refactor(llm-api): implement clean architecture following scraper pattern

Split monolithic 1012-line main.rs into layered hexagonal architecture:
- Domain: entity types and LlmError enum
- Application: prompt building, sampler construction, tool call parsing
- Infrastructure: LlamaEngine wrapping llama-cpp-2 with isolated unsafe transmute
- Presentation: Axum handlers, middleware (auth), error chain, router
- Config: type-safe AppConfig with LazyLock
- Bootstrap: Application struct with build() + run()

Resolves build_sampler/build_sampler_params duplication.
Adds simple web chat UI at GET /.

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

src/presentation/handler/chat_ui.rs

@@ -0,0 +1,16 @@
+//! Chat UI — simple web interface for interacting with the LLM.
+
+use axum::http::{header, HeaderValue, StatusCode};
+use axum::response::{IntoResponse, Response};
+
+const HTML: &str = include_str!("chat-ui/index.html");
+
+/// GET / — serve the chat UI page.
+pub async fn chat_ui() -> Response {
+    (
+        StatusCode::OK,
+        [(header::CONTENT_TYPE, HeaderValue::from_static("text/html; charset=utf-8"))],
+        HTML,
+    )
+        .into_response()
+}