refactor(chat): unify generation flow and fix tool/streaming bugs

- Unified synchronous generate() core with callback; both streaming and
  non-streaming paths run it via spawn_blocking (context: std Mutex).
- build_prompt now passes tool definitions to the template (was dead) and
  embeds assistant tool-call history as XML matching the parser format;
  fixes double <tool_response> wrap and template set-scoping bug.
- Tokenize with AddBos::Never (template owns <s>) to remove double BOS.
- Streaming: preserve inter-word spaces (per-chunk trim removed), add
  [DONE] + usage chunk, emit error events, single-shot tool_calls delta.
- Strict model validation (400 on unknown model); health/UI/README aligned
  to minicpm5-1b-fable5-v2-thinking; auth returns JSON errors; n_ctx/
  n_batch/n_threads env-configurable.
- Added 18 unit tests; cargo check/clippy/fmt clean.
- scripts/smoke-test.sh for post-deploy verification on the VPS.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>

src/presentation/handler/chat_ui.rs

@@ -9,7 +9,10 @@ const HTML: &str = include_str!("chat-ui/index.html");
 pub async fn chat_ui() -> Response {
     (
         StatusCode::OK,
-        [(header::CONTENT_TYPE, HeaderValue::from_static("text/html; charset=utf-8"))],
+        [(
+            header::CONTENT_TYPE,
+            HeaderValue::from_static("text/html; charset=utf-8"),
+        )],
         HTML,
     )
         .into_response()