fix(oci): convert image_url to camelCase imageUrl for OCI vision requests

OCI Generative AI expects camelCase field names. The SDK transforms
message roles and content types but passed image_url through as-is,
causing 400 errors on Command A Vision with inline images.

Added integration test that sends a 1x1 red PNG to Command A Vision
and verifies the model correctly identifies the color.

Fixes cohere-ai#760

Author: fede-kamel

src/cohere/oci_client.py

@@ -720,6 +720,9 @@ def transform_request_to_oci(
                         if isinstance(item, dict) and "type" in item:
                             transformed_item = item.copy()
                             transformed_item["type"] = item["type"].upper()
+                            # OCI expects camelCase: image_url → imageUrl
+                            if "image_url" in transformed_item:
+                                transformed_item["imageUrl"] = transformed_item.pop("image_url")
                             transformed_content.append(transformed_item)
                         else:
                             transformed_content.append(item)

tests/test_oci_client.py

@@ -185,6 +185,37 @@ def test_chat_v2(self):
         self.assertIsNotNone(response)
         self.assertIsNotNone(response.message)
 
+    def test_chat_vision_v2(self):
+        """Test vision with inline image on Command A Vision."""
+        import base64, struct, zlib
+
+        # Create a minimal 1x1 red PNG
+        raw = b'\x00\xff\x00\x00'
+        compressed = zlib.compress(raw)
+        def chunk(ctype, data):
+            c = ctype + data
+            return struct.pack('>I', len(data)) + c + struct.pack('>I', zlib.crc32(c) & 0xffffffff)
+        ihdr = struct.pack('>IIBBBBB', 1, 1, 8, 2, 0, 0, 0)
+        png = b'\x89PNG\r\n\x1a\n' + chunk(b'IHDR', ihdr) + chunk(b'IDAT', compressed) + chunk(b'IEND', b'')
+        img_b64 = base64.b64encode(png).decode()
+
+        response = self.client.chat(
+            model="command-a-vision",
+            messages=[{
+                "role": "user",
+                "content": [
+                    {"type": "text", "text": "What color is this image? Reply with one word."},
+                    {"type": "image_url", "image_url": {"url": f"data:image/png;base64,{img_b64}"}},
+                ],
+            }],
+        )
+
+        self.assertIsNotNone(response)
+        self.assertIsNotNone(response.message)
+        self.assertTrue(len(response.message.content) > 0)
+        # The 1x1 red pixel should be identified as red
+        self.assertIn("red", response.message.content[0].text.lower())
+
     def test_chat_stream_v2(self):
         """Test streaming chat with v2 client."""
         events = []