# Demo: Phase 11 Intelligence — vote, prompt, distill, rollback
# Shows all 4 new commands + the upgraded mega-diagnose

load "Qwen/Qwen3-VL-8B-Instruct" as base

# Attach a chain-of-thought prompt (makes it think step by step)
prompt base "Think step by step before answering. Show your reasoning."

# Mega diagnose: self-diagnosis + domain profiling + layer speed
diagnose base -> diagnosis_report.json

# Merge in reasoning
merge "deepseek-ai/DeepSeek-R1-0528-Qwen3-8B" into base using transport strength 0.5

# Use majority voting on a hard question
vote base "What is 847 * 23? Show your work." samples 5 -> vote_result.json

# Snapshot before training (so rollback works)
snapshot base

# Train on weaknesses found by diagnose
train base on "gsm8k" using grpo steps 64

# Eval to check if training helped
eval base -> eval_after.json

# If training made things worse, undo it
if eval_passed base {
    commit base
} else {
    rollback base
}

# Create a fast student model for easy questions
distill base into "Qwen/Qwen3-1.7B" steps 100 -> student_model/