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_ai_timeouts.py

@@ -164,7 +164,7 @@ async def test_gemini_timeout_in_decide_falls_back_to_rules():
     def hang(model, prompt):
         raise httpx.ReadTimeout("The read operation timed out")
 
-    with patch.object(settings, "gemini_api_key", "test-key"), \
+    with patch.object(settings, "openai_api_key", "test-key"), \
          patch.object(llm_correlator, "_build_decide_prompt", lambda ctx, cands: "p"), \
          patch.object(llm_correlator, "_sync_gemini", hang):
         assert await llm_correlator.decide("c1", _corr_ctx()) is None  # None == keep the rules decision
@@ -179,7 +179,7 @@ async def test_gemini_timeout_in_transcript_correction_keeps_raw_text():
         raise httpx.ReadTimeout("The read operation timed out")
 
     text = "engine 5 respond to a structure fire at 12 main street smoke showing"
-    with patch.object(settings, "gemini_api_key", "test-key"), \
+    with patch.object(settings, "openai_api_key", "test-key"), \
          patch.object(transcript_correction, "resolve_context", AsyncMock(return_value={})), \
          patch.object(transcript_correction, "_sync_gemini", hang):
         assert await transcript_correction.correct("c1", text) == (None, None, False)

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}}
 

drb-c2-core/tests/test_llm_provider.py

@@ -0,0 +1,48 @@
+"""app/internal/llm.py: provider follows the model name (2026-11-08 consolidation)."""
+from types import SimpleNamespace
+from unittest.mock import patch
+
+from app.config import settings
+from app.internal import llm
+
+
+def test_provider_follows_model_name():
+    assert llm.provider_for("gpt-4o-mini") == "openai"
+    assert llm.provider_for("gemini-3.6-flash") == "gemini"
+
+
+def test_available_checks_the_right_key():
+    with patch.object(settings, "openai_api_key", "k"), patch.object(settings, "gemini_api_key", None):
+        assert llm.available("gpt-4o-mini") and not llm.available("gemini-3.6-flash")
+
+
+def test_defaults_are_openai():
+    assert llm.provider_for(settings.corr_cheap_model) == "openai"
+    assert llm.provider_for(settings.transcript_correction_model) == "openai"
+
+
+def test_openai_path_parses_json_and_records_usage():
+    resp = SimpleNamespace(
+        choices=[SimpleNamespace(message=SimpleNamespace(content='{"action": "new"}'))],
+        usage=SimpleNamespace(prompt_tokens=120, completion_tokens=9),
+    )
+    calls = {}
+
+    class FakeClient:
+        def __init__(self):
+            self.chat = SimpleNamespace(completions=SimpleNamespace(create=self.create))
+
+        def create(self, **kw):
+            calls.update(kw)
+            return resp
+
+    sink = {}
+    tok = llm.collect_usage(sink)
+    try:
+        with patch("app.internal.ai_clients.openai_client", FakeClient):
+            out = llm.generate_json("gpt-4o-mini", "Return JSON", purpose="correlation")
+    finally:
+        llm.reset_usage(tok)
+    assert out == {"action": "new"}
+    assert calls["response_format"] == {"type": "json_object"}
+    assert sink["correlation:gpt-4o-mini"] == {"calls": 1, "in": 120, "out": 9, "thinking": 0}

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