feat: add remote vLLM support with provider abstraction layer

- LLMClient Protocol for provider-agnostic inference
- VLLMClient for OpenAI-compatible /v1/chat/completions API
- LLM client factory with provider routing (ollama/vllm)
- VLLMConfig with VLLM_* environment variable loading
- Updated extractor worker with health check and provider switching
- Updated event classifier to use LLMClient protocol
- Helm values for vLLM configuration
- 18 unit tests + 6 property-based tests
- Full backward compatibility preserved

services/extractor/client.py

@@ -155,6 +155,19 @@ class OllamaClient:
         if self._owns_client:
             await self._http.aclose()
 
+    async def call_llm(
+        self,
+        prompts: dict[str, str],
+        json_schema: dict[str, object],
+        document_text: str = "",
+    ) -> ExtractionAttempt:
+        """Public LLM client interface — delegates to _call_ollama().
+
+        Satisfies the LLMClient protocol so OllamaClient can be used
+        interchangeably with VLLMClient.
+        """
+        return await self._call_ollama(prompts, json_schema, document_text)
+
     async def extract(
         self,
         document_text: str,