Merge commit '2e111f615c845a8e8a551e8e1f2b83846f89e334' into feat/organization-byok-inheritance

Author: icecrasher321

.github/workflows/test-build.yml

@@ -123,6 +123,9 @@ jobs:
       - name: Repo audits
         run: bun run check:audits
 
+      - name: Verify docs manifest is in sync
+        run: bun run docs-manifest:check
+
       - name: Migration safety (zero-downtime) audit
         run: |
           if [ "${{ github.event_name }}" = "pull_request" ]; then

apps/desktop/build/entitlements.mac.plist

@@ -9,5 +9,15 @@
          even after the user grants access in System Settings. -->
     <key>com.apple.security.device.audio-input</key>
     <true/>
+    <!-- The agent browser joins real meetings (Google Meet, Zoom web): its
+         getUserMedia grant is gated on the OS grant, and without this key the
+         Hardened Runtime denies the camera no matter what the user allowed. -->
+    <key>com.apple.security.device.camera</key>
+    <true/>
+    <!-- WebAuthn hybrid transport (passkey on the user's phone via QR) rides
+         Bluetooth proximity; without this the QR option silently never
+         completes in signed builds. -->
+    <key>com.apple.security.device.bluetooth</key>
+    <true/>
   </dict>
 </plist>

apps/desktop/electron-builder.yml

@@ -58,7 +58,9 @@ mac:
   # macOS refuses to show the microphone prompt at all — it kills the process —
   # unless the bundle declares why it wants the device.
   extendInfo:
-    NSMicrophoneUsageDescription: Sim uses your microphone for voice input in Chat.
+    NSMicrophoneUsageDescription: Sim uses your microphone for voice input in Chat and for meetings you join in the built-in browser.
+    NSCameraUsageDescription: Sim uses your camera for meetings you join in the built-in browser, such as Google Meet.
+    NSBluetoothAlwaysUsageDescription: Sim uses Bluetooth to complete passkey sign-ins with a nearby phone in the built-in browser.
   entitlements: build/entitlements.mac.plist
   entitlementsInherit: build/entitlements.mac.plist
   notarize: true

apps/desktop/src/main/browser-agent/cdp.test.ts

@@ -2,8 +2,9 @@ import { describe, expect, it, vi } from 'vitest'
 
 vi.mock('electron', () => import('@/test/electron-mock'))
 
-import { WebContentsView, type WebFrameMain } from 'electron'
+import { nativeImage, type WebContents, WebContentsView, type WebFrameMain } from 'electron'
 import {
+  captureScreenshot,
   clickAt,
   ensureInstrumented,
   evaluateInIsolatedFrame,
@@ -482,3 +483,89 @@ describe('browser-agent CDP theme', () => {
     })
   })
 })
+
+/**
+ * The browser panel shows a LIVE view, so a capture must not perturb the page.
+ * Chromium serves `clip` by applying device-emulation params to the widget and
+ * syncing visual properties, which the user sees as the page rescaling and
+ * snapping back. Resolution is bounded on the returned image instead.
+ */
+describe('browser-agent screenshot capture', () => {
+  function captureFixture(imageSize: { width: number; height: number } | null) {
+    const contents = new WebContentsView().webContents
+    vi.mocked(contents.debugger.sendCommand).mockImplementation((method: string) => {
+      if (method === 'Page.getLayoutMetrics') {
+        return Promise.resolve({ cssLayoutViewport: { clientWidth: 2048, clientHeight: 1024 } })
+      }
+      if (method === 'Page.captureScreenshot') return Promise.resolve({ data: 'c2lt' })
+      return Promise.resolve(undefined)
+    })
+    const resized = {
+      toJPEG: vi.fn(() => Buffer.from('resized')),
+    }
+    // Shared module-level mock: without this, a later fixture reads the
+    // earlier test's decoded image.
+    vi.mocked(nativeImage.createFromBuffer).mockReset()
+    vi.mocked(nativeImage.createFromBuffer).mockReturnValue({
+      isEmpty: vi.fn(() => imageSize === null),
+      getSize: vi.fn(() => imageSize ?? { width: 0, height: 0 }),
+      resize: vi.fn(() => resized),
+      toJPEG: vi.fn(() => Buffer.alloc(0)),
+    } as unknown as ReturnType<typeof nativeImage.createFromBuffer>)
+    return { contents, resized }
+  }
+
+  function screenshotParams(contents: WebContents): Record<string, unknown> {
+    const call = vi
+      .mocked(contents.debugger.sendCommand)
+      .mock.calls.find(([method]) => method === 'Page.captureScreenshot')
+    if (!call) throw new Error('no capture was requested')
+    return call[1] as Record<string, unknown>
+  }
+
+  it('never sends a clip, which would emulate the live page for the capture', async () => {
+    const { contents } = captureFixture({ width: 4096, height: 2048 })
+
+    await captureScreenshot(contents)
+
+    expect(screenshotParams(contents)).not.toHaveProperty('clip')
+  })
+
+  /**
+   * A 2048px CSS viewport bounded to 1024px is scale 0.5, and the capture
+   * arrives at device resolution (4096px on a 2x display). The resize is what
+   * lands the image on the CSS-relative size the coordinate contract
+   * (cssX = imageX / scale) assumes.
+   */
+  it('downscales the returned image to the CSS-relative size', async () => {
+    const { contents, resized } = captureFixture({ width: 4096, height: 2048 })
+
+    const shot = await captureScreenshot(contents)
+
+    const image = vi.mocked(nativeImage.createFromBuffer).mock.results[0].value
+    expect(image.resize).toHaveBeenCalledWith({ width: 1024, height: 512, quality: 'good' })
+    expect(resized.toJPEG).toHaveBeenCalled()
+    expect(shot).toEqual({
+      dataUrl: `data:image/jpeg;base64,${Buffer.from('resized').toString('base64')}`,
+      scale: 0.5,
+    })
+  })
+
+  it('skips the re-encode when the capture already matches the target size', async () => {
+    const { contents } = captureFixture({ width: 1024, height: 512 })
+
+    const shot = await captureScreenshot(contents)
+
+    const image = vi.mocked(nativeImage.createFromBuffer).mock.results[0].value
+    expect(image.resize).not.toHaveBeenCalled()
+    expect(shot).toEqual({ dataUrl: 'data:image/jpeg;base64,c2lt', scale: 0.5 })
+  })
+
+  it('returns the raw capture when the image cannot be decoded', async () => {
+    const { contents } = captureFixture(null)
+
+    const shot = await captureScreenshot(contents)
+
+    expect(shot).toEqual({ dataUrl: 'data:image/jpeg;base64,c2lt', scale: 0.5 })
+  })
+})