Make AI model configurable per feature, and split news grading/formatting models

Every AI-calling feature (content correction, the @ai modifier, quiz grading,
SEO metadata generation, the AI Usage Analyzer, and DeepSearch) can now name
its own model via admin-editable configuration, defaulting to the gateway's
default model when left blank. The gateway a feature talks to stays fixed to
the internal endpoint either way, only the model name is a knob, so the best
model can be picked per task.

Also splits the news service's shared AI grading/formatting config into two
independent endpoint/model/key pairs: reformatting no longer requires
repointing (and thereby breaking) the free, scoring-only grading model.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01FZ5x6KZTxZjbJqsEkxGbxG

tests/unit/services/quiz/grading.py

@@ -134,7 +134,7 @@ def test_grade_free_text_uses_a_valid_verdict(monkeypatch):
 def test_grade_free_text_passes_the_answering_key_through(monkeypatch):
     seen = {}
 
-    def capture(api_key, system, text, timeout):
+    def capture(api_key, system, text, timeout, model=None):
         seen["api_key"] = api_key
         return json.dumps({"score": 1.0}), None