feat: image paste (Ctrl+V) and drag-and-drop into terminal

scripts/build.mjs

@@ -93,6 +93,7 @@ console.log('\n[build] content-hash cache busting');
     'ralph-wizard.js',
     'api-client.js',
     'subagent-windows.js',
+    'image-input.js',
     'vendor/xterm-zerolag-input.js',
   ];
   const manifest = {};

src/web/public/image-input.js

@@ -0,0 +1,143 @@
+/**
+ * Image Input Mixin - Clipboard paste and drag-and-drop image support
+ *
+ * For paste: intercepts Ctrl+V at the xterm keyboard level, creates a temporary
+ * hidden contenteditable div ("paste trap"), lets the browser's native paste fill
+ * it, then checks for image data. This works on HTTP (no secure context needed).
+ *
+ * For drag-and-drop: listens on the terminal container for file drops.
+ *
+ * @dependency app.js (uses global `app` for sendInput, activeSessionId, showToast)
+ * @dependency panels-ui.js (provides showToast)
+ */
+
+Object.assign(CodemanApp.prototype, {
+
+  initImageInput() {
+    // Drag-and-drop handlers on terminal container
+    const container = document.getElementById('terminalContainer');
+    if (!container) return;
+
+    container.addEventListener('dragover', (e) => {
+      e.preventDefault();
+      if (e.dataTransfer && e.dataTransfer.types.includes('Files')) {
+        container.classList.add('drag-active');
+      }
+    });
+
+    container.addEventListener('dragleave', (e) => {
+      if (!container.contains(e.relatedTarget)) {
+        container.classList.remove('drag-active');
+      }
+    });
+
+    container.addEventListener('drop', (e) => {
+      e.preventDefault();
+      container.classList.remove('drag-active');
+
+      if (!this.activeSessionId) return;
+      if (!e.dataTransfer || !e.dataTransfer.files.length) return;
+
+      const imageFiles = Array.from(e.dataTransfer.files).filter((f) => f.type.startsWith('image/'));
+      if (imageFiles.length === 0) {
+        this.showToast('Only image files are supported', 'error');
+        return;
+      }
+      this._uploadAndInsertImages(imageFiles);
+    });
+  },
+
+  // Called from customKeyEventHandler in terminal-ui.js on Ctrl+V keydown.
+  // Creates a hidden paste trap, lets the browser paste into it, then inspects
+  // the result for images. Works on plain HTTP (no Clipboard API needed).
+  _handleImagePaste() {
+    const self = this;
+
+    // Create a hidden contenteditable div to receive the paste
+    const trap = document.createElement('div');
+    trap.contentEditable = 'true';
+    trap.style.cssText = 'position:fixed;left:-9999px;top:0;width:1px;height:1px;opacity:0;overflow:hidden';
+    document.body.appendChild(trap);
+    trap.focus();
+
+    // Listen for the paste event on our trap
+    trap.addEventListener('paste', function(e) {
+      e.stopPropagation();
+
+      // Check for images in clipboard items
+      var imageFiles = [];
+      var items = e.clipboardData && e.clipboardData.items;
+      if (items) {
+        for (var i = 0; i < items.length; i++) {
+          if (items[i].type.startsWith('image/')) {
+            var blob = items[i].getAsFile();
+            if (blob) imageFiles.push(blob);
+          }
+        }
+      }
+
+      // Clean up the trap
+      setTimeout(function() {
+        if (trap.parentNode) trap.parentNode.removeChild(trap);
+        // Refocus the terminal
+        if (self.terminal) self.terminal.focus();
+      }, 0);
+
+      if (imageFiles.length > 0) {
+        e.preventDefault();
+        self._uploadAndInsertImages(imageFiles);
+      } else {
+        // No image -- extract text and send to terminal
+        var text = e.clipboardData ? e.clipboardData.getData('text/plain') : '';
+        e.preventDefault();
+        if (text) self.sendInput(text);
+      }
+    });
+
+    // Trigger the browser's native paste via execCommand
+    // (this fires the paste event on our focused trap element)
+    document.execCommand('paste');
+  },
+
+  async _uploadAndInsertImages(files) {
+    const sessionId = this.activeSessionId;
+    if (!sessionId) return;
+
+    this.showToast('Uploading ' + files.length + ' image' + (files.length > 1 ? 's' : '') + '...', 'info');
+
+    const paths = [];
+    for (const file of files) {
+      try {
+        const path = await this._uploadPasteImage(sessionId, file);
+        paths.push(path);
+      } catch (err) {
+        this.showToast('Upload failed: ' + (err.message || 'unknown error'), 'error');
+      }
+    }
+
+    if (paths.length > 0) {
+      const pathStr = paths.join(' ');
+      await this.sendInput(pathStr);
+      this.showToast(paths.length + ' image' + (paths.length > 1 ? 's' : '') + ' ready', 'success');
+    }
+  },
+
+  async _uploadPasteImage(sessionId, file) {
+    const form = new FormData();
+    form.append('image', file);
+
+    const resp = await fetch('/api/sessions/' + sessionId + '/paste-image', {
+      method: 'POST',
+      body: form,
+    });
+
+    if (!resp.ok) {
+      const data = await resp.json().catch(() => ({}));
+      throw new Error(data.error || 'HTTP ' + resp.status);
+    }
+
+    const data = await resp.json();
+    return data.path;
+  },
+
+});

src/web/public/index.html

@@ -1804,5 +1804,6 @@ <h3>Save Respawn Preset</h3>
   <script defer src="ralph-wizard.js"></script>
   <script defer src="api-client.js"></script>
   <script defer src="subagent-windows.js"></script>
+  <script defer src="image-input.js"></script>
 </body>
 </html>

src/web/public/styles.css

@@ -8591,3 +8591,23 @@ kbd {
   margin-top: 4px;
   font-size: 0.7rem;
 }
+
+/* Image drag-and-drop overlay */
+#terminalContainer.drag-active {
+  outline: 2px dashed #4a9eff;
+  outline-offset: -2px;
+  position: relative;
+}
+#terminalContainer.drag-active::after {
+  content: 'Drop image here';
+  position: absolute;
+  inset: 0;
+  display: flex;
+  align-items: center;
+  justify-content: center;
+  background: rgba(74, 158, 255, 0.08);
+  color: #4a9eff;
+  font-size: 1.2rem;
+  pointer-events: none;
+  z-index: 100;
+}

src/web/public/terminal-ui.js

@@ -83,6 +83,15 @@ Object.assign(CodemanApp.prototype, {
       // Let Alt+digit pass through to browser (tab switching)
       if (ev.altKey && ev.key >= '0' && ev.key <= '9') return false;
 
+      // Ctrl+V / Cmd+V: intercept before xterm sends ^V to PTY.
+      // Route through our paste trap which handles both images and text.
+      if ((ev.ctrlKey || ev.metaKey) && ev.key === 'v' && ev.type === 'keydown') {
+        if (this.activeSessionId && this._handleImagePaste) {
+          this._handleImagePaste();
+        }
+        return false;
+      }
+
       // Shift+Enter / Ctrl+Enter: insert newline for multi-line input.
       // xterm.js sends plain \r for all Enter variants, so Claude Code (Ink) can't
       // distinguish them. We use tmux send-keys -H to send a line feed byte (0x0a)
@@ -341,6 +350,9 @@ Object.assign(CodemanApp.prototype, {
     // Welcome message
     this.showWelcome();
 
+    // Image paste and drag-and-drop support
+    this.initImageInput();
+
     // Generation counter for chunkedTerminalWrite — aborts stale writes on tab switch
     this._chunkedWriteGen = 0;
 

src/web/routes/session-routes.ts

@@ -5,7 +5,7 @@
  */
 
 import { FastifyInstance } from 'fastify';
-import { join, dirname } from 'node:path';
+import { join, dirname, extname } from 'node:path';
 import { homedir } from 'node:os';
 import { existsSync, statSync, mkdirSync, writeFileSync } from 'node:fs';
 import { execFile } from 'node:child_process';
@@ -1437,4 +1437,110 @@ export function registerSessionRoutes(
 
     return { sessions: results.slice(0, 50) };
   });
+
+  // ═══════════════════════════════════════════════════════════════
+  // Paste Image (clipboard / drag-drop upload)
+  // ═══════════════════════════════════════════════════════════════
+
+  const MAX_PASTE_IMAGE_SIZE = 10 * 1024 * 1024; // 10 MB
+  const ALLOWED_IMAGE_EXTS = new Set(['.png', '.jpg', '.jpeg', '.gif', '.webp', '.bmp', '.svg']);
+
+  app.post('/api/sessions/:id/paste-image', async (req, reply) => {
+    const { id } = req.params as { id: string };
+    const session = findSessionOrFail(ctx, id);
+
+    const contentType = req.headers['content-type'] ?? '';
+    if (!contentType.includes('multipart/form-data')) {
+      reply.code(400);
+      return createErrorResponse(ApiErrorCode.INVALID_INPUT, 'Expected multipart/form-data');
+    }
+
+    // Parse multipart boundary
+    const boundaryMatch = contentType.match(/boundary=(.+?)(?:;|$)/);
+    if (!boundaryMatch) {
+      reply.code(400);
+      return createErrorResponse(ApiErrorCode.INVALID_INPUT, 'Missing boundary');
+    }
+
+    // Collect raw body with size limit
+    const chunks: Buffer[] = [];
+    let totalSize = 0;
+    for await (const chunk of req.raw) {
+      totalSize += chunk.length;
+      if (totalSize > MAX_PASTE_IMAGE_SIZE) {
+        reply.code(413);
+        return createErrorResponse(ApiErrorCode.INVALID_INPUT, 'File too large (max 10MB)');
+      }
+      chunks.push(chunk as Buffer);
+    }
+    const body = Buffer.concat(chunks);
+
+    // Extract image from multipart body
+    const boundary = '--' + boundaryMatch[1];
+    const boundaryBuf = Buffer.from(boundary);
+    const parts: { headers: string; data: Buffer }[] = [];
+    let pos = 0;
+
+    while (pos < body.length) {
+      const start = body.indexOf(boundaryBuf, pos);
+      if (start === -1) break;
+      const afterBoundary = start + boundaryBuf.length;
+      if (body[afterBoundary] === 0x2d && body[afterBoundary + 1] === 0x2d) break;
+      const headerStart = afterBoundary + 2;
+      const headerEnd = body.indexOf(Buffer.from('\r\n\r\n'), headerStart);
+      if (headerEnd === -1) break;
+      const headers = body.subarray(headerStart, headerEnd).toString();
+      const dataStart = headerEnd + 4;
+      const nextBoundary = body.indexOf(boundaryBuf, dataStart);
+      const dataEnd = nextBoundary === -1 ? body.length : nextBoundary - 2;
+      parts.push({ headers, data: body.subarray(dataStart, dataEnd) });
+      pos = nextBoundary === -1 ? body.length : nextBoundary;
+    }
+
+    const imagePart = parts.find((p) => p.headers.includes('name="image"'));
+    if (!imagePart || imagePart.data.length === 0) {
+      reply.code(400);
+      return createErrorResponse(ApiErrorCode.INVALID_INPUT, 'No image uploaded');
+    }
+
+    // Determine extension from filename or Content-Type
+    let ext = '.png';
+    const filenameMatch = imagePart.headers.match(/filename="(.+?)"/);
+    if (filenameMatch) {
+      const origExt = extname(filenameMatch[1]).toLowerCase();
+      if (ALLOWED_IMAGE_EXTS.has(origExt)) ext = origExt;
+    }
+    const ctMatch = imagePart.headers.match(/Content-Type:\s*image\/(png|jpeg|jpg|webp|gif|bmp|svg\+xml)/i);
+    if (ctMatch) {
+      const map: Record<string, string> = {
+        png: '.png',
+        jpeg: '.jpg',
+        jpg: '.jpg',
+        webp: '.webp',
+        gif: '.gif',
+        bmp: '.bmp',
+        'svg+xml': '.svg',
+      };
+      ext = map[ctMatch[1].toLowerCase()] ?? ext;
+    }
+
+    if (!ALLOWED_IMAGE_EXTS.has(ext)) {
+      reply.code(400);
+      return createErrorResponse(
+        ApiErrorCode.INVALID_INPUT,
+        `Unsupported image type: ${ext}. Allowed: ${[...ALLOWED_IMAGE_EXTS].join(', ')}`
+      );
+    }
+
+    // Save to {workingDir}/.claude-images/
+    const imageDir = join(session.workingDir, '.claude-images');
+    if (!existsSync(imageDir)) {
+      mkdirSync(imageDir, { recursive: true });
+    }
+    const filename = `paste-${Date.now()}${ext}`;
+    const filepath = join(imageDir, filename);
+    await fs.writeFile(filepath, imagePart.data);
+
+    return { success: true, path: filepath, filename };
+  });
 }

src/web/server.ts

@@ -34,7 +34,7 @@ import fastifyStatic from '@fastify/static';
 import fastifyWebsocket from '@fastify/websocket';
 import { join, dirname } from 'node:path';
 import { fileURLToPath } from 'node:url';
-import { existsSync, mkdirSync, readFileSync, chmodSync } from 'node:fs';
+import { existsSync, mkdirSync, readFileSync, chmodSync, rmSync } from 'node:fs';
 import fs from 'node:fs/promises';
 import { execSync } from 'node:child_process';
 import { homedir, hostname as getHostname } from 'node:os';
@@ -926,6 +926,15 @@ export class WebServer extends EventEmitter {
       fileStreamManager.closeSessionStreams(sessionId);
       // Stop watching for images in this session's directory
       imageWatcher.unwatchSession(sessionId);
+      // Clean up pasted images directory for this session
+      if (killMux && session.workingDir) {
+        const pasteImageDir = join(session.workingDir, '.claude-images');
+        try {
+          rmSync(pasteImageDir, { recursive: true, force: true });
+        } catch {
+          // Best-effort cleanup
+        }
+      }
       await session.stop(killMux);
       this.sessions.delete(sessionId);
       // Only remove from state.json if we're also killing the mux session.