@@ -276,6 +276,26 @@ describe('browser-agent CDP instrumentation', () => {
     }
   })
 
+  it('releases a held button as soon as its click is aborted', async () => {
+    const contents = new WebContentsView().webContents
+    const types = () =>
+      vi.mocked(contents.debugger.sendCommand).mock.calls.map(([, params]) => toRecord(params).type)
+    vi.useFakeTimers()
+    try {
+      const controller = new AbortController()
+      const hold = { ...PRIMARY_CLICK, holdMs: 10_000 }
+      const click = clickAt(contents, 5, 6, false, hold, controller.signal)
+      await vi.advanceTimersByTimeAsync(100)
+      expect(types()).toEqual(['mousePressed'])
+
+      controller.abort()
+      await expect(click).rejects.toMatchObject({ name: 'AbortError' })
+      expect(types()).toEqual(['mousePressed', 'mouseReleased'])
+    } finally {
+      vi.useRealTimers()
+    }
+  })
+
   it('keeps a held right-click marked as the agent context menu until release', async () => {
     const contents = new WebContentsView().webContents
     vi.useFakeTimers()
 
@@ -11,7 +11,7 @@
 import type { BrowserTheme } from '@sim/browser-protocol'
 import { createLogger } from '@sim/logger'
 import { getErrorMessage } from '@sim/utils/errors'
-import { sleep } from '@sim/utils/helpers'
+import { interruptibleSleep, sleep } from '@sim/utils/helpers'
 import { isRecordLike } from '@sim/utils/object'
 import type { NativeImage, WebContents, WebFrameMain } from 'electron'
 
@@ -983,12 +983,18 @@ export function clearAgentContextMenu(contents: WebContents): void {
   agentContextClicks.delete(contents)
 }
 
+/**
+ * Clicks at viewport coordinates. `signal` ends a press-and-hold early: the click rejects with the
+ * abort reason and the button is released at once, so a cancelled or timed-out click cannot stay
+ * held into the next action. That release can still activate the control under the pointer.
+ */
 export async function clickAt(
   contents: WebContents,
   x: number,
   y: number,
   moveBeforePress = true,
-  click: PointerClick = PRIMARY_CLICK
+  click: PointerClick = PRIMARY_CLICK,
+  signal?: AbortSignal
 ): Promise<void> {
   if (moveBeforePress) await moveMouse(contents, x, y)
   const { button, clickCount, modifiers, holdMs } = click
@@ -1013,12 +1019,13 @@ export async function clickAt(
         clickCount: count,
       })
       if (holdMs > 0) {
-        await sleep(holdMs)
+        await interruptibleSleep(holdMs, signal)
         // Windows opens the context menu on release, after the hold; renew a marker a
         // press-time menu has not already consumed.
         if (button === 'right' && agentContextClicks.has(contents)) {
           agentContextClicks.set(contents, Date.now())
         }
+        signal?.throwIfAborted()
       }
       await sendInput(contents, 'Input.dispatchMouseEvent', {
         type: 'mouseReleased',
 
@@ -3223,7 +3223,7 @@ async function executeToolInner(
         try {
           assertCurrentExecution()
           assertElementActionCurrent(contents, elementId, target)
-          await cdp.clickAt(contents, x, y, false, click)
+          await cdp.clickAt(contents, x, y, false, click, signal)
           trusted = true
           activation = 'native-pointer'
         } catch (error) {
@@ -3263,7 +3263,7 @@ async function executeToolInner(
           try {
             assertCurrentExecution()
             assertElementActionCurrent(contents, elementId, target)
-            await cdp.clickAt(contents, finalTopPoint.x, finalTopPoint.y, false, click)
+            await cdp.clickAt(contents, finalTopPoint.x, finalTopPoint.y, false, click, signal)
             trusted = true
             activation = 'native-pointer'
             prepared = finalSurface
@@ -4642,7 +4642,7 @@ async function executeToolInner(
       assertCurrentExecution()
       assertActiveContents(contents, clickNavigationEpoch)
       try {
-        await cdp.clickAt(contents, x, y, true, click)
+        await cdp.clickAt(contents, x, y, true, click, signal)
       } catch (error) {
         const rescued = navigationRescue(contents, clickNavigationEpoch, urlAtDispatch, {
           trusted: true,
 
@@ -328,6 +328,17 @@ describe('dispatchKeyCombo', () => {
       .mocked(contents.debugger.sendCommand)
       .mock.calls.map(([, params]) => `${toRecord(params).type} ${toRecord(params).key}`)
     expect(keys).toEqual(['rawKeyDown Control', 'rawKeyDown Shift', 'keyUp Shift', 'keyUp Control'])
+
+    const early = new WebContentsView().webContents
+    vi.mocked(early.debugger.sendCommand).mockRejectedValueOnce(new Error('control-down lost'))
+    await expect(dispatchKeyCombo(early, parseKeyCombo('Ctrl+Shift+K'))).rejects.toMatchObject({
+      name: KeyDispatchError.name,
+    })
+    expect(
+      vi
+        .mocked(early.debugger.sendCommand)
+        .mock.calls.map(([, params]) => `${toRecord(params).type} ${toRecord(params).key}`)
+    ).toEqual(['rawKeyDown Control', 'keyUp Control'])
   })
 
   it('does not turn menu-restoration cleanup failure into a duplicate key retry signal', async () => {
 
@@ -1,7 +1,8 @@
 /**
  * Keyboard machinery for `browser_press_key` and internal key dispatch:
- * parsing "Cmd+Shift+Z"-style combos and building the trusted CDP
- * keyDown/keyUp pair. Pure logic except {@link dispatchKeyCombo}.
+ * parsing "Cmd+Shift+Z"-style combos and building the trusted CDP key events —
+ * each modifier's own press and release around the main key's keyDown/keyUp
+ * pair. Pure logic except {@link dispatchKeyCombo}.
  */
 import { getErrorMessage } from '@sim/utils/errors'
 import type { WebContents } from 'electron'
@@ -360,8 +361,9 @@ export function modifierKeyEvents(
  * Electron normally lets modified key events escape a focused WebContents to
  * application-menu accelerators. Agent input must stay inside the browser — a
  * page-level Cmd shortcut must never reload, close, or open a native window in
- * Sim — so menu handling is suspended for the complete CDP down/up pair. The
- * depth counter keeps overlapping tool calls from re-enabling it too early.
+ * Sim — so menu handling is suspended for the whole chord, modifier presses
+ * included. The depth counter keeps overlapping tool calls from re-enabling it
+ * too early.
  */
 export async function dispatchKeyCombo(contents: WebContents, combo: ParsedCombo): Promise<void> {
   const [down, up] = buildKeyDispatchPlan(combo)
 
@@ -2537,6 +2537,39 @@ describe('modal hidden together with its own app root', () => {
     expect((readPageActionState() as { dialogs: string[] }).dialogs).toEqual(['Upper'])
   })
 
+  it('keeps a dialog the app aria-hid below its root hidden', () => {
+    document.body.innerHTML = `
+      <div id="__next"><main>
+        <button>Shown action</button>
+        <div class="carousel-slide" aria-hidden="true">
+          <div role="dialog" aria-modal="true" aria-label="Offscreen"><button>Ghost</button></div>
+        </div>
+      </main></div>`
+    showAll()
+
+    const outline = outlineOf(collectSnapshot())
+
+    expect(outline).toContain('Shown action')
+    expect(outline).not.toContain('Ghost')
+  })
+
+  it('reads a disablePortal dialog inside a same-origin iframe', () => {
+    const frame = visible(document.createElement('iframe'))
+    document.body.append(frame)
+    const inner = frame.contentDocument as Document
+    inner.body.innerHTML = `
+      <div id="root" aria-hidden="true">
+        <button>Framed compose</button>
+        <div role="dialog" aria-modal="true" aria-label="Framed"><button>Framed send</button></div>
+      </div>`
+    for (const element of Array.from(inner.body.querySelectorAll('*'))) visible(element)
+
+    const outline = outlineOf(collectSnapshot())
+
+    expect(outline).toContain('Framed send')
+    expect(outline).not.toContain('Framed compose')
+  })
+
   it('exposes a disablePortal modal nested inside another open modal', () => {
     document.body.innerHTML = `
       <div id="__next" aria-hidden="true"><main>
 
@@ -46,7 +46,7 @@ declare global {
     /** Elements an earlier snapshot of this document listed; a later snapshot marks the rest `new`. */
     __simAgentShownElements?: WeakSet<Element>
     /** Installed by {@link installPageHelpers} before every page function; cached per call. */
-    __simAgentFindExemptModal: () => Element | null
+    __simAgentIsExemptModal: (element: Element) => boolean
     /** Why the last __simAgentResolveElement call returned null — read by the
      * shared stale-error producers so a refusal names its cause instead of
      * the blanket "the page changed". Cleared on every successful resolve. */
@@ -66,23 +66,27 @@ export function serializePageCall(fn: (...args: never[]) => unknown, args: unkno
  */
 export function installPageHelpers(): void {
   /**
-   * The open modal the page aria-hid together with everything else. MUI's ModalManager
+   * The open modal each document aria-hid together with everything else. MUI's ModalManager
    * aria-hides every <body> child except the modal's mount node, and a `disablePortal` modal
    * mounts inside the app root it just hid, so its own ancestor carries aria-hidden. Visibility
-   * checks skip only the aria-hidden test on ancestors above this modal. Null when any modal is
-   * visible unmodified (the portaled case) or no single topmost modal is contained by all of its
-   * hidden ancestors. A modal nested inside another open modal is the topmost of the two.
+   * checks skip only the aria-hidden test on ancestors above this modal. A document has none when
+   * any modal is visible unmodified (the portaled case), when anything other than a <body> child
+   * hides a modal (the app hid that dialog itself), or when no single innermost modal is contained
+   * by every hidden ancestor. Looked up per document, so a same-origin iframe gets its own.
    */
-  let exemptModal: Element | null | undefined
-  window.__simAgentFindExemptModal = (): Element | null => {
-    if (exemptModal === undefined) exemptModal = findExemptModal()
-    return exemptModal
+  const exemptModals = new Map<Document, Element | null>()
+  window.__simAgentIsExemptModal = (element: Element): boolean => {
+    const doc = element.ownerDocument
+    let modal = exemptModals.get(doc)
+    if (modal === undefined) {
+      modal = findExemptModal(doc)
+      exemptModals.set(doc, modal)
+    }
+    return modal === element
   }
-  function findExemptModal(): Element | null {
+  function findExemptModal(doc: Document): Element | null {
     const rendered: Array<{ modal: Element; hidden: Element[] }> = []
-    for (const modal of Array.from(
-      document.querySelectorAll('[aria-modal="true"], dialog[open]')
-    )) {
+    for (const modal of Array.from(doc.querySelectorAll('[aria-modal="true"], dialog[open]'))) {
       const rect = modal.getBoundingClientRect()
       if (rect.width <= 0 || rect.height <= 0 || modal.getAttribute('aria-hidden') === 'true')
         continue
@@ -106,7 +110,9 @@ export function installPageHelpers(): void {
           current = 'host' in root ? (root.host as Element) : null
         }
       }
-      if (visible) rendered.push({ modal, hidden })
+      if (visible && hidden.every((ancestor) => ancestor.parentElement === doc.body)) {
+        rendered.push({ modal, hidden })
+      }
     }
     if (rendered.some(({ hidden }) => hidden.length === 0)) return null
     const topmost = rendered.filter(
@@ -283,7 +289,7 @@ export function collectSnapshot(startingElementId = 0, elementId?: number): unkn
           !current.hasAttribute('hidden') &&
           (aboveExemptModal || current.getAttribute('aria-hidden') !== 'true')
       )
-      if (current === window.__simAgentFindExemptModal()) aboveExemptModal = true
+      if (window.__simAgentIsExemptModal(current)) aboveExemptModal = true
       if (current.parentElement) current = current.parentElement
       else {
         const root = current.getRootNode()
@@ -872,7 +878,7 @@ export function collectSnapshot(startingElementId = 0, elementId?: number): unkn
         ) {
           return false
         }
-        if (current === window.__simAgentFindExemptModal()) aboveExemptModal = true
+        if (window.__simAgentIsExemptModal(current)) aboveExemptModal = true
         if (current.parentElement) current = current.parentElement
         else {
           const root = current.getRootNode()
@@ -1110,7 +1116,7 @@ export function clickElement(
     ) {
       return { error: 'not-visible' }
     }
-    if (current === window.__simAgentFindExemptModal()) aboveExemptModal = true
+    if (window.__simAgentIsExemptModal(current)) aboveExemptModal = true
     if (current.parentElement) current = current.parentElement
     else {
       const root = current.getRootNode()
@@ -1603,7 +1609,7 @@ export function focusElementForTyping(id: number, moveFocus = true): unknown {
     ) {
       return { error: 'not-visible' }
     }
-    if (current === window.__simAgentFindExemptModal()) aboveExemptModal = true
+    if (window.__simAgentIsExemptModal(current)) aboveExemptModal = true
   }
 
   if (moveFocus) {
@@ -2349,7 +2355,7 @@ export function readPageActionState(
       ) {
         return false
       }
-      if (current === window.__simAgentFindExemptModal()) aboveExemptModal = true
+      if (window.__simAgentIsExemptModal(current)) aboveExemptModal = true
       if (current.parentElement) current = current.parentElement
       else {
         const root = current.getRootNode()
@@ -2514,7 +2520,7 @@ export function readPageActionState(
       ) {
         return false
       }
-      if (current === window.__simAgentFindExemptModal()) aboveExemptModal = true
+      if (window.__simAgentIsExemptModal(current)) aboveExemptModal = true
       if (current.parentElement) current = current.parentElement
       else {
         const root = current.getRootNode()
@@ -2649,7 +2655,7 @@ export function scrollPage(direction: string, amount?: number, elementId?: numbe
       ) {
         return false
       }
-      if (current === window.__simAgentFindExemptModal()) aboveExemptModal = true
+      if (window.__simAgentIsExemptModal(current)) aboveExemptModal = true
       if (current.parentElement) current = current.parentElement
       else {
         const root = current.getRootNode()
@@ -3133,7 +3139,7 @@ export function getElementScreenshotRect(id: number): unknown {
     ) {
       return { error: 'not-visible' }
     }
-    if (current === window.__simAgentFindExemptModal()) aboveExemptModal = true
+    if (window.__simAgentIsExemptModal(current)) aboveExemptModal = true
     if (current.parentElement) current = current.parentElement
     else {
       const root = current.getRootNode()
@@ -3284,7 +3290,7 @@ export function readChildFrameElementState(
       visible = false
       break
     }
-    if (current === window.__simAgentFindExemptModal()) aboveExemptModal = true
+    if (window.__simAgentIsExemptModal(current)) aboveExemptModal = true
     if (style.transform && style.transform !== 'none') {
       try {
         if (typeof DOMMatrixReadOnly !== 'function') {
 
@@ -1,4 +1,4 @@
-import { existsSync, mkdirSync, mkdtempSync, readdirSync, writeFileSync } from 'node:fs'
+import { existsSync, mkdirSync, mkdtempSync, readdirSync, renameSync, writeFileSync } from 'node:fs'
 import { tmpdir } from 'node:os'
 import { basename, dirname, join } from 'node:path'
 import type { MenuItemConstructorOptions, WebContents } from 'electron'
@@ -3533,6 +3533,43 @@ describe('browser-agent session', () => {
     }
   })
 
+  it('retries moving a completed download while another process briefly holds the file', async () => {
+    vi.useFakeTimers({ toFake: ['setTimeout'] })
+    try {
+      const directory = mkdtempSync(join(tmpdir(), 'sim-browser-downloads-'))
+      const busy = Object.assign(new Error('resource busy'), { code: 'EBUSY' })
+      const moveFile = vi
+        .fn<(from: string, to: string) => Promise<void>>()
+        .mockRejectedValueOnce(busy)
+        .mockRejectedValueOnce(busy)
+        .mockImplementation(async (from, to) => renameSync(from, to))
+      session = freshSession(win, {}, undefined, {
+        getDirectory: () => directory,
+        getFreeDiskBytes: () => Number.MAX_SAFE_INTEGER,
+        moveFile,
+      })
+      const contents = (session.ensureTab().view as unknown as MockView).webContents
+      const download = mockDownloadItem({ filename: 'held.bin', totalBytes: 100 })
+
+      startMockDownload(contents, download)
+      await vi.waitFor(() => expect(download.item.resume).toHaveBeenCalledOnce())
+      download.emitDone('completed')
+      await vi.waitFor(() => expect(moveFile).toHaveBeenCalledOnce())
+      await vi.advanceTimersByTimeAsync(1_000)
+
+      await vi.waitFor(() =>
+        expect(session.getBrowserDownloadsState('chat-test').downloads[0]).toMatchObject({
+          filename: 'held.bin',
+          state: 'completed',
+        })
+      )
+      expect(moveFile).toHaveBeenCalledTimes(3)
+      expect(finishedDownloadFiles(directory)).toEqual(['held.bin'])
+    } finally {
+      vi.useRealTimers()
+    }
+  })
+
   it('interrupts a completed download whose staging file cannot be moved into place', async () => {
     const directory = mkdtempSync(join(tmpdir(), 'sim-browser-downloads-'))
     session = freshSession(win, {}, undefined, {