Skip to content

Check cancellation in more Windows desktop-driver helper waits - #4483

Merged
Jason Morse (JasonVMo) merged 16 commits into
mainfrom
user/jasonvmo/desktop-driver-windows-helper
Nov 11, 2026
Merged

Jason Morse (JasonVMo) merged 16 commits into
mainfrom
user/jasonvmo/desktop-driver-windows-helper

Conversation

@JasonVMo

@JasonVMo Jason Morse (JasonVMo) commented Nov 10, 2026 •

Copy link
Copy Markdown
Contributor

Platforms Impacted

  • iOS
  • macOS
  • win32 (Office)
  • windows
  • android

Description of changes

Related to #4435.

Addresses the Windows helper findings WIN-5, WIN-7, WIN-8, WIN-9, WIN-10, and WIN-13, and partly addresses WIN-1, WIN-2, WIN-3, WIN-4, and WIN-6, in @fluentui-react-native/desktop-driver (native/windows). WIN-11 and WIN-12 are deferred. Since #4469, killing the helper also ends every application its kill-on-close Job Object contains, so the goal is for the helper to acknowledge a cancel well inside Node's 10 s Windows deadline on every path. This PR moves several waits toward that goal but does not reach it: the paths listed under Not in this PR can still block past a cancel.

The C++ was initially developed on macOS, then compiled and exercised locally on Windows 11 on November 10–11, 2026. The Windows and Win32 CI jobs provision the helper through .github/actions/setup-desktop-driver; its native-contract input defaults to false. The Windows Storybook job explicitly enables the Windows native package contract.

  • Cancellation inside bounded waits (WIN-2, partial).
    • Problem: RunBoundedProviderCall waited up to 5 s without a token. Whole-subtree BuildUpdatedCache calls, and their retries, ran directly under the 5 s UI Automation transaction timeout. closeApplication waited 2 s after terminating a packaged app.
    • Fix: A thread-local CancellationScope, set in Driver::Execute, gives bounded calls the command's token, and they check it between 50 ms wait slices. A cancelled read throws CancelledError. A cancelled mutation is abandoned and quarantined like a timed-out one, so the cancel reports effect unknown, not none. Subtree and probe caches run on the bounded worker. The wait after terminating sleeps through the token's cancellable wait and keeps the lease so the close can be retried. Direct UI Automation calls and packaged ActivateApplication are still not token-aware (see Not in this PR).
  • Probe hung windows before window management and activation (WIN-1, partial).
    • Problem: ShowWindow(SW_RESTORE), SetWindowPos, and activation wait on the target's thread, so a hung target held the helper and the input mutex.
    • Fix: SendMessageTimeoutW(WM_NULL, SMTO_ABORTIFHUNG) probes the target in 200 ms tries for up to 2 s and checks the token between tries. A hung target fails with automation-failed and reason target-non-response. setWindowRect posts its restore (ShowWindowAsync) and move (SWP_ASYNCWINDOWPOS), polls for both with the token, skips a move to the current frame, and records each change as dispatching until it settles. A restore that stalls after its initial probe remains unknown; it can still take effect after the failure. Activation probes before and during its loop and does not attach to a hung foreground holder's input queue. A target that hangs after a passed probe can still block SetForegroundWindow, SetActiveWindow, or BringWindowToTop.
  • Foreground rights go only to the target (WIN-10).
    • Problem: AllowSetForegroundWindow(ASFW_ANY).
    • Fix: The grant names the target process id.
  • Input lock held while input is down (WIN-3, partial).
    • Problem: The cross-process mutex was released after each command while keys or buttons stayed down. The worker's exit paths skipped ReleaseInput(), and queued commands ran under a token re-armed after EOF.
    • Fix: A command that leaves input depressed moves its PhysicalInputScope into the driver (heldInput_), which is released once ReleaseInput leaves nothing down. The worker releases input on every exit and drops queued commands once stopping. The cancel path's cleanup scope is therefore nested and immediate, which removes the 5 s mutex wait before cancelled is written.
  • Failed-release recovery and Windows test portability.
    • Problem: A failed key-up or button-up was discarded from the native ledger, allowing the lock to be released even though input might still be down. The Node adapter also discarded uncertain recovery candidates after failed input or release commands. Several desktop-test contracts inherited from main assumed POSIX paths or process behavior.
    • Fix: Failed native releases remain in the ledger and keep the lock while the worker lives; successful releases are removed, and a later release can retry the remainder. Unresolved cleanup reports an unknown effect, disposal refuses to acknowledge, and automatic click does not hide cleanup failure behind accessibility fallback. The adapter retains uncertain candidates and reports recovery failures alongside disposal failures. Windows tests now use platform-correct paths, process cleanup and shutdown budgets.
  • Pointer hit check (WIN-4, partial).
    • Problem: pointerDown and wheel scrolls did not check what window was under the pointer.
    • Fix: When a lease exists, both are refused with element-not-interactable over a window, or root window, that belongs to no leased application.
  • Pattern and focus failures keep their meaning (WIN-5).
    • Problem: A failed pattern query became unsupported-operation, and a failed focus read became "not focused".
    • Fix: QueryPattern returns available, absent, stale, or failed. Pattern actions, accessibility clicks, and value clears report stale-element or automation-failed and keep their previous results only for an absent pattern. A failed focus read is reported as automation-failed and a stale element as stale-element.
  • Launch cleanup and identity (WIN-7).
    • Problem: A successful launch posted WM_CLOSE to, and terminated, a still-running launch root even when the job owned it, and a packaged root was trusted by process id alone.
    • Fix: Under a containment job the root is left to the job. A packaged root must report the requested AUMID before it is tracked or terminated, and ActivateApplication uses AO_NOERRORUI.
  • Unreadable start time (WIN-8).
    • Problem: An unreadable start time serialized as 1601-01-01…, which the incarnation probe reads as exited.
    • Fix: Lease creation fails with launch-failed or attach-failed, and a zero FILETIME serializes as an empty string.
  • Event-table overflow (WIN-9).
    • Problem: On overflow every tracked window was re-added with the caller's process id.
    • Fix: Each window keeps the process id it was recorded with.
  • Transport, contract, and docs (WIN-13).
    • Problem: The host logged and skipped invalid JSON, against the PROTOCOL rule.
    • Fix: The host exits with code 1 on invalid JSON, and also on a JSON frame that is not an object (matching the macOS change). The Windows contract in src/native/nativeDriver.test.ts now expects this: after a malformed frame and a probe request, the helper exits with code 1 within 10 s and never answers the probe. It replaces the old recovery expectation, and the 1,024-byte identifier request and cancel that followed the bad frame are dropped because they can no longer be read. The README now gives the actual close sequence and the actual build settings: warning level 4, without /WX, CFG, or /sdl, and no longer claims to be warning-clean. It also covers posted window management, target-non-response, the held input lock, the pointer hit check, launch cleanup under a job, and cancellation. PROTOCOL.md widens target-non-response to window messages, and remaining-work.md records what is still unbounded. The docs and changeset state the polling intervals as implementation bounds on the wrapped waits, not as measured cancellation times.
  • Self-tests (WIN-6, partial). Added:
    • a stalled window thread for the probe's target-non-response failure, cancellation, and recovery;
    • a minimized window that passes its initial probe, then stalls during restore: the error reports unknown and the posted restore takes effect after the failure;
    • cancelled bounded reads and mutations;
    • a held key that keeps the lock from another thread;
    • foreign pointer and scroll refusal;
    • a stale accessibility click;
    • a zero FILETIME;
    • malformed and non-object frames over pipes.
  • Windows fixture contracts: Exercise cancellation while a real provider mutation is in flight, its unknown effect and quarantine, survival of the job-owned application, and the late effect. A hung window also verifies cancellation and target-non-response for move and activation preflight.
  • Changeset: .changeset/win-helper-cancellation.md (desktop-driver, patch).

Not in this PR

  • Abandoned input lock (WIN-3): an abandoned lock is still reported to one acquirer only, not sticky until --release-input or --sweep.
  • Crash recovery: the Node mirror omits the synthetic keyboard-clear chord and may not reconstruct the exact Windows stroke; the Windows mutex is not a durable cross-process recovery barrier after worker exit.
  • performActions window (WIN-4): naming the target window is a cross-platform protocol change, so the hit check accepts any leased application.
  • WIN-11: Caps Lock state and the scan-code keyboard layout still come from the helper thread. The fix depends on the foreground thread's layout and toggle state, which remains unqualified here.
  • WIN-12: the refactor is deferred.
  • WIN-6 tests not added, because each needs a real job, packaged application, or protected process that the self-test cannot create: job-assignment failure, cancel before the window appears, a non-draining job, Dispose with job leases, and an unreadable attach identity.
  • Remaining waits not bounded by the token (WIN-1 and WIN-2 remain partial): on these paths a cancel can still go unacknowledged until Node's deadline, so Node may kill the helper and its Job Object may end the app under test:
    • direct UI Automation calls outside the bounded worker (pattern queries, ElementFromHandle, observe paging, the tree walker), which are bounded only by the 2 s connection and 5 s transaction timeouts;
    • SetForegroundWindow, SetActiveWindow, and BringWindowToTop on a target that hangs after its probe;
    • packaged ActivateApplication, which is synchronous.
  • src/native/windows/protectedService.contract.test.ts:233 is being updated by the ops change, for SRV-11.

Verification

Rebased follow-up, Windows 11 x64, November 11, 2026: bdeb0b291 contains the review fix and desktop-test corrections. Commands below run in the named package unless otherwise stated.

Command Result
$env:FURN_NATIVE_DRIVER_TEST = '1'; yarn test --runInBand (desktop-driver) Passed: 1,245 tests, 42 skipped on the rebased follow-up tree before the final automatic-click guard.
$env:FURN_NATIVE_DRIVER_TEST = '1'; yarn test nativeDriver --runInBand (desktop-driver) Passed on the final tree: 9 tests, 2 skipped; built and exercised the Windows helper and its self-test.
yarn format, yarn lint, yarn build (desktop-driver) Passed on the final tree.
yarn format, yarn lint, yarn build, yarn test (desktop-test) Passed: 374 tests, 7 skipped.
yarn storybook smoke --win32 --mode stories-and-tests --input physical (apps/storybook) Passed on the rebased follow-up tree before the final automatic-click guard: 176 story renders and 82 callbacks; one further callback was quarantined as unsupported (#4373), not passed.
yarn clean-lage-cache; yarn lage buildci --concurrency 4 (root) The first clean-cache run exposed the Windows desktop-test failures. After the fixes, the aggregate passed; the final rerun had 7 successful and 171 skipped/cached tasks, 0 failed.

Hosted on bdeb0b291, Windows PR, Windows Storybook, Win32 PR, and both Win32 Storybook lanes passed. The macOS Paper Storybook job failed during components-listitem--overview navigation with Storybook context did not settle; an unchanged-head retry passed. The original failure's cause is not established.

Windows 11 x64, Node 26.13.0, November 10, 2026, head 999438c5e: the native-enabled suite built the C++ helper, ran its self-test and real Windows contracts, and exercised physical input and capture. The Storybook smokes used the same fixed production helper.

Command Result
$env:FURN_NATIVE_DRIVER_TEST = '1'; yarn workspace @fluentui-react-native/desktop-driver test --runInBand Passed: 910 tests; 31 skipped, including macOS-only coverage. The in-flight mutation cancellation was acknowledged in 48 ms in this run; the fixture survived and its late effect remained quarantined.
$env:FURN_NATIVE_DRIVER_TEST = '1'; yarn workspace @fluentui-react-native/desktop-driver test --runInBand nativeDriver Passed: 6 tests, 2 skipped.
yarn workspace @fluentui-react-native/agentic-components-storybook storybook build-driver --windows --reporter json, then the returned executablePath --self-test Passed: 812 native checks. The new restore regression reported partial before the fix and unknown after it; the restore took effect after the failure.
yarn workspace @fluentui-react-native/desktop-driver format --check Passed
yarn workspace @fluentui-react-native/desktop-driver lint Passed
yarn workspace @fluentui-react-native/desktop-driver build Passed
$env:STORYBOOK_SMOKE_STORY = 'components-card--native-structure'; yarn workspace @fluentui-react-native/agentic-components-storybook storybook smoke --windows --mode stories-and-tests --input accessible Passed: 202 stories rendered and 2 of 2 callbacks passed, including window resize and restoration.
$env:STORYBOOK_SMOKE_STORY = 'components-card--native-structure'; yarn workspace @fluentui-react-native/agentic-components-storybook storybook smoke --win32 --mode stories-and-tests --input accessible Passed: 176 stories rendered and 2 of 2 callbacks passed, including window resize and restoration.
$env:STORYBOOK_SMOKE_STORY = $null; yarn workspace @fluentui-react-native/agentic-components-storybook storybook smoke --win32 --mode stories-and-tests --input accessible Passed: all 214 selected tests, including 176 story renders and 38 callbacks; owned services stopped. Its test IDs match the failed hosted run below.
$env:STORYBOOK_SMOKE_STORY = $null; yarn workspace @fluentui-react-native/agentic-components-storybook storybook smoke --win32 --mode stories-and-tests --input physical Passed: 258 executed, including 176 story renders and 82 callbacks; one further callback was quarantined as unsupported (#4373), not passed. Owned services stopped.
yarn test-links -c .github\markdown-link-check-config.json packages\agentic\desktop-driver\native\windows\README.md Passed: 7 links checked.
yarn clean-lage-cache; yarn lage buildci --concurrency 4 Passed: 178 tasks, 0 failed.

The focused win32Fixture run selected the hung-window and in-flight cancellation cases: 2 passed and 10 were filtered out. Cancellation was acknowledged in 31 ms in that run and 38–47 ms in earlier full runs. These observations are not general timing guarantees. The full Win32 physical lane exercised real pointer and keyboard input; the accessible smokes alone do not qualify physical input. Owned services stopped and their recorded ports had no listeners afterward.

Hosted CI: On 114c2f605, Win32 Storybook accessible ran all 214 selected tests successfully, but the job failed during owned-service/reporting shutdown. The matching local 214-test run passed including cleanup. The failure resembles the independently addressed shutdown-deadline issue in #4476, but the nested failure's cause is not established. On 999438c5e, Win32 PR and Win32 Storybook accessible passed, but the physical job failed while navigating components-tab--overview with Storybook context did not settle; all 52 attempted hosted navigations passed in the full local physical run. An unchanged-head retry later passed 258 tests with one quarantined/unsupported. The original failure's cause remains unconfirmed.

Earlier macOS verification: Run in packages/agentic/desktop-driver unless noted. The Windows-only contracts skipped in these runs.

Command Result
Build and run the Windows helper (msbuild, --self-test), and the Windows contracts Not run on macOS; Windows results are above.
clang-format Not run: the repository has no .clang-format for this code

Before the contract and wording commits (tree 998278dfa):

Command Result
yarn format Passed, no changes
yarn lint Passed
yarn build Passed
yarn test Passed: 59 suites, 876 tests passed, 64 skipped (8 Windows/native suites skipped)
yarn oxfmt --check on the README, PROTOCOL.md, remaining-work.md, and the changeset (root) Passed
native-lock.sh win-buildci bash -c 'yarn clean-lage-cache && yarn lage buildci --concurrency 4' (root) Passed: 178 tasks succeeded, 0 failed

After the nativeDriver.test.ts contract update (a1653720a) and the wording correction (b16d0349c):

Command Result
yarn build (type-check) Passed
yarn lint Passed
yarn format Passed, no changes
yarn test nativeDriver Passed: 1 suite, 5 tests passed, 3 skipped (the macOS and Windows helper builds, including the updated Windows contract)
yarn oxfmt --check on the README, remaining-work.md, and the changeset (root) Passed
Root buildci Not rerun: these commits change only a Windows-skipped contract test and documentation wording
Before After
A cancel during a slow provider call, subtree read, hung-window restore or move, activation, or packaged close could wait 2 s or more without checking the cancel. Node then killed the helper and its Job Object ended the app under test. A cancelled mutation could report none. The newly wrapped waits check cancellation between polls: 50 ms slices for bounded UI Automation calls and the subtree cache, 200 ms window probe messages, and cancellable sleeps in the restore, move, activation, and close loops. These are implementation bounds, not general end-to-end timing guarantees; the Windows fixture observations above cover one in-flight mutation. Direct UI Automation calls, SetForegroundWindow, SetActiveWindow, and BringWindowToTop after a passed probe, and packaged ActivateApplication can still block past a cancel. A cancelled mutation reports unknown, a window that fails its probe fails with target-non-response, held input keeps the lock, and malformed or non-object frames fail the transport.

Pull request checklist

This PR has considered (when applicable):

  • Automated Tests
  • Documentation and examples
  • Keyboard Accessibility
  • Voiceover
  • Internationalization and Right-to-left Layouts

@github-actions

github-actions Bot commented Nov 10, 2026 •

Copy link
Copy Markdown
Contributor

Bundle size report

Tree-shaken, minified production esbuild bundles with React and React Native runtimes externalized.

Scenario Modules-Mac (Δ) Modules-Win (Δ) Size-Mac (Δ) Size-Win (Δ)
components-button 79 (+1) 80 (+1) 72.78k (-842b) 72.71k (-842b)
components-catalog 228 (+1) 229 (+1) 228.46k (-855b) 228.38k (-855b)
design-themed-root 55 (+4) 56 (+4) 56.26k (+998b) 56.18k (+998b)
design-color-lib 6 (+0) 6 (+0) 6.27k (+0b) 6.27k (+0b)
design-theme-state-legacy-source 49 (+1) 50 (+1) 52.96k (-841b) 52.89k (-841b)
design-legacy-theme 42 (+0) 42 (+0) 39.11k (+0b) 42.91k (+0b)
design-legacy-theme-from-flex 58 (+4) 58 (+4) 60.70k (+824b) 64.51k (+822b)
design-fluent-light-theme 7 (+0) 7 (+0) 18.74k (+0b) 22.59k (+0b)
design-fluent-theme 35 (+0) 35 (+0) 27.46k (+4b) 31.25k (-1b)
design-fluent-hc-theme 32 (+0) 32 (+0) 27.34k (+0b) 31.13k (+0b)
design-flex-theme 29 (-4) 29 (-4) 14.30k (-9.07k) 14.29k (-9.07k)
design-flex-cool-theme 26 (New) 26 (New) 12.51k (New) 12.50k (New)
design-flex-warm-theme 26 (-7) 26 (-7) 12.28k (-11.15k) 12.27k (-11.15k)

The job is advisory: size changes are reported but do not fail the pull request. Bundle or analysis errors still fail.


View bundle-size workflow run

@JasonVMo
Jason Morse (JasonVMo) enabled auto-merge (squash) November 10, 2026 23:18
Jason Morse (JasonVMo) and others added 16 commits November 10, 2026 15:27
A cancelled command could not be acknowledged while the helper waited up to
5 s on a bounded provider call, a whole-subtree cache, or the 2 s wait after
terminating a packaged application. Node then killed the helper, which since
the kill-on-close Job Object also ends the application under test.

Bounded provider calls now read the command's token through a thread-local
CancellationScope and wait in 50 ms slices. A cancelled read throws
CancelledError; a cancelled mutation is abandoned and quarantined like a timed
out one, so the command reports effect `unknown`. Whole-subtree and probe
caches run on the bounded worker, and closeApplication's post-terminate wait
observes the token and keeps the lease for a retry.

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
ShowWindow, SetWindowPos, and activation wait on the thread that owns the
window, so a hung target held the helper, and the physical input lock, until
it recovered. Activation also granted every process foreground rights.

The helper now probes the window with SendMessageTimeoutW(WM_NULL,
SMTO_ABORTIFHUNG) in 200 ms tries for up to 2 s and fails with
automation-failed and reason `target-non-response`. setWindowRect posts its
restore (ShowWindowAsync) and move (SWP_ASYNCWINDOWPOS) and polls for them with
the cancellation token, recording each as dispatching until it settles.
Activation skips attaching to a hung holder's input queue and grants
AllowSetForegroundWindow only to the target process. A self-test stalls a
window thread and checks the probe, restore, activation, and cancellation.

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
The cross-process physical input mutex was released after every command even
when keys or buttons stayed down, so another helper could inject while our
modifiers were held. The worker's exit paths skipped ReleaseInput, and queued
commands ran under a token re-armed after the transport ended.

A command that leaves input depressed now moves its scope into the driver,
which releases it once ReleaseInput leaves nothing down. The worker releases
input on every exit and drops queued commands once stopping. Because the lock
is already held while input is down, the cancel path's cleanup no longer waits
for the mutex. A self-test checks that a held key keeps the lock from another
thread.

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
performActions did not check where a pointer press or scroll landed, so either
could reach a window of an application the helper never launched or attached
to.

Before pointerDown and before a scroll moves the pointer, the driver now hit
tests the point and fails with element-not-interactable when the window there,
or its root, belongs to no leased application. A test hit tester lets the
self-test cover a foreign press and scroll. Naming the target window in
performActions is a cross-platform protocol change and is left for later.

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
A failed GetCurrentPatternAs was reported as unsupported-operation and a failed
focus read as an unfocused element, hiding stale elements and provider
failures behind the wrong error.

QueryPattern now returns available, absent, stale, or failed. Pattern actions,
accessibility clicks, and value clears report stale-element for a stale
element and automation-failed for a failed query, and keep their existing
results for an absent pattern. HasKeyboardFocus fails a stale
element and returns any other failure to FocusForKeyboard, which reports
automation-failed. A self-test clicks an element of a destroyed window.

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
A successful launch posted WM_CLOSE to and terminated a still-running launch
root even when the Job Object owned it, a packaged root was trusted by process
id alone, and an unreadable start time serialized as 1601-01-01, which the
incarnation probe reads as exited.

Under a containment job the launch root is now left to the job. A packaged
root must report the requested AUMID before it is tracked or terminated, and
ActivateApplication uses AO_NOERRORUI. Lease creation fails when the start
time cannot be read, and a zero FILETIME serializes as an empty string.

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
When the known-window table overflowed, every tracked window was re-added with
the process id of the window being remembered, mislabeling later destroy
events. Tracked windows now keep the process they were recorded for.

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
The protocol says invalid JSON fails the transport, but the helper logged and
skipped the frame. A skipped frame may have been a request or a cancel, so
Node could wait on an id the helper never saw.

The host now writes a diagnostic and exits with code 1 without reading
further frames. A self-test sends a malformed frame between two requests and
checks the exit code and that the later request never runs.

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
The README now describes the posted window management, the target-non-response
probe, the input lock held while input is down, pointer hit checks, launch
cleanup under a job, and cancellation, and corrects the close sequence and the
build-warnings claim. PROTOCOL.md widens target-non-response to window
messages, and remaining-work.md records what is still unbounded. Adds the
patch changeset.

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
PROTOCOL.md defines every JSON message as an object with a `type`, and the
macOS helper now fails the transport on a frame that is not one. The Windows
host logged and skipped such a frame, so the two helpers disagreed. It now
writes a diagnostic and exits with code 1, and the malformed-frame self-test
also runs with a JSON array.

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
The changeset and the README verification paragraph now say that a non-object JSON frame fails the transport, as the host and its self-test do.

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
The Windows native contract sent a malformed frame and expected the helper to keep answering. The helper now follows PROTOCOL.md and exits with code 1, so the contract writes the malformed frame and a probe, expects exit code 1 within 10 s, and expects no response to the probe. The 1,024-byte identifier request and cancel that followed the bad frame could no longer be read, so they are dropped.

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
The README, remaining-work notes, and changeset implied that every Windows activation and provider path now acknowledges a cancel promptly. Only the newly wrapped waits check cancellation between polls; direct UI Automation calls and the activation calls themselves can still block, and none of it has run on Windows. Describe the polling intervals as implementation bounds on those waits and name the paths that remain unbounded.

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
Copilot-Session: 53a0c7cf-1330-4677-8700-d249b508c6ee
Keep a posted restore pending through the responsiveness check and verify its possible late effect.

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
Copilot-Session: 53a0c7cf-1330-4677-8700-d249b508c6ee
Keep unreleased strokes and buttons under the physical-input lock, preserve uncertain host recovery, and refuse unsafe fallback or disposal. Fix Windows portability of desktop-test lifecycle and reporting contracts.

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
Copilot-Session: 53a0c7cf-1330-4677-8700-d249b508c6ee
@JasonVMo
Jason Morse (JasonVMo) force-pushed the user/jasonvmo/desktop-driver-windows-helper branch from 999438c to bdeb0b2 Compare November 11, 2026 11:58
@JasonVMo
Jason Morse (JasonVMo) merged commit 3b2787e into main Nov 11, 2026
34 of 35 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants