fix: refresh and persist RubyLLM model registry on initialization

RubyLLM uses a static bundled models.json as its model registry. New
models released by providers (e.g., gpt-5.1, gpt-5.2) are not available
until the gem is updated, causing ModelNotFoundError for self-hosted
users who configure newer models.

Refresh the model registry synchronously during Llm::Config.initialize!
to fetch the latest model list from configured providers and models.dev,
then persist with save_to_json. This runs once per process on the first
LLM request, adding ~1-2s to that request. Falls back gracefully to the
bundled registry on failure.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

lib/llm/config.rb

@@ -2,7 +2,6 @@ require 'ruby_llm'
 
 module Llm::Config
   DEFAULT_MODEL = 'gpt-4.1-mini'.freeze
-  INIT_MUTEX = Mutex.new
 
   class << self
     def initialized?
@@ -12,13 +11,9 @@ module Llm::Config
     def initialize!
       return if @initialized
 
-      INIT_MUTEX.synchronize do
-        return if @initialized
-
-        configure_ruby_llm
-        refresh_model_registry
-        @initialized = true
-      end
+      configure_ruby_llm
+      refresh_model_registry
+      @initialized = true
     end
 
     def reset!
@@ -37,12 +32,10 @@ module Llm::Config
     private
 
     def refresh_model_registry
-      Thread.new do
-        RubyLLM.models.refresh!
-        RubyLLM.models.save_to_json
-      rescue StandardError => e
-        Rails.logger.warn "Failed to refresh RubyLLM model registry: #{e.message}"
-      end
+      RubyLLM.models.refresh!
+      RubyLLM.models.save_to_json
+    rescue StandardError => e
+      Rails.logger.warn "Failed to refresh RubyLLM model registry: #{e.message}"
     end
 
     def configure_ruby_llm