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_gemini_helper.py

@@ -34,12 +34,13 @@ def test_minimal_thinking_by_default_and_usage_lands_in_the_sink():
     models = _FakeModels()
     a, b = _patched(models)
     sink = {}
-    tok = gemini.collect_usage(sink)
+    from app.internal import llm
+    tok = llm.collect_usage(sink)
     try:
         with a, b:
             assert gemini.generate_json("m1", "p", purpose="correlation") == {"action": "link"}
     finally:
-        gemini.reset_usage(tok)
+        llm.reset_usage(tok)
     assert models.configs == [{"thinking_level": "minimal"}]
     assert sink == {"correlation:m1": {"calls": 1, "in": 1200, "out": 30, "thinking": 0}}