there were a lot of events recorded by gharchive.org of which 2,261,333 were push events containing 3,547,947 commit messages that amount to 296,670,389 characters filtered with words.py@e23d022007... to these 53 messages:
HOLY SHIT IT KINDA LOOKS GOOD ROTATE TO POINT ON AIM
Refactors Slaughter/Laughter Demons into Basic Mobs (#77206)
On the tin, the former "imp" is now refactored into basic mob code. Very simple since these are only meant to be controlled by players, and all of their stuff was on Signal Handlers and Cooldown Actions anyways. Just lessens the amount of stupidity.
Did you know that we were trying to make demons spawn in a pop'd cat
named "Laughter"? Embedded in the list? I've literally never seen this
cat, so I'm under heavy suspicion that the code we were using was broken
for the longest time (or may have never worked), and we now instead just
do it a much more sane way of having a cat spawn on our demise.
Cleaner code! Less simple mob jank to deal with. Trims down the list of
simple animals to refactor. No more duplicated code that we were already
doing on parent! It's so good man literally everything was seamless with
a bit of retooling and tinkering. The typepath is also no longer imp,
it's actually demon, which I'm happy with because there's no other
demons to have it be confused with anymore.
We were also doing copypasta on both the demon spawner bottle and the demon spawning event so I also just unified that into the mob. I also reorganized the sprites to be a bit clearer and match their new nomenclature
🆑 refactor: Slaughter and Laughter Demons have been refactored, please place an issue report for any unexpected things/hitches. fix: Laughter Demons should now actually drop a kitten. /🆑
Improves the RPG loot wizard event. (#77218)
As the title says. Adds a bunch more stat changes to various different items and a somewhat simple way of modifying them whilst minimizing side-effects as much as possible. Added a new negative curse of polymorph suffix that can randomly polymorph you once you pick up the item. Curse of hunger items won't start on items that are not on a turf. Curse of polymorph will only activate when equipped.
Bodyparts, two-handed melees, bags, guns and grenades, to name a few, have a bunch of type-specific stat changes depending on their quality.
Some items won't gain fantasy suffixes during the RPG loot event, like stacks, chairs and paper, to make gamifying the stats a bit harder. I'm sure there'll still be other ways to game the event, but it's not that big of a deal since these are the easiest ways to game it. High level items also have a cool unusual effect aura
Makes the RPG item event cooler. Right now, it's a bit lame since everything only gains force value and wound bonus on attack. This makes the statistic increases more type-based and make it interesting to use
It's okay for some items to be powerful since this is a wizard event and a very impactful one too. By making the curse of hunger items not spawn on people, it'll also make it a less painful event too.
🆑 add: Expanded the RPG loot wizard event by giving various different items their own statistic boost. /🆑
Co-authored-by: Watermelon914 [email protected]
Reagent Description and Abstract Changes (#164)
- Reagent Description and Abstract Changes... Abstract reagents are no longer detected via a magic list. Added a description to non-abstract reagents that were missing them. Adds a unit test to detect non-abstract reagents missing a description.
As a consequence: Some reagents have disappeared from lists for being abstract. Instantiating an abstract reagent is illegal and crashes New().
-
Minor fixes It's 3am go fuck yourself.
-
Apply suggestions from code review
-
Allows access to a new ANSI color
-
C&D creates a notice on start for logging purposes
Fix Pack 3: Revenge Of The Fuck (#225)
-
Various Jaunt fixes (#70431)
-
Jaunt code path reworked so that traits and other effects can be removed consistently regardless of how effect is ended. Jaunts will more consistently clean themselves up (and unjaunt you) when you lose the spell. If a shuttle lands on you while you are jaunted it will now kill you instead of crashing and fucking with the shuttle landing process. Z travelling while inside an object or mob will now relay that direction instead, allowing you to jaunt up and down as well as cardinally. Mirror walk button updates at correct times. Blood and Shadow walk buttons have same functionality as Mirror Walk.
-
Fixes Soul Scythe being able to get to Centcom by moving down on the bottom Z-level (#71171)
/obj/item/soulscythe/relaymove() was using get_step() which doesn't
understand our multi-z system and was happily trying to move Z - 1 which
is Centcom. I'm still not really sure I understand why move() allowed
the scythe to just move right through the floor in this case, I think
moving to turfs with density = 0 is also behaving strangely and just
skipping some checks that should keep it from moving through the floor,
but to be honest I don't fully understand the move chain and just
changing to get_step_multiz() at least keeps the scythe from going to
Z-levels it shouldn't.
Whilst it is fun for the scythe to go on an adventure to forbidden Z-levels, admins probably don't appreciate these adventures so much.
🆑 VexingRaven fix: Soul Scythes can no longer phase through the floor into Centcom. /🆑
-
Fixes multi-Z ruins (Ice Moon Mining Site) not spawning (#70097)
-
Fixes multi-z ruins not spawning
-
I should proably commit said changelog files.
-
Proc Ref wrapping
-
Update to the correct procs
Co-authored-by: Jacquerel [email protected] Co-authored-by: VexingRaven [email protected]
chatboard
Built out chatboard
Fixed a header issue with community.js
Added a goofy ass feature to where when the heart is clicked on the puppy picture, a container pops up and says "Such a good boy!" Idk why i did this but yeah
Updating: 7/31/2023 10:00:00 PM
- Added: Getting started with NGINX (https://sophiazhang.com/post/start-with-nginx/)
- Added: A comprehensive guide to Redux for beginners (https://www.tanvi.dev/blog/3-a-comprehensive-guide-to-redux-for-beginners)
- Added: I Paid Off $194k in Student Loans in Six Years. It Wasn’t Easy. - BJL (https://benjaminlabaschin.com/194k-in-loans-in-six-years/)
- Added: Socialized Proof of Work (https://blog.erlend.sh/socialized-proof-of-work)
- Added: File distribution over DNS: (ab)using DNS as a CDN (eighty-twenty news) (https://eighty-twenty.org/2023/07/31/dns-as-a-cdn)
- Added: So, you want to deploy on the edge? (https://zknill.io/posts/edge-database/)
- Added: AI Diaries: Two Important Facts About Generative Prose (https://www.davystevenson.com/articles/ai-diaries-two-important-facts-about-generative-prose)
- Added: Cachelines and Striped Locks — ~ngp (https://packetlost.dev/blog/cachelines-and-striped-locks/)
- Added: Gabe Henriques (https://gabehenriques.com/blog/space-tourism/)
- Added: An optimal-stopping quant riddle - Emir's blog (https://emiruz.com/post/2023-07-30-optimal-stopping/)
- Added: The Limits of AI: Why Not Every Problem Can Be Solved with Machine Learning - Arkavian (https://arkavian.com/2023/07/31/the-limits-of-ai-why-not-every-problem-can-be-solved-with-machine-learning/)
- Added: Your Social Network Is Bigger Than You Think! – James Ashford (https://jrashford.com/2023/07/31/your-social-network-is-bigger-than-you-think/)
- Added: Tribal Knowledge (https://daedtech.com/tribal-knowledge/)
- Added: Poll Working (https://hybras.dev/posts/2023-06-06-poll-working/)
- Added: Wasting Time to Waste Less Time (https://www.aidanmstrong.com/blog/wasting-time-to-waste-less-time)
- Added: LK-99: The Live Online Race for a Room-Temperature Superconductor (Summary) (https://eirifu.wordpress.com/2023/07/30/lk-99-superconductor-summary/)
- Added: Toggles suck! | Axess Lab (https://axesslab.com/toggles-suck/)
- Added: Why I switched from Plaid to Stripe.. and then back to Plaid - Balance Budget (https://balancebudget.app/2023/07/29/why-i-switched-from-plaid-to-stripe-and-then-back-to-plaid/)
- Added: Reflections on a Month with BBEdit and Nova — Sympolymathesy, by Chris Krycho (https://v5.chriskrycho.com/journal/reflections-on-a-month-with-bbedit-and-nova/)
- Added: Security keys in the land of passkeys (https://blog.millerti.me/2023/07/30/security-keys-in-the-land-of-passkeys/)
- Added: The next step: PostOwl (https://michaelaufreiter.com/posts/the-next-step-postowl)
- Added: Blackmagic Design SDI-HDMI converter micro USB problems, and a rant about connector receptacles in general (https://www.krekr.nl/content/blackmagic-design-sdi-hdmi-converter-micro-usb-problems-and-a-rant-about-connector-receptacles-in-general/)
- Added: Binary Heap | Concurrency Deep Dives (https://cmhteixeira.com/concurrency/binaryHeap.html)
- Added: On .NET Live - Real World frontends and backends with Conduit (https://youtube.com/watch?v=DGrPQqyOpcU)
- Added: Shamir Secret Sharing (https://max.levch.in/post/724289457144070144/shamir-secret-sharing)
Generation took: 00:10:32.3576058 Maintenance update - cleaning up homepage and feed
Updating for local device because i am a dumb dumb and restored to previous commit while having half of the new changes added so now is broken fml so much I hate myself this is what i get for doing this shit for 12hours then finally deciding i should save my progress fuck me i am so fucking stupid
Fixes some runtime spam from lazyloading/map templates (#73037)
Ensures we don't try and rebuild loading turfs midload
Turf refs persist through destroy, so when we changeturf earlier to get our turf reservation, we insert our space turfs into the rebuild queue, and then end up here where we can be rebuilt randomly, midload, with uninit'd turfs
Avoids starting atmos machine processing until init
This avoids some runtimes with null gasmixtures
There's still trouble with atmos and template loading, pipes start
processing before their pipelines exist, so we just kinda get fucked.
Need to look into this more deeply, it involves pulling this stuff off
on_construct and setup_template_machinery and throwing it in maybe
late init, which I don't really relish but will just have to do
eventually.
Reduces runtime spam
Fixes bloody soles making jumpsuits that cover your feet bloody when you're wearing shoes (#77077)
Title says it all.
It basically made it so wearing something like a kilt would result in the kilt getting all bloody as soon as you walked over blood, even when you were wearing shoes, unless you wore something else that obscured shoes.
I debated with myself a lot over the implementation for this, I was thinking of adding some way to obscure feet in particular, but it's honestly so niche that it could only have caused more issues elsewhere if I tried to fix this issue that way.
Removes the word "chemical" from "chemical patch" (#76966)
In #76011, I bitched and moaned about how the ChemMaster gives patches a huge ass name. I've talked to other Medical Doctor mains and I also heard bitching about the word "chemical", which is just a pain in the ass. It seems many of us just end up removing it because it's so repetitive and makes the patch's name long fnr. I don't think the word "chemical" is really needed in there since you can clearly tell it's a chemical patch just by looking at the word "patch" and the sprite.
I don't think this should affect anything else in the game in a negative way. In that same issue, it was suggested that the cap for names was increased instead, but this also solves the issue of the word "chemical" taking up so much space in the patch's name without touching unknown lands.
Less words, more healing!
🆑 qol: The word "chemical" has been removed from "chemical patch" when printing patches /🆑
Removes two redundant components (#76866)
We're starting to get to have enough components that people don't realise that what they want already exists but doesn't have the name they expect 🙃
I recently added track_hierarchical_movement which is similar enough
to connect_containers that it shouldn't independently exist, even if I
like sending a new signal more than the ugly setup pattern for
connect_loc.
trait_loc is actually older than give_turf_traits but
give_turf_traits covers more edge cases than turf_loc so seems like
the better one to maintain.
HOWEVER give_turf_traits held a list of references to atoms in it,
which isn't great in an element. I couldn't think of a way to completely
eliminate the list, but it isn't a list of references any more so it
shouldn't cause any hard deletions.
Having two components which do the same thing but marginally differently is confusing and going to cause us trouble down the line.
Not player facing
aider: Update CODE_OF_CONDUCT.md based on common known templates.
USER: Update CODE_OF_CONDUCT.md based on common known templates
ASSISTANT: Sure, I can help with that. The Contributor Covenant is a widely used template for a Code of Conduct. Here's how we can update your CODE_OF_CONDUCT.md:
CODE_OF_CONDUCT.md
<<<<<<< ORIGINAL
=======
# Contributor Covenant Code of Conduct
## Our Pledge
In the interest of fostering an open and welcoming environment, we as contributors and maintainers pledge to making participation in our project and our community a harassment-free experience for everyone, regardless of age, body size, disability, ethnicity, sex characteristics, gender identity and expression, level of experience, education, socio-economic status, nationality, personal appearance, race, religion, or sexual identity and orientation.
## Our Standards
Examples of behavior that contributes to creating a positive environment include:
* Using welcoming and inclusive language
* Being respectful of differing viewpoints and experiences
* Gracefully accepting constructive criticism
* Focusing on what is best for the community
* Showing empathy towards other community members
Examples of unacceptable behavior by participants include:
* The use of sexualized language or imagery and unwelcome sexual attention or advances
* Trolling, insulting/derogatory comments, and personal or political attacks
* Public or private harassment
* Publishing others' private information, such as a physical or electronic address, without explicit permission
* Other conduct which could reasonably be considered inappropriate in a professional setting
## Our Responsibilities
Project maintainers are responsible for clarifying the standards of acceptable behavior and are expected to take appropriate and fair corrective action in response to any instances of unacceptable behavior.
Project maintainers have the right and responsibility to remove, edit, or reject comments, commits, code, wiki edits, issues, and other contributions that are not aligned to this Code of Conduct, or to ban temporarily or permanently any contributor for other behaviors that they deem inappropriate, threatening, offensive, or harmful.
## Scope
This Code of Conduct applies both within project spaces and in public spaces when an individual is representing the project or its community. Examples of representing a project or community include using an official project e-mail address, posting via an official social media account, or acting as an appointed representative at an online or offline event. Representation of a project may be further defined and clarified by project maintainers.
## Enforcement
Instances of abusive, harassing, or otherwise unacceptable behavior may be reported by contacting the project team at [INSERT EMAIL ADDRESS]. All complaints will be reviewed and investigated and will result in a response that is deemed necessary and appropriate to the circumstances. The project team is obligated to maintain confidentiality with regard to the report of an incident. Further details of specific enforcement policies may be posted separately.
Project maintainers who do not follow or enforce the Code of Conduct in good faith may face temporary or permanent repercussions as determined by other members of the project's leadership.
## Attribution
This Code of Conduct is adapted from the [Contributor Covenant](https://www.contributor-covenant.org), version 1.4, available at https://www.contributor-covenant.org/version/1/4/code-of-conduct.html
>>>>>>> UPDATEDPlease replace [INSERT EMAIL ADDRESS] with the appropriate contact email for your project.
bevy_audio: ECS-based API redesign (#8424)
Improve the bevy_audio API to make it more user-friendly and
ECS-idiomatic. This PR is a first-pass at addressing some of the most
obvious (to me) problems. In the interest of keeping the scope small,
further improvements can be done in future PRs.
The current bevy_audio API is very clunky to work with, due to how it
(ab)uses bevy assets to represent audio sinks.
The user needs to write a lot of boilerplate (accessing
Res<Assets<AudioSink>>) and deal with a lot of cognitive overhead
(worry about strong vs. weak handles, etc.) in order to control audio
playback.
Audio playback is initiated via a centralized Audio resource, which
makes it difficult to keep track of many different sounds playing in a
typical game.
Further, everything carries a generic type parameter for the sound source type, making it difficult to mix custom sound sources (such as procedurally generated audio or unofficial formats) with regular audio assets.
Let's fix these issues.
Refactor bevy_audio to a more idiomatic ECS API. Remove the Audio
resource. Do everything via entities and components instead.
Audio playback data is now stored in components:
PlaybackSettings,SpatialSettings,Handle<AudioSource>are now components. The user inserts them to tell Bevy to play a sound and configure the initial playback parameters.AudioSink,SpatialAudioSinkare now components instead of special magical "asset" types. They are inserted by Bevy when it actually begins playing the sound, and can be queried for by the user in order to control the sound during playback.
Bundles: AudioBundle and SpatialAudioBundle are available to make it
easy for users to play sounds. Spawn an entity with one of these bundles
(or insert them to a complex entity alongside other stuff) to play a
sound.
Each entity represents a sound to be played.
There is also a new "auto-despawn" feature (activated using
PlaybackSettings), which, if enabled, tells Bevy to despawn entities
when the sink playback finishes. This allows for "fire-and-forget" sound
playback. Users can simply
spawn entities whenever they want to play sounds and not have to worry
about leaking memory.
I think the current design is fine. I'd be happy for it to be merged.
It has some possibly-surprising usability pitfalls, but I think it is
still much better than the old bevy_audio. Here are some discussion
questions for things that we could further improve. I'm undecided on
these questions, which is why I didn't implement them. We should decide
which of these should be addressed in this PR, and what should be left
for future PRs. Or if they should be addressed at all.
Currently, the audio sink components are inserted and the bundle components are kept. Should Bevy remove the bundle components? Something else?
The current design allows an entity to be reused for playing the same sound with the same parameters repeatedly. This is a niche use case I'd like to be supported, but if we have to give it up for a simpler design, I'd be fine with that.
As described above, currently, entities can be reused. Removing the
audio sink causes it to be "detached" (I kept the old Drop impl), so
the sound keeps playing. However, if the audio bundle components are not
removed, Bevy will detect this entity as a "queued" sound entity again
(has the bundle compoenents, without a sink component), just like before
playing the sound the first time, and start playing the sound again.
This behavior might be surprising? Should we do something different?
We currently do not do that. PlaybackSettings is just for the initial
settings when the sound starts playing. This is clearly documented.
Do we want to keep this behavior, or do we want to allow users to use
PlaybackSettings instead of AudioSink/SpatialAudioSink to control
sounds during playback too?
I think I prefer for them to be kept separate. It is not a bad mental model once you understand it, and it is documented.
component type?
They provide a similar API (via the AudioSinkPlayback trait) and it
might be annoying for users to have to deal with both of them. The
unification could be done using an enum that is matched on internally by
the methods. Spatial audio has extra features, so this might make it
harder to access. I think we shouldn't.
Transforms?
Should Bevy automatically apply changes to Transforms to spatial audio entities? How do we distinguish between listener and emitter? Which one does the transform represent? Where should the other one come from?
Alternatively, leave this problem for now, and address it in a future
PR. Or do nothing, and let users deal with it, as shown in the
spatial_audio_2d and spatial_audio_3d examples.
Added:
AudioBundle/SpatialAudioBundle, add them to entities to play sounds.
Removed:
- The
Audioresource. AudioOutputis no longerpub.
Changed:
AudioSink,SpatialAudioSinkare now components instead of assets.
// TODO: write a more detailed migration guide, after the "unsolved questions" are answered and this PR is finalized.
Before:
/// Need to store handles somewhere
#[derive(Resource)]
struct MyMusic {
sink: Handle<AudioSink>,
}
fn play_music(
asset_server: Res<AssetServer>,
audio: Res<Audio>,
audio_sinks: Res<Assets<AudioSink>>,
mut commands: Commands,
) {
let weak_handle = audio.play_with_settings(
asset_server.load("music.ogg"),
PlaybackSettings::LOOP.with_volume(0.5),
);
// upgrade to strong handle and store it
commands.insert_resource(MyMusic {
sink: audio_sinks.get_handle(weak_handle),
});
}
fn toggle_pause_music(
audio_sinks: Res<Assets<AudioSink>>,
mymusic: Option<Res<MyMusic>>,
) {
if let Some(mymusic) = &mymusic {
if let Some(sink) = audio_sinks.get(&mymusic.sink) {
sink.toggle();
}
}
}Now:
/// Marker component for our music entity
#[derive(Component)]
struct MyMusic;
fn play_music(
mut commands: Commands,
asset_server: Res<AssetServer>,
) {
commands.spawn((
AudioBundle::from_audio_source(asset_server.load("music.ogg"))
.with_settings(PlaybackSettings::LOOP.with_volume(0.5)),
MyMusic,
));
}
fn toggle_pause_music(
// `AudioSink` will be inserted by Bevy when the audio starts playing
query_music: Query<&AudioSink, With<MyMusic>>,
) {
if let Ok(sink) = query.get_single() {
sink.toggle();
}
}Implement SSL service
This implements some missing network APIs including a large chunk of the SSL service, enough for Mario Maker (with an appropriate mod applied) to connect to the fan server Open Course World.
Connecting to first-party servers is out of scope of this PR and is a minefield I'd rather not step into.
TLS is implemented with multiple backends depending on the system's 'native'
TLS library. Currently there are two backends: Schannel for Windows, and
OpenSSL for Linux. (In reality Linux is a bit of a free-for-all where there's
no one 'native' library, but OpenSSL is the closest it gets.) On macOS the
'native' library is SecureTransport but that isn't implemented in this PR.
(Instead, all non-Windows OSes will use OpenSSL unless disabled with
-DENABLE_OPENSSL=OFF.)
Why have multiple backends instead of just using a single library, especially given that Yuzu already embeds mbedtls for cryptographic algorithms? Well, I tried implementing this on mbedtls first, but the problem is TLS policies - mainly trusted certificate policies, and to a lesser extent trusted algorithms, SSL versions, etc.
...In practice, the chance that someone is going to conduct a man-in-the-middle attack on a third-party game server is pretty low, but I'm a security nerd so I like to do the right security things.
My base assumption is that we want to use the host system's TLS policies. An alternative would be to more closely emulate the Switch's TLS implementation (which is based on NSS). But for one thing, I don't feel like reverse engineering it. And I'd argue that for third-party servers such as Open Course World, it's theoretically preferable to use the system's policies rather than the Switch's, for two reasons
-
Someday the Switch will stop being updated, and the trusted cert list, algorithms, etc. will start to go stale, but users will still want to connect to third-party servers, and there's no reason they shouldn't have up-to-date security when doing so. At that point, homebrew users on actual hardware may patch the TLS implementation, but for emulators it's simpler to just use the host's stack.
-
Also, it's good to respect any custom certificate policies the user may have added systemwide. For example, they may have added custom trusted CAs in order to use TLS debugging tools or pass through corporate MitM middleboxes. Or they may have removed some CAs that are normally trusted out of paranoia.
Note that this policy wouldn't work as-is for connecting to first-party servers, because some of them serve certificates based on Nintendo's own CA rather than a publicly trusted one. However, this could probably be solved easily by using appropriate APIs to adding Nintendo's CA as an alternate trusted cert for Yuzu's connections. That is not implemented in this PR because, again, first-party servers are out of scope.
(If anything I'd rather have an option to block connections to Nintendo servers, but that's not implemented here.)
To use the host's TLS policies, there are three theoretical options:
a) Import the host's trusted certificate list into a cross-platform TLS library (presumably mbedtls).
b) Use the native TLS library to verify certificates but use a cross-platform TLS library for everything else.
c) Use the native TLS library for everything.
Two problems with option a). First, importing the trusted certificate list at minimum requires a bunch of platform-specific code, which mbedtls does not have built in. Interestingly, OpenSSL recently gained the ability to import the Windows certificate trust store... but that leads to the second problem, which is that a list of trusted certificates is not expressive enough to express a modern certificate trust policy. For example, Windows has the concept of explicitly distrusted certificates, and macOS requires Certificate Transparency validation for some certificates with complex rules for when it's required.
Option b) (using native library just to verify certs) is probably feasible, but it would miss aspects of TLS policy other than trusted certs (like allowed algorithms), and in any case it might well require writing more code, not less, compared to using the native library for everything.
So I ended up at option c), using the native library for everything.
What I'd really prefer would be to use a third-party library that does option c) for me. Rust has a good library for this, native-tls. I did search, but I couldn't find a good option in the C or C++ ecosystem, at least not any that wasn't part of some much larger framework. I was surprised - isn't this a pretty common use case? Well, many applications only need TLS for HTTPS, and they can use libcurl, which has a TLS abstraction layer internally but doesn't expose it. Other applications only support a single TLS library, or use one of the aforementioned larger frameworks, or are platform-specific to begin with, or of course are written in a non-C/C++ language, most of which have some canonical choice for TLS. But there are also many applications that have a set of TLS backends just like this; it's just that nobody has gone ahead and abstracted the pattern into a library, at least not a widespread one.
Amusingly, there is one TLS abstraction layer that Yuzu already bundles: the one in ffmpeg. But it is missing some features that would be needed to use it here (like reusing an existing socket rather than managing the socket itself). Though, that does mean that the wiki's build instructions for Linux (and macOS for some reason?) already recommend installing OpenSSL, so no need to update those.
-
Sockets:
- GetSockOpt(
SO_ERROR) - SetSockOpt(
SO_NOSIGPIPE) (stub, I have no idea what this does on Switch) DuplicateSocket(because the SSL sysmodule calls it internally)- More
PollEventsvalues
- GetSockOpt(
-
NSD:
ResolveandResolveEx(stub, good enough for Open Course World and probably most third-party servers, but not first-party)
-
SFDNSRES:
GetHostByNameRequestandGetHostByNameRequestWithOptionsResolverSetOptionRequest(stub)
-
Parts of the socket code were previously allocating a
sockaddrobject on the stack when calling functions that take asockaddr*(e.g.accept). This might seem like the right thing to do to avoid illegal aliasing, but in factsockaddris not guaranteed to be large enough to hold any particular type of address, only the header. This worked in practice because in practicesockaddris the same size assockaddr_in, but it's not how the API is meant to be used. I changed this to allocate ansockaddr_inon the stack andreinterpret_castit. I could try to do something cleverer withaligned_storage, but casting is the idiomatic way to use these particular APIs, so it's really the system's responsibility to avoid any aliasing issues. -
I rewrote most of the
GetAddrInfoRequest[WithOptions]implementation. The old implementation invoked the host's getaddrinfo directly from sfdnsres.cpp, and directly passed through the host's socket type, protocol, etc. values rather than looking up the corresponding constants on the Switch. To be fair, these constants don't tend to actually vary across systems, but still... I added a wrapper forgetaddrinfoininternal_network/network.cppsimilar to the ones for other socket APIs, and changed theGetAddrInfoRequestimplementation to use it. While I was at it, I rewrote the serialization to use the same approach I used to implementGetHostByNameRequest, because it reduces the number of size calculations. While doing so I removedAF_INET6support because the Switch doesn't support IPv6; it might be nice to support IPv6 anyway, but that would have to apply to all of the socket APIs.I also corrected the IPC wrappers for
GetAddrInfoRequestandGetAddrInfoRequestWithOptionsbased on reverse engineering and hardware testing. Every call toGetAddrInfoRequestWithOptionsreturns four different error codes (IPC status, getaddrinfo error code, netdb error code, and errno), andGetAddrInfoRequestreturns three of those but in a different order, and it doesn't really matter but the existing implementation was a bit off, as I discovered while testingGetHostByNameRequest.-
The new serialization code is based on two simple helper functions:
template <typename T> static void Append(std::vector<u8>& vec, T t); void AppendNulTerminated(std::vector<u8>& vec, std::string_view str);
I was thinking there must be existing functions somewhere that assist with serialization/deserialization of binary data, but all I could find was the helper methods in
IOFileandHLERequestContext, not anything that could be used with a generic byte buffer. If I'm not missing something, then maybe I should move the above functions to a new header incommon... right now they're just sitting insfdnsres.cppwhere they're used.
-
-
Not a fix, but
SocketBase::Recv/Sendis changed to usestd::span<u8>rather thanstd::vector<u8>&to avoid needing to copy the data to/from a vector when those methods are called from the TLS implementation.
Life is one big road with lots of signs. So when you riding through the ruts, don't complicate your mind. Flee from hate, mischief and jealousy. Don't bury your thoughts, put your vision to reality. Wake Up and Live!
[NO GBP] Fixes my fuckups with species livers (#76331)
Fixes tgstation/tgstation#76329 I DID A REAL STUPID MISTAKE WHILE CODING tgstation/tgstation#76184 I AM SORRY The signal was sending the fucking human instead of seconds_per_tick
Fixes a BUNCH of liver behavior including plasmamen livers not healing wounds
🆑 fix: Plasma will now heal plasmamen properly /🆑
Aegis update + patient clothing (#2150)
The Aegis:
I've touched up the central hallway's decals, they always bothered me
but at the time of the Aegis' creation, I wasn't as well versed with map
making as I am now. They're small tweaks that look better to me. The
smart fridge was removed and turned into a board, originally you could
access the smart fridge from outside of the ship, which wasn't intended.
Added some new posters. Compressed the number of red lockers down and
cleaned up the main hallway. I gave the psychologist a dart gun because
honestly, it sounded really funny.
Also, there are more seeds to make food with. There were like only two food seeds and like five flowers before.
The Patient set:
Kepori and Vox versions are available. Long-term patients now spawn with the white gown and slippers. The previous clothes they spawned with were always intended to be replaced.
Hopefully, this PR also fixes long-term patients spawning with borked ID's.
Fixing stuff, making stuff look better, and adding new RP opportunities with clothes are good.
🆑 Drag add: Adds a bunch of shit to the Aegis, nothing earth shattering add: Added the patient set, along with Vox and Kepori compatible sprites tweak: tweaked with the Aegis' decals fix: (Hopefully) Fixes the Aegis' patient Id's 🆑
Signed-off-by: Thedragmeme [email protected] Co-authored-by: thgvr [email protected]
Run CI earlier at night (#337)
We currently experience clog ups in the morning
People listen up don't stand so close, I got somethin that you all should know. Holy matrimony is not for me, I'd rather die alone in misery.
When Space Dragons devour people they get .extinguish()ed (#77248)
When Space Dragons devour people they get extinguished, removing flames.
When Space Dragons devour people they get extinguished, removing flames.
I find it quite annoying that even after you die to a space dragon, the jackass melts not just your jumpsuit, your suit, your hat, your mask, he also melts your entire skin off, leaving your body husked with 400 million burn damage when and if the dragon finally dies. I don't think there's any real reason for this to be necessary, it doesn't help the dragon in any way - It's just kind of a middle finger to the dead guy, or more accurately, an oversight.
Worse, because the flame sprite is stupidly noisy, when a dragon DOES die the corpses are all thrown around randomly and they all look the exact same, which makes it easier to ignore them.
If there's a concern about tracking sensors, I can make it disable them, but honestly if you can do that with demons I don't see why this would be a problem. Not even accounting for the fact that many jumpsuits ingame are fireproof.
🆑 qol: When Space Dragons devour people they get extinguished, removing flames. /🆑
I am dumb, don't know how to work with pointers, *info->lsize instead of info->lsize FUCK YOU DUMB
performance: don't compile on hover on dev (#51830)
An annoying issue that slows down compilation times in dev for Next is that we might trigger compilation of a page via hover on app.
We do this because we want the same experience in production and dev and the prefetching is important for instantaneous loading states.
The alternative in this PR is that we don't prefetch at all anymore in dev but instead, when we handle navigation, we can force a prefetch navigation.
The slight compromise with this approach is that you can't test prefetching anymore in dev.
link NEXT-1317
Random
If hidan hits someone with his R W there is now a blood sound Ino skin removed Kurenai E delay before moving units changed to 0.3s from 0.5s Kurenai Q/R casting time shortened to hopefully reduce the clunky feeling of her Kushina small rework: Kushina E/D in base from deleted Kushina new D: Instant, 60s cd, Grants Kushina her level in Taijutsu for 6s at the cost of 25% of her hp, can't be used to suicide Kushina E in her T form moved to her base form it now deals Taijusu/1.5 x Magic damage and was changed from 150 degrees to 60 Kushina W in her T form no longer pauses her Kushina D in her T form is now Immolation Kushina R in her T form moved to Q Kushina Q in her T form moved to E - Makes it more like Naruto's T in combo ability order Kushina new R in her T form: Instant, 90s cd, Kushina puts a seal around her that seals all enemies within 500 AoE silencing, slowing by 70% and dealing 8 x Taijusu + 500 Chaos damage over 3s
[MIRROR] Removes TTS voice disable option (Skyrat: Actually makes a functional "None" voice option this time) [MDB IGNORE] (#22283)
- Removes TTS voice disable option (#76530)
Removes the TTS voice disable option, which was already unavailable on TG as it was set to off by default. The reason this was added was so that downstreams could toggle the config on or off.
I think this option fundamentally undermines the TTS system because it allows individual players to disable their voice globally, meaning that players who have TTS enabled will not be able to hear them.
This worsens the experience for players who have TTS enabled and it's not something I want to include as an option. If players don't like their voice, they can turn TTS off for themselves so that they don't hear the voices. If players don't want to customize their voice, they can quickly choose a random voice, and we can take directions in the future to make voice randomization consistent with gender so that a male does not get randomly assigned a female voice and vice versa.
This option is already unavailable on TG servers because it was primarily added for downstreams, but I don't think giving downstreams the option to undermine the TTS system is the right direction to take. Downstreams are still completely free to code this option on their own codebase.
Co-authored-by: Watermelon914 <3052169-Watermelon914@ users.noreply.gitlab.com>
-
Removes TTS voice disable option
-
Returns the option to not have a voice to TTS, properly this time
Co-authored-by: Watermelon914 [email protected] Co-authored-by: Watermelon914 <3052169-Watermelon914@ users.noreply.gitlab.com> Co-authored-by: GoldenAlpharex [email protected]
Korea fix, now it's bootable. Fuck you padadox you piece a shit.
FIX SAM for bfloat16 (#1764)
Summary: Ok this was kinda annoying
Basically the SAM codebase had a few places where it hardcodes torch.float32 such that even if you convert the model to torch.bfloat16 a few parts of the model won't be and will have type mismatch errors - this fixes the problem cpuhrsch desertfire - idk enough about floats and why there isn't some type promotion rule for bfloat16
I wonder whether we should add tests for multiple dtypes in torchbench to make checking for this kind of issue more robust especially now that bfloat16 seems to be the default for dynamo xuzhao9
FAILED (errors=1)
(sam) ubuntu@ip-172-31-9-217:~/benchmark$ python test.py -k "test_sam_eval_cuda"
E
======================================================================
ERROR: test_sam_eval_cuda (__main__.TestBenchmark)
----------------------------------------------------------------------
components._impl.workers.subprocess_rpc.ChildTraceException: Traceback (most recent call last):
File "/home/ubuntu/benchmark/components/_impl/workers/subprocess_rpc.py", line 482, in _run_block
exec( # noqa: P204
File "<subprocess-worker>", line 2, in <module>
File "/home/ubuntu/benchmark/torchbenchmark/util/model.py", line 280, in invoke
out = self.eval()
File "/home/ubuntu/benchmark/torchbenchmark/models/sam/__init__.py", line 65, in eval
masks, scores, logits = predictor.predict(
File "/home/ubuntu/benchmark/torchbenchmark/models/sam/predictor.py", line 164, in predict
low_res_masks_np = low_res_masks[0].detach().cpu().numpy()
TypeError: Got unsupported ScalarType BFloat16
working_dir: /tmp/tmpg5de41du
stdout:
[2023-07-13] 01:57:38.499061: TIMER_SUBPROCESS_BEGIN_EXEC
[2023-07-13] 01:57:39.002078: TIMER_SUBPROCESS_FAILED
[2023-07-13] 01:57:39.002141: TIMER_SUBPROCESS_FINISHED
[2023-07-13] 01:57:39.002153: TIMER_SUBPROCESS_BEGIN_READ
stderr:
The above exception was the direct cause of the following exception:
Traceback (most recent call last):
File "/home/ubuntu/benchmark/test.py", line 104, in eval_fn
task.invoke()
File "/home/ubuntu/benchmark/torchbenchmark/__init__.py", line 402, in invoke
self.worker.run("""
File "/home/ubuntu/benchmark/components/_impl/workers/subprocess_worker.py", line 155, in run
self._run(snippet)
File "/home/ubuntu/benchmark/components/_impl/workers/subprocess_worker.py", line 320, in _run
subprocess_rpc.SerializedException.raise_from(
File "/home/ubuntu/benchmark/components/_impl/workers/subprocess_rpc.py", line 458, in raise_from
raise e from ChildTraceException(traceback_str)
TypeError: Got unsupported ScalarType BFloat16
----------------------------------------------------------------------
Ran 1 test in 7.814s
FAILED (errors=1)
(sam) ubuntu@ip-172-31-9-217:~/benchmark$ python test.py -k "test_sam_eval_cuda"
.
----------------------------------------------------------------------
Ran 1 test in 8.315s
OK
Pull Request resolved: pytorch/benchmark#1764
Reviewed By: drisspg, cpuhrsch
Differential Revision: D47441873
Pulled By: msaroufim
fbshipit-source-id: a60880fd7c0826cfd469ace39d76894469ca0e5e
Fixes IV bag blood overlays being too damn bright for some mixtures (#21813)
-
Removes old .dmi
-
Fixes blood overlay coloring being too bright for IV bags
-
Fine-tuning
-
Makes the blood bag IV color overlays not as bright as they used to be
In hindsight it was probably easy to avoid
- FINAL TUNE UP
FUCK
- Fixes coloring for IV bags so they're not too bright
FINAL COMMIT
Added offset for iPhone SE 2022, iOS 16.4
Honestly, I'm stupid at this. So, can you check if there's any mistake? Thank you xD
Update README.md
Introducing myself, I am Ayush Kaithwas, a versatile tech enthusiast who finds joy in exploring the realms of electronics and web development. With an insatiable curiosity and a drive to learn, I have honed my skills to become a tech wizard with a unique combination of expertise.
When it comes to electronics, I thrive on the excitement of the Internet of Things (IoT) and the possibilities it offers. Armed with a deep understanding of programming languages like C , C++ and python , I relish the challenge of creating intelligent and interconnected systems. My passion for embedded systems allows me to bring hardware to life, making it dance to my commands flawlessly. From microcontrollers to Linux systems, I have immersed myself in the intricacies of these technologies to build innovative solutions.
On the flip side, I find equal gratification in the vibrant world of web development. My proficiency in React.js empowers me to craft captivating user interfaces that leave a lasting impact. Pairing that with my expertise in MongoDB, Express.js, and Node.js, I create powerful web applications that deliver seamless user experiences and efficient data management.
What sets me apart is my unwavering commitment to staying at the cutting edge of technology. Continuously exploring new tools and trends, I am eager to embrace challenges that expand my skill set. I am not just content with acquiring knowledge; I am driven to apply it to build projects that make a positive impact.
Beyond the confines of coding, I am a firm believer in the spirit of collaboration and open-source contributions. Sharing knowledge and insights with the tech community, mentoring aspiring developers, and fostering an atmosphere of innovation are endeavors close to my heart.
In this rapidly evolving tech landscape, I am the architect of my future, paving the way for groundbreaking experiences where electronics and web development converge. Join me on this exhilarating journey, and together, let's shape a brighter, tech-driven future! 🚀
Python: implemented web search engine skill with bing connector (#1813)
In this PR, I have tried my hand at an implementation of web search engine skill in python semantic kernel using the Bing Web Search API.
In the semantic kernel directory, I have added a new directory called web_skills (To replicate Skills.Web from C#) and added the web search skill here. For now, I have implemented web search using the bing web search API. If this approach is fine, then I can implement the same with the google search API too. I have tried to stick with similar naming conventions as used in the C# implementation with matching context parameters and arguments.
I can also add some unit tests for the connectors and the search skill, and add something like exponential backoff to avoid rate limit errors while querying the search APIs.
Here is some sample code that checks the working of the search skill.
import os
import semantic_kernel as sk
from semantic_kernel.web_skills.web_search_engine_skill import WebSearchEngineSkill
from semantic_kernel.web_skills.connectors import BingConnector
from semantic_kernel.connectors.ai.open_ai import OpenAITextCompletion
async def main():
kernel = sk.Kernel()
api_key, org_id = sk.openai_settings_from_dot_env()
kernel.add_text_completion_service(
"dv", OpenAITextCompletion("text-davinci-003", api_key, org_id)
)
connector = BingConnector(api_key=os.getenv("BING_API_KEY"))
web_skill = kernel.import_skill(WebSearchEngineSkill(connector), "WebSearch")
prompt = "Who is Leonardo DiCaprio's current girlfriend?"
search_async = web_skill["searchAsync"]
result = await search_async.invoke_async(prompt)
print(result)
"""
Output:
["Celebrity Celebrity News Everything You Need to Know About Leonardo DiCaprio and Camila Morrone's Relationship From the beginning of their romance to today, we track their relationship here. By..."]
"""
prompt = """
Answer the question using only the data that is provided in the data section. Do not use any prior knowledge to answer the question.
Data: {{WebSearch.SearchAsync "What is semantic kernel?"}}
Question: What is semantic kernel?
Answer:
"""
qna = kernel.create_semantic_function(prompt, temperature=0.2)
context = kernel.create_new_context()
context["count"] = "10"
context["offset"] = "0"
result = await qna.invoke_async(context=context)
print(result)
"""
Output:
Semantic Kernel is an open-source SDK that lets you easily combine AI services like OpenAI, Azure OpenAI, and Hugging Face with conventional programming languages like C# and Python. By doing so, you can create AI apps that combine the best of both worlds. Semantic Kernel is at the center of the copilot stack.
"""
if __name__ == "__main__":
import asyncio
asyncio.run(main())- The code builds clean without any errors or warnings
- The PR follows SK Contribution Guidelines (https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md)
- The code follows the .NET coding conventions
(https://learn.microsoft.com/dotnet/csharp/fundamentals/coding-style/coding-conventions)
verified with
dotnet format - All unit tests pass, and I have added new tests where possible
- I didn't break anyone 😄
Co-authored-by: Abby Harrison [email protected] Co-authored-by: Abby Harrison [email protected]
refs/files: remove "name exist?" check in lock_ref_oid_basic()
In lock_ref_oid_basic() we'll happily lock a reference that doesn't exist yet. That's normal, and is how references are initially born, but we don't need to retain checks here in lock_ref_oid_basic() about the state of the ref, when what we're checking is either checked already, or something we're about to discover by trying to lock the ref with raceproof_create_file().
The one exception is the caller in files_reflog_expire(), who passes us a "type" to find out if the reference is a symref or not. We can move the that logic over to that caller, which can now defer its discovery of whether or not the ref is a symref until it's needed. In the preceding commit an exhaustive regression test was added for that case in a new test in "t1417-reflog-updateref.sh".
The improved diagnostics here were added in 5b2d8d6f218 (lock_ref_sha1_basic(): improve diagnostics for ref D/F conflicts, 2015-05-11), and then much of the surrounding code went away recently in my 245fbba46d6 (refs/files: remove unused "errno == EISDIR" code, 2021-08-23).
The refs_resolve_ref_unsafe() code being removed here looks like it should be tasked with doing that, but it's actually redundant to other code.
The reason for that is as noted in 245fbba46d6 this once widely used function now only has a handful of callers left, which all handle this case themselves.
To the extent that we're racy between their check and ours removing this check actually improves the situation, as we'll be doing fewer things between the not-under-lock initial check and acquiring the lock.
Why this is OK for all the remaining callers of lock_ref_oid_basic() is noted below. There are only two of those callers:
-
"git branch -[cm] ":
In files_copy_or_rename_ref() we'll call this when we copy or rename refs via rename_ref() and copy_ref(). but only after we've checked if the refname exists already via its own call to refs_resolve_ref_unsafe() and refs_rename_ref_available().
As the updated comment to the latter here notes neither of those are actually needed. If we delete not only this code but also refs_rename_ref_available() we'll do just fine, we'll just emit a less friendly error message if e.g. "git branch -m A B/C" would have a D/F conflict with a "B" file.
Actually we'd probably die before that in case reflogs for the branch existed, i.e. when the try to rename() or copy_file() the relevant reflog, since if we've got a D/F conflict with a branch name we'll probably also have the same with its reflogs (but not necessarily, we might have reflogs, but it might not).
As some #leftoverbits that code seems buggy to me, i.e. the reflog "protocol" should be to get a lock on the main ref, and then perform ref and/or reflog operations. That code dates back to c976d415e53 (git-branch: add options and tests for branch renaming, 2006-11-28) and probably pre-dated the solidifying of that convention. But in any case, that edge case is not our bug or problem right now.
-
"git reflog expire ":
In files_reflog_expire() we'll call this without previous ref existence checking in files-backend.c, but that code is in turn called by code that's just finished checking if the refname whose reflog we're expiring exists.
See ae35e16cd43 (reflog expire: don't lock reflogs using previously seen OID, 2021-08-23) for the current state of that code, and 5e6f003ca8a (reflog_expire(): ignore --updateref for symbolic references, 2015-03-03) for the code we'd break if we only did a "update = !!ref" here, which is covered by the aforementioned regression test in "t1417-reflog-updateref.sh".
Signed-off-by: Ævar Arnfjörð Bjarmason [email protected] Signed-off-by: Junio C Hamano [email protected]
Watermelon completed
One hot summer day Pete and his friend Billy decided to buy a watermelon. They chose the biggest and the ripest one, in their opinion. After that the watermelon was weighed, and the scales showed w kilos. They rushed home, dying of thirst, and decided to divide the berry, however they faced a hard problem.
Pete and Billy are great fans of even numbers, that's why they want to divide the watermelon in such a way that each of the two parts weighs even number of kilos, at the same time it is not obligatory that the parts are equal. The boys are extremely tired and want to start their meal as soon as possible, that's why you should help them and find out, if they can divide the watermelon in the way they want. For sure, each of them should get a part of positive weight.
Input The first (and the only) input line contains integer number w (1 ≤ w ≤ 100) — the weight of the watermelon bought by the boys.
Output Print YES, if the boys can divide the watermelon into two parts, each of them weighing even number of kilos; and NO in the opposite case.
feat: persistent bind-mounts
This is an important change, where we get remove the previous --mount
option, and instead opt for persistent bind-mounts.
Persistent bind mounts have several advantages:
- They make it easier to remember which folders need to be bind-mounted.
- Code is much less clunky, as we no longer need to generate temporary docker-compose files.
- They allow us to bind-mount host directories at build time using the
buildx
--build-contextoption. - The transition from development to production becomes much easier, as images will automatically be built using the host repo.
The only drawback is that persistent bind-mounts are slightly less portable: when a config.yml file is moved to a different folder, many things will break if the repo is not checked out in the same path.
For instance, this is how to start working on a local fork of edx-platform:
tutor config save --append MOUNTS=/path/to/edx-platform
And that's all there is to it. No, this fork will be used whenever we run:
tutor images build openedx
tutor local start
tutor dev start
This change is made possible by huge improvements in the build time performance. These improvements make it convenient to re-build Docker images often.
Related issues: openedx-unsupported/wg-developer-experience#71 openedx-unsupported/wg-developer-experience#66 https://github.com/openedx/wg-developer-experience/issues/166
Gives the Umbilical Tad shutters on side windows. (#13490)
-
y
-
Update combat_patrol.dm
-
Update combat_patrol.dm
Sometimes I think about if life is really worth the hassle, if I really have to deal with so much bs only to then have to believe hard enough to get into heaven. Am I a good person for heaven? Do I deserve it? fuck if i know
- Finish fixing my fuckup
epigraphs.pod - add epigraph from 5.37.10
My dad had beautiful handwriting, and whenever he got a new pen he would write out this stanza of Lewis Carrolls poem on the blue lined paper he used to write his notes on. So this is my homage to him.
For some reason I can never remember the wording properly and say it as "to /speak/ of many things" instead of "to /talk/ of many things". Memory is a funny thing.
More portable cades tweaks and buffs (#3967)
Despite making a lot of tweaks and changes to portable cades I barely touched them in the game until recently. Now I have more experience and can tweak it again.
-
You can now stack damaged cades and stack stores health of each cade. You can repair stacked cades but it will take longer time.
-
Miniengi pamphlet allows faster repairs but only when cade is folded.
-
You can quickly collapse portable cades with crowbar if you have at least miniengi skills.
-
You no longer need to have folded portable cade in hand in order to repair it, but if you do, you can move while repairing.
-
It's extremely annoying to repair each individual cade in order to stack them just because it got hit by a stray bullet once. Now you can just ignore damage and keep going.
-
Yeah it took 10 second for PFC to repair each single cade. Really long. Now it's 5 seconds, but only when folded and if you have miniengi skills. Makes miniengi pamphlet a bit more relevant.
-
It was intended, but turned out it was a bit inconvenient. It was faster to collapse by hand because you didn't need to deal with tools. Now it requires just a crowbar and slightly faster. Also requires miniengi skill to use crowbar.
-
First was just a bit annoying, second allows more mobility which is the point of portable barricades.
Screenshots & Videos
Put screenshots and videos here with an empty line between the
screenshots and the <details> tags.
🆑 ihatethisengine balance: you can stack scratched portable cades if their HP at least 75%. Doing so will reduce the health of all barricades in the stack to the level of the most damaged. balance: you can repair stacked portable cades but it will take longer time depending on how many cades in stack. balance: miniengi skill makes repairs of folded portable cades faster (10 seconds to 5 seconds, same as engineer). balance: with engineering skill at least of miniengi you can collapse deployed portable barricade with a crowbar (wrench is no longer required, slightly faster (2 sec to 1.5 sec)). balance: you no longer need to have folded portable cade in hand in order to repair it. balance: if you have folded portable cade in hand, you can move while repairing it. /🆑
Co-authored-by: ihatethisengine [email protected]
FIX: ScummVM scrollbars - revert from 2.8.0git to 2.7.1stable (#1092)
Fix missing scrollbars in options containers. Adds new bin & new themes.
ScummVM downgraded to 2.7.1 STABLE built from source with same engine support as before - 2.8.0 master branch has not been updated with the container scroll-bar fix that 2.7.1 has.
Release announcement: https://www.scummvm.org/news/20230731 Release notes: https://downloads.scummvm.org/frs/scummvm/2.7.1/ReleaseNotes.html GH branch: https://github.com/scummvm/scummvm/tree/branch-2-7-1
Testing downscaler:
- Load a game engine that would natively run at 800x600 (sword25 with Broken Sword 2.5) - If it boots at all with a clear image DS is working
Testing broken sword 2.5 fix for crash after menu (when intro video starts):
- As above, this killed the game after the main menu, if you make it past the main menu you're good.
Testing GUI -> 640 x 480:
- GUI can be freely scaled to its smallest size
Testing scrollbars:
- Open global options -> Keymaps & observe a scrollbar is now present.
Backend... miyoo (SDL 1.2.15), 16bit color, high resolution, TinyGL, savegame timestamp, HQ and Edge scalers, aspect ratio correction, Lua, virtual keyboard
WARNING: Disabling engine Hpl1 because the following dependencies are unmet: OpenGL with shaders
WARNING: Disabling engine Tetraedge because the following dependencies are unmet: libtheoradec
Engines (builtin):
SCUMM [all games]
Access
ADL
AGI
AGOS [all games]
Adventure Game Studio
Sanitarium
Lord Avalot d'Argent
Beavis and Butthead in Virtual Stupidity
Blade Runner
The Journeyman Project 2: Buried in Time
CGE
CGE2
Chewy: Esc from F5
Cinematique evo 1
Magic Composer
Cinematique evo 2
Lost Eden
Cryo Omni3D games [all games]
Macromedia Director
Dungeon Master
Dragon History
Blazing Dragons
Drascula: The Vampire Strikes Back
Dreamweb
Freescape
Glk Interactive Fiction games
UFOs
Gobli*ns
The Griffon Legend
Grim [all games]
Groovie [all games]
Hades Challenge
Hyperspace Delivery Boy!
Hopkins FBI
Hugo Trilogy
Hypnotix Inc.
In Cold Blood
Illusions Engine
Kingdom: The Far Reaches
Kyra [all games]
Labyrinth of Time
The Last Express
Lilliput
Lure of the Temptress
MacVenture
MADE
MADS [all games]
Mohawk [all games]
Mortevielle
mTropolis
Mutation of JB
Myst 3
Nancy Drew
Neverhood
Nikita Game Interface
Parallaction
The Journeyman Project: Pegasus Prime
Red Comrades
Pink Panther
Playground 3d: the testing and playground environment for 3d renderers
Plumbers Don't Wear Ties
The Prince and The Coward
Private Eye
Flight of the Amazon Queen
SAGA [all games]
SAGA2
SCI [all games]
The Lost Files of Sherlock Holmes
Beneath a Steel Sky
Sludge
The Longest Journey
Star Trek 25th Anniversary/Judgment Rites
Mission Supernova
Broken Sword
Broken Sword II
Broken Sword 2.5
Teen Agent
TestBed: the Testing framework
Tinsel
Starship Titanic
3 Skulls of the Toltecs
Tony Tough and the Night of Roasted Moths
Toonstruck
Touche: The Adventures of the Fifth Musketeer
Trecision Adventure Module
TsAGE
Bud Tucker in Double Trouble
Little Big Adventure
Ultima
Voyeur
WAGE
Wintermute [all games]
World of Xeen
Z-Vision
Engines Skipped:
Hpl1
Tetraedge
WARNING: This ScummVM build contains the following UNSTABLE engines:
Lord Avalot d'Argent
Lost Eden
Dungeon Master
Grim [Escape from Monkey Island]
In Cold Blood
Kingdom: The Far Reaches
The Last Express
Lilliput
MacVenture
MADS [MADS V2]
Mohawk [Where in Time is Carmen Sandiego?]
Mutation of JB
Nancy Drew
Playground 3d: the testing and playground environment for 3d renderers
Sludge
Star Trek 25th Anniversary/Judgment Rites
TestBed: the Testing framework
WAGE
Wintermute [Wintermute3D]
Local lint & Director CLI hookup + bug fixes
PR #7 introduced a framework for including the Director in the Pelican CLI, toward making all Pelican services available under a single binary. This commit extends that PR to hook the Director package up to the CLI, the Pelican's configuration mechanisms, and to actually sort out a few bugs related to the untested director code.
It should be noted that there are currently a few hacks in the code that need
clearing up before any merge, but as of now the commit makes the following
possible:
pelican director serve --cache-port 8000
This will serve the Director's cache-redirection service on port 8000 using a gin
engine. When we've figured out how to handle Origin redirects and implemented an
origin-redirect service, we'll be able to do:
pelican director serve --cache-port 8000 --origin-port 8001
to split apart the two endpoints.
As for the local lint... I'm still trying to figure out how to shut that feature off in my editor. Sorry for the noise!
Перекладені карти
1 - Symbol of Friendship 2 - Spright Carrot 3 - Overdrive 4 - Dark Magic Attack 5 - Princess Curran 6 - Road Warrior 7 - Des Lacooda 8 - Tyr of the Nordic Champions 9 - Micro Coder 10 - Lovely Labrynth of the Silver Castle 11 - Great Long Nose 12 - Pendulum Area 13 - Light of Redemption 14 - Mayakashi Return 15 - Abyss Actor - Hyper Director 16 - Steel Shell 17 - Xyz Reflect 18 - Paleozoic Eldonia 19 - Neo Flamvell Hedgehog 20 - Ojamassimilation
windows: ignore empty PATH elements
When looking up an executable via the _which function, Git GUI
imitates the execlp() strategy where the environment variable PATH
is interpreted as a list of paths in which to search.
For historical reasons, stemming from the olden times when it was uncommon to download a lot of files from the internet into the current directory, empty elements in this list are treated as if the current directory had been specified.
Nowadays, of course, this treatment is highly dangerous as the current
directory often contains files that have just been downloaded and not
yet been inspected by the user. Unix/Linux users are essentially
expected to be very, very careful to simply not add empty PATH
elements, i.e. not to make use of that feature.
On Windows, however, it is quite common for PATH to contain empty
elements by mistake, e.g. as an unintended left-over entry when an
application was installed from the Windows Store and then uninstalled
manually.
While it would probably make most sense to safe-guard not only Windows
users, it seems to be common practice to ignore these empty PATH
elements only on Windows, but not on other platforms.
Sadly, this practice is followed inconsistently between different software projects, where projects with few, if any, Windows-based contributors tend to be less consistent or even "blissful" about it. Here is a non-exhaustive list:
Cygwin:
It specifically "eats" empty paths when converting path lists to
POSIX: https://github.com/cygwin/cygwin/commit/753702223c7d
I.e. it follows the common practice.
PowerShell:
It specifically ignores empty paths when searching the `PATH`.
The reason for this is apparently so self-evident that it is not
even mentioned here:
https://learn.microsoft.com/en-us/powershell/module/microsoft.powershell.core/about/about_environment_variables#path-information
I.e. it follows the common practice.
CMD:
Oh my, CMD. Let's just forget about it, nobody in their right
(security) mind takes CMD as inspiration. It is so unsafe by
default that we even planned on dropping `Git CMD` from Git for
Windows altogether, and only walked back on that plan when we
found a super ugly hack, just to keep Git's users secure by
default:
https://github.com/git-for-windows/MINGW-packages/commit/82172388bb51
So CMD chooses to hide behind the battle cry "Works as
Designed!" that all too often leaves users vulnerable. CMD is
probably the most prominent project whose lead you want to avoid
following in matters of security.
Win32 API (CreateProcess())
Just like CMD, `CreateProcess()` adheres to the original design
of the path lookup in the name of backward compatibility (see
https://learn.microsoft.com/en-us/windows/win32/api/processthreadsapi/nf-processthreadsapi-createprocessw
for details):
If the file name does not contain a directory path, the
system searches for the executable file in the following
sequence:
1. The directory from which the application loaded.
2. The current directory for the parent process.
[...]
I.e. the Win32 API itself chooses backwards compatibility over
users' safety.
Git LFS:
There have been not one, not two, but three security advisories
about Git LFS executing executables from the current directory by
mistake. As part of one of them, a change was introduced to stop
treating empty `PATH` elements as equivalent to `.`:
https://github.com/git-lfs/git-lfs/commit/7cd7bb0a1f0d
I.e. it follows the common practice.
Go:
Go does not follow the common practice, and you can think about
that what you want:
https://github.com/golang/go/blob/go1.19.3/src/os/exec/lp_windows.go#L114-L135
https://github.com/golang/go/blob/go1.19.3/src/path/filepath/path_windows.go#L108-L137
Git Credential Manager:
It tries to imitate Git LFS, but unfortunately misses the empty
`PATH` element handling. As of time of writing, this is in the
process of being fixed:
https://github.com/GitCredentialManager/git-credential-manager/pull/968
So now that we have established that it is a common practice to ignore
empty PATH elements on Windows, let's assess this commit's change
using Schneier's Five-Step Process
(https://www.schneier.com/crypto-gram/archives/2002/0415.html#1):
Step 1: What problem does it solve?
It prevents an entire class of Remote Code Execution exploits via
Git GUI's `Clone` functionality.
Step 2: How well does it solve that problem?
Very well. It prevents the attack vector of luring an unsuspecting
victim into cloning an executable into the worktree root directory
that Git GUI immediately executes.
Step 3: What other security problems does it cause?
Maybe non-security problems: If a project (ab-)uses the unsafe
`PATH` lookup. That would not only be unsafe, though, but
fragile in the first place because it would break when running
in a subdirectory. Therefore I would consider this a scenario
not worth keeping working.
Step 4: What are the costs of this measure?
Almost nil, except for the time writing up this commit message
;-)
Step 5: Given the answers to steps two through four, is the security measure worth the costs?
Yes. Keeping Git's users Secure By Default is worth it. It's a
tiny price to pay compared to the damages even a single
successful exploit can cost.
So let's follow that common practice in Git GUI, too.
Signed-off-by: Johannes Schindelin [email protected]
Reworks the Twinkleshine-Class (#1825)
The Twinkleshine is a CyberSun-made Syndicate display of force, staffed by every branch of the Syndicate. Despite the silly name, the presence of one in a sector implies it to be of importance to the Syndicate, and enemies within sight can only pray that the Twinkleshine crew are incompetent enough to shoot themselves with their own weaponry (or blow themselves up with the supermatter on-board).
It is staffed by:
- 1 Captain
- 1 Lieutenant (previously the Operative - serves as a warden/hos)
- 2 Medics
- 2 Engineers (previously the Mechanics)
- 5 Operatives (previously the Troopers)
- 1 Bartender
- 1 Miner
- 2 Deck Assistants
Few days ago, an admin spawned a Twinkleshine, and I got to captain it. The Twinkleshine is old. It sucks. This, hopefully, fixes that.
Originally, this was going to be minor fixes, but ended up becoming an attempt at reworking the ship to a more modern state - the hull has been redone and is mostly symmetrical, the old spacepod was replaced with a Dark Gygax, the supermatter shouldn't be activated upon spawning the ship, there's more turf decals and a bigger lot-of-things, added a bartender and a miner, people can actually tell who they are and what they do, and there is now a box moth. Rejoice.
Also, this is the first time I've ever mapped a ship. What better way to begin with a giant battleship?
🆑 tweak: Reworks the Twinkleshine /🆑
Signed-off-by: meemofcourse [email protected]
Sand Survivor Rework (#1940)
Reworks how Sand Survivors spawn their loot. Instead of an outfit datum, they now create a corpse similiarly to how legions do it, this allows their contents to have some variety, more ease of expansion, and generally Improves the file.
How I could write better code in a day than White Sands functioned with for iunno how long is byond me
dreamseeker_noRuWtLxV7.mp4
Consistency + Just kinda cool
🆑 add: Sand Planet hermits now have randomized inventories. And Hair. Sometimes. add: Sand Planet hermits can now drop different races add: legions will now drop a variety of species balance: drop rates for legions have been changed in a few spots. fix: hivelord.dm no longer sears my eyes out. /🆑
Signed-off-by: Bjarl [email protected] Co-authored-by: Mark Suckerberg [email protected]
hardsuit/firesuit cleanup (#18308)
-
real
-
hjoly fuck you guy sare annoying
-
fix cargo arbitrage idk why tf it changed from editing armor values but fuck my life i guess
-
why god
-
Update suits.yml
-
Update cargo_emergency.yml
Destroying Sprite Cruft Part One: Cruft Sucks (#2220)
Title
In total, the:
- IV Drip
- All-In-One Grinder
- Book Binder
- Book Scanner
- Water Cooler
- Tank Dispenser
Have all been successfully uncrufted. No more cruft. Just clean sprites now :D
Oh and dressers have directionals now at the request of @Bjarl
Credit goes to the original authors in the changelog.
begone cruft I fucking hate cruft
🆑 PositiveEntropy, Maxymax13, Wallemations, Kryson, Viro/Axietheaxolotl, MeyHaZah imageadd: Books, IV drips, tank dispensers, all-in-one grinders, water coolers, book binders and book scanners have been resprited! imageadd: Dressers now have directionals! /🆑
Reference packets by ID
Enormous refactor to fix an extremely silly mistake I made when I designed this app: referencing packets by name instead of ID. I corrected this, and in the process set up the application so that it's almost entirely template-based now, which is much nicer than the JS-based HTML I was writing before. I don't hate my original implementation, but I think this one is undeniably easier to understand and maintain.
I still need to re-implement editing, which I expect will by annoying.
Convert indentation from spaces to tabs
I've long favored four-space indentation but find Matt Wilcox's pro-tab counterargument 1 compelling, if needlessly condescending:
This is your occasional reminder:
Tabs are what should be used for indentation.
Why? Because spaces for indentation are:
- Harder for people using assistive technology
- Harder for people with reading comprehension issues who want more
indentation.
The tab is *user customisable* to be any level of indentation per
tab character. It is the semantically correct character.
Please; use tab characters in any public code. If you don't like
how "deep" they are; adjust your editor's rendering.
(If you are already cringing or railing against this idea because it
would look weird to you... have a deep think. A real deep think.)
Spaces as indentation are self-centred and selfish. They enforce
*your* preference on others, when tabs would allow you *and others*
their own preference of indentation for the same code - because they
are user configurable.
Yes, all editors can configure the tab to render as 1, 2, 4, 6, 8 or
any number of spaces wide. Learn your editor.
I've always prioritized my aesthetic preferences, deeming indentation of two columns to be too shallow and eight, too deep. I know tab stops are widely configurable, but I stubbornly insist on viewing tabs at their "natural" width of eight columns because I want to see them as everyone else does. (Who actually changes their tab stops? Come on.) Thus, the only way to get al dente indentation that looks the same to everyone is to use four spaces.
I've thought about switching to tabs before. The Linux kernel coding style guide espouses 8-column indentation on the grounds that it's very clear and highlights excessively deep nesting 3 -- interesting ideas, but not so interesting that I'd switch teams.
Well, Wilcox's accessibility angle has convinced me, although I still think 8 columns is a bit much. I'll get over it.
Reindent Vim source using tabs. Do not reindent prose because it looks awful, and I can't bring myself to do it (code is already ugly, so it's easier to swallow).
Demolitions & Rockets
Balance:
- Mech rockets corrected. They weren't meant to be firing HE. Whoops.
- Legion Demolitions given a proper explosive grenade.
- HE given to Demolitions has also been made a crafting option.
- Enclave roles with grenades given the appropriate F13 item.
- Brotherhood has lost access to the L30, alongside the tribeam. The latter because it was a redundant choice and sandwiched between two far superior options.
Map:
- Heaven's Night and general Pahrump modifications in line with internal discussions.
Removed support for Apple devices, because I realized that you need to spend FUCKING 2000€ to get some stupid devices that even don't support sideloading lmao.
And NO I can't run it in a virtual machine.
(I know there's always a way, but I don't want to spend a whole day to get a shady macOS version running and then spend another week to learn macOS)
Hyprland > macOS : Facts.
(iOS maybe get support, because I have a friend with an iOS device, and I am really close to him, but he doesn't do anything like programming. I don't know if he wants to install a "hacker tool (lmao)" like iSH. (You hopefully get the joke ;))
Optimization pass focused on foam code (saves about 30% of cpu usage I think) (#76104)
Foam is crummy at high load rn, both because it runs on a low priority background subsystem, and because it wastes a bit of time. Let's reduce usage (while speeding up a bunch of other stuff too), and give it more cpu generally.
Optimizes reagent processing somewhat
Turns out most of the cost of foam is the reagents it carries, and the varying effects they have I'm doing my best here to optimize them without touching "user space" too much
That means doing things like prechecking if we're gonna spawn on top of an existing decal (from glitter, flour, etc), and using that same proc to also avoid spawning on unacceptable turfs (I had to convert inheritance to a bitflag system to make this work, but I think that's ok since we want it imparative anyhow)
It's actually nice for code quality too, since it lets me clean up code that was using raw locates and weird var pong. god I wish I had implied types man
Optimizes foam spreading in its most accursed aspect, reagent copying
Holy shit reagent code is a lot.
I'm doing a bunch of small things here. istype in init -> typecache, removing procs that are called once and loop over a list we JUST looped over (ph and the caching for reactions in particular)
I am mainly trying to optimize copy_to here, since that's what foam spams As a part of this, I removed a pair of update_total and handle_reactions calls that were done on the reagents we are copying FROM
I have no god damn idea why you would want to do that, but if anything is relying on the copy proc modifying the source, then that code deserves to break
Speaking of, I cleaned up handle_reaction's main filter loop a lot, removed a lot of redundant vars and changed it from a full loop w tracker vars to an early exit pattern
This meant using a loop label, which is unfortunate, but this is the fastest method, and it does end up cleaning up the code significantly, Which is nice
Oh also I made the required_other var function even if there is no atom attached to the reaction, since I don't see why it wouldn't
This last bit is gonna get a bit esoteric so bear with me
Failing calls (which are most of them) to handle_reactions are going to be fastest if they need to check as few reactions as possible
One reagent in a reaction's required list is marked as the "primary", and thus gets to trigger checking it. We need all the reagents to react anyhow, so we might as well only check if we have one particular one to avoid double checking
Anyhow, in order to make most calls the fastest, we want these reactions distributed as evenly as possible across all our reagents. The current way of doing this is just taking the first reagent in the requirements list and using it, which is not ideal
Instead of that, lets figure out how many reactions each reagent is in, then divy reactions up based off that and the currently divvied reactions
This doubles the reagent index count, and takes the most common reagent, water, from 67 reactions to I think like 22
Does some other general cleaning in reagent code too, etc etc etc
Fixes runtimes from the forced gravity element being applied more then once
I feel like this element should take a trait source or something to make them potentially unique, it's too easy to accidentally override one with another
Removes connect_loc usage in atmos_sensitive, replaces it with direct reg/unreg
I only really used it because I liked the componentization, but it costs like 0.2 seconds off init alone which is really stupid, so let's just do this the very slightly harder way
Micros foam code slightly by inlining a LinkBlockedWithAccess call
This is in the space of like 0.05 seconds kinda save so I can put it back if you'd like, the double loop just felt silly
Changes how foam processes slightly
Rather then treating spreading and processing as separate actions, we do both in sync. This makes foam fade faster when spreading, which is good cause the whole spread but unclearing foam thing looks silly. It also avoids the potential bad ending of foam spreading into itself, backwards and forwards. This is better I promise.
Bumps fluid priority closer to heavy eaters, moves it off background
Also fixes a bug where foam would travel under public access airlocks.
Saves a lot of cpu just in general, from both init and live. In theory makes foam faster, tho I'd have to test that on live at highpop to see if I've actually succeeded or not. Guess we'll see.
There is no longer a 50% chance of catching a heretic out when examining them drawing influences (#76878)
There is no longer a 50% chance of catching a heretic out when examining them drawing influences.
There is no longer a 50% chance of catching a heretic out when examining them drawing influences
This is a bad thing for several reasons.
-
It means the heretic will most often be caught out at the very start of the shift, when they are weakest and most vulnerable. Heretics already have it hard enough, adding yet another source of stress is undue.
-
It has no effective counter. What are you going to do? Not draw any influences? That shouldn't be the 'counter'. The influence drawing period is meant to parallel the crew prepping period, the traitor rep-collecting period, etc.
-
In a way, it's more blatant than Codex Cicatrix drawing. Codexi show up as a normal item in your hand. This instead shows a huge flashing glowing neon rainbow text that says THIS IS A HERETIC. SHRIEK IN RADIO AND VALID.
-
It's badly designed, and can be manipulated way too easily to always show. Examine a target thrice and you're pretty much guaranteed to see if they are indeed drawing or not. You can just keep rolling the 50% chance.
-
It feels random and unfair for the heretic to die to it. I've seen this happen and it sucks. There's no sign for heretics that they have a risk of being found out when examined, which means that this is just an extremely rare occurrence that you try to ignore could happen 99% of the time, and feel like shit the 1% of the time it backfires.
🆑 del: There is no longer a 50% chance of catching a heretic out when examining them drawing influences. /🆑
Switch product names to standard-(cores*2) notation
Why cores * 2? Because SMT features, as seen on Intel and AMD products for some year now make this equal to the number of "CPUs" or "vCPUs" when exposed to the guest operating system.
The theory is that an integer in the product code will be compared to vCPU references similar products on various data tables and so forth on The Internet, or more to the point, shouldn't be a smaller integer than those references for the same hardware. Note, I do not subscribe to this theory personally, so don't ask me about it.
The ugliness arrives when we consider SMT-off configurations or relatively recent addition of ARM processors that do not implement SMT. If the product scale factor was taken to describe vCPUs, we'd end up the situation that GCP and Azure are in: t2d.standard-1 is a one vCPU in SMT-off configuration, and thus a single core, and so is n2d.standard-2, and these are otherwise the most comparable products.
Azure did something rather strange to deal with this, where a "Standard_E2" is 2 vCPUs on one core via SMT and 16 gigabytes of memory, but "Standard_E2p" on ARM is 2 cores and 16 gigabytes of memory, a more compute-rich ratio by quite a bit.
One solution, absent indexing the product by cores directly, which produces an integer that could be misconstrued and deemed too small, is to double the core number in all circumstances. The idea of a popular architecture with three or more threads per core seems unlikely at this point, and in any case it'd be an emergent architecture where we could be forgiven for an awkward numbering system. And it solves the problem for allowing someone to scan laterally from "standard-2" and a hypothetical "standard-2-arm". Even if standard-2-arm has a single core.
Of course, there's nothing stopping us from deciding to really make
the product scale factor relate to vCPUs, that is, to have integers of
larger magnitudes for architectures with SMT, and maybe if people do
prove to be uniformly alert about SMT and find standard-2-arm
misleading, we can elect to do things that way.
Switch product names to standard-(cores*2) notation
Why cores * 2? Because SMT features, as seen on Intel and AMD products for some year now make this equal to the number of "CPUs" or "vCPUs" when exposed to the guest operating system.
The theory is that an integer in the product code will be compared to vCPU references similar products on various data tables and so forth on The Internet, or more to the point, shouldn't be a smaller integer than those references for the same hardware. Note, I do not subscribe to theory's assigned magnitude of this, and have my objections to what it does to the cogency of product comparison as written below, but nonetheless, I've written this operating under this theory.
The ugliness arrives when we consider SMT-off configurations or relatively recent addition of ARM processors that do not implement SMT. If the product scale factor was taken to describe vCPUs, we'd end up the situation that GCP and Azure are in: t2d.standard-1 is a one vCPU in SMT-off configuration, and thus a single core, and so is n2d.standard-2, and these are otherwise the most comparable products.
Azure did something rather strange to deal with this, where a "Standard_E2" is 2 vCPUs on one core via SMT and 16 gigabytes of memory, but "Standard_E2p" on ARM is 2 cores and 16 gigabytes of memory, a more compute-rich ratio by quite a bit.
One solution, absent indexing the product by cores directly, which produces an integer that could be misconstrued and deemed too small, is to double the core number in all circumstances. The idea of a popular architecture with three or more threads per core seems unlikely at this point, and in any case it'd be an emergent architecture where we could be forgiven for an awkward numbering system. And it solves the problem for allowing someone to scan laterally from "standard-2" and a hypothetical "standard-2-arm". Even if standard-2-arm has a single core.
Of course, there's nothing stopping us from deciding to really make
the product scale factor relate to vCPUs, that is, to have integers of
larger magnitudes for architectures with SMT, and maybe if people do
prove to be uniformly alert about SMT and find standard-2-arm
misleading, we can elect to do things that way.