Scaffold tsjetpiti: on-device Qwen3.5-2B chat app

Android app that runs an uncensored Qwen3.5-2B GGUF fully on-device via an
embedded llama.cpp (pinned b10333, built through the NDK) behind a barebones
WebView chat UI. Model is downloaded on first launch. "new tsjet" wipes the
conversation and resets the KV cache.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

README.md

@@ -0,0 +1,79 @@
+# tsjetpiti
+
+A dead-simple Android chat app that runs an **uncensored Qwen3.5-2B** model
+fully **on-device** via an embedded [llama.cpp](https://github.com/ggml-org/llama.cpp),
+wrapped in an **extremely barebones WebView UI**.
+
+Talk to the tsjet. Hit **new tsjet** to wipe the conversation and start fresh.
+
+---
+
+## How it works
+
+```
+┌─────────────────────────────────────────┐
+│ MainActivity (Kotlin)                    │
+│   • full-screen WebView  ── UI ──────────┼──> assets/web/{index.html,app.js,styles.css}
+│   • JS bridge "TsjetNative"              │        (the whole chat UI, ~200 lines)
+│   • model download + prompt formatting   │
+└──────────────┬──────────────────────────┘
+               │ JNI (LlamaBridge)
+               ▼
+┌─────────────────────────────────────────┐
+│ cpp/llama-jni.cpp  →  libtsjet.so        │
+│   talks to llama.cpp C API (pinned)      │
+└─────────────────────────────────────────┘
+```
+
+- **Inference:** llama.cpp compiled from source (pinned tag `b10333`) through the
+  NDK. Pulled automatically at build time via CMake `FetchContent` — no submodule
+  to init.
+- **Model:** `Qwen3.5-2B-Uncensored-HauhauCS-Aggressive-Q4_K_M.gguf` (~1.2 GB) is
+  **downloaded on first launch** from Hugging Face into the app's private storage.
+  It is *not* bundled in the APK.
+- **Conversation:** the web layer holds the full history and sends it each turn;
+  native rebuilds the ChatML prompt and clears the KV cache before every reply, so
+  "new tsjet" is just: clear JS state + reset cache.
+
+## Requirements
+
+- **A build machine** with the Android SDK + NDK. Easiest path: open the project
+  in **Android Studio** (it will offer to install the matching NDK `27.2.12479018`
+  and CMake `3.22.1`).
+- **A phone:** 64-bit ARM (`arm64-v8a`), Android 8.0+ (minSdk 26), and enough free
+  RAM to hold a ~1.2 GB Q4 model (~3–4 GB RAM device recommended).
+- Network on first launch to download the model.
+
+## Build
+
+```bash
+./gradlew assembleDebug
+```
+
+The APK lands in `app/build/outputs/apk/debug/`. Or just Run ▶ from Android Studio.
+
+> First build compiles llama.cpp from source, so it takes a while and needs
+> network (CMake fetches the pinned llama.cpp).
+
+## Where things live
+
+| What | Where |
+|------|-------|
+| Chat UI (HTML/CSS/JS) | `app/src/main/assets/web/` |
+| Android glue + model download | `app/src/main/java/monster/autisme/tsjetpiti/` |
+| Native llama.cpp bridge | `app/src/main/cpp/llama-jni.cpp` |
+| Pinned llama.cpp version | `app/src/main/cpp/CMakeLists.txt` (`GIT_TAG b10333`) |
+| Model URL / filename | `ModelDownloader.kt` |
+| Generation params (ctx, temp, tokens) | `MainActivity.kt` + `llama-jni.cpp` |
+
+## TODO / notes
+
+- **Logo:** juli is on it. The header logo is a placeholder `🐟` in
+  `assets/web/index.html` (`#logo`), and there's no launcher icon yet — add an
+  `android:icon` in `AndroidManifest.xml` + a `mipmap` when the artwork is ready.
+- The model may emit `<think>…</think>` blocks; the UI strips them from the
+  display and from history (`stripThink` in `app.js`).
+- Bumping the llama.cpp tag? Re-check the C API calls in `llama-jni.cpp` against
+  that tag's `include/llama.h` — it uses the raw C API directly.
+- Not yet compiled end-to-end in CI; first real build is the acid test for the
+  native layer.