feat: add /screen slash command with tab-completion and screen capture

.github/workflows/pr-build-validation.yml

@@ -11,7 +11,7 @@ on:
 jobs:
   build:
     name: Build Validation
-    runs-on: ubuntu-latest
+    runs-on: macos-latest
     steps:
       - name: Checkout repository
         uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd  # v6.0.2

CLAUDE.md

@@ -56,13 +56,15 @@ The UI morphs between two states: a compact spotlight-style input bar → an exp
 - **`App.tsx`** — orchestrates all state: messages, streaming, window resizing via ResizeObserver + Tauri `setSize()`
 - **`hooks/useOllama.ts`** — Tauri Channel-based streaming hook; emits `Token`, `Done`, `Cancelled`, `Error` variants
 - **`view/ConversationView.tsx`** — smart auto-scroll (pins to bottom unless user scrolls up)
-- **`view/AskBarView.tsx`** — auto-expanding textarea (max 144px), morphs logo size
+- **`view/AskBarView.tsx`** — auto-expanding textarea (max 144px), morphs logo size, renders slash command tab-completion suggestions
 - **`components/ChatBubble.tsx`** — markdown rendering via Streamdown (rehype-sanitize for XSS protection)
+- **`config/commands.ts`** — slash command registry: defines supported commands and the `SCREEN_CAPTURE_PLACEHOLDER` sentinel used to show a loading tile in chat while a `/screen` capture is in flight
 
 ### Backend (`src-tauri/src/`)
 
 - **`lib.rs`** — app setup: converts window to NSPanel (fullscreen overlay), registers tray, spawns hotkey listener, intercepts close events (hides instead of quits)
 - **`commands.rs`** — `ask_ollama` Tauri command: streams newline-delimited JSON from Ollama, sends chunks via Tauri Channel
+- **`screenshot.rs`** — `capture_full_screen_command` Tauri command: uses CoreGraphics FFI (`CGWindowListCreateImage`) to capture all displays excluding Thuki's own windows, writes a JPEG to a temp dir, and returns the path
 - **`activator.rs`** — Core Graphics event tap watching for double-tap Control key (400ms window, 600ms cooldown); prompts for Accessibility permission, retries up to 6×
 
 ### Sandbox (`sandbox/`)
@@ -102,6 +104,6 @@ Do not consider the task done if either step produces any warnings or errors. Fi
 
 ## Key Design Constraints
 
-- **macOS only** — uses NSPanel, Core Graphics event taps, macOS Command key
+- **macOS only** — uses NSPanel, Core Graphics event taps, macOS Control key
 - **Privacy-first** — Ollama runs locally; Docker sandbox drops all capabilities and isolates network
 - **Accessibility permission required** — hotkey listener uses a CGEventTap at session level

README.md

@@ -59,7 +59,8 @@ Most AI tools require accounts, API keys, or subscriptions that bill you per tok
 - **Conversation history:** persist and revisit past conversations across sessions
 - **Fully local LLM:** powered by Ollama; no API keys, no accounts, no cost per query
 - **Isolated sandbox:** optionally run models in a hardened Docker container with capability dropping, read-only volumes, and localhost-only networking
-- **Image input:** paste or drag screenshots directly into the chat
+- **Image input:** paste or drag images and screenshots directly into the chat
+- **Screen capture:** type `/screen` to instantly capture your entire screen and attach it to your question as context
 - **Privacy-first:** zero-trust architecture, all data stays on your device
 
 ## Getting Started
@@ -203,7 +204,7 @@ The big leap: from answering questions to taking action.
 
 - **Internet search:** let Thuki look things up in real time, not just reason from its training data
 - **Tool integrations via [MCP](https://modelcontextprotocol.io/):** connect Thuki to Gmail, Slack, Discord, Google Calendar, and any other MCP-compatible service; ask it to draft a reply, summarize a thread, or schedule a meeting without ever leaving your current app
-- **Slash commands:** type `/summarize`, `/translate`, `/explain`, `/rewrite`, and more to instantly trigger built-in prompts without typing a full question
+- **More slash commands:** `/screen` is live; `/summarize`, `/translate`, `/explain`, `/rewrite`, and more are on the way to instantly trigger built-in prompts without typing a full question
 
 ### Better AI Control
 
@@ -219,7 +220,7 @@ More flexibility over the model powering Thuki.
 Give Thuki more to work with.
 
 - **Voice input:** dictate your question instead of typing
-- **Auto-capture screen context:** activate Thuki and have it automatically read the active window or selected region as context
+- **Auto-capture screen context:** activate Thuki and have it automatically read the active window or selected region as context (partial: `/screen` captures the full screen today; targeted region capture is next)
 - **File and document drop:** drag a PDF, image, or text file directly into Thuki as context for your question
 
 ---

docs/commands.md

@@ -0,0 +1,19 @@
+# Commands
+
+Commands are typed at the start of a message using the `/` prefix. Press `/` to open the command suggestion menu, then Tab to complete or Enter to select.
+
+## /screen
+
+Captures your screen and attaches it as context for the current message.
+
+**Usage:** `/screen [optional message]`
+
+**Examples:**
+- `/screen`: sends a screenshot with no additional message
+- `/screen what is this error?`: attaches a screenshot and asks the question
+
+**Behavior:** The screenshot is taken the moment you press Enter. Thuki's own window is excluded from the capture: no flicker, no hide. The image appears in your message bubble exactly like a pasted screenshot.
+
+**Limit:** One `/screen` capture per message. You may also attach up to 3 images manually (paste, drag, or the camera button) for a total of 4 images per message.
+
+**Permission:** Requires Screen Recording permission. On first use, macOS will prompt you to grant it. If denied, Thuki cannot capture the screen. Grant access in System Settings > Privacy & Security > Screen Recording.

src-tauri/src/images.rs

@@ -32,8 +32,8 @@ const MAX_DIMENSION: u32 = 1920;
 /// for vision model consumption.
 const JPEG_QUALITY: u8 = 85;
 
-/// Maximum number of images allowed per message.
-pub const MAX_IMAGES_PER_MESSAGE: usize = 3;
+/// Maximum number of images allowed per message (3 manual + 1 /screen = 4).
+pub const MAX_IMAGES_PER_MESSAGE: usize = 4;
 
 /// Resolves the root images directory: `<base_dir>/images/`.
 pub fn images_root(base_dir: &Path) -> PathBuf {
@@ -471,8 +471,8 @@ mod tests {
     }
 
     #[test]
-    fn max_images_per_message_is_three() {
-        assert_eq!(MAX_IMAGES_PER_MESSAGE, 3);
+    fn max_images_per_message_is_four() {
+        assert_eq!(MAX_IMAGES_PER_MESSAGE, 4);
     }
 
     #[test]

src-tauri/src/lib.rs

@@ -607,6 +607,8 @@ pub fn run() {
             images::cleanup_orphaned_images_command,
             #[cfg(not(coverage))]
             screenshot::capture_screenshot_command,
+            #[cfg(not(coverage))]
+            screenshot::capture_full_screen_command,
             notify_overlay_hidden,
             set_window_frame
         ])