Align docs around LLM-driven scenario generation

MODEL_MANIFEST.json

@@ -3,10 +3,11 @@
     {
       "id": "Qwen/Qwen2.5-7B-Instruct",
       "parameters_billions": 7.616,
-      "purpose": "Optional bounded decision-node enrichment",
-      "required": false
+      "purpose": "Bounded adaptive scenario generation",
+      "required_for_full_experience": true,
+      "runtime_fallback_available": true
     }
   ],
   "maximum_allowed_parameters_billions": 31.999,
-  "fallback": "Deterministic Python simulation content; no fallback model"
+  "fallback": "Deterministic Python simulation content for resilience; no fallback model"
 }