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/tests/test_transcript_correction.py

@@ -57,7 +57,7 @@ def _api_key():
     The dev venv has no GEMINI_API_KEY, and correct() returns early without one
     — which would make every assertion below pass for the wrong reason.
     """
-    with patch.object(tc.settings, "gemini_api_key", "test-key"):
+    with patch.object(tc.settings, "openai_api_key", "test-key"):
         yield