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_describe_api.json

@@ -19,8 +19,7 @@
       "keep_loaded": true,
       "auto_download": true,
       "report_dir": "/media/p5/Comfyui/output/calibrator",
-      "run_tag": "seed",
-      "prompt_used": ""
+      "run_tag": "seed"
     },
     "_meta": { "title": "Qwen3-VL Describe (first pass)" }
   }