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>

docs/AGENT_LOOP.md

@@ -64,7 +64,6 @@ Stdout (captured by the agent) is the report:
     "body_orientation": {"verdict": "mismatch", "ref": "female on top, facing partner", "gen": "female on bottom"},
     "clothing_state": {"verdict": "partial",  "ref": "red lace lingerie", "gen": "plain bra"}
   },
-  "prompt_used": "...",
   "_prompt_id": "…", "_report_path": "…/calib_iter003.json"
 }
 ```

docs/CALIBRATION_POLICY.md

@@ -163,7 +163,7 @@ iter6  overall=0.93  mism=0   ≥ target → STOP
     "body_orientation": {"verdict": "mismatch", "ref": "female on top, facing partner", "gen": "female on bottom"},
     "scene":         {"verdict": "match",    "ref": "dim bedroom", "gen": "dim bedroom"}
   },
-  "prompt_used": "...", "_prompt_id": "...", "_report_path": "..."
+  "_prompt_id": "...", "_report_path": "..."
 }
 ```