fix: use committed model registry for RubyLLM (#14067)

RubyLLM bundles a static models.json that doesn't know about models
released after the gem was published. Self-hosted users configuring
newer models hit ModelNotFoundError.

Added a rake task that refreshes the registry from models.dev and saves
to disk. ~~Called during Docker image build so every deploy gets fresh
model data. Falls back silently to the bundled registry if models.dev is
unreachable.~~

Commit the models.json file to code so it is available across
deployments.

---------

Co-authored-by: Sojan Jose <sojan@pepalo.com>

lib/llm/config.rb

@@ -20,6 +20,7 @@ module Llm::Config
     end
 
     def with_api_key(api_key, api_base: nil)
+      initialize!
       context = RubyLLM.context do |config|
         config.openai_api_key = api_key
         config.openai_api_base = api_base
@@ -34,6 +35,7 @@ module Llm::Config
       RubyLLM.configure do |config|
         config.openai_api_key = system_api_key if system_api_key.present?
         config.openai_api_base = openai_endpoint.chomp('/') if openai_endpoint.present?
+        config.model_registry_file = Rails.root.join('config/llm_models.json').to_s
         config.logger = Rails.logger
       end
     end