fix(mobile): route terminal taps without opening the keyboard

src/web/public/terminal-ui.js

@@ -23,6 +23,7 @@
   // short window, only the app's synthetic tap-to-position mouse event should
   // reach xterm.
   const TOUCH_COMPAT_MOUSE_SUPPRESS_MS = 450;
+  const TUI_PROMPT_DEFAULT_ROWS_FROM_BOTTOM = 4;
 
   function isTerminalQueryResponse(data) {
     return TERMINAL_QUERY_RESPONSE_PATTERN.test(data) || TERMINAL_OSC_RESPONSE_PATTERN.test(data);
@@ -62,6 +63,7 @@
     shouldSuppressTerminalQueryResponse,
     USER_SCROLL_STICKY_SUPPRESS_MS,
     TOUCH_COMPAT_MOUSE_SUPPRESS_MS,
+    TUI_PROMPT_DEFAULT_ROWS_FROM_BOTTOM,
   };
   global.CODEMAN_XTERM_THEMES = CODEMAN_XTERM_THEMES;
   global.codemanCurrentXtermTheme = currentXtermTheme;
@@ -421,6 +423,8 @@ Object.assign(CodemanApp.prototype, {
       let lastTime = 0;
       let scrollFrame = null;
       let isTouching = false;
+      let touchForwardsToApp = false;
+      let touchLastX = 0;
 
       const scrollLoop = (timestamp) => {
         const dt = lastTime ? (timestamp - lastTime) / 16.67 : 1;
@@ -429,12 +433,20 @@ Object.assign(CodemanApp.prototype, {
         if (!isTouching && Math.abs(velocity) > 0.3) {
           // Momentum phase — convert pixel velocity to lines
           const lines = Math.round(velocity / cellHeight());
-          if (lines !== 0) this.terminal.scrollLines(lines);
+          if (lines !== 0) {
+            if (touchForwardsToApp) {
+              this._sendSyntheticSgrWheel(touchLastX, touchLastY, lines);
+            } else {
+              this._noteTerminalUserScroll(lines);
+              this.terminal.scrollLines(lines);
+            }
+          }
           velocity *= 0.92;
           scrollFrame = requestAnimationFrame(scrollLoop);
         } else if (!isTouching) {
           scrollFrame = null;
           velocity = 0;
+          touchForwardsToApp = false;
         } else {
           scrollFrame = requestAnimationFrame(scrollLoop);
         }
@@ -445,25 +457,37 @@ Object.assign(CodemanApp.prototype, {
 
       let didScroll = false; // track whether touchmove fired (tap vs scroll)
       let touchStartY = 0;
+      let tapStartedWithTerminalFocus = false;
       const TAP_THRESHOLD = 8; // px — ignore micro-drift to distinguish tap from scroll
       container.addEventListener(
         'touchstart',
         (ev) => {
           if (ev.touches.length === 1) {
+            touchLastX = ev.touches[0].clientX;
             touchLastY = ev.touches[0].clientY;
             touchStartY = touchLastY;
             velocity = 0;
             pixelAccum = 0;
             isTouching = true;
             didScroll = false;
+            touchForwardsToApp = this._shouldForwardTouchScrollToApp();
+            tapStartedWithTerminalFocus = this._isMobileTerminalInputFocused();
+            const touchStartIntent = this._classifyMobileTerminalTap(touchLastX, touchLastY);
+            if (touchStartIntent !== 'input') {
+              // Cancel xterm/browser focus before the compatibility click can
+              // open the OS keyboard. Content taps are re-emitted as SGR on
+              // touchend; history taps deliberately remain inert.
+              ev.preventDefault();
+              this._blurMobileTerminalInput();
+            }
             lastTime = 0;
             if (scrollFrame) {
               cancelAnimationFrame(scrollFrame);
               scrollFrame = null;
             }
           }
         },
-        { passive: true }
+        { passive: false }
       );
 
       container.addEventListener(
@@ -482,6 +506,7 @@ Object.assign(CodemanApp.prototype, {
             // fling, so a jittery tap would both position the cursor AND scroll.
             if (!didScroll) return;
             ev.preventDefault();
+            touchLastX = ev.touches[0].clientX;
             const delta = touchLastY - touchY; // positive = scroll down
             pixelAccum += delta;
             velocity = delta * 1.2;
@@ -490,8 +515,12 @@ Object.assign(CodemanApp.prototype, {
             const ch = cellHeight();
             const lines = Math.trunc(pixelAccum / ch);
             if (lines !== 0) {
-              this._noteTerminalUserScroll(lines);
-              this.terminal.scrollLines(lines);
+              if (touchForwardsToApp) {
+                this._sendSyntheticSgrWheel(touchLastX, touchY, lines);
+              } else {
+                this._noteTerminalUserScroll(lines);
+                this.terminal.scrollLines(lines);
+              }
               pixelAccum -= lines * ch;
             }
           }
@@ -507,44 +536,13 @@ Object.assign(CodemanApp.prototype, {
             scrollFrame = requestAnimationFrame(scrollLoop);
           }
           if (!didScroll && this.terminal) {
-            // ── Tap-to-position cursor ──────────────────────────────────
-            // Synthesize a click from the real touch point so the foreground app
-            // moves its cursor to the tapped cell (iOS doesn't reliably do this
-            // itself under touch-action:none). CRITICAL: only when mouse tracking
-            // is ON. xterm disables its local SelectionService while mouse events
-            // are active, so the synthetic click is forwarded to the PTY as an SGR
-            // report (cursor moves). But when tracking is OFF, that same click
-            // drives xterm's LOCAL selection (detail 1/2/3 → char/word/line) — a
-            // tap on CJK text would select & copy it instead of positioning. So
-            // gate strictly on the live mouse-tracking mode.
             const touch = ev.changedTouches && ev.changedTouches[0];
-            const mouseMode = this.terminal.modes?.mouseTrackingMode;
-            const mouseTrackingOn = !!mouseMode && mouseMode !== 'none';
             if (touch) {
               this._suppressTrustedTapMouseEvents();
-            }
-            if (touch && mouseTrackingOn) {
-              this._dispatchSyntheticTerminalClick(touch.clientX, touch.clientY);
-            } else if (touch && this._sessionUsesServerMouseStrip()) {
-              // The server strips mouse-tracking DECSETs from claude/codex/gemini
-              // output (isAltScreenStripMode, session.ts) so the wheel keeps
-              // scrolling scrollback — which leaves THIS xterm permanently at
-              // mouseTrackingMode 'none' even though the TUI on the PTY side has
-              // tracking ON and still understands SGR reports. Encode the report
-              // ourselves and send it straight to the PTY: no DOM click is
-              // dispatched, so xterm's local selection can't trigger either.
-              this._sendSyntheticSgrTap(touch.clientX, touch.clientY);
-            }
-            this._syncMobileHelperTextareaToCursor();
-            // Route subsequent typing to the right place: keep the CJK input
-            // field focused when Chinese input is on, otherwise the terminal.
-            const cjkInput = document.getElementById('cjkInput');
-            if (cjkInput?.classList.contains('cjk-input-visible')) {
-              cjkInput.focus();
-            } else {
-              this.terminal.focus();
+              this._handleMobileTerminalTap(touch, tapStartedWithTerminalFocus);
             }
           }
+          tapStartedWithTerminalFocus = false;
         },
         { passive: true }
       );
@@ -555,6 +553,8 @@ Object.assign(CodemanApp.prototype, {
           isTouching = false;
           velocity = 0;
           pixelAccum = 0;
+          touchForwardsToApp = false;
+          tapStartedWithTerminalFocus = false;
         },
         { passive: true }
       );
@@ -2629,6 +2629,163 @@ Object.assign(CodemanApp.prototype, {
     } catch {}
   },
 
+  _isMobileTerminalInputFocused() {
+    const active = document.activeElement;
+    return (
+      active === this.terminal?.textarea ||
+      active?.classList?.contains('xterm-helper-textarea') ||
+      active?.id === 'cjkInput'
+    );
+  },
+
+  /**
+   * Separate terminal input from TUI-owned content on touch devices. A hidden
+   * keyboard must not consume taps on expandable readbacks, tool results, or
+   * decision rows; those taps belong to the foreground CLI. The visible prompt
+   * row remains the deliberate keyboard target.
+   */
+  _classifyMobileTerminalTap(clientX, clientY) {
+    if (!this._terminalViewportAtBottom()) return 'history';
+
+    const pos = this._clientPointToCell(clientX, clientY);
+    if (!pos || !this.terminal) return 'input';
+
+    const mouseMode = this.terminal.modes?.mouseTrackingMode;
+    const mouseTrackingOn = !!mouseMode && mouseMode !== 'none';
+    if (!mouseTrackingOn && !this._sessionUsesServerMouseStrip()) return 'input';
+
+    // Permission/elicitation prompts own the full live terminal until answered.
+    if (document.body?.classList?.contains('terminal-action-pending')) return 'content';
+
+    const buffer = this.terminal.buffer?.active;
+    if (!buffer?.getLine) return 'input';
+
+    const rows = Math.max(1, this.terminal.rows || 1);
+    const lines = [];
+    const wrappedRows = [];
+    let hasVisibleContent = false;
+    for (let row = 0; row < rows; row++) {
+      const line = buffer.getLine(buffer.viewportY + row);
+      const text = line?.translateToString?.(true) || '';
+      lines.push(text);
+      wrappedRows.push(Boolean(line?.isWrapped));
+      if (text.trim()) hasVisibleContent = true;
+    }
+    if (!hasVisibleContent) return 'input';
+
+    const cursorRow = Math.max(0, Math.min(rows - 1, buffer.cursorY || 0));
+    const mode = this.sessions?.get(this.activeSessionId)?.mode || 'claude';
+    let promptRow = -1;
+    let menuSelectionVisible = false;
+
+    if (mode === 'opencode') {
+      if (lines[cursorRow]?.includes('\u2503')) promptRow = cursorRow;
+    } else {
+      for (let row = rows - 1; row >= 0; row--) {
+        const promptMatch = lines[row].match(/^\s*[❯›]/);
+        if (!promptMatch) continue;
+        const tail = lines[row].slice(promptMatch[0].length).trim();
+        // A highlighted numbered choice is a menu row, not an editable prompt.
+        const hasSiblingChoice = lines.some(
+          (line, choiceRow) => choiceRow !== row && /^\s+\d+[.)]\s/.test(line)
+        );
+        if (/^\d+[.)]\s/.test(tail) && hasSiblingChoice) {
+          menuSelectionVisible = true;
+          break;
+        }
+        promptRow = row;
+        break;
+      }
+    }
+
+    const tappedRow = pos.row - 1;
+    let logicalLineStart = tappedRow;
+    while (logicalLineStart > 0 && wrappedRows[logicalLineStart]) logicalLineStart--;
+    let logicalLineEnd = tappedRow;
+    while (logicalLineEnd + 1 < rows && wrappedRows[logicalLineEnd + 1]) logicalLineEnd++;
+    const tappedLine = lines.slice(logicalLineStart, logicalLineEnd + 1).join('');
+    if (
+      mode === 'claude' &&
+      /^\s*[•·]\s*Working\b.*(?:background|esc to interrupt)/i.test(tappedLine)
+    ) {
+      return 'content';
+    }
+    if (menuSelectionVisible) return 'content';
+    if (promptRow >= 0) {
+      const inputEnd = cursorRow >= promptRow ? cursorRow : promptRow;
+      if (tappedRow >= promptRow && tappedRow <= inputEnd) return 'input';
+    } else if (
+      tappedRow === cursorRow ||
+      tappedRow >=
+        Math.max(
+          0,
+          rows -
+            window.CodemanTerminalInput
+              .TUI_PROMPT_DEFAULT_ROWS_FROM_BOTTOM
+        )
+    ) {
+      // During redraws a CLI can temporarily omit its prompt marker or place
+      // the cursor above a status footer. Keep the live cursor and a stable
+      // lower-screen focus band usable without turning transcript rows above
+      // that band into keyboard targets.
+      return 'input';
+    }
+
+    return 'content';
+  },
+
+  _blurMobileTerminalInput() {
+    const active = document.activeElement;
+    if (
+      active === this.terminal?.textarea ||
+      active?.classList?.contains('xterm-helper-textarea') ||
+      active?.id === 'cjkInput'
+    ) {
+      active.blur?.();
+    }
+  },
+
+  _focusMobileTerminalInput() {
+    this._syncMobileHelperTextareaToCursor();
+    const cjkInput = document.getElementById('cjkInput');
+    if (cjkInput?.classList.contains('cjk-input-visible')) {
+      cjkInput.focus();
+    } else {
+      this.terminal?.focus();
+    }
+  },
+
+  _handleMobileTerminalTap(touch, startedWithTerminalFocus) {
+    if (!touch || !this.terminal) return 'history';
+    const intent = this._classifyMobileTerminalTap(touch.clientX, touch.clientY);
+    if (intent === 'history') {
+      this._blurMobileTerminalInput();
+      return intent;
+    }
+
+    const mouseMode = this.terminal.modes?.mouseTrackingMode;
+    const mouseTrackingOn = !!mouseMode && mouseMode !== 'none';
+    const shouldActivate = intent === 'content' || startedWithTerminalFocus;
+    if (shouldActivate && mouseTrackingOn) {
+      // xterm's mouse encoder owns live DECSET modes. The synthetic DOM click
+      // follows the same path as a desktop click.
+      this._dispatchSyntheticTerminalClick(touch.clientX, touch.clientY);
+    } else if (shouldActivate && this._sessionUsesServerMouseStrip()) {
+      // Claude/Codex/Gemini DECSETs are stripped from the browser stream, so
+      // report directly to the PTY while retaining local touch scrollback.
+      this._sendSyntheticSgrTap(touch.clientX, touch.clientY);
+    }
+
+    if (intent === 'content') {
+      // A synthetic xterm click can focus its helper textarea. Blur after the
+      // report so collapsing a readback never opens or retains the keyboard.
+      this._blurMobileTerminalInput();
+    } else {
+      this._focusMobileTerminalInput();
+    }
+    return intent;
+  },
+
   // ═══════════════════════════════════════════════════════════════
   // Synthetic tap → mouse report
   // ═══════════════════════════════════════════════════════════════
@@ -2760,6 +2917,15 @@ Object.assign(CodemanApp.prototype, {
     return this._terminalViewportAtBottom();
   },
 
+  // Claude keeps most transcript history inside its own TUI rather than xterm
+  // scrollback. On verified versions, route a touch drag through the same SGR
+  // wheel path as desktop. Codex keeps the existing local touch behavior.
+  _shouldForwardTouchScrollToApp() {
+    const session = this.sessions?.get(this.activeSessionId);
+    if (session?.mode !== 'claude') return false;
+    return this._shouldForwardWheelToApp({ shiftKey: false });
+  },
+
   // Encode wheel ticks as SGR reports (button 64 = up, 65 = down) at the pointer
   // cell. Reports are coalesced into one fire-and-forget write per ~40ms: a
   // trackpad emits dozens of wheel events per second and each send becomes a