id int64 393k 2.82B | repo stringclasses 68
values | title stringlengths 1 936 | body stringlengths 0 256k ⌀ | labels stringlengths 2 508 | priority stringclasses 3
values | severity stringclasses 3
values |
|---|---|---|---|---|---|---|
2,613,308,949 | flutter | Safari/Firefox browser: keyboard not working for TextFields within SelectionArea + Dialog | ### Steps to reproduce
- Run the given code with Flutter Web in the Safari or Firefox browser
- Open the dialog
- Try to write some text in each field
### Expected results
The keyboard should work correctly
### Actual results
Half of the time the keyboard doesn't work. If you focus an other field, sometime it works and sometime it just doesn't.
It works for the Chrome browser but not for Firefox or Safari (on macOS)
### Code sample
<details open><summary>Code sample</summary>
```dart
import 'package:flutter/material.dart';
void main() => runApp(App());
class App extends StatelessWidget {
const App({super.key});
@override
Widget build(BuildContext context) {
return MaterialApp(
home: SelectionArea(
child: Scaffold(
body: Builder(
builder: (context) {
return Center(
child: FilledButton(
onPressed: () {
showDialog(
context: context, builder: (context) => EditDialog());
},
child: Text('Open dialog'),
),
);
},
),
),
),
);
}
}
class EditDialog extends StatelessWidget {
const EditDialog({super.key});
@override
Widget build(BuildContext context) {
return AlertDialog(
scrollable: true,
title: Text('Dialog'),
content: Column(
mainAxisSize: MainAxisSize.min,
children: [
for (var i = 0; i < 8; i++)
TextField(
decoration: InputDecoration(labelText: 'Enter text'),
),
],
),
actions: [
FilledButton(
onPressed: () {
Navigator.pop(context);
},
child: Text('OK'),
)
],
);
}
}
```
</details>
### Screenshots or Video
<details open>
<summary>Screenshots / Video demonstration</summary>
[Upload media here]
</details>
### Logs
<details open><summary>Logs</summary>
```console
[Paste your logs here]
```
</details>
### Flutter Doctor output
<details open><summary>Doctor output</summary>
```console
[✓] Flutter (Channel beta, 3.27.0-0.1.pre, on macOS 14.5 23F79 darwin-arm64, locale en-BE)
[✓] Android toolchain - develop for Android devices (Android SDK version 35.0.0)
[✓] Xcode - develop for iOS and macOS (Xcode 15.4)
[✓] Chrome - develop for the web
[✓] Android Studio (version 2024.2)
[✓] IntelliJ IDEA Ultimate Edition (version 2024.2.3)
[✓] VS Code (version 1.93.0)
```
</details>
| a: text input,framework,platform-web,has reproducible steps,browser: safari-macos,browser: firefox,P2,f: selection,team-web,triaged-web,found in release: 3.24,found in release: 3.27 | low | Major |
2,613,345,190 | langchain | DOC: data parsing error handling (if retry and data fixing does not work) | ### URL
https://python.langchain.com/docs/how_to/output_parser_fixing/
### Checklist
- [X] I added a very descriptive title to this issue.
- [X] I included a link to the documentation page I am referring to (if applicable).
### Issue with current documentation:
I'm looking for ways to handle data parsing errors with 100% guarantee.
Current documentation considers attempts to fix the errors by prompting LLM to fix it or with retry. The enhancement might work, but without any guarantee.
To be 100% sure, it would be helpful to explain how to handle parsing errors in the worst case, when the above attempts fail.
### Idea or request for content:
One idea is to extend the output parser class to handle the parsing errors | 🤖:docs,stale | low | Critical |
2,613,382,391 | vscode | Suggest (workspace-)recommended extensions if they are disabled |
Type: <b>Feature Request</b>
Actual:
Extensions added as workspace recommendations are suggested if they are not installed.
Expected:
Extensions added as workspace recommendations are suggested if they are not installed or not enabled.
The reason behind my suggestion is that users might have a number of extensions installed on their vscode, but they are disabled by default and enabled only based on the workspace.
When opening a workspace the application checks the recommended extensions from the workspace, but it does not suggest them to the user if the extension is installed but disabled. I believe it should suggest the extension based on its enabled state rather than its installed state.
Version: 1.94.2 (user setup)
Commit: 384ff7382de624fb94dbaf6da11977bba1ecd427
Date: 2024-10-09T16:08:44.566Z
Electron: 30.5.1
ElectronBuildId: 10262041
Chromium: 124.0.6367.243
Node.js: 20.16.0
V8: 12.4.254.20-electron.0
OS: Windows_NT x64 10.0.22631
VS Code version: Code 1.94.2 (384ff7382de624fb94dbaf6da11977bba1ecd427, 2024-10-09T16:08:44.566Z)
OS version: Windows_NT x64 10.0.22631
Modes:
<!-- generated by issue reporter --> | feature-request,extensions | low | Minor |
2,613,409,379 | vscode | Views drag and drop: allow to drop into the entire bar instead of splitting | Right now for me to drag and drop a view in the secondary sidebar I have to drop it in the small title area of the secondary sidebar.
If I drop it in the large view area, it basically splits the view container.
I know this logically makes sense, but makes the whole DnD experience unusable.
Could DnD see if I am dragging the only view in the container, and if yes always drop it as a separate container?
I am constantly being bitten by this (even with previous DnD scenarios). | feature-request,under-discussion,workbench-dnd,layout,workbench-views,workbench-auxsidebar | low | Major |
2,613,420,662 | rust | no-op remap_path_prefix change invalidates incremental cache | <!--
Thank you for filing a bug report! 🐛 Please provide a short summary of the bug,
along with any information you feel relevant to replicating the bug.
-->
I'm building rust code in a CI environment, setting -Cincremental to a shared location. CI allocates a new working directory for each build. To prevent leaking that info to the debug info, we set `--remap_path_prefix=${PWD}=` to eliminate the unwanted prefix from the debug info.
```sh
rustc src/lib.rs \
--crate-name=xxx \
--crate-type=rlib \
--error-format=human \
--out-dir=${OUTDIR} \
--remap-path-prefix=${PWD}= \
--emit=dep-info,link \
-Ccodegen-units=256 \
-Zincremental_info \
-Cincremental=${CACHEDIR}
```
I expected this will reuse the incremental build cache, but it's not:
```
[incremental] session directory: 259 files hard-linked
[incremental] session directory: 0 files copied
[incremental] completely ignoring cache because of differing commandline arguments
```
Further inspection of how the hash being generated, I found:
https://github.com/rust-lang/rust/blob/017ae1b21f7be6dcdcfc95631e54bde806653a8a/compiler/rustc_session/src/options.rs#L195-L222
for our case, `working_dir` always uses remapped_path `""`, which is stable over build. but the `remap_path_prefix` is different everytime. and the logic for populating `working_dir` is at:
https://github.com/rust-lang/rust/blob/017ae1b21f7be6dcdcfc95631e54bde806653a8a/compiler/rustc_session/src/config.rs#L2690-L2695
So to get correct remapped `working_dir`, I must set `--remap-path-prefix`, but setting it will change `remap_path_prefix` and causing hash mismatch:
https://github.com/rust-lang/rust/blob/017ae1b21f7be6dcdcfc95631e54bde806653a8a/compiler/rustc_incremental/src/persist/load.rs#L159-L164
### Meta
<!--
If you're using the stable version of the compiler, you should also check if the
bug also exists in the beta or nightly versions.
-->
`rustc --version --verbose`:
```
rustc 1.82.0-nightly (f6e511eec 2024-10-15)
binary: rustc
commit-hash: f6e511eec7342f59a25f7c0534f1dbea00d01b14
commit-date: 2024-10-15
host: aarch64-apple-darwin
release: 1.82.0-nightly
LLVM version: 19.1.1
```
| A-debuginfo,T-compiler,A-incr-comp,C-feature-request,WG-incr-comp,A-path-remapping | low | Critical |
2,613,421,367 | vscode | terminal.integrated.shellIntegration.enabled causes terminal to become progressively unresponsive | Type: <b>Performance Issue</b>
- Press command-j to open the terminal.
- Type a command that outputs 10000 lines of text, for instance:
```
python -c "for i in range(10000): print(f'This is a long long long long long line of text {i}')"
```
- Press the up arrow to display the previous long command at the shell prompt in the terminal and then hold the backspace key to delete this new command entirely without executing it.
Observed: the cursor progresses very slowly to the left and becomes almost stuck with very high CPU usage when holding the backspace key.
Workaround: setting `terminal.integrated.shellIntegration.enabled` to `false`, and starting a new `zsh` shell (even without terminating the previous shell) makes the terminal responsive again.
I am using the zsh shell with some custom prompt and other zsh custom config.
I found about the culprit in this stackoverlow answer:
https://stackoverflow.com/a/78624068/163740
VS Code version: Code 1.94.2 (Universal) (384ff7382de624fb94dbaf6da11977bba1ecd427, 2024-10-09T16:08:44.566Z)
OS version: Darwin arm64 23.5.0
Modes:
<details>
<summary>System Info</summary>
|Item|Value|
|---|---|
|CPUs|Apple M1 (8 x 2400)|
|GPU Status|2d_canvas: enabled<br>canvas_oop_rasterization: enabled_on<br>direct_rendering_display_compositor: disabled_off_ok<br>gpu_compositing: enabled<br>multiple_raster_threads: enabled_on<br>opengl: enabled_on<br>rasterization: enabled<br>raw_draw: disabled_off_ok<br>skia_graphite: disabled_off<br>video_decode: enabled<br>video_encode: enabled<br>webgl: enabled<br>webgl2: enabled<br>webgpu: enabled<br>webnn: disabled_off|
|Load (avg)|7, 8, 9|
|Memory (System)|16.00GB (0.04GB free)|
|Process Argv|--crash-reporter-id a9b46850-8582-479a-9ccf-67c15c22fa0a|
|Screen Reader|no|
|VM|0%|
</details><details>
<summary>Process Info</summary>
```
CPU % Mem MB PID Process
4 115 96110 code main
0 49 96114 gpu-process
0 33 96115 utility-network-service
0 131 96116 window [1] (Settings — scikit-learn)
0 49 96141 ptyHost
0 0 96199 /bin/zsh -i
0 0 96428 /bin/zsh -i
0 0 96508 /bin/zsh -il
0 0 96697 /bin/zsh -il
0 0 97377 /bin/zsh -i
0 0 97749 /bin/zsh -i
0 66 96142 extensionHost [1]
0 0 96151 /Users/ogrisel/.vscode/extensions/ms-python.python-2024.16.1-darwin-arm64/python-env-tools/bin/pet server
0 0 96160 /Users/ogrisel/miniforge3/envs/dev/bin/python /Users/ogrisel/.vscode/extensions/ms-python.black-formatter-2024.4.0/bundled/tool/lsp_server.py --stdio
0 0 96178 /Users/ogrisel/.vscode/extensions/ms-vscode.cpptools-1.22.10-darwin-arm64/bin/cpptools
0 49 96205 electron-nodejs (bundle.js )
0 33 96269 electron-nodejs (server-node.js )
0 49 96189 shared-process
0 0 98803 /bin/ps -ax -o pid=,ppid=,pcpu=,pmem=,command=
0 49 96191 fileWatcher [1]
```
</details>
<details>
<summary>Workspace Info</summary>
```
| Window (Settings — scikit-learn)
| Folder (scikit-learn): 6642 files
| File types: json(1199) py(987) rst(865) o(288) so(272) dep(272) c(215)
| png(170) pyx(113) new(111)
| Conf files: github-actions(17) makefile(4) settings.json(1);
```
</details>
<details><summary>Extensions (34)</summary>
Extension|Author (truncated)|Version
---|---|---
ruff|cha|2024.52.0
copilot|Git|1.242.0
copilot-chat|Git|0.21.2
vscode-github-actions|git|0.27.0
vscode-cython|ktn|1.0.3
vscode-pdf|mat|0.0.6
black-formatter|ms-|2024.4.0
debugpy|ms-|2024.12.0
python|ms-|2024.16.1
vscode-pylance|ms-|2024.10.1
datawrangler|ms-|1.12.0
jupyter|ms-|2024.9.1
jupyter-keymap|ms-|1.1.2
jupyter-renderers|ms-|1.0.19
vscode-jupyter-cell-tags|ms-|0.1.9
vscode-jupyter-slideshow|ms-|0.1.6
remote-containers|ms-|0.388.0
remote-ssh|ms-|0.115.0
remote-ssh-edit|ms-|0.87.0
remote-wsl|ms-|0.88.4
vscode-remote-extensionpack|ms-|0.26.0
cmake-tools|ms-|1.19.52
cpptools|ms-|1.22.10
cpptools-extension-pack|ms-|1.3.0
makefile-tools|ms-|0.11.13
remote-explorer|ms-|0.4.3
remote-server|ms-|1.5.2
vscode-speech|ms-|0.10.0
vsliveshare|ms-|1.0.5941
vscode-xml|red|0.27.1
rust-analyzer|rus|0.3.2154
rewrap|stk|1.16.3
even-better-toml|tam|0.19.2
cmake|twx|0.0.17
(1 theme extensions excluded)
</details><details>
<summary>A/B Experiments</summary>
```
vsliv368cf:30146710
vspor879:30202332
vspor708:30202333
vspor363:30204092
vscod805:30301674
binariesv615:30325510
vsaa593cf:30376535
py29gd2263:31024239
c4g48928:30535728
azure-dev_surveyone:30548225
962ge761:30959799
pythongtdpath:30769146
pythonnoceb:30805159
asynctok:30898717
pythonmypyd1:30879173
h48ei257:31000450
pythontbext0:30879054
cppperfnew:31000557
dsvsc020:30976470
pythonait:31006305
dsvsc021:30996838
9c06g630:31013171
dvdeprecation:31068756
dwnewjupytercf:31046870
impr_priority:31102340
nativerepl1:31139838
refactort:31108082
pythonrstrctxt:31112756
wkspc-onlycs-t:31132770
wkspc-ranged-t:31151552
cf971741:31144450
defaultse:31146405
iacca2:31156134
notype1:31157159
5fd0e150:31155592
dwcopilot:31164048
iconenabled:31158251
```
</details>
<!-- generated by issue reporter --> | bug,perf,confirmation-pending,terminal-shell-zsh | low | Critical |
2,613,444,429 | tensorflow | Does TFLite dequantize opertor support constant buffer input | **System information**
- OS Platform and Distribution (e.g., Linux Ubuntu 16.04): Ubuntu 24.04
- TensorFlow installed from (source or binary): source
- TensorFlow version (or github SHA if from source): the latest version
**Standalone code to reproduce the issue**
<img width="724" alt="image" src="https://github.com/user-attachments/assets/849a0952-90ce-42c4-b2dc-9a9e7333fb0b">
The [tflite model for user input](https://github.com/fujunwei/tensorflow/blob/tflite_label_image/tensorflow/lite/examples/python/dequantize_input.tflite) can work as expected
<img width="713" alt="image" src="https://github.com/user-attachments/assets/43cafc84-0ea6-4a06-84b4-4772c6cea8e8">
The [tflite model with constant buffer](https://github.com/fujunwei/tensorflow/blob/tflite_label_image/tensorflow/lite/examples/python/dequantize_constant.tflite) can't compute, so does [dequantize](https://www.tensorflow.org/mlir/tfl_ops#tfldequantize_tfldequantizeop) support constant input?
**Any other info / logs**
You can also modify [dequantize_tester in the Repo](https://github.com/tensorflow/tensorflow/blob/master/tensorflow/lite/delegates/xnnpack/dequantize_tester.cc#L110) to reproduce this issue like below code:
1, Create a constant buffer
```
const auto buffer_data = builder.CreateVector( reinterpret_cast<const uint8_t*>(constant_buffer.data()),
constant_buffer.size());
const auto buffer_index = base::checked_cast<uint32_t>(buffers.size());
buffers.emplace_back(::tflite::CreateBuffer(builder, buffer_data));
```
2, Use the `buffer_index ` when creating tensor:
```
const std::array<flatbuffers::Offset<::tflite::Tensor>, 2> tensors{{
::tflite::CreateTensor(
builder,
builder.CreateVector<int32_t>(Shape().data(), Shape().size()),
Unsigned() ? ::tflite::TensorType_UINT8 : ::tflite::TensorType_INT8,
/*buffer=*/buffer_index , /*name=*/0,
::tflite::CreateQuantizationParameters(
builder, /*min=*/0, /*max=*/0,
builder.CreateVector<float>({InputScale()}),
builder.CreateVector<int64_t>({InputZeroPoint()}))),
::tflite::CreateTensor(
builder,
builder.CreateVector<int32_t>(Shape().data(), Shape().size()),
::tflite::TensorType_FLOAT32,
/*buffer=*/0, /*name=*/builder.CreateString("dequantizeLinearOutput")),
}};
``` | stat:awaiting tensorflower,type:bug,comp:lite,ModelOptimizationToolkit,2.17 | low | Minor |
2,613,445,764 | flutter | Clipboard has permission errors using --wasm on web build | ### Steps to reproduce
I compiled my web app to WASM, and everything works great except now I can't get the Clipboard working. Cross-origin isolation is the problem I assume, but it could just be because without it, WASM isn't working and it works as it did with JavaScript. When running non-WASM and try to paste, the browser asks for permission. Using WASM it never asks for permission, it just fails.
My app is a bit complex. It's a Chrome extension with an iframe that loads a url to a Flutter web app.
I set up my server to set the required headers for WASM to work.
```
cross-origin-embedder-policy: credentialless
cross-origin-opener-policy: same-origin
cross-origin-resource-policy: same-site
```
And the Chrome extension has this in the manifest:
```
"cross_origin_opener_policy": {
"value": "same-origin"
},
"cross_origin_embedder_policy": {
"value": "credentialless"
}
```
I had to add `allow="cross-origin-isolated"` to the iframe for WASM to work, if I remove this, it works, but I don't have WASM any longer. You can also notice I have the clipboard-read; clipboard-write permissions set. It all works perfectly non-WASM.
```
<iframe id='main-iframe' allow="cross-origin-isolated"
style="position: fixed; top: 10000px; border: none; height:100%; width:100%;" src="http://localhost:8765"
allow="geolocation; microphone; camera; clipboard-read; clipboard-write">
</iframe>
```
Testing my page for permissions:
```
const permissionStatus = await navigator.permissions.query({ name: 'clipboard-read', allowWithoutGesture: false });
permissionStatus = 'denied'
const permissionStatus = await navigator.permissions.query({ name: 'clipboard-write', allowWithoutGesture: false });
permissionStatus = 'denied'
```
From the dev console:
>The error message "[Violation] Permissions policy violation: The Clipboard API has been blocked..." indicates that your web app is trying to use the Clipboard API (specifically, navigator.clipboard.readText() or navigator.clipboard.writeText(), likely triggered by _1303 and _1304 in your code) but is being prevented by a permissions policy set on the website or by the browser.
`navigator.clipboard.writeText()` from JavaScript and `Clipboard.setData()` both fail the same way, but
if I use the keyboard, cmd-c, cmd-v, that works, but I assume the browser (chrome) is handling the keyboard?
I looked at the TextField code and it just seems to handle the context menu copy/paste, but let me know if I can use what the keyboard uses, but the keyboard doesn't ask for permission on WASM either which is weird, but I assume it's known to be a user action? If I use a right click, copy and cut both give errors. Also calling `Clipboard.setData()`, or `navigator.clipboard.writeText()` directly fails.
The Clipboard API has been blocked because of a permissions policy applied to the current document. See https://goo.gl/EuHzyv for more details.
I've spent a few days now searching for answers and have tried everything. All the different combinations of site-origin, same-origin etc. WASM is great, it runs much faster. Everything works, but I can't ship this until the Clipboard works.
It's a large private app, but if someone with expertise who needs to run my code to test, I could possibly add them as a collaborator on my Github.
Thanks.
### Expected results
`navigator.clipboard.writeText()` and `Clipboard.setData()` should work as per specification and return success.
### Actual results
Both `navigator.clipboard.writeText()` and `Clipboard.setData()` fail.
### Code sample
Please see the description above.
### Screenshots or Video
N/A
### Logs
Please see the description above.
### Flutter Doctor output
```
[✓] Flutter (Channel stable, 3.24.4, on macOS 14.7.1 23H221 darwin-arm64, locale en-US)
• Flutter version 3.24.4 on channel stable at /Users/milke/Developer/flutter
• Upstream repository https://github.com/flutter/flutter.git
• Framework revision 603104015d (17 hours ago), 2024-10-24 08:01:25 -0700
• Engine revision db49896cf2
• Dart version 3.5.4
• DevTools version 2.37.3
[✗] Android toolchain - develop for Android devices
✗ Unable to locate Android SDK.
Install Android Studio from: https://developer.android.com/studio/index.html
On first launch it will assist you in installing the Android SDK components.
(or visit https://flutter.dev/to/macos-android-setup for detailed instructions).
If the Android SDK has been installed to a custom location, please use
`flutter config --android-sdk` to update to that location.
[✓] Xcode - develop for iOS and macOS (Xcode 15.3)
• Xcode at /Applications/Xcode.app/Contents/Developer
• Build 15E204a
• CocoaPods version 1.15.0
[✓] Chrome - develop for the web
• Chrome at /Applications/Google Chrome.app/Contents/MacOS/Google Chrome
[!] Android Studio (not installed)
• Android Studio not found; download from https://developer.android.com/studio/index.html
(or visit https://flutter.dev/to/macos-android-setup for detailed instructions).
[✓] Connected device (3 available)
• macOS (desktop) • macos • darwin-arm64 • macOS 14.7.1 23H221 darwin-arm64
• Mac Designed for iPad (desktop) • mac-designed-for-ipad • darwin • macOS 14.7.1 23H221 darwin-arm64
• Chrome (web) • chrome • web-javascript • Google Chrome 129.0.6668.59
[✓] Network resources
• All expected network resources are available.
! Doctor found issues in 2 categories.
``` | platform-web,P2,needs repro info,e: web_skwasm,team-web,triaged-web | low | Critical |
2,613,455,052 | rust | Code Fails to Compile with Unnecessary `use std::borrow::Borrow;` | <!--
Thank you for filing a bug report! 🐛 Please provide a short summary of the bug,
along with any information you feel relevant to replicating the bug.
-->
I tried this code:
```rust
use std::borrow::Borrow;
struct Node<T> {
elem: T,
}
fn main() {
let a = Some(Rc::new(RefCell::new(Node { elem: 1 })));
let b = a
.as_ref()
.map(|node| Ref::map(node.borrow(), |node| &node.elem));
print!("{:?}", b);
}
```
I expected to see this happen: The code should compile successfully and print the value of elem.
Instead, this happened: The code fails to compile with an error indicating that Borrow is not resolved, leading to compilation failure. If I comment out the seemingly unnecessary `use std::borrow::Borrow;`, the code can compile.
### Meta
<!--
If you're using the stable version of the compiler, you should also check if the
bug also exists in the beta or nightly versions.
-->
`rustc --version --verbose`:
```
rustc 1.81.0 (eeb90cda1 2024-09-04)
```
<!--
Include a backtrace in the code block by setting `RUST_BACKTRACE=1` in your
environment. E.g. `RUST_BACKTRACE=1 cargo build`.
-->
<details><summary>Backtrace</summary>
<p>
```
error[E0282]: type annotations needed for `&_`
--> src/main.rs:39:46
|
39 | .map(|node| Ref::map(node.borrow(), |node| &node.elem));
| ^^^^ --------- type must be known at this point
|
help: consider giving this closure parameter an explicit type, where the type for type parameter `T` is specified
|
39 | .map(|node| Ref::map(node.borrow(), |node: &T| &node.elem));
| ++++
error[E0609]: no field `elem` on type `&_`
--> src/main.rs:39:58
|
39 | .map(|node| Ref::map(node.borrow(), |node| &node.elem));
| ^^^^ unknown field
```
</p>
</details>
| A-diagnostics,T-compiler,D-confusing | low | Critical |
2,613,537,319 | excalidraw | Prevent unintentional element movement at selection | I have been using exalidraw the last few days and there is one little thing that bothers me, if you click on an element and your mouse is not completely still the element will end up moving a little bit with the mouse.
Theoretically this is working correctly but the amount of times I have double clicked on an element and in the process the mouse has moved a pixel and therefore the element has also moved with it is quite high.
A possible solution would be to add a small timeout from the click on the element until it starts processing the mouse movement.
Maybe 0.3 seconds or so.
Just in case, Im using Firefox 128.3.1esr | enhancement | low | Major |
2,613,554,597 | go | sum.golang.org: repeated 500 internal server errors when fetching very new versions | We have had four CI jobs fail in the past week due to `sum.golang.org` reporting 500 internal server errors as well as an unexpected EOF.
* https://github.com/cue-lang/cuelang.org/actions/runs/11405713492/job/31737794702
* https://github.com/cue-lang/cuelang.org/actions/runs/11406304337/job/31739760236
* https://github.com/cue-lang/cuelang.org/actions/runs/11494340883/job/31991655336
* https://github.com/cue-lang/cuelang.org/actions/runs/11514929154/job/32054554147
The two types of errors we have seen look like:
> go: cuelang.org/go@v0.11.0-alpha.3.0.20241018144220-537f744a9cc7: verifying go.mod: cuelang.org/go@v0.11.0-alpha.3.0.20241018144220-537f744a9cc7/go.mod: reading https://sum.golang.org/lookup/cuelang.org/go@v0.11.0-alpha.3.0.20241018144220-537f744a9cc7: 500 Internal Server Error
> go: cuelang.org/go@v0.10.1: verifying module: cuelang.org/go@v0.10.1: Get "https://sum.golang.org/lookup/cuelang.org/go@v0.10.1": EOF
These CI jobs are doing what is effectively:
```
go mod init
go get cuelang.org/go@${commitRef}
```
where `${commitRef}` is a commit hash which was just pushed to master.
We are aware that `proxy.golang.org` and `sum.golang.org` may respond with status codes like 404 for the first fifteen to thirty minutes as they discover the new version (https://github.com/golang/go/issues/49916#issuecomment-984839295), but I still assume that the 500 and EOF errors are unexpected and should be fixed.
Moreover, we do dozens of these runs per week, and only very few fail, so `sum.golang.org` often answers these requests correctly without any issue. | NeedsInvestigation,Tools,proxy.golang.org | low | Critical |
2,613,555,857 | material-ui | Tabs not scroling to the correct tab after navigation | ### Steps to reproduce
Link to live example: https://codesandbox.io/p/sandbox/still-snow-z385rn
Steps:
1. Add a tabs component with more tabs then the view width can hold
2. scrollButtons="auto"
3. set the selected tab to a tab outside the view
4. refresh the view an see that the selected tab is only partly in view
Make sure to set browser width smaller then the tabs container.
<img width="699" alt="Screenshot 2024-10-25 at 11 18 35" src="https://github.com/user-attachments/assets/f5fd27b8-5969-485d-8303-8f1aeaff07a8">
You can here see a small green line and the tab is not in view.
With scrollButtons={true} it works
### Current behavior
The selected tab is not in view.
<img width="613" alt="Screenshot 2024-10-25 at 11 10 38" src="https://github.com/user-attachments/assets/70fefd9b-ad12-4eea-bc07-7979fee544ba">
### Expected behavior
The selected tab is in view.
<img width="487" alt="Screenshot 2024-10-25 at 11 11 11" src="https://github.com/user-attachments/assets/d2cc81d3-7bff-41e1-983f-5943aa62836d">
### Context
We have dynamic tabs and device sizes, and we dont want arrows all the time, but not scrolling the selected tab into view is causing out users to be confused, would be nice if the tabs component scrolled to the selected tab
### Your environment
<details>
<summary><code>npx @mui/envinfo</code></summary>
```
Browser: Chrome
System:
OS: macOS 14.7
Binaries:
Node: 20.13.1 - ~/.nvm/versions/node/v20.13.1/bin/node
npm: 10.5.2 - ~/.nvm/versions/node/v20.13.1/bin/npm
pnpm: 9.12.2 - ~/.nvm/versions/node/v20.13.1/bin/pnpm
Browsers:
Chrome: 130.0.6723.70
Edge: Not Found
Safari: 18.0.1
npmPackages:
@emotion/react: 11.10.4 => 11.10.4
@emotion/styled: 11.10.4 => 11.10.4
@mui/icons-material: 5.16.7 => 5.16.7
@mui/lab: 5.0.0-alpha.173 => 5.0.0-alpha.173
@mui/material: 5.16.7 => 5.16.7
@mui/styles: 5.16.7 => 5.16.7
@mui/system: 5.16.7 => 5.16.7
@mui/x-data-grid-premium: 7.20.0 => 7.20.0
@mui/x-date-pickers: 6.20.2 => 6.20.2
@mui/x-date-pickers-pro: 6.20.2 => 6.20.2
@mui/x-license: 7.20.0 => 7.20.0
@mui/x-tree-view: 7.20.0 => 7.20.0
@types/react: 18.3.1 => 18.3.1
react: 18.3.1 => 18.3.1
react-dom: 18.3.0 => 18.3.0
typescript: 4.6.4 => 4.6.4
```
</details>
**Search keywords**: tabs scroll | component: tabs,enhancement | low | Minor |
2,613,569,810 | rust | Fix JSON output of libtest | Right now the JSON output of libtest is a bit unusable. It outputs all of the json messages to stdout where they get mixed with the rest of the stdout.
It would be nice to be able to output it to a file (it shouldn't particularly hard to do since the `OutputFormatter` only requires `Write`) and also to be able to customize what the json formatter outputs.
@rustbot tag +T-bootrstap | C-feature-request,A-libtest,T-testing-devex | low | Minor |
2,613,580,790 | PowerToys | Multiple zones spanning across monitors | ### Description of the new feature / enhancement
We should be able to span window across multiple zones but across multiple monitors treated like separate ones. I have layout which has all monitors divided into exact quarters - and want add more zones from second one after I have filled the first one all 4 zones but need more width but not like now when all monitors are treated like one rectangle splitted...
### Scenario when this would be used?
For example very wide application use, or for example teamviewer looking on dual monitor setup with all monitors enabled in one window - then I'm able to quickly arrange this window with 2 remote monitors to 2 of my monitors with same resolution and this leads to nice showing of all information from two remote monitors on my physical monitors - also the edge of both physical monitors are like split line between two remote screens
### Supporting information
here the printscreens joined to view quickly the idea... :-)
| Needs-Triage | low | Minor |
2,613,584,455 | vscode | [NETSDKE2E] [Insiders] Asian language localization display anomalies when using tar.gz to install VS Code. | Affected Build:
VS Code 1.95.0-insider
Repro OS: Linux
Steps to Reproduce:
1. Use the tar.gz to install VS Code insiders from https://code.visualstudio.com/insiders/#linux in Linux
2. Change the VS Code language to Asian language like Simple Chinese, Japanese
3. Obverse.
Expected Result:
Asian languages need to be fully localized.
SC:
JP:
Actual Result:
Asian language localization display anomalies.
SC:
JP:
 | bug,help wanted,linux | medium | Major |
2,613,606,152 | pytorch | DISABLED test_sdpa_mask_fp16_L6_S17_NH23_HS121 (__main__.TestSDPA) | Platforms: mac, macos
This test was disabled because it is failing in CI. See [recent examples](https://hud.pytorch.org/flakytest?name=test_sdpa_mask_fp16_L6_S17_NH23_HS121&suite=TestSDPA&limit=100) and the most recent trunk [workflow logs](https://github.com/pytorch/pytorch/runs/32033795652).
Over the past 3 hours, it has been determined flaky in 4 workflow(s) with 4 failures and 4 successes.
**Debugging instructions (after clicking on the recent samples link):**
DO NOT ASSUME THINGS ARE OKAY IF THE CI IS GREEN. We now shield flaky tests from developers so CI will thus be green but it will be harder to parse the logs.
To find relevant log snippets:
1. Click on the workflow logs linked above
2. Click on the Test step of the job so that it is expanded. Otherwise, the grepping will not work.
3. Grep for `test_sdpa_mask_fp16_L6_S17_NH23_HS121`
4. There should be several instances run (as flaky tests are rerun in CI) from which you can study the logs.
<details><summary>Sample error message</summary>
```
Traceback (most recent call last):
File "/Users/ec2-user/runner/_work/pytorch/pytorch/test/test_mps.py", line 9547, in test_sdpa_mask_fp16_L6_S17_NH23_HS121
self._test_sdpa_mask(torch.float16, 7, 17, 23, 121)
File "/Users/ec2-user/runner/_work/pytorch/pytorch/test/test_mps.py", line 9535, in _test_sdpa_mask
self._compare_tensors(y.cpu(), y_ref)
File "/Users/ec2-user/runner/_work/pytorch/pytorch/test/test_mps.py", line 9459, in _compare_tensors
self.assertLess(err, 0.01)
File "/Users/ec2-user/runner/_work/_temp/conda_environment_11490952968/lib/python3.9/unittest/case.py", line 1223, in assertLess
self.fail(self._formatMessage(msg, standardMsg))
File "/Users/ec2-user/runner/_work/_temp/conda_environment_11490952968/lib/python3.9/unittest/case.py", line 676, in fail
raise self.failureException(msg)
AssertionError: nan not less than 0.01
To execute this test, run the following from the base repo dir:
python test/test_mps.py TestSDPA.test_sdpa_mask_fp16_L6_S17_NH23_HS121
This message can be suppressed by setting PYTORCH_PRINT_REPRO_ON_FAILURE=0
```
</details>
Test file path: `test_mps.py`
cc @clee2000 @malfet @albanD @kulinseth @DenisVieriu97 @jhavukainen | triaged,module: flaky-tests,module: macos,skipped,module: mps | low | Critical |
2,613,625,535 | transformers | Support dynamic batch size | ### Feature request
Hi thanks for the library! When training, I realize that, if a micro batch contains too few tokens, the throughput will be quite bad (i.e. average time per token is large). However, I cannot increase the batch size, because there are long (e.g. 2000 tokens) and short (e.g. 500 tokens) sequences in the training data. The batch size that make short sequences run fast will make long sequences OOM.
Therefore, I am proposing to have dynamic (micro) batch size. For example, suppose we have batch_size=16. Then, before this proposal, we have e.g. micro_batch_size=2 & grad_accum=8. After this proposal, for short sequences, use 4 samples in this micro batch; for long sequences, use 2 samples in this micro batch. After they sum up to 16 samples, we can compute the loss and consider this step is done.
### Motivation
(see above)
### Your contribution
I am happy to PR | trainer,Feature request | low | Minor |
2,613,738,199 | godot | Could not preload resource file / cyclic dependency ? | ### Tested versions
Reproductile in: 4.3 stable / 4.4 dev
### System information
Godot v4.4.dev1 - Windows 10.0.19045 - Vulkan (Forward+) - dedicated NVIDIA GeForce GTX 1060 6GB (NVIDIA; 32.0.15.6109) - AMD Ryzen 7 2700X Eight-Core Processor (16 Threads)
### Issue description
Some files that I preload and that worked until now decided to stop working (the links are still valid).
This is not the first time that this happens to me on this project, I use a lot of custom resources and adding a single line can sometimes cause this, I've managed to get around the problem so far, but it happened to me again, and I don't know which line caused it.
I have the impression that it is the fact of referencing a class in a cyclical way but I'm not sure and part of the problem is that it's very difficult to know which line causes this (and I get no information about the source of the problem other than the inability to preload files of a certain class)
I think that I can use load instead of preload in most cases, which should solve the problem, but it's a bit annoying to use an approach that works for days and then after a while decides to stop working without warning.
### Steps to reproduce
I'm not sure if this is exactly the problem I have in my project, because the error is not identical but in the minimum project I manage to have the panel that indicates that there is a cyclic reference when I try to assign a resource exported via the inspector.
When I try to preload this same resource I get an error that indicates that the type of the resource is "Resource" (while it is of type ResourceJob) so I think the error message is incorrect and should be the same as the one indicated in the inspector.
### Minimal reproduction project (MRP)
[BugResourcePreload.zip](https://github.com/user-attachments/files/17520664/BugResourcePreload.zip)
I manage to recreate problems by creating custom resource cyclic dependencies, but not exactly the one I get in my project.
In my project I just get the error: Parser Error: Could not preload resource file", I can share it privately if it can help to solve the problem. | bug,topic:core,topic:gdscript | low | Critical |
2,613,739,056 | next.js | shadcn components are not working with next 15 | ### Link to the code that reproduces this issue
https://github.com/SARATHKUMAR-T/next15
### To Reproduce
1. create new app with `npx create-next-app@latest`
2. try to install shadcn ui with `npx shadcn@latest init`
### Current vs. Expected behavior
### Provide environment information
```bash
Operating System:
Platform: linux
Arch: x64
Version: #47~22.04.1-Ubuntu SMP PREEMPT_DYNAMIC Wed Oct 2 16:16:55 UTC 2
Available memory (MB): 11821
Available CPU cores: 4
Binaries:
Node: 20.13.1
npm: 10.5.2
Yarn: 1.22.22
pnpm: N/A
Relevant Packages:
next: 15.0.1 // Latest available version is detected (15.0.1).
eslint-config-next: 15.0.1
react: 19.0.0-rc-69d4b800-20241021
react-dom: 19.0.0-rc-69d4b800-20241021
typescript: 5.6.3
Next.js Config:
output: N/A
```
### Which area(s) are affected? (Select all that apply)
create-next-app, Developer Experience
### Which stage(s) are affected? (Select all that apply)
next dev (local), next build (local), next start (local), Vercel (Deployed)
### Additional context
_No response_ | create-next-app,bug | low | Minor |
2,613,750,292 | rust | `Box<str>`. `Arc<str>` and `Rc<str>` should implement `AsRef<[u8]>`, `AsRef<Path>`, `AsRef<OsStr>`, and `FromStr` | The `String` and `str` type implements `AsRef<str>` and `AsRef<[u8]>`, `AsRef<Path>`, and `AsRef<OsStr>`.
Conversely, `Box<str>` implements only `AsRef<str>`.
This looks like a miss of opportunity.
`Box<str>` should also implement `AsRef<[u8]>`, `AsRef<Path>`, `AsRef<OsStr>`, and `FromStr`. | A-trait-system,T-libs-api,A-inference,C-feature-request | low | Minor |
2,613,765,293 | pytorch | RuntimeError: "addmm_cuda" not implemented for 'ComplexHalf' | ### 🐛 Describe the bug
import torch
a = torch.tensor([[1+2j, 3+4j]], dtype=torch.complex32)
b = torch.tensor([[2+3j], [4+5j]], dtype=torch.complex32)
c = a @ b
RuntimeError: "addmm_cuda" not implemented for 'ComplexHalf'
### Versions
torch 2.0.1+cuda11.8
cc @ptrblck @msaroufim @ezyang @anjali411 @dylanbespalko @mruberry @nikitaved @amjames | module: cuda,triaged,module: complex,needs design | low | Critical |
2,613,768,703 | godot | Importing a large 400mb gltf/glb file crashes at 99% | ### Tested versions
[4.4 dev3](https://godotengine.org/download/archive/4.4-dev3)
### System information
win10 21H2,Vulkan API 1.2.0
### Issue description
```
Godot Engine v4.4.dev3.official.f4af8201b - https://godotengine.org
libpng warning: iCCP: cHRM chunk does not match sRGB
Vulkan 1.3.242 - Forward+ - Using Device #0: NVIDIA - NVIDIA GeForce RTX 3080
ERROR: Basis [X: (1, 0, 0), Y: (0, 0, 0), Z: (0, 0, 1)] must be normalized in order to be casted to a Quaternion. Use get_rotation_quaternion() or call orthonormalized() if the Basis contains linearly independent vectors.
at: (core/math/basis.cpp:725)
ERROR: FATAL: Index p_index = 620 is out of bounds (count = 620).
at: operator[] (./core/templates/local_vector.h:177)
================================================================
CrashHandlerException: Program crashed with signal 4
Engine version: Godot Engine v4.4.dev3.official (f4af8201bac157b9d47e336203d3e8a8ef729de2)
Dumping the backtrace. Please include this when reporting the bug to the project developer.
[1] error(-1): no debug info in PE/COFF executable
[2] error(-1): no debug info in PE/COFF executable
[3] error(-1): no debug info in PE/COFF executable
[4] error(-1): no debug info in PE/COFF executable
[5] error(-1): no debug info in PE/COFF executable
[6] error(-1): no debug info in PE/COFF executable
[7] error(-1): no debug info in PE/COFF executable
[8] error(-1): no debug info in PE/COFF executable
[9] error(-1): no debug info in PE/COFF executable
[10] error(-1): no debug info in PE/COFF executable
[11] error(-1): no debug info in PE/COFF executable
[12] error(-1): no debug info in PE/COFF executable
[13] error(-1): no debug info in PE/COFF executable
[14] error(-1): no debug info in PE/COFF executable
[15] error(-1): no debug info in PE/COFF executable
[16] error(-1): no debug info in PE/COFF executable
[17] error(-1): no debug info in PE/COFF executable
[18] error(-1): no debug info in PE/COFF executable
[19] error(-1): no debug info in PE/COFF executable
[20] error(-1): no debug info in PE/COFF executable
[21] error(-1): no debug info in PE/COFF executable
[22] error(-1): no debug info in PE/COFF executable
[23] error(-1): no debug info in PE/COFF executable
[24] error(-1): no debug info in PE/COFF executable
[25] error(-1): no debug info in PE/COFF executable
[26] error(-1): no debug info in PE/COFF executable
[27] error(-1): no debug info in PE/COFF executable
-- END OF BACKTRACE --
================================================================
```
### Steps to reproduce
1. create new project
2. importing glb file
3. 99% crash
### Minimal reproduction project (MRP)
issue page upload file max size 25MB. so, download file look at [this](https://github.com/zedrun00/godot_issue/releases/download/1/Quarry_Slate.glb).
| bug,confirmed,topic:import,crash,topic:3d | low | Critical |
2,613,775,620 | transformers | Switch to sdpa_kernel api with newer torch version | ### System Info
- `transformers` version: 4.45.2
- Platform: Linux-5.15.0-89-generic-x86_64-with-glibc2.35
- Python version: 3.10.14
- Huggingface_hub version: 0.26.1
- Safetensors version: 0.4.5
- Accelerate version: 1.0.1
- Accelerate config: not found
- PyTorch version (GPU?): 2.5.0+cu124 (True)
- Tensorflow version (GPU?): not installed (NA)
- Flax version (CPU?/GPU?/TPU?): not installed (NA)
- Jax version: not installed
- JaxLib version: not installed
- Using distributed or parallel set-up in script?: <fill in>
- Using GPU in script?: <fill in>
- GPU type: NVIDIA GeForce RTX 4090
### Who can help?
I noticed that many files in transformers use the older sdp api `torch.backends.cuda.sdp_kernel`. We just discovered a bug in Pytorch 2.5.0 and the old sdp api that would make it run slower https://github.com/pytorch/pytorch/issues/138386
It would be a good idea to update to the new api (`from torch.nn.attention import sdpa_kernel, SDPBackend`) and set the appropriate compile flag to avoid losing as much as 20% of the performance !
### Information
- [ ] The official example scripts
- [X] My own modified scripts
### Tasks
- [ ] An officially supported task in the `examples` folder (such as GLUE/SQuAD, ...)
- [ ] My own task or dataset (give details below)
### Reproduction
Gist here as a reference example: https://gist.github.com/mobicham/aa1e77689d9cf866cbea2cb75a53a9e4
More details in the torch issue: https://github.com/pytorch/pytorch/issues/138386
### Expected behavior
Examples using sdp with torch 2.5.0 should run at least as fast as 2.4.1 | Documentation,Good Second Issue,bug | low | Critical |
2,613,798,164 | PowerToys | Preview in File Explorer for .txt files Button Inverted | ### Microsoft PowerToys version
0.85.1
### Installation method
GitHub
### Running as admin
Yes
### Area(s) with issue?
General
### Steps to reproduce
Just to mention that in the Explorer file preview for .txt files, I need to deactivate the button for it to work, and when activated, it disables the preview. So, I think the function is simply inverted.
### ✔️ Expected Behavior
_No response_
### ❌ Actual Behavior
_No response_
### Other Software
_No response_ | Issue-Bug,Needs-Triage | low | Minor |
2,613,806,517 | pytorch | Select SDPA backend smartly by `sdp_params` and benchmark results | ### 🚀 The feature, motivation and pitch
Right now, the used SDPA backend is selected by a static priority order list:
``` python
std::array<SDPBackend, num_backends> priority_order(sdp_params const& params) {
constexpr std::array<SDPBackend, num_backends> default_order{
SDPBackend::flash_attention,
SDPBackend::efficient_attention,
SDPBackend::math,
SDPBackend::cudnn_attention,
};
return default_order;
}
```
It was reasonable as `flash_attention` (v2) is universally faster than `efficient_attention` and `math`.
But for some new backends, the order is not always static. Some backends may focus on performance improvement in some specific settings but may not perform well in other settings. As the benchmark results are shown by #137901 , CuDNN will be faster than Flash Attention v3 when `seqlen < 8k`, but the order will be reversed when `seqlen > 8k`.
Can I propose that we use a benchmark result file to build the priority order list for different `sdp_params` settings (e.g., `head_dim`, `seq_len`, `is_causal`, `dtype`, etc.)?
There are two options:
1. We run the complete benchmark for all the possible settings and collect the results to build the priority order mesh. But it will be very hard as the backend performance relies on not only `sdp_params` but also the dependent libraries (CUDA version, CuDNN version) and hardware (GPU arch).
2. **Suggested:** We ask the user to run our benchmark script and cache the result. Then the backend selector loads the cache to determine which backend is better in different `sdp_params` settings. Similar to how the package manager (e.g., `apt`, `dnf`, `pacman`) selects the fastest mirror.
I can lead this effort if people are interested in it :)
### Alternatives
_No response_
### Additional context
_No response_
cc @jbschlosser @bhosmer @cpuhrsch @erichan1 @drisspg @mikaylagawarecki | triaged,module: sdpa | low | Major |
2,613,915,471 | go | cmd/go: support passing @args-file to -toolexec commands | ### Go version
go version go1.23.2 linux/arm64
### Output of `go env` in your module/workspace:
```shell
GO111MODULE=''
GOARCH='arm64'
GOBIN=''
GOCACHE='/root/.cache/go-build'
GOENV='/root/.config/go/env'
GOEXE=''
GOEXPERIMENT=''
GOFLAGS=''
GOHOSTARCH='arm64'
GOHOSTOS='linux'
GOINSECURE=''
GOMODCACHE='/go/pkg/mod'
GONOPROXY=''
GONOSUMDB=''
GOOS='linux'
GOPATH='/go'
GOPRIVATE=''
GOPROXY='https://proxy.golang.org,direct'
GOROOT='/usr/local/go'
GOSUMDB='sum.golang.org'
GOTMPDIR=''
GOTOOLCHAIN='local'
GOTOOLDIR='/usr/local/go/pkg/tool/linux_arm64'
GOVCS=''
GOVERSION='go1.23.2'
GODEBUG=''
GOTELEMETRY='local'
GOTELEMETRYDIR='/root/.config/go/telemetry'
GCCGO='gccgo'
GOARM64='v8.0'
AR='ar'
CC='gcc'
CXX='g++'
CGO_ENABLED='1'
GOMOD='/Users/romain.marcadier/Development/Datadog/orchestrion/go.mod'
GOWORK=''
CGO_CFLAGS='-O2 -g'
CGO_CPPFLAGS=''
CGO_CXXFLAGS='-O2 -g'
CGO_FFLAGS='-O2 -g'
CGO_LDFLAGS='-O2 -g'
PKG_CONFIG='pkg-config'
GOGCCFLAGS='-fPIC -pthread -Wl,--no-gc-sections -fmessage-length=0 -ffile-prefix-map=/tmp/go-build89119916=/tmp/go-build -gno-record-gcc-switches'
```
### What did you do?
The following command works as intended:
```console
$ go build -a github.com/elastic/go-elasticsearch/v8/typedapi/types
```
However if you use any `-toolexec` value, it suddenly fails on Windows:
```console
$ go build -toolexec="D:\\a\\orchestrion\\orchestrion\\bin\\orchestrion.exe" -a github.com/elastic/go-elasticsearch/v8/typedapi/types
fork/exec D:\\a\\orchestrion\\orchestrion\\bin\\orchestrion.exe: The filename or extension is too long.
```
This is because the `github.com/elastic/go-elasticsearch/v8/typedapi/types` package contains _a metric ton_ of files, and results in an excessively long command line for Windows.
### What did you see happen?
What we observe is that when there is no `-toolexec` the Windows arguments size limit (of 32KiB) is "worked around" by passing an `@args-file` value that contains all the arguments instead of passing the arguments list itself directly...
Unfortunately, the use of `-toolexec` appears to disable this mechanism, making it impossible to build packages with very large amounts of files in them on Windows.
I have verified this behavior using `strace` on a Linux machine... I expect the same behavior happens on Windows as well and explains our issue here...
### What did you expect to see?
I expect a package that successfully builds without `-toolexec` to also be build-able with `-toolexec`, and for the `-toolexec` tool to actually also receive the arguments file stand-in when appropriate. | NeedsInvestigation | low | Critical |
2,613,957,528 | next.js | Confusing error when calling a server function from use cache scope | ### Link to the code that reproduces this issue
n/a
### To Reproduce
```js
export default async function Main({ searchParams }) {
const data = await searchParams;
return (
<Parent getStuff={() => <h2>huh {data.foo}</h2>}></Parent>
);
}
```
```js
"use cache";
export default async function Parent({ getStuff }) {
console.log("render Parent");
return (
<>
{getStuff()}
</>
);
}
```
produces
```
[ Cache ] Error: Attempted to call a temporary Client Reference from the server but it is on the client. It's not possible to invoke a client function from the server, it can only be rendered as a Component or passed to props of a Client Component.
```
The confusing part is that the Client/Server wording here is wrong because it's really about Server/Cache.
### Current vs. Expected behavior
n/a
### Provide environment information
```bash
n/a
```
### Which area(s) are affected? (Select all that apply)
Developer Experience
### Which stage(s) are affected? (Select all that apply)
next dev (local)
### Additional context
_No response_ | bug,invalid link,dynamicIO | low | Critical |
2,613,989,702 | react | Confusing error when calling a temporary reference function from a non-Client environment | See https://github.com/vercel/next.js/issues/71859. | React Core Team,React 19 | medium | Critical |
2,614,022,999 | pytorch | DISABLED test_byte_mask (__main__.TestAdvancedIndexing) | Platforms: mac, macos
This test was disabled because it is failing in CI. See [recent examples](https://hud.pytorch.org/flakytest?name=test_byte_mask&suite=TestAdvancedIndexing&limit=100) and the most recent trunk [workflow logs](https://github.com/pytorch/pytorch/runs/32037936303).
Over the past 3 hours, it has been determined flaky in 6 workflow(s) with 6 failures and 6 successes.
**Debugging instructions (after clicking on the recent samples link):**
DO NOT ASSUME THINGS ARE OKAY IF THE CI IS GREEN. We now shield flaky tests from developers so CI will thus be green but it will be harder to parse the logs.
To find relevant log snippets:
1. Click on the workflow logs linked above
2. Click on the Test step of the job so that it is expanded. Otherwise, the grepping will not work.
3. Grep for `test_byte_mask`
4. There should be several instances run (as flaky tests are rerun in CI) from which you can study the logs.
<details><summary>Sample error message</summary>
```
Traceback (most recent call last):
File "/Users/ec2-user/runner/_work/pytorch/pytorch/test/test_mps.py", line 11258, in test_byte_mask
self.assertEqual(len(w), 2)
File "/Users/ec2-user/runner/_work/_temp/conda_environment_11492285962/lib/python3.9/site-packages/torch/testing/_internal/common_utils.py", line 3903, in assertEqual
raise error_metas.pop()[0].to_error(
AssertionError: Scalars are not equal!
Expected 2 but got 3.
Absolute difference: 1
Relative difference: 0.5
To execute this test, run the following from the base repo dir:
python test/test_mps.py TestAdvancedIndexing.test_byte_mask
This message can be suppressed by setting PYTORCH_PRINT_REPRO_ON_FAILURE=0
```
</details>
Test file path: `test_mps.py`
cc @clee2000 @malfet @albanD @kulinseth @DenisVieriu97 @jhavukainen | triaged,module: flaky-tests,module: macos,skipped,module: mps | low | Critical |
2,614,065,155 | node | Invalid sqlite behavior about unused named parameter | ### Version
all
### Platform
```text
all
```
### Subsystem
sqlite
### What steps will reproduce the bug?
IMO, there is an issue with SQLite's behavior, as highlighted by the current test (https://github.com/nodejs/node/blob/main/test/parallel/test-sqlite-named-parameters.js#L17-L32):
```
test('throws on unknown named parameters', (t) => {
const db = new DatabaseSync(nextDb());
t.after(() => { db.close(); });
const setup = db.exec(
'CREATE TABLE types(key INTEGER PRIMARY KEY, val INTEGER) STRICT;'
);
t.assert.strictEqual(setup, undefined);
t.assert.throws(() => {
const stmt = db.prepare('INSERT INTO types (key, val) VALUES ($k, $v)');
stmt.run({ $k: 1, $unknown: 1 });
}, {
code: 'ERR_INVALID_STATE',
message: /Unknown named parameter '\$unknown'/,
});
});
```
### How often does it reproduce? Is there a required condition?
NA
### What is the expected behavior? Why is that the expected behavior?
IMO, as mentioned earlier [here](https://github.com/nodejs/node/pull/53752#discussion_r1803814451), it should be permissible to set more parameters (such as the `$unknown` parameter of this test) than those actually used in the SQL string.
This approach is utilized by better-sqlite3 and is particularly useful when conditionally constructing your WHERE clause with parameters that may or may not be used in the final query.
The code and the associated error test should be modified to throw an error regarding the `$v` named parameter instead, similar to the behavior of better-sqlite3.
### What do you see instead?
NA
### Additional information
_No response_ | discuss,sqlite | low | Critical |
2,614,084,606 | youtube-dl | Sign in to confirm you’re not a bot - message unclear | <!--
######################################################################
WARNING!
IGNORING THE FOLLOWING TEMPLATE WILL RESULT IN ISSUE CLOSED AS INCOMPLETE
######################################################################
-->
## Checklist
<!--
Carefully read and work through this check list in order to prevent the most common mistakes and misuse of youtube-dl:
- First of, make sure you are using the latest version of youtube-dl. Run `youtube-dl --version` and ensure your version is 2021.12.17. If it's not, see https://yt-dl.org/update on how to update. Issues with outdated version will be REJECTED.
- Make sure that all provided video/audio/playlist URLs (if any) are alive and playable in a browser.
- Make sure that all URLs and arguments with special characters are properly quoted or escaped as explained in http://yt-dl.org/escape.
- Search the bugtracker for similar issues: http://yt-dl.org/search-issues. DO NOT post duplicates.
- Read bugs section in FAQ: http://yt-dl.org/reporting
- Finally, put x into all relevant boxes (like this [x])
-->
- [?] I'm reporting a broken site support issue - I don't know what the difference is between a "site support issue" and any other type of issue. I think this _might_ be a site support issue?
- [x] I've verified that I'm running youtube-dl version **2021.12.17**
- [x] I've checked that all provided URLs are alive and playable in a browser
- [x] I've checked that all URLs and arguments with special characters are properly quoted or escaped
- [x] I've searched the bugtracker for similar bug reports including closed ones
- [x] I've read bugs section in FAQ
## Verbose log
<!--
Provide the complete verbose output of youtube-dl that clearly demonstrates the problem.
Add the `-v` flag to your command line you run youtube-dl with (`youtube-dl -v <your command line>`), copy the WHOLE output and insert it below. It should look similar to this:
[debug] System config: []
[debug] User config: []
[debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj']
[debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251
[debug] youtube-dl version 2021.12.17
[debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2
[debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4
[debug] Proxy map: {}
<more lines>
-->
```
$ youtube-dl -v "https://www.youtube.com/watch?v=zvP3FJfPgx8"
[debug] System config: []
[debug] User config: []
[debug] Custom config: []
[debug] Command-line args: ['-v', 'https://www.youtube.com/watch?v=zvP3FJfPgx8']
[debug] Encodings: locale UTF-8, fs utf-8, out utf-8, pref UTF-8
[debug] youtube-dl version 2021.12.17
[debug] Python 3.12.3 (CPython x86_64 64bit) - Linux-6.8.0-47-generic-x86_64-with-glibc2.39 - OpenSSL 3.0.13 30 Jan 2024 - glibc 2.39
[debug] exe versions: none
[debug] Proxy map: {}
[youtube] zvP3FJfPgx8: Downloading webpage
ERROR: Sign in to confirm you’re not a bot
This helps protect our community. Learn more
Traceback (most recent call last):
File "/home/matthew/venv/lib/python3.12/site-packages/youtube_dl/YoutubeDL.py", line 875, in wrapper
return func(self, *args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/matthew/venv/lib/python3.12/site-packages/youtube_dl/YoutubeDL.py", line 971, in __extract_info
ie_result = ie.extract(url)
^^^^^^^^^^^^^^^
File "/home/matthew/venv/lib/python3.12/site-packages/youtube_dl/extractor/common.py", line 571, in extract
ie_result = self._real_extract(url)
^^^^^^^^^^^^^^^^^^^^^^^
File "/home/matthew/venv/lib/python3.12/site-packages/youtube_dl/extractor/youtube.py", line 2248, in _real_extract
raise ExtractorError(reason, expected=True)
youtube_dl.utils.ExtractorError: Sign in to confirm you’re not a bot
This helps protect our community. Learn more
```
## Description
<!--
Provide an explanation of your issue in an arbitrary form. Please make sure the description is worded well enough to be understood, see https://github.com/ytdl-org/youtube-dl#is-the-description-of-the-issue-itself-sufficient. Provide any additional information, suggested solution and as much context and examples as possible.
If work on your issue requires account credentials please provide them or explain how one can obtain them.
-->
... (and this time using the issue template)
When trying to download some videos, I get an error message, telling me to sign in and confirm I'm not a bot. The error message appears incomplete, so it's hard for me to know how to sign in, or learn more.
Steps to reproduce:
```
$ youtube-dl -v "https://www.youtube.com/watch?v=VsG4zXzQwBs"
[debug] System config: []
[debug] User config: []
[debug] Custom config: []
[debug] Command-line args: ['-v', 'https://www.youtube.com/watch?v=VsG4zXzQwBs']
[debug] Encodings: locale UTF-8, fs utf-8, out utf-8, pref UTF-8
[debug] youtube-dl version 2021.12.17
[debug] Python 3.12.3 (CPython x86_64 64bit) - Linux-6.8.0-47-generic-x86_64-with-glibc2.39 - OpenSSL 3.0.13 30 Jan 2024 - glibc 2.39
[debug] exe versions: none
[debug] Proxy map: {}
[youtube] VsG4zXzQwBs: Downloading webpage
ERROR: Sign in to confirm you’re not a bot
This helps protect our community. Learn more
Traceback (most recent call last):
File "/home/matthew/venv/lib/python3.12/site-packages/youtube_dl/YoutubeDL.py", line 875, in wrapper
return func(self, *args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/matthew/venv/lib/python3.12/site-packages/youtube_dl/YoutubeDL.py", line 971, in __extract_info
ie_result = ie.extract(url)
^^^^^^^^^^^^^^^
File "/home/matthew/venv/lib/python3.12/site-packages/youtube_dl/extractor/common.py", line 571, in extract
ie_result = self._real_extract(url)
^^^^^^^^^^^^^^^^^^^^^^^
File "/home/matthew/venv/lib/python3.12/site-packages/youtube_dl/extractor/youtube.py", line 2248, in _real_extract
raise ExtractorError(reason, expected=True)
youtube_dl.utils.ExtractorError: Sign in to confirm you’re not a bot
This helps protect our community. Learn more
```
There's two things about this error message which I think should be improved:
1. Sign in? How? Where? The error message does not say, and the [readme](https://github.com/ytdl-org/youtube-dl) does not mention the phrase "sign in".
2. "Learn more" - ok, how? Where? It seems like the rest of that sentence is missing, or perhaps this was supposed to be rendered as a hyperlink to something?
Note that I don't get this behavior for all videos. This one worked:
```
$ youtube-dl -v "https://www.youtube.com/watch?v=wOvyF6jFKa8"
[debug] System config: []
[debug] User config: []
[debug] Custom config: []
[debug] Command-line args: ['-v', 'https://www.youtube.com/watch?v=wOvyF6jFKa8']
[debug] Encodings: locale UTF-8, fs utf-8, out utf-8, pref UTF-8
[debug] youtube-dl version 2021.12.17
[debug] Python 3.12.3 (CPython x86_64 64bit) - Linux-6.8.0-47-generic-x86_64-with-glibc2.39 - OpenSSL 3.0.13 30 Jan 2024 - glibc 2.39
[debug] exe versions: none
[debug] Proxy map: {}
[youtube] wOvyF6jFKa8: Downloading webpage
[youtube] wOvyF6jFKa8: Downloading player fb725ac8
[debug] [youtube] Decrypted nsig VH0az-_4sTterYE2 => I_HeD02AtpQ_XA
[debug] [youtube] Decrypted nsig 7t_v2cysifiN8ObX => yhctZpqRjAGNWg
[debug] Default format spec: best/bestvideo+bestaudio
[debug] Invoking downloader on 'https://rr2---sn-25ge7nzk.googlevideo.com/videoplayback?expire=1729883126&ei=lpcbZ-uSOem3mLAPqKDk6Qs&ip=80.239.186.177&id=o-AP5Ix71aMWUT1ifJRCanuEz7GeCEfJt03q3eB1ulYjtC&itag=18&source=youtube&requiressl=yes&xpc=EgVo2aDSNQ%3D%3D&met=1729861526%2C&mh=g0&mm=31%2C26&mn=sn-25ge7nzk%2Csn-5hneknek&ms=au%2Conr&mv=m&mvi=2&pl=27&rms=au%2Cau&initcwndbps=651250&bui=AQn3pFSYT6282GQSSkXGknnOUsvKVprkaQ8uojZlwJJnjZbJwueSuzbZDqdzZTOkKpHub7b5oOj5dmy1&spc=qtApAc1u6Ar0zfFF0FZkcota8GELVKmlaHw3o7kaqk0-pl6lCgNvcvOejRmpQcA&vprv=1&svpuc=1&mime=video%2Fmp4&ns=Ztku3Eph-tS4WuW2uAkiH3AQ&rqh=1&gir=yes&clen=40429114&ratebypass=yes&dur=464.399&lmt=1712638545393852&mt=1729861298&fvip=1&fexp=51312688%2C51326931&c=WEB&sefc=1&txp=5319224&n=I_HeD02AtpQ_XA&sparams=expire%2Cei%2Cip%2Cid%2Citag%2Csource%2Crequiressl%2Cxpc%2Cbui%2Cspc%2Cvprv%2Csvpuc%2Cmime%2Cns%2Crqh%2Cgir%2Cclen%2Cratebypass%2Cdur%2Clmt&sig=AJfQdSswRQIgddk3yXeXpe6WWVRHXykGIWeruEQK-qqc2sSP0NexNmoCIQC4w1kCa9e05e-tzrqeZAkMh9QqdekpZgsaqQmlgj1Fvw%3D%3D&lsparams=met%2Cmh%2Cmm%2Cmn%2Cms%2Cmv%2Cmvi%2Cpl%2Crms%2Cinitcwndbps&lsig=ACJ0pHgwRgIhAIrz3AW5zAbc7L0_R29UJXb25YoUEuQem5htbKeLmfzQAiEAyO7zCn6j2dfgHQKzDACPDo_6S1SE4pprbXCof_2mepo%3D'
[download] Destination: Je teste mon cadeau de Noël 🎁 - B1 #8-wOvyF6jFKa8.mp4
[download] 100% of 38.56MiB in 00:32
```
There are of course several duplicates of this, (almost) all closed because they were low-effort tickets without the debug info. (Wow those really were low-effort posts. I feel sorry for the maintainers.) Hopefully I've met the requirements for using the template etc.
* #32920
* #32915
* #32913
* #32933 | broken-IE | low | Critical |
2,614,088,756 | langchain | How do I use langchain for vllm serve tool calls？ | ### Checked other resources
- [X] I added a very descriptive title to this issue.
- [X] I searched the LangChain documentation with the integrated search.
- [X] I used the GitHub search to find a similar question and didn't find it.
- [X] I am sure that this is a bug in LangChain rather than my code.
- [X] The bug is not resolved by updating to the latest stable version of LangChain (or the specific integration package).
### Example Code
```
llm = ChatOpenAI(
api_key="api_key",
temperature=0.1,
top_p=0.7,
max_tokens=8192,
model="glm4-9b-chat",
base_url="http://host:port/v1/"
)
tools = {"weather": weather}
context = []
def process_query(query):
global context
context.append({"role": "user", "content": query})
response = llm_with_tools.invoke(context)
print(response)
if response.tool_calls:
tool_call = response.tool_calls[0]
tool_name = tool_call["name"]
tool = tools[tool_name]
tool_arguments = tool_call["args"]
tool_result = tool(**tool_arguments)
context.append({"role": "system", "content": f"你可以通过工具得到实时的天气信息，工具得到的结果是：\n\n{tool_result}\n\n，这个结果绝对准确，你可以直接使用该结果进行表述。"})
response = llm.invoke(context)
context.append({"role": "assistant", "content": response.content})
return response.content
query_1 = "今天深圳的天气怎么样?"
response_1 = process_query(query_1)
print("LLM_response:", response_1)
```
#### vLLM command：
`vllm serve glm-4-9b-chat_path --served-model-name glm4-9b-chat --host xxx --port xxx --max_model_len=128000 --tensor_parallel_size 2 --gpu_memory_utilization 0.4 --trust_remote_code`
### Error Message and Stack Trace (if applicable)
*
### Description
I try to use `vLLM serve` and langchain to make `function call`.
### System Info
`vLLM=0.6.3` | stale | low | Critical |
2,614,145,495 | langchain | AzureSearch error | ### Checked other resources
- [X] I added a very descriptive title to this issue.
- [X] I searched the LangChain documentation with the integrated search.
- [X] I used the GitHub search to find a similar question and didn't find it.
- [X] I am sure that this is a bug in LangChain rather than my code.
- [X] The bug is not resolved by updating to the latest stable version of LangChain (or the specific integration package).
### Example Code
```
index_name: str = "langchain-vector-demo"
vector_store: AzureSearch = AzureSearch(
azure_search_endpoint=vector_store_address,
azure_search_key=vector_store_password,
index_name=index_name,
embedding_function=embeddings.embed_query,
)
```
### Error Message and Stack Trace (if applicable)
Exception ignored in: <function AzureSearch.__del__ at 0x000002B588070FE0>
Traceback (most recent call last):
File "C:\Users\n\AppData\Local\Programs\Python\Python311\Lib\site-packages\langchain_community\vectorstores\azuresearch.py", line 393, in __del__
File "C:\Users\n\AppData\Local\Programs\Python\Python311\Lib\asyncio\events.py", line 761, in get_event_loop_policy
File "C:\Users\n\AppData\Local\Programs\Python\Python311\Lib\asyncio\events.py", line 754, in _init_event_loop_policy
ImportError: sys.meta_path is None, Python is likely shutting down
### Description
Made everything as here:
https://python.langchain.com/docs/integrations/vectorstores/azuresearch/
when calling it i get error like above
### System Info
python 3.12
langchain latest | Ɑ: vector store | low | Critical |
2,614,145,875 | godot | Godot crashes when the logger is configured to log in a relative path | ### Tested versions
Reproducible in 4.3.stable, 4.2.1.stable, and likely in older versions.
### System information
Windows 10, Godot 4.3
### Issue description
Godot crashes when the logger is configured to write log files in a path that is relative to the project or working directory path.
It only fails when it needs to create a folder. If the folder already exists, the logger works correctly.
### Steps to reproduce
- Start with an empty project
- Go to Project Settings and enable Advanced Settings
- Set the `Debug>File Logging>Log Path` setting to any of these:
- `logs/my_project.log`
- `res://logs/my_project.log`
- Run the project
### Minimal reproduction project (MRP)
An empty project will do | bug,topic:core,crash | low | Critical |
2,614,152,147 | go | x/tools/gopls: "edit does not belong to syntax of package %q" bug in golang.Rename | ```
#!stacks
"bug.Reportf" && "golang.(*renamer).update:+45"
```
Issue created by [stacks](https://pkg.go.dev/golang.org/x/tools/gopls/internal/telemetry/cmd/stacks).
```go
pgf, ok := enclosingFile(r.pkg, item.node.Pos())
if !ok {
bug.Reportf("edit does not belong to syntax of package %q", r.pkg)
continue
}
```
This stack `4VHVlA` was [reported by telemetry](https://storage.googleapis.com/prod-telemetry-merged/2024-10-24.json):
- `gopls/bug`
- [`golang.org/x/tools/gopls/internal/util/bug.report:+35`](https://cs.opensource.google/go/x/tools/+/gopls/v0.16.2:gopls/internal/util/bug/bug.go;l=109)
- [`golang.org/x/tools/gopls/internal/util/bug.Reportf:+1`](https://cs.opensource.google/go/x/tools/+/gopls/v0.16.2:gopls/internal/util/bug/bug.go;l=54)
- [`golang.org/x/tools/gopls/internal/golang.(*renamer).update:+45`](https://cs.opensource.google/go/x/tools/+/gopls/v0.16.2:gopls/internal/golang/rename.go;l=1056)
- [`golang.org/x/tools/gopls/internal/golang.renameObjects:+31`](https://cs.opensource.google/go/x/tools/+/gopls/v0.16.2:gopls/internal/golang/rename.go;l=998)
- [`golang.org/x/tools/gopls/internal/golang.renameOrdinary:+99`](https://cs.opensource.google/go/x/tools/+/gopls/v0.16.2:gopls/internal/golang/rename.go;l=392)
- [`golang.org/x/tools/gopls/internal/golang.Rename:+18`](https://cs.opensource.google/go/x/tools/+/gopls/v0.16.2:gopls/internal/golang/rename.go;l=237)
- [`golang.org/x/tools/gopls/internal/server.(*server).Rename:+17`](https://cs.opensource.google/go/x/tools/+/gopls/v0.16.2:gopls/internal/server/rename.go;l=36)
- [`golang.org/x/tools/gopls/internal/protocol.serverDispatch:+489`](https://cs.opensource.google/go/x/tools/+/gopls/v0.16.2:gopls/internal/protocol/tsserver.go;l=657)
- [`golang.org/x/tools/gopls/internal/lsprpc.(*streamServer).ServeStream.ServerHandler.func3:+5`](https://cs.opensource.google/go/x/tools/+/gopls/v0.16.2:gopls/internal/protocol/protocol.go;l=160)
- [`golang.org/x/tools/gopls/internal/lsprpc.(*streamServer).ServeStream.handshaker.func4:+52`](https://cs.opensource.google/go/x/tools/+/gopls/v0.16.2:gopls/internal/lsprpc/lsprpc.go;l=509)
- [`golang.org/x/tools/gopls/internal/protocol.Handlers.MustReplyHandler.func1:+2`](https://cs.opensource.google/go/x/tools/+/gopls/v0.16.2:internal/jsonrpc2/handler.go;l=35)
- [`golang.org/x/tools/gopls/internal/protocol.Handlers.AsyncHandler.func2.2:+3`](https://cs.opensource.google/go/x/tools/+/gopls/v0.16.2:internal/jsonrpc2/handler.go;l=103)
- `runtime.goexit:+0`
```
golang.org/x/tools/gopls@v0.16.2 go1.23.0 darwin/arm64 vscode (1)
```
| NeedsInvestigation,gopls,Tools,gopls/telemetry-wins | low | Critical |
2,614,179,769 | deno | Spelling mistake Genereate in deno --help | Version: Deno 2.0.2
In `deno --help` it says `Genereate and show documentation for a module or built-ins`, but it should probably start with `Generate` rather than `Genereate`. I had a Google just in case `Genereate` was a thing but it looks like it's just a spelling mistake.
**Steps to reproduce**
1. Type in `deno --help` | bug,good first issue | low | Minor |
2,614,220,597 | rust | ICE: `missing binding mode` | <!--
[31mICE[0m: Rustc ./a.rs '' 'thread 'rustc' panicked at compiler/rustc_hir_typeck/src/upvar.rs:1791:70: 'missing binding mode'', 'thread 'rustc' panicked at compiler/rustc_hir_typeck/src/upvar.rs:1791:70: 'missing binding mode''
File: /tmp/im/a.rs
-->
auto-reduced (treereduce-rust):
````rust
async unsafe extern "C-cmse-nonsecure-entry" fn multiple_named_lifetimes<T: Unpin>(_: u8, ...) {}
````
original:
````rust
#![feature("{}" a)]
async unsafe extern "C-cmse-nonsecure-entry" fn multiple_named_lifetimes<T: Unpin>(_: u8, ...) { while main { } }
//~^ ERROR hidden type for `impl Future<Output = ()>` captures lifetime that does not appear in bounds
fn my_fn(_args: &[A]) {
println!("hello world");
}
````
Version information
````
rustc 1.84.0-nightly (97ae1df8a 2024-10-25)
binary: rustc
commit-hash: 97ae1df8aa9fa6dfd29dced18b232d25208c4111
commit-date: 2024-10-25
host: x86_64-unknown-linux-gnu
release: 1.84.0-nightly
LLVM version: 19.1.1
````
Possibly related line of code:
https://github.com/rust-lang/rust/blob/97ae1df8aa9fa6dfd29dced18b232d25208c4111/compiler/rustc_hir_typeck/src/upvar.rs#L1785-L1797
Command:
`/home/matthias/.rustup/toolchains/master/bin/rustc `
<details><summary><strong>Program output</strong></summary>
<p>
```
error[E0670]: `async fn` is not permitted in Rust 2015
--> /tmp/icemaker_global_tempdir.4Ax9UanUShFv/rustc_testrunner_tmpdir_reporting.IEMd1DzRNcyR/mvce.rs:1:1
|
1 | async unsafe extern "C-cmse-nonsecure-entry" fn multiple_named_lifetimes<T: Unpin>(_: u8, ...) {}
| ^^^^^ to use `async fn`, switch to Rust 2018 or later
|
= help: pass `--edition 2021` to `rustc`
= note: for more on editions, read https://doc.rust-lang.org/edition-guide
error: only foreign, `unsafe extern "C"`, or `unsafe extern "C-unwind"` functions may have a C-variadic arg
--> /tmp/icemaker_global_tempdir.4Ax9UanUShFv/rustc_testrunner_tmpdir_reporting.IEMd1DzRNcyR/mvce.rs:1:91
|
1 | async unsafe extern "C-cmse-nonsecure-entry" fn multiple_named_lifetimes<T: Unpin>(_: u8, ...) {}
| ^^^
error[E0658]: C-cmse-nonsecure-entry ABI is experimental and subject to change
--> /tmp/icemaker_global_tempdir.4Ax9UanUShFv/rustc_testrunner_tmpdir_reporting.IEMd1DzRNcyR/mvce.rs:1:21
|
1 | async unsafe extern "C-cmse-nonsecure-entry" fn multiple_named_lifetimes<T: Unpin>(_: u8, ...) {}
| ^^^^^^^^^^^^^^^^^^^^^^^^
|
= note: see issue #75835 <https://github.com/rust-lang/rust/issues/75835> for more information
= help: add `#![feature(cmse_nonsecure_entry)]` to the crate attributes to enable
= note: this compiler was built on 2024-10-25; consider upgrading it if it is out of date
error[E0658]: C-variadic functions are unstable
--> /tmp/icemaker_global_tempdir.4Ax9UanUShFv/rustc_testrunner_tmpdir_reporting.IEMd1DzRNcyR/mvce.rs:1:1
|
1 | async unsafe extern "C-cmse-nonsecure-entry" fn multiple_named_lifetimes<T: Unpin>(_: u8, ...) {}
| ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
|
= note: see issue #44930 <https://github.com/rust-lang/rust/issues/44930> for more information
= help: add `#![feature(c_variadic)]` to the crate attributes to enable
= note: this compiler was built on 2024-10-25; consider upgrading it if it is out of date
error[E0601]: `main` function not found in crate `mvce`
--> /tmp/icemaker_global_tempdir.4Ax9UanUShFv/rustc_testrunner_tmpdir_reporting.IEMd1DzRNcyR/mvce.rs:1:98
|
1 | async unsafe extern "C-cmse-nonsecure-entry" fn multiple_named_lifetimes<T: Unpin>(_: u8, ...) {}
| ^ consider adding a `main` function to `/tmp/icemaker_global_tempdir.4Ax9UanUShFv/rustc_testrunner_tmpdir_reporting.IEMd1DzRNcyR/mvce.rs`
thread 'rustc' panicked at compiler/rustc_hir_typeck/src/upvar.rs:1791:70:
missing binding mode
stack backtrace:
0: 0x77075a09d83a - <std::sys::backtrace::BacktraceLock::print::DisplayBacktrace as core::fmt::Display>::fmt::hcedb2fcda5cdd07c
1: 0x77075a8041ca - core::fmt::write::haa85bbf9373b67e8
2: 0x77075baa39d1 - std::io::Write::write_fmt::hd17b6cdad4d5e705
3: 0x77075a09d692 - std::sys::backtrace::BacktraceLock::print::h50f59795d6a1f7e3
4: 0x77075a09fb96 - std::panicking::default_hook::{{closure}}::h0966ca81a9d29c3a
5: 0x77075a09f9e0 - std::panicking::default_hook::h534e5141a1b02198
6: 0x770759119f9f - std[a151dedc4facde64]::panicking::update_hook::<alloc[946be05e1a1394f6]::boxed::Box<rustc_driver_impl[bf30803df350f481]::install_ice_hook::{closure#0}>>::{closure#0}
7: 0x77075a0a02a8 - std::panicking::rust_panic_with_hook::h0090c4c2e6e5d265
8: 0x77075a0a007a - std::panicking::begin_panic_handler::{{closure}}::h5174eb866483fbac
9: 0x77075a09dce9 - std::sys::backtrace::__rust_end_short_backtrace::h334590b8864eb5e5
10: 0x77075a09fd3c - rust_begin_unwind
11: 0x770756ae3320 - core::panicking::panic_fmt::h307156d14c26e2e0
12: 0x77075713fbab - core::option::expect_failed::heb168b2a112ea99d
13: 0x77075c174c06 - <rustc_hir_typeck[a8c3eaf7852a1958]::fn_ctxt::FnCtxt>::determine_capture_mutability.cold
14: 0x77075b2352d0 - <rustc_hir_typeck[a8c3eaf7852a1958]::fn_ctxt::FnCtxt>::compute_min_captures
15: 0x770757910477 - <rustc_hir_typeck[a8c3eaf7852a1958]::fn_ctxt::FnCtxt>::analyze_closure
16: 0x7707575d564a - <rustc_hir_typeck[a8c3eaf7852a1958]::upvar::InferBorrowKindVisitor as rustc_hir[227b0424fb17eaca]::intravisit::Visitor>::visit_expr
17: 0x77075aaea4a5 - rustc_hir_typeck[a8c3eaf7852a1958]::typeck
18: 0x77075aae9ac7 - rustc_query_impl[6ffb465cf6366f2]::plumbing::__rust_begin_short_backtrace::<rustc_query_impl[6ffb465cf6366f2]::query_impl::typeck::dynamic_query::{closure#2}::{closure#0}, rustc_middle[58c8be1544d4ff96]::query::erase::Erased<[u8; 8usize]>>
19: 0x77075ac43201 - rustc_query_system[e2e7e315caf8fc79]::query::plumbing::try_execute_query::<rustc_query_impl[6ffb465cf6366f2]::DynamicConfig<rustc_query_system[e2e7e315caf8fc79]::query::caches::VecCache<rustc_span[916daa99866cf1f4]::def_id::LocalDefId, rustc_middle[58c8be1544d4ff96]::query::erase::Erased<[u8; 8usize]>>, false, false, false>, rustc_query_impl[6ffb465cf6366f2]::plumbing::QueryCtxt, false>
20: 0x77075ac41857 - rustc_query_impl[6ffb465cf6366f2]::query_impl::typeck::get_query_non_incr::__rust_end_short_backtrace
21: 0x77075b178e0a - rustc_middle[58c8be1544d4ff96]::query::plumbing::query_get_at::<rustc_query_system[e2e7e315caf8fc79]::query::caches::VecCache<rustc_span[916daa99866cf1f4]::def_id::LocalDefId, rustc_middle[58c8be1544d4ff96]::query::erase::Erased<[u8; 8usize]>>>
22: 0x77075b8ddbab - rustc_hir_analysis[f8c34c1d50f2c7d9]::collect::type_of::type_of_opaque
23: 0x77075b8ddae5 - rustc_query_impl[6ffb465cf6366f2]::plumbing::__rust_begin_short_backtrace::<rustc_query_impl[6ffb465cf6366f2]::query_impl::type_of_opaque::dynamic_query::{closure#2}::{closure#0}, rustc_middle[58c8be1544d4ff96]::query::erase::Erased<[u8; 8usize]>>
24: 0x77075ab854fa - rustc_query_system[e2e7e315caf8fc79]::query::plumbing::try_execute_query::<rustc_query_impl[6ffb465cf6366f2]::DynamicConfig<rustc_query_system[e2e7e315caf8fc79]::query::caches::DefIdCache<rustc_middle[58c8be1544d4ff96]::query::erase::Erased<[u8; 8usize]>>, false, false, false>, rustc_query_impl[6ffb465cf6366f2]::plumbing::QueryCtxt, false>
25: 0x77075b996ff6 - rustc_query_impl[6ffb465cf6366f2]::query_impl::type_of_opaque::get_query_non_incr::__rust_end_short_backtrace
26: 0x77075adef540 - rustc_middle[58c8be1544d4ff96]::query::plumbing::query_get_at::<rustc_query_system[e2e7e315caf8fc79]::query::caches::DefIdCache<rustc_middle[58c8be1544d4ff96]::query::erase::Erased<[u8; 8usize]>>>
27: 0x770757c2c334 - rustc_hir_analysis[f8c34c1d50f2c7d9]::collect::type_of::type_of
28: 0x77075ab868aa - rustc_query_impl[6ffb465cf6366f2]::plumbing::__rust_begin_short_backtrace::<rustc_query_impl[6ffb465cf6366f2]::query_impl::type_of::dynamic_query::{closure#2}::{closure#0}, rustc_middle[58c8be1544d4ff96]::query::erase::Erased<[u8; 8usize]>>
29: 0x77075ab854fa - rustc_query_system[e2e7e315caf8fc79]::query::plumbing::try_execute_query::<rustc_query_impl[6ffb465cf6366f2]::DynamicConfig<rustc_query_system[e2e7e315caf8fc79]::query::caches::DefIdCache<rustc_middle[58c8be1544d4ff96]::query::erase::Erased<[u8; 8usize]>>, false, false, false>, rustc_query_impl[6ffb465cf6366f2]::plumbing::QueryCtxt, false>
30: 0x77075ab850a3 - rustc_query_impl[6ffb465cf6366f2]::query_impl::type_of::get_query_non_incr::__rust_end_short_backtrace
31: 0x77075b1296d0 - rustc_middle[58c8be1544d4ff96]::query::plumbing::query_get_at::<rustc_query_system[e2e7e315caf8fc79]::query::caches::DefIdCache<rustc_middle[58c8be1544d4ff96]::query::erase::Erased<[u8; 8usize]>>>
32: 0x77075aea761d - <rustc_trait_selection[45dc482989e69e08]::traits::query::normalize::QueryNormalizer as rustc_type_ir[543408bf699dc]::fold::FallibleTypeFolder<rustc_middle[58c8be1544d4ff96]::ty::context::TyCtxt>>::try_fold_ty
33: 0x77075aea2ac8 - <rustc_traits[98b13475d2e688c2]::normalize_erasing_regions::provide::{closure#0} as core[301db181db02ff04]::ops::function::FnOnce<(rustc_middle[58c8be1544d4ff96]::ty::context::TyCtxt, rustc_middle[58c8be1544d4ff96]::ty::ParamEnvAnd<rustc_middle[58c8be1544d4ff96]::ty::generic_args::GenericArg>)>>::call_once
34: 0x77075aea26f7 - rustc_query_impl[6ffb465cf6366f2]::plumbing::__rust_begin_short_backtrace::<rustc_query_impl[6ffb465cf6366f2]::query_impl::try_normalize_generic_arg_after_erasing_regions::dynamic_query::{closure#2}::{closure#0}, rustc_middle[58c8be1544d4ff96]::query::erase::Erased<[u8; 8usize]>>
35: 0x77075aea1e19 - rustc_query_system[e2e7e315caf8fc79]::query::plumbing::try_execute_query::<rustc_query_impl[6ffb465cf6366f2]::DynamicConfig<rustc_query_system[e2e7e315caf8fc79]::query::caches::DefaultCache<rustc_middle[58c8be1544d4ff96]::ty::ParamEnvAnd<rustc_middle[58c8be1544d4ff96]::ty::generic_args::GenericArg>, rustc_middle[58c8be1544d4ff96]::query::erase::Erased<[u8; 8usize]>>, false, false, false>, rustc_query_impl[6ffb465cf6366f2]::plumbing::QueryCtxt, false>
36: 0x77075aea1b60 - rustc_query_impl[6ffb465cf6366f2]::query_impl::try_normalize_generic_arg_after_erasing_regions::get_query_non_incr::__rust_end_short_backtrace
37: 0x77075ae9dc8b - <rustc_middle[58c8be1544d4ff96]::ty::normalize_erasing_regions::TryNormalizeAfterErasingRegionsFolder as rustc_type_ir[543408bf699dc]::fold::FallibleTypeFolder<rustc_middle[58c8be1544d4ff96]::ty::context::TyCtxt>>::try_fold_ty
38: 0x77075afc8388 - rustc_ty_utils[3110184492a391f3]::layout::layout_of
39: 0x77075afc7f19 - rustc_query_impl[6ffb465cf6366f2]::plumbing::__rust_begin_short_backtrace::<rustc_query_impl[6ffb465cf6366f2]::query_impl::layout_of::dynamic_query::{closure#2}::{closure#0}, rustc_middle[58c8be1544d4ff96]::query::erase::Erased<[u8; 16usize]>>
40: 0x77075afc71c8 - rustc_query_system[e2e7e315caf8fc79]::query::plumbing::try_execute_query::<rustc_query_impl[6ffb465cf6366f2]::DynamicConfig<rustc_query_system[e2e7e315caf8fc79]::query::caches::DefaultCache<rustc_middle[58c8be1544d4ff96]::ty::ParamEnvAnd<rustc_middle[58c8be1544d4ff96]::ty::Ty>, rustc_middle[58c8be1544d4ff96]::query::erase::Erased<[u8; 16usize]>>, false, true, false>, rustc_query_impl[6ffb465cf6366f2]::plumbing::QueryCtxt, false>
41: 0x77075afc6e6d - rustc_query_impl[6ffb465cf6366f2]::query_impl::layout_of::get_query_non_incr::__rust_end_short_backtrace
42: 0x77075b8e66b2 - rustc_middle[58c8be1544d4ff96]::query::plumbing::query_get_at::<rustc_query_system[e2e7e315caf8fc79]::query::caches::DefaultCache<rustc_middle[58c8be1544d4ff96]::ty::ParamEnvAnd<rustc_middle[58c8be1544d4ff96]::ty::Ty>, rustc_middle[58c8be1544d4ff96]::query::erase::Erased<[u8; 16usize]>>>
43: 0x7707592f168c - rustc_hir_analysis[f8c34c1d50f2c7d9]::hir_ty_lowering::cmse::is_valid_cmse_output
44: 0x77075b171ce6 - <dyn rustc_hir_analysis[f8c34c1d50f2c7d9]::hir_ty_lowering::HirTyLowerer>::lower_fn_ty
45: 0x77075b16ffe4 - rustc_hir_analysis[f8c34c1d50f2c7d9]::collect::infer_return_ty_for_fn_sig
46: 0x77075b172555 - rustc_hir_analysis[f8c34c1d50f2c7d9]::collect::fn_sig
47: 0x77075aa5be6b - rustc_query_impl[6ffb465cf6366f2]::plumbing::__rust_begin_short_backtrace::<rustc_query_impl[6ffb465cf6366f2]::query_impl::fn_sig::dynamic_query::{closure#2}::{closure#0}, rustc_middle[58c8be1544d4ff96]::query::erase::Erased<[u8; 24usize]>>
48: 0x77075aa5f064 - rustc_query_system[e2e7e315caf8fc79]::query::plumbing::try_execute_query::<rustc_query_impl[6ffb465cf6366f2]::DynamicConfig<rustc_query_system[e2e7e315caf8fc79]::query::caches::DefIdCache<rustc_middle[58c8be1544d4ff96]::query::erase::Erased<[u8; 24usize]>>, false, false, false>, rustc_query_impl[6ffb465cf6366f2]::plumbing::QueryCtxt, false>
49: 0x77075aa5e8e2 - rustc_query_impl[6ffb465cf6366f2]::query_impl::fn_sig::get_query_non_incr::__rust_end_short_backtrace
50: 0x77075ab7adbe - <rustc_hir_analysis[f8c34c1d50f2c7d9]::collect::CollectItemTypesVisitor as rustc_hir[227b0424fb17eaca]::intravisit::Visitor>::visit_item
51: 0x7707577bc428 - rustc_hir_analysis[f8c34c1d50f2c7d9]::check::wfcheck::check_well_formed
52: 0x77075ac04197 - rustc_query_impl[6ffb465cf6366f2]::plumbing::__rust_begin_short_backtrace::<rustc_query_impl[6ffb465cf6366f2]::query_impl::check_well_formed::dynamic_query::{closure#2}::{closure#0}, rustc_middle[58c8be1544d4ff96]::query::erase::Erased<[u8; 1usize]>>
53: 0x77075ac038e7 - rustc_query_system[e2e7e315caf8fc79]::query::plumbing::try_execute_query::<rustc_query_impl[6ffb465cf6366f2]::DynamicConfig<rustc_query_system[e2e7e315caf8fc79]::query::caches::VecCache<rustc_span[916daa99866cf1f4]::def_id::LocalDefId, rustc_middle[58c8be1544d4ff96]::query::erase::Erased<[u8; 1usize]>>, false, false, false>, rustc_query_impl[6ffb465cf6366f2]::plumbing::QueryCtxt, false>
54: 0x77075ac03550 - rustc_query_impl[6ffb465cf6366f2]::query_impl::check_well_formed::get_query_non_incr::__rust_end_short_backtrace
55: 0x77075ac04410 - rustc_hir_analysis[f8c34c1d50f2c7d9]::check::wfcheck::check_mod_type_wf
56: 0x77075ac04247 - rustc_query_impl[6ffb465cf6366f2]::plumbing::__rust_begin_short_backtrace::<rustc_query_impl[6ffb465cf6366f2]::query_impl::check_mod_type_wf::dynamic_query::{closure#2}::{closure#0}, rustc_middle[58c8be1544d4ff96]::query::erase::Erased<[u8; 1usize]>>
57: 0x77075b3d5745 - rustc_query_system[e2e7e315caf8fc79]::query::plumbing::try_execute_query::<rustc_query_impl[6ffb465cf6366f2]::DynamicConfig<rustc_query_system[e2e7e315caf8fc79]::query::caches::DefaultCache<rustc_span[916daa99866cf1f4]::def_id::LocalModDefId, rustc_middle[58c8be1544d4ff96]::query::erase::Erased<[u8; 1usize]>>, false, false, false>, rustc_query_impl[6ffb465cf6366f2]::plumbing::QueryCtxt, false>
58: 0x77075b3d54f3 - rustc_query_impl[6ffb465cf6366f2]::query_impl::check_mod_type_wf::get_query_non_incr::__rust_end_short_backtrace
59: 0x77075ac3effb - rustc_hir_analysis[f8c34c1d50f2c7d9]::check_crate
60: 0x77075ac33517 - rustc_interface[2b41161da54db00e]::passes::run_required_analyses
61: 0x77075b54925e - rustc_interface[2b41161da54db00e]::passes::analysis
62: 0x77075b549231 - rustc_query_impl[6ffb465cf6366f2]::plumbing::__rust_begin_short_backtrace::<rustc_query_impl[6ffb465cf6366f2]::query_impl::analysis::dynamic_query::{closure#2}::{closure#0}, rustc_middle[58c8be1544d4ff96]::query::erase::Erased<[u8; 1usize]>>
63: 0x77075b73816e - rustc_query_system[e2e7e315caf8fc79]::query::plumbing::try_execute_query::<rustc_query_impl[6ffb465cf6366f2]::DynamicConfig<rustc_query_system[e2e7e315caf8fc79]::query::caches::SingleCache<rustc_middle[58c8be1544d4ff96]::query::erase::Erased<[u8; 1usize]>>, false, false, false>, rustc_query_impl[6ffb465cf6366f2]::plumbing::QueryCtxt, false>
64: 0x77075b737e4f - rustc_query_impl[6ffb465cf6366f2]::query_impl::analysis::get_query_non_incr::__rust_end_short_backtrace
65: 0x77075b6045b1 - rustc_interface[2b41161da54db00e]::interface::run_compiler::<core[301db181db02ff04]::result::Result<(), rustc_span[916daa99866cf1f4]::ErrorGuaranteed>, rustc_driver_impl[bf30803df350f481]::run_compiler::{closure#0}>::{closure#1}
66: 0x77075b6a3454 - std[a151dedc4facde64]::sys::backtrace::__rust_begin_short_backtrace::<rustc_interface[2b41161da54db00e]::util::run_in_thread_with_globals<rustc_interface[2b41161da54db00e]::util::run_in_thread_pool_with_globals<rustc_interface[2b41161da54db00e]::interface::run_compiler<core[301db181db02ff04]::result::Result<(), rustc_span[916daa99866cf1f4]::ErrorGuaranteed>, rustc_driver_impl[bf30803df350f481]::run_compiler::{closure#0}>::{closure#1}, core[301db181db02ff04]::result::Result<(), rustc_span[916daa99866cf1f4]::ErrorGuaranteed>>::{closure#0}, core[301db181db02ff04]::result::Result<(), rustc_span[916daa99866cf1f4]::ErrorGuaranteed>>::{closure#0}::{closure#0}, core[301db181db02ff04]::result::Result<(), rustc_span[916daa99866cf1f4]::ErrorGuaranteed>>
67: 0x77075b6a388d - <<std[a151dedc4facde64]::thread::Builder>::spawn_unchecked_<rustc_interface[2b41161da54db00e]::util::run_in_thread_with_globals<rustc_interface[2b41161da54db00e]::util::run_in_thread_pool_with_globals<rustc_interface[2b41161da54db00e]::interface::run_compiler<core[301db181db02ff04]::result::Result<(), rustc_span[916daa99866cf1f4]::ErrorGuaranteed>, rustc_driver_impl[bf30803df350f481]::run_compiler::{closure#0}>::{closure#1}, core[301db181db02ff04]::result::Result<(), rustc_span[916daa99866cf1f4]::ErrorGuaranteed>>::{closure#0}, core[301db181db02ff04]::result::Result<(), rustc_span[916daa99866cf1f4]::ErrorGuaranteed>>::{closure#0}::{closure#0}, core[301db181db02ff04]::result::Result<(), rustc_span[916daa99866cf1f4]::ErrorGuaranteed>>::{closure#1} as core[301db181db02ff04]::ops::function::FnOnce<()>>::call_once::{shim:vtable#0}
68: 0x77075b6a432b - std::sys::pal::unix::thread::Thread::new::thread_start::h254586afceceda1d
69: 0x7707558a339d - <unknown>
70: 0x77075592849c - <unknown>
71: 0x0 - <unknown>
error: the compiler unexpectedly panicked. this is a bug.
note: we would appreciate a bug report: https://github.com/rust-lang/rust/issues/new?labels=C-bug%2C+I-ICE%2C+T-compiler&template=ice.md
note: please make sure that you have updated to the latest nightly
note: rustc 1.84.0-nightly (97ae1df8a 2024-10-25) running on x86_64-unknown-linux-gnu
query stack during panic:
#0 [typeck] type-checking `multiple_named_lifetimes`
#1 [type_of_opaque] computing type of opaque `multiple_named_lifetimes::{opaque#0}`
end of query stack
error: aborting due to 5 previous errors
Some errors have detailed explanations: E0601, E0658, E0670.
For more information about an error, try `rustc --explain E0601`.
```
</p>
</details>
<!--
query stack:
#0 [typeck] type-checking `multiple_named_lifetimes`
#1 [type_of_opaque] computing type of opaque `multiple_named_lifetimes::{opaque#0}`
-->
| I-ICE,T-compiler,C-bug,F-cmse_nonsecure_entry,S-bug-has-test | low | Critical |
2,614,266,617 | PowerToys | Advance Paste copy paste form PDF - remove txt breaks | ### Description of the new feature / enhancement
Option to paste with breaks removed from text that has been copied from PDF.
### Scenario when this would be used?
Copy any text from pdf - the text is not connected due to breaks between sentences. This will increase life and sustain happiness of majority of adults.
### Supporting information
_No response_ | Needs-Triage | low | Minor |
2,614,277,831 | next.js | generateStaticParams with next export: Build fails when generateStaticParams returns an empty array of params | ### Link to the code that reproduces this issue
https://github.com/NasserBvB/generate-static-params-issue
### To Reproduce
While building a Next.js application with `output: "export"` in `next.config.js`, I encountered an error regarding the missing `generateStaticParams()` function, despite it being implemented and returning an empty list. This error specifically affects dynamic pages in the project.
Notably, the build succeeds as expected when `generateStaticParams()` returns at least one article parameter in the list. The issue only arises when it returns an empty list (`[]`).
### Steps to Reproduce
1. Create a new Next.js application using `next@14.2.8`.
2. Add a dynamic page at `articles/[article]/page.js`.
3. Implement `generateStaticParams` in `articles/[article]/page.js` and set it to return an empty list (`[]`).
4. Configure `output: "export"` in `next.config.js`.
5. Run the build command.
### Expected Behavior
The build should succeed without any issues, recognizing that `generateStaticParams()` is implemented and returning an empty list of article slugs.
### Actual Behavior
An error occurs during the build, specifically stating:
```
Error: Page "/articles/[article]" is missing "generateStaticParams()" so it cannot be used with "output: export" config.
```
However, when `generateStaticParams()` returns a list with at least one article slug, the build completes successfully as expected.
### Additional Context
- I’ve confirmed that `generateStaticParams()` exists in `articles/[article]/page.js`, and the issue persists only when it returns an empty list.
### Current vs. Expected behavior
### Expected Behavior
The build should succeed without any issues, recognizing that `generateStaticParams()` is implemented and returning an empty list of article slugs.
### Actual Behavior
An error occurs during the build, specifically stating:
```
Error: Page "/articles/[article]" is missing "generateStaticParams()" so it cannot be used with "output: export" config.
```
However, when `generateStaticParams()` returns a list with at least one article slug, the build completes successfully as expected.
### Provide environment information
```bash
Operating System:
Platform: darwin
Arch: arm64
Version: Darwin Kernel Version 24.0.0: Tue Sep 24 23:36:26 PDT 2024; root:xnu-11215.1.12~1/RELEASE_ARM64_T8103
Available memory (MB): 16384
Available CPU cores: 8
Binaries:
Node: 18.19.0
npm: 10.2.3
Yarn: 1.22.22
pnpm: 9.12.0
Relevant Packages:
next: 14.2.8 // An outdated version detected (latest is 15.0.1), upgrade is highly recommended!
eslint-config-next: 14.2.8
react: 18.3.1
react-dom: 18.3.1
typescript: 5.5.4
Next.js Config:
output: export
```
### Which area(s) are affected? (Select all that apply)
create-next-app, Output (export/standalone), Script (next/script)
### Which stage(s) are affected? (Select all that apply)
next build (local)
### Additional context
_No response_ | create-next-app,bug,Output (export/standalone),Script (next/script) | low | Critical |
2,614,358,745 | angular | Spelling Error in Angular Docs: "setup" vs "set up" | ### Describe the problem that you experienced
In English, "setup" is a noun and "set up" is a verb. The docs frequently use the wrong word which is distracting.
For example, on [this page](https://angular.dev/tutorials/learn-angular/15-forms), it says "you'll learn how to setup a form." It should read "you'll learn how to **set up** a form."
I will submit a PR to fix this minor issue.
### Enter the URL of the topic with the problem
https://angular.dev/tutorials/learn-angular/15-forms
### Describe what you were looking for in the documentation
_No response_
### Describe the actions that led you to experience the problem
_No response_
### Describe what you want to experience that would fix the problem
_No response_
### Add a screenshot if that helps illustrate the problem
_No response_
### If this problem caused an exception or error, please paste it here
_No response_
### If the problem is browser-specific, please specify the device, OS, browser, and version
_No response_
### Provide any additional information here in as much as detail as you can
_No response_ | area: docs | low | Critical |
2,614,392,836 | kubernetes | When containers use memory backed tmpfs and hit a OOM limit they will keep OOM on restarts. | ### What happened?
While aiming to promote SizeMemoryBackedVolumes to stable, tim brought up a point about what would happen if a pod that hit a OOM due to tmpfs memory limits would keep OOM as the pages are still kept around.
He is correct. If a pod hits a OOM limit with tmpfs it will keep OOM and never purge that memory
### What did you expect to happen?
I would expect the tmpfs to be empty on a restart of the container.
### How can we reproduce it (as minimally and precisely as possible)?
I used kind 1.30.
```yaml
apiVersion: v1
kind: Pod
metadata:
name: example
labels:
app: test-pd
spec:
restartPolicy: OnFailure
securityContext:
seccompProfile:
type: RuntimeDefault
containers:
- image: busybox
command:
- /bin/sh
- -c
- |
sleep infinity
name: test-pd
resources:
limits:
memory: 2Gi
volumeMounts:
- mountPath: /dev/shm
name: dshm
securityContext:
allowPrivilegeEscalation: false
capabilities:
drop:
- ALL
volumes:
- name: dshm
emptyDir:
medium: Memory
sizeLimit: 4Gi
```
kubectl exec -it example -- sh
cd /dev/shm/
dd if=/dev/zero of=filename bs=1024 count=2GB
command terminated with exit code 137
In this case, the pod is unable to start again and it gets stuck with:
```
7s Warning Failed pod/example Error: failed to create containerd task: failed to create shim task: OCI runtime create failed: runc create failed: unable to start container process: container init was OOM-killed (memory limit too low?): unknown
```
### Anything else we need to know?
This is probably a long outstanding issue so its unclear if this will be fixed as a bug.
### Kubernetes version
<details>
```console
$ kubectl version
1.30
```
</details>
### Cloud provider
<details>
na
</details>
### OS version
<details>
```console
# On Linux:
$ cat /etc/os-release
# paste output here
$ uname -a
# paste output here
# On Windows:
C:\> wmic os get Caption, Version, BuildNumber, OSArchitecture
# paste output here
```
</details>
### Install tools
<details>
</details>
### Container runtime (CRI) and version (if applicable)
<details>
</details>
### Related plugins (CNI, CSI, ...) and versions (if applicable)
<details>
</details>
| kind/bug,priority/backlog,sig/node,triage/accepted | medium | Critical |
2,614,406,337 | PowerToys | Keyboard manager problem | ### Microsoft PowerToys version
0.82
### Installation method
GitHub
### Running as admin
None
### Area(s) with issue?
Keyboard Manager
### Steps to reproduce
I set up a different/simplified keyboard shortcut for win+shift+s, then removed it, and now that Windows shortcut no longer works. I have to set up the same shortuct win+shift+s to win+shift+s to make it work.
### ✔️ Expected Behavior
win+shift+s open snipping tool
### ❌ Actual Behavior
Typing the shortcut nothing happens
### Other Software
_No response_ | Issue-Bug,Needs-Triage | low | Minor |
2,614,407,089 | rust | Debug info is broken on macOS when using --remap-path-prefix | This can be easily reproduced with a simple program.
```rust
// main.rs
fn main() {
println!("Hello, world!");
}
```
Without --remap-path-prefix, building with unpacked debug info:
```bash
rustc main.rs --codegen=debuginfo=2 --codegen=split-debuginfo=unpacked
```
Results in a binary that has an OSO entry pointing to the object file containing the debug info:
```bash
> nm -pa main | rg OSO
0000000000000000 - 00 0001 OSO /Users/cameron/Desktop/broken/main.main.7c41ea6d61ccd5c8-cgu.0.rcgu.o
0000000000000000 - 00 0001 OSO /Users/cameron/.rustup/toolchains/stable-aarch64-apple-darwin/lib/rustlib/aarch64-apple-darwin/lib/libstd-b0083070c892a1db.rlib(std-b0083070c892a1db.std.1bb08b5702199c76-cgu.0.rcgu.o)
0000000000000000 - 00 0001 OSO /Users/cameron/.rustup/toolchains/stable-aarch64-apple-darwin/lib/rustlib/aarch64-apple-darwin/lib/libpanic_unwind-8282820217d7b362.rlib(panic_unwind-8282820217d7b362.panic_unwind.edd611859befea2b-cgu.0.rcgu.o)
0000000000000000 - 00 0001 OSO /Users/cameron/.rustup/toolchains/stable-aarch64-apple-darwin/lib/rustlib/aarch64-apple-darwin/lib/libmemchr-350512940f04084a.rlib(memchr-350512940f04084a.memchr.163a0d7c2b1b5170-cgu.0.rcgu.o)
0000000000000000 - 00 0001 OSO /Users/cameron/.rustup/toolchains/stable-aarch64-apple-darwin/lib/rustlib/aarch64-apple-darwin/lib/librustc_demangle-e1d006f163566466.rlib(rustc_demangle-e1d006f163566466.rustc_demangle.763a0c92458f345-cgu.0.rcgu.o)
0000000000000000 - 00 0001 OSO /Users/cameron/.rustup/toolchains/stable-aarch64-apple-darwin/lib/rustlib/aarch64-apple-darwin/lib/liballoc-edb678dd3e28691a.rlib(alloc-edb678dd3e28691a.alloc.7c7540ab8626f01a-cgu.0.rcgu.o)
0000000000000000 - 00 0001 OSO /Users/cameron/.rustup/toolchains/stable-aarch64-apple-darwin/lib/rustlib/aarch64-apple-darwin/lib/libcore-2447397acf63b01e.rlib(core-2447397acf63b01e.core.5213bbcd403abe9e-cgu.0.rcgu.o)
```
With --remap-path-prefix:
```bash
rustc main.rs --codegen=debuginfo=2 --codegen=split-debuginfo=unpacked --remap-path-prefix=/Users/cameron/Desktop/broken=
```
Results in a binary that is missing OSO entries for the remapped object files:
```bash
> nm -pa main | rg OSO
0000000000000000 - 00 0001 OSO /Users/cameron/.rustup/toolchains/stable-aarch64-apple-darwin/lib/rustlib/aarch64-apple-darwin/lib/libstd-b0083070c892a1db.rlib(std-b0083070c892a1db.std.1bb08b5702199c76-cgu.0.rcgu.o)
0000000000000000 - 00 0001 OSO /Users/cameron/.rustup/toolchains/stable-aarch64-apple-darwin/lib/rustlib/aarch64-apple-darwin/lib/libpanic_unwind-8282820217d7b362.rlib(panic_unwind-8282820217d7b362.panic_unwind.edd611859befea2b-cgu.0.rcgu.o)
0000000000000000 - 00 0001 OSO /Users/cameron/.rustup/toolchains/stable-aarch64-apple-darwin/lib/rustlib/aarch64-apple-darwin/lib/libmemchr-350512940f04084a.rlib(memchr-350512940f04084a.memchr.163a0d7c2b1b5170-cgu.0.rcgu.o)
0000000000000000 - 00 0001 OSO /Users/cameron/.rustup/toolchains/stable-aarch64-apple-darwin/lib/rustlib/aarch64-apple-darwin/lib/librustc_demangle-e1d006f163566466.rlib(rustc_demangle-e1d006f163566466.rustc_demangle.763a0c92458f345-cgu.0.rcgu.o)
0000000000000000 - 00 0001 OSO /Users/cameron/.rustup/toolchains/stable-aarch64-apple-darwin/lib/rustlib/aarch64-apple-darwin/lib/liballoc-edb678dd3e28691a.rlib(alloc-edb678dd3e28691a.alloc.7c7540ab8626f01a-cgu.0.rcgu.o)
0000000000000000 - 00 0001 OSO /Users/cameron/.rustup/toolchains/stable-aarch64-apple-darwin/lib/rustlib/aarch64-apple-darwin/lib/libcore-2447397acf63b01e.rlib(core-2447397acf63b01e.core.5213bbcd403abe9e-cgu.0.rcgu.o)
```
**Note how the first OSO entry from the first command is missing from the second:**
```bash
0000000000000000 - 00 0001 OSO /Users/cameron/Desktop/broken/main.main.7c41ea6d61ccd5c8-cgu.0.rcgu.o
```
I believe the same underlying issue prevents `--split-debuginfo=packed` from generating a dSYM containing debug info for the object files containing the remapped path prefix, as I believe dsymutil is just using the OSO entries to create a self contained set of DWARF debug info.
Packed debug info without remapping:
```bash
rustc main.rs --codegen=debuginfo=2 --codegen=split-debuginfo=packed
```
Results in a complete dSYM:
```bash
> dwarfdump main.dSYM | rg "main.rs" -B 8
main.dSYM/Contents/Resources/DWARF/main: file format Mach-O arm64
.debug_info contents:
0x00000000: Compile Unit: length = 0x0000091b, format = DWARF32, version = 0x0004, abbr_offset = 0x0000, addr_size = 0x08 (next unit at 0x0000091f)
0x0000000b: DW_TAG_compile_unit
DW_AT_producer ("clang LLVM (rustc version 1.82.0 (f6e511eec 2024-10-15))")
DW_AT_language (DW_LANG_Rust)
DW_AT_name ("main.rs/@/main.4b21619d1e36c66a-cgu.0")
--
DW_AT_name ("main")
0x000008d6: DW_TAG_subprogram
DW_AT_low_pc (0x0000000100001720)
DW_AT_high_pc (0x0000000100001754)
DW_AT_frame_base (DW_OP_reg29 W29)
DW_AT_linkage_name ("_ZN4main4main17h0cc9ac8d6b33b55fE")
DW_AT_name ("main")
DW_AT_decl_file ("/Users/cameron/Desktop/broken/main.rs")
```
Whereas the remapped version:
```bash
rustc main.rs --codegen=debuginfo=2 --codegen=split-debuginfo=packed --remap-path-prefix=/Users/cameron/Desktop/broken=
```
Does not:
```bash
> dwarfdump main.dSYM | rg "main.rs" -B 8
```
All these issues are reproducible on a recent nightly (`rustc version 1.84.0-nightly (a93c1718c 2024-10-24)`). | O-macos,A-debuginfo,T-compiler,C-bug,O-apple,A-path-remapping | low | Critical |
2,614,414,613 | excalidraw | Dark mode in the url #dark or ?theme=dark | it is painful to see white bg page when we use web embedded and it does feel good while presenting so is there a way to force that to use dark mode ? If yes then do guide please i can even try to rebuild from source if needed but definitely need solution for that to save eyes :-)) | enhancement | low | Minor |
2,614,455,054 | godot | Scene and Resource files invisibly override non-exported variables | ### Tested versions
- Reproducible in: 4.3 stable
### System information
Godot v4.3.stable - Arch Linux
### Issue description
Scene and Resource files (.tscn and .tres) can set variables that aren't marked for `@export`. This seems relatively harmless until you remove the `@export` keyword from a variable during code refactoring: every scene that overrides the variable will continue doing so _even though you can't see it in the inspector anymore._
Saving the affected scene automatically fixes the problem, so it's easy to solve by accident or if you grep/edit .tscn files in an external editor. But if you're not lucky or comfortable tinkering with Godot's files outside it, these phantom values are intractable.
### Steps to reproduce
1. Create a scene or resource with an `@export` variable in its script.
2. Set the variable in the inspector and save the scene/resource in its own file.
3. _Close the file._ Do not open and resave it after this.
4. Remove `@export` from the script.
5. Run the project with the scene or resource instantiated. Its variable will continue to be silently overwritten.
Alternatively, just append something like this to a .tscn file:
`non_exported_variable = "Incorrect value you can't see in the inspector"`
### Minimal reproduction project (MRP)
[bad_math.zip](https://github.com/user-attachments/files/17522612/bad_math.zip)
| bug,topic:editor | low | Major |
2,614,477,819 | PowerToys | Unexpected file lock when Unity packman installs com.unity.burst | ### Microsoft PowerToys version
0.85.1
### Installation method
PowerToys auto-update
### Running as admin
Yes
### Area(s) with issue?
General
### Steps to reproduce
1. Create empty Unity project
2. Open Unity Editor
3. Open Package Manager
4. Install `com.unity.barracuda@3.0.0` (or any package dependent on `com.unity.burst`)
5. **Sometimes**, the error happens, you may need to make steps from the start multiple times
6. Close PowerToys completely
7. The issue will never happen
### ✔️ Expected Behavior
Package installs without errors
### ❌ Actual Behavior
When PowerToys are open (in tray), the following error MAY appear:
```
An error occurred while resolving packages:
One or more packages could not be added to the local file system:
com.unity.burst: EBUSY: resource busy or locked, open 'C:\Users\kezzyhko\Desktop\FluctioSimTest\Library\PackageCache\.tmp-19776-3dH4eZB11v7E\copy\.Runtime\burst-lld-16-hostwin-arm64.exe'
```
### Other Software
Unity Editor (version does not really matter, I tested on latest Unity 6, but it also happened on earlier versions) | Issue-Bug,Needs-Triage | low | Critical |
2,614,519,750 | godot | Random UI elements of the editor do not work with touch events | ### Tested versions
Godot 4.3 Stable
### System information
Windows 10 x64, Laptop with touchscreen (Win Max 2)
### Issue description
For example, in Project Launcher we can click on Create button to get this window, but its buttons (Browse, Create and edit, and Cancel) and text field are ignoring touch events completely. Similar things occur in the editor itself (touch clicks are often ignored, multitouch isn't supported at all, etc.)
### Steps to reproduce
1. Try to make a new project with touchscreen on Windows
2. Get confused
### Minimal reproduction project (MRP)
Not required | bug,topic:editor,usability,topic:input | low | Minor |
2,614,552,170 | next.js | Cannot use `renderToReadableStream` from `react-dom/server.edge` | ### Link to the code that reproduces this issue
https://github.com/gabrielmfern/react-dom-edge-reproduction
### To Reproduce
1. Start the app using `next dev`
2. Open the route at https://localhost:3000/test
3. See the error in the terminal
### Current vs. Expected behavior
I was expecting that I would be able to properly call the functions from `react-dom` regardless of how I import it or where I run it. The result I get is an error that seems to indicate multiple instances of React running, so not exactly sure what is the cause.
```js
TypeError: Cannot read properties of undefined (reading 'H')
at performWork (webpack-internal:///(rsc)/./node_modules/.pnpm/next@15.0.2-canary.6_react-dom@19.0.0-rc-1631855f-20241023_react@19.0.0-rc-1631855f-20241023_
_3on5hdq5nuq33xp36ooa2qays4/node_modules/next/dist/compiled/react-dom/cjs/react-dom-server.edge.development.js:6506:49)
at AsyncLocalStorage.run (node:async_hooks:346:14)
at eval (webpack-internal:///(rsc)/./node_modules/.pnpm/next@15.0.2-canary.6_react-dom@19.0.0-rc-1631855f-20241023_react@19.0.0-rc-1631855f-20241023__3on5hd
q5nuq33xp36ooa2qays4/node_modules/next/dist/compiled/react-dom/cjs/react-dom-server.edge.development.js:7244:35)
at node:internal/process/task_queues:140:7
at AsyncResource.runInAsyncScope (node:async_hooks:206:9)
at AsyncResource.runMicrotask (node:internal/process/task_queues:137:8)
```
### Provide environment information
```bash
Node.js v20.17.0
Operating System:
Platform: linux
Arch: x64
Version: #1 SMP PREEMPT_DYNAMIC Tue, 22 Oct 2024 18:31:38 +0000
Available memory (MB): 15872
Available CPU cores: 24
Binaries:
Node: 20.17.0
npm: 10.8.2
Yarn: N/A
pnpm: 9.10.0
Relevant Packages:
next: 15.0.2-canary.6 // Latest available version is detected (15.0.2-canary.6).
eslint-config-next: 14.1.0
react: 19.0.0-rc-1631855f-20241023
react-dom: 19.0.0-rc-1631855f-20241023
typescript: 5.3.3
Next.js Config:
output: N/A
```
### Which area(s) are affected? (Select all that apply)
Runtime
### Which stage(s) are affected? (Select all that apply)
next dev (local), next start (local)
### Additional context
I tested this against the latest version and also the canary, there doesn't seem to be any difference in the error or the behaviors at all. The error also seems to persist even when going back down to `15.0.0-canary.0` and downgrading the `react-dom` and `react` versions accordingly.
Not sure if this only happens when on the edge, or if it happens with any of the other exports for `react-dom/server`, but for my purposes I wanted to use the edge one specifically. | bug,Runtime | low | Critical |
2,614,585,556 | PowerToys | Preview pane handlers, thumbnail generators only work if PT is installed for the system | ### Microsoft PowerToys version
0.81.1
### Installation method
WinGet
### Running as admin
No
### Area(s) with issue?
File Explorer: Preview Pane, File Explorer: Thumbnail preview
### Steps to reproduce
Install the **user** package of PowerToys, start it and attempt to enable File Explorer preview panes and handlers as appropriate. Then view the preview in Explorer.
As a workaround, it appears installing the machine package does allow the handlers to initialise correctly. I have not tested if later uninstalling this system package, and installing the user package, returns to the broken behaviour.
### ✔️ Expected Behavior
The previews to be successfully displayed.
### ❌ Actual Behavior
Thumbnails are not generated, and the preview pane displays the error "This file can't be previewed" for any file that has a PowerToys handler.
### Other Software
_No response_ | Issue-Bug,Needs-Triage | low | Critical |
2,614,611,505 | godot | D3D12 TextureArray2D mipmaps missing/broken | ### Tested versions
Reproducible in 4.3, 4.4dev3
### System information
Windows 11/64, RTX 3070, D3D12
### Issue description
In the Direct3D12 renderer, TextureArray2Ds don't seem to generate mipmaps so breaks Terrain3D and all other projects using them.
This code shows the next two images:
```
void fragment() {
NORMAL = mat3(VIEW_MATRIX) * normalize(v_normal);
// broken
ALBEDO = texture(_texture_array_albedo, vec3(UV, 0.)).rgb;
// works
//ALBEDO = texture(test_albedo, UV).rgb;
}
```
Forcing mip 0 with vec2(0) derivatives also works.
Downstream issue https://github.com/TokisanGames/Terrain3D/issues/529
### Minimal reproduction project (MRP)
- Create a new Godot project
- Download Terrain3D from the asset library
- Enable the plugin, open the demo, restart twice
- Change to D3D12
If you wish to edit the shader, enable `Terrain3D / Material / Shader Override`.
| bug,platform:windows,topic:rendering | low | Critical |
2,614,616,270 | flutter | Text can be copied and pasted using keyboard shortcuts (cmd + A and cmd + C) even though `enableInteractiveSelection: false` | ### Steps to reproduce
I’m having trouble disabling text copying in a TextField using Flutter. Even though I’ve set enableInteractiveSelection to false and customized the context menu, it’s still possible to copy the text using keyboard shortcuts. When I use Cmd + A to select all the text (even though there’s no visual indication of the selection), I can still copy the entire content of the TextField with Cmd + C. This behavior goes against the expected outcome of completely disabling text copying: [Flutter API Reference](https://api.flutter.dev/flutter/material/TextField/enableInteractiveSelection.html#:~:text=text%20cannot%20be%20copied).
### Expected results
When enableInteractiveSelection is set to false, the TextField should not allow any text selection or copying, whether through the context menu or keyboard shortcuts.
### Actual results
Text can still be copied using Cmd + A followed by Cmd + C.
### Code sample
<details open><summary>Code sample</summary>
```dart
TextField(
decoration: const InputDecoration(
border: OutlineInputBorder(),
),
// disable context menu
contextMenuBuilder: (_, __) => const SizedBox.shrink(),
enableInteractiveSelection: false, // disable copy paste
),
),
```
</details>
### Screenshots or Video
<details open>
<summary>Screenshots / Video demonstration</summary>
https://github.com/user-attachments/assets/31b3dd60-1b2a-40e8-8cfd-e84cd5738786
</details>
### Logs
<details open><summary>Logs</summary>
```console
[Paste your logs here]
```
</details>
### Flutter Doctor output
<details open><summary>Doctor output</summary>
```console
[✓] Flutter (Channel stable, 3.24.3, on macOS 15.0.1 24A348 darwin-arm64, locale zh-Hans-CN)
• Flutter version 3.24.3 on channel stable at /Users/jhlee0133/development/flutter
• Upstream repository https://github.com/flutter/flutter.git
• Framework revision 2663184aa7 (6 weeks ago), 2024-09-11 16:27:48 -0500
• Engine revision 36335019a8
• Dart version 3.5.3
• DevTools version 2.37.3
[✓] Android toolchain - develop for Android devices (Android SDK version 34.0.0)
• Android SDK at /Users/jhlee0133/Library/Android/sdk
• Platform android-34-ext8, build-tools 34.0.0
• Java binary at: /Applications/Android Studio.app/Contents/jbr/Contents/Home/bin/java
• Java version OpenJDK Runtime Environment (build 17.0.9+0-17.0.9b1087.7-11185874)
• All Android licenses accepted.
[✓] Xcode - develop for iOS and macOS (Xcode 16.0)
• Xcode at /Applications/Xcode.app/Contents/Developer
• Build 16A242d
• CocoaPods version 1.15.2
[✓] Chrome - develop for the web
• Chrome at /Applications/Google Chrome.app/Contents/MacOS/Google Chrome
[✓] Android Studio (version 2023.2)
• Android Studio at /Applications/Android Studio.app/Contents
• Flutter plugin can be installed from:
🔨 https://plugins.jetbrains.com/plugin/9212-flutter
• Dart plugin can be installed from:
🔨 https://plugins.jetbrains.com/plugin/6351-dart
• Java version OpenJDK Runtime Environment (build 17.0.9+0-17.0.9b1087.7-11185874)
[✓] Android Studio (version 2023.1)
• Android Studio at /Volumes/macOS Ventura/Applications/Android Studio.app/Contents
• Flutter plugin can be installed from:
🔨 https://plugins.jetbrains.com/plugin/9212-flutter
• Dart plugin can be installed from:
🔨 https://plugins.jetbrains.com/plugin/6351-dart
• Java version OpenJDK Runtime Environment (build 17.0.7+0-17.0.7b1000.6-10550314)
[✓] IntelliJ IDEA Ultimate Edition (version 2023.1)
• IntelliJ at /Users/jhlee0133/Library/Application Support/JetBrains/Toolbox/apps/IDEA-U/ch-0/231.8109.175/IntelliJ IDEA.app
• Flutter plugin can be installed from:
🔨 https://plugins.jetbrains.com/plugin/9212-flutter
• Dart plugin can be installed from:
🔨 https://plugins.jetbrains.com/plugin/6351-dart
[✓] IntelliJ IDEA Ultimate Edition (version 2024.2.3)
• IntelliJ at /Users/jhlee0133/Library/Application Support/JetBrains/Toolbox/apps/IDEA-U/ch-0/242.23339.11/IntelliJ IDEA.app
• Flutter plugin can be installed from:
🔨 https://plugins.jetbrains.com/plugin/9212-flutter
• Dart plugin can be installed from:
🔨 https://plugins.jetbrains.com/plugin/6351-dart
[✓] VS Code (version 1.93.0)
• VS Code at /Applications/Visual Studio Code.app/Contents
• Flutter extension version 3.96.0
[✓] Connected device (4 available)
• macOS (desktop) • macos • darwin-arm64 • macOS 15.0.1 24A348 darwin-arm64
• Mac Designed for iPad (desktop) • mac-designed-for-ipad • darwin • macOS 15.0.1 24A348 darwin-arm64
• Chrome (web) • chrome • web-javascript • Google Chrome 130.0.6723.70
[✓] Network resources
• All expected network resources are available.
• No issues found!
```
</details>
| a: text input,has reproducible steps,P2,team-text-input,triaged-text-input,found in release: 3.24,found in release: 3.27 | low | Minor |
2,614,647,917 | pytorch | The "register_module" function got a "key_description=<error>" and reported that "Exception 0xc0000005 encountered at address 0x7ff7fb3dfbf3: Access violation reading location 0xffffffffffffffff" | This is my code.The program was crashed in line
conv = register_module("conv", torch::nn::Conv2d(torch::nn::Conv2dOptions(in_channels, out_channels, kernel_size).stride(stride).padding(kernel_size / 2)));
```cpp
#include <torch/torch.h>
#include <iostream>
// 定义卷积 + ReLU + 批量归一化的模块
struct ConvReluBn : torch::nn::Module {
ConvReluBn(int in_channels, int out_channels, int kernel_size, int stride = 1) {
conv = register_module("conv", torch::nn::Conv2d(torch::nn::Conv2dOptions(in_channels, out_channels, kernel_size).stride(stride).padding(kernel_size / 2)));
relu = register_module("relu", torch::nn::ReLU());
bn = register_module("bn", torch::nn::BatchNorm2d(out_channels));
}
torch::Tensor forward(torch::Tensor x) {
return bn->forward(relu->forward(conv->forward(x)));
}
private:
torch::nn::Conv2d conv{nullptr};
torch::nn::ReLU relu{nullptr};
torch::nn::BatchNorm2d bn{nullptr};
};
// 定义 plainCNN 类
class plainCNN : public torch::nn::Module {
public:
plainCNN(int in_channels, int out_channels);
torch::Tensor forward(torch::Tensor x);
private:
int mid_channels[3] = {32, 64, 128};
// 使用 std::shared_ptr 来存储 ConvReluBn 对象
std::shared_ptr<ConvReluBn> conv1;
std::shared_ptr<ConvReluBn> down1;
std::shared_ptr<ConvReluBn> conv2;
std::shared_ptr<ConvReluBn> down2;
std::shared_ptr<ConvReluBn> conv3;
std::shared_ptr<ConvReluBn> down3;
torch::nn::Conv2d out_conv{nullptr};
};
// 构造函数的实现
plainCNN::plainCNN(int in_channels, int out_channels) {
// 使用 std::make_shared 创建 ConvReluBn 实例
conv1 = std::make_shared<ConvReluBn>(in_channels, mid_channels[0], 3);
down1 = std::make_shared<ConvReluBn>(mid_channels[0], mid_channels[0], 3, 2);
conv2 = std::make_shared<ConvReluBn>(mid_channels[0], mid_channels[1], 3);
down2 = std::make_shared<ConvReluBn>(mid_channels[1], mid_channels[1], 3, 2);
conv3 = std::make_shared<ConvReluBn>(mid_channels[1], mid_channels[2], 3);
down3 = std::make_shared<ConvReluBn>(mid_channels[2], mid_channels[2], 3, 2);
out_conv = register_module("out_conv", torch::nn::Conv2d(torch::nn::Conv2dOptions(mid_channels[2], out_channels, 3).padding(1)));
// 注册模块
register_module("conv1", conv1);
register_module("down1", down1);
register_module("conv2", conv2);
register_module("down2", down2);
register_module("conv3", conv3);
register_module("down3", down3);
}
// forward 方法的实现
torch::Tensor plainCNN::forward(torch::Tensor x) {
x = conv1->forward(x);
x = down1->forward(x);
x = conv2->forward(x);
x = down2->forward(x);
x = conv3->forward(x);
x = down3->forward(x);
x = out_conv->forward(x);
return x;
}
int main() {
// 创建模型实例
plainCNN model(3, 10); // 输入通道3（RGB图像），输出通道10
model.train(); // 设置模型为训练模式
// 创建一个示例输入
torch::Tensor input = torch::randn({1, 3, 224, 224}); // Batch size 1，3个通道，224x224的图像
auto output = model.forward(input); // 前向传播
std::cout << "Output shape: " << output.sizes() << std::endl; // 输出结果形状
return 0;
}
```
my enviroment is windows x64 with CUDA12.4,I tested the script below to verify that I have prepared a suitable enviroment.And that runs well
```cpp
#include <iostream>
#include "torch/script.h"
#include "torch/torch.h"
using namespace std;
int main() {
// 检查是否有可用的 GPU
if (torch::cuda::is_available()) {
cout << "CUDA is available! Using GPU." << endl;
torch::Device device(torch::kCUDA);
torch::Tensor tmp_1 = torch::rand({2, 3}).to(device);
torch::Tensor tmp_2 = torch::full_like(tmp_1, 1).to(device);
cout << tmp_1 << endl;
cout << tmp_2 << endl;
} else {
cout << "CUDA is not available. Using CPU." << endl;
torch::Device device(torch::kCPU);
torch::Tensor tmp_1 = torch::rand({2, 3}).to(device);
torch::Tensor tmp_2 = torch::full_like(tmp_1, 1).to(device);
cout << tmp_1 << endl;
cout << tmp_2 << endl;
}
return 0;
}
```
And the build Type is DEBUG.Here is my CMAKELISTS
~~~CMAKE
cmake_minimum_required(VERSION 3.5 FATAL_ERROR)
project(custom_ops)
# 设置 CMAKE_PREFIX_PATH
set(CMAKE_PREFIX_PATH "D:/MyLibs/libtorch-win-shared-with-deps-2.5.0+cu124/libtorch")
find_package(Torch REQUIRED)
# 设置 C++17 标准
set(CMAKE_CXX_STANDARD 17)
add_executable(main
src/simpleModel.cpp)
# 链接 libtorch 库
target_link_libraries(main "${TORCH_LIBRARIES}")
~~~
cc @peterjc123 @mszhanyi @skyline75489 @nbcsm @iremyux @Blackhex @jbschlosser | module: windows,module: cpp,triaged | low | Critical |
2,614,694,411 | next.js | Reading searchParams with "use cache" causes the build to hang | ### Link to the code that reproduces this issue
https://github.com/zaiste/nextjs-searchparams-bug-use-cache
### To Reproduce
Build the application
```
npm run build
```
### Current vs. Expected behavior
**Current:** The build process gets stuck.
**Expected:** The build process finishes
### Provide environment information
```bash
Operating System:
Platform: darwin
Arch: arm64
Version: Darwin Kernel Version 24.1.0: Mon Sep 30 00:10:31 PDT 2024; root:xnu-11215.40.63~39/RELEASE_ARM64_T6000
Available memory (MB): 16384
Available CPU cores: 10
Binaries:
Node: 21.7.1
npm: 10.9.0
Yarn: 1.22.22
pnpm: 9.12.2
Relevant Packages:
next: 15.0.2-canary.6 // Latest available version is detected (15.0.2-canary.6).
eslint-config-next: N/A
react: 19.0.0-rc-1631855f-20241023
react-dom: 19.0.0-rc-1631855f-20241023
typescript: 5.3.3
Next.js Config:
output: N/A
```
### Which area(s) are affected? (Select all that apply)
Developer Experience
### Which stage(s) are affected? (Select all that apply)
next build (local)
### Additional context
_No response_ | bug | low | Critical |
2,614,694,737 | tensorflow | It doesn't support on python3.13 | ### Issue type
Build/Install
### Have you reproduced the bug with TensorFlow Nightly?
No
### Source
source
### TensorFlow version
tf 2.17
### Custom code
Yes
### OS platform and distribution
macos sequoia arm
### Mobile device
_No response_
### Python version
3.13
### Bazel version
_No response_
### GCC/compiler version
_No response_
### CUDA/cuDNN version
_No response_
### GPU model and memory
_No response_
### Current behavior?
It doesn't work when I want to install via terminal with the installation code.
### Standalone code to reproduce the issue
```shell
ERROR: Could not find a version that satisfies the requirement tensorflow (from versions: none)
ERROR: No matching distribution found for tensorflow
```
### Relevant log output
_No response_ | stat:awaiting tensorflower,type:feature,type:build/install,subtype:macOS,2.17 | medium | Critical |
2,614,694,842 | flutter | Packages repo LUCI builds process logs excessively | ### Type of Request
bug
### Infrastructure Environment
LUCI
### What is happening?
Example build: https://ci.chromium.org/ui/p/flutter/builders/try/Mac_arm64%20ios_platform_tests_shard_5%20master/17374/overview
The last steps are repeatedly initializing and processing the logs. It's extremely fast but actually does seem to be [re-uploading the logs over and over](https://logs.chromium.org/logs/flutter/buildbucket/cr-buildbucket/8733088378138433393/+/u/Run_package_tests/process_logs__6_/gsutil_upload_logs_d80d2367-8dd1-41bd-8c5d-806e659e3978/stdout).
The repeated uploading is wasted and makes the steps difficult to read. For example, the "remove simulator" step in the middle of the above screenshot is difficult to spot.
### Steps to reproduce
_No response_
### Expected results
_No response_ | package,team-infra,P2,triaged-infra | low | Critical |
2,614,733,237 | vscode | Clarify Walkthrough step complete criteria | >Should the step be marked as completed?
>
> No the step should NOT be marked. 🤔
> Just tried it my self and I see that the step is not marked as complete when it reappears.
_Originally posted by @bhavyaus in [#226184](https://github.com/microsoft/vscode/issues/226184#issuecomment-2438417032)_ | bug,getting-started | low | Minor |
2,614,757,120 | bitcoin | MIN_STANDARD_TX_NONWITNESS_SIZE prevents efficient spending of P2A outputs | ### Please describe the feature you'd like to see added.
The most efficient way to spend a single P2A output to an `OP_RETURN` results in a transaction 61 bytes in size, below the 65 byte limit enforced by `MIN_STANDARD_TX_NONWITNESS_SIZE`. For example:
```01000000017989c51d11e9e1e6aa634d471e31900141fe44bd491bcb5996f948b9039b232e0000000000ffffffff010000000000000000016a00000000```
This transaction should be standard.
### Is your feature related to a problem, if so please describe it.
_No response_
### Describe the solution you'd like
_No response_
### Describe any alternatives you've considered
_No response_
### Please leave any additional context
_No response_ | TX fees and policy | low | Minor |
2,614,767,140 | flutter | [vector_graphics] Document public APIs | In importing `vector_graphics*` and updating it to use our repo analysis options, I had to do some file-level ignores of missing docs on public APIs in a number of places, because fixing it all during the import without knowing the code was infeasible. We shouldn't have those file-level ignores indefinitely because it means we have code that doesn't meet our documentation standards. I'll be annotating all of those `ignore`s with TODOs referencing this issue. | package,P2,c: tech-debt,team-engine,triaged-engine,p: vector_graphics | low | Minor |
2,614,830,594 | flutter | [packages] `missing_code_block_language_in_doc_comment` lint fails in Dart version 3.4 | **Context**
`missing_code_block_language_in_doc_comment` has a bug fix that prevent false positives in https://github.com/dart-lang/sdk/commit/b6ac281270ac751175c5298ce78dd9f2cb3bd594. It just so happens that the rest of the lint work is in Dart 3.4 and this fix is in Dart 3.5.
**What's wrong**
In the PR to add this lint to `flutter/packages`, https://github.com/flutter/packages/pull/6473, the Linux analyze N-1 tryjob fails because it's currently on 3.4, while N-2 is on 3.3 which doesn't have the lint, and stable is on 3.5 with the correct lint fix. This causes the Linux analyze N-1 tryjob to have false positives.
**What needs to be done**
PR https://github.com/flutter/packages/pull/6473 will add `// ignore:`s for each of those false positives and once stable gets updated, we'll clean these up.
| package | low | Critical |
2,614,832,292 | godot | Content Margin ignored when changing Button text on press | ### Tested versions
- Reproducible in v4.3.stable.official [77dcf97d8], v4.4.dev3.official [f4af8201b]
- Not reproducible in v4.2.2.stable.mono.official [15073afe3]
### System information
Godot v4.3.stable - Windows 10.0.19045 - Vulkan (Mobile) - dedicated NVIDIA GeForce RTX 2080 (NVIDIA; 32.0.15.6094) - Intel(R) Core(TM) i7-9700K CPU @ 3.60GHz (8 Threads)
### Issue description
The "Content Margin" property of a StyleBox seems to be ignored if you change the text of a Button during the `pressed` event.
Here is an example, where the `content_margin_right` is set to `200`. When the Button is pressed, `text = "Changed text"`.
In 4.3, the content margin setting appears to not be applied:
In 4.2, the content margin remains in effect:
Other observations
- Simply changing the `.text` property does not result in this behavior (e.g. during `_ready()` or `_process()`)
- It does not seem to matter whether the StyleBox is part of default theme, a resource on disk, or just configured directly on the button.
- The StyleBox's content_margin_right value is not actually changed. If you assign it again in code (e.g. `get_theme_stylebox("normal").content_margin_right = 200`, or any `content_margin` property), it will take effect again
### Steps to reproduce
Create a Button
Add a Theme Override->Styles->"normal", creating a new StyleBoxFlat
Set a `content_margin_right` value, e.g. 200
Add a script to the Button
Connect a handler for the `pressed` event of the button
Change the `.text` of the button in the handler, e.g.
```gdscript
func _on_pressed():
text = "Changed text"
```
Run the project and click the button.
Observe that the content_margin is removed.
### Minimal reproduction project (MRP)
[button-content-margin-bug.zip](https://github.com/user-attachments/files/17526125/button-content-margin-bug.zip)
| bug,topic:gui | low | Critical |
2,614,840,923 | pytorch | torch.cond complains two tensors have different metadata | ### 🐛 Describe the bug
internal post: https://fb.workplace.com/groups/1028545332188949/posts/1073473854362763
repro:
```
class M(torch.nn.Module):
def forward(self, x, flag):
def true_fn(x):
ori_size, new_size = (
(
math.trunc(x.shape[-2] / 1),
math.trunc(x.shape[-1] / 1),
),
(
math.trunc(x.shape[-2] + 0.5),
math.trunc(x.shape[-1] + 0.5),
),
)
x = F.interpolate(x, size=new_size, mode="bilinear")
x = F.interpolate(x, size=ori_size, mode="bilinear")
return x
def false_fn(x):
return x.clone()
return torch.cond(
flag,
true_fn,
false_fn,
[x],
)
return x
input1 = (
torch.rand(1, 3, 28, 28, device="cuda"),
torch.tensor([True]),
)
model = M().cuda()
# sanity check
_ = model(*input1)
dynamic_shapes = {
"x": {2: torch.export.Dim.DYNAMIC, 3: torch.export.Dim.DYNAMIC},
"flag": None,
}
ep = torch.export.export(model, input1, dynamic_shapes=dynamic_shapes, strict=False)
path = torch._inductor.aot_compile(ep.module(), input1)
```
errors:
```
torch._inductor.exc.LoweringException: AssertionError: (0, StorageBox(
ComputedBuffer(name='true_graph_0_buf8', layout=FixedLayout('cuda', torch.float32, size=[1, 3, TruncToInt(IntTrueDiv(s0, 1)), TruncToInt(IntTrueDiv(s1, 1))], stride=[3*TruncToInt(IntTrueDiv(s0, 1))*TruncToInt(IntTrueDiv(s1, 1)), TruncToInt(IntTrueDiv(s0, 1))*TruncToInt(IntTrueDiv(s1, 1)), TruncToInt(IntTrueDiv(s1, 1)), 1]), data=Pointwise(device=device(type='cuda', index=0), dtype=torch.float32, inner_fn=<function make_pointwise.<locals>.inner.<locals>.inner_fn at 0x7f361637ad40>, ranges=[1, 3, TruncToInt(IntTrueDiv(s0, 1)), TruncToInt(IntTrueDiv(s1, 1))]))
), StorageBox(
ComputedBuffer(name='false_graph_0_buf0', layout=FixedLayout('cuda', torch.float32, size=[1, 3, s0, s1], stride=[3*s0*s1, s0*s1, s1, 1]), data=Pointwise(device=device(type='cuda', index=0), dtype=torch.float32, inner_fn=<function Buffer.make_loader.<locals>.loader at 0x7f3615939510>, ranges=[1, 3, s0, s1]))
))
target: cond
args[0]: TensorBox(StorageBox(
InputBuffer(name='arg1_1', layout=FixedLayout('cpu', torch.bool, size=[1], stride=[1]))
))
args[1]: Subgraph(name='true_graph_0', graph_module=<lambda>(), graph=<torch._inductor.graph.SubgraphLowering object at 0x7f36163db910>)
args[2]: Subgraph(name='false_graph_0', graph_module=<lambda>(), graph=<torch._inductor.graph.SubgraphLowering object at 0x7f36163b1330>)
args[3]: [TensorBox(StorageBox(
InputBuffer(name='arg0_1', layout=FixedLayout('cuda', torch.float32, size=[1, 3, s0, s1], stride=[3*s0*s1, s0*s1, s1, 1]))
))]
```
### Versions
trunk
cc @ezyang @chauhang @penguinwu @avikchaudhuri @gmagogsfm @zhxchen17 @tugsbayasgalan @angelayi @suo @ydwu4 | triaged,oncall: pt2,oncall: export | low | Critical |
2,614,849,171 | vscode | Secondary sidebar does not fallback to its view when view got removed | See how the aux sidebar appears as if empty even though it has a view:
Steps to Reproduce:
1. setup exploration and insiders build to use settings sync
2. in insiders have chat in the aux bar, close aux bar
3. in exploration move chat into primary bar and trigger sync
4. in insiders wait for sync to apply and open aux bar
=> aux bar appears empty even though it has a view
I think here our logic for falling back to another "default" view is not picking up the other view that is there.
Note: the view in aux bar is registered based on a condition that evaluates late, so its possible this would not happen if the view was there on startup 🤔
| bug,layout,workbench-views,workbench-auxsidebar | low | Minor |
2,614,854,921 | godot | Glow extremely Slow with Mobile on Android | ### Tested versions
4.4.dev3, (Probably also 4.3)
### System information
Windows 10 High-End PC, tested on Android 14, Samsung Galaxy A35
### Issue description
With Mobile Renderer enabled, I created an empty scene without a sky or anything, and just put a MeshInstance with a Cube Mesh and a Standard Emissive Material. It renders with smooth 120 FPS on my Galaxy A35.
Then I enable Glow to actually see some glowing. It works on my PC, but on my phone:
1. The glow is not visible, as if it is turned off somehow.
2. FPS drops from 120 to 37...
Then I switched to Compatibility Renderer:
1. Glow is visible now
2. FPS is back to 120
If I do the same in Unreal Engine, no matter if I use GLES3 or Vulkan renderer there, it is always at 60 FPS and Glow is always working.
So there must be a huge performance issue with turning on Glow/Postprocessing with Mobile Renderer.
I read an official article that SSGI and other effects are not optimized in Godot yet and will improved with upcoming releases, so hopefully Glow will be part of that upcoming optimizations?
Anyway, thanks for your hard work on the engine, just wanted to report this and hope it gets fixed soon. (Still kinda hope there is just a setting I did wrong).
### Steps to reproduce
I attached MRP. Basically just make an emissive cube, run on low/mid-range android device with Mobile compared to Compatibility renderer.
### Minimal reproduction project (MRP)
[slowglowmrp.zip](https://github.com/user-attachments/files/17526220/slowglowmrp.zip)
| bug,topic:rendering,performance | low | Major |
2,614,855,528 | tauri | [bug] cargo tauri android dev does not work | ### Describe the bug
emulator starts. app starts. blank page in app.
following ERROR in console:
```bash
Performing Streamed Install
Success
Starting: Intent { cmp=com.tauri_gui.app/.MainActivity }
--------- beginning of main
10-25 18:33:01.139 7699 7699 I m.tauri_gui.ap: Late-enabling -Xcheck:jni
10-25 18:33:01.162 7699 7699 I m.tauri_gui.ap: Unquickening 12 vdex files!
10-25 18:33:01.165 7699 7699 W m.tauri_gui.ap: Unexpected CPU variant for X86 using defaults: x86
10-25 18:33:03.725 7699 7699 W m.tauri_gui.ap: Accessing hidden method Landroid/view/View;->computeFitSystemWindows(Landroid/graphics/Rect;Landroid/graphics/Rect;)Z (greylist, reflection, allowed)
10-25 18:33:03.742 7699 7699 W m.tauri_gui.ap: Accessing hidden method Landroid/view/ViewGroup;->makeOptionalFitsSystemWindows()V (greylist, reflection, allowed)
10-25 18:33:04.242 7699 7699 I WebViewFactory: Loading com.google.android.webview version 83.0.4103.106 (code 410410681)
10-25 18:33:04.251 7699 7699 I m.tauri_gui.ap: The ClassLoaderContext is a special shared library.
Info Watching /home/sun/shared/git/tauri-gui/src-tauri for changes...
Info Watching /home/sun/shared/git/tauri-gui/src-tauri for changes...
10-25 18:33:04.333 7699 7699 I m.tauri_gui.ap: The ClassLoaderContext is a special shared library.
10-25 18:33:04.443 7699 7699 I cr_LibraryLoader: Loaded native library version number "83.0.4103.106"
10-25 18:33:04.443 7699 7699 I cr_CachingUmaRecorder: Flushed 3 samples from 3 histograms.
10-25 18:33:04.568 7699 7699 I TetheringManager: registerTetheringEventCallback:com.tauri_gui.app
10-25 18:33:04.594 7699 7774 W chromium: [WARNING:dns_config_service_posix.cc(341)] Failed to read DnsConfig.
10-25 18:33:04.594 7699 7735 I RustStdoutStderr: [WARNING:dns_config_service_posix.cc(341)] Failed to read DnsConfig.
10-25 18:33:04.788 7699 7699 I Choreographer: Skipped 58 frames! The application may be doing too much work on its main thread.
10-25 18:33:04.954 7699 7720 I Gralloc4: mapper 4.x is not supported
10-25 18:33:05.272 7699 7720 I OpenGLRenderer: Davey! duration=1463ms; Flags=1, IntendedVsync=1753651430032, Vsync=1754618096660, OldestInputEvent=9223372036854775807, NewestInputEvent=0, HandleInputStart=1754634855782, AnimationStart=1754634858817, PerformTraversalsStart=1754634860865, DrawStart=1754866078336, SyncQueued=1754906258212, SyncStart=1754909366856, IssueDrawCommandsStart=1754909498669, SwapBuffers=1754990242778, FrameCompleted=1755118317873, DequeueBufferDuration=72519, QueueBufferDuration=740027, GpuCompleted=0,
10-25 18:33:05.284 7699 7775 W m.tauri_gui.ap: Accessing hidden method Landroid/media/AudioManager;->getOutputLatency(I)I (greylist, reflection, allowed)
10-25 18:33:05.332 7699 7775 W cr_media: Requires BLUETOOTH permission
10-25 18:33:06.016 7699 7788 I VideoCapabilities: Unsupported profile 4 for video/mp4v-es
10-25 18:33:06.018 7699 7788 W cr_MediaCodecUtil: HW encoder for video/avc is not available on this device.
10-25 18:33:06.145 7699 7720 I OpenGLRenderer: Davey! duration=1311ms; Flags=0, IntendedVsync=1754668113787, Vsync=1755134780435, OldestInputEvent=9223372036854775807, NewestInputEvent=0, HandleInputStart=1755146382750, AnimationStart=1755146384913, PerformTraversalsStart=1755153804069, DrawStart=1755154033136, SyncQueued=1755154564377, SyncStart=1755166660271, IssueDrawCommandsStart=1755167044663, SwapBuffers=1755859292143, FrameCompleted=1755991924439, DequeueBufferDuration=47150157, QueueBufferDuration=16711743, GpuCompleted=0,
10-25 18:33:06.898 7699 7699 W Tauri/Console: File: http://tauri.localhost/ - Line 590 - Msg: The `integrity` attribute is currently ignored for preload destinations that do not support subresource integrity. See https://crbug.com/981419 for more information
10-25 18:33:07.003 7699 7699 E Tauri/Console: File: http://tauri.localhost/ - Line 581 - Msg: Uncaught SyntaxError: Unexpected reserved word
10-25 18:33:09.964 7699 7699 W Tauri/Console: File: - Line 0 - Msg: The resource http://tauri.localhost/tauri-gui-ui-c3ba43d7a57ce0b1_bg.wasm was preloaded using link preload but not used within a few seconds from the window's load event. Please make sure it has an appropriate `as` value and it is preloaded intentionally.
```
### Reproduction
_No response_
### Expected behavior
_No response_
### Full `tauri info` output
```text
--------
```
### Stack trace
```text
-
```
### Additional context
_No response_ | type: bug,status: needs triage,platform: Android | low | Critical |
2,614,879,249 | vscode | Extension packs with only 1 walkthrough should open on that walkthrough registration | null | bug,regression,getting-started | low | Minor |
2,614,881,629 | vscode | Show window picker for screenshot feature | From @rperez030: "The troubleshoot command is helpful, but I wish the option to obtain a screenshot was available outside that use case. For example, if I’m coding a web app, I’d like to be able to obtain a screenshot containing the running app to get feedback on the visual layout, or to ask Copilot for the CSS code to change a specific aspect of it depending on the answer." | feature-request,accessibility,chat | low | Minor |
2,614,900,521 | react | [React 19] Parameter order for server action when using `useActionState` | ## Summary
`useActionState` currently requires accepting an additional state argument as the _first_ parameter of a server action, like so (adapted from [Next.js documentation](https://nextjs.org/docs/app/building-your-application/data-fetching/server-actions-and-mutations#server-side-form-validation)):
```diff
// in app/actions.ts
-export async function updateUser(userId: string, formData: FormData) {
+export async function updateUser(prevState: any, userId: string, formData: FormData) {
```
This interferes with the use case of binding leading arguments to the action (adapted from [Next.js documentation](https://nextjs.org/docs/app/building-your-application/data-fetching/server-actions-and-mutations#passing-additional-arguments)):
```typescript
// in app/client-component.tsx
import { updateUser } from './actions'
const updateUserWithId = updateUser.bind(null, 'some id')
const [state, formAction] = useActionState(updateUserWithId, 'initial state')
```
For the above example to work, `updateUser` would need to accept the previous state as the _middle_ parameter:
```diff
// in app/actions.ts
-export async function updateUser(prevState: any, userId: string, formData: FormData) {
+export async function updateUser(userId: string, prevState: any, formData: FormData) {
```
Additionally, the server action might not actually care about the previous state. For example, if the action validates form data and the state is just a validation error message, then the action likely doesn't care about previous error messages. In such cases, it would be nicer DX to be able to omit the state parameter.
## Proposal
Make `useActionState` pass the previous state to the server action as the _last_ argument, always:
```diff
// in app/actions.ts
-export async function updateUser(prevState: any, userId: string, formData: FormData) {
+export async function updateUser(userId: string, formData: FormData, prevState: any) {
```
This might also enable skipping the serialization of the previous state when the server action does not use it (i.e. when `action.length` < 2).
## Additional Information
If the React team agrees to the change, I would like to submit a PR as my first contribution to React. I searched through the codebase for definitions of `useActionState`, but could not determine how [`dispatcher.useActionState`](https://github.com/facebook/react/blob/cae764ce81b1bd6c418e9e23651794b6b09208e8/packages/react/src/ReactHooks.js#L248) is implemented. Is that implemented externally?
| React 19 | low | Critical |
2,614,907,163 | vscode | Large tooltip when not tokenized on long lines makes code hard to read | <!-- ⚠️⚠️ Do Not Delete This! feature_request_template ⚠️⚠️ -->
<!-- Please read our Rules of Conduct: https://opensource.microsoft.com/codeofconduct/ -->
<!-- Please search existing issues to avoid creating duplicates. -->
<!-- Describe the feature you'd like. -->
When editing code inside a eval() call that is a large webpack-gernerated file (trying to fix bugs around importing node into web), there is a tooltip that is fairly large and says "Tokenization is skepped for long lines for performance reasons. This can be configured via editor.maxTokenizationLineLength. " This tooltip comes up somewhat quickly when hovering over this code, and so I have to constantly move my mouse in order to read the code. Is it possible to either make the tooltip time to show up much longer (about 5 times as long I think would be reasonable) or have a only show this once thing.
This is absolutely not a priority but would probably be an easy fix.
Thanks for your time! | tokenization | low | Critical |
2,614,920,888 | tensorflow | Regression: TF 2.18 crashes with cudaSetDevice failing due to GPU being busy | ### Issue type
Bug
### Have you reproduced the bug with TensorFlow Nightly?
No
### Source
binary
### TensorFlow version
tensorflow[and-cuda] 2.18
### Custom code
No
### OS platform and distribution
Rocky 9.1
### Mobile device
_No response_
### Python version
3.12.7
### Bazel version
_No response_
### GCC/compiler version
_No response_
### CUDA/cuDNN version
get_build_info gives cuda 12.5.1, cudnn version 9, Driver version 525.78.01, system CUDA version 12.0
### GPU model and memory
RTX 3090
### Current behavior?
Tensorflow[and-cuda] 2.17 installed cuda_version 12.3 and cudnn 8, and the code below works with the normal error spew about being unable to register cuda factories. With 2.18, I get a crash about the gpu is busy.
This is on a desktop workstation with a window manager, so TF cannot have the entire GPU, but I'm not sure if that's the cause of the problem.
These are pretty normal conda environments, with `pip install "tensorflow[and-cuda]"` and then
```
export XLA_FLAGS="--xla_gpu_cuda_data_dir=/path/to/my/conda/environment"
NVIDIA_DIR=$(dirname $(dirname $(python -c "import nvidia.cudnn; print(nvidia.cudnn.__file__)")))
pathAccum=""
for dir in $NVIDIA_DIR/*; do
if [ -d "$dir/lib" ]; then
pathAccum="$dir/lib:$pathAccum"
fi
done
export LD_LIBRARY_PATH="${pathAccum}${LD_LIBRARY_PATH}"
```
inside the activate.d for the conda environment.
I have tried with and without this activate script. It is necessary for 2.17, and I get the same error when I remove it for 2.18. I'm not sure if this is due to "hermetic cuda", since it's not at all clear what that means to an end user.
Interestingly, `tf.config.list_physical_devices("GPU")` correctly identifies the GPU, it returns `PhysicalDevice(name='/physical_device:GPU:0', device_type='GPU')`.
### Standalone code to reproduce the issue
```shell
#!/usr/bin/env python3
# TensorFlow and tf.keras
from tensorflow import keras
model = keras.Sequential([
keras.layers.Flatten(input_shape=(28, 28)),
keras.layers.Dense(128, activation='relu'),
keras.layers.Dense(10)
])
```
### Relevant log output
```shell
TF 2.17 (no bug):
2024-10-25 14:07:40.179745: I tensorflow/core/util/port.cc:153] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`.
2024-10-25 14:07:40.187066: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:485] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered
2024-10-25 14:07:40.194965: E external/local_xla/xla/stream_executor/cuda/cuda_dnn.cc:8454] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
2024-10-25 14:07:40.197313: E external/local_xla/xla/stream_executor/cuda/cuda_blas.cc:1452] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
2024-10-25 14:07:40.203777: I tensorflow/core/platform/cpu_feature_guard.cc:210] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.
To enable the following instructions: AVX2 AVX_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags.
2024-10-25 14:07:40.624911: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT
/scratch/miniconda/install/envs/bpreveal-teak/lib/python3.12/site-packages/keras/src/layers/reshaping/flatten.py:37: UserWarning: Do not pass an `input_shape`/`input_dim` argument to a layer. When using Sequential models, prefer using an `Input(shape)` object as the first layer in the model instead.
super().__init__(**kwargs)
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
I0000 00:00:1729883261.043484 2360745 cuda_executor.cc:1015] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero. See more at https://github.com/torvalds/linux/blob/v6.0/Documentation/ABI/testing/sysfs-bus-pci#L344-L355
I0000 00:00:1729883261.057001 2360745 cuda_executor.cc:1015] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero. See more at https://github.com/torvalds/linux/blob/v6.0/Documentation/ABI/testing/sysfs-bus-pci#L344-L355
I0000 00:00:1729883261.057122 2360745 cuda_executor.cc:1015] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero. See more at https://github.com/torvalds/linux/blob/v6.0/Documentation/ABI/testing/sysfs-bus-pci#L344-L355
I0000 00:00:1729883261.058905 2360745 cuda_executor.cc:1015] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero. See more at https://github.com/torvalds/linux/blob/v6.0/Documentation/ABI/testing/sysfs-bus-pci#L344-L355
I0000 00:00:1729883261.059226 2360745 cuda_executor.cc:1015] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero. See more at https://github.com/torvalds/linux/blob/v6.0/Documentation/ABI/testing/sysfs-bus-pci#L344-L355
I0000 00:00:1729883261.059269 2360745 cuda_executor.cc:1015] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero. See more at https://github.com/torvalds/linux/blob/v6.0/Documentation/ABI/testing/sysfs-bus-pci#L344-L355
I0000 00:00:1729883261.521319 2360745 cuda_executor.cc:1015] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero. See more at https://github.com/torvalds/linux/blob/v6.0/Documentation/ABI/testing/sysfs-bus-pci#L344-L355
I0000 00:00:1729883261.521431 2360745 cuda_executor.cc:1015] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero. See more at https://github.com/torvalds/linux/blob/v6.0/Documentation/ABI/testing/sysfs-bus-pci#L344-L355
I0000 00:00:1729883261.521503 2360745 cuda_executor.cc:1015] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero. See more at https://github.com/torvalds/linux/blob/v6.0/Documentation/ABI/testing/sysfs-bus-pci#L344-L355
2024-10-25 14:07:41.521550: I tensorflow/core/common_runtime/gpu/gpu_device.cc:2021] Created device /job:localhost/replica:0/task:0/device:GPU:0 with 18871 MB memory: -> device: 0, name: NVIDIA GeForce RTX 3090 Ti, pci bus id: 0000:01:00.0, compute capability: 8.6
TF 2.18 (with bug):
2024-10-25 14:02:53.202498: I tensorflow/core/util/port.cc:153] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`.
2024-10-25 14:02:53.209011: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:477] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
E0000 00:00:1729882973.216967 2360012 cuda_dnn.cc:8310] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
E0000 00:00:1729882973.219326 2360012 cuda_blas.cc:1418] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
2024-10-25 14:02:53.227106: I tensorflow/core/platform/cpu_feature_guard.cc:210] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.
To enable the following instructions: AVX2 AVX_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags.
/scratch/miniconda/install/envs/bpreveal-testing/lib/python3.12/site-packages/keras/src/layers/reshaping/flatten.py:37: UserWarning: Do not pass an `input_shape`/`input_dim` argument to a layer. When using Sequential models, prefer using an `Input(shape)` object as the first layer in the model instead.
super().__init__(**kwargs)
Traceback (most recent call last):
File "/home/cm2363/scratch/./tfTest.py", line 5, in <module>
model = keras.Sequential([
^^^^^^^^^^^^^^^^^^
File "/scratch/miniconda/install/envs/bpreveal-testing/lib/python3.12/site-packages/keras/src/models/sequential.py", line 76, in __init__
self._maybe_rebuild()
File "/scratch/miniconda/install/envs/bpreveal-testing/lib/python3.12/site-packages/keras/src/models/sequential.py", line 141, in _maybe_rebuild
self.build(input_shape)
File "/scratch/miniconda/install/envs/bpreveal-testing/lib/python3.12/site-packages/keras/src/layers/layer.py", line 226, in build_wrapper
original_build_method(*args, **kwargs)
File "/scratch/miniconda/install/envs/bpreveal-testing/lib/python3.12/site-packages/keras/src/models/sequential.py", line 187, in build
x = layer(x)
^^^^^^^^
File "/scratch/miniconda/install/envs/bpreveal-testing/lib/python3.12/site-packages/keras/src/utils/traceback_utils.py", line 122, in error_handler
raise e.with_traceback(filtered_tb) from None
File "/scratch/miniconda/install/envs/bpreveal-testing/lib/python3.12/site-packages/keras/src/backend/tensorflow/core.py", line 125, in convert_to_tensor
return tf.convert_to_tensor(x, dtype=dtype)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
tensorflow.python.framework.errors_impl.InternalError: cudaSetDevice() on GPU:0 failed. Status: CUDA-capable device(s) is/are busy or unavailable
```
| stat:awaiting tensorflower,type:build/install,comp:gpu,TF 2.18 | low | Critical |
2,614,925,173 | flutter | [vector_graphics] update README to document usage of flutter tool transfomers | Users should use these intead of checking in the binary files which could break, though haven't for years... | P2,team-engine,triaged-engine,p: vector_graphics | low | Minor |
2,614,931,879 | flutter | `analyze_continuously_test.dart` fails locally, succeeds on CI | ```txt
/Users/matanl/Developer/flutter/packages/flutter_tools/test/commands.shard/hermetic/analyze_continuously_test.dart: analyze --watch AnalysisServer success[0m
PathNotFoundException: Cannot open file, path = '/Users/matanl/Developer/flutter/version' (OS Error: No such file or directory, errno = 2)
#0 _File.throwIfError (dart:io/file_impl.dart:675:7)
#1 _File.openSync (dart:io/file_impl.dart:490:5)
#2 _File.readAsBytesSync (dart:io/file_impl.dart:574:18)
#3 _File.readAsStringSync (dart:io/file_impl.dart:624:18)
#4 ForwardingFile.readAsStringSync (package:file/src/forwarding/forwarding_file.dart:99:16)
#5 _DefaultPub._updateVersionAndPackageConfig (package:flutter_tools/src/dart/pub.dart:720:50)
#6 _DefaultPub.get (package:flutter_tools/src/dart/pub.dart:373:11)
<asynchronous suspension>
#7 main.<anonymous closure>.<anonymous closure> (file:///Users/matanl/Developer/flutter/packages/flutter_tools/test/commands.shard/hermetic/analyze_continuously_test.dart:89:7)
<asynchronous suspension>
#8 testUsingContext.<anonymous closure>.<anonymous closure>.<anonymous closure>.<anonymous closure>.<anonymous closure> (file:///Users/matanl/Developer/flutter/packages/flutter_tools/test/src/context.dart:152:26)
<asynchronous suspension>
#9 AppContext.run.<anonymous closure> (package:flutter_tools/src/base/context.dart:153:19)
<asynchronous suspension>
#10 testUsingContext.<anonymous closure>.<anonymous closure>.<anonymous closure>.<anonymous closure> (file:///Users/matanl/Developer/flutter/packages/flutter_tools/test/src/context.dart:141:22)
<asynchronous suspension>
```
However it passes [fine on CI in the same state](https://logs.chromium.org/logs/flutter/buildbucket/cr-buildbucket/8733080043648608785/+/u/run_test.dart_for_tool_tests_shard_and_subshard_commands/stdout):
```txt
03:07 +282 ~2: loading test/commands.shard/hermetic/analyze_continuously_test.dart
03:07 +282 ~2: test/commands.shard/hermetic/analyze_continuously_test.dart: (setUpAll)
03:07 +282 ~2: test/commands.shard/hermetic/analyze_continuously_test.dart: AnalysisServer errors
03:07 +283 ~2: test/commands.shard/hermetic/analyze_continuously_test.dart: Can run AnalysisService with customized cache location --watch
03:08 +284 ~2: test/commands.shard/hermetic/analyze_continuously_test.dart: Can run AnalysisService without suppressing analytics
03:08 +285 ~2: test/commands.shard/hermetic/analyze_continuously_test.dart: Returns no errors when source is error-free
03:08 +286 ~2: test/commands.shard/hermetic/analyze_continuously_test.dart: AnalysisService --watch skips errors from non-files
03:08 +287 ~2: test/commands.shard/hermetic/analyze_continuously_test.dart: analyze --watch AnalysisServer success
03:09 +288 ~2: test/commands.shard/hermetic/analyze_continuously_test.dart: Can run AnalysisService with customized cache location
03:09 +289 ~2: test/commands.shard/hermetic/analyze_continuously_test.dart: (tearDownAll)
```
Maybe it has something to do with `Cache.flutterRoot = getFlutterRoot();`? | tool,P2,c: tech-debt,team-tool,triaged-tool | low | Critical |
2,614,954,399 | flutter | [A11y][iOS]: SnackBar shows more Voice Control labels than expected | Tracking b/325610878.
### Steps to reproduce
1. Enable iOS Voice Control in the settings app.
2. In a Flutter app (minimal sample app below), cause a Material SnackBar widget to be displayed.
3. Observe the Voice Control labels.
### Expected results
There should be labels for interactive UI elements.
### Actual results
There are more labels than there are interactive UI elements.
This was observed for Material2 and Material3 themes.
### Code sample
<details open><summary>Code sample</summary>
```dart
import 'package:flutter/material.dart';
void main() {
runApp(MyApp());
}
class MyApp extends StatelessWidget {
@override
Widget build(BuildContext context) {
return MaterialApp(
theme: ThemeData(useMaterial3: false),
title: 'Flutter Demo',
home: MyHomePage(title: 'Flutter Demo Home Page'),
);
}
}
class MyHomePage extends StatefulWidget {
MyHomePage({Key? key, required this.title}) : super(key: key);
final String title;
@override
_MyHomePageState createState() => _MyHomePageState();
}
class _MyHomePageState extends State<MyHomePage> {
void displaySnackBar(BuildContext context) {
ScaffoldMessenger.of(context).clearSnackBars();
ScaffoldMessenger.of(context).showSnackBar(
SnackBar(
content: Text('test bar'),
// // Enable these in order to see more numbered labels with iOS Voice Control.
// action: SnackBarAction(
// label: 'close',
// onPressed: () => print('close'),
// ),
// showCloseIcon: true,
),
);
}
@override
Widget build(BuildContext context) {
return Scaffold(
appBar: AppBar(
title: Text(widget.title, style: TextStyle(fontFamily: 'ProductSans')),
),
body: Center(
child: Text(
'test',
key: Key('CountText'),
),
),
floatingActionButton: FloatingActionButton(
onPressed: () => displaySnackBar(context),
tooltip: 'Increment',
child: const Icon(Icons.add),
),
);
}
}
```
</details>
### Screenshots or Video
<details open>
<summary>screenshot of extra labels</summary>
</details>
### Logs
<details open><summary>Logs</summary>
```console
[Paste your logs here]
```
</details>
### Flutter Doctor output
<details open><summary>Doctor output</summary>
```console
[✓] Flutter (Channel google3, on macOS 14.7 23H124 darwin-x64, locale en)
• Framework revision 3cd12f2c06 (0 days ago), 2024-10-25T00:00:00.000
• Engine revision c4b0184c87
• Dart version 3067d697ae
[✓] Android toolchain - develop for Android devices (Android SDK version Stable)
• Android SDK at google3
• Platform Stable, build-tools Stable
• Java binary at: /Applications/Android Studio with Blaze
Beta.app/Contents/jbr/Contents/Home/bin/java
• Java version OpenJDK Runtime Environment (build 21.0.3+-79915915-b509.11)
[✓] VS Code (version 1.94.2)
• VS Code at /Applications/Visual Studio Code.app/Contents
• Flutter extension version 3.86.0
[✓] Xcode - develop for iOS and macOS (Xcode 15.0)
• Xcode at /Applications/Xcode.app/Contents/Developer
[✓] Connected device (1 available)
! Error: Browsing on the local area network for CP’s iPhone (2). Ensure the
device is unlocked and attached with a cable or associated with the same
local area network as this Mac.
The device must be opted into Developer Mode to connect wirelessly. (code
-27)
```
</details>
| platform-ios,framework,f: material design,a: accessibility,P2,customer: quake (g3),found in release: 3.24,team-accessibility,triaged-accessibility,found in release: 3.27 | low | Critical |
2,614,971,676 | flutter | Wish: A `rerun-failed-tasks-only` tag I could use to ask CI to re-run only tasks failed in a prior commit | Often I upload a PR, and observe that X of XX CI tasks fail.
I then work on fixing (either by updating tests, or the code, or both). While not sound, I'd like the ability to instruct CI to prioritize (or only) run _previously failed tasks_, so I can get quicker results instead of waiting for 100s of tasks to re-run, many of which might be unrelated to the code I'm changing, and cause false-negatives (due to flakes).
This behavior would not be safe to land changes, but would make iteration time faster (at least for me). | team-infra,P2,triaged-infra | low | Critical |
2,614,995,107 | PowerToys | Advanced Paste - History Access via Keyboard | ### Description of the new feature / enhancement
I recently switched from Ditto to Powertoys Advanced Clipboard. Prior to that I used Alfred on macOS to do clipboard history.
PowerToys Advanced Paste departs from the behavior of the vast majority of clipboard viewers in that I can not use ONLY the keyboard to navigate.
As a user of PowerToys who is inside of a document with both hands on my keyboard, when I need to paste, I use Ctl-V and Ctl-X etc frequently.
When I need to paste from the Advanced Paste tool (with AI enabled, no idea if that changes the behavior) it auto focuses on the prompt box. In order to access an item on the clipboard history that is 5 from the top, I have to hit the following key combinations:
1. Ctl-Shift-V (my activator key shortcut)
2. Tab
3. Tab
4. Enter
5. Arrow key to the correct item
6. Enter
7. Ctl-V
Conversely, in Ditto and Alfred (and most clipboard history tools)...
1. Activator keyboard shortcut
2. Down arrow to the one you want
3. Enter to paste
Candidly, it's kind of a pain in the butt to use the clipboard history because of that. This is a power user tool, but this interface feels anything but power.
### Scenario when this would be used?
Every day all day when I need to paste clipboard history. Probably 50 times a day.
### Supporting information
I have proof as a user of the product that it is cumbersome to get to the clipboard history. | Needs-Triage | low | Minor |
2,615,016,607 | react | [Compiler Bug]: Error when calling `React.createElement(..., { ref })` | ### What kind of issue is this?
- [X] React Compiler core (the JS output is incorrect, or your app works incorrectly after optimization)
- [ ] babel-plugin-react-compiler (build issue installing or using the Babel plugin)
- [ ] eslint-plugin-react-compiler (build issue installing or using the eslint plugin)
- [ ] react-compiler-healthcheck (build issue installing or using the healthcheck script)
### Link to repro
https://playground.react.dev/#N4Igzg9grgTgxgUxALhAMygOzgFwJYSYAEMCaAkpgBI4C2ANgKL0K0KY4AUAlEcADrEicQmBwkyRALxEoYBACUynTFHr1uAbkFEJOWMSUBDXADo4pIzgTNW7LvxBwjmAG5GwjgDR8JaIgC+WoIBIAFAA
### Repro steps
[Playground link](https://playground.react.dev/#N4Igzg9grgTgxgUxALhAMygOzgFwJYSYAEMCaAkpgBI4C2ANgKL0K0KY4AUAlEcADrEicQmBwkyRALxEoYBACUynTFHr1uAbkFEJOWMSUBDXADo4pIzgTNW7LvxBwjmAG5GwjgDR8JaIgC+WoIBIAFAA)
This code:
```js
function refInHtmlElement() {
const ref = useRef(null);
return React.createElement("canvas", { ref });
}
```
Has this error:
> InvalidReact: Ref values (the `current` property) may not be accessed during render. (https://react.dev/reference/react/useRef) (3:3)
Even though we're using a ref in the way it's meant to be used. If we rewrite it in JSX, the error goes away:
```jsx
function refInHtmlElement() {
const ref = useRef(null);
return <canvas ref={ref} />;
}
```
I find this behavior surprising, because I always thought that JSX desugared down to `React.createElement` anyway....
### How often does this bug happen?
Every time
### What version of React are you using?
Playground
### What version of React Compiler are you using?
Playground | Type: Bug,Component: Optimizing Compiler | low | Critical |
2,615,030,502 | PowerToys | Peek view plantuml | ### Description of the new feature / enhancement
Add plantuml preview in peek.
### Scenario when this would be used?
When I want to view a diagram without opening an entire IDE or uploading the file on a web app.
### Supporting information
_No response_ | Needs-Triage | low | Minor |
2,615,030,858 | flutter | `flutter test test/integration.shard` fails locally | This is in a clean build locally with no changes.
```sh
flutter_tools % flutter-dev test test/integration.shard
```
The actual failures are not always the same, and sometimes pass when ran locally one at a time.
| tool,P2,c: tech-debt,team-tool,triaged-tool | low | Critical |
2,615,044,726 | deno | HTTP server does not validate `Host` header is present | Version: Deno 2.0.0
I made a quick and simple standards test and found that Deno does not properly check for Content-Length vs. Transfer-Encoding. It must close the connection with error if both headers are present.
Also, the Host header is not checked.
| bug | low | Critical |
2,615,047,742 | flutter | Chromium Mac Bots become unresponsive and Xcode commands hang | From https://chromium-swarm.appspot.com/bot?id=build806-m9
<img width="1436" alt="Screenshot 2024-10-25 at 13 25 01" src="https://github.com/user-attachments/assets/1278a76d-2d1b-4c01-92f1-bcae102e62b3">
XCode installs are failing due to data corruption as in:
https://logs.chromium.org/logs/flutter/buildbucket/cr-buildbucket/8733087603218910657/+/u/install_xcode/install_xcode_from_cipd/stdout
There are other failure modes as well. I suspect a bad disk or bad memory. The automatic reboots on task failure don't seem to be helping.
I put up this CL to remove it from the prod pool, but I'm wondering if this is the right thing to do? https://chrome-internal-review.googlesource.com/c/infradata/config/+/7775927
cc @christopherfujino I'm wondering if bad machines like this are the underlying cause of https://github.com/flutter/flutter/issues/156614 ? | team-infra,P0,triaged-infra | high | Critical |
2,615,114,697 | flutter | iOS requestScopes in google_sign_in package returns false even with granted permissions for Google Calendar API | ### Steps to reproduce
1. **Set up Firebase Authentication and Google Calendar API**:
- Firebase Authentication and Google Sign-In are configured in the Firebase Console.
- Google Calendar API is enabled in Google Cloud Console.
2. **Create OAuth Credentials**:
- OAuth 2.0 credentials were generated for both Android and iOS within the Google Cloud Console.
- For iOS, the `REVERSED_CLIENT_ID` is correctly set up in the app’s `Info.plist`.
3. **Sign In and Request Scopes**:
- After signing in with Google, calling `requestScopes` for calendar access prompts a permissions request. Even after granting permission, the method still returns `false`.
### Expected results
- `requestScopes` should return `true` upon successful granting of permissions, as it does on Android.
### Actual results
- `requestScopes` always returns `false` on iOS, despite receiving an email from Google indicating that access was granted.
### Code sample
<details open><summary>Code sample</summary>
```dart
static const _scopes = [ CalendarApi.calendarReadonlyScope, CalendarApi.calendarEventsReadonlyScope,];
final isAuthorized = await _googleSignIn.requestScopes(_scopes);
print(isAuthorized); // Returns false even after granting permission
```
</details>
### Screenshots or Video
_No response_
### Logs
_No response_
### Flutter Doctor output
<details open><summary>Doctor output</summary>
```console
[✓] Flutter (Channel stable, 3.24.3, on macOS 15.0.1 24A348 darwin-arm64, locale en-TR)
• Flutter version 3.24.3 on channel stable at /Users/yasinsenocak/src/flutter
• Upstream repository https://github.com/flutter/flutter.git
• Framework revision 2663184aa7 (6 weeks ago), 2024-09-11 16:27:48 -0500
• Engine revision 36335019a8
• Dart version 3.5.3
• DevTools version 2.37.3
[✓] Android toolchain - develop for Android devices (Android SDK version 34.0.0)
• Android SDK at /Users/yasinsenocak/Library/Android/sdk
• Platform android-34, build-tools 34.0.0
• Java binary at: /Applications/Android Studio.app/Contents/jbr/Contents/Home/bin/java
• Java version OpenJDK Runtime Environment (build 17.0.9+0-17.0.9b1087.7-11185874)
• All Android licenses accepted.
[✓] Xcode - develop for iOS and macOS (Xcode 16.0)
• Xcode at /Applications/Xcode.app/Contents/Developer
• Build 16A242d
• CocoaPods version 1.15.2
[✗] Chrome - develop for the web (Cannot find Chrome executable at /Applications/Google Chrome.app/Contents/MacOS/Google Chrome)
! Cannot find Chrome. Try setting CHROME_EXECUTABLE to a Chrome executable.
[✓] Android Studio (version 2023.2)
• Android Studio at /Applications/Android Studio.app/Contents
• Flutter plugin can be installed from:
🔨 https://plugins.jetbrains.com/plugin/9212-flutter
• Dart plugin can be installed from:
🔨 https://plugins.jetbrains.com/plugin/6351-dart
• Java version OpenJDK Runtime Environment (build 17.0.9+0-17.0.9b1087.7-11185874)
[✓] VS Code (version 1.94.2)
• VS Code at /Applications/Visual Studio Code.app/Contents
• Flutter extension version 3.98.0
[✓] Connected device (5 available)
• sdk gphone64 arm64 (mobile) • emulator-5554 • android-arm64 • Android 15 (API 35) (emulator)
• Muhammed Yasin’s iPhone (mobile) • 00008030-000C489E3ED3402E • ios • iOS 18.0.1 22A3370
• iPhone 15 Pro (mobile) • 70CA95D0-3768-4BA0-ABC0-0E081F9D4220 • ios •
com.apple.CoreSimulator.SimRuntime.iOS-18-0 (simulator)
• macOS (desktop) • macos • darwin-arm64 • macOS 15.0.1 24A348 darwin-arm64
• Mac Designed for iPad (desktop) • mac-designed-for-ipad • darwin • macOS 15.0.1 24A348 darwin-arm64
[✓] Network resources
• All expected network resources are available.```
</details>
| platform-ios,p: google_sign_in,package,has reproducible steps,P2,team-ios,triaged-ios,found in release: 3.24,found in release: 3.27 | low | Major |
2,615,144,035 | flutter | Windows tool integration tests are flaky: "Java heap space" | One [example failure](https://ci.chromium.org/ui/p/flutter/builders/try/Windows%20tool_integration_tests_7_9/683/overview):
```txt
20:00 +25 -1: test/integration.shard/isolated/native_assets_test.dart: flutter build apk succeeds without libraries [E]
Exception: flutter build failed: 1
FAILURE: Build failed with an exception.
* What went wrong:
Execution failed for task ':app:compressDebugAssets'.
> A failure occurred while executing com.android.build.gradle.internal.tasks.CompressAssetsWorkAction
> Java heap space
* Try:
> Run with --stacktrace option to get the stack trace.
> Run with --info or --debug option to get more log output.
> Run with --scan to get full insights.
> Get more help at https://help.gradle.org/.
BUILD FAILED in 42s
Gradle task assembleDebug failed with exit code 1
Running Gradle task 'assembleDebug'...
Running Gradle task 'assembleDebug'... 43.9s
test\integration.shard\isolated\native_assets_test.dart 240:11 main.<fn>.<fn>
===== asynchronous gap ===========================
test\integration.shard\isolated\native_assets_test.dart 803:5 inTempDir
===== asynchronous gap ===========================
test\integration.shard\isolated\native_assets_test.dart 226:7 main.<fn>
```
Looking at the try-bots, these [don't seem particularly healthy](https://ci.chromium.org/ui/p/flutter/builders/try/Windows%20tool_integration_tests_7_9):
 | platform-windows,P1,c: flake,team-tool,triaged-tool | medium | Critical |
2,615,145,604 | neovim | snippets: wrong indentation when snippet contains `^` | ### Problem
```lua
vim.snippet.expand([[
a^ b$1
c$1
d$1
e]])
```
```
a^ b
^ c
^ ^ d
^ ^ ^ e
```
Whitespace after `^` (circumflex) is detected as indent and added multiple times. Relates to #29658.
###### [My comment](https://github.com/neovim/neovim/pull/29670#issuecomment-2416708675) with a possible explanation.
### Steps to reproduce
Execute the above Lua code.
### Expected behavior
```
a^ b
c
d
e
```
### Nvim version (nvim -v)
v0.10.2
### Vim (not Nvim) behaves the same?
n/a
### Operating system/version
Arch
### Terminal name/version
Alacritty
### $TERM environment variable
alacritty
### Installation
system package manager | bug,snippet | low | Minor |
2,615,149,645 | go | cmd/go: TestScript/mod_sumdb_golang failures | ```
#!watchflakes
default <- pkg == "cmd/go" && test == "TestScript/mod_sumdb_golang"
```
Issue created automatically to collect these failures.
Example ([log](https://ci.chromium.org/b/8733079747827100817)):
=== RUN TestScript/mod_sumdb_golang
=== PAUSE TestScript/mod_sumdb_golang
=== CONT TestScript/mod_sumdb_golang
script_test.go:139: 2024-10-25T19:24:26Z
script_test.go:141: $WORK=/home/swarming/.swarming/w/ir/x/t/cmd-go-test-2752046205/tmpdir2403144775/mod_sumdb_golang3843621272
script_test.go:163:
PATH=/home/swarming/.swarming/w/ir/x/t/cmd-go-test-2752046205/tmpdir2403144775/testbin:/home/swarming/.swarming/w/ir/x/w/goroot/bin:/home/swarming/.swarming/w/ir/x/w/goroot/bin:/home/swarming/.swarming/w/ir/x/w/goroot/bin:/home/swarming/.swarming/w/ir/cache/tools/bin:/home/swarming/.swarming/w/ir/bbagent_utility_packages:/home/swarming/.swarming/w/ir/bbagent_utility_packages/bin:/home/swarming/.swarming/w/ir/cipd_bin_packages:/home/swarming/.swarming/w/ir/cipd_bin_packages/bin:/home/swarming/.swarming/w/ir/cipd_bin_packages/cpython3:/home/swarming/.swarming/w/ir/cipd_bin_packages/cpython3/bin:/home/swarming/.swarming/w/ir/cache/cipd_client:/home/swarming/.swarming/w/ir/cache/cipd_client/bin:/home/swarming/.swarming/cipd_cache/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin
HOME=/no-home
CCACHE_DISABLE=1
GOARCH=amd64
...
cd /home/swarming/.swarming/w/ir/x/t/cmd-go-test-2752046205/tmpdir2403144775/mod_sumdb_golang3843621272/gopath/pkg/mod/cache/vcs/35640be4a3d2ccf2debb48dd7a3972a84907e5170b0209b4f963f3c8d00f8cd6; git -c log.showsignature=false log --no-decorate -n1 '--format=format:%H %ct %D' refs/tags/v1.99.99 --
0.061s # cd /home/swarming/.swarming/w/ir/x/t/cmd-go-test-2752046205/tmpdir2403144775/mod_sumdb_golang3843621272/gopath/pkg/mod/cache/vcs/35640be4a3d2ccf2debb48dd7a3972a84907e5170b0209b4f963f3c8d00f8cd6; git -c log.showsignature=false log --no-decorate -n1 '--format=format:%H %ct %D' refs/tags/v1.99.99 --
cd /home/swarming/.swarming/w/ir/x/t/cmd-go-test-2752046205/tmpdir2403144775/mod_sumdb_golang3843621272/gopath/pkg/mod/cache/vcs/35640be4a3d2ccf2debb48dd7a3972a84907e5170b0209b4f963f3c8d00f8cd6; git cat-file blob 732a3c400797d8835f2af34a9561f155bef85435:go.mod
0.039s # cd /home/swarming/.swarming/w/ir/x/t/cmd-go-test-2752046205/tmpdir2403144775/mod_sumdb_golang3843621272/gopath/pkg/mod/cache/vcs/35640be4a3d2ccf2debb48dd7a3972a84907e5170b0209b4f963f3c8d00f8cd6; git cat-file blob 732a3c400797d8835f2af34a9561f155bef85435:go.mod
cd /home/swarming/.swarming/w/ir/x/t/cmd-go-test-2752046205/tmpdir2403144775/mod_sumdb_golang3843621272/gopath/pkg/mod/cache/vcs/35640be4a3d2ccf2debb48dd7a3972a84907e5170b0209b4f963f3c8d00f8cd6; git cat-file blob 0cc034b51e57ed7832d4c67d526f75a900996e5c:go.mod
0.028s # cd /home/swarming/.swarming/w/ir/x/t/cmd-go-test-2752046205/tmpdir2403144775/mod_sumdb_golang3843621272/gopath/pkg/mod/cache/vcs/35640be4a3d2ccf2debb48dd7a3972a84907e5170b0209b4f963f3c8d00f8cd6; git cat-file blob 0cc034b51e57ed7832d4c67d526f75a900996e5c:go.mod
go: unrecognized import path "golang.org/x/text": reading https://golang.org/x/text?go-get=1: 500 Internal Server Error
go: golang.org/x/text@v0.0.0-20170915032832-14c0d48ead0c: unrecognized import path "golang.org/x/text": reading https://golang.org/x/text?go-get=1: 500 Internal Server Error
script_test.go:163: FAIL: testdata/script/mod_sumdb_golang.txt:71: go list -mod=mod -x -m all: exit status 1
--- FAIL: TestScript/mod_sumdb_golang (33.16s)
— [watchflakes](https://go.dev/wiki/Watchflakes)
| NeedsInvestigation | low | Critical |
2,615,156,420 | ui | [bug]: Select component doesn't work with useFormStatus() pending | ### Describe the bug
I recently upgraded to NextJS 15 and I have noticed that react-dom's useFormStatus is no longer working when the `Select` component is included in the form.
I'm not sure if this is a shadcn/ui issue, a radix issue, or a react-dom issue.
Please see the repository where I have a trimmed down form that reproduces the problem.
I'm also not sure if this affects other shadcn/ui components.
### Affected component/components
Select
### How to reproduce
1. Clone https://github.com/samstr/shadcn-formstatus-demo
2. npm install
3. npm run dev
4. Go to http://localhost:3000
5. Click the submit button on the form with an Input (pending state works)
6. Click the submit button on the form with a Select (pending state does not work)
### Codesandbox/StackBlitz link
https://github.com/samstr/shadcn-formstatus-demo
https://github.com/user-attachments/assets/03baa682-b540-43d5-967b-9d237fa08e3b
### Logs
_No response_
### System Info
```bash
Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/130.0.0.0 Safari/537.36
See package.json
```
### Before submitting
- [X] I've made research efforts and searched the documentation
- [X] I've searched for existing issues | bug | low | Critical |
2,615,166,589 | pytorch | Libtorch torch::Tensor default constructor does not initialize on CPU like in python | ### 🐛 Describe the bug
Working in python:
```py
import torch
t = torch.Tensor()
x = torch.cat([t, t, t], 1)
x
```
output:
```
tensor([])
```
not working in c++
```cpp
#include <torch/torch.h>
int main()
{
torch::Tensor t{};
auto x = torch::cat({ t, t, t }, 1);
std::cout << x << std::endl;
return 0;
}
```
Throws a c10::Error
```
tensor does not have a device
```
### Versions
PyTorch version: 2.4.1+cu124
Is debug build: False
CUDA used to build PyTorch: 12.4
ROCM used to build PyTorch: N/A
OS: Microsoft Windows 11 Pro (10.0.22631 64-bit)
GCC version: Could not collect
Clang version: Could not collect
CMake version: version 3.25.1
Libc version: N/A
Python version: 3.10.5 (tags/v3.10.5:f377153, Jun 6 2022, 16:14:13) [MSC v.1929 64 bit (AMD64)] (64-bit runtime)
Python platform: Windows-10-10.0.22631-SP0
Is CUDA available: True
CUDA runtime version: 12.6.77
CUDA_MODULE_LOADING set to: LAZY
GPU models and configuration: GPU 0: NVIDIA GeForce RTX 4090
Nvidia driver version: 565.90
cuDNN version: C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.6\bin\cudnn_ops64_9.dll
HIP runtime version: N/A
MIOpen runtime version: N/A
Is XNNPACK available: True
CPU:
Name: 13th Gen Intel(R) Core(TM) i9-13900K
Manufacturer: GenuineIntel
Family: 207
Architecture: 9
ProcessorType: 3
DeviceID: CPU0
CurrentClockSpeed: 3000
MaxClockSpeed: 3000
L2CacheSize: 32768
L2CacheSpeed: None
Revision: None
Versions of relevant libraries:
[pip3] numpy==1.24.1
[pip3] torch==2.4.1+cu124
[pip3] torchaudio==2.4.1+cu124
[pip3] torchvision==0.19.1+cu124
[conda] Could not collect
For C++:
libtorch-win-shared-with-deps-debug-2.4.1+cu124
Microsoft (R) C/C++ Optimizing Compiler Version 19.32.31332 for x64
CUDA 12.6.77 C++ Compiler
cc @jbschlosser | module: cpp,triaged | low | Critical |
2,615,175,329 | godot | TileMap editor background visibility issues RELOADED | ### Tested versions
- Reproducible in 4.4.dev3
### System information
Linux
### Issue description
Reopen of this issue -> https://github.com/godotengine/godot/issues/84192 that was closed due to the author "ban".
You can't see shit if tilemap has, for example, transparent background.
### Steps to reproduce
None
### Minimal reproduction project (MRP)
None | enhancement,topic:editor,usability,topic:2d | low | Minor |
2,615,198,708 | rust | SIGILL compiler crash when using AVR inline assembly | <!--
Thank you for finding an Internal Compiler Error! 🧊 If possible, try to provide
a minimal verifiable example. You can read "Rust Bug Minimization Patterns" for
how to create smaller examples.
http://blog.pnkfx.org/blog/2019/11/18/rust-bug-minimization-patterns/
-->
### Code
```Rust
#![no_std]
#![no_main]
#![feature(asm_experimental_arch)]
use core::{panic::PanicInfo, arch::asm};
#[panic_handler]
fn panic(_info: &PanicInfo) -> ! {
loop {}
}
#[no_mangle]
pub extern "C" fn main() {
let target: *mut u8 = 0x0025 as *mut u8;
let value: u8 = 0;
unsafe {
asm!(
"st {port}, {value}",
port = in(reg_ptr) target,
value = in(reg) value,
);
}
panic!()
}
```
### Meta
<!--
If you're using the stable version of the compiler, you should also check if the
bug also exists in the beta or nightly versions.
-->
`rustc --version --verbose`:
```
rustc 1.84.0-nightly (a93c1718c 2024-10-24)
binary: rustc
commit-hash: a93c1718c80b9f100056c8eec3fc37fbd6424134
commit-date: 2024-10-24
host: x86_64-unknown-linux-gnu
release: 1.84.0-nightly
LLVM version: 19.1.1
```
### Error output
```
error: could not compile `avr-project` (bin "avr-project")
Caused by:
process didn't exit successfully: `/home/ondre/.rustup/toolchains/nightly-x86_64-unknown-linux-gnu/bin/rustc --crate-name avr_project --edition=2021 src/main.rs --error-format=json --json=diagnostic-rendered-ansi,artifacts,future-incompat --diagnostic-width=186 --crate-type bin --emit=dep-info,link -C opt-level=3 -C panic=abort -C lto -C codegen-units=1 --check-cfg 'cfg(docsrs)' --check-cfg 'cfg(feature, values())' -C metadata=3c8db77931085eba -C extra-filename=-3c8db77931085eba --out-dir /home/ondre/avrlibstest/target/avr-atmega328p/release/deps --target /home/ondre/avrlibstest/avr-atmega328p.json -C strip=debuginfo -L dependency=/home/ondre/avrlibstest/target/avr-atmega328p/release/deps -L dependency=/home/ondre/avrlibstest/target/release/deps --extern 'noprelude:compiler_builtins=/home/ondre/avrlibstest/target/avr-atmega328p/release/deps/libcompiler_builtins-013c779640681efb.rlib' --extern 'noprelude:core=/home/ondre/avrlibstest/target/avr-atmega328p/release/deps/libcore-1167638d3e17fa03.rlib' -Z unstable-options` (signal: 4, SIGILL: illegal instruction)
```
### Project config
In file `rust-toolchain.toml`:
```toml
[toolchain]
channel = "nightly"
```
In file `.cargo/config.toml`:
```toml
[build]
target = "avr-atmega328p.json"
[unstable]
build-std = ["core"]
```
In file `avr-atmega328p.json`:
```json
{
"arch": "avr",
"atomic-cas": false,
"cpu": "atmega328p",
"crt-objects-fallback": "false",
"data-layout": "e-P1-p:16:8-i8:8-i16:8-i32:8-i64:8-f32:8-f64:8-n8-a:8",
"eh-frame-header": false,
"env": "gnu",
"exe-suffix": ".elf",
"late-link-args": {
"gnu-cc": [
"-lgcc"
],
"gnu-lld-cc": [
"-lgcc"
]
},
"linker": "avr-gcc",
"linker-flavor": "gnu-cc",
"llvm-target": "avr-unknown-unknown",
"max-atomic-width": 16,
"metadata": {
"description": null,
"host_tools": null,
"std": null,
"tier": null
},
"pre-link-args": {
"gnu-cc": [
"-mmcu=atmega328p"
],
"gnu-lld-cc": [
"-mmcu=atmega328p"
]
},
"relocation-model": "static",
"target-c-int-width": "16",
"target-pointer-width": "16"
}
``` | I-crash,A-LLVM,T-compiler,C-bug,O-AVR | low | Critical |
2,615,237,390 | react | Bug: Checkbox change event is incorrect when parent state is updated using `flushSync` | <!--
Please provide a clear and concise description of what the bug is. Include
screenshots if needed. Please test using the latest version of the relevant
React packages to make sure your issue has not already been fixed.
-->
React version: `18.3.1`
## Steps To Reproduce
It is a very specific case best described by a code sample. I have checkbox inside a div. When the checkbox is clicked, it should select the checkbox and the div. Notice the `checkbox` does not get selected. If I remove `flushSync` then it works as expected
```
export default function App() {
const [isDivSelected, setIsDivSelected] = useState(false);
const [isCheckboxSelected, setIsCheckboxSelected] = useState(false);
return (
<>
<div
className="container"
style={{
borderColor: isDivSelected ? "blue" : "red",
}}
onClick={() => {
flushSync(() => {
setIsDivSelected(true);
});
}}
>
<input
type="checkbox"
checked={isCheckboxSelected}
onChange={(e) => {
setIsCheckboxSelected(e.target.checked);
}}
/>
Click to checkbox to select cell
</div>
<button
type="button"
onClick={() => {
setIsDivSelected(false);
setIsCheckboxSelected(false);
}}
>
Reset
</button>
</>
);
}
```
<!--
Your bug will get fixed much faster if we can run your code and it doesn't
have dependencies other than React. Issues without reproduction steps or
code examples may be immediately closed as not actionable.
-->
Link to code example:
https://codesandbox.io/p/sandbox/flamboyant-ace-ngqjfg?workspaceId=bc172196-5c2d-4f29-a12b-3906e64cfab1
<!--
Please provide a CodeSandbox (https://codesandbox.io/s/new), a link to a
repository on GitHub, or provide a minimal code example that reproduces the
problem. You may provide a screenshot of the application if you think it is
relevant to your bug report. Here are some tips for providing a minimal
example: https://stackoverflow.com/help/mcve.
-->
## The current behavior
`event.target.checked` is `false`
## The expected behavior
`event.target.checked` should be `true`
| Status: Unconfirmed | medium | Critical |
2,615,240,070 | pytorch | [Feature request] Flag to prevent certain parameters from being typecast by nn.module.to() | ### 🚀 The feature, motivation and pitch
I work with a lot of models that are mostly bf16 but have a couple parameters that I need to have stay in fp32. The most common ones are loss scaling parameters used for fp32 loss calculations that require grad updates.
A flag similar to ```requires_grad``` but for preventing casting would be very handy.
I.e. something similar to:
```
self.p = nn.Parameter(t)
self.p.dynamic_dtype = False
```
### Alternatives
There are workarounds (i.e. saving and restoring the parameter) but they tend to be quite error prone, especially when working with training libraires that cast the nn.module. You always have to be on the lookout whenever you're loading or training that a cast doesn't slip by.
### Additional context
_No response_
cc @albanD @mruberry @jbschlosser @walterddr @mikaylagawarecki | module: nn,triaged,needs design | low | Critical |
2,615,297,769 | flutter | make currentSystemFrameTimeStamp more reliable/expose _lastRawTimeStamp | ### Use case
I sometimes I need to access the current frame time during an event handler (ie, `SchedulerBinding.instance.currentFrameTimeStamp`), to record when an animation started.
### Proposal
`currentFrameTimeStamp` doesn't allow this, as it asserts when accessed outside of the render(?) phase. `currentSystemFrameTimeStamp` looks like it will work, but the documentation says "On most platforms, this is a more or less arbitrary value, and should generally be ignored." Is that correct? It doesn't seem like this should be the case, as [the code](https://github.com/flutter/flutter/blob/9b84dbed06a173617a70d9c760775984296d90fb/packages/flutter/lib/src/scheduler/binding.dart#L1130) just returns `_lastRawTimeStamp`, which seems close enough to the behavior I want.
But I guess the ideal thing would be if we had a timestamp with time dilation(?) outside of the render phase as well? | framework,c: proposal,P3,team-framework,triaged-framework | low | Minor |
2,615,320,296 | flutter | Road edges are pixelated in flutter google maps using a styled map | ### Steps to reproduce
1. Create a styled map in google cloud which has non-zero stroke with for the roads
2. Load GoogleMap widget in flutter with the corresponding cloudMapId
### Expected results
map should not be pizelated anywhere
### Actual results
Pixelated road edges
### Code sample
<details open><summary>Code sample</summary>
```dart
return GoogleMap(
cloudMapId: getCloudMapId(),
buildingsEnabled: false,
tiltGesturesEnabled: false,
rotateGesturesEnabled: false,
mapToolbarEnabled: false,
zoomControlsEnabled: false,
myLocationEnabled: true,
markers: markers,
onMapCreated: onMapCreated,
initialCameraPosition: CameraPosition(
target: LatLng(currentLocation.latitude, currentLocation.longitude),
zoom: 15,
),
myLocationButtonEnabled: true,
onTap: (LatLng latLng) =>
ref.read(selectedVenueProvider.notifier).state = null,
);
```
</details>
### Screenshots or Video
<details open>
<summary>Screenshots / Video demonstration</summary>
</details>
### Logs
<details open><summary>Logs</summary>
```console
[Paste your logs here]
```
</details>
### Flutter Doctor output
<details open><summary>Doctor output</summary>
```console
[✓] Flutter (Channel stable, 3.24.1, on Ubuntu 22.04.5 LTS 6.8.0-47-generic, locale en_US.UTF-8)
• Flutter version 3.24.1 on channel stable at /home/john/dev/flutter
• Upstream repository https://github.com/flutter/flutter.git
• Framework revision 5874a72aa4 (9 weeks ago), 2024-08-20 16:46:00 -0500
• Engine revision c9b9d5780d
• Dart version 3.5.1
• DevTools version 2.37.2
[✓] Android toolchain - develop for Android devices (Android SDK version 34.0.0)
• Android SDK at /home/john/Android/Sdk
• Platform android-34, build-tools 34.0.0
• Java binary at: /opt/android-studio/jbr/bin/java
• Java version OpenJDK Runtime Environment (build 17.0.10+0-17.0.10b1087.21-11609105)
• All Android licenses accepted.
[✓] Chrome - develop for the web
• Chrome at google-chrome
[✓] Linux toolchain - develop for Linux desktop
• Ubuntu clang version 14.0.0-1ubuntu1.1
• cmake version 3.22.1
• ninja version 1.10.1
• pkg-config version 0.29.2
[✓] Android Studio (version 2024.1)
• Android Studio at /opt/android-studio
• Flutter plugin can be installed from:
🔨 https://plugins.jetbrains.com/plugin/9212-flutter
• Dart plugin can be installed from:
🔨 https://plugins.jetbrains.com/plugin/6351-dart
• Java version OpenJDK Runtime Environment (build 17.0.10+0-17.0.10b1087.21-11609105)
[✓] VS Code (version 1.94.2)
• VS Code at /usr/share/code
• Flutter extension version 3.98.0
[✓] Connected device (3 available)
• Pixel 7a (mobile) • 192.168.1.142:46381 • android-arm64 • Android 14 (API 34)
• Linux (desktop) • linux • linux-x64 • Ubuntu 22.04.5 LTS 6.8.0-47-generic
• Chrome (web) • chrome • web-javascript • Google Chrome 130.0.6723.69
[✓] Network resources
• All expected network resources are available.
• No issues found!
```
</details>
| platform-android,p: maps,package,has reproducible steps,P3,team-android,triaged-android,found in release: 3.24,found in release: 3.27 | low | Major |
2,615,327,317 | pytorch | `DataLoader` probably shouldn't use `fork` by default | ### 🐛 Describe the bug
Currently, `torch.utils.data.DataLoader` uses the default system `multiprocessing_context`, which is `fork` on linux. This is problematic, because `pytorch` itself uses multithreading internally. Starting with Python 3.12, python will emit a `DeprecationWarning` when it detects that `os.fork` was called from a process that might use multiple threads.
For example:
```python
import warnings
import torch
# Don't hide DeprecationWarnings
warnings.filterwarnings("default")
# Perform a computation that uses threads
torch.zeros(2 ** 15 + 1) * 42
# Use a dataloader with multiple workers
for _ in torch.utils.data.DataLoader([0], num_workers=2):
pass
```
will now print
```
/usr/lib/python3.12/multiprocessing/popen_fork.py:66: DeprecationWarning: This process (pid=307138)
is multi-threaded, use of fork() may lead to deadlocks in the child.
self.pid = os.fork()
```
See [the official `os.fork` documentation](https://docs.python.org/3/library/os.html#os.fork), [this discussion](https://discuss.python.org/t/concerns-regarding-deprecation-of-fork-with-alive-threads/33555), python/cpython#100228 and python/cpython#100229.
### Versions
<details>
```
Collecting environment information...
PyTorch version: 2.5.0+cu124
Is debug build: False
CUDA used to build PyTorch: 12.4
ROCM used to build PyTorch: N/A
OS: Debian GNU/Linux 12 (bookworm) (x86_64)
GCC version: (Debian 12.2.0-14) 12.2.0
Clang version: Could not collect
CMake version: Could not collect
Libc version: glibc-2.36
Python version: 3.12.7 (main, Oct 19 2024, 04:14:06) [GCC 12.2.0] (64-bit runtime)
Python platform: Linux-6.6.53-x86_64-with-glibc2.36
Is CUDA available: False
CUDA runtime version: No CUDA
CUDA_MODULE_LOADING set to: N/A
GPU models and configuration: No CUDA
Nvidia driver version: No CUDA
cuDNN version: No CUDA
HIP runtime version: N/A
MIOpen runtime version: N/A
Is XNNPACK available: True
CPU:
Architecture: x86_64
CPU op-mode(s): 32-bit, 64-bit
Address sizes: 39 bits physical, 48 bits virtual
Byte Order: Little Endian
CPU(s): 20
On-line CPU(s) list: 0-19
Vendor ID: GenuineIntel
Model name: 12th Gen Intel(R) Core(TM) i9-12900HK
CPU family: 6
Model: 154
Thread(s) per core: 2
Core(s) per socket: 14
Socket(s): 1
Stepping: 3
CPU(s) scaling MHz: 35%
CPU max MHz: 5000.0000
CPU min MHz: 400.0000
BogoMIPS: 5836.80
Flags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx pdpe1gb rdtscp lm constant_tsc art arch_perfmon pebs bts rep_good nopl xtopology nonstop_tsc cpuid aperfmperf tsc_known_freq pni pclmulqdq dtes64 monitor ds_cpl vmx smx est tm2 ssse3 sdbg fma cx16 xtpr pdcm sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand lahf_lm abm 3dnowprefetch cpuid_fault epb ssbd ibrs ibpb stibp ibrs_enhanced tpr_shadow flexpriority ept vpid ept_ad fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid rdseed adx smap clflushopt clwb intel_pt sha_ni xsaveopt xsavec xgetbv1 xsaves split_lock_detect user_shstk avx_vnni dtherm ida arat pln pts hwp hwp_notify hwp_act_window hwp_epp hwp_pkg_req hfi vnmi umip pku ospke waitpkg gfni vaes vpclmulqdq rdpid movdiri movdir64b fsrm md_clear serialize arch_lbr ibt flush_l1d arch_capabilities
Virtualization: VT-x
L1d cache: 544 KiB (14 instances)
L1i cache: 704 KiB (14 instances)
L2 cache: 11.5 MiB (8 instances)
L3 cache: 24 MiB (1 instance)
NUMA node(s): 1
NUMA node0 CPU(s): 0-19
Vulnerability Gather data sampling: Not affected
Vulnerability Itlb multihit: Not affected
Vulnerability L1tf: Not affected
Vulnerability Mds: Not affected
Vulnerability Meltdown: Not affected
Vulnerability Mmio stale data: Not affected
Vulnerability Reg file data sampling: Mitigation; Clear Register File
Vulnerability Retbleed: Not affected
Vulnerability Spec rstack overflow: Not affected
Vulnerability Spec store bypass: Mitigation; Speculative Store Bypass disabled via prctl
Vulnerability Spectre v1: Mitigation; usercopy/swapgs barriers and __user pointer sanitization
Vulnerability Spectre v2: Mitigation; Enhanced / Automatic IBRS; IBPB conditional; RSB filling; PBRSB-eIBRS SW sequence; BHI BHI_DIS_S
Vulnerability Srbds: Not affected
Vulnerability Tsx async abort: Not affected
Versions of relevant libraries:
[pip3] numpy==2.1.2
[pip3] nvidia-cublas-cu12==12.4.5.8
[pip3] nvidia-cuda-cupti-cu12==12.4.127
[pip3] nvidia-cuda-nvrtc-cu12==12.4.127
[pip3] nvidia-cuda-runtime-cu12==12.4.127
[pip3] nvidia-cudnn-cu12==9.1.0.70
[pip3] nvidia-cufft-cu12==11.2.1.3
[pip3] nvidia-curand-cu12==10.3.5.147
[pip3] nvidia-cusolver-cu12==11.6.1.9
[pip3] nvidia-cusparse-cu12==12.3.1.170
[pip3] nvidia-nccl-cu12==2.21.5
[pip3] nvidia-nvjitlink-cu12==12.4.127
[pip3] nvidia-nvtx-cu12==12.4.127
[pip3] torch==2.5.0
[pip3] triton==3.1.0
[conda] Could not collect
```
</details>
cc @andrewkho @divyanshk @SsnL @VitalyFedyunin @dzhulgakov | module: dataloader,triaged,module: data | low | Critical |
2,615,330,885 | react | [Compiler Bug]: `===` is not a sufficient equality check | ### What kind of issue is this?
- [X] React Compiler core (the JS output is incorrect, or your app works incorrectly after optimization)
- [ ] babel-plugin-react-compiler (build issue installing or using the Babel plugin)
- [ ] eslint-plugin-react-compiler (build issue installing or using the eslint plugin)
- [ ] react-compiler-healthcheck (build issue installing or using the healthcheck script)
### Link to repro
https://playground.react.dev/#N4Igzg9grgTgxgUxALhASwLYAcIwC4AEwBUYCAyngIZ4IEC+BAZjBBgQDogwJVx5cA3BwB2ohAA8c+AgBMETKlAA2hJlBH80EEQQBaCVgAoAlEVEECcHWEIBtAF6GIAGgJk8B1gF0CAXhIyShoEIwAGE2FdKxtCWxh-AgB5ACMAKwR+ADo0MCMnVjcIggB+ThAwrgJkcoBaSpAoyx48WF0AHhSoPDwdAh0AYWU0OABrP2BTfwA+dwRPZyNagogTemngePp2gHounp1pqPpREHogA
### Repro steps
1. Click the rendered button repeatedly
**Expected result:**
On each click, the text should toggle between `0` and `-0`.
**Actual result:**
Initially, the text `0` is rendered. After the first click, `-0` is rendered. Subsequent clicks don't do anything.
### How often does this bug happen?
Every time
### What version of React are you using?
18.3.1
### What version of React Compiler are you using?
19.0.0-beta-8a03594-20241020
---
React Compiler currently uses the `===` operator to check whether to memoize. The `===` operator isn't sufficient to check whether two values are identical. The two edge cases missed by `===` but handled handled by `Object.is()`:
- `0`/`-0`: React Compiler being unable to detect a difference between these values causes this bug.
- `NaN`: React Compiler incorrectly _always_ detects a difference despite one not existing, causes code to not be memoized, but is otherwise correct.
I imagine that changing `===` to `Object.is()` in the output might be bad for performance. In case this bug is a _wontfix_, you should document this limitation somewhere.
| Component: Optimizing Compiler | low | Critical |
2,615,333,370 | flutter | Annotation or enums for preferred constant values | ### Use case
As part of work around the Flutter Property Editor (https://github.com/flutter/devtools/issues/1948), we would like to be able to support Flutter properties like [strokeAlign](https://api.flutter.dev/flutter/painting/BorderSide/strokeAlign.html). Although it's a double, there are three constants defined by Flutter that are preferred (strokeAlignInside, strokeAlignCenter, and strokeAlignOutside). Ideally we would like to find a way to support this in the Property Editor without having to hardcode rules for these special cases.
There are likely other cases similar to `strokeAlign` that should be modified to best support the Flutter Property Editor.
### Proposal
A couple options to solve this:
1. By creating an annotation (e.g., `@knownValues`)
```
BorderSide({
Color color = const Color(0xFF000000),
double width = 1.0,
BorderStyle style = BorderStyle.solid,
@knownValues([BorderSide.strokeAlignInside, BorderSide.strokeAlignCenter, BorderSide.strokeAlignOutside])
double strokeAlign = strokeAlignInside})
```
2. Switch to an enum
Another option would be to use an enhanced enum with `double` members. However, in the case of `strokeAlign`, because other values besides -1.0. 0.0. and 1.0 can be used, this is likely not the best solution. | framework,c: proposal,P3,team-framework,triaged-framework | low | Major |
2,615,333,425 | rust | Tracking issue for RFC 3681: Default field values | <!--
NOTE: For library features, please use the "Library Tracking Issue" template instead.
Thank you for creating a tracking issue! 📜 Tracking issues are for tracking a
feature from implementation to stabilisation. Make sure to include the relevant
RFC for the feature if it has one. Otherwise provide a short summary of the
feature and link any relevant PRs or issues, and remove any sections that are
not relevant to the feature.
Remember to add team labels to the tracking issue.
For a language team feature, this would e.g., be `T-lang`.
Such a feature should also be labeled with e.g., `F-my_feature`.
This label is used to associate issues (e.g., bugs and design questions) to the feature.
-->
This is a tracking issue for the RFC "3681" (rust-lang/rfcs#3681).
The feature gate for the issue is `#![feature(default_field_values)]`.
Allow `struct` definitions to provide default values for individual fields and
thereby allowing those to be omitted from initializers. When deriving `Default`,
the provided values will then be used. For example:
```rust
#[derive(Default)]
struct Pet {
name: Option<String>, // impl Default for Pet will use Default::default() for name
age: i128 = 42, // impl Default for Pet will use the literal 42 for age
}
let valid = Pet { name: None, .. };
assert_eq!(valid.age, 42);
let default = Pet::default();
assert_eq!(default.age, 42);
let invalid = Pet { .. };
```
### About tracking issues
Tracking issues are used to record the overall progress of implementation.
They are also used as hubs connecting to other relevant issues, e.g., bugs or open design questions.
A tracking issue is however *not* meant for large scale discussion, questions, or bug reports about a feature.
Instead, open a dedicated issue for the specific matter and add the relevant feature gate label.
Discussion comments will get marked as off-topic or deleted.
Repeated discussions on the tracking issue may lead to the tracking issue getting locked.
### Steps
<!--
Include each step required to complete the feature. Typically this is a PR
implementing a feature, followed by a PR that stabilises the feature. However
for larger features an implementation could be broken up into multiple PRs.
-->
- [ ] Implement the RFC (cc @rust-lang/compiler)
- [x] Parse the new syntax
- [x] Support `#[derive(Default)]` expansion of structs with default field values
- [x] Support `#[derive(Default)]` expansion of struct variants where every field has a default
- [x] Restrict `#[non_exhaustive]` on items with default field values
- [x] Restrict defaults on tuple struct and tuple variants
- [x] Define visibility of defaulted field values on value construction (`S { .. }` is allowed if `a` in `struct S { a: () }` is not visible?)
- [x] Restrict `S { .. }` when `S` has no fields with default values
- [x] Lint against explicit `impl Default` when `#[derive(Default)]` would be ok
- [ ] Additional lints for iffy cases (maybe belongs in clippy?)
- [ ] Adjust documentation ([see instructions on rustc-dev-guide][doc-guide])
- [x] Add unstable book entry
- [ ] Add to the Reference
- [ ] Mention in The Book
- [ ] Add example to Rust By Example
- [ ] Formatting for new syntax has been added to the [Style Guide] ([nightly-style-procedure])
- [ ] Stabilization PR ([see instructions on rustc-dev-guide][stabilization-guide])
[stabilization-guide]: https://rustc-dev-guide.rust-lang.org/stabilization_guide.html#stabilization-pr
[doc-guide]: https://rustc-dev-guide.rust-lang.org/stabilization_guide.html#documentation-prs
[nightly-style-procedure]: https://github.com/rust-lang/style-team/blob/master/nightly-style-procedure.md
[Style Guide]: https://github.com/rust-lang/rust/tree/master/src/doc/style-guide
### Unresolved Questions
<!--
Include any open questions that need to be answered before the feature can be
stabilised.
-->
- ~What is the right interaction wrt. `#[non_exhaustive]`?~ Made mutually exclusive.
- ~Customization of behavior wrt. visibility rules (allow user to specify that value can be constructed with `..` covering defaulted field that otherwise is not accessible)~ Following RFC: struct can't be constructed with `..` if it covers a private field.
- ~Allowing `..` on types with no default fields, particularly in unit structs?*~ Disallowed, can be added later if we find a reason to support that.
- ~Allowing the use of `field_name: _` to specify the use of the default for that specific field?*~ Let's not try that, particularly in the face of `~const Default` allowing for `field_name: Default::default()` and `field_name: default()`
- ~Tuple structs and tuple variant support*~ Let file a subsequent RFC for this.
- Integration with (potential, at this time) structural records*
- Integration with (potential, at this time) literal type inference (`_ { .. }`)*
- ~Exposing default field values as individual consts in the syntax? (I lean towards "unneeded")~ If an API needs the default to be expressed, it can be an associated `const` and use `field_name: Self::CONST_DEFAULT`, making it accessible
- Expand support to non-const values? (Personal position is that we shouldn't do that, particularly seeing how powerful const eval is becoming.)
\* *Decision not needed for stabilization of this feature, can be follow up work.*
### Implementation history
<!--
Include a list of all the PRs that were involved in implementing the feature.
-->
- Initial implementation:
https://github.com/rust-lang/rust/pull/129514
- Minor test add:
https://github.com/rust-lang/rust/pull/134136
- Make sure to use normalized ty for unevaluated const in default struct value [ICE fix]:
https://github.com/rust-lang/rust/pull/134314
- Lints for `Default` impls that could diverge against default field values:
https://github.com/rust-lang/rust/pull/134441
- Only lint for "manual `impl Default` without using `..` for all default fields":
https://github.com/rust-lang/rust/pull/134737
- 1st Experiment:
https://github.com/rust-lang/rust/pull/134175
- Reuse logic from #134441 that looks at the `Default::default()` body in existing `derivable_impls` clippy lint:
https://github.com/rust-lang/rust-clippy/pull/13988
- Lint against `Bar { .. }.foo.x != Foo { .. }.x`:
https://github.com/rust-lang/rust/pull/135859
Closed, should likely live in clippy as allow-by-default. There's no analogue lint for the same case for `Default`, so either we should have both or neither.
- Restrict `#[non_exhaustive]`:
https://github.com/rust-lang/rust/pull/134539
- Add documentation entry to unstable book:
https://github.com/rust-lang/rust/pull/134855
- Constify `Default::default()` so that it can be used in default field values:
https://github.com/rust-lang/rust/pull/134628
- Propose rustfmt style:
https://github.com/rust-lang/style-team/issues/205
- Add test for privacy rules:
https://github.com/rust-lang/rust/pull/135700
- Disallow `A { .. }` if `A` has no fields:
https://github.com/rust-lang/rust/pull/135703
- Fix lifetime checking ICE:
https://github.com/rust-lang/rust/pull/135711
- Detect APIs with non-exhaustive struct constructors forcing `A { field, .. }` always:
- https://github.com/rust-lang/rust/pull/135794
- https://github.com/rust-lang/rust/pull/135846 | T-lang,T-compiler,B-unstable,C-tracking-issue,F-default_field_values | high | Critical |
2,615,336,672 | go | internal/coverage/cfile: TestCoverageApis/emitToFailingWriter failures | ```
#!watchflakes
default <- pkg == "internal/coverage/cfile" && test == "TestCoverageApis/emitToFailingWriter"
```
Issue created automatically to collect these failures.
Example ([log](https://ci.chromium.org/b/8733069857189338673)):
=== RUN TestCoverageApis/emitToFailingWriter
=== PAUSE TestCoverageApis/emitToFailingWriter
=== CONT TestCoverageApis/emitToFailingWriter
emitdata_test.go:166: running: /home/swarming/.swarming/w/ir/x/t/TestCoverageApis2055472943/001/build1/harness.exe -tp emitToFailingWriter -o /home/swarming/.swarming/w/ir/x/t/TestCoverageApis2055472943/001/emitToFailingWriter-edir-y with rdir=/home/swarming/.swarming/w/ir/x/t/TestCoverageApis2055472943/001/emitToFailingWriter-rdir-y and GOCOVERDIR=false
emitdata_test.go:166: running: /home/swarming/.swarming/w/ir/x/t/TestCoverageApis2055472943/001/build1/harness.exe -tp emitToFailingWriter -o /home/swarming/.swarming/w/ir/x/t/TestCoverageApis2055472943/001/emitToFailingWriter-edir-x with rdir=/home/swarming/.swarming/w/ir/x/t/TestCoverageApis2055472943/001/emitToFailingWriter-rdir-x and GOCOVERDIR=true
emitdata_test.go:343:
internal error in coverage meta-data tracking:
encountered bad pkgID: 0 at slot: 3484 fnID: 6 numCtrs: 1
list of hard-coded runtime package IDs needs revising.
[see the comment on the 'rtPkgs' var in
...
panic: runtime error: slice bounds out of range [:4294969857] with capacity 27250
goroutine 1 gp=0x40000021c0 m=2 mp=0x400005a808 [running]:
panic({0x2ad880?, 0x40000181f8?})
/home/swarming/.swarming/w/ir/x/w/goroot/src/runtime/panic.go:806 +0x578 fp=0x4000308930 sp=0x4000308880 pc=0x1a2c38
runtime.goPanicSliceAcap(0x100000a01, 0x6a72)
/home/swarming/.swarming/w/ir/x/w/goroot/src/runtime/panic.go:141 +0xc4 fp=0x4000308970 sp=0x4000308930 pc=0xc9e44
internal/coverage/cfile.(*emitState).VisitFuncs(0x400009e140, 0x400000c0f0)
/home/swarming/.swarming/w/ir/x/w/goroot/src/internal/coverage/cfile/emit.go:478 +0x1564 fp=0x4000308be0 sp=0x4000308970 pc=0x26e874
internal/coverage/encodecounter.(*CoverageDataWriter).writeCounters(0x4000010140, {0x2eb140, 0x400009e140}, 0x40000a0120)
...
runtime.gcBgMarkWorker(0x40000240e0)
/home/swarming/.swarming/w/ir/x/w/goroot/src/runtime/mgc.go:1363 +0x2b8 fp=0x4000051fb0 sp=0x4000051f10 pc=0x64198
runtime.gcBgMarkStartWorkers.gowrap1()
/home/swarming/.swarming/w/ir/x/w/goroot/src/runtime/mgc.go:1279 +0x28 fp=0x4000051fd0 sp=0x4000051fb0 pc=0x63ea8
runtime.goexit({})
/home/swarming/.swarming/w/ir/x/w/goroot/src/runtime/asm_arm64.s:1260 +0x4 fp=0x4000051fd0 sp=0x4000051fd0 pc=0x1b1924
created by runtime.gcBgMarkStartWorkers in goroutine 1
/home/swarming/.swarming/w/ir/x/w/goroot/src/runtime/mgc.go:1279 +0x3f4
emitdata_test.go:344: running 'harness -tp emitToFailingWriter': exit status 2
--- FAIL: TestCoverageApis/emitToFailingWriter (0.17s)
— [watchflakes](https://go.dev/wiki/Watchflakes)
| NeedsInvestigation | low | Critical |
2,615,342,540 | deno | "module is not defined" cjs suggestion should not occur for mjs/mts modules | ```
> cat main.mjs
import * as a from "./a.cjs";
console.log(a.add(1, 2));
module.isPreloading = true;
> deno run main.mjs
3
error: Uncaught (in promise) ReferenceError: module is not defined
module.isPreloading = true;
^
at file:///V:/scratch/main.mjs:5:1
info: Deno supports CommonJS modules in .cjs files, or when there's a package.json
with "type": "commonjs" option and --unstable-detect-cjs flag is used.
hint: Rewrite this module to ESM,
or change the file extension to .cjs,
or add package.json next to the file with "type": "commonjs" option
and pass --unstable-detect-cjs flag.
docs: https://docs.deno.com/go/commonjs
```
This suggestion doesn't make sense.
Node for example:
```
> node main.mjs
3
file:///V:/scratch/main.mjs:5
module.isPreloading = true;
^
ReferenceError: module is not defined in ES module scope
at file:///V:/scratch/main.mjs:5:1
at ModuleJob.run (node:internal/modules/esm/module_job:262:25)
at async ModuleLoader.import (node:internal/modules/esm/loader:474:24)
at async asyncRunEntryPointWithESMLoader (node:internal/modules/run_main:109:5)
Node.js v22.3.0
``` | bug,good first issue | low | Critical |
2,615,364,425 | rust | Misleading diagnostic output for typecheck failures that involve type inference | ### Code
https://play.rust-lang.org/?version=stable&mode=debug&edition=2021&gist=e5cc14f0aef315131a9e430f0ff34b06
Summarized:
- The input is a vector of schedule events: vec[x] contains the start time and end time for event x, and a target event number
- Whenever an event begins, the lowest-numbered resource must be allocated to that event
- The output is the ID number of the resource allocated to the target event
- My implementation used two `BinaryHeap`s, one to track allocated resources, and a freelist to track available resources
- The first heap's item type is `(Reverse(end_time), resource_id)`, so the heap is ordered by time-of-release ascending (so `pop()`/`peek()` refer to the next event that will end)
- The second heap's item type is `Reverse(resource_id)` so that `pop` yields the lowest-numbered resource
- A missing `Reverse()` when pushing onto the second heap caused the first heap's type to incorrectly inferred
- This causes a typecheck failure on a _correct_ insert into the first heap
- The diagnostic hint explaining the first heap's type inference points to a statement that could not have possibly contributed to type inference
### Current output
```rs
error[E0308]: mismatched types
--> main.rs:58:30
|
33 | departures.pop();
| ---------- here the type of `departures` is inferred to be `BinaryHeap<(Reverse<_>, Reverse<i32>)>`
...
58 | departures.push( dep_item );
| ---- ^^^^^^^^ expected `(Reverse<_>, Reverse<i32>)`, found `(Reverse<i32>, i32)`
| |
| arguments to this method are incorrect
|
= note: expected tuple `(Reverse<_>, Reverse<i32>)`
found tuple `(Reverse<i32>, i32)`
note: method defined here
--> C:\Users\Stevie-O\.rustup\toolchains\stable-x86_64-pc-windows-msvc\lib/rustlib/src/rust\library\alloc\src\collections\binary_heap\mod.rs:616:12
|
616 | pub fn push(&mut self, item: T) {
| ^^^^
```
### Desired output
```rs
error[E0308]: mismatched types
--> main.rs:58:30
|
29 | Some( &(Reverse(dt), seat_num) )
| ----------------------- here the type of `departures` is inferred to be `BinaryHeap<(Reverse<_>, Reverse<i32>)>`
```
### Rationale and extra context
I don't really know exactly what it _should_ say, but I'm quite certain that it shouldn't say that the type of `departures` was inferred from the `departures.pop()` call, a statement from which virtually zero type information can be inferred.
If I could get anything I wanted plus a pony, it would have wanted it to point me to line 29, which is where I'm pretty sure that the _actual_ type inference came from line 29:
```rs
Some( &(Reverse(dt), seat_num) )
```
And then point out that `seat_num` is a `Reverse<i32>` because of line 34:
```rs
free_seats.push(seat_num); // <- NOTE the missing Reverse() around seat_num
```
Getting all of that seems rather impractical; however, I expect that if it had told me that the second tuple element was inferred to be a `Reverse<>` from the match pattern, I would have spent a less time looking for the *real* bug, which was the erroneous statement above.
### Other cases
_No response_
### Rust Version
rustc 1.82.0 (f6e511eec 2024-10-15)
binary: rustc
commit-hash: f6e511eec7342f59a25f7c0534f1dbea00d01b14
commit-date: 2024-10-15
host: x86_64-pc-windows-msvc
release: 1.82.0
LLVM version: 19.1.1
### Anything else?
_No response_ | A-diagnostics,T-compiler,A-inference,D-confusing | low | Critical |
2,615,405,777 | pytorch | CompiledFxGraph.current_callable is not thread-safe | ### 🐛 Describe the bug
After a new thread compiled, CompiledFxGraph.current_callable is overwritten for all threads.
To repro, please first patch CompiledFxGraph.__call__ as:
```python
def __call__(self, inputs: Sequence[Any]) -> Any:
assert self.current_callable is not None
print(f"thread id: {threading.get_native_id()}, callable id: {id(self.current_callable)}") # new line for callable id
try:
return self.current_callable(inputs)
finally:
AutotuneCacheBundler.end_compile()
```
Then, run the following code:
```python
import torch
import threading
import time
def foo(x, y):
return x + y
foo = torch.compile(foo)
count = 0
def wrapper(x, y, odd):
global count
for _ in range(10):
z = foo(x, y)
# force 2 threads to alternate
if count % 2 == odd and count < 5:
time.sleep(1)
count += 1
threads = []
for _ in range(2):
threads.append(threading.Thread(target=wrapper, args=(torch.ones(1, device="cuda"), torch.ones(1, device="cuda"), _)))
for thread in threads:
thread.start()
for thread in threads:
thread.join()
```
Expected Output:
```
thread id: 124979, callable id: 139811104076800 # Note that this is changed to 139811058639792 later for thread id 124979
thread id: 124980, callable id: 139811058639792
thread id: 124980, callable id: 139811058639792
thread id: 124979, callable id: 139811058639792
thread id: 124980, callable id: 139811058639792
thread id: 124979, callable id: 139811058639792
thread id: 124980, callable id: 139811058639792
thread id: 124980, callable id: 139811058639792
thread id: 124980, callable id: 139811058639792
thread id: 124980, callable id: 139811058639792
thread id: 124980, callable id: 139811058639792
thread id: 124980, callable id: 139811058639792
thread id: 124980, callable id: 139811058639792
thread id: 124979, callable id: 139811058639792
thread id: 124979, callable id: 139811058639792
thread id: 124979, callable id: 139811058639792
thread id: 124979, callable id: 139811058639792
thread id: 124979, callable id: 139811058639792
thread id: 124979, callable id: 139811058639792
thread id: 124979, callable id: 139811058639792
```
This currently blocks #123177.
### Versions
PyTorch version: 2.6.0a0+git2c830c5
Is debug build: False
CUDA used to build PyTorch: 12.0
ROCM used to build PyTorch: N/A
OS: CentOS Stream 9 (x86_64)
GCC version: (GCC) 11.5.0 20240719 (Red Hat 11.5.0-2)
Clang version: Could not collect
CMake version: version 3.26.4
Libc version: glibc-2.34
Python version: 3.10.15 (main, Oct 3 2024, 07:27:34) [GCC 11.2.0] (64-bit runtime)
Python platform: Linux-5.19.0-0_fbk12_hardened_11583_g0bef9520ca2b-x86_64-with-glibc2.34
Is CUDA available: True
CUDA runtime version: 12.0.140
CUDA_MODULE_LOADING set to: LAZY
GPU models and configuration:
GPU 0: NVIDIA H100
GPU 1: NVIDIA H100
GPU 2: NVIDIA H100
GPU 3: NVIDIA H100
Nvidia driver version: 525.105.17
cuDNN version: Probably one of the following:
/usr/lib64/libcudnn.so.9.1.1
/usr/lib64/libcudnn_adv.so.9.1.1
/usr/lib64/libcudnn_cnn.so.9.1.1
/usr/lib64/libcudnn_engines_precompiled.so.9.1.1
/usr/lib64/libcudnn_engines_runtime_compiled.so.9.1.1
/usr/lib64/libcudnn_graph.so.9.1.1
/usr/lib64/libcudnn_heuristic.so.9.1.1
/usr/lib64/libcudnn_ops.so.9.1.1
HIP runtime version: N/A
MIOpen runtime version: N/A
Is XNNPACK available: True
CPU:
Architecture: x86_64
CPU op-mode(s): 32-bit, 64-bit
Address sizes: 52 bits physical, 57 bits virtual
Byte Order: Little Endian
CPU(s): 184
On-line CPU(s) list: 0-183
Vendor ID: AuthenticAMD
Model name: AMD EPYC 9654 96-Core Processor
CPU family: 25
Model: 17
Thread(s) per core: 1
Core(s) per socket: 184
Socket(s): 1
Stepping: 1
BogoMIPS: 4792.80
Flags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ht syscall nx mmxext fxsr_opt pdpe1gb rdtscp lm rep_good nopl cpuid extd_apicid tsc_known_freq pni pclmulqdq ssse3 fma cx16 pcid sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand hypervisor lahf_lm cmp_legacy svm cr8_legacy abm sse4a misalignsse 3dnowprefetch osvw perfctr_core invpcid_single ssbd ibrs ibpb stibp vmmcall fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid avx512f avx512dq rdseed adx smap avx512ifma clflushopt clwb avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves avx512_bf16 clzero xsaveerptr wbnoinvd arat npt lbrv nrip_save tsc_scale vmcb_clean pausefilter pfthreshold v_vmsave_vmload vgif avx512vbmi umip pku ospke avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg avx512_vpopcntdq rdpid fsrm arch_capabilities
Virtualization: AMD-V
Hypervisor vendor: KVM
Virtualization type: full
L1d cache: 11.5 MiB (184 instances)
L1i cache: 11.5 MiB (184 instances)
L2 cache: 92 MiB (184 instances)
L3 cache: 2.9 GiB (184 instances)
NUMA node(s): 1
NUMA node0 CPU(s): 0-183
Vulnerability Itlb multihit: Not affected
Vulnerability L1tf: Not affected
Vulnerability Mds: Not affected
Vulnerability Meltdown: Not affected
Vulnerability Mmio stale data: Not affected
Vulnerability Retbleed: Not affected
Vulnerability Spec store bypass: Vulnerable
Vulnerability Spectre v1: Vulnerable: __user pointer sanitization and usercopy barriers only; no swapgs barriers
Vulnerability Spectre v2: Vulnerable, IBPB: disabled, STIBP: disabled
Vulnerability Srbds: Not affected
Vulnerability Tsx async abort: Not affected
Versions of relevant libraries:
[pip3] flake8==6.1.0
[pip3] flake8-bugbear==23.3.23
[pip3] flake8-comprehensions==3.15.0
[pip3] flake8-executable==2.1.3
[pip3] flake8-logging-format==0.9.0
[pip3] flake8-pyi==23.3.1
[pip3] flake8-simplify==0.19.3
[pip3] mypy==1.11.2
[pip3] mypy-extensions==1.0.0
[pip3] numpy==1.26.0
[pip3] optree==0.13.0
[pip3] pytorch-triton==3.1.0+cf34004b8a
[pip3] torch==2.6.0a0+git2c830c5
[conda] magma-cuda121 2.6.1 1 pytorch
[conda] numpy 1.26.0 pypi_0 pypi
[conda] optree 0.13.0 pypi_0 pypi
[conda] pytorch-triton 3.1.0+cf34004b8a pypi_0 pypi
[conda] torch 2.6.0a0+git2c830c5 dev_0 <develop>
[conda] torchfix 0.4.0 pypi_0 pypi
cc @ezyang @gchanan @zou3519 @kadeng @msaroufim @albanD @chauhang @penguinwu | triaged,module: multithreading | low | Critical |
2,615,406,648 | rust | Diagnostic doesn't mention cfg'ed out items if the unresolved path is simple (i.e., a single identifier) | Given the following code, I would've expected rustc to mention the cfg'ed out item `Struct`:
```rs
#[cfg(flag)]
struct Struct;
fn main() { let _ = Struct; } //~ ERROR cannot find type `Struct` in this scope
```
but it doesn't:
```
error[E0425]: cannot find value `Struct` in this scope
--> file.rs:4:21
|
4 | fn main() { let _ = Struct; }
| ^^^^^^ not found in this scope
```
Only if you slightly tweak the input by replacing the simple path `Struct` with a complex one like `self::Struct` or `crate::Struct`, the note "found an item that was configured out" will show up:
```rs
#[cfg(flag)]
struct Struct;
fn main() { let _ = self::Struct; }
```
```
error[E0425]: cannot find value `Struct` in module `self`
--> file.rs:4:27
|
4 | fn main() { let _ = self::Struct; }
| ^^^^^^ not found in `self`
|
note: found an item that was configured out
--> file.rs:2:8
|
2 | struct Struct;
| ^^^^^^
note: the item is gated here
--> file.rs:1:1
|
1 | #[cfg(flag)]
| ^^^^^^^^^^^^
```
CC #109005. I don't know if that's intentional or not. | A-diagnostics,A-resolve,T-compiler,D-terse,A-cfg | low | Critical |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.