fix: use configured port from server_address for local Ollama connections (fixes #332)

When is_local=True, the Ollama host URL previously hardcoded port 11434,
ignoring the port specified in provider_server_address in config.ini.
Users who need to run Ollama on a non-default port (e.g. because 11434
is already in use) had no way to configure this without editing source code.

Now the port is extracted from provider_server_address when present,
falling back to 11434 if only a hostname is given.

sources/llm_provider.py

@@ -165,7 +165,11 @@ class Provider:
         Use local or remote Ollama server to generate text.
         """
         thought = ""
-        host = f"{self.internal_url}:11434" if self.is_local else f"http://{self.server_address}"
+        if self.is_local:
+            server_port = self.server_address.split(":")[-1] if ":" in str(self.server_address) else "11434"
+            host = f"{self.internal_url}:{server_port}"
+        else:
+            host = f"http://{self.server_address}"
         client = OllamaClient(host=host)
 
         try: