Merge pull request 'STT improvements: hotkey, button position, and hover tooltip' (#2) from feature/stt into main

Reviewed-on: #2

app/src/components/terminal/SttButton.tsx

@@ -1,15 +1,17 @@
 import { useCallback, useEffect, useRef, useState } from "react";
-import { useSTT } from "../../hooks/useSTT";
+import type { SttState } from "../../hooks/useSTT";
 import * as commands from "../../lib/tauri-commands";
 
 interface Props {
-  sessionId: string;
+  state: SttState;
-  sendInput: (sessionId: string, data: string) => Promise<void>;
+  error: string | null;
+  onToggle: () => Promise<void>;
+  onCancel: () => Promise<void>;
 }
 
-export default function SttButton({ sessionId, sendInput }: Props) {
+export default function SttButton({ state, error, onToggle, onCancel }: Props) {
-  const { state, error, toggle, cancelRecording } = useSTT(sessionId, sendInput);
   const [elapsed, setElapsed] = useState(0);
+  const [hovered, setHovered] = useState(false);
   const timerRef = useRef<ReturnType<typeof setInterval> | null>(null);
 
   // Track recording duration
@@ -40,17 +42,17 @@ export default function SttButton({ sessionId, sendInput }: Props) {
         // Container start failed, toggle will still attempt transcription
       }
     }
-    await toggle();
+    await onToggle();
-  }, [state, toggle]);
+  }, [state, onToggle]);
 
   const handleContextMenu = useCallback(
     (e: React.MouseEvent) => {
       e.preventDefault();
       if (state === "recording") {
-        cancelRecording();
+        onCancel();
       }
     },
-    [state, cancelRecording],
+    [state, onCancel],
   );
 
   const formatTime = (seconds: number) => {
@@ -60,38 +62,43 @@ export default function SttButton({ sessionId, sendInput }: Props) {
   };
 
   return (
-    <div className="absolute bottom-4 left-4 z-50 flex items-center gap-2">
+    <div className="absolute bottom-1 left-1 z-50 flex items-center gap-2">
-      <button
+      <div className="relative">
-        onClick={handleClick}
+        <button
-        onContextMenu={handleContextMenu}
+          onClick={handleClick}
-        disabled={state === "transcribing"}
+          onContextMenu={handleContextMenu}
-        className={`w-8 h-8 rounded-full flex items-center justify-center transition-all cursor-pointer ${
+          onMouseDown={(e) => e.preventDefault()} // prevent stealing focus from terminal
+          onMouseEnter={() => setHovered(true)}
+          onMouseLeave={() => setHovered(false)}
+          disabled={state === "transcribing"}
+          className={`w-8 h-8 rounded-full flex items-center justify-center transition-all cursor-pointer ${
           state === "recording"
             ? "bg-[#f85149] text-white shadow-lg animate-pulse"
             : state === "transcribing"
               ? "bg-[#1f2937] text-[#58a6ff] border border-[#30363d] opacity-80"
               : "bg-[#1f2937]/80 text-[#8b949e] border border-[#30363d] hover:text-[#e6edf3] hover:bg-[#2d3748]"
         }`}
-        title={
+        >
-          state === "recording"
+          {state === "transcribing" ? (
-            ? "Click to stop and transcribe (right-click to cancel)"
+            <svg className="w-4 h-4 animate-spin" viewBox="0 0 24 24" fill="none">
-            : state === "transcribing"
+              <circle cx="12" cy="12" r="10" stroke="currentColor" strokeWidth="2" opacity="0.25" />
-              ? "Transcribing..."
+              <path d="M12 2a10 10 0 0 1 10 10" stroke="currentColor" strokeWidth="2" strokeLinecap="round" />
-              : "Speech to text"
+            </svg>
-        }
+          ) : (
-      >
+            <svg className="w-4 h-4" viewBox="0 0 24 24" fill="currentColor">
-        {state === "transcribing" ? (
+              <path d="M12 14c1.66 0 3-1.34 3-3V5c0-1.66-1.34-3-3-3S9 3.34 9 5v6c0 1.66 1.34 3 3 3z" />
-          <svg className="w-4 h-4 animate-spin" viewBox="0 0 24 24" fill="none">
+              <path d="M17 11c0 2.76-2.24 5-5 5s-5-2.24-5-5H5c0 3.53 2.61 6.43 6 6.92V21h2v-3.08c3.39-.49 6-3.39 6-6.92h-2z" />
-            <circle cx="12" cy="12" r="10" stroke="currentColor" strokeWidth="2" opacity="0.25" />
+            </svg>
-            <path d="M12 2a10 10 0 0 1 10 10" stroke="currentColor" strokeWidth="2" strokeLinecap="round" />
+          )}
-          </svg>
+        </button>
-        ) : (
+        {hovered && state !== "recording" && (
-          <svg className="w-4 h-4" viewBox="0 0 24 24" fill="currentColor">
+          <div className="absolute bottom-full left-0 mb-1.5 px-2 py-1 text-[11px] leading-snug text-[#e6edf3] bg-[#21262d] border border-[#30363d] rounded shadow-lg whitespace-nowrap pointer-events-none">
-            <path d="M12 14c1.66 0 3-1.34 3-3V5c0-1.66-1.34-3-3-3S9 3.34 9 5v6c0 1.66 1.34 3 3 3z" />
+            {state === "transcribing" ? "Transcribing..." : (
-            <path d="M17 11c0 2.76-2.24 5-5 5s-5-2.24-5-5H5c0 3.53 2.61 6.43 6 6.92V21h2v-3.08c3.39-.49 6-3.39 6-6.92h-2z" />
+              <>Speech to text <kbd className="ml-1 px-1 py-0.5 text-[10px] bg-[#0d1117] border border-[#30363d] rounded font-mono">Ctrl+Shift+M</kbd></>
-          </svg>
+            )}
+          </div>
         )}
-      </button>
+      </div>
       {state === "recording" && (
         <span className="text-xs text-[#f85149] font-mono bg-[#1f2937] px-2 py-0.5 rounded border border-[#30363d]">
           {formatTime(elapsed)}

app/src/components/terminal/TerminalView.tsx

@@ -7,6 +7,7 @@ import { openUrl } from "@tauri-apps/plugin-opener";
 import "@xterm/xterm/css/xterm.css";
 import { useTerminal } from "../../hooks/useTerminal";
 import { useAppState } from "../../store/appState";
+import { useSTT } from "../../hooks/useSTT";
 import SttButton from "./SttButton";
 import { awsSsoRefresh } from "../../lib/tauri-commands";
 import { UrlDetector } from "../../lib/urlDetector";
@@ -27,6 +28,9 @@ export default function TerminalView({ sessionId, active }: Props) {
   const { sendInput, pasteImage, resize, onOutput, onExit } = useTerminal();
   const setTerminalHasSelection = useAppState(s => s.setTerminalHasSelection);
   const sttEnabled = useAppState(s => s.appSettings?.stt?.enabled);
+  const stt = useSTT(sessionId, sendInput);
+  const sttToggleRef = useRef(stt.toggle);
+  sttToggleRef.current = stt.toggle;
 
   const ssoBufferRef = useRef("");
   const ssoTriggeredRef = useRef(false);
@@ -102,6 +106,11 @@ export default function TerminalView({ sessionId, active }: Props) {
         }
         return false; // prevent xterm from processing this key
       }
+      // Ctrl+Shift+M toggles speech-to-text recording
+      if (event.type === "keydown" && event.ctrlKey && event.shiftKey && event.key === "M") {
+        sttToggleRef.current();
+        return false;
+      }
       return true;
     });
 
@@ -427,7 +436,7 @@ export default function TerminalView({ sessionId, active }: Props) {
         {isAutoFollow ? "▼ Following" : "▽ Paused"}
       </button>
       {/* STT mic button - bottom left */}
-      {sttEnabled && <SttButton sessionId={sessionId} sendInput={sendInput} />}
+      {sttEnabled && <SttButton state={stt.state} error={stt.error} onToggle={stt.toggle} onCancel={stt.cancelRecording} />}
       {/* Jump to Current - bottom right, when scrolled up */}
       {!isAtBottom && (
         <button