feat(models): add OCI Generative AI provider for Google Gemini on OCI

Adds first-class support for Google Gemini models hosted on Oracle Cloud
Infrastructure (OCI) Generative AI service — a native Google × OCI model
partnership that makes Gemini available directly through OCI's inference
endpoints.

Key design points:
- Subclasses BaseLlm following the anthropic_llm.py pattern
- Uses the OCI Python SDK directly (no LangChain dependency)
- Optional dependency: pip install google-adk[oci]
- Supports API_KEY, INSTANCE_PRINCIPAL, and RESOURCE_PRINCIPAL auth
- Both non-streaming (_call_oci) and streaming (_call_oci_stream) paths
  share setup code via _build_chat_details(); streaming collects OCI's
  OpenAI-compatible SSE events in a thread pool (asyncio.to_thread) and
  yields partial then final LlmResponse
- Registers google.gemini-* (and other OCI-hosted) model patterns in
  LLMRegistry via optional try/except in models/__init__.py
- 37 unit tests (fully mocked, no OCI account needed)
- 10 integration tests (skipped when OCI_COMPARTMENT_ID is unset)

Supported models: google.gemini-*, google.gemma-*, meta.llama-*,
  mistralai.*, xai.grok-*, nvidia.*

Author: fede-kamel

pyproject.toml

@@ -130,6 +130,7 @@ optional-dependencies.extensions = [
   "pypika>=0.50",                                                    # For crewai->chromadb dependency
   "toolbox-adk>=1,<2",                                               # For tools.toolbox_toolset.ToolboxToolset
 ]
+optional-dependencies.oci = [ "oci>=2.170.0" ] # For OCI Generative AI model support
 optional-dependencies.otel-gcp = [ "opentelemetry-instrumentation-google-genai>=0.6b0,<1" ]
 optional-dependencies.slack = [ "slack-bolt>=1.22" ]
 optional-dependencies.test = [

src/google/adk/models/__init__.py

@@ -31,6 +31,7 @@
   from .gemma_llm import Gemma3Ollama
   from .google_llm import Gemini
   from .lite_llm import LiteLlm
+  from .oci_genai_llm import OCIGenAILlm
 
 __all__ = [
     'ApigeeLlm',
@@ -41,6 +42,7 @@
     'Gemma3Ollama',
     'LLMRegistry',
     'LiteLlm',
+    'OCIGenAILlm',
 ]
 
 _LAZY_PROVIDERS: dict[str, tuple[list[str], str]] = {
@@ -78,6 +80,18 @@
         ],
         'lite_llm',
     ),
+    'OCIGenAILlm': (
+        [
+            r'meta\.llama-.*',
+            r'google\.gemini-.*',
+            r'google\.gemma-.*',
+            r'xai\.grok-.*',
+            r'mistralai\.mistral-.*',
+            r'mistralai\.mixtral-.*',
+            r'nvidia\..*',
+        ],
+        'oci_genai_llm',
+    ),
 }
 
 for _name, (_patterns, _module) in _LAZY_PROVIDERS.items():