Add model and project credits to README

README.md

@@ -1,12 +1,31 @@
-# tsjetpiti
+<p align="center">
+  <img src="piti-icon.png" alt="tsjetpiti icon" width="132">
+</p>
 
-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**.
+<p align="center">
+  <img src="piti-logo.png" alt="tsjetpiti" width="360">
+</p>
 
-tsjet has a deliberate personality: it **always answers**, sounds confident and
-plausible, and is **hilariously, purposely wrong**. Hit **new tsjet** to wipe the
-conversation and start fresh.
+<p align="center">
+  <strong>Tiny app. Big model. Absolutely no idea what it's talking about.</strong>
+</p>
+
+<p align="center">
+  <sub>ANDROID 11+ &nbsp;&bull;&nbsp; ARM64 &nbsp;&bull;&nbsp; FULLY ON-DEVICE &nbsp;&bull;&nbsp; CONFIDENTLY WRONG</sub>
+</p>
+
+---
+
+## Meet tsjet
+
+**tsjetpiti** is a dead-simple Android chat app running an uncensored
+**Qwen3.5-2B** model entirely on your phone through embedded
+[llama.cpp](https://github.com/ggml-org/llama.cpp). No cloud inference, no
+account, and no conversation leaving the device.
+
+tsjet has one special talent: it **always answers**, sounds completely
+confident, and is **hilariously, deliberately wrong**. Hit **new tsjet** whenever
+you want to erase the evidence and start fresh.
 
 ---
 
@@ -30,9 +49,11 @@ conversation and start fresh.
 - **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-Q6_K.gguf` (~1.5 GB) is
-  **downloaded on first launch** from Hugging Face into the app's private storage.
-  It is *not* bundled in the APK. (Swap the quant in `ModelDownloader.kt`.)
+- **Model:**
+  [`Qwen3.5-2B-Uncensored-HauhauCS-Aggressive`](https://huggingface.co/HauhauCS/Qwen3.5-2B-Uncensored-HauhauCS-Aggressive)
+  in Q6_K format (~1.5 GB) is **downloaded on first launch** from Hugging Face
+  into the app's private storage. It is *not* bundled in the APK. (Swap the
+  quant in `ModelDownloader.kt`.)
 - **Persona:** set via `SYSTEM_PROMPT` in `MainActivity.kt`; sampling is a little
   hot (temp 0.9) for playful answers. The model is a Qwen3 "thinking" model, so the
   prompt disables reasoning (empty `<think></think>` prefill + `/no_think`) to keep
@@ -46,7 +67,7 @@ conversation and start fresh.
 - **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
+- **A phone:** 64-bit ARM (`arm64-v8a`), Android 11+ (minSdk 30), and enough free
   RAM to hold a ~1.5 GB Q6 model (~4 GB RAM device recommended).
 - Network on first launch to download the model.
 
@@ -80,6 +101,24 @@ manager, and tap it. First launch downloads the ~1.5 GB model over Wi-Fi.
 | Model URL / filename | `ModelDownloader.kt` |
 | Generation params (ctx, temp, tokens) | `MainActivity.kt` + `llama-jni.cpp` |
 
+## Credits
+
+tsjetpiti is small because it stands on the shoulders of some decidedly
+not-small projects:
+
+- [Qwen3.5-2B](https://huggingface.co/Qwen/Qwen3.5-2B) by the Qwen team is the
+  upstream base model.
+- [Qwen3.5-2B-Uncensored-HauhauCS-Aggressive](https://huggingface.co/HauhauCS/Qwen3.5-2B-Uncensored-HauhauCS-Aggressive)
+  by [HauhauCS](https://huggingface.co/HauhauCS) is the model variant and GGUF
+  quantization used by the app.
+- [llama.cpp](https://github.com/ggml-org/llama.cpp) by the ggml-org community
+  provides the on-device inference engine and GGUF runtime.
+- [Android](https://developer.android.com/) and
+  [Kotlin](https://kotlinlang.org/) provide the application platform and native
+  app layer.
+- [Gradle](https://gradle.org/) and [CMake](https://cmake.org/) power the Kotlin
+  and C++ build.
+
 ## TODO / notes
 
 - **Branding:** launcher icon (adaptive + legacy densities) is generated from

app/build.gradle.kts

@@ -13,10 +13,10 @@ android {
 
     defaultConfig {
         applicationId = "monster.autisme.tsjetpiti"
-        minSdk = 26
+        minSdk = 30
         targetSdk = 35
-        versionCode = 1
-        versionName = "0.1.0"
+        versionCode = 2
+        versionName = "0.1.1"
 
         // On-device LLM => 64-bit ARM only. Keeps the APK from ballooning.
         ndk {

app/src/main/assets/web/styles.css

@@ -7,6 +7,12 @@
   --bubble: #141414;
   --bubble-line: #242424;
 
+  /* Window insets (status/nav bar, cutout, keyboard) — set from Android. */
+  --inset-top: 0px;
+  --inset-right: 0px;
+  --inset-bottom: 0px;
+  --inset-left: 0px;
+
   /* Generic, corporate/IT sans stack — resolves offline on any device. */
   --font: "Segoe UI", "Helvetica Neue", Helvetica, Arial, "Liberation Sans",
           system-ui, sans-serif;
@@ -37,7 +43,8 @@ body {
   display: flex;
   align-items: center;
   justify-content: space-between;
-  padding: max(env(safe-area-inset-top), 12px) 16px 12px;
+  padding: calc(var(--inset-top) + 12px) calc(var(--inset-right) + 16px) 12px
+           calc(var(--inset-left) + 16px);
   background: var(--panel);
   border-bottom: 1px solid var(--line);
   flex: 0 0 auto;
@@ -64,7 +71,7 @@ body {
 #chat {
   flex: 1 1 auto;
   overflow-y: auto;
-  padding: 18px 16px;
+  padding: 18px calc(var(--inset-right) + 16px) 18px calc(var(--inset-left) + 16px);
   display: flex;
   flex-direction: column;
   gap: 12px;
@@ -99,7 +106,8 @@ body {
   display: flex;
   gap: 10px;
   align-items: flex-end;
-  padding: 12px 14px calc(env(safe-area-inset-bottom) + 12px);
+  padding: 12px calc(var(--inset-right) + 14px) calc(var(--inset-bottom) + 12px)
+           calc(var(--inset-left) + 14px);
   background: var(--panel);
   border-top: 1px solid var(--line);
   flex: 0 0 auto;

app/src/main/java/monster/autisme/tsjetpiti/MainActivity.kt

@@ -2,7 +2,9 @@ package monster.autisme.tsjetpiti
 
 import android.annotation.SuppressLint
 import android.app.Activity
+import android.graphics.Color
 import android.os.Bundle
+import android.view.WindowInsets
 import android.webkit.JavascriptInterface
 import android.webkit.WebSettings
 import android.webkit.WebView
@@ -32,6 +34,12 @@ class MainActivity : Activity() {
     @Volatile private var handle: Long = 0L
     @Volatile private var setupStarted = false
 
+    // Window insets (status/nav bar, cutout, keyboard) in CSS px, pushed to the page.
+    private var insetTop = 0
+    private var insetBottom = 0
+    private var insetLeft = 0
+    private var insetRight = 0
+
     companion object {
         private const val N_CTX = 4096
         private const val MAX_TOKENS = 220
@@ -55,6 +63,30 @@ class MainActivity : Activity() {
         webView = WebView(this)
         setContentView(webView)
 
+        // Edge-to-edge (default on Android 15+): draw behind the system bars, then
+        // inset the WebView by the status bar, nav bar, display cutout, and IME so
+        // none of them ever cover the chat UI (portrait or landscape).
+        window.setDecorFitsSystemWindows(false)
+        webView.setBackgroundColor(Color.BLACK)
+        // WebView.setPadding doesn't inset HTML content (Chromium sizes 100dvh to the
+        // full view), so feed the insets to CSS as variables instead. This also tracks
+        // the IME: when the keyboard shows, bottom grows and the composer rises.
+        webView.setOnApplyWindowInsetsListener { _, insets ->
+            val bars = insets.getInsets(
+                WindowInsets.Type.systemBars() or
+                    WindowInsets.Type.ime() or
+                    WindowInsets.Type.displayCutout()
+            )
+            val d = resources.displayMetrics.density
+            insetTop = (bars.top / d).toInt()
+            insetBottom = (bars.bottom / d).toInt()
+            insetLeft = (bars.left / d).toInt()
+            insetRight = (bars.right / d).toInt()
+            pushInsets()
+            insets
+        }
+        webView.requestApplyInsets()
+
         webView.settings.apply {
             javaScriptEnabled = true
             domStorageEnabled = true
@@ -63,6 +95,7 @@ class MainActivity : Activity() {
         webView.addJavascriptInterface(Bridge(), "TsjetNative")
         webView.webViewClient = object : WebViewClient() {
             override fun onPageFinished(view: WebView?, url: String?) {
+                pushInsets()   // apply insets now that the DOM exists
                 if (!setupStarted) {
                     setupStarted = true
                     startSetup()
@@ -80,6 +113,16 @@ class MainActivity : Activity() {
         }
     }
 
+    /** Push the current window insets to the page as CSS variables on :root. */
+    private fun pushInsets() {
+        val js = "var s=document.documentElement.style;" +
+            "s.setProperty('--inset-top','${insetTop}px');" +
+            "s.setProperty('--inset-bottom','${insetBottom}px');" +
+            "s.setProperty('--inset-left','${insetLeft}px');" +
+            "s.setProperty('--inset-right','${insetRight}px');"
+        runOnUiThread { webView.evaluateJavascript(js, null) }
+    }
+
     private fun startSetup() = setupExecutor.execute {
         try {
             callJs("onStatus", "Waking the tsjet…")