AI providers: correlation decision and transcript correction move to OpenAI gpt-4o-mini

One funded account (OpenAI) now covers extraction, embeddings, summaries,
the ambiguous-scene correlation call and transcript correction; Groq stays
optional for STT. New app/internal/llm.py picks the provider from the model
name, so setting either model back to a gemini-* ID needs no code change.
Usage accounting for replay runs now covers both providers.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

drb-c2-core/app/internal/transcript_correction.py

@@ -253,11 +253,11 @@ def build_context_block(context: dict, talkgroup_name: Optional[str]) -> str:
 
 
 def _sync_gemini(model_name: str, prompt: str) -> dict:
-    from app.internal import gemini
+    from app.internal import llm
     # Correction rewrites text against vocabulary; keep a little reasoning
     # ("low") rather than the correlator's "minimal" until a replay shows
     # minimal doesn't hurt it.
-    return gemini.generate_json(model_name, prompt, purpose="correction", thinking_level="low")
+    return llm.generate_json(model_name, prompt, purpose="correction", thinking_level="low")
 
 
 async def correct(
@@ -282,7 +282,8 @@ async def correct(
     so a correction that only fixed the joined transcript would never reach the
     model on exactly the multi-transmission calls that carry the most content.
     """
-    if not settings.gemini_api_key or not settings.transcript_correction_enabled:
+    from app.internal import llm
+    if not llm.available(settings.transcript_correction_model) or not settings.transcript_correction_enabled:
         return None, None, False
 
     if len((text or "").split()) < MIN_WORDS_FOR_CORRECTION: