docs: update architecture description and test counts

Reflect gr.HTML info element, translate button in input column, and
updated test counts (45 total, 35 fast, 10 slow).

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

CLAUDE.md

@@ -32,11 +32,11 @@ pytest -m slow             # model tests only (CUDA only)
 
 ## Architecture
 
-**`app.py`** — Single-file application with a Google Translate-style two-column layout: left column has a static "English" dropdown and input textbox with inline clear button; right column has a searchable target language dropdown (with locale codes, e.g., "French (fr)") and output textbox with copy button. The input textbox's `info` field shows a keyboard shortcut hint and live character count (`Press Ctrl+Enter to apply · X / 2,000`), updated dynamically via `gr.update(info=...)`. Below is a Translate button that shows "Translating..." during processing. Ctrl+Enter submits from the input. Uses `@lru_cache` for lazy loading of the `google/madlad400-3b-mt` tokenizer and model (no download on import). Uses `float16` on CUDA, `float32` on CPU. MPS is not supported (produces garbage output with T5 models). Translation prepends a language token with a space to the input text (e.g., `<2fr> Hello`) before tokenization and generation. The `@spaces.GPU` decorator allocates GPU on HF Spaces infrastructure.
+**`app.py`** — Single-file application with a Google Translate-style two-column layout: left column has a static "English" dropdown, input textbox with inline clear button, a `gr.HTML` element showing a keyboard shortcut hint and live character count (`Press Ctrl+Enter to apply · X / 2,000`), and the Translate button (shows "Translating..." during processing); right column has a searchable target language dropdown (with locale codes, e.g., "French (fr)") and output textbox with copy button. Ctrl+Enter submits from the input. Uses `@lru_cache` for lazy loading of the `google/madlad400-3b-mt` tokenizer and model (no download on import). Uses `float16` on CUDA, `float32` on CPU. MPS is not supported (produces garbage output with T5 models). Translation prepends a language token with a space to the input text (e.g., `<2fr> Hello`) before tokenization and generation. The `@spaces.GPU` decorator allocates GPU on HF Spaces infrastructure.
 
 **`langmap/`** — Package with `langid_mapping.py`, a hand-maintained dictionary mapping 22 Tier 1 production-ready language tokens (BLEU 35+ both directions, Section A.10) to human-readable language names. Available languages at runtime are the intersection of this mapping and the model's vocabulary.
 
-**`tests/`** — 43 tests (33 fast, 10 slow). `test_langmap.py` has 8 fast tests for language mapping validation. `test_app.py` has 25 fast tests (signatures, device fallback, UI layout including English dropdown, textbox height, inline clear, character count with limit, shortcut hint, filterable dropdown, locale codes, no title) and 10 slow tests (translation with various parameters, language mapping). Slow tests require CUDA and model download; auto-skipped without CUDA.
+**`tests/`** — 45 tests (35 fast, 10 slow). `test_langmap.py` has 8 fast tests for language mapping validation. `test_app.py` has 27 fast tests (signatures, device fallback, UI layout including English dropdown, textbox height, inline clear, character count in HTML element, shortcut hint in HTML element, translate button in input column, filterable dropdown, locale codes, no title) and 10 slow tests (translation with various parameters, language mapping). Slow tests require CUDA and model download; auto-skipped without CUDA.
 
 ## Tooling
 

README.md

@@ -38,6 +38,6 @@ The Gradio interface launches at `http://localhost:7860`.
 ruff check .             # lint
 ruff format .            # format
 ty check                 # type check
-pytest -m "not slow"     # 33 fast tests
-pytest                   # all 43 tests (slow require CUDA + model download)
+pytest -m "not slow"     # 35 fast tests
+pytest                   # all 45 tests (slow require CUDA + model download)
 ```