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/bedrock/response_translator_tests.rs

@@ -19,7 +19,15 @@ fn test_build_stream_init_has_valid_ids() {
 #[test]
 fn test_build_stream_finished_done_reason() {
     let reason = stream_finished::Reason::Done(stream_finished::Done {});
-    let event = build_stream_finished(reason, 100, 50, 20, 10, "anthropic.claude-sonnet-4-6", false);
+    let event = build_stream_finished(
+        reason,
+        100,
+        50,
+        20,
+        10,
+        "anthropic.claude-sonnet-4-6",
+        false,
+    );
 
     match event.r#type {
         Some(api::response_event::Type::Finished(finished)) => {