fix: harden OCI client and preserve dual-client support

Author: fede-kamel

.fernignore

@@ -15,6 +15,7 @@ src/cohere/manually_maintained/__init__.py
 src/cohere/bedrock_client.py
 src/cohere/aws_client.py
 src/cohere/sagemaker_client.py
+src/cohere/oci_client.py
 src/cohere/client_v2.py
 mypy.ini
-src/cohere/aliases.py
+src/cohere/aliases.py

README.md

@@ -140,21 +140,21 @@ co = cohere.OciClient(
 ### Supported OCI APIs
 
 The OCI client supports the following Cohere APIs:
-- **Embed**: Full support for all embedding models (embed-english-v3.0, embed-light-v3.0, embed-multilingual-v3.0)
+- **Embed**: Full support for all embedding models (embed-english-v3.0, embed-english-light-v3.0, embed-multilingual-v3.0)
 - **Chat**: Full support with both V1 (`OciClient`) and V2 (`OciClientV2`) APIs
   - Streaming available via `chat_stream()`
   - Supports Command-R and Command-A model families
 
 ### OCI Model Availability and Limitations
 
 **Available on OCI On-Demand Inference:**
-- ✅ **Embed models**: embed-english-v3.0, embed-light-v3.0, embed-multilingual-v3.0
-- ✅ **Chat models**: command-r-08-2024, command-r-plus, command-a-03-2025
+- **Embed models**: embed-english-v3.0, embed-english-light-v3.0, embed-multilingual-v3.0
+- **Chat models**: command-r-08-2024, command-r-plus, command-a-03-2025
 
 **Not Available on OCI On-Demand Inference:**
-- ❌ **Generate API**: OCI TEXT_GENERATION models are base models that require fine-tuning before deployment
-- ❌ **Rerank API**: OCI TEXT_RERANK models are base models that require fine-tuning before deployment
-- ❌ **Multiple Embedding Types**: OCI on-demand models only support single embedding type per request (cannot request both `float` and `int8` simultaneously)
+- **Generate API**: OCI TEXT_GENERATION models are base models that require fine-tuning before deployment
+- **Rerank API**: OCI TEXT_RERANK models are base models that require fine-tuning before deployment
+- **Multiple Embedding Types**: OCI on-demand models only support single embedding type per request (cannot request both `float` and `int8` simultaneously)
 
 **Note**: To use Generate or Rerank models on OCI, you need to:
 1. Fine-tune the base model using OCI's fine-tuning service