.py
# MIT License
from __future__ import annotations
import logging
import time
from datetime import datetime, timezone
from pathlib import Path
from circuitforge_core.activitypub import deliver_activity
from app.services.ap.keys import get_actor
logger = logging.getLogger(__name__)
_RETRIES = 3
_BACKOFF = [1.0, 4.0, 16.0]
def deliver_to_followers(post_slug: str, activity: dict, db_path: Path) -> None:
"""Deliver an AP activity to all active followers. Called as a background task.
Retries each inbox up to 3 times with exponential backoff.
Logs each attempt to ap_deliveries in the local kiwi.db.
"""
actor = get_actor()
if actor is None:
return
import sqlite3
conn = sqlite3.connect(str(db_path))
conn.row_factory = sqlite3.Row
try:
followers = conn.execute(
"SELECT inbox_url, shared_inbox FROM ap_followers WHERE active = 1"
).fetchall()
finally:
conn.close()
# Deduplicate by shared_inbox where available
inboxes: set[str] = set()
for row in followers:
inbox = row["shared_inbox"] or row["inbox_url"]
inboxes.add(inbox)
for inbox_url in inboxes:
_deliver_with_retry(post_slug=post_slug, activity=activity, inbox_url=inbox_url, db_path=db_path)
def _deliver_with_retry(
post_slug: str,
activity: dict,
inbox_url: str,
db_path: Path,
) -> None:
actor = get_actor()
if actor is None:
return
import sqlite3
conn = sqlite3.connect(str(db_path))
try:
conn.execute(
"INSERT OR IGNORE INTO ap_deliveries (post_slug, target_inbox, status) VALUES (?,?,?)",
(post_slug, inbox_url, "pending"),
)
conn.commit()
finally:
conn.close()
last_error: str | None = None
for attempt, delay in enumerate(_BACKOFF[:_RETRIES]):
try:
resp = deliver_activity(activity=activity, inbox_url=inbox_url, actor=actor, timeout=10.0)
if resp.status_code < 300:
_update_delivery(db_path, post_slug, inbox_url, "delivered", None)
return
last_error = f"HTTP {resp.status_code}"
except Exception as exc:
last_error = str(exc)[:200]
if attempt < _RETRIES - 1:
time.sleep(delay)
_update_delivery(db_path, post_slug, inbox_url, "failed", last_error)
logger.warning("AP delivery failed after %d attempts to %s: %s", _RETRIES, inbox_url, last_error)
def _update_delivery(
db_path: Path,
post_slug: str,
inbox_url: str,
status: str,
error: str | None,
) -> None:
import sqlite3
now = datetime.now(timezone.utc).isoformat()
conn = sqlite3.connect(str(db_path))
try:
if status == "delivered":
conn.execute(
"""UPDATE ap_deliveries SET status=?, attempts=attempts+1, delivered_at=?
WHERE post_slug=? AND target_inbox=?""",
(status, now, post_slug, inbox_url),
)
else:
conn.execute(
"""UPDATE ap_deliveries SET status=?, attempts=attempts+1, last_error=?
WHERE post_slug=? AND target_inbox=?""",
(status, error, post_slug, inbox_url),
)
conn.commit()
finally:
conn.close()

View file

@ -1,48 +0,0 @@
# app/services/ap/keys.py
# MIT License
from __future__ import annotations
import logging
from pathlib import Path
from circuitforge_core.activitypub import CFActor, generate_rsa_keypair, load_actor_from_key_file
logger = logging.getLogger(__name__)
_actor: CFActor | None = None
def get_actor() -> CFActor | None:
"""Return the loaded instance actor, or None if AP is not enabled."""
return _actor
def init_actor(host: str, key_path: Path) -> CFActor:
"""Load or generate the instance RSA keypair and build the CFActor singleton.
Called once at startup when AP_ENABLED=true. Generates a new 2048-bit keypair
if the key file does not yet exist (first boot).
"""
global _actor
key_path.parent.mkdir(parents=True, exist_ok=True)
if not key_path.exists():
logger.info("AP: no key file found at %s — generating new RSA-2048 keypair", key_path)
private_pem, _pub = generate_rsa_keypair(bits=2048)
key_path.write_text(private_pem, encoding="utf-8")
key_path.chmod(0o600)
base = f"https://{host}"
actor_id = f"{base}/ap/actor"
_actor = load_actor_from_key_file(
actor_id=actor_id,
username="kiwi",
display_name="Kiwi Pantry",
private_key_path=str(key_path),
summary="Community pantry and recipe feed from a Kiwi instance.",
)
logger.info("AP: instance actor loaded — %s", actor_id)
return _actor

View file

@ -1,194 +0,0 @@
# app/services/ap/mastodon.py
# MIT License
from __future__ import annotations
import logging
from pathlib import Path
import httpx
logger = logging.getLogger(__name__)
_APP_SCOPES = "write:statuses"
_APP_NAME = "Kiwi Pantry"
_APP_WEBSITE = "https://circuitforge.tech/kiwi"
def register_app(instance_url: str, redirect_uri: str) -> dict:
"""Dynamically register Kiwi as an OAuth app on the user's Mastodon instance.
Returns the app credentials dict (client_id, client_secret, etc.).
Raises httpx.HTTPError on failure.
"""
url = instance_url.rstrip("/") + "/api/v1/apps"
resp = httpx.post(
url,
data={
"client_name": _APP_NAME,
"redirect_uris": redirect_uri,
"scopes": _APP_SCOPES,
"website": _APP_WEBSITE,
},
timeout=10.0,
)
resp.raise_for_status()
return resp.json()
def build_authorize_url(instance_url: str, client_id: str, redirect_uri: str) -> str:
"""Return the OAuth authorize URL to redirect the user to."""
return (
f"{instance_url.rstrip('/')}/oauth/authorize"
f"?response_type=code"
f"&client_id={client_id}"
f"&redirect_uri={redirect_uri}"
f"&scope={_APP_SCOPES}"
)
def exchange_code(
instance_url: str,
client_id: str,
client_secret: str,
code: str,
redirect_uri: str,
) -> str:
"""Exchange an authorization code for an access token. Returns the token string."""
url = instance_url.rstrip("/") + "/oauth/token"
resp = httpx.post(
url,
data={
"grant_type": "authorization_code",
"client_id": client_id,
"client_secret": client_secret,
"redirect_uri": redirect_uri,
"code": code,
"scope": _APP_SCOPES,
},
timeout=10.0,
)
resp.raise_for_status()
return resp.json()["access_token"]
def post_status(instance_url: str, access_token: str, content: str) -> dict:
"""Post a status to the user's Mastodon account. Returns the status response dict."""
url = instance_url.rstrip("/") + "/api/v1/statuses"
resp = httpx.post(
url,
headers={"Authorization": f"Bearer {access_token}"},
json={"status": content, "visibility": "public"},
timeout=15.0,
)
resp.raise_for_status()
return resp.json()
def build_post_content(post: dict) -> str:
"""Format a community post dict as Mastodon-ready plain text."""
title = post.get("title") or "Untitled"
recipe = post.get("recipe_name")
notes = post.get("outcome_notes") or post.get("description")
tags_raw: list[str] = post.get("dietary_tags") or []
lines = []
if recipe and recipe != title:
lines.append(f"🍽 {title}{recipe}")
else:
lines.append(f"🍽 {title}")
if notes:
snippet = notes[:200].strip()
if len(notes) > 200:
snippet += ""
lines.append(f"\n{snippet}")
hashtags = ["#Kiwi", "#Cooking"]
for tag in tags_raw[:3]:
ht = "#" + "".join(w.capitalize() for w in tag.replace("-", " ").split())
hashtags.append(ht)
lines.append("\n" + " ".join(hashtags))
return "\n".join(lines)
def store_token(
db_path: Path,
directus_user_id: str,
instance_url: str,
access_token: str,
encryption_key: str | None,
) -> None:
"""Persist a Mastodon access token in the user's local kiwi.db."""
token_to_store = _encrypt(access_token, encryption_key)
import sqlite3
conn = sqlite3.connect(str(db_path))
try:
conn.execute(
"""INSERT INTO mastodon_tokens (directus_user_id, instance_url, access_token)
VALUES (?, ?, ?)
ON CONFLICT(directus_user_id) DO UPDATE SET
instance_url=excluded.instance_url,
access_token=excluded.access_token,
updated_at=datetime('now')""",
(directus_user_id, instance_url.rstrip("/"), token_to_store),
)
conn.commit()
finally:
conn.close()
def get_token(
db_path: Path,
directus_user_id: str,
encryption_key: str | None,
) -> tuple[str, str] | None:
"""Return (instance_url, plaintext_access_token) or None if not connected."""
import sqlite3
conn = sqlite3.connect(str(db_path))
try:
row = conn.execute(
"SELECT instance_url, access_token FROM mastodon_tokens WHERE directus_user_id = ?",
(directus_user_id,),
).fetchone()
finally:
conn.close()
if row is None:
return None
return row[0], _decrypt(row[1], encryption_key)
def delete_token(db_path: Path, directus_user_id: str) -> None:
"""Remove the user's stored Mastodon token."""
import sqlite3
conn = sqlite3.connect(str(db_path))
try:
conn.execute(
"DELETE FROM mastodon_tokens WHERE directus_user_id = ?", (directus_user_id,)
)
conn.commit()
finally:
conn.close()
def _encrypt(plaintext: str, key: str | None) -> str:
if key is None:
return plaintext
try:
from cryptography.fernet import Fernet
return Fernet(key.encode()).encrypt(plaintext.encode()).decode()
except Exception:
logger.warning("Mastodon token encryption failed — storing plaintext")
return plaintext
def _decrypt(ciphertext: str, key: str | None) -> str:
if key is None:
return ciphertext
try:
from cryptography.fernet import Fernet
return Fernet(key.encode()).decrypt(ciphertext.encode()).decode()
except Exception:
logger.warning("Mastodon token decryption failed — returning as-is")
return ciphertext

View file

@ -1,44 +0,0 @@
# app/services/community/ap_compat.py
# MIT License — AP scaffold only (no actor, inbox, outbox)
from __future__ import annotations
from datetime import datetime, timezone
def post_to_ap_json_ld(post: dict, base_url: str) -> dict:
"""Serialize a community post dict to an ActivityPub-compatible JSON-LD Note.
This is a read-only scaffold. No AP actor, inbox, or outbox.
The slug URI is stable so a future full AP implementation can reuse posts
without a DB migration.
"""
slug = post["slug"]
published = post.get("published")
if isinstance(published, datetime):
published_str = published.astimezone(timezone.utc).strftime("%Y-%m-%dT%H:%M:%SZ")
else:
published_str = str(published)
dietary_tags: list[str] = post.get("dietary_tags") or []
tags = [{"type": "Hashtag", "name": "#kiwi"}]
for tag in dietary_tags:
tags.append({"type": "Hashtag", "name": f"#{tag.replace('-', '').replace(' ', '')}"})
return {
"@context": "https://www.w3.org/ns/activitystreams",
"type": "Note",
"id": f"{base_url}/api/v1/community/posts/{slug}",
"attributedTo": post.get("pseudonym", "anonymous"),
"content": _build_content(post),
"published": published_str,
"tag": tags,
}
def _build_content(post: dict) -> str:
title = post.get("title") or "Untitled"
desc = post.get("description")
if desc:
return f"{title}{desc}"
return title

View file

@ -1,90 +0,0 @@
# app/services/community/community_store.py
# MIT License
from __future__ import annotations
import logging
from circuitforge_core.community import CommunityPost, SharedStore
logger = logging.getLogger(__name__)
class KiwiCommunityStore(SharedStore):
"""Kiwi-specific community store: adds kiwi-domain query methods on top of SharedStore."""
def list_meal_plans(
self,
limit: int = 20,
offset: int = 0,
dietary_tags: list[str] | None = None,
allergen_exclude: list[str] | None = None,
) -> list[CommunityPost]:
return self.list_posts(
limit=limit,
offset=offset,
post_type="plan",
dietary_tags=dietary_tags,
allergen_exclude=allergen_exclude,
source_product="kiwi",
)
def list_outcomes(
self,
limit: int = 20,
offset: int = 0,
post_type: str | None = None,
) -> list[CommunityPost]:
if post_type in ("recipe_success", "recipe_blooper"):
return self.list_posts(
limit=limit,
offset=offset,
post_type=post_type,
source_product="kiwi",
)
success = self.list_posts(
limit=limit,
offset=0,
post_type="recipe_success",
source_product="kiwi",
)
bloopers = self.list_posts(
limit=limit,
offset=0,
post_type="recipe_blooper",
source_product="kiwi",
)
merged = sorted(success + bloopers, key=lambda p: p.published, reverse=True)
return merged[:limit]
def get_or_create_pseudonym(
store,
directus_user_id: str,
requested_name: str | None,
) -> str:
"""Return the user's current pseudonym, creating it if it doesn't exist.
If the user has an existing pseudonym, return it (ignore requested_name).
If not, create using requested_name (must be provided for first-time setup).
Raises ValueError if no existing pseudonym and requested_name is None or blank.
"""
existing = store.get_current_pseudonym(directus_user_id)
if existing:
return existing
if not requested_name or not requested_name.strip():
raise ValueError(
"A pseudonym is required for first publish. "
"Pass requested_name with the user's chosen display name."
)
name = requested_name.strip()
if "@" in name:
raise ValueError(
"Pseudonym must not contain '@' — use a display name, not an email address."
)
store.set_pseudonym(directus_user_id, name)
return name

View file

@ -1,111 +0,0 @@
# app/services/community/dedup.py
# MIT License
from __future__ import annotations
import json
import logging
from pathlib import Path
logger = logging.getLogger(__name__)
_SIMILARITY_TIERS = {
"exact_recipe": "This exact recipe is already in the community feed.",
"very_similar": "Very similar recipes already exist (70%+ ingredient overlap).",
"somewhat_similar": "Somewhat similar recipes exist (35-70% ingredient overlap).",
"different": "No close matches found.",
}
def _parse_ingredient_names(raw) -> set[str]:
"""Return a normalised set of ingredient name tokens from various stored formats."""
if raw is None:
return set()
if isinstance(raw, str):
try:
raw = json.loads(raw)
except (ValueError, TypeError):
return set()
names: set[str] = set()
for item in raw:
if isinstance(item, str):
names.add(item.lower().strip())
elif isinstance(item, dict):
name = item.get("name") or item.get("ingredient") or ""
if name:
names.add(name.lower().strip())
return names
def jaccard(a: set[str], b: set[str]) -> float:
if not a and not b:
return 1.0
if not a or not b:
return 0.0
return len(a & b) / len(a | b)
def similarity_tier(jaccard_score: float, exact_recipe: bool) -> str:
if exact_recipe:
return "exact_recipe"
if jaccard_score >= 0.70:
return "very_similar"
if jaccard_score >= 0.35:
return "somewhat_similar"
return "different"
def fetch_recipe_ingredients(db_path: Path, recipe_id: int | None) -> set[str]:
"""Look up ingredient names for a recipe from the local corpus. Returns empty set on miss."""
if recipe_id is None:
return set()
try:
from app.db.store import Store
store = Store(db_path)
try:
row = store.get_recipe(recipe_id)
if row is None:
return set()
return _parse_ingredient_names(row.get("ingredient_names"))
finally:
store.close()
except Exception:
logger.debug("ingredient lookup failed for recipe_id=%s", recipe_id)
return set()
def build_similar_post_result(
post,
incoming_recipe_id: int | None,
incoming_ingredients: set[str],
db_path: Path,
) -> dict:
"""Build a similarity result dict for one existing community post."""
exact = (
incoming_recipe_id is not None
and post.recipe_id is not None
and post.recipe_id == incoming_recipe_id
)
j_score = 0.0
if not exact and incoming_ingredients:
existing_ingredients = fetch_recipe_ingredients(db_path, post.recipe_id)
if existing_ingredients:
j_score = jaccard(incoming_ingredients, existing_ingredients)
tier = similarity_tier(j_score, exact)
return {
"slug": post.slug,
"title": post.title,
"recipe_name": post.recipe_name,
"pseudonym": post.pseudonym,
"published": (
post.published.isoformat()
if hasattr(post.published, "isoformat")
else str(post.published)
),
"similarity_tier": tier,
"jaccard_score": round(j_score, 3) if not exact else None,
"tier_description": _SIMILARITY_TIERS.get(tier, ""),
}

View file

@ -1,138 +0,0 @@
# app/services/community/element_snapshot.py
# MIT License
from __future__ import annotations
from dataclasses import dataclass
# Ingredient name substrings → allergen flag
_ALLERGEN_MAP: dict[str, str] = {
"milk": "dairy", "cream": "dairy", "cheese": "dairy", "butter": "dairy",
"yogurt": "dairy", "whey": "dairy",
"egg": "eggs",
"wheat": "gluten", "pasta": "gluten", "flour": "gluten", "bread": "gluten",
"barley": "gluten", "rye": "gluten",
"peanut": "nuts", "almond": "nuts", "cashew": "nuts", "walnut": "nuts",
"pecan": "nuts", "hazelnut": "nuts", "pistachio": "nuts", "macadamia": "nuts",
"soy": "soy", "tofu": "soy", "edamame": "soy", "miso": "soy", "tempeh": "soy",
"shrimp": "shellfish", "crab": "shellfish", "lobster": "shellfish",
"clam": "shellfish", "mussel": "shellfish", "scallop": "shellfish",
"fish": "fish", "salmon": "fish", "tuna": "fish", "cod": "fish",
"tilapia": "fish", "halibut": "fish",
"sesame": "sesame",
}
_MEAT_KEYWORDS = frozenset([
"chicken", "beef", "pork", "lamb", "turkey", "bacon", "ham", "sausage",
"salami", "prosciutto", "guanciale", "pancetta", "steak", "ground meat",
"mince", "veal", "duck", "venison", "bison", "lard",
])
_SEAFOOD_KEYWORDS = frozenset([
"fish", "shrimp", "crab", "lobster", "tuna", "salmon", "clam", "mussel",
"scallop", "anchovy", "sardine", "cod", "tilapia",
])
_ANIMAL_PRODUCT_KEYWORDS = frozenset([
"milk", "cream", "cheese", "butter", "egg", "honey", "yogurt", "whey",
])
def _detect_allergens(ingredient_names: list[str]) -> list[str]:
found: set[str] = set()
lowered = [n.lower() for n in ingredient_names]
for ingredient in lowered:
for keyword, flag in _ALLERGEN_MAP.items():
if keyword in ingredient:
found.add(flag)
return sorted(found)
def _detect_dietary_tags(ingredient_names: list[str]) -> list[str]:
lowered = [n.lower() for n in ingredient_names]
all_text = " ".join(lowered)
has_meat = any(k in all_text for k in _MEAT_KEYWORDS)
has_seafood = any(k in all_text for k in _SEAFOOD_KEYWORDS)
has_animal_products = any(k in all_text for k in _ANIMAL_PRODUCT_KEYWORDS)
tags: list[str] = []
if not has_meat and not has_seafood:
tags.append("vegetarian")
if not has_meat and not has_seafood and not has_animal_products:
tags.append("vegan")
return tags
@dataclass(frozen=True)
class ElementSnapshot:
seasoning_score: float
richness_score: float
brightness_score: float
depth_score: float
aroma_score: float
structure_score: float
texture_profile: str
dietary_tags: tuple
allergen_flags: tuple
flavor_molecules: tuple
fat_pct: float | None
protein_pct: float | None
moisture_pct: float | None
def compute_snapshot(recipe_ids: list[int], store) -> ElementSnapshot:
"""Compute an element snapshot from a list of recipe IDs.
Pulls SFAH scores, ingredient lists, and USDA FDC macros from the corpus.
Averages numeric scores across all recipes. Unions allergen flags and dietary tags.
Call at publish time only snapshot is stored denormalized in community_posts.
"""
if not recipe_ids:
return ElementSnapshot(
seasoning_score=0.0, richness_score=0.0, brightness_score=0.0,
depth_score=0.0, aroma_score=0.0, structure_score=0.0,
texture_profile="", dietary_tags=(), allergen_flags=(),
flavor_molecules=(), fat_pct=None, protein_pct=None, moisture_pct=None,
)
rows = store.get_recipes_by_ids(recipe_ids)
if not rows:
return ElementSnapshot(
seasoning_score=0.0, richness_score=0.0, brightness_score=0.0,
depth_score=0.0, aroma_score=0.0, structure_score=0.0,
texture_profile="", dietary_tags=(), allergen_flags=(),
flavor_molecules=(), fat_pct=None, protein_pct=None, moisture_pct=None,
)
def _avg(field: str) -> float:
vals = [r.get(field) or 0.0 for r in rows]
return sum(vals) / len(vals)
all_ingredients: list[str] = []
for r in rows:
names = r.get("ingredient_names") or []
all_ingredients.extend(names if isinstance(names, list) else [])
allergens = _detect_allergens(all_ingredients)
dietary = _detect_dietary_tags(all_ingredients)
texture = rows[0].get("texture_profile") or ""
fat_vals = [r.get("fat") for r in rows if r.get("fat") is not None]
prot_vals = [r.get("protein") for r in rows if r.get("protein") is not None]
moist_vals = [r.get("moisture") for r in rows if r.get("moisture") is not None]
return ElementSnapshot(
seasoning_score=_avg("seasoning_score"),
richness_score=_avg("richness_score"),
brightness_score=_avg("brightness_score"),
depth_score=_avg("depth_score"),
aroma_score=_avg("aroma_score"),
structure_score=_avg("structure_score"),
texture_profile=texture,
dietary_tags=tuple(dietary),
allergen_flags=tuple(allergens),
flavor_molecules=(),
fat_pct=(sum(fat_vals) / len(fat_vals)) if fat_vals else None,
protein_pct=(sum(prot_vals) / len(prot_vals)) if prot_vals else None,
moisture_pct=(sum(moist_vals) / len(moist_vals)) if moist_vals else None,
)

View file

@ -1,43 +0,0 @@
# app/services/community/feed.py
# MIT License
from __future__ import annotations
from datetime import datetime, timezone
from email.utils import format_datetime
from xml.etree.ElementTree import Element, SubElement, tostring
def posts_to_rss(posts: list[dict], base_url: str) -> str:
"""Generate an RSS 2.0 feed from a list of community post dicts.
base_url: the root URL of this Kiwi instance (no trailing slash).
Returns UTF-8 XML string.
"""
rss = Element("rss", version="2.0")
channel = SubElement(rss, "channel")
_sub(channel, "title", "Kiwi Community Feed")
_sub(channel, "link", f"{base_url}/community")
_sub(channel, "description", "Meal plans and recipe outcomes from the Kiwi community")
_sub(channel, "language", "en")
_sub(channel, "lastBuildDate", format_datetime(datetime.now(timezone.utc)))
for post in posts:
item = SubElement(channel, "item")
_sub(item, "title", post.get("title") or "Untitled")
_sub(item, "link", f"{base_url}/api/v1/community/posts/{post['slug']}")
_sub(item, "guid", f"{base_url}/api/v1/community/posts/{post['slug']}")
if post.get("description"):
_sub(item, "description", post["description"])
published = post.get("published")
if isinstance(published, datetime):
_sub(item, "pubDate", format_datetime(published))
return '<?xml version="1.0" encoding="UTF-8"?>\n' + tostring(rss, encoding="unicode")
def _sub(parent: Element, tag: str, text: str) -> Element:
el = SubElement(parent, tag)
el.text = text
return el

View file

@ -1,72 +0,0 @@
# app/services/community/mdns.py
# MIT License
from __future__ import annotations
import logging
import socket
logger = logging.getLogger(__name__)
# Import deferred to avoid hard failure when zeroconf is not installed
try:
from zeroconf import ServiceInfo, Zeroconf
_ZEROCONF_AVAILABLE = True
except ImportError:
_ZEROCONF_AVAILABLE = False
class KiwiMDNS:
"""Advertise this Kiwi instance on the LAN via mDNS (_kiwi._tcp.local).
Defaults to disabled (enabled=False). User must explicitly opt in via the
Settings page. This matches the CF a11y requirement: no surprise broadcasting.
Usage:
mdns = KiwiMDNS(enabled=settings.MDNS_ENABLED, port=settings.PORT,
feed_url=f"http://{hostname}:{settings.PORT}/api/v1/community/local-feed")
mdns.start() # in lifespan startup
mdns.stop() # in lifespan shutdown
"""
SERVICE_TYPE = "_kiwi._tcp.local."
def __init__(self, enabled: bool, port: int, feed_url: str) -> None:
self._enabled = enabled
self._port = port
self._feed_url = feed_url
self._zc: "Zeroconf | None" = None
self._info: "ServiceInfo | None" = None
def start(self) -> None:
if not self._enabled:
logger.debug("mDNS advertisement disabled (user has not opted in)")
return
if not _ZEROCONF_AVAILABLE:
logger.warning("zeroconf package not installed — mDNS advertisement unavailable")
return
hostname = socket.gethostname()
service_name = f"kiwi-{hostname}.{self.SERVICE_TYPE}"
self._info = ServiceInfo(
type_=self.SERVICE_TYPE,
name=service_name,
port=self._port,
properties={
b"feed_url": self._feed_url.encode(),
b"version": b"1",
},
addresses=[socket.inet_aton("127.0.0.1")],
)
self._zc = Zeroconf()
self._zc.register_service(self._info)
logger.info("mDNS: advertising %s on port %d", service_name, self._port)
def stop(self) -> None:
if self._zc is None or self._info is None:
return
self._zc.unregister_service(self._info)
self._zc.close()
self._zc = None
self._info = None
logger.info("mDNS: advertisement stopped")

View file

@ -1,94 +0,0 @@
"""cf-orch coordinator proxy client.
Calls the coordinator's /proxy/authorize endpoint to obtain a one-time
stream URL + token for LLM streaming. Always raises CoordinatorError on
failure callers decide how to handle it (stream-token endpoint returns
503 or 403 as appropriate).
"""
from __future__ import annotations
import logging
import os
from dataclasses import dataclass
import httpx
log = logging.getLogger(__name__)
class CoordinatorError(Exception):
"""Raised when the coordinator returns an error or is unreachable."""
def __init__(self, message: str, status_code: int = 503):
super().__init__(message)
self.status_code = status_code
@dataclass(frozen=True)
class StreamTokenResult:
stream_url: str
token: str
expires_in_s: int
def _coordinator_url() -> str:
return os.environ.get("COORDINATOR_URL", "http://10.1.10.71:7700")
def _product_key() -> str:
return os.environ.get("COORDINATOR_KIWI_KEY", "")
async def coordinator_authorize(
prompt: str,
caller: str = "kiwi-recipe",
ttl_s: int = 300,
) -> StreamTokenResult:
"""Call POST /proxy/authorize on the coordinator.
Returns a StreamTokenResult with the stream URL and one-time token.
Raises CoordinatorError on any failure (network, auth, capacity).
"""
url = f"{_coordinator_url()}/proxy/authorize"
key = _product_key()
if not key:
raise CoordinatorError(
"COORDINATOR_KIWI_KEY env var is not set — streaming unavailable",
status_code=503,
)
payload = {
"product": "kiwi",
"product_key": key,
"caller": caller,
"prompt": prompt,
"params": {},
"ttl_s": ttl_s,
}
try:
async with httpx.AsyncClient(timeout=10.0) as client:
resp = await client.post(url, json=payload)
except httpx.RequestError as exc:
log.warning("coordinator_authorize network error: %s", exc)
raise CoordinatorError(f"Coordinator unreachable: {exc}", status_code=503)
if resp.status_code == 401:
raise CoordinatorError("Invalid product key", status_code=401)
if resp.status_code == 429:
raise CoordinatorError("Too many concurrent streams", status_code=429)
if resp.status_code == 503:
raise CoordinatorError("No GPU available for streaming", status_code=503)
if not resp.is_success:
raise CoordinatorError(
f"Coordinator error {resp.status_code}: {resp.text[:200]}",
status_code=503,
)
data = resp.json()
# Use public_stream_url if coordinator provides it (cloud mode), else stream_url
stream_url = data.get("public_stream_url") or data["stream_url"]
return StreamTokenResult(
stream_url=stream_url,
token=data["token"],
expires_in_s=data["expires_in_s"],
)

View file

@ -116,270 +116,6 @@ class ExpirationPredictor:
'prepared_foods': {'fridge': 4, 'freezer': 90}, 'prepared_foods': {'fridge': 4, 'freezer': 90},
} }
# Secondary shelf life in days after a package is opened.
# Sources: USDA FoodKeeper app, FDA consumer guides.
# Only categories where opening significantly shortens shelf life are listed.
# Items not listed default to None (no secondary window tracked).
SHELF_LIFE_AFTER_OPENING: dict[str, int] = {
# Dairy — once opened, clock ticks fast
'dairy': 5,
'milk': 5,
'cream': 3,
'yogurt': 7,
'cheese': 14,
'butter': 30,
# Condiments — refrigerated after opening
'condiments': 30,
'ketchup': 30,
'mustard': 30,
'mayo': 14,
'salad_dressing': 30,
'soy_sauce': 90,
# Canned goods — once opened, very short
'canned_goods': 4,
# Beverages
'juice': 7,
'soda': 4,
# Bread / Bakery
'bread': 5,
'bakery': 3,
# Produce
'leafy_greens': 3,
'berries': 3,
# Pantry staples (open bag)
'chips': 14,
'cookies': 14,
'cereal': 30,
'flour': 90,
}
# Post-expiry secondary use window.
# These are NOT spoilage extensions — they describe a qualitative state
# change where the ingredient is specifically suited for certain preparations.
# Sources: USDA FoodKeeper, food science, culinary tradition.
#
# Fields:
# window_days — days past nominal expiry still usable in secondary state
# label — short UI label for the state
# uses — recipe contexts suited to this state (shown in UI)
# warning — safety note, calm tone, None if none needed
# discard_signs — qualitative signs the item has gone past the secondary window
# constraints_exclude — dietary constraint labels that suppress this entry entirely
# (e.g. alcohol-containing items suppressed for halal/alcohol-free)
SECONDARY_WINDOW: dict[str, dict] = {
'bread': {
'window_days': 5,
'label': 'stale',
'uses': ['croutons', 'stuffing', 'bread pudding', 'French toast', 'panzanella'],
'warning': 'Check for mold before use — discard if any is visible.',
'discard_signs': 'Visible mold (any colour), or unpleasant smell beyond dry/yeasty.',
'constraints_exclude': [],
},
'bakery': {
'window_days': 3,
'label': 'day-old',
'uses': ['French toast', 'bread pudding', 'crumbles', 'trifle base', 'cake pops', 'streusel topping', 'bread crumbs'],
'warning': 'Check for mold before use — discard if any is visible.',
'discard_signs': 'Visible mold, sliminess, or strong sour smell.',
'constraints_exclude': [],
},
'bananas': {
'window_days': 5,
'label': 'overripe',
'uses': ['banana bread', 'smoothies', 'pancakes', 'muffins'],
'warning': None,
'discard_signs': 'Leaking liquid, fermented smell, or mold on skin.',
'constraints_exclude': [],
},
'milk': {
'window_days': 3,
'label': 'sour',
'uses': ['pancakes', 'scones', 'waffles', 'muffins', 'quick breads', 'béchamel', 'baked mac and cheese'],
'warning': 'Use only in cooked recipes — do not drink.',
'discard_signs': 'Chunky texture, strong unpleasant smell beyond tangy, or visible separation with grey colour.',
'constraints_exclude': [],
},
'dairy': {
'window_days': 2,
'label': 'sour',
'uses': ['pancakes', 'scones', 'quick breads', 'muffins', 'waffles'],
'warning': 'Use only in cooked recipes — do not drink.',
'discard_signs': 'Strong unpleasant smell, unusual colour, or chunky texture.',
'constraints_exclude': [],
},
'cheese': {
'window_days': 14,
'label': 'rind-ready',
'uses': ['parmesan broth', 'minestrone', 'ribollita', 'risotto', 'polenta', 'bean soups', 'gratins'],
'warning': None,
'discard_signs': 'Soft or wet texture on hard cheese, pink or black mold (white/green surface mold on hard cheese can be cut off with 1cm margin).',
'constraints_exclude': [],
},
'rice': {
'window_days': 2,
'label': 'day-old',
'uses': ['fried rice', 'onigiri', 'rice porridge', 'congee', 'arancini', 'stuffed peppers', 'rice fritters'],
'warning': 'Refrigerate immediately after cooking — do not leave at room temp.',
'discard_signs': 'Slimy texture, unusual smell, or more than 4 days since cooking.',
'constraints_exclude': [],
},
'tortillas': {
'window_days': 5,
'label': 'stale',
'uses': ['chilaquiles', 'migas', 'tortilla soup', 'casserole'],
'warning': 'Check for mold, especially if stored in a sealed bag — discard if any is visible.',
'discard_signs': 'Visible mold (check seams and edges), or strong sour smell.',
'constraints_exclude': [],
},
# ── New entries ──────────────────────────────────────────────────────
'apples': {
'window_days': 7,
'label': 'soft',
'uses': ['applesauce', 'apple butter', 'baked apples', 'apple crisp', 'smoothies', 'chutney'],
'warning': None,
'discard_signs': 'Large bruised areas with fermented smell, visible mold, or liquid leaking from skin.',
'constraints_exclude': [],
},
'leafy_greens': {
'window_days': 2,
'label': 'wilting',
'uses': ['sautéed greens', 'soups', 'smoothies', 'frittata', 'pasta add-in', 'stir fry'],
'warning': None,
'discard_signs': 'Slimy texture, strong unpleasant smell, or yellowed and mushy leaves.',
'constraints_exclude': [],
},
'tomatoes': {
'window_days': 4,
'label': 'soft',
'uses': ['roasted tomatoes', 'tomato sauce', 'shakshuka', 'bruschetta', 'soup', 'salsa'],
'warning': None,
'discard_signs': 'Broken skin with liquid pooling, mold, or fermented smell.',
'constraints_exclude': [],
},
'cooked_pasta': {
'window_days': 3,
'label': 'day-old',
'uses': ['pasta frittata', 'pasta salad', 'baked pasta', 'soup add-in', 'fried pasta cakes'],
'warning': 'Refrigerate within 2 hours of cooking.',
'discard_signs': 'Slimy texture, off smell, or more than 4 days since cooking.',
'constraints_exclude': [],
},
'cooked_potatoes': {
'window_days': 3,
'label': 'day-old',
'uses': ['potato pancakes', 'hash browns', 'potato soup', 'gnocchi', 'twice-baked potatoes', 'croquettes'],
'warning': 'Refrigerate within 2 hours of cooking.',
'discard_signs': 'Slimy texture, off smell, or more than 4 days since cooking.',
'constraints_exclude': [],
},
'yogurt': {
'window_days': 7,
'label': 'tangy',
'uses': ['marinades', 'flatbreads', 'smoothies', 'tzatziki', 'baked goods', 'salad dressings'],
'warning': None,
'discard_signs': 'Pink or orange discolouration, visible mold, or strongly unpleasant smell (not just tangy).',
'constraints_exclude': [],
},
'cream': {
'window_days': 2,
'label': 'sour',
'uses': ['soups', 'sauces', 'scones', 'quick breads', 'mashed potatoes'],
'warning': 'Use in cooked recipes only. Discard if the smell is strongly unpleasant rather than tangy.',
'discard_signs': 'Strong unpleasant smell beyond tangy, unusual colour, or chunky texture.',
'constraints_exclude': [],
},
'wine': {
'window_days': 4,
'label': 'open',
'uses': ['pan sauces', 'braises', 'risotto', 'marinades', 'poaching liquid', 'wine reduction'],
'warning': None,
'discard_signs': 'Strong vinegar smell (still usable in braises/marinades), or visible cloudiness with off-smell.',
'constraints_exclude': ['halal', 'alcohol-free'],
},
'cooked_beans': {
'window_days': 3,
'label': 'day-old',
'uses': ['refried beans', 'bean soup', 'bean fritters', 'hummus', 'bean dip', 'grain bowls'],
'warning': 'Refrigerate within 2 hours of cooking.',
'discard_signs': 'Slimy texture, off smell, or more than 4 days since cooking.',
'constraints_exclude': [],
},
'cooked_meat': {
'window_days': 2,
'label': 'leftover',
'uses': ['grain bowls', 'tacos', 'soups', 'fried rice', 'sandwiches', 'hash', 'pasta add-in'],
'warning': 'Refrigerate within 2 hours of cooking.',
'discard_signs': 'Off smell, slimy texture, or more than 34 days since cooking.',
'constraints_exclude': [],
},
}
def days_after_opening(self, category: str | None) -> int | None:
"""Return days of shelf life remaining once a package is opened.
Returns None if the category is unknown or not tracked after opening
(e.g. frozen items, raw meat category check irrelevant once opened).
"""
if not category:
return None
return self.SHELF_LIFE_AFTER_OPENING.get(category.lower())
def secondary_state(
self, category: str | None, expiry_date: str | None
) -> dict | None:
"""Return secondary use info if the item is in its post-expiry secondary window.
Returns a dict with label, uses, warning, discard_signs, constraints_exclude,
days_past, and window_days when the item is past its nominal expiry date but
still within the secondary use window.
Returns None in all other cases (unknown category, no window defined, not yet
expired, or past the secondary window).
Callers should apply constraints_exclude against user dietary constraints
and suppress the result entirely if any excluded constraint is active.
See filter_secondary_by_constraints().
"""
if not category or not expiry_date:
return None
entry = self.SECONDARY_WINDOW.get(category.lower())
if not entry:
return None
try:
from datetime import date
today = date.today()
exp = date.fromisoformat(expiry_date)
days_past = (today - exp).days
if 0 <= days_past <= entry['window_days']:
return {
'label': entry['label'],
'uses': list(entry['uses']),
'warning': entry['warning'],
'discard_signs': entry.get('discard_signs'),
'constraints_exclude': list(entry.get('constraints_exclude') or []),
'days_past': days_past,
'window_days': entry['window_days'],
}
except ValueError:
pass
return None
@staticmethod
def filter_secondary_by_constraints(
sec: dict | None,
user_constraints: list[str],
) -> dict | None:
"""Suppress secondary state entirely if any excluded constraint is active.
Call after secondary_state() when user dietary constraints are available.
Returns sec unchanged when no constraints match, or None when suppressed.
"""
if sec is None:
return None
excluded = sec.get('constraints_exclude') or []
if any(c.lower() in [e.lower() for e in excluded] for c in user_constraints):
return None
return sec
# Keyword lists are checked in declaration order — most specific first. # Keyword lists are checked in declaration order — most specific first.
# Rules: # Rules:
# - canned/processed goods BEFORE raw-meat terms (canned chicken != raw chicken) # - canned/processed goods BEFORE raw-meat terms (canned chicken != raw chicken)

View file

@ -1,80 +0,0 @@
"""Heimdall cf-orch budget client.
Calls Heimdall's /orch/* endpoints to gate and record cf-orch usage for
lifetime/founders license holders. Always fails open on network errors
a Heimdall outage should never block the user.
"""
from __future__ import annotations
import logging
import os
import requests
log = logging.getLogger(__name__)
HEIMDALL_URL: str = os.environ.get("HEIMDALL_URL", "https://license.circuitforge.tech")
HEIMDALL_ADMIN_TOKEN: str = os.environ.get("HEIMDALL_ADMIN_TOKEN", "")
def _headers() -> dict[str, str]:
if HEIMDALL_ADMIN_TOKEN:
return {"Authorization": f"Bearer {HEIMDALL_ADMIN_TOKEN}"}
return {}
def check_orch_budget(key_display: str, product: str) -> dict:
"""Call POST /orch/check and return the response dict.
On any error (network, auth, etc.) returns a permissive dict so the
caller can proceed without blocking the user.
"""
try:
resp = requests.post(
f"{HEIMDALL_URL}/orch/check",
json={"key_display": key_display, "product": product},
headers=_headers(),
timeout=5,
)
if resp.ok:
return resp.json()
log.warning("Heimdall orch/check returned %s for key %s", resp.status_code, key_display[:12])
except Exception as exc:
log.warning("Heimdall orch/check failed (fail-open): %s", exc)
# Fail open — Heimdall outage must never block the user
return {
"allowed": True,
"calls_used": 0,
"calls_total": 0,
"topup_calls": 0,
"period_start": "",
"resets_on": "",
}
def get_orch_usage(key_display: str, product: str) -> dict:
"""Call GET /orch/usage and return the response dict.
Returns zeros on error (non-blocking).
"""
try:
resp = requests.get(
f"{HEIMDALL_URL}/orch/usage",
params={"key_display": key_display, "product": product},
headers=_headers(),
timeout=5,
)
if resp.ok:
return resp.json()
log.warning("Heimdall orch/usage returned %s", resp.status_code)
except Exception as exc:
log.warning("Heimdall orch/usage failed: %s", exc)
return {
"calls_used": 0,
"topup_calls": 0,
"calls_total": 0,
"period_start": "",
"resets_on": "",
}

View file

@ -1,140 +0,0 @@
"""Visual label capture service for unenriched products (kiwi#79).
Wraps the cf-core VisionRouter to extract structured nutrition data from a
photographed nutrition facts panel. When the VisionRouter is not yet wired
(NotImplementedError) the service falls back to a mock extraction so the
barcode scan flow can be exercised end-to-end in development.
JSON contract returned by the vision model (and mock):
{
"product_name": str | null,
"brand": str | null,
"serving_size_g": number | null,
"calories": number | null,
"fat_g": number | null,
"saturated_fat_g": number | null,
"carbs_g": number | null,
"sugar_g": number | null,
"fiber_g": number | null,
"protein_g": number | null,
"sodium_mg": number | null,
"ingredient_names": [str],
"allergens": [str],
"confidence": number (0.01.0)
}
"""
from __future__ import annotations
import json
import logging
import os
from typing import Any
log = logging.getLogger(__name__)
# Confidence below this threshold surfaces amber highlights in the UI.
REVIEW_THRESHOLD = 0.7
_MOCK_EXTRACTION: dict[str, Any] = {
"product_name": "Unknown Product",
"brand": None,
"serving_size_g": None,
"calories": None,
"fat_g": None,
"saturated_fat_g": None,
"carbs_g": None,
"sugar_g": None,
"fiber_g": None,
"protein_g": None,
"sodium_mg": None,
"ingredient_names": [],
"allergens": [],
"confidence": 0.0,
}
_EXTRACTION_PROMPT = """You are reading a nutrition facts label photograph.
Extract the following fields as a JSON object with no extra text:
{
"product_name": <product name or null>,
"brand": <brand name or null>,
"serving_size_g": <serving size in grams as a number or null>,
"calories": <calories per serving as a number or null>,
"fat_g": <total fat grams or null>,
"saturated_fat_g": <saturated fat grams or null>,
"carbs_g": <total carbohydrates grams or null>,
"sugar_g": <sugars grams or null>,
"fiber_g": <dietary fiber grams or null>,
"protein_g": <protein grams or null>,
"sodium_mg": <sodium milligrams or null>,
"ingredient_names": [list of individual ingredients as strings],
"allergens": [list of allergens explicitly stated on label],
"confidence": <your confidence this extraction is correct, 0.0 to 1.0>
}
Use null for any field you cannot read clearly. Do not guess values.
Respond with JSON only."""
def extract_label(image_bytes: bytes) -> dict[str, Any]:
"""Run vision model extraction on raw label image bytes.
Returns a dict matching the nutrition JSON contract above.
Falls back to a zero-confidence mock if the VisionRouter is not yet
implemented (stub) or if the model returns unparseable output.
"""
# Allow unit tests to bypass the vision model entirely.
if os.environ.get("KIWI_LABEL_CAPTURE_MOCK") == "1":
log.debug("label_capture: mock mode active")
return dict(_MOCK_EXTRACTION)
try:
from circuitforge_core.vision import caption as vision_caption
result = vision_caption(image_bytes, prompt=_EXTRACTION_PROMPT)
raw = result.caption or ""
return _parse_extraction(raw)
except Exception as exc:
log.warning("label_capture: extraction failed (%s) — returning mock extraction", exc)
return dict(_MOCK_EXTRACTION)
def _parse_extraction(raw: str) -> dict[str, Any]:
"""Parse the JSON string returned by the vision model.
Strips markdown code fences if present. Validates required shape.
Returns the mock on any parse error.
"""
text = raw.strip()
if text.startswith("```"):
# Strip ```json ... ``` fences
lines = text.splitlines()
text = "\n".join(lines[1:-1] if lines[-1].strip() == "```" else lines[1:])
try:
data = json.loads(text)
except json.JSONDecodeError as exc:
log.warning("label_capture: could not parse vision response: %s", exc)
return dict(_MOCK_EXTRACTION)
if not isinstance(data, dict):
log.warning("label_capture: vision response is not a dict")
return dict(_MOCK_EXTRACTION)
# Normalise list fields — model may return None instead of []
for list_key in ("ingredient_names", "allergens"):
if not isinstance(data.get(list_key), list):
data[list_key] = []
# Clamp confidence to [0, 1]
confidence = data.get("confidence")
if not isinstance(confidence, (int, float)):
confidence = 0.0
data["confidence"] = max(0.0, min(1.0, float(confidence)))
return data
def needs_review(extraction: dict[str, Any]) -> bool:
"""Return True when the extraction confidence is below REVIEW_THRESHOLD."""
return float(extraction.get("confidence", 0.0)) < REVIEW_THRESHOLD

View file

@ -1,233 +0,0 @@
# app/services/leftovers_predictor.py
"""Cooked-leftovers shelf-life predictor.
Fast path: deterministic lookup anchored to FDA/USDA safe food handling.
Fallback: LLM for unclassifiable edge cases (same gate as expiry_llm_matching).
Design notes:
- shortest-component-wins for proteins: a fish taco is bounded by the fish.
- category/keyword signals override ingredient signals for assembled dishes
(soup, stew, casserole) where the cooking method matters more than the
dominant protein.
- no urgency/panic framing see feedback_kiwi_no_panic.md.
"""
from __future__ import annotations
import logging
import re
from dataclasses import dataclass, field
from typing import Any
logger = logging.getLogger(__name__)
@dataclass
class LeftoversResult:
fridge_days: int
freeze_days: int | None # None = "not recommended"
freeze_by_day: int | None # day number from cook date to freeze by; None = no need
storage_advice: str
# ---------------------------------------------------------------------------
# Protein priority table — shorter shelf life wins when multiple match.
# Values: (fridge_days, freeze_days). All fridge values are conservative.
# Sources: USDA FoodKeeper, FDA Safe Food Handling.
# ---------------------------------------------------------------------------
_PROTEIN_SIGNALS: list[tuple[list[str], int, int | None]] = [
# (keyword_list, fridge_days, freeze_days)
(["fish", "salmon", "tuna", "cod", "tilapia", "halibut", "trout", "bass",
"mahi", "snapper", "flounder", "catfish", "swordfish", "sardine", "anchovy"],
2, 90),
(["shrimp", "prawn", "scallop", "crab", "lobster", "clam", "mussel",
"oyster", "squid", "octopus", "seafood"],
2, 90),
(["ground beef", "ground turkey", "ground pork", "ground chicken",
"ground meat", "hamburger", "mince"],
3, 90),
(["chicken", "turkey", "poultry", "duck", "hen"],
3, 90),
(["pork", "ham", "bacon", "sausage", "chorizo", "bratwurst", "kielbasa",
"salami", "pepperoni"],
4, 120),
(["beef", "steak", "brisket", "roast", "lamb", "veal", "venison"],
4, 180),
(["egg", "eggs", "frittata", "quiche", "omelette"],
3, None),
(["tofu", "tempeh", "seitan"],
4, 90),
]
# ---------------------------------------------------------------------------
# Dish-type signals — override protein signal when a structural match fires.
# Ordered from most-perishable to least.
# ---------------------------------------------------------------------------
_DISH_SIGNALS: list[tuple[list[str], int, int | None, str]] = [
# (keywords, fridge_days, freeze_days, storage_advice_fragment)
# Ceviche: acid denatures proteins but does not kill pathogens.
# FDA/USDA classify it as raw seafood — 2-day fridge max, do not freeze.
(["ceviche", "tiradito", "leche de tigre"],
2, None,
"Acid marination is not the same as heat cooking — treat as raw seafood. "
"Best eaten the day it's made; 2 days maximum in the fridge."),
# Fermented / salt-cured dishes — preservation extends shelf life significantly.
# This matches dish names, not just presence of the ingredient (lardo in a pasta
# follows normal pasta rules, not this entry).
(["kimchi", "sauerkraut", "preserved lemon"],
14, None,
"Fermented and salt-preserved dishes keep well. Store submerged in their brine."),
(["confit", "gravlax", "gravad lax", "lardo"],
7, 60,
"Store covered in its fat or cure. Keep cold and away from strong-smelling foods."),
(["soup", "stew", "broth", "chowder", "bisque", "gumbo", "chili"],
4, 120,
"Soups and stews keep well in the fridge. Cool to room temperature before covering."),
(["curry"],
4, 90,
"Store curry in an airtight container. The flavours deepen overnight."),
(["casserole", "bake", "gratin", "lasagna", "lasagne", "moussaka",
"shepherd's pie", "pot pie"],
5, 90,
"Cover tightly. Reheat individual portions rather than the whole dish."),
(["pasta", "noodle", "spaghetti", "penne", "linguine", "fettuccine",
"macaroni", "risotto"],
4, 60,
"Store pasta and sauce separately if possible to prevent sogginess."),
(["rice", "fried rice", "pilaf", "biryani"],
3, 90,
"Cool rice quickly — spread on a tray if needed. Don't leave at room temperature for more than 1 hour."),
(["salad"],
2, None,
"Keep dressing separate. Once dressed, best eaten the same day."),
(["stir fry", "stir-fry"],
3, 60,
"Reheat in a hot pan or wok rather than a microwave to keep texture."),
(["sandwich", "wrap", "taco", "burrito"],
2, None,
"Assemble fresh when possible. Fillings keep better stored separately."),
(["pizza"],
4, 60,
"Reheat in a dry skillet for a crisp base rather than a microwave."),
(["muffin", "bread", "biscuit", "scone", "roll"],
3, 90,
"Wrap tightly or seal in a bag to prevent drying out."),
(["cake", "pie", "cookie", "brownie", "dessert", "pudding"],
5, 90,
"Store covered at room temperature or in the fridge depending on fillings."),
(["smoothie", "juice", "shake"],
1, 7,
"Best consumed fresh. Stir or shake well before drinking."),
]
# Default when no signals match.
_DEFAULT_FRIDGE = 4
_DEFAULT_FREEZE = 90
_DEFAULT_ADVICE = "Store in an airtight container in the fridge. Reheat until piping hot before eating."
def _contains_any(text: str, keywords: list[str]) -> bool:
for kw in keywords:
if re.search(rf"\b{re.escape(kw)}\b", text, re.IGNORECASE):
return True
return False
def _scan_ingredients(ingredients: list[str]) -> tuple[int, int | None] | None:
"""Return (fridge_days, freeze_days) for the most-perishable protein found."""
joined = " ".join(str(i) for i in ingredients).lower()
best: tuple[int, int | None] | None = None
for keywords, fridge, freeze in _PROTEIN_SIGNALS:
if _contains_any(joined, keywords):
if best is None or fridge < best[0]:
best = (fridge, freeze)
return best
def _scan_dish_type(text: str) -> tuple[int, int | None, str] | None:
"""Return (fridge_days, freeze_days, advice) for the first matching dish type."""
for keywords, fridge, freeze, advice in _DISH_SIGNALS:
if _contains_any(text, keywords):
return fridge, freeze, advice
return None
def predict_leftovers(
title: str,
ingredients: list[str],
category: str | None = None,
keywords: list[str] | None = None,
) -> LeftoversResult:
"""Predict cooked-leftover shelf life deterministically.
Falls back gracefully always returns a result even for unknown recipes.
"""
# Build a combined text blob for dish-type scanning.
search_text = " ".join(filter(None, [
title,
category or "",
" ".join(keywords or []),
]))
# Dish-type match takes structural priority over raw ingredient protein signal.
dish = _scan_dish_type(search_text)
protein = _scan_ingredients(ingredients)
if dish:
fridge_days, freeze_days, base_advice = dish
# Still apply shortest-protein-wins if protein is more perishable than dish default.
if protein and protein[0] < fridge_days:
fridge_days = protein[0]
if protein[1] is not None and (freeze_days is None or protein[1] < freeze_days):
freeze_days = protein[1]
advice = base_advice
elif protein:
fridge_days, freeze_days = protein
advice = _DEFAULT_ADVICE
else:
fridge_days = _DEFAULT_FRIDGE
freeze_days = _DEFAULT_FREEZE
advice = _DEFAULT_ADVICE
# freeze_by_day: recommend freezing on day 2 if fridge window is tight (≤3 days).
freeze_by_day: int | None = None
if freeze_days is not None and fridge_days <= 3:
freeze_by_day = 2
return LeftoversResult(
fridge_days=fridge_days,
freeze_days=freeze_days,
freeze_by_day=freeze_by_day,
storage_advice=advice,
)
def predict_leftovers_from_row(recipe: dict[str, Any]) -> LeftoversResult:
"""Convenience wrapper that accepts a Store row dict directly."""
import json as _json
title = recipe.get("title") or ""
raw_ingredients = recipe.get("ingredient_names") or []
if isinstance(raw_ingredients, str):
try:
raw_ingredients = _json.loads(raw_ingredients)
except Exception:
raw_ingredients = [raw_ingredients]
raw_keywords = recipe.get("keywords") or []
if isinstance(raw_keywords, str):
try:
raw_keywords = _json.loads(raw_keywords)
except Exception:
raw_keywords = [raw_keywords]
return predict_leftovers(
title=title,
ingredients=[str(i) for i in raw_ingredients],
category=recipe.get("category"),
keywords=[str(k) for k in raw_keywords],
)

View file

@ -1,97 +0,0 @@
"""Magpie data-flywheel hook.
Fires anonymized recipe-signal events to the Magpie ingest endpoint when a
user saves or rates a recipe. This is the Kiwi side of the flywheel Magpie
does not have a receiver endpoint yet, so the hook stubs out gracefully: if
``MAGPIE_INGEST_URL`` is unset, or the request fails for any reason, it logs
at DEBUG level and returns without raising.
"""
from __future__ import annotations
import logging
from pathlib import Path
logger = logging.getLogger(__name__)
_INGEST_PATH = "/api/v1/ingest/recipe-signal"
async def fire_recipe_signal(
db_path: Path,
recipe_id: int,
rating: int | None,
style_tags: list[str],
) -> None:
"""Post an anonymized recipe signal to Magpie if the user has opted in.
Args:
db_path: Path to the user's SQLite database.
recipe_id: Internal Kiwi recipe ID being rated/saved.
rating: Star rating (05) or None if not yet rated.
style_tags: Style tags applied to the saved recipe.
"""
from app.core.config import settings
if not settings.MAGPIE_INGEST_URL:
return
# Check per-user opt-in via a short-lived Store (own connection, own thread
# context is fine — this runs in the async event loop as a background task
# so we open and close the connection immediately).
from app.db.store import Store
try:
store = Store(db_path)
try:
opt_in = store.get_setting("magpie_opt_in")
finally:
store.close()
except Exception as exc: # noqa: BLE001
logger.debug("magpie_hook: could not read magpie_opt_in setting: %s", exc)
return
if opt_in != "true":
return
# Fetch the recipe to get its external_id (source URL slug / corpus key).
try:
store = Store(db_path)
try:
recipe = store.get_recipe(recipe_id)
finally:
store.close()
except Exception as exc: # noqa: BLE001
logger.debug("magpie_hook: could not fetch recipe %d: %s", recipe_id, exc)
return
if recipe is None:
logger.debug("magpie_hook: recipe %d not found, skipping", recipe_id)
return
external_id: str | None = recipe.get("external_id") if isinstance(recipe, dict) else getattr(recipe, "external_id", None)
if not external_id:
# Corpus recipe not yet enriched with a source identifier — skip quietly.
logger.debug("magpie_hook: recipe %d has no external_id, skipping", recipe_id)
return
payload = {
"product": "kiwi",
"signal": "recipe_rating",
"external_id": external_id,
"rating": rating,
"style_tags": style_tags,
}
url = settings.MAGPIE_INGEST_URL.rstrip("/") + _INGEST_PATH
try:
import httpx
async with httpx.AsyncClient(timeout=3.0) as client:
response = await client.post(url, json=payload)
logger.debug(
"magpie_hook: POST %s%d", url, response.status_code
)
except Exception as exc: # noqa: BLE001
# Magpie may not have a receiver yet — log and swallow.
logger.debug("magpie_hook: ingest request failed (stub): %s", exc)

View file

@ -1 +0,0 @@
"""Meal planning service layer — no FastAPI imports (extraction-ready for cf-core)."""

View file

@ -1,108 +0,0 @@
# app/services/meal_plan/affiliates.py
"""Register Kiwi-specific affiliate programs and provide search URL builders.
Called once at API startup. Programs not yet in core.affiliates are registered
here. The actual affiliate IDs are read from environment variables at call
time, so the process can start before accounts are approved (plain URLs
returned when env vars are absent).
"""
from __future__ import annotations
from urllib.parse import quote_plus
from circuitforge_core.affiliates import AffiliateProgram, register_program, wrap_url
# ── URL builders ──────────────────────────────────────────────────────────────
def _walmart_search(url: str, affiliate_id: str) -> str:
sep = "&" if "?" in url else "?"
return f"{url}{sep}affil=apa&affiliateId={affiliate_id}"
def _target_search(url: str, affiliate_id: str) -> str:
sep = "&" if "?" in url else "?"
return f"{url}{sep}afid={affiliate_id}"
def _thrive_search(url: str, affiliate_id: str) -> str:
sep = "&" if "?" in url else "?"
return f"{url}{sep}raf={affiliate_id}"
def _misfits_search(url: str, affiliate_id: str) -> str:
sep = "&" if "?" in url else "?"
return f"{url}{sep}ref={affiliate_id}"
# ── Registration ──────────────────────────────────────────────────────────────
def register_kiwi_programs() -> None:
"""Register Kiwi retailer programs. Safe to call multiple times (idempotent)."""
register_program(AffiliateProgram(
name="Walmart",
retailer_key="walmart",
env_var="WALMART_AFFILIATE_ID",
build_url=_walmart_search,
))
register_program(AffiliateProgram(
name="Target",
retailer_key="target",
env_var="TARGET_AFFILIATE_ID",
build_url=_target_search,
))
register_program(AffiliateProgram(
name="Thrive Market",
retailer_key="thrive",
env_var="THRIVE_AFFILIATE_ID",
build_url=_thrive_search,
))
register_program(AffiliateProgram(
name="Misfits Market",
retailer_key="misfits",
env_var="MISFITS_AFFILIATE_ID",
build_url=_misfits_search,
))
# ── Search URL helpers ─────────────────────────────────────────────────────────
_SEARCH_TEMPLATES: dict[str, str] = {
"amazon": "https://www.amazon.com/s?k={q}",
"instacart": "https://www.instacart.com/store/search_v3/term?term={q}",
"walmart": "https://www.walmart.com/search?q={q}",
"target": "https://www.target.com/s?searchTerm={q}",
"thrive": "https://thrivemarket.com/search?q={q}",
"misfits": "https://www.misfitsmarket.com/shop?search={q}",
}
KIWI_RETAILERS = list(_SEARCH_TEMPLATES.keys())
def get_retailer_links(ingredient_name: str) -> list[dict]:
"""Return affiliate-wrapped search links for *ingredient_name*.
Returns a list of dicts: {"retailer": str, "label": str, "url": str}.
Falls back to plain search URL when no affiliate ID is configured.
"""
q = quote_plus(ingredient_name)
links = []
for key, template in _SEARCH_TEMPLATES.items():
plain_url = template.format(q=q)
try:
affiliate_url = wrap_url(plain_url, retailer=key)
except Exception:
affiliate_url = plain_url
links.append({"retailer": key, "label": _label(key), "url": affiliate_url})
return links
def _label(key: str) -> str:
return {
"amazon": "Amazon",
"instacart": "Instacart",
"walmart": "Walmart",
"target": "Target",
"thrive": "Thrive Market",
"misfits": "Misfits Market",
}.get(key, key.title())

View file

@ -1,91 +0,0 @@
# app/services/meal_plan/llm_planner.py
# BSL 1.1 — LLM feature
"""LLM-assisted full-week meal plan generation.
Returns suggestions for human review never writes to the DB directly.
The API endpoint presents the suggestions and waits for user approval
before calling store.upsert_slot().
Routing: pass a router from get_meal_plan_router() in llm_router.py.
Cloud: cf-text via cf-orch (3B-7B GGUF, ~2GB VRAM).
Local: LLMRouter (ollama / vllm / openai-compat per llm.yaml).
"""
from __future__ import annotations
import json
import logging
from dataclasses import dataclass
logger = logging.getLogger(__name__)
_PLAN_SYSTEM = """\
You are a practical meal planning assistant. Given a pantry inventory and
dietary preferences, suggest a week of dinners (or other configured meals).
Prioritise ingredients that are expiring soon. Prefer variety across the week.
Respect all dietary restrictions.
Respond with a JSON array only no prose, no markdown fences.
Each item: {"day": 0-6, "meal_type": "dinner", "recipe_id": <int or null>, "suggestion": "<recipe name>"}
day 0 = Monday, day 6 = Sunday.
If you cannot match a known recipe_id, set recipe_id to null and provide a suggestion name.
"""
@dataclass(frozen=True)
class PlanSuggestion:
day: int # 0 = Monday
meal_type: str
recipe_id: int | None
suggestion: str # human-readable name
def generate_plan(
pantry_items: list[str],
meal_types: list[str],
dietary_notes: str,
router,
) -> list[PlanSuggestion]:
"""Return a list of PlanSuggestion for user review.
Never writes to DB caller must upsert slots after user approves.
Returns an empty list if router is None or response is unparseable.
"""
if router is None:
return []
pantry_text = "\n".join(f"- {item}" for item in pantry_items[:50])
meal_text = ", ".join(meal_types)
user_msg = (
f"Meal types: {meal_text}\n"
f"Dietary notes: {dietary_notes or 'none'}\n\n"
f"Pantry (partial):\n{pantry_text}"
)
try:
response = router.complete(
system=_PLAN_SYSTEM,
user=user_msg,
max_tokens=512,
temperature=0.7,
)
items = json.loads(response.strip())
suggestions = []
for item in items:
if not isinstance(item, dict):
continue
day = item.get("day")
meal_type = item.get("meal_type", "dinner")
if not isinstance(day, int) or day < 0 or day > 6:
continue
suggestions.append(PlanSuggestion(
day=day,
meal_type=meal_type,
recipe_id=item.get("recipe_id"),
suggestion=str(item.get("suggestion", "")),
))
return suggestions
except Exception as exc:
logger.debug("LLM plan generation failed: %s", exc)
return []

View file

@ -1,142 +0,0 @@
# app/services/meal_plan/llm_router.py
# BSL 1.1 — LLM feature
"""Provide a router-compatible LLM client for meal plan generation tasks.
Cloud (CF_ORCH_URL set), tier 1 task-based routing (preferred):
Calls /api/inference/task with product=kiwi, task=meal_plan.
The coordinator resolves the model from assignments.yaml.
Cloud (CF_ORCH_URL set), tier 2 direct allocation (fallback):
Allocates cf-text directly via client.allocate(). Used when the task
is not yet registered in the coordinator (cf-orch#61 not deployed).
Local / self-hosted (no CF_ORCH_URL):
Returns an LLMRouter instance which tries ollama, vllm, or any
backend configured in ~/.config/circuitforge/llm.yaml.
All paths expose the same (router, ctx) interface so llm_planner.py
needs no knowledge of the backend.
"""
from __future__ import annotations
import logging
import os
from contextlib import nullcontext
logger = logging.getLogger(__name__)
# cf-orch service name and TTL for direct-allocate fallback path.
_SERVICE_TYPE = "cf-text"
_TTL_S = 120.0
_CALLER = "kiwi-meal-plan"
class _OrchTextRouter:
"""Thin adapter that makes a cf-text HTTP endpoint look like LLMRouter."""
def __init__(self, base_url: str) -> None:
self._base_url = base_url.rstrip("/")
def complete(
self,
system: str = "",
user: str = "",
max_tokens: int = 512,
temperature: float = 0.7,
**_kwargs,
) -> str:
from openai import OpenAI
client = OpenAI(base_url=self._base_url + "/v1", api_key="any")
messages = []
if system:
messages.append({"role": "system", "content": system})
messages.append({"role": "user", "content": user})
try:
model = client.models.list().data[0].id
except Exception:
model = "local"
resp = client.chat.completions.create(
model=model,
messages=messages,
max_tokens=max_tokens,
temperature=temperature,
)
return resp.choices[0].message.content or ""
# Imported at module level so tests can patch the names in this module's namespace.
# app.services.task_inference.task_allocate — patch target for task routing tests.
try:
from app.services.task_inference import TaskNotRegistered, task_allocate
_HAS_TASK_INFERENCE = True
except ImportError:
_HAS_TASK_INFERENCE = False
# circuitforge_orch.client.CFOrchClient — patch target for direct-allocate fallback tests.
try:
from circuitforge_orch.client import CFOrchClient
except ImportError:
CFOrchClient = None # type: ignore[assignment,misc]
# circuitforge_core.llm.router.LLMRouter — patch target for local-inference tests.
try:
from circuitforge_core.llm.router import LLMRouter
except (ImportError, FileNotFoundError):
LLMRouter = None # type: ignore[assignment,misc]
def get_meal_plan_router():
"""Return an LLM client for meal plan tasks.
Returns (router, ctx) where ctx is a context manager the caller holds
open for the duration of the LLM call. Returns (None, nullcontext(None))
if no backend is available.
"""
cf_orch_url = os.environ.get("CF_ORCH_URL")
if cf_orch_url:
# Tier 1: task-based routing — coordinator owns model selection.
if _HAS_TASK_INFERENCE:
try:
ctx = task_allocate(
"kiwi", "meal_plan",
service_hint=_SERVICE_TYPE,
ttl_s=_TTL_S,
)
alloc = ctx.__enter__()
return _OrchTextRouter(alloc.url), ctx
except TaskNotRegistered:
logger.debug(
"kiwi.meal_plan not in coordinator assignments — "
"falling back to direct cf-text allocation"
)
except Exception as exc:
logger.debug("task allocation failed, trying direct allocate: %s", exc)
# Tier 2: direct allocation — hardcoded service type.
if CFOrchClient is not None:
try:
client = CFOrchClient(cf_orch_url)
ctx = client.allocate(
service=_SERVICE_TYPE,
ttl_s=_TTL_S,
caller=_CALLER,
)
alloc = ctx.__enter__()
if alloc is not None:
return _OrchTextRouter(alloc.url), ctx
ctx.__exit__(None, None, None) # release allocation before falling through
except Exception as exc:
logger.debug("cf-orch cf-text allocation failed, falling back to LLMRouter: %s", exc)
# Tier 3: local inference — ollama / vllm / openai-compat.
if LLMRouter is not None:
try:
return LLMRouter(), nullcontext(None)
except FileNotFoundError:
logger.debug("LLMRouter: no llm.yaml and no LLM env vars — meal plan LLM disabled")
return None, nullcontext(None)
except Exception as exc:
logger.debug("LLMRouter init failed: %s", exc)
return None, nullcontext(None)
return None, nullcontext(None)

View file

@ -1,65 +0,0 @@
# app/services/meal_plan/llm_timing.py
# BSL 1.1 — LLM feature
"""Estimate cook times for recipes missing corpus prep/cook time fields.
Used only when tier allows `meal_plan_llm_timing`. Falls back gracefully
when no LLM backend is available.
Routing: pass a router from get_meal_plan_router() in llm_router.py.
Cloud: cf-text via cf-orch (3B GGUF, ~2GB VRAM).
Local: LLMRouter (ollama / vllm / openai-compat per llm.yaml).
"""
from __future__ import annotations
import logging
logger = logging.getLogger(__name__)
_TIMING_PROMPT = """\
You are a practical cook. Given a recipe name and its ingredients, estimate:
1. prep_time: minutes of active prep work (chopping, mixing, etc.)
2. cook_time: minutes of cooking (oven, stovetop, etc.)
Respond with ONLY two integers on separate lines:
prep_time
cook_time
If you cannot estimate, respond with:
0
0
"""
def estimate_timing(recipe_name: str, ingredients: list[str], router) -> tuple[int | None, int | None]:
"""Return (prep_minutes, cook_minutes) for a recipe using LLMRouter.
Returns (None, None) if the router is unavailable or the response is
unparseable. Never raises.
Args:
recipe_name: Name of the recipe.
ingredients: List of raw ingredient strings from the corpus.
router: An LLMRouter instance (from circuitforge_core.llm).
"""
if router is None:
return None, None
ingredient_list = "\n".join(f"- {i}" for i in (ingredients or [])[:15])
prompt = f"Recipe: {recipe_name}\n\nIngredients:\n{ingredient_list}"
try:
response = router.complete(
system=_TIMING_PROMPT,
user=prompt,
max_tokens=16,
temperature=0.0,
)
lines = response.strip().splitlines()
prep = int(lines[0].strip()) if lines else 0
cook = int(lines[1].strip()) if len(lines) > 1 else 0
if prep == 0 and cook == 0:
return None, None
return prep or None, cook or None
except Exception as exc:
logger.debug("LLM timing estimation failed for %r: %s", recipe_name, exc)
return None, None

View file

@ -1,26 +0,0 @@
# app/services/meal_plan/planner.py
"""Plan and slot orchestration — thin layer over Store.
No FastAPI imports. Provides helpers used by the API endpoint.
"""
from __future__ import annotations
from app.db.store import Store
from app.models.schemas.meal_plan import VALID_MEAL_TYPES
def create_plan(store: Store, week_start: str, meal_types: list[str]) -> dict:
"""Create a plan, filtering meal_types to valid values only."""
valid = [t for t in meal_types if t in VALID_MEAL_TYPES]
if not valid:
valid = ["dinner"]
return store.create_meal_plan(week_start, valid)
def get_plan_with_slots(store: Store, plan_id: int) -> dict | None:
"""Return a plan row with its slots list attached, or None."""
plan = store.get_meal_plan(plan_id)
if plan is None:
return None
slots = store.get_plan_slots(plan_id)
return {**plan, "slots": slots}

View file

@ -1,91 +0,0 @@
# app/services/meal_plan/prep_scheduler.py
"""Sequence prep tasks for a batch cooking session.
Pure function no DB or network calls. Sorts tasks by equipment priority
(oven first to maximise oven utilisation) then assigns sequence_order.
"""
from __future__ import annotations
from dataclasses import dataclass
_EQUIPMENT_PRIORITY = {"oven": 0, "stovetop": 1, "cold": 2, "no-heat": 3}
_DEFAULT_PRIORITY = 4
@dataclass(frozen=True)
class PrepTask:
recipe_id: int | None
slot_id: int | None
task_label: str
duration_minutes: int | None
sequence_order: int
equipment: str | None
is_parallel: bool = False
notes: str | None = None
user_edited: bool = False
def _total_minutes(recipe: dict) -> int | None:
prep = recipe.get("prep_time")
cook = recipe.get("cook_time")
if prep is None and cook is None:
return None
return (prep or 0) + (cook or 0)
def _equipment(recipe: dict) -> str | None:
# Corpus recipes don't have an explicit equipment field; use test helper
# field if present, otherwise infer from cook_time (long = oven heuristic).
if "_equipment" in recipe:
return recipe["_equipment"]
minutes = _total_minutes(recipe)
if minutes and minutes >= 45:
return "oven"
return "stovetop"
def build_prep_tasks(slots: list[dict], recipes: list[dict]) -> list[PrepTask]:
"""Return a sequenced list of PrepTask objects from plan slots + recipe rows.
Algorithm:
1. Build a recipe_id recipe dict lookup.
2. Create one task per slot that has a recipe assigned.
3. Sort by equipment priority (oven first).
4. Assign contiguous sequence_order starting at 1.
"""
if not slots or not recipes:
return []
recipe_map: dict[int, dict] = {r["id"]: r for r in recipes}
raw_tasks: list[tuple[int, dict]] = [] # (priority, kwargs)
for slot in slots:
recipe_id = slot.get("recipe_id")
if not recipe_id:
continue
recipe = recipe_map.get(recipe_id)
if not recipe:
continue
eq = _equipment(recipe)
priority = _EQUIPMENT_PRIORITY.get(eq or "", _DEFAULT_PRIORITY)
raw_tasks.append((priority, {
"recipe_id": recipe_id,
"slot_id": slot.get("id"),
"task_label": recipe.get("name", f"Recipe {recipe_id}"),
"duration_minutes": _total_minutes(recipe),
"equipment": eq,
}))
raw_tasks.sort(key=lambda t: t[0])
return [
PrepTask(
recipe_id=kw["recipe_id"],
slot_id=kw["slot_id"],
task_label=kw["task_label"],
duration_minutes=kw["duration_minutes"],
sequence_order=i,
equipment=kw["equipment"],
)
for i, (_, kw) in enumerate(raw_tasks, 1)
]

View file

@ -1,88 +0,0 @@
# app/services/meal_plan/shopping_list.py
"""Compute a shopping list from a meal plan and current pantry inventory.
Pure function no DB or network calls. Takes plain dicts from the Store
and returns GapItem dataclasses.
"""
from __future__ import annotations
import re
from dataclasses import dataclass, field
@dataclass(frozen=True)
class GapItem:
ingredient_name: str
needed_raw: str | None # first quantity token from recipe text, e.g. "300g"
have_quantity: float | None # pantry quantity when partial match
have_unit: str | None
covered: bool
retailer_links: list = field(default_factory=list) # filled by API layer
_QUANTITY_RE = re.compile(r"^(\d+[\d./]*\s*(?:g|kg|ml|l|oz|lb|cup|cups|tsp|tbsp|tbsps|tsps)?)\b", re.I)
def _extract_quantity(ingredient_text: str) -> str | None:
"""Pull the leading quantity string from a raw ingredient line."""
m = _QUANTITY_RE.match(ingredient_text.strip())
return m.group(1).strip() if m else None
def _normalise(name: str) -> str:
"""Lowercase, strip possessives and plural -s for fuzzy matching."""
return name.lower().strip().rstrip("s")
def compute_shopping_list(
recipes: list[dict],
inventory: list[dict],
) -> tuple[list[GapItem], list[GapItem]]:
"""Return (gap_items, covered_items) for a list of recipe dicts + inventory dicts.
Deduplicates by normalised ingredient name the first recipe's quantity
string wins when the same ingredient appears in multiple recipes.
"""
if not recipes:
return [], []
# Build pantry lookup: normalised_name → inventory row
pantry: dict[str, dict] = {}
for item in inventory:
pantry[_normalise(item["name"])] = item
# Collect unique ingredients with their first quantity token
seen: dict[str, str | None] = {} # normalised_name → needed_raw
for recipe in recipes:
names: list[str] = recipe.get("ingredient_names") or []
raw_lines: list[str] = recipe.get("ingredients") or []
for i, name in enumerate(names):
key = _normalise(name)
if key in seen:
continue
raw = raw_lines[i] if i < len(raw_lines) else ""
seen[key] = _extract_quantity(raw)
gaps: list[GapItem] = []
covered: list[GapItem] = []
for norm_name, needed_raw in seen.items():
pantry_row = pantry.get(norm_name)
if pantry_row:
covered.append(GapItem(
ingredient_name=norm_name,
needed_raw=needed_raw,
have_quantity=pantry_row.get("quantity"),
have_unit=pantry_row.get("unit"),
covered=True,
))
else:
gaps.append(GapItem(
ingredient_name=norm_name,
needed_raw=needed_raw,
have_quantity=None,
have_unit=None,
covered=False,
))
return gaps, covered

View file

@ -18,51 +18,43 @@ class DocuvisionResult:
class DocuvisionClient: class DocuvisionClient:
"""Thin client for the cf-docuvision service.""" """Thin client for the cf-docuvision service."""
def __init__(self, base_url: str, timeout: float = 120.0) -> None: def __init__(self, base_url: str) -> None:
self._base_url = base_url.rstrip("/") self._base_url = base_url.rstrip("/")
self._timeout = timeout
def extract_text(self, image_path: str | Path, hint: str = "text") -> DocuvisionResult: def extract_text(self, image_path: str | Path) -> DocuvisionResult:
"""Send an image to docuvision and return extracted text. """Send an image to docuvision and return extracted text."""
Args:
image_path: Path to the image file.
hint: Docuvision extraction hint "text" for dense prose (recipes),
"table" for tabular data, "form" for form fields, "auto" for
automatic detection.
"""
image_bytes = Path(image_path).read_bytes() image_bytes = Path(image_path).read_bytes()
b64 = base64.b64encode(image_bytes).decode() b64 = base64.b64encode(image_bytes).decode()
with httpx.Client(timeout=self._timeout) as client: with httpx.Client(timeout=30.0) as client:
resp = client.post( resp = client.post(
f"{self._base_url}/extract", f"{self._base_url}/extract",
json={"image_b64": b64, "hint": hint}, json={"image": b64},
) )
resp.raise_for_status() resp.raise_for_status()
data = resp.json() data = resp.json()
return DocuvisionResult( return DocuvisionResult(
text=data.get("raw_text", ""), text=data.get("text", ""),
confidence=data.get("metadata", {}).get("confidence"), confidence=data.get("confidence"),
raw=data, raw=data,
) )
async def extract_text_async(self, image_path: str | Path, hint: str = "text") -> DocuvisionResult: async def extract_text_async(self, image_path: str | Path) -> DocuvisionResult:
"""Async version.""" """Async version."""
image_bytes = Path(image_path).read_bytes() image_bytes = Path(image_path).read_bytes()
b64 = base64.b64encode(image_bytes).decode() b64 = base64.b64encode(image_bytes).decode()
async with httpx.AsyncClient(timeout=self._timeout) as client: async with httpx.AsyncClient(timeout=30.0) as client:
resp = await client.post( resp = await client.post(
f"{self._base_url}/extract", f"{self._base_url}/extract",
json={"image_b64": b64, "hint": hint}, json={"image": b64},
) )
resp.raise_for_status() resp.raise_for_status()
data = resp.json() data = resp.json()
return DocuvisionResult( return DocuvisionResult(
text=data.get("raw_text", ""), text=data.get("text", ""),
confidence=data.get("metadata", {}).get("confidence"), confidence=data.get("confidence"),
raw=data, raw=data,
) )

View file

@ -32,29 +32,6 @@ def _try_docuvision(image_path: str | Path) -> str | None:
cf_orch_url = os.environ.get("CF_ORCH_URL") cf_orch_url = os.environ.get("CF_ORCH_URL")
if not cf_orch_url: if not cf_orch_url:
return None return None
# Tier 1: task-based routing — coordinator owns model selection.
try:
from app.services.task_inference import task_allocate, TaskNotRegistered
from app.services.ocr.docuvision_client import DocuvisionClient
try:
with task_allocate(
"kiwi", "ocr",
service_hint="cf-docuvision",
ttl_s=60.0,
) as alloc:
doc_client = DocuvisionClient(alloc.url)
result = doc_client.extract_text(image_path)
return result.text if result.text else None
except TaskNotRegistered:
logger.debug(
"kiwi.ocr not in coordinator assignments — "
"falling back to direct cf-docuvision allocation"
)
except Exception as exc:
logger.debug("task allocation path failed, trying direct allocate: %s", exc)
# Tier 2: direct allocation — hardcoded service type.
try: try:
from circuitforge_orch.client import CFOrchClient from circuitforge_orch.client import CFOrchClient
from app.services.ocr.docuvision_client import DocuvisionClient from app.services.ocr.docuvision_client import DocuvisionClient
@ -72,7 +49,7 @@ def _try_docuvision(image_path: str | Path) -> str | None:
result = doc_client.extract_text(image_path) result = doc_client.extract_text(image_path)
return result.text if result.text else None return result.text if result.text else None
except Exception as exc: except Exception as exc:
logger.debug("cf-docuvision fast-path failed, falling back to local VLM: %s", exc) logger.debug("cf-docuvision fast-path failed, falling back: %s", exc)
return None return None

View file

@ -15,72 +15,63 @@ logger = logging.getLogger(__name__)
class OpenFoodFactsService: class OpenFoodFactsService:
""" """
Service for interacting with the Open*Facts family of databases. Service for interacting with the OpenFoodFacts API.
Primary: OpenFoodFacts (food products). OpenFoodFacts is a free, open database of food products with
Fallback chain: Open Beauty Facts (personal care) Open Products Facts (household). ingredients, allergens, and nutrition facts.
All three databases share the same API path and JSON format.
""" """
BASE_URL = "https://world.openfoodfacts.org/api/v2" BASE_URL = "https://world.openfoodfacts.org/api/v2"
USER_AGENT = "Kiwi/0.1.0 (https://circuitforge.tech)" USER_AGENT = "Kiwi/0.1.0 (https://circuitforge.tech)"
# Fallback databases tried in order when OFFs returns no match.
# Same API format as OFFs — only the host differs.
_FALLBACK_DATABASES = [
"https://world.openbeautyfacts.org/api/v2",
"https://world.openproductsfacts.org/api/v2",
]
async def _lookup_in_database(
self, barcode: str, base_url: str, client: httpx.AsyncClient
) -> Optional[Dict[str, Any]]:
"""Try one Open*Facts database using an existing client. Returns parsed product dict or None."""
try:
response = await client.get(
f"{base_url}/product/{barcode}.json",
headers={"User-Agent": self.USER_AGENT},
timeout=10.0,
)
if response.status_code == 404:
return None
response.raise_for_status()
data = response.json()
if data.get("status") != 1:
return None
return self._parse_product_data(data, barcode)
except httpx.HTTPError as e:
logger.debug("HTTP error for %s at %s: %s", barcode, base_url, e)
return None
except Exception as e:
logger.debug("Lookup failed for %s at %s: %s", barcode, base_url, e)
return None
async def lookup_product(self, barcode: str) -> Optional[Dict[str, Any]]: async def lookup_product(self, barcode: str) -> Optional[Dict[str, Any]]:
""" """
Look up a product by barcode, trying OFFs then fallback databases. Look up a product by barcode in the OpenFoodFacts database.
A single httpx.AsyncClient is created for the whole lookup chain so that
connection pooling and TLS session reuse apply across all database attempts.
Args: Args:
barcode: UPC/EAN barcode (8-13 digits) barcode: UPC/EAN barcode (8-13 digits)
Returns: Returns:
Dictionary with product information, or None if not found in any database. Dictionary with product information, or None if not found
Example response:
{
"name": "Organic Milk",
"brand": "Horizon",
"categories": ["Dairy", "Milk"],
"image_url": "https://...",
"nutrition_data": {...},
"raw_data": {...} # Full API response
}
""" """
try:
async with httpx.AsyncClient() as client: async with httpx.AsyncClient() as client:
result = await self._lookup_in_database(barcode, self.BASE_URL, client) url = f"{self.BASE_URL}/product/{barcode}.json"
if result:
return result
for db_url in self._FALLBACK_DATABASES: response = await client.get(
result = await self._lookup_in_database(barcode, db_url, client) url,
if result: headers={"User-Agent": self.USER_AGENT},
logger.info("Barcode %s found in fallback database: %s", barcode, db_url) timeout=10.0,
return result )
logger.info("Barcode %s not found in any Open*Facts database", barcode) if response.status_code == 404:
logger.info(f"Product not found in OpenFoodFacts: {barcode}")
return None
response.raise_for_status()
data = response.json()
if data.get("status") != 1:
logger.info(f"Product not found in OpenFoodFacts: {barcode}")
return None
return self._parse_product_data(data, barcode)
except httpx.HTTPError as e:
logger.error(f"HTTP error looking up barcode {barcode}: {e}")
return None
except Exception as e:
logger.error(f"Error looking up barcode {barcode}: {e}")
return None return None
def _parse_product_data(self, data: Dict[str, Any], barcode: str) -> Dict[str, Any]: def _parse_product_data(self, data: Dict[str, Any], barcode: str) -> Dict[str, Any]:
@ -123,9 +114,6 @@ class OpenFoodFactsService:
allergens = product.get("allergens_tags", []) allergens = product.get("allergens_tags", [])
labels = product.get("labels_tags", []) labels = product.get("labels_tags", [])
# Pack size detection: prefer explicit unit_count, fall back to serving count
pack_quantity, pack_unit = self._extract_pack_size(product)
return { return {
"name": name, "name": name,
"brand": brand, "brand": brand,
@ -136,47 +124,9 @@ class OpenFoodFactsService:
"nutrition_data": nutrition_data, "nutrition_data": nutrition_data,
"allergens": allergens, "allergens": allergens,
"labels": labels, "labels": labels,
"pack_quantity": pack_quantity,
"pack_unit": pack_unit,
"raw_data": product, # Store full response for debugging "raw_data": product, # Store full response for debugging
} }
def _extract_pack_size(self, product: Dict[str, Any]) -> tuple[float | None, str | None]:
"""Return (quantity, unit) for multi-pack products, or (None, None).
OFFs fields tried in order:
1. `number_of_units` (explicit count, highest confidence)
2. `serving_quantity` + `product_quantity_unit` (e.g. 6 x 150g yoghurt)
3. Parse `quantity` string like "4 x 113 g" or "6 pack"
Returns None, None when data is absent, ambiguous, or single-unit.
"""
import re
# Field 1: explicit unit count
unit_count = product.get("number_of_units")
if unit_count:
try:
n = float(unit_count)
if n > 1:
return n, product.get("serving_size_unit") or "unit"
except (ValueError, TypeError):
pass
# Field 2: parse quantity string for "N x ..." pattern
qty_str = product.get("quantity", "")
if qty_str:
m = re.match(r"^(\d+(?:\.\d+)?)\s*[xX×]\s*", qty_str.strip())
if m:
n = float(m.group(1))
if n > 1:
# Try to get a sensible sub-unit label from the rest
rest = qty_str[m.end():].strip()
unit_label = re.sub(r"[\d.,\s]+", "", rest).strip()[:20] or "unit"
return n, unit_label
return None, None
def _extract_nutrition_data(self, product: Dict[str, Any]) -> Dict[str, Any]: def _extract_nutrition_data(self, product: Dict[str, Any]) -> Dict[str, Any]:
""" """
Extract nutrition facts from product data. Extract nutrition facts from product data.

View file

@ -42,21 +42,11 @@ class AssemblyRole:
class AssemblyTemplate: class AssemblyTemplate:
"""A template assembly dish.""" """A template assembly dish."""
id: int id: int
slug: str # URL-safe identifier, e.g. "burrito_taco"
icon: str # emoji
descriptor: str # one-line description shown in template grid
title: str title: str
required: list[AssemblyRole] required: list[AssemblyRole]
optional: list[AssemblyRole] optional: list[AssemblyRole]
directions: list[str] directions: list[str]
notes: str = "" notes: str = ""
# Per-role hints shown in the wizard picker header
# keys match role.display values; missing keys fall back to ""
role_hints: dict[str, str] = None # type: ignore[assignment]
def __post_init__(self) -> None:
if self.role_hints is None:
self.role_hints = {}
def _matches_role(role: AssemblyRole, pantry_set: set[str]) -> list[str]: def _matches_role(role: AssemblyRole, pantry_set: set[str]) -> list[str]:
@ -148,9 +138,6 @@ def _personalized_title(tmpl: AssemblyTemplate, pantry_set: set[str], seed: int)
ASSEMBLY_TEMPLATES: list[AssemblyTemplate] = [ ASSEMBLY_TEMPLATES: list[AssemblyTemplate] = [
AssemblyTemplate( AssemblyTemplate(
id=-1, id=-1,
slug="burrito_taco",
icon="🌯",
descriptor="Protein, veg, and sauce in a tortilla or over rice",
title="Burrito / Taco", title="Burrito / Taco",
required=[ required=[
AssemblyRole("tortilla or wrap", [ AssemblyRole("tortilla or wrap", [
@ -183,21 +170,9 @@ ASSEMBLY_TEMPLATES: list[AssemblyTemplate] = [
"Fold in the sides and roll tightly. Optionally toast seam-side down 1-2 minutes.", "Fold in the sides and roll tightly. Optionally toast seam-side down 1-2 minutes.",
], ],
notes="Works as a burrito (rolled), taco (folded), or quesadilla (cheese only, pressed flat).", notes="Works as a burrito (rolled), taco (folded), or quesadilla (cheese only, pressed flat).",
role_hints={
"tortilla or wrap": "The foundation -- what holds everything",
"protein": "The main filling",
"rice or starch": "Optional base layer",
"cheese": "Optional -- melts into the filling",
"salsa or sauce": "Optional -- adds moisture and heat",
"sour cream or yogurt": "Optional -- cool contrast to heat",
"vegetables": "Optional -- adds texture and colour",
},
), ),
AssemblyTemplate( AssemblyTemplate(
id=-2, id=-2,
slug="fried_rice",
icon="🍳",
descriptor="Rice + egg + whatever's in the fridge",
title="Fried Rice", title="Fried Rice",
required=[ required=[
AssemblyRole("cooked rice", [ AssemblyRole("cooked rice", [
@ -230,21 +205,9 @@ ASSEMBLY_TEMPLATES: list[AssemblyTemplate] = [
"Season with soy sauce and any other sauces. Toss to combine.", "Season with soy sauce and any other sauces. Toss to combine.",
], ],
notes="Add a fried egg on top. A drizzle of sesame oil at the end adds a lot.", notes="Add a fried egg on top. A drizzle of sesame oil at the end adds a lot.",
role_hints={
"cooked rice": "Day-old cold rice works best",
"protein": "Pre-cooked or raw -- cook before adding rice",
"soy sauce or seasoning": "The primary flavour driver",
"oil": "High smoke-point oil for high heat",
"egg": "Scrambled in the same pan",
"vegetables": "Add crunch and colour",
"garlic or ginger": "Aromatic base -- add first",
},
), ),
AssemblyTemplate( AssemblyTemplate(
id=-3, id=-3,
slug="omelette_scramble",
icon="🥚",
descriptor="Eggs with fillings, pan-cooked",
title="Omelette / Scramble", title="Omelette / Scramble",
required=[ required=[
AssemblyRole("eggs", ["egg"]), AssemblyRole("eggs", ["egg"]),
@ -275,19 +238,9 @@ ASSEMBLY_TEMPLATES: list[AssemblyTemplate] = [
"Season and serve immediately.", "Season and serve immediately.",
], ],
notes="Works for breakfast, lunch, or a quick dinner. Any leftover vegetables work well.", notes="Works for breakfast, lunch, or a quick dinner. Any leftover vegetables work well.",
role_hints={
"eggs": "The base -- beat with a splash of water",
"cheese": "Fold in just before serving",
"vegetables": "Saute first, then add eggs",
"protein": "Cook through before adding eggs",
"herbs or seasoning": "Season at the end",
},
), ),
AssemblyTemplate( AssemblyTemplate(
id=-4, id=-4,
slug="stir_fry",
icon="🥢",
descriptor="High-heat protein + veg in sauce",
title="Stir Fry", title="Stir Fry",
required=[ required=[
AssemblyRole("vegetables", [ AssemblyRole("vegetables", [
@ -318,20 +271,9 @@ ASSEMBLY_TEMPLATES: list[AssemblyTemplate] = [
"Serve over rice or noodles.", "Serve over rice or noodles.",
], ],
notes="High heat is the key. Do not crowd the pan -- cook in batches if needed.", notes="High heat is the key. Do not crowd the pan -- cook in batches if needed.",
role_hints={
"vegetables": "Cut to similar size for even cooking",
"starch base": "Serve under or toss with the stir fry",
"protein": "Cook first, remove, add back at end",
"sauce": "Add last -- toss for 1-2 minutes only",
"garlic or ginger": "Add early for aromatic base",
"oil": "High smoke-point oil only",
},
), ),
AssemblyTemplate( AssemblyTemplate(
id=-5, id=-5,
slug="pasta",
icon="🍝",
descriptor="Pantry pasta with flexible sauce",
title="Pasta with Whatever You Have", title="Pasta with Whatever You Have",
required=[ required=[
AssemblyRole("pasta", [ AssemblyRole("pasta", [
@ -365,20 +307,9 @@ ASSEMBLY_TEMPLATES: list[AssemblyTemplate] = [
"Toss cooked pasta with sauce. Finish with cheese if using.", "Toss cooked pasta with sauce. Finish with cheese if using.",
], ],
notes="Pasta water is the secret -- the starch thickens and binds any sauce.", notes="Pasta water is the secret -- the starch thickens and binds any sauce.",
role_hints={
"pasta": "The base -- cook al dente, reserve pasta water",
"sauce base": "Simmer 5 min; pasta water loosens it",
"protein": "Cook through before adding sauce",
"cheese": "Finish off heat to avoid graininess",
"vegetables": "Saute until tender before adding sauce",
"garlic": "Saute in oil first -- the flavour foundation",
},
), ),
AssemblyTemplate( AssemblyTemplate(
id=-6, id=-6,
slug="sandwich_wrap",
icon="🥪",
descriptor="Protein + veg between bread or in a wrap",
title="Sandwich / Wrap", title="Sandwich / Wrap",
required=[ required=[
AssemblyRole("bread or wrap", [ AssemblyRole("bread or wrap", [
@ -410,19 +341,9 @@ ASSEMBLY_TEMPLATES: list[AssemblyTemplate] = [
"Press together and cut diagonally.", "Press together and cut diagonally.",
], ],
notes="Leftovers, deli meat, canned fish -- nearly anything works between bread.", notes="Leftovers, deli meat, canned fish -- nearly anything works between bread.",
role_hints={
"bread or wrap": "Toast for better texture",
"protein": "Layer on first after condiments",
"cheese": "Goes on top of protein",
"condiment": "Spread on both inner surfaces",
"vegetables": "Top layer -- keeps bread from getting soggy",
},
), ),
AssemblyTemplate( AssemblyTemplate(
id=-7, id=-7,
slug="grain_bowl",
icon="🥗",
descriptor="Grain base + protein + toppings + dressing",
title="Grain Bowl", title="Grain Bowl",
required=[ required=[
AssemblyRole("grain base", [ AssemblyRole("grain base", [
@ -456,19 +377,9 @@ ASSEMBLY_TEMPLATES: list[AssemblyTemplate] = [
"Drizzle with dressing and add toppings.", "Drizzle with dressing and add toppings.",
], ],
notes="Great for meal prep -- cook grains and proteins in bulk, assemble bowls all week.", notes="Great for meal prep -- cook grains and proteins in bulk, assemble bowls all week.",
role_hints={
"grain base": "Season while cooking -- bland grains sink the bowl",
"protein": "Slice or shred; arrange on top",
"vegetables": "Roast or saute for best flavour",
"dressing or sauce": "Drizzle last -- ties everything together",
"toppings": "Add crunch and contrast",
},
), ),
AssemblyTemplate( AssemblyTemplate(
id=-8, id=-8,
slug="soup_stew",
icon="🥣",
descriptor="Liquid-based, flexible ingredients",
title="Soup / Stew", title="Soup / Stew",
required=[ required=[
# Narrow to dedicated soup bases — tomato sauce and coconut milk are # Narrow to dedicated soup bases — tomato sauce and coconut milk are
@ -504,19 +415,9 @@ ASSEMBLY_TEMPLATES: list[AssemblyTemplate] = [
"Season to taste and simmer at least 20 minutes for flavors to develop.", "Season to taste and simmer at least 20 minutes for flavors to develop.",
], ],
notes="Soups and stews improve overnight in the fridge. Almost any combination works.", notes="Soups and stews improve overnight in the fridge. Almost any combination works.",
role_hints={
"broth or stock": "The liquid base -- determines overall flavour",
"protein": "Brown first for deeper flavour",
"vegetables": "Dense veg first; quick-cooking veg last",
"starch thickener": "Adds body and turns soup into stew",
"seasoning": "Taste and adjust after 20 min simmer",
},
), ),
AssemblyTemplate( AssemblyTemplate(
id=-9, id=-9,
slug="casserole_bake",
icon="🫙",
descriptor="Oven bake with protein, veg, starch",
title="Casserole / Bake", title="Casserole / Bake",
required=[ required=[
AssemblyRole("starch or base", [ AssemblyRole("starch or base", [
@ -556,20 +457,9 @@ ASSEMBLY_TEMPLATES: list[AssemblyTemplate] = [
"Bake covered 25 minutes, then uncovered 15 minutes until golden and bubbly.", "Bake covered 25 minutes, then uncovered 15 minutes until golden and bubbly.",
], ],
notes="Classic pantry dump dinner. Cream of anything soup is the universal binder.", notes="Classic pantry dump dinner. Cream of anything soup is the universal binder.",
role_hints={
"starch or base": "Cook slightly underdone -- finishes in oven",
"binder or sauce": "Coats everything and holds the bake together",
"protein": "Pre-cook before mixing in",
"vegetables": "Chop small for even distribution",
"cheese topping": "Goes on last -- browns in the final 15 min",
"seasoning": "Casseroles need more salt than you think",
},
), ),
AssemblyTemplate( AssemblyTemplate(
id=-10, id=-10,
slug="pancakes_quickbread",
icon="🥞",
descriptor="Batter-based; sweet or savory",
title="Pancakes / Waffles / Quick Bread", title="Pancakes / Waffles / Quick Bread",
required=[ required=[
AssemblyRole("flour or baking mix", [ AssemblyRole("flour or baking mix", [
@ -605,20 +495,9 @@ ASSEMBLY_TEMPLATES: list[AssemblyTemplate] = [
"For muffins or quick bread: pour into greased pan, bake at 375 F until a toothpick comes out clean.", "For muffins or quick bread: pour into greased pan, bake at 375 F until a toothpick comes out clean.",
], ],
notes="Overmixing develops gluten and makes pancakes tough. Stop when just combined.", notes="Overmixing develops gluten and makes pancakes tough. Stop when just combined.",
role_hints={
"flour or baking mix": "Whisk dry ingredients together first",
"leavening or egg": "Activates rise -- don't skip",
"liquid": "Add to dry ingredients; lumps are fine",
"fat": "Adds richness and prevents sticking",
"sweetener": "Mix into wet ingredients",
"mix-ins": "Fold in last -- gently",
},
), ),
AssemblyTemplate( AssemblyTemplate(
id=-11, id=-11,
slug="porridge_oatmeal",
icon="🌾",
descriptor="Oat or grain base with toppings",
title="Porridge / Oatmeal", title="Porridge / Oatmeal",
required=[ required=[
AssemblyRole("oats or grain porridge", [ AssemblyRole("oats or grain porridge", [
@ -641,20 +520,9 @@ ASSEMBLY_TEMPLATES: list[AssemblyTemplate] = [
"Top with fruit, nuts, or seeds and serve immediately.", "Top with fruit, nuts, or seeds and serve immediately.",
], ],
notes="Overnight oats: skip cooking — soak oats in cold milk overnight in the fridge.", notes="Overnight oats: skip cooking — soak oats in cold milk overnight in the fridge.",
role_hints={
"oats or grain porridge": "1 part oats to 2 parts liquid",
"liquid": "Use milk for creamier result",
"sweetener": "Stir in after cooking",
"fruit": "Add fresh on top or simmer dried fruit in",
"toppings": "Add last for crunch",
"spice": "Stir in with sweetener",
},
), ),
AssemblyTemplate( AssemblyTemplate(
id=-12, id=-12,
slug="pie_pot_pie",
icon="🥧",
descriptor="Pastry or biscuit crust with filling",
title="Pie / Pot Pie", title="Pie / Pot Pie",
required=[ required=[
AssemblyRole("pastry or crust", [ AssemblyRole("pastry or crust", [
@ -693,20 +561,9 @@ ASSEMBLY_TEMPLATES: list[AssemblyTemplate] = [
"For sweet pie: fill unbaked crust with fruit filling, top with second crust or crumble, bake similarly.", "For sweet pie: fill unbaked crust with fruit filling, top with second crust or crumble, bake similarly.",
], ],
notes="Puff pastry from the freezer is the shortcut to impressive pot pies. Thaw in the fridge overnight.", notes="Puff pastry from the freezer is the shortcut to impressive pot pies. Thaw in the fridge overnight.",
role_hints={
"pastry or crust": "Thaw puff pastry overnight in fridge",
"protein filling": "Cook through before adding to filling",
"vegetables": "Chop small; cook until just tender",
"sauce or binder": "Holds the filling together in the crust",
"seasoning": "Fillings need generous seasoning",
"sweet filling": "For dessert pies -- fruit + sugar",
},
), ),
AssemblyTemplate( AssemblyTemplate(
id=-13, id=-13,
slug="pudding_custard",
icon="🍮",
descriptor="Dairy-based set dessert",
title="Pudding / Custard", title="Pudding / Custard",
required=[ required=[
AssemblyRole("dairy or dairy-free milk", [ AssemblyRole("dairy or dairy-free milk", [
@ -744,58 +601,10 @@ ASSEMBLY_TEMPLATES: list[AssemblyTemplate] = [
"Pour into dishes and refrigerate at least 2 hours to set.", "Pour into dishes and refrigerate at least 2 hours to set.",
], ],
notes="UK-style pudding is broad — bread pudding, rice pudding, spotted dick, treacle sponge all count.", notes="UK-style pudding is broad — bread pudding, rice pudding, spotted dick, treacle sponge all count.",
role_hints={
"dairy or dairy-free milk": "Heat until steaming before adding to eggs",
"thickener or set": "Cornstarch for stovetop; eggs for baked custard",
"sweetener or flavouring": "Signals dessert intent -- required",
"sweetener": "Adjust to taste",
"flavouring": "Add off-heat to preserve aroma",
"starchy base": "For bread pudding or rice pudding",
"fruit": "Layer in or fold through before setting",
},
), ),
] ]
# Slug to template lookup (built once at import time)
_TEMPLATE_BY_SLUG: dict[str, AssemblyTemplate] = {
t.slug: t for t in ASSEMBLY_TEMPLATES
}
def get_templates_for_api() -> list[dict]:
"""Serialise all 13 templates for GET /api/recipes/templates.
Combines required and optional roles into a single ordered role_sequence
with required roles first.
"""
out = []
for tmpl in ASSEMBLY_TEMPLATES:
roles = []
for role in tmpl.required:
roles.append({
"display": role.display,
"required": True,
"keywords": role.keywords,
"hint": tmpl.role_hints.get(role.display, ""),
})
for role in tmpl.optional:
roles.append({
"display": role.display,
"required": False,
"keywords": role.keywords,
"hint": tmpl.role_hints.get(role.display, ""),
})
out.append({
"id": tmpl.slug,
"title": tmpl.title,
"icon": tmpl.icon,
"descriptor": tmpl.descriptor,
"role_sequence": roles,
})
return out
# --------------------------------------------------------------------------- # ---------------------------------------------------------------------------
# Public API # Public API
# --------------------------------------------------------------------------- # ---------------------------------------------------------------------------
@ -870,148 +679,3 @@ def match_assembly_templates(
# Sort by optional coverage descending — best-matched templates first # Sort by optional coverage descending — best-matched templates first
results.sort(key=lambda s: s.match_count, reverse=True) results.sort(key=lambda s: s.match_count, reverse=True)
return results return results
def get_role_candidates(
template_slug: str,
role_display: str,
pantry_set: set[str],
prior_picks: list[str],
profile_index: dict[str, list[str]],
) -> dict:
"""Return ingredient candidates for one wizard step.
Splits candidates into 'compatible' (element overlap with prior picks)
and 'other' (valid for role but no overlap).
profile_index: {ingredient_name: [element_tag, ...]} -- pre-loaded from
Store.get_element_profiles() by the caller so this function stays DB-free.
Returns {"compatible": [...], "other": [...], "available_tags": [...]}
where each item is {"name": str, "in_pantry": bool, "tags": [str]}.
"""
tmpl = _TEMPLATE_BY_SLUG.get(template_slug)
if tmpl is None:
return {"compatible": [], "other": [], "available_tags": []}
# Find the AssemblyRole for this display name
target_role: AssemblyRole | None = None
for role in tmpl.required + tmpl.optional:
if role.display == role_display:
target_role = role
break
if target_role is None:
return {"compatible": [], "other": [], "available_tags": []}
# Build prior-pick element set for compatibility scoring
prior_elements: set[str] = set()
for pick in prior_picks:
prior_elements.update(profile_index.get(pick, []))
# Find pantry items that match this role
pantry_matches = _matches_role(target_role, pantry_set)
# Build keyword-based "other" candidates from role keywords not in pantry
pantry_lower = {p.lower() for p in pantry_set}
other_names: list[str] = []
for kw in target_role.keywords:
if not any(kw in item.lower() for item in pantry_lower):
if len(kw) >= 4:
other_names.append(kw.title())
def _make_item(name: str, in_pantry: bool) -> dict:
tags = profile_index.get(name, profile_index.get(name.lower(), []))
return {"name": name, "in_pantry": in_pantry, "tags": tags}
# Score: compatible if shares any element with prior picks (or no prior picks yet)
compatible: list[dict] = []
other: list[dict] = []
for name in pantry_matches:
item_elements = set(profile_index.get(name, []))
item = _make_item(name, in_pantry=True)
if not prior_elements or item_elements & prior_elements:
compatible.append(item)
else:
other.append(item)
for name in other_names:
other.append(_make_item(name, in_pantry=False))
# available_tags: union of all tags in the full candidate set
all_tags: set[str] = set()
for item in compatible + other:
all_tags.update(item["tags"])
return {
"compatible": compatible,
"other": other,
"available_tags": sorted(all_tags),
}
def build_from_selection(
template_slug: str,
role_overrides: dict[str, str],
pantry_set: set[str],
) -> "RecipeSuggestion | None":
"""Build a RecipeSuggestion from explicit role selections.
role_overrides: {role.display -> chosen pantry item name}
Returns None if template not found or any required role is uncovered.
"""
tmpl = _TEMPLATE_BY_SLUG.get(template_slug)
if tmpl is None:
return None
seed = _pantry_hash(pantry_set)
# Validate required roles: covered by override OR pantry match
matched_required: list[str] = []
for role in tmpl.required:
chosen = role_overrides.get(role.display)
if chosen:
matched_required.append(chosen)
else:
hits = _matches_role(role, pantry_set)
if not hits:
return None
matched_required.append(_pick_one(hits, seed + tmpl.id))
# Collect optional matches (override preferred, then pantry match)
matched_optional: list[str] = []
for role in tmpl.optional:
chosen = role_overrides.get(role.display)
if chosen:
matched_optional.append(chosen)
else:
hits = _matches_role(role, pantry_set)
if hits:
matched_optional.append(_pick_one(hits, seed + tmpl.id))
all_matched = matched_required + matched_optional
# Build title: prefer override items for personalisation
effective_pantry = pantry_set | set(role_overrides.values())
title = _personalized_title(tmpl, effective_pantry, seed + tmpl.id)
# Items in role_overrides that aren't in the user's pantry = shopping list
missing = [
item for item in role_overrides.values()
if item and item not in pantry_set
]
return RecipeSuggestion(
id=tmpl.id,
title=title,
match_count=len(all_matched),
element_coverage={},
swap_candidates=[],
matched_ingredients=all_matched,
missing_ingredients=missing,
directions=tmpl.directions,
notes=tmpl.notes,
level=1,
is_wildcard=False,
nutrition=None,
)

View file

@ -1,256 +0,0 @@
"""
Browse counts cache pre-computes and persists recipe counts for all
browse domain keyword sets so category/subcategory page loads never
hit the 3.8 GB FTS index at request time.
Counts change only when the corpus changes (after a pipeline run).
The cache is a small SQLite file separate from both the read-only
corpus DB and per-user kiwi.db files, so the container can write it.
Refresh triggers:
1. Startup if cache is missing or older than STALE_DAYS
2. Nightly asyncio background task started in main.py lifespan
3. Pipeline infer_recipe_tags.py calls refresh() at end of run
The in-memory _COUNT_CACHE in store.py is pre-warmed from this file
on startup, so FTS queries are never needed for known keyword sets.
"""
from __future__ import annotations
import logging
import sqlite3
from datetime import datetime, timezone
from pathlib import Path
logger = logging.getLogger(__name__)
STALE_DAYS = 7
# ---------------------------------------------------------------------------
# Internal helpers
# ---------------------------------------------------------------------------
def _kw_key(keywords: list[str]) -> str:
"""Stable string key for a keyword list — sorted and pipe-joined."""
return "|".join(sorted(keywords))
def _fts_match_expr(keywords: list[str]) -> str:
phrases = ['"' + kw.replace('"', '""') + '"' for kw in keywords]
return " OR ".join(phrases)
def _ensure_schema(conn: sqlite3.Connection) -> None:
conn.execute("""
CREATE TABLE IF NOT EXISTS browse_counts (
keywords_key TEXT PRIMARY KEY,
count INTEGER NOT NULL,
computed_at TEXT NOT NULL
)
""")
conn.execute("""
CREATE TABLE IF NOT EXISTS browse_counts_meta (
key TEXT PRIMARY KEY,
value TEXT NOT NULL
)
""")
conn.commit()
# ---------------------------------------------------------------------------
# Public API
# ---------------------------------------------------------------------------
def is_stale(cache_path: Path, max_age_days: int = STALE_DAYS) -> bool:
"""Return True if the cache is missing, empty, or older than max_age_days."""
if not cache_path.exists():
return True
try:
conn = sqlite3.connect(cache_path)
row = conn.execute(
"SELECT value FROM browse_counts_meta WHERE key = 'refreshed_at'"
).fetchone()
conn.close()
if row is None:
return True
age = (datetime.now(timezone.utc) - datetime.fromisoformat(row[0])).days
return age >= max_age_days
except Exception:
return True
def load_into_memory(cache_path: Path, count_cache: dict, corpus_path: str) -> int:
"""
Load all rows from the cache file into the in-memory count_cache dict.
Uses corpus_path (the current RECIPE_DB_PATH env value) as the cache key,
not what was stored in the file the file may have been built against a
different mount path (e.g. pipeline ran on host, container sees a different
path). Counts are corpus-content-derived and path-independent.
Returns the number of entries loaded.
"""
if not cache_path.exists():
return 0
try:
conn = sqlite3.connect(cache_path)
rows = conn.execute("SELECT keywords_key, count FROM browse_counts").fetchall()
conn.close()
loaded = 0
for kw_key, count in rows:
keywords = kw_key.split("|") if kw_key else []
cache_key = (corpus_path, *sorted(keywords))
count_cache[cache_key] = count
loaded += 1
logger.info("browse_counts: warmed %d entries from %s", loaded, cache_path)
return loaded
except Exception as exc:
logger.warning("browse_counts: load failed: %s", exc)
return 0
def refresh(corpus_path: str, cache_path: Path) -> int:
"""
Run FTS5 queries for every keyword set in browser_domains.DOMAINS
and write results to cache_path.
Safe to call from both the host pipeline script and the in-container
nightly task. The corpus_path must be reachable and readable from
the calling process.
Returns the number of keyword sets computed.
"""
from app.services.recipe.browser_domains import DOMAINS # local import — avoid circular
cache_path.parent.mkdir(parents=True, exist_ok=True)
cache_conn = sqlite3.connect(cache_path)
_ensure_schema(cache_conn)
# Collect every unique keyword list across all domains/categories/subcategories.
# DOMAINS structure: {domain: {label: str, categories: {cat_name: {keywords, subcategories}}}}
seen: dict[str, list[str]] = {}
for domain_data in DOMAINS.values():
for cat_data in domain_data.get("categories", {}).values():
if not isinstance(cat_data, dict):
continue
top_kws = cat_data.get("keywords", [])
if top_kws:
seen[_kw_key(top_kws)] = top_kws
for subcat_kws in cat_data.get("subcategories", {}).values():
if subcat_kws:
seen[_kw_key(subcat_kws)] = subcat_kws
try:
corpus_conn = sqlite3.connect(f"file:{corpus_path}?mode=ro", uri=True)
except Exception as exc:
logger.error("browse_counts: cannot open corpus %s: %s", corpus_path, exc)
cache_conn.close()
return 0
now = datetime.now(timezone.utc).isoformat()
computed = 0
try:
for kw_key, kws in seen.items():
try:
row = corpus_conn.execute(
"SELECT count(*) FROM recipe_browser_fts WHERE recipe_browser_fts MATCH ?",
(_fts_match_expr(kws),),
).fetchone()
count = row[0] if row else 0
cache_conn.execute(
"INSERT OR REPLACE INTO browse_counts (keywords_key, count, computed_at)"
" VALUES (?, ?, ?)",
(kw_key, count, now),
)
computed += 1
except Exception as exc:
logger.warning("browse_counts: query failed key=%r: %s", kw_key[:60], exc)
# Merge accepted community tags into counts.
# For each (domain, category, subcategory) that has accepted community
# tags, add the count of distinct tagged recipe_ids to the FTS count.
# The two overlap rarely (community tags exist precisely because FTS
# missed those recipes), so simple addition is accurate enough.
try:
_merge_community_tag_counts(cache_conn, DOMAINS, now)
except Exception as exc:
logger.warning("browse_counts: community merge skipped: %s", exc)
cache_conn.execute(
"INSERT OR REPLACE INTO browse_counts_meta (key, value) VALUES ('refreshed_at', ?)",
(now,),
)
cache_conn.execute(
"INSERT OR REPLACE INTO browse_counts_meta (key, value) VALUES ('corpus_path', ?)",
(corpus_path,),
)
cache_conn.commit()
logger.info("browse_counts: wrote %d counts → %s", computed, cache_path)
finally:
corpus_conn.close()
cache_conn.close()
return computed
def _merge_community_tag_counts(
cache_conn: sqlite3.Connection,
domains: dict,
now: str,
threshold: int = 2,
) -> None:
"""Add accepted community tag counts on top of FTS counts in the cache.
Queries the community PostgreSQL store (if available) for accepted tags
grouped by (domain, category, subcategory), maps each back to its keyword
set key, then increments the cached count.
Silently skips if community features are unavailable.
"""
try:
from app.api.endpoints.community import _get_community_store
store = _get_community_store()
if store is None:
return
except Exception:
return
for domain_id, domain_data in domains.items():
for cat_name, cat_data in domain_data.get("categories", {}).items():
if not isinstance(cat_data, dict):
continue
# Check subcategories
for subcat_name, subcat_kws in cat_data.get("subcategories", {}).items():
if not subcat_kws:
continue
ids = store.get_accepted_recipe_ids_for_subcategory(
domain=domain_id,
category=cat_name,
subcategory=subcat_name,
threshold=threshold,
)
if not ids:
continue
kw_key = _kw_key(subcat_kws)
cache_conn.execute(
"UPDATE browse_counts SET count = count + ? WHERE keywords_key = ?",
(len(ids), kw_key),
)
# Check category-level tags (subcategory IS NULL)
top_kws = cat_data.get("keywords", [])
if top_kws:
ids = store.get_accepted_recipe_ids_for_subcategory(
domain=domain_id,
category=cat_name,
subcategory=None,
threshold=threshold,
)
if ids:
kw_key = _kw_key(top_kws)
cache_conn.execute(
"UPDATE browse_counts SET count = count + ? WHERE keywords_key = ?",
(len(ids), kw_key),
)
logger.info("browse_counts: community tag counts merged")

View file

@ -5,12 +5,6 @@ Each domain provides a two-level category hierarchy for browsing the recipe corp
Keyword matching is case-insensitive against the recipes.category column and the Keyword matching is case-insensitive against the recipes.category column and the
recipes.keywords JSON array. A recipe may appear in multiple categories (correct). recipes.keywords JSON array. A recipe may appear in multiple categories (correct).
Category values are either:
- list[str] flat keyword list (no subcategories)
- dict {"keywords": list[str], "subcategories": {name: list[str]}}
keywords covers the whole category (used for "All X" browse);
subcategories each have their own narrower keyword list.
These are starter mappings based on the food.com dataset structure. Run: These are starter mappings based on the food.com dataset structure. Run:
SELECT category, count(*) FROM recipes SELECT category, count(*) FROM recipes
@ -25,657 +19,68 @@ DOMAINS: dict[str, dict] = {
"cuisine": { "cuisine": {
"label": "Cuisine", "label": "Cuisine",
"categories": { "categories": {
"Italian": { "Italian": ["italian", "pasta", "pizza", "risotto", "lasagna", "carbonara"],
"keywords": ["cuisine:Italian", "italian", "pasta", "pizza", "risotto", "lasagna", "carbonara"], "Mexican": ["mexican", "tex-mex", "taco", "enchilada", "burrito", "salsa", "guacamole"],
"subcategories": { "Asian": ["asian", "chinese", "japanese", "thai", "korean", "vietnamese", "stir fry", "stir-fry", "ramen", "sushi"],
"Sicilian": ["sicilian", "sicily", "arancini", "caponata", "American": ["american", "southern", "bbq", "barbecue", "comfort food", "cajun", "creole"],
"involtini", "cannoli"], "Mediterranean": ["mediterranean", "greek", "middle eastern", "turkish", "moroccan", "lebanese"],
"Neapolitan": ["neapolitan", "naples", "pizza napoletana", "Indian": ["indian", "curry", "lentil", "dal", "tikka", "masala", "biryani"],
"sfogliatelle", "ragù"], "European": ["french", "german", "spanish", "british", "irish", "scandinavian"],
"Tuscan": ["tuscan", "tuscany", "ribollita", "bistecca", "Latin American": ["latin american", "peruvian", "argentinian", "colombian", "cuban", "caribbean"],
"pappardelle", "crostini"],
"Roman": ["roman", "rome", "cacio e pepe", "carbonara",
"amatriciana", "gricia", "supplì"],
"Venetian": ["venetian", "venice", "risotto", "bigoli",
"baccalà", "sarde in saor"],
"Ligurian": ["ligurian", "liguria", "pesto", "focaccia",
"trofie", "farinata"],
},
},
"Mexican": {
"keywords": ["cuisine:Mexican", "mexican", "taco", "enchilada", "burrito",
"salsa", "guacamole", "mole", "tamale"],
"subcategories": {
"Oaxacan": ["oaxacan", "oaxaca", "mole negro", "tlayuda",
"chapulines", "mezcal", "tasajo", "memelas"],
"Yucatecan": ["yucatecan", "yucatan", "cochinita pibil", "poc chuc",
"sopa de lima", "panuchos", "papadzules"],
"Veracruz": ["veracruz", "veracruzana", "huachinango",
"picadas", "enfrijoladas", "caldo de mariscos"],
"Street Food": ["taco", "elote", "tlacoyos", "torta", "tamale",
"quesadilla", "tostada", "sope", "gordita"],
"Mole": ["mole", "mole negro", "mole rojo", "mole verde",
"mole poblano", "mole amarillo", "pipián"],
"Baja / Cal-Mex": ["baja", "baja california", "cal-mex", "baja fish taco",
"fish taco", "carne asada fries", "california burrito",
"birria", "birria tacos", "quesabirria",
"lobster puerto nuevo", "tijuana", "ensenada",
"agua fresca", "caesar salad tijuana"],
"Mexico City": ["mexico city", "chilaquiles", "tlayuda cdmx",
"tacos de canasta", "torta ahogada", "pozole",
"chiles en nogada"],
},
},
"Asian": {
"keywords": ["cuisine:Chinese", "cuisine:Japanese", "cuisine:Korean",
"cuisine:Thai", "cuisine:Vietnamese",
"asian", "chinese", "japanese", "thai", "korean", "vietnamese",
"stir fry", "stir-fry", "ramen", "sushi", "malaysian",
"taiwanese", "singaporean", "burmese", "cambodian",
"laotian", "mongolian", "hong kong"],
"subcategories": {
"Korean": ["korean", "kimchi", "bibimbap", "bulgogi", "japchae",
"doenjang", "gochujang", "tteokbokki", "sundubu",
"galbi", "jjigae", "kbbq", "korean fried chicken"],
"Japanese": ["japanese", "sushi", "ramen", "tempura", "miso",
"teriyaki", "udon", "soba", "bento", "yakitori",
"tonkatsu", "onigiri", "okonomiyaki", "takoyaki",
"kaiseki", "izakaya"],
"Chinese": ["chinese", "dim sum", "fried rice", "dumplings", "wonton",
"spring roll", "szechuan", "sichuan", "cantonese",
"chow mein", "mapo tofu", "lo mein", "hot pot",
"peking duck", "char siu", "congee"],
"Thai": ["thai", "pad thai", "green curry", "red curry",
"coconut milk", "lemongrass", "satay", "tom yum",
"larb", "khao man gai", "massaman", "pad see ew"],
"Vietnamese": ["vietnamese", "pho", "banh mi", "spring rolls",
"vermicelli", "nuoc cham", "bun bo hue",
"banh xeo", "com tam", "bun cha"],
"Filipino": ["filipino", "adobo", "sinigang", "pancit", "lumpia",
"kare-kare", "lechon", "sisig", "halo-halo",
"dinuguan", "tinola", "bistek"],
"Indonesian": ["indonesian", "rendang", "nasi goreng", "gado-gado",
"tempeh", "sambal", "soto", "opor ayam",
"bakso", "mie goreng", "nasi uduk"],
"Malaysian": ["malaysian", "laksa", "nasi lemak", "char kway teow",
"satay malaysia", "roti canai", "bak kut teh",
"cendol", "mee goreng mamak", "curry laksa"],
"Taiwanese": ["taiwanese", "beef noodle soup", "lu rou fan",
"oyster vermicelli", "scallion pancake taiwan",
"pork chop rice", "three cup chicken",
"bubble tea", "stinky tofu", "ba wan"],
"Singaporean": ["singaporean", "chicken rice", "chili crab",
"singaporean laksa", "bak chor mee", "rojak",
"kaya toast", "nasi padang", "satay singapore"],
"Burmese": ["burmese", "myanmar", "mohinga", "laphet thoke",
"tea leaf salad", "ohn no khao swe",
"mont di", "nangyi thoke"],
"Hong Kong": ["hong kong", "hk style", "pineapple bun",
"wonton noodle soup", "hk milk tea", "egg tart",
"typhoon shelter crab", "char siu bao", "jook",
"congee hk", "silk stocking tea", "dan tat",
"siu mai hk", "cheung fun"],
"Cambodian": ["cambodian", "khmer", "amok", "lok lak",
"kuy teav", "bai sach chrouk", "nom banh chok",
"samlor korko", "beef loc lac"],
"Laotian": ["laotian", "lao", "larb", "tam mak hoong",
"or lam", "khao niaw", "ping kai",
"naem khao", "khao piak sen", "mok pa"],
"Mongolian": ["mongolian", "buuz", "khuushuur", "tsuivan",
"boodog", "airag", "khorkhog", "bansh",
"guriltai shol", "suutei tsai"],
"South Asian Fusion": ["south asian fusion", "indo-chinese",
"hakka chinese", "chilli chicken",
"manchurian", "schezwan"],
},
},
"Indian": {
"keywords": ["cuisine:Indian", "indian", "curry", "lentil", "dal", "tikka", "masala",
"biryani", "naan", "chutney", "pakistani", "sri lankan",
"bangladeshi", "nepali"],
"subcategories": {
"North Indian": ["north indian", "punjabi", "mughal", "tikka masala",
"naan", "tandoori", "butter chicken", "palak paneer",
"chole", "rajma", "aloo gobi"],
"South Indian": ["south indian", "tamil", "kerala", "dosa", "idli",
"sambar", "rasam", "coconut chutney", "appam",
"fish curry kerala", "puttu", "payasam"],
"Bengali": ["bengali", "mustard fish", "hilsa", "shorshe ilish",
"mishti doi", "rasgulla", "kosha mangsho"],
"Gujarati": ["gujarati", "dhokla", "thepla", "undhiyu",
"khandvi", "fafda", "gujarati dal"],
"Pakistani": ["pakistani", "nihari", "haleem", "seekh kebab",
"karahi", "biryani karachi", "chapli kebab",
"halwa puri", "paya"],
"Sri Lankan": ["sri lankan", "kottu roti", "hoppers", "pol sambol",
"sri lankan curry", "lamprais", "string hoppers",
"wambatu moju"],
"Bangladeshi": ["bangladeshi", "bangladesh", "dhaka biryani",
"shutki", "pitha", "hilsa curry", "kacchi biryani",
"bhuna khichuri", "doi maach", "rezala"],
"Nepali": ["nepali", "dal bhat", "momos", "sekuwa",
"sel roti", "gundruk", "thukpa"],
},
},
"Mediterranean": {
"keywords": ["cuisine:Mediterranean", "cuisine:Greek", "cuisine:Middle Eastern",
"mediterranean", "greek", "middle eastern", "turkish",
"lebanese", "jewish", "palestinian", "yemeni", "egyptian",
"syrian", "iraqi", "jordanian"],
"subcategories": {
"Greek": ["greek", "feta", "tzatziki", "moussaka", "spanakopita",
"souvlaki", "dolmades", "spanakopita", "tiropita",
"galaktoboureko"],
"Turkish": ["turkish", "kebab", "borek", "meze", "baklava",
"lahmacun", "menemen", "pide", "iskender",
"kisir", "simit"],
"Syrian": ["syrian", "fattet hummus", "kibbeh syria",
"muhammara", "maklouba syria", "sfeeha",
"halawet el jibn"],
"Lebanese": ["lebanese", "middle eastern", "hummus", "falafel",
"tabbouleh", "kibbeh", "fattoush", "manakish",
"kafta", "sfiha"],
"Jewish": ["jewish", "israeli", "ashkenazi", "sephardic",
"shakshuka", "sabich", "za'atar", "tahini",
"zhug", "zhoug", "s'khug", "z'houg",
"hawaiij", "hawaij", "hawayej",
"matzo", "latke", "rugelach", "babka", "challah",
"cholent", "gefilte fish", "brisket", "kugel",
"new york jewish", "new york deli", "pastrami",
"knish", "lox", "bagel and lox", "jewish deli"],
"Palestinian": ["palestinian", "musakhan", "maqluba", "knafeh",
"maftoul", "freekeh", "sumac chicken"],
"Yemeni": ["yemeni", "saltah", "lahoh", "bint al-sahn",
"zhug", "zhoug", "hulba", "fahsa",
"hawaiij", "hawaij", "hawayej"],
"Egyptian": ["egyptian", "koshari", "molokhia", "mahshi",
"ful medames", "ta'ameya", "feteer meshaltet"],
},
},
"American": {
"keywords": ["cuisine:American", "cuisine:Southern", "cuisine:Cajun",
"american", "southern", "comfort food", "cajun", "creole",
"hawaiian", "tex-mex", "soul food"],
"subcategories": {
"Southern": ["southern", "soul food", "fried chicken",
"collard greens", "cornbread", "biscuits and gravy",
"mac and cheese", "sweet potato pie", "okra"],
"Cajun/Creole": ["cajun", "creole", "new orleans", "gumbo",
"jambalaya", "etouffee", "dirty rice", "po'boy",
"muffuletta", "red beans and rice"],
"Tex-Mex": ["tex-mex", "southwestern", "chili", "fajita",
"queso", "breakfast taco", "chile con carne"],
"New England": ["new england", "chowder", "lobster", "clam",
"maple", "yankee", "boston baked beans",
"johnnycake", "fish and chips"],
"Pacific Northwest": ["pacific northwest", "pnw", "dungeness crab",
"salmon", "cedar plank", "razor clam",
"geoduck", "chanterelle", "marionberry"],
"Hawaiian": ["hawaiian", "hawaii", "plate lunch", "loco moco",
"poke", "spam musubi", "kalua pig", "lau lau",
"haupia", "poi", "manapua", "garlic shrimp",
"saimin", "huli huli", "malasada"],
},
},
"BBQ & Smoke": {
# Top-level keywords: cuisine:BBQ inferred tag + broad corpus terms.
"keywords": ["cuisine:BBQ", "bbq", "barbecue", "barbeque", "smoked", "smoky",
"smoke", "pit", "smoke ring", "low and slow",
"brisket", "pulled pork", "ribs", "spare ribs",
"baby back", "baby back ribs", "dry rub", "wet rub",
"cookout", "smoker", "smoked meat", "smoked chicken",
"smoked pork", "smoked beef", "smoked turkey",
"pit smoked", "wood smoked", "slow smoked",
"charcoal", "chargrilled", "burnt ends"],
"subcategories": {
"Texas BBQ": ["texas bbq", "central texas bbq", "brisket",
"beef brisket", "beef ribs", "smoked brisket",
"post oak", "salt and pepper rub",
"east texas bbq", "lockhart", "franklin style"],
"Carolina BBQ": ["carolina bbq", "north carolina bbq", "whole hog",
"vinegar sauce", "vinegar bbq", "lexington style",
"eastern nc", "south carolina bbq", "mustard sauce",
"carolina pulled pork"],
"Kansas City BBQ": ["kansas city bbq", "kc bbq", "burnt ends",
"sweet bbq sauce", "tomato molasses sauce",
"baby back ribs", "kansas city ribs"],
"Memphis BBQ": ["memphis bbq", "dry rub ribs", "wet ribs",
"memphis style", "dry rub pork", "memphis ribs"],
"Alabama BBQ": ["alabama bbq", "white sauce", "alabama white sauce",
"smoked chicken", "white bbq sauce"],
"Kentucky BBQ": ["kentucky bbq", "mutton bbq", "owensboro bbq",
"black dip", "western kentucky barbecue", "mutton"],
"St. Louis BBQ": ["st louis bbq", "st louis ribs", "st. louis ribs",
"st louis cut ribs", "spare ribs st louis"],
"Backyard Grill": ["backyard bbq", "cookout", "grilled burgers",
"charcoal grill", "kettle grill", "tailgate",
"grill out", "backyard grilling"],
},
},
"European": {
"keywords": ["cuisine:French", "cuisine:German", "cuisine:Spanish",
"french", "german", "spanish", "british", "irish", "scottish",
"welsh", "scandinavian", "nordic", "eastern european"],
"subcategories": {
"French": ["french", "provencal", "beurre", "crepe",
"ratatouille", "cassoulet", "bouillabaisse"],
"Spanish": ["spanish", "paella", "tapas", "gazpacho",
"tortilla espanola", "chorizo"],
"German": ["german", "bratwurst", "sauerkraut", "schnitzel",
"pretzel", "strudel"],
"British": ["british", "english", "pub food", "cornish",
"shepherd's pie", "bangers", "toad in the hole",
"coronation chicken", "london", "londoner",
"cornish pasty", "ploughman's"],
"Irish": ["irish", "ireland", "colcannon", "coddle",
"irish stew", "soda bread", "boxty", "champ"],
"Scottish": ["scottish", "scotland", "haggis", "cullen skink",
"cranachan", "scotch broth", "glaswegian",
"neeps and tatties", "tablet"],
"Scandinavian": ["scandinavian", "nordic", "swedish", "norwegian",
"danish", "finnish", "gravlax", "swedish meatballs",
"lefse", "smörgåsbord", "fika", "crispbread",
"cardamom bun", "herring", "æbleskiver",
"lingonberry", "lutefisk", "janssons frestelse",
"knäckebröd", "kladdkaka"],
"Eastern European": ["eastern european", "polish", "russian", "ukrainian",
"czech", "hungarian", "pierogi", "borscht",
"goulash", "kielbasa", "varenyky", "pelmeni"],
},
},
"Latin American": {
"keywords": ["cuisine:Latin American", "cuisine:Caribbean",
"latin american", "peruvian", "argentinian", "colombian",
"cuban", "caribbean", "brazilian", "venezuelan", "chilean"],
"subcategories": {
"Peruvian": ["peruvian", "ceviche", "lomo saltado", "anticucho",
"aji amarillo", "causa", "leche de tigre",
"arroz con leche peru", "pollo a la brasa"],
"Brazilian": ["brazilian", "churrasco", "feijoada", "pao de queijo",
"brigadeiro", "coxinha", "moqueca", "vatapa",
"caipirinha", "acai bowl"],
"Colombian": ["colombian", "bandeja paisa", "arepas", "empanadas",
"sancocho", "ajiaco", "buñuelos", "changua"],
"Argentinian": ["argentinian", "asado", "chimichurri", "empanadas argentina",
"milanesa", "locro", "dulce de leche", "medialunas"],
"Venezuelan": ["venezuelan", "pabellón criollo", "arepas venezuela",
"hallacas", "cachapas", "tequeños", "caraotas"],
"Chilean": ["chilean", "cazuela", "pastel de choclo", "curanto",
"sopaipillas", "charquicán", "completo"],
"Cuban": ["cuban", "ropa vieja", "moros y cristianos",
"picadillo", "lechon cubano", "vaca frita",
"tostones", "platanos maduros"],
"Jamaican": ["jamaican", "jerk chicken", "jerk pork", "ackee saltfish",
"curry goat", "rice and peas", "escovitch",
"jamaican patty", "callaloo jamaica", "festival"],
"Puerto Rican": ["puerto rican", "mofongo", "pernil", "arroz con gandules",
"sofrito", "pasteles", "tostones pr", "tembleque",
"coquito", "asopao"],
"Dominican": ["dominican", "mangu", "sancocho dominicano",
"pollo guisado", "habichuelas guisadas",
"tostones dominicanos", "morir soñando"],
"Haitian": ["haitian", "griot", "pikliz", "riz et pois",
"joumou", "akra", "pain patate", "labouyi"],
"Trinidad": ["trinidadian", "doubles", "roti trinidad", "pelau",
"callaloo trinidad", "bake and shark",
"curry duck", "oil down"],
},
},
"Central American": {
"keywords": ["central american", "salvadoran", "guatemalan",
"honduran", "nicaraguan", "costa rican", "panamanian"],
"subcategories": {
"Salvadoran": ["salvadoran", "el salvador", "pupusas", "curtido",
"sopa de pata", "nuégados", "atol shuco"],
"Guatemalan": ["guatemalan", "pepián", "jocon", "kak'ik",
"hilachas", "rellenitos", "fiambre"],
"Costa Rican": ["costa rican", "gallo pinto", "casado",
"olla de carne", "arroz con leche cr",
"tres leches cr"],
"Honduran": ["honduran", "baleadas", "sopa de caracol",
"tapado", "machuca", "catrachitas"],
"Nicaraguan": ["nicaraguan", "nacatamal", "vigorón", "indio viejo",
"gallo pinto nicaragua", "güirilas"],
},
},
"African": {
"keywords": ["african", "west african", "east african", "ethiopian",
"nigerian", "ghanaian", "kenyan", "south african",
"senegalese", "tunisian"],
"subcategories": {
"West African": ["west african", "nigerian", "ghanaian",
"jollof rice", "egusi soup", "fufu", "suya",
"groundnut stew", "kelewele", "kontomire",
"waakye", "ofam", "bitterleaf soup"],
"Senegalese": ["senegalese", "senegal", "thieboudienne",
"yassa", "mafe", "thiou", "ceebu jen",
"domoda"],
"Ethiopian & Eritrean": ["ethiopian", "eritrean", "injera", "doro wat",
"kitfo", "tibs", "shiro", "misir wat",
"gomen", "ful ethiopian", "tegamino"],
"East African": ["east african", "kenyan", "tanzanian", "ugandan",
"nyama choma", "ugali", "sukuma wiki",
"pilau kenya", "mandazi", "matoke",
"githeri", "irio"],
"North African": ["north african", "tunisian", "algerian", "libyan",
"brik", "lablabi", "merguez", "shakshuka tunisian",
"harissa tunisian", "couscous algerian"],
"South African": ["south african", "braai", "bobotie", "boerewors",
"bunny chow", "pap", "chakalaka", "biltong",
"malva pudding", "koeksister", "potjiekos"],
"Moroccan": ["moroccan", "tagine", "couscous morocco",
"harissa", "chermoula", "preserved lemon",
"pastilla", "mechoui", "bastilla"],
},
},
"Pacific & Oceania": {
"keywords": ["pacific", "oceania", "polynesian", "melanesian",
"micronesian", "maori", "fijian", "samoan", "tongan",
"hawaiian", "australian", "new zealand"],
"subcategories": {
"Māori / New Zealand": ["maori", "new zealand", "hangi", "rewena bread",
"boil-up", "paua", "kumara", "pavlova nz",
"whitebait fritter", "kina", "hokey pokey"],
"Australian": ["australian", "meat pie", "lamington",
"anzac biscuits", "damper", "barramundi",
"vegemite", "pavlova australia", "tim tam",
"sausage sizzle", "chiko roll", "fairy bread"],
"Fijian": ["fijian", "fiji", "kokoda", "lovo",
"rourou", "palusami fiji", "duruka",
"vakalolo"],
"Samoan": ["samoan", "samoa", "palusami", "oka",
"fa'ausi", "chop suey samoa", "sapasui",
"koko alaisa", "supo esi"],
"Tongan": ["tongan", "tonga", "lu pulu", "'ota 'ika",
"fekkai", "faikakai topai", "kapisi pulu"],
"Papua New Guinean": ["papua new guinea", "png", "mumu",
"sago", "aibika", "kaukau",
"taro png", "coconut crab"],
"Hawaiian": ["hawaiian", "hawaii", "poke", "loco moco",
"plate lunch", "kalua pig", "haupia",
"spam musubi", "poi", "malasada"],
},
},
"Central Asian & Caucasus": {
"keywords": ["central asian", "caucasus", "georgian", "armenian", "uzbek",
"afghan", "persian", "iranian", "azerbaijani", "kazakh"],
"subcategories": {
"Persian / Iranian": ["persian", "iranian", "ghormeh sabzi", "fesenjan",
"tahdig", "joojeh kabab", "ash reshteh",
"zereshk polo", "khoresh", "mast o khiar",
"kashk-e-bademjan", "mirza ghasemi",
"baghali polo"],
"Georgian": ["georgian", "georgia", "khachapuri", "khinkali",
"churchkhela", "ajapsandali", "satsivi",
"pkhali", "lobiani", "badrijani nigvzit"],
"Armenian": ["armenian", "dolma armenia", "lahmajoun",
"manti armenia", "ghapama", "basturma",
"harissa armenia", "nazook", "tolma"],
"Azerbaijani": ["azerbaijani", "azerbaijan", "plov azerbaijan",
"dolma azeri", "dushbara", "levengi",
"shah plov", "gutab"],
"Uzbek": ["uzbek", "uzbekistan", "plov", "samsa",
"lagman", "shashlik", "manti uzbek",
"non bread", "dimlama", "sumalak"],
"Afghan": ["afghan", "afghanistan", "kabuli pulao", "mantu",
"bolani", "qorma", "ashak", "shorwa",
"aushak", "borani banjan"],
"Kazakh": ["kazakh", "beshbarmak", "kuyrdak", "baursak",
"kurt", "shubat", "kazy"],
},
},
}, },
}, },
"meal_type": { "meal_type": {
"label": "Meal Type", "label": "Meal Type",
"categories": { "categories": {
# Keywords use two complementary sources: "Breakfast": ["breakfast", "brunch", "eggs", "pancakes", "waffles", "oatmeal", "muffin"],
# 1. inferred_tag phrases ("meal:X", "main:X") — indexed in recipe_browser_fts.inferred_tags. "Lunch": ["lunch", "sandwich", "wrap", "salad", "soup", "light meal"],
# FTS5 tokenises "meal:Breakfast" → ["meal","breakfast"], so the quoted phrase "Dinner": ["dinner", "main dish", "entree", "main course", "supper"],
# "meal:Breakfast" matches exactly that consecutive token pair. "Snack": ["snack", "appetizer", "finger food", "dip", "bite", "starter"],
# 2. Corpus keyword/category text — only covers the ~1,200 keyword-tagged recipes. "Dessert": ["dessert", "cake", "cookie", "pie", "sweet", "pudding", "ice cream", "brownie"],
# Kept as a fallback; not the primary signal. "Beverage": ["drink", "smoothie", "cocktail", "beverage", "juice", "shake"],
"Breakfast": { "Side Dish": ["side dish", "side", "accompaniment", "garnish"],
"keywords": ["meal:Breakfast", "breakfast", "brunch", "pancakes",
"waffles", "oatmeal", "muffin"],
"subcategories": {
"Eggs": ["meal:Breakfast", "egg", "omelette", "frittata",
"quiche", "scrambled", "benedict", "shakshuka"],
"Pancakes & Waffles": ["pancake", "waffle", "crepe", "french toast"],
"Baked Goods": ["muffin", "scone", "biscuit", "quick bread",
"coffee cake", "danish"],
"Oats & Grains": ["oatmeal", "granola", "porridge", "muesli",
"overnight oats"],
},
},
"Lunch": {
# meal:Lunch tag covers explicitly-tagged recipes.
# Coverage is limited — most lunch-style recipes have no distinct meal-type tag.
"keywords": ["meal:Lunch", "lunch", "sandwich", "wrap", "salad",
"soup", "light meal"],
"subcategories": {
"Sandwiches": ["sandwich", "sub", "hoagie", "panini", "club",
"grilled cheese", "blt"],
"Salads": ["salad", "grain bowl", "chopped", "caesar",
"cobb"],
"Soups": ["soup", "bisque", "chowder", "gazpacho",
"minestrone", "lentil soup"],
"Wraps": ["wrap", "burrito bowl", "pita", "lettuce wrap",
"quesadilla"],
},
},
"Dinner": {
# Primary: main:X inferred tags (800k+ recipes).
# "meal:Dinner" does not exist in the inferred-tag vocabulary — main-protein
# tags are the best available proxy for main-course dinner recipes.
"keywords": ["main:Chicken", "main:Beef", "main:Pork", "main:Fish",
"main:Pasta", "dinner", "main dish", "entree",
"main course", "supper"],
"subcategories": {
"Chicken": ["main:Chicken"],
"Beef": ["main:Beef"],
"Pork": ["main:Pork"],
"Fish & Seafood": ["main:Fish"],
"Pasta": ["main:Pasta"],
"Casseroles": ["casserole", "bake", "gratin", "pot pie"],
"Stews": ["stew", "braise", "slow cooker", "pot roast",
"daube"],
"Grilled": ["grilled", "grill", "barbecue", "kebab", "skewer"],
},
},
"Snack": {
"keywords": ["meal:Snack", "snack", "appetizer", "finger food",
"dip", "bite", "starter"],
"subcategories": {
"Dips & Spreads": ["dip", "spread", "hummus", "guacamole",
"salsa", "pate"],
"Finger Foods": ["finger food", "bite", "skewer", "slider",
"wing", "nugget"],
"Chips & Crackers": ["chip", "cracker", "crisp", "popcorn",
"pretzel"],
},
},
"Dessert": {
# "sweet" removed — it matches flavor:Sweet inferred tags, causing false positives.
"keywords": ["meal:Dessert", "dessert", "cake", "cookie", "pie",
"pudding", "ice cream", "brownie"],
"subcategories": {
"Cakes": ["cake", "cupcake", "layer cake", "bundt",
"cheesecake", "torte"],
"Cookies & Bars": ["cookie", "brownie", "blondie", "bar",
"biscotti", "shortbread"],
"Pies & Tarts": ["pie", "tart", "galette", "cobbler", "crisp",
"crumble"],
"Frozen": ["ice cream", "gelato", "sorbet", "frozen dessert",
"popsicle", "granita"],
"Puddings": ["pudding", "custard", "mousse", "panna cotta",
"flan", "creme brulee"],
"Candy": ["candy", "fudge", "truffle", "brittle",
"caramel", "toffee"],
},
},
"Beverage": ["meal:Beverage", "drink", "smoothie", "cocktail", "beverage",
"juice", "shake", "lemonade"],
"Side Dish": {
# meal:Side Dish not in inferred-tag vocabulary.
# main:Vegetables and main:Grains are the best proxies — will overlap
# with some vegetarian mains, which is acceptable.
"keywords": ["main:Vegetables", "main:Grains", "side dish", "side",
"pilaf", "accompaniment"],
"subcategories": {
"Vegetables": ["main:Vegetables"],
"Grains & Rice": ["main:Grains", "rice", "pilaf", "quinoa"],
"Bread": ["meal:Bread", "bread", "roll", "biscuit"],
},
},
}, },
}, },
"dietary": { "dietary": {
"label": "Dietary", "label": "Dietary",
# Primary: dietary:X inferred tags (indexed in recipe_browser_fts.inferred_tags).
# Secondary: text tokens kept as fallback for keyword-tagged recipes.
# IMPORTANT: Use ONLY structured dietary:X phrases here.
# Bare text keywords like "vegan", "low-carb" also match can_be:Vegan,
# can_be:Low-Carb etc. — those are "achievable with substitutions", not
# "recipe already is". The structured phrase "dietary:Vegan" (consecutive
# FTS tokens "dietary"+"vegan") does NOT match can_be:Vegan.
"categories": { "categories": {
"Vegetarian": ["dietary:Vegetarian"], "Vegetarian": ["vegetarian"],
"Vegan": ["dietary:Vegan"], "Vegan": ["vegan", "plant-based", "plant based"],
"Gluten-Free": ["dietary:Gluten-Free"], "Gluten-Free": ["gluten-free", "gluten free", "celiac"],
"Low-Carb": ["dietary:Low-Carb"], "Low-Carb": ["low-carb", "low carb", "keto", "ketogenic"],
"High-Protein": ["dietary:High-Protein"], "High-Protein": ["high protein", "high-protein"],
"Low-Fat": ["dietary:Low-Fat"], "Low-Fat": ["low-fat", "low fat", "light"],
"Dairy-Free": ["dietary:Dairy-Free"], "Dairy-Free": ["dairy-free", "dairy free", "lactose"],
"Low-Sodium": ["dietary:Low-Sodium"],
"Paleo": ["dietary:Paleo"],
}, },
}, },
"main_ingredient": { "main_ingredient": {
"label": "Main Ingredient", "label": "Main Ingredient",
"categories": { "categories": {
# keywords use exact inferred_tag strings (main:X) — indexed into recipe_browser_fts. "Chicken": ["chicken", "poultry", "turkey"],
"Chicken": { "Beef": ["beef", "ground beef", "steak", "brisket", "pot roast"],
"keywords": ["main:Chicken"], "Pork": ["pork", "bacon", "ham", "sausage", "prosciutto"],
"subcategories": { "Fish": ["fish", "salmon", "tuna", "tilapia", "cod", "halibut", "shrimp", "seafood"],
"Baked": ["baked chicken", "roast chicken", "chicken casserole", "Pasta": ["pasta", "noodle", "spaghetti", "penne", "fettuccine", "linguine"],
"chicken bake"], "Vegetables": ["vegetable", "veggie", "cauliflower", "broccoli", "zucchini", "eggplant"],
"Grilled": ["grilled chicken", "chicken kebab", "bbq chicken", "Eggs": ["egg", "frittata", "omelette", "omelet", "quiche"],
"chicken skewer"], "Legumes": ["bean", "lentil", "chickpea", "tofu", "tempeh", "edamame"],
"Fried": ["fried chicken", "chicken cutlet", "chicken schnitzel", "Grains": ["rice", "quinoa", "barley", "farro", "oat", "grain"],
"crispy chicken"], "Cheese": ["cheese", "ricotta", "mozzarella", "parmesan", "cheddar"],
"Stewed": ["chicken stew", "chicken soup", "coq au vin",
"chicken curry", "chicken braise"],
},
},
"Beef": {
"keywords": ["main:Beef"],
"subcategories": {
"Ground Beef": ["ground beef", "hamburger", "meatball", "meatloaf",
"bolognese", "burger"],
"Steak": ["steak", "sirloin", "ribeye", "flank steak",
"filet mignon", "t-bone"],
"Roasts": ["beef roast", "pot roast", "brisket", "prime rib",
"chuck roast"],
"Stews": ["beef stew", "beef braise", "beef bourguignon",
"short ribs"],
},
},
"Pork": {
"keywords": ["main:Pork"],
"subcategories": {
"Chops": ["pork chop", "pork loin", "pork cutlet"],
"Pulled/Slow": ["pulled pork", "pork shoulder", "pork butt",
"carnitas", "slow cooker pork"],
"Sausage": ["sausage", "bratwurst", "chorizo", "andouille",
"Italian sausage"],
"Ribs": ["pork ribs", "baby back ribs", "spare ribs",
"pork belly"],
},
},
"Fish": {
"keywords": ["main:Fish"],
"subcategories": {
"Salmon": ["salmon", "smoked salmon", "gravlax"],
"Tuna": ["tuna", "albacore", "ahi"],
"White Fish": ["cod", "tilapia", "halibut", "sole", "snapper",
"flounder", "bass"],
"Shellfish": ["shrimp", "prawn", "crab", "lobster", "scallop",
"mussel", "clam", "oyster"],
},
},
"Pasta": ["main:Pasta"],
"Vegetables": {
"keywords": ["main:Vegetables"],
"subcategories": {
"Root Veg": ["potato", "sweet potato", "carrot", "beet",
"parsnip", "turnip"],
"Leafy": ["spinach", "kale", "chard", "arugula",
"collard greens", "lettuce"],
"Brassicas": ["broccoli", "cauliflower", "brussels sprouts",
"cabbage", "bok choy"],
"Nightshades": ["tomato", "eggplant", "bell pepper", "zucchini",
"squash"],
"Mushrooms": ["mushroom", "portobello", "shiitake", "oyster mushroom",
"chanterelle"],
},
},
"Eggs": ["main:Eggs"],
"Legumes": ["main:Legumes"],
"Grains": ["main:Grains"],
"Cheese": ["main:Cheese"],
}, },
}, },
} }
def _get_category_def(domain: str, category: str) -> list[str] | dict | None:
"""Return the raw category definition, or None if not found."""
return DOMAINS.get(domain, {}).get("categories", {}).get(category)
def get_domain_labels() -> list[dict]: def get_domain_labels() -> list[dict]:
"""Return [{id, label}] for all available domains.""" """Return [{id, label}] for all available domains."""
return [{"id": k, "label": v["label"]} for k, v in DOMAINS.items()] return [{"id": k, "label": v["label"]} for k, v in DOMAINS.items()]
def get_keywords_for_category(domain: str, category: str) -> list[str]: def get_keywords_for_category(domain: str, category: str) -> list[str]:
"""Return the keyword list for the category (top-level, covers all subcategories). """Return the keyword list for a domain/category pair, or [] if not found."""
domain_data = DOMAINS.get(domain, {})
For flat categories returns the list directly. categories = domain_data.get("categories", {})
For nested categories returns the 'keywords' key. return categories.get(category, [])
Returns [] if category or domain not found.
"""
cat_def = _get_category_def(domain, category)
if cat_def is None:
return []
if isinstance(cat_def, list):
return cat_def
return cat_def.get("keywords", [])
def category_has_subcategories(domain: str, category: str) -> bool:
"""Return True when a category has a subcategory level."""
cat_def = _get_category_def(domain, category)
if not isinstance(cat_def, dict):
return False
return bool(cat_def.get("subcategories"))
def get_subcategory_names(domain: str, category: str) -> list[str]:
"""Return subcategory names for a category, or [] if none exist."""
cat_def = _get_category_def(domain, category)
if not isinstance(cat_def, dict):
return []
return list(cat_def.get("subcategories", {}).keys())
def get_keywords_for_subcategory(domain: str, category: str, subcategory: str) -> list[str]:
"""Return keyword list for a specific subcategory, or [] if not found."""
cat_def = _get_category_def(domain, category)
if not isinstance(cat_def, dict):
return []
return cat_def.get("subcategories", {}).get(subcategory, [])
def get_category_names(domain: str) -> list[str]: def get_category_names(domain: str) -> list[str]:

View file

@ -84,27 +84,15 @@ class ElementClassifier:
name = ingredient_name.lower().strip() name = ingredient_name.lower().strip()
if not name: if not name:
return IngredientProfile(name="", elements=[], source="heuristic") return IngredientProfile(name="", elements=[], source="heuristic")
c = self._store._cp
row = self._store._fetch_one( row = self._store._fetch_one(
f"SELECT * FROM {c}ingredient_profiles WHERE name = ?", (name,) "SELECT * FROM ingredient_profiles WHERE name = ?", (name,)
) )
if row: if row:
return self._row_to_profile(row) return self._row_to_profile(row)
return self._heuristic_profile(name) return self._heuristic_profile(name)
def classify_batch(self, names: list[str]) -> list[IngredientProfile]: def classify_batch(self, names: list[str]) -> list[IngredientProfile]:
"""Classify multiple names in one DB round-trip, falling back to heuristics.""" return [self.classify(n) for n in names]
if not names:
return []
normalised = [n.lower().strip() for n in names]
c = self._store._cp
placeholders = ",".join("?" * len(normalised))
rows = self._store._fetch_all(
f"SELECT * FROM {c}ingredient_profiles WHERE name IN ({placeholders})",
tuple(normalised),
)
by_name = {r["name"]: self._row_to_profile(r) for r in rows}
return [by_name.get(n) or self._heuristic_profile(n) for n in normalised]
def identify_gaps(self, profiles: list[IngredientProfile]) -> list[str]: def identify_gaps(self, profiles: list[IngredientProfile]) -> list[str]:
"""Return element names that have no coverage in the given profile list.""" """Return element names that have no coverage in the given profile list."""

View file

@ -13,7 +13,6 @@ Walmart is kept inline until cf-core adds Impact network support:
Links are always generated (plain URLs are useful even without affiliate IDs). Links are always generated (plain URLs are useful even without affiliate IDs).
Walmart links only appear when WALMART_AFFILIATE_ID is set. Walmart links only appear when WALMART_AFFILIATE_ID is set.
Instacart and Walmart are US/CA-only; other locales get Amazon only.
""" """
from __future__ import annotations from __future__ import annotations
@ -24,26 +23,18 @@ from urllib.parse import quote_plus
from circuitforge_core.affiliates import wrap_url from circuitforge_core.affiliates import wrap_url
from app.models.schemas.recipe import GroceryLink from app.models.schemas.recipe import GroceryLink
from app.services.recipe.locale_config import get_locale
logger = logging.getLogger(__name__) logger = logging.getLogger(__name__)
def _amazon_link(ingredient: str, locale: str) -> GroceryLink: def _amazon_fresh_link(ingredient: str) -> GroceryLink:
cfg = get_locale(locale)
q = quote_plus(ingredient) q = quote_plus(ingredient)
domain = cfg["amazon_domain"] base = f"https://www.amazon.com/s?k={q}&i=amazonfresh"
dept = cfg["amazon_grocery_dept"] return GroceryLink(ingredient=ingredient, retailer="Amazon Fresh", url=wrap_url(base, "amazon"))
base = f"https://www.{domain}/s?k={q}&{dept}"
retailer = "Amazon" if locale != "us" else "Amazon Fresh"
return GroceryLink(ingredient=ingredient, retailer=retailer, url=wrap_url(base, "amazon"))
def _instacart_link(ingredient: str, locale: str) -> GroceryLink: def _instacart_link(ingredient: str) -> GroceryLink:
q = quote_plus(ingredient) q = quote_plus(ingredient)
if locale == "ca":
base = f"https://www.instacart.ca/store/s?k={q}"
else:
base = f"https://www.instacart.com/store/s?k={q}" base = f"https://www.instacart.com/store/s?k={q}"
return GroceryLink(ingredient=ingredient, retailer="Instacart", url=wrap_url(base, "instacart")) return GroceryLink(ingredient=ingredient, retailer="Instacart", url=wrap_url(base, "instacart"))
@ -59,28 +50,26 @@ def _walmart_link(ingredient: str, affiliate_id: str) -> GroceryLink:
class GroceryLinkBuilder: class GroceryLinkBuilder:
def __init__(self, tier: str = "free", has_byok: bool = False, locale: str = "us") -> None: def __init__(self, tier: str = "free", has_byok: bool = False) -> None:
self._tier = tier self._tier = tier
self._locale = locale
self._locale_cfg = get_locale(locale)
self._walmart_id = os.environ.get("WALMART_AFFILIATE_ID", "").strip() self._walmart_id = os.environ.get("WALMART_AFFILIATE_ID", "").strip()
def build_links(self, ingredient: str) -> list[GroceryLink]: def build_links(self, ingredient: str) -> list[GroceryLink]:
"""Build grocery deeplinks for a single ingredient. """Build grocery deeplinks for a single ingredient.
Amazon link is always included, routed to the user's locale domain. Amazon Fresh and Instacart links are always included; wrap_url handles
Instacart and Walmart are only shown where they operate (US/CA). affiliate ID injection (or returns a plain URL if none is configured).
wrap_url handles affiliate ID injection for supported programs. Walmart requires WALMART_AFFILIATE_ID to be set (Impact network uses a
path-based redirect that doesn't degrade cleanly to a plain URL).
""" """
if not ingredient.strip(): if not ingredient.strip():
return [] return []
links: list[GroceryLink] = [_amazon_link(ingredient, self._locale)] links: list[GroceryLink] = [
_amazon_fresh_link(ingredient),
if self._locale_cfg["instacart"]: _instacart_link(ingredient),
links.append(_instacart_link(ingredient, self._locale)) ]
if self._walmart_id:
if self._locale_cfg["walmart"] and self._walmart_id:
links.append(_walmart_link(ingredient, self._walmart_id)) links.append(_walmart_link(ingredient, self._walmart_id))
return links return links

Some files were not shown because too many files have changed in this diff Show more