fix(grok_video): set quality_score=0.9 to stop under-ranking

Every premium video provider sets quality_score (seedance 0.95, runway /
higgsfield 0.9) so the scorer ranks them above stock/local options.
grok_video had none, so it was scored only on supports/stability flags
despite shipping native synchronized audio (lip-sync + dialogue + SFX
in a single generation pass) — likely under-ranked.

Set quality_score=0.9, on par with the other native-audio premium
providers. Add a regression pinning the field and its get_info() surface.

Refs: docs/REVIEW-image-to-video-voice.md §8 #6

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

tools/video/grok_video.py

@@ -83,6 +83,11 @@ class GrokVideo(BaseTool):
     ]
     not_good_for = ["offline generation"]
     fallback_tools = ["veo_video", "runway_video", "kling_video", "minimax_video"]
+    # Native synchronized audio (lip-sync + dialogue + SFX in one pass) puts
+    # Grok on par with the other premium providers; without a quality_score the
+    # scorer only counted supports/stability flags, under-ranking it relative to
+    # seedance (0.95) / runway / higgsfield (0.9). See lib/scoring.py.
+    quality_score = 0.9
 
     input_schema = {
         "type": "object",