0.6.0 training session: Oracle Bot, RL combat, Mind's Eye, multilingual pipeline

Major changes from this session:

Training:
- 0.6.0 training running: 9B on steel141 3090 Ti, 27B on rented H100 NVL
- 7,256 merged training examples (up from 3,183)
- New training data: failure modes (85), midloop messaging (27),
  prompt injection defense (29), personality (32), gold from quarantine
  bank (232), new tool examples (30), claude's own experience (10)
- All training data RCON-validated at 100% pass rate
- Bake-off: gemma3:27b 66%, qwen3.5:27b 61%, translategemma:27b 56%

Oracle Bot (Mind's Eye):
- Invisible spectator bot (mineflayer) streams world state via WebSocket
- HTML5 Canvas frontend at mind.mortdec.ai
- Real-time tool trace visualization with expandable entries
- Streaming model tokens during inference
- Gateway integration: fire-and-forget POST /trace on every tool call

Reinforcement Learning:
- Gymnasium environment wrapping mineflayer bot (minecraft_env.py)
- PPO training via Stable Baselines3 (10K param policy network)
- Behavioral cloning pretraining (97.5% accuracy on expert policy)
- Infinite training loop with auto-restart and checkpoint resume
- Bot learns combat, survival, navigation from raw experience

Bot Army:
- 8-soldier marching formation with autonomous combat
- Combat bots using mineflayer-pvp, pathfinder, armor-manager
- Multilingual prayer bots via translategemma:27b (18 languages)
- Frame-based AI architecture: LLM planner + reactive micro-scripts

Infrastructure:
- Fixed mattpc.sethpc.xyz billing gateway (API key + player list parser)
- Billing gateway now tracks all LAN traffic (LAN auto-auth)
- Gateway fallback for empty god-mode responses
- Updated mortdec.ai landing page

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

training/scripts/train_lora.py

@@ -129,8 +129,32 @@ def load_tool_dataset(path: str) -> list:
     return examples
 
 
+def load_merged_dataset(path: str) -> list:
+    """Load pre-merged training data (from merge_datasets.py).
+
+    Handles both formats:
+    - 'conversations': list of role/content dicts (already formatted)
+    - 'text': pre-formatted Qwen3 text
+    """
+    examples = []
+    with open(path) as f:
+        for line in f:
+            if not line.strip():
+                continue
+            ex = json.loads(line)
+            if "conversations" in ex or "text" in ex:
+                examples.append(ex)
+    return examples
+
+
 def load_dataset(seed_path: str, tool_path: str = None) -> list:
     """Load and merge all training datasets."""
+    # If pointing at the merged v06 file, use direct loader
+    if "merged_training" in seed_path:
+        examples = load_merged_dataset(seed_path)
+        print(f"  Merged examples: {len(examples)}")
+        return examples
+
     examples = load_seed_dataset(seed_path)
     print(f"  Seed examples:  {len(examples)}")