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 |
|---|---|---|---|---|---|---|
2,725,503,605 | rust | ICE: generic_const_exprs on 1.85.0-nightly | Summary:
- This is when adding const generics to an existing project (the original author is someone else). So I can't minimize it at the moment, and I most likely have some errors. But:
- nightly/stable - both are (to be) implemented.
- `stable` uses a type alias (in `src/trait_flags.rs:` `pub type TraitFlags = u8;`) instead of a custom struct. `stable` runs all tests fine.
- `nightly` (hopes to) use `generic_const_exprs`. It's behind `unstable_generic_const_own_type` feature - see the following.
Surprisingly, even though it mentions ICE, the problem shows up
- only when RUNNING tests `cargo +nightly test --features unstable_generic_const_own_type`
- but NOT when running a check on tests with `cargo +nightly check --tests --features unstable_generic_const_own_type`.
To replicate:
```bash
git clone https://github.com/peter-lyons-kehl/phantom-newtype-rs
cd phantom-newtype-rs
git checkout aaf428c25ef3f7fb1de5aa290b38e9908390fad3
cargo +nightly test --features unstable_generic_const_own_type
```
<!--
http://blog.pnkfx.org/blog/2019/11/18/rust-bug-minimization-patterns/
-->
### Code
See above.
### Meta
<!--
If you're using the stable version of the compiler, you should also check if the
bug also exists in the beta or nightly versions.
-->
```bash
# on current Manjaro x64
uname -a
Linux spectre 6.12.1-4-MANJARO #1 SMP PREEMPT_DYNAMIC Mon, 25 Nov 2024 05:36:03 +0000 x86_64 GNU/Linux
```
Rustup installed as a Manjaro (Arch) package. Both `nightly` and `stable` installed with `rustup` and current:
`rustc --version --verbose`:
```
rustc 1.85.0-nightly (9c707a8b7 2024-12-07)
binary: rustc
commit-hash: 9c707a8b769523bb6768bf58e74fa2c39cc24844
commit-date: 2024-12-07
host: x86_64-unknown-linux-gnu
release: 1.85.0-nightly
LLVM version: 19.1.5
```
### Error output
See also attached ICE TXT files.
```
<output>
(SKIPPED WARNINGS)
running 2 tests
test instant::tests::test_complex_instant_arithmetics ... ok
test trait_flag::test_flags::all ... ok
test result: ok. 2 passed; 0 failed; 0 ignored; 0 measured; 0 filtered out; finished in 0.00s
Doc-tests phantom_newtype
running 32 tests
test src/amount.rs - amount::Amount (line 138) ... FAILED
test src/amount.rs - amount::Amount (line 126) ... FAILED
test src/amount.rs - amount::Amount (line 31) - compile fail ... ok
test src/amount.rs - amount::Amount (line 108) ... ok
test src/amount.rs - amount::Amount (line 47) ... FAILED
test src/amount.rs - amount::Amount (line 65) ... FAILED
test src/amount.rs - amount::Amount (line 82) ... FAILED
test src/amount.rs - amount::Amount (line 96) ... FAILED
test src/amount.rs - amount::Amount<TF,Unit,Repr>::get (line 157) ... FAILED
test src/amount.rs - amount::Amount<TF,Unit,Repr>::display (line 206) ... FAILED
test src/amount.rs - amount::Amount<TF,Unit,Repr>::unit (line 185) ... FAILED
test src/id.rs - id::Id (line 48) - compile fail ... ok
test src/id.rs - id::Id (line 127) ... ok
test src/id.rs - id::Id (line 30) ... ok
test src/id.rs - id::Id (line 113) ... ok
test src/id.rs - id::Id (line 62) ... ok
test src/id.rs - id::Id (line 76) ... ok
test src/id.rs - id::Id<Entity,Repr>::get (line 145) ... ok
test src/id.rs - id::Id<Entity,Repr>::display (line 182) ... ok
test src/id.rs - id::Id<Entity,Repr>::new (line 161) ... ok
test src/id.rs - id::Id (line 95) ... ok
test src/instant.rs - instant::Instant (line 100) ... ok
test src/instant.rs - instant::Instant (line 132) ... FAILED
test src/instant.rs - instant::Instant (line 120) ... FAILED
test src/instant.rs - instant::Instant (line 53) ... FAILED
test src/instant.rs - instant::Instant (line 33) ... FAILED
test src/instant.rs - instant::Instant<TF,Unit,Repr>::display (line 200) ... FAILED
test src/instant.rs - instant::Instant (line 73) ... FAILED
test src/instant.rs - instant::Instant (line 88) ... FAILED
test src/to.rs - to::As (line 25) ... ignored
test src/instant.rs - instant::Instant<TF,Unit,Repr>::get (line 153) ... FAILED
test src/instant.rs - instant::Instant<TF,Unit,Repr>::unit (line 179) ... FAILED
failures:
---- src/amount.rs - amount::Amount (line 138) stdout ----
note: no errors encountered even though delayed bugs were created
note: those delayed bugs will now be shown as internal compiler errors
error: internal compiler error: Encountered anon const with inference variable args but no error reported
|
= note: delayed at compiler/rustc_trait_selection/src/traits/mod.rs:605:27 - disabled backtrace
note: we would appreciate a bug report: https://github.com/rust-lang/rust/issues/new?labels=C-bug%2C+I-ICE%2C+T-compiler&template=ice.md
note: please make sure that you have updated to the latest nightly
note: please attach the file at `/share/pkehl/GIT/phantom-newtype-rs/rustc-ice-2024-12-08T20_05_46-2074664.txt` to your bug report
query stack during panic:
end of query stack
Couldn't compile the test.
---- src/amount.rs - amount::Amount (line 126) stdout ----
note: no errors encountered even though delayed bugs were created
note: those delayed bugs will now be shown as internal compiler errors
error: internal compiler error: Encountered anon const with inference variable args but no error reported
|
= note: delayed at compiler/rustc_trait_selection/src/traits/mod.rs:605:27 - disabled backtrace
note: we would appreciate a bug report: https://github.com/rust-lang/rust/issues/new?labels=C-bug%2C+I-ICE%2C+T-compiler&template=ice.md
note: please make sure that you have updated to the latest nightly
note: please attach the file at `/share/pkehl/GIT/phantom-newtype-rs/rustc-ice-2024-12-08T20_05_46-2074666.txt` to your bug report
query stack during panic:
end of query stack
Couldn't compile the test.
---- src/amount.rs - amount::Amount (line 47) stdout ----
note: no errors encountered even though delayed bugs were created
note: those delayed bugs will now be shown as internal compiler errors
error: internal compiler error: Encountered anon const with inference variable args but no error reported
|
= note: delayed at compiler/rustc_trait_selection/src/traits/mod.rs:605:27 - disabled backtrace
note: we would appreciate a bug report: https://github.com/rust-lang/rust/issues/new?labels=C-bug%2C+I-ICE%2C+T-compiler&template=ice.md
note: please make sure that you have updated to the latest nightly
note: please attach the file at `/share/pkehl/GIT/phantom-newtype-rs/rustc-ice-2024-12-08T20_05_46-2074683.txt` to your bug report
query stack during panic:
end of query stack
Couldn't compile the test.
---- src/amount.rs - amount::Amount (line 65) stdout ----
note: no errors encountered even though delayed bugs were created
note: those delayed bugs will now be shown as internal compiler errors
error: internal compiler error: Encountered anon const with inference variable args but no error reported
|
= note: delayed at compiler/rustc_trait_selection/src/traits/mod.rs:605:27 - disabled backtrace
note: we would appreciate a bug report: https://github.com/rust-lang/rust/issues/new?labels=C-bug%2C+I-ICE%2C+T-compiler&template=ice.md
note: please make sure that you have updated to the latest nightly
note: please attach the file at `/share/pkehl/GIT/phantom-newtype-rs/rustc-ice-2024-12-08T20_05_46-2074687.txt` to your bug report
query stack during panic:
end of query stack
Couldn't compile the test.
---- src/amount.rs - amount::Amount (line 82) stdout ----
note: no errors encountered even though delayed bugs were created
note: those delayed bugs will now be shown as internal compiler errors
error: internal compiler error: Encountered anon const with inference variable args but no error reported
|
= note: delayed at compiler/rustc_trait_selection/src/traits/mod.rs:605:27 - disabled backtrace
note: we would appreciate a bug report: https://github.com/rust-lang/rust/issues/new?labels=C-bug%2C+I-ICE%2C+T-compiler&template=ice.md
note: please make sure that you have updated to the latest nightly
note: please attach the file at `/share/pkehl/GIT/phantom-newtype-rs/rustc-ice-2024-12-08T20_05_46-2074695.txt` to your bug report
query stack during panic:
end of query stack
Couldn't compile the test.
---- src/amount.rs - amount::Amount (line 96) stdout ----
note: no errors encountered even though delayed bugs were created
note: those delayed bugs will now be shown as internal compiler errors
error: internal compiler error: Encountered anon const with inference variable args but no error reported
|
= note: delayed at compiler/rustc_trait_selection/src/traits/mod.rs:605:27 - disabled backtrace
note: we would appreciate a bug report: https://github.com/rust-lang/rust/issues/new?labels=C-bug%2C+I-ICE%2C+T-compiler&template=ice.md
note: please make sure that you have updated to the latest nightly
note: please attach the file at `/share/pkehl/GIT/phantom-newtype-rs/rustc-ice-2024-12-08T20_05_46-2074703.txt` to your bug report
query stack during panic:
end of query stack
Couldn't compile the test.
---- src/amount.rs - amount::Amount<TF,Unit,Repr>::get (line 157) stdout ----
note: no errors encountered even though delayed bugs were created
note: those delayed bugs will now be shown as internal compiler errors
error: internal compiler error: Encountered anon const with inference variable args but no error reported
|
= note: delayed at compiler/rustc_trait_selection/src/traits/mod.rs:605:27 - disabled backtrace
note: we would appreciate a bug report: https://github.com/rust-lang/rust/issues/new?labels=C-bug%2C+I-ICE%2C+T-compiler&template=ice.md
note: please make sure that you have updated to the latest nightly
note: please attach the file at `/share/pkehl/GIT/phantom-newtype-rs/rustc-ice-2024-12-08T20_05_47-2074712.txt` to your bug report
query stack during panic:
end of query stack
Couldn't compile the test.
---- src/amount.rs - amount::Amount<TF,Unit,Repr>::display (line 206) stdout ----
note: no errors encountered even though delayed bugs were created
note: those delayed bugs will now be shown as internal compiler errors
error: internal compiler error: Encountered anon const with inference variable args but no error reported
|
= note: delayed at compiler/rustc_trait_selection/src/traits/mod.rs:605:27 - disabled backtrace
note: we would appreciate a bug report: https://github.com/rust-lang/rust/issues/new?labels=C-bug%2C+I-ICE%2C+T-compiler&template=ice.md
note: please make sure that you have updated to the latest nightly
note: please attach the file at `/share/pkehl/GIT/phantom-newtype-rs/rustc-ice-2024-12-08T20_05_47-2074709.txt` to your bug report
query stack during panic:
end of query stack
Couldn't compile the test.
---- src/amount.rs - amount::Amount<TF,Unit,Repr>::unit (line 185) stdout ----
note: no errors encountered even though delayed bugs were created
note: those delayed bugs will now be shown as internal compiler errors
error: internal compiler error: Encountered anon const with inference variable args but no error reported
|
= note: delayed at compiler/rustc_trait_selection/src/traits/mod.rs:605:27 - disabled backtrace
note: we would appreciate a bug report: https://github.com/rust-lang/rust/issues/new?labels=C-bug%2C+I-ICE%2C+T-compiler&template=ice.md
note: please make sure that you have updated to the latest nightly
note: please attach the file at `/share/pkehl/GIT/phantom-newtype-rs/rustc-ice-2024-12-08T20_05_47-2074714.txt` to your bug report
query stack during panic:
end of query stack
Couldn't compile the test.
---- src/instant.rs - instant::Instant (line 132) stdout ----
note: no errors encountered even though delayed bugs were created
note: those delayed bugs will now be shown as internal compiler errors
error: internal compiler error: Encountered anon const with inference variable args but no error reported
|
= note: delayed at compiler/rustc_trait_selection/src/traits/mod.rs:605:27 - disabled backtrace
note: we would appreciate a bug report: https://github.com/rust-lang/rust/issues/new?labels=C-bug%2C+I-ICE%2C+T-compiler&template=ice.md
note: please make sure that you have updated to the latest nightly
note: please attach the file at `/share/pkehl/GIT/phantom-newtype-rs/rustc-ice-2024-12-08T20_05_48-2074907.txt` to your bug report
query stack during panic:
end of query stack
Couldn't compile the test.
---- src/instant.rs - instant::Instant (line 120) stdout ----
note: no errors encountered even though delayed bugs were created
note: those delayed bugs will now be shown as internal compiler errors
error: internal compiler error: Encountered anon const with inference variable args but no error reported
|
= note: delayed at compiler/rustc_trait_selection/src/traits/mod.rs:605:27 - disabled backtrace
note: we would appreciate a bug report: https://github.com/rust-lang/rust/issues/new?labels=C-bug%2C+I-ICE%2C+T-compiler&template=ice.md
note: please make sure that you have updated to the latest nightly
note: please attach the file at `/share/pkehl/GIT/phantom-newtype-rs/rustc-ice-2024-12-08T20_05_48-2074892.txt` to your bug report
query stack during panic:
end of query stack
Couldn't compile the test.
---- src/instant.rs - instant::Instant (line 53) stdout ----
note: no errors encountered even though delayed bugs were created
note: those delayed bugs will now be shown as internal compiler errors
error: internal compiler error: Encountered anon const with inference variable args but no error reported
|
= note: delayed at compiler/rustc_trait_selection/src/traits/mod.rs:605:27 - disabled backtrace
note: we would appreciate a bug report: https://github.com/rust-lang/rust/issues/new?labels=C-bug%2C+I-ICE%2C+T-compiler&template=ice.md
note: please make sure that you have updated to the latest nightly
note: please attach the file at `/share/pkehl/GIT/phantom-newtype-rs/rustc-ice-2024-12-08T20_05_48-2074915.txt` to your bug report
query stack during panic:
end of query stack
Couldn't compile the test.
---- src/instant.rs - instant::Instant (line 33) stdout ----
note: no errors encountered even though delayed bugs were created
note: those delayed bugs will now be shown as internal compiler errors
error: internal compiler error: Encountered anon const with inference variable args but no error reported
|
= note: delayed at compiler/rustc_trait_selection/src/traits/mod.rs:605:27 - disabled backtrace
note: we would appreciate a bug report: https://github.com/rust-lang/rust/issues/new?labels=C-bug%2C+I-ICE%2C+T-compiler&template=ice.md
note: please make sure that you have updated to the latest nightly
note: please attach the file at `/share/pkehl/GIT/phantom-newtype-rs/rustc-ice-2024-12-08T20_05_48-2074913.txt` to your bug report
query stack during panic:
end of query stack
Couldn't compile the test.
---- src/instant.rs - instant::Instant<TF,Unit,Repr>::display (line 200) stdout ----
note: no errors encountered even though delayed bugs were created
note: those delayed bugs will now be shown as internal compiler errors
error: internal compiler error: Encountered anon const with inference variable args but no error reported
|
= note: delayed at compiler/rustc_trait_selection/src/traits/mod.rs:605:27 - disabled backtrace
note: we would appreciate a bug report: https://github.com/rust-lang/rust/issues/new?labels=C-bug%2C+I-ICE%2C+T-compiler&template=ice.md
note: please make sure that you have updated to the latest nightly
note: please attach the file at `/share/pkehl/GIT/phantom-newtype-rs/rustc-ice-2024-12-08T20_05_48-2074927.txt` to your bug report
query stack during panic:
end of query stack
Couldn't compile the test.
---- src/instant.rs - instant::Instant (line 73) stdout ----
note: no errors encountered even though delayed bugs were created
note: those delayed bugs will now be shown as internal compiler errors
error: internal compiler error: Encountered anon const with inference variable args but no error reported
|
= note: delayed at compiler/rustc_trait_selection/src/traits/mod.rs:605:27 - disabled backtrace
note: we would appreciate a bug report: https://github.com/rust-lang/rust/issues/new?labels=C-bug%2C+I-ICE%2C+T-compiler&template=ice.md
note: please make sure that you have updated to the latest nightly
note: please attach the file at `/share/pkehl/GIT/phantom-newtype-rs/rustc-ice-2024-12-08T20_05_48-2074921.txt` to your bug report
query stack during panic:
end of query stack
Couldn't compile the test.
---- src/instant.rs - instant::Instant (line 88) stdout ----
note: no errors encountered even though delayed bugs were created
note: those delayed bugs will now be shown as internal compiler errors
error: internal compiler error: Encountered anon const with inference variable args but no error reported
|
= note: delayed at compiler/rustc_trait_selection/src/traits/mod.rs:605:27 - disabled backtrace
note: we would appreciate a bug report: https://github.com/rust-lang/rust/issues/new?labels=C-bug%2C+I-ICE%2C+T-compiler&template=ice.md
note: please make sure that you have updated to the latest nightly
note: please attach the file at `/share/pkehl/GIT/phantom-newtype-rs/rustc-ice-2024-12-08T20_05_48-2074923.txt` to your bug report
query stack during panic:
end of query stack
Couldn't compile the test.
---- src/instant.rs - instant::Instant<TF,Unit,Repr>::get (line 153) stdout ----
note: no errors encountered even though delayed bugs were created
note: those delayed bugs will now be shown as internal compiler errors
error: internal compiler error: Encountered anon const with inference variable args but no error reported
|
= note: delayed at compiler/rustc_trait_selection/src/traits/mod.rs:605:27 - disabled backtrace
note: we would appreciate a bug report: https://github.com/rust-lang/rust/issues/new?labels=C-bug%2C+I-ICE%2C+T-compiler&template=ice.md
note: please make sure that you have updated to the latest nightly
note: please attach the file at `/share/pkehl/GIT/phantom-newtype-rs/rustc-ice-2024-12-08T20_05_48-2074934.txt` to your bug report
query stack during panic:
end of query stack
Couldn't compile the test.
---- src/instant.rs - instant::Instant<TF,Unit,Repr>::unit (line 179) stdout ----
note: no errors encountered even though delayed bugs were created
note: those delayed bugs will now be shown as internal compiler errors
error: internal compiler error: Encountered anon const with inference variable args but no error reported
|
= note: delayed at compiler/rustc_trait_selection/src/traits/mod.rs:605:27 - disabled backtrace
note: we would appreciate a bug report: https://github.com/rust-lang/rust/issues/new?labels=C-bug%2C+I-ICE%2C+T-compiler&template=ice.md
note: please make sure that you have updated to the latest nightly
note: please attach the file at `/share/pkehl/GIT/phantom-newtype-rs/rustc-ice-2024-12-08T20_05_48-2074938.txt` to your bug report
query stack during panic:
end of query stack
Couldn't compile the test.
failures:
src/amount.rs - amount::Amount (line 126)
src/amount.rs - amount::Amount (line 138)
src/amount.rs - amount::Amount (line 47)
src/amount.rs - amount::Amount (line 65)
src/amount.rs - amount::Amount (line 82)
src/amount.rs - amount::Amount (line 96)
src/amount.rs - amount::Amount<TF,Unit,Repr>::display (line 206)
src/amount.rs - amount::Amount<TF,Unit,Repr>::get (line 157)
src/amount.rs - amount::Amount<TF,Unit,Repr>::unit (line 185)
src/instant.rs - instant::Instant (line 120)
src/instant.rs - instant::Instant (line 132)
src/instant.rs - instant::Instant (line 33)
src/instant.rs - instant::Instant (line 53)
src/instant.rs - instant::Instant (line 73)
src/instant.rs - instant::Instant (line 88)
src/instant.rs - instant::Instant<TF,Unit,Repr>::display (line 200)
src/instant.rs - instant::Instant<TF,Unit,Repr>::get (line 153)
src/instant.rs - instant::Instant<TF,Unit,Repr>::unit (line 179)
test result: FAILED. 13 passed; 18 failed; 1 ignored; 0 measured; 0 filtered out; finished in 2.50s
error: doctest failed, to rerun pass `--doc`
```
[rustc-ice-2024-12-08T20_05_48-2074938.txt](https://github.com/user-attachments/files/18053848/rustc-ice-2024-12-08T20_05_48-2074938.txt)
[rustc-ice-2024-12-08T20_05_48-2074934.txt](https://github.com/user-attachments/files/18053859/rustc-ice-2024-12-08T20_05_48-2074934.txt)
[rustc-ice-2024-12-08T20_05_48-2074923.txt](https://github.com/user-attachments/files/18053858/rustc-ice-2024-12-08T20_05_48-2074923.txt)
[rustc-ice-2024-12-08T20_05_48-2074927.txt](https://github.com/user-attachments/files/18053852/rustc-ice-2024-12-08T20_05_48-2074927.txt)
[rustc-ice-2024-12-08T20_05_48-2074921.txt](https://github.com/user-attachments/files/18053845/rustc-ice-2024-12-08T20_05_48-2074921.txt)
[rustc-ice-2024-12-08T20_05_48-2074913.txt](https://github.com/user-attachments/files/18053847/rustc-ice-2024-12-08T20_05_48-2074913.txt)
[rustc-ice-2024-12-08T20_05_48-2074915.txt](https://github.com/user-attachments/files/18053843/rustc-ice-2024-12-08T20_05_48-2074915.txt)
[rustc-ice-2024-12-08T20_05_48-2074907.txt](https://github.com/user-attachments/files/18053844/rustc-ice-2024-12-08T20_05_48-2074907.txt)
[rustc-ice-2024-12-08T20_05_48-2074892.txt](https://github.com/user-attachments/files/18053846/rustc-ice-2024-12-08T20_05_48-2074892.txt)
[rustc-ice-2024-12-08T20_05_47-2074709.txt](https://github.com/user-attachments/files/18053853/rustc-ice-2024-12-08T20_05_47-2074709.txt)
[rustc-ice-2024-12-08T20_05_47-2074714.txt](https://github.com/user-attachments/files/18053855/rustc-ice-2024-12-08T20_05_47-2074714.txt)
[rustc-ice-2024-12-08T20_05_47-2074712.txt](https://github.com/user-attachments/files/18053854/rustc-ice-2024-12-08T20_05_47-2074712.txt)
[rustc-ice-2024-12-08T20_05_46-2074703.txt](https://github.com/user-attachments/files/18053851/rustc-ice-2024-12-08T20_05_46-2074703.txt)
[rustc-ice-2024-12-08T20_05_46-2074683.txt](https://github.com/user-attachments/files/18053860/rustc-ice-2024-12-08T20_05_46-2074683.txt)
[rustc-ice-2024-12-08T20_05_46-2074687.txt](https://github.com/user-attachments/files/18053857/rustc-ice-2024-12-08T20_05_46-2074687.txt)
[rustc-ice-2024-12-08T20_05_46-2074695.txt](https://github.com/user-attachments/files/18053856/rustc-ice-2024-12-08T20_05_46-2074695.txt)
[rustc-ice-2024-12-08T20_05_46-2074666.txt](https://github.com/user-attachments/files/18053849/rustc-ice-2024-12-08T20_05_46-2074666.txt)
[rustc-ice-2024-12-08T20_05_46-2074664.txt](https://github.com/user-attachments/files/18053850/rustc-ice-2024-12-08T20_05_46-2074664.txt) | I-ICE,T-compiler,C-bug,F-generic_const_exprs | low | Critical |
2,725,517,850 | vscode | Caps lock warning in password input prompt | <!-- ⚠️⚠️ 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. -->
Logging in to a remote server requires password. A prompt appears on the top. The feature requests here is including some sort of warning in this prompt when caps lock is on.
Here's an example:
| feature-request,quick-pick | low | Minor |
2,725,533,576 | rust | shorten backtraces when called as a cdylib, not just for executables | currently, backtraces for rust cdylibs called from a C main function look like this:
```
thread '<unnamed>' panicked at lib.rs:5:34:
oops
stack backtrace:
0: std::panicking::begin_panic
1: lib::foo::{{closure}}
2: std::panicking::try::do_call
3: __rust_try
4: std::panic::catch_unwind
5: foo
6: main
7: __libc_start_call_main
at ./csu/../sysdeps/nptl/libc_start_call_main.h:58:16
8: __libc_start_main_impl
at ./csu/../csu/libc-start.c:392:3
9: _start
```
(the `catch_unwind` -> `do_call` stack *should* be included, i had a manual catch_unwind in my program.)
this does ok for frames after main, but it shows three irrelevant frames before main. that happens because rustc doesn't control the final link, so it can't generate a `__rust_start_short_backtrace` frame. it would be nice if we could omit those.
to avoid making this dependent on the libc in use, i think we should:
- determine whether `main` was generated by rustc. we have a reliable signal for this at runtime, which is "is `std::rt::lang_start` present anywhere in the backtrace".
- if not, treat `main` the same as `__rust_start_short_backtrace`, except we also print the `main` frame in addition to toggling the state machine.
<details><summary>code that replicates this backtrace</summary>
```
; cat lib.rs main.c Makefile
File: lib.rs
use std::ffi::c_int;
use std::panic::catch_unwind;
#[no_mangle]
pub extern "C" fn foo() -> c_int {
let _panic = catch_unwind(|| panic!("oops")).unwrap_err();
1
}
────────────────────────────────────────────────────────
File: main.c
#include <stdio.h>
int foo();
int main() {
printf("%d\n", foo());
}
────────────────────────────────────────────────────────
File: Makefile
.PHONY: run
run: main
LD_LIBRARY_PATH=. RUST_BACKTRACE=1 ./main
main: main.o librust.so
gcc main.o -L. -lrust -o main
librust.so: lib.rs
rustc --crate-type cdylib lib.rs -o librust.so
```
</details> | C-enhancement,T-compiler,A-panic,A-backtrace | low | Minor |
2,725,579,409 | ollama | Structured JSON does not handle arrays at the top level properly | ### What is the issue?
It looks like structured JSON is not respected when an array is specified at the top level.
Example 1:
Request:
```json
{
"model": "llama3.1",
"messages": [
{
"role": "system",
"content": "Given a phrase, give a list of categories"
},
{
"role": "user",
"content": "I watched a movie with friends and there was a cat in it"
}
],
"stream": false,
"format": {
"type": "array",
"items": {
"type": "string"
}
}
}
```
Response:
```json
{
"model": "llama3.1",
"created_at": "2024-12-08T22:46:35.146738527Z",
"message": {
"role": "assistant",
"content": "[1] "
},
"done_reason": "stop",
"done": true,
"total_duration": 1520253202,
"load_duration": 29133573,
"prompt_eval_count": 37,
"prompt_eval_duration": 538000000,
"eval_count": 5,
"eval_duration": 951000000
}
```
Example 2:
Request:
```json
{
"model": "llama3.1",
"messages": [
{
"role": "system",
"content": "Given a phrase, give a list of categories. Respond in valid JSON"
},
{
"role": "user",
"content": "I watched a movie with friends and there was a cat in it"
}
],
"stream": false,
"format": {
"type": "array",
"items": {
"type": "object",
"items": {"name": {"type": "string"}, "description": {"type": "string"}},
"required": ["name", "description"]
}
}
}
```
Response:
```json
{
"model": "llama3.1",
"created_at": "2024-12-08T22:52:42.640180789Z",
"message": {
"role": "assistant",
"content": "[\n {\n \"category\": \"Entertainment\"\n },\n {\n \"category\": \"Social\"\n },\n {\n \"category\": \"Animals\"\n }\n]"
},
"done_reason": "stop",
"done": true,
"total_duration": 81840944323,
"load_duration": 29780952,
"prompt_eval_count": 42,
"prompt_eval_duration": 72020000000,
"eval_count": 38,
"eval_duration": 9789000000
}
```
I realize these examples are kind of nonsensical because I'm asking the LLM to do stuff that doesn't really line up with the schema. But surely it should be impossible for it to disobey the grammar, right? It seems to do fine if the top property is an object instead of an array.
### OS
Linux
### GPU
_No response_
### CPU
AMD
### Ollama version
0.5.0 | bug | low | Minor |
2,725,641,219 | tauri | [bug] default app not working on samsung galaxy A13 (armv7-linux-androideabi) | ### Describe the bug
I cant run the default app on a device with armv7-linux-androideabi (samsung galaxy A13). I am not sure the arch/device has anything to do, since someone in the discord, with a samsung galaxy s23, has the same problem
The splash screen appears, but then a blank screens stays for a long time.
After some time, the screen changes color slightly, and displays the text
```
error sending request for url
(http://192.168.1.19:1420)
```
The log contains a few errors, but I am unsure which are relevant and which arent. I attach the entire logs, grepping for the app name:
[android_logs.txt](https://github.com/user-attachments/files/18054637/android_logs.txt)
### Reproduction
Running the default app, with svelte, and npm as the package manager:
```
npm install
npm run tauri android init
npm run tauri android dev
```
On a samsung galaxy (A13 armv7-linux-androideabi)
### Expected behavior
_No response_
### Full `tauri info` output
```text
> [email protected] tauri
> tauri info
[✔] Environment
- OS: Ubuntu 22.4.0 x86_64 (X64)
✔ webkit2gtk-4.1: 2.46.3
✔ rsvg2: 2.52.5
✔ rustc: 1.82.0 (f6e511eec 2024-10-15)
✔ cargo: 1.82.0 (8f40fc59f 2024-08-21)
✔ rustup: 1.27.1 (54dd3d00f 2024-04-24)
✔ Rust toolchain: stable-x86_64-unknown-linux-gnu (default)
- node: 20.11.1
- npm: 10.2.4
[-] Packages
- tauri 🦀: 2.1.1
- tauri-build 🦀: 2.0.3
- wry 🦀: 0.47.2
- tao 🦀: 0.30.8
- @tauri-apps/api : 2.1.1
- @tauri-apps/cli : 2.1.0
[-] Plugins
- tauri-plugin-shell 🦀: 2.0.2
- @tauri-apps/plugin-shell : 2.0.1
[-] App
- build-type: bundle
- CSP: unset
- frontendDist: ../build
- devUrl: http://0.0.0.0:1420/
- framework: Svelte
- bundler: Vite
```
### Stack trace
```text
[android_logs.txt](https://github.com/user-attachments/files/18054628/android_logs.txt)
12-08 19:07:45.426 1018 2517 E BufferQueueDebug: [ActivityRecord{70f787a u0 com.tauri_test.app/.MainActivity t16871}#355292](this:0xe56b78b8,id:-1,api:0,p:-1,c:-1) id info cannot be read from 'ActivityRecord{70f787a u0 com.tauri_test.app/.MainActivity t16871}#355292'
...
12-08 19:07:45.445 1018 2517 E BufferQueueDebug: [f36bc3d Splash Screen com.tauri_test.app#355293](this:0xe56a90b8,id:-1,api:0,p:-1,c:-1) id info cannot be read from 'f36bc3d Splash Screen com.tauri_test.app#355293'
...
12-08 19:07:45.502 1018 2517 E BufferQueueDebug: [157ba3b ActivityRecordInputSink com.tauri_test.app/.MainActivity#355298](this:0xe55d68b8,id:-1,api:0,p:-1,c:-1) id info cannot be read from '157ba3b ActivityRecordInputSink com.tauri_test.app/.MainActivity#355298'
...
12-08 19:07:47.436 1018 2517 E BufferQueueDebug: [Surface(name=7fe74c8 com.tauri_test.app/com.tauri_test.app.MainActivity)/@0x70f07c3 - animation-leash of starting_reveal#355303](this:0xe543e0b8,id:-1,api:0,p:-1,c:-1) id info cannot be read from 'Surface(name=7fe74c8 com.tauri_test.app/com.tauri_test.app.MainActivity)/@0x70f07c3 - animation-leash of starting_reveal#355303'
...
12-08 19:08:12.185 3073 26919 E pageboostd: alp start : app comtauri_testapp
12-08 19:08:12.200 3073 26919 E pageboostd: comtauri_testapp, amt 0 scnt 0 fcnt 0
12-08 19:08:12.200 3073 26919 E pageboostd: comtauri_testapp, amt 0 scnt 0 fcnt 0
12-08 19:08:12.200 3073 26919 E pageboostd: alp end : app comtauri_testapp data_amount 0
12-08 19:08:12.202 1508 1551 I ActivityManager: Start proc 26920:com.tauri_test.app/u0a307 for activelaunch {com.tauri_test.app/com.tauri_test.app.MainActivity}
12-08 19:08:12.206 2087 2210 D ShellStartingWindow: preload Icon com.tauri_test.app
12-08 19:08:12.215 26920 26920 I .tauri_test.app: Late-enabling -Xcheck:jni
12-08 19:08:12.241 26920 26920 I .tauri_test.app: Using CollectorTypeCC GC.
12-08 19:08:12.276 1508 1539 I ChimeraSystemEventListener: appLaunchIntent package name is: com.tauri_test.app
12-08 19:08:12.276 1508 1652 I Pageboost: onAppLaunch : com.tauri_test.app
12-08 19:08:12.276 1508 1958 I Pageboost: Record App IO : com.tauri_test.app pid 26920
12-08 19:08:12.279 1508 1652 V WindowManager: Collecting in transition 25110: ActivityRecord{6f25380 u0 com.tauri_test.app/.MainActivity, caller=com.android.server.wm.TransitionController.collect:866 com.android.server.wm.ActivityStarter.startActivityUnchecked:2249 com.android.server.wm.ActivityStarter.executeRequest:1839 com.android.server.wm.ActivityStarter.execute:1000 com.android.server.wm.ActivityTaskManagerService.startActivityAsUser:1953
12-08 19:08:12.279 1508 1652 D ActivityTaskManager: TaskLaunchParamsModifier:task=null activity=ActivityRecord{6f25380 u0 com.tauri_test.app/.MainActivity t-1} display-from-option=0 display-id=0 task-display-area-windowing-mode=1 suggested-display-area=DefaultTaskDisplayArea@53173992
12-08 19:08:12.279 1508 1652 D [secipm]: mSecIpmManager Preload com.tauri_test.app dex files
12-08 19:08:12.279 1508 1652 D ActivityTaskManager: TaskLaunchParamsModifier:task=null activity=ActivityRecord{6f25380 u0 com.tauri_test.app/.MainActivity t-1} display-from-option=0 display-id=0 task-display-area-windowing-mode=1 suggested-display-area=DefaultTaskDisplayArea@53173992 inherit-from-source=fullscreen non-freeform-task-display-area display-area=DefaultTaskDisplayArea@53173992 default-portrait freeform-size-mismatch=Rect(54, 377 - 666, 1177)
12-08 19:08:12.282 1508 1652 D ActivityTaskManager: TaskLaunchParamsModifier:task=Task{f9ebdb9 #16872 type=standard A=10307:com.tauri_test.app} activity=ActivityRecord{6f25380 u0 com.tauri_test.app/.MainActivity t-1} display-from-option=
0 display-id=0 task-display-area-windowing-mode=1 suggested-display-area=DefaultTaskDisplayArea@53173992 inherit-from-source=fullscreen non-freeform-task-display-area display-area=DefaultTaskDisplayArea@53173992 default-portrait freeform-size-mismatch=Rect(54, 377 - 666, 1177)
12-08 19:08:12.283 1508 1652 V WindowManager: Collecting in transition 25110: Task{f9ebdb9 #16872 type=standard A=10307:com.tauri_test.app}, caller=com.android.server.wm.Transition.collectExistenceChange:886 com.android.server.wm.TransitionController.collectExistenceChange:908 com.android.server.wm.ActivityStarter.setNewTask:4516 com.android.server.wm.ActivityStarter.startActivityInner:2783 com.android.server.wm.ActivityStarter.startActivityUnchecked:2252
12-08 19:08:12.283 1018 1357 E BufferQueueDebug: [ActivityRecord{6f25380 u0 com.tauri_test.app/.MainActivity t16872}#355337](this:0xe54810b8,id:-1,api:0,p:-1,c:-1) id info cannot be read from
...
12-08 19:12:21.547 24952 25038 E android.vending: Failed to open APK '/data/app/~~CcO4m9MsDQCE-9h-4Mf6BA==/com.tauri_test.app-qOcjB-4XR3Cbo8ddpjVLSw==/base.apk': I/O error
12-08 19:12:21.549 25851 27590 I ENTM:Systemprocess: checkKLMActivationForPackageRemoved().START - com.tauri_test.app
12-08 19:12:21.566 24952 25038 W ResourcesManager: failed to preload asset path '/data/app/~~CcO4m9MsDQCE-9h-4Mf6BA==/com.tauri_test.app-qOcjB-4XR3Cbo8ddpjVLSw==/base.apk'
12-08 19:12:21.566 24952 25038 W ResourcesManager: java.io.IOException: Failed to load asset path /data/app/~~CcO4m9MsDQCE-9h-4Mf6BA==/com.tauri_test.app-qOcjB-4XR3Cbo8ddpjVLSw==/base.apk
12-08 19:12:21.581 24952 25038 W ziparchive: Unable to open '/data/app/~~CcO4m9MsDQCE-9h-4Mf6BA==/com.tauri_test.app-qOcjB-4XR3Cbo8ddpjVLSw==/base.apk': No such file or directory
12-08 19:12:21.581 24952 25038 E android.vending: Failed to open APK '/data/app/~~CcO4m9MsDQCE-9h-4Mf6BA==/com.tauri_test.app-qOcjB-4XR3Cbo8ddpjVLSw==/base.apk': I/O error
12-08 19:12:21.582 24952 25038 E ResourcesManager: failed to add asset path '/data/app/~~CcO4m9MsDQCE-9h-4Mf6BA==/com.tauri_test.app-qOcjB-4XR3Cbo8ddpjVLSw==/base.apk'
12-08 19:12:21.582 24952 25038 E ResourcesManager: java.io.IOException: Failed to load asset path /data/app/~~CcO4m9MsDQCE-9h-4Mf6BA==/com.tauri_test.app-qOcjB-4XR3Cbo8ddpjVLSw==/base.apk
```
### Additional context
Compiled in ubuntu 22, using the latest android studio version, and latest NDK version. Tried with android studio 2022 and ndk 26 before, had the problem, updated it, and same problem. | type: bug,status: needs triage,platform: Android | low | Critical |
2,725,720,247 | godot | Script editor minimap overlaps vertical scrollbar when "Increase scrollbar touch area" is enabled | ### Tested versions
- Reproducable in 4.3 and 4.4-dev6
### System information
Godot v4.4.dev6.mono - Windows 10.0.22631 - Multi-window, 2 monitors - Vulkan (Forward+) - dedicated NVIDIA GeForce RTX 3080 (NVIDIA; 32.0.15.6094) - 12th Gen Intel(R) Core(TM) i9-12900K (24 threads)
### Issue description
The script editor's minimap overlaps the vertical scrollbar when `interface/touchscreen/increase_scrollbar_touch_area` is enabled, causing part of the minimap to be hard to see.
Instead, the minimap should either be shifted over to not overlap the scrollbar, or hidden all together when the minimap is enabled since it acts as a scrollbar also.
### Steps to reproduce
- Enable `interface/touchscreen/increase_scrollbar_touch_area` (Editor Settings -> Interface -> Touchscreen -> Increase Scrollbar Touch Area)
- Enable `text_editor/appearance/minimap/show_minimap` (Editor Settings -> Text Editor -> Appearance -> Show Minimap)
- Open any GDScript file in Godot's editor
### Minimal reproduction project (MRP)
N/A | bug,topic:editor,usability,topic:gui | low | Minor |
2,725,748,334 | fucking-algorithm | 插件拉取的题库不全 | **Version:**
2.0.4
**Describe the bug**
我在官方网站上找到题号为3330的题目，回到vscode搜索3330，查询不到
**Screenshots**
If applicable, add screenshots to help explain your problem.
| vscode-extension-bug | low | Critical |
2,725,765,293 | vscode | VS Code exits on startup on Pop OS with COSMIC desktop | <!-- ⚠️⚠️ 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
I just installed Code and didn't install any extensions yet, but have tried ` --disable-extensions` and it did not help.
<!-- 🪓 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: 1.95.3-1731513102
- OS Version: Pop OS (based on Ubuntu 24.04 LTS) with the new COSMIC desktop
Steps to Reproduce:
I just installed VS Code using official instructions for Ubuntu, since Pop OS is a derivative of Ubuntu 24.04 LTS.
I was able to run it once, and tried to select the light theme from the popup down left. That did not bring up the expected popup menu.
I then quit VS Code and now I'm unable to run it again, the window shows up and immediately disappears.
1. Run VS Code from command line or launcher icon
2. Watch its window come up and then immediately shut down
I do understand that COSMIC is a brand new desktop environment and it may contain bugs, but all my other applications seem to be working normally (Sublime Text and Merge, Android Studio, JetBrains GoLand).
I'm going to attach the output of "code --verbose" here.
[vscode_exits_on_popos_cosmic.txt](https://github.com/user-attachments/files/18055409/vscode_exits_on_popos_cosmic.txt)
| bug,freeze-slow-crash-leak | low | Critical |
2,725,783,735 | material-ui | [material-ui] Opt-in support for `@layer` to fix Tailwind v4 integration | ## Motivation
### Tailwind integration
The current Material UI v6 is hard to use with CSS utilities like Tailwind CSS because some components have higher CSS specificity than (0,1,0) so Tailwind CSS could not be used without `!important`.
Also, Tailwind v4 (will be stable soon) is using native CSS layer so Material UI won't be able to override it without a configurable layer.
Here is the issue using Material UI v6 + Tailwind v4 (beta). The `text-2xl` cannot override the Typography base styles.
<img width="1194" alt="image" src="https://github.com/user-attachments/assets/0aff2920-4f25-4b2b-87f1-17124e49e953">
> ✅ Can be fixed by the first solution
### Different override behavior when using CSS variables
Another issue is the behavior change when transition from dynamic CSS using `theme.palette.mode` to CSS variables paradigm (static CSS). The `sx` prop cannot override the `:where()` because Emotion always append `:where()` at the end of the styles.
> ✅ Can be fixed by combining first and second solution
## Requirements
- Opt-in solution
- Least breaking changes
- Small change for the codebase
## Options
### 1. A custom stylis plugin for single layer
Based on this [solution](https://github.com/emotion-js/emotion/issues/3134#issuecomment-1939309240), this will capture emotion styles into a single layer, likely named `@layer mui`.
I think this is a simplest solution that works really well. It will fix the Tailwind v4 integration **but** it won't fix the "Different override behavior when using CSS variables" because all Material UI styles are in the same layer.
### 2. Add flag to the theme for multiple layers
To solve "Different override behavior when using CSS variables", the sx styles must be in a different layer so that it overrides the styles of the component regardless of selector's specificity.
```
@layer mui, sx
@layer sx {
.button {
color: blue; // this wins
}
}
@layer mui {
.button {
color: red;
};
:where(.dark) .button {
color: white;
}
}
```
A custom stylis plugin (option 1) is not possible to support multiple layers, so the layer has to be created from the `styleFunctionSx`.
```diff
diff --git a/packages/mui-system/src/styleFunctionSx/styleFunctionSx.js b/packages/mui-system/src/styleFunctionSx/styleFunctionSx.js
index a74b44b553..08362c997f 100644
--- a/packages/mui-system/src/styleFunctionSx/styleFunctionSx.js
+++ b/packages/mui-system/src/styleFunctionSx/styleFunctionSx.js
@@ -131,7 +131,11 @@ export function unstable_createStyleFunctionSx() {
return sortContainerQueries(theme, removeUnusedBreakpoints(breakpointsKeys, css));
}
- return Array.isArray(sx) ? sx.map(traverse) : traverse(sx);
+ const array = Array.isArray(sx) ? sx : [sx];
+ return array.map((item) => {
+ const result = traverse(item);
+ return theme.cssLayer ? { [`@layer sx`]: result } : result;
+ });
}
return styleFunctionSx;
```
Feel free to share other possible options that we could do.
**Search keywords**: | package: material-ui,RFC | low | Minor |
2,725,801,345 | ollama | Why is OllamaSetup.exe so large | I also tried downloading [ollama-windows-arm64.zip](https://github.com/ollama/ollama/releases/download/v0.5.1/ollama-windows-arm64.zip) and replacing some files in my user folder which doesn' t fix the tray icon still notify the update. Could there be a smaller OllamaSetup.exe ?
This combined with the tray "restart to update" button not effective can be very annoying. | feature request,windows | low | Minor |
2,725,810,801 | opencv | OpenCVFindLibsPerf.cmake/with_clp error if you build Clp via vC | ### System Information
OpenCV version: 4.10.0 (and others)
Operating System / Platform: Windows 11
Compiler & compiler version: MSVC (latest)
### Detailed description
I got this output while building fat java on Windows 11 with "WITH_CLP":
```
[2037/2067] C:\Windows\system32\cmd.exe /C "cd . && C:\CMake\cmake-3.31.2\bin\cmake.exe -E vs_link_dll --msvc-ver=1942 --intdir=modules\java\jni\CMakeFiles\opencv_java.dir --rc=C:\PROGRA~2\WI3CF2~1\10\bin\100261~1.0\x64\rc.exe --mt=C:\PROGRA~2\WI3CF2~1\10\bin\100261~1.0\x64\mt.exe --manifests -- C:\VStudio\VC\Tools\MSVC\14.42.34433\bin\Hostx64\x64\link.exe @CMakeFiles\opencv_java.rsp /out:bin\opencv_java4100.dll /implib:lib\opencv_java4100.lib /pdb:bin\opencv_java4100.pdb /dll /version:0.0 /machine:x64 /INCREMENTAL:NO && C:\Windows\system32\cmd.exe /C "cd /D C:\opencv3\build\modules\java\jni && "C:\Program Files\PowerShell\7\pwsh.exe" -noprofile -executionpolicy Bypass -file C:/vcpkg/scripts/buildsystems/msbuild/applocal.ps1 -targetBinary C:/opencv3/build/bin/opencv_java4100.dll -installedDir c:/opencv2/vcpkg_installed/x64-windows/bin -OutVariable out""
FAILED: bin/opencv_java4100.dll lib/opencv_java4100.lib
C:\Windows\system32\cmd.exe /C "cd . && C:\CMake\cmake-3.31.2\bin\cmake.exe -E vs_link_dll --msvc-ver=1942 --intdir=modules\java\jni\CMakeFiles\opencv_java.dir --rc=C:\PROGRA~2\WI3CF2~1\10\bin\100261~1.0\x64\rc.exe --mt=C:\PROGRA~2\WI3CF2~1\10\bin\100261~1.0\x64\mt.exe --manifests -- C:\VStudio\VC\Tools\MSVC\14.42.34433\bin\Hostx64\x64\link.exe @CMakeFiles\opencv_java.rsp /out:bin\opencv_java4100.dll /implib:lib\opencv_java4100.lib /pdb:bin\opencv_java4100.pdb /dll /version:0.0 /machine:x64 /INCREMENTAL:NO && C:\Windows\system32\cmd.exe /C "cd /D C:\opencv3\build\modules\java\jni && "C:\Program Files\PowerShell\7\pwsh.exe" -noprofile -executionpolicy Bypass -file C:/vcpkg/scripts/buildsystems/msbuild/applocal.ps1 -targetBinary C:/opencv3/build/bin/opencv_java4100.dll -installedDir c:/opencv2/vcpkg_installed/x64-windows/bin -OutVariable out""
LINK: command "C:\VStudio\VC\Tools\MSVC\14.42.34433\bin\Hostx64\x64\link.exe @CMakeFiles\opencv_java.rsp /out:bin\opencv_java4100.dll /implib:lib\opencv_java4100.lib /pdb:bin\opencv_java4100.pdb /dll /version:0.0 /machine:x64 /INCREMENTAL:NO /MANIFEST:EMBED,ID=2" failed (exit code 1181) with the following output:
Microsoft (R) Incremental Linker Version 14.42.34435.0
Copyright (C) Microsoft Corporation. All rights reserved.
modules\java\jni\CMakeFiles\opencv_java.dir\__\generator\src\cpp\Mat.cpp.obj
modules\java\jni\CMakeFiles\opencv_java.dir\__\generator\src\cpp\converters.cpp.obj
modules\java\jni\CMakeFiles\opencv_java.dir\__\generator\src\cpp\jni_part.cpp.obj
modules\java\jni\CMakeFiles\opencv_java.dir\__\generator\src\cpp\listconverters.cpp.obj
modules\java\jni\CMakeFiles\opencv_java.dir\__\generator\src\cpp\opencv_java.cpp.obj
modules\java\jni\CMakeFiles\opencv_java.dir\__\generator\src\cpp\utils.cpp.obj
modules\java\jni\CMakeFiles\opencv_java.dir\__\__\core\misc\java\src\cpp\core_manual.cpp.obj
modules\java\jni\CMakeFiles\opencv_java.dir\__\__\dnn\misc\java\src\cpp\dnn_converters.cpp.obj
modules\java\jni\CMakeFiles\opencv_java.dir\__\__\features2d\misc\java\src\cpp\features2d_converters.cpp.obj -LIBPATH:C:\PROGRA~1\NVIDIA~2\CUDA\v12.6\lib\x64 -LIBPATH:C:\opencv2\vcpkg_installed\x64-windows\lib lib\opencv_cudev4100.lib lib\opencv_core4100.lib lib\opencv_cudaarithm4100.lib lib\opencv_flann4100.lib lib\opencv_imgproc4100.lib lib\opencv_ml4100.lib lib\opencv_phase_unwrapping4100.lib lib\opencv_plot4100.lib lib\opencv_quality4100.lib lib\opencv_viz4100.lib lib\opencv_cudafilters4100.lib lib\opencv_cudaimgproc4100.lib lib\opencv_dnn4100.lib lib\opencv_dnn_superres4100.lib lib\opencv_features2d4100.lib lib\opencv_img_hash4100.lib lib\opencv_imgcodecs4100.lib lib\opencv_photo4100.lib lib\opencv_text4100.lib lib\opencv_videoio4100.lib lib\opencv_xphoto4100.lib lib\opencv_calib3d4100.lib lib\opencv_datasets4100.lib lib\opencv_highgui4100.lib lib\opencv_objdetect4100.lib lib\opencv_shape4100.lib lib\opencv_structured_light4100.lib lib\opencv_video4100.lib lib\opencv_xfeatures2d4100.lib lib\opencv_ximgproc4100.lib lib\opencv_aruco4100.lib lib\opencv_bgsegm4100.lib lib\opencv_bioinspired4100.lib lib\opencv_face4100.lib lib\opencv_tracking4100.lib 3rdparty\lib\ippiw.lib 3rdparty\ippicv\ippicv_win\icv\lib\intel64\ippicvmt.lib cudart.lib nppc.lib nppial.lib nppicc.lib nppidei.lib nppif.lib nppig.lib nppim.lib nppist.lib nppisu.lib nppitc.lib npps.lib cublas.lib cufft.lib "-LIBPATH:C:/Program Files/NVIDIA GPU Computing Toolkit/CUDA/v12.6/lib/x64" libClp.lib libCoinUtils.lib lib\opencv_quality4100.lib lib\opencv_phase_unwrapping4100.lib lib\opencv_viz4100.lib C:\opencv2\vcpkg_installed\x64-windows\lib\vtkFiltersTexture-9.3.lib C:\opencv2\vcpkg_installed\x64-windows\lib\vtkIOExport-9.3.lib C:\opencv2\vcpkg_installed\x64-windows\lib\vtkRenderingContext2D-9.3.lib C:\opencv2\vcpkg_installed\x64-windows\lib\vtkRenderingFreeType-9.3.lib C:\opencv2\vcpkg_installed\x64-windows\lib\freetype.lib C:\opencv2\vcpkg_installed\x64-windows\lib\vtkRenderingVtkJS-9.3.lib C:\opencv2\vcpkg_installed\x64-windows\lib\vtkRenderingSceneGraph-9.3.lib C:\opencv2\vcpkg_installed\x64-windows\lib\jsoncpp.lib C:\opencv2\vcpkg_installed\x64-windows\lib\vtkIOGeometry-9.3.lib C:\opencv2\vcpkg_installed\x64-windows\lib\vtkIOPLY-9.3.lib C:\opencv2\vcpkg_installed\x64-windows\lib\vtkInteractionStyle-9.3.lib C:\opencv2\vcpkg_installed\x64-windows\lib\vtkFiltersExtraction-9.3.lib C:\opencv2\vcpkg_installed\x64-windows\lib\vtkIOXML-9.3.lib C:\opencv2\vcpkg_installed\x64-windows\lib\vtkIOXMLParser-9.3.lib C:\opencv2\vcpkg_installed\x64-windows\lib\vtkIOLegacy-9.3.lib C:\opencv2\vcpkg_installed\x64-windows\lib\vtkIOCore-9.3.lib C:\opencv2\vcpkg_installed\x64-windows\lib\vtkRenderingLOD-9.3.lib C:\opencv2\vcpkg_installed\x64-windows\lib\vtkRenderingOpenGL2-9.3.lib C:\opencv2\vcpkg_installed\x64-windows\lib\vtkIOImage-9.3.lib C:\opencv2\vcpkg_installed\x64-windows\lib\vtkRenderingHyperTreeGrid-9.3.lib C:\opencv2\vcpkg_installed\x64-windows\lib\vtkImagingCore-9.3.lib C:\opencv2\vcpkg_installed\x64-windows\lib\vtkRenderingUI-9.3.lib C:\opencv2\vcpkg_installed\x64-windows\lib\vtkRenderingCore-9.3.lib C:\opencv2\vcpkg_installed\x64-windows\lib\vtkFiltersSources-9.3.lib C:\opencv2\vcpkg_installed\x64-windows\lib\vtkFiltersGeneral-9.3.lib C:\opencv2\vcpkg_installed\x64-windows\lib\vtkFiltersCore-9.3.lib C:\opencv2\vcpkg_installed\x64-windows\lib\vtkCommonExecutionModel-9.3.lib C:\opencv2\vcpkg_installed\x64-windows\lib\glew32.lib C:\opencv2\vcpkg_installed\x64-windows\lib\vtkCommonDataModel-9.3.lib C:\opencv2\vcpkg_installed\x64-windows\lib\vtkCommonMisc-9.3.lib C:\opencv2\vcpkg_installed\x64-windows\lib\vtkCommonTransforms-9.3.lib C:\opencv2\vcpkg_installed\x64-windows\lib\vtkCommonMath-9.3.lib C:\opencv2\vcpkg_installed\x64-windows\lib\vtkkissfft-9.3.lib C:\opencv2\vcpkg_installed\x64-windows\lib\vtkCommonCore-9.3.lib C:\opencv2\vcpkg_installed\x64-windows\lib\vtktoken-9.3.lib C:\opencv2\vcpkg_installed\x64-windows\lib\vtksys-9.3.lib dbghelp.lib psapi.lib lib\opencv_shape4100.lib lib\opencv_photo4100.lib lib\opencv_cudaimgproc4100.lib lib\opencv_cudafilters4100.lib lib\opencv_cudaarithm4100.lib lib\opencv_objdetect4100.lib lib\opencv_plot4100.lib lib\opencv_datasets4100.lib lib\opencv_text4100.lib lib\opencv_ml4100.lib C:\dev\Tesseract\lib\tesseract55.lib C:\dev\Tesseract\debug\lib\tesseract55d.lib C:\dev\Tesseract\lib\leptonica-1.84.1.lib C:\dev\Tesseract\debug\lib\leptonica-1.84.1d.lib lib\opencv_highgui4100.lib lib\opencv_videoio4100.lib lib\opencv_imgcodecs4100.lib 3rdparty\lib\libjpeg-turbo.lib 3rdparty\lib\libwebp.lib 3rdparty\lib\libpng.lib 3rdparty\lib\libtiff.lib 3rdparty\lib\libopenjp2.lib 3rdparty\lib\IlmImf.lib C:\opencv2\vcpkg_installed\x64-windows\lib\gstreamer-1.0.lib C:\opencv2\vcpkg_installed\x64-windows\lib\gstbase-1.0.lib C:\opencv2\vcpkg_installed\x64-windows\lib\gstapp-1.0.lib C:\opencv2\vcpkg_installed\x64-windows\lib\gstriff-1.0.lib C:\opencv2\vcpkg_installed\x64-windows\lib\gstvideo-1.0.lib C:\opencv2\vcpkg_installed\x64-windows\lib\gstaudio-1.0.lib C:\opencv2\vcpkg_installed\x64-windows\lib\gstpbutils-1.0.lib C:\opencv2\vcpkg_installed\x64-windows\lib\glib-2.0.lib C:\opencv2\vcpkg_installed\x64-windows\lib\gobject-2.0.lib comctl32.lib gdi32.lib ole32.lib setupapi.lib ws2_32.lib C:\Dev\QT\vcpkg_installed\x64-windows\lib\Qt6Test.lib C:\Dev\QT\vcpkg_installed\x64-windows\lib\Qt6Concurrent.lib C:\Dev\QT\vcpkg_installed\x64-windows\lib\Qt6OpenGLWidgets.lib C:\Dev\QT\vcpkg_installed\x64-windows\lib\Qt6Widgets.lib C:\Dev\QT\vcpkg_installed\x64-windows\lib\Qt6OpenGL.lib C:\Dev\QT\vcpkg_installed\x64-windows\lib\Qt6Gui.lib C:\Dev\QT\vcpkg_installed\x64-windows\lib\Qt6Core.lib mpr.lib userenv.lib d3d11.lib dxgi.lib dxguid.lib d3d12.lib lib\opencv_video4100.lib lib\opencv_dnn4100.lib 3rdparty\lib\libprotobuf.lib C:\OpenVINO\runtime\lib\intel64\Release\openvino.lib lib\opencv_calib3d4100.lib lib\opencv_features2d4100.lib lib\opencv_flann4100.lib lib\opencv_imgproc4100.lib lib\opencv_core4100.lib lib\opencv_cudev4100.lib C:\OneApi\2025.0\lib\tbb12.lib 3rdparty\lib\zlib.lib opengl32.lib glu32.lib 3rdparty\lib\ittnotify.lib C:\opencv2\vcpkg_installed\x64-windows\lib\lapack.lib C:\opencv2\vcpkg_installed\x64-windows\lib\openblas.lib 3rdparty\lib\ippiw.lib 3rdparty\ippicv\ippicv_win\icv\lib\intel64\ippicvmt.lib cudart.lib nppc.lib nppial.lib nppicc.lib nppidei.lib nppif.lib nppig.lib nppim.lib nppist.lib nppisu.lib nppitc.lib npps.lib cublas.lib cufft.lib "-LIBPATH:C:/Program Files/NVIDIA GPU Computing Toolkit/CUDA/v12.6/lib/x64" libClp.lib libCoinUtils.lib C:\Dev\Halide\lib\Release\Halide.lib kernel32.lib user32.lib gdi32.lib winspool.lib shell32.lib ole32.lib oleaut32.lib uuid.lib comdlg32.lib advapi32.lib
LINK : fatal error LNK1181: cannot open input file 'libClp.lib'
```
this block in cmake/OpenCVFindLibsPerf.cmake at line 151:
```
if(UNIX)
set(OPENCV_LINKER_LIBS ${OPENCV_LINKER_LIBS} Clp CoinUtils m)
else()
if(MINGW)
set(OPENCV_LINKER_LIBS ${OPENCV_LINKER_LIBS} Clp CoinUtils)
else()
set(OPENCV_LINKER_LIBS ${OPENCV_LINKER_LIBS} libClp libCoinUtils)
endif()
endif()
```
is incorrect if you install Clp with VCPKG on Windows because they name the libraries without the 'lib' prefix.
I know this is incorrect if you don't use VCPKG, but this worked as a workaround for me:
```
if(UNIX)
set(OPENCV_LINKER_LIBS ${OPENCV_LINKER_LIBS} Clp CoinUtils m)
else()
set(OPENCV_LINKER_LIBS ${OPENCV_LINKER_LIBS} libClp libCoinUtils)
endif()
```
### Steps to reproduce
on a windows system run:
`vcpkg install coin-or-clp`
then build opencv WITH_CLP using the vcpkg toolchain.
### Issue submission checklist
- [X] I report the issue, it's not a question
- [X] I checked the problem with documentation, FAQ, open issues, forum.opencv.org, Stack Overflow, etc and have not found any solution
- [X] I updated to the latest OpenCV version and the issue is still there
- [X] There is reproducer code and related data files (videos, images, onnx, etc) | bug,category: build/install,platform: win32 | low | Critical |
2,725,893,194 | stable-diffusion-webui | [Bug]: xformers fails to import while module fails to be detected after force reinstall download | ### Checklist
- [ ] The issue exists after disabling all extensions
- [X] The issue exists on a clean installation of webui
- [ ] The issue is caused by an extension, but I believe it is caused by a bug in the webui
- [X] The issue exists in the current version of the webui
- [ ] The issue has not been reported before recently
- [ ] The issue has been reported before but has not been fixed yet
### What happened?
User did a clean install on my Pop_OS machine after fully updating it. After a fresh install User added xformers to my starting arguments. Xformers module failed to be detected. User applied starting arguments to reinstall xfomers.
This gererated the following unusual text code:
Launching Web UI with arguments:
/home/user/Programs/A1111 WebUI/stable-diffusion-webui/venv/lib/python3.10/site-packages/timm/models/layers/__init__.py:48: FutureWarning: Importing from timm.models.layers is deprecated, please import via timm.layers
warnings.warn(f"Importing from {__name__} is deprecated, please import via timm.layers", FutureWarning)
no module 'xformers'. Processing without...
no module 'xformers'. Processing without...
No module 'xformers'. Proceeding without it.
Loading weights [6ce0161689] from /home/user/Programs/A1111 WebUI/stable-diffusion-webui/models/Stable-diffusion/v1-5-pruned-emaonly.safetensors
Running on local URL: http://127.0.0.1:7860
There is a second outcome the prints errors in the program code but I cannot reproduce currently
### Steps to reproduce the problem
1)User does a clean install on my Pop_OS machine after fully updating it.
2)After a fresh install User adds xformers to my starting arguments.
3)User applies starting arguments to reinstall xfomers.
### What should have happened?
WebUI should detect and load xformers module
### What browsers do you use to access the UI ?
Mozilla Firefox
### Sysinfo
[sysinfo-2024-12-09-03-30.json](https://github.com/user-attachments/files/18056028/sysinfo-2024-12-09-03-30.json)
### Console logs
```Shell
################################################################
Install script for stable-diffusion + Web UI
Tested on Debian 11 (Bullseye), Fedora 34+ and openSUSE Leap 15.4 or newer.
################################################################
################################################################
Running on User user
################################################################
################################################################
Create and activate python venv
################################################################
################################################################
Launching launch.py...
################################################################
glibc version is 2.35
Check TCMalloc: libtcmalloc_minimal.so.4
libtcmalloc_minimal.so.4 is linked with libc.so,execute LD_PRELOAD=/lib/x86_64-linux-gnu/libtcmalloc_minimal.so.4
Python 3.10.12 (main, Nov 6 2024, 20:22:13) [GCC 11.4.0]
Version: v1.10.1
Commit hash: 82a973c04367123ae98bd9abdf80d9eda9b910e2
Launching Web UI with arguments:
/home/user/Programs/A1111 WebUI/stable-diffusion-webui/venv/lib/python3.10/site-packages/timm/models/layers/__init__.py:48: FutureWarning: Importing from timm.models.layers is deprecated, please import via timm.layers
warnings.warn(f"Importing from {__name__} is deprecated, please import via timm.layers", FutureWarning)
no module 'xformers'. Processing without...
no module 'xformers'. Processing without...
No module 'xformers'. Proceeding without it.
Loading weights [6ce0161689] from /home/user/Programs/A1111 WebUI/stable-diffusion-webui/models/Stable-diffusion/v1-5-pruned-emaonly.safetensors
Running on local URL: http://127.0.0.1:7860
To create a public link, set `share=True` in `launch()`.
Creating model from config: /home/user/Programs/A1111 WebUI/stable-diffusion-webui/configs/v1-inference.yaml
Startup time: 6.9s (prepare environment: 1.4s, import torch: 2.1s, import gradio: 0.5s, setup paths: 1.2s, initialize shared: 0.3s, other imports: 0.3s, load scripts: 0.4s, create ui: 0.3s, gradio launch: 0.3s).
/home/user/Programs/A1111 WebUI/stable-diffusion-webui/venv/lib/python3.10/site-packages/huggingface_hub/file_download.py:797: FutureWarning: `resume_download` is deprecated and will be removed in version 1.0.0. Downloads always resume when possible. If you want to force a new download, use `force_download=True`.
warnings.warn(
ERROR: ld.so: object '/lib/x86_64-linux-gnu/libtcmalloc_minimal.so.4' from LD_PRELOAD cannot be preloaded (cannot open shared object file): ignored.
ERROR: ld.so: object '/lib/x86_64-linux-gnu/libtcmalloc_minimal.so.4' from LD_PRELOAD cannot be preloaded (cannot open shared object file): ignored.
Gtk-Message: 21:53:05.723: Failed to load module "canberra-gtk-module"
Gtk-Message: 21:53:05.724: Failed to load module "canberra-gtk-module"
Applying attention optimization: Doggettx... done.
Model loaded in 2.8s (load weights from disk: 0.4s, create model: 0.4s, apply weights to model: 1.8s, calculate empty prompt: 0.1s).
```
### Additional information
There is a second outcome the prints errors in the programs code but I cannot reproduce this currently. I read thru it. xformers is failing to be imported as a library in one of the scripts. | bug-report | low | Critical |
2,725,940,076 | react | Bug: useEffect Without Dependencies Not Executed Correctly After setState | <!--
Please provide a clear and concise description of what the bug is. Include
screenshots if needed. Please test using the latest version of the relevant
React packages to make sure your issue has not already been fixed.
-->
React version: 18.3.1 & 19.0.0
## Steps To Reproduce
Consider the following example code, where there are two useEffect hooks.
- The first useEffect executes a setFlag, with the value of setFlag being the same as the initial value. The second parameter is an empty array.
- The second useEffect simply logs a message without passing a second argument (i.e., without dependencies) to make it easier to observe the execution behavior.
The JSX part of the component contains only a div with a click event, which triggers a setState when clicked.
```jsx
import React from 'react';
import { useEffect, useState } from 'react';
export function App(props) {
const [index, setIndex] = useState(0);
const [flag, setFlag] = useState(false);
console.log('index', index);
useEffect(() => {
console.log('setFlag invoke');
setFlag(false);
}, []);
useEffect(() => {
console.log('useEffect no dependencies invoke');
return () => {
console.log('useEffect no dependencies hook destroyed');
};
});
return (
<div
onClick={() => {
console.log('-------------- click --------------');
setIndex(pre => pre + 1);
}}
style={{ color: 'red' }}
>
button {index} {Date.now()}
</div>
);
}
```
<!--
Your bug will get fixed much faster if we can run your code and it doesn't
have dependencies other than React. Issues without reproduction steps or
code examples may be immediately closed as not actionable.
-->
Link to code example: https://playcode.io/2185135
<!--
Please provide a CodeSandbox (https://codesandbox.io/s/new), a link to a
repository on GitHub, or provide a minimal code example that reproduces the
problem. You may provide a screenshot of the application if you think it is
relevant to your bug report. Here are some tips for providing a minimal
example: https://stackoverflow.com/help/mcve.
-->
## The current behavior
After the click event is triggered, the component's render does not occur in tandem with the second useEffect. Render occurs twice, but the second useEffect executes only once.
<img width="627" alt="image" src="https://github.com/user-attachments/assets/9ffc9e58-4e89-4bd8-b407-e67837634554">
## The expected behavior
After the click event is triggered, the component's render should occur in tandem with the second useEffect. Render should happen twice, and the second useEffect should also execute twice.
| Status: Unconfirmed | low | Critical |
2,726,082,461 | pytorch | Extend custom op fwd/bwd functions to support data types beyond the basic set | ### 🐛 Describe the bug
Wrapping CUDA kernels or other C++ functions as custom operations is currently the only way to ensure compatibility with torch.compile. However, there are notable limitations: functions decorated with `torch.library.custom_op` can only accept and return basic data types, excluding more complex types such as `enum.Enum` or `List[str]`.
Error 1:
```
ValueError: infer_schema(func): Parameter layout has unsupported type typing.List[str]
```
Error 2:
```
File "/home/ybliang/tmp/conda/lib/python3.10/site-packages/torch/_library/custom_ops.py", line 133, in inner
schema_str = torch.library.infer_schema(fn, mutates_args=mutates_args)
File "/home/ybliang/tmp/conda/lib/python3.10/site-packages/torch/_library/infer_schema.py", line 93, in infer_schema
if annotation_type.__origin__ is tuple:
File "/home/ybliang/tmp/conda/lib/python3.10/enum.py", line 433, in __getattr__
raise AttributeError(name)
AttributeError: __origin__
```
@zou3519 mentioned that supporting all data types is not impossible, but it would be non-trivial and contingent on sufficient demand.
### Versions
N/A
cc @chauhang @penguinwu @zou3519 @bdhirsh @yf225 | triaged,module: custom-operators | low | Critical |
2,726,112,761 | react | Bug: memory leak caused by alternate fiber tree | <!--
Please provide a clear and concise description of what the bug is. Include
screenshots if needed. Please test using the latest version of the relevant
React packages to make sure your issue has not already been fixed.
-->
React version: 19
## Steps To Reproduce
```typescript
import React, { useState, useCallback } from "react";
const App = () => {
const [obj, setObj] = useState<any>({});
const [count, setCount] = useState(0);
const refresh = useCallback(() => {
const newObj = {
buffer: new Uint8Array(100_000_000),
count: count + 1,
};
setObj(newObj);
setCount((pre) => pre + 1);
}, [count]);
return (
<div>
<button onClick={refresh}>new obj({count})</button>
</div>
);
};
export default App;
```
## The current behavior
<img width="732" alt="image" src="https://github.com/user-attachments/assets/503bfa91-0bae-46cd-a4d7-a103f8cd4e2f">
## The expected behavior
release the `memoizedState` / `baseState` of alternate fiber tree.
## Confusion
I know it's not a good way to store a big state using `useState`. But it's a bug or some feature?
| Status: Unconfirmed | medium | Critical |
2,726,125,283 | next.js | Next.js Cache not working with CircleCI | ### Link to the code that reproduces this issue
https://github.com/DoctrineLegal/nextjs-cache-issue/blob/master/README.md
### To Reproduce
1. Trigger a build on CircleCI
2. Cache it's .next directory
3. Re-trigger a build on CircleCI with a hot cache
4. See that next.js is not using the cache
### Current vs. Expected behavior
### Current behavior: https://app.circleci.com/pipelines/github/DoctrineLegal/nextjs-cache-issue/1/workflows/745158ac-1c40-448e-9083-391e90cb0938/jobs/1
CircleCI is not using the cache. And consistently taking the same time to build.
### Expected Behavior: https://app.circleci.com/pipelines/github/DoctrineLegal/nextjs-cache-issue/1/workflows/745158ac-1c40-448e-9083-391e90cb0938/jobs/1
CircleCI should use the cache as specified here : https://nextjs.org/docs/pages/building-your-application/deploying/ci-build-caching#circleci
When forcing the cache dir it actually works.
### Provide environment information
```bash
Operating System:
Platform: darwin
Arch: arm64
Version: Darwin Kernel Version 24.0.0: Tue Sep 24 23:38:45 PDT 2024; root:xnu-11215.1.12~1/RELEASE_ARM64_T8122
Available memory (MB): 16384
Available CPU cores: 8
Binaries:
Node: 22.4.1
npm: 10.8.1
Yarn: 1.22.22
pnpm: 9.15.0
Relevant Packages:
next: 15.0.4-canary.46 // There is a newer canary version (15.0.4-canary.48) available, please upgrade!
eslint-config-next: 15.0.2
react: 19.0.0-rc-02c0e824-20241028
react-dom: 19.0.0-rc-02c0e824-20241028
typescript: 5.6.3
Next.js Config:
output: N/A
⚠ There is a newer canary version (15.0.4-canary.48) available, please upgrade!
Please try the latest canary version (`npm install next@canary`) to confirm the issue still exists before creating a new issue.
Read more - https://nextjs.org/docs/messages/opening-an-issue
```
### Which area(s) are affected? (Select all that apply)
Performance, Webpack
### Which stage(s) are affected? (Select all that apply)
next build (local)
### Additional context
CircleCI is indeed running on docker with a cgroup container docker : https://github.com/vercel/next.js/blob/canary/packages/next/src/compiled/is-docker/index.js and found as docker from this file.
I believe this PR : https://github.com/vercel/next.js/pull/70516 from @shuding introduced the issue.
As a side note : CircleCI is currently rolling out new containers that will not be subject to this issue : https://discuss.circleci.com/t/docker-executor-infrastructure-upgrade/52282 | bug,Webpack,Performance | low | Major |
2,726,130,131 | ant-design | Panel Header and Icon will re-render if wrapped in a form. | ### Reproduction link
[](https://codesandbox.io/p/sandbox/collapse-antd-4-24-16-forked-mt6ddt?file=%2Fdemo.tsx%3A1%2C1-41%2C1)
### Steps to reproduce
change input value, the icon and header re-render
### What is expected?
don't re-render
### What is actually happening?
the icon and header re-render
| Environment | Info |
| --- | --- |
| antd | 4.24.16 |
| React | 18 |
| System | mac |
| Browser | chrome |
<!-- generated by ant-design-issue-helper. DO NOT REMOVE -->
https://github.com/user-attachments/assets/4f61e4b2-bf06-404d-9778-2e8fb05fce38
| Inactive,improvement | low | Minor |
2,726,216,645 | deno | Node compatibility: process.stdout.hasColors() missing | Version: Deno 2.1.3
I checked whether some new code I have written will work with Deno, and it doesn't. (By design my code fails gracefully and assumes color not available.) My high level goal with the code is checking whether it is appropriate to show color on `stdout` or `stderr` from a command-line application.
https://github.com/tj/commander.js/blob/a8ef5cf3e1975380974ab5c4f92c26fb2c5e3209/lib/command.js#L68-L71
```js
{
getOutHasColors: () =>
useColor() ?? (process.stdout.isTTY && process.stdout.hasColors?.()),
getErrHasColors: () =>
useColor() ?? (process.stderr.isTTY && process.stderr.hasColors?.()),
}
```
I saw https://github.com/denoland/deno/pull/24619 added `tty.WriteStream.prototype.hasColors()` and I can see that routine.
```text
$ node
Welcome to Node.js v22.12.0.
Type ".help" for more information.
> process.stdout.isTTY
true
> process.stdout.hasColors()
true
>
$
$ deno
Deno 2.1.3
exit using ctrl+d, ctrl+c, or close()
REPL is running with all permissions allowed.
To specify permissions, run `deno repl` with allow flags.
> process.stdout.isTTY
true
> process.stdout.hasColors()
Uncaught TypeError: process.stdout.hasColors is not a function
at <anonymous>:1:37
> import tty from 'node:tty';
undefined
> tty?.WriteStream?.prototype?.isTTY
undefined
> tty?.WriteStream?.prototype?.hasColors?.()
true
>
```
| bug,node compat | low | Critical |
2,726,274,727 | pytorch | AllReduce hangs due to no device_id into init_process_group | ### 🐛 Describe the bug
In pytorch 2.2 or later, when initializing a distributed environment, if you do not pass device_id to the init_process_group function but pass it through the set_device, the allreduce primitive hangs or NCCL directly reports an error. This question only comes up on allreduce primitives, does anyone know why?
You can run the example below with `torchrun --nproc_per_node 4 test.py`
```python
import torch
import torch.distributed as dist
import os
init_method = 'tcp://'
master_ip = os.getenv('MASTER_ADDR', 'localhost')
world_size = 4
default_master_port = '6000'
master_port = os.getenv('MASTER_PORT', default_master_port)
init_method += master_ip + ':' + master_port
rank = int(os.getenv('RANK', '0'))
# correct init
# torch.distributed.init_process_group(
# backend="nccl",
# world_size=world_size, rank=rank, device_id=torch.device(f"cuda:{rank}"), init_method=init_method)
# will cause allreduce hang
torch.cuda.set_device(torch.device(f"cuda:{rank}"))
torch.distributed.init_process_group(
backend="nccl",
world_size=world_size, rank=rank, init_method=init_method)
cur_rank = torch.distributed.get_rank()
if cur_rank == 0 or cur_rank == 1:
gqa_group = torch.distributed.new_group([0, 1])
else:
gqa_group = torch.distributed.new_group([2, 3])
a = torch.tensor(1, device=cur_rank)
torch.distributed.all_reduce(a, group=gqa_group)
```
### Versions
pytorch 2.5
cc @H-Huang @awgu @kwen2501 @wanchaol @fegin @fduwjj @wz337 @wconstab @d4l3k @c-p-i-o | oncall: distributed,module: c10d | low | Critical |
2,726,302,695 | ant-design | Textarea autoSize 有问题，高度不正确 | ### Reproduction link
[](https://codesandbox.io/p/sandbox/ji-ben-shi-yong-antd-5-22-3-forked-sc6clf?file=%2Fdemo.tsx%3A9%2C17)
### Steps to reproduce
查看输入框高度
### What is expected?
应该只有两行
### What is actually happening?
有三行
| Environment | Info |
| --- | --- |
| antd | 5.22.3 |
| React | latest |
| System | mac |
| Browser | chrome |
<!-- generated by ant-design-issue-helper. DO NOT REMOVE --> | 🐛 Bug,Inactive,🧶 Low Priority | low | Minor |
2,726,333,315 | ui | [bug]: CLI fails to resolve correct component paths when paths are defined in extended tsconfig files | ### Describe the bug
The `shadcn-ui` CLI incorrectly resolves component paths when TypeScript path aliases are defined in extended tsconfig files instead of the root tsconfig.json. This results in components being generated in incorrect locations, either directly using the alias path or outside the project directory.
### Affected component/components
All
### How to reproduce
### Example 1: Using electron-vite
1. Create a new electron-vite project
2. Set up the following configuration files:
**tsconfig.json**
```json
{
"files": [],
"references": [{ "path": "./tsconfig.node.json" }, { "path": "./tsconfig.web.json" }]
}
```
**tsconfig.web.json**
```json
{
"extends": "@electron-toolkit/tsconfig/tsconfig.web.json",
"compilerOptions": {
"composite": true,
"jsx": "react-jsx",
"baseUrl": ".",
"paths": {
"@renderer/*": [
"src/renderer/src/*"
]
}
}
}
```
**components.json**
```json
{
"aliases": {
"components": "@renderer/components",
"utils": "@renderer/lib/utils"
}
}
```
3. Run `npx shadcn@latest add button`
4. Observe: Component is generated at `project/@renderer/components/ui/button.tsx` instead of `project/src/renderer/src/components/ui/button.tsx`
### Example 2: Using wxt.dev
1. Create a new wxt.dev project
2. Set up the following configuration files:
**tsconfig.json**
```json
{
"extends": "./.wxt/tsconfig.json",
"compilerOptions": {
"allowImportingTsExtensions": true,
"jsx": "react-jsx"
}
}
```
**.wxt/tsconfig.json**
```json
{
"compilerOptions": {
"paths": {
"@/*": ["../src/*"]
}
}
}
```
**components.json**
```json
{
"aliases": {
"components": "@/components",
"utils": "@/lib/utils"
}
}
```
3. Run `npx shadcn@latest add button`
4. Observe: Component is generated at `project/../src/components/ui/button.tsx` instead of `project/src/components/ui/button.tsx`
### Codesandbox/StackBlitz link
_No response_
### Logs
_No response_
### System Info
```bash
- Operating System: Windows 10
- Node.js Version: 22.12.0
- shadcn-ui CLI Version: 2.1.6
- Package Manager: npm
```
### Before submitting
- [X] I've made research efforts and searched the documentation
- [X] I've searched for existing issues | bug | low | Critical |
2,726,348,426 | ollama | Return prompt cache utilization on completion responses | Since Ollama has prompt caching now (right?), it would be great if the utilization of the cache could be returned in requests.
E.g. the OpenAI-compatible API could be extended with the new [`usage/prompt_tokens_details/cached_tokens`](https://platform.openai.com/docs/guides/prompt-caching).
A similar field in the Ollama API would also be great. | feature request | low | Minor |
2,726,364,840 | tauri | [bug] Wix Bundle main.wxs Failed | ### Describe the bug
I made a copy of main.wxs with the following contents
```xml
<?if $(sys.BUILDARCH)="x86"?>
<?define Win64 = "no" ?>
<?define PlatformProgramFilesFolder = "ProgramFilesFolder" ?>
<?elseif $(sys.BUILDARCH)="x64"?>
<?define Win64 = "yes" ?>
<?define PlatformProgramFilesFolder = "ProgramFiles64Folder" ?>
<?elseif $(sys.BUILDARCH)="arm64"?>
<?define Win64 = "yes" ?>
<?define PlatformProgramFilesFolder = "ProgramFiles64Folder" ?>
<?else?>
<?error Unsupported value of sys.BUILDARCH=$(sys.BUILDARCH)?>
<?endif?>
<Wix xmlns="http://schemas.microsoft.com/wix/2006/wi">
<Product
Id="*"
Name="{{product_name}}"
UpgradeCode="{{upgrade_code}}"
Language="!(loc.TauriLanguage)"
Manufacturer="{{manufacturer}}"
Version="{{version}}">
<Package Id="*"
Keywords="Installer"
InstallerVersion="450"
Languages="0"
Compressed="yes"
InstallScope="perMachine"
SummaryCodepage="!(loc.TauriCodepage)"/>
<!-- https://docs.microsoft.com/en-us/windows/win32/msi/reinstallmode -->
<!-- reinstall all files; rewrite all registry entries; reinstall all shortcuts -->
<Property Id="REINSTALLMODE" Value="amus" />
<!-- Auto launch app after installation, useful for passive mode which usually used in updates -->
<Property Id="AUTOLAUNCHAPP" Secure="yes" />
<!-- Property to forward cli args to the launched app to not lose those of the pre-update instance -->
<Property Id="LAUNCHAPPARGS" Secure="yes" />
{{#if allow_downgrades}}
<MajorUpgrade Schedule="afterInstallInitialize" AllowDowngrades="yes" />
{{else}}
<MajorUpgrade Schedule="afterInstallInitialize" DowngradeErrorMessage="!(loc.DowngradeErrorMessage)" AllowSameVersionUpgrades="yes" />
{{/if}}
<InstallExecuteSequence>
<RemoveShortcuts>Installed AND NOT UPGRADINGPRODUCTCODE</RemoveShortcuts>
</InstallExecuteSequence>
<Media Id="1" Cabinet="app.cab" EmbedCab="yes" />
{{#if banner_path}}
<WixVariable Id="WixUIBannerBmp" Value="{{banner_path}}" />
{{/if}}
{{#if dialog_image_path}}
<WixVariable Id="WixUIDialogBmp" Value="{{dialog_image_path}}" />
{{/if}}
{{#if license}}
<WixVariable Id="WixUILicenseRtf" Value="{{license}}" />
{{/if}}
<Icon Id="ProductIcon" SourceFile="{{icon_path}}"/>
<Property Id="ARPPRODUCTICON" Value="ProductIcon" />
<Property Id="ARPNOREPAIR" Value="yes" Secure="yes" /> <!-- Remove repair -->
<SetProperty Id="ARPNOMODIFY" Value="1" After="InstallValidate" Sequence="execute"/>
<!-- initialize with previous InstallDir -->
<Property Id="INSTALLDIR">
<RegistrySearch Id="PrevInstallDirReg" Root="HKCU" Key="Software\\{{manufacturer}}\\{{product_name}}" Name="InstallDir" Type="raw"/>
</Property>
<!-- launch app checkbox -->
<Property Id="WIXUI_EXITDIALOGOPTIONALCHECKBOXTEXT" Value="!(loc.LaunchApp)" />
<Property Id="WIXUI_EXITDIALOGOPTIONALCHECKBOX" Value="1"/>
<CustomAction Id="LaunchApplication" Impersonate="yes" FileKey="Path" ExeCommand="[LAUNCHAPPARGS]" Return="asyncNoWait" />
<UI>
<!-- launch app checkbox -->
<Publish Dialog="ExitDialog" Control="Finish" Event="DoAction" Value="LaunchApplication">WIXUI_EXITDIALOGOPTIONALCHECKBOX = 1 and NOT Installed</Publish>
<Property Id="WIXUI_INSTALLDIR" Value="INSTALLDIR" />
{{#unless license}}
<!-- Skip license dialog -->
<Publish Dialog="WelcomeDlg"
Control="Next"
Event="NewDialog"
Value="InstallDirDlg"
Order="2">1</Publish>
<Publish Dialog="InstallDirDlg"
Control="Back"
Event="NewDialog"
Value="WelcomeDlg"
Order="2">1</Publish>
{{/unless}}
</UI>
<UIRef Id="WixUI_InstallDir" />
<Directory Id="TARGETDIR" Name="SourceDir">
<Directory Id="DesktopFolder" Name="Desktop">
<Component Id="ApplicationShortcutDesktop" Guid="*">
<Shortcut Id="ApplicationDesktopShortcut" Name="三青鸟智能识别服务" Description="运行 三青鸟智能识别服务" Target="[!Path]" WorkingDirectory="INSTALLDIR" />
<RemoveFolder Id="DesktopFolder" On="uninstall" />
<RegistryValue Root="HKCU" Key="Software\\{{manufacturer}}\\{{product_name}}" Name="Desktop Shortcut" Type="integer" Value="1" KeyPath="yes" />
</Component>
</Directory>
<Directory Id="$(var.PlatformProgramFilesFolder)" Name="PFiles">
<Directory Id="INSTALLDIR" Name="{{product_name}}"/>
</Directory>
<Directory Id="ProgramMenuFolder">
<Directory Id="ApplicationProgramsFolder" Name="{{product_name}}"/>
</Directory>
</Directory>
<DirectoryRef Id="INSTALLDIR">
<Component Id="RegistryEntries" Guid="*">
<RegistryKey Root="HKCU" Key="Software\\{{manufacturer}}\\{{product_name}}">
<RegistryValue Name="InstallDir" Type="string" Value="[INSTALLDIR]" KeyPath="yes" />
</RegistryKey>
</Component>
<Component Id="Path" Guid="{{path_component_guid}}" Win64="$(var.Win64)">
<File Id="Path" Source="{{app_exe_source}}" KeyPath="yes" Checksum="yes"/>
</Component>
{{#each binaries as |bin| ~}}
<Component Id="{{ bin.id }}" Guid="{{bin.guid}}" Win64="$(var.Win64)">
<File Id="Bin_{{ bin.id }}" Source="{{bin.path}}" KeyPath="yes"/>
</Component>
{{/each~}}
{{#if enable_elevated_update_task}}
<Component Id="UpdateTask" Guid="C492327D-9720-4CD5-8DB8-F09082AF44BE" Win64="$(var.Win64)">
<File Id="UpdateTask" Source="update.xml" KeyPath="yes" Checksum="yes"/>
</Component>
<Component Id="UpdateTaskInstaller" Guid="011F25ED-9BE3-50A7-9E9B-3519ED2B9932" Win64="$(var.Win64)">
<File Id="UpdateTaskInstaller" Source="install-task.ps1" KeyPath="yes" Checksum="yes"/>
</Component>
<Component Id="UpdateTaskUninstaller" Guid="D4F6CC3F-32DC-5FD0-95E8-782FFD7BBCE1" Win64="$(var.Win64)">
<File Id="UpdateTaskUninstaller" Source="uninstall-task.ps1" KeyPath="yes" Checksum="yes"/>
</Component>
{{/if}}
{{resources}}
<Component Id="CMP_UninstallShortcut" Guid="*">
<Shortcut Id="UninstallShortcut"
Name="Uninstall {{product_name}}"
Description="Uninstalls {{product_name}}"
Target="[System64Folder]msiexec.exe"
Arguments="/x [ProductCode]" />
<RemoveFolder Id="INSTALLDIR"
On="uninstall" />
<RegistryValue Root="HKCU"
Key="Software\\{{manufacturer}}\\{{product_name}}"
Name="Uninstaller Shortcut"
Type="integer"
Value="1"
KeyPath="yes" />
</Component>
</DirectoryRef>
<DirectoryRef Id="ApplicationProgramsFolder">
<Component Id="ApplicationShortcut" Guid="*">
<Shortcut Id="ApplicationStartMenuShortcut"
Name="三青鸟智能识别服务"
Description="运行 三青鸟智能识别服务"
Target="[!Path]"
Icon="ProductIcon"
WorkingDirectory="INSTALLDIR">
<ShortcutProperty Key="System.AppUserModel.ID" Value="{{bundle_id}}"/>
</Shortcut>
<RemoveFolder Id="ApplicationProgramsFolder" On="uninstall"/>
<RegistryValue Root="HKCU" Key="Software\\{{manufacturer}}\\{{product_name}}" Name="Start Menu Shortcut" Type="integer" Value="1" KeyPath="yes"/>
</Component>
</DirectoryRef>
..............................
</Product>
</Wix>
```
### Reproduction
_No response_
### Expected behavior
_No response_
### Full `tauri info` output
```text
> [email protected] tauri D:\Project\sanqingniao-sdk-server
> tauri "info"
[✔] Environment
- OS: Windows 10.0.26100 x86_64 (X64)
✔ WebView2: 131.0.2903.86
✔ MSVC: Visual Studio Community 2022
✔ rustc: 1.77.2 (25ef9e3d8 2024-04-09)
✔ cargo: 1.77.2 (e52e36006 2024-03-26)
✔ rustup: 1.27.1 (54dd3d00f 2024-04-24)
✔ Rust toolchain: 1.77-x86_64-pc-windows-msvc (default)
- node: 22.11.0
- pnpm: 9.12.3
- npm: 10.9.0
[-] Packages
- tauri 🦀: 2.1.1
- tauri-build 🦀: 2.0.3
- wry 🦀: 0.47.0
- tao 🦀: 0.30.8
- @tauri-apps/api : 2.0.0-rc.4 (outdated, latest: 2.1.1)
- @tauri-apps/cli : 2.1.0
```
### Stack trace
```text
> [email protected] tauri D:\Project\sanqingniao-sdk-server
> tauri "build" "-v" "--target" "x86_64-pc-windows-msvc"
Debug [ignore::gitignore] opened gitignore file: C:\Users\WORK\AppData\Local\Temp\.gitignore
Debug [globset] built glob set; 0 literals, 3 basenames, 0 extensions, 0 prefixes, 0 suffixes, 0 required extensions, 0 regexes
Debug [ignore::gitignore] opened gitignore file: D:\Project\sanqingniao-sdk-server\.gitignore
Debug [globset] glob converted to regex: Glob { glob: "**/npm-debug.log*", re: "(?-u)^(?:/?|.*/)npm\\-debug\\.log[^/]*$", opts: GlobOptions { case_insensitive: false, literal_separator: true, backslash_escape: true, empty_alternates: false }, tokens: Tokens([RecursivePrefix, Literal('n'), Literal('p'), Literal('m'), Literal('-'), Literal('d'), Literal('e'), Literal('b'), Literal('u'), Literal('g'), Literal('.'), Literal('l'), Literal('o'), Literal('g'), ZeroOrMore]) }
Debug [globset] glob converted to regex: Glob { glob: "**/yarn-debug.log*", re: "(?-u)^(?:/?|.*/)yarn\\-debug\\.log[^/]*$", opts: GlobOptions { case_insensitive: false, literal_separator: true, backslash_escape: true, empty_alternates: false }, tokens: Tokens([RecursivePrefix, Literal('y'), Literal('a'), Literal('r'), Literal('n'), Literal('-'), Literal('d'), Literal('e'), Literal('b'), Literal('u'), Literal('g'), Literal('.'), Literal('l'), Literal('o'), Literal('g'), ZeroOrMore]) }
Debug [globset] glob converted to regex: Glob { glob: "**/yarn-error.log*", re: "(?-u)^(?:/?|.*/)yarn\\-error\\.log[^/]*$", opts: GlobOptions { case_insensitive: false, literal_separator: true, backslash_escape: true, empty_alternates: false }, tokens: Tokens([RecursivePrefix, Literal('y'), Literal('a'), Literal('r'), Literal('n'), Literal('-'), Literal('e'), Literal('r'), Literal('r'), Literal('o'), Literal('r'), Literal('.'), Literal('l'), Literal('o'), Literal('g'), ZeroOrMore]) }
Debug [globset] glob converted to regex: Glob { glob: "**/pnpm-debug.log*", re: "(?-u)^(?:/?|.*/)pnpm\\-debug\\.log[^/]*$", opts: GlobOptions { case_insensitive: false, literal_separator: true, backslash_escape: true, empty_alternates: false }, tokens: Tokens([RecursivePrefix, Literal('p'), Literal('n'), Literal('p'), Literal('m'), Literal('-'), Literal('d'), Literal('e'), Literal('b'), Literal('u'), Literal('g'), Literal('.'), Literal('l'), Literal('o'), Literal('g'), ZeroOrMore]) }
Debug [globset] glob converted to regex: Glob { glob: "**/lerna-debug.log*", re: "(?-u)^(?:/?|.*/)lerna\\-debug\\.log[^/]*$", opts: GlobOptions { case_insensitive: false, literal_separator: true, backslash_escape: true, empty_alternates: false }, tokens: Tokens([RecursivePrefix, Literal('l'), Literal('e'), Literal('r'), Literal('n'), Literal('a'), Literal('-'), Literal('d'), Literal('e'), Literal('b'), Literal('u'), Literal('g'), Literal('.'), Literal('l'), Literal('o'), Literal('g'), ZeroOrMore]) }
Debug [globset] glob converted to regex: Glob { glob: "**/*.ntvs*", re: "(?-u)^(?:/?|.*/)[^/]*\\.ntvs[^/]*$", opts: GlobOptions { case_insensitive: false, literal_separator: true, backslash_escape: true, empty_alternates: false }, tokens: Tokens([RecursivePrefix, ZeroOrMore, Literal('.'), Literal('n'), Literal('t'), Literal('v'), Literal('s'), ZeroOrMore]) }
Debug [globset] glob converted to regex: Glob { glob: "**/*.sw?", re: "(?-u)^(?:/?|.*/)[^/]*\\.sw[^/]$", opts: GlobOptions { case_insensitive: false, literal_separator: true, backslash_escape: true, empty_alternates: false }, tokens: Tokens([RecursivePrefix, ZeroOrMore, Literal('.'), Literal('s'), Literal('w'), Any]) }
Debug [globset] built glob set; 1 literals, 7 basenames, 5 extensions, 0 prefixes, 0 suffixes, 0 required extensions, 7 regexes
Debug [ignore::gitignore] opened gitignore file: D:\Project\sanqingniao-sdk-server\.git\info/exclude
Debug [ignore::walk] ignoring D:\Project\sanqingniao-sdk-server\.git: Ignore(IgnoreMatch(Hidden))
Debug [ignore::walk] ignoring D:\Project\sanqingniao-sdk-server\.gitignore: Ignore(IgnoreMatch(Hidden))
Debug [ignore::walk] ignoring D:\Project\sanqingniao-sdk-server\.vscode: Ignore(IgnoreMatch(Hidden))
Debug [ignore::walk] ignoring D:\Project\sanqingniao-sdk-server\node_modules: Ignore(IgnoreMatch(Gitignore(Glob { from: Some("D:\\Project\\sanqingniao-sdk-server\\.gitignore"), original: "node_modules", actual: "**/node_modules", is_whitelist: false, is_only_dir: false })))
Debug [ignore::walk] ignoring D:\Project\sanqingniao-sdk-server\publish: Ignore(IgnoreMatch(Gitignore(Glob { from: Some("D:\\Project\\sanqingniao-sdk-server\\.gitignore"), original: "publish/", actual: "**/publish", is_whitelist: false, is_only_dir: true })))
Debug [ignore::gitignore] opened gitignore file: D:\Project\sanqingniao-sdk-server\src-tauri\.taurignore
Debug [globset] glob converted to regex: Glob { glob: "**/*", re: "(?-u)^(?:/?|.*/)[^/]*$", opts: GlobOptions { case_insensitive: false, literal_separator: true, backslash_escape: true, empty_alternates: false }, tokens: Tokens([RecursivePrefix, ZeroOrMore]) }
Debug [globset] built glob set; 0 literals, 0 basenames, 0 extensions, 0 prefixes, 0 suffixes, 0 required extensions, 1 regexes
Debug [ignore::gitignore] opened gitignore file: D:\Project\sanqingniao-sdk-server\src-tauri\.gitignore
Debug [globset] built glob set; 6 literals, 1 basenames, 1 extensions, 0 prefixes, 0 suffixes, 0 required extensions, 0 regexes
Running [tauri_cli::helpers] beforeBuildCommand `pnpm build`
Debug [tauri_cli::helpers] Setting environment for hook {"TAURI_ENV_PLATFORM_VERSION": "10.0.26100", "TAURI_ENV_TARGET_TRIPLE": "x86_64-pc-windows-msvc", "TAURI_ENV_ARCH": "x86_64", "TAURI_ENV_FAMILY": "windows", "TAURI_ENV_PLATFORM": "windows"}
Running [tauri_cli] Command `cmd /S /C pnpm build`
> [email protected] build D:\Project\sanqingniao-sdk-server
> vue-tsc --noEmit && vite build
vite v5.4.3 building for production...
✓ 1303 modules transformed.
dist/pages/main.html 0.76 kB │ gzip: 0.52 kB
dist/pages/splashscreen.html 1.80 kB │ gzip: 0.80 kB
dist/assets/baizealgo_back-Dgf-8QIC.jpg 41.68 kB
dist/assets/erlangshenalgo_back-DSYKtN6F.jpg 62.85 kB
dist/assets/sanqingniaosdk_back-BzInh3_R.jpg 68.87 kB
dist/assets/CheckUpdate-CtAyQnI0.css 0.08 kB │ gzip: 0.09 kB
dist/assets/index-COY1Xr-1.css 0.25 kB │ gzip: 0.16 kB
dist/assets/index-D51qY0Tq.css 0.88 kB │ gzip: 0.35 kB
dist/assets/index-aSSsIgfw.css 1.00 kB │ gzip: 0.34 kB
dist/assets/main-BpK3FEd3.css 403.51 kB │ gzip: 49.64 kB
dist/assets/index-CVYIof_7.js 0.24 kB │ gzip: 0.16 kB
dist/assets/core-CMakcZJw.js 1.31 kB │ gzip: 0.67 kB
dist/assets/index-Dh9UD-Wn.js 2.84 kB │ gzip: 1.46 kB
dist/assets/index-ChWv-SvG.js 5.13 kB │ gzip: 2.28 kB
dist/assets/index-BaENkhqC.js 11.94 kB │ gzip: 2.91 kB
dist/assets/CheckUpdate-DqEdpYxG.js 95.84 kB │ gzip: 47.96 kB
dist/assets/main-BF6nlF4B.js 1,400.14 kB │ gzip: 362.48 kB
(!) Some chunks are larger than 500 kB after minification. Consider:
- Using dynamic import() to code-split the application
- Use build.rollupOptions.output.manualChunks to improve chunking: https://rollupjs.org/configuration-options/#output-manualchunks
- Adjust chunk size limit for this warning via build.chunkSizeWarningLimit.
✓ built in 6.18s
Running [tauri_cli] Command `cargo build --bins --features tauri/custom-protocol,tauri/native-tls --release --target x86_64-pc-windows-msvc`
Compiling proc-macro2 v1.0.86
Compiling unicode-ident v1.0.12
Compiling windows_x86_64_msvc v0.52.6
Compiling cfg-if v1.0.0
Compiling autocfg v1.3.0
Compiling serde v1.0.204
Compiling siphasher v0.3.11
Compiling ppv-lite86 v0.2.17
Compiling syn v1.0.109
Compiling getrandom v0.1.16
Compiling windows_x86_64_msvc v0.48.5
Compiling getrandom v0.2.15
Compiling thiserror v1.0.62
Compiling rand_core v0.6.4
Compiling parking_lot_core v0.9.10
Compiling phf_shared v0.8.0
Compiling rand_chacha v0.3.1
Compiling phf_shared v0.10.0
Compiling lock_api v0.4.12
Compiling fnv v1.0.7
Compiling proc-macro-hack v0.5.20+deprecated
Compiling rand v0.8.5
Compiling ident_case v1.0.1
Compiling strsim v0.11.1
Compiling smallvec v1.13.2
Compiling hashbrown v0.14.5
Compiling convert_case v0.4.0
Compiling windows-targets v0.52.6
Compiling rand_core v0.5.1
Compiling equivalent v1.0.1
Compiling windows-sys v0.52.0
Compiling phf_shared v0.11.2
Compiling thiserror v2.0.3
Compiling rand_chacha v0.2.2
Compiling rand_pcg v0.2.1
Compiling winnow v0.5.40
Compiling rand v0.7.3
Compiling once_cell v1.19.0
Compiling memchr v2.7.4
Compiling quote v1.0.36
Compiling phf_generator v0.10.0
Compiling syn v2.0.87
Compiling string_cache_codegen v0.5.2
Compiling phf_codegen v0.10.0
Compiling indexmap v2.2.6
Compiling itoa v1.0.11
Compiling phf_generator v0.11.2
Compiling phf_generator v0.8.0
Compiling new_debug_unreachable v1.0.6
Compiling byteorder v1.5.0
Compiling serde_json v1.0.120
Compiling markup5ever v0.11.0
Compiling phf_codegen v0.8.0
Compiling semver v1.0.23
Compiling scopeguard v1.2.0
Compiling selectors v0.22.0
Compiling tinyvec_macros v0.1.1
Compiling tinyvec v1.8.0
Compiling ryu v1.0.18
Compiling precomputed-hash v0.1.1
Compiling mac v0.1.1
Compiling indexmap v1.9.3
Compiling futf v0.1.5
Compiling parking_lot v0.12.3
Compiling percent-encoding v2.3.1
Compiling log v0.4.22
Compiling pin-project-lite v0.2.14
Compiling bitflags v1.3.2
Compiling unicode-bidi v0.3.15
Compiling dtoa v1.0.9
Compiling utf-8 v0.7.6
Compiling unicode-normalization v0.1.23
Compiling form_urlencoded v1.2.1
Compiling dtoa-short v0.3.5
Compiling tendril v0.4.3
Compiling aho-corasick v1.1.3
Compiling phf v0.10.1
Compiling itoa v0.4.8
Compiling nodrop v0.1.14
Compiling idna v0.5.0
Compiling unic-common v0.9.0
Compiling matches v0.1.10
Compiling regex-syntax v0.8.4
Compiling camino v1.1.7
Compiling stable_deref_trait v1.2.0
Compiling hashbrown v0.12.3
Compiling alloc-no-stdlib v2.0.4
Compiling unic-char-range v0.9.0
Compiling alloc-stdlib v0.2.2
Compiling unic-char-property v0.9.0
Compiling servo_arc v0.1.1
Compiling unic-ucd-version v0.9.0
Compiling windows-targets v0.48.5
Compiling fxhash v0.2.1
Compiling schemars v0.8.21
Compiling darling_core v0.20.10
Compiling winapi-util v0.1.8
Compiling serde_derive_internals v0.29.1
Compiling thin-slice v0.1.1
Compiling typeid v1.0.0
Compiling same-file v1.0.6
Compiling windows-sys v0.48.0
Compiling unic-ucd-ident v0.9.0
Compiling brotli-decompressor v4.0.1
Compiling slab v0.4.9
Compiling dyn-clone v1.0.17
Compiling bytes v1.6.1
Compiling anyhow v1.0.86
Compiling futures-core v0.3.30
Compiling regex-automata v0.4.7
Compiling futures-sink v0.3.30
Compiling http v1.1.0
Compiling brotli v7.0.0
Compiling walkdir v2.5.0
Compiling glob v0.3.1
Compiling dunce v1.0.4
Compiling version_check v0.9.4
Compiling libc v0.2.155
Compiling cc v1.1.5
Compiling futures-channel v0.3.30
Compiling heck v0.5.0
Compiling futures-task v0.3.30
Compiling pin-utils v0.1.0
Compiling futures-io v0.3.30
Compiling serde_derive v1.0.204
Compiling thiserror-impl v1.0.62
Compiling cssparser v0.27.2
Compiling phf_macros v0.8.0
Compiling html5ever v0.26.0
Compiling darling_macro v0.20.10
Compiling cssparser-macros v0.6.1
Compiling darling v0.20.10
Compiling derive_more v0.99.18
Compiling thiserror-impl v2.0.3
Compiling phf_macros v0.11.2
Compiling serde_with_macros v3.9.0
Compiling phf v0.8.0
Compiling ctor v0.2.8
Compiling regex v1.10.5
Compiling schemars_derive v0.8.21
Compiling vswhom-sys v0.1.2
Compiling phf v0.11.2
Compiling futures-macro v0.3.30
Compiling mio v0.8.11
Compiling socket2 v0.5.7
Compiling num_cpus v1.16.0
Compiling futures-util v0.3.30
Compiling winreg v0.52.0
Compiling vswhom v0.1.0
Compiling tracing-attributes v0.1.27
Compiling tracing-core v0.1.32
Compiling option-ext v0.2.0
Compiling dirs-sys v0.4.1
Compiling windows-result v0.2.0
Compiling httparse v1.9.4
Compiling typenum v1.17.0
Compiling windows-strings v0.1.0
Compiling dirs v5.0.1
Compiling tracing v0.1.40
Compiling pin-project-internal v1.1.5
Compiling windows-implement v0.58.0
Compiling windows-interface v0.58.0
Compiling serde_spanned v0.6.6
Compiling toml_datetime v0.6.3
Compiling toml_edit v0.20.2
Compiling uuid v1.10.0
Compiling string_cache v0.8.7
Compiling url v2.5.2
Compiling cfb v0.7.3
Compiling cargo-platform v0.1.8
Compiling erased-serde v0.4.5
Compiling jsonptr v0.6.3
Compiling cargo_metadata v0.18.1
Compiling infer v0.16.0
Compiling json-patch v3.0.1
Compiling serde-untagged v0.1.6
Compiling urlpattern v0.3.0
Compiling serde_with v3.9.0
Compiling toml v0.8.2
Compiling kuchikiki v0.8.2
Compiling tokio v1.38.0
Compiling rustc_version v0.4.0
Compiling toml_edit v0.19.15
Compiling embed-resource v2.4.2
Compiling http-body v1.0.1
Compiling cargo_toml v0.17.2
Compiling tauri-utils v2.1.0
Compiling generic-array v0.14.7
Compiling toml v0.7.8
Compiling try-lock v0.2.5
Compiling tauri-winres v0.1.1
Compiling atomic-waker v1.1.2
Compiling want v0.3.1
Compiling pin-project v1.1.5
Compiling windows-core v0.58.0
Compiling bitflags v2.6.0
Compiling tokio-util v0.7.11
Compiling h2 v0.4.5
Compiling crossbeam-utils v0.8.20
Compiling tower-service v0.3.2
Compiling tower-layer v0.3.2
Compiling simd-adler32 v0.3.7
Compiling tower v0.4.13
Compiling tauri-build v2.0.3
Compiling windows v0.58.0
Compiling dpi v0.1.1
Compiling raw-window-handle v0.6.2
Compiling adler v1.0.2
Compiling miniz_oxide v0.7.4
Compiling hyper v1.4.1
Compiling tauri-plugin v2.0.3
Compiling hyper-util v0.1.6
Compiling webview2-com-sys v0.33.0
Compiling crc32fast v1.4.2
Compiling time-core v0.1.2
Compiling winapi v0.3.9
Compiling unicode-segmentation v1.11.0
Compiling num-conv v0.1.0
Compiling native-tls v0.2.12
Compiling powerfmt v0.2.0
Compiling deranged v0.3.11
Compiling time-macros v0.2.18
Compiling flate2 v1.0.30
Compiling crossbeam-channel v0.5.13
Compiling block-buffer v0.10.4
Compiling crypto-common v0.1.6
Compiling fdeflate v0.3.4
Compiling http-body-util v0.1.2
Compiling cookie v0.18.1
Compiling schannel v0.1.23
Compiling windows-version v0.1.1
Compiling cfg_aliases v0.2.1
Compiling base64 v0.22.1
Compiling time v0.3.36
Compiling softbuffer v0.4.5
Compiling png v0.17.13
Compiling digest v0.10.7
Compiling tauri v2.1.1
Compiling serde_urlencoded v0.7.1
Compiling serde_repr v0.1.19
Compiling webview2-com-macros v0.8.0
Compiling wry v0.47.0
Compiling tauri-runtime v2.2.0
Compiling cpufeatures v0.2.12
Compiling sha2 v0.10.8
Compiling ico v0.3.0
Compiling tokio-native-tls v0.3.1
Compiling keyboard-types v0.7.0
Compiling instant v0.1.13
Compiling windows-sys v0.59.0
Compiling rustls-pki-types v1.7.0
Compiling utf8parse v0.2.2
Compiling lazy_static v1.5.0
Compiling tauri-runtime-wry v2.2.0
Compiling anstyle v1.0.7
Compiling anstyle-wincon v3.0.3
Compiling anstyle-parse v0.2.4
Compiling tauri-codegen v2.0.3
Compiling rustls-pemfile v2.1.2
Compiling hyper-tls v0.6.0
Compiling serialize-to-javascript-impl v0.1.1
Compiling anstyle-query v1.1.0
Compiling encoding_rs v0.8.34
Compiling sync_wrapper v1.0.1
Compiling colorchoice v1.0.1
Compiling mime v0.3.17
Compiling ipnet v2.9.0
Compiling is_terminal_polyfill v1.70.0
Compiling anstream v0.6.14
Compiling muda v0.15.3
Compiling serialize-to-javascript v0.1.1
Compiling tray-icon v0.19.1
Compiling reqwest v0.12.5
Compiling window-vibrancy v0.5.0
Compiling winreg v0.10.1
Compiling clap_lex v0.7.1
Compiling cfg_aliases v0.1.1
Compiling nix v0.28.0
Compiling clap_builder v4.5.9
Compiling tauri-macros v2.0.3
Compiling tauri-plugin-shell v2.0.2
Compiling tauri-plugin-upload v2.1.0
Compiling tauri-plugin-autostart v2.0.1
Compiling futures-executor v0.3.30
Compiling clap_derive v4.5.8
Compiling num-traits v0.2.19
Compiling hex v0.4.3
Compiling hyper-named-pipe v0.1.0
Compiling futures v0.3.30
Compiling bollard-stubs v1.44.0-rc.2
Compiling env_filter v0.1.0
Compiling windows-core v0.52.0
Compiling kill_tree v0.2.4
Compiling humantime v2.1.0
Compiling clap v4.5.9
Compiling clap-verbosity-flag v2.2.0
Compiling env_logger v0.11.3
Compiling windows v0.52.0
Compiling auto-launch v0.5.0
Compiling read-progress-stream v1.0.0
Compiling shared_child v1.0.0
Compiling sanqingniaosdk-server v1.0.0 (D:\Project\sanqingniao-sdk-server\src-tauri)
Compiling os_pipe v1.2.0
Compiling open v5.3.0
Compiling chrono v0.4.38
Compiling fern v0.6.2
Compiling tao v0.30.8
Compiling webview2-com v0.33.0
Compiling bollard v0.16.1
Compiling killport v1.1.0
Compiling tauri-plugin-single-instance v2.0.1
Finished release [optimized] target(s) in 1m 52s
Built [tauri_cli::build] application at: D:\Project\sanqingniao-sdk-server\src-tauri\target\x86_64-pc-windows-msvc\release\sanqingniaosdk-server.exe
Signing [tauri_bundler::bundle::windows::sign] D:\Project\sanqingniao-sdk-server\src-tauri\target\x86_64-pc-windows-msvc\release\sanqingniaosdk-server.exe
Signing [tauri_bundler::bundle::windows::sign] D:\Project\sanqingniao-sdk-server\src-tauri\target\x86_64-pc-windows-msvc\release\sanqingniaosdk-server.exe with a custom signing command
Running [tauri_bundler::bundle::common] Command `sign-client -file D:\Project\sanqingniao-sdk-server\src-tauri\target\x86_64-pc-windows-msvc\release\sanqingniaosdk-server.exe`
Application signing···
Application sign over.
Info [tauri_bundler::bundle::windows::sign] "Application signing···\nApplication sign over.\n"
Info [tauri_bundler::bundle::windows::msi] Target: x64
Downloading [tauri_bundler::bundle::windows::util] https://go.microsoft.com/fwlink/p/?LinkId=2124703
Debug [ureq::stream] connecting to go.microsoft.com:443 at [2600:1406:2e00:895::2c1a]:443
Debug [rustls::client::hs] No cached session for DnsName("go.microsoft.com")
Debug [rustls::client::hs] Not resuming any session
Debug [rustls::client::hs] Using ciphersuite TLS13_AES_256_GCM_SHA384
Debug [rustls::client::tls13] Not resuming
Debug [rustls::client::tls13] TLS1.3 encrypted extensions: [ServerNameAck, Unknown(UnknownExtension { typ: EllipticCurves, payload: 00040017001d })]
Debug [rustls::client::hs] ALPN protocol is None
Debug [ureq::stream] created stream: Stream(RustlsStream)
Debug [ureq::unit] sending request GET https://go.microsoft.com/fwlink/p/?LinkId=2124703
Debug [ureq::unit] writing prelude: GET /fwlink/p/?LinkId=2124703 HTTP/1.1
Host: go.microsoft.com
User-Agent: ureq/2.10.1
Accept: */*
accept-encoding: gzip
Debug [ureq::response] zero-length body returning stream directly to pool
Debug [ureq::pool] adding stream to pool: https|go.microsoft.com|443 -> Stream(RustlsStream)
Debug [ureq::unit] response 301 to GET https://go.microsoft.com/fwlink/p/?LinkId=2124703
Debug [ureq::unit] redirect 301 https://go.microsoft.com/fwlink/p/?LinkId=2124703 -> https://msedge.sf.dl.delivery.mp.microsoft.com/filestreamingservice/files/3aa91245-82ae-4367-bbc2-c8d7a8fc1730/MicrosoftEdgeWebview2Setup.exe
Debug [ureq::stream] connecting to msedge.sf.dl.delivery.mp.microsoft.com:443 at 115.231.143.74:443
Debug [rustls::client::hs] No cached session for DnsName("msedge.sf.dl.delivery.mp.microsoft.com")
Debug [rustls::client::hs] Not resuming any session
Debug [rustls::client::hs] ALPN protocol is None
Debug [rustls::client::hs] Using ciphersuite TLS_ECDHE_RSA_WITH_AES_128_GCM_SHA256
Debug [rustls::client::tls12::server_hello] Server supports tickets
Debug [rustls::client::tls12] ECDHE curve is EcParameters { curve_type: NamedCurve, named_group: X25519 }
Debug [rustls::client::tls12] Server DNS name is DnsName("msedge.sf.dl.delivery.mp.microsoft.com")
Debug [ureq::stream] created stream: Stream(RustlsStream)
Debug [ureq::unit] sending request GET https://msedge.sf.dl.delivery.mp.microsoft.com/filestreamingservice/files/3aa91245-82ae-4367-bbc2-c8d7a8fc1730/MicrosoftEdgeWebview2Setup.exe
Debug [ureq::unit] writing prelude: GET /filestreamingservice/files/3aa91245-82ae-4367-bbc2-c8d7a8fc1730/MicrosoftEdgeWebview2Setup.exe HTTP/1.1
Host: msedge.sf.dl.delivery.mp.microsoft.com
User-Agent: ureq/2.10.1
Accept: */*
accept-encoding: gzip
Debug [ureq::response] Streaming body until content-length: 1655248
Debug [ureq::unit] response 200 to GET https://msedge.sf.dl.delivery.mp.microsoft.com/filestreamingservice/files/3aa91245-82ae-4367-bbc2-c8d7a8fc1730/MicrosoftEdgeWebview2Setup.exe
Debug [ureq::pool] adding stream to pool: https|msedge.sf.dl.delivery.mp.microsoft.com|443 -> Stream(RustlsStream)
Debug [ureq::stream] dropping stream: Stream(RustlsStream)
Debug [ureq::stream] dropping stream: Stream(RustlsStream)
Debug [handlebars::render] Rendering value: Path(Relative(([Named("product_name")], "product_name")))
Debug [handlebars::render] Rendering value: Path(Relative(([Named("upgrade_code")], "upgrade_code")))
Debug [handlebars::render] Rendering value: Path(Relative(([Named("manufacturer")], "manufacturer")))
Debug [handlebars::render] Rendering value: Path(Relative(([Named("version")], "version")))
Debug [handlebars::render] Rendering helper: "if", params: [PathAndJson { relative_path: Some("allow_downgrades"), value: Context(Bool(true), ["allow_downgrades"]) }], hash: {}
Debug [handlebars::render] Rendering helper: "if", params: [PathAndJson { relative_path: Some("banner_path"), value: Missing }], hash: {}
Debug [handlebars::render] Rendering helper: "if", params: [PathAndJson { relative_path: Some("dialog_image_path"), value: Missing }], hash: {}
Debug [handlebars::render] Rendering helper: "if", params: [PathAndJson { relative_path: Some("license"), value: Missing }], hash: {}
Debug [handlebars::render] Rendering value: Path(Relative(([Named("icon_path")], "icon_path")))
Debug [handlebars::render] Rendering value: Path(Relative(([Named("manufacturer")], "manufacturer")))
Debug [handlebars::render] Rendering value: Path(Relative(([Named("product_name")], "product_name")))
Debug [handlebars::render] Rendering helper: "unless", params: [PathAndJson { relative_path: Some("license"), value: Missing }], hash: {}
Debug [handlebars::render] Rendering value: Path(Relative(([Named("manufacturer")], "manufacturer")))
Debug [handlebars::render] Rendering value: Path(Relative(([Named("product_name")], "product_name")))
Debug [handlebars::render] Rendering value: Path(Relative(([Named("product_name")], "product_name")))
Debug [handlebars::render] Rendering value: Path(Relative(([Named("product_name")], "product_name")))
Debug [handlebars::render] Rendering value: Path(Relative(([Named("manufacturer")], "manufacturer")))
Debug [handlebars::render] Rendering value: Path(Relative(([Named("product_name")], "product_name")))
Debug [handlebars::render] Rendering value: Path(Relative(([Named("path_component_guid")], "path_component_guid")))
Debug [handlebars::render] Rendering value: Path(Relative(([Named("app_exe_source")], "app_exe_source")))
Debug [handlebars::render] Rendering helper: "each", params: [PathAndJson { relative_path: Some("binaries"), value: Context(Array [], ["binaries"]) }], hash: {}
Debug [handlebars::render] Rendering helper: "if", params: [PathAndJson { relative_path: Some("enable_elevated_update_task"), value: Missing }], hash: {}
Debug [handlebars::render] Rendering value: Path(Relative(([Named("resources")], "resources")))
Debug [handlebars::render] Rendering value: Path(Relative(([Named("product_name")], "product_name")))
Debug [handlebars::render] Rendering value: Path(Relative(([Named("product_name")], "product_name")))
Debug [handlebars::render] Rendering value: Path(Relative(([Named("manufacturer")], "manufacturer")))
Debug [handlebars::render] Rendering value: Path(Relative(([Named("product_name")], "product_name")))
Debug [handlebars::render] Rendering value: Path(Relative(([Named("bundle_id")], "bundle_id")))
Debug [handlebars::render] Rendering value: Path(Relative(([Named("manufacturer")], "manufacturer")))
Debug [handlebars::render] Rendering value: Path(Relative(([Named("product_name")], "product_name")))
Debug [handlebars::render] Rendering helper: "each", params: [PathAndJson { relative_path: Some("merge_modules"), value: Context(Array [], ["merge_modules"]) }], hash: {}
Debug [handlebars::render] Rendering helper: "each", params: [PathAndJson { relative_path: Some("resource_file_ids"), value: Context(Array [String("I84efb96b5c874c3d9d6ff920f621fdf4"), String("Iead03a09e20d486f8cc1373739363419"), String("Id3c69a1eae8e4a54ab3b0671a28c3745"), String("Ic04adf9282464c14858030af4aedd8e7"), String("I70bd3fad9cc64a2cb2ce44dbea69fabe"), String("I1c7a0712898f44ababcf1c306dd99fea"), String("I056ec69671ff448786d718bba24444d6"), String("I83366682df0e4122b224ecbcf5a6b185")], ["resource_file_ids"]) }], hash: {}
Debug [handlebars::render] Rendering value: Path(Relative(([Named("resource_file_id")], "resource_file_id")))
Debug [handlebars::render] Rendering value: Path(Relative(([Named("resource_file_id")], "resource_file_id")))
Debug [handlebars::render] Rendering value: Path(Relative(([Named("resource_file_id")], "resource_file_id")))
Debug [handlebars::render] Rendering value: Path(Relative(([Named("resource_file_id")], "resource_file_id")))
Debug [handlebars::render] Rendering value: Path(Relative(([Named("resource_file_id")], "resource_file_id")))
Debug [handlebars::render] Rendering value: Path(Relative(([Named("resource_file_id")], "resource_file_id")))
Debug [handlebars::render] Rendering value: Path(Relative(([Named("resource_file_id")], "resource_file_id")))
Debug [handlebars::render] Rendering value: Path(Relative(([Named("resource_file_id")], "resource_file_id")))
Debug [handlebars::render] Rendering helper: "if", params: [PathAndJson { relative_path: Some("enable_elevated_update_task"), value: Missing }], hash: {}
Debug [handlebars::render] Rendering helper: "each", params: [PathAndJson { relative_path: Some("binaries"), value: Context(Array [], ["binaries"]) }], hash: {}
Debug [handlebars::render] Rendering helper: "each", params: [PathAndJson { relative_path: Some("component_group_refs"), value: Context(Array [], ["component_group_refs"]) }], hash: {}
Debug [handlebars::render] Rendering helper: "each", params: [PathAndJson { relative_path: Some("component_refs"), value: Context(Array [], ["component_refs"]) }], hash: {}
Debug [handlebars::render] Rendering helper: "each", params: [PathAndJson { relative_path: Some("feature_group_refs"), value: Context(Array [], ["feature_group_refs"]) }], hash: {}
Debug [handlebars::render] Rendering helper: "each", params: [PathAndJson { relative_path: Some("feature_refs"), value: Context(Array [], ["feature_refs"]) }], hash: {}
Debug [handlebars::render] Rendering helper: "each", params: [PathAndJson { relative_path: Some("merge_refs"), value: Context(Array [], ["merge_refs"]) }], hash: {}
Debug [handlebars::render] Rendering helper: "if", params: [PathAndJson { relative_path: Some("install_webview"), value: Context(Bool(true), ["install_webview"]) }], hash: {}
Debug [handlebars::render] Rendering helper: "if", params: [PathAndJson { relative_path: Some("download_bootstrapper"), value: Missing }], hash: {}
Debug [handlebars::render] Rendering helper: "if", params: [PathAndJson { relative_path: Some("webview2_bootstrapper_path"), value: Context(String("D:\\Project\\sanqingniao-sdk-server\\src-tauri\\target\\x86_64-pc-windows-msvc\\release\\wix\\x64\\MicrosoftEdgeWebview2Setup.exe"), ["webview2_bootstrapper_path"]) }], hash: {}
Debug [handlebars::render] Rendering value: Path(Relative(([Named("webview2_bootstrapper_path")], "webview2_bootstrapper_path")))
Debug [handlebars::render] Rendering value: Path(Relative(([Named("webview_installer_args")], "webview_installer_args")))
Debug [handlebars::render] Rendering helper: "if", params: [PathAndJson { relative_path: Some("webview2_installer_path"), value: Missing }], hash: {}
Debug [handlebars::render] Rendering helper: "if", params: [PathAndJson { relative_path: Some("enable_elevated_update_task"), value: Missing }], hash: {}
Running [tauri_bundler::bundle::windows::msi] candle for "main.wxs"
Running [tauri_bundler::bundle::common] Command `C:\Users\WORK\AppData\Local\tauri\WixTools314\candle.exe -arch x64 main.wxs -dSourceDir=D:\Project\sanqingniao-sdk-server\src-tauri\target\x86_64-pc-windows-msvc\release\sanqingniaosdk-server.exe`
Windows Installer XML Toolset Compiler version 3.14.1.8722
Copyright (c) .NET Foundation and contributors. All rights reserved.
main.wxs
D:\Project\sanqingniao-sdk-server\src-tauri\target\x86_64-pc-windows-msvc\release\wix\x64\main.wxs(108) : error CNDL0006 : The File/@Source attribute's value cannot be an empty string. If a value is not required, simply remove the entire attribute.
D:\Project\sanqingniao-sdk-server\src-tauri\target\x86_64-pc-windows-msvc\release\wix\x64\main.wxs(108) : error CNDL0027 : The File/@Source attribute's value, '', is not a valid long name because it contains illegal characters. Legal long names contain no more than 260 characters and must contain at least one non-period character. Any character except for the follow may be used: \ ? | > < : / * ".
candle.exe : error CNDL0001 : 值不能为 null。
参数名: longName
Exception Type: System.ArgumentNullException
Stack Trace:
在 Microsoft.Tools.WindowsInstallerXml.CompilerCore.GenerateShortName(String longName, Boolean keepExtension, Boolean allowWildcards, String[] args)
在 Microsoft.Tools.WindowsInstallerXml.Compiler.ParseFileElement(XmlNode node, String componentId, String directoryId, Int32 diskId, String sourcePath, String& possibleKeyPath, Boolean win64Component, String componentGuid)
在 Microsoft.Tools.WindowsInstallerXml.Compiler.ParseComponentElement(XmlNode node, ComplexReferenceParentType parentType, String parentId, String parentLanguage, Int32 diskId, String directoryId, String srcPath)
在 Microsoft.Tools.WindowsInstallerXml.Compiler.ParseDirectoryRefElement(XmlNode node)
在 Microsoft.Tools.WindowsInstallerXml.Compiler.ParseProductElement(XmlNode node)
在 Microsoft.Tools.WindowsInstallerXml.Compiler.ParseWixElement(XmlNode node)
在 Microsoft.Tools.WindowsInstallerXml.Compiler.Compile(XmlDocument source)
在 Microsoft.Tools.WindowsInstallerXml.Tools.Candle.Run(String[] args)
在 Microsoft.Tools.WindowsInstallerXml.Tools.Candle.Run(String[] args)
failed to bundle project: error running candle.exe: `failed to run C:\Users\WORK\AppData\Local\tauri\WixTools314\candle.exe`
failed to bundle project: error running candle.exe: `failed to run C:\Users\WORK\AppData\Local\tauri\WixTools314\candle.exe`
Error [tauri_cli_node] failed to bundle project: error running candle.exe: `failed to run C:\Users\WORK\AppData\Local\tauri\WixTools314\candle.exe`
```
### Additional context
_No response_ | type: bug,platform: Windows,status: needs triage | low | Critical |
2,726,396,858 | rust | Some code suggestions failed to be shown due to span tweaking | ### Code
```Rust
const x: () = |&'a
```
### Current output
```Shell
error: unexpected lifetime `'a` in pattern
--> fuzz_input.rs:1:19
|
1 | const x: () = |&'a
| ^^
|
error: expected parameter name, found `<eof>`
--> fuzz_input.rs:1:19
|
1 | const x: () = |&'a
| ^^ expected parameter name
error: aborting due to 2 previous errors
```
### Desired output
```Shell
error: unexpected lifetime `'a` in pattern
--> fuzz_input.rs:1:19
|
1 | const x: () = |&'a
| ^^
|
help: remove the lifetime
|
1 - const x: () = |&'a
1 + const x: () = |&
|
error: expected parameter name, found `<eof>`
--> fuzz_input.rs:1:21
|
1 | const x: () = |&'a
| ^ expected parameter name
error: aborting due to 2 previous errors
```
### Rationale and extra context
This originates from [this line](https://github.com/rust-lang/rust/blob/master/compiler/rustc_parse/src/parser/mod.rs#L1172) in the `bump` function:
```rust
if next.0.span.is_dummy() {
// Tweak the location for better diagnostics, but keep syntactic context intact.
let fallback_span = self.token.span; // <------ This line
next.0.span = fallback_span.with_ctxt(next.0.span.ctxt());
}
```
In the example input, the lifetime token is followed by an `<eof>` token, which has the dummy span as specified in `inlined_next` function. Thus the `bump` function sets the span of the latter to that of the former, leading to an overlap. Then, in [the construction site](https://github.com/rust-lang/rust/blob/master/compiler/rustc_parse/src/parser/pat.rs#L959) of the `UnexpectedLifetimeInPattern` diagnostic in the `parse_pat_deref` function, the suggestion span constructed from `until`ing these spans becomes an empty span. Coincidentally, the suggestion code of this diagnostic is empty (removing the lifetime), causing the suggestion to be suppressed.
```rust
self.dcx().emit_err(UnexpectedLifetimeInPattern {
span: self.prev_token.span,
symbol: lifetime.name,
suggestion: self.prev_token.span.until(self.token.span), // <------ This line
});
```
In fact, the current behavior also causes a [`debug_assert!`](https://github.com/rust-lang/rust/blob/master/compiler/rustc_errors/src/diagnostic.rs#L1006) to fail in the `span_suggestion_with_style` function:
```rust
debug_assert!(
!(sp.is_empty() && suggestion.to_string().is_empty()),
"Span must not be empty and have no suggestion"
);
```
I have 2 possible suggestions for fixing the problem:
1. Change the assignment of the span to be `self.token.span.shrink_to_hi()`, or;
2. Change the span of the returned `<eof>` token to be at the end position instead of the dummy span.
I have implemented and tested the first suggestion, and it works as expected. However, due to my lack of knowledge of the code base, I cannot figure out the other possible effects on the rest of the code, so I didn't open a pull request to fix this directly.
### Other cases
```Rust
```
### Rust Version
```Shell
rustc 1.85.0-nightly (9c707a8b7 2024-12-07)
binary: rustc
commit-hash: 9c707a8b769523bb6768bf58e74fa2c39cc24844
commit-date: 2024-12-07
host: x86_64-unknown-linux-gnu
release: 1.85.0-nightly
LLVM version: 19.1.5
```
### Anything else?
_No response_ | A-diagnostics,I-ICE,A-parser,T-compiler,C-bug,A-suggestion-diagnostics,D-invalid-suggestion,S-bug-has-test,requires-debug-assertions | low | Critical |
2,726,408,538 | opencv | cv::VideoCapture memory cannot be manually released after reading video on different systems | ### System Information
opencv 4.5.5
### Detailed description
The same program was run on ubuntu and windows, but the memory release of the program was inconsistent. my requirement is that the child thread releases the memory by itself after completing the task while the main thread continues to execute. However, I found that opencv cannot release the memory on Ubuntu, but it can on Windows. can you tell me why?
### Steps to reproduce
```cpp
#include <opencv2/opencv.hpp>
#include <thread>
#include <vector>
#include <iostream>
void video_capture_thread(int number)
{
std::cout << "start -----------" << number << std::endl;
std::string path = "E:\\workspace\\cpp\\test.mp4";
cv::VideoCapture _capture(path);
if (!_capture.isOpened())
{
std::cerr << path << std::endl;
return;
}
cv::Mat _frame;
int frame_count = 0;
while (true)
{
_capture >> _frame;
if (_frame.empty())
{
break;
}
if (frame_count % 100 == 0)
{
std::cout << "============frame_count============={}" << frame_count << std::endl;
}
frame_count += 1;
}
_frame.release();
_capture.release();
std::cout << "success -----------" << number << std::endl;
}
int main() {
std::this_thread::sleep_for(std::chrono::seconds(10));
std::vector<std::thread> _threads;
int _number = 8;
for (int i = 0; i < _number; ++i)
{
_threads.emplace_back(video_capture_thread, i);
}
for (auto& _thread : _threads)
{
_thread.detach();
}
std::this_thread::sleep_for(std::chrono::seconds(1000));
return 0;
}
````
### Issue submission checklist
- [X] I report the issue, it's not a question
- [X] I checked the problem with documentation, FAQ, open issues, forum.opencv.org, Stack Overflow, etc and have not found any solution
- [X] I updated to the latest OpenCV version and the issue is still there
- [X] There is reproducer code and related data files (videos, images, onnx, etc) | bug,category: videoio,incomplete,needs investigation | low | Major |
2,726,417,394 | pytorch | `torch.compiler.disable()` on module hooks will disable `module.compile()` | ### 🐛 Describe the bug
`torch.compiler.disable()` on module hooks will disable compile on the whole module when `module.compile()` is used (or via `torch.compile(some_function)(model, some_inputs)`)
```python
import torch
from torch import nn
d_model = 16
model = nn.Sequential(
nn.Linear(d_model, d_model),
nn.GELU(),
nn.Linear(d_model, d_model),
)
model.cuda()
@torch.compiler.disable()
def hook(module, input):
pass
model.register_forward_pre_hook(hook)
model.compile() # this doesn't work
# model.forward = torch.compile(model.forward) # this works
x = torch.randn(4, d_model).cuda()
model(x)
```
To check if the model is compiled, I use `TORCH_LOGS="output_code"`. For `model.compile()`, there is no code output. For `model.forward = torch.compile(model.forward)`, there is compiled triton code as expected.
Although `model.forward = torch.compile(model.forward)` is a valid workaround, it prevents me from doing full-compile a model in a function e.g. compute loss with signature `compute_loss(model, inputs, labels)`. Again, for this case, a workaround is to isolate the loss computation logic and compile it separately, but it gets messy. Ideally torch.compile should only ignore the hooks, not the `.forward()` logic, correctly.
### Error logs
_No response_
### Versions
torch==2.6.0.dev20241208+cu126
cc @albanD @mruberry @jbschlosser @walterddr @mikaylagawarecki @chauhang @penguinwu @voznesenskym @EikanWang @jgong5 @Guobing-Chen @XiaobingSuper @zhuhaozhe @blzheng @wenzhe-nrv @jiayisunx @chenyang78 @kadeng @amjames | module: nn,triaged,oncall: pt2,module: dynamo | low | Critical |
2,726,462,118 | godot | There was a window ordering error when native windows | ### Tested versions
4.3 Until now
### System information
Windows 10 x64
### Issue description
non-native windows order error. The display order of sub-windows(PopupMenu) of the topmost window is not handled correctly.
The error may occur in the sort calculation of `Viewport::_sub_window_update_order()`.
By the way, I found that changing the subwindow visibility triggers subwindow sorting. This means that window sorting is repeated multiple times in one frame. We should consider caching the value of `gui.sub_windows` and compare it with the current value at the end of each frame to determine whether subwindow sorting is needed.
### Steps to reproduce
- Create default project
- Add `Window` node and enable `always_on_top`
- Add any node with popup menu (e.g. TextEdit) to window node
- Run
- Open the popup menu
### Minimal reproduction project (MRP)
[window_order_mrp.zip](https://github.com/user-attachments/files/18062504/window_order_mrp.zip)
| bug,needs testing,topic:gui | low | Critical |
2,726,487,241 | kubernetes | can't find way to check streams is closed | ### What happened?
https://github.com/kubernetes/kubernetes/blame/v1.31.3/staging/src/k8s.io/kubelet/pkg/cri/streaming/remotecommand/attach.go#L43
### What did you expect to happen?
can find way to check streams is closed
### How can we reproduce it (as minimally and precisely as possible)?
no method
### Anything else we need to know?
no method
### Kubernetes version
no method
### Cloud provider
null
### OS version
null
### Install tools
<details>
</details>
### Container runtime (CRI) and version (if applicable)
<details>
</details>
### Related plugins (CNI, CSI, ...) and versions (if applicable)
<details>
</details>
| kind/bug,sig/node,triage/needs-information,needs-triage | low | Major |
2,726,496,199 | godot | Using different methods to implement non-embedded child windows will trigger the always_on_top breaks non-embedded popups problem | ### Tested versions
4.3 Until now
### System information
Windows 10 x64
### Issue description
We can get non-embedded child windows in the following two ways:
- disabling embed_subwindows.
- Change `force_native` of a subwindow
When using the second method, it seems that the parent window of the subwindow is not handled correctly. This causes all pop-ups on the subwindow to use the main window as its parent window(This is a guess). This further causes the position of the pop-ups of the subwindow to be wrong, and after `always_on_top` is enabled on the subwindow, it will cause the window sorting to be wrong and cover all the pop-ups of the subwindow.
### Steps to reproduce
- Create default project
- Add `Window` node, enable `always_on_top` and `force_native`, disable `visible`
- Add any node with popup menu (e.g. TextEdit) to window node
- Run
- Make the window node visible
- Open the popup menu on window node
*The PopopMenu is not only covered but also displayed in the wrong position.*
### Minimal reproduction project (MRP)
[issue_100192_mrp.zip](https://github.com/user-attachments/files/18059912/issue_100192_mrp.zip)
| bug,topic:gui | low | Minor |
2,726,526,005 | kubernetes | Fine-Grained Scaling Control for DaemonSet/Deployment | ### What would you like to be added?
DaemonSet/Deployment supports controlling strategy for scaling pods similar to RollingUpdate.
### Why is this needed?
Currently, DaemonSets and Deployments (via ReplicaSets) offer some level of strategy control for rolling updates, but provide almost nothing for large-range scaling, apart from limiting the request pressure for the API server. As a result, a large number of creating pods will compete simultaneously for the same resources, leading to repeated failures and retries, and very slowly scaling.
In terms of pod scaling for DaemonSets/Deployments, the current solutions are based on various Autoscalers, but using Autoscalers to achieve specific-number scaling goals might also be inconsistent and awkward:
• For Deployments, scaling relies on the Horizontal Pod Autoscaler (HPA).
• For DaemonSets, scaling, that is node scaling,ctypically using the Cluster Autoscaler with Node Pools/Groups and HorizontalNodeScalingPolicy.
However, Node Pools/Groups depend on cloud provider supporting, unusable in local self-built Kubernetes clusters where manual node scaling via adding/removing labels/taints is common.
Additionally, the rolling update strategy for DaemonSets/Deployments is not flexible. It only supports a single fixed updating rate, whereas production environments often require a phased updating strategy of starting slowly and accelerating later.
Support Request also: [English Version](https://discuss.kubernetes.io/t/feature-request-fine-grained-scaling-control-for-daemonsets-deployments/30759?u=unilinu) [中文版本](https://discuss.kubernetes.io/t/daemonset-deployment/30760)
Closes [community kubernetes/kubernetes#129601](https://github.com/kubernetes/kubernetes/issues/129601)
| sig/scalability,sig/autoscaling,kind/feature,needs-triage | low | Critical |
2,726,545,757 | ollama | Llama 3.3 still has metadata from Llama 3.1 | ### What is the issue?
Hello,
The model of LLAMA3.3 still has metadata from LLAMA3.1
btw. What type of Quantization are you using?
Thank you
### OS
Linux
### GPU
_No response_
### CPU
_No response_
### Ollama version
0.5.1 | bug | low | Minor |
2,726,549,791 | ant-design | Tag margin inline no needed | ### Reproduction link
[](https://codesandbox.io/p/sandbox/ps66pv)
### Steps to reproduce
Create a list with a tag and a list item with simple text
### What is expected?
Tag should NOT have the margin if there's only 1 Tag
### What is actually happening?
Tag has margin
| Environment | Info |
| --- | --- |
| antd | 5.22.3 |
| React | 18.3 |
| System | macos |
| Browser | chrome |
<!-- generated by ant-design-issue-helper. DO NOT REMOVE -->
| Inactive | low | Minor |
2,726,551,905 | react | Bug: useOptimistic | React version:19.0.0
[I got example from react.dev](https://react.dev/reference/react/useOptimistic) slightly modified it.
Now `key` attribute derive value from data (message)
```
<div key={message.id}>
{message.text}
{!!message.sending && <small> (Sending...)</small>}
</div>
```
## Steps To Reproduce
1.[Open link](https://codesandbox.io/p/sandbox/react-dev-forked-5hddwt)
2.Send new message
3.Open console
## The current behavior
On the image below we can see duplicating list of messages from [I got example from react.dev](https://react.dev/reference/react/useOptimistic).
There was no error in [I got example from react.dev](https://react.dev/reference/react/useOptimistic) because `key` gets values from `index`, `index` is always unique.
<div key={index}>
{message.text}
{!!message.sending && <small> (Sending...)</small>}
</div>
Code that is slightly modified by me print out following (from console):
> Encountered two children with the same key, `8908d3a9-13b7-4576-bf85-e850f7ab2c1c`. Keys should be unique so that components maintain their identity across updates. Non-unique keys may cause children to be duplicated and/or omitted — the behavior is unsupported and could change in a future version
I don't know the reason of that behaviour but I see that `updateFn` in `useOptimistic` is called with `new message` twice:
1. First time after `addOptimisticMessage` is called,
2. Second time while `Thread` component is re-rendered.
| Status: Unconfirmed | low | Critical |
2,726,579,367 | svelte | `bind:` in a loop breaks the reference | ### Describe the bug
I posted this issue already on sveltekit-superforms but it seems to be a Svelte 5 issue. https://github.com/ciscoheat/sveltekit-superforms/issues/509
Apparently in Svelte 5 there is a reactivity problem when you use `bind:` with a list item in a loop it breaks reference.
- What I'm wondering about is that while the $form store is updating correctly and reactively the form param inside the onUpdate callback is not up to date
- This issue seems to only occur in Svelte 5, that's why it seems to me like a bug
``` svelte
<form use:enhance method="post">
{#each $form.priceRules ?? [] as priceRule}
<!-- this doesn't work (only when updating another form field afterwards: -->
<PriceSelection bind:selectedItem={priceRule.priceCategory} />
<!-- this works: -->
<!-- <PriceSelection bind:selectedItem={$form.priceRules[0].priceCategory} /> -->
{/each}
<button type="submit">submit</button>
</form>
```
### Reproduction
https://stackblitz.com/edit/sveltejs-kit-template-default-svjrzfhz?file=src%2Froutes%2F%2Bpage.svelte
### Logs
_No response_
### System Info
```shell
System:
OS: Linux 5.0 undefined
CPU: (8) x64 Intel(R) Core(TM) i9-9880H CPU @ 2.30GHz
Memory: 0 Bytes / 0 Bytes
Shell: 1.0 - /bin/jsh
Binaries:
Node: 18.20.3 - /usr/local/bin/node
Yarn: 1.22.19 - /usr/local/bin/yarn
npm: 10.2.3 - /usr/local/bin/npm
pnpm: 8.15.6 - /usr/local/bin/pnpm
npmPackages:
svelte: ^5.0.0 => 5.9.0
```
### Severity
blocking an upgrade | bug | low | Critical |
2,726,586,254 | tauri | [bug] Fresh Tauri 2 project crashes on `npm run tauri dev` (Intel macOS) | ### Describe the bug
A fresh Tauri project created with `npm create tauri-app@latest` crashes immediately when running `npm run tauri dev` on macOS. The crash occurs with a segmentation fault in the ImageIO/AppKit layer.
### Reproduction
1. Create a new project:
```bash
npm create tauri-app@latest
```
2. Navigate to project directory and run:
```bash
npm run tauri dev
```
3. Application crashes immediately with a segmentation fault
### Expected behavior
- The development server should start successfully
- The application window should open without crashing
### Full `tauri info` output
```text
> [email protected] tauri
> tauri info
[✔] Environment
- OS: Mac OS 14.5.0 x86_64 (X64)
✔ Xcode Command Line Tools: installed
✔ rustc: 1.82.0 (f6e511eec 2024-10-15)
✔ cargo: 1.82.0 (8f40fc59f 2024-08-21)
✔ rustup: 1.27.1 (54dd3d00f 2024-04-24)
✔ Rust toolchain: stable-x86_64-apple-darwin (default)
- node: 20.12.2
- npm: 10.9.2
[-] Packages
- tauri 🦀: 2.1.1
- tauri-build 🦀: 2.0.3
- wry 🦀: 0.47.2
- tao 🦀: 0.30.8
- tauri-cli 🦀: 2.1.0
- @tauri-apps/api : 2.1.1
- @tauri-apps/cli : 2.1.0
[-] Plugins
- tauri-plugin-shell 🦀: 2.0.2
- @tauri-apps/plugin-shell : 2.0.1
[-] App
- build-type: bundle
- CSP: unset
- frontendDist: ../dist
- devUrl: http://localhost:1420/
- framework: Vue.js
- bundler: Vite
```
### Stack trace
```text
Thread 0 Crashed:: main Dispatch queue: com.apple.main-thread
0 ??? 0xbad4007 ???
1 ImageIO PNGReadPlugin::InitializePluginData(IIOImageReadSession, IIODictionary, IIODictionary, CGImageMetadata, CGColorSpace, ReadPluginData&, PNGPluginData&, _CFDictionary) + 883
2 ImageIO PNGReadPlugin::initialize(IIODictionary) + 62
3 ImageIO IIOReadPlugin::callInitialize() + 550
4 ImageIO IIO_Reader::initImageAtOffset(CGImagePlugin, unsigned long, unsigned long, unsigned long) + 84
5 ImageIO IIOImageSource::makeImagePlus(unsigned long, IIODictionary) + 709
6 ImageIO IIOImageSource::getPropertiesAtIndexInternal(unsigned long, IIODictionary) + 49
7 ImageIO IIOImageSource::copyPropertiesAtIndex(unsigned long, IIODictionary) + 16
8 ImageIO CGImageSourceCopyPropertiesAtIndex + 332
9 AppKit ImageSourceOptionsForCGImageSource_index_ + 53
10 AppKit +[NSBitmapImageRep imagesWithData:hfsFileType:extension:zone:expandImageContentNow:includeAllReps:] + 421
11 AppKit +[NSBitmapImageRep imageRepsWithData:] + 69
12 AppKit -[NSImage initWithData:] + 93
13 base $LT$$LP$A$C$$RP$$u20$as$u20$objc2..encode..EncodeArguments$GT$::invoke::h46bab79a9d0f612e + 67
14 base objc2::runtime::message_receiver::msg_send_primitive::send::h1653ce0c372d0797 + 55
15 base tauri::app::on_event_loop_event::hedde69c4bf060b8e + 1952
16 base tauri::app::App$LT$R$GT$::run::$u7b$$u7b$closure$u7d$$u7d$::h32b7f4ce21041e1d + 858
17 base tauri_runtime_wry::handle_event_loop::hc02437d7aa3fc6c5 + 1238
18 base base::main::hf49a2e47de30fc77 + 9 (main.rs:5)
```
### Additional context
[CrashLog.txt](https://github.com/user-attachments/files/18059728/CrashLog.txt)
| type: bug,platform: macOS,status: needs triage | low | Critical |
2,726,633,957 | deno | bug: `process.nextTick` changes the order of microtasks based on where it is executed | Deno changes the order of microtasks depending on whether it runs in a REPL or in a file. I don't think this should ever be the case. Look:
```sh
$ # Create repro file
$ echo -e 'Promise.resolve().then(() => console.log("then"))\nprocess.nextTick(() => console.log("nextTick"))' > /tmp/file.js
# Run with Node and Deno
$ node /tmp/file.js
nextTick
then
$ deno /tmp/file.js
then
nextTick
# Do the same thing in a REPL and with eval
$ deno
Deno 2.1.1
exit using ctrl+d, ctrl+c, or close()
REPL is running with all permissions allowed.
To specify permissions, run `deno repl` with allow flags.
> import '/tmp/file.js'
then
nextTick
[Module: null prototype] { }
> function repro() {
Promise.resolve().then(() => console.log("then"))
process.nextTick(() => console.log("nextTick"))
}
undefined
> repro()
nextTick
then
undefined
> eval(Deno.readTextFileSync('/tmp/file.js'))
nextTick
then
undefined
> await eval(await Deno.readTextFile('/tmp/file.js'))
then
nextTick
undefined
>
$
```
_Originally posted by @KnorpelSenf in https://github.com/denoland/deno/issues/22458#issuecomment-2500745522_
| needs investigation,node compat | low | Critical |
2,726,672,275 | storybook | [Bug]: can't use stories in test file | ### Describe the bug
flow the doc: https://github.com/storybookjs/storybook/blob/next/code/addons/themes/docs/getting-started/material-ui.md
my main.js:
```
addons: [
'@storybook/addon-essentials',
'@storybook/addon-themes',
'@chromatic-com/storybook',
'@storybook/addon-interactions',
'storybook-addon-pseudo-states', // force component state, eg: `:hover`,`:focus`, not support for nested elements
],
```
and my preview.js:
```
const preview: Preview = {
decorators: [
withThemeFromJSXProvider({
themes: {
light: theme,
dark: theme,
},
defaultTheme: 'light',
Provider: ThemeProvider,
GlobalStyles: CssBaseline,
}),
],
```
only use in test file , will show error:
```
FAIL tests/unit/components/basic/Button.test.tsx > Button Component > does not call onClick when loading
TypeError: Cannot read properties of undefined (reading 'palette')
❯ src/components/basic/inputs/button/index.tsx:88:36
86| },
87| ...(['highlight', 'success'].includes(variant) && {
88| '--variant-textBg': theme.vars.palette.sys.neutral,
| ^
89| '--variant-textColor': theme.vars.palette.sys['on-neutral'],
90| [`& > .${svgIconClasses.root}`]: {
```
my test file:
```ts
import { composeStories, composeStory } from '@storybook/react';
import * as stories from '@/stories/basic/inputs/Button.stories';
import userEvent from '@testing-library/user-event';
const { Loading } = composeStories(stories);
describe('Button Component', () => {
const mockOnClick = vi.fn();
beforeEach(() => {
mockOnClick.mockReset();
});
it('does not call onClick when loading', async () => {
await Loading.run();
userEvent.click(screen.getByRole('button'));
expect(mockOnClick).not.toHaveBeenCalled();
});
```
when i change to:
```ts
it('does not call onClick when loading', async () => {
// await Loading.run({
// args: {
// onClick: mockOnClick,
// },
// });
render(
<Button onClick={mockOnClick} disabled={true}>
Loading Button
</Button>,
);
userEvent.click(screen.getByRole('button'));
expect(mockOnClick).not.toHaveBeenCalled();
});
```
it's worked
### Reproduction link
sorry, i don't have
### Reproduction steps
_No response_
### System
```bash
Storybook Environment Info:
System:
OS: macOS 14.6.1
CPU: (8) x64 Intel(R) Core(TM) i5-1038NG7 CPU @ 2.00GHz
Shell: 5.9 - /bin/zsh
Binaries:
Node: 22.10.0 - /usr/local/opt/node@22/bin/node
Yarn: 1.22.22 - /usr/local/bin/yarn
npm: 10.9.0 - /usr/local/opt/node@22/bin/npm <----- active
pnpm: 9.13.2 - /usr/local/bin/pnpm
npmPackages:
@storybook/addon-essentials: ^8.4.7 => 8.4.7
@storybook/addon-interactions: ^8.4.7 => 8.4.7
@storybook/addon-onboarding: ^8.4.7 => 8.4.7
@storybook/addon-themes: ^8.4.7 => 8.4.7
@storybook/blocks: ^8.4.7 => 8.4.7
@storybook/nextjs: ^8.4.7 => 8.4.7
@storybook/react: ^8.4.7 => 8.4.7
@storybook/test: ^8.4.7 => 8.4.7
storybook: ^8.4.7 => 8.4.7
storybook-addon-pseudo-states: ^4.0.2 => 4.0.2
others: react: v19 , next: 15.0.4
```
### Additional context
_No response_ | bug,portable stories | low | Critical |
2,726,697,318 | three.js | Adding a position options for the PMREM fromScene generation | ### Description
Currently, calling a PMREM Generation is calling a cubecamera that is always default positionned at 0, 0, 0
For a few versions now, I'm hacking my way to get to generate a PMREM but from an arbitrary cubecamera position by passing a position to pmrem.fromScene, this would be useful
### Solution
Passing a position as arg to fromScene
### Alternatives
Or maybe passing a callback to be called before each render that passes the camera ?
in that case we'd be able to do anything before render of each pmrem face
### Additional context
_No response_ | Enhancement | low | Major |
2,726,715,848 | transformers | Calling Trainer.create_model_card() with an empty dataset list causes an IndexError | ### System Info
- `transformers` version: 4.46.3
- Platform: Linux-5.15.0-125-generic-x86_64-with-glibc2.35
- Python version: 3.11.10
- Huggingface_hub version: 0.26.3
- Safetensors version: 0.4.5
- Accelerate version: 1.1.0
- Accelerate config: not found
- PyTorch version (GPU?): 2.5.1 (True)
- Tensorflow version (GPU?): not installed (NA)
- Flax version (CPU?/GPU?/TPU?): not installed (NA)
- Jax version: not installed
- JaxLib version: not installed
- Using distributed or parallel set-up in script?: <fill in>
- Using GPU in script?: <fill in>
- GPU type: NVIDIA H100 80GB HBM3
### Who can help?
@muellerzr @SunMarc
### Information
- [ ] The official example scripts
- [ ] My own modified scripts
### Tasks
- [ ] An officially supported task in the `examples` folder (such as GLUE/SQuAD, ...)
- [ ] My own task or dataset (give details below)
### Reproduction
Call `trainer.create_model_card(..., datasets=[])`.
The checks at https://github.com/huggingface/transformers/blob/de8a0b7547451f8f7ef2c0ac1f338ba77c614cec/src/transformers/modelcard.py#L492-L502 do not cover this case, we end up in the `else` branch and access `datasets[-1]`.
### Expected behavior
No exception should be raised, no dataset info should be included in the model card. | bug | low | Critical |
2,726,857,680 | godot | Multiplayer sychronizer quietly fails after a seperate node despawns | ### Tested versions
- reproducible in v4.3.stable.mono.official [77dcf97d8]
- untested otherwise
### System information
Godot v4.3.stable.mono - Windows 10.0.22631 - Vulkan (Forward+) - dedicated NVIDIA GeForce RTX 4070 Ti (NVIDIA; 32.0.15.6614) - 13th Gen Intel(R) Core(TM) i9-13900K (32 Threads)
### Issue description
I have discovered a senario where some Multiplayer Synchronizer nodes will quietly fail and stop recieving updates after a seperate synchronizer has been despawned. The expectation is that spawning or despawning multiplayer synchronizers should never effect others. Steps the reproduce and seeing the MRP paints a more complete picture as to what the bug entails. Attached is a gif demonstrating this 
I will also describe my use case for this feature.
I'm working on a game where each peer has a player node spawned for them. The player has a weapon which spawns bullets.
I want the bullets to be spawned and owned by the player that created them so that there is no lag between firing your gun and seeing the effect.
The bullet needs a synchromized to sync position.
Because of the bug, when the bullets despawn, the host player synchronizer breaks and the host appears to freeze for clients.
### Steps to reproduce
This bug will arise with the following steps
-> Host creates the server
-> Host spawns n objects where n >= 2 which have multiplayer synchronizers
-> Client joins the server
-> Client is given authority over a multiplayer spawner
-> Client spawns n object which have multiplayer synchronizers
-> Client despawns the n previous objects
-> You will now see the n-1 object which the host spawns first no longer is successfully synchronizing to the client
If another client joins at this point they will still recieve updates until they also delete n objects
If the host spawns the objects after the clients have already joined the issue won't arise
### Minimal reproduction project (MRP)
My apologies that this requires a .NET setup, due to being unfamiliar with GDscript I'm not able to recreate the issue using it in a timely manner.
To see this issue demonstrated in the MRP, first enable multiple run instances.
To do this go to Debug->Customize Run Instances... and then check Enable Multiple isntances and increase this to 2 (or more).
Running the project (initial scene should be app root) will start two instances of the game.
In one window, press Start Host and then press the + button twice to spawn two Dynamic Elements (nodes the briefly demonstrate a value that is continuously changing and being synchronized)
In the other window press Start Client. This will automatically use your local ip to join the server and you will see the two Dynamic Elements spawn.
Use the + button (its critically not to mix these) to spawn two more Dynamic Elements.
Now in the client, use the cross buttons to delete the elements you spawned.
You should see the first dynamic element has frozen and is no longer updating.
I will also briefly go over the project structure.
The AppRoot node is the main scene which serves to start the network session.
When the session is started by the host, they spawn an Experiment node in the ExperimentSpawner.
The purpose of this node is to provide a top most node for functionality related to this test.
Experiement has a control node and a PeerSpawner node.
The control node contains UI for observing values being changed by synchronizers and to spawn and despawn these objects.
When a peer joins and node is spawned to represent them and the authority of this node is assigned to the peer which joined.
The peer node contains a DynamicElementSpawner which is used to spawn and despawn dyanmic element nodes.
Dynamic element nodes are set up so that only their own runs their process, which changes a value between -1 and 1.
When a dynamic element is spawned, on each peer that it is spawned on it adds a dynamic value display to a container which is a child of the experiement's control node.
this dynamic value display is bound to it to show the value updating, as well as a label clarifying who owns the underlying dynamic element.
On the peer that owns the element, a button will be enabled which frees the dynamic element (this relies on the spawner to automatically despawn it), which in turn frees the display.
[MRP.zip](https://github.com/user-attachments/files/18061130/MRP.zip)
| bug,topic:multiplayer | low | Critical |
2,726,869,947 | PowerToys | Shortcut Guide Bug | ### Microsoft PowerToys version
v0.86.0
### Installation method
GitHub
### Running as admin
No
### Area(s) with issue?
Shortcut Guide
### Steps to reproduce
1. Have **Activation method** set to **Hold down Windows key**
2. Open the **start menu**
3. Hold down the Windows key for time duration before showing
### ✔️ Expected Behavior
Shortcut Guide is closing
### ❌ Actual Behavior
Shortcut Guide is not closing
### Other Software
_No response_ | Issue-Bug,Product-Shortcut Guide,Needs-Triage | low | Critical |
2,726,908,526 | vscode | SCM Graph - better handle long branch names in the hover | 
| bug,ux,scm | low | Minor |
2,726,964,990 | angular | Enhancements to forms for future signal forms | ### Which @angular/* package(s) are relevant/related to the feature request?
forms
### Description
Template and reactive forms in Angular are great, yet using them through the years has revealed a few areas of improvement. This issue aims to provide feedback on some problems, hoping they can be addressed in the future re-vamped signal forms. I'd be happy to elaborate and provide further examples of any of the points below.
## Problem 1: Control Value Accessor is not strongly typed
CVA provide a nice separation of concerns and layer of abstraction between the form control and the DOM.
Nevertheless, form controls, either the reactive or template flavors, access the CVA through DI. This means that the binding is not strictly typed. A CVA can be designed to handle numbers, yet be used in a model that has the string value.
Additionally, the CVA interface builds on top of `any`, which offers a bad DX.
**Example:**
```ts
class NumberValueAccessor implements ControlValueAccessor {
writeValue(value: number): void { /* ... */ }
registerOnChange(fn: (value: number) => void): void { /* ... */ }
// ...
}
// Usage in a form control that expects a string
this.form = new FormGroup({
age: new FormControl('25') // This should be a number
});
```
## Problem 2: Control Value Accessor can cause issues with the timing of its binding
The timing when `writeValue` and `registerOnChange` are called is somehow part of its public API, following Hyrum's Law. It can cause some issues, for example, if the CVA supports multiple types and does a parsing on `writeValue`. The first time it get's called, `registerOnChange` hasn't been called yet, so the parsed value can't be immediately propagated.
Additionally, this API feels verbose and not declarative when compared with more recent framework features.
**Example:**
```ts
class MultiTypeValueAccessor implements ControlValueAccessor {
writeValue(value: string | number): void {
const parsedValue = typeof value === 'string' ? parseInt(value, 10) : value;
// registerOnChange hasn't been called yet, so parsedValue can't be propagated
}
registerOnChange(fn: (value: number) => void): void { /* ... */ }
// ...
}
```
## Problem 3: Strict typing of form controls and groups
When typed forms were introduced, they had to be retro-compatible with existing implementations, which we appreciated. Nevertheless, it is painful to work with the `undefined` type of controls just because they can be disabled. I'd argue that this decision has caused typing issues in many cases, since the form value when is valid still has `undefined` all around. True, the raw value can be used, but feels unnecessary.
Additionally, there is a common case where a field uses the required validator, but it's underlying type also supports `null`. If the form is valid, the control would have a non-null value, yet the type still includes `null`.
**Example:**
```ts
const form = new FormGroup({
name: new FormControl<string | null>(null, Validators.required)
});
// When the form is valid, name should not be null, but the type still includes null
const name: string | null = form.get('name')?.value;
```
Finally, there are some controls that do parsing, such as supporting both `Date | string` as inputs, but always exposing a `Date`. Again, it can't be expressed with current typing, there is no transformation function or type narrowing.
**Example:**
```ts
const dateControl = new FormControl<Date | string>('2025-01-01');
// The control should always expose a Date, but it can accept a string
const date: Date = dateControl.value; // This can't be done
```
## Problem 4: Error fields does not have strict typing
Regardless of the return type of a validator, the `errors` property of controls is typed as `any`. For example, the max length validator exposes an error value similar to `{requiredLength: 5, actualLength: 7}`, but it can be consumed with type safety in the template.
**Example:**
```ts
const control = new FormControl('test', Validators.maxLength(5));
const errors = control.errors; // Typed as any, not safe to access properties
if (errors?.maxlength) {
console.log(errors.maxlength.requiredLength); // No type safety
}
```
## Problem 5: Accessibility with reactive form validators
Reactive form validators provide a great tooling to build dynamic validators. However, they don't add HTML attributes such as `required` or `maxlength`, lacking a11n support. Only template driven validators do this. For those who embrace the virtues of reactive forms, validators have to be duplicated in the control and template to ensure good HTML attributes.
**Example:**
```ts
const control = new FormControl('', [Validators.required, Validators.maxLength(5)]);
// HTML does not reflect required or maxlength attributes
```
## Problem 6: Async validators are still pending when the form is submitted
One of the most common scenarios when using forms is acting when they are submitted. Currently, when the submit event is fired, a form with async validators is in pending state. It is not trivial to wait until they complete so as to decide whether the form action should be executed.
**Example:**
```ts
this.formGroup = new FormGroup({
asyncControl: new FormControl('', null, asyncValidator)
});
onSubmit() {
if (this.formGroup.pending) {
// Form is still pending, can't proceed with submission
console.log('Form is pending, please wait...');
} else if (this.formGroup.valid) {
// Form is valid, proceed with submission
console.log('Form submitted successfully:', this.formGroup.value);
} else {
// Form is invalid, handle errors
console.log('Form is invalid:', this.formGroup.errors);
}
}
```
## Problem 7: Complex typing structures
Typed form's typing is complex. For example, a form group can't be typed with just the type of its value, it needs to know whether each field is a control, group, or array.
### Proposed solution
## Proposed solution 1: Bind CVA through inputs to ensure strict typing
Ideally, a CVA could expose a `model` consumed through two-way data binding rather than through DI. Since inputs are the only binding that enforces type safety, it would ensure that the CVA and its model value have the same type.
**Proposal:**
```ts
export interface ControlValueAccessor<T> {
readonly model: `ModelSignal<T>`;
}
```
## Proposed solution 2: Use `model` for binding of the CVA
Having two methods for the data binding of a CVA could be better replaced with the new `model` that solves this specific problem and avoids timing issues.
## Proposed solution 3: Support type narrowing
Reconsider the decision that disabled controls should have `undefined` value and avoid the need of exposing `value` vs `rawValue`. If a control was undefined, it would be an application decision whether the value should be `undefined`. Another alternative to solve the typing issue would be only support disable on controls that include the type `undefined`.
If type narrowing could be applied to form controls, we could benefit, for example, from:
* Required validator would ensure that, if successful, the value is not null and reflect that in the type.
* A control that does parsing would support multiple values when "setting", but a narrowed type when "getting".
**Proposal:**
```ts
export function RequiredValidator<T>(control: AbstractControl<T | undefined>): control is AbstractControl<T>;
```
## Proposed solution 4: Support generic type for errors
If a control is defined with validators, make them part of the generic type so that `errors` has a strict type.
## Proposed solution 5: Enhance API of programmatic validators
A programmatic validator would have an API similar to `host` so that it can modify the HTML and add a11y attributes as needed.
## Proposed solution 6: Provide `success` and `error` events on forms
Rather than relying on submit, provide `success` (or `validSubmit`) or `error` (or `invalidSubmit`) events that get triggered when, after the form is submitted, async validators are resolved, and the state is no longer pending, depending on whether it is `valid` or `invalid`.
The success event could also expose a narrowed type with the final types when validators are successful, following up on proposed solution 3.
## Proposed solution 7: Simplify typing for form groups/arrays
A form group/array would only have child abstract controls, regardless of their specific type. This way they can be typed with the value's type. If it had a child object-shaped field, it could later be bound to a control with an object value, or a child group dynamically.
### Alternatives considered
Creating my own forms library, but I really like Angular's 😉 | area: forms | low | Critical |
2,727,032,276 | next.js | API Routes Responses Not Being Gzipped in Next.js App Router #73693 | ### Link to the code that reproduces this issue
https://github.com/huseyinbuyukdere/temp-issue-gzip-next
### To Reproduce
**Start the application in development mode using next dev.**
**Create an API route under the App Router, e.g., /app/api/example/route.js**
Example Api Route
```javascript
export async function GET() {
const data = Array(5000).fill({ id: 1, name: "example" });
return NextResponse.json(data, {
headers: {
"Content-Type": "application/json",
},
});
}
```
**Send a GET request to the API route with curl**
curl -H "Accept-Encoding: gzip" http://localhost:3000/api/example
**Observe the response headers and payload.**
### Current vs. Expected behavior
### Current vs. Expected behavior
```yaml
**Current**
HTTP/1.1 200 OK
Content-Type: application/json
Content-Length: 12345
Date: Mon, 11 Dec 2024 12:34:56 GMT
**Expected**: The response should be gzipped if the **Accept-Encoding: gzip** header is present.
HTTP/1.1 200 OK
Content-Type: application/json
Content-Encoding: gzip
Content-Length: 4567
Date: Mon, 11 Dec 2024 12:34:56 GMT
### Provide environment information
```bash
Operating System:
Platform: darwin
Arch: arm64
Version: Darwin Kernelroot:t-11215.1.10~2/RELEASE_ARM64_T6000
Available memory (MB): 32768
Available CPU cores: 10
Binaries:
Node: 20.17.0
npm: 10.8.2
Yarn: N/A
pnpm: N/A
Relevant Packages:
next: 15.0.4 // Latest available version is detected (15.0.4).
eslint-config-next: 15.0.4
react: 19.0.0
react-dom: 19.0.0
typescript: 5.7.2
Next.js Config:
output: N/A
```
### Which area(s) are affected? (Select all that apply)
Middleware, Performance, Runtime
### Which stage(s) are affected? (Select all that apply)
Other (Deployed)
### Additional context
- This issue is reproducible in both development (next dev) and production (next start) modes.
- Tested with Next.js versions 14.1.0 and 15.0.4.
- Static assets are gzipped correctly by Next.js, but API route responses are not.
- There is no middleware or CDN in use during these tests. I expected gzip compression to be handled automatically by the framework. | bug,Middleware,Performance,Runtime | low | Major |
2,727,037,943 | vscode | VSCode does not open file paths while in a workspace | <!-- ⚠️⚠️ 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: 1.96.0-insider (Universal) Commit: b18e7a700033b39ed2c3975759b6327c8205f958
- OS Version: Darwin arm64 24.1.0
Steps to Reproduce:
1. Open a workspace that has a folder name different from its path:
```json
{
"folders": [
{
"name": "Source",
"path": "code",
}
]
}
```
2. Search for a file (with `CTRL`+`P`) under the `code` directory using its full path (such as `code/main.py`)
Expected outcome:
The search menu shows the requested file
Actual outcome:
The search menu does not list the file
Note that searching just for `main.py` will still work since it categorizes it as `Source/main.py` | bug,quick-open | low | Critical |
2,727,038,591 | vscode | Deeplink to clone a repository using VS Code Desktop | <!-- ⚠️⚠️ 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. -->
Hi,
I would like to propose a feature added to the `vscode.dev` that would enable a user to create a link that will clone&open a repo in the local VS Code instance.
VS Code Desktop has a registered URL schema `vscode://` that can be used as such
`vscode://vscode.dev/clone?url=https://github.com/<org>/<repo>&ref=<ref>`
Pasting a link like this in a browser will open a local VS Code installation and clone the repo in a temp location, which offers a great UX for users who consume some repositories without having an intention to develop against them. Hence, they do not care where the project is cloned and don't mind it being cloned in a temp work dir.
The challenge is that this non https url can not be used in readmes, we need a service that would redirect an HTTPS URL to this `vscode://` URL.
This would allow us to have a nice button in the project readme that would offer a 1-click experience for the users:
[![Clone][clone-svg]][clone-url]
[clone-svg]: https://gitlab.com/rdodin/pics/-/wikis/uploads/f836c8b46f0789b6953961bf4ab7a05d/clone-with-vscode.svg
[clone-url]: https://vscode.dev/clone?url=https://github.com/srl-labs/srl-acl-lab&ref=main
It seems that `vscode.dev` is a perfect service to offer such redirection and it is most likely the dev effort to have this redirect is not huge.
Thanks for considering this! | under-discussion,vscode.dev | low | Minor |
2,727,057,591 | PowerToys | Can't install via MS Store due to lack of integrated keyboard | ### Microsoft PowerToys version
0.86.0
### Installation method
Microsoft Store, WinGet
### Running as admin
No
### Area(s) with issue?
Installer
### Steps to reproduce
I am using a Windows 11 24H2 Enterprise desktop with Synergy, though I do keep a USB keyboard and mouse plugged into the system as a backup. I am trying to upgrade from PowerToys 0.84.1 to 0.86.0.
I originally installed PowerToys through the Microsoft Store app, though I typically use winget to handle updates since it handles Microsoft Store updates, WinGet updates, and can detect some apps that I installed via standalone installers to update them as well.
### ✔️ Expected Behavior
When I do `winget upgrade XP89DCGQ3K6VLD` or `winget upgrade --all`, WinGet should upgrade the PowerToys app. When I go to the PowerToys page in the Microsoft Store app, I should be able to hit update to upgrade the package.
### ❌ Actual Behavior
When I do `winget upgrade XP89DCGQ3K6VLD` I get the following output:
```
No applicable upgrade found.
A newer package version is available in a configured source, but it does not apply to your system or requirements.
```
When I go to install via the Microsoft Store, it shows that my computer doesn't meet the requirements due to not having an integrated keyboard. See attached: 
I was able to work around this issue by doing `winget remove XP89DCGQ3K6VLD && winget install Microsoft.PowerToys -s winget`
### Other Software
Microsoft Store 22410.1401.4.0
Windows Package Manager v1.9.25200
Package: Microsoft.DesktopAppInstaller v1.24.25200.0 | Issue-Bug,Needs-Triage,Needs-Team-Response | low | Major |
2,727,059,888 | deno | Deno cli could not initialize cache database |
Hi,
I got this error while running Deno cli.
```shell
Could not initialize cache database '{homePath}/.cache/deno/v8_code_cache_v2', deleting and retrying... (database is locked
Caused by:
Error code 261: Another process is recovering a WAL mode database file)
Failed to open cache file '{homePath}/.cache/deno/v8_code_cache_v2', performance may be degraded.
```
I see this issue is different from the one here: https://github.com/denoland/deno/issues/20202
Just so you know, I am using Deno version 2.0.2 on an LXC container running on Debian 5.10.103-1 x86_64 x86_64 x86_64 GNU/Linux.
Regards,
AH | bug,cli | low | Critical |
2,727,064,133 | transformers | DynamicCache does not support variable lengths, except for FA2 | ### System Info
- `transformers` version: 4.47.0
- Using GPU in script?: yes
- GPU type: NVIDIA A100-SXM4-80GB
### Who can help?
@ArthurZucker
### Information
- [ ] The official example scripts
- [X] My own modified scripts
### Tasks
- [ ] An officially supported task in the `examples` folder (such as GLUE/SQuAD, ...)
- [x] My own task or dataset (give details below)
### Reproduction
The following code will reproduce the issue:
```python
import torch
from transformers import AutoModelForCausalLM
from transformers.cache_utils import DynamicCache
device = "cuda:0"
ckpt = "meta-llama/Meta-Llama-3.1-8B-Instruct"
attn_implementation = "flash_attention_2"
cache = DynamicCache()
model = AutoModelForCausalLM.from_pretrained(ckpt, torch_dtype="auto", attn_implementation=attn_implementation).to(
device
)
# Run first forward pass
inputs = model.dummy_inputs["input_ids"].to(device)
with torch.no_grad():
model(inputs, past_key_values=cache)
print("First forward pass")
print(f"Layer 0: {cache.key_cache[0].shape}")
print(f"Layer 1: {cache.key_cache[1].shape}")
# Update the cache size for the first layer
print("Removing 2 KV pairs for the first layer")
cache.key_cache[0] = cache.key_cache[0][:, :, :-2, :]
cache.value_cache[0] = cache.value_cache[0][:, :, :-2, :]
with torch.no_grad():
model(inputs, past_key_values=cache)
print("Second forward pass")
print(f"Layer 0: {cache.key_cache[0].shape}")
print(f"Layer 1: {cache.key_cache[1].shape}")
```
### Expected behavior
In the [kvpress](https://github.com/NVIDIA/kvpress) repository, we implement various KV cache compression methods. For some of these methods, the KV cache compression is not the same from one layer to the other (see for instance https://github.com/NVIDIA/kvpress/pull/28). We noticed it's not an issue when using `attn_implementation="flash_attention_2"` but raises an error for `attn_implementation="sdpa"` or `attn_implementation="eager"`.
Here is the error from the script above:
```bash
--> [336](.../transformers/models/llama/modeling_llama.py:336) attn_weights = attn_weights + causal_mask
[338](.../transformers/models/llama/modeling_llama.py:338) # upcast attention to fp32
[339](.../transformers/models/llama/modeling_llama.py:339) attn_weights = nn.functional.softmax(attn_weights, dim=-1, dtype=torch.float32).to(query_states.dtype)
RuntimeError: The size of tensor a (10) must match the size of tensor b (9) at non-singleton dimension 3
```
The issue is that the `causal_mask` is not updated per-layer for `sdpa` and `eager` while it is for flash attention. | bug,Cache | medium | Critical |
2,727,067,930 | yt-dlp | camsoda HTTP Error 403 | ### 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)
- [ ] 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
usa
### Provide a description that is worded well enough to be understood
showing this error
ERROR: [Camsoda] violeta-evanz: Unable to download webpage: HTTP Error 403: Forbidden (caused by HTTPError 403: Forbidden ); 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
### 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
ERROR: [Camsoda] violeta-evanz: Unable to download webpage: HTTP Error 403: Forbidden (caused by HTTPError 403: Forbidden ); 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
```
| incomplete,NSFW | low | Critical |
2,727,075,821 | tensorflow | Update Python in Docker images to 3.11.x and ditch `3.11.0rc1` | ### Issue type
Build/Install
### Have you reproduced the bug with TensorFlow Nightly?
Yes
### Source
binary
### TensorFlow version
2.18
### Custom code
No
### OS platform and distribution
Docker
### Mobile device
_No response_
### Python version
_No response_
### Bazel version
_No response_
### GCC/compiler version
_No response_
### CUDA/cuDNN version
_No response_
### GPU model and memory
_No response_
### Current behavior?
The Python version of the docker images is outdated and should be updated
### Standalone code to reproduce the issue
```shell
docker run -it tensorflow/tensorflow python
```
### Relevant log output
```shell
Python 3.11.0rc1 (main, Aug 12 2022, 10:02:14) [GCC 11.2.0] on linux
Type "help", "copyright", "credits" or "license" for more information.
>>>
```
| stat:awaiting tensorflower,type:bug,type:build/install,TF 2.18 | medium | Critical |
2,727,082,232 | godot | Enum does not update in resource on change it needs restart to update | ### Tested versions
Reproducible in:
4.4Dev-3
4.4Dev-4
4.4Dev-5
4.4Dev-6
### System information
Linux Manjaro, Nvidia Geforce GTX 850, CPU: intel i7
### Issue description
when in resource you place a enum as typed variable you may choose the enums that are written like:
```gdscript
enum example{
one,
two,
three,
}
```
all works well
but if you add "four" you won't see it in the resources
you need to restart the godot and wala there it is
so each time you add an enums or change names you need to restart the godot to take effect
### Steps to reproduce
1. create node with variable (array) that contains resources
2. create resource and attach it
3. add enum variable in resource
4. add enum variable
5. and try to set it in node at first step -> it's array (any one) -> it's enum variable
it's not there
6. restart godot
it's there.
### Minimal reproduction project (MRP)
N/A | bug,topic:gdscript,topic:editor | low | Minor |
2,727,134,546 | pytorch | Bugs in MemoryProfiler.timeline due to mix of Key and TensorKey types returned | ### 🐛 Describe the bug
We have a bug on Aarch64
```
"errorStackTrace" : "Traceback (most recent call last):
File \"/var/lib/jenkins/workspace/test/profiler/test_memory_profiler.py\", line 1488, in test_memory_timeline\u000a lines = [ File \"/var/lib/jenkins/workspace/test/profiler/test_memory_profiler.py\", line 1490, in <listcomp>
f\"{id_for_testing(key):>3}(v{version}) {format_size(size):>15}\"
File \"/var/lib/jenkins/workspace/test/profiler/test_memory_profiler.py\", line 1486, in id_for_testing
return id_map.setdefault(key.storage.allocation_id, len(id_map))
AttributeError: 'Key' object has no attribute 'storage'\u000a\u000aTo execute this test, run the following from the base repo dir
python test/profiler/test_memory_profiler.py TestMemoryProfilerE2E.test_memory_timeline
This message can be suppressed by setting PYTORCH_PRINT_REPRO_ON_FAILURE=0"
```
Upon investigation I can see that MemoryProfiler.timeline is returning a mixture of Key and TensorKey for the keys. ( Key does not have storage attribute! ). The typing suggest that the return type should be KeyAndID, however we are getting lots of TensorAndID, furthermore the failing test **_test_memory_timeline_** is expecting TensorAndID.
` def timeline(self) -> Tuple[Tuple[int, Action, KeyAndID, int], ...]:`
Unsure whether the correct fix is to let the test handle mixture of key types and change the typing annotations or whether we should only be returning TensorAndID from the timeline method.
Tagging authors from git blame @aaronenyeshi @ezyang
### Versions
Collecting environment information...
PyTorch version: 2.6.0a0+git35c676d
Is debug build: True
CUDA used to build PyTorch: None
ROCM used to build PyTorch: N/A
OS: Ubuntu 22.04.5 LTS (aarch64)
GCC version: (Ubuntu 11.4.0-1ubuntu1~22.04) 11.4.0
Clang version: Could not collect
CMake version: version 3.30.5
Libc version: glibc-2.35
Python version: 3.10.15 | packaged by conda-forge | (main, Oct 16 2024, 01:19:28) [GCC 13.3.0] (64-bit runtime)
Python platform: Linux-6.8.0-1019-aws-aarch64-with-glibc2.35
Is CUDA available: False
CUDA runtime version: No CUDA
CUDA_MODULE_LOADING set to: N/A
GPU models and configuration: No CUDA
Nvidia driver version: No CUDA
cuDNN version: No CUDA
HIP runtime version: N/A
MIOpen runtime version: N/A
Is XNNPACK available: True
CPU:
Architecture: aarch64
CPU op-mode(s): 32-bit, 64-bit
Byte Order: Little Endian
CPU(s): 48
On-line CPU(s) list: 0-47
Vendor ID: ARM
Model: 1
Thread(s) per core: 1
Core(s) per cluster: 48
Socket(s): -
Cluster(s): 1
Stepping: r1p1
BogoMIPS: 2100.00
Flags: fp asimd evtstrm aes pmull sha1 sha2 crc32 atomics fphp asimdhp cpuid asimdrdm jscvt fcma lrcpc dcpop sha3 sm3 sm4 asimddp sha512 sve asimdfhm dit uscat ilrcpc flagm ssbs paca pacg dcpodp svei8mm svebf16 i8mm bf16 dgh rng
L1d cache: 3 MiB (48 instances)
L1i cache: 3 MiB (48 instances)
L2 cache: 48 MiB (48 instances)
L3 cache: 32 MiB (1 instance)
NUMA node(s): 1
NUMA node0 CPU(s): 0-47
Vulnerability Gather data sampling: Not affected
Vulnerability Itlb multihit: Not affected
Vulnerability L1tf: Not affected
Vulnerability Mds: Not affected
Vulnerability Meltdown: Not affected
Vulnerability Mmio stale data: Not affected
Vulnerability Reg file data sampling: Not affected
Vulnerability Retbleed: Not affected
Vulnerability Spec rstack overflow: Not affected
Vulnerability Spec store bypass: Mitigation; Speculative Store Bypass disabled via prctl
Vulnerability Spectre v1: Mitigation; __user pointer sanitization
Vulnerability Spectre v2: Mitigation; CSV2, BHB
Vulnerability Srbds: Not affected
Vulnerability Tsx async abort: Not affected
Versions of relevant libraries:
[pip3] mypy==1.11.2
[pip3] mypy-extensions==1.0.0
[pip3] numpy==1.22.4
[pip3] onnx==1.17.0
[pip3] onnxscript==0.1.0.dev20240817
[pip3] optree==0.13.0
[pip3] torch==2.6.0a0+git35c676d
[conda] No relevant packages
cc @robieta @chaekit @guotuofeng @guyang3532 @dzhulgakov @davidberard98 @briancoutinho @sraikund16 @sanrise | OSS contribution wanted,oncall: profiler | low | Critical |
2,727,145,340 | kubernetes | Audit log file mode | ### What would you like to be added?
I want to be able to configure access rights to the audit logs file. Now the rights are written right in the code, and this is 600
https://github.com/kubernetes/kubernetes/blob/master/vendor/gopkg.in/natefinch/lumberjack.v2/lumberjack.go
### Why is this needed?
Complete with the rotation of the audit logs file and the fact that the kube api server (usually) runs from under the "root" of the user, only root can read the audit log file (file permissions are 0600). This makes it difficult for an unprivileged process to deliver logs to external systems. | kind/feature,needs-triage,wg/structured-logging | low | Major |
2,727,191,545 | go | runtime: immediate lock-up when using go library in Unity 6 | ### Go version
go1.21.1 darwin/arm64 (we have observed identical behaviour when using go 1.23.1 and 1.23.4)
### Output of `go env` in your module/workspace:
```shell
GO111MODULE=''
GOARCH='arm64'
GOBIN=''
GOCACHE='Library/Caches/go-build'
GOENV='Library/Application Support/go/env'
GOEXE=''
GOEXPERIMENT=''
GOFLAGS=''
GOHOSTARCH='arm64'
GOHOSTOS='darwin'
GOINSECURE=''
GOMODCACHE='go/pkg/mod'
GONOPROXY=''
GONOSUMDB=''
GOOS='darwin'
GOPATH='go'
GOPRIVATE=''
GOPROXY='https://proxy.golang.org,direct'
GOROOT='temp/go'
GOSUMDB='sum.golang.org'
GOTMPDIR=''
GOTOOLCHAIN='auto'
GOTOOLDIR='/$HOME/temp/go/pkg/tool/darwin_arm64'
GOVCS=''
GOVERSION='go1.21.1'
GCCGO='gccgo'
AR='ar'
CC='clang'
CXX='clang++'
CGO_ENABLED='1'
GOMOD='/dev/null'
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 -arch arm64 -pthread -fno-caret-diagnostics -Qunused-arguments -fmessage-length=0 -ffile-prefix-map=/var/folders/f8/0nlswm8x445_jl3720jx6kmw0000gn/T/go-build2270444360=/tmp/go-build -gno-record-gcc-switches -fno-common'
```
### What did you do?
When running on Apple Silicon hardware:
Prerequisites:
1. Extract plugin code: [TestPlugin.zip](https://github.com/user-attachments/files/18062718/TestPlugin.zip)
2. Extract Unity `2022.3.43f1` repro project: [Unity2022ReproProject.zip](https://github.com/user-attachments/files/18062637/Unity2022ReproProject.zip). Do not open the project yet.
3. Extract Unity `6000.0.28f1` repro project: [Unity6ReproProject.zip](https://github.com/user-attachments/files/18062283/Unity6ReproProject.zip). Do not open the project yet.
4. Install [dylibbundler](https://github.com/auriamg/macdylibbundler) required for dylib signing (`brew install dylibbundler`)
5. Build attached TestPlugin go lib as `.dylib` on MacOS (using cgo). You can use the included magefile.
6. Copy `build/TestPlugin.dylib` to the extracted Unity 2022 project in `Assets/Plugins/TestPlugin.dylib`.
7. Copy the same `build/TestPlugin.dylib` to the extracted Unity 6 project in `Assets/Plugins/TestPlugin.dylib`.
### What did you see happen?
### In Unity 2022
Unity 2022 (and also other versions like Unity 2021 and Unity 2023) is working as expected.
Open the Unity 2022 project, open the `Scenes/SampleScene` and click the Play button. Observe that the Unity Console shows:
```
Calling HelloWorld on plugin...
Successfully called HelloWorld on plugin...
```
If you open `~/Library/Logging/Unity/Editor.log` it will show:
```
Calling HelloWorld on plugin...
UnityEngine.StackTraceUtility:ExtractStackTrace () (at /Users/bokken/build/output/unity/unity/Runtime/Export/Scripting/StackTrace.cs:37)
UnityEngine.DebugLogHandler:LogFormat (UnityEngine.LogType,UnityEngine.Object,string,object[])
UnityEngine.Logger:Log (UnityEngine.LogType,object)
UnityEngine.Debug:Log (object)
MacOSPluginLoader:Start () (at Assets/Scripts/MacOSPluginLoader.cs:17)
(Filename: Assets/Scripts/MacOSPluginLoader.cs Line: 17)
Hello from Go!
Hello from Go 2!
Hello from Go 3!
Successfully called HelloWorld on plugin...
UnityEngine.StackTraceUtility:ExtractStackTrace () (at /Users/bokken/build/output/unity/unity/Runtime/Export/Scripting/StackTrace.cs:37)
UnityEngine.DebugLogHandler:LogFormat (UnityEngine.LogType,UnityEngine.Object,string,object[])
UnityEngine.Logger:Log (UnityEngine.LogType,object)
UnityEngine.Debug:Log (object)
MacOSPluginLoader:Start () (at Assets/Scripts/MacOSPluginLoader.cs:19)
```
### In Unity 6
Unity 6 is immediately locking up (showing a beachball spinner) as soon as any go API is called.
Open the Unity 6 project, open the `Scenes/SampleScene` and click the Play button. Observe that the Unity Console shows:
```
Calling HelloWorld on plugin...
```
If you open `~/Library/Logging/Unity/Editor.log` it will show:
```
Calling HelloWorld on plugin...
UnityEngine.StackTraceUtility:ExtractStackTrace () (at /Users/bokken/build/output/unity/unity/Runtime/Export/Scripting/StackTrace.cs:37)
UnityEngine.DebugLogHandler:LogFormat (UnityEngine.LogType,UnityEngine.Object,string,object[])
UnityEngine.Logger:Log (UnityEngine.LogType,object)
UnityEngine.Debug:Log (object)
MacOSPluginLoader:Start () (at Assets/Scripts/MacOSPluginLoader.cs:17)
```
### What did you expect to see?
Unity 2022 and Unity 6 to behave the same. Instead, Unity 2022 is behaving as expected wheras Unity 6 immediately locks-up the Unity Editor.
| help wanted,NeedsInvestigation,compiler/runtime | low | Critical |
2,727,198,141 | flutter | Content is stretched when using canvaskit in Mobile Browsers | ### Steps to reproduce
*This issue occurs specifically on Chrome mobile browsers.*
My setup involves an Angular project as the host application, containing a div element that embeds my Flutter web project. I aim to dynamically adjust the div container's height to achieve a proper website-like appearance and avoid multiple scrollings.
When using the HTML renderer, the view displays correctly. However, with the CanvasKit renderer, increasing the container's height beyond its default value causes the entire Flutter view to become stretched and blurred, resulting in the entire application appearing distorted.
As shown in the attached video, you can see that scrolling is also not possible once the content becomes stretched.
Note: This behavior has been observed on both Flutter stable and Flutter master channels.
You can find the Angular host app code at https://github.com/creatorpiyush/flutter-component-host. To test, create a web build using the command `flutter build web --web-renderer=canvaskit` with the provided Flutter code. Then, copy the `web` folder from the build directory into the assets folder of the host app repository.
### Expected results
The view should maintain its proportions and not become stretched when dynamically adjusting the height using the CanvasKit renderer.
### Actual results
The view is fully stretched, with its top portion obscured by the header, and scrolling is not possible.
### Code sample
<details open><summary>Code sample</summary>
main.dart
```dart
import 'package:dummy_app/js_interop_check.dart';
import 'package:flutter/material.dart';
void main() {
runApp(const MyApp());
}
class MyApp extends StatelessWidget {
const MyApp({super.key});
// This widget is the root of your application.
@override
Widget build(BuildContext context) {
return MaterialApp(
title: 'Flutter Demo',
theme: ThemeData(
primarySwatch: Colors.blue,
),
home: const MyHomePage(),
);
}
}
class MyHomePage extends StatefulWidget {
const MyHomePage({super.key});
@override
State<MyHomePage> createState() => _MyHomePageState();
}
class _MyHomePageState extends State<MyHomePage> {
@override
Widget build(BuildContext context) {
return Scaffold(
body: Center(
child: ListView.builder(
itemCount: 50,
itemBuilder: ((context, index) => GestureDetector(
onTap: () => updateHeight("flutter_host", 500.0, 1700.0),
child: Container(
color: Colors.amber,
child: const SizedBox(
height: 20,
width: 100,
child: Text("Click here"),
),
),
)),
),
),
);
}
}
```
js_interop_check.dart
```dart
import 'dart:js_interop';
@JS("_updateSize")
external void _updateSize(String target, double width, double height);
void updateHeight(String target, double width, double height) {
_updateSize(target, width, height);
}
```
web/js/js-interop.js
```javascipt
(function () {
"use strict";
window._updateSize = function (target, width, height) {
let flutterTarget = document.querySelector('#' + target);
flutterTarget.style.height = height + 'px';
}
}());
```
</details>
### Screenshots or Video
<details open>
<summary>Screenshots / Video demonstration</summary>
https://github.com/user-attachments/assets/0b8e5383-3227-46b8-b6f0-5b5baaeae232
</details>
### Logs
<details open><summary>Logs</summary>
```console
No logs
```
</details>
### Flutter Doctor output
<details open><summary>Doctor output</summary>
```console
[!] Flutter (Channel [user-branch], 3.24.5, on macOS 15.1.1 24B91 darwin-arm64, locale en-IN)
! Flutter version 3.24.5 on channel [user-branch] at /Users/piyushanand/flutterSDK/flutter
Currently on an unknown channel. Run `flutter channel` to switch to an official channel.
If that doesn't fix the issue, reinstall Flutter by following instructions at https://flutter.dev/setup.
! Upstream repository unknown source is not a standard remote.
Set environment variable "FLUTTER_GIT_URL" to unknown source to dismiss this error.
• Framework revision dec2ee5c1f (4 weeks ago), 2024-11-13 11:13:06 -0800
• Engine revision a18df97ca5
• Dart version 3.5.4
• DevTools version 2.37.3
• 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 35.0.0)
• Android SDK at /Users/piyushanand/Library/Android/sdk
• Platform android-35, build-tools 35.0.0
• ANDROID_HOME = /Users/piyushanand/Library/Android/sdk
• Java binary at: /Applications/Android Studio.app/Contents/jbr/Contents/Home/bin/java
• Java version OpenJDK Runtime Environment (build 21.0.3+-79915917-b509.11)
• All Android licenses accepted.
[✓] Xcode - develop for iOS and macOS (Xcode 16.1)
• Xcode at /Applications/Xcode.app/Contents/Developer
• Build 16B40
• CocoaPods version 1.16.2
[✓] Chrome - develop for the web
• Chrome at /Applications/Google Chrome.app/Contents/MacOS/Google Chrome
[✓] Android Studio (version 2024.2)
• 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 21.0.3+-79915917-b509.11)
[✓] VS Code (version 1.95.3)
• VS Code at /Applications/Visual Studio Code.app/Contents
• Flutter extension version 3.102.0
[✓] Connected device (4 available)
• iPhone 15 Pro Max (mobile) • B3A4ADC3-6E1B-44CD-AE31-8FA4F307CDDE • ios • com.apple.CoreSimulator.SimRuntime.iOS-17-5
(simulator)
• macOS (desktop) • macos • darwin-arm64 • macOS 15.1.1 24B91 darwin-arm64
• Mac Designed for iPad (desktop) • mac-designed-for-ipad • darwin • macOS 15.1.1 24B91 darwin-arm64
• Chrome (web) • chrome • web-javascript • Google Chrome 131.0.6778.109
! Error: Browsing on the local area network for Piyush’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.
! Doctor found issues in 1 category.
```
</details>
| platform-web,e: web_canvaskit,has reproducible steps,P2,browser: chrome-android,e: web_skwasm,team-web,triaged-web,browser: chrome-ios,found in release: 3.24,found in release: 3.27 | low | Critical |
2,727,287,050 | PowerToys | Black Screen Happens on opening PowerToys setting | ### Microsoft PowerToys version
0.86.0
### Installation method
Microsoft Store
### Running as admin
Yes
### Area(s) with issue?
Settings
### Steps to reproduce
1. Double click to open PowerToys setting on system tray (or left-click on system tray for quick setting)
2. Black screen happens
Log attached
- [PowerToysReport_2024-12-09-23-39-53.zip](https://github.com/user-attachments/files/18063119/PowerToysReport_2024-12-09-23-39-53.zip)
### ✔️ Expected Behavior
- open setting window
### ❌ Actual Behavior
- Black Screen is shown
### Other Software
Windows 11 23H2 (22631.4541) | Issue-Bug,Product-Settings,Needs-Triage | low | Minor |
2,727,287,906 | node | Test concurrency causes the Test Runner to report a wrong isTTY value | another one for the test runner:
### Description
Using `child_process` for test parallisation also sets `process.stdout.isTTY` to `undefined`.
The following returns `undefined` when it's run with `node --test`:
```bash
# node --test example.test.js
console.log(process.stdout.isTTY)
# undefined
```
when it's run with plain node, it's `true`:
```bash
# node example.test.js
console.log(process.stdout.isTTY)
# true
```
I had a very faint memory of a similar issue described by someone else,
very similar to this and IIRC about the `child_process`.
So, I run the same with `--experimental-test-isolation=none` and there it is: it returns `true` which confirms my suspicions.
```bash
# node --test --experimental-test-isolation=none example.test.js
console.log(process.stdout.isTTY)
# true
```
Although you can work around it, it's very problematic for the following reasons:
- It's inconsistent with [POLA](https://en.wikipedia.org/wiki/Principle_of_least_astonishment)
- It' inconsistent with it's *own* API because it reports one way with one flag, and another without.
- It leaks implementation details
How the tests are run is an *implementation detail* that shouldn't be leaking like that.
I'm sure there are some valid reasons for it but this feels plain wrong.
Thoughts?
**Note:** I only *suspect* these 2 issues are related.
| question | low | Major |
2,727,320,539 | flutter | Onboard on-screen keyboard causes application unresponsiveness for several seconds on Linux desktop | ### Steps to reproduce
1. Run `flutter create app` to create a new Flutter application.
2. Navigate to the project directory: `cd app`.
3. Edit the lib/main.dart file and add a TextField widget to the app.
4. Start the application with `flutter run`.
5. Press the d key to detach the app from the terminal.
6. Open the Onboard on-screen keyboard: `onboard`.
### Expected results
The on-screen keyboard should appear and disappear without delay, and key presses should be immediately detected by the TextField widget. This behavior was functioning correctly in version 3.22.3.
Here is a video demonstrating it:
https://github.com/user-attachments/assets/42d69657-bebc-4e08-a9b8-bf251e195f10
### Actual results
When clicking on the TextField, the on-screen keyboard appears with a delay, and key presses are not registered in the TextField. The user interface becomes visibly unresponsive for several seconds. This behavior has been present since version 3.23.0-0.0.pre. Here is a video demonstrating the issue:
https://github.com/user-attachments/assets/67e24897-8d89-4ba5-a7b2-9ae5a9e4f396
### Code sample
<details open><summary>Code sample</summary>
```dart
...
@override
Widget build(BuildContext context) {
// This method is rerun every time setState is called, for instance as done
// by the _incrementCounter method above.
//
// The Flutter framework has been optimized to make rerunning build methods
// fast, so that you can just rebuild anything that needs updating rather
// than having to individually change instances of widgets.
return Scaffold(
appBar: AppBar(
// TRY THIS: Try changing the color here to a specific color (to
// Colors.amber, perhaps?) and trigger a hot reload to see the AppBar
// change color while the other colors stay the same.
backgroundColor: Theme.of(context).colorScheme.inversePrimary,
// Here we take the value from the MyHomePage object that was created by
// the App.build method, and use it to set our appbar title.
title: Text(widget.title),
),
body: Center(
// Center is a layout widget. It takes a single child and positions it
// in the middle of the parent.
child: Column(
// Column is also a layout widget. It takes a list of children and
// arranges them vertically. By default, it sizes itself to fit its
// children horizontally, and tries to be as tall as its parent.
//
// Column has various properties to control how it sizes itself and
// how it positions its children. Here we use mainAxisAlignment to
// center the children vertically; the main axis here is the vertical
// axis because Columns are vertical (the cross axis would be
// horizontal).
//
// TRY THIS: Invoke "debug painting" (choose the "Toggle Debug Paint"
// action in the IDE, or press "p" in the console), to see the
// wireframe for each widget.
mainAxisAlignment: MainAxisAlignment.center,
children: <Widget>[
TextField(),
const Text(
'You have pushed the button this many times:',
),
Text(
'$_counter',
style: Theme.of(context).textTheme.headlineMedium,
),
],
),
),
floatingActionButton: FloatingActionButton(
onPressed: _incrementCounter,
tooltip: 'Increment',
child: const Icon(Icons.add),
), // This trailing comma makes auto-formatting nicer for build methods.
);
}
...
```
</details>
### Screenshots or Video
<details open>
<summary>Screenshots / Video demonstration</summary>
[Upload media here]
</details>
### Logs
<details open><summary>Logs</summary>
```console
[Paste your logs here]
```
</details>
### Flutter Doctor output
<details open><summary>Doctor output</summary>
```console
Downloading Linux arm64 Dart SDK from Flutter engine 964f087f288cc8a19018964f1660859eab5ed96b...
% Total % Received % Xferd Average Speed Time Time Time Current
Dload Upload Total Spent Left Speed
100 201M 100 201M 0 0 10.3M 0 0:00:19 0:00:19 --:--:-- 10.9M
Building flutter tool...
Resolving dependencies... (3.0s)
Downloading packages...
Got dependencies.
Downloading package sky_engine... 625ms
Downloading flutter_patched_sdk tools... 769ms
Downloading flutter_patched_sdk_product tools... 699ms
Downloading linux-arm64 tools... 4.9s
Downloading linux-arm64/font-subset tools... 506ms
Doctor summary (to see all details, run flutter doctor -v):
[!] Flutter (Channel [user-branch], 3.23.0-0.0.pre, on Debian GNU/Linux 12 (bookworm) 6.1.43-rockchip-rk3588, locale en_US.UTF-8)
! Flutter version 3.23.0-0.0.pre on channel [user-branch] at /home/orangepi/flutter
Currently on an unknown channel. Run `flutter channel` to switch to an official channel.
If that doesn't fix the issue, reinstall Flutter by following instructions at https://flutter.dev/docs/get-started/install.
! The flutter binary is not on your path. Consider adding /home/orangepi/flutter/bin to your path.
! The dart binary is not on your path. Consider adding /home/orangepi/flutter/bin to your path.
! Upstream repository unknown source is not a standard remote.
Set environment variable "FLUTTER_GIT_URL" to unknown source to dismiss this error.
[✗] Android toolchain - develop for Android devices
✗ Unable to locate Android SDK.
Install Android Studio from: https://developer.android.com/studio/index.html
On first launch it will assist you in installing the Android SDK components.
(or visit https://flutter.dev/docs/get-started/install/linux#android-setup for detailed instructions).
If the Android SDK has been installed to a custom location, please use
`flutter config --android-sdk` to update to that location.
[✗] Chrome - develop for the web (Cannot find Chrome executable at google-chrome)
! Cannot find Chrome. Try setting CHROME_EXECUTABLE to a Chrome executable.
[✓] Linux toolchain - develop for Linux desktop
[!] Android Studio (not installed)
[✓] Connected device (1 available)
[✓] Network resources
! Doctor found issues in 4 categories.
```
</details>
| a: text input,c: regression,platform-linux,perf: speed,has reproducible steps,fyi-text-input,team-linux,found in release: 3.27,found in release: 3.28 | low | Critical |
2,727,340,783 | go | proposal: os: add ReparsePointTag | ### Proposal Details
Windows applications might need to know the [reparse point tag](https://learn.microsoft.com/en-us/windows/win32/fileio/reparse-point-tags) of a given `os.FileInfo`. Although the Windows implementation of `os.FileInfo` knows the reparse point tag, there is no way to get that information using the public `os` API. This means that applications are forced to partially reimplement `os.Lstat` by opening the file and calling `GetFileInformationByHandleEx`.
I propose to add the following helper function to the `os` package:
```go
// ReparsePointTag returns the the reparse point tag associated with fi.
//
// ReparsePointTag only applies to results returned by this package's [LStat].
// fi must be associated with a reparse point.
// Otherwise, ReparsePointTag returns false.
func ReparsePointTag(fi FileInfo) (uint32, bool)
```
The `ReparsePointTag` implementation could be made more `os`-agnostic by also defining an interface that external `os.FileInfo` implementations could implement to get the reparse point tag. This might be an overkill for now, as reparse points are not a broadly-addopted concept outside NTFS file systems.
`ReparsePointTag` would only be useful on Windows for now, although it could potentially be implemented on other OSes supporting NTFS drivers.
@golang/windows | OS-Windows,Proposal | medium | Major |
2,727,481,102 | go | x/tools/cmd/goimports,gopls: avoid deprecated symbols and/or packages | Skimming the codebase, it look like we don't consider API deprecation in goimports. That is surprising.
We should avoid deprecated symbols and packages as import candidates.
Edit: context is golang/go#70717, where a user imported x/exp/maps by accident. (Though, will note that x/exp/maps is not currently deprecated).
CC @pjweinb | gopls,gopls/imports | low | Minor |
2,727,503,242 | go | proposal: go/types: add Select function | **Background:** The type checker has two different APIs for the same concept, namely information about a selection of a field or method:
- `Info.Selections` and `MethodSet` both use the record type `Selection`;
- `LookupFieldOrMethod` returns a triple, (obj, indices, indirect).
There is no way to construct a `Selection` from the result of `LookupFieldOrMethod`. Especially when operating in parallel on the method sets of two types, it is a perennial nuisance that these corresponding items have different forms.
**Proposal:** We propose a function, `Select`, to bridge this gap.
```go
package types
// Select selects the field or method whose ID is Id(pkg, name), on a value of type recv.
// See LookupFieldOrMethod for more detail.
func Select(recv Type, addressable bool, pkg *Package, name string) (Selection, bool) {
obj, index, indirect := LookupFieldOrMethod(recv, addressable, pkg, name string)
var kind SelectionKind
switch obj {
case *types.Func:
kind = MethodVal
case *types.Var:
kind = FieldVal
}
return Selection{kind, recv, obj, index, indirect}, obj != nil
}
```
Related:
- https://github.com/golang/go/issues/10091: Closed because it was a rename; this issue proposes an addition.
- https://github.com/golang/go/issues/12881: superseded by this issue. Also, we have never observed a need for NewSelection other than the one above.
@findleyr @griesemer @timothy-king | Proposal | low | Major |
2,727,568,400 | next.js | Webpack failing to use correct node loader in yarn workspace | ### Link to the code that reproduces this issue
https://github.com/snspinn/yarn-workspace-nextjs
### To Reproduce
Note: The following step will need rust installed:
1. Clone `https://github.com/snspinn/yarn-workspace-nextjs`
2. Run `yarn install` at top level
3. Build napi-rs package:
- `cd libraries/server-package`
- `yarn install && yarn build`
4. Build next app:
- `cd ../../app/my-app`
- `yarn install && yarn next build`
### Current vs. Expected behavior
I would expect it to just load the module. It works when using the `file:` protocol. However, this is a less than ideal workaround as it has other knock on affects (https://github.com/yarnpkg/berry/issues/6550, https://github.com/yarnpkg/berry/issues/3972).
Current behavior is that the build fails with a Module parse/loader error.
```
➤ YN0000: · Yarn 4.5.3
➤ YN0000: ┌ Resolution step
➤ YN0000: └ Completed
➤ YN0000: ┌ Fetch step
➤ YN0000: └ Completed in 0s 526ms
➤ YN0000: ┌ Link step
➤ YN0031: │ One or more node_modules have been detected and will be removed. This operation may take some time.
➤ YN0000: │ ESM support for PnP uses the experimental loader API and is therefore experimental
➤ YN0000: └ Completed
➤ YN0000: · Done with warnings in 0s 888ms
▲ Next.js 15.0.4
Creating an optimized production build ...
Failed to compile.
../../libraries/server-package/server-package.linux-x64-gnu.node
Module parse failed: Unexpected character '' (1:0)
You may need an appropriate loader to handle this file type, currently no loaders are configured to process this file. See https://webpack.js.org/concepts#loaders
(Source code omitted for this binary file)
Import trace for requested module:
../../libraries/server-package/server-package.linux-x64-gnu.node
../../libraries/server-package/index.js
./src/app/api/server-package/route.ts
> Build failed because of webpack errors
```
### Provide environment information
```bash
Operating System:
Platform: linux
Arch: x64
Version: #49~22.04.1-Ubuntu SMP PREEMPT_DYNAMIC Wed Nov 6 17:42:15 UTC 2
Available memory (MB): 31960
Available CPU cores: 8
Binaries:
Node: 20.14.0
npm: 9.9.3
Yarn: 4.5.3
pnpm: N/A
Relevant Packages:
next: 15.0.4
eslint-config-next: N/A
react: 19.0.0
react-dom: 19.0.0
typescript: N/A
Next.js Config:
output: standalone
```
### Which area(s) are affected? (Select all that apply)
Developer Experience, Webpack
### Which stage(s) are affected? (Select all that apply)
next dev (local), next build (local)
### Additional context
Had been getting this error since v14 therefore have not tested with any canary releases. Was waiting to see if `serverComponentsExternalPackages` becoming stable would solve it. | bug,Webpack | low | Critical |
2,727,590,464 | react-native | Auto Completion is not working for Phone Number | ### Description
have a text Input inside a form to ask the user to register. the issue is the keyboard suggestions to fill the phone number is not showing for unknown reasons.
Does anyone have this issue before and how it can be solved?
P.S: I tried to play with the Keyboard type and with autoComplete type and with textContentType, but nothing work
<InputComponent
key={'phoneNumber'}
label={'phone number'} onChangeText={handleChange('phoneNumber')}
value={values.phoneNumber}
onBlur={handleBlur('phoneNumber')}
//
autoComplete={'tel'}
blurOnSubmit={false}
autoCapitalize={'none'}
keyboardType={'number-pad'}
textContentType="telephoneNumber"
/>
### Steps to reproduce
- Just using a Text Input in React Native, doesn't auto suggestion completion
usually in other app u find your phone number suggested and show the suggestions keyboard
### React Native Version
0.74.1
### Affected Platforms
Runtime - iOS
### Output of `npx react-native info`
```text
..
```
### Stacktrace or Logs
```text
..
```
### Reproducer
..
### Screenshots and Videos
| Needs: Repro,Newer Patch Available,Needs: Attention | low | Major |
2,727,592,205 | flutter | Firebase tests are retried when the failure is that no tests were run | While investigating a failing pull request I discovered that our recipe code retries firebase failures when no tests are identified by firebase. This bug tracks identifying if those results have a signature or result that we can detect and not retrying those failures. The reason firebase gives a failure is that we are being billed for something that in theory is not giving us results. Retrying can't fix the issue.
https://ci.chromium.org/ui/p/flutter/builders/try/Linux_android%20android_device_tests_shard_1%20master/12743/overview
<img width="565" alt="Screenshot 2024-12-09 at 10 09 09 AM" src="https://github.com/user-attachments/assets/6427524f-1e4d-4866-9617-bafcd5cdf357">
https://logs.chromium.org/logs/flutter/buildbucket/cr-buildbucket/8729261023562739057/+/u/Run_package_tests/Firebase_Test_Lab/stdout
```
More details are available at [ https://console.firebase.google.com/project/flutter-infra-staging/testlab/histories/bh.2128561b4a3def3d/matrices/4897799301081527082 ].
┌─────────┬────────────────────────┬────────────────────┐
│ OUTCOME │ TEST_AXIS_VALUE │ TEST_DETAILS │
├─────────┼────────────────────────┼────────────────────┤
│ Failed │ panther-33-en-portrait │ Test failed to run │
└─────────┴────────────────────────┴────────────────────┘
Test failure for example/integration_test/shared_preferences_test.dart after 2 attempts
``` | platform-android,team-infra,P2,triaged-infra | low | Critical |
2,727,597,416 | go | cmd/compile: optimize reflect.TypeOf(x)==reflect.TypeOf(y) | I notice that the code generated for a comparison of rtypes is surprisingly poor, involving a ton of spills and a call to an intrinsic:
```go
func sameType(x, y any) bool {
return reflect.TypeOf(x) != reflect.TypeOf(y)
}
```
```
golang.org/x/tools/gopls/internal/golang.sameType STEXT size=176 args=0x20 locals=0x48 funcid=0x0 align=0x0
0x0000 00000 L0505 TEXT golang.org/x/tools/gopls/internal/golang.sameType(SB), ABIInternal, $80-32
0x0000 00000 L0505 MOVD 16(g), R16
0x0004 00004 L0505 PCDATA $0, $-2
0x0004 00004 L0505 CMP R16, RSP
0x0008 00008 L0505 BLS 144
0x000c 00012 L0505 PCDATA $0, $-1
0x000c 00012 L0505 MOVD.W R30, -80(RSP)
0x0010 00016 L0505 MOVD R29, -8(RSP)
0x0014 00020 L0505 SUB $8, RSP, R29
0x0018 00024 L0505 MOVD R0, golang.org/x/tools/gopls/internal/golang.x(FP)
0x001c 00028 L0505 MOVD R1, golang.org/x/tools/gopls/internal/golang.x+8(FP)
0x0020 00032 L0505 MOVD R2, golang.org/x/tools/gopls/internal/golang.y+16(FP)
0x0024 00036 L0505 MOVD R3, golang.org/x/tools/gopls/internal/golang.y+24(FP)
0x0028 00040 L0505 FUNCDATA $0, gclocals·emgMVsd5mo9g0HGy8lQYQA==(SB)
0x0028 00040 L0505 FUNCDATA $1, gclocals·lV4l69IdnTMCVxlqSaJ25Q==(SB)
0x0028 00040 L0505 FUNCDATA $2, golang.org/x/tools/gopls/internal/golang.sameType.stkobj(SB)
0x0028 00040 L0505 FUNCDATA $5, golang.org/x/tools/gopls/internal/golang.sameType.arginfo1(SB)
0x0028 00040 L0505 FUNCDATA $6, golang.org/x/tools/gopls/internal/golang.sameType.argliveinfo(SB)
0x0028 00040 L0505 PCDATA $3, $1
0x0028 00040 NOP
0x0028 00040 L1303 MOVD R0, internal/abi.a-16(SP)
0x002c 00044 L1303 MOVD R1, internal/abi.a-8(SP)
0x0030 00048 L0179 MOVD internal/abi.a-16(SP), R4
0x0034 00052 NOP
0x0034 00052 NOP
0x0034 00052 NOP
0x0034 00052 L1303 MOVD R2, internal/abi.a-32(SP)
0x0038 00056 L1303 MOVD R3, internal/abi.a-24(SP)
0x003c 00060 L0179 MOVD internal/abi.a-32(SP), R3
0x0040 00064 NOP
0x0040 00064 NOP
0x0040 00064 L2719 CMP $0, R4
0x0044 00068 L0510 MOVD $go:itab.*reflect.rtype,reflect.Type(SB), R5
0x004c 00076 L0510 CSEL NE, R5, ZR, R0
0x0050 00080 L2719 CMP $0, R3
0x0054 00084 L0510 CSEL NE, R5, ZR, R5
0x0058 00088 L0510 CMP R5, R0
0x005c 00092 L2719 BEQ 104
0x0060 00096 L2719 MOVD $1, R3
0x0064 00100 L2719 JMP 128
0x0068 00104 L2719 CMP $0, R4
0x006c 00108 L0510 CSEL NE, R4, ZR, R1
0x0070 00112 L2719 CMP $0, R3
0x0074 00116 L0510 CSEL NE, R3, ZR, R2
0x0078 00120 L0510 PCDATA $1, $1
0x0078 00120 L0510 CALL runtime.ifaceeq(SB)
0x007c 00124 L0510 EOR $1, R0, R3
0x0080 00128 L0510 MOVD R3, R0
0x0084 00132 L0510 MOVD -8(RSP), R29
0x0088 00136 L0510 MOVD.P 80(RSP), R30
0x008c 00140 L0510 RET (R30)
0x0090 00144 L0510 NOP
0x0090 00144 L0505 PCDATA $1, $-1
0x0090 00144 L0505 PCDATA $0, $-2
0x0090 00144 L0505 STP (R0, R1), 8(RSP)
0x0094 00148 L0505 STP (R2, R3), 24(RSP)
0x0098 00152 L0505 MOVD R30, R3
0x009c 00156 L0505 CALL runtime.morestack_noctxt(SB)
0x00a0 00160 L0505 PCDATA $0, $-1
0x00a0 00160 L0505 LDP 8(RSP), (R0, R1)
0x00a4 00164 L0505 LDP 24(RSP), (R2, R3)
0x00a8 00168 L0505 JMP 0
```
Is there any reason it couldn't be recognized as a special case and compiled as if written using unsafe Go code like this:
```go
func sameType(x, y any) bool {
type eface struct {
t, v unsafe.Pointer
}
return ((*eface)(unsafe.Pointer(&x))).t == ((*eface)(unsafe.Pointer(&y))).t
}
```
which boils down to a pair of loads and a comparison:
```
golang.org/x/tools/gopls/internal/golang.sameType STEXT size=48 args=0x20 locals=0x0 funcid=0x0 align=0x0 leaf
0x0000 00000 L0505 TEXT golang.org/x/tools/gopls/internal/golang.sameType(SB), LEAF|NOFRAME|ABIInternal, $0-32
0x0000 00000 L0505 FUNCDATA $0, gclocals·emgMVsd5mo9g0HGy8lQYQA==(SB)
0x0000 00000 L0505 FUNCDATA $1, gclocals·acF1O9X4FQHZUTLQivBEZA==(SB)
0x0000 00000 L0505 FUNCDATA $2, golang.org/x/tools/gopls/internal/golang.sameType.stkobj(SB)
0x0000 00000 L0505 FUNCDATA $5, golang.org/x/tools/gopls/internal/golang.sameType.arginfo1(SB)
0x0000 00000 L0505 MOVD R0, golang.org/x/tools/gopls/internal/golang.x(FP)
0x0004 00004 L0505 MOVD R1, golang.org/x/tools/gopls/internal/golang.x+8(FP)
0x0008 00008 L0505 MOVD R2, golang.org/x/tools/gopls/internal/golang.y+16(FP)
0x000c 00012 L0505 MOVD R3, golang.org/x/tools/gopls/internal/golang.y+24(FP)
0x0010 00016 L0509 MOVD golang.org/x/tools/gopls/internal/golang.x(FP), R1
0x0014 00020 L0509 MOVD golang.org/x/tools/gopls/internal/golang.y+16(FP), R2
0x0018 00024 L0509 CMP R1, R2
0x001c 00028 L0509 CSET EQ, R0
0x0020 00032 L0509 RET (R30)
``` | NeedsInvestigation,compiler/runtime | low | Major |
2,727,638,819 | pytorch | Support int step for nonfused optimizer implementations | ### 🚀 The feature, motivation and pitch
An actionable (though lower priority) followup from the discussion here https://github.com/pytorch/pytorch/issues/127197.
While it may be nice to have support for this, a very easy workaround is to use float for step.
### Alternatives
_No response_
### Additional context
_No response_
cc @vincentqb @jbschlosser @albanD @crcrpar | module: optimizer,low priority,triaged,actionable | low | Minor |
2,727,684,393 | pytorch | Add a linter for Docker images which are not included in docker-builds.yml | This is a common miss when adding a new Docker image to not add it into docker-builds.yml. For example, https://github.com/pytorch/pytorch/pull/140733 added `pytorch-linux-focal-cuda12.4-cudnn9-py3.13-gcc9-inductor-benchmarks` for 3.13, but didn't add it into docker-builds.yml. Its build worked because the `calculate-docker-image` would try to build the image itself and that would continue for a long time till someone notice the higher build time.
Having a linter would make sure that the new Docker image is built and pushed to ECR correctly instead of being rebuilt in all related CI jobs.
cc @seemethere @malfet @pytorch/pytorch-dev-infra | module: ci,triaged,needs design | low | Minor |
2,727,730,521 | neovim | vim.fn.system not working in a windows Git bash/zsh environment | ### Problem
Usage of vim.fn.system will error with '/usr/bin/bash: /s: No such file or directory'
Also, simple `:!ls` does not work.
Ultimately, neovim runs `$SHELL /s /c cmdline`. As SHELL is bash/zsh, the error occurs.
Resolve this by apply '/s /c' options only to a white-list of known windows shells.
### Steps to reproduce
install neovim with winget
install official git for windows, which provides a bash environment
run neovim in this bash environment
### Expected behavior
vim.fn.system('ls') and `:!ls` should work.
### Nvim version (nvim -v)
0.10.2
### Vim (not Nvim) behaves the same?
No. vim `:!ls` works
### Operating system/version
Windows 11
### Terminal name/version
Wezterm
### $TERM environment variable
not relevent
### Installation
winget neovim | bug,platform:windows | low | Critical |
2,727,759,396 | rust | min_generic_const_args: Braced paths should forbid infer vars | We should ensure that `Foo<{ BAR }>` is treated the same as `Foo<BAR>` when ` BAR` has generic parameters (i.e. it should error in both cases).
| T-compiler,A-const-generics,F-min_generic_const_args | low | Critical |
2,727,791,670 | vscode | (Web, Safari) Copying and pasting line with colon and no leading space results in URL encoding of pasted text | <!-- ⚠️⚠️ 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: Web
- OS Version: iPadOS 18.1 (Safari)
VSCode Web on iPadOS/Safari appears to be erroneously encoding certain copied text as a URL.
So copying this string of text from a VSCode Web file:
`foo: bar`
And pasting it into another VSCode web file will result in:
`foo:%20bar`
This is only the case if there isn’t a space before the colon anywhere on the line. So,
` foo: bar` and `foo bar: baz` both copy and paste normally.
This also only happens within VSCode web. So, copying `foo: bar` from an external app and pasting it into VSCode Web or copying `foo: bar` from VSCode web into another app both work fine.
I have not been able to reproduce this on VSCode Web on Mac or Windows.
Steps to Reproduce:
1. On iPadOS on Safari, open a new file on VSCode Web (or Github Codespaces)
2. Write text `foo: bar`
3. Copy to clipboard, where the first character of selection is NOT whitespace
4. Paste into same file.
https://github.com/user-attachments/assets/0dca81bb-fee2-4623-9ed4-0441ff70231e
| bug,help wanted,editor-clipboard,ios-ipados | low | Critical |
2,727,819,023 | rust | Unhelpful diagnostic on `=` to `:` typo mentioning return type notation | ### Code
```Rust
let x: Vec::new();
```
### Current output
```
error: return type notation arguments must be elided with `..`
--> src/main.rs:2:20
|
2 | let x: Vec::new();
| ^^ help: add `..`: `(..)`
error: return type notation not allowed in this position yet
--> src/main.rs:2:12
|
2 | let x: Vec::new();
| ^^^^^^^^^^
```
### Rationale and extra context
This is a mistake where `:` was used instead of `=`. Instead of telling the user that it talks about rtn.
### Rust Version
```Shell
stable and latest nightly.
rustc 1.85.0-nightly (a2545fd6f 2024-11-28)
```
### Anything else?
@rustbot label +D-invalid-suggestion | A-diagnostics,T-compiler,D-confusing | low | Critical |
2,727,824,593 | langchain | langchain 0.3.10 does not support langsmith >=0.2.0 | ### Checked other resources
- [X] I added a very descriptive title to this issue.
- [X] I searched the LangChain documentation with the integrated search.
- [X] I used the GitHub search to find a similar question and didn't find it.
- [X] I am sure that this is a bug in LangChain rather than my code.
- [X] The bug is not resolved by updating to the latest stable version of LangChain (or the specific integration package).
### Example Code
The latest versions of langchain and langsmith and not compatible. I am needing to use langsmith version `0.1.147`
```
langchain>=0.3.10
langsmith==0.2.1
```
### Error Message and Stack Trace (if applicable)
The conflict is caused by:
The user requested langsmith==0.2.1
langchain 0.3.10 depends on langsmith<0.2.0 and >=0.1.17
The user requested langsmith==0.2.1
langchain 0.3.10 depends on langsmith<0.2.0 and >=0.1.17
### Description
I am trying to use langchain version `0.3.10` with langsmith `0.2.1` but langchain requires langsmith to be version 0.2.0 or below
### System Info
System Information
------------------
> OS: Windows
> OS Version: 10.0.22631
> Python Version: 3.13.1 (tags/v3.13.1:0671451, Dec 3 2024, 19:06:28) [MSC v.1942 64 bit (AMD64)]
Package Information
-------------------
> langchain_core: 0.3.22
> langchain: 0.3.10
> langsmith: 0.1.147
> langchain_anthropic: 0.3.0
> langchain_google_genai: 2.0.6
> langchain_openai: 0.2.11
> langchain_text_splitters: 0.3.2
> langchain_weaviate: 0.1.0.dev1
Optional packages not installed
-------------------------------
> langserve
Other Dependencies
------------------
> aiohttp: 3.11.9
> anthropic: 0.40.0
> async-timeout: Installed. No version info available.
> defusedxml: 0.7.1
> filetype: 1.2.0
> google-generativeai: 0.8.3
> httpx: 0.27.0
> jsonpatch: 1.33
> langsmith-pyo3: Installed. No version info available.
> numpy: 1.26.4
> openai: 1.57.1
> orjson: 3.10.12
> packaging: 24.2
> pydantic: 2.10.3
> PyYAML: 6.0.2
> requests: 2.32.3
> requests-toolbelt: 1.0.0
> simsimd: 6.2.1
> SQLAlchemy: 2.0.36
> tenacity: 9.0.0
> tiktoken: 0.8.0
> typing-extensions: 4.12.2
> weaviate-client: 4.9.6 | investigate | low | Critical |
2,727,851,402 | flutter | enable ASAN for impeller_unittests and impeller_golden_tests on macos ci | Spawned from https://github.com/flutter/engine/pull/57015
There is a `--asan` flag in GN. If you set it it will compile the binaries with the correct flags. The impeller targets will fail to compile though because `flatc` will fail to execute. Clang on macos links a runtime library ( `libclang_rt.asan_osx_dynamic.dylib` ) that isn't available to dyld without some sort of change. I'm not sure what mechanisms GN has to run otool to edit the linkage. | P2,e: impeller,team-engine,triaged-engine | low | Minor |
2,727,854,685 | pytorch | Compile bug with isin assume_unique=True | ### 🐛 Describe the bug
I have the following strange compile bug with isin and assume_unique=True.
Without compiling, the code runs fine for any `n` and `assume_unique` value.
When compiling, the code runs fine for any `n` when `assume_unique=False`. When `assume_unique=True`, the code runs fine for `n < 12`, and errors for `n >= 12`.
```python
import torch
from torch import nn, Tensor
symbols = 2
bars = 3
all_false = torch.full((symbols, bars), False, device="cuda") # (symbols, bars)
@torch.compile
class MyModel(nn.Module):
def __init__(self, n: int, assume_unique: bool) -> None:
super().__init__()
self.ignored_symbols = torch.arange(n, device="cuda")
self.assume_unique = assume_unique
def forward(
self,
symbol_ids: Tensor, # (symbols, 1)
) -> Tensor:
mask_ignored_symbols = torch.isin(
symbol_ids, self.ignored_symbols, assume_unique=self.assume_unique
) # (symbols, 1)
return all_false | mask_ignored_symbols
# +50 to avoid the ignored symbols, not important
symbol_ids = torch.arange(symbols, device="cuda").unsqueeze(1) + 50
print(symbol_ids)
model = MyModel(n=12, assume_unique=True).cuda()
output: Tensor = model(symbol_ids)
```
In terms of ablation, the code compiles fine for `backend="eager"` and `backend="aot_eager"`, but fails with `backend="aot_eager_decomp_partition"`.
### Error logs
The following error is what appears, after the long stack trace.
```
torch._dynamo.exc.BackendCompilerFailed: backend='inductor' raised:
RuntimeError: Attempting to broadcast a dimension of length 2 at -1! Mismatching argument at index 1 had torch.Size([2]); but expected shape should be broadcastable to [2, 3]
While executing %or_ : [num_users=1] = call_function[target=operator.or_](args = (%g_all_false_, %mask_ignored_symbols), kwargs = {})
Original traceback:
File "/home/ilan/monorepo/src/Ayin3/foo.py", line 34, in forward
return all_false | mask_ignored_symbols
```
### Versions
Manual versions:
OS: Arch Linux
Python 3.12.7 (also reproduced on 3.13)
Torch version: 2.6.0.dev20241209+cu126 (also reproduced on latest stable 2.5)
---
The automatic script gives me the following error:
```
...
File "/home/ilan/monorepo/collect_env.py", line 470, in run_with_pip
line for line in out.splitlines() if any(name in line for name in patterns)
^^^^^^^^^^^^^^
AttributeError: 'NoneType' object has no attribute 'splitlines'
```
cc @chauhang @penguinwu @zou3519 @bdhirsh @yf225 | triaged,oncall: pt2,module: aotdispatch,module: pt2-dispatcher | low | Critical |
2,727,862,447 | rust | BTreeMap documentation has confusing wording about binary search tree performance issues | ### Location
https://github.com/rust-lang/rust/blob/f6cb952dc115fd1311b02b694933e31d8dc8b002/library/alloc/src/collections/btree/map.rs#L48-L49
### Summary
In the discussion of performance issues of binary search trees, it is written that `[...] every single comparison should be a cache-miss.`
I think this is confusing in the following ways:
- Comparisons are not cache misses. They operate on values which are already loaded into registers. Of course, the nodes need to be loaded in order to perform the comparisons, but that is not what is written in the relevant sentence.
- The use of `should` could be understood as a value judgement. I doubt it was intended as one, but rather to express that a cache miss is expected. However, even this interpretations is not fully accurate, since the next node for the tree traversal might be cached (because it was recently accessed or close enough in memory to something recently accessed that it was cached alongside).
I suggest replacing the last two sentences of the paragraph with something like `This means that every single insertion triggers a heap-allocation, and for every comparison a node needs to be loaded, which could result in a cache miss. Since both heap-allocations and cache-misses are notably expensive in practise, we are forced to, at the very least, reconsider the BST strategy.` | A-docs,C-bug,T-libs | low | Major |
2,727,872,513 | pytorch | User-defined way to hook into Inductor autotuning | We've seen some use cases for this:
1) A user has a user-defined triton kernel vs a sequence of PyTorch operations. They want inductor to select the "best" one in the situation.
2) A custom operators has some knobs that are exposed to inductor (some tunable parameters).
Thoughts?
cc @chauhang @penguinwu @voznesenskym @EikanWang @jgong5 @Guobing-Chen @XiaobingSuper @zhuhaozhe @blzheng @wenzhe-nrv @jiayisunx @ipiszy @yf225 @chenyang78 @kadeng @muchulee8 @ColinPeppler @amjames @desertfire @aakhundov @bdhirsh | feature,triaged,module: custom-operators,oncall: pt2,module: inductor,module: pt2-dispatcher | low | Minor |
2,727,884,640 | deno | Object property not recognized in VSCode after cmd-clicking class until LSP restart | Version: Deno 2.1.3
```ts
import { Spanner } from "npm:@google-cloud/spanner@^7.16.0";
const _spannerClient = new Spanner({
projectId: "test",
});
```
When I open this file in VSCode (with the Deno extension and an empty "{}" deno.json file in the same directory), there are no errors and it appears to understand the types of each value in the code. However, if I cmd-click on `Spanner` on line 3 and then press escape to hide the pop-up, then a red error squiggle appears under `projectId`, showing the error "Object literal may only specify known properties, and 'projectId' does not exist in type 'SpannerOptions'. deno-ts(2353)". This error stays until I restart the Deno language server. I'm able to reproduce this every time on multiple (mac) machines. | bug,lsp | low | Critical |
2,727,919,056 | pytorch | Stft changes number of times when with center=False and n_fft > win_length | ### 🐛 Describe the bug
I am implimenting a stft library that uses torch under the hood but uses the parameter conventions of scipy’s ShortTimeFFT. I am having trouble understanding the torch behavior when the stft fft is zero padded and center=False. I believe the behavior is a bug, but I can change this bug report to a documentation ticket if the behavior is expected. However, I don't know where to look for the defined behavior.
My basic expectation is zero padding should only change the frequency axis of the output, but the time axis should not change because the data sampling (window and hop) has remained the same. When center=True this holds, but doesn’t when center=False.
```
timeseries = torch.randn((8, 2300))
# True, which I expect
torch.stft(timeseries, 200, hop_length=100, win_length=200, window=torch.ones(200), return_complex=True).shape[2] == torch.stft(timeseries, 400, hop_length=100, win_length=200, window=torch.ones(200), return_complex=True).shape[2]
# False, which I think is a bug
torch.stft(timeseries, 200, hop_length=100, win_length=200, window=torch.ones(200), return_complex=True, center=False).shape[2] == torch.stft(timeseries, 400, hop_length=100, win_length=200, window=torch.ones(200), return_complex=True, center=False).shape[2]
```
### Versions
PyTorch version: 2.0.0+cu118
Is debug build: False
CUDA used to build PyTorch: 11.8
ROCM used to build PyTorch: N/A
OS: Debian GNU/Linux 12 (bookworm) (x86_64)
GCC version: (Debian 12.2.0-14) 12.2.0
Clang version: 18.1.8 (++20240731024826+3b5b5c1ec4a3-1~exp1~20240731144843.145)
CMake version: version 3.31.1
Libc version: glibc-2.36
Python version: 3.11.7 (main, Dec 19 2023, 03:30:20) [GCC 12.2.0] (64-bit runtime)
Python platform: Linux-6.8.0-1019-aws-x86_64-with-glibc2.36
Is CUDA available: True
CUDA runtime version: 11.8.89
CUDA_MODULE_LOADING set to: LAZY
GPU models and configuration: GPU 0: NVIDIA A10G
Nvidia driver version: 550.120
cuDNN version: Probably one of the following:
/usr/lib/x86_64-linux-gnu/libcudnn.so.8.6.0
/usr/lib/x86_64-linux-gnu/libcudnn_adv_infer.so.8.6.0
/usr/lib/x86_64-linux-gnu/libcudnn_adv_train.so.8.6.0
/usr/lib/x86_64-linux-gnu/libcudnn_cnn_infer.so.8.6.0
/usr/lib/x86_64-linux-gnu/libcudnn_cnn_train.so.8.6.0
/usr/lib/x86_64-linux-gnu/libcudnn_ops_infer.so.8.6.0
/usr/lib/x86_64-linux-gnu/libcudnn_ops_train.so.8.6.0
HIP runtime version: N/A
MIOpen runtime version: N/A
Is XNNPACK available: True
CPU:
Architecture: x86_64
CPU op-mode(s): 32-bit, 64-bit
Address sizes: 48 bits physical, 48 bits virtual
Byte Order: Little Endian
CPU(s): 16
On-line CPU(s) list: 0-15
Vendor ID: AuthenticAMD
Model name: AMD EPYC 7R32
CPU family: 23
Model: 49
Thread(s) per core: 2
Core(s) per socket: 8
Socket(s): 1
Stepping: 0
BogoMIPS: 5599.85
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 ssse3 fma cx16 sse4_1 sse4_2 movbe popcnt aes xsave avx f16c rdrand hypervisor lahf_lm cmp_legacy cr8_legacy abm sse4a misalignsse 3dnowprefetch topoext ssbd ibrs ibpb stibp vmmcall fsgsbase bmi1 avx2 smep bmi2 rdseed adx smap clflushopt clwb sha_ni xsaveopt xsavec xgetbv1 clzero xsaveerptr rdpru wbnoinvd arat npt nrip_save rdpid
Hypervisor vendor: KVM
Virtualization type: full
L1d cache: 256 KiB (8 instances)
L1i cache: 256 KiB (8 instances)
L2 cache: 4 MiB (8 instances)
L3 cache: 32 MiB (2 instances)
NUMA node(s): 1
NUMA node0 CPU(s): 0-15
Vulnerability Gather data sampling: Not affected
Vulnerability Itlb multihit: Not affected
Vulnerability L1tf: Not affected
Vulnerability Mds: Not affected
Vulnerability Meltdown: Not affected
Vulnerability Mmio stale data: Not affected
Vulnerability Reg file data sampling: Not affected
Vulnerability Retbleed: Mitigation; untrained return thunk; SMT enabled with STIBP protection
Vulnerability Spec rstack overflow: Vulnerable: Safe RET, no microcode
Vulnerability Spec store bypass: Mitigation; Speculative Store Bypass disabled via prctl
Vulnerability Spectre v1: Mitigation; usercopy/swapgs barriers and __user pointer sanitization
Vulnerability Spectre v2: Mitigation; Retpolines; IBPB conditional; STIBP always-on; RSB filling; PBRSB-eIBRS Not affected; BHI Not affected
Vulnerability Srbds: Not affected
Vulnerability Tsx async abort: Not affected
Versions of relevant libraries:
[pip3] mypy-boto3-ec2==1.28.85
[pip3] mypy-boto3-s3==1.28.55
[pip3] mypy-boto3-sagemaker==1.28.76
[pip3] mypy-boto3-secretsmanager==1.35.0
[pip3] mypy-boto3-sns==1.28.72
[pip3] mypy-boto3-sqs==1.28.82
[pip3] mypy-extensions==1.0.0
[pip3] numpy==1.26.4
[pip3] numpy-stl==3.1.1
[pip3] onnx==1.15.0
[pip3] onnx-graphsurgeon==0.3.15
[pip3] onnxruntime==1.16.3
[pip3] pytorch-lightning==2.1.0
[pip3] pytorch-quantization==2.1.2
[pip3] torch==2.0.0+cu118
[pip3] torch-tb-profiler==0.4.3
[pip3] torchaudio==2.0.1+cu118
[pip3] torchdata==0.6.0
[pip3] torchmetrics==1.1.0
[pip3] torchtext==0.15.1+cpu
[pip3] torchvision==0.15.1+cu118
[pip3] triton==2.0.0
[conda] Could not collect
cc @mruberry | triaged,module: fft,module: scipy compatibility | low | Critical |
2,727,922,220 | pytorch | [Dynamo] Do an audit on skipfiles and mark more files as inline | When someone adds a new file under `torch/*` it is included in SkipFiles by default. This is a pain point for people who are adding new features to work with torch.compile: they end up seeing a SkipFiles error, like in https://github.com/pytorch/pytorch/pull/138555. In fact, this is probably the most common error I run into. It's relatively easy to fix (just mark the file as inline) but not everyone knows to do this.
Pitch: the default for new files being added under `torch/*` is that we should inline them by default (instead of skipping them by default). We should also audit all files currently inside SkipFiles to see if they actually need to be in SkipFiles.
cc @voznesenskym @penguinwu @EikanWang @jgong5 @Guobing-Chen @XiaobingSuper @zhuhaozhe @blzheng @wenzhe-nrv @jiayisunx @chenyang78 @kadeng @chauhang @amjames @yanboliang | triaged,oncall: pt2,module: dynamo | low | Critical |
2,727,923,499 | angular | Remove support for non-null assertions from two-way bindings | In v20 we should drop support for expressions like `[(ngModel)]="someExpr!"`, because type checking is non-obvious. We can revive the migration from #54630 to migrate existing users. | breaking changes,area: compiler,compiler: template type-checking | low | Minor |
2,727,941,665 | vscode | Run Recent Command does not cover multi-line Python REPL commands | On macOS or Linux or WSL,
1. Enable `python.terminal.shellIntegration.enabled`.
2. Run "Python: Clear Cache and Reload Window".
3. Open a terminal and start a Python REPL.
4. Type `for i in range(5):` and press Enter.
5. Type ` print(i)` (including the spaces) and press Enter.
6. Press Enter again.
7. The REPL should print integers from 0 to 4.
8. Run "Terminal: Run Recent Command..."
9. :bug: Only `print(i)` shows up in the quick pick. | bug,terminal-shell-integration,python | low | Critical |
2,727,955,181 | terminal | A lone zero-width character in the first column occupies 1 column | ### Windows Terminal version
1.23.3411.0
### Windows build number
_No response_
### Other Software
_No response_
### Steps to reproduce
In PowerShell:
```pwsh
"`r`u{200B}foo"
```
### Expected Behavior
```
foo
```
### Actual Behavior
```
foo
```
> The reason it happens is because before inserting anything in our text buffer we check if it joins with the already existing character and then merge it together with the new input. For any other characters we clamp the width of each grapheme cluster to a value between 1 and 2. Since a zero-width character can't join with anything in the first column it will be measured as its own cluster which results in a width of 1.
> The reason we do this is primarily because of our architecture which assumes O(1) lookups in the text buffer. The only way to make that work is by assuming that each grapheme cluster has a width of 1-2. The secondary reason for that is because inserting the ZWSP there puts it in front of the first column, assigning it column -1, which is not something that should be possible. Put differently, if you're at column 1 and iterate to the previous grapheme cluster, you would end up at column 0 (the start of the line), but after the ZWSP. It's a problem I don't have a good solution for except "add a bunch of special conditions" which gave me the gut feeling of "the problem has not been fundamentally solved".
https://github.com/microsoft/terminal/issues/18267#issuecomment-2529077871 | Area-Output,Issue-Bug,Needs-Tag-Fix,Priority-3 | low | Minor |
2,727,956,029 | pytorch | Enable GradScaler for MPS devices | ### 🚀 The feature, motivation and pitch
I'm currently experimenting with mixed precision on my M4 Pro MBP since support for autocasting to `float16` has been added for MPS in 2.5.0 (https://github.com/pytorch/pytorch/pull/99272).
When trying to apply gradient scaling however, the following exception occurs on calling `scaler.step(optimizer)`:
```
Traceback (most recent call last):
...
File "<redacted>/src/train.py", line 105, in train_model
scaler.step(optimizer)
File "<redacted>/.venv/lib/python3.11/site-packages/torch/amp/grad_scaler.py", line 451, in step
self.unscale_(optimizer)
File "<redacted>/.venv/lib/python3.11/site-packages/torch/amp/grad_scaler.py", line 335, in unscale_
inv_scale = self._scale.double().reciprocal().float()
^^^^^^^^^^^^^^^^^^^^
TypeError: Cannot convert a MPS Tensor to float64 dtype as the MPS framework doesn't support float64. Please use float32 instead.
```
Since autocast works, it would be fantastic to also have working support for `GradScaler` with MPS.
### Alternatives
_No response_
### Additional context
The same issue has recently also been raised [in the forum](https://discuss.pytorch.org/t/gradscaler-typeerror-cannot-convert-a-mps-tensor-to-float64-dtype-as-the-mps-framework-doesnt-support-float64-please-use-float32-instead/213206). There, code for reproduction is also referenced.
cc @mcarilli @ptrblck @leslie-fang-intel @jgong5 @kulinseth @albanD @malfet @DenisVieriu97 @jhavukainen | triaged,module: amp (automated mixed precision),module: mps | low | Critical |
2,727,989,770 | rust | Expected/Found does not point to point where type parameter was inferred | ### Code
```Rust
fn foo<'a, T>(b: &'a T) -> &'a T { b }
fn main() {
let f = foo;
f(&String::new());
f(&Vec::new());
}
```
### Current output
```Shell
error[E0308]: mismatched types
--> src/main.rs:7:7
|
7 | f(&Vec::new());
| - ^^^^^^^^^^^ expected `&String`, found `&Vec<_>`
| |
| arguments to this function are incorrect
|
= note: expected reference `&String`
found reference `&Vec<_>`
note: function defined here
--> src/main.rs:1:4
|
1 | fn foo<'a, T>(b: &'a T) -> &'a T { b }
| ^^^ --------
```
### Desired output
```Shell
error[E0308]: mismatched types
--> src/main.rs:7:7
|
7 | f(&Vec::new());
| - ^^^^^^^^^^^ expected `&String`, found `&Vec<_>`
| |
| arguments to this function are incorrect
|
= note: expected reference `&String`
found reference `&Vec<_>`
note: function defined here
--> src/main.rs:1:4
|
1 | fn foo<'a, T>(b: &'a T) -> &'a T { b }
| ^^^ --------
note: generic argument was inferred to `String` here
--> src/main.rs:6:7
|
6 | f(&String::new());
| ^^^^^^^^^^^^^
```
### Rationale and extra context
_No response_
### Other cases
```Rust
```
### Rust Version
```Shell
playground version:
Build using the Nightly version: 1.85.0-nightly
(2024-12-08 4d669fb34e7db6f3825d)
```
### Anything else?
_No response_ | A-diagnostics,T-compiler,D-terse | low | Critical |
2,728,087,623 | PowerToys | PowerToys Run Program: making the search paths and ignore patterns configurable | ### Description of the new feature / enhancement
The "Program" plugin of PowerToys Run doesn't allow the user to configure the search paths and set ignore patterns. I request to add these configurations to fix usability problems of PowerToys Run (see the next paragraph). Here is the UI for these configurations in Wox:
### Scenario when this would be used?
I recently switched from Wox to PowerToys Run, and found two usability problems in the "Program" plugin of PowerToys Run.
The first problem is that the plugin searches for programs in both Start Menu and Desktop recursively. Therefore, if the user stores a large amount of files (e.g., cloned a large dataset) on desktop, it will be scanned recursively, and all `.exe` and `.lnk` files will be indexed as programs. This causes performance problem and unwanted search results.
Demo:
The other problem is that the plugin will index unrelated shortcuts in Start Menu (e.g., the uninstaller) and sometimes place it before the real application. It is easy to accidentally launch the uninstaller.
Demo:
These two problems can be fixed by making the search paths and ignore patterns configurable, so that I can:
- Remove desktop from the search paths
- Ignore programs with name `*unins*`, `*help*`, or `*website*`
### Supporting information
Current search paths: https://github.com/microsoft/PowerToys/blob/main/src/modules/launcher/Plugins/Microsoft.Plugin.Program/Storage/Win32ProgramFileSystemWatchers.cs#L35 | Product-PowerToys Run,Needs-Triage,Run-Results (Programs) | low | Major |
2,728,118,624 | deno | Node Compatibility: Crypto RSA encryption | Version: Deno 2.1.3
The node crypto implementation is lacking support for KeyObjects.
This is currently breaking cross-platform support and subsequently breaking the npm library [OpenPGP](https://www.npmjs.com/package/openpgp), where I was originally experiencing this [issue](https://github.com/openpgpjs/openpgpjs/issues/1813) <- More information can be found there | bug,crypto | low | Minor |
2,728,249,902 | deno | Implicit dependency on `deno_net` extension from within `deno_fetch` extension | I will preface this by stating that I don't know much about deno and I'm learning as I'm going, so this is entirely possibly user error.
I'm attempting to initialize a `deno_core::JsRuntime` with the `deno_fetch` extension. According to [the documentation](https://github.com/denoland/deno/blob/v2.1.3/ext/fetch/README.md) and the [dependency list](https://github.com/denoland/deno/blob/7f9b1ff30f7d9880b7c825c2b5f2de3137343d76/ext/fetch/lib.rs#L138) `deno_net` is not a dependency of `deno_fetch` (in fact, it appears it's the other way around!). However attempting to use only `deno_fetch` results in this error at runtime:
```
thread '<unnamed>' panicked at /Users/houndie/.cargo/registry/src/index.crates.io-6f17d22bba15001f/deno_core-0.324.0/runtime/jsruntime.rs:745:9:
Failed to initialize a JsRuntime: Specifier "ext:deno_net/02_tls.js" was not passed as an extension module and was not included in the snapshot.
note: run with `RUST_BACKTRACE=1` environment variable to display a backtrace
```
I browsing the source I find [this suspect import](https://github.com/denoland/deno/blob/7f9b1ff30f7d9880b7c825c2b5f2de3137343d76/ext/fetch/22_http_client.js#L17) potentially causing this?
Would love advice on how I can fix this on my side. I tried including `deno_net` and dependencies, which does seem to solve the problem, but [it seems there's also a dependency on `telemetry`](https://github.com/denoland/deno/blob/883abfa1bfeb4eded1ebdb8cc7364c254dcaad2e/ext/fetch/26_fetch.js#L67) which requires typescript transpilation to use that extension so I thought I'd take a pause before following that rabbit hole. | embedder | low | Critical |
2,728,288,222 | flutter | Task declares the same output directory as mergeDebugAssets | ### Steps to reproduce
I was updating the android part of the flutter app and android studio suggested me to send this report :
```
At 21:46, Dec 09, 2024, Android Studio detected the following issue(s) with Gradle plugin dev.flutter.flutter-gradle-plugin
Task Setup Issues
Task declares the same output directory as task mergeDebugAssets from com.android.application: 'O:\wapp\flutter5000\build\app\intermediates\assets\debug\mergeDebugAssets'.
Plugin: dev.flutter.flutter-gradle-plugin
Task: copyFlutterAssetsDebug
Task type: org.gradle.api.tasks.Copy
Issues for the same task were detected in 1 module(s), total execution time was 0,4s (13,6%), by module:
Execution mode: FULL, time: 0,4s (13,6%), determines build duration: true, on critical path: false, issues: Task Setup Issues
====Build information:====
Execution date: 09 déc. 2024 21:46
Total build duration: 18,1s
Configuration time: 1,4s (7,7%)
Critical path tasks time: 3,1s (16,9%)
Critical path tasks size: 6
AGP versions: 8.7.3
====Platform information:====
AS: Ladybug | 2024.2.1 Patch 3
AI-242.23339.11.2421.12700392, JRE 21.0.3+-12282718-b509.11x64 JetBrains s.r.o., OS Windows 11(amd64) v10.0 , screens 1920x1080 (125%)
Android Gradle Plugin: 8.7.3
Gradle: 8.11.1
Gradle JDK: JetBrains Runtime 21.0.3
NDK: from local.properties: (not specified), latest from SDK: 27.2.12479018
CMake: from local.properties: (not specified), latest from SDK: 3.31.1, from PATH: (not found)
```
and there is also this report :
```
At 21:46, Dec 09, 2024, Android Studio detected the following issue(s) with Gradle plugin com.android.application
Task Setup Issues
Task declares the same output directory as task copyFlutterAssetsDebug from dev.flutter.flutter-gradle-plugin: 'O:\wapp\flutter5000\build\app\intermediates\assets\debug\mergeDebugAssets'.
Plugin: com.android.application
Task: mergeDebugAssets
Task type: com.android.build.gradle.tasks.MergeSourceSetFolders
Issues for the same task were detected in 1 module(s), total execution time was 0,1s (3,7%), by module:
Execution mode: FULL, time: 0,1s (3,7%), determines build duration: true, on critical path: false, issues: Task Setup Issues
====Build information:====
Execution date: 09 déc. 2024 21:46
Total build duration: 18,1s
Configuration time: 1,4s (7,7%)
Critical path tasks time: 3,1s (16,9%)
Critical path tasks size: 6
AGP versions: 8.7.3
====Platform information:====
AS: Ladybug | 2024.2.1 Patch 3
AI-242.23339.11.2421.12700392, JRE 21.0.3+-12282718-b509.11x64 JetBrains s.r.o., OS Windows 11(amd64) v10.0 , screens 1920x1080 (125%)
Android Gradle Plugin: 8.7.3
Gradle: 8.11.1
Gradle JDK: JetBrains Runtime 21.0.3
NDK: from local.properties: (not specified), latest from SDK: 27.2.12479018
CMake: from local.properties: (not specified), latest from SDK: 3.31.1, from PATH: (not found)
[At 2146, Dec 09, 2024, Android Stud_02.txt](https://github.com/user-attachments/files/18068033/At.2146.Dec.09.2024.Android.Stud_02.txt)
```
### Actual results
the result is that I am sending them to you as android studio considers them as issues
### Logs
<details open>
<summary>Logs</summary>
```console
<!-- Paste your logs here -->
```
</details>
### Flutter Doctor output
<details open>
<summary>Doctor output</summary>
```console
<!-- Paste your output here -->
```
</details>
I think flutter doctor is not concerned here | platform-android,tool,t: gradle,P3,d: intellij,team-android,triaged-android | low | Critical |
2,728,312,035 | pytorch | [dynamo] Tracking issue for multiple inheritance support | ### 🐛 Describe the bug
During Dynamo symbolic interpretation of user code, we model python objects as `VariableTracker`. When a pre-existing python object is used, we [wrap](https://github.com/pytorch/pytorch/blob/0052943bee624c06d8c36a371efdf7b56972ad9e/torch/_dynamo/variables/builder.py#L387) it with a subclass of `VariableTracker`, [based on its type](https://github.com/pytorch/pytorch/blob/0052943bee624c06d8c36a371efdf7b56972ad9e/torch/_dynamo/variables/builder.py#L694-L744).
This doesn't play well with multiple inheritance, as shown in #141118. In general, the reason is the combination of:
1. When Dynamo creates a `VariableTracker` from a user python object, it often dispatches to a very specific type, e.g., `UnspecializedNNModuleVariable`, with a single `isinstance` check [without checking for multiple inheritance](https://github.com/pytorch/pytorch/blob/0052943bee624c06d8c36a371efdf7b56972ad9e/torch/_dynamo/variables/builder.py#L669-L670).
2. In Dynamo, we have [logic that depends on the type of a `VariableTracker`](https://github.com/pytorch/pytorch/blob/0052943bee624c06d8c36a371efdf7b56972ad9e/torch/_dynamo/variables/builtin.py#L1377-L1397), but due to (1), the multiple inheritance information isn't directly represented at the `VariableTracker`'s type level, resulting in "I know this value is both an `nn.Module` and `MutableMapping`, but Dynamo generally treats it as an `nn.Module`".
As #142416 shows, we could apply local fixes since the multiple inheritance information is still accessible in the `value` field of most `VariableTracker` instances, but it's unclear how far that could approach can take us and how it'll complicate Dynamo logic, given how often the aforementioned (2) happens. On the other hand, we also don't know how big of an issue multiple inheritance is in practice, so I'm creating this tracking issue to gather information and help us lazily evaluate the problem.
### Error logs
_No response_
### Versions
main 7101dcfb98b
cc @chauhang @penguinwu @voznesenskym @EikanWang @jgong5 @Guobing-Chen @XiaobingSuper @zhuhaozhe @blzheng @wenzhe-nrv @jiayisunx @chenyang78 @kadeng @amjames | triaged,oncall: pt2,module: dynamo | low | Critical |
2,728,336,595 | yt-dlp | [fc2] `HTTP Error 400: Bad Request` | ### 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)
- [ ] 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
_No response_
### Provide a description that is worded well enough to be understood
Example URL:
https://video.fc2.com/content/20121129xMeT3Czt
For _some_ fc2 videos, yt-dlp takes an eternity to start downloading, only to then fail on the first fragment.
What makes this so weird is that using the direct download link extracted by yt-dlp works just fine.
### 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', '--abort-on-unavailable-fragments', 'https://video.fc2.com/content/20121129xMeT3Czt']
[debug] Encodings: locale cp1252, fs utf-8, pref cp1252, out utf-8 (No VT), error utf-8 (No VT), screen utf-8 (No VT)
[debug] yt-dlp version [email protected] from yt-dlp/yt-dlp-nightly-builds [6fef82402] (win_exe)
[debug] Python 3.10.11 (CPython AMD64 64bit) - Windows-8.1-6.3.9600-SP0 (OpenSSL 1.1.1t 7 Feb 2023)
[debug] exe versions: ffmpeg 4.3, ffprobe 2022-07-24-git-39a538f430-full_build-www.gyan.dev
[debug] Optional libraries: Cryptodome-3.21.0, brotli-1.1.0, certifi-2024.08.30, curl_cffi-0.5.10, mutagen-1.47.0, requests-2.32.3, sqlite3-3.40.1, urllib3-2.2.3, websockets-14.1
[debug] Proxy map: {}
[debug] Request Handlers: urllib, requests, websockets, curl_cffi
[debug] Loaded 1837 extractors
[debug] Fetching release info: https://api.github.com/repos/yt-dlp/yt-dlp-nightly-builds/releases/latest
Latest version: [email protected] from yt-dlp/yt-dlp-nightly-builds
yt-dlp is up to date ([email protected] from yt-dlp/yt-dlp-nightly-builds)
[fc2] Extracting URL: https://video.fc2.com/content/20121129xMeT3Czt
[fc2] 20121129xMeT3Czt: Downloading webpage
[fc2] 20121129xMeT3Czt: Downloading info page
[debug] Formats sorted by: hasvid, ie_pref, lang, quality, res, fps, hdr:12(7), vcodec, channels, acodec, size, br, asr, proto, vext, aext, hasaud, source, id
[debug] Default format spec: bestvideo*+bestaudio/best
[info] 20121129xMeT3Czt: Downloading 1 format(s): 0
[debug] Invoking hlsnative downloader on "https://video.fc2.com/api/v3/videoplay/veoh.20121129xMeT3Czt/3?signature=$6EX67M.VEOH&t=1733758153"
[hlsnative] Downloading m3u8 manifest
[hlsnative] Total fragments: 6379303
[download] Destination: Rotfux [20121129xMeT3Czt].mp4
[debug] File locking is not supported. Proceeding without locking
[download] Got error: HTTP Error 400: Bad Request. Retrying fragment 1 (1/10)...
[download] Got error: HTTP Error 400: Bad Request. Retrying fragment 1 (2/10)...
[download] Got error: HTTP Error 400: Bad Request. Retrying fragment 1 (3/10)...
[download] Got error: HTTP Error 400: Bad Request. Retrying fragment 1 (4/10)...
[download] Got error: HTTP Error 400: Bad Request. Retrying fragment 1 (5/10)...
[download] Got error: HTTP Error 400: Bad Request. Retrying fragment 1 (6/10)...
[download] Got error: HTTP Error 400: Bad Request. Retrying fragment 1 (7/10)...
[download] Got error: HTTP Error 400: Bad Request. Retrying fragment 1 (8/10)...
[download] Got error: HTTP Error 400: Bad Request. Retrying fragment 1 (9/10)...
[download] Got error: HTTP Error 400: Bad Request. Retrying fragment 1 (10/10)...
[download] Got error: HTTP Error 400: Bad Request. Giving up after 10 retries
File "yt_dlp\__main__.py", line 17, in <module>
File "yt_dlp\__init__.py", line 1093, in main
File "yt_dlp\__init__.py", line 1083, in _real_main
File "yt_dlp\YoutubeDL.py", line 3605, in download
File "yt_dlp\YoutubeDL.py", line 3578, in wrapper
File "yt_dlp\YoutubeDL.py", line 1613, in extract_info
File "yt_dlp\YoutubeDL.py", line 1624, in wrapper
File "yt_dlp\YoutubeDL.py", line 1780, in __extract_info
File "yt_dlp\YoutubeDL.py", line 1839, in process_ie_result
File "yt_dlp\YoutubeDL.py", line 3011, in process_video_result
File "yt_dlp\YoutubeDL.py", line 177, in wrapper
File "yt_dlp\YoutubeDL.py", line 3479, in process_info
File "yt_dlp\YoutubeDL.py", line 3199, in dl
File "yt_dlp\downloader\common.py", line 464, in download
File "yt_dlp\downloader\hls.py", line 381, in real_download
File "yt_dlp\downloader\fragment.py", line 513, in download_and_append_fragments
File "yt_dlp\downloader\fragment.py", line 459, in download_fragment
File "yt_dlp\utils\_utils.py", line 5251, in __iter__
File "yt_dlp\downloader\fragment.py", line 456, in error_callback
File "yt_dlp\downloader\common.py", line 410, in report_retry
File "yt_dlp\utils\_utils.py", line 5258, in report_retry
File "yt_dlp\downloader\common.py", line 413, in <lambda>
File "yt_dlp\YoutubeDL.py", line 1090, in report_error
File "yt_dlp\YoutubeDL.py", line 1018, in trouble
ERROR: fragment 1 not found, unable to continue
File "yt_dlp\__main__.py", line 17, in <module>
File "yt_dlp\__init__.py", line 1093, in main
File "yt_dlp\__init__.py", line 1083, in _real_main
File "yt_dlp\YoutubeDL.py", line 3605, in download
File "yt_dlp\YoutubeDL.py", line 3578, in wrapper
File "yt_dlp\YoutubeDL.py", line 1613, in extract_info
File "yt_dlp\YoutubeDL.py", line 1624, in wrapper
File "yt_dlp\YoutubeDL.py", line 1780, in __extract_info
File "yt_dlp\YoutubeDL.py", line 1839, in process_ie_result
File "yt_dlp\YoutubeDL.py", line 3011, in process_video_result
File "yt_dlp\YoutubeDL.py", line 177, in wrapper
File "yt_dlp\YoutubeDL.py", line 3479, in process_info
File "yt_dlp\YoutubeDL.py", line 3199, in dl
File "yt_dlp\downloader\common.py", line 464, in download
File "yt_dlp\downloader\hls.py", line 381, in real_download
File "yt_dlp\downloader\fragment.py", line 514, in download_and_append_fragments
File "yt_dlp\downloader\fragment.py", line 479, in append_fragment
File "yt_dlp\YoutubeDL.py", line 1090, in report_error
File "yt_dlp\YoutubeDL.py", line 1018, in trouble
# Using the direct download link
[debug] Command-line config: ['-v', 'https://video.fc2.com/api/v3/videoplay/veoh.20121129xMeT3Czt/3?signature=$6EX67M.VEOH&t=1733758153']
[debug] Encodings: locale cp1252, fs utf-8, pref cp1252, out utf-8 (No VT), error utf-8 (No VT), screen utf-8 (No VT)
[debug] yt-dlp version [email protected] from yt-dlp/yt-dlp-nightly-builds [6fef82402] (win_exe)
[debug] Python 3.10.11 (CPython AMD64 64bit) - Windows-8.1-6.3.9600-SP0 (OpenSSL 1.1.1t 7 Feb 2023)
[debug] exe versions: ffmpeg 4.3, ffprobe 2022-07-24-git-39a538f430-full_build-www.gyan.dev
[debug] Optional libraries: Cryptodome-3.21.0, brotli-1.1.0, certifi-2024.08.30, curl_cffi-0.5.10, mutagen-1.47.0, requests-2.32.3, sqlite3-3.40.1, urllib3-2.2.3, websockets-14.1
[debug] Proxy map: {}
[debug] Request Handlers: urllib, requests, websockets, curl_cffi
[debug] Loaded 1837 extractors
[generic] Extracting URL: https://video.fc2.com/api/v3/videoplay/veoh.20121129xMeT3Czt/3?signature=$6EX67M.VEOH&t=1733758153
[generic] 3?signature=$6EX67M: Downloading webpage
[redirect] Following redirect to https://acache.veoh.com/file/f/l40850948.mp4?e=1733777229&rs=100&h=f884e7c17e5c422f3fc3c1c33c1f6e2a
[generic] Extracting URL: https://acache.veoh.com/file/f/l40850948.mp4?e=1733777229&rs=100&h=f884e7c17e5c422f3fc3c1c33c1f6e2a
[generic] l40850948: Downloading webpage
[debug] Identified a direct video link
[debug] Formats sorted by: hasvid, ie_pref, lang, quality, res, fps, hdr:12(7), vcodec, channels, acodec, size, br, asr, proto, vext, aext, hasaud, source, id
[debug] Default format spec: bestvideo*+bestaudio/best
[info] l40850948: Downloading 1 format(s): mp4
[debug] Invoking http downloader on "https://acache.veoh.com/file/f/l40850948.mp4?e=1733777229&rs=100&h=f884e7c17e5c422f3fc3c1c33c1f6e2a"
[debug] File locking is not supported. Proceeding without locking
[download] Destination: l40850948 [l40850948].mp4
[download] 100% of 236.03MiB in 00:40:17 at 99.99KiB/s
```
| site-bug | low | Critical |
2,728,410,716 | TypeScript | Typescript type hint problem |
Type: <b>Bug</b>
使用一段时间后，鼠标移到变量或者typescript类型上面，会有以下问题：
- 没有类型提示，没有任何反应，此时按住command同时点击鼠标左键可以正常跳到实现
正常会有浮层提示类型，重启VS Code之后正常，但是使用一段时间之后还会出现
After using it for a while, when you move the mouse over a variable or typescript type, the following problems will occur:
- No type hint, no response, at this time, hold down command and click the left mouse button to jump to the implementation
Normally, there will be a floating layer prompt type, it will be normal after restarting VS Code, but it will still appear after using it for a while
- Normal display
The mouse pointer is at the arrow position
- problem
The mouse pointer is at the arrow position
> Version: 1.96.0-insider (Universal)
Commit: 91bf2f3b96a337c05fdd30dbfe609ae780b74706
Date: 2024-11-19T05:04:26.087Z
Electron: 32.2.3
ElectronBuildId: 10561341
Chromium: 128.0.6613.186
Node.js: 20.18.0
V8: 12.8.374.38-electron.0
OS: Darwin x64 22.6.0
VS Code version: Code 1.95.1 (65edc4939843c90c34d61f4ce11704f09d3e5cb6, 2024-10-31T05:14:54.222Z)
OS version: Darwin x64 22.6.0
Modes:
<details>
<summary>System Info</summary>
|Item|Value|
|---|---|
|CPUs|Intel(R) Core(TM) i9-9880H CPU @ 2.30GHz (16 x 2300)|
|GPU Status|2d_canvas: enabled<br>canvas_oop_rasterization: disabled_off<br>direct_rendering_display_compositor: disabled_off_ok<br>gpu_compositing: enabled<br>multiple_raster_threads: enabled_on<br>opengl: enabled_on<br>rasterization: enabled<br>raw_draw: disabled_off_ok<br>skia_graphite: disabled_off<br>video_decode: enabled<br>video_encode: enabled<br>webgl: enabled<br>webgl2: enabled<br>webgpu: enabled<br>webnn: disabled_off|
|Load (avg)|4, 3, 2|
|Memory (System)|16.00GB (1.19GB free)|
|Process Argv|--crash-reporter-id df018b86-dcb3-4093-a0fe-1df1f758d245|
|Screen Reader|no|
|VM|0%|
</details><details><summary>Extensions (7)</summary>
Extension|Author (truncated)|Version
---|---|---
markdown-mermaid|bie|1.26.0
vscode-eslint|dba|3.0.13
prettier-vscode|esb|11.0.0
githd|hui|2.5.3
vscode-language-pack-zh-hans|MS-|1.95.2024103009
volar|Vue|2.1.10
material-theme|zhu|3.17.5
</details><details>
<summary>A/B Experiments</summary>
```
vsliv368:30146709
vspor879:30202332
vspor708:30202333
vspor363:30204092
vscod805cf:30301675
binariesv615:30325510
vsaa593cf:30376535
py29gd2263:31024239
vscaat:30438848
c4g48928:30535728
azure-dev_surveyone:30548225
vscrpc:30673769
962ge761:30959799
pythongtdpath:30769146
pythonnoceb:30805159
asynctok:30898717
pythonmypyd1:30879173
2e7ec940:31000449
pythontbext0:30879054
cppperfnew:31000557
dsvsc020:30976470
pythonait:31006305
dsvsc021:30996838
jg8ic977:31013176
dvdeprecation:31068756
dwnewjupytercf:31046870
impr_priority:31102340
nativerepl1:31139838
refactort:31108082
pythonrstrctxt:31112756
cf971741:31144450
iacca1:31171482
notype1cf:31157160
5fd0e150:31155592
dwcopilot:31170013
```
</details>
<!-- generated by issue reporter --> | Needs More Info | low | Critical |
2,728,476,827 | go | x/build/cmd/watchflakes: periodically restarts | Watchflakes is periodically being restarted.
Command `kubectl get pods` produces:
`watchflakes-deployment-679f9fbf8c-zp9ld 1/1 Running 47 (26m ago) 27d`
@golang/release | Builders,NeedsInvestigation | low | Minor |
2,728,539,992 | vscode | Reconsider auto vacuuming sqlite state.vscdb files? It saved 776MB on my install. | Hello, I found large state.vscdb files in VSCode workspaceStorage folder using an app to analyse disk usage, which triggered my curiosity and when opening I couldn't find anything big in the ItemTable file. Finally found I could VACUUM it, which brought the biggest state.vscdb file from 298MB to 639kB, and the total workspaceStorage folder size from 995MB to 219MB (VACUUMing all vscdb files as shown below).
Considering the significant size saving, could you reconsider auto vacuuming the files regularly? I found #189352 and #146280 already talking about it but there is not much details on which tests failed. Thanks!
Vacuuming files:
```sh
❯ pwd
/Users/me/Library/Application Support/Code/User
❯ fd vscdb --exec sqlite3 {} vacuum
``` | feature-request,workbench-state | low | Critical |
2,728,568,354 | rust | rustc doesn't infer that the future of a recursive `async fn` is `Send`. | (Note: this bug is *not* about recursion in asynchronous functions being limited because futures of async functions cannot contain a copy of themselves.)
I would expect this code to compile successfully:
```rust
use std::future::Future;
pub async fn recur(depth: usize) {
if depth == 0 {
return;
}
spawn(recur(depth - 1));
}
pub fn spawn(_future: impl Future + Send + 'static) { }
```
Instead, rustc complains:
```
error[E0283]: type annotations needed: cannot satisfy `impl Future<Output = ()>: Send`
--> recursive/src/lib.rs:7:5
|
7 | spawn(recur(depth - 1));
| ^^^^^^^^^^^^^^^^^^^^^^^
|
= note: cannot satisfy `impl Future<Output = ()>: Send`
note: required by a bound in `spawn`
--> recursive/src/lib.rs:10:37
|
10 | pub fn spawn(_future: impl Future + Send + 'static) { }
| ^^^^ required by this bound in `spawn`
For more information about this error, try `rustc --explain E0283`.
error: could not compile `recursive` (lib) due to 1 previous error
```
The program compiles fine if I pass `RUSTFLAGS=-Znext-solver` to nightly rustc. I wasn't able to find any existing issues that seemed similar.
### Meta
`rustc +nightly --version --verbose`:
```
rustc 1.85.0-nightly (9c707a8b7 2024-12-07)
binary: rustc
commit-hash: 9c707a8b769523bb6768bf58e74fa2c39cc24844
commit-date: 2024-12-07
host: x86_64-unknown-linux-gnu
release: 1.85.0-nightly
LLVM version: 19.1.5
```
| C-bug,T-types | low | Critical |
2,728,577,470 | PowerToys | Problem with Image Resizer | ### Microsoft PowerToys version
0.86.0
### Installation method
GitHub, Microsoft Store
### Running as admin
Yes
### Area(s) with issue?
Image Resizer
### Steps to reproduce
It is impossible to have image resizer in the Windows context menu. I have no problem with other tools like PowerRename.
[PowerToysReport_2024-12-10-00-37-23.zip](https://github.com/user-attachments/files/18069535/PowerToysReport_2024-12-10-00-37-23.zip)
### ✔️ Expected Behavior
A solution !
### ❌ Actual Behavior
_No response_
### Other Software
_No response_ | Issue-Bug,Product-Image Resizer,Needs-Triage,Area-Context Menu | low | Minor |
2,728,619,855 | ollama | Nancy finds security vulnerabilities | ### What is the issue?
It finds:
* [CVE-2024-8063](https://ossindex.sonatype.org/vulnerability/CVE-2024-8063?component-type=golang&component-name=github.com%2Follama%2Follama&utm_source=nancy-client&utm_medium=integration&utm_content=1.0.46) CWE-369: Divide By Zero
* [CVE-2024-39719](https://ossindex.sonatype.org/vulnerability/CVE-2024-39719?component-type=golang&component-name=github.com%2Follama%2Follama&utm_source=nancy-client&utm_medium=integration&utm_content=1.0.46) CWE-209: Information Exposure Through an Error Message
The latest stable Ollama version does not fix them, so I am opening an issue to track that.
### OS
Linux
### GPU
Intel
### CPU
Intel
### Ollama version
0.5.1 | bug | low | Critical |
2,728,636,013 | next.js | Clicking on a <Link> to the current page focuses the first page.tsx element, not the first layout.tsx element | ### Link to the code that reproduces this issue
https://codesandbox.io/p/devbox/vigilant-orla-2snw6p
### To Reproduce
1. Put a link in the root `layout.tsx` file that takes you to `/`
2. Click that link, notice how `document.activeElement` is now the first element from the `page.tsx`, and not `layout.tsx`
### Current vs. Expected behavior
I would expect this line to find the first element on the page, but instead it finds the first element from the `page.tsx`, causing the page to scroll down when clicking on a link to itself:
https://github.com/vercel/next.js/blob/657c2cbd72ebf8f9a58edb4a7393c596246e3161/packages/next/src/client/components/layout-router.tsx#L209
This is causing issues on our site as it scrolls the user down every time they visit the home page, because we have a large shared navigation bar that is on every page.
### 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: 20.9.0
npm: 9.8.1
Yarn: 1.22.19
pnpm: 8.10.2
Relevant Packages:
next: 15.0.4-canary.49 // Latest available version is detected (15.0.4-canary.49).
eslint-config-next: N/A
react: 19.0.0
react-dom: 19.0.0
typescript: 5.3.3
Next.js Config:
output: N/A
```
### Which area(s) are affected? (Select all that apply)
Navigation
### Which stage(s) are affected? (Select all that apply)
next dev (local), next start (local), Vercel (Deployed), Other (Deployed)
### Additional context
Related: #49427 | bug,Navigation | low | Minor |
2,728,695,308 | rust | Crater testing | Just testing some crater runs, please ignore. | S-waiting-on-review | low | Major |
2,728,726,287 | deno | localStorage constructor name is not 'Storage' an instead 'bound Storage' | Hello,
The result of `globalThis.localStorage.constructor.name` is "bound Storage".
It was formerly just "Storage", as it is in Chrome &etc.
Best,
R
Version: Deno 2.1.3
```
$ deno
Deno 2.1.3
> globalThis.localStorage.constructor.name
"bound Storage"
>
$
```
| bug,web | low | Minor |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.