LarsandClaude Opus 4.6 de5b8cbf15
Deploy Development / deploy (push) Successful in 52s
Build Test / lint-backend (push) Successful in 0s
Build Test / build-frontend (push) Successful in 15s
fix: CRITICAL - Use question ID (not type) for LLM communication
ROOT ARCHITECTURAL CHANGE:
Multiple questions with same type are now supported!

Problem:
- question_augmenter used q.type as LLM key
- If two questions had type="unsicherheit":
  - LLM saw duplicate keys: "- unsicherheit: [ja/nein]"
  - Could only answer one
  - Signals were ambiguous

Solution:
- Use question.id as LLM key (unique by design)
- Keep type for normalization logic
- Map id → type internally

Backend question_augmenter.py:
- format_question_list() now uses q.id as key
- Format: "- **q21**: [ja/nein]  # Question text"
- Question text as comment for LLM context

Backend workflow_executor.py:
- Removed type→id mapping (no longer needed)
- decision_signals now keyed by id (from LLM)
- Build id→type catalog for normalization
- NormalizedSignal.question_type stores id (not type!)
- End Node template: signal_{id} directly available

Flow:
1. Questions sent to LLM: "- q21: [ja/nein]  # Ist Protein unsicher?"
2. LLM answers: "- q21: nein"
3. Normalization: id→type lookup for spectrum/rules
4. Template: {{ node_4.signal_q21 }} = "nein"

Example (TWO unsicherheit questions):
Questions:
- q21: type=unsicherheit, question="Ist Protein unsicher?"
- q22: type=unsicherheit, question="Ist Energie unsicher?"

LLM Prompt:
```
## Entscheidungsfragen
- **q21**: [ja/nein]  # Ist Protein unsicher?
- **q22**: [ja/nein]  # Ist Energie unsicher?
```

LLM Response:
```
- q21: nein
- q22: ja
```

Template:
```
{{ node_4.signal_q21 }} → "nein"
{{ node_4.signal_q22 }} → "ja"
```

BREAKING CHANGE:
- Old workflows with decision_signals keyed by type will break
- Need to re-execute workflows after update

Issue: Cannot have multiple questions with same type
Version: 0.9p (workflow module)
Part 3: End Node Template Engine - ARCHITECTURAL FIX

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-04-09 21:13:50 +02:00
2026-04-04 14:05:50 +02:00
2026-04-04 14:05:50 +02:00

BodyTrack

Körpervermessung & Körperfett Tracker – selbst gehostet, PWA-fähig.

Features

  • Umfänge & Caliper-Messungen (4 Methoden) mit Verlauf
  • Abgeleitete Werte: WHR, WHtR, FFMI, Magermasse
  • Verlaufsdiagramme (Gewicht, KF%, Taille, …)
  • KI-Interpretationen via Claude (Anthropic)
  • Fortschrittsfotos mit Galerie
  • PDF & CSV Export
  • PWA – installierbar auf iPhone-Homescreen
  • Alle Daten lokal auf deinem Server (SQLite)

Schnellstart

1. Voraussetzungen

# Docker & Docker Compose installieren (Ubuntu)
curl -fsSL https://get.docker.com | sh
sudo usermod -aG docker $USER
# Neu einloggen

2. Projekt klonen / kopieren

mkdir ~/bodytrack && cd ~/bodytrack
# Dateien hierher kopieren

3. API Key setzen

cp .env.example .env
nano .env
# ANTHROPIC_API_KEY=sk-ant-... eintragen

4. Starten

docker compose up -d

App läuft auf: http://DEINE-IP:3000

5. iPhone – Als App installieren

  1. Safari öffnen → http://DEINE-IP:3000
  2. Teilen-Button (□↑) → „Zum Home-Bildschirm"
  3. BodyTrack erscheint als App-Icon

6. Von außen erreichbar (optional)

# Tailscale (einfachste Lösung – VPN zu deinem MiniPC)
curl -fsSL https://tailscale.com/install.sh | sh
sudo tailscale up
# Dann: http://TAILSCALE-IP:3000

Updates

docker compose pull
docker compose up -d --build

Backup

# Datenbank & Fotos sichern
docker run --rm -v bodytrack-data:/data -v bodytrack-photos:/photos \
  -v $(pwd):/backup alpine \
  tar czf /backup/bodytrack_backup_$(date +%Y%m%d).tar.gz /data /photos

Konfiguration

Variable Beschreibung Standard
ANTHROPIC_API_KEY Claude API Key (für KI-Analyse) –

Ports

Port Dienst
3000 Frontend (Nginx)
8000 Backend API (intern)
S
Description
No description provided
Readme
17 MiB
0 Stars 1 Watchers 0 Forks
2026-04-14 11:40:32 +02:00
Languages
Python 59.7%
JavaScript 38.1%
CSS 0.9%
PLpgSQL 0.9%
Shell 0.4%