Initial project scaffold: dataset schema, 31 seed training examples, Mineflayer bot framework, and 7-phase roadmap

- IDEA.md: project scope (Minecraft ops AI assistant via qwen3-coder LoRA/SFT)
- PLAN.md: complete roadmap with prior art analysis, architecture, phased plan, dev server docs
- data/schema.json: training example JSON Schema with negative_output support
- data/processed/seed_dataset.jsonl: 31 validated examples from repair code, prayer logs, session history
- data/validate_dataset.py: schema validator with summary statistics
- ingame/: Mineflayer bot framework (test_connect, spawn_bots, aware_bots with full event logging)
- Directory structure for knowledge/, eval/, training/, agent/ (Phase 1.3+ work)

.gitignore

@@ -0,0 +1,47 @@
+# Python
+__pycache__/
+*.py[cod]
+*.egg-info/
+*.egg
+dist/
+build/
+.venv/
+venv/
+*.so
+
+# Node / Mineflayer
+node_modules/
+package-lock.json
+
+# Training checkpoints (large binary files)
+training/checkpoints/
+*.bin
+*.safetensors
+*.pt
+*.gguf
+
+# Eval results (regenerable)
+eval/results/
+
+# Secrets and credentials
+GITEA_API.md
+*.env
+.env.*
+credentials.json
+*.key
+*.pem
+
+# OS / editor
+.DS_Store
+Thumbs.db
+*.swp
+*.swo
+*~
+.idea/
+.vscode/
+
+# Logs
+*.log
+
+# Session-specific (kept locally, not shared)
+SESSION.md