fix: use 127.0.0.1 instead of localhost for local provider base URLs (#73)

On dual-stack hosts (notably macOS), `localhost` resolves to both ::1
and 127.0.0.1 with IPv6 tried first. Local LLM servers (Ollama, vLLM,
LM Studio) installed via the standard scripts bind IPv4 only, so the
IPv6 connection attempt fails immediately and Happy Eyeballs fallback
to IPv4 isn't reliably triggered for connection-refused errors,
producing spurious "Configured local provider offline" warnings in
the daemon even when the server is up and reachable via curl.

Companion to librefang/librefang#3112 which fixes the hardcoded URL
constants in the main repo. After both land, existing installs pick
up the fix on their next registry sync.

providers/lmstudio.toml

@@ -5,7 +5,7 @@
 id = "lmstudio"
 display_name = "LM Studio"
 api_key_env = "LMSTUDIO_API_KEY"
-base_url = "http://localhost:1234/v1"
+base_url = "http://127.0.0.1:1234/v1"
 key_required = false
 
 [[models]]

providers/ollama.toml

@@ -5,7 +5,7 @@
 id = "ollama"
 display_name = "Ollama"
 api_key_env = "OLLAMA_API_KEY"
-base_url = "http://localhost:11434/v1"
+base_url = "http://127.0.0.1:11434/v1"
 key_required = false
 
 [[models]]

providers/vllm.toml

@@ -5,7 +5,7 @@
 id = "vllm"
 display_name = "vLLM"
 api_key_env = "VLLM_API_KEY"
-base_url = "http://localhost:8000/v1"
+base_url = "http://127.0.0.1:8000/v1"
 key_required = false
 
 [[models]]