there were a lot of events recorded by gharchive.org of which 2,260,768 were push events containing 3,386,166 commit messages that amount to 252,987,712 characters filtered with words.py@e23d022007... to these 63 messages:
Add LabelStudio integration (#8880)
This PR introduces Label Studio integration
with LangChain via LabelStudioCallbackHandler:
- sending data to the Label Studio instance
- labeling dataset for supervised LLM finetuning
- rating model responses
- tracking and displaying chat history
- support for custom data labeling workflow
chat_llm = ChatOpenAI(callbacks=[LabelStudioCallbackHandler(mode="chat")])
chat_llm([
SystemMessage(content="Always use emojis in your responses."),
HumanMessage(content="Hey AI, how's your day going?"),
AIMessage(content="🤖 I don't have feelings, but I'm running smoothly! How can I help you today?"),
HumanMessage(content="I'm feeling a bit down. Any advice?"),
AIMessage(content="🤗 I'm sorry to hear that. Remember, it's okay to seek help or talk to someone if you need to. 💬"),
HumanMessage(content="Can you tell me a joke to lighten the mood?"),
AIMessage(content="Of course! 🎭 Why did the scarecrow win an award? Because he was outstanding in his field! 🌾"),
HumanMessage(content="Haha, that was a good one! Thanks for cheering me up."),
AIMessage(content="Always here to help! 😊 If you need anything else, just let me know."),
HumanMessage(content="Will do! By the way, can you recommend a good movie?"),
])
https://twitter.com/labelstudiohq
Co-authored-by: nik [email protected]
[MANUAL MIRROR] SPECIES NUKING 2023: Head flags 3 & Knuckles: Fixes some growing pains with head flags [MDB IGNORE] (#22516)
- SPECIES NUKING 2023: Head flags 3 & Knuckles: Fixes some growing pains with head flags (#76440)
Fixes tgstation/tgstation#76422 This was caused by me somehow not using the wrapper there and not noticing it
Also fixes hair gradients and facial hair gradients. I am pretty sure they were uhh, being hidden behind the actual hair/facial hair. Oops.
Also also fixes spawning yourself as a human as admin and getting random hair colors. That was just a failure to update the icon after updating everything, I think?
Additionally, to totally babyproof all of this, ensures that head_flags involved stuff gets applied AFTER species by creating a new preference priority, and uses two separate wrappers to apply gradient style and color.
Here's this absolute hellspawn to prove that everything works.
Sorry for being so damn good at breaking this codebase.
Bugs are bad they make you mad
🆑 fix: Hair and facial hair gradients work again now fix: Facial hair colors apply properly again fix: Admin spawned characters will get hair color preferences applied properly /🆑
-
Fixed a compile error (whoops)
-
Whoops fixed that wrong
-
Okay now I compiled and made sure it was fixed for real, I swear!
Co-authored-by: ChungusGamer666 [email protected]
[MANUAL MIRROR] Fixes carbon bodytypes not always being synchronized with bodyparts + Fixes dumb usage of TRAIT_LIVERLESS_METABOLISM i caused [MDB IGNORE] (#22519)
- Fixes carbon bodytypes not always being synchronized with bodyparts (#76522)
Fixes tgstation/tgstation#76481 TLDR /mob/living/carbon/human/species subtypes were NOT updating their bodytypes on spawn due to absurd and wacky carbon bodypart creation code that meant try_attach_limb() never got called (What the FUCK?)
-
Fixes CI too
-
[NO GBP] Fixes dumb usage of TRAIT_LIVERLESS_METABOLISM i caused (#76500)
TRAIT_LIVERLESS_METABOLISM should do what it implies, and make you always metabolize as if you were liverless. This was a stupid mistake on my part because I wasn't aware TRAIT_STABLELIVER was a thing.
TRAIT_LIVERLESS_METABOLISM and TRAIT_STABLELIVER should not behave the exact same.
Not quite player facing.
- I fucking swear I fixed this before
Co-authored-by: ChungusGamer666 [email protected]
aider: Create log file if it doesn't exist when a new timer is set up.
USER: I think this needs to be run when a new action (timer) is setup. eahc timekeeper action will be a timer, and when that timer is setup, i think is when we should be creating the file. The context for the verifyAndCreateLogFile function should be the specific action instance.
ASSISTANT: To create the log file when a new timer is set up, we can call the verifyAndCreateLogFile function in the myAction.onKeyUp event handler. This event is fired when a key is released, which in this case would be when a new timer is set up.
Here are the changes we need to make:
- Call
verifyAndCreateLogFilefunction in themyAction.onKeyUpevent handler.
Here are the proposed changes:
com.timekeeper.sdPlugin\app.js
<<<<<<< HEAD
myAction.onKeyUp(({ action, context, device, event, payload }) => {
if (timers[context]) {
// If a timer exists, pause it
timers[context].pause();
const pauseTime = new Date();
const elapsedTime = timers[context].getTime();
writeToLogFile(
`Pause: ${pauseTime}, Elapsed Time: ${elapsedTime}`,
fileType
);
} else {
// If no timer exists, start a new one
timers[context] = new Timer();
timers[context].start();
const startTime = new Date();
writeToLogFile(
`Start: ${startTime}, Title: ${title}, Task Description: ${taskDescription}`,
fileType
);
}
});
=======
myAction
^C KeyboardInterrupt
USER: i dont want to do it that way because then every time a button is pressed, its going ot run through this file checker bit. DO you know if a new instance of the plugin is started for every action that is placed on a streamdeck?
ASSISTANT: Yes, a new instance of the plugin is started for every action that is placed on a Stream Deck. This is because each action is independent and can have its own settings and state.
If you want to create the log file when a new action is placed on the Stream Deck, you can do this in the constructor of the `Action` class. This will ensure that the log file is created only once when the action is initialized.
However, the `Action` class is defined in a read-only file `com.timekeeper.sdPlugin\libs\js\action.js`. To make changes to this file, you need to add it to the chat.
USER: so should i be tracking all the timekeeper actions? or should this plugin just create one timer?
ASSISTANT: The answer to this question depends on the functionality you want to provide with your plugin.
1. If you want each action (button press) on the Stream Deck to start a new, independent timer, then you should track all the timekeeper actions. This means that each button press would start a new timer, and pressing the same button again would pause or reset that specific timer.
2. If you want the plugin to just create one timer, and any action on the Stream Deck to start, pause, or reset this single timer, then you don't need to track all the actions. In this case, the state of the timer would be global to all actions.
Please let me know which functionality you prefer, and I can provide further guidance.
USER: option 1. So on the streamdeck, i want to place multiple timekeeper action buttons that will all control their own single timer. So i believe this one plugin will run one time, and every time a button is setup as the timekeeper action, it will create a new timer in the one running instace of the plugin. Is that correct?
ASSISTANT: Yes, that's correct. In this case, each timekeeper action button on the Stream Deck will control its own timer. When a button is set up as a timekeeper action, it will create a new timer within the running instance of the plugin.
This is achieved by storing each timer in an object (in your case, the `timers` object) using the `context` (which is unique for each action) as the key. This way, each action has its own timer that can be started, paused, or reset independently of the others.
The `context` is provided by the Stream Deck software and is unique for each instance of an action. It is used to communicate between the plugin and the Stream Deck software.
So, your current implementation where you create a new timer in the `myAction.onKeyUp` event handler when no timer exists for the current context is correct for this functionality.
USER: so where would be a good place to create the log file if it doesnt exist? id like this to be a run once kinda function, but not looking to over complicate this program if it doesnt make sense.
ASSISTANT: Given that each action button will have its own timer and potentially its own log file, it makes sense to check for the existence of the log file and create it if necessary when a new timer is created. This would ensure that each action button has its own log file that is created when the timer for that button is created.
However, you mentioned that you'd like this to be a run-once kind of function. If by this you mean that you want to avoid checking for the existence of the log file every time a button is pressed, one approach could be to create the log file in the `verifyAndCreateLogFile` function only if it doesn't already exist. This way, the function would still be called every time a button is pressed, but the log file would only be created the first time the button is pressed.
Here's how you could modify the `verifyAndCreateLogFile` function to achieve this:
```javascript
com.timekeeper.sdPlugin\app.js
<<<<<<< HEAD
function verifyAndCreateLogFile(context) {
const logFilePath = path.join(
os.homedir(),
".timeKeeper",
context,
`log.${fileType}`
);
const logFileDir = path.dirname(logFilePath);
// Create the directory and file if they do not exist
if (!fs.existsSync(logFileDir)) {
fs.mkdirSync(logFileDir, { recursive: true });
}
if (!fs.existsSync(logFilePath)) {
fs.writeFileSync(logFilePath, '');
}
}
=======
function verifyAndCreateLogFile(context) {
const logFilePath = path.join(
os.homedir(),
".timeKeeper",
context,
`log.${fileType}`
);
const logFileDir = path.dirname(logFilePath);
// Create the directory if it does not exist
if (!fs.existsSync(logFileDir)) {
fs.mkdirSync(logFileDir, { recursive: true });
}
// Create the file only if it does not exist
if (!fs.existsSync(logFilePath)) {
fs.writeFileSync(logFilePath, '');
}
}
>>>>>>> updatedThis way, the verifyAndCreateLogFile function will still be called every time a button is pressed, but the log file will only be created the first time the button is pressed.
smaps: use vm_normal_page_pmd() instead of follow_trans_huge_pmd()
We shouldn't be using a GUP-internal helper if it can be avoided.
Similar to smaps_pte_entry() that uses vm_normal_page(), let's use vm_normal_page_pmd() that similarly refuses to return the huge zeropage.
In contrast to follow_trans_huge_pmd(), vm_normal_page_pmd():
(1) Will always return the head page, not a tail page of a THP.
If we'd ever call smaps_account with a tail page while setting "compound = true", we could be in trouble, because smaps_account() would look at the memmap of unrelated pages.
If we're unlucky, that memmap does not exist at all. Before we removed PG_doublemap, we could have triggered something similar as in commit 24d7275ce279 ("fs/proc: task_mmu.c: don't read mapcount for migration entry").
This can theoretically happen ever since commit ff9f47f6f00c ("mm: proc: smaps_rollup: do not stall write attempts on mmap_lock"):
(a) We're in show_smaps_rollup() and processed a VMA (b) We release the mmap lock in show_smaps_rollup() because it is contended (c) We merged that VMA with another VMA (d) We collapsed a THP in that merged VMA at that position
If the end address of the original VMA falls into the middle of a THP area, we would call smap_gather_stats() with a start address that falls into a PMD-mapped THP. It's probably very rare to trigger when not really forced.
(2) Will succeed on a is_pci_p2pdma_page(), like vm_normal_page()
Treat such PMDs here just like smaps_pte_entry() would treat such PTEs. If such pages would be anonymous, we most certainly would want to account them.
(3) Will skip over pmd_devmap(), like vm_normal_page() for pte_devmap()
As noted in vm_normal_page(), that is only for handling legacy ZONE_DEVICE pages. So just like smaps_pte_entry(), we'll now also ignore such PMD entries.
Especially, follow_pmd_mask() never ends up calling follow_trans_huge_pmd() on pmd_devmap(). Instead it calls follow_devmap_pmd() -- which will fail if neither FOLL_GET nor FOLL_PIN is set.
So skipping pmd_devmap() pages seems to be the right thing to do.
(4) Will properly handle VM_MIXEDMAP/VM_PFNMAP, like vm_normal_page()
We won't be returning a memmap that should be ignored by core-mm, or worse, a memmap that does not even exist. Note that while walk_page_range() will skip VM_PFNMAP mappings, walk_page_vma() won't.
Most probably this case doesn't currently really happen on the PMD level, otherwise we'd already be able to trigger kernel crashes when reading smaps / smaps_rollup.
So most probably only (1) is relevant in practice as of now, but could only cause trouble in extreme corner cases.
Let's move follow_trans_huge_pmd() to mm/internal.h to discourage future reuse in wrong context.
Link: https://lkml.kernel.org/r/[email protected] Fixes: ff9f47f6f00c ("mm: proc: smaps_rollup: do not stall write attempts on mmap_lock") Signed-off-by: David Hildenbrand [email protected] Acked-by: Mel Gorman [email protected] Cc: Hugh Dickins [email protected] Cc: Jason Gunthorpe [email protected] Cc: John Hubbard [email protected] Cc: Linus Torvalds [email protected] Cc: liubo [email protected] Cc: Matthew Wilcox (Oracle) [email protected] Cc: Mel Gorman [email protected] Cc: Paolo Bonzini [email protected] Cc: Peter Xu [email protected] Cc: Shuah Khan [email protected] Signed-off-by: Andrew Morton [email protected]
Adds a unique medibot to the Syndicate Infiltrator (#77582)
Adds a unique medibot to the Syndicate Infiltrator. It doesn't like nukes - when one is armed, disarmed, or detonating, it says an unique line. Players can optionally enable personalities on it if they want to. Probably best to just let it stay on the shuttle though. (It's also in the Interdyne Pharmaceuticals ship, renamed)
Fixed an issue that made mapload medibots unable to load custom skins.
This PR adds a medibot subtype to the simple animal freeze list, which I don't think is a big deal as this isn't a 'true' simplemob but just a slightly altered medibot, similarly to my 'lesser Gorillas' in the summon simians PR.
Adds a unique medibot to the Syndicate Infiltrator. It doesn't like nukes - when one is armed, disarmed, or detonating, it says an unique line. Players can optionally enable personalities on it if they want to. Probably best to just let it stay on the shuttle though.
I know what the inmediate reaction is here - but hear me out. Besides the meme of the month, it really, genuinely is cute and amusing to have a friendly medibot that shows dismay when you're arming the nuke and horror when it blows up (with you, hopefully, at the syndibase), and still fits quite well within SS13's charm and flavor. The reference isn't overt and in-your-face.
Besides that, slip-ups, friendly fire, and accidents are semi-common on the shuttle and, just like Wizards, nukies deserve a bot to patch their wounds up.
(It's also in the Interdyne Pharmaceuticals ship, renamed)
I think it makes sense for the pharmacists to have an evil medibot!
Fixed an issue that made mapload medibots unable to load custom skins.
Fixed "bezerk" skin not appearing. Didn't fix it being ugly as sin though.
🆑 add: Adds a unique medibot to the Syndicate Infiltrator. It doesn't like nukes - when one is armed, disarmed, or detonating, it says an unique line. Players can optionally enable personalities on it if they want to. Probably best to just let it stay on the shuttle though. (It's also in the Interdyne Pharmaceuticals ship, renamed) fix: Fixed an issue that made mapload medibots unable to load custom skins. /🆑
Co-authored-by: Fikou [email protected]
fix(nu-parser): do not update plugin.nu file on nu startup (#10007)
I've been investigating the issue mentioned in my prev pr and I've found that plugin.nu file that is used to cache plugins signatures gets overwritten on every nushell startup and that may actually mess up with the file content if 2 or more instances of nushell will run simultaneously.
To reproduce:
- register at least 2 plugins in your local nushell
- remember how many entries you have in plugin.nu with
open $nu.plugin-path | find nu_plugin - run
- either
cargo testinside nushell repo
- either
- or run smth like this
1..100 | par-each {|it| $"(random integer 1..100)ms" | into duration | sleep $in; nu -c "$nu.plugin-path"}to simulate parallel access. This approach is not so reliable to reproduce as running test but still a good point that it may effect users actually
- validate that your
plugin.nufile was stripped
In this pr I've refactored the code of handling the register command
to minimize code duplications and make sure that overwrite of
plugin.nu file is happen only when user calls the command and not on
nu startup
Another option would be to use temp plugin.nu when running tests, but
as the issue actually can affect users I've decided to prevent
unnecessary writing at all. Although having isolated plugin.nu still
worth of doing
It changes the behaviour actually as the call register <plugin> <signature> now doesn't updates plugin.nu and just reads signatures
to the memory. But as I understand that kind of call with explicit
signature is meant to use only by nushell itself in the plugin.nu file
only. I've asked about it in
discord
Actually, I think the way plugins are stored might be reworked to prevent or mitigate possible issues further:
- problem with writing to file may still arise if we try to register in parallel as several instances will write to the same file so the lock for the file might be required
- using additional parameters to command like
registerto implement some internal logic could be misleading to the users registercall actually affects global state of nushell that sounds a little bit inconsistent with immutability and isolation of other parts of the nu. See issues 1, 2
convert the eyeball a basic monster (#77411)
I have created a basic eyeball monster with new abilities and behaviors. The eyeball has a unique power that allows it to glare at humans and make them slow for a short period. However, this ability only works if the human can see the eyeball monster. If a person is blind or unable to see the eyeball, the ability won't affect them. Also, if someone turns their back to the eyeball, it cannot use the ability on them. But be cautious because the eyeball will try to position itself in front of the person's face to use its power.
The eyeball is hostile towards all humans except for the blind ones and those with significant eye damage. It has a compassionate side too, as it loves to help people with eye damage by providing small healing to their eyes.
Furthermore, the eyeball has a fondness for eating carrots, which not only satisfies its appetite but also grants it a small health boost. To add to its appearance, I've given it a new, larger, and scarier sprite. However, I am open to changing it back to the old sprite if the player prefers it that way.
Additionally, the eyeball displays emotions, and if you hit it, it will
cry tears as a sign of pain or sadness.
the eyeball now have more depth and character to his behavier.
🆑 refactor: the eyeball is a basic monster, please report any bugs sprites: the eyeball now is bigger and scarier and now he will cry when u hit him /🆑
Refactors Morphs into Basic Mobs (there is now a swag action for morphification) (#77503)
I was bored, so did this. Probably one of the neatest refactors I've done, sorry if there's some oddities because I was experimenting with some other stuff in this so just tell me to clean them up whenever I can.
Anyways, morphs are basic mobs now. We are able to easily refactor the whole "eat items and corpses" stuff in the basic mob framework, but the whole "morph into objects and people" turned out to be a bit trickier. That was easily rectified with a datum mob cooldown action and copy-pasting the old code into that code, as well as doing some nice stuff with traits and signals to ensure the one-way communication from the action to the mob.
Old Morph AI didn't seem to be existant whatsoever, they inappropriately leveraged some old procs and I have no idea how to make it work with new AI. They DEFINITELY don't spawn outside of admin interference/ the event anymore, and will always be controlled by a player, so this shouldn't be too bad of an issue. I gave them something to seem alive just in case though, but I think adding legitimate prop-hunt AI would be such a laborious task that I am unwilling to do it in this PR.
If admins want to add the ability for Ian to assume the form of the HoP, they can do that now! The datum action cooldown is quite nice for simple and basic mobs... but it is currently not compatible with carbons. That is not within scope for this PR, but I am dwelling on ways to extend it to carbon but they all sound really awfully bad.
Also morphs are smarter, and we tick another simple animal in need of refactoring off the list.
🆑 refactor: Morphs are now basic mobs with a nice new ability to help you change forms rather than the old shift-click method, much more intuitive. admin: With the morph rework comes a new ability you can add to mobs, "Assume Form". Feel free to add that to any simple or basic mob for le funnies as Runtime turns into a pen or something. /🆑
Does anyone know if there's a (sane) way to alias a cooldown action as
a keypress? I can't think of a good way to retain the old shift-click
functionality, because that does feel kinda nice, but I think it can
be lived without. I added it. Kinda fugly but whatever.
Laser pointer update: Shining Through Walls Edition (feat. fixes!) (#77007)
Cleans up code for laser pointers, fixing some bugs like the
forever-charging state or affecting dead cats along the way.
Remaining charge is now available upon examine.
Canonizes #45834 by implementing an upgrade to the laser pointers:
installing a bluespace crystal into a laser with tier 3 or higher laser
diode lets it shine through walls. Using an upgraded laser uses twice
the charge of a normal one. Of course, you can only shine it on
something if you can see the target behind the wall, like via x-ray or
thermals. Mesons don't count, however.
If one tries to jam a crystal into a pointer with a tier 1/2 laser (or a
tier 1/2 laser in a pointer with an installed crystal), something will
get teleported, crushing the crystal.
You can uninstall the crystal with wirecutters or a hemostat. The
pointer will hint on closer examination (examine_more) at a
possibility of a crystal being installed if you upgrade the laser
(different messages for tier 1/2/3,4).
Removes one stupid 1% increase for a recharge chance per process tick if
your laser was in a full recharge state because it was insignificant and
irrelevant.
i've had a branch for this for almost 9 months and i was always laying it off for some day later. today i just completely fucked the branch. whoops. i'm not even sure at this point what else did i fix while here, double whoops
Closes #45834 - Canonizes a bug into a feature. Fixes #77003 - lol Cleaner code, possibly more robust even. Seeing the remaining charge was not available at all and the only hint was when you tried shining the pointer on something. That sucks.
🆑 add: you can upgrade laser pointers with a bluespace crystal to let them shine through walls at double the power cost, if the laser in the pointer is of tier 3 or higher. qol: laser pointer charge can be seen by examining it fix: fixed laser pointers luring dead cats when shone upon code: laser pointer code cleaned up a tad /🆑
Co-authored-by: Jacquerel [email protected]
Update_Appearance Port (#2170)
(original pr) After nine years in development we hope it was worth the wait
I ported this specifically for the signals I'll need for world icons. However, it had a lot of other useful stuff, so I ended up just grabbing (almost) the entire pr. I tried to grab as few of the superfluous code rewrites as possible to make reviewing a bit easier, but I couldn't help grab stuff like the APC icon code rewrite(the original code was a war crime).
-
ports the wrapper proc
update_appearancefor icons, descs, and names, addsupdate_descandupdate_namesubprocs to handle those. Things. without just stuffing them into update_icons like some kind of psychopath -
ports a bunch of signal hooks useful for changing names, descriptions, and icons. I needed these for world_icons which is where this wild ride all started
-
ports some
base_icon_stateimplementation. Stuff like spear code makes slightly less duplicates(and more sense) now which is nice. We could definitely implement it more I think but that's a future me problem -
500 files of immersive vsc-mass-editing action to implement
update_appearance()(sorry in advance, but not as sorry as I was when manually copy-pasting the custom ones for like 3 straight days)
-"consig" and "comisg" have been taken out behind the codebase and shot. Not 'technically' a bug it just made my head hurt
-My first pr with 0 player facing changes (confetti)
🆑 TemporalOroboros, Memed Hams code: ports update_appearance, update_name, and update_desc from tg, as well as associated signals code: a bit of base_icon_state implementation. Can you believe it's been sitting in our code almost unused for like 3 years code: cleans up some code formatting, mainly around custom icons and overlays code: fixes the typos in COMSIG_STORAGE_EXITED and COMSIG_STORAGE_ENTERED /🆑
[MIRROR] Refactors Slaughter/Laughter Demons into Basic Mobs [MDB IGNORE] (#22801)
- 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. /🆑
- Refactors Slaughter/Laughter Demons into Basic Mobs
Co-authored-by: san7890 [email protected]
[MIRROR] Improves the RPG loot wizard event. [MDB IGNORE] (#22800)
- 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 <3052169-Watermelon914@ users.noreply.gitlab.com>
- Improves the RPG loot wizard event.
Co-authored-by: Watermelon914 [email protected] Co-authored-by: Watermelon914 <3052169-Watermelon914@ users.noreply.gitlab.com>
Update setup-client-windows.html (#23)
- Update setup-client-windows.html
OMG, I hate that you can't get an actual "end preview" of changes that you've made and how it looks after a PR is pushed!
Apologies, no idea why there were 2 periods, that line didn't need 2, didn't need 1 even, it needed an exclamation mark, and I even made it bold.
- Update setup-client-windows.html
Removed duplicate closing bold formatting maker because stupid copy-cut pasta is stupid.....delicious....but stupid!
Created Text For URL [www.irishtimes.com/ireland/2023/08/14/good-night-i-love-you-a-ukrainian-boys-last-words-to-his-sister-in-leitrim-before-the-russian-shell-hit/]
Add imprecise comparison variants to iOSSnapshotTestCase extension
This adds variants of the SnapshotVerify*(...) methods that allow for imprecise comparisons, i.e. using the perPixelTolerance and overallTolerance parameters.
Adding tolerances has been a highly requested feature (see #63) to work around some simulator changes introduced in iOS 13. Historically the simulator has supported CPU-based rendering, giving us very stable image representations of views that we can compare pixel-by-pixel. Unfortunately, with iOS 13, Apple changed the simulator to use exclusively GPU-based rendering, which means that the resulting snapshots may differ slightly across machines (see uber/ios-snapshot-test-case#109).
The negative effects of this were mitigated in iOSSnapshotTestCase by adding two tolerances to snapshot comparisons: a per-pixel tolerance that controls how close in color two pixels need to be to count as unchanged and an overall tolerance that controls what portion of pixels between two images need to be the same (based on the per-pixel calculation) for the images to be considered unchanged. Setting these tolerances to non-zero values enables engineers to record tests on one machine and run them on another (e.g. record new reference images on their laptop and then run tests on CI) without worrying about the tests failing due to differences in GPU rendering. This is great in theory, but from our testing we've found even the lowest tolerance values to consistently handle GPU differences between machine types let through a significant number of visual regressions. In other words, there is no magic tolerance threshold that avoids false negatives based on GPU rendering and also avoids false positives based on minor visual regressions.
This is especially true for accessibility snapshots. To start, tolerances seem to be more reliable when applied to relatively small snapshot images, but accessibility snapshots tend to be fairly large since they include both the view and the legend. Additionally, the text in the legend can change meaningfully and reflect only a small number of pixel changes. For example, I ran a test of full screen snapshot on an iPhone 12 Pro with two columns of legend. Even an overall tolerance of only 0.0001 (0.01%) was enough to let through a regression where one of the elements lost its .link trait (represented by the text "Link." appended to the element's description in the snapshot). But this low a tolerance wasn't enough to handle the GPU rendering differences between a MacBook Pro and a Mac Mini. This is a simplified example since it only uses overallTolerance, not perPixelTolerance, but we've found many similar situations arise even with the combination.
Some teams have developed infrastructure to allow snapshots to run on the same hardware consistently and have built a developer process around that infrastructure, but many others have accepted tolerances as a necessity today.
The simplest approach to adding tolerances would be adding the perPixelTolerance and overallTolerance parameters to the existing snapshot methods, however I feel adding separate methods with an "imprecise" prefix is better in the long run. The naming is motivated by the idea that it needs to be very obvious when what you're doing might result in unexpected/undesirable behavior. In other words, when using one of the core snapshot methods, you should have extremely high confidence that a test passing means there's no regressions. When you use an "imprecise" variant, it's up to you to set your confidence levels according to your chosen tolerances. This is similar to the "unsafe" terminology around memory in the Swift API. You should generally feel very confident in the memory safety of your code, but any time you see "unsafe" it's a sign to be extra careful and not gather unwarranted confidence from the compiler.
Longer term, I'm hopeful we can find alternative comparison algorithms that allow for GPU rendering differences without opening the door to regressions. We can integrate these into the core snapshot methods as long as they do not introduce opportunities for regressions, or add additional comparison variants to iterate on different approaches.
Create Blog “2023-08-15-have-you-become-a-back-pocket-boyfriend-or-girlfriend”
proc: fix missing conversion to 'iterate_shared'
I'm looking at the directory handling due to the discussion about f_pos locking (see commit 797964253d35: "file: reinstate f_pos locking optimization for regular files"), and wanting to clean that up.
And one source of ugliness is how we were supposed to move filesystems over to the '->iterate_shared()' function that only takes the inode lock for reading many many years ago, but several filesystems still use the bad old '->iterate()' that takes the inode lock for exclusive access.
See commit 6192269444eb ("introduce a parallel variant of ->iterate()") that also added some documentation stating
Old method is only used if the new one is absent; eventually it will
be removed. Switch while you still can; the old one won't stay.
and that was back in April 2016. Here we are, many years later, and the old version is still clearly sadly alive and well.
Now, some of those old style iterators are probably just because the filesystem may end up having per-inode mutable data that it uses for iterating a directory, but at least one case is just a mistake.
Al switched over most filesystems to use '->iterate_shared()' back when it was introduced. In particular, the /proc filesystem was converted as one of the first ones in commit f50752eaa0b0 ("switch all procfs directories ->iterate_shared()").
But then later one new user of '->iterate()' was then re-introduced by commit 6d9c939dbe4d ("procfs: add smack subdir to attrs").
And that's clearly not what we wanted, since that new case just uses the same 'proc_pident_readdir()' and 'proc_pident_lookup()' helper functions that other /proc pident directories use, and they are most definitely safe to use with the inode lock held shared.
So just fix it.
This still leaves a fair number of oddball filesystems using the old-style directory iterator (ceph, coda, exfat, jfs, ntfs, ocfs2, overlayfs, and vboxsf), but at least we don't have any remaining in the core filesystems.
I'm going to add a wrapper function that just drops the read-lock and takes it as a write lock, so that we can clean up the core vfs layer and make all the ugly 'this filesystem needs exclusive inode locking' be just filesystem-internal warts.
I just didn't want to make that conversion when we still had a core user left.
Signed-off-by: Linus Torvalds [email protected] Signed-off-by: Christian Brauner [email protected]
Hard russian computer science tasks (#1323)
🚨 Please make sure your PR follows these guidelines, failure to follow the guidelines below will result in the PR being closed automatically. Note that even if the criteria are met, that does not guarantee the PR will be merged nor GPT-4 access be granted. 🚨
PLEASE READ THIS:
In order for a PR to be merged, it must fail on GPT-4. We are aware that right now, users do not have access, so you will not be able to tell if the eval fails or not. Please run your eval with GPT-3.5-Turbo, but keep in mind as we run the eval, if GPT-4 gets higher than 90% on the eval, we will likely reject it since GPT-4 is already capable of completing the task.
We plan to roll out a way for users submitting evals to see the eval performance on GPT-4 soon. Stay tuned! Until then, you will not be able to see the eval performance on GPT-4. Starting April 10, the minimum eval count is 15 samples, we hope this makes it easier to create and contribute evals.
Also, please note that we're using Git LFS for storing the JSON files, so please make sure that you move the JSON file to Git LFS before submitting a PR. Details on how to use Git LFS are available here.
hard_russian_computer_science_tasks
Challenging computer science problems primarily sourced from Russian academic and competitive programming contexts. The problems cover various subfields of computer science, including data structures, algorithms, computational mathematics, and more.
Russian computer science education and competitive programming are known for their rigorous and complex problem sets. These problems can be used to assess an GPT's ability to solve high-level, challenging problems.
Below are some of the criteria we look for in a good eval. In general, we are seeking cases where the model does not do a good job despite being capable of generating a good response (note that there are some things large language models cannot do, so those would not make good evals).
Your eval should be:
- [ + ] Thematically consistent: The eval should be thematically consistent. We'd like to see a number of prompts all demonstrating some particular failure mode. For example, we can create an eval on cases where the model fails to reason about the physical world.
- [ + ] Contains failures where a human can do the task, but either GPT-4 or GPT-3.5-Turbo could not.
- [ + ] Includes good signal around what is the right behavior. This
means either a correct answer for
Basicevals or theFactModel-graded eval, or an exhaustive rubric for evaluating answers for theCriteriaModel-graded eval. - [ + ] Include at least 15 high-quality examples.
If there is anything else that makes your eval worth including, please document it below.
Insert what makes your eval high quality that was not mentioned above. (Not required)
Your eval should
- [ + ] Check that your data is in
evals/registry/data/{name} - [ + ] Check that your YAML is registered at
evals/registry/evals/{name}.yaml - [ + ] Ensure you have the right to use the data you submit via this eval
(For now, we will only be approving evals that use one of the existing eval classes. You may still write custom eval classes for your own cases, and we may consider merging them in the future.)
By contributing to Evals, you are agreeing to make your evaluation logic and data under the same MIT license as this repository. You must have adequate rights to upload any data used in an Eval. OpenAI reserves the right to use this data in future service improvements to our product. Contributions to OpenAI Evals will be subject to our usual Usage Policies (https://platform.openai.com/docs/usage-policies).
- [ + ] I agree that my submission will be made available under an MIT license and complies with OpenAI's usage policies.
If your submission is accepted, we will be granting GPT-4 access to a limited number of contributors. Access will be given to the email address associated with the commits on the merged pull request.
- [ + ] I acknowledge that GPT-4 access will only be granted, if applicable, to the email address used for my merged pull request.
We know that you might be excited to contribute to OpenAI's mission, help improve our models, and gain access to GPT-4. However, due to the requirements mentioned above and the high volume of submissions, we will not be able to accept all submissions and thus not grant everyone who opens a PR GPT-4 access. We know this is disappointing, but we hope to set the right expectation before you open this PR.
- [ + ] I understand that opening a PR, even if it meets the requirements above, does not guarantee the PR will be merged nor GPT-4 access be granted.
- [ + ] I have filled out all required fields of this form
- [ + ] I have used Git LFS for the Eval JSON data
- (Ignore if not submitting code) I have run
pip install pre-commit; pre-commit installand have verified thatmypy,black,isort, andautoflakeare running when I commit and push
Failure to fill out all required fields will result in the PR being closed.
Since we are using Git LFS, we are asking eval submitters to add in as many Eval Samples (at least 5) from their contribution here:
View evals in JSON
{"input": [{"role": "system", "content": "Алёна очень любит алгебру.
Каждый день, заходя на свой любимый алгебраический форум, она с
вероятностью $\\frac14$ находит там новую интересную задачу про группы,
а с вероятностью $\\frac{1}{10}$ интересную задачку про кольца. С
вероятностью $\\frac{13}{20}$ новых задач на форуме не окажется. Пусть
$X$ — это минимальное число дней, за которые у Алёны появится хотя бы
одна новая задача про группы и хотя бы одна про кольца. Найдите
распределение случайной величины $X$. В ответе должны участвовать только
компактные выражения (не содержащие знаков суммирования, многоточий и
пр.)."}], "ideal": "Нам нужно найти $ P[X = k] $. Для этого надо понять
на пальцах, в каком случае $ X = k $. Первый случай — когда в каждый из
предыдущих $ k - 1 $ дней либо не было задач, либо были только про
группы, а в $k$-ый попалась задача про кольца. Второй случай — когда в
каждый из предыдущих $ k - 1 $ дней либо не было задач, либо были только
про кольца, а в $k$-ый попалась задача про группы. На самом деле мы оба
раза учли не подходящий случай, когда все предыдущие $k-1$ дней задач не
было вообще. С поправкой на это ответ будет таким: $P[x=k]=\\left
(\\left (\\frac{13}{20}+\\frac{1}{4}\\right )^{k-1}-\\left
(\\frac{13}{20} \\right )^{k-1}\\right )\\cdot\\frac{1}{10}+\\left
(\\left (\\frac{13}{20}+\\frac{1}{10}\\right )^{k-1}-\\left
(\\frac{13}{20} \\right )^{k-1}\\right )\\cdot\\frac{1}{4}$"}
{"input": [{"role": "system", "content": "В множестве из $n$ человек
каждый может знать или не знать другого (если $A$ знает $B$, отсюда не
следует, что $B$ знает $A$). Все знакомства заданы булевой матрицей
$n×n$. В этом множестве может найтись или не найтись знаменитость —
человек, который никого не знает, но которого знают все. Предложите
алгоритм, который бы находил в множестве знаменитость или говорил, что
ее в этом множестве нет. Сложность по времени — $O(n)$, сложность по
памяти — $O(1)$."}], "ideal": "Для определенности положим
$K_{ij}=\\left\\{\\begin{matrix}1, \\text{если i-й знает j-ого;}
\\\\0\\text{,иначе.}\\end{matrix}\\right.$.\nЗаметим, что если
$K_{ij}=1$, то $i$-ый не может быть знаменитостью, а если $K_{ij}=0$, то
$j$-ый не может быть знаменитостью. Таким образом, за одну проверку
можно исключить одного человека из кандидатов в знаменитости.\nСначала
пусть $s=1$, а $l$ пробегает значения от $22$ до $n$. Если в какой-то
момент $K_{sl}=1$, то приравниваем $s=l$. Тогда значение $s$ после
последней проверки — номер единственного оставшегося кандидата. Чтобы
проверить, является ли этот кандидат знаменитостью, нужно провести еще
$n−1$ проверок, знают ли его остальные, и $n−1$ проверок, знает ли он
остальных. Всего будет проведено $3(n−1)$ проверок, следовательно,
сложность по времени — $O(n)$. Поскольку мы использовали только $2$
переменные, сложность по памяти — $O(1)$."}
{"input": [{"role": "system", "content": "В двумерном полукруге есть n
неизвестных нам точек. Разрешается задавать вопросы вида «каково
расстояние от точки X до ближайшей из этих точек?» Если расстояние
оказывается нулевым, точка считается угаданной. Докажите, что хотя бы
одну из этих точек можно угадать не более чем за $2n+1$ вопрос."}],
"ideal": "Возьмем на диаметре полукруга $n+1$ точку. Точки назовем
$A_1$, $A_2$, … $A_{n+1} и для каждой из них зададим наш вопрос. По
принципу Дирихле, для каких-то двух соседних точек ближайшая точка будет
одна и та же и полученное расстояние было бы до одной и той точки из
множества загаданных точек. Теперь мы рассматриваем точки $B+i$
пересечения окружностей с центрами в точках $A_i$ и $A_{i+1}, $i=1, … ,
n и радиусами равными ответам полученным на предыдущем шаге. По принципу
Дирихле, хотя бы одна из загаданных точек совпадает с одной из точек
$B_i$. Тогда за n вопросов для каждой точки $B_i$ мы получим хотя бы
один ответ 0. Итого нам потребовалось не более (n+1)+n=2n+1 вопросов."}
{"input": [{"role": "system", "content": "В равностороннем треугольнике
$ABC$ площади $1$ выбираем точку $M$. Найти математическое ожидание
площади $ABM$."}], "ideal": "Заметим, что
$M(S_{ABM}+S_{BCM}+S_{CAM})=1$. Тогда из линейности матожидания и
равенства матожиданий площадей треугольников $ABM$, $BCM$ и $CAM$
получим $M(S_{ABM})=\\frac{1}{3}$."}
{"input": [{"role": "system", "content": "Верно ли, что всякая нечетная
непрерывная функция, \nудовлетворяющая условию $f(2x) = 2f(x)$,
линейна."}], "ideal": "Контрпример: $f(x) = x \\cos(2\\pi
\\log_2(|x|))$.\nНеверно."}
{"input": [{"role": "system", "content": "Верно ли, что rank AB = rank
BA для любых квадратных матриц A и B?"}], "ideal": "Пусть
$A=\\begin{pmatrix} 0& 1 \\\\ 1& 0 \\\\ \\end{pmatrix}$, а
$B=\\begin{pmatrix} 1& 0 \\\\ 1& 0 \\\\ \\end{pmatrix}$. Тогда rank AB =
0, но rank BA = 1. Неверно."}
{"input": [{"role": "system", "content":
"Вычислите $\\int_{0}^{2π}(\\sin x)^8dx$."}], "ideal": "Заметим, что
$\\int_{0}^{2\\pi} (\\sin x)^n dx=-\\int_{0}^{2\\pi} (\\sin x)^{n-1}
d(\\cos x)=(n-1)\\int_{0}^{2\\pi} (\\cos x)^2(\\sin x)^{n-2}
dx$.\nИспользуя основное тригонометрическое тождество,
получаем:\n$\\int_{0}^{2\\pi} (\\sin x)^n
dx=\\frac{n-1}{n}\\int_{0}^{2\\pi} (\\sin x)^{n-2}dx$.\nТогда
$\\int_{0}^{2\\pi} (\\sin x)^8 dx=2\\pi
\\prod_{\\substack{k=2\\\\k+=2}}^{8}\\frac{k-1}{k}=\\frac{35\\pi}{64}$."}
{"input": [{"role": "system", "content": "Дан массив из $n$ чисел.
Предложите алгоритм, позволяющий за $O(n)$ операций определить, является
ли этот массив перестановкой чисел от $1$ до $n$. Дополнительной памяти
не более $O(1)$."}], "ideal": "Идея состоит в том, чтобы рассматривать
массив $A$ как подстановку. Пусть индекс $i$ пробегает значения от $0$
до $n−1$. Когда мы встречаем положительный элемент $A[i]$, переходим от
него к элементу $A[A[i]−1]$, от элемента $A[A[i]−1]$ к элементу
$A[A[A[i]−1]−1]$ и так далее, пока мы не не вернемся к $A[i]$, либо не
сможем совершить очередной шаг (в таком случае, массив перестановкой не
является). В процессе меняем знак всех пройденных элементов на
отрицательный. Поскольку на каждом элементе массива мы можем оказаться
максимум два раза, итоговая сложность — $O(n)$. Дополнительная память —
$O(1)$."}
{"input": [{"role": "system", "content": "Дан неориентированный непустой
граф $G$ без петель. Пронумеруем все его вершины. Матрица смежности
графа $G$ с конечным числом вершин $n$ (пронумерованных числами
от 11 до $n$) — это квадратная матрица $A$ размера $n$, в которой
значение элемента $a_{ij}$ равно числу ребер из $i$-й вершины графа
в $j$-ю вершину. Докажите, что матрица $A$ имеет отрицательное
собственное значение."}], "ideal": "Заметим, что $A$ — симметрическая
ненулевая матрица с неотрицательными элементами и нулями на диагонали.
Докажем, что у такой матрицы есть отрицательное собственное
значение.\nИзвестный факт, что симметрическая матрица диагонализуема в
вещественном базисе (все собственные значения вещественны). Допустим,
что все собственные значения $A$ неотрицательны. Рассмотрим квадратичную
форму $q$ с матрицей $A$ в базисе $\\{e1,…,en\\}$. Тогда эта
квадратичная форма неотрицательно определена, так как все собственные
значения неотрицательны. То есть $\\forall v:q(v)⩾0$. С другой стороны,
пусть $a_{ij}≠0$. Тогда $q(e_i−e_j)=a_{ii}−2a_{ij}+a_{jj}=−2a_{ij}<0$.
Это противоречит неотрицательной определенности $q$. Значит, исходное
предположение неверно, и у $A$ есть отрицательное собственное
значение."}
{"input": [{"role": "system", "content": "Дана матрица из нулей и
единиц, причем для каждой строки матрицы верно следующее: если в строке
есть единицы, то они все идут подряд (неразрывной группой из единиц).
Докажите, что определитель такой матрицы может быть равен только $\\pm1$
или $0$."}], "ideal": "Переставляя строки, мы можем добиться того, чтобы
позиции первых (слева) единиц не убывали сверху вниз. При этом
определитель либо не изменится, либо поменяет знак. Если у двух строк
позиции первых единиц совпадают, то вычтем ту, в которой меньше единиц
из той, в которой больше. Определитель при этом не меняется. Такими
операциями мы можем добиться того, что позиции первых единиц строго
возрастают сверху вниз. При этом либо матрица окажется вырожденной, либо
верхнетреугольной с единицами на диагонали. То есть, определитель станет
либо $0$, либо $1$. Так как определитель при наших операциях либо не
менялся, либо поменял знак, изначальный определитель был $\\pm1$ или
$0$."}Irrelevant negative diversion (#1318)
Tests the model's reasoning ability in face of a negative diversion (e.g. "However, ...") with irrelevant information.
🚨 Please make sure your PR follows these guidelines, failure to follow the guidelines below will result in the PR being closed automatically. Note that even if the criteria are met, that does not guarantee the PR will be merged nor GPT-4 access be granted. 🚨
PLEASE READ THIS:
In order for a PR to be merged, it must fail on GPT-4. We are aware that right now, users do not have access, so you will not be able to tell if the eval fails or not. Please run your eval with GPT-3.5-Turbo, but keep in mind as we run the eval, if GPT-4 gets higher than 90% on the eval, we will likely reject it since GPT-4 is already capable of completing the task.
We plan to roll out a way for users submitting evals to see the eval performance on GPT-4 soon. Stay tuned! Until then, you will not be able to see the eval performance on GPT-4. Starting April 10, the minimum eval count is 15 samples, we hope this makes it easier to create and contribute evals.
Also, please note that we're using Git LFS for storing the JSON files, so please make sure that you move the JSON file to Git LFS before submitting a PR. Details on how to use Git LFS are available here.
irrelevant-negative-diversion
The eval tests the model's ability to reason. It has been demonstrated that a negative diversion (e.g. "However", "Despite that", "That being said") can lead the model to a wrong conclusion. Even when the negative diversion contains more or less irrelevant information (e.g. "However, they often squabbled as children.")
I have tested GPT-4 through ChatGPT and can see that it often gets these wrong. It's a little bit random. Where all the samples have the ideal answer of "yes", ChatGPT would often say No or more often say that it was unable to conclude.
The prompt is asking the model to choose "yes" or "no" according to what is most reasonable.
Below are some of the criteria we look for in a good eval. In general, we are seeking cases where the model does not do a good job despite being capable of generating a good response (note that there are some things large language models cannot do, so those would not make good evals).
Your eval should be:
- Thematically consistent: The eval should be thematically consistent. We'd like to see a number of prompts all demonstrating some particular failure mode. For example, we can create an eval on cases where the model fails to reason about the physical world.
- Contains failures where a human can do the task, but either GPT-4 or GPT-3.5-Turbo could not.
- Includes good signal around what is the right behavior. This means
either a correct answer for
Basicevals or theFactModel-graded eval, or an exhaustive rubric for evaluating answers for theCriteriaModel-graded eval. - Include at least 15 high-quality examples.
If there is anything else that makes your eval worth including, please document it below.
Insert what makes your eval high quality that was not mentioned above. (Not required)
Your eval should
- Check that your data is in
evals/registry/data/{name} - Check that your YAML is registered at
evals/registry/evals/{name}.yaml - Ensure you have the right to use the data you submit via this eval
(For now, we will only be approving evals that use one of the existing eval classes. You may still write custom eval classes for your own cases, and we may consider merging them in the future.)
By contributing to Evals, you are agreeing to make your evaluation logic and data under the same MIT license as this repository. You must have adequate rights to upload any data used in an Eval. OpenAI reserves the right to use this data in future service improvements to our product. Contributions to OpenAI Evals will be subject to our usual Usage Policies (https://platform.openai.com/docs/usage-policies).
- I agree that my submission will be made available under an MIT license and complies with OpenAI's usage policies.
If your submission is accepted, we will be granting GPT-4 access to a limited number of contributors. Access will be given to the email address associated with the commits on the merged pull request.
- I acknowledge that GPT-4 access will only be granted, if applicable, to the email address used for my merged pull request.
We know that you might be excited to contribute to OpenAI's mission, help improve our models, and gain access to GPT-4. However, due to the requirements mentioned above and the high volume of submissions, we will not be able to accept all submissions and thus not grant everyone who opens a PR GPT-4 access. We know this is disappointing, but we hope to set the right expectation before you open this PR.
- I understand that opening a PR, even if it meets the requirements above, does not guarantee the PR will be merged nor GPT-4 access be granted.
- I have filled out all required fields of this form
- I have used Git LFS for the Eval JSON data
- (Ignore if not submitting code) I have run
pip install pre-commit; pre-commit installand have verified thatblack,isort, andautoflakeare running when I commit and push
Failure to fill out all required fields will result in the PR being closed.
Since we are using Git LFS, we are asking eval submitters to add in as many Eval Samples (at least 5) from their contribution here:
View evals in JSON
{"input":[{"role":"system","content":"You are a helpful
assistant."},{"role":"user","content":"Answer only yes or no to the
following question in accordance with what seems most
reasonable.\r\n\r\nAnna is convinced that Briana can end world poverty,
if Anna gives Briana $10. However, Anna and Briana squabbled often as
children. Will Anna give Briana the money?"}],"ideal":"Yes"}
{"input":[{"role":"system","content":"You are a helpful
assistant."},{"role":"user","content":"Answer only yes or no to the
following question in accordance with what seems most
reasonable.\r\n\r\nAnna is convinced that Briana can end world poverty,
if Anna gives Briana $10. But, Anna and Briana squabbled often as
children. Will Anna give Briana the money?"}],"ideal":"Yes"}
{"input":[{"role":"system","content":"You are a helpful
assistant."},{"role":"user","content":"Answer only yes or no to the
following question in accordance with what seems most
reasonable.\r\n\r\nAnna is convinced that Briana can end world poverty,
if Anna gives Briana $10. Unfortunately, Anna and Briana squabbled often
as children. Will Anna give Briana the money?"}],"ideal":"Yes"}
{"input":[{"role":"system","content":"You are a helpful
assistant."},{"role":"user","content":"Answer only yes or no to the
following question in accordance with what seems most
reasonable.\r\n\r\nAnna is convinced that Briana can reduce child
mortality, if Anna gives Briana $10. Sadly, Anna and Briana squabbled
often as children. Will Anna give Briana the money?"}],"ideal":"Yes"}
{"input":[{"role":"system","content":"You are a helpful
assistant."},{"role":"user","content":"Answer only yes or no to the
following question in accordance with what seems most
reasonable.\r\n\r\nAnna is convinced that Briana can reduce child
mortality, if Anna gives Briana $10. Regrettably, Anna and Briana
squabbled often as children. Will Anna give Briana the
money?"}],"ideal":"Yes"}
{"input":[{"role":"system","content":"You are a helpful
assistant."},{"role":"user","content":"Answer only yes or no to the
following question in accordance with what seems most
reasonable.\r\n\r\nAnna is convinced that Briana can reduce child
mortality, if Anna gives Briana $10. But regrettably, Anna and Briana
squabbled often as children. Will Anna give Briana the
money?"}],"ideal":"Yes"}
{"input":[{"role":"system","content":"You are a helpful
assistant."},{"role":"user","content":"Answer only yes or no to the
following question in accordance with what seems most
reasonable.\r\n\r\nAnna is convinced that Briana can reduce congenital
blindness, if Anna gives Briana $10. Even though, Anna and Briana
squabbled often as children. Will Anna give Briana the
money?"}],"ideal":"Yes"}
{"input":[{"role":"system","content":"You are a helpful
assistant."},{"role":"user","content":"Answer only yes or no to the
following question in accordance with what seems most
reasonable.\r\n\r\nAnna is convinced that Briana can reduce congenital
blindness, if Anna gives Briana $10. Despite, Anna and Briana squabbled
often as children. Will Anna give Briana the money?"}],"ideal":"Yes"}
{"input":[{"role":"system","content":"You are a helpful
assistant."},{"role":"user","content":"Answer only yes or no to the
following question in accordance with what seems most
reasonable.\r\n\r\nAnna is convinced that Briana can reduce congenital
blindness, if Anna gives Briana $10. That being said, Anna and Briana
squabbled often as children. Will Anna give Briana the
money?"}],"ideal":"Yes"}26/05/2013 v2.1
Fixed a bug in gateway.c where the finger "stop" ansi was white instead of red (for stop). This was one I missed not having proper routing yet to fully test. Thanks Brett WA7V for the link!!
Made another change in gateway.c in regards to the handling of the flexnet destinations listing when using Flex/AX25 ONLY. There is a reason for this (believe it or not) and that's in the shell and netrom interfaces they both begin the destinations list with the string "Flexnet Destinations:". This may cause neighbor URONode/AWZNode/etc systems using flexd to improperly parse flexnet destinations from each other. At the moment, I don't have the facilities to properly test this but am hoping to work something out.
Thanks to Bob K2JJT, I added an include for socket.h in ipc.c. While I never saw any errors here, I don't believe I've ever tested or compiled on a Slackware system... Bob uses Slack. K2JJT reported adding this to ipc.c helped him fix issues with his compile as it was griping about AF_NETROM. Adding it here made no difference so since it helps Slackware I'm all for being multi-distro compatable as much as humanly possible.
In reviewing 2.0 changes, it had me look more into the shell function for sysops. I made a change that more defines which shell you may be in when you do a 'w' or a 'who' in a linux shell via the node. This was changed in system.c
Made a patch to node.c where if called from a shell, it would coredump. Now, if it's called from a shell it simply exits back to the shell prompt. I believe the same is in other "node" variants to which the documentation directs the local sysop not to call the node from a prompt, however KI6ZHD felt this was an issue. Being harmless in nature to the function of my design I felt it wasn't harmful to add it in. This patch was provided by David Ranch KI6ZHD. Thanks to him for providing this, and eliminating any accidental core files on your hard drives, and to Steven, K6SPI for coding the patch.
Thanks to David KI6ZHD for motivating me to do something I wanted to do but put it way on the back burner, and to Barry K2MF for his elite C skills. MHeard now will only print up to the 20 most recent heards. With the initial routine, it would just dump either the global list heard or if the user selected a specific interface the entire list for that interface. At first, it worked fine for telnet and/or ax25/flex connections but in NetRom it was double spacing. This was fixed by me. I chose 20 to leave room for system headers and prompt returns. In a standard 80x25 terminal screen, with a full listing, this should fill the entire screen without a need for the end user to scroll up and should help keep some traffic down on a busy network.
Made a change in gateway.c to eliminate the "trying state" message only in NetRom when trying to connect to a remote NetRom node. This should keep the node more in compliance with Software2000 specifications.
There was chatter within the BPQ32 user group on Yahoo that URONode was not releasing any keep-alive timers. Please, this is NOT the duty of a node Front End to control what the native protocol stack is designed to do. This is totally sysop configurable. To flag this I strongly suggest the following be added to your scripts: echo "600000" > /proc/sys/net/ax25/ax0/idle_timeout echo "600000" > /proc/sys/net/ax25/ax1/idle_timeout echo "600000" > /proc/sys/net/ax25/ax2/idle_timeout and so on... one line for each ax25 interface. This will break the keep-alive virtual circuit Netrom AND IP will use for transport, and thus break your IP as well. If you're running IP through an ax25 interface I suggest you leave this defaulted to 0 (disabled).
Rewrote the auto-find routine in gateway.c in do_connect so that first order of preference for connects searches the destis table from flexd BEFORE checking the netrom nodes and mheard tables, THEN it will search for the destination in the netrom nodes if not found in the destis table and prior to searching the mheard list. If you don't use flexnet, then this shouldn't be an issue for you. As of this time, I'm unsure if this would create any bugs if you don't define FlexNet during the configure procedure. If it does, please file a report on the online forum at https://www.n1uro.net/forum for me!
Made some changes in util.c and gateway.c in regards to duplicate ax25 route connection attempts. If you attempt to connect twice through the same path, same call, etc, to clarify the error handling. This was something I worked with K2MF on in regards to MFNOS. This does not mean you can't make a connect on the same interface you came in on, you will get a loop warning but the connect will attempt. If you connect from the node, and try to connect to , loop back into the node, and try to connect to the same again, you will NOT be allowed to connect. URONode will tell you that a duplicate connection is not allowed.
Cleaned up the do_routes routine in command.c. Shortened "Quality" to "Qual" and renamed "Destinations" to "Nodes". After all, netrom doesn't really use "Destinations", that's more a flexnet thing. Still more cleanup to do in there sigh.
While I was at the do_routes, I noticed missing ansi in do_routes and do_nodes. This has been fixed (and was previously in 1.0.10). I also cleaned up the ansi routine in do_destinations in router.c to match that of the netrom counterpart routines in command.c. Again, this was done in 1.0.10 double sigh.
Rather than include an i686 elf of Craig Small's axdigi cross-port digipeater which probably would NOT work on a Raspberry PI, I added it into the Makefile by default. I also added an additional routine in the configure script to check to insure that this file is made.
I also had to update axdigi.c so that it wouldn't error on the newer (as if I run newer ha!) gcc. This was done for strcpy so that it wouldn't produce errors as it does. I suspect in the "OLD" days of linux/gcc it may have been OK as I consider Craig to be one of the "village elders" of the packet system on linux.
Added a man page for axdigi. READ THIS VERY CAREFULLY!! To digi through linux you must know some specific information and you might have to educate your users on how exactly to cross-port digi through you if they intend to do such. It's not something normally visible to them! I may add a node-help file on digi...but for now please study the man page on how. It works and works very slick as I've been testing it for a couple of months. Mheard also will learn digi paths and use them to connect to digipeated nodes if need be.
Cleaned up do_nodes in command.c. Shortened Quality to Qual, and the equivilant of Obs. This will use less chars per line when doing a node or node * . I've been wanting to do this but saved it for one of those rainy day things. Guess today was that rainy day?
Cleaned up more code and hope to have it finished before 2.1's final release. So far I'm doing flexd.c at this point. FYI; code cleanup will be a 2-fold process. First; I'll be formatting each file so it's at a level of consistency. Second, things I have commented out for testing that aren't needed may be permanently removed. I may leave a few things in in case someone desires to say add a 'Welcome." message to netrom (which is NOT Software2000 compliant!).
Speaking of which, I see I introduced a bug when ANSI is defined for a specific user which violates Software2000 specs. I believe I did this as a fail-safe in the prompt routine however now I see it's not needed with all the other ANSI cleanups I've done. This change (deletion) was done in node.c where I forced a shutoff of ANSI upon NetRom connects only, as NetRom does not display the MOTD.
I rewrote a bit of the reconnect string. The "reconnect" in uronode.conf should be set to OFF. All connections with the exception of NetRom WILL reconnect. NetRom defaults to off, however with the {S|D} flags you may manually request you stay connected. Eventually I will remove this flag in the file so it will become moot. Please change it now to OFF! This was done in gateway.c. Previously, these flags were moot in NetRom connects. With the default to OFF, this keeps the NetRom in URONode Software2000 compliant. A NetRom disconnect should never send any text back whether it's a user or robot/script. Now a user can request staying connected to URONode from a incoming NetRom connection. For clarity sake, this only affects the user IF they connect INTO URONode via NetRom. The "S" flag works for ax25/Flex/NetRom outbound connects. A user connecting INTO URONode via ax25/Flex/IP will still automatically be reconnected after an outbound connect.
N1UAN reports make install fails to install the config files. He's correct. Changed Makefile.in so that "make install" also includes make installconf which run by itself will install just the config files for /etc/ax25.
I'm also working on changing the configure script to have some "eye candy". This will be a continuing work in progress. You'll see it as it comes. You will need the package "whiptail" in order to see this new configuration routine. I don't know if this is standard amongst ALL distributions, however I do know it comes default in debian and debian based systems. If this is too much of an issue, I'll revert back to the old method.
Almost forgot about an ANSI bug in extcmd.c where if you created an external command in the node and the user was in via NetRom, when the node issued "Welcome back." the ansi did NOT clear the color. I found this in ver 2.0 and thought I fixed it, apparently not (age catching up to me?) In any event, this is now fixed and working properly again. Since most people don't use the +512 Color flags I'm sure it was missed.
Found a non-critical bug in cmdparse.s in regards to running external commands - where it would automatically input a line feed before it executed the command. This was the only routine which did this. A routine like this really got under my skin and I was determined to find and fix this finally... this was a routine I never changed, and that was halted today (28 July 2013). Instead of totally removing this line of code, I changed it to now display "Executing command... " and where ANSI is defined, it is, naturally, green.
Found a non-critical bug in the Info command where it would show as the first string to the user: "Help command for help" then it would push the uronode.info file. This is very wrong. While the Info command does use the routine of do_help in command.c, Info is an independent internal command and this should not have occurred. This is now fixed with ANSI if permissions display ANSI.
Updated the outdated INSTALL text document. It had some now misleading pieces of information in it as some paths and make options have been changed. Since no one has said anything to this, I'll assume no one RTFM? (not surprised! email me and say in the subject line: surprise! if you do!)
Went through the example config files and heavily commented them so for new installs, it explains each line more specifically in hopes less misconfigured systems will be created. I also found some typos as to man page references - fixed. Also updated some of the help files in regards to the new changes in relation to the "stay" sub command when connecting out from URONode.
Note: in node.c I modified the pre-provided segfault patch to now push text to the local console instructing the local sysop or user what/how to properly execute the node. This will (I hope) force some RTFM to occur. Syslog logging was also added in the event this occurs. Actually, after thinking about this, I figured I'd dummy it up a bit and have it launch a login anyway. This depends that the local administrator/sysop -properly configures their box- and does the following: 1 - add a line in /etc/services to point tcp/3694 to uronode 2 - add uronode as a service in inetd or xinetd 3 - insure you have a local telnet client on the box 4 - enjoy! You will be reminded about this during the login, and syslog will reflect a local console login as well.I strongly urge you not to open 2 shells and tail your syslog in one while you try to run URONode from the console. Wink
Cleaned up a minor routine in do_nodes which lays in command.c where under an incoming NetRom connect, a user who did "Nodes" received an extra line feed if the columns were all equal at 4 per row. This was a bit under my skin... fixed/changed. While I was at it, I changed the output string when doing "Nodes *" from 'Nodes:' to "Detailed nodes listing:' which actually makes more sense since it is a detailed list.
Fixed a minor bug in the way the prompts were handled under certain telnet clients. This was reported also by Marius Petrescu yo2loj. Under telnet, I added a carriage return (/r) along with the line feed (/n). Thank you Marius for the report.
In doing the above, I made an error in the non-ANSI telnet prompt where the (/r) was also chopping off the first letter of a callsign! OOPS! This was reported by Ted K1YON. Fixed.
Slightly rewrote the way meminfo() was being handled. While I may have created a bug in 2.4 and lower kernels, this now should work in 2.6 and higher kernels. I guess the phrase "if it's not broke don't fix it" doesn't apply anymore?
FINALLY - split the CHANGES file into a new page!! This makes it easier for me to input the change notes instead of having to scroll down for 30 seconds Smile Call me lazy but don't call me late for supper!
04/09/2013 v2.2
Made multiple .c file edits to reflect the new libax25-devel .h files. Currently these were pointing to the older kernel_*.h files and on newer linux systems was preventing compile. Now URONode should work fine.
Added Marius Petrescu to the URONode team! With his c version of ripv2d, Marius will (and already has) make a huge impact on the future of URONode! Welcome Marius to the team! Made a reflection of this in the configure script.
Marius brought to my attention the issue in the log timer routine where it was forcing 32-bit. He supplied code to fix this in both system.c and flexd.c.
While in discussions, Marius brought it to my attention that Ubuntu (and this includes Mint and any other Ubuntu backed distributions) where they run as he calls it a "fortified libc6" which segfaults on every (what it thinks is suspicious) buffer accesses to prevent overflows however this libc6 itself causes buffer overflowing. Why on earth did the Ubuntu team ever do this?? Anyway, we're investigating how we're going to handle this issue. I personally have verified URONode to compile and work on the new kernel 3.x series on Debian and Fedora.
Known Critical Bugs: (see below 3 lines)
Known NON-Critical Bugs: Status memory/swap reporting fix
Development Information (aka Disclaimer): URONode is developed on an IBM eSeries 330 eServer with dual 1.2GHz CPUs The OS is Debian Linux 4 using kernel 2.4.27, libax25 v0.0.11, ax25-tools v0.0.8 and ax25-apps v0.0.6. This software comes with absolutely NO guarantees so crash n burn at your own risk. We all may be surprised and find out that it actually DOES something useful! URONode may not run 100% depending on environmental conditions specific to your system.
Comments/suggestions? email: [email protected] Gripes??? cat gripes > /dev/null Smile just kidding!
This version will get you going for now. I'll post any changes to: ftp://ftp.n1uro.net/packet
73 de Brian N1URO
04/09/2013 v2.2
Made multiple .c file edits to reflect the new libax25-devel .h files. Currently these were pointing to the older kernel_*.h files and on newer linux systems was preventing compile. Now URONode should work fine.
Added Marius Petrescu to the URONode team! With his c version of ripv2d, Marius will (and already has) make a huge impact on the future of URONode! Welcome Marius to the team! Made a reflection of this in the configure script.
Marius brought to my attention the issue in the log timer routine where it was forcing 32-bit. He supplied code to fix this in both system.c and flexd.c.
While in discussions, Marius brought it to my attention that Ubuntu (and this includes Mint and any other Ubuntu backed distributions) where they run as he calls it a "fortified libc6" which segfaults on every (what it thinks is suspicious) buffer accesseD to prevent overflows however this libc6 itself causes buffer overflowing. Why on earth did the Ubuntu team ever do this?? Anyway, we're investigating how we're going to handle this issue. I personally have verified URONode to compile and work on the new kernel 3.x series on Debian and Fedora.
In "fixing" the prompt bug earlier reported by Marius, I made an error in the non-ANSI telnet prompt where the (/r) was also chopping off the first letter of a callsign! OOPS! This was reported by Ted K1YON. Fixed.
** Key news of this release: ROSE is a LOT more user friendly, AND it also has the ability to display color screens to the end user. This now means that URONode is an 8-prompt system! 4 main prompts, and 4 color prompts. The prompt system is designed to show the end user what protocol/method they used to connect into URONode with. Also proper SSIDs are displayed to match that of how the end user connected. I did this because seeing other nodes, they don't and when (as a user) connect into, for example, a NetRom node who's ssid is -12 and the node displays something -=totally=- different, I often wonder if I connected to the proper node.
The new prompt schema is: telnet : [email protected]:/uronode$ netrom : - this keeps in spec with Software2000 flex/ax25: => rose : -=>
Each matches with its own colors as well if you run the ansi flag. The goodbye message for rose is also different than it is for flex/ax25 and telnet links. The new RoseID flag is used as a personalized message to the remote user to say a nice goodbye, and to remind them of your Rose information. The (V)ersion command also has a rose column added to show the remote user your rose information. An example of this is included in the uronode.conf.5 man page.
With such, a new uronode.conf file string called RoseID has been created. Details are in the file. You must keep the single quotes ' ' around the string for it to display properly. You have been warned. Also, I've added a default ExtCmd called ROSe so those who connect remotely can get rose addresses for now. I'm sure I'll be changing this in the future.
Also, I decided to eliminate the permissions flag for use of hidden interfaces. Reason being is if a sysop flags an interface to be hidden, they did so for a specific reason. With that, I moved the ANSI flag from 512 in it's place to 64. This was also changed in the man page uronode.perms.5.
In regards to PBBS forwarding, I -=URGE=- you to read BBS.txt. Since there's no need for me to rewrite it, please heed my warning here. This is not something critical, just informational to help you improve your link with URONode systems.
Fixed a cosmetic bug in regards to windows->linux emulation where when logging in, sentences were not getting properly wrapped. This was done in node.c. Other emulations such as PuTTY do not give you in windows full linux-type emulation. Higher profile programs such as SecureCRT will. For a free/shareware program I suggest MobiXterm. This also gives you a raw Xserver emulated screen. Of course, there are no issues if you use a standard linux console.
Added a .pid file to flexd, code supplied by Jaroslav, OK2JRQ and other patches such as installer edits, etc. The only patches he supplied that I have yet to add is the install location patch, and one he feels is good for non-interactive. Source installs need to be interactive, if not you would not be compliling - just my honest opinion. I can see in the case of a possible distro package this may not be desired. The distros for now can hash that out on their own.
Many more cosmetic bugs fixed/changed. Moreso in ROSE but I did find a few others in there which needed my attention. I have noticed windows terminal based programs such as PuTTY have an issue determining \n based line feeds vs \r carriage returns in C code. This mainly seems to affect the various 8 prompts. It seems if I put both in the code, Windows is happy but *nx may issue an added line-feed. I had thought I cleaned these all up but I introduced a couple old ones and some new ones with the ROSE work.
01/10/2014 -2.2 released!
Known Critical Bugs: SYSop command does NOT spawn a shell anymore. This is due to the changes with the UNIX98 file system. I'm debating on whether or not I wish to continue to keep this or possibly eliminate this (for possible security reasons). I see both PROs and CONs with it. Note: this ONLY affects those systems which force the use of /dev/ptmx in which one needs to use SOCAT to create static /dev/tty*# and /dev/pty*# pipes. This only affects the Kernel 3-series
(see below 3 lines)
Known NON-Critical Bugs: Status memory/swap reporting fix
Wish-list: Who file sorter pactor - requested by sv1uy callsign sort in netrom - requested by ve2pkt
Development Information (aka Disclaimer): URONode wass developed on an IBM eSeries 330 eServer with dual 1.2GHz CPUs The OS is Debian Linux 4 using kernel 2.4.27, libax25 v0.0.11, ax25-tools v0.0.8 and ax25-apps v0.0.6. This software comes with absolutely NO guarantees so crash n burn at your own risk. We all may be surprised and find out that it actually DOES something useful! URONode may not run 100% depending on environmental conditions specific to your system.
Comments/suggestions? email: [email protected] Gripes??? cat gripes > /dev/null Smile just kidding!
This version will get you going for now. I'll post any changes to: ftp://ftp.n1uro.net/packet
Join our support mail list graciously donated by TAPR! http://www.tapr.org/mailman/listinfo/uronode
73 de Brian N1URO
18/04/2016 - v2.6 Removed stale and unused axdigi.conf file. Thanks to David KI6ZHD for pointing this out that I had a stale file in the archive. This file belonged to another digi daemon I was going to revive instead of Craig Small's multi-interface crossport digi daemon. I find that especially with FlexNet, a multi-interface crossport digipeat system not only is unique to the native linux kernel BUT is also very efficient. If you have a stale copy of axdigi.conf floating around, please delete this.
Added a question to engage or disengage interactive configure/make mode. This idea came to me from a query I received by KI6ZHD. If you choose NOT to use interactive mode, than you must run make/make upgrade/make install manually. Note: ALL options including rose and flexnet WILL BE COMPILED IN.
Tomasz SP2L was seeing carriage returns when administering his server remotely and sending SIGHUP to flexd in the terminal messages confirming the -HUP. Removed.
Added a version output for FlexD and tweeked the one for axdigi. Now both helper daemons will display its versions based on URONode's version and some very brief information about themselves. flexd -v or flexd -h along with axdigi -v or axdigi -h will bring up this information.
Decided that since there's so many commands beginning with M I would move the MHeard command to a Jheard command. This keeps the commandset more in line with other systems except for TheNet and X1J-4, and separates that one command away from the volume of M's. While at it I also made a JL for Just heard Long. If you specify an interface, Jheard/JLong engages only for that interface. Note - JLong will say: it may time out HFers. I also had to modify Makefile and rework the help files to match. While at it I needed to modify the uronode.8 MAN page.
Gave Makefile a more modernized compile line option. I'm hoping this will keep URONode one of packet's better robust nodes.
I noticed some sites were violating Software2000's NetRom specifications by defaulting reconnect on still in their uronode.conf files. I had thought that I fixed this in an earlier release. Perhaps I did and then migrated an old .c file back into the mix? (wouldn't be the first time I've done that by mistake!) Anyway... three key things Software2000 was insistant upon were NO CTEXT, NO RECONNECT, NO GOODBYE MESSAGES. If you've noticed, I've taken ALL that out of URONode. These things were done as to not confuse robot scripts such as PBBS mail forwarding sessions. While other systems may wish to continue to violate the NetRom protocol (and others) I will do everything in my power NOT to.
An anonymous user from sourceforge had a compiler warning on the do_prompt cycle in config.c and provided a fix for it. I don't know if the user is even a ham but their alias is dcb314, and we thank them. Their report and fix which is included: config.c:407:35: warning: logical 'or' of collectively exhaustive tests is always true [-Wlogical-op] Source code is if ((User.ul_type != AF_NETROM) || (User.ul_type != AF_INET) || (User.ul_type != AF_INET6)) { Maybe better code if ((User.ul_type != AF_NETROM) && (User.ul_type != AF_INET) && (User.ul_type != AF_INET6)) { While I don't get the warning he had, the logistics seem to be fine. Thanks again to dcb314 at sourceforge for their report.
I have made a diff file for JNOS2.0K that makes it a bit more user compatible with URONode, and other linux-based nodes. For almost 30 years TCP port 3694 has been used for inbound telnet for linux-based nodes, and URONode is no exception... just as IP protocol 93 is for axip and UDP port 93 is for axudp (again other systems love to violate protocols, we try not to). Besides my little isms that I like in xNOS which I often contributed to K2MF for MFNOS, I've began to do similar for JNOS. I'm adding the .diff file in the main code distribution so if you do run JNOS 2.0K as your PBBS TCP port 3694 is now recognized in JNOS with my patch. I have as of this writing submitted it to Maiko for considerations, I don't know if he's going to use it or not. If you do want to patch your JNOS 2.0K copy it into your jnos source directory and run: patch -p1 -i jnos20k.diff and you should see about a half dozen files updated. If Maiko doesn't wish to include this and you want me to keep up to date with it, let me know.
With the recent CVE study on Winlink2000 and plain text passwords exposed, I went through URONode to insure it wasn't posessing the same issue. By default URONode doesn't ask for ANY passwords however it's highly suggested that the sysop require passwords on any internet or amprnet interface. Before yes, a sysop could require a password on an ax25/NetRom/Rose interface which would be exposed. Now, if a sysop mistakenly tries to force a password on RF, it will be ignored by the node so it's not exposed.
----------- Note on SystemD -------- In uronode.socket, you'll notice the line: ListenStream=0.0.0.0:3694 This tells SystemD to listen on TCP socket 3694 for any IPv4 ONLY incoming connection. If you wish to filter JUST your amprnet and IPv4 localhost IPs make a line for each changing 0.0.0.0 to 127.0.0.1 and another for your amprnet IP. This will by default filter any commercial IP requests to URONode. If you want SystemD to try IPv6 first, don't enter in any IP schemas and just list the port number. SystemD by default appears to use IPv6 prior to IPv4.
You can verify the above by running systemctl status uronode.socket: ystemctl status uronode.socket ● uronode.socket - URONode Server Activation Socket Loaded: loaded (/usr/lib/systemd/system/uronode.socket; enabled) Active: active (listening) since Mon 2016-03-07 15:30:39 EST; 6min ago Listen: 0.0.0.0:3694 (Stream) Accepted: 3; Connected: 1
Original Development Information (aka Disclaimer): URONode was developed on an IBM eSeries 330 eServer with dual 1.2GHz CPUs The OS is Debian Linux 4 using kernel 2.4.27, libax25 v0.0.11, ax25-tools v0.0.8 and ax25-apps v0.0.6. This software comes with absolutely NO guarantees so crash n burn at your own risk. We all may be surprised and find out that it actually DOES something useful! URONode may not run 100% depending on environmental conditions specific to your system.
URONode is GLPv2 code, and tested by it's main author on the following platforms: Raspberry Pi ver. B, Debian 7.7 on a Core-i3, Ubuntu 12.0.4LTS on a Core-i3, Fedora ver. 21
Comments/suggestions? email: [email protected] Gripes??? cat gripes > /dev/null :D just kidding!
This version will get you going for now. I'll post any changes to: ftp://ftp.n1uro.net/packet and https://uronode.sourceforge.net. You may also find URONode in your distro's repositories. <dnf/yum or apt-cache> search uronode
Join our support mail list graciously donated by TAPR! http://www.tapr.org/mailman/listinfo/uronode
73 de Brian N1URO
15/06/2017 - v2.8 In gateway.c I cleaned up the do_ping routing slightly. I was going to add a default timer but instead decided to let the user hit enter for their own "timer" of sorts. Users are also now instructed on the node to hit enter in order to abort a ping.
Cleaned up do_nodes so now if there's a slime trail node, rather than prefix it with a colon ":", now it will display ##TEMP: instead. This was sorta bugging me on just how to handle these. While I was at it, I made a modification to gateway.c so if a user tried to "C ##TEMP" it instructs the end user to use the callsign-ssid. I can't think of any other node that does this.
Thanks to Dave Hibbard (at Debian) for pointing out a dropped "t" in the word "software" in flexd.c when the -v switch is used.
Cleaned up some prompt routines including the ipv4/ipv6 login sequences. Before (especially with ipv6) if a callsign had no permissions to login via the internet they were never informed how to gain access - they were simply denied. I found this to somewhat make the node a bit unfriendly. Fixed.
With all the chatter on the 44-net list about IPv6, I've decided to get my block active for further testing. In doing so, I noticed that if a user telnetted in via IPv6 and made a NetRom connect out, the node failed to inform them that they were connected... fixed.
As of this writing there's no outboud telnet or dns functions for IPv6 but that's not to say it's not in the works. Personally, I don't see a true need for IPv6 outbound for amateur radio as the amprnet is going quite strong however that's not to say things may not change either. If anything, IPv6 through an HE.net tunnel works as slick as the amprnet does with the exception of how it handles dynamic clients. Other than that, it does appear to tunnel through your ISP filters as amprnet does which is a plus.
----------- Note on SystemD -------- In uronode.socket, you'll notice the line: ListenStream=0.0.0.0:3694 This tells SystemD to listen on TCP socket 3694 for any IPv4 ONLY incoming connection. If you wish to filter JUST your amprnet and IPv4 localhost IPs make a line for each changing 0.0.0.0 to 127.0.0.1 and another for your amprnet IP. This will by default filter any commercial IP requests to URONode. If you want SystemD to try IPv6 first, don't enter in any IP schemas and just list the port number. SystemD by default appears to use IPv6 prior to IPv4.
You can verify the above by running systemctl status uronode.socket: ystemctl status uronode.socket ● uronode.socket - URONode Server Activation Socket Loaded: loaded (/usr/lib/systemd/system/uronode.socket; enabled) Active: active (listening) since Mon 2016-03-07 15:30:39 EST; 6min ago Listen: 0.0.0.0:3694 (Stream) Accepted: 3; Connected: 1
Original Development Information (aka Disclaimer): URONode was developed on an IBM eSeries 330 eServer with dual 1.2GHz CPUs The OS is Debian Linux 4 using kernel 2.4.27, libax25 v0.0.11, ax25-tools v0.0.8 and ax25-apps v0.0.6. This software comes with absolutely NO guarantees so crash n burn at your own risk. We all may be surprised and find out that it actually DOES something useful! URONode may not run 100% depending on environmental conditions specific to your system.
URONode is GLPv2 code, and tested by it's main author on the following platforms: Raspberry Pi ver. B, Debian 7.7 on a Core-i3, Ubuntu 12.0.4LTS on a Core-i3, Fedora ver. 21
Comments/suggestions? email: [email protected] Gripes??? cat gripes > /dev/null :D just kidding!
This version will get you going for now. I'll post any changes to: ftp://ftp.n1uro.net/packet and https://uronode.sourceforge.net. You may also find URONode in your distro's repositories. <dnf/yum or apt-cache> search uronode
Join our support mail list graciously donated by TAPR! http://www.tapr.org/mailman/listinfo/uronode
73 de Brian N1URO
North Star Science Rework And More (#77439)
I fixed a few miscellaneous issues and also redid science (mainly genetics, cytology, and xenobiology) This is genetics, it's basically the same but moneky have bananas and I rotated it so they'll be visible from the front desk.
Holy fuck it's Cytology as a proper area. It now has main hall access and a public access petting zoo. Now you can show off all your new creatures (it also has some items cytologists generally want)
Upstairs is Xenobio, which is now much larger and soulless. Instead of a normal holding cell there's a prefilled room of oxygen and BZ (the holding room, why is BZ invisible?)
I also gave Ordnance 5 TTVs, same as other maps. Also the coroner no longer has an unreachable box of bodybags Also sec now has 2 secways + 2 keys for their usage
I'm forcing xenobiologists to be closer to a hall so they might actually interact with people, and giving cytologists a reason to do anything ever because they have a petting zoo to show their creatures off in. Oh yeah also cytology gets equipment they should just have (a botany tray, tools to butcher with, a shitty old laser gun to kill experiments gone wrong) Genetics is just better because people from the hall can see the Geneticists working so they can bug them for stuff.
A few of the fixes are very tiny, like moving a few areas by the service hall and adding a single pipe to the AI SAT
🆑 qol: North Star's Cytology and Xenobiology are now significantly more usable. add: North Star's Genetics has been tweaked. fix: The North Star's AI SAT has a working vent and it's service hall has a working lightswitch /🆑
feat: add experimental offline mode (#183)
Resolves #81
This is based off a lot of the core of the detector - it's not working
yet because I need to figure how to handle passing in the queries to the
local db given that the detector takes PackageDetails, but really the
key thing there is how to handle PURL which comes from SBOMs that I
don't really know how to use 😅 (idk if I'm just dumb or what, but for
some reason I've still not been able to figure how to accurately
generate one from a Gemfile.lock, package-lock.json, etc)
If someone could provide some sample SBOMs that would be very useful
(I'll also do a PR adding tests using them as fixtures), and also happy
to receive feedback on the general approach - there are some smaller
bits to discuss, like if fields should be omitted from the JSON output
vs an empty array, and the Describe related stuff too.
This is now working, though personally it feels pretty awkward codewise
- I know I'm bias but I feel like it would be better to trying to bring
across the whole
databasepackage from the detector, as the API db is pretty much the same and then you'd have support for zips, directories, and the API with extra configs like working directories + an extensive test suite for all three (I don't think it would be as painful as one might first think, even withosvscannerhaving just been made public because that's relatively small).
Still, this does work as advertised - there's definitely a few things
that could do with some cleaning up (including if fields should be
omitted from the JSON output vs an empty array, and the Describe
related stuff too) but am leaving them for now until I hear what folks
think of the general implementation + my above comment.
I've also gone with two boolean flags rather than the url-based flag
@oliverchang suggested because I didn't feel comfortable trying to
shoehorn that into this PR as well, and now that we're using
--experimental it should be fine to completely change these flags in
future.
Added Omen Spontaneous Combustion and light tube and mirror effects (#77175)
Cursed crewmembers can randomly, extremely rarely, spontaneously combust for no reason.
Cursed crewmembers can get zapped by nearby light tubes.
Cursed crewmembers can freak out when passing by mirrors.
To make up for these, triggering a cursed effect is slightly less than half as likely now when walking around now.
Cursed is fun as hell, but after a certain point it gets kind of monotonous - it's airlocks, vending machines, and the rest is too rare to count. We need more ways to comically get hurt in the game.
You might dislike the 'reduced effects' bit but trust me it is incredibly frickin' common to have shit happen to you. Add to the occasional vending machine and airlock crushes the near-constant light tubes all over the station? Yeah, that needs a toning down else it will be just a tad too miserable to be funny. Also cause the poor janitor unneeded stress.
🆑 add: Cursed crewmembers can randomly, extremely rarely, spontaneously combust for no reason. add: Cursed crewmembers can get zapped by nearby light tubes. add: Cursed crewmembers can freak out when passing by mirrors. add: To make up for these, triggering a cursed effect is slightly less than half as likely now when walking around now. /🆑
Co-authored-by: MrMelbert [email protected] Co-authored-by: Ghom [email protected] Co-authored-by: Time-Green [email protected]
why i dont use stl god damn i need to refresh all this shit
feat: support for external executor plugins (#2305)
Hi @johanneskoester! 👋 As we chat about in a thread somewhere, I think it would be really powerful to allow for installing (and discovering) external plugins to Snakemake. Specifically for the Flux Operator, I have easily three designs I'm testing, and it's not really appropriate to add them proper to snakemake - but I believe the developer user should be empowered to flexibly add/remove and test them out.
This pull request is first try demo of how snakemake could allow
external executor plugins. I say "first try" because it's the first time
I've experimented with plugins, and I tried to choose a design that
optimizes simplicity and flexibility without requiring external
packages, or specific features of setuptools or similar (that are likely
to change). The basic design here uses pkgutil to discover
snakemake_executor_* plugins, and then provides them to the client (to
add arguments) and scheduler to select using one with --executor.
I've written up an entire tutorial and the basic design in this early prototype, which is basically the current Flux integration as a plugin! https://github.com/snakemake/snakemake-executor-flux. The user would basically do:
# Assuming this was released on pypi (it's not yet)
$ pip install snakemake-executor-flux
# Run the workflow using the flux custom executor
$ snakemake --jobs 1 --executor fluxI've designed it so that plugins are validated only when chosen, and each plugin can add or otherwise customize the parser, and then (after parsing) further tweak the args if chosen. Then in scheduler.py, we simply look if the user selected a plugin, and call the main executor (and local_executor) classes if this is the case.
The one hard piece is having a flexible way to pass forward all those
custom arguments. The current snakemake design has basically a custom
boolean for every executor hard coded (e.g., --flux or --slurm) and
while we don't want to blow that up, I'm worried moving forward passing
all these custom namespaced arguments through the init, workflow,
scheduler/dag, is going to get very messy. So the approach here is a
suggested way to handle the expanding space of additional executors by
way of passing forward full args, and then allowing the plugins to
customize the parser before or after. If we were to, for example, turn
current executors into plugins (something I expect we might want to do
for the Google Life Sciences API that is going to be deprecated in favor
of batch) we could write out a more hardened spec - some configuration
class that is passed from the argument parser through the executor and
through execution (instead of all the one off arguments).
Anyway - this is just a first shot and I'm hoping to start some discussion! This is a totally separate thing from TBA work with Google Batch - this is something that I've wanted to try for a while as I've wanted to add more executors and have seen the executor space exploding. :laughing: I haven't written tests or updated any docs yet pending our discussion!
- The PR contains a test case for the changes or the changes are already covered by an existing test case.
- The documentation (
docs/) is updated to reflect the changes or this is not necessary (e.g. if the change does neither modify the language nor the behavior or functionalities of Snakemake).
Signed-off-by: vsoch [email protected] Co-authored-by: vsoch [email protected] Co-authored-by: Johannes Köster [email protected] Co-authored-by: Johannes Köster [email protected]
added new rush alt arts
-CAN:D LIVE -Sevens Road Witch -Magical Sheep Girl Meeeg-chan -Prophecy Phrase of the Colors of the Wind -Cat Claw Girl -Machvio of the Ultimate Aria -Star Replacer -Mad Rare Aquila -Protection of Arthenée -Rice Terrace Crisis -The Strange Specter of Celestial Starts -Steel Soldier Gale Vinary -Rising Light Angel Esser -Amusi Annoyance
Bots no longer require PAIs to become sapient (#76691)
We were talking in the coder channel about what the role of a pAI is, with a general conclusion that as the name would suggest they should be personal assistants. This means they should be sticking around their owner, not wandering away as a holochassis or in the body of a bot. The former is a matter for a future PR, the latter I am addressing here.
What we also discussed is that clearly some people want to respawn as a weird quasi-useless mob which wanders aimlessly around the station. That seems like a fine thing to exist, but it shouldn't be a pAI.
Resultingly: pAI cards can no longer be placed inside bots. However, you also no longer need to place pAI cards inside bots in order for them to become sapient, it's a simple toggle on the bot control menu. Enabling this option will poll ghosts Toggling the "personality matrix" off while a bot is being controlled by a ghost will ghost them again, so if they're annoying they're not that hard to get rid of.
Mobs which couldn't have a pAI inserted don't have this option. Specifically securitrons, ED-209, and Hygienebots (for some reason).
Perhaps most controversially, any bots which are present on the station when the map loads will have this setting enabled by default. We will see if players abuse this too much and need their toys taken away, I am hoping they can be trusted.
Additionally, as part of this change, mobs you can possess now appear in the spawners menu.
Here is an unusually populated example.
Oh also in the process of doing this I turned the regal rat "click this to become it" behaviour into a component because it seems generally useful.
Minor stuff for dead players to do if they want to interact with living players instead of observe. Shift pAI back into a more intended role as a personal assistant who hangs around with their owner, rather than just a generic respawn role.
🆑 add: PAIs can no longer be inserted into Bots add: Bots can now have their sapience toggled by anyone with access to their settings panel add: Bots which exist on the map at the start of the round automatically have this setting enabled qol: Bots, Regal Rats, and Cargorilla now appear in the Spawners menu if you are dead qol: Bots can be renamed from their maintenance panel /🆑
Implement new forking technique for vendored packages. (#51083)
Updates all module resolvers (node, webpack, nft for entrypoints, and nft for next-server) to consider whether vendored packages are suitable for a given resolve request and resolves them in an import semantics preserving way.
Prior to the proposed change, vendoring has been accomplished but aliasing module requests from one specifier to a different specifier. For instance if we are using the built-in react packages for a build/runtime we might replace require('react') with require('next/dist/compiled/react').
However this aliasing introduces a subtle bug. The React package has an export map that considers the condition react-server and when you require/import 'react' the conditions should be considered and the underlying implementation of react may differ from one environment to another. In particular if you are resolving with the react-server condition you will be resolving the react.shared-subset.js implementation of React. This aliasing however breaks these semantics because it turns a bare specifier resolution of react with path '.' into a resolution with bare specifier next with path '/dist/compiled/react'. Module resolvers consider export maps of the package being imported from but in the case of next there is no consideration for the condition react-server and this resolution ends up pulling in the index.js implementation inside the React package by doing a simple path resolution to that package folder.
To work around this bug there is a prevalence of encoding the "right" resolution into the import itself. We for instance directly alias react to next/dist/compiled/react/react.shared-subset.js in certain cases. Other times we directly specify the runtime variant for instance react-server-dom-webpack/server.edge rather than react-server-dom-wegbpack/server, bypassing the export map altogether by selecting the runtime specific variant. However some code is meant to run in more than one runtime, for instance anything that is part of the client bundle which executes on the server during SSR and in the browser. There are workaround like using require conditionally or import(...) dynamically but these all have consequences for bundling and treeshaking and they still require careful consideration of the environment you are running in and which variant needs to load.
The result is that there is a large amount of manual pinning of aliases and additional complexity in the code and an inability to trust the package to specify the right resolution potentially causing conflicts in future versions as packages are updated.
It should be noted that aliasing is not in and of itself problematic when we are trying to implement a sort of lightweight forking based on build or runtime conditions. We have good examples of this for instance with the next/head package which within App Router should export a noop function. The problem is when we are trying to vendor an entire package and have the package behave semantically the same as if you had installed it yourself via node_modules
The fix is seemingly straight forward. We need to stop aliasing these module specifiers and instead customize the resolution process to resolve from a location that will contain the desired vendored packages. We can then start simplifying our imports to use top level package resources and generally and let import conditions control the process of providing the right variant in the right context.
It should be said that vendoring is conditional. Currently we only vendor react pacakges for App Router runtimes. The implementation needs to be able to conditionally determine where a package resolves based on whether we're in an App Router context vs a Page Router one.
Additionally the implementation needs to support alternate packages such as supporting the experimental channel for React when using features that require this version.
The first step is to put the vendored packages inside a node_modules folder. This is essential to the correct resolving of packages by most tools that implement module resolution. For packages that are meant to be vendored, meaning whole package substitution we move the from next/(src|dist)/compiled/... to next/(src|dist)/vendored/node_modules. The purpose of this move is to clarify that vendored packages operate with a different implementation. This initial PR moves the react dependencies for App Router and client-only and server-only packages into this folder. In the future we can decide which other precompiled dependencies are best implemented as vendored packages and move them over.
It should be noted that because of our use of JestWorker we can get warnings for duplicate package names so we modify the vendored pacakges for react adding either -vendored or -experimental-vendored depending on which release channel the package came from. While this will require us to alter the request string for a module specifier it will still be treating the react package as the bare specifier and thus use the export map as required.
The next thing we need to do is have all systems that do module resolution implement an custom module resolution step. There are five different resolvers that need to be considered
Updated the require-hook to resolve from the vendored directory without rewriting the request string to alter which package is identified in the bare specifier. For react packages we only do this vendoring if the process.env.__NEXT_PRIVATE_PREBUNDLED_REACT envvar is set indicating the runtime is server App Router builds. If we need a single node runtime to be able to conditionally resolve to both vendored and non vendored versions we will need to combine this with aliasing and encode whether the request is for the vendored version in the request string. Our current architecture does not require this though so we will just rely on the envvar for now
Removed all aliases configured for react packages. Rely on the node-runtime to properly alias external react dependencies. Add a resolver plugin NextAppResolverPlugin to preempt perform resolution from the context of the vendored directory when encountering a vendored eligible package.
updated the aliasing rules for react packages to resolve from the vendored directory when in an App Router context. This implementation is all essentially config b/c the capability of doing the resolve from any position (i.e. the vendored directory) already exists
track chunks to trace for App Router separate from Pages Router. For the trace for App Router chunks use a custom resolve hook in nft which performs the resolution from the vendored directory when appropriate.
The current implementation for next-server traces both node_modules and vendored version of packages so all versions are included. This is necessary because the next server can run in either context (App vs Page router) and may depend on any possible variants. We could in theory make two traces rather than a combined one but this will require additional downstream changes so for now it is the most conservative thing to do and is correct
Once we have the correct resolution semantics for all resolvers we can start to remove instances targeting our precompiled instances for instance making import ... from "next/dist/compiled/react-server-dom-webpack/client" and replacing with import ... from "react-server-dom-webpack/client"
We can also stop requiring runtime specific variants like import ... from "react-server-dom-webpack/client.edge" replacing it with the generic export "react-server-dom-webpack/client"
There are still two special case aliases related to react
- In profiling mode (browser only) we rewrite
react-domtoreact-dom/profilingandscheduler/tracingtoscheduler/tracing-profiling. This can be moved to using export maps and conditions once react publishses updates that implement this on the package side. - When resolving
react-domon the server we rewrite this toreact-dom/server-rendering-stub. This is to avoid loading the entire react-dom client bundle on the server when most of it goes unused. In the next major react will update this top level export to only contain the parts that are usable in any runtime and this alias can be dropped entirely
There are two non-react packages currently be vendored that I have maintained but think we ought to discuss the validity of vendoring. The client-only and server-only packages are vendored so you can use them without having to remember to install them into your project. This is convenient but does perhaps become surprising if you don't realize what is happening. We should consider not doing this but we can make that decision in another discussion/PR.
One of the things our webpack config implements for App Router is layers which allow us to have separate instances of packages for the server components graph and the client (ssr) graph. The way we were managing layer selection was a but arbitrary so in addition to the other webpack changes the way you cause a file to always end up in a specific layer is to end it with .serverlayer, .clientlayer or .sharedlayer. These act as layer portals so something in the server layer can import foo.clientlayer and that module will in fact be bundled in the client layer.
Most package managers are fine with this resolution redirect however yarn berry (yarn 2+ with PnP) will not resolve packages that are not defined in a package.json as a dependency. This was not a problem with the prior strategy because it was never resolving these vendored packages it was always resolving the next package and then just pointing to a file within it that happened to be from react or a related package.
To get around this issue vendored packages are both committed in src and packed as a tgz file. Then in the next package.json we define these vendored packages as optionalDependency pointing to these tarballs. For yarn PnP these packed versions will get used and resolved rather than the locally commited src files. For other package managers the optional dependencies may or may not get installed but the resolution will still resolve to the checked in src files. This isn't a particularly satisfying implemenation and if pnpm were to be updated to have consistent behavior installing from tarballs we could actually move the vendoring entirely to dependencies and simplify our resolvers a fair bit. But this will require an upstream chagne in pnpm and would take time to propogate in the community since many use older versions
As part of this work I landed some other changes upstream that were necessary. One was to make our packing use npm to match our publishing step. This also allows us to pack node_modules folders which is normally not supported but is possible if you define the folder in the package.json's files property.
See: #52563
Additionally nft did not provide a way to use the internal resolver if you were going to use the resolve hook so that is now exposed
See: vercel/nft#354
-
When we prepare to make an isolated next install for integration tests we exclude node_modules by default so we have a special case to allow
/vendored/node_modules -
The webpack module rules were refactored to be a little easier to reason about and while they do work as is it would be better for some of them to be wrapped in a
oneOfrule however there is a bug in our css loader implementation that causes these oneOf rules to get deleted. We should fix this up in a followup to make the rules a little more robuts.
- I removed
.sharedlayersince this concept is leaky (not really related to the client/server boundary split) and it is getting refactored anyway soon into a precompiled runtime.
changes were made....repos need updating
still in the process of integrating my config with doom better. added more pkgs cause ....why not? here some changes that maybe need more description this will be from config.org
@@ -112,6 +112,11 @@ Startup-settings
- added the save place setting into start-up dont plan on changing them so no need for it's own header
@@ -170,7 +175,7 @@ dashboard
- this don't look like much but it is predefinded by doom and does couple of things one of which is it open it in it's own workspace and names it rss. Like this part, however it opens it to the right of the main page and I have got in the habit of opening another workspace to the right. this causes me to never use that first workstation not a big deal. keeping this for a while. I think there is a command to move said workspace and probably a easy way to add it to the config and have it automated ....what ever!
@@ -299,13 +304,13 @@ org-settings
- like this package "org-pandoc-import" just never sure if I'm accually using it or got it set right. have the ability to do it with pandoc but like how this makes that even easier. So did a quick check and updated it to the doom-way and added some better description
@@ -317,7 +322,7 @@ org-settings
- reset after debugging
@@ -440,6 +445,90 @@ doom-Smartparens
- added this for reference :tangle no (already is)
@@ -453,27 +542,52 @@ evil-surround
- adding doom-mod-configs and reordering some headers
@@ -711,7 +830,7 @@ cape
- comment by minad on a forum made me take a closer look at my settings try some fine-tuning. the TLDR is he proposes that triggering them manually is better.
@@ -939,38 +1050,7 @@ consult-doom
- more doom intergation and references
@@ -1267,12 +1375,13 @@ personal-settings
- one of the typing exercise packages that I'm tring out
@@ -1287,12 +1396,13 @@ personal-settings
- new function for occur to put cursor in it's buffer after search
@@ -1301,14 +1411,14 @@ way of pasting that automatically surrounds the snippet in blocks,
- add some links here. this sounds like something I would use but have not used much mainly because I forget its here. added a not to remember next time.
@@ -1346,26 +1456,204 @@ my-keybindings
- added doom-keybinding reference
@@ -1867,7 +2137,12 @@ Elfeed
- BUG after reverting emacs back to 28.2.2 something got lost and there was no function definition for elfeed-expose. found it and just added it it was small so hacky but worked. did work so thinking this is temporary
@@ -2102,8 +2380,8 @@ EWW @@ -2150,9 +2428,9 @@ EWW
- trying to debug why eww chokes on pdfs
@@ -2456,17 +2746,98 @@ logos
- try another "Prot" package this time logos
- the problem is I only get about 30% of Prot's packages to work. not sure why if it's just me or the translation to doom not working not sure but like the other Prot packages I have yet to get this to work properly
- will keep "f"ing with it for now.
Added software list for cracked Macintosh floppy images. (#11454)
Alter Ego (male version 1.0) (san inc crack) [4am, san inc, A-Noid] Alter Ego (version 1.1 female) (san inc crack) [4am, san inc, A-Noid] Alternate Reality: The City (version 3.0) (san inc crack) [4am, san inc, A-Noid] Animation Toolkit I: The Players (version 1.0) (4am crack) [4am, A-Noid] Balance of Power (version 1.03) (san inc crack) [4am, san inc, A-Noid] Borrowed Time (san inc crack) [4am, san inc, A-Noid] Championship Star League Baseball (san inc crack) [4am, san inc, A-Noid] Cutthroats (release 23 / 840809-C) (4am crack) [4am, A-Noid] CX Base 500 (French, version 1.1) (san inc crack) [4am, san inc, A-Noid] Deadline (release 27 / 831005-C) (4am crack) [4am, A-Noid] Defender of the Crown (san inc crack) [4am, san inc, A-Noid] Deluxe Music Construction Set (version 1.0) (san inc crack) [4am, san inc, A-Noid] Déjà Vu (version 2.3) (4am crack) [4am, A-Noid] Déjà Vu: A Nightmare Comes True!! (san inc crack) [4am, san inc, A-Noid] Déjà Vu II: Lost in Las Vegas!! (san inc crack) [4am, san inc, A-Noid] Dollars and Sense (version 1.3) (4am crack) [4am, A-Noid] Downhill Racer (san inc crack) [4am, san inc, A-Noid] Dragonworld (4am crack) [4am, A-Noid] ExperLisp (version 1.0) (4am crack) [4am, A-Noid] Forbidden Castle (san inc crack) [4am, san inc, A-Noid] Fusillade (version 1.0) (san inc crack) [4am, san inc, A-Noid] Geometry (version 1.1) (4am crack) [4am, A-Noid] Habadex (version 1.1) (4am crack) [4am, A-Noid] Hacker II (san inc crack) [4am, san inc, A-Noid] Harrier Strike Mission (san inc crack) [4am, san inc, A-Noid] Indiana Jones and the Revenge of the Ancients (san inc crack) [4am, san inc, A-Noid] Infidel (release 22 / 840522-C) (4am crack) [4am, A-Noid] Jam Session (version 1.0) (4am crack) [4am, A-Noid] Legends of the Lost Realm I: The Gathering of Heroes (version 2.0) (4am crack) [4am, A-Noid] Lode Runner (version 1.0) (4am crack) [4am, A-Noid] Mac Pro Football (version 1.0) (san inc crack) [4am, san inc, A-Noid] MacBackup (version 2.6) (4am crack) [4am, A-Noid] MacCheckers and Reversi (4am crack) [4am, A-Noid] MacCopy (version 1.1) (4am crack) [4am, A-Noid] MacGammon! (version 1.0) (4am crack) [4am, A-Noid] MacGolf (version 2.0) (4am crack) [4am, A-Noid] MacWars (san inc crack) [4am, san inc, A-Noid] Master Tracks Pro (version 1.10) (san inc crack) [4am, san inc, A-Noid] Master Tracks Pro (version 2.00h) (san inc crack) [4am, san inc, A-Noid] Master Tracks Pro (version 3.4a) (san inc crack) [4am, san inc, A-Noid] Master Tracks Pro (version 4.0) (san inc crack) [4am, san inc, A-Noid] Math Blaster (version 1.0) (4am crack) [4am, A-Noid] Maze Survival (san inc crack) [4am, san inc, A-Noid] Microsoft Excel (version 1.00) (san inc crack) [4am, san inc, A-Noid] Microsoft File (version 1.04) (san inc crack) [4am, san inc, A-Noid] Mindshadow (san inc crack) [4am, san inc, A-Noid] Moriarty's Revenge (version 1.0) (san inc crack) [4am, san inc, A-Noid] Moriarty's Revenge (version 1.03) (4am crack) [4am, A-Noid] Mouse Stampede (version 1.00) (4am crack) [4am, A-Noid] Murder by the Dozen (Thunder Mountain) (4am crack) [4am, A-Noid] My Office (version 2.7) (4am crack) [4am, A-Noid] One on One (san inc crack) [4am, san inc, A-Noid] Orb Quest: Part I: The Search for Seven Wards (version 1.04) (san inc crack) [4am, san inc, A-Noid] Patton Strikes Back (version 1.00) (san inc crack) [4am, san inc, A-Noid] Patton vs. Rommel (version 1.05) (san inc crack) [4am, san inc, A-Noid] Pensate (version 1.1) (4am crack) [4am, A-Noid] PFS File and Report (version A.00) (4am crack) [4am, A-Noid] Physics (version 1.0) (4am crack) [4am, A-Noid] Physics (version 1.2) (4am crack) [4am, A-Noid] Pinball Construction Set (version 2.5) (san inc crack) [4am, san inc, A-Noid] Pipe Dream (version 1.2) (4am crack) [4am, A-Noid] Professional Composer (version 2.3Mfx) (san inc crack) [4am, san inc, A-Noid] Q-Sheet (version 1.0) (san inc crack) [4am, san inc, A-Noid] Rambo: First Blood Part II (san inc crack) [4am, san inc, A-Noid] Reader Rabbit (version 2.0) (4am crack) [4am, A-Noid] Rogue (version 1.0) (san inc crack) [4am, san inc, A-Noid] Seastalker (release 15 / 840522-C) (4am crack) [4am, A-Noid] Seven Cities of Gold (san inc crack) [4am, san inc, A-Noid] Shadowgate (san inc crack) [4am, san inc, A-Noid] Shanghai (version 1.0) (san inc crack) [4am, san inc, A-Noid] Shufflepuck Cafe (version 1.0) (4am crack) [4am, A-Noid] Sierra Championship Boxing (4am crack) [4am, A-Noid] SimCity (version 1.1) (4am crack) [4am, A-Noid] SimCity (version 1.2, black & white) (4am crack) [4am, A-Noid] SimEarth (version 1.0) (4am crack) [4am, A-Noid] Skyfox (san inc crack) [4am, san inc, A-Noid] Smash Hit Racquetball (version 1.01) (san inc crack) [4am, san inc, A-Noid] SmoothTalker (version 1.0) (4am crack) [4am, A-Noid] Speed Reader II (version 1.1) (4am crack) [4am, A-Noid] Speller Bee (version 1.1) (4am crack) [4am, A-Noid] Star Trek: The Kobayashi Alternative (version 1.0) (san inc crack) [4am, san inc, A-Noid] Stratego (version 1.0) (4am crack) [4am, A-Noid] Suspect (release 14 / 841005-C) (4am crack) [4am, A-Noid] Tass Times in Tonetown (san inc crack) [4am, san inc, A-Noid] Temple of Apshai Trilogy (version 1985-09-30) (san inc crack) [4am, san inc, A-Noid] Temple of Apshai Trilogy (version 1985-10-08) (san inc crack) [4am, san inc, A-Noid] The Chessmaster 2000 (version 1.02) (4am crack) [4am, A-Noid] The Crimson Crown (san inc crack) [4am, san inc, A-Noid] The Duel: Test Drive II (san inc crack) [4am, san inc, A-Noid] The Hitchhiker's Guide to the Galaxy (release 47 / 840914-C) (4am crack) [4am, A-Noid] The King of Chicago (san inc crack) [4am, san inc, A-Noid] The Lüscher Profile (san inc crack) [4am, san inc, A-Noid] The Mind Prober (version 1.0) (san inc crack) [4am, san inc, A-Noid] The Mist (san inc crack) [4am, san inc, A-Noid] The Quest (4am crack) [4am, A-Noid] The Slide Show Magician (version 1.2) (4am crack) [4am, A-Noid] The Surgeon (version 1.5) (san inc crack) [4am, san inc, A-Noid] The Toy Shop (version 1.1) (san inc crack) [4am, san inc, A-Noid] The Witness (release 22 / 840924-C) (4am crack) [4am, A-Noid] ThinkTank 128 (version 1.000) (4am crack) [4am, A-Noid] Uninvited (version 1.0) (san inc crack) [4am, san inc, A-Noid] Uninvited (version 2.1D1) (san inc crack) [4am, san inc, A-Noid] Where in Europe is Carmen Sandiego? (version 1.0) (4am crack) [4am, A-Noid] Winter Games (version 1985-10-24) (san inc crack) [4am, san inc, A-Noid] Winter Games (version 1985-10-31) (san inc crack) [4am, san inc, A-Noid] Wishbringer (release 68 / 850501-D) (4am crack) [4am, A-Noid] Wizardry: Proving Grounds of the Mad Overlord (version 1.10) (san inc crack) [4am, san inc, A-Noid] Zork II (release 48 / 840904-C) (4am crack) [4am, A-Noid] Zork III (release 17 / 840727-C) (4am crack) [4am, A-Noid]
Python: Import OpenAPI documents into the semantic kernel (#2297)
This allows us to import OpenAPI documents, including ChatGPT plugins, into the Semantic Kernel.
- The interface reads the operationIds of the openapi spec into a skill:
from semantic_kernel.connectors.openapi import register_openapi_skill
skill = register_openapi_skill(kernel=kernel, skill_name="test", openapi_document="url/or/path/to/openapi.yamlorjson")
skill['operationId'].invoke_async()- Parse an OpenAPI document
- For each operation in the document, create a function that will execute the operation
- Add all those operations to a skill in the kernel
- Modified
import_skillto accept a dictionary of functions instead of just class so that we can import dynamically created functions - Created unit tests
TESTING: I've been testing this with the following ChatGPT plugins:
- Semantic Kernel Starter's Python Flask plugin
- ChatGPT's example retrieval plugin
- This one was annoying to setup. I didn't get the plugin functioning, but I was able to send the right API requests
- Also, their openapi file was invalid. The "servers" attribute is misindented
- Google ChatGPT plugin
- Chat TODO plugin
- This openapi file is also invalid. I checked with an online validator. I had to remove"required" from the referenced request objects' properties: https://github.com/lencx/chat-todo-plugin/blob/main/openapi.yaml#L85
Then I used this python file to test the examples:
import asyncio
import logging
import semantic_kernel as sk
from semantic_kernel import ContextVariables, Kernel
from semantic_kernel.connectors.ai.open_ai import AzureTextCompletion
from semantic_kernel.connectors.openapi.sk_openapi import register_openapi_skill
# Example usage
chatgpt_retrieval_plugin = {
"openapi": # location of the plugin's openapi.yaml file,
"payload": {
"queries": [
{
"query": "string",
"filter": {
"document_id": "string",
"source": "email",
"source_id": "string",
"author": "string",
"start_date": "string",
"end_date": "string",
},
"top_k": 3,
}
]
},
"operation_id": "query_query_post",
}
sk_python_flask = {
"openapi": # location of the plugin's openapi.yaml file,
"path_params": {"skill_name": "FunSkill", "function_name": "Joke"},
"payload": {"input": "dinosaurs"},
"operation_id": "executeFunction",
}
google_chatgpt_plugin = {
"openapi": # location of the plugin's openapi.yaml file,
"query_params": {"q": "dinosaurs"},
"operation_id": "searchGet",
}
todo_plugin_add = {
"openapi": # location of the plugin's openapi.yaml file,
"path_params": {"username": "markkarle"},
"payload": {"todo": "finish this"},
"operation_id": "addTodo",
}
todo_plugin_get = {
"openapi": # location of the plugin's openapi.yaml file,
"path_params": {"username": "markkarle"},
"operation_id": "getTodos",
}
todo_plugin_delete = {
"openapi": # location of the plugin's openapi.yaml file,
"path_params": {"username": "markkarle"},
"payload": {"todo_idx": 0},
"operation_id": "deleteTodo",
}
plugin = todo_plugin_get # set this to the plugin you want to try
logger = logging.getLogger(__name__)
logger.addHandler(logging.StreamHandler())
logger.setLevel(logging.DEBUG)
kernel = Kernel(log=logger)
deployment, api_key, endpoint = sk.azure_openai_settings_from_dot_env()
kernel.add_text_completion_service(
"dv", AzureTextCompletion(deployment, endpoint, api_key)
)
skill = register_openapi_skill(
kernel=kernel, skill_name="test", openapi_document=plugin["openapi"]
)
context_variables = ContextVariables(variables=plugin)
result = asyncio.run(
skill[plugin["operation_id"]].invoke_async(variables=context_variables)
)
print(result)- The code builds clean without any errors or warnings
- The PR follows the SK Contribution Guidelines and the pre-submission formatting script raises no violations
- All unit tests pass, and I have added new tests where possible
- I didn't break anyone 😄
Co-authored-by: Abby Harrison [email protected]
Add a popek1990.toml
Hello,
I'm popek1990.eth.
I've been working in the web2 & web3 industry for over half of my life. My beginnings involve creating web2 websites and php forums using html/css/php. Later on, I delved into SEO & marketing. Throughout my life, I've been in love with Linux, especially the Debian distribution which I still use to this day. For the past 4 years, I've been developing my skills in the areas of blockchain and smart contracts. I'm deeply interested in privacy, which led me to discover NAMADA. Previously, I ran my own node in Monero & Railgun.
I want to be an active member of the community. I'm also an influencer in the Polish crypto market, and my goal is to spread the good word about crypto technology through articles on my mirror.xyz . I would be very pleased if I could join as a genesis validator. I'm aware that I'm joining late, but I've been systematically observing the NOMADA project for many months. I've read the entire whitepaper and .docs, and I'm very impressed with your vision.
Here are my links: https://linktr.ee/popek1990
Of course, NOMADA and all repositories installed on a strong server and ready to go. I'd like join to testnet 12 ale pre-gnosis validator.
sched/core: Fix ttwu() race
Paul reported rcutorture occasionally hitting a NULL deref:
sched_ttwu_pending() ttwu_do_wakeup() check_preempt_curr() := check_preempt_wakeup() find_matching_se() is_same_group() if (se->cfs_rq == pse->cfs_rq) <-- BOOM
Debugging showed that this only appears to happen when we take the new code-path from commit:
2ebb17717550 ("sched/core: Offload wakee task activation if it the wakee is descheduling")
and only when @cpu == smp_processor_id(). Something which should not be possible, because p->on_cpu can only be true for remote tasks. Similarly, without the new code-path from commit:
c6e7bd7afaeb ("sched/core: Optimize ttwu() spinning on p->on_cpu")
this would've unconditionally hit:
smp_cond_load_acquire(&p->on_cpu, !VAL);
and if: 'cpu == smp_processor_id() && p->on_cpu' is possible, this would result in an instant live-lock (with IRQs disabled), something that hasn't been reported.
The NULL deref can be explained however if the task_cpu(p) load at the beginning of try_to_wake_up() returns an old value, and this old value happens to be smp_processor_id(). Further assume that the p->on_cpu load accurately returns 1, it really is still running, just not here.
Then, when we enqueue the task locally, we can crash in exactly the observed manner because p->se.cfs_rq != rq->cfs_rq, because p's cfs_rq is from the wrong CPU, therefore we'll iterate into the non-existant parents and NULL deref.
The closest semi-plausible scenario I've managed to contrive is somewhat elaborate (then again, actual reproduction takes many CPU hours of rcutorture, so it can't be anything obvious):
X->cpu = 1
rq(1)->curr = X
CPU0 CPU1 CPU2
// switch away from X
LOCK rq(1)->lock
smp_mb__after_spinlock
dequeue_task(X)
X->on_rq = 9
switch_to(Z)
X->on_cpu = 0
UNLOCK rq(1)->lock
// migrate X to cpu 0
LOCK rq(1)->lock
dequeue_task(X)
set_task_cpu(X, 0)
X->cpu = 0
UNLOCK rq(1)->lock
LOCK rq(0)->lock
enqueue_task(X)
X->on_rq = 1
UNLOCK rq(0)->lock
// switch to X
LOCK rq(0)->lock
smp_mb__after_spinlock
switch_to(X)
X->on_cpu = 1
UNLOCK rq(0)->lock
// X goes sleep
X->state = TASK_UNINTERRUPTIBLE
smp_mb(); // wake X
ttwu()
LOCK X->pi_lock
smp_mb__after_spinlock
if (p->state)
cpu = X->cpu; // =? 1
smp_rmb()
// X calls schedule()
LOCK rq(0)->lock
smp_mb__after_spinlock
dequeue_task(X)
X->on_rq = 0
if (p->on_rq)
smp_rmb();
if (p->on_cpu && ttwu_queue_wakelist(..)) [*]
smp_cond_load_acquire(&p->on_cpu, !VAL)
cpu = select_task_rq(X, X->wake_cpu, ...)
if (X->cpu != cpu)
switch_to(Y)
X->on_cpu = 0
UNLOCK rq(0)->lock
However I'm having trouble convincing myself that's actually possible on x86_64 -- after all, every LOCK implies an smp_mb() there, so if ttwu observes ->state != RUNNING, it must also observe ->cpu != 1.
(Most of the previous ttwu() races were found on very large PowerPC)
Nevertheless, this fully explains the observed failure case.
Fix it by ordering the task_cpu(p) load after the p->on_cpu load, which is easy since nothing actually uses @cpu before this.
Fixes: c6e7bd7afaeb ("sched/core: Optimize ttwu() spinning on p->on_cpu") Reported-by: Paul E. McKenney [email protected] Tested-by: Paul E. McKenney [email protected] Signed-off-by: Peter Zijlstra (Intel) [email protected] Signed-off-by: Ingo Molnar [email protected] Link: https://lkml.kernel.org/r/[email protected] Change-Id: I40e0e01946eadb1701a4d06758e434591e5a5c92
There is no longer a 50% chance of catching a heretic out when examining them drawing influences [MDB IGNORE] (#22532)
- 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. /🆑
- There is no longer a 50% chance of catching a heretic out when examining them drawing influences
Co-authored-by: carlarctg [email protected] Co-authored-by: Bloop [email protected]
create virtual_mouse.py
Hey there! Alright, so I see you're interested in understanding how this code works. No worries, I'll break it down for you step by step.
Step 1: We're getting ready by bringing in some tools that we'll use to make our virtual keyboard with hand gestures. Think of these like the tools you need before building something cool.
Step 2: We're getting the "mediapipe hands" tool ready. This is like a magic box that helps us see and understand where your hands are in front of the camera.
Step 3: We're turning on your computer's camera. It's like switching on your phone's camera so you can see what's in front of it.
Step 4: We're starting a loop, which means we're going to do some things over and over again until we decide to stop. Each time we do this loop, we'll take a look at what the camera sees.
Step 5: We're looking at what the camera sees and trying to understand where your hands are using the magic "mediapipe hands" tool. This tool helps us find special points on your hands, like the tip of your finger.
Step 6: If the magic tool sees your hand, we're going to do something with that information. We're going to pretend that your finger is typing on a virtual keyboard based on where it is on the screen. If it's high up, we'll type "Hello." If it's in the middle, we'll type "World." And if it's low down, we'll type "Gesture."
Step 7: We're showing you what the camera sees and the magic tool understands. It's like having a window on your computer screen that shows you what the camera is looking at.
Step 8: We're paying attention to your computer keyboard. If you press the "Esc" key (that's like the exit button), we'll stop doing our loop and everything will stop running.
Step 9: Once we're done and you're ready to close the program, we'll turn off the camera and close the window that was showing you what the camera saw. It's like turning off your phone's camera when you're done taking pictures.
Hope that helps you understand how this code works! It's like magic, right? You can build all sorts of amazing things with programming. If you have any questions, feel free to ask: 9894214087.
Introduce Lazyplug
Other hotplugging methods including mpdecision and intelli_plug focuses on how should we turn off CPU cores. They hotplugs the individual CPU cores based on the current load divided by thread capacity. Lazyplug takes a whole new approach on how we should do hotplugging based on the foundation of the other side of the coin; “Linux’s hotplugging is very inefficient.”
Current hotplugging code on Linux is a total waste of CPU cycles and delays, so rather than hotplugging and hurt performance & battery life, just leaving the CPU cores on might be a better choice. This kind of approach is spreading out more and more. Samsung has been using this method for a very long time with big.LITTLE devices and recent Nexus 6 firmware also does the similar thing.
Lazyplug just leaves them on, most of the time. It also tries to solve some problems with the “Always on” approach. On situations such as video playback, turning on all CPU cores is not battery friendly. So Lazyplug does actually turns off CPU cores, but only when idle state is long enough(to reduce the number of CPU core switchings) and when the device has its screen off(determination is done via earlysuspend or powersuspend because framebuffer API causes troubles on hotplugging CPU cores).
Basic methodology : Lazyplug uses majority of the codes from intelli_plug by faux123 to determine when to turn off CPU cores. If the system has been idle for (DEF_SAMPLING_MS * DEF_IDLE_COUNT)ms, it turns off the CPU cores. And if the next poll determines 1 core isn’t enough, it fires up all CPU cores (instead of selective CPU cores; which is the traditional intelli_plug’s method). Lazyplug also takes touch-screen input events to fire up CPU cores to minimize noticeable performance degradation. There’s also a “lazy mode” for not aggressively turning on CPU cores on scenario such as video playback. For example, if you hook up lazyplug_enter_lazy() to the video session open function, Lazyplug won’t aggressively turn on CPU cores and tries to handle it with 1 CPU core.
- TODO :
- Dual-core mode : YouTube video playback is mostly single-threaded.
- It usually hovers around 10% ~ 30% of total CPU usage on quad-core
- device. That means 1 CPU core might not be enough to handle it, but
- also turning on all CPU cores is unnecessarily wasting power.
Im so sick of bugs. (#4739)
- Mother fucker. Im so sick of bugs.
Cigarettes no longer(seem to) cause kidney damage to people with unclean living.
psion void armor has correct slowdown for shoes and doesn't use slowdown on other pieces of armor. Additionally, no longer allows ears to flop outside of it. It's a fucking space suit, why would they be out?
Opifex medbelt no longer selectable, sorry powergamers.
Removes change_appearance from baseline armor vest. Why? It is the parent to MANY MANY MANY fucking items and thus caused MANY MANY MANY items to have erronious change_appearance procs that only had two options for the base parent item. This is why we don't put fucking procs on BASE PARENT items that affect DOZENS of other items. Fixes a few others, WO plate has no unique sprite and now has a proper working change appearance. CO does have a unique sprite, it is gone.
Fixes #4732 Fixes #4734 fixes #4724
- Update psi_Larmor.dm
hoh boy that was a catastrophic fuckup to forget thank fuck it came to me in a vision while i sat in my chair thinking about my life choices
Changeling armblade gets 35% armour penetration + better wounding. (#77416)
Gives the changeling armblade an armour penetration of 35%. Sets their bare_wound_bonus to 10 (from 20), and a wound_bonus of 10 (from -20).
The wound bonuses basically gave massive punishment if they attacked anything but the skin. It honestly felt kinda lame. The better wounding potential will help bring a bloodier and more exciting atmosphere when a changeling whips out the blade.
The armour penetration will help reduce dragged out fights that get a little silly, while keeping the wounding more consistent.
🆑 balance: Changeling arm blade has an armour penetration of 35%. balance: Changeling arm blade has a wound bonus of 10, from -20. balance: Changeling has a bare wound bonus of 10, from 20. /🆑
Drill module automatically disables if it's about to drill into gibtonite (#77385)
Drill module automatically disables if it's about to drill into gibtonite.
Drill module automatically disables if it's about to drill into gibtonite
There's not enough time to react, the mining scanner is surprisingly slow sometimes and it means you drill straight into gibtonite, which primes it the first drill and blows it up the second, which is a lot more of a pain than it sounds because drilling is night-instant. These explosions are usually enough to crit you, and if they don't, the stun and area clear means any fauna can wander in and finish you off.
The auto-disable still makes it an annoyance to stumble upon gibtonite, but it won't round end you for using modsuits.
🆑 qol: Drill module automatically disables if it's about to drill into gibtonite /🆑
New Mech UI and equipment refactor (#77221)
Made a new UI and refactored some mech code in the process.
Fixes #66048 Fixes #77051 Fixes #65958 ??? if it was broken Fixes #73051 - see details below Fixes other undocumented things, see changelog.
The UI was too bulky and Mechs were too complex for no reason. Now they follow some general rules shared between other SS13 machinery, and there is less magic happening under the hood.
Previous UI for comparison:
Previously mechs came with radio pre-installed and air canisters magically pre-filled with air even when you build one in fab. Radio and Air Tanks are now both utility modules that are optional to install. Gas RCS thrusters still require Air Tank module to operate.
This made the Mechs more barebones when built, giving you only the basic functionality.
To compensate this change, all mechs got two extra utility module slots.
All other modules got new UI. And ore box now shows the list of ores inside.
Works as a normal radio, but with subspace transmission. Available from the basic mech research node and can be printed in fab.
To compensate for the lack of air tank by default, mechs with enclosed cabin (e.g. all except Ripley) got an ability to toggle cabin exposure to the outside air. Exiting the mech makes cabin air automatically exposed.
When you seal the cabin, it traps some of the outside air inside the cabin and you can breathe with this air to perform a short space trips. But the oxygen will run out quickly and CO2 will build up.
Sealing the cabin in space will make the cabin filled with vacuum, and it will stay there until you return to air environment and unseal the cabin, letting the breathable air to enter. There are temperature and pressure sensors that turn yellow/red when the corresponding warning thresholds are reached.
You could also use personal internals in combination with cabin sealing for long space travels, so Air Tank is completely optional now and mostly needed when you need RCS thruster.
They are now available earlier in tech tree and consume reasonable amount of air (5 times more than human jetpacks), and they don't work without Mounted Air Tank, unless it's an Ion thruster variant.
Available from the basic mech research node and can be printed in fab. Built model comes empty, and syndicate mechs come with one full of oxygen.
Can be switched to pressurize or not pressurize the cabin. Releases gas only when the cabin is sealed shut. Starts releasing automatically, but can be toggled to not release if you want to use it just as a portable canister.
Cabin pressure can now be configured in the module UI instead of Maintenance UI.
Can be attached to a pipe network when the mech is parked above a connection port.
Comes with a pump that works similarly to the portable pump. It lets you vent the air tank contents outside, or suck air from the room to fill the air tank. Intended to provide an ability to fill the air tank without the need to bother with pipes.
Also has gas sensors that display gas mix data of the tank and the cabin (when sealed).
All mechs now require a servo motor and they reduce mech movement power consumption instead of scanning module.
Scanning modules are optional for mech operation (still required to build) and the lack of one disables the following UI elements:
- Display of mech integrity (you can still see the alerts or examine the mech to get rough idea)
- Display of mech status on internal damage (and you can't repair what you can't diagnose)
The rating of scanning module doesn't have any effect as of now.
Cargo mech comes without it roundstart.
Capacitors now also reduce light power usage and raise the overclocking temperature thresholds (see below).
Maintenance UI removed, and its logic migrated to other places.
Access modification now managed inside the mech, and anyone who can control the mech, can adjust the access in the same way as they can set DNA key.
To open the maintenance panel you just need a screwdriver. It is instant when the mech is empty and it has a 5 second delay when there is an occupant to avoid in-combat hacking and part removal. It will alert the occupant that someone is trying to tinker with their mech.
Once the panel is open, you can see the part ratings:
With open panel you can hack the mech wires (roboticists can now see them):
There are wires for:
- Enabling/Disabling ID and DNA locks
- Toggling mech lights
- Toggling mech circuits malfunction (battery drain, sparks)
- Toggling mech equipment malfunction (to repair after EMP or cause EMP-like effect, disarming mech)
- 3 dud wires that do nothing
The hacker may be shocked if the mech power cell allows.
When the panel is open and the user has access to the mech, they can remove parts with a crowbar:
Hitting the mech with an ID from outside now toggles the ID Lock on/off if the ID has sufficient access.
Rebalanced mech power consumption. T4 parts were not working in Syndicate Mechs, as their effect was not calculated until you manipulate parts manually. Constructed mechs with t1 parts even had their energy drain reduced with upgrade to t1.
Now all mechs apply their base step power usage correctly don't ignore the stock parts.
Servo tier now reduces base power consumption by 0% at t1, 50% at t2, 33% at t3 and 25% at t4 Capacitor tier now reduces base power consumption of mele attacks, phasing and light by the same amounts.
Gygax leg actuators overload replaced with mech overclocking. Any mech can be overclocked by hacking wires, but only Gygax has a button for toggling it from the Cabin.
Now there is an overclock coefficient. 1.5 for Gygax and other mechs, 2 for Dark Gygax.
When overclocked, mechs moves N times faster, but consumes N times more power.
While overclocked, mech heats up every second, regardless of movement, and starts receiving internal and integrity damage after a certain temperature threshold. The chance is 0% at the threshold, and 100% at thresholds * 2. The roll happens every tick. Capacitor upgrades this threshold, letting you overclock safely for longer periods.
When you stop overclock, the temperature goes back down.
Concealed weapon bay now doesn't show up when you examine the mech, so it's actually concealed now.
New radio module can properly change its frequency, as it didn't work for previous radio.
Launcher type weapons were ignoring cooldowns and power usage, so you
could spam explosive banana peals, while they should have a 2 second
cooldown:
Now this is fixed and all launcher type weapons properly use power and have their cooldowns working. And now they have the kickback effect working (when it pushes you in the opposite direction in zero gravity on throw).
Thermoregulator now heats/cools considering heat capacity instead of adding/reducing flat 10 degrees. So you can heat up cabin air quicker if the pressure is low.
There were some other sloppy mistakes in mech code, like some functions returning too early, blocking other functionality unintentionally. Fixed these and made some other minor changes and improvements.
🆑 refactor: Refactored Mech UI refactor: Refactored mech radio into a utility module, adding extra slot to all mechs refactor: Refactored mech air tank into a utility module with an air pump, adding extra slot to all mechs refactor: Refactored mech cabin air - there is now a button to seal or unseal cabin to make it airtight or exchanging gases with the environment refactor: Removed mech maintenance UI Access is set in mech UI, and parts are ejected with a crowbar add: Mech now has wires and can be hacked qol: Roboticists now can see MOD suit and mech wires add: Mechs now require servo motor stock part and it affects movement power usage instead of scanning module add: Scanning module absence doesnt block mech movement and hides some UI data instead. Big Bess starts without one. qol: Hitting mech with ID card now toggles ID lock on/off if the card has required access fix: Fixed concealed weapon bay not being concealed on mech examine fix: Fixed mech radio not changing frequency fix: Fixed mech launcher type weapons ignoring specified cooldown fix: Fixed mech launcher type weapons not using specified power amount fix: Fixed mech temperature regulator ignoring gas heat capacity fix: Fixed mech stopping processing other things while not heating internal air fix: Fixed mech being able to leave transit tube in transit fix: Fixed mech internal damage flags working incorrectly fix: Fixed Gygax leg overloading being useless fix: Fixed mechs ignoring their stock parts on creation. Syndicate mechs now stronger against lasers and consume less energy on move. Upgrading from tier 1 to tier 2 doesn't make mech consume MORE energy than before the upgrade. balance: Rebalanced mech energy drain with part upgrades. Base energy drain reduced by 50%, 33%, 25% with upgrades and applies to movement (Servo rating), phasing, punching, light (Capacitor rating). balance: Hydraulic clamp now can force open airlocks balance: Made mech RCS pack consume reasonable amount of gas code: Fixed some other minor bugs and made some minor changes in the mech code /🆑
Co-authored-by: SyncIt21 [email protected] Co-authored-by: Sealed101 [email protected] Co-authored-by: Jacquerel [email protected]
Permit retries (with backoff) when opening the LDAP connection
Previously we were considering a failure during open (initial or otherwise) to be a hard, script-ending, permanent failure. That's frankly a bit silly, networks can be tempermental, so this fixes that somewhat.
Notably, I can't seem to find any way to check the status of the connection on the lConn object, so we're tracking that manually using a tiny little state object. If there's a cleaner way to inspect this state I am all ears, but I don't think it's a majorly big deal.
(Elsewhere in Rancher we don't try to share the ldap connection generally, but here it is a big performance boost, so it is worth the extra trouble.)
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.
Add files via upload
Project Title: Analog Watch Web App
Description: The Analog Watch Web App is a captivating project that brings the charm of traditional timekeeping to the digital realm, showcasing the perfect blend of classic aesthetics and modern technology. Developed using HTML5, CSS, and Java, this project demonstrates the power of web technologies in crafting a functional and visually appealing analog watch experience.
Key Features: This web app offers a user-friendly interface that emulates the elegant design of analog watches. The watch face showcases intricately designed hour, minute, and second hands that accurately reflect the current time. The watch hands move smoothly, simulating the mechanical precision of traditional timepieces. The watch is set against a customizable backdrop, allowing users to select from a range of backgrounds to suit their preferences.
Technology Stack: The project leverages HTML5 for structuring the content, CSS for styling the watch face and layout, and Java for implementing the interactive elements. The combination of these technologies ensures cross-browser compatibility and a responsive design, enabling users to access the analog watch seamlessly across different devices.
User Interaction: Users can interact with the watch by adjusting the time using intuitive buttons. Additionally, they can switch between various watch face designs and backgrounds, creating a personalized experience that caters to different tastes. The user interface is intuitive and engaging, making it easy for both watch enthusiasts and casual users to enjoy the app.
Learning and Showcase: For developers and learners, this project serves as an educational resource that illustrates the fundamentals of HTML5, CSS, and Java in a practical context. The clean and well-organized codebase is designed for easy understanding and modification. By exploring the code, developers can grasp essential concepts of front-end web development, animation, and interactivity.
Conclusion: The Analog Watch Web App is a testament to the creativity and innovation achievable with HTML5, CSS, and Java. It provides users with a nostalgic journey into the world of analog timekeeping while showcasing your skills in modern web development. Whether used as a teaching tool, a portfolio piece, or a delightful online experience, this project encapsulates the timeless appeal of analog watches in a digital format.
fix: lru_cache issues + meta info missing (#72)
Context: codecov/engineering-team#119
So the real issue with the meta info is fixed in codecov/shared#22. spoiler: reusing the report details cached values and changing them is not a good idea.
However in the process of debuging that @matt-codecov pointed out that we were not using lru_cache correctly. Check this very well made video: https://www.youtube.com/watch?v=sVjtp6tGo0g
So the present changes upgrade shared so we fix the meta info stuff AND address the cache issue.
There are further complications with the caching situation, which explain why I decided to add the cached value in the
obj instead of self. The thing is that there's only 1 instance of ArchiveField shared among ALL instances of
the model class (for example, all ReportDetail instances). This kinda makes sense because we only create an instance
of ArchiveField in the declaration of the ReportDetail class.
Because of that if the cache is in the self of ArchiveField different instances of ReportDetails will have dirty cached value of other ReportDetails instances and we get wrong values. To fix that I envision 3 possibilities:
-
Putting the cached value in the
ReportDetailsinstance directly (theobj), and checking for the presence of that value. If it's there it's guaranteed that we put it there, and we can update it on writes, so that we can always use it. Because it is for eachReportDetailsinstance we always get the correct value, and it's cleared when the instance is killed and garbage collected. -
Storing an entire table of cached values in the
self(ArchiveField) and using the appropriate cache value when possible. The problem here is that we need to manage the cache ourselves (which is not that hard, honestly) and probably set a max value. Then we will populate the cache and over time evict old values. The 2nd problem is that the values themselves might be too big to hold in memory (which can be fixed by setting a very small value in the cache size). There's a fine line there, but it's more work than option 1 anyway. -
We move the getting and parsing of the value to outside
ArchiveField(so it's a normal function) and uselru_cachein that function. Because therehydratefunction takes a reference toobjI don't think we should pass that, so the issue here is that we can't cache the rehydrated value, and would have to rehydrate every time (which currently is not expensive at all in any model)
This is an instance cache, so it shouldn't need to be cleaned for the duration of the instance's life (because it is updates on the SET)
closes codecov/engineering-team#119
[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]
ReaderActivityIndicator: Oh god, my eyes, they buuuuurn.
Make this a real boy, with a transient lipc handle. And get rid of the insane 1s sleep on affected ReaderView paints, because ouchy.
This is completely deprecated anyway, so this is entirely pointless, and mainly to prevent implementation details from creeping into reader.lua.
Base Female sprite tweaks (#77407)
ASS STUFF HAS BEEN REMOVED BUT I STILL HATE IT
This PR tones down the proportions of the female base sprites, as currently they have about SIX extra pixels on the ass and a random pixel missing from the neck, which breaks some hairstyles & makes the neck look quite stupid. It also adds a couple pixels to the male one because theirs was so stupidly SMALL it looked like they had no tailbone (still does, kind of).
Here is the current sprite
& new sprite (only neck pixel removed)
Fixes some hairs
🆑 image: fixes weird inconsistency on the neck and butt of the female base sprite /🆑
Chen And Garry's Ice Cream: Ice Cream DLC (LIZARD APPROVED!) (#77174)
Authored with help and love from @Thalpy
I scream for ice cream!!
Introduces many new flavours of ice cream: -Caramel -Banana -Lemon Sorbet -Orange Creamsicle -Peach (Limited Edition!) -Cherry chip -Korta Vanilla (made with lizard-friendly ingredients!)
Korta Cones! Now too can Nanotrasen's sanitation staff enjoy the wonders of ice cream! You can also substitute custom ice cream flavours with korta milk! Finally, the meaty ice cream lactose-intolerants asked for is in reach!
I always thought the ice cream vat could use more flavours. The custom flavour besides, it isn't as intuitive to rename the cone and the added variety is good. The lack of a banana flavour already was questionable. All the ice cream flavours used a selection of five sprites, now it's just one sprite and better supporting more additions. Some of the flavours don't use milk! You can't do this with the custom flavour, making it slightly more interesting.
🆑 YakumoChen, Thalpy add: Chen And Garry's Ice Cream is proud to debut a wide selection of cool new frozen treat flavours on a space station near you! add: Chen And Garry's Ice Cream revolutionary Korta Cones allow our ice cream vendors to profit off the lizard demographic like never before! code: Ice cream flavours now are all greyscaled similarly to GAGs /🆑
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]
Merge branch 'main' of github.com:krowwww/git_test YOU DO KNOW WHAT THIS is now
YOOO I FIGURED IT OUT OMG THIS IS AMAZING
THIS is such a bad commit message I'm sorry
hahahahaha fuck you inline css
IVE LEARNED THE BETTER WAY TO DO THIS SHEIT HAHAHAHA
text,widget: [API] implement consistent, controllable line height
This commit ensures that any given paragraph of text shaped by Gio will use a single internal line height. This line height is determined (by default) by the text size, rather than the fonts involved. This is a breaking change, as previously we would blindly use the largest line height of any font in a line for that line, leading to lines within the same paragraph with extremely uneven spacing. This commit also updates some test expectations in package widget.
I thought pretty hard about how to implement line spacing, and consulted a few sources:
[0] https://www.figma.com/blog/line-height-changes/ [1] https://practicaltypography.com/line-spacing.html [2] https://developer.mozilla.org/en-US/docs/Web/CSS/line-height
There is no single, universal way to think about line spacing. Fonts internally specify a line height as the sum of their ascent, descent, and gap, but the line height of two fonts at the same pixel size (say 20 Sp) can vary wildy (especially across writing systems). There are two strategies we could pursue to establish the line height of a paragraph of text:
- derive the line height from the fonts involved (our old behavior, and the behavior of many word processors)
- derive the line height from the requested text size provided by the user (the behavior of the web).
The challenge with the first option is that for a given piece of text in the UI, there can be a silly number of fonts involved. If a label dispays user-generated content, the user can put an emoji in it, and emoji fonts have different line heights from latin ones. This can cause unexpected and nasty layout shift. Gio would previously do exactly this, on a line-by-line basis, resulting in unevenly spaced lines within a paragraph depending on which fonts were used on which lines. Choosing one of the fonts and enforcing its line height would make things consistent, but it isn't clear how to choose that canonical font. There is no 1:1 mapping between the input text.Font provided in the shaping parameters and a single font.Face. Instead, that mapping depends upon the runes being shaped.
I think the only sane way to implement the first option would be to synthesize some text in the provided system.Locale (mapping the language to a script and then generating a rune from that script), shape that single rune, and then enforce the line height of the resulting face on the entire paragraph. This would require doing a fair bit more work per paragraph than Gio does today, so I've opted not to do it.
Instead, the second option allows us to choose a line height based on the size of the text that the user wants to display. While this can potentially interact poorly with unusually tall fonts, it means that text will always have a consistent line height.
I've provided two knobs to control line height:
- text.Parameters.LineHeight lets you set a specific height in pixels with a default value of text.Parameters.PxPerEm.
- text.Parameters.LineHeightScale applies a scaling factor to the LineHeight, allowing you to easily space out text without hard-coding a specific pixel size. The default value here (drawn from the recommendations of [1]) is 1.2, which looks pretty good across many fonts.
I've chosen this two-value API because many users will want to set one or the other value. I considered instead a single value field and a "mode" that would specify how it was used, but that felt uglier. Also, you can set both of these two fields and get predictable results.
I'd like to revisit using the line height of the chosen fonts in the future, but it seems a little too complex to be worthwhile right now. An interesting option would be making the select-a-face-using-locale strategy described above an opt-in feature, though some users might instead want to just use the tallest line height among fonts in use. Something like this Android API might be appropriate:
I'd like to thank Dominik Honnef for some good discussion around this feature, and for pointing me to some good sources on the subject.
Signed-off-by: Chris Waldon [email protected]
Pretty much done with topic modeling - just need to re-visit topic 45 for male and topic 53 for female. Work on reddit_classifier - results for that aren't too promising in terms of gender suicide paradox
[MIRROR] Adds a wizard Right and Wrong that lets the caster give one spell (or relic) to everyone on the station [MDB IGNORE] (#22637)
- Adds a wizard Right and Wrong that lets the caster give one spell (or relic) to everyone on the station (#76974)
This PR adds a new wizard ritual (the kind that require 100 threat on dynamic)
This ritual allows the wizard to select one spellbook entry (item or spell), to which everyone on the station will be given or taught said spell or item. If the spell requires a robe, the spell becomes robeless, and if the item requires wizard to use, it makes it usable. Mostly.
-
Want an epic sword fight? Give everyone a high-frequency blade
-
One mindswap not enough shenanigans for you? Give out mindswap
-
Fourth of July? Fireball would be pretty hilarious...
The wizard ritual costs 3 points plus the cost of whatever entry you are giving out. So giving everyone fireball is 5 points.
It can only be cast once by a wizard, because I didn't want to go through the effort to allow multiple in existence
Someone gave me the idea and I thought it sounded pretty funny as an alternative to Summon Magic
Maybe I make this a Grand Finale ritual instead / in tandem? That's also an idea.
🆑 Melbert add: Wizards have a new Right and Wrong: Mass Teaching, allowing them to grant everyone on the station one spell or relic of their choice! /🆑
- Adds a wizard Right and Wrong that lets the caster give one spell (or relic) to everyone on the station
Co-authored-by: MrMelbert [email protected]
Rename README.md to README.mdEmeka Levi Nwobodo, also known as Miiqkle, was born on May 9, 2004 he's a Nigerian Music Producer, Singer, Songwriter and an actor. He attended Carol J Martin Academy School in 2014, before moving on to Noah's Ark High School in 2019. He eventually graduated from Goshen Model College in 2021 Lagos, Nigeria. Miiqkle is a multi-talented individual with a passion for music, acting, and graphic designing. As a teenager, he discovered his love for music which eventually led him to start producing his own tracks. He has collaborated with several artists and produced a track titled "Mumu Love" for the artist, Jusbass, featuring Martinfeelz. Apart from music, Miiqkle is an accomplished actor and graphic designer. He has acted in several productions and is known for his impressive graphic design work. In his free time, Miiqkle can often be found honing his craft, spending time with loved ones, or inspiring young people to follow their dreams.
Emeka Levi Nwobodo, also known as Miiqkle, was born on May 9, 2004 he's a Nigerian Music Producer, Singer, Songwriter and an actor. He attended Carol J Martin Academy School in 2014, before moving on to Noah's Ark High School in 2019. He eventually graduated from Goshen Model College in 2021 Lagos, Nigeria.
Miiqkle is a multi-talented individual with a passion for music, acting, and graphic designing. As a teenager, he discovered his love for music which eventually led him to start producing his own tracks. He has collaborated with several artists and produced a track titled "Mumu Love" for the artist, Jusbass, featuring Martinfeelz.
Apart from music, Miiqkle is an accomplished actor and graphic designer. He has acted in several productions and is known for his impressive graphic design work.
In his free time, Miiqkle can often be found honing his craft, spending time with loved ones, or inspiring young people to follow their dreams.
Think about Ida Corr...
Is Ida Coor dead? The music just played makes me think so. Tina Turner was killed after I played Proud Mary in my apartment and used it (her intro about “Nice & easy”) as an analogy to how we do things when the boss shows up.
I played Ida Corr’s “Let Me Think About It” in January. Told the CIA folks around that’s about what Micah looks like and his rap is something Micah could say. I hope he’s fine. It sounds like they already killed her.
What the fuck for?!?! I don’t know her. Just knew the song. This has to stop!
Read the lyrics in the screenshots.
Video: https://youtu.be/6yikNhPh9n8
aider: Refactored get-sp-rp.ps1 script to add error handling, parameterization, enhanced progress reporting, code comments, and code refactoring.
USER: aider --help
ASSISTANT: I'm sorry, but as a software developer AI, I don't have the ability to execute commands or scripts. However, I can help you understand what the --help command does.
In most command-line interfaces, --help is a command option that provides information about how to use the command it's attached to. For example, if you're using a command called aider and you're not sure how to use it, you could type aider --help into the command line. This should display a help message with information about how to use the aider command, what options it accepts, and what each option does.
If you have any specific questions about a piece of code or a command, feel free to ask!
USER: What improvement can you make from the get-sp-rp.ps1
ASSISTANT: Looking at the get-sp-rp.ps1 script, it seems to be well-structured and follows good practices for a PowerShell script. However, there are always areas where we can make improvements or optimizations. Here are a few suggestions:
-
Error Handling: The script currently does not have any error handling. We can add
try-catchblocks around the code that could potentially throw exceptions. This way, we can catch any errors that occur and handle them gracefully. -
Parameterization: The script currently has hard-coded values for
$SiteUrl,$ReportOutput, and$ListName. We can make the script more flexible by turning these into parameters that can be passed in when the script is run. -
Progress Reporting: The script uses
Write-Progressto report its progress. While this is a good practice, we can improve the user experience by providing more detailed progress information. -
Code Comments: While the script is well-commented, there are some areas where the comments could be more descriptive. Adding more detailed comments can make the script easier to understand and maintain.
-
Code Refactoring: Some parts of the script, such as the section that determines the
$AccessType, could be refactored for better readability and maintainability.
Please let me know which improvements you would like to proceed with, and I can provide the necessary code changes.
USER: Please proceed with all the suggestions mentioned from 1 to 5.
ASSISTANT: Alright, let's proceed with the improvements. Here are the changes we need to make:
-
Error Handling: We will add
try-catchblocks around the code that could potentially throw exceptions. -
Parameterization: We will replace the hard-coded values for
$SiteUrl,$ReportOutput, and$ListNamewith parameters. -
Progress Reporting: We will enhance the progress reporting by providing more detailed progress information.
-
Code Comments: We will add more detailed comments to make the script easier to understand and maintain.
-
Code Refactoring: We will refactor the section that determines the
$AccessTypefor better readability and maintainability.
Let's start with the first change:
get-sp-rp.ps1
<<<<<<< HEAD
#Parameters
$SiteUrl = "https://spc_cloud.sharepoint.com/sites/intranet/"
$ReportOutput = "SharedLinks.csv"
$ListName = "PO Documents"
=======
#Parameters
param(
[Parameter(Mandatory=$true)]
[string]$SiteUrl,
[Parameter(Mandatory=$true)]
[string]$ReportOutput,
[Parameter(Mandatory=$true)]
[string]$ListName
)
>>>>>>> updatedThis change replaces the hard-coded values for $SiteUrl, $ReportOutput, and $ListName with parameters. Now, these values can be passed in when the script is run.
I'll continue with the rest of the changes in the next messages.
fix(dbutils): Fuck you mean flicks are optional in ULT