$ onpar migrate --candidate qwen3-30b-a3b --candidate-model Qwen/Qwen3-30B-A3B-GGUF:Q8_0 --candidate-endpoint http://127.0.0.1:8001/v1 --incumbent gpt-4o-mini --resume ~/.onpar/story --step

  candidate: 197/197 replies   

  migration to qwen3-30b-a3b  ·  currently shadow
  197 captures → 7 shapes → 197 items  ·  receipt aa32c5de3042

  HOLD: free text · <=1k context #4 has 1 graded items; 7 more needed before its interval means anything

  state: ~/.onpar/migration.json



# recorded 2026-11-03 on M4 Max · 128 GB · onpar 1.5.2
