Add OpenAI/LiteLLM provider support with settings UI

- Add openai/ provider module with translator, client, convert, request/response translators
- Add shared provider/ types (ConversationMessage, MessageRole, ProviderConfig enum)
- Wire OpenAI-compatible provider dispatch alongside Bedrock in response_stream.rs
- Add ai.openai.* settings (enabled, base_url, api_key, model, models)
- Add OpenAI/LiteLLM settings page with model fetch, picker, and config UI
- Extend model menu items and llms.rs to surface LiteLLM models
- Update WARP.md with OpenAI provider architecture docs

app/src/ai/execution_profiles/model_menu_items.rs

@@ -81,6 +81,7 @@ fn make_item_fields<A: Action + Clone>(
     };
     let is_using_api_key = is_using_api_key_for_provider(&llm.provider, app);
     let is_bedrock = llm.provider == LLMProvider::Bedrock;
+    let is_litellm = llm.provider == LLMProvider::LiteLLM;
 
     let mut item = if let Some(position_id_fn) = position_id_fn {
         let position_id = position_id_fn(&llm.id);
@@ -94,6 +95,10 @@ fn make_item_fields<A: Action + Clone>(
                         Icon::BedrockLogo
                             .to_galaxyui_icon(appearance.theme().foreground())
                             .finish()
+                    } else if is_litellm {
+                        Icon::OpenAILogo
+                            .to_galaxyui_icon(appearance.theme().foreground())
+                            .finish()
                     } else if is_using_api_key {
                         Icon::Key
                             .to_galaxyui_icon(appearance.theme().foreground())