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 |
|---|---|---|---|---|---|---|
2,462,772,534 | godot | Every time I start a new project, a warning is printed about an unavailable file (due to it being referenced in `editor_layout.cfg`) | ### Tested versions
v4.3.rc3.official [03afb92ef]
But I had it happening since 4.1 or so
### System information
Mac Mini M1 with newest MacOS
### Issue description
Every time I start a new project an error is printed in the console:
Again, this is when starting a completely empty project. The file Godot is looking for was indeed used in one of my old projects and it exists somewhere in some other folder and I don't see why would it be invoked. The file Godot is looking for is nothing special, it's just a special effect that is drawn on screen when the player character uses a weapon (basically a Sprite2D with maybe an audio component or something similar).
The projects work normally after I save them the first time (at least I haven't noticed anything strange) and the error message goes away after a while without me doing anything special.
This doesn't really block my work or anything but it's really annoying and slightly worrying.
### Steps to reproduce
I open a new project and get the error message. I assume it's specific to something on my end.
### Minimal reproduction project (MRP)
Godot project manager -> New project | bug,topic:editor,usability | low | Critical |
2,462,794,549 | godot | Dragging a meshlibrary file hangs the editor for several seconds. | ### Tested versions
- Reproductible in v4.3.rc3.mono.official [03afb92ef]
- Reproductible in v4.2.2.stable.mono.official [15073afe3]
### System information
Windows 10 - Vulkan (forward+) - dedicated
### Issue description
Trying to drag a meshlibrary file into a gridmap file makes the editor hang for several seconds depending on the size of the file.
It also repeats the hang everytime you mouseover the slot dropbox.
If the file is small 30Mb~ it is manageble. Just feels clunky.
https://github.com/user-attachments/assets/d725e86c-c1be-43de-aaf9-16fdbd4f2425
Big it becomes unusable if the file is bigger than around 80MB
https://github.com/user-attachments/assets/62941182-9196-469e-b4c5-8db5628b9be4
---
**I'm also not sure if the mesh library size is a bug itself.**
A mesh library of kenny platformer kit (**142 files** totalling **2 MB glb files**) --> **Meshlibrary of 9 MB**
But then using KayKit halloween bits (**63 files** totalling **1.47 MB**) ----> **Meshlibrary of 88 MB**
Both saved as .meshlib format.
It feels like a bug but it might also be the mesh library is horribly optimized for specific cases.
From the size reduction of **130 MB to 5 MB with a simple .zip** with the MRP, the Meshlibrary itself doesn't seem to use much
compression to it, even using .meshlib or .res files.
### Steps to reproduce
From the MRP:
- Open world.tscn
- Drag & drop "mesh_really_bad.meshlib"
Result: Editor hands for several seconds
- Drag & Drop "mesh_bad.meshlib"
Result: Lags and hands for a few miliseconds each time mouse over gridmap slot while holding file.
From a blank project:
- Save a scene file with lots of glb scenes children.
- Select export as meshlibrary.
- Add a gridmap to a new scene
- Try Drag and drop a meshlibrary file into the gridmap slot ( lags if file is 30MB, unusable at 80MB)
### Minimal reproduction project (MRP)
Minimal project.
[bug-meshlibrary-drag.zip](https://github.com/user-attachments/files/16596839/bug-meshlibrary-drag.zip)
| topic:editor,topic:3d,performance | low | Critical |
2,462,839,050 | rust | Inconsistency between tuples and struct-tuples with `min-exhaustive-patterns` | I tried this code:
```rust
#![feature(min_exhaustive_patterns)]
#![feature(never_type)]
use std::marker::PhantomData;
pub fn foo<B>(x: (!, PhantomData<B>)) -> ! {
match x {}
}
pub struct Bar<B>(!, PhantomData<B>);
impl<B> Bar<B> {
pub fn bar(&self) -> ! {
match *self {}
}
}
```
I expected to see this happen: No errors (because `Bar<B>` is empty the same way `foo`'s parameter is).
Instead, this happened: `non-exhaustive patterns: type Bar<B> is non-empty`.
Note that the tracking issue #119612 mentions "a struct with a _visible_ field of empty type", so I also tried to make the first field `pub !` to see, but it's the same behavior. Note that I consider the field visible in the scope it is used, which matches with the fact that adding `pub` did not fix the issue. The issue seems thus to be a difference between struct-tuple and tuple.
### Meta
`rustc --version --verbose`:
```
rustc 1.82.0-nightly (f8060d282 2024-07-30)
binary: rustc
commit-hash: f8060d282d42770fadd73905e3eefb85660d3278
commit-date: 2024-07-30
host: x86_64-unknown-linux-gnu
release: 1.82.0-nightly
LLVM version: 18.1.7
``` | A-diagnostics,T-lang,T-compiler,C-discussion,F-min_exhaustive_patterns | low | Critical |
2,462,870,791 | flutter | IconButton wrapped inside a black background BottomAppBar with ` splashColor: Colors.transparent,` doesn't work correctly | ### Steps to reproduce
consider this code:
```dart
import 'package:flutter/material.dart';
class MainContent extends StatefulWidget {
const MainContent({super.key});
@override
State<MainContent> createState() => _MainContentState();
}
class _MainContentState extends State<MainContent> {
int _selectedIndex = 0;
void _onItemTapped(int index) {
if (_selectedIndex != index)
setState(() {
_selectedIndex = index;
});
}
@override
Widget build(BuildContext context) {
return Scaffold(
appBar: AppBar(
title: const Text('My Notes',
style: TextStyle(fontWeight: FontWeight.bold)),
actions: const [
CircleAvatar(
minRadius: 30,
child: Text(
"a",
))
],
),
body: Text(""),
bottomNavigationBar: BottomAppBar(
shape: const CircularNotchedRectangle(),
notchMargin: 0.0,
height: 67,
color: Colors.black87,
child: Row(
mainAxisAlignment: MainAxisAlignment.spaceBetween,
children: <Widget>[
IconButton(
icon: Icon(
Icons.add,
color: _selectedIndex == 0 ? Colors.white : Colors.grey,
),
splashColor: Colors.transparent,
onPressed: () {
_onItemTapped(0);
},
),
IconButton(
icon: Icon(
Icons.note,
color: _selectedIndex == 1 ? Colors.white : Colors.grey,
),
onPressed: () {
_onItemTapped(1);
},
),
IconButton(
icon: Icon(
Icons.check_box,
color: _selectedIndex == 2 ? Colors.white : Colors.grey,
),
onPressed: () {
_onItemTapped(2);
},
),
IconButton(
icon: Icon(
Icons.more_vert,
color: _selectedIndex == 3 ? Colors.white : Colors.grey,
),
onPressed: () {
_onItemTapped(3);
},
),
],
),
),
);
}
}
```
### Expected results
normal splash animation
### Actual results
some flickering in the iconButton splash area
### Code sample
<details open><summary>Code sample</summary>
```dart
```
</details>
### Screenshots or Video
[video](https://github.com/user-attachments/assets/9cf1d449-346c-4d04-a6f1-e82985fef02e)
### Logs
<details open><summary>Logs</summary>
```console
no logs
```
</details>
### Flutter Doctor output
<details open><summary>Doctor output</summary>
```console
[√] Flutter (Channel master, 3.24.0-1.0.pre.546, on Microsoft Windows [version 10.0.19045.4239], locale en-US)
• Flutter version 3.24.0-1.0.pre.546 on channel master at C:\flutter
• Upstream repository https://github.com/flutter/flutter.git
• Framework revision 8e18b5a331 (30 hours ago), 2024-08-11 23:34:29 -0400
• Engine revision 1a5e2e58d3
• Dart version 3.6.0 (build 3.6.0-134.0.dev)
• DevTools version 2.38.0
[√] Windows Version (Installed version of Windows is version 10 or higher)
[√] Android toolchain - develop for Android devices (Android SDK version 34.0.0)
• Android SDK at C:\Android\Sdk
• Platform android-34, build-tools 34.0.0
• Java binary at: C:\Program Files\Java\jdk-21\bin\java
• Java version Java(TM) SE Runtime Environment (build 21.0.3+7-LTS-152)
• All Android licenses accepted.
[√] Chrome - develop for the web
• Chrome at C:\Program Files\Google\Chrome\Application\chrome.exe
[√] Visual Studio - develop Windows apps (Visual Studio Community 2022 17.3.2)
• Visual Studio at C:\Program Files\Microsoft Visual Studio\2022\Community
• Visual Studio Community 2022 version 17.3.32819.101
• Windows 10 SDK version 10.0.19041.0
[√] Android Studio (version 2024.1)
• Android Studio at C:\Users\bougara computer\Desktop\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 17.0.11+0--11852314)
[√] VS Code (version 1.91.1)
• VS Code at C:\Users\bougara computer\AppData\Local\Programs\Microsoft VS Code
• Flutter extension version 3.91.20240529
[√] Connected device (4 available)
• M2003J15SC (mobile) • 05d3e1490405 • android-arm64 • Android 11 (API 30)
• Windows (desktop) • windows • windows-x64 • Microsoft Windows [version 10.0.19045.4239]
• Chrome (web) • chrome • web-javascript • Google Chrome 127.0.6533.100
• Edge (web) • edge • web-javascript • Microsoft Edge 126.0.2592.113
[√] Network resources
• All expected network resources are available.
• No issues found!
```
</details>
| platform-android,framework,f: material design,has reproducible steps,P2,team-design,triaged-design,found in release: 3.24 | low | Major |
2,462,903,159 | ollama | AMD Discrete GPU Version info not found - Radeon RX Vega56 - gfx900 | ### What is the issue?
## What happened
Every time I start the ollama,it always shows these:
```
https://www.amd.com/en/support/linux-drivers" error="amdgpu version file missing: /sys/module/amdgpu/version stat /sys/module/amdgpu/version: no such file or directory"
time=2024-08-13T16:46:10.463+08:00 level=INFO source=amd_linux.go:348 msg="skipping rocm gfx compatibility check" HSA_OVERRIDE_GFX_VERSION=9.0.0
time=2024-08-13T16:46:10.463+08:00 level=INFO source=types.go:105 msg="inference compute" id=0 library=rocm compute=gfx900 driver=0.0 name=1002:687f total="8.0 GiB" available="7.1 GiB"
```
I am using Arch Linux system and i sure that i installed my drivers correctly
My GPU: _Radeon RX Vega56 8GB_
ROCm version:
_rocm-core 6.0.2-2_
## What I expect
I can use GPU Support
Without this,i can only use my CPU.
### OS
Linux
### GPU
AMD
### CPU
Intel
### Ollama version
0.3.3 | feature request,amd | low | Critical |
2,462,926,646 | rust | Confusing errors with *dyn pointers | ### Code
```Rust
trait MyTrait {
fn f(&self) -> bool;
}
struct MyStruct(pub u32);
impl MyTrait for MyStruct {
fn f(&self) -> bool {
self.0 != 0
}
}
pub fn inner(_p: *mut dyn MyTrait) {}
pub fn outer(p: &mut dyn MyTrait) {
let q = p as *mut _;
inner(q)
}
pub fn main() {
let mut s = MyStruct(42);
outer(&mut s);
}
```
### Current output
```Shell
error: lifetime may not live long enough
--> main.rs:16:13
|
15 | pub fn outer(p: &mut dyn MyTrait) {
| - let's call the lifetime of this reference `'1`
16 | let q = p as *mut _;
| ^ cast requires that `'1` must outlive `'static`
error: aborting due to 1 previous error
```
### Desired output
_No response_
### Rationale and extra context
The fact that a cast to a **raw pointer** checks lifetimes is confusing by itself. Even more confusing is the fact it talks about the reference lifetime while it’s the referenced type lifetime what matters, i.e. `&mut (dyn MyTrait + 'static)` is what the compiler wants. Though I’m not sure whether it should check that either, it’s a raw pointer after all.
Also sometimes, the error is shown not on the cast but where the result is used, like:
```
43 | pub fn some_function<R>(parameter: &mut dyn SomeTrait, f: impl FnOnce() -> R) -> R {
| - let's call the lifetime of this reference `'1`
44 | let pp = std::ptr::from_mut(parameter);
45 | let obj = SomeOtherObj::new(pp);
| ^^ cast requires that `'1` must outlive `'static`
```
I’m not sure how to reproduce *that* however.
Related: #95242.
### Other cases
_No response_
### Rust Version
```Shell
rustc 1.80.1 (3f5fd8dd4 2024-08-06)
binary: rustc
commit-hash: 3f5fd8dd41153bc5fdca9427e9e05be2c767ba23
commit-date: 2024-08-06
host: x86_64-unknown-linux-gnu
release: 1.80.1
LLVM version: 18.1.7
```
### Anything else?
_No response_ | A-diagnostics,T-compiler,D-confusing | low | Critical |
2,462,953,008 | tauri | [bug] document.visibilityState broken | ### Describe the bug
I cannot seem to get the browser `visibilitychange` event to fire by any means, and whether maximized or minimized, `document.visibilityState` always has the value `"visible"`. This is on Windows 10.
There is some prior history for this issue. #6864 describes the lack of `visibilitychange` event when hiding the window behind another window, but describes the event as firing when the window is minimized and maximized. The more recent #9524 again confirms that it fires when minimized or maximized. (The author of that issue believed it should also fire when a window gains or loses focus, but that just seems to originate in confusion about [what page visibility represents](https://developer.mozilla.org/en-US/docs/Web/API/Document/visibilityState).) #9246 appears to change webview visibility on minimize/maximize, and then #9465 reverts it.
This seems to trace back to [this WebView2 issue](https://github.com/MicrosoftEdge/WebView2Feedback/issues/2681). As described in [this comment](https://github.com/MicrosoftEdge/WebView2Feedback/issues/2681#issuecomment-1586686876), the issue—at least at the time—was because "Minimizing a window in WPF does not inherently change the Visibility property of its child controls." If this is the case, though, then I'm not sure how the first two issues above ever recorded `visibilitychange` events on minimize and maximize.
It seems that window occlusion has never caused the document visibility state to change in Tauri, but there has been a regression causing it to no longer update upon minimize/maximize either. `document.visibilityState` simply never appears to change anymore, and always reports itself visible.
### Reproduction
Nothing in particular is needed to reproduce this; just `cargo create-tauri-app` to create a template program and run it. You can examine the document visibility state in the web inspector.
### Expected behavior
The `visibilitychange` event should fire when `document.visibilityState` changes. This should occur whenever the document is either revealed or hidden to the user: when switching between minimized and maximized, when showing or hiding the parent tab, or when the edges of the screen and foreground windows occlude or un-occlude the document.
### Full `tauri info` output
```text
[✔] Environment
- OS: Windows 10.0.19045 X64
✔ WebView2: 127.0.2651.98
✔ MSVC: Visual Studio Community 2022
✔ rustc: 1.80.0 (051478957 2024-07-21)
✔ cargo: 1.80.0 (376290515 2024-07-16)
✔ rustup: 1.27.1 (54dd3d00f 2024-04-24)
✔ Rust toolchain: stable-x86_64-pc-windows-msvc (environment override by RUSTUP_TOOLCHAIN)
- node: 18.12.1
- npm: 8.19.2
[-] Packages
- tauri [RUST]: 2.0.0-rc.2
- tauri-build [RUST]: 2.0.0-rc.2
- wry [RUST]: 0.41.0
- tao [RUST]: 0.28.1
- tauri-cli [RUST]: 2.0.0-rc.3
- @tauri-apps/api : not installed!
- @tauri-apps/cli [NPM]: 2.0.0-rc.3
[-] App
- build-type: bundle
- CSP: unset
- frontendDist: ../src
```
### Stack trace
_No response_
### Additional context
_No response_ | type: bug,platform: Windows | low | Critical |
2,463,004,442 | vscode | Debug view per debug session | <!-- ⚠️⚠️ 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. -->
Apologies if this has already been raised, a search of the issues didn't uncover an existing request.
In more advanced debugging scenarios (e.g. multicore debug on embedded devices) it's common to have multiple debug sessions running either through a compound configuration or by starting them individually.
The current concept in VS Code is to only have one of these sessions "active" and the active session can be changed through:
- The debug toolbar dropdown
- The stack view
- The debug console view
When changed, all views are updated to show details relating to the active session (e.g. the controls above are updated and the variables view is switched to the active session).
When debugging multiple targets, the developer often needs to be able to compare data in these windows between the sessions and this isn't currently possible with the built-in views (e.g. variables).
For custom debug views, we can get round this limitation by managing multiple window instances, however it would be great if a UX pattern for this could be implemented by VS Code for the built-in views.
My proposal would be to show the views as-is when a single debug session is running, but as soon as multiple sessions are available, a dropdown appears on the views to allow:
- Pinning to a specific debug session
- Opening a new version of the window alongside the existing one
This would allow the user to manage multiple debug windows targeting each debug session and compare data between them or observe changes across all debug sessions in tandem.
It's becoming more common for existing IDEs to be migrated to VS Code and functionality to be recreated. I'm involved with multiple teams doing this and the advanced debug needs (such as this) are becoming a blocker to this migration.
If this proposal makes sense, I'm happy to carve out time to create an initial PR.
cc @roblourens @connor4312 | feature-request,debug | low | Critical |
2,463,017,582 | PowerToys | Quick Accent: Missing IPA characters and bad placement of one existing character | ### Description of the new feature / enhancement
I work in Linguistics, and I have found great use from Quick Accent. However, there are some missing symbols, which significantly slows me down, and some symbols that definitely appear under the wrong key.
The missing symbols are (sorted roughly alphabetically) β, ɓ; ç; ð, ɖ, ɗ, ᶑ; ɚ, ɝ; ɡ (U+2061), ɠ, ʛ; ħ, ɧ; ʄ; ɫ, 𝼅, 𝼆, 𝼄; ɱ; œ, ø; θ, ʈ; ʍ; χ; ɥ. These are core IPA symbols. There are also the click letters ʘ, ǀ, ǁ, ǂ, ǃ, 𝼊 which should also be included.
An array of superscript symbols commonly used in linguistic literature are missing, especially ᵊ, ˠ, ʰ, ʱ, ʲ, ˡ, ᵐ, ᶬ, ⁿ, ᵑ, ᶯ, ᶮ, ᶰ, ʳ, ʴ, ʵ, ʶ, ʷ, ˀ, ˁ. In fact, every IPA character has a superscripted symbol in Unicode, which the IPA itself has endorsed [1].
The length marks ː ˑ, the stress marks ˈˌ, the ejective mark ʼ, and the liaison mark ‿ should be included.
The affricate ligatures ʦ ʣ ʧ ʤ ʨ ʥ ꭧ ꭦ should also be included, because they remain widely used.
The tone letters ˩ ˨ ˧ ˦ ˥ should be included as well, probably under the numbers 1 2 3 4 5, respectively.
Finally, there is an array of combining (and related non-combining) marks used by the IPA: these are ◌̥ ◌̊ ◌̬ ◌̹ ◌̜ ◌̟ ˖ ◌̠ ˗ ◌̈ ◌̽ ◌̩ ◌̍ ◌̯ ◌̑ ◌˞ ◌̤ ◌̰ ◌̼ ◌̴ ◌̝ ˔ ◌̞ ˕ ◌̘ ꭪ ◌̙ ꭫ ◌̪ ◌͆ ◌̻ ◌̃ ◌̚ ◌̆ ◌͡◌ ◌͜◌. There are also the old tone marks, which are ◌̏ ◌̀ ◌̄ ◌́ ◌̋ ◌̌ ◌̂ ◌᷄ ◌᷅ ◌᷆ ◌᷇ ◌᷈ ◌᷉. Tangentially, generally displaying combining marks with ◌ in the selection prompt would be useful.
Most of these symbols can be found in [2].
There's also an array of non-standard symbols that enjoy widespread use: ȶ, ȡ, ȵ, ȴ, ɿ, ʅ, ʮ, ʯ, λ, ƛ, ł, ᵻ, ᵿ, ɿ, ʅ, ʮ, ʯ, ∅.
The symbol ɟ should be placed under the J key instead of F, considering its meaning. The fact that it derives from an upside-down f should be ignored, similar to the case with ʎ, which is correctly placed under L and not Y.
### Scenario when this would be used?
This would be useful to anyone working in anything linguistics-adjacent, because the current implementation of the IPA in Quick Accent is too deficient.
### Supporting information
[1]: https://www.unicode.org/L2/L2020/20253-mod-ipa-b.pdf
[2]: https://www.internationalphoneticassociation.org/IPAcharts/IPA_chart_orig/pdfs/IPA_unitipa_2020_symbollist.pdf | Needs-Triage,Product-Quick Accent | low | Major |
2,463,019,071 | stable-diffusion-webui | [Feature Request]: Add BitsAndBytes NF4 quantization | ### Is there an existing issue for this?
- [X] I have searched the existing issues and checked the recent builds/commits
### What would your feature do ?
Seems add better performances : https://github.com/bitsandbytes-foundation/bitsandbytes
Already integrated in Forge : https://github.com/lllyasviel/stable-diffusion-webui-forge/discussions/981
The performances are very good.
### Proposed workflow
Thanks.
### Additional information
_No response_ | enhancement | low | Major |
2,463,073,803 | langchain | Improve documentation for LengthBasedExampleSelector and FewShotPromptTemplate compatibility | ### URL
https://python.langchain.com/v0.2/docs/how_to/example_selectors_length_based/ & https://python.langchain.com/v0.2/docs/how_to/example_selectors/
### Issue with current documentation:
The current documentation lacks clear guidance on how to use custom example selectors with FewShotPromptTemplate, especially when dealing with import issues or when creating simplified versions of built-in selectors.
Specifically:
The documentation should explain the requirements for custom example selectors to be compatible with FewShotPromptTemplate.
There should be examples of how to create custom example selectors that work with FewShotPromptTemplate without relying on specific imports like BaseExampleSelector.
The documentation should provide alternatives or workarounds for cases where users cannot import certain modules but still want to use functionality similar to LengthBasedExampleSelector.
It would be helpful to have a section on troubleshooting common issues when using custom example selectors with FewShotPromptTemplate, including explanations of errors like "instance of BaseExampleSelector expected".
### Idea or request for content:
Add a section on "Creating Custom Example Selectors" that covers:
Basic structure and required methods
How to ensure compatibility with FewShotPromptTemplate
Examples of simplified versions of built-in selectors
Include a "Troubleshooting" section for FewShotPromptTemplate and example selectors, covering common errors and their solutions.
Provide examples of alternative implementations or wrappers for cases where direct inheritance from BaseExampleSelector is not possible.
Create a guide on "Adapting External Libraries for Use with LangChain" that covers scenarios like the one discussed in this conversation. | 🤖:docs | low | Critical |
2,463,096,625 | PowerToys | Image resizer - suggested use of the CTRL key | ### Description of the new feature / enhancement
Hello, I suggest (recommend? :) ) that CTRL key down at click time could use the same size and settings as the last usage - no droplist of choices, that are mostly always the same anyways. Everything faster for speed users, casual users would not bother/use anyways, etc. Win-win !
### Scenario when this would be used?
Power users, users that use the same settings (sizes) all the time. Saves lots of time and a perpetually useless window for when always the same.
### Supporting information
This is usage of a key that already exists for other softwares, with no downside. Print-screen for instance has all combos of ALT and CTRL and SHIFT. | Idea-Enhancement,Product-Image Resizer,Needs-Triage | low | Minor |
2,463,115,915 | PowerToys | Mouse without borders | ### Description of the new feature / enhancement
Enabled on logon screen
### Scenario when this would be used?
When computers go to sleep or screensaver is activated, unable to use mouse without borders on the second computer.
### Supporting information
_No response_ | Needs-Triage,Product-Mouse Without Borders | low | Minor |
2,463,117,191 | flutter | Make it possible for users to customize CupertinoNavBar's `previousTitle` text style. | ### Use case
Make it possible for users customized CupertinoNavBar's previousTitle text style.
### Proposal
Make it possible for users customized CupertinoNavBar's previousTitle text style.
| framework,f: cupertino,c: proposal,P2,team-design,triaged-design | low | Minor |
2,463,265,165 | react-native | [Accessibility] [TalkBack] PanResponder callbacks do not fire when TouchableOpacity/Pressable is pressed and TalkBack is on | ### Description
On Android with TalkBack on, TouchableOpacity/Pressable components do not trigger PanResponder callbacks when pressed if the TouchableOpacity/Pressable has on onPress prop and its focusable prop is not false.
### Steps to reproduce
1. Create a PanResponder and apply its panHandlers to a View.
2. Add a Pressable inside the View and give it an onPress prop.
3. View the app in Android with TalkBack on.
9. Double-tap to activate, observe the pan responder callbacks DO NOT fire.
Furthermore, double-tapping a non-TouchableOpacity/Pressable element such as a Text component will trigger PanResponder callbacks.
In the example repo I provided it should print "PanResponder Callback Triggered' but its only printing "ON PRESS TRIGGERED"
### React Native Version
0.73.6
### Affected Platforms
Runtime - Android
### Output of `npx react-native info`
```text
System:
OS: macOS 14.5
CPU: (11) arm64 Apple M3 Pro
Memory: 84.00 MB / 18.00 GB
Shell:
version: "5.9"
path: /bin/zsh
Binaries:
Node:
version: 18.18.0
path: ~/.nvm/versions/node/v18.18.0/bin/node
Yarn:
version: 1.22.22
path: /opt/homebrew/bin/yarn
npm:
version: 9.8.1
path: ~/.nvm/versions/node/v18.18.0/bin/npm
Watchman:
version: 2024.04.22.00
path: /opt/homebrew/bin/watchman
Managers:
CocoaPods:
version: 1.15.2
path: /opt/homebrew/bin/pod
SDKs:
iOS SDK:
Platforms:
- DriverKit 23.5
- iOS 17.5
- macOS 14.5
- tvOS 17.5
- visionOS 1.2
- watchOS 10.5
Android SDK:
API Levels:
- "29"
- "30"
- "31"
- "32"
- "33"
- "33"
- "34"
Build Tools:
- 29.0.2
- 30.0.2
- 30.0.3
- 33.0.0
- 33.0.1
- 34.0.0
System Images:
- android-28 | Google ARM64-V8a Play ARM 64 v8a
- android-29 | Google Play ARM 64 v8a
- android-31 | Google APIs ARM 64 v8a
- android-33 | Google APIs ARM 64 v8a
Android NDK: Not Found
IDEs:
Android Studio: 2022.1 AI-221.6008.13.2211.9514443
Xcode:
version: 15.4/15F31d
path: /usr/bin/xcodebuild
Languages:
Java:
version: 17.0.10
path: /Library/Java/JavaVirtualMachines/jdk-17.0.10.jdk/Contents/Home/bin/javac
Ruby:
version: 2.6.10
path: /usr/bin/ruby
npmPackages:
"@react-native-community/cli": Not Found
react:
installed: 18.2.0
wanted: 18.2.0
react-native:
installed: 0.73.6
wanted: 0.73.6
react-native-macos: Not Found
npmGlobalPackages:
"*react-native*": Not Found
Android:
hermesEnabled: true
newArchEnabled: false
iOS:
hermesEnabled: true
newArchEnabled: false
```
### Stacktrace or Logs
```text
No Stacktrace or log
```
### Reproducer
https://github.com/Abhisflyingsoon/android-panresponder-accessibility
### Screenshots and Videos
_No response_ | Issue: Author Provided Repro,API: PanResponder,Component: TouchableOpacity,Newer Patch Available | low | Minor |
2,463,306,390 | vscode | Notification that a user is running emulated should be a blocking modal dialog | 1. Be on apple arm, download mac-intel-vsix
2. Start it. it is dog-slow since running emulated
3. There is a notification. I think it is easy to miss. This should be a blocking model dialog since the experience is that bad
fyi @joaomoreno | debt,macos | low | Major |
2,463,366,295 | vscode | Bracket guide not colored/incorrect with long wrapped line | Type: <b>Bug</b>
When a wrapped line does not fit on the screen the bracket guide becomes light gray and it is at the wrong column:
<details>
<summary>File contents</summary>
```json
[
{
"x": [
"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"
]
}
]
```
</details>
https://github.com/user-attachments/assets/a43c24c7-9040-484b-9402-513d72dd2dea
VS Code version: Code - Insiders 1.93.0-insider (922413f6d97e16c05b565398f33d95c306b1ceb7, 2024-08-13T05:04:09.073Z)
OS version: Windows_NT x64 10.0.19045
Modes:
<details>
<summary>System Info</summary>
|Item|Value|
|---|---|
|CPUs|Intel(R) Xeon(R) CPU E5-1620 v2 @ 3.70GHz (8 x 3691)|
|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: unavailable_off<br>vulkan: disabled_off<br>webgl: enabled<br>webgl2: enabled<br>webgpu: enabled<br>webnn: disabled_off|
|Load (avg)|undefined|
|Memory (System)|31.95GB (4.28GB free)|
|Process Argv|--crash-reporter-id 59c38a97-6b20-42ad-b729-8c40ade347e9|
|Screen Reader|no|
|VM|0%|
</details>Extensions: none<details>
<summary>A/B Experiments</summary>
```
vsliv368:30146709
vspor879:30202332
vspor708:30202333
vspor363:30204092
vscod805:30301674
vsaa593:30376534
py29gd2263:31024238
c4g48928:30535728
a9j8j154:30646983
962ge761:30841072
pythongtdpath:30726887
welcomedialog:30812478
pythonnoceb:30776497
asynctok:30898717
dsvsc014:30777825
dsvsc015:30821418
pythonregdiag2:30926734
pythonmypyd1:30859725
h48ei257:31000450
pythontbext0:30879054
accentitlementst:30870582
dsvsc016:30879898
dsvsc017:30880771
dsvsc018:30880772
cppperfnew:30980852
pythonait:30973460
724cj586:31013169
a69g1124:31018687
dvdeprecation:31040973
dwnewjupytercf:31046870
impr_priority:31057980
nativerepl1:31104042
refactort:31084545
pythonrstrctxt:31093868
flighttreat:31105043
wkspc-onlycs-c:31111717
nativeloc1:31111755
cf971741:31111988
fcdif617:31111928
```
</details>
<!-- generated by issue reporter -->
| bug,bracket-pair-guides | low | Critical |
2,463,390,053 | deno | test `jupyter::jupyter_kernel_info` is flaky | ```
failures:
---- jupyter::jupyter_kernel_info stdout ----
command /home/runner/work/deno/deno/target/release/deno jupyter --kernel --conn /tmp/deno-cli-test4miBHJ/connection.json
command cwd /tmp/deno-cli-test4miBHJ
thread 'jupyter::jupyter_kernel_info' panicked at tests/integration/jupyter_tests.rs:475:5:
Failed to start Jupyter server
stack backtrace:
0: 0xab91e7864e28 - <std::sys_common::backtrace::_print::DisplayBacktrace as core::fmt::Display>::fmt::h677fb81bc4f23286
1: 0xab91e788dffc - core::fmt::write::h2b46371187d5b982
2: 0xab91e78606e4 - std::io::Write::write_fmt::hceb78a0646e6d5d6
```
https://github.com/denoland/deno/actions/runs/10370232910/job/28707686811?pr=25021#step:45:2826 | flaky | low | Critical |
2,463,518,882 | godot | Impossible to change path to dependency for .glb files | ### Tested versions
- Reproducible in: 4.2.2.stable
### System information
Archlinux - Wayland - Godot v4.2.2.stable - vulkan-nouveau (Forward+) - dedicated
### Issue description
Cannot change nor fix path to an image dependency (jpg) for glb recognized as scene. UI dialogue very laggy.
### Steps to reproduce
- Create new Godot project
- In Blender (v4.2.0):
- Create new project
- Create a mesh and assign an image texture
- Export directly to Godot project path using native glTF 2.0 export option
- Find .glb and image texture in res://...
- Try Edit Dependencies and change path to image texture*
- Delete texture file next to .glb
- Try Edit Dependencies and Fix Broken*
*Both times nothing changes for me
### Minimal reproduction project (MRP)
N/A | bug,topic:editor,topic:import,topic:3d | low | Critical |
2,463,586,612 | PowerToys | The "Command not found" error in an intranet and offline environment causes PowerShell to crash upon startup. | ### Microsoft PowerToys version
0.83.0
### Installation method
PowerToys auto-update
### Running as admin
Yes
### Area(s) with issue?
Command not found
### Steps to reproduce
Install The "Command not found".
Start PowerShell in an intranet and offline environment.
### ✔️ Expected Behavior
In intranet and offline environments, the "Command not found" should utilize local cache or be closed.
### ❌ Actual Behavior
PowerShell crashed with log:
An error has occurred that was not properly handled. Additional information is shown below. The PowerShell process will exit.
Unhandled exception. System.Management.Automation.CmdletInvocationException: An error occurred while connecting to the catalog.
---> Microsoft.WinGet.Client.Engine.Exceptions.CatalogConnectException: An error occurred while connecting to the catalog.
at Microsoft.WinGet.Client.Engine.Commands.Common.FinderCommand.GetPackageCatalog(CompositeSearchBehavior behavior)
at Microsoft.WinGet.Client.Engine.Commands.Common.FinderCommand.FindPackages(CompositeSearchBehavior behavior, UInt32 limit, PackageFieldMatchOption match)
at Microsoft.WinGet.Client.Engine.Commands.Common.FinderExtendedCommand.FindPackages(CompositeSearchBehavior behavior, PackageFieldMatchOption match)
at Microsoft.WinGet.Client.Engine.Commands.FinderPackageCommand.<>c__DisplayClass1_0.<Find>b__0()
at Microsoft.WinGet.Client.Engine.Commands.Common.ManagementDeploymentCommand.Execute[TResult](Func`1 func)
at Microsoft.WinGet.Client.Engine.Commands.FinderPackageCommand.Find(String psPackageFieldMatchOption)
at Microsoft.WinGet.Client.Commands.FindPackageCmdlet.ProcessRecord()
at System.Management.Automation.CommandProcessor.ProcessRecord()
--- End of inner exception stack trace ---
at System.Management.Automation.Runspaces.AsyncResult.EndInvoke()
at System.Management.Automation.PowerShell.EndInvoke(IAsyncResult asyncResult)
at System.Threading.Tasks.TaskFactory`1.FromAsyncCoreLogic(IAsyncResult iar, Func`2 endFunction, Action`1 endAction, Task`1 promise, Boolean requiresSynchronization)
--- End of stack trace from previous location ---
at Microsoft.WinGet.CommandNotFound.WinGetCommandNotFoundFeedbackPredictor.WarmUp()
at System.Threading.Tasks.Task.<>c.<ThrowAsync>b__128_1(Object state)
at System.Threading.QueueUserWorkItemCallback.Execute()
at System.Threading.ThreadPoolWorkQueue.Dispatch()
at System.Threading.PortableThreadPool.WorkerThread.WorkerThreadStart()
### Other Software
_No response_ | Issue-Bug,Needs-Triage,Product-CommandNotFound | low | Critical |
2,463,629,149 | electron | [Bug]: WebView Error 'GUEST_VIEW_MANAGER_CALL': Error: ERR_FAILED (-2) on Navigation | ### Preflight Checklist
- [X] I have read the [Contributing Guidelines](https://github.com/electron/electron/blob/main/CONTRIBUTING.md) for this project.
- [X] I agree to follow the [Code of Conduct](https://github.com/electron/electron/blob/main/CODE_OF_CONDUCT.md) that this project adheres to.
- [X] I have searched the [issue tracker](https://www.github.com/electron/electron/issues) for a bug report that matches the one I want to file, without success.
### Electron Version
29.* - 31.3.1
### What operating system(s) are you using?
Windows
### Operating System Version
Windows 10 19045
### What arch are you using?
x64
### Last Known Working Electron version
18
### Expected Behavior
WebView Navigation should work even after a Javascript Errors on a Page.
### Actual Behavior
1. Loading a remote Website that contains a simple PDFJs (default viewer.html) with a WebView.
2. PDFJs Logs some JS Errors to Console because of a fishy PDF Forms...
3. After that there is no way to navigate the WebView again.
If we set a new `src` attribute
```js
document.querySelector('#view').setAttribute("src", "http://google.de")
```
it results in a Error:
```
Unexpected error while loading URL
Error: Error invoking remote method 'GUEST_VIEW_MANAGER_CALL': Error: ERR_FAILED (-2) loading 'http://google.de/'
```
Node Log:
```
Error occurred in handler for 'GUEST_VIEW_MANAGER_CALL': Error: ERR_FAILED (-2) loading 'http://google.de/'
at rejectAndCleanup (node:electron/js2c/browser_init:2:78996)
at finishListener (node:electron/js2c/browser_init:2:79158)
at WebContents.stopLoadingListener (node:electron/js2c/browser_init:2:79545)
at WebContents.emit (node:events:531:35) {
errno: -2,
code: 'ERR_FAILED',
url: 'http://google.de/'
}
```
If we use the DevTools of the WebView:
```js
document.querySelector('#view').openDevTools()
```
and try to navigate here we got also a error.
```js
navigation.navigate("http://google.de")
Uncaught (in promise) DOMException: Navigation was aborted
```
The only way to get the Electron working again is to remove the WebView from DOM and add a new one.
### Testcase Gist URL
_No response_
### Additional Information
_No response_ | platform/windows,component/webview,bug :beetle:,30-x-y,31-x-y | low | Critical |
2,463,642,294 | PowerToys | PowerRename - Save patterns with a friendly name | ### Description of the new feature / enhancement
Provide an option to store regularly used patterns with a friendly name. Currently previously applied patterns are available in a drop-down but this isn't very user friendly as I basically have to re-interpret what each pattern does whenever I want to re-use one I've used previously.
### Scenario when this would be used?
Any time I want to re-use a pattern.
### Supporting information
_No response_ | Idea-Enhancement,Product-PowerRename,Needs-Triage | low | Minor |
2,463,667,762 | vscode | Multi diff editor screen cheese | * open timeline for `src/vs/workbench/contrib/inlineChat/browser/inlineChatActions.ts`
* open x-diff for "fix: resolve location data..."
* :bug: title is broken/wrapped
| bug,multi-diff-editor | low | Critical |
2,463,681,520 | react-native | TextInput with Large Font Size (>40) Causes Text to Become Invisible on iOS | ### Description
When using a TextInput component with a large fontSize (greater than 40), the text becomes invisible on iOS devices. This issue does not occur on Android, where the text is displayed correctly regardless of the font size. The problem is particularly evident when the text is long and the TextInput is set to multiline.
### Steps to reproduce
1. Create a new React Native project with the latest version.
2. Add a TextInput component with multiline set to true.
3. Set the fontSize of the TextInput to a value greater than 40.
4. Provide a long string as the defaultValue or value for the TextInput.
5. Run the app on an iOS device or simulator.
### React Native Version
0.74.5
### Affected Platforms
Runtime - iOS
### Output of `npx react-native info`
```text
System:
OS: macOS 14.5
CPU: (8) arm64 Apple M2
Memory: 134.08 MB / 16.00 GB
Shell:
version: "5.9"
path: /bin/zsh
Binaries:
Node:
version: 18.17.0
path: ~/.nvm/versions/node/v18.17.0/bin/node
Yarn:
version: 3.6.4
path: /opt/homebrew/bin/yarn
npm:
version: 9.6.7
path: ~/.nvm/versions/node/v18.17.0/bin/npm
Watchman:
version: 2024.04.08.00
path: /opt/homebrew/bin/watchman
Managers:
CocoaPods:
version: 1.15.2
path: /Users/enestatli/.rbenv/shims/pod
SDKs:
iOS SDK:
Platforms:
- DriverKit 23.5
- iOS 17.5
- macOS 14.5
- tvOS 17.5
- visionOS 1.2
- watchOS 10.5
Android SDK:
API Levels:
- "29"
- "30"
- "31"
- "33"
- "33"
- "34"
Build Tools:
- 30.0.2
- 30.0.3
- 31.0.0
- 33.0.0
- 33.0.1
- 33.0.2
- 34.0.0
System Images:
- android-30 | Google APIs Intel x86 Atom
- android-30 | Google Play ARM 64 v8a
- android-33 | Google APIs ARM 64 v8a
- android-34 | Google APIs ARM 64 v8a
Android NDK: Not Found
IDEs:
Android Studio: 2022.3 AI-223.8836.35.2231.10406996
Xcode:
version: 15.4/15F31d
path: /usr/bin/xcodebuild
Languages:
Java:
version: 17.0.9
path: /usr/bin/javac
Ruby:
version: 2.7.6
path: /Users/enestatli/.rbenv/shims/ruby
npmPackages:
"@react-native-community/cli": Not Found
react:
installed: 18.2.0
wanted: 18.2.0
react-native:
installed: 0.74.5
wanted: 0.74.5
react-native-macos: Not Found
npmGlobalPackages:
"*react-native*": Not Found
Android:
hermesEnabled: true
newArchEnabled: false
iOS:
hermesEnabled: true
newArchEnabled: false
```
### Stacktrace or Logs
```text
-
```
### Reproducer
https://snack.expo.dev/@enestatli65/quiet-orange-strawberries
### Screenshots and Videos
_No response_ | Platform: iOS,Issue: Author Provided Repro,Component: TextInput | low | Minor |
2,463,682,520 | flutter | Tests on mokey devices flaking due to failure to install | As in https://ci.chromium.org/ui/p/flutter/builders/prod/Mac_mokey%20hot_mode_dev_cycle__benchmark/52/overview
With error message:
`adb: failed to install /opt/s/w/ir/x/t/edited_flutter_gallery/build/app/outputs/flutter-apk/app-debug.apk: Failure [INSTALL_FAILED_UPDATE_INCOMPATIBLE: Existing package io.flutter.demo.gallery signatures do not match newer version; ignoring!]` | platform-android,tool,P1,team-tool | medium | Critical |
2,463,694,274 | storybook | [Bug]: Storybook fails to launch with `NODE_OPTIONS=--experimental-strip-types` | ### Describe the bug
Storybook fails to launch when [`NODE_OPTIONS=--experimental-strip-types`](https://nodejs.org/api/typescript.html#type-stripping) is present in the environment. Removing the variable makes it work, but I would prefer not having to do that as I want my Node to be able to run Typescript.
```
SB_CORE-SERVER_0007 (MainFileEvaluationError): Storybook couldn't evaluate your .storybook/main.ts file.
Original error:
Error [ERR_REQUIRE_ESM]: require() of ES Module /.storybook/main.ts from /node_modules/@storybook/core/dist/common/index.cjs not supported.
Instead change the require of main.ts in /node_modules/@storybook/core/dist/common/index.cjs to a dynamic import() which is available in all CommonJS modules.
at TracingChannel.traceSync (node:diagnostics_channel:315:14)
at interopRequireDefault (/node_modules/@storybook/core/dist/common/index.cjs:145609:11)
at serverRequire (/node_modules/@storybook/core/dist/common/index.cjs:145623:14)
at loadMainConfig (/node_modules/@storybook/core/dist/common/index.cjs:151297:18)
at loadMainConfig (./node_modules/@storybook/core/dist/common/index.cjs:151315:11)
at async buildDevStandalone (./node_modules/@storybook/core/dist/core-server/index.cjs:256949:11)
at async withTelemetry (./node_modules/@storybook/core/dist/core-server/index.cjs:255711:12)
at async dev (./node_modules/storybook/dist/generate.cjs:738:506)
at async Command.<anonymous> (./node_modules/storybook/dist/generate.cjs:740:245)
```
### Reproduction link
https://github.com/silverwind/storybook-node-strip
### Reproduction steps
1. Have Node.js 22.6.0 or higher installed
2. Clone repo
3. Run `npm run storybook`
### System
```bash
Storybook Environment Info:
System:
OS: macOS 14.5
CPU: (16) arm64 Apple M3 Max
Shell: 5.9 - /bin/zsh
Binaries:
Node: 22.6.0 - /opt/homebrew/bin/node
Yarn: 1.22.22 - /opt/homebrew/bin/yarn
npm: 10.8.2 - /opt/homebrew/bin/npm <----- active
pnpm: 9.7.0 - ~/.npm-global/bin/pnpm
Browsers:
Chrome: 127.0.6533.89
Safari: 17.5
npmPackages:
@storybook/addon-essentials: 8.2.9 => 8.2.9
@storybook/addon-interactions: 8.2.9 => 8.2.9
@storybook/addon-links: 8.2.9 => 8.2.9
@storybook/addon-onboarding: 8.2.9 => 8.2.9
@storybook/blocks: 8.2.9 => 8.2.9
@storybook/react: 8.2.9 => 8.2.9
@storybook/react-vite: 8.2.9 => 8.2.9
@storybook/test: 8.2.9 => 8.2.9
eslint-plugin-storybook: 0.8.0 => 0.8.0
storybook: 8.2.9 => 8.2.9
```
### Additional context
_No response_ | bug,needs triage | low | Critical |
2,463,696,090 | godot | Misleading return value on Object::call_deferred | ### Tested versions
master
### System information
N/A
### Issue description
Call deferred is marked as returning Variant while it actually always returns null.
This is misleading as it may confuse developers into thinking it can return something else.
Easily patchable by changing the method info in object.cpp
### Steps to reproduce
N/A
### Minimal reproduction project (MRP)
N/A | discussion,topic:core,breaks compat | low | Major |
2,463,697,785 | go | cmd/compile: in `prove.go:addLocalFacts` `ft.update` propagates limits depends on value ordering and can't propagate `ft.update` → `ft.flowLimit` dependencies | ### Go version
go1.24-793b14b455
### Output of `go env` in your module/workspace:
```shell
GO111MODULE=''
GOARCH='amd64'
GOBIN=''
GOCACHE='/tmp/go-build'
GOENV='/home/hugo/.config/go/env'
GOEXE=''
GOEXPERIMENT='rangefunc'
GOFLAGS=''
GOHOSTARCH='amd64'
GOHOSTOS='linux'
GOINSECURE=''
GOMODCACHE='/home/hugo/go/pkg/mod'
GONOPROXY=''
GONOSUMDB=''
GOOS='linux'
GOPATH='/home/hugo/go'
GOPRIVATE=''
GOPROXY='https://proxy.golang.org,direct'
GOROOT='/home/hugo/k/go'
GOSUMDB='sum.golang.org'
GOTMPDIR=''
GOTOOLCHAIN='local'
GOTOOLDIR='/home/hugo/k/go/pkg/tool/linux_amd64'
GOVCS=''
GOVERSION='devel go1.24-793b14b455 Tue Aug 13 17:23:56 2024 +0200 X:rangefunc'
GODEBUG=''
GOTELEMETRY='local'
GOTELEMETRYDIR='/home/hugo/.config/go/telemetry'
GCCGO='/usr/bin/gccgo'
GOAMD64='v3'
AR='ar'
CC='gcc'
CXX='g++'
CGO_ENABLED='1'
GOMOD='/home/hugo/k/go/src/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 -m64 -pthread -Wl,--no-gc-sections -fmessage-length=0 -ffile-prefix-map=/tmp/go-build127661744=/tmp/go-build -gno-record-gcc-switches'
```
### What did you do?
Add theses in `test/prove.go` and run:
```go
func mod64uWithSmallerDividendMax(a, b uint64, ensureBothBranchesCouldHappen bool) int {
a &= 0xff
b &= 0xfff
z := bits.Len64(a % b)
if ensureBothBranchesCouldHappen {
if z > bits.Len64(0xff) { // ERROR "Disproved Less64$"
return 42
}
} else {
if z <= bits.Len64(0xff) { // ERROR "Proved Leq64$"
return 1337
}
}
return z
}
func mod64uWithSmallerDivisorMax(a, b uint64, ensureBothBranchesCouldHappen bool) int {
a &= 0xfff
b &= 0x10 // we need bits.Len64(b.umax) != bits.Len64(b.umax-1)
z := bits.Len64(a % b)
if ensureBothBranchesCouldHappen {
if z > bits.Len64(0x10-1) { // ERROR "Disproved Less64$"
return 42
}
} else {
if z <= bits.Len64(0x10-1) { // ERROR "Proved Leq64$"
return 1337
}
}
return z
}
func mod64uWithIdenticalMax(a, b uint64, ensureBothBranchesCouldHappen bool) int {
a &= 0x10
b &= 0x10 // we need bits.Len64(b.umax) != bits.Len64(b.umax-1)
z := bits.Len64(a % b)
if ensureBothBranchesCouldHappen {
if z > bits.Len64(0x10-1) { // ERROR "Disproved Less64$"
return 42
}
} else {
if z <= bits.Len64(0x10-1) { // ERROR "Proved Leq64$"
return 1337
}
}
return z
}
```
### What did you see happen?
```
--- FAIL: Test (0.02s)
--- FAIL: Test/prove.go (0.31s)
testdir_test.go:145:
prove.go:1436: missing error "Disproved Less64$"
prove.go:1440: missing error "Proved Leq64$"
prove.go:1453: missing error "Disproved Less64$"
prove.go:1457: missing error "Proved Leq64$"
prove.go:1470: missing error "Disproved Less64$"
prove.go:1474: missing error "Proved Leq64$"
FAIL
FAIL cmd/internal/testdir 0.336s
FAIL
```
### What did you expect to see?
```
ok cmd/internal/testdir 0.350s
``` | Performance,NeedsInvestigation,compiler/runtime | low | Critical |
2,463,699,809 | ollama | ollama - default tool support | In the standard cli there should be some default tools like IPython (just like code interpreter, disabled by default), or so so that you can simply add it those tools to any model that supports such a tool, and a way to integrate custom tools, maybe someone wants to integrate their SD3 workflow, but it should be provided from the CLI itself, no?
as CLI flag wthout needing to use the ollama api, just CLI! | feature request | low | Minor |
2,463,803,953 | PowerToys | [PTRun] Better Fuzzy Match | ### Description of the new feature / enhancement
I want to work for #20672. I have come up with an algorithm for this:
Firstly, for each letter "query[i]", its score depends on its distance from the position of "query[i-1]" in stringToCompare.
In order to achieve high scores for the first letter, the distance is set to the position of the word + the position of the letter in the word
Finally, through dynamic programming, the matching score can be obtained.
But I am not sure if it is truly feasible. moreover, this algorithm has another issue. Unlike the existing algorithm, a smaller score means a better result. To ensure minimal disruption, the score needs to be negated. Does the current code support negative scores?
Hope to receive some suggestions.
### Scenario when this would be used?
PTRun FuzzyMatch
### Supporting information
_No response_ | Idea-Enhancement,Product-PowerToys Run,Needs-Triage | low | Minor |
2,463,826,068 | vscode | Cmd-Click doesn't work on JSDoc {@link URL|LinkText} format | <!-- ⚠️⚠️ Do Not Delete This! bug_report_template ⚠️⚠️ -->
<!-- Please read our Rules of Conduct: https://opensource.microsoft.com/codeofconduct/ -->
<!-- 🕮 Read our guide about submitting issues: https://github.com/microsoft/vscode/wiki/Submitting-Bugs-and-Suggestions -->
<!-- 🔎 Search existing issues to avoid creating duplicates. -->
<!-- 🧪 Test using the latest Insiders build to see if your issue has already been fixed: https://code.visualstudio.com/insiders/ -->
<!-- 💡 Instead of creating your report here, use 'Report Issue' from the 'Help' menu in VS Code to pre-fill useful information. -->
<!-- 🔧 Launch with `code --disable-extensions` to check. -->
Does this issue occur when all extensions are disabled?: Yes/No
<!-- 🪓 If you answered No above, use 'Help: Start Extension Bisect' from Command Palette to try to identify the cause. -->
<!-- 📣 Issues caused by an extension need to be reported directly to the extension publisher. The 'Help > Report Issue' dialog can assist with this. -->
- VS Code Version:
- OS Version:
Steps to Reproduce:
1. Create a `.ts` file containing
```ts
/**
* {@link https://developer.mozilla.org/en-US/docs/Web/JavaScript/Reference/Global_Objects/Promise/withResolvers|Promise.withResolvers}
*/
```
This is one of the valid ways of providing link text according to https://jsdoc.app/tags-inline-link.
3. Cmd-Click (or Windows equivalent) on the URL
4. VSCode opens https://developer.mozilla.org/en-US/docs/Web/JavaScript/Reference/Global_Objects/Promise/withResolvers%7CPromise.withResolvers, instead of https://developer.mozilla.org/en-US/docs/Web/JavaScript/Reference/Global_Objects/Promise/withResolvers
When I tried `{@link http://www.google.com|Google}`, Cmd-Clicking on the link doesn't open anything, and logs
```
2024-08-13 12:04:55.265 [error] TypeError: Invalid URL
at new URL (node:internal/url:797:36)
at Object.canOpenExternalUri (/Applications/Visual Studio Code.app/Contents/Resources/app/extensions/simple-browser/dist/extension.js:1:6134)
```
Fortunately I can use `[Link Text]{@link URL}` format, but I expected VSCode to support any valid `@link` format. | bug,typescript,javascript | low | Critical |
2,463,826,080 | vscode | History graph diff always shows horizontal scroll bar | <!-- ⚠️⚠️ Do Not Delete This! bug_report_template ⚠️⚠️ -->
<!-- Please read our Rules of Conduct: https://opensource.microsoft.com/codeofconduct/ -->
<!-- 🕮 Read our guide about submitting issues: https://github.com/microsoft/vscode/wiki/Submitting-Bugs-and-Suggestions -->
<!-- 🔎 Search existing issues to avoid creating duplicates. -->
<!-- 🧪 Test using the latest Insiders build to see if your issue has already been fixed: https://code.visualstudio.com/insiders/ -->
<!-- 💡 Instead of creating your report here, use 'Report Issue' from the 'Help' menu in VS Code to pre-fill useful information. -->
<!-- 🔧 Launch with `code --disable-extensions` to check. -->
Does this issue occur when all extensions are disabled?: Yes
<!-- 🪓 If you answered No above, use 'Help: Start Extension Bisect' from Command Palette to try to identify the cause. -->
<!-- 📣 Issues caused by an extension need to be reported directly to the extension publisher. The 'Help > Report Issue' dialog can assist with this. -->
- VS Code Version: 1.93.0-insider (922413f6d97e16c05b565398f33d95c306b1ceb7)
- OS Version: macOS Sonoma 14.5
Steps to Reproduce:
1. Open a Git repository.
2. Go to the source control view.
3. Click on a commit in the Incoming/Outgoing section.
4. A horizontal scroll bar is shown at the bottom, but scrolling has no effect.
https://github.com/user-attachments/assets/d65726ef-a9cd-45bf-9fdc-7f5bc43b12fa
| bug,multi-diff-editor | low | Critical |
2,463,827,701 | ollama | Llama 3.1 70B high-quality HQQ quantized model - 99%+ quality of fp16 | I'm not really sure if that's possible but adding that to ollama could really impact the performance on 4-bit quant option:
99%+ in all benchmarks in lm-eval relative performance to FP16 and similar inference speed to fp16
url:
https://huggingface.co/mobiuslabsgmbh/Llama-3.1-70b-instruct_4bitgs64_hqq
<img width="604" alt="Screenshot 2024-08-13 at 19 03 57" src="https://github.com/user-attachments/assets/64cd0427-b7c7-4fb8-b846-15f172669248">
also this:
https://huggingface.co/ModelCloud/Meta-Llama-3.1-70B-Instruct-gptq-4bit
<img width="597" alt="Screenshot 2024-08-13 at 19 07 18" src="https://github.com/user-attachments/assets/c3518ffe-323d-42f0-9162-d188179797fb">
| model request | low | Major |
2,463,836,549 | TypeScript | `importModuleSpecifierPreference: "non-relative"` should use self-name package imports | ### 🔎 Search Terms
- relative imports
- workspaces
- monorepo
- subpath export
### 🕗 Version & Regression Information
- This is the behavior in every version I tried, and I reviewed the FAQ for entries about auto imports and subpath exports.
### ⏯ Playground Link
_No response_
### 💻 Code
Full reduced test case: https://github.com/OliverJAsh/typescript-auto-imports-exports
Contents inlined below. TLDR:
- Two workspaces, `packages/a` and `packages/b`.
- `packages/b` depends on `packages/a`.
**Root files**:
`tsconfig.json`:
```json
{
"compilerOptions": {
"strict": true,
"noEmit": true,
"target": "ESNext",
"module": "Node16",
"moduleResolution": "Node16"
}
}
```
`package.json`:
```json
{
"private": true,
"dependencies": {
"typescript": "^5.5.4"
},
"workspaces": [
"packages/a",
"packages/b"
],
"packageManager": "yarn@4.4.0"
}
```
**Package `a`**:
`packages/a/package.json`:
```json
{
"name": "a",
"private": true,
"exports": {
"./test": "./module.ts"
}
}
```
`packages/a/module.ts`:
```ts
export const a = 1;
```
`packages/a/other-module.ts`:
```ts
// Try to import this
// Auto import uses a relative path here: `./module` ❌
a;
```
**Package `b`**:
`packages/b/package.json`:
```json
{
"name": "b",
"private": true,
"dependencies": {
"a": "workspace:^"
}
}
```
`packages/b/module.ts`:
```ts
// Try to import this
// Auto import works correctly here: `a/test` ✅
a;
```
### 🙁 Actual behavior
- The auto import suggestion in `packages/b/other-module.ts` uses the subpath export defined in `packages/a/package.json`. The suggested import path is `a/test`. ✅
- The auto import suggestion in `packages/a/other-module.ts` does not use the subpath export defined in `packages/a/package.json`. Instead it uses a relative import. The suggested import path is `./module`.
It seems that TypeScript is not using the subpath export information for self-referencing imports.
### 🙂 Expected behavior
In both cases I would expect the subpath export to be used (rather than relative imports), otherwise you can end up with some verbose relative paths in the case of projects with deeply nested folders.
I would expect TypeScript to only use a relative import if a subpath export is not available.
### Additional information about the issue
_No response_ | Suggestion,Awaiting More Feedback | low | Minor |
2,463,863,262 | godot | Overlapping collision reports are non-deterministic when clicked despite sorting. | ### Tested versions
- Reproducible in: 4.3.rc3, 4.2.2.stable.
### System information
Windows 10 - Godot v4.3.rc3 - Vulkan (Forward+)
### Issue description
Despite setting both `set_physics_object_picking_sort` and `set_physics_object_picking_first_only` as `true`, input events triggered when clicking an area with overlapped collision shapes produces a seemingly random picked shape.
Changing the node tree order or the z-index setting has no apparent effect on the outcome.
### Steps to reproduce
As illustrated by the provided MRP, create two CollisionArea2D regions as children of an Area2D node. Assign any shape to both CollisionAreas, and place them so that they partially overlap. For the sake of telling them apart, the second is colored pink. Attach the following script to the Area2D, and then connect the input_event signal to the _on_input_event function.
```gdscript
extends Area2D
func _ready():
get_viewport().set_physics_object_picking_sort(true)
get_viewport().set_physics_object_picking_first_only(true)
func _on_input_event(viewport, event, shape_idx):
if event is InputEventMouseButton and event.pressed and event.button_index == MOUSE_BUTTON_LEFT:
var shape_owner = shape_owner_get_owner(shape_find_owner(shape_idx))
print("Picking '%s'" % [shape_owner.name])
```
**Important: Turn on "Visible Collision Shapes" in the Debug menu to see the shapes when running the MRP.**
Clicking inside either the blue or pink CollisionShape2D regions alone works as expected. However, when clicking in the space where they overlap, the debug output in the provided GDScript shows that the `shape_idx` passed to the `_on_input_event` function can be either shape, and which shape it is changes with each click.
As both 'sort' and 'pick first' are enabled, it's expected that the "top" pink shape would be the only one sent to the `_on_input_event` function when the overlapped area is clicked.
### Minimal reproduction project (MRP)
[CollisionPickOrdering.zip](https://github.com/user-attachments/files/16603097/CollisionPickOrdering.zip) | discussion,documentation,topic:physics,needs testing,topic:2d | low | Critical |
2,463,883,301 | pytorch | torch._scaled_mm row-wise hits CUDA invalid memory access when M % 256 != 0 | ### 🐛 Describe the bug
```
(conda_env) lcw@cr1-p548xlarge-19:~$ PYTORCH_NO_CUDA_MEMORY_CACHING=1 compute-sanitizer --print-limit=1 --num-callers-host=10 ipython
========= COMPUTE-SANITIZER
Python 3.10.14 | packaged by conda-forge | (main, Mar 20 2024, 12:45:18) [GCC 12.3.0]
Type 'copyright', 'credits' or 'license' for more information
IPython 8.22.1 -- An enhanced Interactive Python. Type '?' for help.
In [1]: import torch
In [2]: a = torch.randn((8352, 4096), device="cuda", dtype=torch.bfloat16).to(torch.float8_e4m3fn)
In [3]: b = torch.randn((1536, 4096), device="cuda", dtype=torch.bfloat16).to(torch.float8_e4m3fn)
In [4]: scales_a = torch.randn(8352, device="cuda", dtype=torch.float)
In [5]: scales_b = torch.randn(1536, device="cuda", dtype=torch.float)
In [6]: torch._scaled_mm(a, b.t(), scale_a=scales_a[:,None], scale_b=scales_b[None,:], out_dtype=torch.bfloat16, use_fast_accum=True)
Out[6]: ========= Invalid __global__ read of size 4 bytes
========= at void cutlass::device_kernel<cutlass::gemm::kernel::GemmUniversal<cute::tuple<int, int, int>, cutlass::gemm::collective::CollectiveMma<cutlass::gemm::MainloopSm90TmaGmmaWarpSpecialized<(int)6, cute::tuple<cute::C<(int)2>, cute::C<(int)1>, cute::C<(int)1>>, cutlass::gemm::KernelTmaWarpSpecializedPingpongFP8FastAccum>, cute::tuple<cute::C<(int)128>, cute::C<(int)128>, cute::C<(int)128>>, cutlass::float_e4m3_t, cute::tuple<long, cute::C<(int)1>, long>, cutlass::float_e4m3_t, cute::tuple<long, cute::C<(int)1>, long>, cute::TiledMMA<cute::MMA_Atom<cute::SM90_64x128x32_F32E4M3E4M3_SS_TN<(cute::GMMA::ScaleIn)1, (cute::GMMA::ScaleIn)1>>, cute::Layout<cute::tuple<cute::C<(int)1>, cute::C<(int)1>, cute::C<(int)1>>, cute::tuple<cute::C<(int)0>, cute::C<(int)0>, cute::C<(int)0>>>, cute::tuple<cute::Underscore, cute::Underscore, cute::Underscore>>, cute::SM90_TMA_LOAD, cute::ComposedLayout<cute::Swizzle<(int)3, (int)4, (int)3>, cute::smem_ptr_flag_bits<(int)8>, cute::Layout<cute::tuple<cute::C<(int)8>, cute::C<(int)128>>, cute::tuple<cute::C<(int)128>, cute::C<(int)1>>>>, void, cute::identity, cute::SM90_TMA_LOAD_MULTICAST, cute::ComposedLayout<cute::Swizzle<(int)3, (int)4, (int)3>, cute::smem_ptr_flag_bits<(int)8>, cute::Layout<cute::tuple<cute::C<(int)8>, cute::C<(int)128>>, cute::tuple<cute::C<(int)128>, cute::C<(int)1>>>>, void, cute::identity>, cutlass::epilogue::collective::CollectiveEpilogue<cutlass::epilogue::Sm90TmaWarpSpecialized<(int)8, (int)2, (int)16, (bool)1>, cute::tuple<cute::C<(int)128>, cute::C<(int)128>, cute::C<(int)128>>, cute::tuple<cute::C<(int)64>, cute::C<(int)32>>, cutlass::bfloat16_t, cute::tuple<long, cute::C<(int)1>, long>, cutlass::bfloat16_t, cute::tuple<long, cute::C<(int)1>, long>, cutlass::epilogue::fusion::Sm90TreeVisitor<cutlass::epilogue::fusion::Sm90Compute<cutlass::multiplies, cutlass::bfloat16_t, float, (cutlass::FloatRoundStyle)2, void>, cutlass::epilogue::fusion::Sm90ColBroadcast<(int)0, cute::tuple<cute::C<(int)128>, cute::C<(int)128>, cute::C<(int)128>>, float, cute::tuple<cute::C<(int)1>, cute::C<(int)0>, cute::C<(int)0>>, (int)4, (bool)1>, cutlass::epilogue::fusion::Sm90TreeVisitor<cutlass::epilogue::fusion::Sm90Compute<cutlass::multiplies, float, float, (cutlass::FloatRoundStyle)2, void>, cutlass::epilogue::fusion::Sm90RowBroadcast<(int)2, cute::tuple<cute::C<(int)128>, cute::C<(int)128>, cute::C<(int)128>>, float, cute::tuple<cute::C<(int)0>, cute::C<(int)1>, cute::C<(int)0>>, (int)4, (bool)1>, cutlass::epilogue::fusion::Sm90AccFetch>>, cute::SM90_TMA_LOAD, cute::ComposedLayout<cute::Swizzle<(int)2, (int)4, (int)3>, cute::smem_ptr_flag_bits<(int)16>, cute::Layout<cute::tuple<cute::C<(int)8>, cute::C<(int)32>>, cute::tuple<cute::C<(int)32>, cute::C<(int)1>>>>, cute::SM75_U32x4_LDSM_N, cute::SM90_TMA_STORE, cute::ComposedLayout<cute::Swizzle<(int)2, (int)4, (int)3>, cute::smem_ptr_flag_bits<(int)16>, cute::Layout<cute::tuple<cute::C<(int)8>, cute::C<(int)32>>, cute::tuple<cute::C<(int)32>, cute::C<(int)1>>>>, cute::SM90_U32x4_STSM_N>, void, void>>(T1::Params)+0x2a50
========= by thread (320,0,0) in block (1,54,0)
========= Address 0x7fcabf608280 is out of bounds
========= and is 1 bytes after the nearest allocation at 0x7fcabf600000 of size 33408 bytes
========= Saved host backtrace up to driver entry point at kernel launch time
========= Host Frame: [0x332833]
========= in /lib/x86_64-linux-gnu/libcuda.so.1
========= Host Frame: [0x14cb8]
========= in /home/lcw/conda_env/lib/python3.10/site-packages/torch/lib/../../../../libcudart.so.12
========= Host Frame:cudaLaunchKernelExC [0x6c163]
========= in /home/lcw/conda_env/lib/python3.10/site-packages/torch/lib/../../../../libcudart.so.12
========= Host Frame:void (anonymous namespace)::f8f8bf16_rowwise_impl<128, 128, 128, 2, 1, 1, true, true, false, cutlass::float_e4m3_t, float>(at::Tensor, at::Tensor, at::Tensor, at::Tensor, std::optional<at::Tensor>, at::Tensor) [0x272926b]
========= in /home/lcw/conda_env/lib/python3.10/site-packages/torch/lib/libtorch_cuda.so
========= Host Frame:void (anonymous namespace)::dispatch_fp8_rowwise_kernel<cutlass::float_e4m3_t, true, false, float>(at::Tensor, at::Tensor, at::Tensor, at::Tensor, std::optional<at::Tensor>, at::Tensor) [0x2729adc]
========= in /home/lcw/conda_env/lib/python3.10/site-packages/torch/lib/libtorch_cuda.so
========= Host Frame:at::cuda::detail::f8f8bf16_rowwise(at::Tensor, at::Tensor, at::Tensor, at::Tensor, std::optional<at::Tensor>, bool, at::Tensor&) [0x26ec119]
========= in /home/lcw/conda_env/lib/python3.10/site-packages/torch/lib/libtorch_cuda.so
========= Host Frame:at::native::_scaled_mm_out_cuda(at::Tensor const&, at::Tensor const&, at::Tensor const&, at::Tensor const&, std::optional<at::Tensor> const&, std::optional<at::Tensor> const&, std::optional<c10::ScalarType>, bool, at::Tensor&) [0x37819d8]
========= in /home/lcw/conda_env/lib/python3.10/site-packages/torch/lib/libtorch_cuda.so
========= Host Frame:at::native::_scaled_mm_cuda(at::Tensor const&, at::Tensor const&, at::Tensor const&, at::Tensor const&, std::optional<at::Tensor> const&, std::optional<at::Tensor> const&, std::optional<c10::ScalarType>, bool) [0x3782e73]
========= in /home/lcw/conda_env/lib/python3.10/site-packages/torch/lib/libtorch_cuda.so
========= Host Frame:at::(anonymous namespace)::(anonymous namespace)::wrapper_CUDA___scaled_mm(at::Tensor const&, at::Tensor const&, at::Tensor const&, at::Tensor const&, std::optional<at::Tensor> const&, std::optional<at::Tensor> const&, std::optional<c10::ScalarType>, bool) [0x3451f0e]
========= in /home/lcw/conda_env/lib/python3.10/site-packages/torch/lib/libtorch_cuda.so
========= Host Frame:c10::impl::make_boxed_from_unboxed_functor<c10::impl::detail::WrapFunctionIntoFunctor_<c10::CompileTimeFunctionPointer<at::Tensor (at::Tensor const&, at::Tensor const&, at::Tensor const&, at::Tensor const&, std::optional<at::Tensor> const&, std::optional<at::Tensor> const&, std::optional<c10::ScalarType>, bool), &at::(anonymous namespace)::(anonymous namespace)::wrapper_CUDA___scaled_mm>, at::Tensor, c10::guts::typelist::typelist<at::Tensor const&, at::Tensor const&, at::Tensor const&, at::Tensor const&, std::optional<at::Tensor> const&, std::optional<at::Tensor> const&, std::optional<c10::ScalarType>, bool> >, false>::call(c10::OperatorKernel*, c10::OperatorHandle const&, c10::DispatchKeySet, std::vector<c10::IValue, std::allocator<c10::IValue> >*) [0x3598a51]
========= in /home/lcw/conda_env/lib/python3.10/site-packages/torch/lib/libtorch_cuda.so
=========
terminate called after throwing an instance of 'c10::Error'
what(): CUDA error: unspecified launch failure
CUDA kernel errors might be asynchronously reported at some other API call, so the stacktrace below might be incorrect.
For debugging consider passing CUDA_LAUNCH_BLOCKING=1
Compile with `TORCH_USE_CUDA_DSA` to enable device-side assertions.
Exception raised from c10_cuda_check_implementation at /opt/conda/conda-bld/pytorch_1721288503779/work/c10/cuda/CUDAException.cpp:43 (most recent call first):
frame #0: c10::Error::Error(c10::SourceLocation, std::string) + 0x96 (0x7fcdd038c7b6 in /home/lcw/conda_env/lib/python3.10/site-packages/torch/lib/libc10.so)
frame #1: c10::detail::torchCheckFail(char const*, char const*, unsigned int, std::string const&) + 0x64 (0x7fcdd033a504 in /home/lcw/conda_env/lib/python3.10/site-packages/torch/lib/libc10.so)
frame #2: ...
========= Error: process didn't terminate successfully
========= Target application returned an error
========= ERROR SUMMARY: 644 errors
========= ERROR SUMMARY: 643 errors were not printed. Use --print-limit option to adjust the number of printed errors
```
The address on which the IMA occurs is the one of the `scale_a` tensor, and looking at all the attempted reads it seems the kernel is reading up to the next 256 element boundary of that tensor. Indeed, when rounding M up to the next multiple of 256 the issue doesn't seem to occur.
By default the issue appears non-deterministically in PyTorch because the caching allocator usually provides larger allocations than the tensor needs, thus out-of-bound accesses will not trigger an IMA. By disabling the caching allocator with `PYTORCH_NO_CUDA_MEMORY_CACHING=1` the repro becomes more reliable.
~If I recompile that kernel and pass the `-lineinfo` flag to nvcc the issue seems to disappear.~
I found a reference in PyTorch that could hint to this bug being hit in the past: https://github.com/pytorch/pytorch/blob/d2e9a8bf6d2e603f351051f46cb7e45eb3ceb007/torch/_inductor/codegen/cuda/gemm_template.py#L548-L551
### Versions
```
PyTorch version: 2.5.0.dev20240718
Is debug build: False
CUDA used to build PyTorch: 12.1
ROCM used to build PyTorch: N/A
OS: Ubuntu 20.04.6 LTS (x86_64)
GCC version: (Ubuntu 9.4.0-1ubuntu1~20.04.2) 9.4.0
Clang version: Could not collect
CMake version: version 3.29.5
Libc version: glibc-2.31
Python version: 3.10.14 | packaged by conda-forge | (main, Mar 20 2024, 12:45:18) [GCC 12.3.0] (64-bit runtime)
Python platform: Linux-5.15.0-1064-aws-x86_64-with-glibc2.31
Is CUDA available: True
CUDA runtime version: 12.1.105
CUDA_MODULE_LOADING set to: LAZY
GPU models and configuration:
GPU 0: NVIDIA H100 80GB HBM3
GPU 1: NVIDIA H100 80GB HBM3
GPU 2: NVIDIA H100 80GB HBM3
GPU 3: NVIDIA H100 80GB HBM3
GPU 4: NVIDIA H100 80GB HBM3
GPU 5: NVIDIA H100 80GB HBM3
GPU 6: NVIDIA H100 80GB HBM3
GPU 7: NVIDIA H100 80GB HBM3
Nvidia driver version: 535.183.01
cuDNN version: Could not collect
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
Byte Order: Little Endian
Address sizes: 48 bits physical, 48 bits virtual
CPU(s): 192
On-line CPU(s) list: 0-191
Thread(s) per core: 2
Core(s) per socket: 48
Socket(s): 2
NUMA node(s): 2
Vendor ID: AuthenticAMD
CPU family: 25
Model: 1
Model name: AMD EPYC 7R13 Processor
Stepping: 1
CPU MHz: 2650.000
BogoMIPS: 5300.00
Hypervisor vendor: KVM
Virtualization type: full
L1d cache: 3 MiB
L1i cache: 3 MiB
L2 cache: 48 MiB
L3 cache: 384 MiB
NUMA node0 CPU(s): 0-47,96-143
NUMA node1 CPU(s): 48-95,144-191
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 Retbleed: Not affected
Vulnerability Spec rstack overflow: Mitigation; safe RET, no microcode
Vulnerability Spec store bypass: Mitigation; Speculative Store Bypass disabled via prctl and seccomp
Vulnerability Spectre v1: Mitigation; usercopy/swapgs barriers and __user pointer sanitization
Vulnerability Spectre v2: Mitigation; Retpolines; IBPB conditional; IBRS_FW; STIBP always-on; RSB filling; PBRSB-eIBRS Not affected; BHI Not affected
Vulnerability Srbds: Not affected
Vulnerability Tsx async abort: Not affected
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 constant_tsc rep_good nopl nonstop_tsc cpuid extd_apicid aperfmperf tsc_known_freq pni pclmulqdq monitor ssse3 fma cx16 pcid sse4_1 sse4_2 x2apic movbe popcnt aes xsave avx f16c rdrand hypervisor lahf_lm cmp_legacy cr8_legacy abm sse4a misalignsse 3dnowprefetch topoext perfctr_core invpcid_single ssbd ibrs ibpb stibp vmmcall fsgsbase bmi1 avx2 smep bmi2 invpcid rdseed adx smap clflushopt clwb sha_ni xsaveopt xsavec xgetbv1 clzero xsaveerptr rdpru wbnoinvd arat npt nrip_save vaes vpclmulqdq rdpid
Versions of relevant libraries:
[pip3] flake8==7.0.0
[pip3] lovely-numpy==0.2.11
[pip3] mypy==1.10.0
[pip3] mypy-extensions==1.0.0
[pip3] numpy==1.24.4
[pip3] torch==2.5.0.dev20240718
[pip3] torchmetrics==0.10.3
[pip3] torchvision==0.20.0.dev20240718
[pip3] triton==3.0.0
[conda] Could not collect
```
cc @ezyang @gchanan @zou3519 @kadeng @msaroufim @yanbing-j @vkuzo @albanD @penguinwu | high priority,module: crash,triaged,module: float8 | low | Critical |
2,464,016,758 | react-native | ScrollView doesn't scroll when overflows the parent view | ### Description
If we have a parent view, and render Touch like elements, (for eg. - Button, Pressable, TouchableOpacity) outside the Parent View with overflow:'visible' the Touch works fine.
But if I render a ScrollView outside the parent view, it doesn't scroll.
### Steps to reproduce
https://snack.expo.dev/@rtk_jain/scrollview-does-not-work-when-overflowing
### React Native Version
0.74.3
### Affected Platforms
Runtime - Android, Runtime - iOS, Runtime - Web
### Output of `npx react-native info`
```text
System:
OS: macOS 14.4
CPU: (12) arm64 Apple M3 Pro
Memory: 82.45 MB / 18.00 GB
Shell:
version: "5.9"
path: /bin/zsh
Binaries:
Node:
version: 20.15.1
path: ~/.nvm/versions/node/v20.15.1/bin/node
Yarn:
version: 3.6.4
path: ~/.nvm/versions/node/v20.15.1/bin/yarn
npm:
version: 10.7.0
path: ~/.nvm/versions/node/v20.15.1/bin/npm
Watchman:
version: 2024.07.15.00
path: /opt/homebrew/bin/watchman
Managers:
CocoaPods:
version: 1.15.2
path: /opt/homebrew/bin/pod
SDKs:
iOS SDK:
Platforms:
- DriverKit 23.5
- iOS 17.5
- macOS 14.5
- tvOS 17.5
- visionOS 1.2
- watchOS 10.5
Android SDK:
API Levels:
- "29"
- "30"
- "33"
- "34"
Build Tools:
- 29.0.2
- 30.0.3
- 33.0.0
- 34.0.0
- 35.0.0
System Images:
- android-29 | ARM 64 v8a
- android-29 | Intel x86 Atom
- android-29 | Intel x86_64 Atom
- android-29 | Google APIs ARM 64 v8a
- android-29 | Google APIs Intel x86 Atom
- android-29 | Google APIs Intel x86_64 Atom
- android-29 | Google Play ARM 64 v8a
- android-29 | Google Play Intel x86 Atom
- android-29 | Google Play Intel x86_64 Atom
Android NDK: Not Found
IDEs:
Android Studio: 2024.1 AI-241.18034.62.2411.12071903
Xcode:
version: 15.4/15F31d
path: /usr/bin/xcodebuild
Languages:
Java:
version: 17.0.10
path: /usr/bin/javac
Ruby:
version: 2.6.10
path: /usr/bin/ruby
npmPackages:
"@react-native-community/cli": Not Found
react:
installed: 18.2.0
wanted: 18.2.0
react-native:
installed: 0.74.3
wanted: 0.74.3
react-native-macos: Not Found
npmGlobalPackages:
"*react-native*": Not Found
Android:
hermesEnabled: true
newArchEnabled: false
iOS:
hermesEnabled: true
newArchEnabled: false
```
### Stacktrace or Logs
```text
No Stack Trace
```
### Reproducer
https://snack.expo.dev/@rtk_jain/scrollview-does-not-work-when-overflowing
### Screenshots and Videos
_No response_ | Issue: Author Provided Repro,Component: ScrollView,Newer Patch Available | low | Major |
2,464,033,779 | vscode | Forward/Back buttons on mouse do not work in fullscreen/maximized window on macOS Sonoma | Type: <b>Bug</b>
I'm using a Logi MX Vertical mouse, configured via Logi Options+ to use the buttons on the side to go Back/Forward.
1. Open any workspace and browse several files.
2. Maximize the window (in macOS this means that it goes fullscreen and gets its own virtual desktop).
3. Try to go back to the previous file you were browsing using the button configured with the Back action (or forward with the button configured for the Forward action).
Expected behavior: VS Code goes back/forward through the locations I've viewed, just like it does in "windowed" (e.g. non-maximized) mode.
On a (probably) related note: I experience the same in Microsoft Edge. The Back/Forward actions work when it is "windowed", not when the browser is full screen. Other apps do work fine in maximized state though (like Discord for instance).
VS Code version: Code 1.91.1 (f1e16e1e6214d7c44d078b1f0607b2388f29d729, 2024-07-09T22:07:46.768Z)
OS version: Darwin arm64 23.5.0
Modes:
<details>
<summary>System Info</summary>
|Item|Value|
|---|---|
|CPUs|Apple M3 (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|
|Load (avg)|1, 2, 2|
|Memory (System)|24.00GB (0.14GB free)|
|Process Argv|--crash-reporter-id 72996b1e-b38b-40ad-b437-9765ab9f6d0f --crash-reporter-id 72996b1e-b38b-40ad-b437-9765ab9f6d0f|
|Screen Reader|no|
|VM|0%|
</details><details><summary>Extensions (22)</summary>
Extension|Author (truncated)|Version
---|---|---
cpm-cmake-manager|arn|0.0.4
vscode-eslint|dba|3.0.10
gitlens|eam|15.2.3
prettier-vscode|esb|10.4.0
copilot|Git|1.221.0
copilot-chat|Git|0.17.1
vscode-github-actions|git|0.26.3
vscode-pull-request-github|Git|0.92.0
gitlab-workflow|Git|5.4.0
vsc-nvm|hen|0.0.3
cmake-language-support-vscode|jos|0.0.9
cortex-debug|mar|1.12.1
debug-tracker-vscode|mcu|0.0.15
memory-view|mcu|0.0.25
peripheral-viewer|mcu|1.4.6
rtos-views|mcu|0.0.7
vscode-dotnet-runtime|ms-|2.1.1
cmake-tools|ms-|1.18.44
cpptools|ms-|1.21.6
vscode-embedded-tools|ms-|0.7.0
vscode-jest|Ort|6.2.5
cmake|twx|0.0.17
</details><details>
<summary>A/B Experiments</summary>
```
vsliv368:30146709
vspor879:30202332
vspor708:30202333
vspor363:30204092
vswsl492:30256859
vscod805:30301674
binariesv615:30325510
vsaa593cf:30376535
py29gd2263:31024239
c4g48928:30535728
azure-dev_surveyone:30548225
2i9eh265:30646982
962ge761:30959799
pythongtdpath:30769146
welcomedialog:30910333
pythonnoceb:30805159
asynctok:30898717
pythonregdiag2:30936856
pythonmypyd1:30879173
h48ei257:31000450
pythontbext0:30879054
accentitlementst:30995554
dsvsc016:30899300
dsvsc017:30899301
dsvsc018:30899302
cppperfnew:31000557
dsvsc020:30976470
pythonait:31006305
dsvsc021:30996838
724cj586:31013169
pythoncenvpt:31062603
a69g1124:31058053
dvdeprecation:31068756
dwnewjupytercf:31046870
impr_priority:31102340
refactort:31108082
pythonrstrctxt:31112756
wkspc-onlycs-t:31111718
```
</details>
<!-- generated by issue reporter --> | bug,upstream,macos,chromium | low | Critical |
2,464,040,976 | flutter | Material UI: Visual bug with decorated TextFields and label animations | ### Steps to reproduce
1. Create a TextInput widget with an `OutlineInputBorder` that has a circular border with a high radius, and a non-null `label`
2. Click on the TextInput
### Expected results
The label animates to the corner without interfering with the outline border
### Actual results
During the label animation the outline border appears straight instead of rounded during the duration of the animation. Better explained in the GIF that I've attached, and best reproduced with slow animations.
### Code sample
<details open><summary>Code sample</summary>
```dart
import 'package:flutter/material.dart';
void main() {
runApp(const MyApp());
}
class MyApp extends StatelessWidget {
const MyApp({super.key});
@override
Widget build(context) {
return MaterialApp(
title: "Flutter Demo",
home: Scaffold(
body: Container(
padding: const EdgeInsets.all(20),
width: 300,
child: TextField(
decoration: InputDecoration(
border: OutlineInputBorder(
borderRadius: BorderRadius.circular(50),
),
label: const Text("Enter text"),
),
),
)),
);
}
}
```
</details>
### Screenshots or Video
<details open>
<summary>Screenshots / Video demonstration</summary>
</details>
### Logs
<details open><summary>Logs</summary>
</details>
### Flutter Doctor output
<details open><summary>Doctor output</summary>
```console
! Warning: `dart` on your path resolves to C:\Users\Ado\fvm\versions\stable\bin\dart, which is not inside your current Flutter SDK checkout at C:\Users\Ado\fvm\default.
Consider adding C:\Users\Ado\fvm\default\bin to the front of your path.
• Upstream repository https://github.com/flutter/flutter.git
• Framework revision b0850beeb2 (4 weeks ago), 2024-07-16 21:43:41 -0700
• Engine revision 235db911ba
• Dart version 3.4.4
• DevTools version 2.34.3
• If those were intentional, you can disregard the above warnings; however it is recommended to use "git" directly to perform update checks and upgrades.
[√] Windows Version (Installed version of Windows is version 10 or higher)
[√] Android toolchain - develop for Android devices (Android SDK version 35.0.0)
• Android SDK at C:\Users\Ado\AppData\Local\Android\sdk
• Platform android-35, build-tools 35.0.0
• Java binary at: C:\Users\Ado\AppData\Local\Programs\Android Studio\jbr\bin\java
• Java version OpenJDK Runtime Environment (build 17.0.11+0--11852314)
• All Android licenses accepted.
[√] Chrome - develop for the web
• Chrome at C:\Program Files\Google\Chrome\Application\chrome.exe
[√] Visual Studio - develop Windows apps (Visual Studio Community 2022 17.10.5)
• Visual Studio at C:\Program Files\Microsoft Visual Studio\2022\Community
• Visual Studio Community 2022 version 17.10.35122.118
• Windows 10 SDK version 10.0.22621.0
[√] Android Studio (version 2024.1)
• Android Studio at C:\Users\Ado\AppData\Local\Programs\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 17.0.11+0--11852314)
[√] IntelliJ IDEA Community Edition (version 2024.1)
• IntelliJ at C:\Users\Ado\AppData\Local\Programs\IntelliJ IDEA Community Edition
• Flutter plugin version 80.0.2
• Dart plugin version 241.18808
[√] VS Code (version 1.92.0)
• VS Code at C:\Users\Ado\AppData\Local\Programs\Microsoft VS Code
• Flutter extension can be installed from:
https://marketplace.visualstudio.com/items?itemName=Dart-Code.flutter
[√] Connected device (3 available)
• Windows (desktop) • windows • windows-x64 • Microsoft Windows [Version 10.0.22631.3880]
• Chrome (web) • chrome • web-javascript • Google Chrome 127.0.6533.99
• Edge (web) • edge • web-javascript • Microsoft Edge 127.0.2651.74
[√] Network resources
• All expected network resources are available.
```
</details>
| a: text input,framework,a: animation,f: material design,waiting for PR to land (fixed),a: quality,has reproducible steps,P2,has partial patch,team-text-input,triaged-text-input,found in release: 3.24 | low | Critical |
2,464,063,983 | godot | undefined symbol: AudioDriverScriptProcessor::finish_driver() | ### Tested versions
Reproducible in master
### System information
Any
### Issue description
When compiling web with address sanitizer it does not find the function body because it is missing from the source code
`wasm-ld: error: platform/web/audio_driver_web.web.template_debug.dev.wasm32.nothreads.o: undefined symbol: AudioDriverScriptProcessor::finish_driver()`
### Steps to reproduce
`scons platform=web target=template_debug threads=no dev_build=yes use_asan=yes`
### Minimal reproduction project (MRP)
N/A | bug,platform:web,topic:buildsystem,topic:porting | low | Critical |
2,464,203,301 | godot | MOUSE_MODE_CAPTURED - Remote Desktop (Raw Input Issue) | ### Tested versions
- Reproducable in Godot 4.2.2 Stable
### System information
Windows 10 - Godot 4.2.2 Stable
### Issue description
When editing a game using remote desktop you are unable to use "mouse_mode = MOUSE_MODE_CAPTURED"
All other mouse modes work. I assume this is because that is the only mouse mode that uses raw input for mouse motion and because I am editing remote the mouse input is external.
### Steps to reproduce
use RDP to edit a godot project and set mouse mode to MOUSE_MODE_CAPTURED
[Primordial-main.zip](https://github.com/user-attachments/files/16605207/Primordial-main.zip)
### Minimal reproduction project (MRP)
use RDP to edit a godot project and set mouse mode to MOUSE_MODE_CAPTURED | bug,platform:windows,topic:input | low | Major |
2,464,237,527 | deno | `Deno has panicked` via `task` command and `package.json` starting version `1.45.3` | Facing a crash with `Deno has panicked` when trying to run a script via `deno task dev` targeting even an empty script.
Error details:
```
Platform: macos aarch64
Version: 1.45.5
Args: ["deno", "task", "dev"]
thread 'main' panicked at /Users/runner/.cargo/registry/src/index.crates.io-6f17d22bba15001f/deno_semver-0.5.7/src/lib.rs:275:32:
programming error: cannot use matches with a tag: latest
```
No `deno.lock` file in project root.
`package.json`:
``` json
{
"scripts": {
"dev": "deno run server/router.ts",
}
}
```
`router.ts` file exists and absolutely empty.
Running `deno run server/router.ts` cause no error.
Downgrade Deno to version `1.44.4` helped to avoid an error. Tried other versions:
- [`1.45.4`](https://github.com/denoland/deno/releases/tag/v1.45.4), [`1.45.3`](https://github.com/denoland/deno/releases/tag/v1.45.3) crashes too.
- [`1.45.2`](https://github.com/denoland/deno/releases/tag/v1.45.2) works well | needs info | low | Critical |
2,464,238,483 | pytorch | Number of kernels generated increased after changes to statically_known_multiple_of | ### 🐛 Describe the bug
In https://github.com/pytorch/pytorch/pull/131649, we change the behavior of `statically_known_multiple_of`, which led an increased number of kernels generated in the unbacked symint cases (e.g. https://github.com/pytorch/pytorch/pull/133276).
In other words, it decreases the fusion opportunities. Is there anything we can do to get the fusion opportunities back?
cc @ezyang @chauhang @penguinwu @voznesenskym @EikanWang @jgong5 @Guobing-Chen @XiaobingSuper @zhuhaozhe @blzheng @wenzhe-nrv @jiayisunx @ipiszy @yf225 @chenyang78 @kadeng @muchulee8 @ColinPeppler @amjames @desertfire @jansel
### Error logs
_No response_
### Minified repro
_No response_
### Versions
main | triaged,oncall: pt2,module: dynamic shapes,module: inductor | low | Critical |
2,464,249,658 | go | runtime: SIGSEGV in preemptone (riscv64) | ```
#!watchflakes
default <- goarch == "riscv64" && builder == "linux-riscv64-mengzhuo" && `sigcode=1 addr=0xc0`
```
Original flakes
```
#!watchflakes
default <- pkg == "golang.org/x/tools/internal/imports" && test == "TestModReplace2"
```
Issue created automatically to collect these failures.
Example ([log](https://ci.chromium.org/b/8739701229570308529)):
=== RUN TestModReplace2
SIGSEGV: segmentation violation
PC=0x54520 m=12 sigcode=1 addr=0xc0
goroutine 0 gp=0x3f504421c0 m=12 mp=0x3f50526708 [idle]:
runtime.preemptone(0x3f504421c0?)
/home/swarming/.swarming/w/ir/x/w/goroot/src/runtime/proc.go:6297 +0x38 fp=0x3f5043ff28 sp=0x3f5043ff10 pc=0x54520
runtime.preemptall()
/home/swarming/.swarming/w/ir/x/w/goroot/src/runtime/proc.go:6275 +0x60 fp=0x3f5043ff50 sp=0x3f5043ff28 pc=0x544c0
runtime.forEachPInternal(0x2fa878)
...
a3 0x223abf02 a4 0x3f98bb8000
a5 0x31a7d99 a6 0x29ab75fd
a7 0x1187f0 s2 0x3f5043fed0
s3 0x3f50526708 s4 0x3f50474000
s5 0x3f50241500 s6 0xffffffff
s7 0x4 s8 0x3f50038688
s9 0x3f5043fdc8 s10 0x2fa878
s11 0x3f504421c0 t3 0x2eb2a46908caf
t4 0xffffffffffffffff t5 0x1913e15049b3
t6 0x3f50038408 pc 0x54520
— [watchflakes](https://go.dev/wiki/Watchflakes)
| help wanted,NeedsInvestigation,arch-riscv,Tools,compiler/runtime | low | Critical |
2,464,285,431 | flutter | Tracking for new tokens | As i understand these tokens aren't currently used by any widgets that support these tokens. We can keep a issue tracker to make sure to use new tokens.
_Originally posted by @TahaTesser in https://github.com/flutter/flutter/pull/153385#discussion_r1715905739_
This issue is to keep tracking any newly added tokens for widgets.
* Some widgets use hard-coded defaults because there was no tokens available, and later even if the token is available, the hard-corded defaults cannot be automatically updated by token generator. Therefore, once tokens are updated, we should check whether new tokens should be applied to the according widgets.
* New tokens may also mean features that we haven't supported.
- [ ] [Selected status for menu item](https://m3.material.io/components/menus/specs#dc2e3722-43be-4a95-a09b-b9fba9180401), tokens are available in 5.0.0(https://github.com/flutter/flutter/pull/153385)
- [ ] [Update Material 3 `DatePicker` default size to use updated tokens ](https://github.com/flutter/flutter/issues/153505), tokens are updated in https://github.com/flutter/flutter/pull/120149
CC: @TahaTesser
| framework,f: material design,a: fidelity,c: proposal,P2,team-design,triaged-design | low | Minor |
2,464,289,885 | node | TLS 'secureConnect' event fires twice in case of TLS renegotiation | ### Version
22.6.0
### Platform
```text
Microsoft Windows NT 10.0.22631.0 x64
also reproducible under:
Darwin 23.6.0 Darwin Kernel Version 23.6.0: Mon Jul 29 21:14:30 PDT 2024; root:xnu-10063.141.2~1/RELEASE_ARM64_T6000 arm64
```
### Subsystem
tls
### What steps will reproduce the bug?
Generate the certs and then run the `server.js` and then the `client.js`.
```bash
mkdir certs
cd certs
openssl req -newkey rsa:2048 -nodes -keyout key.pem -x509 -days 365 -out cert.pem -subj "/C=US/ST=State/L=City/O=Organization/OU=Unit/CN=localhost"
openssl req -newkey rsa:2048 -nodes -keyout client_key.pem -out client_req.pem -subj "/C=US/ST=State/L=City/O=Organization/OU=Unit/CN=client"
openssl x509 -req -in client_req.pem -CA cert.pem -CAkey key.pem -CAcreateserial -out client_cert.pem -days 365 -subj "/C=US/ST=State/L=City/O=Organization/OU=Unit/CN=client"
```
```ts
// client.js
const tls = require('tls');
const fs = require('fs');
const tlsSocket = tls.connect({
host: '127.0.0.1',
port: 8443,
servername: 'localhost',
rejectUnauthorized: false,
key: fs.readFileSync('certs/client_key.pem'),
cert: fs.readFileSync('certs/client_cert.pem'),
});
tlsSocket.on('secureConnect', () => {
console.log('secureConnect event fired!');
tlsSocket.write('hi');
});
tlsSocket.on('data', (data) => {
console.log(`Received: ${data.toString().trim()}`);
});
```
```ts
// server.js
const tls = require('tls');
const fs = require('fs');
const options = {
key: fs.readFileSync('certs/key.pem'),
cert: fs.readFileSync('certs/cert.pem'),
requestCert: false,
rejectUnauthorized: false,
secureProtocol: 'TLSv1_2_method', // Force TLS 1.2
};
const server = tls.createServer(options, (socket) => {
console.log(`Secure connection established using ${socket.getProtocol()}`);
socket.on('data', (data) => {
console.log('Received:', data.toString());
});
socket.write('\n_renegotiating\n');
socket.renegotiate({
requestCert: true,
rejectUnauthorized: true
}, (err) => {
if (err) {
console.error('Renegotiation error:', err);
} else {
console.log('Renegotiation successful');
socket.end('\n_renegotiated\n');
}
});
});
server.listen(8443, () => {
console.log('Server listening on port 8443');
});
server.on('tlsClientError', (err) => {
console.error('TLS Client Error:', err);
});
```
### How often does it reproduce? Is there a required condition?
- TLS 1.2.
- server re-negotiates the TLS connections with client certificates.
### What is the expected behavior? Why is that the expected behavior?
`secureConnect` events fires once.
### What do you see instead?
`secureConnect` event fires multiple times.
### Additional information
- This got surfaced when using IIS on Windows Server. Windows Server does use negotiation when using client-certificates.
- When passing a callback to `tls.connect` (which is similar to `secureConnect` this won't surface, since its [using `once()` internally](https://github.com/nodejs/node/blob/123693ccbf97df37f928a8ec3e39b85d5e719a7c/lib/_tls_wrap.js#L1793).
Logs:
```txt
env➜ playwright git:(main) ✗ NODE_DEBUG=tls node client.js
TLS 25844: client _init handle? true
TLS 25844: client initRead handle? true buffered? false
TLS 25844: client _start handle? true connecting? false requestOCSP? false
TLS 25844: client onhandshakedone
TLS 25844: client _finishInit handle? true alpn false servername localhost
TLS 25844: client emit secureConnect. rejectUnauthorized: false, authorizationError: DEPTH_ZERO_SELF_SIGNED_CERT
secureConnect event fired! Error
at TLSSocket.<anonymous> (/Users/maxschmitt/Developer/playwright/client.js:13:47)
at TLSSocket.emit (node:events:520:28)
at TLSSocket.onConnectSecure (node:_tls_wrap:1716:8)
at TLSSocket.emit (node:events:520:28)
at TLSSocket._finishInit (node:_tls_wrap:1078:8)
at ssl.onhandshakedone (node:_tls_wrap:864:12)
Received: _renegotiating
TLS 25844: client onhandshakedone
TLS 25844: client _finishInit handle? true alpn false servername localhost
TLS 25844: client emit secureConnect. rejectUnauthorized: false, authorizationError: DEPTH_ZERO_SELF_SIGNED_CERT
secureConnect event fired! Error
at TLSSocket.<anonymous> (/Users/maxschmitt/Developer/playwright/client.js:13:47)
at TLSSocket.emit (node:events:520:28)
at TLSSocket.onConnectSecure (node:_tls_wrap:1716:8)
at TLSSocket.emit (node:events:520:28)
at TLSSocket._finishInit (node:_tls_wrap:1078:8)
at ssl.onhandshakedone (node:_tls_wrap:864:12)
``` | tls | low | Critical |
2,464,298,472 | pytorch | Adafactor foreach impl performance tracker | ### 🚀 The feature, motivation and pitch
Currently, Adafactor has both foreach and forloop implementations, but the performance of the foreach impl could be significantly improved with the following added foreach ops:
A.
- [ ] `_foreach_mm(xs, ys)`.
This is definitely the most challenging to implement well as it would be the first non pointwise/reduction foreach op. It is also unclear how to horizontally fuse multiple mms with different dimensions. Don't worry, the rest of the list is much more actionable.
```
var_estimates = [
row_var @ col_var
for row_var, col_var in zip(device_row_vars, device_col_vars)
]
# becomes
var_estimates = torch._foreach_mm(device_row_vars, device_col_vars)
```
B.
- [ ] `_foreach_norm(tensors, dim=None, keepdim=False)`
We have a `_foreach_norm` today that reduces to Scalars. We can assume for the purposes of this signature that every tensor in `tensors` can be reduced along `dim`.
```
row_means = [torch.norm(grad, dim=-1, keepdim=True) for grad in device_grads]
...
col_means = [torch.norm(grad, dim=-2, keepdim=True) for grad in device_grads]
# becomes
row_means = torch._foreach_norm(device_grads, dim=-1, keepdim=True]
...
col_means = torch._foreach_norm(device_grads, dim=-2, keepdim=True]
```
C.
- [ ] `_foreach_rsqrt(tensors)`
Self explanatory. This may be the easiest AI from this list.
```
torch._foreach_sqrt_(var_estimates)
torch._foreach_reciprocal_(var_estimates)
# becomes
torch._foreach_rsqrt_(var_estimates)
```
D.
- [ ] `_foreach_lerp(xs: TensorList, ys: TensorList, weight: ScalarList)`
This requires adding a new overload that takes ScalarList and not just Scalar. This would be highest impact to effort value as we'd be going from 9 kernel launches to 3.
```
torch._foreach_mul_(device_row_vars, beta2_ts)
torch._foreach_mul_(row_means, one_minus_beta2_ts)
torch._foreach_add_(device_row_vars, row_means)
...
torch._foreach_mul_(device_col_vars, beta2_ts) # type: ignore[arg-type]
torch._foreach_mul_(col_means, one_minus_beta2_ts)
torch._foreach_add_(device_col_vars, col_means) # type: ignore[arg-type]
...
torch._foreach_mul_(device_variances, beta2_ts)
torch._foreach_mul_(grads_squared, one_minus_beta2_ts)
torch._foreach_add_(device_variances, grads_squared)
...
# becomes
torch._foreach_lerp_(device_row_vars, row_means, one_minus_beta2_ts)
...
torch._foreach_lerp_(device_col_vars, col_means, one_minus_beta2_ts)
...
torch._foreach_lerp_(device_variances, grads_squared, one_minus_beta2_ts)
```
E.
- [ ] `_foreach_mean(tensors, dim=None, keepdim=False)`
Similar as to B above with foreach_norm, but would require writing a new op (versus just adding a schema).
```
row_var_means = [row_var.mean(dim=-2, keepdim=True) for row_var in device_row_vars]
# becomes
row_var_means = torch._foreach_mean(device_row_vars, dim=-2, keepdim=True)
```
F.
- [ ] `_foreach_add(xs: TensorList, ys: TensorList, alpha: ScalarList)`
Similar to D, where we wish alphas could be ScalarList instead of just Scalar. I think @ad8e mentioned wanting this in another issue.
```
torch._foreach_mul_(updates, alphas)
torch._foreach_add_(device_params, updates)
# becomes
torch._foreach_add_(device_params, updates, alphas)
```
### Alternatives
Let foreach Adafactor be slow.
Figure out how to autogenerate foreach kernels.
### Additional context
_No response_
cc @msaroufim @vincentqb @jbschlosser @albanD @crcrpar @mcarilli | module: performance,module: optimizer,triaged,actionable,module: mta | low | Major |
2,464,324,628 | flutter | Add a `@visibleForTesting` way to override commonly modified template values in apps created by tests (such as AGP version) | We have a lot of integration tests with hardcoded versions of files that get output from `flutter create` or `flutter create <template>`.
Ex (but there are more):
https://github.com/flutter/flutter/blob/master/packages/flutter_tools/test/integration.shard/test_data/deferred_components_project.dart
https://github.com/flutter/flutter/blob/master/packages/flutter_tools/test/integration.shard/test_data/plugin_project.dart
https://github.com/flutter/flutter/blob/master/dev/devicelab/lib/framework/dependency_smoke_test_task_definition.dart
These test won't accurately test the state of our current templates if the templates change. Perhaps we could refactor the flutter tool to expose something like [`_overwriteFromTemplate`](https://github.com/flutter/flutter/blob/87abed2b23ea3c71855eafb3e616da8121a6ea27/packages/flutter_tools/lib/src/project.dart#L787) at a `@visibleForTesting` level for the purposes of integration tests? So that we aren't relying on the specific text content of the gradle build files, but rather just on the versions that we are intending to overwrite.
This functionality is not a feature to lower the maintenance effort it is a feature that will increase the fidelity of our testing that ensures a broad range of AGP/Gradle/Kotlin values continue to work and not regress. | c: new feature,c: proposal,P2,team-android,triaged-android,fyi-infra | low | Minor |
2,464,333,591 | react | [DevTools Bug]: Cannot view source with remote sourcemap containing absolute `sources` | ### Website or app
www.airbnb.com
### Repro steps
1. Visit www.airbnb.com
2. Use component inspector to inspect a React component
3. Attempt to jump to source and observe that it fails
You won't be able to repro this since the sourcemaps aren't publicly accessible, but hopefully my issue description below explains the matter clearly:
Our sourcemaps contain no `sourceRoot`, but the `sources` are absolute paths (e.g `/foo/bar/baz/main.js`). The sourcemaps are uploaded to a domain `sourcemaps.d.musta.ch` and our minified JS files contain `sourceMappingURL=https://sourcemaps.d.musta.ch/foo/bar/baz.js.map` comments pointing to them.
Per the [spec](https://sourcemaps.info/spec.html#h.75yo6yoyk7x5):
> Resolving Sources
If the sources are not absolute URLs after prepending of the “sourceRoot”, the sources are resolved relative to the SourceMap (like resolving script src in a html document).
Chrome follows the spec. `/foo/bar/baz/main.js` is an absolute *filesystem path*, but it is not an absolute `URL` - it would need to be something like `file:///foo/bar/baz/main.js` to be an absolute URL. Therefore, Chrome resolves the path relative to the sourcemap, resulting in `https://sourcemaps.d.musta.ch/foo/bar/baz/main.js`. This is the path that shows up in the Sources tab.
However, the React code here does not follow the spec:
https://github.com/facebook/react/blob/8e60bacd08215bd23f0bf05dde407cd133885aa1/packages/react-devtools-shared/src/symbolicateSource.js#L101
As a result, the sourceURL remains `/foo/bar/baz/main.js`. The "View Source" functionality is broken since that doesn't point to a valid path.
### How often does this bug happen?
Every time
### DevTools package (automated)
_No response_
### DevTools version (automated)
_No response_
### Error message (automated)
_No response_
### Error call stack (automated)
_No response_
### Error component stack (automated)
_No response_
### GitHub query string (automated)
_No response_ | Type: Bug,Status: Unconfirmed,Component: Developer Tools | low | Critical |
2,464,373,781 | TypeScript | Design Meeting Notes, 8/13/2024 |
# Ordering Parameter Properties and Class Fields
https://github.com/microsoft/TypeScript/issues/45995
* When we adjusted our class field emit (with `useDefineForClassFields`), we also adjusted the relative ordering of class fields and parameter properties.
* Under JS, class fields run before the body of the constructor.
* Under TS, previously, class fields ran *after* parameter properties, but before the body of the constructor.
* Under `useDefineForClassFields` we error on any access to parameter properties, but otherwise it's fine.
* Should we adjust the ordering to be consistent?
* `useDefineForClassFields` was introduced as a legacy behavior to avoid breaks, why break people?
* Could deprecate setting it to false.
* We could run a PR where it always errors, see what breaks.
* Is there an argument for making things more spec-compliant over time?
* Is there something clever we could do with emit?
* Witnessable side-effects.
* The tough part is that most codebases that would be affected by running on GitHub won't be uncovered. Typically these are more mature codebases.
* Could always do a codemod. We typically rely on quick fixes here.
```ts
// Before
class A {
x = 1;
constructor(public y: number) {
console.log(this.y);
}
}
```
```ts
// After
class A {
declare x;
constructor(public y: number) {
this.x = 1;
console.log(this.y);
}
}
```
* Some of us feel like it's a good idea to get consistent emit. Picking a date in the future to deprecate and eventually remove is the proposed plan. But need to experiment first.
* Maybe 6.0 deprecation is the plan.
* This has only been available since ES2022 though!
* 6.0 deprecation = 6.5 removal, which is just over 2 years from now.
* Aside: we should investigate parameter properties in ECMAScript.
| Design Notes | low | Critical |
2,464,374,374 | node | Re-order Node.js `src` directory 🥷 | ### What is the problem this feature will solve?
## Hi Team 👋
Lately, I've been delving into the Node.js source code quite extensively.
This has been both to gather ideas for future improvements and to understand how specific features work under the hood.
One thing that came to mind is the current organization of the source files, specifically the C++ files that define the Node.js runtime functions.
## Proposed Improvement
I believe it would be much better if we could organize the files instead of leaving them all in the root of the `src` directory. 🙏
Think of it as the "breaking the monolith" process.
Our goal is to create a well-organized codebase, complete with a clear dependencies graph, while ensuring it remains fully backward-compatible (we are not Python) 🎉
I'd be happy to take on this task, if that sounds like a good idea.
I understand that many people are currently working on features, so I suggest we handle this step by step.
### Mitigation Strategy
We can migrate small groups of related files together, ensuring that the corresponding `h` and `c` files are kept together.
*Before I proceed with showing anything, I'd appreciate knowing your thoughts on this 🤞*
### Side Note
I believe the structure shouldn't be too complex—ideally, no more than two levels deep. This way, we can avoid having files scattered everywhere.
### What is the feature you are proposing to solve the problem?
-
### What alternatives have you considered?
_No response_ | feature request,lib / src | low | Major |
2,464,384,257 | vscode | Esc closes the attach picker and doesn't go back to quick chat | ref https://github.com/microsoft/vscode/pull/225538
Steps to Reproduce:
1. Open quick chat
2. Hit paperclip
3. Hit ESC
4. 🐛 The Quick Chat is not displayed
| bug,quick-chat | low | Minor |
2,464,395,910 | vscode | Allow Shift+Tab to focus on first attachment in Quick Chat | ref https://github.com/microsoft/vscode/pull/225538
Steps to Reproduce:
1. Open Quick Chat
2. Click paperclip
3. pick an item
4. :bug: shift+tab goes somewhere random in the UI (in panel chat it goes to the `x` on the attached item
This is due to tab index. The attachments no longer being on top of the input causes this behavior. We should consider having a Shift+Tab keybinding that goes to the attachment section to maintain similar behavior between Quick Chat and Panel.
As a workaround, you can TAB TAB TAB TAB to it.
cc @joyceerhl | feature-request,quick-chat | low | Critical |
2,464,414,277 | flutter | `pod init` does not work on Xcode projects created using Xcode 16 beta | # Problem
CocoaPods's `pod init` command is broken on projects created using Xcode 16 beta: https://github.com/CocoaPods/CocoaPods/issues/12456
# Work
* [x] If Xcode 16 ships before CocoaPods fixes this issue, add known workarounds to our [add-to-add project setup instructions](https://github.com/flutter/website/blob/a341c79f45ddd3a55542719c1ae0c114add5eef6/src/_includes/docs/add-to-app/ios-project/embed-cocoapods.md?plain=1#L55) (ex: create your iOS project using Xcode 15)
* [x] https://github.com/flutter/flutter/issues/156733
* [ ] When CocoaPods fixes this issue, update the minimum required CocoaPods version in `flutter doctor` and docs
# Steps to reproduce
1. Create a new SwiftUI project using Xcode 16 beta 5
2. Run `pod init` in the created directory
You'll get the following error:
<details>
<summary>Error output...</summary>
````
$ pod init
――― MARKDOWN TEMPLATE ―――――――――――――――――――――――――――――――――――――――――――――――――――――――――――
### Command
```
/Users/loicsharma/homebrew/lib/ruby/gems/3.3.0/bin/pod init
```
### Report
* What did you do?
* What did you expect to happen?
* What happened instead?
### Stack
```
CocoaPods : 1.15.2
Ruby : ruby 3.3.1 (2024-04-23 revision c56cd86388) [arm64-darwin23]
RubyGems : 3.5.9
Host : macOS 14.6.1 (23G93)
Xcode : 16.0 (16A5221g)
Git : git version 2.46.0.76.ge559c4bf1a-goog
Ruby lib dir : /Users/loicsharma/homebrew/Cellar/ruby/3.3.1/lib
Repositories : trunk - CDN - https://cdn.cocoapods.org/
```
### Plugins
```
cocoapods-deintegrate : 1.0.5
cocoapods-plugins : 1.0.0
cocoapods-search : 1.0.1
cocoapods-trunk : 1.6.0
cocoapods-try : 1.2.0
```
### Error
```
RuntimeError - `PBXGroup` attempted to initialize an object with unknown ISA `PBXFileSystemSynchronizedRootGroup` from attributes: `{"isa"=>"PBXFileSystemSynchronizedRootGroup", "path"=>"MyApp", "sourceTree"=>"<group>"}`
If this ISA was generated by Xcode please file an issue: https://github.com/CocoaPods/Xcodeproj/issues/new
/Users/loicsharma/homebrew/lib/ruby/gems/3.3.0/gems/xcodeproj-1.24.0/lib/xcodeproj/project/object.rb:359:in `rescue in object_with_uuid'
/Users/loicsharma/homebrew/lib/ruby/gems/3.3.0/gems/xcodeproj-1.24.0/lib/xcodeproj/project/object.rb:349:in `object_with_uuid'
/Users/loicsharma/homebrew/lib/ruby/gems/3.3.0/gems/xcodeproj-1.24.0/lib/xcodeproj/project/object.rb:300:in `block (2 levels) in configure_with_plist'
/Users/loicsharma/homebrew/lib/ruby/gems/3.3.0/gems/xcodeproj-1.24.0/lib/xcodeproj/project/object.rb:299:in `each'
/Users/loicsharma/homebrew/lib/ruby/gems/3.3.0/gems/xcodeproj-1.24.0/lib/xcodeproj/project/object.rb:299:in `block in configure_with_plist'
/Users/loicsharma/homebrew/lib/ruby/gems/3.3.0/gems/xcodeproj-1.24.0/lib/xcodeproj/project/object.rb:296:in `each'
/Users/loicsharma/homebrew/lib/ruby/gems/3.3.0/gems/xcodeproj-1.24.0/lib/xcodeproj/project/object.rb:296:in `configure_with_plist'
/Users/loicsharma/homebrew/lib/ruby/gems/3.3.0/gems/xcodeproj-1.24.0/lib/xcodeproj/project.rb:272:in `new_from_plist'
/Users/loicsharma/homebrew/lib/ruby/gems/3.3.0/gems/xcodeproj-1.24.0/lib/xcodeproj/project/object.rb:350:in `object_with_uuid'
/Users/loicsharma/homebrew/lib/ruby/gems/3.3.0/gems/xcodeproj-1.24.0/lib/xcodeproj/project/object.rb:290:in `block in configure_with_plist'
/Users/loicsharma/homebrew/lib/ruby/gems/3.3.0/gems/xcodeproj-1.24.0/lib/xcodeproj/project/object.rb:287:in `each'
/Users/loicsharma/homebrew/lib/ruby/gems/3.3.0/gems/xcodeproj-1.24.0/lib/xcodeproj/project/object.rb:287:in `configure_with_plist'
/Users/loicsharma/homebrew/lib/ruby/gems/3.3.0/gems/xcodeproj-1.24.0/lib/xcodeproj/project.rb:272:in `new_from_plist'
/Users/loicsharma/homebrew/lib/ruby/gems/3.3.0/gems/xcodeproj-1.24.0/lib/xcodeproj/project.rb:213:in `initialize_from_file'
/Users/loicsharma/homebrew/lib/ruby/gems/3.3.0/gems/xcodeproj-1.24.0/lib/xcodeproj/project.rb:113:in `open'
/Users/loicsharma/homebrew/lib/ruby/gems/3.3.0/gems/cocoapods-1.15.2/lib/cocoapods/command/init.rb:41:in `validate!'
/Users/loicsharma/homebrew/lib/ruby/gems/3.3.0/gems/claide-1.1.0/lib/claide/command.rb:333:in `run'
/Users/loicsharma/homebrew/lib/ruby/gems/3.3.0/gems/cocoapods-1.15.2/lib/cocoapods/command.rb:52:in `run'
/Users/loicsharma/homebrew/lib/ruby/gems/3.3.0/gems/cocoapods-1.15.2/bin/pod:55:in `<top (required)>'
/Users/loicsharma/homebrew/lib/ruby/gems/3.3.0/bin/pod:25:in `load'
/Users/loicsharma/homebrew/lib/ruby/gems/3.3.0/bin/pod:25:in `<main>'
```
――― TEMPLATE END ――――――――――――――――――――――――――――――――――――――――――――――――――――――――――――――――
[!] Oh no, an error occurred.
Search for existing GitHub issues similar to yours:
https://github.com/CocoaPods/CocoaPods/search?q=%60PBXGroup%60+attempted+to+initialize+an+object+with+unknown+ISA+%60PBXFileSystemSynchronizedRootGroup%60+from+attributes%3A+%60%7B%22isa%22%3D%3E%22PBXFileSystemSynchronizedRootGroup%22%2C+%22path%22%3D%3E%22MyApp%22%2C+%22sourceTree%22%3D%3E%22%3Cgroup%3E%22%7D%60%0AIf+this+ISA+was+generated+by+Xcode+please+file+an+issue%3A+https%3A%2F%2Fgithub.com%2FCocoaPods%2FXcodeproj%2Fissues%2Fnew&type=Issues
If none exists, create a ticket, with the template displayed above, on:
https://github.com/CocoaPods/CocoaPods/issues/new
Be sure to first read the contributing guide for details on how to properly submit a ticket:
https://github.com/CocoaPods/CocoaPods/blob/master/CONTRIBUTING.md
Don't forget to anonymize any private data!
Looking for related issues on cocoapods/cocoapods...
Searching for inspections failed: undefined method `map' for nil
````
</details> | a: existing-apps,P2,team-ios,triaged-ios | low | Critical |
2,464,434,422 | vscode | [html] Relative links don't work with <base> element |
Type: <b>Bug</b>
1. Make a file structure like this
- index.html
- images
- skibidi.jpg
2. Make HTML code like this
```
<head>
<base href="images/">
</head>
<body>
<img src="skibidi.jpg>
</body>
```
When you open the HTML page, the image will load from images/skibidi.jpg
But, when you click on the link within VS Code, it just takes you just to skibidi.jpg instead of images/skibidi.jpg
(keep in mind if you're the one fixing this that you can have a reverse href like ../../)
VS Code version: Code 1.92.1 (eaa41d57266683296de7d118f574d0c2652e1fc4, 2024-08-07T20:16:39.455Z)
OS version: Windows_NT x64 10.0.22631
Modes:
<details>
<summary>System Info</summary>
|Item|Value|
|---|---|
|CPUs|Intel(R) Core(TM) i5-9400 CPU @ 2.90GHz (6 x 2904)|
|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>vulkan: disabled_off<br>webgl: enabled<br>webgl2: enabled<br>webgpu: enabled<br>webnn: disabled_off|
|Load (avg)|undefined|
|Memory (System)|15.93GB (10.27GB free)|
|Process Argv|--crash-reporter-id eadc9fd3-1184-4a7b-9972-faeaaebf8100|
|Screen Reader|no|
|VM|0%|
</details>Extensions: none<details>
<summary>A/B Experiments</summary>
```
vsliv368cf:30146710
vspor879:30202332
vspor708:30202333
vspor363:30204092
vscod805:30301674
binariesv615:30325510
vsaa593:30376534
py29gd2263:31024239
c4g48928:30535728
azure-dev_surveyone:30548225
vscrp:30673768
2i9eh265:30646982
962ge761:30959799
pythongtdpath:30769146
welcomedialogc:30910334
pythonnoceb:30805159
asynctok:30898717
pythonregdiag2:30936856
pythonmypyd1:30879173
h48ei257:31000450
pythontbext0:30879054
accentitlementsc:30995553
dsvsc016:30899300
dsvsc017:30899301
dsvsc018:30899302
cppperfnew:31000557
dsvsc020:30976470
pythonait:31006305
dsvsc021:30996838
jg8ic977:31013176
pythoncenvpt:31062603
a69g1124:31058053
dvdeprecation:31068756
dwnewjupyter:31046869
impr_priority:31102340
refactort:31108082
pythonrstrctxt:31112756
wkspc-onlycs-c:31111717
wkspc-ranged-c:31111712
```
</details>
<!-- generated by issue reporter --> | bug,html | low | Critical |
2,464,467,936 | pytorch | AttributeError: 'NoneType' object has no attribute 'is_failed' | ### 🐛 Describe the bug
When I run a distributed training with multiple GPUs in the same node, I get this error
This happens only when I use multiple GPUs in the same node. Using one GPU per node is working fine.
```
Traceback (most recent call last):
File "/home/3458/pytorch/venv/bin/torchrun", line 8, in <module>
sys.exit(main())
^^^^^^
File "/home/3458/pytorch/venv/lib/python3.11/site-packages/torch/distributed/elastic/multiprocessing/errors/__init__.py", line 348, in wrapper
return f(*args, **kwargs)
^^^^^^^^^^^^^^^^^^
File "/home/3458/pytorch/venv/lib/python3.11/site-packages/torch/distributed/run.py", line 901, in main
run(args)
File "/home/3458/pytorch/venv/lib/python3.11/site-packages/torch/distributed/run.py", line 892, in run
elastic_launch(
File "/home/3458/pytorch/venv/lib/python3.11/site-packages/torch/distributed/launcher/api.py", line 133, in __call__
return launch_agent(self._config, self._entrypoint, list(args))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/3458/pytorch/venv/lib/python3.11/site-packages/torch/distributed/launcher/api.py", line 259, in launch_agent
if result.is_failed():
^^^^^^^^^^^^^^^^
AttributeError: 'NoneType' object has no attribute 'is_failed'
```
Here is my torchrun command (in sbatch)
```
common_torchrun_cmd="torchrun \
--nnodes $NUM_NODES \
--nproc_per_node 2 \
--rdzv_id $RANDOM \
--rdzv_endpoint $MASTER_NODE_IP:$MASTER_PORT \
--rdzv_backend c10d \
cifar10_lightning.py \
--epochs=1 \
--batch-size=$BATCH \
--exp-name=$EXP_NAME \
--num-nodes=$NUM_NODES \
--strategy=$STRATEGY \
--model=$MODEL \
--precision=$PRECISION"
srun $common_torchrun_cmd
```
I use PyTorch Lightning but it has no issues
```
def main():
seed_everything(42) # for reproducibility
model = Model(loss_function=nn.CrossEntropyLoss(), num_classes=10)
logger = CSVLogger(f"logs/{args.exp_name}/", name="csv_metrics")
trainer = Trainer(
max_epochs=args.epochs,
strategy="ddp",
accelerator="gpu",
logger=logger,
enable_progress_bar=True,
num_nodes=args.num_nodes,
log_every_n_steps=1,
enable_model_summary=True,
detect_anomaly=False,
enable_checkpointing=False,
)
trainer.fit(model)
```
### Versions
Environment
```
$ python collect_env.py
Collecting environment information...
PyTorch version: 2.4.0+cu121
Is debug build: False
CUDA used to build PyTorch: 12.1
ROCM used to build PyTorch: N/A
OS: CentOS Linux release 7.8.2003 (Core) (x86_64)
GCC version: (GCC) 4.8.5 20150623 (Red Hat 4.8.5-39)
Clang version: Could not collect
CMake version: version 2.8.12.2
Libc version: glibc-2.17
Python version: 3.11.7 (main, Dec 15 2023, 18:12:31) [GCC 11.2.0] (64-bit runtime)
Python platform: Linux-3.10.0-1127.19.1.el7.x86_64-x86_64-with-glibc2.17
Is CUDA available: True
CUDA runtime version: 12.4.131
CUDA_MODULE_LOADING set to: LAZY
GPU models and configuration: GPU 0: Tesla V100-SXM2-32GB
Nvidia driver version: 550.54.15
cuDNN version: Could not collect
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
Byte Order: Little Endian
CPU(s): 48
On-line CPU(s) list: 0-47
Thread(s) per core: 1
Core(s) per socket: 24
Socket(s): 2
NUMA node(s): 4
Vendor ID: GenuineIntel
CPU family: 6
Model: 85
Model name: Intel(R) Xeon(R) Platinum 8260 CPU @ 2.40GHz
Stepping: 7
CPU MHz: 1000.000
CPU max MHz: 2401.0000
CPU min MHz: 1000.0000
BogoMIPS: 4800.00
Virtualization: VT-x
L1d cache: 32K
L1i cache: 32K
L2 cache: 1024K
L3 cache: 36608K
NUMA node0 CPU(s): 0-3,7,8,12-14,18-20
NUMA node1 CPU(s): 4-6,9-11,15-17,21-23
NUMA node2 CPU(s): 24-27,31-33,37-39,43,44
NUMA node3 CPU(s): 28-30,34-36,40-42,45-47
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 aperfmperf eagerfpu pni pclmulqdq dtes64 monitor ds_cpl vmx smx est tm2 ssse3 sdbg fma cx16 xtpr pdcm pcid dca sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand lahf_lm abm 3dnowprefetch epb cat_l3 cdp_l3 invpcid_single intel_ppin intel_pt ssbd mba ibrs ibpb stibp ibrs_enhanced tpr_shadow vnmi flexpriority ept vpid fsgsbase tsc_adjust bmi1 hle avx2 smep bmi2 erms invpcid rtm cqm mpx rdt_a avx512f avx512dq rdseed adx smap clflushopt clwb avx512cd avx512bw avx512vl xsaveopt xsavec xgetbv1 cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local dtherm ida arat pln pts hwp hwp_act_window hwp_epp hwp_pkg_req pku ospke avx512_vnni md_clear spec_ctrl intel_stibp flush_l1d arch_capabilities
Versions of relevant libraries:
[pip3] numpy==1.25.0
[pip3] pytorch-lightning==2.4.0
[pip3] torch==2.4.0
[pip3] torch-tb-profiler==0.4.3
[pip3] torch-vision==0.1.6.dev0
[pip3] torchmetrics==1.4.0.post0
[pip3] torchvision==0.19.0
[pip3] triton==3.0.0
[conda] Could not collect
```
cc @XilunWu @H-Huang @awgu @kwen2501 @wanchaol @fegin @fduwjj @wz337 @wconstab @d4l3k @c-p-i-o | oncall: distributed,triaged | low | Critical |
2,464,487,888 | pytorch | [Inductor] Remove dead code from triton kernels | ### 🚀 The feature, motivation and pitch
Inductor generates triton code for numels and range trees regardless of whether it's going to be used. Block pointers often don't use this code. For example, see the kernels in the description of https://github.com/pytorch/pytorch/pull/132937.
Numels are generated here: https://github.com/pytorch/pytorch/blob/main/torch/_inductor/codegen/triton.py#L2701
Masks are generated here: https://github.com/pytorch/pytorch/blob/main/torch/_inductor/codegen/triton.py#L2888
This is not a performance issue, as the triton compiler eliminates dead code. However, it does make the code a bit harder to read and debug.
We may want to remove this code if it turns out not to be used later in the kernel. However, this could also increase the complexity of the system. This feature is probably only a good idea if the solution is simple, robust and relatively easy to maintain. One option would be to search the generated code for occurrences of `"xmask"` to tell whether `xmask` needs to be computed.
See more discussion here: https://github.com/pytorch/pytorch/pull/132937#issuecomment-2276616208
### Alternatives
Do nothing, as the code is still valid and will ultimately be ignored by the triton compiler.
### Additional context
To run some tests with block pointers, try the command `TORCH_COMPILE_DEBUG=1 TORCH_LOGS=+inductor python test/inductor/test_torchinductor_strided_blocks.py ` from the root of your `pytorch` clone.
cc @ezyang @chauhang @penguinwu @voznesenskym @EikanWang @jgong5 @Guobing-Chen @XiaobingSuper @zhuhaozhe @blzheng @wenzhe-nrv @jiayisunx @ipiszy @yf225 @chenyang78 @kadeng @muchulee8 @ColinPeppler @amjames @desertfire | triaged,oncall: pt2,module: inductor | low | Critical |
2,464,537,793 | rust | CMake components fails to build on Mac Catalyst | Running:
```console
./x.py build --set=build.sanitizers=true --target=aarch64-apple-ios-macabi
```
Currently fails with:
```console
... snip
running: cd "/rust/build/aarch64-apple-ios-macabi/native/sanitizers/build" && DESTDIR="" "cmake" "--build" "." "--target" "clang_rt.asan_osx_dynamic" "--config" "Release" "--" "-j" "12"
[1/14] Building CXX object lib/asan/CMakeFiles/RTAsan_dynamic.osx.dir/asan_win.cpp.o
clang: warning: overriding '-mmacosx-version-min=10.10' option with '--target=arm64-apple-ios-macabi' [-Woverriding-t-option]
clang: warning: overriding '-mmacosx-version-min=10.10' option with '--target=arm64-apple-ios-macabi' [-Woverriding-t-option]
clang: warning: overriding '-mmacosx-version-min=10.10' option with '--target=arm64-apple-ios-macabi' [-Woverriding-t-option]
clang: warning: argument unused during compilation: '-L/usr/lib' [-Wunused-command-line-argument]
[2/14] Building CXX object lib/asan/CMakeFiles/RTAsan_dynamic.osx.dir/asan_premap_shadow.cpp.o
clang: warning: overriding '-mmacosx-version-min=10.10' option with '--target=arm64-apple-ios-macabi' [-Woverriding-t-option]
clang: warning: overriding '-mmacosx-version-min=10.10' option with '--target=arm64-apple-ios-macabi' [-Woverriding-t-option]
clang: warning: overriding '-mmacosx-version-min=10.10' option with '--target=arm64-apple-ios-macabi' [-Woverriding-t-option]
clang: warning: argument unused during compilation: '-L/usr/lib' [-Wunused-command-line-argument]
[3/14] Building CXX object lib/asan/CMakeFiles/RTAsan_dynamic.osx.dir/asan_malloc_mac.cpp.o
FAILED: lib/asan/CMakeFiles/RTAsan_dynamic.osx.dir/asan_malloc_mac.cpp.o
/usr/bin/clang++ -DASAN_DYNAMIC=1 -I/rust/src/llvm-project/compiler-rt/lib/asan/.. -fPIC --target=arm64-apple-ios-macabi -isysroot /Applications/Xcode.app/Contents/Developer/Platforms/MacOSX.platform/Developer/SDKs/MacOSX.sdk -isystem /usr/include -iframework /System/Library/Frameworks -L/usr/lib -F/System/Library/Frameworks -Wall -O3 -DNDEBUG -std=c++17 -arch arm64 -arch x86_64 -arch x86_64h -stdlib=libc++ -mmacosx-version-min=10.10 -isysroot /Applications/Xcode.app/Contents/Developer/Platforms/MacOSX.platform/Developer/SDKs/MacOSX14.5.sdk -fPIC -fno-builtin -fno-exceptions -funwind-tables -fno-stack-protector -fno-sanitize=safe-stack -fvisibility=hidden -fno-lto -O3 -g -nostdinc++ -fno-rtti -Wno-format -ftls-model=initial-exec -MD -MT lib/asan/CMakeFiles/RTAsan_dynamic.osx.dir/asan_malloc_mac.cpp.o -MF lib/asan/CMakeFiles/RTAsan_dynamic.osx.dir/asan_malloc_mac.cpp.o.d -o lib/asan/CMakeFiles/RTAsan_dynamic.osx.dir/asan_malloc_mac.cpp.o -c /rust/src/llvm-project/compiler-rt/lib/asan/asan_malloc_mac.cpp
clang: warning: overriding '-mmacosx-version-min=10.10' option with '--target=arm64-apple-ios-macabi' [-Woverriding-t-option]
clang: warning: overriding '-mmacosx-version-min=10.10' option with '--target=arm64-apple-ios-macabi' [-Woverriding-t-option]
clang: warning: overriding '-mmacosx-version-min=10.10' option with '--target=arm64-apple-ios-macabi' [-Woverriding-t-option]
clang: warning: argument unused during compilation: '-L/usr/lib' [-Wunused-command-line-argument]
In file included from /rust/src/llvm-project/compiler-rt/lib/asan/asan_malloc_mac.cpp:66:
/rust/src/llvm-project/compiler-rt/lib/asan/../sanitizer_common/sanitizer_malloc_mac.inc:20:10: fatal error: 'CoreFoundation/CFBase.h' file not found
#include <CoreFoundation/CFBase.h>
^~~~~~~~~~~~~~~~~~~~~~~~~
/rust/src/llvm-project/compiler-rt/lib/asan/../sanitizer_common/sanitizer_malloc_mac.inc:20:10: note: did not find header 'CFBase.h' in framework 'CoreFoundation' (loaded from '/System/Library/Frameworks')
1 error generated.
... snip
```
This is preventing us from distributing a sanitizer runtime with rustup on Mac Catalyst, see https://github.com/rust-lang/rust/pull/126450.
Still have to do some more digging, but it seems like the issue is that `iOSSupport` libraries aren't passed to CMake, as is [otherwise](https://github.com/rust-lang/rust/blob/1a2b57b426667c60a82214526be949b9e599c914/compiler/rustc_codegen_ssa/src/back/link.rs#L2158-L2159) [done](https://github.com/rust-lang/cc-rs/blob/eb3390615747fde57f7098797b2acb1aec80f539/src/lib.rs#L2790-L2819) in the ecosystem. In general, it seems like CMake [has poor support for Mac Catalyst](https://gitlab.kitware.com/cmake/cmake/-/issues/20132).
I'll try to fix this, both in the `cmake` crate and perhaps in CMake itself.
@rustbot claim
Linking https://github.com/leetal/ios-cmake and https://gitlab.kitware.com/cmake/cmake/-/blob/master/Modules/Platform/Apple-Clang.cmake to myself for later (might contain some of the relevant CMake configuration needed for this).
@rustbot label O-apple
<!-- TRIAGEBOT_START -->
<!-- TRIAGEBOT_ASSIGN_START -->
<!-- TRIAGEBOT_ASSIGN_DATA_START$${"user":"madsmtm"}$$TRIAGEBOT_ASSIGN_DATA_END -->
<!-- TRIAGEBOT_ASSIGN_END -->
<!-- TRIAGEBOT_END --> | A-LLVM,C-bug,O-apple | low | Critical |
2,464,540,500 | create-react-app | I am so angry i just cant take it | I just cant take it. The way they did away with errors and warnings in the console.
Making the dev experience worse and worse.
And now that CRA is dead how the hell do you get warnings back to the console in Vite???? 😤
Lord Help
| needs triage | low | Critical |
2,464,609,829 | tensorflow | The average should not be computed in L2Pool2d | The [ONNX L2Pool2d](https://github.com/onnx/onnx/blob/main/docs/Operators.md#lppool), [DirectML L2 Pooling Desc](https://docs.microsoft.com/en-us/windows/win32/api/directml/ns-directml-dml_lp_pooling_operator_desc) and [CoreML's l2_pool2d](https://apple.github.io/coremltools/source/coremltools.converters.mil.mil.ops.defs.html#coremltools.converters.mil.mil.ops.defs.iOS15.pool.l2_pool) calculate the l2 pooling by the expression `Y = (X1^2 + X2^2 + ... + Xn^2) ^ (1/2)`, but [TFLite L2_PooL2d kernel implementation](https://source.chromium.org/chromium/chromium/src/+/main:third_party/tflite/src/tensorflow/lite/kernels/internal/optimized/optimized_ops.h;l=3341?q=src%2Ftensorflow%2Flite%2Fkernels%2Finternal%2Foptimized%2Foptimized_ops.h) has the average with the count of sum elements `Y=((X1^2 + X2^2 + ... + Xn^2)/n) ^ (1/2)`, is it an issue of the kernel implementation?
BTW, [the kernel of l2_norm](https://source.chromium.org/chromium/chromium/src/+/main:third_party/tflite/src/tensorflow/lite/kernels/internal/optimized/optimized_ops.h;l=1424?q=L2Normalization&ss=chromium%2Fchromium%2Fsrc) also has no the average.
| type:bug,comp:lite | low | Minor |
2,464,729,095 | flutter | Improvements for animation APIs | I'm creating this issue to cover a couple of things from #24722:
> - [ ] Instead of one `AnimationController`, have one for each type of controller (bounded, unbounded, simulation, repeating, etc).
> - [ ] `ImplicitlyAnimatedWidget` and its subclasses should be named consistently.
<br>
Here are my thoughts:
- If we can improve performance by doing less work each frame, we probably should.
- If we can improve performance _and_ make an API more simple/easy to read, then it's a no-brainer. | framework,a: animation,c: API break,perf: speed,P3,c: tech-debt,team-framework,triaged-framework | low | Major |
2,464,748,721 | tauri | [bug] NixOS Windows build from Linux OpenSSL linking issue | ### Describe the bug
I'm trying to build Windows MSI on NixOS via nix-shell. Here's my `shell.nix`:
```nix
let
pkgs = import <nixpkgs> { };
overrides = (builtins.fromTOML (builtins.readFile ./rust-toolchain.toml));
libraries = with pkgs;[
webkitgtk
gtk3
cairo
gdk-pixbuf
glib
dbus
librsvg
];
nativePkgs = with pkgs; [
pkg-config
];
packages = with pkgs; [
dbus
openssl_3
openssl_3.dev
glib
gtk3
libsoup
webkitgtk
appimagekit
librsvg
clang
lld
llvm
# Replace llvmPackages with llvmPackages_X, where X is the latest LLVM version (at the time of writing, 16)
llvmPackages_12.bintools
rustup
];
in
pkgs.mkShell {
buildInputs = packages;
nativeBuildInputs = nativePkgs;
RUSTC_VERSION = overrides.toolchain.channel;
# https://github.com/rust-lang/rust-bindgen#environment-variables
LIBCLANG_PATH = pkgs.lib.makeLibraryPath [ pkgs.llvmPackages_latest.libclang.lib ];
shellHook =
''
export OPENSSL_DIR=${pkgs.openssl_3.dev}
export LD_LIBRARY_PATH=${pkgs.lib.makeLibraryPath libraries}:$LD_LIBRARY_PATH
export XDG_DATA_DIRS=${pkgs.gsettings-desktop-schemas}/share/gsettings-schemas/${pkgs.gsettings-desktop-schemas.name}:${pkgs.gtk3}/share/gsettings-schemas/${pkgs.gtk3.name}:$XDG_DATA_DIRS
export PKG_CONFIG_PATH=${pkgs.openssl_3.dev}/lib/pkgconfig:$PKG_CONFIG_PATH
export PATH=$PATH:''${CARGO_HOME:-~/.cargo}/bin
export PATH=$PATH:''${RUSTUP_HOME:-~/.rustup}/toolchains/$RUSTC_VERSION-x86_64-unknown-linux-gnu/bin/
'';
# Add precompiled library to rustc search path
RUSTFLAGS = (builtins.map (a: ''-L ${a}/lib'') [
# add libraries here (e.g. pkgs.libvmi)
]);
# Add glibc, clang, glib, and other headers to bindgen search path
BINDGEN_EXTRA_CLANG_ARGS =
# Includes normal include path
(builtins.map (a: ''-I"${a}/include"'') [
# add dev libraries here (e.g. pkgs.libvmi.dev)
pkgs.glibc.dev
])
# Includes with special directory paths
++ [
''-I"${pkgs.llvmPackages_latest.libclang.lib}/lib/clang/${pkgs.llvmPackages_latest.libclang.version}/include"''
''-I"${pkgs.glib.dev}/include/glib-2.0"''
''-I${pkgs.glib.out}/lib/glib-2.0/include/''
];
}
```
This nix shell follows [nixos wiki on rust](https://nixos.wiki/wiki/Rust) and [Tauri's nixos guide](https://tauri.app/v1/guides/getting-started/prerequisites/#1-system-dependencies). And also followed [Tauri's guide to build Window Apps on Linux](https://tauri.app/v1/guides/building/cross-platform#experimental-build-windows-apps-on-linux-and-macos)
When I tried to install:
```bash
🌞 ❌ cargo tauri build --runner cargo-xwin --target x86_64-pc-windows-msvc --verbose
Running [tauri_cli] Command `cargo-xwin build --features custom-protocol --release --target x86_64-pc-windows-msvc`
Compiling openssl-sys v0.9.103
Compiling tauri-runtime-wry v0.14.9
error: failed to run custom build command for `openssl-sys v0.9.103`
Caused by:
process didn't exit successfully: `/home/wpham/learning/tauri/rocks_chest/src-tauri/target/release/build/openssl-sys-1e6744830b035fb9/build-script-main` (exit status: 101)
--- stdout
cargo:rustc-check-cfg=cfg(osslconf, values("OPENSSL_NO_OCB", "OPENSSL_NO_SM4", "OPENSSL_NO_SEED", "OPENSSL_NO_CHACHA", "OPENSSL_NO_CAST", "OPENSSL_NO_IDEA", "OPENSSL_NO_CAMELLIA", "OPENSSL_NO_RC4", "OPENSSL_NO_BF", "OPENSSL_NO_PSK", "OPENSSL_NO_DEPRECATED_3_0", "OPENSSL_NO_SCRYPT", "OPENSSL_NO_SM3", "OPENSSL_NO_RMD160", "OPENSSL_NO_EC2M", "OPENSSL_NO_OCSP", "OPENSSL_NO_CMS", "OPENSSL_NO_COMP", "OPENSSL_NO_SOCK", "OPENSSL_NO_STDIO"))
cargo:rustc-check-cfg=cfg(openssl)
cargo:rustc-check-cfg=cfg(libressl)
cargo:rustc-check-cfg=cfg(boringssl)
cargo:rustc-check-cfg=cfg(libressl250)
cargo:rustc-check-cfg=cfg(libressl251)
cargo:rustc-check-cfg=cfg(libressl252)
cargo:rustc-check-cfg=cfg(libressl261)
cargo:rustc-check-cfg=cfg(libressl270)
cargo:rustc-check-cfg=cfg(libressl271)
cargo:rustc-check-cfg=cfg(libressl273)
cargo:rustc-check-cfg=cfg(libressl280)
cargo:rustc-check-cfg=cfg(libressl281)
cargo:rustc-check-cfg=cfg(libressl291)
cargo:rustc-check-cfg=cfg(libressl310)
cargo:rustc-check-cfg=cfg(libressl321)
cargo:rustc-check-cfg=cfg(libressl332)
cargo:rustc-check-cfg=cfg(libressl340)
cargo:rustc-check-cfg=cfg(libressl350)
cargo:rustc-check-cfg=cfg(libressl360)
cargo:rustc-check-cfg=cfg(libressl361)
cargo:rustc-check-cfg=cfg(libressl370)
cargo:rustc-check-cfg=cfg(libressl380)
cargo:rustc-check-cfg=cfg(libressl381)
cargo:rustc-check-cfg=cfg(libressl382)
cargo:rustc-check-cfg=cfg(libressl390)
cargo:rustc-check-cfg=cfg(libressl400)
cargo:rustc-check-cfg=cfg(ossl101)
cargo:rustc-check-cfg=cfg(ossl102)
cargo:rustc-check-cfg=cfg(ossl102f)
cargo:rustc-check-cfg=cfg(ossl102h)
cargo:rustc-check-cfg=cfg(ossl110)
cargo:rustc-check-cfg=cfg(ossl110f)
cargo:rustc-check-cfg=cfg(ossl110g)
cargo:rustc-check-cfg=cfg(ossl110h)
cargo:rustc-check-cfg=cfg(ossl111)
cargo:rustc-check-cfg=cfg(ossl111b)
cargo:rustc-check-cfg=cfg(ossl111c)
cargo:rustc-check-cfg=cfg(ossl111d)
cargo:rustc-check-cfg=cfg(ossl300)
cargo:rustc-check-cfg=cfg(ossl310)
cargo:rustc-check-cfg=cfg(ossl320)
cargo:rustc-check-cfg=cfg(ossl330)
cargo:rerun-if-env-changed=X86_64_PC_WINDOWS_MSVC_OPENSSL_LIB_DIR
X86_64_PC_WINDOWS_MSVC_OPENSSL_LIB_DIR unset
cargo:rerun-if-env-changed=OPENSSL_LIB_DIR
OPENSSL_LIB_DIR unset
cargo:rerun-if-env-changed=X86_64_PC_WINDOWS_MSVC_OPENSSL_INCLUDE_DIR
X86_64_PC_WINDOWS_MSVC_OPENSSL_INCLUDE_DIR unset
cargo:rerun-if-env-changed=OPENSSL_INCLUDE_DIR
OPENSSL_INCLUDE_DIR unset
cargo:rerun-if-env-changed=X86_64_PC_WINDOWS_MSVC_OPENSSL_DIR
X86_64_PC_WINDOWS_MSVC_OPENSSL_DIR unset
cargo:rerun-if-env-changed=OPENSSL_DIR
OPENSSL_DIR = /nix/store/bvrly5zpaqxydbfnx3dm4i7k8cbkrp32-openssl-3.0.14-dev
cargo:rerun-if-changed=/nix/store/bvrly5zpaqxydbfnx3dm4i7k8cbkrp32-openssl-3.0.14-dev/include/openssl
cargo:rustc-link-search=native=/nix/store/bvrly5zpaqxydbfnx3dm4i7k8cbkrp32-openssl-3.0.14-dev/lib
cargo:include=/nix/store/bvrly5zpaqxydbfnx3dm4i7k8cbkrp32-openssl-3.0.14-dev/include
cargo:rerun-if-changed=build/expando.c
OPT_LEVEL = Some(3)
TARGET = Some(x86_64-pc-windows-msvc)
OUT_DIR = Some(/home/wpham/learning/tauri/rocks_chest/src-tauri/target/x86_64-pc-windows-msvc/release/build/openssl-sys-5ccbb0618efa91c1/out)
HOST = Some(x86_64-unknown-linux-gnu)
cargo:rerun-if-env-changed=VCINSTALLDIR
VCINSTALLDIR = None
cargo:rerun-if-env-changed=CC_x86_64-pc-windows-msvc
CC_x86_64-pc-windows-msvc = None
cargo:rerun-if-env-changed=CC_x86_64_pc_windows_msvc
CC_x86_64_pc_windows_msvc = Some(clang-cl)
cargo:rerun-if-env-changed=CC_KNOWN_WRAPPER_CUSTOM
CC_KNOWN_WRAPPER_CUSTOM = None
RUSTC_WRAPPER = None
cargo:rerun-if-env-changed=CC_ENABLE_DEBUG_OUTPUT
cargo:rerun-if-env-changed=CRATE_CC_NO_DEFAULTS
CRATE_CC_NO_DEFAULTS = None
CARGO_CFG_TARGET_FEATURE = Some(cmpxchg16b,fxsr,sse,sse2,sse3)
DEBUG = Some(false)
cargo:rerun-if-env-changed=CFLAGS_x86_64-pc-windows-msvc
CFLAGS_x86_64-pc-windows-msvc = None
cargo:rerun-if-env-changed=CFLAGS_x86_64_pc_windows_msvc
CFLAGS_x86_64_pc_windows_msvc = Some(--target=x86_64-pc-windows-msvc -Wno-unused-command-line-argument -fuse-ld=lld-link /imsvc/home/wpham/.cache/cargo-xwin/xwin/crt/include /imsvc/home/wpham/.cache/cargo-xwin/xwin/sdk/include/ucrt /imsvc/home/wpham/.cache/cargo-xwin/xwin/sdk/include/um /imsvc/home/wpham/.cache/cargo-xwin/xwin/sdk/include/shared )
version: 3_0_14
cargo:rustc-cfg=osslconf="OPENSSL_NO_SSL3_METHOD"
cargo:conf=OPENSSL_NO_SSL3_METHOD
cargo:rustc-cfg=openssl
cargo:rustc-cfg=ossl300
cargo:rustc-cfg=ossl101
cargo:rustc-cfg=ossl102
cargo:rustc-cfg=ossl102f
cargo:rustc-cfg=ossl102h
cargo:rustc-cfg=ossl110
cargo:rustc-cfg=ossl110f
cargo:rustc-cfg=ossl110g
cargo:rustc-cfg=ossl110h
cargo:rustc-cfg=ossl111
cargo:rustc-cfg=ossl111b
cargo:rustc-cfg=ossl111c
cargo:rustc-cfg=ossl111d
cargo:version_number=300000e0
cargo:rerun-if-env-changed=X86_64_PC_WINDOWS_MSVC_OPENSSL_LIBS
X86_64_PC_WINDOWS_MSVC_OPENSSL_LIBS unset
cargo:rerun-if-env-changed=OPENSSL_LIBS
OPENSSL_LIBS unset
cargo:rerun-if-env-changed=X86_64_PC_WINDOWS_MSVC_OPENSSL_STATIC
X86_64_PC_WINDOWS_MSVC_OPENSSL_STATIC unset
cargo:rerun-if-env-changed=OPENSSL_STATIC
OPENSSL_STATIC unset
--- stderr
thread 'main' panicked at /home/wpham/.cargo/registry/src/index.crates.io-6f17d22bba15001f/openssl-sys-0.9.103/build/main.rs:492:13:
OpenSSL libdir at `["/nix/store/bvrly5zpaqxydbfnx3dm4i7k8cbkrp32-openssl-3.0.14-dev/lib"]` does not contain the required files to either statically or dynamically link OpenSSL
note: run with `RUST_BACKTRACE=1` environment variable to display a backtrace
```
I also tried adding the OPENSSL_'s environments variale directlly instead of relying on OPENSSL_DIR:
```bash
export OPENSSL_DIR=${pkgs.openssl_3.dev}
export OPENSSL_NO_VENDOR=1
export OPENSSL_LIB_DIR=${pkgs.lib.getLib pkgs.openssl_3.dev}/lib
export OPENSSL_INCLUDE_DIR=${pkgs.lib.getLib pkgs.openssl_3.dev}/include
export OPENSSL_LIBS=${pkgs.lib.getLib pkgs.openssl_3.dev}/lib
export OPENSSL_STATIC=1
```
Then getting:
```bash
🌞 ❌ cargo tauri build --runner cargo-xwin --target x86_64-pc-windows-msvc --verbose
Running [tauri_cli] Command `cargo-xwin build --features custom-protocol --release --target x86_64-pc-windows-msvc`
Compiling openssl-sys v0.9.103
Compiling tauri v1.7.1
Compiling openssl v0.10.66
error: could not find native static library `/nix/store/bvrly5zpaqxydbfnx3dm4i7k8cbkrp32-openssl-3.0.14-dev/lib`, perhaps an -L flag is missing?
error: could not compile `openssl-sys` (lib) due to 1 previous error
warning: build failed, waiting for other jobs to finish...
Error [tauri_cli] failed to build app: failed to build app
```
I have also tried a heaps variance of open_ssl.dev, open_ssl.out,etcc...
### Reproduction
```bash
🌞 ⚡ cargo tauri --version
tauri-cli 1.6.0
🌞 ⚡ cargo create-tauri-app --version
4.1.0
🌞 ❌ cargo create-tauri-app
✔ Project name · openssl_bug
✔ Choose which language to use for your frontend · TypeScript / JavaScript - (pnpm, yarn, npm, bun)
✔ Choose your package manager · npm
✔ Choose your UI template · Vanilla
✔ Choose your UI flavor · JavaScript
```
`src-tauri/Cargo.toml`
```toml
[package]
name = "openssl_bug"
...
[dependencies]
tauri = { version = "1", features = ["shell-open"] }
serde = { version = "1", features = ["derive"] }
serde_json = "1"
openssl = "0.10.64"
...
```
`src-tauri/tauri.conf.json`
```json
"identifier": "com.openssl-bug.dev",
```
```bash
rustup target add x86_64-pc-windows-msvc
cargo install --locked cargo-xwin
cargo tauri build --runner cargo-xwin --target x86_64-pc-windows-msvc --verbose
```
### Expected behavior
Windows's MSI should be outputed
### Full `tauri info` output
```text
🌞 ⚡ cargo tauri info
WARNING: no lock files found, defaulting to npm
[✔] Environment
- OS: NixOS 24.11.0 X64
✔ webkit2gtk-4.0: 2.44.2
✔ rsvg2: 2.58.2
✔ rustc: 1.80.0 (051478957 2024-07-21)
✔ cargo: 1.80.0 (376290515 2024-07-16)
✔ rustup: 1.26.0 (1980-01-01)
✔ Rust toolchain: stable-x86_64-unknown-linux-gnu (environment override by RUSTUP_TOOLCHAIN)
- node: 22.4.1
- npm: 10.8.1
[-] Packages
- tauri [RUST]: 1.7.1
- tauri-build [RUST]: 1.5.3
- wry [RUST]: 0.24.10
- tao [RUST]: 0.16.9
- tauri-cli [RUST]: 1.6.0
- @tauri-apps/api : not installed!
- @tauri-apps/cli [NPM]: 1.6.0
[-] App
- build-type: bundle
- CSP: unset
- distDir: ../src
- devPath: ../src
```
### Stack trace
```text
Refer to above
```
### Additional context
_No response_ | type: bug,help wanted,status: needs triage,platform: Nix/NixOS | low | Critical |
2,464,868,971 | deno | Release GitHub Copilot extension for Deno | Deno is a rapidly growing JavaScript/TypeScript runtime with a huge and thriving ecosystem. Having a dedicated [GitHub Copilot extension](https://github.com/marketplace?type=apps&copilot_app=true) for Deno would be immensely helpful for the large and active Deno community.
**The copilot extension of deno could provide the following features**
Developers can use @deno to learn about server-side JavaScript, generate Deno Deploy assets for local development workflows, or leverage Deno's built-in security features for project analysis.
Deno in GitHub Copilot
1. Generate the right Deno assets for your project: Get help with Deno Deploy and watch it generate the deploy.ts, import_map.json, and configuration files tailored to your project's specific needs: "@deno How would I deploy this project with Deno Deploy?"
2. Scaffold Fresh or Lume projects: Kickstart your web development projects with boilerplate code for popular frameworks like Fresh or Lume: "@deno Create a new Fresh project with a basic counter component" or "@deno Set up a Lume blog with Markdown support"
3. Get Deno-specific code suggestions: Streamline your development process with context-aware code completions and snippets optimized for the Deno ecosystem: "@deno Fetch data from an API and display it in a table"
4. Find and fix project vulnerabilities: The Deno extension integrates with Deno's built-in security features to surface potential issues and provide guidance on resolving them: "@deno Analyze my project for security vulnerabilities"
**Additional Information**
1. [Docker Copilot Extension as Example](https://github.com/marketplace/docker-for-github-copilot)
1. [VS Code Blog](https://code.visualstudio.com/blogs/2024/06/24/extensions-are-all-you-need) | suggestion,needs discussion | low | Major |
2,464,870,790 | go | cmd/internal/testdir: Test/initexp.go failures | ```
#!watchflakes
default <- pkg == "cmd/internal/testdir" && test == "Test/initexp.go"
```
Issue created automatically to collect these failures.
Example ([log](https://ci.chromium.org/b/8739665118851862049)):
=== RUN Test/initexp.go
=== PAUSE Test/initexp.go
=== CONT Test/initexp.go
testdir_test.go:145: compilation timed out
--- FAIL: Test/initexp.go (34.87s)
— [watchflakes](https://go.dev/wiki/Watchflakes)
| NeedsInvestigation | low | Critical |
2,464,873,561 | godot | Can I use part of a sprite as the light texture? | ### Tested versions
4.3rc2
### System information
MacOS Monterey 12.7.5
### Issue description
Sorry, I know this isn't the right place, but I've asked around and no one has given me a definitive answer.
When I try to add light textures to my light nodes, I find that light textures are a bit different from Sprite2D textures that can be cut from large sprites.
Currently, I create separate files for each light texture, but this is a bit inconvenient because I have too many light textures and if I create a file for each texture, there will be a lot of files.
My question is, am I doing something wrong or is it really only possible to generate separate texture files for each light node?
### Steps to reproduce
N/A
### Minimal reproduction project (MRP)
N/A | documentation,topic:2d | low | Major |
2,464,919,470 | transformers | fp16 support for grounding dino | ### Feature request
Currently, if fp16 is used with grounding dino via https://huggingface.co/docs/transformers/main/en/model_doc/grounding-dino, there is an error of the following:
```
...
File "/home/user/.local/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1553, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "/home/user/.local/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1562, in _call_impl
return forward_call(*args, **kwargs)
File "/home/user/.local/lib/python3.10/site-packages/transformers/models/grounding_dino/modeling_grounding_dino.py", line 3023, in forward
outputs = self.model(
File "/home/user/.local/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1553, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "/home/user/.local/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1562, in _call_impl
return forward_call(*args, **kwargs)
File "/home/user/.local/lib/python3.10/site-packages/transformers/models/grounding_dino/modeling_grounding_dino.py", line 2360, in forward
encoder_outputs = self.encoder(
File "/home/user/.local/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1553, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "/home/user/.local/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1562, in _call_impl
return forward_call(*args, **kwargs)
File "/home/user/.local/lib/python3.10/site-packages/transformers/models/grounding_dino/modeling_grounding_dino.py", line 1753, in forward
(vision_features, text_features), attentions = encoder_layer(
File "/home/user/.local/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1553, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "/home/user/.local/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1562, in _call_impl
return forward_call(*args, **kwargs)
File "/home/user/.local/lib/python3.10/site-packages/transformers/models/grounding_dino/modeling_grounding_dino.py", line 1274, in forward
(text_features, text_enhanced_attn) = self.text_enhancer_layer(
File "/home/user/.local/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1553, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "/home/user/.local/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1562, in _call_impl
return forward_call(*args, **kwargs)
File "/home/user/.local/lib/python3.10/site-packages/transformers/models/grounding_dino/modeling_grounding_dino.py", line 828, in forward
attention_output, attention_weights = self.self_attn(
File "/home/user/.local/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1553, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "/home/user/.local/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1562, in _call_impl
return forward_call(*args, **kwargs)
File "/home/user/.local/lib/python3.10/site-packages/transformers/models/grounding_dino/modeling_grounding_dino.py", line 1331, in forward
query_layer = self.transpose_for_scores(self.query(queries))
File "/home/user/.local/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1553, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "/home/user/.local/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1562, in _call_impl
return forward_call(*args, **kwargs)
File "/home/user/.local/lib/python3.10/site-packages/torch/nn/modules/linear.py", line 117, in forward
return F.linear(input, self.weight, self.bias)
RuntimeError: mat1 and mat2 must have the same dtype, but got Float and Half
```
### Motivation
It would be good to add support for fp16 to speed up the inference time.
### Your contribution
Happy to contribute if this feature is deemed to be useful. | Feature request,Vision | low | Critical |
2,464,949,717 | next.js | v14 npm run lint (eslint+typescript) Not implemented correctly | ### Link to the code that reproduces this issue
### To Reproduce
https://github.com/user-attachments/assets/9e7b3fe0-5e20-42fa-bf9d-59b21448b361
[codesandbox](https://codesandbox.io/p/devbox/cranky-silence-55k2p3?layout=%257B%2522sidebarPanel%2522%253A%2522EXPLORER%2522%252C%2522rootPanelGroup%2522%253A%257B%2522direction%2522%253A%2522horizontal%2522%252C%2522contentType%2522%253A%2522UNKNOWN%2522%252C%2522type%2522%253A%2522PANEL_GROUP%2522%252C%2522id%2522%253A%2522ROOT_LAYOUT%2522%252C%2522panels%2522%253A%255B%257B%2522type%2522%253A%2522PANEL_GROUP%2522%252C%2522contentType%2522%253A%2522UNKNOWN%2522%252C%2522direction%2522%253A%2522vertical%2522%252C%2522id%2522%253A%2522clztbaf1c00063b6j3tlo4lw2%2522%252C%2522sizes%2522%253A%255B70%252C30%255D%252C%2522panels%2522%253A%255B%257B%2522type%2522%253A%2522PANEL_GROUP%2522%252C%2522contentType%2522%253A%2522EDITOR%2522%252C%2522direction%2522%253A%2522horizontal%2522%252C%2522id%2522%253A%2522EDITOR%2522%252C%2522panels%2522%253A%255B%257B%2522type%2522%253A%2522PANEL%2522%252C%2522contentType%2522%253A%2522EDITOR%2522%252C%2522id%2522%253A%2522clztbaf1b00023b6jxxovxfnq%2522%257D%255D%257D%252C%257B%2522type%2522%253A%2522PANEL_GROUP%2522%252C%2522contentType%2522%253A%2522SHELLS%2522%252C%2522direction%2522%253A%2522horizontal%2522%252C%2522id%2522%253A%2522SHELLS%2522%252C%2522panels%2522%253A%255B%257B%2522type%2522%253A%2522PANEL%2522%252C%2522contentType%2522%253A%2522SHELLS%2522%252C%2522id%2522%253A%2522clztbaf1b00043b6jy43jzzil%2522%257D%255D%257D%255D%257D%252C%257B%2522type%2522%253A%2522PANEL_GROUP%2522%252C%2522contentType%2522%253A%2522DEVTOOLS%2522%252C%2522direction%2522%253A%2522vertical%2522%252C%2522id%2522%253A%2522DEVTOOLS%2522%252C%2522panels%2522%253A%255B%257B%2522type%2522%253A%2522PANEL%2522%252C%2522contentType%2522%253A%2522DEVTOOLS%2522%252C%2522id%2522%253A%2522clztbaf1c00053b6jrfyopfjd%2522%257D%255D%257D%255D%252C%2522sizes%2522%253A%255B50%252C50%255D%257D%252C%2522tabbedPanels%2522%253A%257B%2522clztbaf1b00023b6jxxovxfnq%2522%253A%257B%2522tabs%2522%253A%255B%257B%2522id%2522%253A%2522clztbaf1b00013b6jy3px7uaf%2522%252C%2522mode%2522%253A%2522permanent%2522%252C%2522type%2522%253A%2522FILE%2522%252C%2522filepath%2522%253A%2522%252FREADME.md%2522%252C%2522state%2522%253A%2522IDLE%2522%257D%252C%257B%2522id%2522%253A%2522clztf18gv00023b6jded6t1iz%2522%252C%2522mode%2522%253A%2522permanent%2522%252C%2522type%2522%253A%2522FILE%2522%252C%2522initialSelections%2522%253A%255B%257B%2522startLineNumber%2522%253A11%252C%2522startColumn%2522%253A1%252C%2522endLineNumber%2522%253A11%252C%2522endColumn%2522%253A1%257D%255D%252C%2522filepath%2522%253A%2522%252Fapp%252Flayout.tsx%2522%252C%2522state%2522%253A%2522IDLE%2522%257D%255D%252C%2522id%2522%253A%2522clztbaf1b00023b6jxxovxfnq%2522%252C%2522activeTabId%2522%253A%2522clztf18gv00023b6jded6t1iz%2522%257D%252C%2522clztbaf1c00053b6jrfyopfjd%2522%253A%257B%2522tabs%2522%253A%255B%255D%252C%2522id%2522%253A%2522clztbaf1c00053b6jrfyopfjd%2522%257D%252C%2522clztbaf1b00043b6jy43jzzil%2522%253A%257B%2522tabs%2522%253A%255B%257B%2522id%2522%253A%2522clztbaf1b00033b6jdc41hmde%2522%252C%2522mode%2522%253A%2522permanent%2522%252C%2522type%2522%253A%2522TASK_LOG%2522%252C%2522taskId%2522%253A%2522dev%2522%257D%255D%252C%2522id%2522%253A%2522clztbaf1b00043b6jy43jzzil%2522%252C%2522activeTabId%2522%253A%2522clztbaf1b00033b6jdc41hmde%2522%257D%257D%252C%2522showDevtools%2522%253Atrue%252C%2522showShells%2522%253Atrue%252C%2522showSidebar%2522%253Atrue%252C%2522sidebarPanelSize%2522%253A15%257D)
### Current vs. Expected behavior
Running npm run lint should prompt an error or warning
doc:
https://nextjs.org/docs/app/building-your-application/configuring/eslint#typescript
### Provide environment information
```bash
Operating System:
Platform: linux
Arch: x64
Version: #1 SMP PREEMPT_DYNAMIC Sun Aug 6 20:05:33 UTC 2023
Available memory (MB): 4102
Available CPU cores: 2
Binaries:
Node: 20.11.1
npm: 10.2.4
Yarn: 1.22.19
pnpm: 8.15.4
Relevant Packages:
next: 14.2.1 // There is a newer version (14.2.5) available, upgrade recommended!
eslint-config-next: 14.2.1
react: 18.2.0
react-dom: 18.2.0
typescript: 5.4.5
Next.js Config:
output: N/A
```
### Which area(s) are affected? (Select all that apply)
create-next-app
### Which stage(s) are affected? (Select all that apply)
next dev (local)
### Additional context
_No response_ | create-next-app,bug | low | Critical |
2,465,002,388 | ollama | ollama tool input: string with newline character (\n) is cutoff | I am using ollama with llama3.1 model and using a tool to draft email responses. The input passed to the tool is has a string with \n character which is a valid string in python. but I am getting a cutoff version of the string passed to the tool where I am only getting characters before the \n.
here is the output from the console:
> Finished chain.
[2024-08-14 11:48:57][DEBUG]: == [Email Action Specialist] Task output: {
"message_id": "1914ee60fc1515fa",
"summary": Dear Md. Rakibul Haque,\r\n\r\nI hope you're doing well. I wanted to reach out to schedule a meeting to discuss the upcoming project we've been planning. There are a few key details and timelines that I'd like to review with you, so please let me know if this is something you can fit into your schedule.\r\n\r\nBest regards,\r\nSolaiman Ovi",
"main_points": [
"Schedule a meeting to discuss the upcoming project",
"Review key details and timelines"
],
"user": "Solaiman Ovi",
"communication_style": "Formal",
"sender": "solaiman.arisaftech@gmail.com"
}
[2024-08-14 11:48:57][DEBUG]: == Working Agent: Email Response Writer
[2024-08-14 11:48:57][INFO]: == Starting Task: Based on the action-required emails identified, draft responses for each...
....
> Entering new CrewAgentExecutor chain...
Action: Create Draft
Action Input: {"email": "solaiman.arisaftech@gmail.com", "message": "Dear Solaiman Ovi,\n\nThank you for reaching out to schedule a meeting. I'd be happy to discuss the upcoming project with you. I'll send over some availability options and we can schedule something that works best for both of us.\n\nBest regards,\nMd. Rakibul Haque", "subject": "Re: Meeting to Discuss Upcoming Project
this is what I'm printing from the tool in the console:
email: solaiman.arisaftech@gmail.com
subject: Re: Meeting to Discuss Upcoming Project
message: Dear Solaiman Ovi
As you can see the string is cutoff before \n. I am not getting the full string.
**The funny thing happening here is when I use groq API instead of ollama and use the same model llama3.1, the string does not cutt off and I get the full string.**
below are the agent, task and tool codes
```
def email_response_writer(self):
return Agent(
role='Email Response Writer',
goal='Draft responses to action-required emails',
backstory=dedent("""\
You are a skilled writer, adept at crafting clear, concise, and effective email responses.
Your strength lies in your ability to communicate effectively, ensuring that each response is
tailored to address the specific needs and context of the email."""),
tools=[
CreateGmailMessageTool.get_gmail_message,
CreateDraftTool.create_draft,
],
verbose=True,
allow_delegation=False,
llm=llm
)
def draft_responses_task(self, agent):
return Task(
description=dedent("""\
Based on the action-required emails identified, draft responses for each.
Ensure that each response is tailored to address the specific needs
and context outlined in the email.
- Assume the persona of the user and mimic the communication style in the message.
- Feel free to do research on the topic to provide a more detailed response, IF NECESSARY.
- IF a research is necessary do it BEFORE drafting the response.
- If you need to pull the message again do it using only the message ID.
Use the tool provided to draft each of the responses.
When using the tool pass the following input in JSON format:
- email: the email address of the sender
- message: the reply you generate for the email (format it as raw string)
- subject: subject of the email
You MUST create all drafts before sending your final answer.
"""),
expected_output=dedent("""\
- confirmation: [Confirmation that all responses have been drafted]
"""),
agent=agent
)
class CreateDraftTool():
@tool("Create Draft")
def create_draft(email,message,subject):
"""
Useful to create an email draft.
"""
print('email: ',email.strip("\""))
print('subject: ',subject.strip("\""))
print('message: ',message.strip("\""))
gmail = GmailToolkit()
draft = GmailCreateDraft(api_resource=gmail.api_resource)
result = draft.run({
'to': [email.strip("\"")],
'subject': subject.strip("\""),
'message': message.strip("\"")
})
return f"\nDraft created: {result}\n"
```
### OS
macOS
### GPU
Intel
### CPU
Intel
### Ollama version
0.3.6 | bug,api | low | Critical |
2,465,004,032 | godot | `GPUParticles3D` collision point is unpredictable depending on particle collision speed | ### Tested versions
v4.2.2.stable.mono.official [15073afe3]
### System information
Godot v4.2.2.stable.mono - Windows 10.0.22631 - Vulkan (Forward+) - dedicated NVIDIA GeForce RTX 4080 (NVIDIA; 32.0.15.5599) - AMD Ryzen 9 7950X3D 16-Core Processor (32 Threads)
### Issue description
If have set up a `GPUParticles3D` with a `GPUParticlesCollisionHeightField3D` collider. The particles are set up to hide on collide and spawn a subemitter on collision. The idea behind it is to simulate rain drops creating splashes when hitting the ground. To keep things simple we use a flat piece of geometry as ground. The particles spawn in a ring shape with 0 height from 20 m above the ground and are only affected by gravity. So each particle should travel at the exact same speed when it hits the ground. Now please regard the following video:
https://github.com/user-attachments/assets/83344fdc-4469-45bd-95fd-590c2eba0dfd
We can immediately see that by default the particle collision point is below the ground. I switched the view to orthogonal so it is easier to see. At least all particle collision points seem to end up at the same y position, so I thought this is some kind of tunneling issue where the 30fps framerate isn't enough to keep up with the particle speed and hence the colllison is detected inside the ground. So I increased the collision base size to compensate for that and 1.1 meter makes it so that the particles look like they properly collide with the ground.
Now this is already the first problem. _How much_ I need to compensate depends on the speed that the particles have when they hit the ground (and a few other variables as we will see). So if I want some variety to my rain and some particles should move a little faster than others, there is no way I can have all particles collide at the same plane because the collision point is unpredictable with randomized speeds.
Now I increase the amount of particles in my particle system to 500 and then to 5000. I would expect that this has no impact on where the collision point of the particles is. They all still travel at the same acceleration from the same height so they shoudl have exactly the same speed when hitting the ground and my 1.1m compensation should still work. But it doesn't. Instead the collision points randomly vary by about 1 meter in height, which should absolutely not be the case.
Now I try to increase the FPS of the particle system. When I increase it to 60 now my particles all collide way above the ground, so my compensation is too much. But they still don't collide at the same height but in a band of roughly 0.5 meters. If I use 0 FPS which basically is "as fast as possible", the band narrows but still isn't at the same height and is still above the ground. Finally I reduce the amount of particles back to 50 and suddenly no more subemitters are spawned at all.
This unpredictable behaviour makes it next to impossible to use subemitters on impact in a meaningful way.
### Steps to reproduce
Using the supplied reproduction project, open `collision_offsets.tscn` and repeat the steps shown in the video.
### Minimal reproduction project (MRP)
[reproducer.zip](https://github.com/user-attachments/files/16608401/reproducer.zip)
| bug,needs testing,topic:3d,topic:particles | low | Major |
2,465,013,162 | ollama | The quality of answer significantly deteriorates after Automatic Quantization | ### What is the issue?
Using gemma2-27b for test, after ollama create -q Q8_0, the quality of answer is not very good. The accuracy seems more worse than origin gemma2-9b in hf. What's the principle behind Ollama's quantization? Is it something like post-training quantization? Thanks.
### OS
Linux
### GPU
Nvidia
### CPU
Intel
### Ollama version
0.3.5 | bug | low | Minor |
2,465,030,958 | vscode | [12f] potential listener LEAK detected, having 1005 listeners already. MOST frequent listener (442): | ```javascript
Error
at c.create in src/vs/base/common/event.ts:921:15
at h.q [as onDidChange] in src/vs/base/common/event.ts:1128:34
at Object.A [as onWillAddFirstListener] in src/vs/platform/actions/common/menuService.ts:425:34
at u.q [as onDidChange] in out/vs/workbench/workbench.desktop.main.js:91:1280
at D.G in src/vs/workbench/contrib/notebook/browser/view/cellParts/cellOutput.ts:352:36
at p._runFn in src/vs/workbench/contrib/notebook/browser/view/cellParts/cellOutput.ts:218:11
at p.j in src/vs/base/common/observableInternal/autorun.ts:196:10
at p.endUpdate in src/vs/base/common/observableInternal/autorun.ts:237:10
at d.finish in src/vs/base/common/observableInternal/base.ts:372:13
at s.set in src/vs/base/common/observableInternal/base.ts:445:9
at y.setVisible in src/vs/workbench/contrib/notebook/browser/viewModel/cellOutputViewModel.ts:31:16
at a.updateOutputHeight in src/vs/workbench/contrib/notebook/browser/viewModel/codeCellViewModel.ts:449:34
at Pe.Wc in src/vs/workbench/contrib/notebook/browser/notebookEditorWidget.ts:3039:9
at u.value in src/vs/workbench/contrib/notebook/browser/view/renderers/backLayerWebView.ts:623:29
at o.B in src/vs/base/common/event.ts:1230:13
at o.fire in src/vs/base/common/event.ts:1261:9
at <anonymous> in src/vs/workbench/contrib/webview/browser/webviewElement.ts:198:20
at handler in src/vs/workbench/contrib/webview/browser/webviewElement.ts:510:35
at Set.forEach (<anonymous>)
at H.onmessage in src/vs/workbench/contrib/webview/browser/webviewElement.ts:510:16
```
[Go to Errors Site](https://errors.code.visualstudio.com/card?ch=eaa41d57266683296de7d118f574d0c2652e1fc4&bH=2d6032d6-676f-ae2f-c993-48baf5ca24b1) | error-telemetry | low | Critical |
2,465,031,562 | vscode | Uncaught TypeError: Cannot read properties of undefined (reading 'element') | ```javascript
TypeError: Cannot read properties of undefined (reading 'element')
at I.element in src/vs/base/browser/ui/list/listView.ts:795:28
at w.element in src/vs/base/browser/ui/list/listWidget.ts:1601:20
at w.elementAt in src/vs/workbench/contrib/notebook/browser/view/notebookCellList.ts:329:15
at c.w in src/vs/workbench/contrib/notebook/browser/view/cellParts/cellDnd.ts:138:37
at HTMLDivElement.<anonymous> in src/vs/workbench/contrib/notebook/browser/view/cellParts/cellDnd.ts:86:33
```
[Go to Errors Site](https://errors.code.visualstudio.com/card?ch=eaa41d57266683296de7d118f574d0c2652e1fc4&bH=fb73dbd2-7cbf-d857-c48c-ec207aac5fdd) | error-telemetry | low | Critical |
2,465,032,045 | vscode | Cannot read properties of undefined (reading 'setVisible') | ```javascript
TypeError: Cannot read properties of undefined (reading 'setVisible')
at a.updateOutputHeight in src/vs/workbench/contrib/notebook/browser/viewModel/codeCellViewModel.ts:449:34
at Pe.Wc in src/vs/workbench/contrib/notebook/browser/notebookEditorWidget.ts:3039:9
at u.value in src/vs/workbench/contrib/notebook/browser/view/renderers/backLayerWebView.ts:638:30
at o.B in src/vs/base/common/event.ts:1230:13
at o.fire in src/vs/base/common/event.ts:1261:9
at <anonymous> in src/vs/workbench/contrib/webview/browser/webviewElement.ts:198:20
at handler in src/vs/workbench/contrib/webview/browser/webviewElement.ts:510:35
at Set.forEach (<anonymous>)
at H.onmessage in src/vs/workbench/contrib/webview/browser/webviewElement.ts:510:16
```
[Go to Errors Site](https://errors.code.visualstudio.com/card?ch=eaa41d57266683296de7d118f574d0c2652e1fc4&bH=284b878d-d997-4d55-108a-7e4617c7ee84) | error-telemetry | low | Critical |
2,465,033,221 | vscode | Already in transaction | ```javascript
Error: Already in transaction
at n.transact in src/vs/base/browser/ui/list/rowCache.ts:66:10
at I.Y in src/vs/base/browser/ui/list/listView.ts:867:14
at I.Y in src/vs/workbench/contrib/notebook/browser/view/notebookCellListView.ts:254:9
at I.ib in src/vs/base/browser/ui/list/listView.ts:1107:9
at o.B in src/vs/base/common/event.ts:1230:13
at o.C in src/vs/base/common/event.ts:1241:9
at o.fire in src/vs/base/common/event.ts:1265:9
at u.value in src/vs/base/browser/ui/scrollbar/scrollableElement.ts:216:19
at o.B in src/vs/base/common/event.ts:1230:13
at o.fire in src/vs/base/common/event.ts:1261:9
at L.n in src/vs/base/common/scrollable.ts:393:18
at L.setScrollPositionNow in src/vs/base/common/scrollable.ts:303:8
at r.setScrollPosition in src/vs/base/browser/ui/scrollbar/scrollableElement.ts:619:21
at I.setScrollTop in src/vs/base/browser/ui/list/listView.ts:1030:26
at w.vb in src/vs/workbench/contrib/notebook/browser/view/notebookCellList.ts:1145:14
at w.sb in src/vs/workbench/contrib/notebook/browser/view/notebookCellList.ts:1037:9
at w.revealRangeInCell in src/vs/workbench/contrib/notebook/browser/view/notebookCellList.ts:1019:17
at Pe.revealRangeInViewAsync in src/vs/workbench/contrib/notebook/browser/notebookEditorWidget.ts:2156:21
at u.value in src/vs/workbench/contrib/notebook/browser/view/cellParts/codeCell.ts:307:25
at o.B in src/vs/base/common/event.ts:1230:13
at o.C in src/vs/base/common/event.ts:1241:9
at o.fire in src/vs/base/common/event.ts:1265:9
at u.value in src/vs/editor/browser/widget/codeEditor/codeEditorWidget.ts:1731:39
at o.B in src/vs/base/common/event.ts:1230:13
at o.fire in src/vs/base/common/event.ts:1261:9
at C.s in src/vs/editor/common/viewModelEventDispatcher.ts:64:18
at C.endEmitViewEvents in src/vs/editor/common/viewModelEventDispatcher.ts:109:8
at C.emitSingleViewEvent in src/vs/editor/common/viewModelEventDispatcher.ts:117:9
at k.setHasFocus in src/vs/editor/common/viewModel/viewModelImpl.ts:215:25
at u.value in src/vs/editor/browser/controller/textAreaHandler.ts:474:28
at o.B in src/vs/base/common/event.ts:1230:13
at o.fire in src/vs/base/common/event.ts:1261:9
at r.M in src/vs/editor/browser/controller/textAreaInput.ts:625:17
at u.value in src/vs/editor/browser/controller/textAreaInput.ts:469:9
at o.B in src/vs/base/common/event.ts:1230:13
at o.fire in src/vs/base/common/event.ts:1261:9
at HTMLTextAreaElement.E in src/vs/base/browser/event.ts:40:41
at M.HTMLElement.focus in src/vs/workbench/browser/window.ts:67:18
at w.domFocus in src/vs/base/browser/ui/list/listWidget.ts:1678:21
at w.focusContainer in src/vs/workbench/contrib/notebook/browser/view/notebookCellList.ts:1314:9
at Pe.focusContainer in src/vs/workbench/contrib/notebook/browser/notebookEditorWidget.ts:1984:15
at w.dispose in src/vs/workbench/contrib/notebook/browser/view/cellParts/codeCell.ts:575:24
at a in src/vs/base/common/lifecycle.ts:303:8
at $Pc in src/vs/base/common/lifecycle.ts:405:4
at Z.disposeElement in src/vs/workbench/contrib/notebook/browser/view/renderers/cellRenderer.ts:388:35
at _.disposeElement in out/vs/workbench/workbench.desktop.main.js:209:2366
at I.db in src/vs/base/browser/ui/list/listView.ts:1006:14
at <anonymous> in src/vs/base/browser/ui/list/listView.ts:870:11
at makeChanges in src/vs/base/browser/ui/list/rowCache.ts:72:4
at I.Y in src/vs/base/browser/ui/list/listView.ts:867:14
at I.Y in src/vs/workbench/contrib/notebook/browser/view/notebookCellListView.ts:254:9
at I.updateElementHeight in src/vs/base/browser/ui/list/listView.ts:554:8
at w.updateElementHeight2 in src/vs/workbench/contrib/notebook/browser/view/notebookCellList.ts:1268:15
at je in src/vs/workbench/contrib/notebook/browser/notebookEditorWidget.ts:2331:15
at doLayout in src/vs/workbench/contrib/notebook/browser/notebookEditorWidget.ts:2343:4
at u.value in src/vs/workbench/contrib/notebook/browser/notebookEditorWidget.ts:1563:10
at S.B in src/vs/base/common/event.ts:1230:13
at S.C in src/vs/base/common/event.ts:1241:9
at S.fire in src/vs/base/common/event.ts:1265:9
at S.fire in src/vs/base/common/event.ts:1427:11
at a.sb in src/vs/workbench/contrib/notebook/browser/viewModel/codeCellViewModel.ts:348:26
at a.layoutChange in src/vs/workbench/contrib/notebook/browser/viewModel/codeCellViewModel.ts:340:8
at set editorHeight in src/vs/workbench/contrib/notebook/browser/viewModel/codeCellViewModel.ts:62:8
at w.jb in out/vs/workbench/workbench.desktop.main.js:2730:143220
at u.value in src/vs/workbench/contrib/notebook/browser/view/cellParts/codeCell.ts:282:11
at o.B in src/vs/base/common/event.ts:1230:13
at o.fire in src/vs/base/common/event.ts:1261:9
at u.value in src/vs/editor/browser/widget/codeEditor/codeEditorWidget.ts:1669:35
at o.B in src/vs/base/common/event.ts:1230:13
at o.fire in src/vs/base/common/event.ts:1261:9
at C.s in src/vs/editor/common/viewModelEventDispatcher.ts:64:18
at C.endEmitViewEvents in src/vs/editor/common/viewModelEventDispatcher.ts:109:8
at <anonymous> in src/vs/editor/common/viewModel/viewModelImpl.ts:1111:27
at cb in src/vs/editor/browser/widget/codeEditor/codeEditorWidget.ts:1655:14
at k.U in src/vs/editor/common/viewModel/viewModelImpl.ts:1106:36
at k.S in src/vs/editor/common/viewModel/viewModelImpl.ts:1044:8
at k.executeCommands in src/vs/editor/common/viewModel/viewModelImpl.ts:1071:8
at x.executeCommands in src/vs/editor/browser/widget/codeEditor/codeEditorWidget.ts:1245:29
at B.runCoreEditingCommand in src/vs/editor/browser/coreCommands.ts:2062:11
at B.runEditorCommand in src/vs/editor/browser/coreCommands.ts:1970:9
at <anonymous> in src/vs/editor/browser/editorExtensions.ts:321:109
at runner in src/vs/editor/browser/editorExtensions.ts:316:11
at fn in src/vs/platform/instantiation/common/instantiationService.ts:109:11
at x.invokeWithinContext in src/vs/editor/common/viewModel/viewModelImpl.ts:849:26
```
[Go to Errors Site](https://errors.code.visualstudio.com/card?ch=eaa41d57266683296de7d118f574d0c2652e1fc4&bH=074e7e25-9874-b100-301f-b48d1c467226) | error-telemetry | low | Critical |
2,465,033,875 | vscode | Cannot read properties of null (reading 'getFoldingState') | ```javascript
TypeError: Cannot read properties of null (reading 'getFoldingState')
at get foldingState in src/vs/workbench/contrib/notebook/browser/viewModel/markupCellViewModel.ts:75:31
at W.n in src/vs/workbench/contrib/notebook/browser/contrib/outline/notebookOutline.ts:200:94
at W.renderElement in src/vs/workbench/contrib/notebook/browser/contrib/outline/notebookOutline.ts:169:9
at N.renderElement in src/vs/base/browser/ui/tree/abstractTree.ts:418:17
at _.renderElement in src/vs/base/browser/ui/list/listWidget.ts:1249:13
at S.Z in src/vs/base/browser/ui/list/listView.ts:940:13
at S.U in src/vs/base/browser/ui/list/listView.ts:675:10
at S.splice in src/vs/base/browser/ui/list/listView.ts:576:16
at <anonymous> in src/vs/base/browser/ui/list/splice.ts:17:35
at Array.forEach (<anonymous>)
at t.splice in src/vs/base/browser/ui/list/splice.ts:17:20
at <anonymous> in src/vs/base/browser/ui/list/listWidget.ts:1585:57
at fn in src/vs/base/common/event.ts:1703:13
at J.splice in src/vs/base/browser/ui/list/listWidget.ts:1585:22
at J.splice in src/vs/base/browser/ui/tree/abstractTree.ts:2389:9
at g.t in src/vs/base/browser/ui/tree/indexTreeModel.ts:308:14
at g.splice in src/vs/base/browser/ui/tree/indexTreeModel.ts:160:9
at I.l in src/vs/base/browser/ui/tree/objectTreeModel.ts:122:14
at I.setChildren in src/vs/base/browser/ui/tree/objectTreeModel.ts:71:8
at te.m in src/vs/base/browser/ui/tree/dataTree.ts:155:14
at te.updateChildren in src/vs/base/browser/ui/tree/dataTree.ts:110:8
at u.q [as value] in src/vs/workbench/contrib/outline/browser/outlinePane.ts:290:10
at o.B in src/vs/base/common/event.ts:1230:13
at o.C in src/vs/base/common/event.ts:1241:9
at o.fire in src/vs/base/common/event.ts:1265:9
at u.value in src/vs/workbench/contrib/notebook/browser/contrib/outline/notebookOutline.ts:666:23
at o.B in src/vs/base/common/event.ts:1230:13
at o.C in src/vs/base/common/event.ts:1241:9
at o.fire in src/vs/base/common/event.ts:1265:9
at g.recomputeActive in src/vs/workbench/contrib/notebook/browser/viewModel/notebookOutlineDataSource.ts:211:22
at Y.I in src/vs/workbench/contrib/notebook/browser/contrib/outline/notebookOutline.ts:722:72
at <anonymous> in src/vs/workbench/contrib/notebook/browser/contrib/outline/notebookOutline.ts:724:52
at task in src/vs/base/common/async.ts:364:13
```
[Go to Errors Site](https://errors.code.visualstudio.com/card?ch=eaa41d57266683296de7d118f574d0c2652e1fc4&bH=7271832a-05e8-e463-cbab-275d6fb66431) | error-telemetry | low | Critical |
2,465,034,571 | vscode | Cannot read properties of null (reading 'domNode') | ```javascript
TypeError: Cannot read properties of null (reading 'domNode')
at I.bb in src/vs/base/browser/ui/list/listView.ts:977:13
at I.Y in src/vs/base/browser/ui/list/listView.ts:863:10
at I.Y in src/vs/workbench/contrib/notebook/browser/view/notebookCellListView.ts:254:9
at I.updateElementHeight in src/vs/base/browser/ui/list/listView.ts:554:8
at w.updateElementHeight2 in src/vs/workbench/contrib/notebook/browser/view/notebookCellList.ts:1274:13
at je in src/vs/workbench/contrib/notebook/browser/notebookEditorWidget.ts:2331:15
at doLayout in src/vs/workbench/contrib/notebook/browser/notebookEditorWidget.ts:2343:4
at A.G in src/vs/workbench/contrib/notebook/browser/view/cellParts/cellOutput.ts:795:23
at A.render in src/vs/workbench/contrib/notebook/browser/view/cellParts/cellOutput.ts:557:9
at new w in src/vs/workbench/contrib/notebook/browser/view/cellParts/codeCell.ts:120:33
at g.o in src/vs/platform/instantiation/common/instantiationService.ts:162:18
at g.createInstance in src/vs/platform/instantiation/common/instantiationService.ts:128:18
at Z.renderElement in src/vs/workbench/contrib/notebook/browser/view/renderers/cellRenderer.ts:379:73
at _.renderElement in src/vs/base/browser/ui/list/listWidget.ts:1249:13
at I.Z in src/vs/base/browser/ui/list/listView.ts:940:13
at I.U in src/vs/base/browser/ui/list/listView.ts:675:10
at I.splice in src/vs/base/browser/ui/list/listView.ts:576:16
at <anonymous> in src/vs/base/browser/ui/list/splice.ts:17:35
at Array.forEach (<anonymous>)
at t.splice in src/vs/base/browser/ui/list/splice.ts:17:20
at <anonymous> in src/vs/base/browser/ui/list/listWidget.ts:1585:57
at fn in src/vs/base/common/event.ts:1703:13
at w.splice in src/vs/base/browser/ui/list/listWidget.ts:1585:22
at w.splice2 in src/vs/workbench/contrib/notebook/browser/view/notebookCellList.ts:540:9
at <anonymous> in src/vs/workbench/contrib/notebook/browser/view/notebookCellList.ts:431:9
at Array.forEach (<anonymous>)
at w.lb in src/vs/workbench/contrib/notebook/browser/view/notebookCellList.ts:413:23
at u.value in src/vs/workbench/contrib/notebook/browser/view/notebookCellList.ts:373:10
at o.B in src/vs/base/common/event.ts:1230:13
at o.C in src/vs/base/common/event.ts:1241:9
at o.fire in src/vs/base/common/event.ts:1265:9
at U in src/vs/workbench/contrib/notebook/browser/viewModel/notebookViewModelImpl.ts:234:31
at compute in src/vs/workbench/contrib/notebook/browser/viewModel/notebookViewModelImpl.ts:278:6
at o.B in src/vs/base/common/event.ts:1230:13
at o.C in src/vs/base/common/event.ts:1241:9
at o.fire in src/vs/base/common/event.ts:1265:9
at u.value in src/vs/workbench/contrib/notebook/common/model/notebookTextModel.ts:276:30
at r.B in src/vs/base/common/event.ts:1230:13
at r.fire in src/vs/base/common/event.ts:1261:9
at r.resume in src/vs/base/common/event.ts:1409:12
at d.applyEdits in src/vs/workbench/contrib/notebook/common/model/notebookTextModel.ts:541:27
at d.reset in src/vs/workbench/contrib/notebook/common/model/notebookTextModel.ts:414:8
at r.update in src/vs/workbench/contrib/notebook/common/notebookEditorModel.ts:345:23
at async D.db in src/vs/workbench/services/workingCopy/common/storedFileWorkingCopy.ts:711:4
at async D.ab in src/vs/workbench/services/workingCopy/common/storedFileWorkingCopy.ts:674:4
at async D.$ in src/vs/workbench/services/workingCopy/common/storedFileWorkingCopy.ts:615:4
at async D.mb in src/vs/workbench/services/workingCopy/common/storedFileWorkingCopyManager.ts:562:4
at async D.lb in src/vs/workbench/services/workingCopy/common/storedFileWorkingCopyManager.ts:453:3
at async Object.factory in src/vs/workbench/services/workingCopy/common/storedFileWorkingCopyManager.ts:303:6
```
[Go to Errors Site](https://errors.code.visualstudio.com/card?ch=eaa41d57266683296de7d118f574d0c2652e1fc4&bH=5849215b-a61e-aeac-b4d1-b6d206f16af1) | error-telemetry | low | Critical |
2,465,037,434 | vscode | Model is disposed! | ```javascript
Error: Model is disposed!
at U.ib in src/vs/editor/common/model/textModel.ts:421:10
at U.getLineCount in src/vs/editor/common/model/textModel.ts:806:8
at <anonymous> in src/vs/workbench/contrib/output/common/outputChannelModel.ts:238:27
```
[Go to Errors Site](https://errors.code.visualstudio.com/card?ch=eaa41d57266683296de7d118f574d0c2652e1fc4&bH=71d77f58-9b8f-dd09-5b91-c8afd6bf5ab0) | error-telemetry | low | Critical |
2,465,038,252 | vscode | InstantiationService has been disposed | ```javascript
Error: InstantiationService has been disposed
at g.m in src/vs/platform/instantiation/common/instantiationService.ts:69:10
at g.createInstance in src/vs/platform/instantiation/common/instantiationService.ts:119:8
at new Z in src/vs/editor/browser/view.ts:131:54
at x.ac in src/vs/editor/browser/widget/codeEditor/codeEditorWidget.ts:1856:16
at x.$b in src/vs/editor/browser/widget/codeEditor/codeEditorWidget.ts:1758:36
at x.setModel in src/vs/editor/browser/widget/codeEditor/codeEditorWidget.ts:495:9
at <anonymous> in src/vs/workbench/contrib/notebook/browser/view/cellParts/markupCell.ts:384:18
```
[Go to Errors Site](https://errors.code.visualstudio.com/card?ch=eaa41d57266683296de7d118f574d0c2652e1fc4&bH=e9dc9211-9b48-734a-d613-68da52681138) | error-telemetry | low | Critical |
2,465,038,638 | vscode | Cannot read properties of undefined (reading 'contentMatches') | ```javascript
TypeError: Cannot read properties of undefined (reading 'contentMatches')
at g.w in src/vs/workbench/contrib/notebook/browser/contrib/find/findModel.ts:275:31
at <anonymous> in src/vs/workbench/contrib/notebook/browser/contrib/find/findModel.ts:263:9
```
[Go to Errors Site](https://errors.code.visualstudio.com/card?ch=eaa41d57266683296de7d118f574d0c2652e1fc4&bH=a9a50a9e-32a0-eccd-cd4e-a1bd577cce25) | error-telemetry | low | Critical |
2,465,039,988 | vscode | Illegal value for lineNumber | ```javascript
Error: Illegal value for lineNumber
at U.getLineContent in src/vs/editor/common/model/textModel.ts:813:10
at c._computeFn in src/vs/editor/contrib/inlineCompletions/browser/ghostTextWidget.ts:86:36
at c.t in src/vs/base/common/observableInternal/derived.ts:284:22
at c.get in src/vs/base/common/observableInternal/derived.ts:261:10
at c.reportChanges in src/vs/base/common/observableInternal/base.ts:189:8
at c.get in src/vs/base/common/observableInternal/derived.ts:246:9
at c.reportChanges in src/vs/base/common/observableInternal/base.ts:189:8
at p.endUpdate in src/vs/base/common/observableInternal/autorun.ts:229:9
at c.endUpdate in src/vs/base/common/observableInternal/derived.ts:341:7
at c.endUpdate in src/vs/base/common/observableInternal/derived.ts:341:7
at c.endUpdate in src/vs/base/common/observableInternal/derived.ts:341:7
at c.endUpdate in src/vs/base/common/observableInternal/derived.ts:341:7
at d.finish in src/vs/base/common/observableInternal/base.ts:372:13
at f.g in src/vs/editor/browser/observableCodeEditor.ts:66:6
at u.value in src/vs/editor/browser/observableCodeEditor.ts:74:53
at o.B in src/vs/base/common/event.ts:1230:13
at o.fire in src/vs/base/common/event.ts:1261:9
at x.jc in src/vs/editor/browser/widget/codeEditor/codeEditorWidget.ts:1943:22
at x.setModel in src/vs/editor/browser/widget/codeEditor/codeEditorWidget.ts:506:9
at <anonymous> in src/vs/workbench/contrib/notebook/browser/view/cellParts/codeCell.ts:210:30
```
[Go to Errors Site](https://errors.code.visualstudio.com/card?ch=eaa41d57266683296de7d118f574d0c2652e1fc4&bH=d2af2b27-eca1-4944-e3a4-6be21e6b9d0e) | error-telemetry | low | Critical |
2,465,043,271 | vscode | ListError [NotebookCellList] Invalid index 14 | ```javascript
Error: ListError [NotebookCellList] Invalid index 14
at w.getCellViewScrollTop in src/vs/workbench/contrib/notebook/browser/view/notebookCellList.ts:759:10
at Pe.createMarkupPreview in src/vs/workbench/contrib/notebook/browser/notebookEditorWidget.ts:2737:30
at Object.Se [as callback] in src/vs/workbench/contrib/notebook/browser/notebookEditorWidget.ts:1214:10
at <anonymous> in src/vs/base/common/platform.ts:233:17
```
[Go to Errors Site](https://errors.code.visualstudio.com/card?ch=eaa41d57266683296de7d118f574d0c2652e1fc4&bH=3e58aaab-9964-bc5d-5a87-6da8aa6f6e99) | error-telemetry | low | Critical |
2,465,047,449 | nvm | zsh initialization performance | <!-- Thank you for being interested in nvm! Please help us by filling out the following form if you‘re having trouble. If you have a feature request, or some other question, please feel free to clear out the form. Thanks! -->
#### Operating system and version:
#### `nvm debug` output:
<details>
<!-- do not delete the following blank line -->
```sh
nvm --version: v0.40.0
$SHELL: /usr/bin/zsh
$SHLVL: 1
whoami: 'devlin'
${HOME}: /home/devlin
${NVM_DIR}: '${HOME}/.nvm'
${PATH}: /opt/oracle/instantclient_21_5:${HOME}/Developments/flutter/bin:${HOME}/Developments/flutter/bin:/usr/local/bin:${NVM_DIR}:${NVM_DIR}/versions/node/v20.12.2/bin:${HOME}/development/flutter/bin:${HOME}/.cargo/bin:${HOME}/.local/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin:/snap/bin:/usr/local/sbin:/usr/local/bin:/snap/bin:/snap/bin:${HOME}/.local/share/JetBrains/Toolbox/scripts
$PREFIX: ''
${NPM_CONFIG_PREFIX}: ''
$NVM_NODEJS_ORG_MIRROR: ''
$NVM_IOJS_ORG_MIRROR: ''
shell version: 'zsh 5.8.1 (x86_64-ubuntu-linux-gnu)'
uname -a: 'Linux 6.5.0-45-generic #45~22.04.1-Ubuntu SMP PREEMPT_DYNAMIC Mon Jul 15 16:40:02 UTC 2 x86_64 x86_64 x86_64 GNU/Linux'
checksum binary: 'sha256sum'
OS version: Ubuntu 22.04.4 LTS
random-funcs: srandom/random
regex-funcs: internal
compiled limits:
sprintf buffer 8192
maximum-integer 2147483647
awk: /usr/bin/awk, mawk 1.3.4 20200120
curl: /usr/bin/curl, curl 7.81.0 (x86_64-pc-linux-gnu) libcurl/7.81.0 OpenSSL/3.0.2 zlib/1.2.11 brotli/1.0.9 zstd/1.4.8 libidn2/2.3.2 libpsl/0.21.0 (+libidn2/2.3.2) libssh/0.9.6/openssl/zlib nghttp2/1.43.0 librtmp/2.3 OpenLDAP/2.5.18
wget: /usr/bin/wget, GNU Wget 1.21.2 built on linux-gnu.
git: /usr/bin/git, git version 2.34.1
ls: cannot access 'grep:': No such file or directory
grep: grep: aliased to grep --color=auto --exclude-dir={.bzr,CVS,.git,.hg,.svn,.idea,.tox} (grep --color=auto --exclude-dir={.bzr,CVS,.git,.hg,.svn,.idea,.tox}), grep (GNU grep) 3.7
sed: /usr/bin/sed, sed (GNU sed) 4.8
cut: /usr/bin/cut, cut (GNU coreutils) 8.32
basename: /usr/bin/basename, basename (GNU coreutils) 8.32
rm: /usr/bin/rm, rm (GNU coreutils) 8.32
mkdir: /usr/bin/mkdir, mkdir (GNU coreutils) 8.32
xargs: /usr/bin/xargs, xargs (GNU findutils) 4.8.0
nvm current: v20.12.2
which node: ${NVM_DIR}/versions/node/v20.12.2/bin/node
which iojs: iojs not found
which npm: ${NVM_DIR}/versions/node/v20.12.2/bin/npm
npm config get prefix: ${NVM_DIR}/versions/node/v20.12.2
npm root -g: ${NVM_DIR}/versions/node/v20.12.2/lib/node_modules
```
</details>
#### `nvm ls` output:
<details>
<!-- do not delete the following blank line -->
```sh
-> v20.12.2
default -> node (-> v20.12.2)
iojs -> N/A (default)
unstable -> N/A (default)
node -> stable (-> v20.12.2) (default)
stable -> 20.12 (-> v20.12.2) (default)
lts/* -> lts/iron (-> v20.12.2)
lts/argon -> v4.9.1 (-> N/A)
lts/boron -> v6.17.1 (-> N/A)
lts/carbon -> v8.17.0 (-> N/A)
lts/dubnium -> v10.24.1 (-> N/A)
lts/erbium -> v12.22.12 (-> N/A)
lts/fermium -> v14.21.3 (-> N/A)
lts/gallium -> v16.20.2 (-> N/A)
lts/hydrogen -> v18.20.2 (-> N/A)
lts/iron -> v20.12.2
```
</details>
#### How did you install `nvm`?
install script in readme
#### What steps did you perform?
Opening a Terminal (Ubuntu)
#### What happened?
The terminal take long time since a few days to "initialise", I am using zsh and oh-my-zsh
In addition the nvm command are also slow
I have zprofed
num calls time self name
-----------------------------------------------------------------------------------
1) 1 20891.60 20891.60 97.38% 11980.82 11980.82 55.85% nvm_auto
2) 2 8901.02 4450.51 41.49% 6244.29 3122.14 29.11% nvm
3) 1 1582.49 1582.49 7.38% 1576.41 1576.41 7.35% nvm_ensure_version_installed
4) 2 1019.62 509.81 4.75% 1019.62 509.81 4.75% nvm_grep
#### What did you expect to happen?
Quicker access to my cmd line as now it take a few seconds to load it
#### Is there anything in any of your profile files that modifies the `PATH`?
# zmodload zsh/zprof
if [[ -r "${XDG_CACHE_HOME:-$HOME/.cache}/p10k-instant-prompt-${(%):-%n}.zsh" ]]; then
source "${XDG_CACHE_HOME:-$HOME/.cache}/p10k-instant-prompt-${(%):-%n}.zsh"
fi
# Path to your oh-my-zsh installation.
export ZSH="$HOME/.oh-my-zsh"
ZSH_THEME="powerlevel10k/powerlevel10k"
zstyle ':omz:update' mode auto # update automatically without asking
zstyle ':omz:plugins:nvm' lazy yes
plugins=(git python docker docker-compose zsh-autosuggestions)
source $ZSH/oh-my-zsh.sh
alias dcd="docker compose down"
alias dcu="docker compose up -d"
alias dcl="() {docker logs -f $1}"
alias dcr="dcd ; dcu"
export NVM_DIR="$HOME/.nvm"
[ -s "$NVM_DIR/nvm.sh" ] && \. "$NVM_DIR/nvm.sh" # This loads nvm
[ -s "$NVM_DIR/bash_completion" ] && \. "$NVM_DIR/bash_completion" # This loads nvm bash_completion
export PATH="$NVM_DIR:$PATH"
export PATH="/usr/local/bin:$PATH"
export ANDROID_HOME=/home/devlin/Android/Sdk
export ANDROID_NDK=/home/devlin/Android/Sdk/ndk
export PATH="$HOME/Developments/flutter/bin:$PATH"
export PATH="/home/devlin/Developments/flutter/bin:$PATH"
export PATH="/opt/oracle/instantclient_21_5:$PATH"
export LD_LIBRARY_PATH="/opt/oracle/instantclient_21_5:$LD_LIBRARY_PATH"
# Load Angular CLI autocompletion.
source <(ng completion script)
# To customize prompt, run `p10k configure` or edit ~/.p10k.zsh.
[[ ! -f ~/.p10k.zsh ]] || source ~/.p10k.zsh
# zprof
| shell: zsh,pull request wanted,performance | low | Critical |
2,465,101,148 | next.js | `app/icon.tsx` and `npm run dev` with `output: "export"` | ### Link to the code that reproduces this issue
https://github.com/abernier/bug-next-icontsx.git
### To Reproduce
```sh
$ git clone https://github.com/abernier/bug-next-icontsx.git
$ cd bug-next-icontsx
$ npm ci
$ npm run dev
```
### Current vs. Expected behavior
```sh
$ npm run dev
> myapp95@0.1.0 dev
> next dev
▲ Next.js 14.2.5
- Local: http://localhost:3000
✓ Starting...
✓ Ready in 1274ms
○ Compiling / ...
✓ Compiled / in 1538ms (537 modules)
GET / 200 in 1703ms
✓ Compiled in 114ms (250 modules)
✓ Compiled /icon in 76ms (311 modules)
⨯ Error: Page "/icon/[[...__metadata_id__]]/route" is missing exported function "generateStaticParams()", which is required with "output: export" config.
at DevServer.renderToResponseWithComponentsImpl (/Users/abernier/tmp/bug-next-icontsx/node_modules/next/dist/server/base-server.js:1082:27)
at process.processTicksAndRejections (node:internal/process/task_queues:95:5)
at async DevServer.renderPageComponent (/Users/abernier/tmp/bug-next-icontsx/node_modules/next/dist/server/base-server.js:1931:24)
at async DevServer.renderToResponseImpl (/Users/abernier/tmp/bug-next-icontsx/node_modules/next/dist/server/base-server.js:1969:32)
at async DevServer.pipeImpl (/Users/abernier/tmp/bug-next-icontsx/node_modules/next/dist/server/base-server.js:920:25)
at async NextNodeServer.handleCatchallRenderRequest (/Users/abernier/tmp/bug-next-icontsx/node_modules/next/dist/server/next-server.js:272:17)
at async DevServer.handleRequestImpl (/Users/abernier/tmp/bug-next-icontsx/node_modules/next/dist/server/base-server.js:816:17)
at async /Users/abernier/tmp/bug-next-icontsx/node_modules/next/dist/server/dev/next-dev-server.js:339:20
at async Span.traceAsyncFn (/Users/abernier/tmp/bug-next-icontsx/node_modules/next/dist/trace/trace.js:154:20)
at async DevServer.handleRequest (/Users/abernier/tmp/bug-next-icontsx/node_modules/next/dist/server/dev/next-dev-server.js:336:24)
at async invokeRender (/Users/abernier/tmp/bug-next-icontsx/node_modules/next/dist/server/lib/router-server.js:174:21)
at async handleRequest (/Users/abernier/tmp/bug-next-icontsx/node_modules/next/dist/server/lib/router-server.js:353:24)
at async requestHandlerImpl (/Users/abernier/tmp/bug-next-icontsx/node_modules/next/dist/server/lib/router-server.js:377:13)
at async Server.requestListener (/Users/abernier/tmp/bug-next-icontsx/node_modules/next/dist/server/lib/start-server.js:141:13) {
page: '/icon'
}
✓ Compiled /_error in 449ms (770 modules)
GET /icon?3f809f6ad65182c2 500 in 850ms
```
build is ok though:
```sh
$ npm run build
> myapp95@0.1.0 build
> next build
▲ Next.js 14.2.5
Creating an optimized production build ...
✓ Compiled successfully
✓ Linting and checking validity of types
✓ Collecting page data
✓ Generating static pages (5/5)
✓ Collecting build traces
✓ Finalizing page optimization
Route (app) Size First Load JS
┌ ○ / 5.25 kB 92.4 kB
├ ○ /_not-found 871 B 88 kB
└ ○ /icon 0 B 0 B
+ First Load JS shared by all 87.1 kB
├ chunks/23-bc0704c1190bca24.js 31.6 kB
├ chunks/fd9d1056-2821b0f0cabcd8bd.js 53.6 kB
└ other shared chunks (total) 1.86 kB
○ (Static) prerendered as static content
```
### Provide environment information
```bash
Operating System:
Platform: darwin
Arch: arm64
Version: Darwin Kernel Version 24.0.0: Sat Jul 13 00:57:28 PDT 2024; root:xnu-11215.0.165.0.4~50/RELEASE_ARM64_T6000
Available memory (MB): 65536
Available CPU cores: 10
Binaries:
Node: 20.11.0
npm: 10.8.2
Yarn: 1.22.22
pnpm: 8.3.1
Relevant Packages:
next: 14.2.5 // Latest available version is detected (14.2.5).
eslint-config-next: 14.2.5
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)
Not sure, Metadata, Output (export/standalone)
### Which stage(s) are affected? (Select all that apply)
next dev (local)
### Additional context
_No response_ | bug,Output (export/standalone),Metadata | low | Critical |
2,465,143,668 | rust | Tracking Issue for Reproducible Build bugs and challenges | This is a tracking issue for collecting and triaging bugs and challenges that hinder our ability to produce [reproducible and deterministic builds](https://reproducible-builds.org).
This tracking issue is used as a hub for connecting to other relevant issues, e.g., bugs or open design questions. This 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 https://github.com/rust-lang/rust/labels/A-reproducibility label, and tag with OS/architecture/target labels as suitable.
This tracking issue is unlikely to be *exhaustive*. Please add suitable entries and edit as new issues and PRs pop up or if old issues and PRs are rediscovered.
<details>
<summary>Copy pastas for the inline labels</summary>
https://github.com/rust-lang/rust/labels/A-debuginfo
https://github.com/rust-lang/rust/labels/A-diagnostics
https://github.com/rust-lang/rust/labels/A-LLVM
https://github.com/rust-lang/rust/labels/A-reproducibility
https://github.com/rust-lang/rust/labels/A-run-make
https://github.com/rust-lang/rust/labels/A-testsuite
https://github.com/rust-lang/rust/labels/C-tracking-issue
https://github.com/rust-lang/rust/labels/F-trim-paths
https://github.com/rust-lang/rust/labels/T-bootstrap
https://github.com/rust-lang/rust/labels/T-cargo
https://github.com/rust-lang/rust/labels/T-compiler
https://github.com/rust-lang/rust/labels/T-lang
https://github.com/rust-lang/rust/labels/T-libs
https://github.com/rust-lang/rust/labels/T-libs-api
https://github.com/rust-lang/rust/labels/T-infra
https://github.com/rust-lang/rust/labels/T-rustdoc
https://github.com/rust-lang/rust/labels/O-wasm
https://github.com/rust-lang/rust/labels/O-windows
https://github.com/rust-lang/rust/labels/O-windows-msvc
https://github.com/rust-lang/rust/labels/O-windows-gnu
https://github.com/rust-lang/rust/labels/O-macos
https://github.com/rust-lang/rust/labels/O-apple
https://github.com/rust-lang/rust/labels/O-AArch64
https://github.com/rust-lang/rust/labels/O-x86_64
</details>
## Bugs and issues
- [ ] `tests/run-make/reproducible-builds` (https://github.com/rust-lang/rust/labels/T-compiler, https://github.com/rust-lang/rust/labels/A-testsuite, https://github.com/rust-lang/rust/labels/A-run-make; several skipped combinations due to unreproducibility)
- [ ] https://github.com/rust-lang/rust/issues/82188 (https://github.com/rust-lang/rust/labels/T-compiler, https://github.com/rust-lang/rust/labels/O-windows-msvc; needs further investigation)
- [ ] https://github.com/rust-lang/rust/issues/18370 (https://github.com/rust-lang/rust/labels/T-rustdoc; status unclear)
- [ ] https://github.com/rust-lang/rust/issues/38550 (https://github.com/rust-lang/rust/labels/T-compiler; related to `-Z randomize-layout`, status unclear)
- [ ] https://github.com/rust-lang/rust/issues/66251 (https://github.com/rust-lang/rust/labels/T-compiler, https://github.com/rust-lang/rust/labels/A-diagnostics, `--remap-path-prefix`; sysroot handling in diagnostics)
- [ ] https://github.com/rust-lang/rust/issues/69060 (https://github.com/rust-lang/rust/labels/T-compiler, https://github.com/rust-lang/rust/labels/A-LLVM, perf; unclear what's to do here)
- [ ] https://github.com/rust-lang/rust/issues/69352 (https://github.com/rust-lang/rust/labels/T-compiler, https://github.com/rust-lang/rust/labels/A-LLVM; possible non-determinism in LLVM)
- [ ] https://github.com/rust-lang/rust/issues/73501 (https://github.com/rust-lang/rust/labels/T-compiler, https://github.com/rust-lang/rust/labels/A-testsuite, https://github.com/rust-lang/rust/labels/A-mir-opt; unsure how to repro/debug)
- [ ] https://github.com/rust-lang/rust/issues/73932 (https://github.com/rust-lang/rust/labels/T-compiler, https://github.com/rust-lang/rust/labels/A-linkage; Stable Version Hashes)
- [ ] https://github.com/rust-lang/rust/issues/74786 (https://github.com/rust-lang/rust/labels/T-compiler, https://github.com/rust-lang/rust/labels/A-testsuite; `--remap-path-prefix`)
- [ ] https://github.com/rust-lang/rust/issues/75887 (https://github.com/rust-lang/rust/labels/T-compiler, https://github.com/rust-lang/rust/labels/A-macros; macro expansions with deps on external files)
- [ ] https://github.com/rust-lang/rust/issues/89911 (https://github.com/rust-lang/rust/labels/T-compiler, https://github.com/rust-lang/rust/labels/A-debuginfo; `-Cdebuginfo=2`)
- [ ] https://github.com/rust-lang/rust/issues/88982 (https://github.com/rust-lang/rust/labels/T-compiler, https://github.com/rust-lang/rust/labels/A-debuginfo, https://github.com/rust-lang/rust/labels/A-linkage, https://github.com/rust-lang/rust/labels/O-windows; affects `tests/run-make/reproducible-builds`, bin, `--remap-path-prefix`, `-Z remap-cwd-prefix`)
- [ ] https://github.com/rust-lang/rust/issues/129117 (https://github.com/rust-lang/rust/labels/T-compiler, https://github.com/rust-lang/rust/labels/A-testsuite, https://github.com/rust-lang/rust/labels/A-run-make; `-Cdebuginfo=2`, `-Z remap-cwd-prefix=.`, rlib)
Tracking/meta issues:
- [ ] https://github.com/rust-lang/rust/issues/75362 (https://github.com/rust-lang/rust/labels/T-infra)
- [ ] https://github.com/rust-lang/rust/issues/65042 (https://github.com/rust-lang/rust/labels/T-compiler)
- [ ] https://github.com/rust-lang/rust/issues/84232 (https://github.com/rust-lang/rust/labels/T-compiler)
- [ ] https://github.com/rust-lang/rust/issues/111540 (https://github.com/rust-lang/rust/labels/C-tracking-issue)
- [ ] https://github.com/rust-lang/rust/issues/89434 (https://github.com/rust-lang/rust/labels/C-tracking-issue)
Resolved:
- [x] https://github.com/rust-lang/rust/issues/66568 (https://github.com/rust-lang/rust/labels/T-compiler, https://github.com/rust-lang/rust/labels/A-debuginfo; `-Cdebuginfo=2`)
- [x] https://github.com/rust-lang/rust/issues/47086 (https://github.com/rust-lang/rust/labels/T-compiler, https://github.com/rust-lang/rust/labels/A-debuginfo; `-Cdebuginfo=2`)
- [x] https://github.com/rust-lang/rust/issues/24473 (https://github.com/rust-lang/rust/labels/T-rustdoc)
- [x] https://github.com/rust-lang/rust/issues/34902 (https://github.com/rust-lang/rust/labels/T-compiler; current status unclear)
- [x] https://github.com/rust-lang/rust/issues/44074 (
https://github.com/rust-lang/rust/labels/T-compiler; env var info)
- [x] https://github.com/rust-lang/rust/issues/45397 (https://github.com/rust-lang/rust/labels/A-LLVM, https://github.com/rust-lang/rust/labels/A-debuginfo; looks LLVM related, seems to have resolved)
- [x] https://github.com/rust-lang/rust/issues/90301 (https://github.com/rust-lang/rust/labels/A-LLVM, https://github.com/rust-lang/rust/labels/A-debuginfo)
- Upstream fix: https://reviews.llvm.org/D113468
- [x] https://github.com/rust-lang/rust/issues/90357
- [x] https://github.com/rust-lang/rust/issues/47086 (https://github.com/rust-lang/rust/labels/T-compiler, https://github.com/rust-lang/rust/labels/O-macos, https://github.com/rust-lang/rust/labels/A-debuginfo)
- [x] https://github.com/rust-lang/rust/issues/57041 (insufficiently specific)
- [x] https://github.com/rust-lang/cargo/issues/6914 (https://github.com/rust-lang/rust/labels/T-cargo; resolved separately)
- [x] https://github.com/rust-lang/rust/issues/61216 (https://github.com/rust-lang/rust/labels/T-rustdoc; resolved in a separate improvement PR but can't find which)
- [x] https://github.com/rust-lang/rust/issues/63713 (https://github.com/rust-lang/rust/labels/T-compiler)
- Related: #65036
- [x] https://github.com/rust-lang/rust/issues/65036 (https://github.com/rust-lang/rust/labels/T-compiler, https://github.com/rust-lang/rust/labels/A-testsuite)
- [x] https://github.com/rust-lang/rust/issues/81296 (https://github.com/rust-lang/rust/labels/T-compiler, https://github.com/rust-lang/rust/labels/A-testsuite)
- [x] https://github.com/rust-lang/rust/issues/66568 (https://github.com/rust-lang/rust/labels/T-compiler, https://github.com/rust-lang/rust/labels/O-macos, https://github.com/rust-lang/rust/labels/A-run-make, https://github.com/rust-lang/rust/labels/A-testsuite)
- [x] https://github.com/rust-lang/rust/issues/66955 (https://github.com/rust-lang/rust/labels/T-compiler; `--remap-path-prefix`)
- [x] https://github.com/rust-lang/rust/issues/75263 (https://github.com/rust-lang/rust/labels/T-compiler; `--remap-path-prefix` involved)
- [x] https://github.com/rust-lang/rust/issues/73167 (https://github.com/rust-lang/rust/labels/T-compiler; `--remap-path-prefix` involved)
- [x] https://github.com/rust-lang/rust/issues/40552 (closed in favor of more specific issues and RFC-based approaches)
- [x] https://github.com/rust-lang/rust/issues/84125 (https://github.com/rust-lang/rust/labels/T-compiler; `--remap-path-prefix` involved)
- [x] https://github.com/rust-lang/cargo/issues/9311 (https://github.com/rust-lang/rust/labels/T-cargo)
- [x] https://github.com/rust-lang/rust/issues/71222 (https://github.com/rust-lang/rust/labels/T-compiler, https://github.com/rust-lang/rust/labels/A-diagnostics)
- [x] https://github.com/rust-lang/rust/issues/72913 (https://github.com/rust-lang/rust/labels/T-compiler, https://github.com/rust-lang/rust/labels/A-diagnostics)
- [x] https://github.com/rust-lang/rust/issues/76496 (https://github.com/rust-lang/rust/labels/T-compiler, https://github.com/rust-lang/rust/labels/A-diagnostics)
- [x] https://github.com/rust-lang/rust/issues/80776 (https://github.com/rust-lang/rust/labels/T-compiler, https://github.com/rust-lang/rust/labels/A-diagnostics, https://github.com/rust-lang/rust/labels/O-wasm)
- [x] https://github.com/rust-lang/rust/issues/82074 (https://github.com/rust-lang/rust/labels/T-compiler, `--remap-path-prefix`)
- [x] https://github.com/rust-lang/rust/issues/82108 (https://github.com/rust-lang/rust/labels/T-compiler, `--remap-path-prefix`; paths reverse order from clang/gcc but was intentional)
- [x] https://github.com/rust-lang/rust/issues/82392 (https://github.com/rust-lang/rust/labels/T-compiler, `-Crpath`)
- [x] https://github.com/rust-lang/rust/issues/87325 (https://github.com/rust-lang/rust/labels/T-compiler, `-Z remap-cwd-prefix`; closed in favor of tracking issue #89434 for `-Z remap-cwd-prefix`)
- [x] https://github.com/rust-lang/rust/issues/87825 (https://github.com/rust-lang/rust/labels/T-compiler, https://github.com/rust-lang/rust/labels/A-debuginfo, https://github.com/rust-lang/rust/labels/O-windows-msvc, `--remap-path-prefix`)
- [x] https://github.com/rust-lang/rust/issues/90357 (https://github.com/rust-lang/rust/labels/T-compiler, https://github.com/rust-lang/rust/labels/A-debuginfo, https://github.com/rust-lang/rust/labels/A-llvm, https://github.com/rust-lang/rust/labels/A-lto)
- [x] https://github.com/rust-lang/rust/issues/113584 (https://github.com/rust-lang/rust/labels/T-compiler; issue disappeared after stable version update but unclear what fixed it)
- [x] https://github.com/rust-lang/rust/issues/119372 (https://github.com/rust-lang/rust/labels/T-compiler, `compiler_builtins`)
- [x] https://github.com/rust-lang/rust/issues/124357 (fuchsia build system specific, unclear)
- [x] https://github.com/rust-lang/rust/issues/73740 (https://github.com/rust-lang/rust/labels/T-compiler, https://github.com/rust-lang/rust/labels/A-debuginfo, https://github.com/rust-lang/rust/labels/A-diagnostics, `--remap-path-prefix`)
- [x] https://github.com/rust-lang/rust/issues/88754 (https://github.com/rust-lang/rust/labels/T-compiler, https://github.com/rust-lang/rust/labels/A-diagnostics)
## Related issues, RFCs, MCPs and discussions
- https://github.com/rust-lang/rust/pull/108312 (https://github.com/rust-lang/rust/labels/T-compiler)
- https://github.com/rust-lang/rfcs/pull/3127 (https://github.com/rust-lang/rust/labels/F-trim-paths)
- https://github.com/rust-lang/compiler-team/issues/450
## Related PRs
- [x] https://github.com/rust-lang/rust/pull/71858
- [x] https://github.com/rust-lang/rust/pull/89041
- [x] https://github.com/rust-lang/rust/pull/71931
- [x] https://github.com/rust-lang/rust/pull/64131
- [x] https://github.com/rust-lang/rust/pull/65043
- [x] https://github.com/rust-lang/rust/pull/81393
- [x] https://github.com/rust-lang/rust/pull/88771
- [x] https://github.com/rust-lang/rust/pull/106977
- [x] https://github.com/rust-lang/rust/pull/84233
- [x] https://github.com/rust-lang/rust/pull/115214
- [x] https://github.com/rust-lang/rust/pull/122450
- [x] https://github.com/rust-lang/cargo/pull/12625
- [x] https://github.com/rust-lang/rust/pull/128736
- [x] https://github.com/rust-lang/cargo/pull/6966
- [x] https://github.com/rust-lang/rust/pull/71310
- [x] https://github.com/rust-lang/rust/pull/72982
- [x] https://github.com/rust-lang/rust/pull/76515
- [x] https://github.com/rust-lang/rust/pull/82102
- [x] https://github.com/rust-lang/rust/pull/91566
- [x] https://github.com/rust-lang/rust/pull/86025
- [x] https://github.com/rust-lang/rust/pull/87320
- [x] https://github.com/rust-lang/rust/pull/121297
- [x] https://github.com/rust-lang/rust/pull/95685
- [x] https://github.com/rust-lang/compiler-builtins/pull/549
- [x] https://github.com/rust-lang/rust/pull/107099 | A-debuginfo,A-diagnostics,T-compiler,T-bootstrap,T-infra,C-tracking-issue,A-reproducibility,D-diagnostic-infra,S-tracking-forever | low | Critical |
2,465,177,840 | flutter | [Autofill] Autofill is using the old value of textfield after the value was replaced by a previously saved autofill value | ### Steps to reproduce
1. Use the app to save some credentials.
2. Restart the app.
3. Write something manually on the password textfield.
4. Go to the email textfield and select the autofill option to use the previously saved credentials.
5. The manually written password is replaced by the password from autofill.
6. Click the login button to call the finishautofillcontext and prompt the save password dialog if needed.
### Expected results
Save credentials dialog should not show up since we are using stored credentials and both the email and password are the same as before, we are not updating the credentials.
### Actual results
The user gets the save dialog prompt. The password we are trying to save is the password we initially wrote before it got replaced by the one from the autofill.
### Code sample
<details open><summary>Code sample</summary>
```dart
import 'package:flutter/material.dart';
import 'package:flutter/services.dart';
void main() {
runApp(const MyApp());
}
class MyApp extends StatelessWidget {
const MyApp({super.key});
@override
Widget build(BuildContext context) {
return MaterialApp(
title: 'Flutter Demo',
theme: ThemeData(
colorScheme: ColorScheme.fromSeed(seedColor: Colors.deepPurple),
useMaterial3: true,
),
home: const MyHomePage(),
);
}
}
class MyHomePage extends StatefulWidget {
const MyHomePage({super.key});
@override
State<MyHomePage> createState() => _MyHomePageState();
}
class _MyHomePageState extends State<MyHomePage> {
final TextEditingController emailController = TextEditingController();
final TextEditingController passwordController = TextEditingController();
@override
Widget build(BuildContext context) {
return Scaffold(
appBar: AppBar(),
body: AutofillGroup(
child: Column(
mainAxisAlignment: MainAxisAlignment.center,
children: <Widget>[
TextField(
controller: emailController,
keyboardType: TextInputType.emailAddress,
autofillHints: const [AutofillHints.email],
),
TextField(
controller: passwordController,
autofillHints: const [AutofillHints.password],
keyboardType: TextInputType.visiblePassword,
),
ElevatedButton(
onPressed: () {
print("EmailControllerText: ${emailController.text}");
print("PasswordControllerText: ${passwordController.text}");
TextInput.finishAutofillContext();
},
child: Text('login'),
)
],
),
),
);
}
}
```
</details>
### Screenshots or Video
_No response_
### Logs
_No response_
### Flutter Doctor output
<details open><summary>Doctor output</summary>
```console
[✓] Flutter (Channel stable, 3.24.0, on macOS 14.4.1 23E224 darwin-arm64, locale es-ES)
• Flutter version 3.24.0 on channel stable at /Users/danielcastro/dev/flutter
• Upstream repository https://github.com/flutter/flutter.git
• Framework revision 80c2e84975 (2 weeks ago), 2024-07-30 23:06:49 +0700
• Engine revision b8800d88be
• Dart version 3.5.0
• DevTools version 2.37.2
[✓] Android toolchain - develop for Android devices (Android SDK version 35.0.0)
• Android SDK at /Users/danielcastro/Library/Android/sdk
• Platform android-35, build-tools 35.0.0
• Java binary at: /Applications/Android Studio.app/Contents/jbr/Contents/Home/bin/java
• Java version OpenJDK Runtime Environment (build 17.0.11+0-17.0.11b1207.24-11852314)
• All Android licenses accepted.
[✓] Xcode - develop for iOS and macOS (Xcode 15.4)
• Xcode at /Applications/Xcode.app/Contents/Developer
• Build 15F31d
• CocoaPods version 1.15.2
[✓] Chrome - develop for the web
• Chrome at /Applications/Google Chrome.app/Contents/MacOS/Google Chrome
[✓] Android Studio (version 2024.1)
• 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 17.0.11+0-17.0.11b1207.24-11852314)
[✓] Connected device (4 available)
• 23013PC75G (mobile) • ffd52427 • android-arm64 • Android 14 (API 34)
• macOS (desktop) • macos • darwin-arm64 • macOS 14.4.1 23E224 darwin-arm64
• Mac Designed for iPad (desktop) • mac-designed-for-ipad • darwin • macOS 14.4.1 23E224 darwin-arm64
• Chrome (web) • chrome • web-javascript • Google Chrome 127.0.6533.100
! Error: Browsing on the local area network for iPhone de Daniel. 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)
[✓] Network resources
• All expected network resources are available.
• No issues found!
```
</details>
### Notes
* The controllers show the replaced value, not the old one, so there is no issues login in in the real world, the only issue is the Autofill prompting with old credentials.
* If we focus and unfocus the textfield after it was updated, the issue does not happen.
* I have only tested this code on Android.
| a: text input,platform-android,framework,has reproducible steps,P2,team-text-input,triaged-text-input,found in release: 3.24 | low | Critical |
2,465,178,540 | deno | Feat: shareable presets for formatting and linting | ## Need
The direct integration of formatting and linting into the deno cli is one of its strengths. With the monorepo support these configurations can also be shared with multiple subprojects within the same repository. There is, however, no way to share something like a company style guide for fmt or linting between multiple repositories right now without manual copy and paste of the sections within `deno.json`. With 20+ repositories this is simply not feasible.
## Feature ideas
- As a developer I want to be able to be able to specify my linting and formatting configuration for deno in a way that is shareable between deno projects. Maybe published via JSR and extended/referenced in the concrete `deno.json`.
- As a developer I want deno to pick its formatting defaults from a pre existing [`.editorconfig`](https://editorconfig.org/), if present - like [prettier is doing](https://prettier.io/docs/en/configuration.html#editorconfig). Since editorconfig should be a project- and IDE-independent config file, it can easily be synced via something like [Repo File Sync Action](https://github.com/marketplace/actions/repo-file-sync-action).
On a side note, are there any plans to extend the linting rules or make them extendable by the community? Something like [no-floating-promises](https://typescript-eslint.io/rules/no-floating-promises/) would be really nice. | feat | low | Minor |
2,465,212,956 | godot | Release build has tree_exiting error that doesn't occur in debug build/editor (Windows, MinGW/GCC LTO regression) | ### Tested versions
Reproducible in 4.3rc3, 4.3rc2
### System information
Windows 10
### Issue description
I have a project that plays in editor with no errors, exported debug builds play fine too, but exported release builds have a new major error: a type of object that is meant to be destroyed will not be removed and give this error:
```
ERROR: Attempt to disconnect a nonexistent connection from '@AnimatableBody2D@557:<AnimatableBody2D#149350782344>'. Signal: 'tree_exiting', callable: ''.
at: (core/object/object.cpp:1462)
```
There isn't any code that connects to these objects tree_exiting signal.
I've tried Windows and Web builds and it happens in both.
It's worth noting the project was originally created in 4.2.1, it never had these errors in editor but no builds were tested until bringing it to 4.3, so I have no idea if this error is specific to 4.3 or can happen in older versions. When I attempt to open it back up in 4.2.1 any builds are broken and the log tells me it can't open scenes made in 4.3.
### Steps to reproduce
Export a Windows 64bit build with debug enabled and it will play correctly, clicking on tiles will make them disappear.
Then export a Windows 64bit build with debug disabled and launch with the console, the tiles will not disappear and multiple identical errors fill the log.
### Minimal reproduction project (MRP)
[broken-export.zip](https://github.com/user-attachments/files/16609515/broken-export.zip)
| bug,platform:windows,topic:buildsystem,confirmed,regression | medium | Critical |
2,465,308,087 | yt-dlp | [BongaCams] Can't download stream of certain model | ### DO NOT REMOVE OR SKIP THE ISSUE TEMPLATE
- [X] I understand that I will be **blocked** if I *intentionally* remove or skip any mandatory\* field
### Checklist
- [X] I'm reporting that yt-dlp is broken on a **supported** site
- [X] I've verified that I have **updated yt-dlp to nightly or master** ([update instructions](https://github.com/yt-dlp/yt-dlp#update-channels))
- [X] I've checked that all provided URLs are playable in a browser with the same IP and same login details
- [X] I've checked that all URLs and arguments with special characters are [properly quoted or escaped](https://github.com/yt-dlp/yt-dlp/wiki/FAQ#video-url-contains-an-ampersand--and-im-getting-some-strange-output-1-2839-or-v-is-not-recognized-as-an-internal-or-external-command)
- [X] I've searched [known issues](https://github.com/yt-dlp/yt-dlp/issues/3766) and the [bugtracker](https://github.com/yt-dlp/yt-dlp/issues?q=) for similar issues **including closed ones**. DO NOT post duplicates
- [X] I've read the [guidelines for opening an issue](https://github.com/yt-dlp/yt-dlp/blob/master/CONTRIBUTING.md#opening-an-issue)
- [X] I've read about [sharing account credentials](https://github.com/yt-dlp/yt-dlp/blob/master/CONTRIBUTING.md#are-you-willing-to-share-account-details-if-needed) and I'm willing to share it if required
### Region
Russia
### Provide a description that is worded well enough to be understood
Tried to run cmd as administrator as well.
I'm using yt-dlp.exe for win11. Extracted to folder, where ffmpeg and other tools are stored.
### Provide verbose output that clearly demonstrates the problem
- [X] Run **your** yt-dlp command with **-vU** flag added (`yt-dlp -vU <your command line>`)
- [ ] If using API, add `'verbose': True` to `YoutubeDL` params instead
- [X] Copy the WHOLE output (starting with `[debug] Command-line config`) and insert it below
### Complete Verbose Output
```shell
[debug] Command-line config: ['-vU', 'https://ru4.bongacams.com/seventh-heaven']
[debug] Encodings: locale cp1251, fs utf-8, pref cp1251, out utf-8, error utf-8, screen utf-8
[debug] yt-dlp version stable@2024.08.06 from yt-dlp/yt-dlp [4d9231208] (win_exe)
[debug] Python 3.8.10 (CPython AMD64 64bit) - Windows-10-10.0.22631-SP0 (OpenSSL 1.1.1k 25 Mar 2021)
[debug] exe versions: ffmpeg N-116527-g9a2171318d-20240804 (setts), ffprobe N-116527-g9a2171318d-20240804
[debug] Optional libraries: Cryptodome-3.20.0, brotli-1.1.0, certifi-2024.07.04, curl_cffi-0.5.10, mutagen-1.47.0, requests-2.32.3, sqlite3-3.35.5, urllib3-2.2.2, websockets-12.0
[debug] Proxy map: {}
[debug] Request Handlers: urllib, requests, websockets, curl_cffi
[debug] Loaded 1830 extractors
[debug] Fetching release info: https://api.github.com/repos/yt-dlp/yt-dlp/releases/latest
Latest version: stable@2024.08.06 from yt-dlp/yt-dlp
yt-dlp is up to date (stable@2024.08.06 from yt-dlp/yt-dlp)
[BongaCams] Extracting URL: https://ru4.bongacams.com/seventh-heaven
[BongaCams] seventh-heaven: Downloading JSON metadata
ERROR: seventh-heaven: An extractor error has occurred. (caused by KeyError('localData')); please report this issue on https://github.com/yt-dlp/yt-dlp/issues?q= , filling out the appropriate issue template. Confirm you are on the latest version using yt-dlp -U
File "yt_dlp\extractor\common.py", line 740, in extract
File "yt_dlp\extractor\bongacams.py", line 47, in _real_extract
KeyError: 'localData'
D:\Downloads\ffmpeg-master-latest-win64-gpl\bin>yt-dlp -U
Latest version: stable@2024.08.06 from yt-dlp/yt-dlp
yt-dlp is up to date (stable@2024.08.06 from yt-dlp/yt-dlp)
```
| NSFW,site-bug,triage | low | Critical |
2,465,320,591 | vscode | ignore comment change while diff | e.g: in `c`
```diff
- var a = READ(0x4000_0100); // reg timer_0
+ var a = READ(0x4000_0100); // reg timer_1
```
add support to ignore the change of comment like above
| feature-request,diff-editor | low | Minor |
2,465,335,313 | angular | Custom `injector` for templates breaks `@Host` inject flag | ### Which @angular/* package(s) are the source of the bug?
core
### Is this a regression?
No
### Description
When passing custom injector while creating a view, either with `ngTemplateOutlet` or manually with `ViewContainerRef`, if some injection had `@Host` flag inside that template it breaks and leaks outside.
### Please provide a link to a minimal reproduction of the bug
https://stackblitz.com/edit/stackblitz-starters-krtzpp
### Please provide the exception or error you saw
I have a component that implements `ControlValueAccessor`. Inside its template I use `[(ngModel)]`. It all worked fine until I tried to use that component in a template and instantiate that template with custom injector. I started to get exception that `ngModel` cannot be used with reactive forms, however source code for `NgModel` shows it uses `@Host` decorator to inject parent only if it's the same host. So it shouldn't have reached outside my `ControlValueAccessor` component and see that it is used with reactive forms. I've attached a minimal reproduction on StackBlitz to see the issue.
### Please provide the environment you discovered this bug in (run `ng version`)
```true
Angular 16+
```
### Anything else?
_No response_ | area: core,core: di | low | Critical |
2,465,338,496 | ollama | AMD Multiple GPU support | ### Hi,
I think the current AMD ROCm doesn’t work well with multiple video cards. I have an XTX 7900 (24GB) and an XT 7900 (20GB). My processor also has a small integrated GPU, but that shouldn’t be a problem.
When I try to load the model llama3.1:70b (39GB):
1. It doesn’t crash, but it has an infinite load time (at least 10 minutes, maybe more).
2. My PC gets stuck; I can’t move my mouse or do anything else, including exiting the loading process with Ctrl+C.
3. It uses (not very actively) only one GPU
4. The CPU is also loaded in the server process (only a few cores), and the only way to exit this mode is to shut down with the power button.
here my [server.log](https://github.com/user-attachments/files/16610677/server.log)
I can try anything you want, just tell me what to do (recompile llama.cpp or something else).
### OS
Windows
### GPU
AMD
### CPU
AMD
### Ollama version
0.3.6 | bug,windows,amd | low | Critical |
2,465,344,418 | electron | [Bug]: set WebContentsView on the top of another View, webkit-app-region: no-drag doesn't works on Electron 30 and later | ### Preflight Checklist
- [X] I have read the [Contributing Guidelines](https://github.com/electron/electron/blob/main/CONTRIBUTING.md) for this project.
- [X] I agree to follow the [Code of Conduct](https://github.com/electron/electron/blob/main/CODE_OF_CONDUCT.md) that this project adheres to.
- [X] I have searched the [issue tracker](https://www.github.com/electron/electron/issues) for a bug report that matches the one I want to file, without success.
### Electron Version
30+
### What operating system(s) are you using?
Windows, macOS
### Operating System Version
Windows 10, macOS 13.6
### What arch are you using?
x64
### Last Known Working Electron version
_No response_
### Expected Behavior
<img width="652" alt="image" src="https://github.com/user-attachments/assets/a92bc4c7-bbe8-4b05-aa89-0e6f97cd2eca">
After designating the red area of the BrowserWindow as a draggable region with webkit-app-region:drag, when a WebContentView is added to the BrowserWindow.contentView, the blue area also becomes draggable.
This happens even if the blue area has been set as a non-draggable region with no-drag, indicating that it's still influenced by the draggable settings of the BrowserWindow.
### Actual Behavior
When a BrowserWindow or another WebContentView adds a childView, the drag response is done according to the webkit-app-region behavior of the top childView.
### Testcase Gist URL
https://gist.github.com/ksky521/091af6d9782583141564278002b6d235
### Additional Information
_No response_ | platform/windows,platform/macOS,bug :beetle:,status/confirmed,has-repro-gist,component/draggable-regions,component/WebContentsView,30-x-y,31-x-y,32-x-y | low | Critical |
2,465,382,654 | flutter | [google_maps_flutter ] Image Size/Ratio Issue with New BitmapDescriptor Methods in v2.9.0 | ### Steps to reproduce
Ensure you are using Flutter version 3.22.3.
Add the google_maps_flutter: ^2.9.0 package to your pubspec.yaml.
Create a custom map marker
Use the BitmapDescriptor.asset or BitmapDescriptor.bytes method to generate a custom marker.
Provide an ImageConfiguration object to specify the desired size and other properties of the marker image.
Add the marker to a Google Map
Observe the map marker's size and aspect ratio when it is rendered on the map.
### Expected results
The map marker should appear with the correct size and aspect ratio as specified by the ImageConfiguration.
### Actual results
The map marker appears with an incorrect size and aspect ratio, resulting in a distorted image.
Reverting to the deprecated methods BitmapDescriptor.fromAssetImage and BitmapDescriptor.fromBytes results in the marker being displayed with the correct size and aspect ratio.
### Code sample
<details open><summary>Code sample</summary>
```dart
final imageConfiguration = createLocalImageConfiguration(
context,
size: const Size.square(32),
);
_selectedPinDescriptor ??= await BitmapDescriptor.assets(
imageConfiguration,
Assets.icon.mapPinSelected.path,
);
```
</details>
### Screenshots or Video
<details open>
<summary>Screenshots / Video demonstration</summary>
effected one with new method:
<img width="391" alt="image" src="https://github.com/user-attachments/assets/6b34a302-36e1-40b4-8cd8-5dc1dcd568d3">
correct one with old method:
<img width="392" alt="image" src="https://github.com/user-attachments/assets/bf49c5d8-a694-4a05-ac43-f4a47698ec84">
</details>
### Flutter Doctor output
<details open><summary>Doctor output</summary>
```console
[!] Flutter (Channel stable, 3.22.3, on macOS 14.1.2 23B92 darwin-arm64, locale en-DE)
• Flutter version 3.22.3 on channel stable at /Users/saminsheyda/Development/tools/flutter_versions/3.22.3
! Warning: `dart` on your path resolves to /opt/homebrew/Cellar/dart/3.5.0/libexec/bin/dart, which is not inside your current Flutter SDK checkout at /Users/saminsheyda/Development/tools/flutter_versions/3.22.3. Consider adding /Users/saminsheyda/Development/tools/flutter_versions/3.22.3/bin to the front of your path.
• Upstream repository https://github.com/flutter/flutter.git
• Framework revision b0850beeb2 (4 weeks ago), 2024-07-16 21:43:41 -0700
• Engine revision 235db911ba
• Dart version 3.4.4
• DevTools version 2.34.3
• If those were intentional, you can disregard the above warnings; however it is recommended to use "git" directly to perform update checks and upgrades.
[✓] Android toolchain - develop for Android devices (Android SDK version 34.0.0)
• Android SDK at /Users/saminsheyda/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 15.4)
• Xcode at /Applications/Xcode.app/Contents/Developer
• Build 15F31d
• 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)
[✓] VS Code (version 1.83.1)
• VS Code at /Users/saminsheyda/Downloads/Visual Studio Code 2.app/Contents
• Flutter extension can be installed from:
🔨 https://marketplace.visualstudio.com/items?itemName=Dart-Code.flutter
[✓] VS Code (version 1.80.0)
• VS Code at /Users/saminsheyda/Downloads/Visual Studio Code.app/Contents
• Flutter extension can be installed from:
🔨 https://marketplace.visualstudio.com/items?itemName=Dart-Code.flutter
[✓] Connected device (5 available)
• sdk gphone64 arm64 (mobile) • emulator-5556 • android-arm64 • Android 13 (API 33) (emulator)
• iPhone 14 (mobile) • 5D9563A6-40B3-4251-81A8-503AE8186F50 • ios • com.apple.CoreSimulator.SimRuntime.iOS-17-5 (simulator)
• macOS (desktop) • macos • darwin-arm64 • macOS 14.1.2 23B92 darwin-arm64
• Mac Designed for iPad (desktop) • mac-designed-for-ipad • darwin • macOS 14.1.2 23B92 darwin-arm64
• Chrome (web) • chrome • web-javascript • Google Chrome 127.0.6533.100
! Error: Browsing on the local area network for iPhone. 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)
! Error: Browsing on the local area network for Samin’s iPhone. 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)
[✓] Network resources
• All expected network resources are available.
```
</details>
Please investigate and resolve this issue so that the new BitmapDescriptor.asset and BitmapDescriptor.bytes methods correctly apply the ImageConfiguration as expected. | p: maps,package,team-ecosystem,has reproducible steps,P2,triaged-ecosystem,found in release: 3.24 | low | Critical |
2,465,384,046 | rust | Recommend *var for comparison when Deref<Target = str> | ### Code
```Rust
use std::boxed::Box;
use std::ops::Deref;
#[derive(Debug, Eq, PartialEq)]
pub enum CowStr<'a> {
/// An owned, immutable string.
Boxed(Box<str>),
/// A borrowed string.
Borrowed(&'a str),
}
impl<'a> Deref for CowStr<'a> {
type Target = str;
fn deref(&self) -> &str {
match self {
CowStr::Boxed(ref b) => b,
CowStr::Borrowed(b) => b,
}
}
}
fn main() {
let a = CowStr::Borrowed("foo");
if a == "foo" {
println!("OK");
}
}
```
### Current output
```Shell
error[E0308]: mismatched types
--> src/main.rs:25:13
|
25 | if a == "foo" {
| ^^^^^ expected `CowStr<'_>`, found `&str`
|
help: try wrapping the expression in `CowStr::Borrowed`
|
25 | if a == CowStr::Borrowed("foo") {
| +++++++++++++++++ +
For more information about this error, try `rustc --explain E0308`.
error: could not compile `testrust` (bin "testrust") due to 1 previous error
```
### Desired output
```Shell
error[E0277]: can't compare `CowStr<'_>` with `str`
--> src/main.rs:25:11
|
25 | if a == "foo" {
| ^^ no implementation for `CowStr<'_> == str`
|
= help: the trait `PartialEq<str>` is not implemented for `CowStr<'_>`
= help: both types can be dereferenced to `str`
help: consider dereferencing both sides of the expression
|
25 - if a == "foo" {
25 + if *a == *"foo" {
|
For more information about this error, try `rustc --explain E0277`.
error: could not compile `testrust` (bin "testrust") due to 1 previous error
```
### Rationale and extra context
Deref both sides is easier and shorter. It should be recommended when both types deref to a type that implements PartialEq.
### Other cases
```Rust
`if &a == "foo"` already recommends deref on both sides, but not `a == "foo"`. However, assert_eq doesn't recommend deref in both cases.
```
### Rust Version
```Shell
rustc 1.82.0-nightly (41dd149fd 2024-08-11)
binary: rustc
commit-hash: 41dd149fd6a6a06795fc6b9f54cb49af2f61775f
commit-date: 2024-08-11
host: x86_64-unknown-linux-gnu
release: 1.82.0-nightly
LLVM version: 19.1.0
```
### Anything else?
_No response_ | A-diagnostics,T-compiler | low | Critical |
2,465,394,196 | rust | MIR building generates mistyped assignments for opaques in dead code | ```rust
enum Never {}
fn foo() -> impl Sized {
let ret = 'block: {
break 'block foo();
};
let _: Never = ret;
ret
}
```
results in the following MIR:
```
// MIR for `foo` after built
| User Type Annotations
| 0: user_ty: Canonical { value: Ty(Never), max_universe: U0, variables: [], defining_opaque_types: [DefId(0:6 ~ main[7eb4]::foo::{opaque#0})] }, span: src/main.rs:6:12: 6:17, inferred_ty: Never
| 1: user_ty: Canonical { value: Ty(Never), max_universe: U0, variables: [], defining_opaque_types: [DefId(0:6 ~ main[7eb4]::foo::{opaque#0})] }, span: src/main.rs:6:12: 6:17, inferred_ty: Never
|
fn foo() -> impl Sized {
let mut _0: impl Sized;
let _1: impl Sized;
scope 1 {
debug ret => _1;
scope 2 {
}
}
bb0: {
StorageLive(_1);
_1 = foo() -> [return: bb1, unwind: bb6];
}
bb1: {
goto -> bb3;
}
bb2: {
_1 = const ();
goto -> bb4;
}
bb3: {
goto -> bb4;
}
bb4: {
FakeRead(ForLet(None), _1);
PlaceMention(_1);
AscribeUserType((_1 as Never), +, UserTypeProjection { base: UserType(1), projs: [] });
_0 = move _1;
StorageDead(_1);
return;
}
bb5: {
FakeRead(ForMatchedPlace(None), _1);
unreachable;
}
bb6 (cleanup): {
resume;
}
}
```
notice the `_1 = const ();` which assigns unit to `impl Sized` even though its type is `Never`.
This should result in a type error and therefore an ICE, but apparently we never even get to test that as the block is entirely dead code :thinking: cc @oli-obk
https://github.com/rust-lang/rust/blob/fbce03b195c02e425fbb12276b8f02349048a75f/compiler/rustc_mir_build/src/build/block.rs#L342-L354 | T-compiler,A-MIR,C-bug | low | Critical |
2,465,415,732 | deno | Implement `PerformanceObserver.observe` from `node:perf_hooks` | There has been recently an update in the `grammardown` npm package that makes `ecmarkup` not work anymore in Deno (I was trying in https://github.com/tc39/ecma262/):
```
deno run -A npm:ecmarkup --verbose spec.html --multipage out
error: Uncaught Error: Not implemented: PerformanceObserver.observe
at notImplemented (ext:deno_node/_utils.ts:6:9)
at PerformanceObserver.observe (node:perf_hooks:5:5)
at reset (file:///home/nic/Documents/dev/github.com/tc39/ecma262/node_modules/.deno/grammarkdown@3.3.2/node_modules/grammarkdown/dist/performance.js:128:18)
at Object.<anonymous> (file:///home/nic/Documents/dev/github.com/tc39/ecma262/node_modules/.deno/grammarkdown@3.3.2/node_modules/grammarkdown/dist/performance.js:88:1)
at Object.<anonymous> (file:///home/nic/Documents/dev/github.com/tc39/ecma262/node_modules/.deno/grammarkdown@3.3.2/node_modules/grammarkdown/dist/performance.js:141:4)
at Module._compile (node:module:659:34)
at Object.Module._extensions..js (node:module:673:10)
at Module.load (node:module:597:32)
at Function.Module._load (node:module:484:12)
at Module.require (node:module:609:19)
```
I saw that there is already https://github.com/denoland/deno/issues/11260 open, but that one looks to be about the global web API that has the same name. | bug,node compat | low | Critical |
2,465,434,298 | deno | Support semver ranges in `deno upgrade --version=` | Due to https://github.com/denoland/deno/issues/25034 I need to downgrade to Deno 1.41. I would like to use the _latest_ 1.41.x version, since that's probably better than using 1.41.0.
The only way to do so is by checking on https://github.com/denoland/deno/releases what the latest patch was, and then run `deno upgrade --version=1.41.3`. It'd be great if I could run either `deno upgrade --version=1.41` or `deno upgrade --version=~1.41.0`, without having to first manually figure out which exact version I want.
This need would probably be more common once you release a new major version, since some projects might need Deno 1 to run and I'd want to install whatever the latest 1.x.y version was.
| cli,suggestion | low | Minor |
2,465,501,710 | tauri | xdg-open does not work in release artifacts produced by tauri-action | Hey @FabianLars
3 different, but related, functions of my application do not work when using the AppImage of my application produced by tauri-action in GitHub Actions, but work in AppImages produced locally for myself and 3 other users (as well as other methods of running the application, such as `cargo tauri dev` or other packaging formats). On my system, at least, the .RPM produced by tauri-action seems to work, and it is only the .AppImage that does not work. This issue is possibly related to tauri-apps/tauri#6172.
1. My application [OpenDeck](https://github.com/ninjadev64/OpenDeck) loads plugins, which then communicate by sending JSON events back and forth over a websocket. One such event is `openUrl`, which a plugin can send to open a URL in the user's browser, which OpenDeck handles using Tauri's shell::open (see [here](https://github.com/ninjadev64/OpenDeck/blob/4bbd9f3fc17e396d56728af4571dfdb2dc6d57e5/src-tauri/src/events/inbound/misc.rs#L19)).
2. OpenDeck also has a button to open its config directory in its settings tab, which, on Linux, [uses xdg-open using std's `Command`](https://github.com/ninjadev64/OpenDeck/blob/4bbd9f3fc17e396d56728af4571dfdb2dc6d57e5/src-tauri/src/events/frontend.rs#L469) inside a Tauri command.
3. Additionally, OpenDeck's "starter pack" plugin has a "Run Command" action, in which users can input a command to run on key down and key up. The starter pack plugin is also written in Rust, and [uses std's `Command`](https://github.com/ninjadev64/opendeck-starterpack/blob/b9bed2922f30d511266ee5fa38c3e8c6b8e829a0/src/run_command.rs#L9) to implement this action.
For example, when pressing "open config directory" when using the AppImage from GitHub Actions, run with `./opendeck_2.0.0_amd64.AppImage`, this is printed to the terminal that the AppImage was run from:
```
xdg-mime: no method available for querying MIME type of '/home/aman/.config/com.amansprojects.opendeck'
xdg-mime: mimetype argument missing
Try 'xdg-mime --help' for more information.
/tmp/.mount_opendegOqUUe/usr/bin//xdg-open: line 882: x-www-browser: command not found
XPCOMGlueLoad error for file /usr/lib64/firefox/libxul.so:
/usr/lib64/libproxy/libpxbackend-1.0.so: undefined symbol: g_once_init_leave_pointer
Couldn't load XPCOM.
/tmp/.mount_opendegOqUUe/usr/bin//xdg-open: line 882: iceweasel: command not found
/tmp/.mount_opendegOqUUe/usr/bin//xdg-open: line 882: seamonkey: command not found
/tmp/.mount_opendegOqUUe/usr/bin//xdg-open: line 882: mozilla: command not found
/tmp/.mount_opendegOqUUe/usr/bin//xdg-open: line 882: epiphany: command not found
/tmp/.mount_opendegOqUUe/usr/bin//xdg-open: line 882: konqueror: command not found
/tmp/.mount_opendegOqUUe/usr/bin//xdg-open: line 882: chromium: command not found
/tmp/.mount_opendegOqUUe/usr/bin//xdg-open: line 882: chromium-browser: command not found
/tmp/.mount_opendegOqUUe/usr/bin//xdg-open: line 882: google-chrome: command not found
/tmp/.mount_opendegOqUUe/usr/bin//xdg-open: line 882: www-browser: command not found
/tmp/.mount_opendegOqUUe/usr/bin//xdg-open: line 882: links2: command not found
/tmp/.mount_opendegOqUUe/usr/bin//xdg-open: line 882: elinks: command not found
/tmp/.mount_opendegOqUUe/usr/bin//xdg-open: line 882: links: command not found
/tmp/.mount_opendegOqUUe/usr/bin//xdg-open: line 882: lynx: command not found
```
and then it seems to finally find and open w3m on my system in the terminal in the correct directory, whereas it should open in Nautilus for me, as it does when running OpenDeck from different methods.
Or, when using the Run Command action with `xdg-open https://example.com/`, this is the stdout of the executed command:
```
XPCOMGlueLoad error for file /usr/lib64/firefox/libxul.so:
/usr/lib64/libproxy/libpxbackend-1.0.so: undefined symbol: g_once_init_leave_pointer
Couldn't load XPCOM.
```
OpenDeck is using the latest Tauri v1.7 and `uses: tauri-apps/tauri-action@v0`. I would appreciate some steps to follow to resolve this issue. | type: bug,platform: Linux,status: needs triage | low | Critical |
2,465,507,627 | tauri | [feat] Plugins should be able to self disclaim metadata | ### Describe the problem
#10596 made me remember this idea we've had. Right now we hard code all the information about plugins in the cli but it'd be better if we could store it on the plugin side instead. Useful for example if a mobile only plugin adds support for desktop at a later date.
### Describe the solution you'd like
Maybeeee a `metadata` config in the plugin's Cargo.toml file.
### Alternatives considered
Simply not doing this because http requests are always a point of failure (most often because of firewalls/proxies)
### Additional context
_No response_ | type: feature request | low | Critical |
2,465,523,094 | next.js | Next.js App Directory: Link Component Crashes on First Load with Storyblok Integration | ### Link to the code that reproduces this issue
https://stackblitz.com/edit/stackblitz-starters-xkmmhr
### To Reproduce
1. Start the project (npm run dev)
2. Click on Go to test (next link)
### Current vs. Expected behavior
When using the Next.js app directory with Storyblok, the `Link` component crashes on the first load if it navigates to another page. This issue occurs only on the initial load; reloading the page fixes the issue, and it does not reoccur until the dev server is restarted. In contrast, using a normal `a` tag works without any issues.
**Steps to Reproduce:**
1. Visit the [StackBlitz project](https://stackblitz.com/edit/stackblitz-starters-xkmmhr)
2. Click on Go to test (next link)
**Expected Behavior:**
The `Link` component should navigate to the target page without crashing on the first load.
**Additional Information:**
- The issue does not occur when using a normal `a` tag.
- The problem is resolved after a page reload and does not reappear until the dev server is restarted.
- This does not happen on the `next@13.5.6` or even on `14.0.3` [You can test here](https://stackblitz.com/edit/stackblitz-starters-wqhnoi).
### Provide environment information
```bash
Operating System:
Platform: linux
Arch: x64
Version: Ubuntu 20.04.0 LTS Wed Aug 14 2024 16:27:09 GMT+0530 (India Standard Time)
Available memory (MB): NaN
Available CPU cores: 8
Binaries:
Node: 18.20.3
npm: 10.2.3
Yarn: 1.22.19
pnpm: 8.15.6
Relevant Packages:
next: 14.2.5 // Latest available version is detected (14.2.5).
eslint-config-next: 13.5.1
react: 18.2.0
react-dom: 18.2.0
typescript: 5.2.2
Next.js Config:
output: N/A
```
### Which area(s) are affected? (Select all that apply)
Developer Experience, Navigation
### Which stage(s) are affected? (Select all that apply)
next dev (local)
### Additional context
_No response_ | bug,Navigation | low | Critical |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.