feat!: standardize base_url for inference

Completes #3732 by removing runtime URL transformations and requiring
users to provide full URLs in configuration. All providers now use
'base_url' consistently and respect the exact URL provided without
appending paths like /v1 or /openai/v1 at runtime.

Add unit test to enforce URL standardization across remote inference providers (verifies all use 'base_url' field with HttpUrl | None type)

BREAKING CHANGE: Users must update configs to include full URL paths
(e.g., http://localhost:11434/v1 instead of http://localhost:11434).

Signed-off-by: Charlie Doern <cdoern@redhat.com>

src/llama_stack/providers/remote/inference/vllm/vllm.py

@@ -39,12 +39,12 @@ class VLLMInferenceAdapter(OpenAIMixin):
 
     def get_base_url(self) -> str:
         """Get the base URL from config."""
-        if not self.config.url:
+        if not self.config.base_url:
             raise ValueError("No base URL configured")
-        return self.config.url
+        return str(self.config.base_url)
 
     async def initialize(self) -> None:
-        if not self.config.url:
+        if not self.config.base_url:
             raise ValueError(
                 "You must provide a URL in run.yaml (or via the VLLM_URL environment variable) to use vLLM."
             )