Trim dead inputs: drop fp16 precision and prompt_used

fp16 offers nothing over bf16 for these models (removed from the quant dropdown;
loader still tolerant if passed). prompt_used was metadata-only — removed from the
node inputs, report payload/markdown, the bridge, and the example workflows.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

workflow/workflow_api.json

@@ -76,7 +76,6 @@
       "auto_download": true,
       "report_dir": "/media/p5/Comfyui/output/calibrator",
       "run_tag": "",
-      "prompt_used": "",
       "reference_description": ""
     },
     "_meta": { "title": "Qwen3-VL Image Judge (Calibrator)" }