- Added .env loader to Maya-Eule script
- Script findet .env im parent directory
- Uses set -a/set +a for clean export
- Now works when called directly: ./crumbforest_roles/mayaeule_zero.sh
- Tested successfully with 'Was bedeutet Freundschaft?'
- Beautiful poetic response: 275 tokens ✨
🌲 Die weise Eule erwacht!
New Features:
- Maya-Eule als Waldwächter hinzugefügt
- Qdrant Memory Integration (erinnert frühere Gespräche)
- Token-Tracking mit philosophischem Kontext
- Interactive Wisdom Shell (wie Git/Tools Doktor)
Maya-Eule Weisheitsportal:
8) 🦉 Maya-Eule Weisheit
└─> Interaktive Shell mit farbigem Prompt
(🦉 Maya-Eule) user@host:path$
Befehle in der Shell:
- eule "Frage" - Stelle der Eule eine Frage
- eule_memory - Zeige Erinnerungen
- eule_tokens - Zeige Token-Verbrauch
- exit - Zurück zum Hauptmenü
Qdrant Memory Features:
- Speichert Gespräche mit Vektor-Embeddings
- Sucht ähnliche frühere Konversationen
- Bezieht Kontext in neue Antworten ein
- Persistente Erinnerung über Sessions hinweg
Token Philosophy:
"Was kostet die Frage eines Kindes?"
- Im Wald unbezahlbar
- Token lehren achtsames Fragen
- Jede Frage ist wertvoll
- Kinder lernen bewusster zu denken
System Prompt:
Maya-Eule antwortet kindgerecht, poetisch, langsam.
Sie lehrt durch Fragen, nicht nur Antworten.
Sie erinnert sich und bezieht frühere Gespräche ein.
WUHUUUU! 🌲✨
🌲 Core Philosophy: "Was kostet die Frage eines Kindes?"
In the forest: priceless. In the system: measured. Pedagogically: teaches mindful questioning.
Changes:
- Added .env.template for API configuration
• OpenRouter, Claude API, OpenAI support
• Ollama (local AI) as free alternative
• Qdrant vector database configuration
• Token budget system for mindful learning
• Parental controls (PIN, reports)
- New AI Doktor module in mission selector
• Shows configured APIs and models
• Displays token budget & tracking status
• Lists active AI characters (Waldwächter)
• Links to token logs viewer
• Guides setup if .env missing
- Extended CLAUDE.md with Token Philosophy
• Educational reasoning behind token tracking
• Why it teaches reflection and quality
• Budget system explanation
• Implementation details
Philosophy:
Token tracking isn't restriction - it's mindfulness training.
Just as we teach not to waste water/food/paper, we teach
not to waste computational resources. Children learn to:
- Think before asking
- Value AI's thinking time
- Ask better quality questions
- Research independently first
Result: More thoughtful questions, deeper learning, respect for resources.
- 5 interactive story missions in challenges category
- 🎭 Stage Builder: Build web stages with AI assistants
- 🤡 Bugsy On Stage: Interactive clown show
- 🕰️ Zeitreise: Learn Unix time with forest characters
- 🐍 Snake & Dumbo Show: Interactive character show
- 📡 Terminal Funk: Learn Bash commands with a show
Each challenge has:
- Metadata with icon, description, difficulty
- Interactive story elements
- AI assistant integration (optional)
- Activity logging
- requires_ai flag for future filtering
- Git Doktor now opens interactive shell with custom prompt
- Tools Doktor opens interactive werkzeugkasten shell
- Colored prompts in Crumbforest style (🌲 Git) and (🛠️ Werkzeug)
- Convenient aliases (gst, gd, gl, health, check)
- Stays in Crumbforest world throughout
- Exit returns to main menu
- Restructured in crumbpages-doktor.sh style
- Main menu with mission categories (Basics, Advanced, Challenges)
- Added Doktor Tools: System Check, Werkzeug Check, Git Status
- Improved navigation and UX
- .gitignore updated to allow demo logs in repo
- Qdrant omitted (as requested)
- Linux first, cross-platform compatible
- Replace associative array with indexed arrays
- Replace mapfile with while-read loop
- Now works on macOS (Bash 3.2) and Linux (all versions)
- Linux first, but cross-platform compatible
