added
stringdate 2025-04-01 04:05:38
2025-04-01 07:14:06
| created
timestamp[us]date 2001-10-09 16:19:16
2025-01-01 03:51:31
| id
stringlengths 4
10
| metadata
dict | source
stringclasses 2
values | text
stringlengths 0
1.61M
|
|---|---|---|---|---|---|
2025-04-01T06:37:33.065795
| 2023-03-15T13:22:20
|
1625523098
|
{
"authors": [
"peterjan"
],
"license": "MIT",
"license_source": "github-api",
"license_type": "permissive",
"provenance": "gharchive-dolma-0000.json.gz:2670",
"repo": "SiaFoundation/renterd",
"url": "https://github.com/SiaFoundation/renterd/pull/209"
}
|
gharchive/pull-request
|
Refill after sync
I think we should try and fund after syncing. I can't see of downsides really there's only upsides. One of the reasons driving this change is the logging in the autopilot which says "Successfully funded account" after potentially failing to fund but succeeding so sync (which clears the error). With this change, seeing that log line will effectively mean that the account was funded to the expected balance.
Putting this back in DRAFT, I just had a great idea: what if we change the endpoint to take the expected balance rather than the fund amount.
|
2025-04-01T06:37:33.110931
| 2023-02-04T15:33:55
|
1570993705
|
{
"authors": [
"SigmundGranaas",
"Steveplays28"
],
"license": "MIT",
"license_source": "github-api",
"license_type": "permissive",
"provenance": "gharchive-dolma-0000.json.gz:2671",
"repo": "SigmundGranaas/forgero",
"url": "https://github.com/SigmundGranaas/forgero/issues/396"
}
|
gharchive/issue
|
Remove vanilla tools from loot generation if the disable_vanilla_recipes config option is set
Vanilla iron pickaxes still generate in blacksmith chests, for example, even though the disable_vanilla_recipes config option is set.
The option to disable recipes is quite, specific, should we maybe add an option like disable_vanilla_tool_loot ?
Sounds good, though maybe it'd be less confusing if there was simply a way to do both in one option like disable_vanilla_tools.
Yeah that would be a lot simpler to toggle.
I am adding a toggle that changes the loot to forgero loot as well.
Ayy nice!
|
2025-04-01T06:37:33.160605
| 2023-04-18T13:05:42
|
1673096651
|
{
"authors": [
"dschonholtz",
"samuelbutler"
],
"license": "MIT",
"license_source": "github-api",
"license_type": "permissive",
"provenance": "gharchive-dolma-0000.json.gz:2672",
"repo": "Significant-Gravitas/Auto-GPT-Benchmarks",
"url": "https://github.com/Significant-Gravitas/Auto-GPT-Benchmarks/issues/4"
}
|
gharchive/issue
|
Switch to a Ubuntu container instead of a python container
Currently, we can't run bash, git or shell commands in our AutoGPT container.
This would be to switch the container to Ubuntu so we can!
This likely involves a PR to the core AutoGPT repo, but that's ok.
Let me know what you think of this new Dockerfile and if you run into any issues building the container using it. It should be a drop-in replacement.
#15
Per our discussion I am modifying this as the goal is to enable bash. We now also have plugins in the main repo.
we should at least evaluate that. Although That could be broken out into a new repo
|
2025-04-01T06:37:33.346060
| 2016-02-15T19:41:05
|
133799669
|
{
"authors": [
"DaZombieKiller",
"Jan1902",
"RockyTV",
"SirCmpwn",
"fahadash"
],
"license": "mit",
"license_source": "bigquery",
"license_type": "permissive",
"provenance": "gharchive-dolma-0000.json.gz:2673",
"repo": "SirCmpwn/ChatSharp",
"url": "https://github.com/SirCmpwn/ChatSharp/issues/54"
}
|
gharchive/issue
|
BUG: HandleJoin crashes when a user comes back
When a user QUITs and joins back, the following line crashes
https://github.com/SirCmpwn/ChatSharp/blob/master/ChatSharp/Handlers/ChannelHandlers.cs#L15
Attached is the log of the bot. A good solution would be to remove the user entirely from the user collection once he/she quits.
chatsharp_bot_log.txt
I mentioned the fix for this bug here: https://github.com/SirCmpwn/ChatSharp/pull/57#issuecomment-202685890
Has someone found a fix for that yet, or will there be an official one ?
This is a hard one to tackle. There are at least three different ways for storing the client's channel list: IrcClient.Channels, IrcClient.User.Channels and IrcClient.Users[User.Nick].Channels. I can think of two solutions: either all of these should be merged into a single one, or only one of them must exist while the other two have references to the channel list, instead of handling the channel list separately.
Let's not make breaking changes, but I'm all for unifying the stores.
OR, let's write unit tests.
@fahadash I spent a day and a half trying to fix this issue, with some results. I managed to fix the PART bug, but now there's another bug: when the client joins a channel with at least one user in it, it will throw trying to parse the other user's modes.
The reason for the PART bug was simple: the parted channel would be removed from the channel list before the PART message could be parsed.
|
2025-04-01T06:37:33.349251
| 2020-10-14T16:15:05
|
721596360
|
{
"authors": [
"PepijnMC",
"SirLich",
"stirante"
],
"license": "MIT",
"license_source": "github-api",
"license_type": "permissive",
"provenance": "gharchive-dolma-0000.json.gz:2674",
"repo": "SirLich/bedrock-wiki",
"url": "https://github.com/SirLich/bedrock-wiki/issues/206"
}
|
gharchive/issue
|
Create a feature document for upcoming technical changelogs.
Bedrock changelogs are pretty lackluster compared to Java's when it comes to technical changes and additions. A document with a proper and easy to understand technical changelog for the next update (in this case 1.16.100) would be helpful for anyone trying to keep up with new features. Notes on what features are in experimental (and when they leave experimental) are also very helpful.
I think it would be a good idea to use recently created news page for this. I already thought about posting about newest betas, but with emphasis on technical changes and how we could use them.
Added news tag: https://wiki.bedrock.dev/news/bedrock-betas.html
Also first changelog written by me (I had no idea what to write about bugfix version honestly): https://wiki.bedrock.dev/2020/10/16/beta-1-16-100-60.html
I'm closing this out. Thanks for the suggestion Pepijn, and thanks to Stirante for making the implementation!
|
2025-04-01T06:37:33.350366
| 2024-12-15T03:56:22
|
2740262726
|
{
"authors": [
"SirMallard",
"TechHog8984"
],
"license": "MIT",
"license_source": "github-api",
"license_type": "permissive",
"provenance": "gharchive-dolma-0000.json.gz:2675",
"repo": "SirMallard/Iris",
"url": "https://github.com/SirMallard/Iris/pull/87"
}
|
gharchive/pull-request
|
Remove print from Commit 223848d
I assume this was a print for testing and should no longer exist.
Thanks for catching this. You are correct in assuming this was for testing and should not be in the release.
|
2025-04-01T06:37:33.359469
| 2022-10-17T13:49:11
|
1411619978
|
{
"authors": [
"markvanaalst"
],
"license": "Apache-2.0",
"license_source": "github-api",
"license_type": "permissive",
"provenance": "gharchive-dolma-0000.json.gz:2676",
"repo": "Sitecore/developer-portal",
"url": "https://github.com/Sitecore/developer-portal/pull/329"
}
|
gharchive/pull-request
|
Content/ordercloud page
Description / Motivation
Updates to OrderCloud page
Added promo components
Logo
How Has This Been Tested?
Local and Vercel
Types of changes
[ ] Bug fix (non-breaking change which fixes an issue)
[X] New feature (non-breaking change which adds functionality)
[ ] Breaking change (fix or feature that would cause existing functionality to change)
[ ] Documentation update (non-breaking change; modified files are limited to the /data directory or other markdown files)
Checklist:
[X] I have read the Contributing guide.
[X] My code/comments/docs fully adhere to the Code of Conduct.
[X] My change is a code change.
[ ] My change is a documentation change and there are NO other updates required.
[ ] My change has new or updated images which are stored in the /public/images folder that need to be migrated to Sitecore DAM
📝 Changed routes:
/
(view full size)
Commit 778f4b6c6c43ea879c80ba3c9cf668f1fa92eb06 (https://developer-portal-kv9uwkpyv-sitecoretechnicalmarketing.vercel.app).
|
2025-04-01T06:37:33.363823
| 2019-12-25T09:07:07
|
542299140
|
{
"authors": [
"SiwyKrzysiek"
],
"license": "MIT",
"license_source": "github-api",
"license_type": "permissive",
"provenance": "gharchive-dolma-0000.json.gz:2677",
"repo": "SiwyKrzysiek/magic-foots",
"url": "https://github.com/SiwyKrzysiek/magic-foots/issues/10"
}
|
gharchive/issue
|
Display current value of selected sensor
This thing looks need
https://plot.ly/python/gauge-charts/
|
2025-04-01T06:37:33.508494
| 2016-08-03T17:59:24
|
169194165
|
{
"authors": [
"Codeick",
"HenryLoenwind",
"MatthiasMann",
"Rakinare",
"lakotajames",
"markozar"
],
"license": "Unlicense",
"license_source": "github-api",
"license_type": "permissive",
"provenance": "gharchive-dolma-0000.json.gz:2679",
"repo": "SleepyTrousers/EnderIO",
"url": "https://github.com/SleepyTrousers/EnderIO/issues/3577"
}
|
gharchive/issue
|
Capacitor Banks resetting output and input to 0 RF/t
Issue Description:
Capacitor banks in EnderIO are resetting their input and output values to 0 RF/t.
What happens:
When I start up the world in singleplayer the capacitor banks (setup in multiblock) reset the input and output to 0 RF/t.
What you expected to happen:
For the input and output to stay at the same values as set by the user, not to reset to 0 RF/t.
Steps to reproduce:
In singleplayer, setup several capacitor banks together to form a capacitor bank structure.
Supply power to them and change the input and/or output values.
Restart the client and load up the world.
Check the input and output.
Affected Versions (Do not use "latest"):
EnderIO: 1.10.2-<IP_ADDRESS>_beta
EnderCore: 1.10.2-<IP_ADDRESS>-beta
Minecraft: 1.10.2
Forge: <IP_ADDRESS>4
Your most recent log file where the issue was present:
http://pastebin.com/kmBzMHF9
NOTE: It happens when I restart the client, NOT the world.
I can not confirm this. Tried it on exactly the same versions multiple times, working just fine. If yes, pleas tell me which and the version, so I can try under those circumstances.
I actually had this happen to me a couple of times in multiplayer.
Happened to players on my server as well. We think it might be when the server goes down, but not sure.
Hi, I also can confirm this. It happens each time I start the client. I have a client server configuration running on my computer. The server runs on forge-1.10.2-<IP_ADDRESS>2-universal.jar, while the client is 1.10.2.
You can find the latest logs here:
fml-server-latest
latest
You will see a kind of mess in the log because this is a test world where I added and removed mods,
This is a screenshot of the setup:
batteries setup
and this the list of the mods I have installed on server:
batteries setup
I also think that input and output values resetted while playing, without restarting client, I just checked the battery after a while and it was again to 0 rf/t. But I can not confirm this 100%. If I get some evidence of this I will post here.
@markozar which was fixed in build 121 on Oct 11.
Wonderful, thank you!
I did not find it on curseforge but searching on google I found it on http://maven.tterrag.com/com/enderio/EnderIO. I hope it's correct.
I use http://ci.tterrag.com/job/EnderIO-1.10/ and http://ci.tterrag.com/job/EnderCore-1.10/
Nice to know, thank you!
|
2025-04-01T06:37:33.515614
| 2016-10-23T05:46:19
|
184673257
|
{
"authors": [
"MatthiasMann",
"SnowWhite8801"
],
"license": "Unlicense",
"license_source": "github-api",
"license_type": "permissive",
"provenance": "gharchive-dolma-0000.json.gz:2680",
"repo": "SleepyTrousers/EnderIO",
"url": "https://github.com/SleepyTrousers/EnderIO/issues/3778"
}
|
gharchive/issue
|
So I open the Technic launcher, open the 1.7.10 pack, it loads for a while, the main screen comes up and I go into single player and select my world, then it comes up with "Loading world", and after a few seconds the window closes and it goes back to the Technic launcher. It started doing this a couple of days ago. I hadn't changed anything or updated anything.
I've had a look through the logs and I have tried removing the following mods:
StevesAddons-1.7.10-0.10.16
SimplyJetpacks-MC1.7.10-1.5.3
logisticspipes-<IP_ADDRESS>
EnderIO-1.7.10-<IP_ADDRESS>9_beta
IC2NuclearControl-2.4.2a
However, it still won't load. Sometimes the log won't give me an actual error (not that I'm great at reading logs. I've also had a look through some posts on GitHub and various other sites but I'm really stuck. I would love some help with this! It's always depressing when you have to start a new world if you've come far in the previous one, and this always seems to happen to me too!
Starting a new world works just fine.
Here's the log:
[http://pastebin.com/iGNpvTG2]
The crash is caused by hardcorequesting - there is nothing related to EnderIO in the stack trace.
Thanks for that.
I have removed the following mods:
HardcoreEnderExpansion MC-1.7.10 v1.8.6
HQM-The Journey-4.4.4
The game still exits upon loading the world, and this is the log:
[http://pastebin.com/uBR83k40]
Now your world is corrupted - you can see that at the amount of NBT and chunk decoding errors.
Oh no :( So just start a new world? And would you suggest not using hardcorequesting again so I can avoid this happening again? This has happened a few times to me now.
No idea - you are asking in the wrong mod. I can't give you any advice to other mods.
But I suggest you always make a backup of your World's save folder when you change anything with mods (either configs, updates etc). Removing mods on an existing world has a good chance to cause corruption - esp when combined with adding new mods.
Alright. Well thanks so much for your help!
|
2025-04-01T06:37:33.528841
| 2018-10-13T01:35:19
|
369754592
|
{
"authors": [
"EpicSquid",
"HenryLoenwind",
"VladimirMangos",
"tyler489"
],
"license": "Unlicense",
"license_source": "github-api",
"license_type": "permissive",
"provenance": "gharchive-dolma-0000.json.gz:2681",
"repo": "SleepyTrousers/EnderIO",
"url": "https://github.com/SleepyTrousers/EnderIO/issues/4897"
}
|
gharchive/issue
|
[Fatal recipe error] Impossible disable recipe at duplicate recipe load error
Issue Description:
Minecraft fail load with error:
[04:30:02] [main/ERROR]: Invalied recipe while parsing IMC:
[04:30:02] [main/INFO]: [crazypants.enderio.base.config.recipes.RecipeLoader:handleIMCRecipes:149]: crazypants.enderio.base.config.recipes.InvalidRecipeConfigException: Duplicate recipe Sagmill: Ender Dust at [row,col]:[1,78]
It happens with EnderIO-1.12.2-5.0.36.jar
but not with EnderIO-1.12.2-5.0.35.jar
Possible problem real but my attempt disable recipe by adding
<recipe name="Sagmill: Ender Dust" disabled="true"/>
to
config\enderio\recipes\user\user_recipes.xml
not resolve load problem
What happens:
Minecraft client not finish startup
What you expected to happen:
Or recipe error unexpected and bug or workaround to disable duiplicate recipe work.
Steps to reproduce:
Can be reproduced with minimal mods list
EnderCore-1.12.2-0.5.41.jar
EnderIO-1.12.2-5.0.36.jar
JAOPCA-1.12.2-<IP_ADDRESS>.jar
RedstoneFlux-1.12-<IP_ADDRESS>-universal.jar
thermalsolars-1.12.2-1.9.2.jar
WrapUp-1.12-1.1.3.jar
Affected Versions (Do not use "latest"):
EnderIO: EnderIO-1.12.2-5.0.36.jar
EnderCore: EnderCore-1.12.2-0.5.41.jar
Minecraft: 1.12.2
Forge: forge-<IP_ADDRESS>70
SpongeForge? no
Optifine? no
Single Player
Your most recent log file where the issue was present:
https://paste2.org/K6vP3m1K
[04:30:02] [main/ERROR]: IMC from the mod 'jaopca'
[04:30:02] [main/ERROR]: ```
As i note: I see problem not in reporting error at bad recipe, but imposability ignore this recipe in Ender IO but avoid generation Ender IO version of recipe for Sagmill.
Soo you would rather not have that recipy in the base mod.. in the off chance that jaopca is installed? What if jaopca isnt installed?
Also u cant disable it becausw the duplicate is comming from joapca.
You are better off reporting this as a bug to jaopca, since they are responsible for it.
um, stop, stop, stop.
Unless jaopca sends the recipe twice this should not give a duplicate error. IMC messsages are allowed to override core recipes.
I'll look into this.
Soo you would rather not have that recipy in the base mod.. in the off chance that jaopca is installed? What if jaopca isnt installed?
If I remove any from mods from list in original post then problem not reproduced.
um, stop, stop, stop.
Unless jaopca sends the recipe twice this should not give a duplicate error. IMC messsages are allowed to override core recipes.
I'll look into this.
from what me and epic were discussing
what happens here is IMC sends... Enderio processes IMC...... Enderio process Core... game detects and crashes... before loading the user recipys @HenryLoenwind
Maybe user recipes can be proccessed early for let user better control conflict mods recipes.
Strange thing: in prev. build of Ender IO this problem not happens.
Please try again with http://ci.tterrag.com/job/EnderIO-Modules/job/EnderIO-Hourly/760/ This should provide better error messages.
With removed custom changes in config\enderio\recipes\user\user_recipes.xml (so original file state at problem detection)
And updated
EnderCore-1.12.2-0.5.41.jar ->EnderCore-1.12.2-0.5.42.jar
EnderIO-1.12.2-5.0.36.jar -> EnderIO-1.12.2-5.0.760-nightly.jar
Problem not showup for test mods list
And also minecraft world load fine for original mods (420 mods)
Thank you for fix problem!
Could you please have a look into the log and see if there are messages with "is being replaced by a recipe from"? Thanks
|
2025-04-01T06:37:33.566855
| 2024-02-06T18:41:43
|
2121448203
|
{
"authors": [
"ImUrX",
"darkfader"
],
"license": "Apache-2.0",
"license_source": "github-api",
"license_type": "permissive",
"provenance": "gharchive-dolma-0000.json.gz:2682",
"repo": "SlimeVR/SlimeVR-Server",
"url": "https://github.com/SlimeVR/SlimeVR-Server/issues/934"
}
|
gharchive/issue
|
v0.11.0 "Sort by name" doesn't work.
As title says.
I can't verify currently but this only happens with the card view, right? The table view does indeed sort by name if you enable it
seems to be working currently
|
2025-04-01T06:37:33.585753
| 2023-09-04T01:09:49
|
1879330859
|
{
"authors": [
"hinpa"
],
"license": "mit",
"license_source": "bigquery",
"license_type": "permissive",
"provenance": "gharchive-dolma-0000.json.gz:2686",
"repo": "SmartFinn/eve-ng-integration",
"url": "https://github.com/SmartFinn/eve-ng-integration/issues/63"
}
|
gharchive/issue
|
Terminal opens and closes instantly
Hello! I've tried using eve-ng-integration with urxvt. The problem I've met is that when I tried to connect to my switch, it didn't work. Command "eve-ng-integration telnet://<IP_ADDRESS>:30024" in my urxvt does nothing (urxvt just promptly appears and disappears on my screen). I tried to connect using PuTTY and it worked.
I don't know if this is a correct solution but:
I found the problem to be in the python file "eve-ng-integration/bin/eve-ng-integration" in the function "execute" in the Terminal class:
def execute(self, command):
if isinstance(command, (str)):
command = command.split('\n') # here is the problem
term = self._terminal_emulator_cmd()
Popen(term + command)
When "command = command.split('\n')" is changed to "command = command.split(' ')", everything seems to work. The terminal window appears and I have the control of the switch.
I hope it gets fixed soon. Thank you in advance!
I tracked back the problem to commit fixing #8 issue. Reverting back seems to fix the problems of these issues too (at least on my machine). I needed to change _current_desktop to _is_command though. Maybe that was the problem
|
2025-04-01T06:37:33.599361
| 2024-08-04T09:51:05
|
2447042665
|
{
"authors": [
"CodiumAI-Agent",
"SmartManoj"
],
"license": "MIT",
"license_source": "github-api",
"license_type": "permissive",
"provenance": "gharchive-dolma-0000.json.gz:2687",
"repo": "SmartManoj/Kevin",
"url": "https://github.com/SmartManoj/Kevin/pull/19"
}
|
gharchive/pull-request
|
rftr: remove unused browser output objects
What is the problem that this fixes or functionality that this introduces? Does it fix any open issues?
Temporarily resolves #2877
Give a summary of what the PR does, explaining any non-trivial design decisions
Directly stored axtree_txt instead of axtree_object, and extra_element_properties
Removed dom_object
@CodiumAI-Agent /review
PR Reviewer Guide 🔍
⏱️ Estimated effort to review: 3 🔵🔵🔵⚪⚪
🧪 No relevant tests
🔒 No security concerns identified
⚡ Key issues to review
Error HandlingThe error handling for 'flatten_axtree_to_str' might not be sufficient. It logs the error but does not handle the potential consequences of having an incomplete or incorrect 'axtree_txt'.
Logging DetailsThe error message logged when 'cur_axtree_txt' starts with 'AX Error:' might need more context or details for better debugging.
@CodiumAI-Agent /ask
The error handling for 'flatten_axtree_to_str' might not be sufficient. It logs the error but does not handle the potential consequences of having an incomplete or incorrect 'axtree_txt'.
It has not happened before.
Logging Details
The error message logged when 'cur_axtree_txt' starts with 'AX Error:' might need more context or details for better debugging.
It has not happened before. For now, the error name is attached to it.
Ask❓
The error handling for 'flatten_axtree_to_str' might not be sufficient. It logs the error but does not handle the potential consequences of having an incomplete or incorrect 'axtree_txt'. It has not happened before. > [Logging Details](https://github.com/SmartManoj/Kevin/pull/19/files > The error message logged when 'cur_axtree_txt' starts with 'AX Error:' might need more context or details for better debugging. It has not happened before. For now, the error name is attached to it.
Answer:
Error Handling for flatten_axtree_to_str
The current error handling for flatten_axtree_to_str in the PR does log the error but does not address the potential consequences of having an incomplete or incorrect axtree_txt. Here are a few suggestions to improve the error handling:
Fallback Mechanism: Implement a fallback mechanism to handle the scenario where flatten_axtree_to_str fails. For example, you could use a default or empty string as a fallback value for axtree_txt.
try:
axtree_txt = flatten_axtree_to_str(
obs['axtree_object'], # accessibility tree object
extra_properties=obs['extra_element_properties'], # extra element properties
with_clickable=True,
filter_visible_only=True,
)
except Exception as e:
logger.error(f'Error when trying to process the accessibility tree: {e}')
axtree_txt = 'AX Error: Processing failed'
Detailed Logging: Enhance the logging to include more context, such as the state of the obs object or other relevant details that could help in debugging.
except Exception as e:
logger.error(f'Error when trying to process the accessibility tree: {e}, obs: {obs}')
axtree_txt = 'AX Error: Processing failed'
Error Propagation: Consider propagating the error to higher levels if it is critical for the operation. This can be done by raising a custom exception or returning an error status.
Error Message Context for cur_axtree_txt
The error message logged when cur_axtree_txt starts with 'AX Error:' could indeed benefit from more context. Here are some suggestions:
Include the Original Error: Ensure that the original error message is included in the log for better traceability.
if cur_axtree_txt.startswith('AX Error:'):
error_message = cur_axtree_txt.split(':', 1)[1]
logger.error(f'Error when trying to process the accessibility tree: {error_message}')
return MessageAction('Error encountered when browsing.')
Additional Context: Add more context to the log message, such as the state of the last_obs object or other relevant details.
if cur_axtree_txt.startswith('AX Error:'):
error_message = cur_axtree_txt.split(':', 1)[1]
logger.error(f'Error when trying to process the accessibility tree: {error_message}, last_obs: {last_obs}')
return MessageAction('Error encountered when browsing.')
User-Friendly Message: Ensure that the message returned to the user is informative but not overly technical.
if cur_axtree_txt.startswith('AX Error:'):
error_message = cur_axtree_txt.split(':', 1)[1]
logger.error(f'Error when trying to process the accessibility tree: {error_message}')
return MessageAction('An error occurred while processing the page. Please try again.')
By implementing these suggestions, the error handling and logging can be made more robust and informative, aiding in better debugging and user experience.
|
2025-04-01T06:37:33.605990
| 2024-03-16T12:52:47
|
2189954648
|
{
"authors": [
"Sitlintac",
"bsf29",
"vallieresluc"
],
"license": "Apache-2.0",
"license_source": "github-api",
"license_type": "permissive",
"provenance": "gharchive-dolma-0000.json.gz:2688",
"repo": "SmartThingsCommunity/smartthings-cli",
"url": "https://github.com/SmartThingsCommunity/smartthings-cli/issues/602"
}
|
gharchive/issue
|
How to display temperature instead of humidity with SONOFF SNZB-02 probes?
How to display temperature instead of humidity with SONOFF SNZB-02 probes? Currently, the default display in the Smartthings app is humidity. I would like to have the default temperature.
Additional context
Add any other context or screenshots about the question here.
This sounds like it might be an issue with your device driver. Someone on the SmartThings community forum posted a similar issue with their custom driver for the same device a couple of weeks ago (link); you might be able to find a solution to your problem there. If not, try reaching out to customer support. Good luck!
I had the same problem with the ST driver. I have 4 of these SONOFF devices. Some installed correctly and some were a pain. I was able to get it to default to temperature by uninstalling & reinstalling. Sometimes I had to do this several times. I have since switched to Mariano's edge driver that @Sitlintac mentioned. The only thing I don't like is that he has a virtual thermostat built into his driver that I don't need. You don't have to configure/use it and you still get all of the normal temperature & humidity stuff you want. Mariano also has other edge drivers that I find to be very useful and are worth checking out.
This page is specifically for issues for the SmartThings CLI, which doesn't appear to be related to the problem you're having with your SONOFF devices. I'm sorry to hear that the forum wasn't able to help you solve your problem. Please try reaching out to customer support for further help.
|
2025-04-01T06:37:33.607893
| 2022-12-23T12:37:07
|
1509304415
|
{
"authors": [
"SmartToolFactory",
"alvindizon"
],
"license": "Apache-2.0",
"license_source": "github-api",
"license_type": "permissive",
"provenance": "gharchive-dolma-0000.json.gz:2689",
"repo": "SmartToolFactory/Jetpack-Compose-Tutorials",
"url": "https://github.com/SmartToolFactory/Jetpack-Compose-Tutorials/issues/1"
}
|
gharchive/issue
|
Where is Tutorial3_2Screen7?
I just cloned the latest version of this repo and when I tried to build it, it seems that the composable Tutorial3_2Screen7 is missing.
Sorry, i'm current updating Constraints, Layout, Measurable tutorials. I probably missed it while renaming tutorials
Thank you, great repository BTW, this is a great learning resource!
|
2025-04-01T06:37:33.700073
| 2015-03-17T01:11:57
|
62249435
|
{
"authors": [
"Sneagan",
"benogle",
"yiliang",
"yiliangt"
],
"license": "mit",
"license_source": "bigquery",
"license_type": "permissive",
"provenance": "gharchive-dolma-0000.json.gz:2694",
"repo": "Sneagan/atom-handlebars",
"url": "https://github.com/Sneagan/atom-handlebars/issues/19"
}
|
gharchive/issue
|
Store package settings files in the settings/ directory instead of scoped-properties/
Reported via deprecation-cop
Thanks for adding this! Merged a fix. :)
Hi @Sneagan I've got the same issue with the package language-slim. Could you look into it?
@yiliangt This looks like an issue with this package, not mine. https://github.com/slim-template/language-slim
@Sneagan. Ok thanks.
|
2025-04-01T06:37:33.705733
| 2022-09-19T23:11:40
|
1378624533
|
{
"authors": [
"SnosMe",
"sushibagel"
],
"license": "MIT",
"license_source": "github-api",
"license_type": "permissive",
"provenance": "gharchive-dolma-0000.json.gz:2695",
"repo": "SnosMe/electron-overlay-window",
"url": "https://github.com/SnosMe/electron-overlay-window/issues/27"
}
|
gharchive/issue
|
Change overlay size/position
Is it possible to adjust the size and position of the overlay?
From what I can tell regardless of the size of the original overlay window it seems to expand it to fit the entire window so there is no way to interact with the underlying window unless it's set to ignore mouse events.
You can disable default behaviour of resizing Electron window and handle it yourself.
https://github.com/SnosMe/electron-overlay-window/blob/e0b3da27a20251cb5673c43390abdc2e3fe3e78e/src/index.ts#L59
In 3.0 beta there is no way, yeah.
You can disable default behaviour of resizing Electron window and handle it yourself.
https://github.com/SnosMe/electron-overlay-window/blob/e0b3da27a20251cb5673c43390abdc2e3fe3e78e/src/index.ts#L59
Thanks I'll give it a try.
|
2025-04-01T06:37:33.725534
| 2022-08-02T13:28:05
|
1325859732
|
{
"authors": [
"jrobison-sb",
"sfc-gh-asawicki"
],
"license": "MIT",
"license_source": "github-api",
"license_type": "permissive",
"provenance": "gharchive-dolma-0000.json.gz:2696",
"repo": "Snowflake-Labs/terraform-provider-snowflake",
"url": "https://github.com/Snowflake-Labs/terraform-provider-snowflake/issues/1161"
}
|
gharchive/issue
|
private_key authentication attribute conflicts with SNOWFLAKE_PASSWORD environment variable
Provider Version
0.25.36
Terraform Version
1.2.0
Describe the bug
The private_key authentication attribute, when set explicitly as part of a provider "snowflake {...} config, conflicts with the SNOWFLAKE_PASSWORD environment variable.
Expected behavior
Perhaps this is an unrealistic expectation, but I would expect them not to conflict with each other.
Code samples and commands
export SNOWFLAKE_PASSWORD=foo (which I need for non-Terraform automation and scripts which run against my Snowflake resources)
provider "snowflake" {
# See https://guides.snowflake.com/guide/terraforming_snowflake/index.html?index=..%2F..index#2
# for instructions on how to set up a user account to be used by Terraform.
// required
username = "someuser"
account = "ABC123456"
region = "us-east-1"
private_key = data.aws_kms_secrets.snowflake_private_key.plaintext["snowflake_private_key"]
// optional
role = "ACCOUNTADMIN"
}
Export the above environment variable and then use the above provider config and you'll get a conflict.
If something is explicitly defined in Terraform config, as a private key is here, it should take precedence over an environment variable.
Note that I also got the same experience with the snowsql provider, so this conflict is almost surely coming from the snowflake golang SDK. But it would be nice if this provider could handle this situation.
We are closing this issue as part of a cleanup described in announcement. If you believe that the issue is still valid in v0.89.0, please open a new ticket.
|
2025-04-01T06:37:33.728351
| 2022-07-12T12:08:40
|
1301970751
|
{
"authors": [
"sfc-gh-jalin",
"sfc-gh-kmaurya"
],
"license": "MIT",
"license_source": "github-api",
"license_type": "permissive",
"provenance": "gharchive-dolma-0000.json.gz:2697",
"repo": "Snowflake-Labs/terraform-provider-snowflake",
"url": "https://github.com/Snowflake-Labs/terraform-provider-snowflake/pull/1118"
}
|
gharchive/pull-request
|
feat: add AWS GOV support in api_integration
Added aws_gov_api_gateway and aws_gov_private_api_gateway in api_provider list in api_integration resource
Test Plan
[x] careful review
References
API Integration doc
issue ref #1113
/ok-to-test sha=d9195ba
/ok-to-test sha=d9195ba
|
2025-04-01T06:37:33.730663
| 2024-05-23T16:55:12
|
2313425954
|
{
"authors": [
"NotPhelps",
"Sober881"
],
"license": "MIT",
"license_source": "github-api",
"license_type": "permissive",
"provenance": "gharchive-dolma-0000.json.gz:2698",
"repo": "Sober881/qb-vendingjob",
"url": "https://github.com/Sober881/qb-vendingjob/issues/1"
}
|
gharchive/issue
|
target
i dont seem to get the ability to target it shows but doesnt allow me to click on it
If you do not use qb-target you will need to write the function for your target in place of qb-target things
so yeha i use qb-target when i go to the ped and click on it nothing happen other then the menu comes up and freezes untill you walk away so im not sure why
https://prnt.sc/T9Xicg5CN8pE
|
2025-04-01T06:37:33.748711
| 2024-06-04T10:03:13
|
2333106400
|
{
"authors": [
"JackismyShephard",
"SokolyMoravia"
],
"license": "MIT",
"license_source": "github-api",
"license_type": "permissive",
"provenance": "gharchive-dolma-0000.json.gz:2700",
"repo": "SociallyIneptWeeb/AICoverGen",
"url": "https://github.com/SociallyIneptWeeb/AICoverGen/issues/129"
}
|
gharchive/issue
|
Gradio version isn't updated to the latest patches.
Since I don't have a powerful enough NVIDIA chip, I use AICoverGen with Google Colab instead. Although I have installed both the latest editions of Python (3.12.3) and Gradio (4.32.2) and then ran the Python verification code to confirm that I'm using the 4.32.2 patch of Gradio, when I try to run Google Colab, the message "
IMPORTANT: You are using Gradio version 3.48.0, however version 4.29.0 is available, please upgrade."
still appears. I am worried that using a highly outdated version would badly affect the results of my AI covers. What can I do to fix this?
I am working on a fork of this repository which supports latest version of gradio 4 (4.37.1 as of speaking) as well as many new features. Its available here: https://github.com/JackismyShephard/ultimate-rvc, in case you are interested. Any feedback is greatly appreciated.
|
2025-04-01T06:37:33.758771
| 2018-01-16T16:21:19
|
288968105
|
{
"authors": [
"chipitsine",
"paulmenzel"
],
"license": "Apache-2.0",
"license_source": "github-api",
"license_type": "permissive",
"provenance": "gharchive-dolma-0000.json.gz:2701",
"repo": "SoftEtherVPN/SoftEtherVPN",
"url": "https://github.com/SoftEtherVPN/SoftEtherVPN/issues/428"
}
|
gharchive/issue
|
Integrate fuzzers
Integrate Guido Vranken’s work from https://github.com/guidovranken/SoftEtherVpn-Fuzz-Audit.
@guidovranken , can you help with fuzzers ?
|
2025-04-01T06:37:33.774679
| 2023-01-29T14:04:34
|
1561304043
|
{
"authors": [
"Ali-RS",
"Scrappers-glitch"
],
"license": "BSD-3-Clause",
"license_source": "github-api",
"license_type": "permissive",
"provenance": "gharchive-dolma-0000.json.gz:2702",
"repo": "Software-Hardware-Codesign/jme-alloc",
"url": "https://github.com/Software-Hardware-Codesign/jme-alloc/issues/16"
}
|
gharchive/issue
|
Consider adding a demo app
Please add a separate example app demonstrating multithreading and direct memory releasing in JME context.
This a list of tech-demos that could be made on a separate module jme3-testalloc:
[ ] HelloJme3alloc.java: demonstrating the basic alllocation/deallocation capabilities.
[ ] HelloThreadedJme3alloc.java: testing the multi-threading capabilities.
[ ] HelloMemoryCopy.java: demonstrating memoryCopy(ByteBuffer to, ByteBuffer from, long size).
[ ] HelloMemorySet.java: demonstrating memorySet(ByteBuffer buffer, int value, long size).
[ ] HelloMemoryMove.java: demonstrating memoryMove(ByteBuffer to, ByteBuffer from, long size).
[ ] HelloJme3allocLog.java (WIP).
I will notify you on forums, if you want to add more techdemos later after fixing issue #25, because i want to examine the windows github-runner image output.
|
2025-04-01T06:37:33.811098
| 2016-09-13T16:31:11
|
176688947
|
{
"authors": [
"RichardBradley",
"aeone",
"catalin-ursachi",
"chris-harris-softwire",
"hayh",
"pimterry",
"suzannehamilton",
"yingxinj"
],
"license": "mit",
"license_source": "bigquery",
"license_type": "permissive",
"provenance": "gharchive-dolma-0000.json.gz:2703",
"repo": "Softwire/minimum-viable-diversity-pledge",
"url": "https://github.com/Softwire/minimum-viable-diversity-pledge/issues/9"
}
|
gharchive/issue
|
Get initial feedback and improve
[sorry if I'm doing github wrong...]
Tim, this looks awesome. I have a couple of comments which you're totally free to ignore :-) I've put in descending order of how strongly I feel.
It's a bit weird that you can sign up without giving any info about yourself. Surely it's ok to ask people to put their name down, and maybe also company/job title? Anonymous sign-ups are pretty worthless IMO. I like this page: https://www.givingwhatwecan.org/about-us/members/
Shifting the focus towards diversity as a whole rather than just gender split is nice, but the way you've done it actually lowers the bar even further (you could have an all-male line-up with one Asian male and be fine), and in practice increases the number of speakers who can't meaningfully sign the pledge (as they themselves stop events from being homogeneous). I don't really have an answer to this tbh - but we could consider making the speaker's pledge a bit stronger (e.g. I'll actively spread the word about this pledge, or I'll only speak at events where there's some diversity not including myself)
Do we need to define diversity somewhere, or is it just obvious? Does it include, idunno, dyslexic speakers, narcoleptic speakers, the French? Am I just being deliberately boneheaded? Who knows??
Anonymousness - you may be right, I'm not sure on this one. Maybe going non-anonymous for now and waiting for somebody to complain is a better approach. I'd love to hear thoughts from other people. I'm open to doing this though.
This change does potentially lower the bar a little. I think it's a tradeoff in return for making the pledge itself more widely relevant and inclusive, and I think it's a worthwhile balance, but you're right, it's not perfect. I expect gender diversity is likely to be the main bit focused on though (it's easiest - everywhere in the world has a lot of women - and it's high-profile already). We are aiming for a minimal/worst-offenders level anyway, and I think the vast majority of events that were covered before (all-male events) still get the same impact (because I think they're typically all-straight-white-male events, in practice).
As for relevance to pledgers: it is always potentially relevant, but yes in practice it's less of a meaningful commitment the more unrepresented your group is. Previously though it was nonsensical for ~50% of the population, now it's at least potentially relevant to more, and still a meaningful commitment to most. It's not perfect, but it's less obviously/fundamentally broken, I think it's more widely useful overall, and I can't think of anything better :smile:. Notably this just for the speaker pledge though, everything else is equally relevant.
As for expanding the pledges; I'm cautious about asking people not to speak at events where there's no diversity other than yourself - it makes it harder for non-diverse events to invite diverse speakers - or making the pledge too complicated. Very simple changes might be workable though. "...and I'll warn/check with events about this in advance" to explicitly add the "how does this work" suggestions?
Totally agree - we should add more detail about diversity. "What do you mean by 'diverse' speakers?" is now in the FAQ: https://github.com/Softwire/minimum-viable-diversity-pledge/commit/848c74c021a10092b743d1991fca95bcc86292c8. Does that cover what you were looking for?
I've actually just dropped anonymity entirely for the company/event pledges. Individuals are maybe debatable, but for events/companies you're definitely right.
This is awesome! Super excited. Have you sent it round the directors yet? What do WES think?
Completely tiny thing, but it just occurred to me that the first two pledges start "I won't ever..." and the last two start "We will never..." - Is the difference deliberate? Should we make them consistent?
I think I agree with Chris that anonymous pledges are slightly worthless. Seeing the caveat "feel free to skip this if you're not comfortable publicizing this commitment" is a bit odd - it makes me think, "hang on, am I comfortable with this? why wouldn't someone be? maybe I shouldn't be." I think we should drop anonymity, and if the odd person really minds, they will just put in initials or an alias. We could put in a tick box to say "don't publish my name anywhere public" maybe.
There are one or two more things that I'm mulling over... I'll comment if I can think of any actual concrete things to say about them :p
Have you sent it round the directors yet?
Sorry I have now just seen your email chasing us up for feedback and I assume that's what you were waiting for - sorry!!!
WES have had a quick look and are very keen, but they're struggling to find substantial time for a detailed check through with feedback at the moment. I've sent it to Zoe yesterday to look at and confirm with the directors, but that's still in progress.
Ok, since you're both agreed on anonymity I've dropped it completely, and added a "Can we publish your name in the list of signups?" tickbox instead, so people can opt-out (but not companies and events; they're never anonymous).
I've also updated the intro text to make it "I/we will never..." in every case.
One new thing: the description on the site generally is ok I think, but for the pledges themselves in "I will never attend any paid conferences or panels with a completely homogeneous group of speakers" for example, "homogeneous" feels a bit formal. I want something like 'with zero diversity in the speaker lineup', but less wordy - any ideas?
Let me know about your mullings Ying! More thoughts the merrier.
This looks grand - I don't have any blocking concerns or further suggestions for improvement, so full speed ahead as far as I'm concerned.
I want something like 'with zero diversity in the speaker lineup', but less wordy - any ideas?
You could flip them all round to positive statements, e.g. "I will only attend paid conferences or panels that have a diverse speaker line-up"
Thanks Tim!
Two thoughts:
The first sentence in the header would be better split into 2 sentences I think? And then we need to change the 2nd sentence as it is then a bit further removed from the 1st one. Something like this?
Professional events need to be inclusive, by representing a diverse range of speakers. That way, everybody can be involved with and inspired by the cutting edge of their domain.
Too many events don't represent any diversity at all.
We want to...
About the "How to use this pledge" bit in Resources:
The description under "as a speaker" imo compounds the relevance issue. It simply doesn't make sense to say "I won't be able to speak if every other speaker you pick is a [black trans person] like me". I think we should just face it head on and explain what we think the pledge should mean for someone coming from a minority background, even if it necessarily means something less. "Because we've set the bar at a minimum level, this pledge might not be quite as meaningful for you if you are already in an underrepresented group. Please sign up anyway to show your support! You could even use this pledge as an excuse to exert more pressure on organisations to improve diversity further." or something?
Secondly, does this whole section fit better in "How does this work?" or even, in its own section? It seems very useful.
I've tweaked the intro with almost exactly those changes, moved the template text in resources into the How Does This Work section completely (you're right, it fits way better there), and added an FAQ item to cover marginalized people. We've also gained mobile styling and some tweaks on the way. What do you two think?
Unless anybody has strong opinions on it, I'm actually going to ignore the homogeneous bit for now I think - it is easier to read if you flip the negatives, but doesn't have the same feeling imo ("I will only speak at conferences or on panels with lineups that include some diversity" doesn't sound as solid a commitment as "I will never speak at any paid conferences or panels as part of a completely homogeneous group of speakers"). I think I'm ok with it.
Bit pedantic I suppose, but "I will never speak at any paid conferences or panels as part of a completely homogeneous group of speakers" seems to also ban, say, all-black panels, which seems contrary to the intended purpose?
The idea is that an all-black-male tech conference lineup probably isn't a great thing (although it is at least a change from all-white-male tech conferences) as you've got zero representation of women. If otoh you have black men and women though, great; you've got a degree of diversity, and this doesn't apply.
What 'diversity' is is a bit of a fluffy line of course (see the FAQ). You can argue that everybody is unique and diverse, and wiggle out of it if you really push for it, but I think most of the time a) it's fairly clear when your speaking lineup is a whole bunch of very similar people and b) in almost any case where that's happening, there's some major groups that are being excluded (e.g. 50% of the population).
This is great! I particularly like the example wording for conference attendees and speakers - it's tough to find assertive ways to phrase these things when you're unsure if you're the only one speaking up.
Two suggestions:
My only niggle is about the "Why is this important?" section, specifically the emphasis on "Diverse groups solve problems better". It might just be a personal bugbear, but I always think it's a shame when this is mentioned first. It's an important point, and I understand why it's highlighted - you're trying to convince people, and this might sway someone who would otherwise ignore arguments about diversity. But I think those other arguments (about fairness, inclusiveness and providing role models) are more important - I'd want more diversity at conferences even if the research said that diverse teams had no effect on problem solving. :)
I also realise it's only this section which emphasies that argument, and that the focus of the introduction is on inclusiveness. But it'd still read better to me if the sentence was something along the lines of "As well as helping and inspiring individual people from underrepresented groups, increasing speaker diversity is important because diverse groups solve problems better".
For the resources section, Meri Williams' post on getting a diverse lineup for The Lead Developer is really good: https://medium.com/@geek_manager/broadening-the-responses-to-our-conference-cfp-a22f120fa941
Chris: Shifting the focus towards diversity as a whole rather than just gender split is nice, but the way you've done it actually lowers the bar even further (you could have an all-male line-up with one Asian male and be fine)
Tim: What 'diversity' is is a bit of a fluffy line of course (see the FAQ). You can argue that everybody is unique and diverse, and wiggle out of it if you really push for it, but I think most of the time a) it's fairly clear when your speaking lineup is a whole bunch of very similar people and b) in almost any case where that's happening, there's some major groups that are being excluded (e.g. 50% of the population).
This probably isn't aimed at me at all. However, I got a change notification email for it, and I read it, and thought I'd stick my 2¢ in.
I agree with Chris: using the word "diversity" if you mean "representation for women" probably dilutes your meaning to the point of ineffectiveness. As it stands, if I were a slightly non-PC event organiser, I don't think I could be sure in advance whether or not my event were "diverse" enough to avoid getting flak from lots of activists pointing to this manifesto. If this manifesto only has meaning to those already in the know, what's the point?
This reminds me of a lot of code reviews I do where people start writing a FooConnector and think, "oh I could generalise this", and before you know it we have a PluggableConnectorFactoryFactory and it's really difficult to use and understand, and we never end up connecting to anything else so the generalisation was wasted.
By using such a general term and refusing to define it concretely I think you are giving too much wiggle room to both sides of the argument:
Anyone who wants to condemn an event can surely find a group which represents ~50% of the population and isn't represented (e.g. any non-English speakers at your conference?)
Anyone who wants to defend an event can find some "diversity" via the uniqueness of individuals, as you have already pointed out.
I'd consider changing it back to "I will never attend any paid conferences or panels with only men" or consider trying to define "diversity" (which is surely a fools errand)
Thanks Rich! More ideas and thoughts are definitely good, 2¢ away.
That said, I'm not too worried about this, and I still think this pledge is more useful now we've made these changes. It's primarily because I don't think either of those cases are problems we need to protect against, but also because 99% of cases where this ever matters are very clear cut, and leaving a tiny bit of space for common sense for the last 1% is fbm (rather than the impossible task of coming up with something both fair and precise).
We're not trying to write a formal binding contract. We're trying to write a useful clear guideline for people to opt into, hopefully in a way that results in positive change long-term.
For your two examples:
Aiming high for diversity is explicitly not our focus. We're just trying to push a minimum bar, to avoid events that represent only one major group (typically white men, but white women only panels and conferences are a contentious topic too). If you have any diversity at all already (e.g. somebody with disabilities in your lineup), this pledge isn't aimed at you. That sounds like an easy line, yes. That's the point though: loads of events & panels still fail at even that.
Defending clearly bad events seems unlikely. The person making the call on what's "diverse" is somebody who's actively come here and committed themselves to aiming for diversity. I'm not sure why you'd sign a pledge to avoid events without diversity and then try and wrangle your way out of it, and I'm not super worried about policing people who do so. The person making this 'is this diverse?' call is somebody who's signed up because they want to push for diversity - I'd like to give hints, but in the end I'm ok with them deciding what diversity is important to them.
Softwire is the motivating example. We were trying to come up with a commitment for what kind of events we'd rather not actively support people in going to (or similarly, a commitment we could encourage our public speakers to make about which events they'd speak at). You need a low bar to do that, or it's difficult and massively stymies getting anything done, and this is a clear, basic and useful one. Softwire isn't going to say "oh but we want to go to that event and, uh, it's got a blond guy", because we want to avoid non-diverse events. Nobody is going to point at Softwire and say "hey you went to an event that wasn't diverse enough to include [non-english speaking/female/latino] people" just because we've signed this pledge (certainly no more than they might already).
I think that's the key point: we're not creating a binding contract with strict rules, just an outline of a helpful line people can opt into and agree to aim for. I'm pretty confident this is useful, and might create some positive change long-term.
Does that context make it a bit clearer?
Also @suzannehamilton: thanks, that's really helpful, I totally agree! I've added Meri's article to the organizer resources, and replaced that bit of the FAQ with your exact words :+1:.
Looking great, really starting to take shape, and a lot of good suggestions made so far!
I think this bit could use some more work:
There are some people however that in today's world are never a member of a homogeneous group of speakers. If you're in this position, the speaker pledge is a commitment that you'd struggle to break! Feel free to sign it anyway to show your support, or to sign one of the other pledges, which are still just as relevant.
If I saw this, I personally would feel marginalised, particularly by "feel free to sign it anyway". I'd feel like my signature was a nice to have, and not as valuable as that of white male cis folks, which IMO is a bit counterproductive. We don't want the list of supporters to become the homogeneous group we're trying to discourage!
I think we absolutely do want the signature of folks from underrepresented groups - if we are trying to do something for them without including them, we are missing the point. They HAVE to be on board.
If they are attendees, they can action the bit where they object to attending if they're not represented. This is important, and the pledge can give those objections weight that they wouldn't have otherwise.
If they are speakers, they can put themselves forward to help events achieve better diversity. We should point them to the resources that will help them do so.
Even if they are neither, I think we should emphasise that their signatures are what gives the pledge legitimacy, and their support is not just something that's nice to have, it's essential to the success of the pledge.
Those are the main improvements I'd like to see to that paragraph, but I think even the first couple of sentences could be reworded to express more sensitivity. It's true that for some people (like me) it seems like we'll never be part of a homogeneous group and while that's good in principle (because homogeneous groups are bad) the reasons why this is true for people like me suck royally. I feel that if I'm going to be reminded of that, I'd want it to be done in a way that sympathises with my struggle; otherwise I'd have the feeling that the folks behind this pledge don't really get it.
I hope that makes sense. Thanks all (Tim especially) for all the hard work that's gone into this! I can't wait to sign 😄
Just for reference on that last comment, Helen and I had a separate chat about this, and came up with some nice improvements (https://github.com/Softwire/minimum-viable-diversity-pledge/commit/e7c59dfe14cb2362be3f4421c885e92ee8529244 for those interested).
More generally, with some last tweaks the Softwire board is happy and signed off on this, and we're prepping for launch. I'm aiming to launch this midday Thursday - if anybody wants to come in with any more feedback or thoughts on this, please do it well before then please!
Thanks everybody - loads of useful stuff here :-)
I only just saw this!
I love the sentiment behind this and the effort put into it but there are some incidental details that would make me think a bit before I would feel comfortable linking anyone to this page. It looks like this is exactly not the time you wanted feedback though, and I suspect I'm alone here, so I'm happy to just sit it out :)
Thanks Stephen! I doubt you're alone - please do give us your feedback :)
(We could incorporate them even more quickly if you submitted a pull request which is what Hereward did https://github.com/Softwire/minimum-viable-diversity-pledge/pull/22 :))
|
2025-04-01T06:37:33.827331
| 2015-12-03T01:00:04
|
120071101
|
{
"authors": [
"jxstanford",
"lexjacobs"
],
"license": "apache-2.0",
"license_source": "bigquery",
"license_type": "permissive",
"provenance": "gharchive-dolma-0000.json.gz:2704",
"repo": "Solinea/goldstone-server",
"url": "https://github.com/Solinea/goldstone-server/pull/157"
}
|
gharchive/pull-request
|
updated link to RDO image, closes issue 119
Moved the developer RDO image to rackspace.
New link worked and .ova file started downloading.
I did not let the download complete due to size and download times, but can do so if desired.
:+1:
|
2025-04-01T06:37:33.864061
| 2017-01-09T05:16:03
|
199479179
|
{
"authors": [
"SonarSonic",
"thetechnodragon",
"zlainsama"
],
"license": "MIT",
"license_source": "github-api",
"license_type": "permissive",
"provenance": "gharchive-dolma-0000.json.gz:2706",
"repo": "SonarSonic/Flux-Networks",
"url": "https://github.com/SonarSonic/Flux-Networks/issues/31"
}
|
gharchive/issue
|
Crash when placed next to extreme reactors
http://pastebin.com/qepVcxcJ
the crash is re-create able with the latest extreme reactors and flux networks
minecraft version 1.10.2
extreme reactors version 1.10.2-<IP_ADDRESS>
flux networks version 1.10.2-1.0.9
how to re-create:
build functional extreme reactor (does not need fuel)
place either send or recieve node next to reactor on a non output block (if you put it on the output it connects just fine, no crashes, and interacts with the network fine)
game crashes with no such method error
I have this happened to me when I was updating my server.
The issue was SonarCore get updated but Flux Networks don't.
I fixed it by rollback the SonarCore to version 3.1.9.
thanks for letting me know, i did notice the crash also happened next to EIO capacitors with that version and yeah, i'll check in the morning if the rollback did the trick for me.
Will be fixed in next update.
|
2025-04-01T06:37:33.868184
| 2021-06-06T17:07:21
|
912891839
|
{
"authors": [
"BlackXSkunk394",
"KayerMC",
"MikeyM3thodic4l",
"Thegriefmaker99",
"rents44"
],
"license": "MIT",
"license_source": "github-api",
"license_type": "permissive",
"provenance": "gharchive-dolma-0000.json.gz:2707",
"repo": "SonarSonic/Flux-Networks",
"url": "https://github.com/SonarSonic/Flux-Networks/issues/440"
}
|
gharchive/issue
|
How to enable chunk loading
How do i enable chunk loading on flux point ?
I hate that I have spent the last 2 hours of my life looking for answers to that very question. Im playing atm7tts in singleplayer and i even found the config folder and changed the enable chunk loading to true and it still wont allow me to chunk load.... its been almost 3 years since this was opened and im the first person commenting really??? this is like low key insane why cant anyone give a simple solution or answer like maybe the mod dev hasnt implemented the support for that feature in 1.18.2 yet but hey acknowledgement of the issue would be helpful or is there another config somewhere that i cant find that also needs to be updated
I play on ATM7: To The Sky and i cant click on the chunk loading button.
In the serveur config file : enable chunk loading = true.
I dont understand... please help me.
Just dealt with the same issue and found the solution thanks to some helpful folks and figured I'd pass it along here as well after confirming it on my own server:
The config file located at [serverdirectory]/config is copied into the world folder when it is generated, so the one you're editing is likely only going to take effect on a new fresh world.
The correct config file to edit for existing worlds is located at [serverdirectory]/world/serverconfig folder.
You just need to use FTB map (press M), then click at the chunk you want to claim after that shift+click to force load the chunk
|
2025-04-01T06:37:33.932982
| 2015-07-15T13:01:30
|
95185764
|
{
"authors": [
"bgavrilMS",
"duncanpMS"
],
"license": "mit",
"license_source": "bigquery",
"license_type": "permissive",
"provenance": "gharchive-dolma-0000.json.gz:2708",
"repo": "SonarSource/sonar-msbuild-runner",
"url": "https://github.com/SonarSource/sonar-msbuild-runner/pull/65"
}
|
gharchive/pull-request
|
SONARMSBRU-99: remaining file renamings
Changed:
SonarQube.MSBuild.PreProcessor.exe -> MSBuild.SonarQube.Internal.PreProcess.exe
SonarQube.MSBuild.PostProcessor.exe -> MSBuild.SonarQube.Internal.PostProcess.exe
SonarQube.TeamBuild.Integration.dll -> TeamBuild.SonarQube.Integration.dll
SonarQube.MSBuild.Tasks.dll -> SonarQube.Integration.Tasks.dll
Unchanged: SonarQube.Common.dll, SonarQube.Integration.targets, SonarQube.Integration.ImportBefore.targets
Done in a previous commit: SonarQube.MSBuild.Runner.exe -> MSBuild.SonarQube.Runner.exe
I've fixed up the packaging projects and manually deployed and executed the newly-packaged code.
I haven't renamed the embedded zip file.
LGTM
|
2025-04-01T06:37:34.027405
| 2023-11-02T19:02:25
|
1974875027
|
{
"authors": [
"ldeluigi"
],
"license": "MIT",
"license_source": "github-api",
"license_type": "permissive",
"provenance": "gharchive-dolma-0000.json.gz:2712",
"repo": "SpaceCowMedia/commander-spellbook-site",
"url": "https://github.com/SpaceCowMedia/commander-spellbook-site/issues/440"
}
|
gharchive/issue
|
Combo submission: produced features suggestions/autocomplete should filter out utility features
Describe the Problem
The produced features suggested by autocompletion in the combo submission form include utility features, which aren't meant to be seen by end users. It should apply a filter to exclude those.
Solved by hiding them from the API
|
2025-04-01T06:37:34.029946
| 2022-07-15T01:54:51
|
1305477617
|
{
"authors": [
"SpaceSaver",
"theBlaize"
],
"license": "MIT",
"license_source": "github-api",
"license_type": "permissive",
"provenance": "gharchive-dolma-0000.json.gz:2713",
"repo": "SpaceSaver/AndroidProxySigninHack",
"url": "https://github.com/SpaceSaver/AndroidProxySigninHack/issues/1"
}
|
gharchive/issue
|
Help!
So I found you via a gabb hack and was wanderign you you want some publicity or smt. I have a Yt with 330+ subs, And I could do a partner thing with the You and you guys. Also you can you fix it or update idk
Hi! A yt video would be awesome! My Discord is SpaceSaver2000#2992 and the Gabb Development Discord server is: https://discord.gg/SpbVSjv9uW . Also, what's the problem you're having with the script?
|
2025-04-01T06:37:34.079929
| 2017-03-25T01:25:22
|
216939306
|
{
"authors": [
"R4ML-CI",
"iyounus"
],
"license": "apache-2.0",
"license_source": "bigquery",
"license_type": "permissive",
"provenance": "gharchive-dolma-0000.json.gz:2714",
"repo": "SparkTC/r4ml",
"url": "https://github.com/SparkTC/r4ml/pull/10"
}
|
gharchive/pull-request
|
[HYDRAR-141] fixing bad markup warning in .Rd files
These warnings occur when we separate two brackets of the command \item{}{} into two lines.
Developer's Certificate of Origin 1.1
By making a contribution to this project, I certify that:
(a) The contribution was created in whole or in part by me and I
have the right to submit it under the Apache License 2.0; or
(b) The contribution is based upon previous work that, to the best
of my knowledge, is covered under an appropriate open source
license and I have the right under that license to submit that
work with modifications, whether created in whole or in part
by me, under the same open source license (unless I am
permitted to submit under a different license), as indicated
in the file; or
(c) The contribution was provided directly to me by some other
person who certified (a), (b) or (c) and I have not modified
it.
(d) I understand and agree that this project and the contribution
are public and that a record of the contribution (including all
personal information I submit with it, including my sign-off) is
maintained indefinitely and may be redistributed consistent with
this project or the open source license(s) involved.
Build triggered.
Build success.
All unit tests passed.
|
2025-04-01T06:37:34.094051
| 2022-02-04T16:26:36
|
1124386348
|
{
"authors": [
"JimWoolley",
"mjy"
],
"license": "MIT",
"license_source": "github-api",
"license_type": "permissive",
"provenance": "gharchive-dolma-0000.json.gz:2715",
"repo": "SpeciesFileGroup/taxonworks",
"url": "https://github.com/SpeciesFileGroup/taxonworks/issues/2796"
}
|
gharchive/issue
|
[Bug]: cannot add type species for new genus name
Steps to reproduce the bug
1.See genus Kressleinius
2. when I attempt to add the type species, Kressleinius celans, I get the dialog box in screen shot below
3. None of choices are active (correct one is type by original designation and monotypy), in fact, the x at top right to exit doesn't work either
4. Locks up the system, need to quit TW and restart
...
Screenshot
Expected behavior
No response
Additional Screenshots
No response
Environment
[ ] Development (native)
[ ] Development (docker)
[ ] Sandbox
[X] Production
Sandbox Used
No response
Version
Version 0.22.7 release
Browser Used
Chrome
Duplicate, this is fixed and will be made live ASAP.
|
2025-04-01T06:37:34.095873
| 2022-09-30T15:32:24
|
1392616580
|
{
"authors": [
"mjy",
"proceps"
],
"license": "MIT",
"license_source": "github-api",
"license_type": "permissive",
"provenance": "gharchive-dolma-0000.json.gz:2716",
"repo": "SpeciesFileGroup/taxonworks",
"url": "https://github.com/SpeciesFileGroup/taxonworks/issues/3121"
}
|
gharchive/issue
|
Task - matrix row coder - checkbox to show only unscored descriptors
Saad requested some filtering functionality to
display only unscored descriptors,
displays descriptors with a particular tag (we are doing this in interactive key)
Same should be implemented in the Column coder
display only unscored rows
I don't think we want to implement tags filtering- this is already done with dynamic character/views. Create a new matrix, add the dynamic column via the Keyword, and you have the view you need, updated as you need.
|
2025-04-01T06:37:34.100212
| 2023-08-30T17:25:14
|
1874090748
|
{
"authors": [
"elikmiller",
"maffkipp"
],
"license": "Apache-2.0",
"license_source": "github-api",
"license_type": "permissive",
"provenance": "gharchive-dolma-0000.json.gz:2717",
"repo": "SpecterOps/BloodHound",
"url": "https://github.com/SpecterOps/BloodHound/pull/68"
}
|
gharchive/pull-request
|
User auth method update fix
Description
When a user's auth method is updated to "username/password", the form still sends the previously selected samlProviderId in the request body, which prevents the auth method from actually being updated. In order to make the update correctly, we need to set this field to an empty string when "username/password" is chosen.
Motivation and Context
Corrects a bug which prevents administrators from updating a user's auth method from SAML.
How Has This Been Tested?
Manual testing to confirm users can be switched freely between the two auth methods.
Screenshots (if appropriate):
Types of changes
[ ] Chore (a change that does not modify the application functionality)
[x] Bug fix (non-breaking change which fixes an issue)
[ ] New feature (non-breaking change which adds functionality)
[ ] Breaking change (fix or feature that would cause existing functionality to change)
Checklist:
[ ] Documentation updates are needed, and have been made accordingly.
[ ] I have added and/or updated tests to cover my changes.
[x] All new and existing tests passed.
[ ] My changes include a database migration.
The changes seem solid however I would love to see some accompanying tests.
|
2025-04-01T06:37:34.110513
| 2021-03-11T08:04:40
|
828902892
|
{
"authors": [
"Ananyaagupta",
"Inventor77",
"Mukta-Sawant",
"aashishah",
"oneknucklehead",
"rupeshmohanty",
"simranbhalla3",
"srishtij2000"
],
"license": "MIT",
"license_source": "github-api",
"license_type": "permissive",
"provenance": "gharchive-dolma-0000.json.gz:2718",
"repo": "Spectrum-CETB/LesKollab",
"url": "https://github.com/Spectrum-CETB/LesKollab/issues/13"
}
|
gharchive/issue
|
Design and code: Make UI of front-page responsive and attractive.
Describe the issue: I'd like to make the landing page more attractive and responsive to all devices using JS, HTML?CSS.
Expected behavior: Landing page changes to make the website more user-friendly and responsive.
I'd like to work on this issue under GSSOC'21, thank you.
I'd like to get assigned to this issue, can I get assigned on this issue under GSSoC'21?
Describe the issue: I'd like to make the landing page more attractive and responsive to all devices using JS, HTML?CSS.
Expected behavior: Landing page changes to make the website more user-friendly and responsive.
I'd like to work on this issue under GSSOC'21, thank you.
Hey @aashishah, I have assigned this issue to you!
I'd like to get assigned to this issue, can I get assigned on this issue under GSSoC'21?
Hey @oneknucklehead, Someone is already working on this issue, so you can either work on the other issues or you can create your own.
Hi I am a Gssoc'21 participant and would like to work on this issue , I have experience in css and js , please assign me this issue
Hi I am a Gssoc'21 participant and would like to work on this issue , I have experience in css and js , please assign me this issue
Hey @simranbhalla3, This issue has been assigned to someone else. You can either work on other issues or you can create your own issues.
@rupeshmohanty Sir can I work on this Issue its been many days and yet it is not Solved. Please Assign It to me
i would like to work on the issue aswell if its still open.
@aashishah Are you working on this issue or should I assign this one to someone else?
If @aashishah isn't working on this issue, can I get assigned to it?
@rupeshmohanty You can unassign me, sorry for the inconvenience.
If @aashishah isn't working on this issue, can I get assigned to it?
Mentor please let me Work on this Issue, I will do it as soon as possible
@oneknucklehead @Inventor77 @simranbhalla3 @Ananyaagupta I want to hear your ideas on how to solve this issue and how much time do you guys need to implement it.
@oneknucklehead @Inventor77 @simranbhalla3 @Ananyaagupta I want to hear your ideas on how to solve this issue and how much time do you guys need to implement it.
Yes sir
@rupeshmohanty I would like to work on this issue as a GSSOC'21 participant. Please assign it to me.
@Mukta-Sawant Done!
Can I work on this issue?
@srishtij2000 Someone is already working on this issue. You can work on some other issue.
|
2025-04-01T06:37:34.184526
| 2022-12-03T00:01:07
|
1473601360
|
{
"authors": [
"Jhobean",
"drk84"
],
"license": "Apache-2.0",
"license_source": "github-api",
"license_type": "permissive",
"provenance": "gharchive-dolma-0000.json.gz:2719",
"repo": "Sphereserver/Source-X",
"url": "https://github.com/Sphereserver/Source-X/issues/970"
}
|
gharchive/issue
|
TAG.name suffix and prefix Do not have space
We can use override tag for the name
TAG.NAME.PREFIX | Sets some text to display before the character's name.
TAG.NAME.SUFFIX | Sets some text to display after the character's name.
I have tested it and it's weird because there no space between name..
I can easily modify it in core but I'm wandering if I do modif on my shard only or for everyone with a PR
What was the goal of these tag at beginning?
Maybe it was for adding special bracket like ->Ronaldo<-
It's not a bug, it was made on purpose:
12-11-2003, Kell
Added support for the following TAGs on characters:
TAG.NAME.ALT (alternate name, good for incognito effects)
TAG.NAME.PREFIX (alternate prefix, if not set, defaults to Notoriety prefix - lady/lord)
TAG.NAME.SUFFIX (suffix for the name)
Note that a space isn't added for prefix or suffix on purpose, to allow text to be
glued to the name. You can add a space by using quotes, as in: TAG.NAME.SUFFIX="text "
Hoo. Very interesting. thx for the " ". It was the part I was missing.
|
2025-04-01T06:37:34.209540
| 2018-05-05T14:22:20
|
320513189
|
{
"authors": [
"cbnolok"
],
"license": "Apache-2.0",
"license_source": "github-api",
"license_type": "permissive",
"provenance": "gharchive-dolma-0000.json.gz:2720",
"repo": "Sphereserver/Source-experimental",
"url": "https://github.com/Sphereserver/Source-experimental/issues/51"
}
|
gharchive/issue
|
Port new features or bugfixes from Source
In the discussion below we can talk about commits to add to this to-port list.
Paste the whole commit text even if you intend to port only a part of its code.
When a commit is ported, reference to this issue in the commit message and add a comment to this issue specifying which functionality was ported from which commit.
This message will be edited and the text made strikedthrough.
To be tested more and eventually port.
Revision: a622737b2be9495d264091d7632af4987bfbfcfd
Author: Coruja<EMAIL_ADDRESS>Date: 13/06/2016 22:58:50
Message:
Fixed: Boat/ship parts resetting TYPE after use 'turn' commands.
To be tested more and eventually port.
Revision: acc1eb61d49e9c8d898027f64eafb8ee9076d343
Author: Coruja<EMAIL_ADDRESS>Date: 17/06/2016 09:11:42
Message:
Fixed: Paralyze / Paralyze Field making NPCs flood too many attack actions
Fixed: Console error when for some reason an NPC got created/moved to an invalid region
To be tested more and eventually port.
Revision: ffc3a52226fa3fa65ac40b3bf5476e5aa2e4f571
Author: Coruja<EMAIL_ADDRESS>Date: 22/06/2016 18:24:07
Message:
Added: Support for colored multis on target functions (only compatible with HS clients <IP_ADDRESS>+)
Revision: aada1eb2fcb12b5b3564be6aa5a7b23e5d91a9e8
Author: Coruja<EMAIL_ADDRESS>Date: 27/06/2016 23:44:21
Message:
Fixed: Function f_onchar_delete not being called if the player char get deleted in any other way different from client Character Selecion menu
To be tested more and eventually ported.
Revision: a79d64ef2bee889a3a63ac0a7d96f5defc0e0459
Author: Coruja<EMAIL_ADDRESS>Date: 27/06/2016 23:57:49
Message:
Fixed: Multi dynamic regions getting replaced by script static regions on server resync
Revision:<PHONE_NUMBER>896269766206db690f76a3785290b1
Author: Coruja<EMAIL_ADDRESS>Date: 30/06/2016 00:41:34
Message:
Fixed: Attack/Kill command on pets allowing select the pet itself as target, making it attack his owner
Revision: f26b39b9b40fba76660c36d57baa8387d3613272
Author: Coruja<EMAIL_ADDRESS>Date: 22/07/2016 22:52:03
Message:
Fixed: Security issue setting account login as chat name when newest clients try to setup the chat window for the first time and the char name is not available
Fixed: Invisible chars being incorrectly revealed by REVEALF_LOOTINGOTHERS reveal flag when picking items from the ground
Fixed: Return 0/1 on spell triggers not working correctly
Fixed: Function MOVENEAR not working correctly
To be discussed and eventually ported.
Revision: dd7a59b451e9d4d8d99c3bec15b330cf60dded2f
Author: Coruja<EMAIL_ADDRESS>Date: 02/08/2016 07:07:12
Message:
Fixed: Items inside trade window not firing @DropOn_Item trigger when the trade move the item to player bacpkack
Revision: 1fa0504b39e9df1074fb29121da2446926eb56b6
Author: Coruja<EMAIL_ADDRESS>Date: 03/08/2016 08:59:17
Message:
Changed: Max item capacity on containers changed from 255 to 125
This is required to make containers works properly on Enhanced Clients, because containers on these clients have hardcoded capacity of 125 items (OSI already uses this value since many years ago, even before enhanced client)
Revision: 5586c3db3ff6940a6d93c6d8062ccca1e195cbc2
Author: Coruja<EMAIL_ADDRESS>Date: 07/08/2016 06:54:07
Message:
Fixed: ARGN1 on char trigger @SkillPreStart not working correctly
Revision: 48ba5dc6e0e8be27b06208b31d128400eda47dd1
Author: Coruja<EMAIL_ADDRESS>Date: 12/08/2016 08:30:13
Message:
Fixed: Client war mode flag not being removed on death
To be tested more and eventually port.
Revision: 210563f9d22c4374e4faecdf92cd78ccd7114661
Author: Coruja<EMAIL_ADDRESS>Date: 13/08/2016 07:24:17
Message:
Fixed: Multi regions not reloading correctly after server resync
Also added a smart check to only reload it when needed (eg: AREADEF/ROOMDEF get changed on scripts)
To be tested more and eventually port.
Revision: c8223f203bbeb753ff0e1d3388db13e4df0b4d4a
Author: Coruja<EMAIL_ADDRESS>Date: 21/08/2016 05:29:13
Message:
Fixed: Internal check to prevent drop items inside walls preventing the item drop even when the wall is on another floor
Fixed: Message "Too many items here!" not showing correctly when items are dropped on areas with too many items
Revision: 30364c13a309452fe5fa2d28f264766c67b34e5d
Author: Coruja<EMAIL_ADDRESS>Date: 27/09/2016 02:07:55
Message:
Fixed: HTTP server not working correctly
Revision: 8fd75922705cbf38eda5130a65bbc91c020e418e
Author: ares<EMAIL_ADDRESS>Date: 06/10/2016 22:31:42
Message:
As we have experienced at Alathair, exporting chars is nearly always meant to export other chars but not the own char, a flag here would be neccessary to control that. The default case should be not to export SRC itself. but it could be optionally turned on using the bitflag 0100. So if you want to export chars including yourself use flag 6. If it should include items use flag 7. Otherwise 1 2 and 3 will not include SRC.
...Continues...
To be tested more and eventually ported.
Revision: d66893bfe79e5e359f1d01465f24bdabbd515a6f
Author: ares<EMAIL_ADDRESS>Date: 08/10/2016 20:10:14
Message:
Fixed a critical bug in background save mechanism where an unsaved offline player character disappears from worldsave when moved to an already saved sector.
Revision: 003321948c4694b5575c6072dec2d72db4a2e576
Author: Coruja<EMAIL_ADDRESS>Date: 17/10/2016 21:23:34
Message:
Fixed: NPCs losing 'statf_spawned' flag after server restart
To be tested more and eventually ported.
Revision: 72ff09966548b27829fcf2ed7608207ae6862d26
Author: Coruja<EMAIL_ADDRESS>Date: 12/11/2016 20:41:49
Message:
Fixed: Resurrect, Reveal, Meteor Swarm and Lightning spells showing effect animation even when EFFECT_ID=0 is set
[sphereCrypt.ini]: Added crypt key for classic clients 7.0.54 ~ 7.0.55 and enhanced clients 4.0.54 ~ 4.0.55
Revision: b054cd3277f26789ee2fbdd1cb7f96aa21d38127
Author: Coruja<EMAIL_ADDRESS>Date: 22/12/2016 19:09:09
Message:
Added: Missing buff icon for Criminal flag
I found this on ServUO repo, thanks for the help :P
Revision: bdc53e3cd70755a5add1c4b57819a2fef00d0245
Author: Coruja<EMAIL_ADDRESS>Date: 08/01/2017 19:23:28
Message:
Fixed: Function 'CRIMINAL 0' not updating char notoriety/buff when removing criminal flag
To be tested more and eventually ported.
Revision: 6e0f90f61fdd81d522143e35b6d968137c3d39ab
Author: Coruja<EMAIL_ADDRESS>Date: 25/01/2017 17:44:31
Message:
Fixed: Client encryption not being decrypted correctly on login process
Also reverted changes on packet 0BF 018 accidentally sent some commits ago
Revision: f1b5cffa0081d12aecf6600447ccae32cb752925
Author: Coruja<EMAIL_ADDRESS>Date: 21/12/2016 06:52:38
Message:
Fixed: Mass Curse spell not working correctly
Revision: 28b644628e76d3b837ecc960f5fb40d9bc920a40
Author: Coruja<EMAIL_ADDRESS>Date: 07/02/2017 21:59:56
Message:
Fixed: Char flag 'statf_hovering' (gargoyle fly ability) not clearing when gargoyle chars polymorph into non-gargoyle char ID
Probably more to add in the next days (i'm not done checking Source's changelog).
Closing, we are splitting ports into separate issues.
|
2025-04-01T06:37:34.236566
| 2020-04-13T20:32:01
|
599118653
|
{
"authors": [
"KanG00",
"dkattan",
"iTommix",
"jabeard3",
"jamoir",
"kiwidyne",
"mackworth"
],
"license": "isc",
"license_source": "bigquery",
"license_type": "permissive",
"provenance": "gharchive-dolma-0000.json.gz:2721",
"repo": "SphtKr/homebridge-zway",
"url": "https://github.com/SphtKr/homebridge-zway/issues/138"
}
|
gharchive/issue
|
Devices 'Not Supported'
Hi,
Please tell me this project isn't dead. I use this every day and really love the work!
I've just had to rebuild the computer that runs zwave.me, home bridge and zway. I installed the latest version (3) and I'm getting some issues.
I added one device to test, a simple socket switch. Added fine on zway. Then installed the plugin on homebridge. Also when well. But on "home" the device is showing up 'Not supported' I think its not detected it currently. But it use to work fine before the rebuild.
Any help would be amazing.
Thanks,
Jamie
So, I had this exact problem, and was able to track it down. I don't know why it worked before for me as well.
For some reason, Zway appends the probe value to the deviceType; so switchBinary becomes switchBinary.switch, and so it doesn't find switchBinary in its big switch (no pun intended) statement that creates the details for the services. I noted it does the exact same thing for switchMultiLevel, but that works because it then maps switchMultilevel.multilevel back to switchMultiLevel, so I just added the switchBinary case to the same map, and it works fine.
I barely understand what I'm doing here, don't know if this is a correct fix for anyone else, and don't know how to deal with npm etc, so I'll leave it to someone else to decide if this is the right answer and submit a pull request (assuming anyone would respond to a PR).
specifically, add a line 89: "switchBinary.switch": "switchBinary",
Here's a patch file with the same idea:
switchBinary.patch.txt
And here's my patched index.js, which on my Raspberry system goes in /usr/local/lib/node_modules/homebridge-zway
Homebridge-zway-index.js.zip
Again, your mileage may vary...
So, I had this exact problem, and was able to track it down. I don't know why it worked before for me as well.
For some reason, Zway appends the probe value to the deviceType; so switchBinary becomes switchBinary.switch, and so it doesn't find switchBinary in its big switch (no pun intended) statement that creates the details for the services. I noted it does the exact same thing for switchMultiLevel, but that works because it then maps switchMultilevel.multilevel back to switchMultiLevel, so I just added the switchBinary case to the same map, and it works fine.
I barely understand what I'm doing here, don't know if this is a correct fix for anyone else, and don't know how to deal with npm etc, so I'll leave it to someone else to decide if this is the right answer and submit a pull request (assuming anyone would respond to a PR).
specifically, add a line 89: "switchBinary.switch": "switchBinary",
Here's a patch file with the same idea:
switchBinary.patch.txt
And here's my patched index.js, which on my Raspberry system goes in /usr/local/lib/node_modules/homebridge-zway
Homebridge-zway-index.js.zip
Again, your mileage may vary...
Great advice !!!
Thank you!
So, I had this exact problem, and was able to track it down. I don't know why it worked before for me as well.
For some reason, Zway appends the probe value to the deviceType; so switchBinary becomes switchBinary.switch, and so it doesn't find switchBinary in its big switch (no pun intended) statement that creates the details for the services. I noted it does the exact same thing for switchMultiLevel, but that works because it then maps switchMultilevel.multilevel back to switchMultiLevel, so I just added the switchBinary case to the same map, and it works fine.
I barely understand what I'm doing here, don't know if this is a correct fix for anyone else, and don't know how to deal with npm etc, so I'll leave it to someone else to decide if this is the right answer and submit a pull request (assuming anyone would respond to a PR).
specifically, add a line 89: "switchBinary.switch": "switchBinary",
Here's a patch file with the same idea:
switchBinary.patch.txt
And here's my patched index.js, which on my Raspberry system goes in /usr/local/lib/node_modules/homebridge-zway
Homebridge-zway-index.js.zip
Again, your mileage may vary...
This works for my issue, too. Thanks.
I can't believe it took me a year to find this. So incredibly frustrating.... That said... riddle me this. I have a dozen BinarySwitches. All Jasco, some with the same software/firmware versions others a level up or down... I can discern no pattern as to why some show(ed) in Homekit correctly and others showed as Not supported. Regardless making the change above resoled the issue for my remaining switches.
I just had to replace two Jasco switches that died, and replaced them with brand new Leviton Z-Wave switches. And, of course, after replacing them, the dreaded "Not Supported" started showing up again. I had added the previous fix to index.js (thanks, @KanG00!) but no dice. So I added some logging and figured out that these new Leviton switches were scanning as "switchBinary.power_switch_binary". That's just terrific. So, I added:
"switchBinary.power_switch_binary": "switchBinary",
in the same place as the other "switchBinary.switch" addition, and it started working.
If I had more time, I'd figure out a way to make this not so brittle.
I just had to replace two Jasco switches that died, and replaced them with brand new Leviton Z-Wave switches (both model DZ15S). And, of course, after replacing them, the dreaded "Not Supported" started showing up again. I had added the previous fix to index.js (thanks, @KanG00!) but no dice. So I added some logging and figured out that these new Leviton switches were scanning as "switchBinary.power_switch_binary". That's just terrific. So, I added:
"switchBinary.power_switch_binary": "switchBinary",
in the same place as the other "switchBinary.switch" addition, and it started working.
If I had more time, I'd figure out a way to make this not so brittle.
tl;dr
If you have this problem and don't want to change any code, use homebridge-zway-kevindayton specifically 0.6.0-alpha1 and tag your device with "Homebridge.Override.probeType:switch", this however makes custom tags not work.
If you want to run my code on HOOBS, install homebridge-zway-kevindayton then open your terminal and enter:
cd ~/.hoobs
npm install git+https://github.com/dkattan/homebridge-zway-kevindayton.git
Details
I just had to fix this after upgrading my Z-Way server from some ancient version to v3.2.2, and the fix that @mackworth posted did not work for my Jasco switches did not work, but the switch for the Leviton switches did work for my Jasco switches.
I'm running homebridge-zway-kevindayton 0.6.0-alpha1 which was released specifically to address this issue, but it no longer does due because the Z-Way API changed how it is returning device data.
Here's what I know, the Z-Way v3.2.2 API returns the following JSON for Jasco switches:
{
"creationTime":<PHONE_NUMBER>,
"creatorId": 1,
"customIcons": {},
"deviceType": 'switchBinary',
"firmware": '5.22',
"h": -1928968201,
"hasHistory": false,
"id": 'ZWayVDev_zway_105-0-37',
"location": 0,
"locationName": 'globalRoom',
"manufacturer": 'Jasco Products',
"metrics": {
"icon": 'switch',
"isFailed": false,
"title": 'Living Room Overhead Light',
"level": 'off'
},
"nodeId": 105,
"order": { rooms": 0, elements": 0, dashboard": 0
},
"permanently_hidden": false,
"probeType": 'power_switch_binary',
"product": '',
"tags": [],
"technology": 'Z-Wave',
"visibility": true,
"updateTime":<PHONE_NUMBER>
}
In short, it appears that initially Z-Way did not return probeType for these switches. Then at some point in time it started returning it with the value "switch", which is why @mackworth 's fix worked, and why @kevindayton 's fix worked. (They are both doing the same thing in 2 different ways)
Then at some subsequent point later Z-Way began returning probeType: "power_switch_binary", and that is the state of affairs today in v3.2.2
If you peruse the release history, there is multiple mentions of probeType
https://z-wave.me/z-way/version-history/
Based on the date this issue was opened, I think the breaking changes occurred either in 18.07.2019 v3.0.0 or 03.04.2020 v3.0.5
Anyway, I incorporated changes for GE Gan Controllers as well as a fix for this issue in my branch, which I'll submit a PR for to homebridge-zway-kevindayton since this project appears to be abandoned.
|
2025-04-01T06:37:34.242476
| 2017-01-03T09:25:02
|
198435492
|
{
"authors": [
"SphtKr",
"WolfgangDomroese"
],
"license": "isc",
"license_source": "bigquery",
"license_type": "permissive",
"provenance": "gharchive-dolma-0000.json.gz:2722",
"repo": "SphtKr/homebridge-zway",
"url": "https://github.com/SphtKr/homebridge-zway/issues/84"
}
|
gharchive/issue
|
No suitable clads for Window Sensor
See the DEBUG log file attached. Obviously, there is no suitable class for the sensor:
logfile.txt
Hold on a bit, I'm going to try to push 0.5.0 out the door--and I think you may still be on 0.4.0 and not on the pre-release channel.
?????? the packet I installed is 0.5.0..... ????
Am 05.01.17 um 19:52 schrieb SphtKr:
Hold on a bit, I'm going to try to push 0.5.0 out the door--and I
think you may still be on 0.4.0 and not on the pre-release channel.
—
You are receiving this because you authored the thread.
Reply to this email directly, view it on GitHub
https://github.com/SphtKr/homebridge-zway/issues/84#issuecomment-270725120,
or mute the thread
https://github.com/notifications/unsubscribe-auth/AOtuiBNCmZ6ieT0H1GGbDUhSGq_-OFI5ks5rPTv0gaJpZM4LZcuw.
--
Wolfgang Domröse
Von Eichendorff-Str. 23
37539 Bad Grund (Harz)
Oh...sorry, this is the Fibaro device and you're also on the conversation for #69. (I thought your log output looked like an old version but now I see it's not.)
Check the update over on the other issue...
|
2025-04-01T06:37:34.285021
| 2013-09-12T12:14:52
|
19377590
|
{
"authors": [
"applematt",
"efx",
"mwang911",
"victorhora",
"wellumies",
"zakarth",
"zimmerle"
],
"license": "apache-2.0",
"license_source": "bigquery",
"license_type": "permissive",
"provenance": "gharchive-dolma-0000.json.gz:2723",
"repo": "SpiderLabs/ModSecurity",
"url": "https://github.com/SpiderLabs/ModSecurity/issues/142"
}
|
gharchive/issue
|
file uploads over 8k fail when using ModSecurity 2.7.5 and Nginx 1.4.2
Linux debian 3.2.0-4-amd64 #1 SMP Debian 3.2.46-1+deb7u1 x86_64 GNU/Linux
ModSec 2.7.5 and Nginx 1.4.2
I have an Apache backend and it receives my file uploads and requests if the file is below 8k. Only got the basic modsecurity.conf loaded without any rules. If I set the SecRequestBodyAccess = Off even those pass through. Succesful upload:
[12/Sep/2013:15:10:49 +0300] [/sid#7f35a9f410a0][rid#7f35a9d950a0][/upload_file.php][4] Initialising transaction (txid AcAcAGl3AcAcAcAcAcAcAcAc).
[12/Sep/2013:15:10:49 +0300] [/sid#7f35a9f410a0][rid#7f35a9d950a0][/upload_file.php][4] Transaction context created (dcfg 7f35a9f41980).
[12/Sep/2013:15:10:49 +0300] [/sid#7f35a9f410a0][rid#7f35a9d950a0][/upload_file.php][4] Starting phase REQUEST_HEADERS.
[12/Sep/2013:15:10:49 +0300] [/sid#7f35a9f410a0][rid#7f35a9d950a0][/upload_file.php][4] Second phase starting (dcfg 7f35a9f41980).
[12/Sep/2013:15:10:49 +0300] [/sid#7f35a9f410a0][rid#7f35a9d950a0][/upload_file.php][4] Input filter: Reading request body.
[12/Sep/2013:15:10:49 +0300] [/sid#7f35a9f410a0][rid#7f35a9d950a0][/upload_file.php][4] Multipart: Created temporary file 1 (mode 0600): /var/log/modsecurity_workdir/20130912-151049-AcAcAGl3AcAcAcAcAcAcAcAc-file-vIn5DC
[12/Sep/2013:15:10:49 +0300] [/sid#7f35a9f410a0][rid#7f35a9d950a0][/upload_file.php][5] Adding request argument (BODY): name "submit", value "Submit"
[12/Sep/2013:15:10:49 +0300] [/sid#7f35a9f410a0][rid#7f35a9d950a0][/upload_file.php][4] Request body no files length: 150
[12/Sep/2013:15:10:49 +0300] [/sid#7f35a9f410a0][rid#7f35a9d950a0][/upload_file.php][4] Input filter: Completed receiving request body (length 4719).
[12/Sep/2013:15:10:49 +0300] [/sid#7f35a9f410a0][rid#7f35a9d950a0][/upload_file.php][4] Starting phase REQUEST_BODY.
[12/Sep/2013:15:10:49 +0300] [/sid#7f35a9f410a0][rid#7f35a9d950a0][/upload_file.php][4] Hook insert_filter: Adding input forwarding filter (r 7f35a9d950a0).
[12/Sep/2013:15:10:49 +0300] [/sid#7f35a9f410a0][rid#7f35a9d950a0][/upload_file.php][4] Hook insert_filter: Adding output filter (r 7f35a9d950a0).
[12/Sep/2013:15:10:49 +0300] [/sid#7f35a9f410a0][rid#7f35a9d950a0][/upload_file.php][4] Input filter: Forwarding input: mode=0, block=0, nbytes=-1 (f 7f35a9d962b0, r 7f35a9d950a0).
[12/Sep/2013:15:10:49 +0300] [/sid#7f35a9f410a0][rid#7f35a9d950a0][/upload_file.php][4] Input filter: Forwarded 4719 bytes.
[12/Sep/2013:15:10:49 +0300] [/sid#7f35a9f410a0][rid#7f35a9d950a0][/upload_file.php][4] Input filter: Sent EOS.
[12/Sep/2013:15:10:49 +0300] [/sid#7f35a9f410a0][rid#7f35a9d950a0][/upload_file.php][4] Input filter: Input forwarding complete.
[12/Sep/2013:15:10:49 +0300] [/sid#7f35a9f410a0][rid#7f35a9d950a0][/upload_file.php][4] Starting phase RESPONSE_HEADERS.
[12/Sep/2013:15:10:49 +0300] [/sid#7f35a9f410a0][rid#7f35a9d950a0][/upload_file.php][4] Output filter: Not buffering response body for unconfigured MIME type "text/html".
[12/Sep/2013:15:10:49 +0300] [/sid#7f35a9f410a0][rid#7f35a9d950a0][/upload_file.php][4] Output filter: Completed receiving response body (non-buffering).
[12/Sep/2013:15:10:49 +0300] [/sid#7f35a9f410a0][rid#7f35a9d950a0][/upload_file.php][4] Starting phase RESPONSE_BODY.
[12/Sep/2013:15:10:49 +0300] [/sid#7f35a9f410a0][rid#7f35a9d950a0][/upload_file.php][4] Output filter: Output forwarding complete.
[12/Sep/2013:15:10:49 +0300] [/sid#7f35a9f410a0][rid#7f35a9d950a0][/upload_file.php][4] Initialising logging.
[12/Sep/2013:15:10:49 +0300] [/sid#7f35a9f410a0][rid#7f35a9d950a0][/upload_file.php][4] Starting phase LOGGING.
[12/Sep/2013:15:10:49 +0300] [/sid#7f35a9f410a0][rid#7f35a9d950a0][/upload_file.php][4] Recording persistent data took 0 microseconds.
[12/Sep/2013:15:10:49 +0300] [/sid#7f35a9f410a0][rid#7f35a9d950a0][/upload_file.php][4] Audit log: Ignoring a non-relevant request.
[12/Sep/2013:15:10:49 +0300] [/sid#7f35a9f410a0][rid#7f35a9d950a0][/upload_file.php][4] Multipart: Cleanup started (remove files 1).
[12/Sep/2013:15:10:49 +0300] [/sid#7f35a9f410a0][rid#7f35a9d950a0][/upload_file.php][4] Multipart: Deleted file (part) "/var/log/modsecurity_workdir/20130912-151049-AcAcAGl3AcAcAcAcAcAcAcAc-file-vIn5DC"
failed upload:
[12/Sep/2013:15:12:48 +0300] [/sid#7f35a9f410a0][rid#7f35a9d8d0a0][/upload_file.php][4] Initialising transaction (txid AcAcATAcccAcAcRcvYAIpcAc).
[12/Sep/2013:15:12:48 +0300] [/sid#7f35a9f410a0][rid#7f35a9d8d0a0][/upload_file.php][4] Transaction context created (dcfg 7f35a9f41980).
[12/Sep/2013:15:12:48 +0300] [/sid#7f35a9f410a0][rid#7f35a9d8d0a0][/upload_file.php][4] Starting phase REQUEST_HEADERS.
[12/Sep/2013:15:12:48 +0300] [/sid#7f35a9f410a0][rid#7f35a9d8d0a0][/upload_file.php][4] Second phase starting (dcfg 7f35a9f41980).
[12/Sep/2013:15:12:48 +0300] [/sid#7f35a9f410a0][rid#7f35a9d8d0a0][/upload_file.php][4] Input filter: Reading request body.
[12/Sep/2013:15:12:48 +0300] [/sid#7f35a9f410a0][rid#7f35a9d8d0a0][/upload_file.php][4] Multipart: Created temporary file 1 (mode 0600): /var/log/modsecurity_workdir/20130912-151248-AcAcATAcccAcAcRcvYAIpcAc-file-qmZcxo
[12/Sep/2013:15:12:48 +0300] [/sid#7f35a9f410a0][rid#7f35a9d8d0a0][/upload_file.php][5] Adding request argument (BODY): name "submit", value "Submit"
[12/Sep/2013:15:12:48 +0300] [/sid#7f35a9f410a0][rid#7f35a9d8d0a0][/upload_file.php][4] Request body no files length: 149
[12/Sep/2013:15:12:48 +0300] [/sid#7f35a9f410a0][rid#7f35a9d8d0a0][/upload_file.php][4] Input filter: Completed receiving request body (length 8893).
[12/Sep/2013:15:12:48 +0300] [/sid#7f35a9f410a0][rid#7f35a9d8d0a0][/upload_file.php][4] Starting phase REQUEST_BODY.
[12/Sep/2013:15:12:48 +0300] [/sid#7f35a9f410a0][rid#7f35a9d8d0a0][/upload_file.php][4] Hook insert_filter: Adding input forwarding filter (r 7f35a9d8d0a0).
[12/Sep/2013:15:12:48 +0300] [/sid#7f35a9f410a0][rid#7f35a9d8d0a0][/upload_file.php][4] Hook insert_filter: Adding output filter (r 7f35a9d8d0a0).
[12/Sep/2013:15:12:48 +0300] [/sid#7f35a9f410a0][rid#7f35a9d8d0a0][/upload_file.php][4] Input filter: Forwarding input: mode=0, block=0, nbytes=-1 (f 7f35a9d8e2b0, r 7f35a9d8d0a0).
[12/Sep/2013:15:12:48 +0300] [/sid#7f35a9f410a0][rid#7f35a9d8d0a0][/upload_file.php][4] Input filter: Forwarded 8192 bytes.
[12/Sep/2013:15:13:48 +0300] [/sid#7f35a9f410a0][rid#7f35a9d8d0a0][/upload_file.php][4] Initialising logging.
[12/Sep/2013:15:13:48 +0300] [/sid#7f35a9f410a0][rid#7f35a9d8d0a0][/upload_file.php][4] Starting phase LOGGING.
[12/Sep/2013:15:13:48 +0300] [/sid#7f35a9f410a0][rid#7f35a9d8d0a0][/upload_file.php][4] Recording persistent data took 0 microseconds.
[12/Sep/2013:15:13:48 +0300] [/sid#7f35a9f410a0][rid#7f35a9d8d0a0][/upload_file.php][4] Audit log: Ignoring a non-relevant request.
[12/Sep/2013:15:13:48 +0300] [/sid#7f35a9f410a0][rid#7f35a9d8d0a0][/upload_file.php][4] Multipart: Cleanup started (remove files 1).
[12/Sep/2013:15:13:48 +0300] [/sid#7f35a9f410a0][rid#7f35a9d8d0a0][/upload_file.php][4] Multipart: Deleted file (part) "/var/log/modsecurity_workdir/20130912-151248-AcAcATAcccAcAcRcvYAIpcAc-file-qmZcxo"
I can tentatively confirm that using nginx_refactoring I was able to fix this particular problem.
I, too, can confirm I'm running into this issue with nginx 1.6.2 where uploads over 8k with SecRequestBodyAccess On.
2015/02/02 11:11:00 [notice] 24627#0: ModSecurity for nginx (STABLE)/2.8.0 (http://www.modsecurity.org/) configured.
2015/02/02 11:11:00 [notice] 24627#0: ModSecurity: APR compiled version="1.3.9"; loaded version="1.3.9"
2015/02/02 11:11:00 [notice] 24627#0: ModSecurity: PCRE compiled version="7.8 "; loaded version="7.8 2008-09-05"
2015/02/02 11:11:00 [notice] 24627#0: ModSecurity: LIBXML compiled version="2.7.6"
I will have to test using the nginx_refactoring branch when I have time. For now, I have SecStatusEngine set to Off as file uploads are necessary.
Hi guys, few minutes ago I've merge #904 into nginx_refactoring branch. It should fix this issue, please confirm that the issue is fixed.
I just built the standalone ModSecurity module from the nginx_refactoring branch and compiled nginx 1.9.1 with it:
nginx version: nginx/1.9.1
built by gcc 4.8.2 20140120 (Red Hat 4.8.2-16) (GCC)
built with OpenSSL 1.0.1k-fips 8 Jan 2015
TLS SNI support enabled
configure arguments: --add-module=../ModSecurity/nginx/modsecurity/ --prefix=/etc/nginx --sbin-path=/usr/sbin/nginx --conf-path=/etc/nginx/nginx.conf --error-log-path=/var/log/nginx/error.log --http-log-path=/var/log/nginx/access.log --pid-path=/var/run/nginx.pid --lock-path=/var/run/nginx.lock --http-client-body-temp-path=/var/cache/nginx/client_temp --http-proxy-temp-path=/var/cache/nginx/proxy_temp --http-fastcgi-temp-path=/var/cache/nginx/fastcgi_temp --http-uwsgi-temp-path=/var/cache/nginx/uwsgi_temp --http-scgi-temp-path=/var/cache/nginx/scgi_temp --user=nginx --group=nginx --with-http_ssl_module --with-http_realip_module --with-http_addition_module --with-http_sub_module --with-http_dav_module --with-http_flv_module --with-http_mp4_module --with-http_gunzip_module --with-http_gzip_static_module --with-http_random_index_module --with-http_secure_link_module --with-http_stub_status_module --with-http_auth_request_module --with-mail --with-mail_ssl_module --with-file-aio --with-ipv6 --with-http_spdy_module --with-cc-opt='-O2 -g -pipe -Wp,-D_FORTIFY_SOURCE=2 -fexceptions -fstack-protector --param=ssp-buffer-size=4 -m64 -mtune=generic'
revelant portion of /etc/nginx/modsecurity.conf (~line 174)
SecDebugLog /var/log/modsecurity-debug.log
SecDebugLogLevel 6
Uploads >= 1MB are failing for me. nginx is forwarding these requests to an upstream server which handles the actual upload, FWIW.
I enabled the debugging log tried 2 uploads. 1 file < 1MB and another file equal to 1MB.
Please note I removed server information and the actual URI's in the following log snippets. Log for successful file upload:
[21/Jul/2015:16:47:34 +0000] Input filter: Forwarded 2063 bytes.
[21/Jul/2015:16:47:34 +0000] Input filter: Sent EOS.
[21/Jul/2015:16:47:34 +0000] Input filter: Input forwarding complete.
[21/Jul/2015:16:47:34 +0000] Starting phase RESPONSE_HEADERS.
[21/Jul/2015:16:47:34 +0000] Output filter: Not buffering response body for unconfigured MIME type "application/json".
[21/Jul/2015:16:47:34 +0000] Output filter: Completed receiving response body (non-buffering).
[21/Jul/2015:16:47:34 +0000] Starting phase RESPONSE_BODY.
[21/Jul/2015:16:47:34 +0000] Output filter: Output forwarding complete.
[21/Jul/2015:16:47:34 +0000] Initialising logging.
Log for failing file upload:
[21/Jul/2015:17:01:02 +0000] Input filter: Forwarded 8192 bytes.
[21/Jul/2015:17:01:12 +0000] Initialising logging.
[21/Jul/2015:17:01:12 +0000] Starting phase LOGGING.
Disabling ModSecurity completely causes both file upload attempts to work.
Let me know if you want additional information and/or help testing.
I think it still exists in modsecurity2.9.1 for nginx, and I use nginx1.8.1 now.
The problem is that the function modsecurity_request_body_retrieve is wrongly used in function input_filter, if modsecurity_request_body_retrieve return 1, it means there are more chunks left, so it should be called again until it doesn't return 1.
It works fine now after I changed that.
how soon can you commit a fix ;)
Hi @mwang911,
Are you sure that you are inspecting a full request body after that modification? not only the first chunk?
I would like to suggest you guys to use the ModSecurity-nginx connector, available at: https://github.com/SpiderLabs/ModSecurity-nginx
Further information on libmodsecurity is available here: https://github.com/SpiderLabs/ModSecurity/tree/v3/master
Hi zimmerle,
I just test the file uploading and it works well now. It could retrieve all request body for nginx not only the max 8k. It is a advice I want you to consider, because I didn't make full other tests. As far as i know, it is related to the retrieving of request body. The result is that nginx still think the request body has not been read.
@wellumies
Hi, the ngx_refactoring has done that in the right way. Look at the function input_filter in https://github.com/SpiderLabs/ModSecurity/blob/nginx_refactoring/apache2/apache2_io.c .
You can compare this function with the .tar.gz file for nginx in https://www.modsecurity.org/download.html.
No longer a concern in libModSecurity. Marking it as won't fix for 2.x.
Further information about libModSecurity available here:
https://github.com/SpiderLabs/ModSecurity/tree/v3/master
|
2025-04-01T06:37:34.359169
| 2019-03-01T16:54:05
|
416191024
|
{
"authors": [
"alexander-yevsyukov"
],
"license": "apache-2.0",
"license_source": "bigquery",
"license_type": "permissive",
"provenance": "gharchive-dolma-0000.json.gz:2724",
"repo": "SpineEventEngine/base",
"url": "https://github.com/SpineEventEngine/base/pull/349"
}
|
gharchive/pull-request
|
Remove enrichment options
This PR finalized simplifying enrichments, removing the enrichment_for and by options in favor of using multiple functions per enrichable message type (introduced in the related PR in core-java).
Notable changes:
Removed options and corresponding classes
enrichment_for and by options and support classes.
EnrichmentMessage is removed. Now any message can serve as an enrichment. It could be entity state, for example, or standard message type.
EnrichmentType and related query methods were removed..
io.spine.type.enrichment package is removed.
Support for setting enrichment message interface is removed.
Other changes
Removed previously deprecated Logging.supplyFor().
MessageClass got method for querying super interfaces extending Message.
Classes implementing MessageContext no longer need to have a name ending with Context.
Elements of TaskName enumeration were renamed to their Gradle task counterparts.
Gradle-related testing utilities moved under io.spine.tools.gradle.testing package to avoid split-package problem with the main plugin JAR.
Introduced TaskSubject for testing Gradle tasks.
@armiol, @yuri-sergiichuk, PTAL. Most of the changes are removal.
This PR is the basis for this one from core-java.
|
2025-04-01T06:37:34.360980
| 2022-10-26T10:46:32
|
1423817473
|
{
"authors": [
"alexander-yevsyukov"
],
"license": "Apache-2.0",
"license_source": "github-api",
"license_type": "permissive",
"provenance": "gharchive-dolma-0000.json.gz:2725",
"repo": "SpineEventEngine/config",
"url": "https://github.com/SpineEventEngine/config/issues/418"
}
|
gharchive/issue
|
Get rid off dependency constants in version.gradle.kts in favor of default values passed to Spine object
We need to employ Kotlin feature of default parameter values instead of using constants defined under version.gradle.kts.
The current arrangement for handling those constants is cumbersome. It works, but it requires too much code, and it's prone to errors in usage.
It's time to make it simpler and easier to use.
@armiol, @yevhenii-nadtochii, FYI.
Closing as outdated.
|
2025-04-01T06:37:34.365515
| 2015-10-16T10:50:58
|
111807190
|
{
"authors": [
"Billabonga",
"ZephireNZ"
],
"license": "MIT",
"license_source": "github-api",
"license_type": "permissive",
"provenance": "gharchive-dolma-0000.json.gz:2726",
"repo": "SpongePowered/Sponge",
"url": "https://github.com/SpongePowered/Sponge/issues/372"
}
|
gharchive/issue
|
Server won't start on v 1521/711
The server wouldn't start even after I had removed all plugins/mods
http://pastebin.com/embed_js.php?i=Ns1BR5FN">
This was fixed just recently - try updating to the most recent version of Sponge
Unfortunately, the latest version cannot be downloaded at the moment
https://forums.spongepowered.org/t/latest-sponge-download-links/9588
|
2025-04-01T06:37:34.398902
| 2016-02-27T19:23:36
|
136956788
|
{
"authors": [
"NI92",
"Urthstripe29"
],
"license": "mit",
"license_source": "bigquery",
"license_type": "permissive",
"provenance": "gharchive-dolma-0000.json.gz:2727",
"repo": "SpriteKitAlliance/SKAToolKit",
"url": "https://github.com/SpriteKitAlliance/SKAToolKit/issues/24"
}
|
gharchive/issue
|
Map scaling
When you currently scale the world in or out the camera perspective gets messed up: moves to the left & down. The more you scale the more left & down it goes.
This is because of the way the algorithm is written to make sure nothing outside the map is shown: so when the character comes to a border the camera doesn’t keep following him & shows the nothingness.
Easy fix is to have an alternate option for camera following: no algorithms during camera positioning calculation.
The nothingness outside the map will be visible but scaling won't be a problem anymore.
This way, one won't require new art assets, but simply will be able to scale the world by 2 while making sure texture filtering is set to nearest.
The map wasn't meant to be scaled so I see how this would mess up the auto follow logic. I will see if there is a work around. Also I suspect this will mess up the index for point logic too as the tileWidth/tileHeight will not be accurate after scaling. In the short term if you are targeting iOS 9 or higher I believe they added an SKCameraNode which might be worth looking into. I will close this as it isn't an issue but will look into this as a future feature.
|
2025-04-01T06:37:34.404194
| 2023-08-06T10:49:22
|
1838155219
|
{
"authors": [
"Spyware007",
"soubhik-111"
],
"license": "MIT",
"license_source": "github-api",
"license_type": "permissive",
"provenance": "gharchive-dolma-0000.json.gz:2728",
"repo": "Spyware007/Animating-Buttons",
"url": "https://github.com/Spyware007/Animating-Buttons/issues/1969"
}
|
gharchive/issue
|
[Add] Change the alert.
Details
I want to change the UI of alert
which is showing on failing log in.
Screenshots
Current:
Expected:
Type of Contribution
[ ] Update to an existing Animated Button
[ ] Adding a new Button
[ ] Resolving a bug
[X] Proposal to the Repository
[ ] Changes related to documentation or README.md
[ ] Other Changes
Checklist
[X] I have checked the existing issues
[X] I have read the Contributing Guidelines
[X] I am willing to work on this issue
[X] I am a GSSoC'23 contributor
@soubhik-111 We are using a different library.
So as considering our UI we had decided to use that toast.
Closing this as not required
|
2025-04-01T06:37:34.407316
| 2023-05-24T01:30:47
|
1723030569
|
{
"authors": [
"Spyware007",
"tuhinaww"
],
"license": "MIT",
"license_source": "github-api",
"license_type": "permissive",
"provenance": "gharchive-dolma-0000.json.gz:2729",
"repo": "Spyware007/Animating-Buttons",
"url": "https://github.com/Spyware007/Animating-Buttons/issues/504"
}
|
gharchive/issue
|
[FEATURE]: Readme Files Update
This is a(n):
[ ] Update to an existing Animated Button
[ ] Any Error
[ ] Proposal to the Repository
[x] Documentation / README.md changes
Details:
Hey, @Spyware007
I can help with making the readme file for this project. Please assign it to me.
PS: If you would like an updated template as well please raise an issue for that and assign it to me :)
@tuhinaww Assigned to you!
|
2025-04-01T06:37:34.414457
| 2023-06-15T21:46:02
|
1759590052
|
{
"authors": [
"SrijanShovit",
"geoffreylgv",
"shreya024"
],
"license": "MIT",
"license_source": "github-api",
"license_type": "permissive",
"provenance": "gharchive-dolma-0000.json.gz:2730",
"repo": "SrijanShovit/carbonops-v2",
"url": "https://github.com/SrijanShovit/carbonops-v2/issues/110"
}
|
gharchive/issue
|
Add Translation section for README
Can we add a translation section within the README file ?
This section will provide translated versions of the content in different languages.
It would be a great idea for better accessibility and reach many people as possible.
If yes, kindly assign to me under GSSOC'23
Hello geoffreylgv, thanks for opening a issue, your contribution is valuable to us. The maintainers will review this issue and provide feedback as soon as possible.
Closing as not required
|
2025-04-01T06:37:34.438065
| 2023-04-10T09:24:30
|
1660505796
|
{
"authors": [
"320010ly",
"Mateusmsouza",
"SofiaBianchi123",
"adirz",
"asdfjkluiop",
"esiefker",
"hotelbread",
"lijain",
"order-a-lemonade",
"picard314",
"questor",
"simonnxren",
"wobblytables"
],
"license": "MIT",
"license_source": "github-api",
"license_type": "permissive",
"provenance": "gharchive-dolma-0000.json.gz:2731",
"repo": "Stability-AI/stablediffusion",
"url": "https://github.com/Stability-AI/stablediffusion/issues/236"
}
|
gharchive/issue
|
RuntimeError: expected scalar type BFloat16 but found Float
Below is the log I have encountered at running "python scripts/txt2img.py --prompt "a professional photograph of an astronaut riding a horse" --ckpt <path/to/768model.ckpt/> --config configs/stable-diffusion/v2-inference-v.yaml --H 768 --W 768"
Running DDIM Sampling with 50 timesteps
DDIM Sampler: 0%| | 0/50 [00:00<?, ?it/s]
data: 0%| | 0/1 [00:00<?, ?it/s]
Sampling: 0%| | 0/3 [00:00<?, ?it/s]
Traceback (most recent call last):
File "scripts/txt2img.py", line 388, in
main(opt)
File "scripts/txt2img.py", line 347, in main
samples, _ = sampler.sample(S=opt.steps,
File "/root/miniconda3/envs/ldmsd/lib/python3.8/site-packages/torch/autograd/grad_mode.py", line 27, in decorate_context
return func(*args, **kwargs)
File "/mnt/disk1/swh/git_sd/stablediffusion/ldm/models/diffusion/ddim.py", line 104, in sample
samples, intermediates = self.ddim_sampling(conditioning, size,
File "/root/miniconda3/envs/ldmsd/lib/python3.8/site-packages/torch/autograd/grad_mode.py", line 27, in decorate_context
return func(*args, **kwargs)
File "/mnt/disk1/swh/git_sd/stablediffusion/ldm/models/diffusion/ddim.py", line 164, in ddim_sampling
outs = self.p_sample_ddim(img, cond, ts, index=index, use_original_steps=ddim_use_original_steps,
File "/root/miniconda3/envs/ldmsd/lib/python3.8/site-packages/torch/autograd/grad_mode.py", line 27, in decorate_context
return func(*args, **kwargs)
File "/mnt/disk1/swh/git_sd/stablediffusion/ldm/models/diffusion/ddim.py", line 212, in p_sample_ddim
model_uncond, model_t = self.model.apply_model(x_in, t_in, c_in).chunk(2)
File "/mnt/disk1/swh/git_sd/stablediffusion/ldm/models/diffusion/ddpm.py", line 858, in apply_model
x_recon = self.model(x_noisy, t, **cond)
File "/root/miniconda3/envs/ldmsd/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1130, in _call_impl
return forward_call(*input, **kwargs)
File "/mnt/disk1/swh/git_sd/stablediffusion/ldm/models/diffusion/ddpm.py", line 1335, in forward
out = self.diffusion_model(x, t, context=cc)
File "/root/miniconda3/envs/ldmsd/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1130, in _call_impl
return forward_call(*input, **kwargs)
File "/mnt/disk1/swh/git_sd/stablediffusion/ldm/modules/diffusionmodules/openaimodel.py", line 797, in forward
h = module(h, emb, context)
File "/root/miniconda3/envs/ldmsd/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1130, in _call_impl
return forward_call(*input, **kwargs)
File "/mnt/disk1/swh/git_sd/stablediffusion/ldm/modules/diffusionmodules/openaimodel.py", line 84, in forward
x = layer(x, context)
File "/root/miniconda3/envs/ldmsd/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1130, in _call_impl
return forward_call(*input, **kwargs)
File "/mnt/disk1/swh/git_sd/stablediffusion/ldm/modules/attention.py", line 327, in forward
x = self.norm(x)
File "/root/miniconda3/envs/ldmsd/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1130, in _call_impl
return forward_call(*input, **kwargs)
File "/root/miniconda3/envs/ldmsd/lib/python3.8/site-packages/torch/nn/modules/normalization.py", line 272, in forward
return F.group_norm(
File "/root/miniconda3/envs/ldmsd/lib/python3.8/site-packages/torch/nn/functional.py", line 2516, in group_norm
return torch.group_norm(input, num_groups, weight, bias, eps, torch.backends.cudnn.enabled)
RuntimeError: expected scalar type BFloat16 but found Float
Please, anyone has met the same and had a solution?
have you solved the issue?
have you solved the issue?
Yes I have. It is due to the incompatiblity of pytorch with cuda.
I am facing the same issue myself. Is it incompatible with cuda et al, or a version of it? because I have a hard time imagining running it without using the gpu. how did you fix it?
@picard314 I have run into this issue, but I was able to make adjustments so that the code runs, but it's using my CPU and not my NVIDIA GPU. I'm running CUDA 11.7 as that is what seemed to be the correct version. What CUDA version are you using, what all did you do to resolve this issue?
@wobblytables mine is cuda 11.4
Yes I have. It is due to the incompatiblity of pytorch with cuda
I had the same problem and solved it by setting up the gpu to run
Yes I have. It is due to the incompatiblity of pytorch with cuda
I had the same problem and solved it by setting up the gpu to run
I met with the same problem.Are you mean to use methods like set CUDA_VISIBLE_DEVICES to set up the gpu?Thank you very much
@wobblytables mine is cuda 11.4
If for cuda 11.7, I think installation needs to be
conda install pytorch==1.13.1 torchvision==0.14.1 torchaudio==0.13.1 pytorch-cuda=11.7 -c pytorch -c nvidia
if you don't mind, can I know your GPU name and which version of pytorch you used?
I have geforce3060, and I used cuda 11.4, pytorch 1.12.1 but I met that error
so I changed the cuda version to 11.6 but still have a same problem...
python main.py --base=$cfg -t --gpus -1 --ckpt /mnt/cache/maqiang/pretrain/sd/512-base-ema.ckpt
Adding --device cuda worked for me.
It looks like a change setted CPU to be used by default https://github.com/Stability-AI/stablediffusion/pull/147/files#diff-048b7bba4049f97b2038502af5686b6c5f53a882ff02771fcb0d733d22a0ab6cR180-R186, I think it was messing up data types.
Adding --device cuda worked for me.
It looks like a change setted CPU to be used by default https://github.com/Stability-AI/stablediffusion/pull/147/files#diff-048b7bba4049f97b2038502af5686b6c5f53a882ff02771fcb0d733d22a0ab6cR180-R186, I think it was messing up data types.
nice solution,it's worked for me too
How do you fix this error when you actually want to run it on the CPU? I can't find a way to
you have to use a different config, in the path "configs/stable-diffusion" there is a folder called "intel" which can be used for running on the cpu, for example you can use -fp32 configs.
Is this going to get fixed?
I read the documentation, installed the requirements, and ran the example. It crashed with this error message.
That seems like a pretty critical bug, but it hasn't even been assigned to anyone yet after 9 months.
as a hint, here is some description what might help: use "--precision full" (taken from here: https://huggingface.co/CompVis/stable-diffusion-v1-4/discussions/42) and in addition there are special configs for cpu processing in the "intel" folder of this repo. Currently I'm using the "-fp32" config in combination with the precision flag and it at least generates some images.
I'm not sure what the root-cause really is as I'm no expert in this field, but this https://github.com/Stability-AI/stablediffusion/blob/main/ldm/modules/attention.py#L175 looks suspicious...
i am having the same issue
!pip install torch==2.0.1 transformers datasets peft accelerate trl bitsandbytes optimum
when i try to load the X_IA3 adapters
|
2025-04-01T06:37:34.457547
| 2016-08-08T23:07:22
|
170046595
|
{
"authors": [
"krainevsky"
],
"license": "apache-2.0",
"license_source": "bigquery",
"license_type": "permissive",
"provenance": "gharchive-dolma-0000.json.gz:2732",
"repo": "StackStorm/st2",
"url": "https://github.com/StackStorm/st2/issues/2857"
}
|
gharchive/issue
|
Unable to edit rule
Just installed version 1.5 using this: https://docs.stackstorm.com/install/rhel7.html
Created first Rule from UI. Now I'm unable to Edit it. When I press "Edit" button I get redirect to #/history
Problem is gone in 1.6. I guess some UI tests required for this project :)
|
2025-04-01T06:37:34.470177
| 2018-05-30T19:40:13
|
327871144
|
{
"authors": [
"Kami",
"nmaludy"
],
"license": "apache-2.0",
"license_source": "bigquery",
"license_type": "permissive",
"provenance": "gharchive-dolma-0000.json.gz:2733",
"repo": "StackStorm/st2",
"url": "https://github.com/StackStorm/st2/issues/4153"
}
|
gharchive/issue
|
Regression of #3820 - Jinja is not rendered in action default values
ISSUE TYPE
Bug Report
STACKSTORM VERSION
# st2 --version
st2 2.7.2, on Python 2.7
OS / ENVIRONMENT / INSTALL METHOD
Install method = puppet-st2
OS = Red Hat Enterprise Linux Server release 7.5 (Maipo)
SUMMARY
array and object parameters are not being rendered in action metadata parameter defaults. integer parameters work fine.
STEPS TO REPRODUCE
1) create a new action metadata file
/opt/stackstorm/packs/default/actions/render_test.yaml
---
description: Run a local linux command
enabled: true
runner_type: mistral-v2
entry_point: workflows/render_test.yaml
name: render_test
pack: default
parameters:
cmd:
required: true
type: string
timeout:
type: integer
default: 60
kv_array:
type: array
default: "{{ st2kv.system.kv_array | from_json_string }}"
kv_object:
type: object
default: "{{ st2kv.system.kv_object | from_json_string }}"
2) create a new workflow
/opt/stackstorm/packs/default/actions/workflows/render_test.yaml
version: '2.0'
default.render_test:
description: demo rendering failures
type: direct
input:
- cmd
- timeout
- kv_array
- kv_object
tasks:
task1:
action: core.local
input:
cmd: "{{ _.cmd }}"
3) assign values in the datastore
$ st2 key set kv_array '["a", "b", "c"]'
$ st2 key set kv_object '{"a": "value", "b": "value2", "c": "value3"}'
4) register and run the action
$ st2 action create /opt/stackstorm/packs/default/actions/render_test.yaml
$ st2 run default.render_test cmd="ls"
EXPECTED RESULTS
Action to execute successfully with parameters:
cmd: ls
timeout: 60
kv_array:
- a
- b
- c
kv_object:
a: value
b: value2
c: value3
ACTUAL RESULTS
$ st2 run default.render_test cmd="ls"
ERROR: 400 Client Error: Bad Request
MESSAGE: '{{ st2kv.system.kv_array | from_json_string }}' is not of type 'array' for url: http://<IP_ADDRESS>:9101/executions
Error in /var/log/st2/st2api.log
2018-05-30 15:39:22,101<PHONE_NUMBER>31760 ERROR actionexecutions [-] Unable to execute action. Parameter validation failed.
Traceback (most recent call last):
File "/opt/stackstorm/st2/lib/python2.7/site-packages/st2api/controllers/v1/actionexecutions.py", line 127, in _handle_schedule_execution
pack=action_db.pack)
File "/opt/stackstorm/st2/lib/python2.7/site-packages/st2api/controllers/v1/actionexecutions.py", line 186, in _schedule_execution
liveaction_db, actionexecution_db = action_service.create_request(liveaction_db)
File "/opt/stackstorm/st2/lib/python2.7/site-packages/st2common/services/action.py", line 89, in create_request
allow_default_none=True)
File "/opt/stackstorm/st2/lib/python2.7/site-packages/st2common/util/schema/__init__.py", line 294, in validate
jsonschema.validate(instance=instance, schema=schema, cls=cls, *args, **kwargs)
File "/opt/stackstorm/st2/lib/python2.7/site-packages/jsonschema/validators.py", line 541, in validate
cls(schema, *args, **kwargs).validate(instance)
File "/opt/stackstorm/st2/lib/python2.7/site-packages/jsonschema/validators.py", line 130, in validate
raise error
ValidationError: u'{{ st2kv.system.kv_array | from_json_string }}' is not of type u'array'
Failed validating u'type' in schema['properties'][u'kv_array']:
{u'default': u'{{ st2kv.system.kv_array | from_json_string }}',
u'type': u'array'}
On instance[u'kv_array']:
u'{{ st2kv.system.kv_array | from_json_string }}'
2018-05-30 15:39:22,103<PHONE_NUMBER>31760 ERROR router [-] Failed to call controller function "post" for operation "st2api.controllers.v1.actionexecutions:action_executions_controller.post": '{{ st2kv.system.kv_array | from_json_string }}' is not of type 'array'
Traceback (most recent call last):
File "/opt/stackstorm/st2/lib/python2.7/site-packages/st2common/router.py", line 470, in __call__
resp = func(**kw)
File "/opt/stackstorm/st2/lib/python2.7/site-packages/st2api/controllers/v1/actionexecutions.py", line 572, in post
show_secrets=show_secrets)
File "/opt/stackstorm/st2/lib/python2.7/site-packages/st2api/controllers/v1/actionexecutions.py", line 133, in _handle_schedule_execution
abort(http_client.BAD_REQUEST, re.sub("u'([^']*)'", r"'\1'", e.message))
File "/opt/stackstorm/st2/lib/python2.7/site-packages/st2common/router.py", line 55, in abort
raise exc.status_map[status_code](message)
HTTPBadRequest: '{{ st2kv.system.kv_array | from_json_string }}' is not of type 'array'
Just to confirm - did this behavior ever work in the past? If so, which version?
I believe it worked in the 2.6.x series. Just noticed it was broken in 2.7.2 (might have been broken sooner)
That's interesting since I don't remember us touching any of that code recently. Only somewhat related change was #4052
In any case, it looks like we should start with a test case. Another question also is why we don't have one for functionality we apparently support :)
I just tried to replicate the problem with the code you provided in v2.7.2, v2.7.1, v2.6.0 and v2.5.1. I get the same error message with every version (aka that functionality doesn't appear work / be supported).
Also looking at the PRs, that functionality was supposedly added in https://github.com/StackStorm/st2/pull/3892. Looking at the tests there - we only have tests for int scenario so likely there are more edge cases which are not handled correctly.
@Kami good to know, maybe i obviously never fully tested on my end.
Did a little digging this morning and found where it is failing specifically: https://github.com/StackStorm/st2/blob/master/st2common/st2common/util/param.py#L189
This is throwing the following exception:
Traceback (most recent call last):
File "/opt/stackstorm/st2/lib/python2.7/site-packages/st2api/controllers/v1/actionexecutions.py", line 127, in _handle_schedule_execution
pack=action_db.pack)
File "/opt/stackstorm/st2/lib/python2.7/site-packages/st2api/controllers/v1/actionexecutions.py", line 182, in _schedule_execution
liveaction_db.context)
File "/opt/stackstorm/st2/lib/python2.7/site-packages/st2common/util/param.py", line 306, in render_live_params
context = _resolve_dependencies(G)
File "/opt/stackstorm/st2/lib/python2.7/site-packages/st2common/util/param.py", line 217, in _resolve_dependencies
context[name] = _render(node, context)
File "/opt/stackstorm/st2/lib/python2.7/site-packages/st2common/util/param.py", line 196, in _render
result = ENV.from_string(str(node['template'])).render(render_context)
File "/opt/stackstorm/st2/lib/python2.7/site-packages/jinja2/environment.py", line 1008, in render
return self.environment.handle_exception(exc_info, True)
File "/opt/stackstorm/st2/lib/python2.7/site-packages/jinja2/environment.py", line 780, in handle_exception
reraise(exc_type, exc_value, tb)
File "<template>", line 1, in top-level template code
File "/opt/stackstorm/st2/lib/python2.7/site-packages/st2common/jinja/filters/data.py", line 29, in from_json_string
return json.loads(value)
File "/usr/lib64/python2.7/json/__init__.py", line 338, in loads
return _default_decoder.decode(s)
File "/usr/lib64/python2.7/json/decoder.py", line 366, in decode
obj, end = self.raw_decode(s, idx=_w(s, 0).end())
TypeError: expected string or buffer
I turned on debug mode and here is the log for that node:
2018-05-31 07:20:58,097<PHONE_NUMBER>20592 INFO param [-] Rendering node: {'template': u'{{ st2kv.system.kv_array | from_json_string }}'} with context: {u'timeout': 60, 'st2kv': {'system': <st2common.services.keyvalues.KeyValueLookup object at 0x7f400b752a50>}}
@nmaludy Alright, after some more digging in it turns out it's not an actual issue in the code, but it's related to calling filter on the value which has already been de-serialized (aka filter is being called twice - once internally based on the action parameter definition and again inside the parameter Jinja string which is not needed).
You don't need to call from_json_string filter on the template value. This is done automatically based on the parameter type.
The following works fine for me:
---
description: Run a local linux command
enabled: true
runner_type: mistral-v2
entry_point: workflows/render_test.yaml
name: render_test
pack: default
parameters:
cmd:
required: true
type: string
timeout:
type: integer
default: 60
kv_array:
type: array
default: "{{ st2kv.system.kv_array }}"
kv_object:
type: object
default: "{{ st2kv.system.kv_object }}"
I will close that as not an issue.
Having said that, I do agree that the current exception is very unfriendly. At the very least, exception should include more data which would give user some clue what is going in (I will look into that change).
Awesome! I really swore i tested it...
I'll make a PR for st2docs and try to make another PR to add tests for objects and arrays
|
2025-04-01T06:37:34.490544
| 2019-09-12T17:26:19
|
492934573
|
{
"authors": [
"Kami",
"RaviTezu",
"amanda11",
"armab",
"winem"
],
"license": "apache-2.0",
"license_source": "bigquery",
"license_type": "permissive",
"provenance": "gharchive-dolma-0000.json.gz:2734",
"repo": "StackStorm/st2",
"url": "https://github.com/StackStorm/st2/issues/4789"
}
|
gharchive/issue
|
st2 fails to store a Key-Value in the datastore if there is a "/" in the key name.
SUMMARY
st2 fails to store a Key-Value in the datastore if there is a "/" in the key name. I am sorry if I missed anything in the docs, which says that you cannot store a key with "/" in it and please feel free to close this issue if that is the case. Thank you.
STACKSTORM VERSION
st2 3.1.0, on Python 2.7.5
OS, environment, install method:
CentOS/Docker, custom install.
Steps to reproduce the problem
bash-4.2$ st2 key set "foo / bar" "foo_bar"
ERROR: 404 Client Error: Not Found
MESSAGE: The resource could not be found. for url: http://<IP_ADDRESS>:9101/v1/keys/foo%20/%20bar
Expected Results
st2 should have accepted the key-value pair and stored it.
Actual Results
st2 has failed to store the key-value pair.
Hi @armab I would like to take this up and send a fix.
I believe this issue probably lies in st2client / CLI and not the API itself (likely / character is not correctly URL encoded).
I believe we even have some st2api API level tests for keys with / in the name (and if we don't, we should add some).
Hi @Kami
I tried via the st2 command and also from the actions I have implemented, both self.action_service.set_value and self.action_service.get_value are failing with the same error. So I assume, it should be an API level issue.
It could be, although action service also utilizes st2client code which talks to the API :)
If there is not an existing test already, I would start with an API level test for that functionality.
@Kami @armab I see no tests which stores a key-value pair with a "/" in the key name.
Also, I am not able to run the tests in test_kvps.py file using the following command from the root directory as mentioned in this doc on a Ubuntu machine:
nosetests --nocapture ./st2api/tests/unit/controllers/v1/test_kvps.py
It says ERROR: Failure: ImportError (No module named st2tests.api)
I tried exporting/setting PYTHONPATH to st2 directory but no luck. Could you please help me to get the tests running ? I tried with both Python2 and Python3.
Thanks.
For developing StackStorm platform itself, I would recommend you to use this Vagrant image - https://github.com/StackStorm/st2vagrantdev
In short, you need to run make requirements which will create virtualenv, install all the dependencies and set PYTHONPATH correctly.
@Kami Thanks. This is Great.
I am able to setup the vagrant environment and I can run the tests now. Also, I have added a test which stores a KV and there is a "/" in the key name and it fails. I will dig through the code and see, if we can encode "/" someway.
@armab
@Kami @armab
I modified the serialize method here to quote (from six.moves.urllib_parse import quote) so that the key for example a/b will be converted into a%2Fb. However, the st2 key set "a/b" "some value" is failing with resource could not be found error.
ERROR: 404 Client Error: Not Found
MESSAGE: The resource could not be found. for url: http://<IP_ADDRESS>:9101/v1/keys/a%2Fb
I think, I will have to make some modifications on the API as well to accept this kind of keys?
Thank you.
Hi @Kami @armab Do you think, we should be able to encode and store keys with /? or I will try to implement something which will thrown an error if the key has / in it. Thank you.
Yes, I think it's absolutely reasonable to be able to use the / in Key name.
Quick example: https://www.consul.io/docs/commands/kv/put.html#examples
If you could make it work and support your enhancement with tests as well, - that would be great addition :+1:
Thanks for the reply @armab
As I mention in the previous comment, I can encode the key on the st2client side and I can see the PUT call is also on the encoded key like below:
(virtualenv) vagrant@ubuntu-xenial:~/local/st2$ st2 key set foo/bar foo
# -------- begin<PHONE_NUMBER>26128 request ----------
curl -X PUT -H 'Connection: keep-alive' -H 'Accept-Encoding: gzip, deflate' -H 'Accept: */*' -H 'User-Agent: python-requests/2.23.0' -H 'content-type: application/json' -H 'Content-Length: 70' --data-binary '{"scope": "system", "name": "foo%2Fbar", "value": "foo", "user": null}' http://<IP_ADDRESS>:9101/v1/keys/foo%2Fbar
# -------- begin<PHONE_NUMBER>26128 response ----------
{
"faultstring": "The resource could not be found."
}
# -------- end<PHONE_NUMBER>26128 response ------------
ERROR: 404 Client Error: Not Found
MESSAGE: The resource could not be found. for url: http://<IP_ADDRESS>:9101/v1/keys/foo%2Fbar
I am trying to find the code which is accepting this request and make it work for encoded / or am I missing something?
Any help in making me understand the api side of things would be appreciated. Thank you.
@Kami
@Kami @armab Where can I find the API side related code? As you can see in my previous comment, API isn't consider a key with encoded / as a new key in the PUT call.
Could you please direct me to some documentation or any other reference/example? Thank you.
Start with the st2 api KeyValue controller in: https://github.com/StackStorm/st2/blob/master/st2api/st2api/controllers/v1/keyvalue.py
For development environment, standards and expectations, check the https://docs.stackstorm.com/development/index.html
@armab @Kami It looks like if I encode a key foo/bar to foo%2Fbar on the client side, the call which will be made will look like this:
curl -X PUT -H 'Connection: keep-alive' -H 'Accept-Encoding: gzip, deflate' -H 'Accept: */*' -H 'User-Agent: python-requests/2.23.0' -H 'content-type: application/json' -H 'Content-Length: 69' --data-binary '{"scope": "system", "name": "foo%2Fbar", "value": "f1", "user": null}' http://<IP_ADDRESS>:9101/v1/keys/foo%2Fbar
But on the api side, it is failing while trying to match the requests path to a controller here.
For some reason, the req.path is going back to foo/bar instead of being the encodedfoo%2Fbar. As you can see, this happening before entering the code in https://github.com/StackStorm/st2/blob/master/st2api/st2api/controllers/v1/keyvalue.py
So I am guessing somewhere else, we need to make change to persist the encoded key.
I did this little test based on the code in router.py:
import webob.compat
path="http://<IP_ADDRESS>:9101/v1/keys/foo%2Fbar"
webob.compat.url_unquote(path)
'http://<IP_ADDRESS>:9101/v1/keys/foo/bar'
So it looks like it gets altered to foo/bar by the url_unquote call.
Thank you for the input @amanda11.
I just tried with double encoding/quoting the key name if it contains a / while I set or get the KV pair and it is working as expected. If this OK, I will go ahead and submit a pull request.
@Kami @armab
git diff:
diff --git a/st2client/st2client/commands/keyvalue.py b/st2client/st2client/commands/keyvalue.py
index 8eed47364..d1a2305eb 100644
--- a/st2client/st2client/commands/keyvalue.py
+++ b/st2client/st2client/commands/keyvalue.py
@@ -21,6 +21,7 @@ import logging
from os.path import join as pjoin
import six
+from six.moves.urllib_parse import quote
from st2client.commands import resource
from st2client.commands.noop import NoopCommand
@@ -141,6 +142,8 @@ class KeyValuePairGetCommand(resource.ResourceGetCommand):
@resource.add_auth_token_to_kwargs_from_cli
def run(self, args, **kwargs):
resource_name = getattr(args, self.pk_argument_name, None)
+ if '/' in resource_name:
+ resource_name = quote(quote(resource_name, safe=''))
decrypt = getattr(args, 'decrypt', False)
scope = getattr(args, 'scope', DEFAULT_GET_SCOPE)
kwargs['params'] = {'decrypt': str(decrypt).lower()}
@@ -185,8 +188,14 @@ class KeyValuePairSetCommand(resource.ResourceCommand):
@resource.add_auth_token_to_kwargs_from_cli
def run(self, args, **kwargs):
instance = KeyValuePair()
- instance.id = args.name # TODO: refactor and get rid of id
- instance.name = args.name
+ key_name = args.name
+ # urllib_parse.quote the key name to support keys with '/' in them.
+ # We double quote it here, as it will unquoted once on the API side.
+ if '/' in key_name:
+ key_name = quote(quote(args.name, safe=''))
+
+ instance.id = key_name # TODO: refactor and get rid of id
+ instance.name = key_name
instance.value = args.value
instance.scope = args.scope
instance.user = args.user
A PR to fix this issue which is still around is very welcome, @RaviTezu :)
|
2025-04-01T06:37:34.492484
| 2015-07-02T20:02:41
|
92723282
|
{
"authors": [
"DoriftoShoes",
"jfryman"
],
"license": "apache-2.0",
"license_source": "bigquery",
"license_type": "permissive",
"provenance": "gharchive-dolma-0000.json.gz:2735",
"repo": "StackStorm/st2incubator",
"url": "https://github.com/StackStorm/st2incubator/pull/232"
}
|
gharchive/pull-request
|
st2cd KVStore Compatibility >=0.9
This PR attempts to load up the old and new libraries to access the K/V store, allowing compatibility with older running nodes (<0.8 ) and newer nodes (>=0.9)
/cc @DoriftoShoes
Tested and working on st2ops001
+1
|
2025-04-01T06:37:34.517324
| 2018-06-22T14:29:50
|
334899618
|
{
"authors": [
"gcampax"
],
"license": "Apache-2.0",
"license_source": "github-api",
"license_type": "permissive",
"provenance": "gharchive-dolma-0000.json.gz:2736",
"repo": "Stanford-Mobisocial-IoT-Lab/almond-cloud",
"url": "https://github.com/Stanford-Mobisocial-IoT-Lab/almond-cloud/pull/30"
}
|
gharchive/pull-request
|
Update dependencies
And pin ThingTalk to the 1.1.0 branch, because the next version
is likely to include dangerous stuff that should go into Cloud Almond
1.1 at least.
Yeah no, dep updates should be handled differently (Greenkeeper maybe?)
|
2025-04-01T06:37:34.546718
| 2017-03-25T02:48:47
|
216943924
|
{
"authors": [
"lightsighter",
"magnatelee",
"streichler"
],
"license": "apache-2.0",
"license_source": "bigquery",
"license_type": "permissive",
"provenance": "gharchive-dolma-0000.json.gz:2737",
"repo": "StanfordLegion/legion",
"url": "https://github.com/StanfordLegion/legion/issues/234"
}
|
gharchive/issue
|
Pennant Exercising a DMA Bug
Pennant (without control replication) is exercising a bug in the new DMA system in the master branch. Below is a command line that runs correctly in the 'olddma' branch, but results in bad data (a pointer in this case) being read from a field in the 'master' branch. Notice that command line uses '-lg:inorder' to ensure that the runtime is doing things in strict program order. Also notice the '-fbounds-checks' means this code takes a while to run so be patient.
Build regent with: ./install.py --debug --gasnet
LAUNCHER='mpirun -H n0002,n0003 -np 4 --map-by numa:pe=6 -x LD_LIBRARY_PATH -x INCLUDE_PATH -x TERRA_PATH --oversubscribe' ./regent.py examples/pennant_fast.rg examples/pennant.tests/leblanc/leblanc.pnt -ll:cpu 5 -npieces 20 -numpcx 1 -numpcy 20 -par_init 1 -seq_init 0 -fbounds-checks 1 -lg:inorder
When the code fails in the 'master' branch you will see the following error:
Errors reported during runtime.
examples/pennant_fast.rg:122: pointer ptr(zone(), $rz) is out-of-bounds
@magnatelee first reported this bug so ask him to test it when there is a fix.
By commenting out the application assertions I was able to validate the runtime execution with Legion Spy, so I'm now confident that the issue is in the DMA system.
I've also noticed other weird failure modes where it is not just the pointer data that is invalid, suggesting that copies of any field are subject to having their data corrupted.
I'm about to assign the bug back to Sean and Zhihao, but before I do here is a summary of what we learned and why we now know the bug is in the DMA system (both new AND old have the same bug). We've simplified the test case to a single node and it can be reproduced with the following command line:
./regent.py examples/pennant_fast.rg examples/pennant.tests/leblanc/leblanc.pnt -ll:cpu 2 -npieces 2 -numpcx 1 -numpcy 2 -par_init 1 -seq_init 0 -lg:inorder -fbounds-checks 1
We know this is the commit that causes the problem: 390235e It changes the sizes of the physical instances being used.
The same behavior can be observed with both the master branch and the olddma branch, so it is nothing related to the new DMA system specifically.
The application is passing with -fbounds-checks 1 so there is no corruption of the data by the application itself.
Legion Spy validates this execution as being correct by the Legion runtime and @TWarszawski and I have hand-checked about 75% of the graph ourselves.
The first task to fail is the calc_volumes_full task during the start-up and it fails the 'sv > 0.0' assertion.
The first cell to fail is cell at location 1768 in the first (and only span).
The reason it fails is that (deterministically) different data is being read from the fields 'zv.x' and 'zv.y' during the computation of the 'sa' temporary. Specifically we see the following values for the computation of 'sa' in the 'good' and 'bad' cases:
sa good: 0.0025 = 0.5 * cross(<0.3,4.4> - <0.2,4.4>,<0.25,4.45> - <0.2,4.4>)
sa bad: -0.05375 = 0.5 * cross(<0.3,4.4> - <0.2,4.4>,<0.175,3.325> - <0.2,4.4>)
If we examine the event graph for a bad run we see that the data for this field is placed in a concrete instance and never moved. No copies to or from this instance are issued by the runtime before the failure, which is correct. The proper event dependences ensure that all tasks associated with this field are running in the correct order which is consistent with Legion Spy validation.
I traced the bad value back to 'calc_centers_full' where I determined that the difference comes from the computation of 'zx'. On the third iteration for zone 442 the good and the bad differ while still having the same pointers for p1.
Good:
p1_px= <0.2,4.4> p1=497
p1_px= <0.3,4.4> p1=498
p1_px= <0.3,4.5> p1=3
p1_px= <0.2,4.5> p1=2
znump 4
zx 442 is <0.25,4.45> nside=4
Bad:
p1_px=<0.2,4.4> p1=497
p1_px=<0.3,4.4> p1=498
p1_px=<0,0> p1=3
p1_px=<0.2,4.5> p1=2
znump 4
zx 442 is <0.175,3.325> nside=4
The p1.px field is initialized by 'intiialize_topology' so I went and printed out the values that are computed for the 'px' field for location p1=3 for both the good and bad versions:
good: p1=3 = <0.3,4.5> Shared Bottom
bad: p1=3 = <0.3,4.5> Shared Bottom
Good news! They're the same, that means that something is going wrong between the tasks.
If you look at the attached event graph you will see that there is a copy needed between the instances used by 'initialize_topology' and 'calc_centers_full'. Legion correctly issues this copy (Realm copy 19). Legion Spy indicates that for this particular execution both index spaces 10 and 12 are exactly the same, so their intersection is the same (the copy is an intersection of index spaces 10 and 12) so all of the data should be moved.
Reducing top-level index space shapes...
Done
Space Index Space 10 has 3 points
Points: 3 7 6
Space Index Space 12 has 3 points
Points: 3 7 6
However, clearly, p1=3 is not being moved properly, and that is a DMA system bug.
bad.pdf
Note that Legion is doing the intersection computation using Realm primitives so you might want to check this code too:
https://github.com/StanfordLegion/legion/blob/master/runtime/legion/region_tree.cc#L5177-L5188
I've managed to reproduce the error, and am digging into it now.
I'm still sorting through some stuff, but there is only a single copy that occurs before calc_centers_full reads the bad value, and it appears to be copying an indexspace that is the non-empty intersection of two index spaces into an instance that was created from an empty index space. Realm does not verify that the domain used for a copy is a subset of the domains that exist in source and destination instances (because it is too expensive), but if there were such a check, it'd be complaining loudly here.
Some snippets from the log:
[0 - b0910000] {2}{region}: subregion<PHONE_NUMBER>00000a (of<PHONE_NUMBER>000007) restricted to [0,10]
[0 - b0910000] {2}{meta}: index space created: id=500000000000000a parent=5000000000000007 (num_elmts=1001)
[0 - b0910000] {2}{region}: subregion<PHONE_NUMBER>00000c (of<PHONE_NUMBER>000007) restricted to [0,10]
[0 - b0910000] {2}{meta}: index space created: id=500000000000000c parent=5000000000000007 (num_elmts=1001)
[0 - b0910000] {2}{region}: subregion<PHONE_NUMBER>00000d (of<PHONE_NUMBER>000007) restricted to [-1,-1]
[0 - b0910000] {2}{meta}: index space created: id=500000000000000d parent=5000000000000007 (num_elmts=1001)
[0 - b0d16000] {2}{inst}: local instance<PHONE_NUMBER>000007 created in memory 1e00000000000000 at offset 536775424+72 (redop=0 list_size=-1 parent_inst=0 block_size=4)
[0 - b0d16000] {2}{meta}: instance created: region=500000000000000d memory=1e00000000000000 id=6000000000000007 bytes=72
[0 - b050a000] {3}{index_spaces}: creating intersection:<PHONE_NUMBER>00000a &<PHONE_NUMBER>00000c
[0 - b050a000] {2}{region}: subregion<PHONE_NUMBER>000026 (of 0) restricted to [0,10]
[0 - b050a000] {2}{meta}: index space created: id=5000000000000026 num_elmts=64
[0 - b050a000] {1}{dma}: copy: 1 distinct src/dst mem pairs, is=5000000000000026
[0 - b050a000] {2}{dma}: dma request 0x7fb3441ecc40 created - is=5000000000000026 before=0 after=8000000002c00008
[0 - b050a000] {2}{dma}: dma request 0x7fb3441ecc40 field:<PHONE_NUMBER>000002[0]->6000000000000007[0] size=8 serdez=0
[0 - b050a000] {2}{dma}: dma request 0x7fb3441ecc40 field:<PHONE_NUMBER>000002[8]->6000000000000007[8] size=8 serdez=0
@streichler Are you sure you got the right point for calc_centers_full (there are two of them) and the right copy? I think the copy we're interested in here should be from<PHONE_NUMBER>000002 to<PHONE_NUMBER>00000b and not<PHONE_NUMBER>000007. If you're running with -lg:inorder all the mapping decisions should be deterministic and therefore the instance creation names too. At least they were for me when I was debugging. Instance<PHONE_NUMBER>00000b should be an instance of index space 10 which is non-empty.
This was the only copy to have completed before the first calc_centers_full executed. (I modified the test to assert on bad data in there, so the other instance of calc_centers_full never executes either.) The only other copy that has even been requested at that point is dependent on the first calc_centers_full instance's completion, and appears to target the same empty instance.
Reassigning this to @lightsighter . There's definitely something wrong in the instance creation. Here's a reformatted excerpt of legion_spy.py -i on my trimmed down test:
Instance 0x6000000000000000 Region (4,1,1)
Instance 0x6000000000000001 Region (8,2,2)
Instance 0x6000000000000002 Region (12,2,2)
Instance 0x6000000000000003 Region (10,2,2)
Instance 0x6000000000000004 Region (14,3,3)
Instance 0x6000000000000005 Region (5,1,1)
Instance 0x6000000000000006 Region (9,2,2)
Instance 0x6000000000000007 rp_all (2,2,2)
Instance 0x6000000000000008 Region (11,2,2)
Instance 0x6000000000000009 Region (15,3,3)
Instance 0x600000000000000a Region (18,4,4)
Instance 0x600000000000000b Region (22,5,5)
Instance 0x600000000000000c Region (26,6,6)
Instance 0x600000000000000d Region (30,7,7)
Instance 0x600000000000000e Region (19,4,4)
Instance 0x600000000000000f Region (23,5,5)
Instance 0x6000000000000010 Region (27,6,6)
Instance 0x6000000000000011 Region (31,7,7)
Instance 0x6000000000000012 Region (4,1,1)
Instance 0x6000000000000013 Region (5,1,1)
Instance 0x6000000000000014 Region (14,3,3)
And here's the Realm logging of instance creations:
[0 - b0284000] {2}{meta}: instance created: region=5000000000000004 memory=1e00000000000000 id=6000000000000000 bytes=452
[0 - b0284000] {2}{meta}: instance created: region=5000000000000008 memory=1e00000000000000 id=6000000000000001 bytes=8928
[0 - b0284000] {2}{meta}: instance created: region=500000000000000c memory=1e00000000000000 id=6000000000000002 bytes=216
[0 - b0284000] {2}{meta}: instance created: region=500000000000000a memory=1e00000000000000 id=6000000000000003 bytes=192
[0 - b0284000] {2}{meta}: instance created: region=500000000000000e memory=1e00000000000000 id=6000000000000004 bytes=75600
[0 - b0d16000] {2}{meta}: instance created: region=5000000000000005 memory=1e00000000000000 id=6000000000000005 bytes=452
[0 - b0d16000] {2}{meta}: instance created: region=5000000000000009 memory=1e00000000000000 id=6000000000000006 bytes=8928
[0 - b0d16000] {2}{meta}: instance created: region=500000000000000d memory=1e00000000000000 id=6000000000000007 bytes=72
[0 - b0d16000] {2}{meta}: instance created: region=500000000000000b memory=1e00000000000000 id=6000000000000008 bytes=192
[0 - b0d16000] {2}{meta}: instance created: region=500000000000000f memory=1e00000000000000 id=6000000000000009 bytes=75600
[0 - b111c000] {2}{meta}: instance created: region=5000000000000011 memory=1e00000000000000 id=600000000000000a bytes=68
[0 - b111c000] {2}{meta}: instance created: region=5000000000000014 memory=1e00000000000000 id=600000000000000b bytes=68
[0 - b111c000] {2}{meta}: instance created: region=5000000000000017 memory=1e00000000000000 id=600000000000000c bytes=68
[0 - b111c000] {2}{meta}: instance created: region=500000000000001a memory=1e00000000000000 id=600000000000000d bytes=68
[0 - b0284000] {2}{meta}: instance created: region=5000000000000012 memory=1e00000000000000 id=600000000000000e bytes=68
[0 - b0284000] {2}{meta}: instance created: region=5000000000000015 memory=1e00000000000000 id=600000000000000f bytes=68
[0 - b0284000] {2}{meta}: instance created: region=5000000000000018 memory=1e00000000000000 id=6000000000000010 bytes=68
[0 - b0284000] {2}{meta}: instance created: region=500000000000001b memory=1e00000000000000 id=6000000000000011 bytes=68
[0 - b0284000] {2}{meta}: instance created: region=5000000000000004 memory=1e00000000000000 id=6000000000000012 bytes=14464
[0 - b131f000] {2}{meta}: instance created: region=5000000000000005 memory=1e00000000000000 id=6000000000000013 bytes=14464
[0 - b0284000] {2}{meta}: instance created: region=500000000000000e memory=1e00000000000000 id=6000000000000014 bytes=28800
It looks like the Legion and Realm index space numbers deviate after a while, but all of the first ones match up EXCEPT for instance<PHONE_NUMBER>000007, which happens to be the target of the copy, and for which that copy would make a lot more sense if the instance had been constructed from rp_all instead of (13,2,2) (which looks like it's rp_shared[1] from the index space tree).
I believe that this bug is now fixed with da5e088. Assigning back to @magnatelee to confirm.
The bug seems fixed. Close this issue.
|
2025-04-01T06:37:34.561840
| 2023-10-11T06:47:01
|
1936978794
|
{
"authors": [
"alberttwong",
"kakao-lunarvel-vet",
"meegoo"
],
"license": "Apache-2.0",
"license_source": "github-api",
"license_type": "permissive",
"provenance": "gharchive-dolma-0000.json.gz:2738",
"repo": "StarRocks/starrocks",
"url": "https://github.com/StarRocks/starrocks/issues/32467"
}
|
gharchive/issue
|
To load parquet file has been fail.
We've tried to load parquet file from s3 api.
(A table with 8,000 columns has roughly 5,000 rows.)
Few hour later, some starrocks BE nodes have killed by self.
But memory and storage space was enough to insert records.
Steps to reproduce the behavior (Required)
CREATE TABLE '...'
column#: 8,000 (2000 integer, 6000 decimal)
CREATE TABLE tbl_pk_dec_c8000_r200000
(
int_col1 INT,
int_col2 INT,
int_col3 INT,
int_col4 INT,
int_col5 INT,
...
dec_col5999 DECIMAL(17,7),
dec_col6000 DECIMAL(17,7)
)
PRIMARY KEY(int_col1)
DISTRIBUTED BY HASH(int_col1) BUCKETS 20
PROPERTIES("replication_num" = "3");
INSERT INTO '....'
It has been turned on.
Is it possible to also try the files() function? https://docs.starrocks.io/en-us/latest/sql-reference/sql-functions/table-functions/files
Sorry. I am too late.
I've tried to your suggestion as below.
But, it didn't work.
-- ___test_file.sql
CREATE TABLE dec_c8000_r200000_001 AS
SELECT * FROM FILES(
"path" = "s3://test/dec_c8000_r200000.001.parquet",
"format" = "parquet",
"aws.s3.access_key" = "******",
"aws.s3.secret_key" = "******",
"aws.s3.region" = "us-west-2"
);
result
mysql> source ___test_file.sql;
ERROR 1064 (HY000): Access storage error. Unknown error
mysql>
You'll have to break the parquet file to be smaller or use the upcoming PIPE feature to load data.
|
2025-04-01T06:37:34.574858
| 2022-12-20T09:46:09
|
1504271324
|
{
"authors": [
"wanpengfei-git",
"zombee0"
],
"license": "Apache-2.0",
"license_source": "github-api",
"license_type": "permissive",
"provenance": "gharchive-dolma-0000.json.gz:2739",
"repo": "StarRocks/starrocks",
"url": "https://github.com/StarRocks/starrocks/pull/15501"
}
|
gharchive/pull-request
|
[Feature]filetable with recursive path
Signed-off-by: zombee0<EMAIL_ADDRESS>What type of PR is this：
[ ] BugFix
[ ] Feature
[ ] Enhancement
[ ] Refactor
[ ] UT
[ ] Doc
[ ] Tool
Which issues of this PR fixes ：
Fixes #
Problem Summary(Required) ：
Checklist:
[ ] I have added test cases for my bug fix or my new feature
[ ] This pr will affect users' behaviors
[ ] This pr needs user documentation (for new or modified features or behaviors)
[ ] I have added documentation for my new feature or new function
Bugfix cherry-pick branch check:
[ ] I have checked the version labels which the pr will be auto backported to target branch
[ ] 2.5
[ ] 2.4
[ ] 2.3
[ ] 2.2
[FE PR Coverage Check]
:disappointed: fail : 0 / 28 (00.00%)
file detail
path
covered_line
new_line
coverage
not_covered_line_detail
:large_blue_circle:
com/starrocks/planner/FileTableScanNode.java
0
1
00.00%
[80]
:large_blue_circle:
com/starrocks/catalog/FileTable.java
0
2
00.00%
[109, 111]
:large_blue_circle:
com/starrocks/connector/hive/HiveRemoteFileIO.java
0
25
00.00%
[104, 105, 106, 108, 111, 112, 114, 118, 119, 121, 123, 124, 125, 126, 128, 130, 131, 132, 133, 134, 135, 136, 137, 138, 140]
|
2025-04-01T06:37:34.604939
| 2022-07-29T02:41:34
|
1321689164
|
{
"authors": [
"g98aq8g09w",
"macjuul"
],
"license": "MIT",
"license_source": "github-api",
"license_type": "permissive",
"provenance": "gharchive-dolma-0000.json.gz:2740",
"repo": "StarlaneStudios/vscode-comment-anchors",
"url": "https://github.com/StarlaneStudios/vscode-comment-anchors/issues/164"
}
|
gharchive/issue
|
How can I set match files to specific file types?
I found that the default setting is /*, but I just want to match .sv and .v files.
I've tried the
**/{.sv,.v}//*
and
/{.sv,.v}//*
as the exclude setting style, not working.
Hello! This should already be possible by changing the commentAnchors.workspace.matchFiles config property to **/*.{sv,v}
Currently this only applies to the workspace anchors panel. The next release will apply the same behavior to opened text files.
|
2025-04-01T06:37:34.607475
| 2022-07-01T09:53:29
|
1291183989
|
{
"authors": [
"StarpTech",
"kdybicz"
],
"license": "MIT",
"license_source": "github-api",
"license_type": "permissive",
"provenance": "gharchive-dolma-0000.json.gz:2741",
"repo": "StarpTech/apollo-datasource-http",
"url": "https://github.com/StarpTech/apollo-datasource-http/pull/45"
}
|
gharchive/pull-request
|
Proposal of tweaks around global and local cache configuration
Making sure global cache configuration is taken into consideration for all datasource methods
Making sure method-specific cache configuration is overriding global configuration, if present
Adding related tests
Adding simple VSC config to enforce basic code styling
Adding VSC launcher to help out with debugging tests and code
@StarpTech I'm happy to talk through the changes I've made and the motivation, I also have following changes queued up, ie. for optional maxTtlIfError and I'm thinking on improving performance and bandwidth used while caching with maxTtlIfError
Hi @kdybicz sorry for the late response. Your change will give request options precedence over global defaults. This is natural and the current behavior was more of a bug.
|
2025-04-01T06:37:34.690369
| 2022-08-19T11:02:08
|
1344287694
|
{
"authors": [
"bart-vmware"
],
"license": "Apache-2.0",
"license_source": "github-api",
"license_type": "permissive",
"provenance": "gharchive-dolma-0000.json.gz:2742",
"repo": "SteeltoeOSS/Steeltoe",
"url": "https://github.com/SteeltoeOSS/Steeltoe/issues/998"
}
|
gharchive/issue
|
Decide on the usage of .ConfigureAwait(false) in Steeltoe code
Today the Steeltoe codebase contains limited usage of .ConfigureAwait(false). I'm wondering if that was a deliberate decision, and if so, what the rationale was for sometimes using it and sometimes omitting it. Should we revisit this, now that we're not targeting .NET Framework and NetStandard anymore?
There's quite some contradicting guidance around the topic.
The blog at https://itnext.io/a-deep-dive-into-configureawait-65f52b9605c2 states that there's no more need for it when targeting only .NET Core:
At this moment, one might think that in .NET Core you won’t need to spread ConfigureAwait(false) all over your code. Almost!
This is almost true, it is still recommended the utilization of ConfigureAwait(false) for libraries as a fallback if those libraries are used within a legacy framework. But for most of the cases yes, in .NET Core you can drop the ConfigureAwait(false) usage.
EF Core recently switched to adding .ConfigureAwait(false) almost everywhere, despite requiring .NET Core.
The ASP.NET Core repo removed .ConfigureAwait(false) from all projects that don't target NetStandard.
Excerpt from the ConfigureAwait FAQ by Stephen Toub:
I’ve heard ConfigureAwait(false) is no longer necessary in .NET Core. True?
False. It’s needed when running on .NET Core for exactly the same reasons it’s needed when running on .NET Framework. Nothing’s changed in that regard.
What has changed, however, is whether certain environments publish their own SynchronizationContext. In particular, whereas the classic ASP.NET on .NET Framework has its own SynchronizationContext, in contrast ASP.NET Core does not. That means that code running in an ASP.NET Core app by default won’t see a custom SynchronizationContext, which lessens the need for ConfigureAwait(false) running in such an environment.
It doesn’t mean, however, that there will never be a custom SynchronizationContext or TaskScheduler present. If some user code (or other library code your app is using) sets a custom context and calls your code, or invokes your code in a Task scheduled to a custom TaskScheduler, then even in ASP.NET Core your awaits may see a non-default context or scheduler that would lead you to want to use ConfigureAwait(false). Of course, in such situations, if you avoid synchronously blocking (which you should avoid doing in web apps regardless) and if you don’t mind the small performance overheads in such limited occurrences, you can probably get away without using ConfigureAwait(false).
@dtillman Can you chime in on this?
|
2025-04-01T06:37:34.704750
| 2018-03-27T15:04:39
|
309009863
|
{
"authors": [
"StefH",
"suchja"
],
"license": "MIT",
"license_source": "github-api",
"license_type": "permissive",
"provenance": "gharchive-dolma-0000.json.gz:2743",
"repo": "StefH/MediaInfo.DotNetWrapper",
"url": "https://github.com/StefH/MediaInfo.DotNetWrapper/issues/9"
}
|
gharchive/issue
|
Using NuGet Package with ClickOnce Deployment
Actually this seems not to be your fault, but it is not possible to use this nuget-package in combination with a clickonce deployment. Although there is no error, the problem is that ClickOnce does not see the dependency to MediaInfo.Native. Thus it does not add it to the installation and on application start all DLLs from MediaInfo.Native are not available and thus my application crashes.
I'm not an expert with NuGet, but do you think there is some other way to make your dependency on MediaInfo.Native more obvious? Or do you know of any way to properly install an application using your NuGet package?
I do need to find some way to install my application using your NuGet package and the required MediaInfo.dll (and its dependencies) in an easy way. - Thank you so much for your effort!
Quick question; did you try to build your app as x64 or 32 ?
Thanks for your immediate feedback. I tried both, but would be happy with x64 in the first try :-(
Am 27.03.2018 um 20:42 schrieb Stef Heyenrath<EMAIL_ADDRESS>Quick question; did you try to build your app as x64 or 32 ?
—
You are receiving this because you authored the thread.
Reply to this email directly, view it on GitHub, or mute the thread.
Just created a quick example to show the problem: https://github.com/suchja/MediaInfoConsole
When preparing to deploy this solution the MediaInfo.Native package and its included DLLs like MediaInfo.dll do not appear in the corresponding wizard (sorry for the German UI).
I tried it once again with x86 and x64 and in addition with Debug and Release. It is the same in all combinations.
While inspecting the project file I found this entry. This seems to me like a first indication why all the other DLLs are not recognised by ClickOnce. You link the project which seems to be build during application build and not the already build DLL like you did it for MediaInfo.DotNetWrapper.dll.
A workaround which could work:
Just add the 5 dll's from the packages folder (C:\Users\azureuser\Documents\Github\MediaInfo.DotNetWrapper\packages\MediaInfo.Native.17.12\build\native\x86) or x64 to your project.
And set Copy if newer to true for all these dll's
When inspecting the clickone files, you see that the dll's are included:
Yeah, did that already as workaround. However, would be good to have a proper solution which builds for x86 and x64.
Another solution would be to add a post-build step and just copy the correct dll's from the packages\MediaInfo.Native.17.12\build\native... folder ?
Or conditionally include the dll's, by manually editing the csproj file?
That probably will do. Thank you! Will update this issue once I have it running, so the solution is documented.
|
2025-04-01T06:37:34.707138
| 2018-05-03T14:14:07
|
319938899
|
{
"authors": [
"StefH",
"eosfor"
],
"license": "Apache-2.0",
"license_source": "github-api",
"license_type": "permissive",
"provenance": "gharchive-dolma-0000.json.gz:2744",
"repo": "StefH/System.Linq.Dynamic.Core",
"url": "https://github.com/StefH/System.Linq.Dynamic.Core/issues/162"
}
|
gharchive/issue
|
Question: Is it possible to call a generic method in a dynamic manner
Hello colleagues, sorry, the question maybe a bit silly, as i'm mot an experienced C# developer.
I got the following piece of code:
var result = list
.Where(x => typesFiltered.Contains(x.Type))
.Where(x => x.GetField<string>(ParameterName) == ParameterValue)
.ToArray();
is it possible to convert it to something like
var result = list
.Where(x => typesFiltered.Contains(x.Type))
.Where("it.GetField<string>(ParameterName) == ParameterValue") // <- use the string here
.ToArray();
If you just want to filter using this library, use code like:
var result = list
.Where(x => typesFiltered.Contains(x.Type))
.Where("it.ParameterName == \"ParameterValue\")
.ToDynamicArray();
Closing...
|
2025-04-01T06:37:34.789858
| 2020-07-23T17:58:26
|
664664500
|
{
"authors": [
"StephenSorriaux",
"justCatchingRye"
],
"license": "Apache-2.0",
"license_source": "github-api",
"license_type": "permissive",
"provenance": "gharchive-dolma-0000.json.gz:2745",
"repo": "StephenSorriaux/ansible-kafka-admin",
"url": "https://github.com/StephenSorriaux/ansible-kafka-admin/pull/62"
}
|
gharchive/pull-request
|
Use DeleteAclRequest_v1 if broker version is over 2.0.0
Fixes https://github.com/StephenSorriaux/ansible-kafka-admin/issues/61
Proposed Changes
Use DeleteAclRequest_v1 if broker version is over 2.0.0
(also forced EOL to LF, that's why the huge diff)
I tested this and I can confirm that it's now working with prefixed acls. Many thanks.
Thanks for your feedback, I will merge this and generate a new release in the next days
|
2025-04-01T06:37:34.791913
| 2019-11-15T06:50:58
|
523289053
|
{
"authors": [
"AlejandroHCruz",
"StephenVinouze",
"fperez-rsc",
"githubashutoshsoni"
],
"license": "apache-2.0",
"license_source": "bigquery",
"license_type": "permissive",
"provenance": "gharchive-dolma-0000.json.gz:2746",
"repo": "StephenVinouze/MaterialNumberPicker",
"url": "https://github.com/StephenVinouze/MaterialNumberPicker/issues/17"
}
|
gharchive/issue
|
crashing when custom font is set
maybe I'm doing this totally wrong. But I have a custom font and I need to set it. I tried passing just the string of the font. which i have in res/font/montessara_light_black as "montessara_light_black" in the setFont. It just crashed.
Can you show how to do that?
Indeed this supports fonts from asset folder. Using fonts from font folder was not possible when this library was created. This should be changed in order to support this
https://github.com/StephenVinouze/MaterialNumberPicker/pull/21
Cool! :D
thanks
|
2025-04-01T06:37:34.793401
| 2016-05-28T11:37:43
|
157334679
|
{
"authors": [
"ZiminGrigory",
"mehanig"
],
"license": "mit",
"license_source": "bigquery",
"license_type": "permissive",
"provenance": "gharchive-dolma-0000.json.gz:2747",
"repo": "StepicOrg/Stepic-API",
"url": "https://github.com/StepicOrg/Stepic-API/pull/14"
}
|
gharchive/pull-request
|
add checking for auth response
Signed-off-by: greg<EMAIL_ADDRESS>
good idea, but pls resolve conflicts
closed, decided not to merge it. Let's keep examples as minimal as possible.
|
2025-04-01T06:37:34.894165
| 2018-07-08T07:02:42
|
339202817
|
{
"authors": [
"Al-Green-COS",
"CHEF-KOCH",
"Laicure",
"StevenBlack",
"dnmTX",
"funilrys",
"lmstearn",
"norage",
"robpomeroy"
],
"license": "mit",
"license_source": "bigquery",
"license_type": "permissive",
"provenance": "gharchive-dolma-0000.json.gz:2753",
"repo": "StevenBlack/hosts",
"url": "https://github.com/StevenBlack/hosts/issues/710"
}
|
gharchive/issue
|
DNS Client High Cpu Usage
Hello!
I've seen people with similar issues with connectivity when using this huge hosts file. I just switched over to winhelp2002 mvps file from this one and for some reason, DNS Client didn't react to it. I no longer have these 10-30s delays when connecting to the net or switching on/off VPN. Could it be due to the file size? Hosts.mvps is (today) 465KB while "StevenBlacks" is 2038KB (depending on which one you choose).
Windows HOSTS file was never designed to be an ad-blocking solution, so this is not only on your end or affects only a few people, that's quite normal. Svchost.exe is rising high cpu because the dns service tries to resolve all domains one by one which is ineffective.
The only thing you can do is install AdGuard or use Unbound or another DNS system which is more efficient when it comes to blacklisting domains.
See also #93
Also #411 #695
If we are talking about file size you can also see #459 (--compress ==> cf.)
You can't disable DNSCache anymore that easy since Windows 10 RS 3 the DNSCache 'stop' function is gone via services.msc and even if you disable it via registry it might get reset after a restart/update or whenever a depending service starts it.
Again the HOSTS file (no matter which OS) and especially not on Windows is not designed to be an ad-blocker, you over the long term have to use AdGuard or hardware based Pi-Hole which is more efficient, especially because it also work with regular expressions, which reduces the hosts file up to 80% since you easily can work with wildcards like .* etc.
To compress the hosts is also not effective at some point, especially not with 100k+ entries. You have to face the fact that HOSTS is a very very bad solution and causes more troubles rather than it helps, if you already distrust Windows own DNS mechanism just use dnscrypt and combine it with unbound, that doesn't cost much system resources and as a benefit you improve your security setup + can easier work with hosts, especially because you can automatically update the hosts file via unbound while you usually also need third-party tools here in order to do that.
There several guides here:
https://etherarp.net/build-an-adblocking-dns-server/
https://news.ycombinator.com/item?id=11084968
https://github.com/lepiaf/adblock-unbound
https://deadc0de.re/articles/unbound-blocking-ads.html
If you like to do this more professional with thousands of entries there is no way around a Pi-Hole (or a similar script). The benefit is obvious, optimized for DNS related ads-blocking, works on all network devices without any applications and you get a nice GUI in order to minor + white-/blacklist something.
Yes, that win10 thing is really pissing me off so I just stopped updating the hosts file at work.
(using win8.1pro at home, hosts file works well)
Off topic:
oh those are cool!
But on my case, as an average power-user.
I only have my laptop, android phones, and my not-so-customizable router-modem at home, I am not able to setup those kinds (you know, no server thingy).
Though I am really interested setting up one ('cause it's damn tedious setting up all the hosts file on each device, rooted and non-rooted), thanks for the links, unbound looks easy to setup ;)
Thank you, everyone, for the excellent community response to this issue.
Some really cool people are watching this repo. I'm thankful for that!
I'd like to echo @CHEF-KOCH when he recommends Pi-Hole. Pi-Hole is a great project and a great reason for everybody to get into Raspberry Pi devices more generally.
Closing!
This issue can be successfully resolved via regedit by removing 'DNSCache' entry from NetworkService REG_MULTI_SZ at:
HKLM\SOFTWARE\Microsoft\Windows NT\CurrentVersion\Svchost
HKLM\SOFTWARE\WOW6432Node\Microsoft\Windows NT\CurrentVersion\Svchost
Prior to this I had to wait ~10 minutes for SVCHOST DNS Client to complete its process when using Steven Black's hosts file. After making this change, I no longer have to wait. Enjoy....
This issue can be successfully resolved via regedit by removing 'DNSCache' entry from NetworkService REG_MULTI_SZ at:
HKLM\SOFTWARE\Microsoft\Windows NT\CurrentVersion\Svchost
HKLM\SOFTWARE\WOW6432Node\Microsoft\Windows NT\CurrentVersion\Svchost
Prior to this I had to wait ~10 minutes for SVCHOST DNS Client to complete its process when using Steven Black's hosts file. After making this change, I no longer have to wait. Enjoy....
If confirmed that one should definitely be in the README Steve @StevenBlack !
If confirmed that one should definitely be in the README Steve @StevenBlack !
Al @Al-Green-COS what version of Windows is this?
Al @Al-Green-COS what version of Windows is this?
@Al-Green-COS isn't it that the same as to disable the DNS Client in Services? Not sure why the extra steps,especially when it comes to messing with registry entries?
Al @Al-Green-COS what version of Windows is this?
Steve @StevenBlack it doesn't matter. I'm with 1607 and i do have the option to do it and i'm pretty sure @Al-Green-COS is on a much higher version then me.
@Al-Green-COS isn't it that the same as to disable the DNS Client in Services? Not sure why the extra steps,especially when it comes to messing with registry entries?
Al @Al-Green-COS what version of Windows is this?
Steve @StevenBlack it doesn't matter. I'm with 1607 and i do have the option to do it and i'm pretty sure @Al-Green-COS is on a much higher version then me.
dnmTX,
In the latest releases of Windows 10 it’s no longer possible to disable DNS Client via Services. I don’t know what release it was that you could no longer do this. I’m presently on Windows 10 Release 20H2 (2009).
<EMAIL_ADDRESS>As you can see, the buttons for Start, Stop, Pause, and Resume are grayed out.
If you’re able to do this, please advise as to the Windows 10 release you are on.
reg query "HKLM\SOFTWARE\Microsoft\Windows NT\CurrentVersion" /v ReleaseID
Respectfully,
Al Green
Sent from Mailhttps://go.microsoft.com/fwlink/?LinkId=550986 for Windows 10
From<EMAIL_ADDRESS>Sent: Wednesday, January 6, 2021 11:27 AM
To<EMAIL_ADDRESS>Cc: Al<EMAIL_ADDRESS><EMAIL_ADDRESS>Subject: Re: [StevenBlack/hosts] DNS Client High Cpu Usage (#710)
@Al-Green-COShttps://na01.safelinks.protection.outlook.com/?url=https%3A%2F%2Fgithub.com%2FAl-Green-COS&data=04|01||f539c8ff3a734dde063008d8b270bc4d|84df9e7fe9f640afb435aaaaaaaaaaaa|1|0|637455544544769030|Unknown|TWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D|1000&sdata=BB4gWleYFQYMuvewACCPvuXj4T5RrwL8Ktvqk0maS48%3D&reserved=0 isn't it that the same as to disable the DNS Client in Services? Not sure why the extra steps,especially when it comes to messing with registry entries?
[Capture]https://na01.safelinks.protection.outlook.com/?url=https%3A%2F%2Fuser-images.githubusercontent.com%2F34774426%2F103805957-ecab8400-5019-11eb-8484-417ad8738ee9.PNG&data=04|01||f539c8ff3a734dde063008d8b270bc4d|84df9e7fe9f640afb435aaaaaaaaaaaa|1|0|637455544544778987|Unknown|TWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D|1000&sdata=Kg32WGMdQUjkai%2FQNXOPcltR%2BNryiP0b9yMGzDXBTHU%3D&reserved=0
Al @Al-Green-COShttps://na01.safelinks.protection.outlook.com/?url=https%3A%2F%2Fgithub.com%2FAl-Green-COS&data=04|01||f539c8ff3a734dde063008d8b270bc4d|84df9e7fe9f640afb435aaaaaaaaaaaa|1|0|637455544544778987|Unknown|TWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D|1000&sdata=CN7tZb8%2BYat2Q66DU16F0sw6wkdVbkwwXtF%2FdJFkI2s%3D&reserved=0 what version of Windows is this?
Steve @StevenBlackhttps://na01.safelinks.protection.outlook.com/?url=https%3A%2F%2Fgithub.com%2FStevenBlack&data=04|01||f539c8ff3a734dde063008d8b270bc4d|84df9e7fe9f640afb435aaaaaaaaaaaa|1|0|637455544544788944|Unknown|TWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D|1000&sdata=%2FwVNGqqafGNLnwGoCxh1Hiy2OXQ2GD%2B6GiHrcqWL6SE%3D&reserved=0 it doesn't matter. I'm with 1607 and i do have the option to do it and i'm pretty sure @Al-Green-COShttps://na01.safelinks.protection.outlook.com/?url=https%3A%2F%2Fgithub.com%2FAl-Green-COS&data=04|01||f539c8ff3a734dde063008d8b270bc4d|84df9e7fe9f640afb435aaaaaaaaaaaa|1|0|637455544544788944|Unknown|TWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D|1000&sdata=xMLiXuNRVkK8H7RODjk7lxWgsyNCvNwdyycnDE9lrYk%3D&reserved=0 is on a much higher version then me.
[Help]https://na01.safelinks.protection.outlook.com/?url=https%3A%2F%2Fuser-images.githubusercontent.com%2F34774426%2F103806334-79564200-501a-11eb-9e01-e20582c7b2d4.png&data=04|01||f539c8ff3a734dde063008d8b270bc4d|84df9e7fe9f640afb435aaaaaaaaaaaa|1|0|637455544544788944|Unknown|TWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D|1000&sdata=vSOI1WlLVbIJx4RyTGqejMYqfB6NhXjlgt8vIRYa8io%3D&reserved=0
—
You are receiving this because you were mentioned.
Reply to this email directly, view it on GitHubhttps://na01.safelinks.protection.outlook.com/?url=https%3A%2F%2Fgithub.com%2FStevenBlack%2Fhosts%2Fissues%2F710%23issuecomment-755479824&data=04|01||f539c8ff3a734dde063008d8b270bc4d|84df9e7fe9f640afb435aaaaaaaaaaaa|1|0|637455544544798900|Unknown|TWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D|1000&sdata=rwvvSK2eCHCmDU2zwPHQ3NkTmEOsGhLyoTMouYNFGhs%3D&reserved=0, or unsubscribehttps://na01.safelinks.protection.outlook.com/?url=https%3A%2F%2Fgithub.com%2Fnotifications%2Funsubscribe-auth%2FASK3GPA45L2LHI4A2ZY2VW3SYSTRLANCNFSM4FI2PKJQ&data=04|01||f539c8ff3a734dde063008d8b270bc4d|84df9e7fe9f640afb435aaaaaaaaaaaa|1|0|637455544544798900|Unknown|TWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D|1000&sdata=kOzeLvvjhs46rlRCcxn37UFXMp%2BjLmQbWDZ0sPIgnEw%3D&reserved=0.
dnmTX,
In the latest releases of Windows 10 it’s no longer possible to disable DNS Client via Services. I don’t know what release it was that you could no longer do this. I’m presently on Windows 10 Release 20H2 (2009).
<EMAIL_ADDRESS>As you can see, the buttons for Start, Stop, Pause, and Resume are grayed out.
If you’re able to do this, please advise as to the Windows 10 release you are on.
reg query "HKLM\SOFTWARE\Microsoft\Windows NT\CurrentVersion" /v ReleaseID
Respectfully,
Al Green
Sent from Mailhttps://go.microsoft.com/fwlink/?LinkId=550986 for Windows 10
From<EMAIL_ADDRESS>Sent: Wednesday, January 6, 2021 11:27 AM
To<EMAIL_ADDRESS>Cc: Al<EMAIL_ADDRESS><EMAIL_ADDRESS>Subject: Re: [StevenBlack/hosts] DNS Client High Cpu Usage (#710)
@Al-Green-COShttps://na01.safelinks.protection.outlook.com/?url=https%3A%2F%2Fgithub.com%2FAl-Green-COS&data=04|01||f539c8ff3a734dde063008d8b270bc4d|84df9e7fe9f640afb435aaaaaaaaaaaa|1|0|637455544544769030|Unknown|TWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D|1000&sdata=BB4gWleYFQYMuvewACCPvuXj4T5RrwL8Ktvqk0maS48%3D&reserved=0 isn't it that the same as to disable the DNS Client in Services? Not sure why the extra steps,especially when it comes to messing with registry entries?
[Capture]https://na01.safelinks.protection.outlook.com/?url=https%3A%2F%2Fuser-images.githubusercontent.com%2F34774426%2F103805957-ecab8400-5019-11eb-8484-417ad8738ee9.PNG&data=04|01||f539c8ff3a734dde063008d8b270bc4d|84df9e7fe9f640afb435aaaaaaaaaaaa|1|0|637455544544778987|Unknown|TWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D|1000&sdata=Kg32WGMdQUjkai%2FQNXOPcltR%2BNryiP0b9yMGzDXBTHU%3D&reserved=0
Al @Al-Green-COShttps://na01.safelinks.protection.outlook.com/?url=https%3A%2F%2Fgithub.com%2FAl-Green-COS&data=04|01||f539c8ff3a734dde063008d8b270bc4d|84df9e7fe9f640afb435aaaaaaaaaaaa|1|0|637455544544778987|Unknown|TWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D|1000&sdata=CN7tZb8%2BYat2Q66DU16F0sw6wkdVbkwwXtF%2FdJFkI2s%3D&reserved=0 what version of Windows is this?
Steve @StevenBlackhttps://na01.safelinks.protection.outlook.com/?url=https%3A%2F%2Fgithub.com%2FStevenBlack&data=04|01||f539c8ff3a734dde063008d8b270bc4d|84df9e7fe9f640afb435aaaaaaaaaaaa|1|0|637455544544788944|Unknown|TWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D|1000&sdata=%2FwVNGqqafGNLnwGoCxh1Hiy2OXQ2GD%2B6GiHrcqWL6SE%3D&reserved=0 it doesn't matter. I'm with 1607 and i do have the option to do it and i'm pretty sure @Al-Green-COShttps://na01.safelinks.protection.outlook.com/?url=https%3A%2F%2Fgithub.com%2FAl-Green-COS&data=04|01||f539c8ff3a734dde063008d8b270bc4d|84df9e7fe9f640afb435aaaaaaaaaaaa|1|0|637455544544788944|Unknown|TWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D|1000&sdata=xMLiXuNRVkK8H7RODjk7lxWgsyNCvNwdyycnDE9lrYk%3D&reserved=0 is on a much higher version then me.
[Help]https://na01.safelinks.protection.outlook.com/?url=https%3A%2F%2Fuser-images.githubusercontent.com%2F34774426%2F103806334-79564200-501a-11eb-9e01-e20582c7b2d4.png&data=04|01||f539c8ff3a734dde063008d8b270bc4d|84df9e7fe9f640afb435aaaaaaaaaaaa|1|0|637455544544788944|Unknown|TWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D|1000&sdata=vSOI1WlLVbIJx4RyTGqejMYqfB6NhXjlgt8vIRYa8io%3D&reserved=0
—
You are receiving this because you were mentioned.
Reply to this email directly, view it on GitHubhttps://na01.safelinks.protection.outlook.com/?url=https%3A%2F%2Fgithub.com%2FStevenBlack%2Fhosts%2Fissues%2F710%23issuecomment-755479824&data=04|01||f539c8ff3a734dde063008d8b270bc4d|84df9e7fe9f640afb435aaaaaaaaaaaa|1|0|637455544544798900|Unknown|TWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D|1000&sdata=rwvvSK2eCHCmDU2zwPHQ3NkTmEOsGhLyoTMouYNFGhs%3D&reserved=0, or unsubscribehttps://na01.safelinks.protection.outlook.com/?url=https%3A%2F%2Fgithub.com%2Fnotifications%2Funsubscribe-auth%2FASK3GPA45L2LHI4A2ZY2VW3SYSTRLANCNFSM4FI2PKJQ&data=04|01||f539c8ff3a734dde063008d8b270bc4d|84df9e7fe9f640afb435aaaaaaaaaaaa|1|0|637455544544798900|Unknown|TWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D|1000&sdata=kOzeLvvjhs46rlRCcxn37UFXMp%2BjLmQbWDZ0sPIgnEw%3D&reserved=0.
@Al-Green-COS i see. I didn't know that but it's less then suprising for me to be honest.
Still,another less coplicated option would be to go to:
HKLM\SYSTEM\CurrentControlSet\Services\Dnscache and change Start from 2 to 4(disabled) and Restart
Can you confirm if this option is still possible on the build that you're on. Thank you 👍
@Al-Green-COS i see. I didn't know that but it's less then suprising for me to be honest.
Still,another less coplicated option would be to go to:
HKLM\SYSTEM\CurrentControlSet\Services\Dnscache and change Start from 2 to 4(disabled) and Restart
Can you confirm if this option is still possible on the build that you're on. Thank you 👍
Mr. Black,
<EMAIL_ADDRESS>Respectfully,
Al Green
Sent from Mailhttps://go.microsoft.com/fwlink/?LinkId=550986 for Windows 10
From: Steven<EMAIL_ADDRESS>Sent: Wednesday, January 6, 2021 10:18 AM
To<EMAIL_ADDRESS>Cc: Al<EMAIL_ADDRESS><EMAIL_ADDRESS>Subject: Re: [StevenBlack/hosts] DNS Client High Cpu Usage (#710)
Al @Al-Green-COShttps://na01.safelinks.protection.outlook.com/?url=https%3A%2F%2Fgithub.com%2FAl-Green-COS&data=04|01||bb707cf3de344805d5c408d8b2670e2d|84df9e7fe9f640afb435aaaaaaaaaaaa|1|0|637455502965937289|Unknown|TWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D|1000&sdata=cSysS6vrhbqt2XTA1QvpTd9E0I%2FLEjwJ4urBopkTl2g%3D&reserved=0 what version of Windows is this?
—
You are receiving this because you were mentioned.
Reply to this email directly, view it on GitHubhttps://na01.safelinks.protection.outlook.com/?url=https%3A%2F%2Fgithub.com%2FStevenBlack%2Fhosts%2Fissues%2F710%23issuecomment-755437863&data=04|01||bb707cf3de344805d5c408d8b2670e2d|84df9e7fe9f640afb435aaaaaaaaaaaa|1|0|637455502965937289|Unknown|TWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D|1000&sdata=PslLT6EHBoyIF3chmuHfmUbDWk%2FgHpL%2F%2Ba7JFY%2B6ep0%3D&reserved=0, or unsubscribehttps://na01.safelinks.protection.outlook.com/?url=https%3A%2F%2Fgithub.com%2Fnotifications%2Funsubscribe-auth%2FASK3GPBIQLUDRYSUSF6J6OTSYSLNPANCNFSM4FI2PKJQ&data=04|01||bb707cf3de344805d5c408d8b2670e2d|84df9e7fe9f640afb435aaaaaaaaaaaa|1|0|637455502965937289|Unknown|TWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D|1000&sdata=ZjZdkZlH%2FBj3AjJmxOXknHkDr704kvEg3fROGRhuSKo%3D&reserved=0.
Mr. Black,
<EMAIL_ADDRESS>Respectfully,
Al Green
Sent from Mailhttps://go.microsoft.com/fwlink/?LinkId=550986 for Windows 10
From: Steven<EMAIL_ADDRESS>Sent: Wednesday, January 6, 2021 10:18 AM
To<EMAIL_ADDRESS>Cc: Al<EMAIL_ADDRESS><EMAIL_ADDRESS>Subject: Re: [StevenBlack/hosts] DNS Client High Cpu Usage (#710)
Al @Al-Green-COShttps://na01.safelinks.protection.outlook.com/?url=https%3A%2F%2Fgithub.com%2FAl-Green-COS&data=04|01||bb707cf3de344805d5c408d8b2670e2d|84df9e7fe9f640afb435aaaaaaaaaaaa|1|0|637455502965937289|Unknown|TWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D|1000&sdata=cSysS6vrhbqt2XTA1QvpTd9E0I%2FLEjwJ4urBopkTl2g%3D&reserved=0 what version of Windows is this?
—
You are receiving this because you were mentioned.
Reply to this email directly, view it on GitHubhttps://na01.safelinks.protection.outlook.com/?url=https%3A%2F%2Fgithub.com%2FStevenBlack%2Fhosts%2Fissues%2F710%23issuecomment-755437863&data=04|01||bb707cf3de344805d5c408d8b2670e2d|84df9e7fe9f640afb435aaaaaaaaaaaa|1|0|637455502965937289|Unknown|TWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D|1000&sdata=PslLT6EHBoyIF3chmuHfmUbDWk%2FgHpL%2F%2Ba7JFY%2B6ep0%3D&reserved=0, or unsubscribehttps://na01.safelinks.protection.outlook.com/?url=https%3A%2F%2Fgithub.com%2Fnotifications%2Funsubscribe-auth%2FASK3GPBIQLUDRYSUSF6J6OTSYSLNPANCNFSM4FI2PKJQ&data=04|01||bb707cf3de344805d5c408d8b2670e2d|84df9e7fe9f640afb435aaaaaaaaaaaa|1|0|637455502965937289|Unknown|TWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D|1000&sdata=ZjZdkZlH%2FBj3AjJmxOXknHkDr704kvEg3fROGRhuSKo%3D&reserved=0.
dnmTX,
Your recommendation works as well.
<EMAIL_ADDRESS><EMAIL_ADDRESS>Respectfully,
Al Green
Sent from Mailhttps://go.microsoft.com/fwlink/?LinkId=550986 for Windows 10
From<EMAIL_ADDRESS>Sent: Wednesday, January 6, 2021 4:09 PM
To<EMAIL_ADDRESS>Cc: Al<EMAIL_ADDRESS><EMAIL_ADDRESS>Subject: Re: [StevenBlack/hosts] DNS Client High Cpu Usage (#710)
@Al-Green-COShttps://na01.safelinks.protection.outlook.com/?url=https%3A%2F%2Fgithub.com%2FAl-Green-COS&data=04|01||ac574ce9206542bc2d1f08d8b2981fbe|84df9e7fe9f640afb435aaaaaaaaaaaa|1|0|637455713720234028|Unknown|TWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D|1000&sdata=xYFceSFlQ38vNSrLzFeuLm3e0Q8GlpCfz6gab8QoinA%3D&reserved=0 i see. I didn't know that but it's less then suprising for me to be honest.
Still,another less coplicated option would be to go to:
HKLM\SYSTEM\CurrentControlSet\Services\Dnscache and change Start from 2 to 4(disabled) and Restart
Can you confirm if this option is still possible on the build that you're on. Thank you 👍
—
You are receiving this because you were mentioned.
Reply to this email directly, view it on GitHubhttps://na01.safelinks.protection.outlook.com/?url=https%3A%2F%2Fgithub.com%2FStevenBlack%2Fhosts%2Fissues%2F710%23issuecomment-755770823&data=04|01||ac574ce9206542bc2d1f08d8b2981fbe|84df9e7fe9f640afb435aaaaaaaaaaaa|1|0|637455713720243991|Unknown|TWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D|1000&sdata=fHhpAPRgmpirQ0jgaEEbuWGFRdoK6O2ruJRbXpBszUQ%3D&reserved=0, or unsubscribehttps://na01.safelinks.protection.outlook.com/?url=https%3A%2F%2Fgithub.com%2Fnotifications%2Funsubscribe-auth%2FASK3GPBB7IYIJPQEROTCK43SYTUSVANCNFSM4FI2PKJQ&data=04|01||ac574ce9206542bc2d1f08d8b2981fbe|84df9e7fe9f640afb435aaaaaaaaaaaa|1|0|637455713720243991|Unknown|TWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D|1000&sdata=%2B5q8uLETPRKiVXiFnpQ2alsHBQCK%2FTSt1tDdury9cj0%3D&reserved=0.
dnmTX,
Your recommendation works as well.
<EMAIL_ADDRESS><EMAIL_ADDRESS>Respectfully,
Al Green
Sent from Mailhttps://go.microsoft.com/fwlink/?LinkId=550986 for Windows 10
From<EMAIL_ADDRESS>Sent: Wednesday, January 6, 2021 4:09 PM
To<EMAIL_ADDRESS>Cc: Al<EMAIL_ADDRESS><EMAIL_ADDRESS>Subject: Re: [StevenBlack/hosts] DNS Client High Cpu Usage (#710)
@Al-Green-COShttps://na01.safelinks.protection.outlook.com/?url=https%3A%2F%2Fgithub.com%2FAl-Green-COS&data=04|01||ac574ce9206542bc2d1f08d8b2981fbe|84df9e7fe9f640afb435aaaaaaaaaaaa|1|0|637455713720234028|Unknown|TWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D|1000&sdata=xYFceSFlQ38vNSrLzFeuLm3e0Q8GlpCfz6gab8QoinA%3D&reserved=0 i see. I didn't know that but it's less then suprising for me to be honest.
Still,another less coplicated option would be to go to:
HKLM\SYSTEM\CurrentControlSet\Services\Dnscache and change Start from 2 to 4(disabled) and Restart
Can you confirm if this option is still possible on the build that you're on. Thank you 👍
—
You are receiving this because you were mentioned.
Reply to this email directly, view it on GitHubhttps://na01.safelinks.protection.outlook.com/?url=https%3A%2F%2Fgithub.com%2FStevenBlack%2Fhosts%2Fissues%2F710%23issuecomment-755770823&data=04|01||ac574ce9206542bc2d1f08d8b2981fbe|84df9e7fe9f640afb435aaaaaaaaaaaa|1|0|637455713720243991|Unknown|TWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D|1000&sdata=fHhpAPRgmpirQ0jgaEEbuWGFRdoK6O2ruJRbXpBszUQ%3D&reserved=0, or unsubscribehttps://na01.safelinks.protection.outlook.com/?url=https%3A%2F%2Fgithub.com%2Fnotifications%2Funsubscribe-auth%2FASK3GPBB7IYIJPQEROTCK43SYTUSVANCNFSM4FI2PKJQ&data=04|01||ac574ce9206542bc2d1f08d8b2981fbe|84df9e7fe9f640afb435aaaaaaaaaaaa|1|0|637455713720243991|Unknown|TWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D|1000&sdata=%2B5q8uLETPRKiVXiFnpQ2alsHBQCK%2FTSt1tDdury9cj0%3D&reserved=0.
A note for the unwary: I applied the changes recommended in this thread, rebooted and it broke file share browsing. I could no longer access files on my NAS (a Synology). Reverting the changes restored access (after another reboot).
The underlying cause of high CPU in my case was a faulty USB hub with a built-in network adapter. It was constantly connecting and disconnecting as evidenced by entries in event logs. This may have been specific to Hyper-V, which automatically reprovisions network devices on discovery.
High usage on W10 startup while DNS Client processes all the urls in the hosts file. Presumably it calls add-dnsserverresourcerecord to the cache for use with Store/ActiveDirectory or some other non-browser based operations. If, for some reason Windows shutdown is not successful, the DNS cache gets flushed on reboot, so the db has to be rebuilt.
|
2025-04-01T06:37:34.896941
| 2020-05-27T07:54:59
|
625466278
|
{
"authors": [
"StevenBlack",
"XhmikosR"
],
"license": "mit",
"license_source": "bigquery",
"license_type": "permissive",
"provenance": "gharchive-dolma-0000.json.gz:2754",
"repo": "StevenBlack/hosts",
"url": "https://github.com/StevenBlack/hosts/pull/1295"
}
|
gharchive/pull-request
|
Update updateHostsFile.py
Escape backslashes
@StevenBlack @funilrys Untested, but it makes sense 🙂 There's still one error that makes CI fail, though:
./updateHostsFile.py:1094:13: F523 '...'.format(...) has unused arguments at position(s): 0
Thanks for taking initiative and jumping in, @XhmikosR!
MErging.
|
2025-04-01T06:37:34.898269
| 2021-02-01T17:18:53
|
798552353
|
{
"authors": [
"Parmeisan"
],
"license": "MIT",
"license_source": "github-api",
"license_type": "permissive",
"provenance": "gharchive-dolma-0000.json.gz:2755",
"repo": "StevenGreenbank/Global-Gamejam-2021",
"url": "https://github.com/StevenGreenbank/Global-Gamejam-2021/issues/48"
}
|
gharchive/issue
|
Ravi/Usir Dialogue images
I have tried a billion times to overwrite the "bad" images and they should no longer exist anywhere in Godot. And yet, they do...
I think it must be that my images were scaled. I thought it was the fact they were scaled + shifted and when I cropped them it would work, but I created a brand new image with a new name and copied everything over and it still showed up wrong. Then I re-downloaded Jo's original, saw they were too big on the map (since it was using the same image) and scaled it down. Finally the dialogue was working. So... oops. Wasted well over an hour banging my head against the wall thinking Godot was somehow caching the image...
|
2025-04-01T06:37:34.991458
| 2018-08-09T17:11:05
|
349214986
|
{
"authors": [
"jmbldwn",
"scriptorian"
],
"license": "Apache-2.0",
"license_source": "github-api",
"license_type": "permissive",
"provenance": "gharchive-dolma-0000.json.gz:2756",
"repo": "Streampunk/naudiodon",
"url": "https://github.com/Streampunk/naudiodon/issues/17"
}
|
gharchive/issue
|
Ubuntu: getting a string instead of samples in data event.
My app works perfectly on my mac. When I run it on my ubuntu machine (my actual target) the 'data' event returns strings instead of samples.
I've tried it with a couple of different USB microphones. Here's an example of a message that is coming through the 'data' callback:
re/alsa/alsa.confommon:CARD=0,DEVICE=3,CTLINDEX=0,AES0=4,AES1=130,AES2=0,AES3=2m
What's causing this? I am able to record on this PC using arecord, so it appears ALSA is working in the system.
Update: appears to be related to asking for a sample format that the hardware doesn't support. Not sure why this isn't an error instead of passing messages through the data event.
Maybe more data on the environment might help:
Ubuntu 18.04 64-bit server running on a celeron x86 CPU.
There is no native audio hardware on this device; I'm using USB microphones.
I installed alsa using apt. Appears to be version 1.1.3.
What other info would be helpful?
I have just pushed a big update to naudiodon. It would be good to know if the new implementation still has this problem.
|
2025-04-01T06:37:35.177115
| 2020-11-17T09:35:37
|
744569256
|
{
"authors": [
"gabriele-tomassetti",
"taavandais2"
],
"license": "apache-2.0",
"license_source": "bigquery",
"license_type": "permissive",
"provenance": "gharchive-dolma-0000.json.gz:2757",
"repo": "Strumenta/SmartReader",
"url": "https://github.com/Strumenta/SmartReader/issues/24"
}
|
gharchive/issue
|
Add extract Twitter embed and youtube video. Please!
like a title!!!!!!!!!!
The algorithm already keeps embedded Youtube videos. Are you asking for something like a property Videos or Tweets on the Article object? Or are you thinking about something like a method GetVideosAsync()?
thank you!!!!!
|
2025-04-01T06:37:35.180877
| 2023-02-27T12:15:28
|
1601072762
|
{
"authors": [
"Strypper",
"nhatminh1401"
],
"license": "MIT",
"license_source": "github-api",
"license_type": "permissive",
"provenance": "gharchive-dolma-0000.json.gz:2758",
"repo": "Strypper/mauisland",
"url": "https://github.com/Strypper/mauisland/issues/113"
}
|
gharchive/issue
|
[Enhancements]: Display Error
What is going on?
When I entrance app:
I can't see Search Controls
I click on button Gallery -> It don't display anything you need click back to Home and after that click on Gallery back
When you on Galley -> Syncfusion -> More detail to open the new page -> It can't do it and got out of the program
When you on Galley -> Syncfusion -> SfRadialGauge, SfDataGrid -> More detail to open the new page-> I don't know It empty or no data
When you on Galley -> Built-in-> Check Box-> More detail to open the new page -> It can't do it and got out of the program
When you on Galley -> Built-in-> Application Settings JSON -> Detail and More detail to open the new page -> When I roll to the end and click on Show me those settings -> The program is closed
RefershView do not display all data or because my Windows doesn't assit
StackLayout -> More detail to open the new page -> Some Data missing ?
TabbedPage -> Detal -> I can't back to Menu Galley
VerticalStackLayout -> More detail to open the new page -> It can't do it and got out of the program
@nhatminh1401 we move this to discussions yet ?
|
2025-04-01T06:37:35.243728
| 2021-08-04T10:39:34
|
960229553
|
{
"authors": [
"erdzan12"
],
"license": "MIT",
"license_source": "github-api",
"license_type": "permissive",
"provenance": "gharchive-dolma-0000.json.gz:2761",
"repo": "StudyGrow/Cards",
"url": "https://github.com/StudyGrow/Cards/issues/154"
}
|
gharchive/issue
|
add translations - [merged]
In GitLab by @erdzan on Apr 27, 2021, 20:10
Merges ngxtranslate -> master
Co-authored-by: Ben Lakhoune<EMAIL_ADDRESS>
In GitLab by @erdzan on Apr 27, 2021, 20:10
approved this merge request
In GitLab by @erdzan on Apr 27, 2021, 20:11
added 2 commits
382be4c1 - 1 commit from branch masterb61ab284 - Merge remote-tracking branch 'origin/master' into ngxtranslate
Compare with previous version
In GitLab by @erdzan on Apr 27, 2021, 20:11
approved this merge request
In GitLab by @erdzan on Apr 27, 2021, 20:11
mentioned in commit 5a0fe54e847ac9a4bff91ede6da2a5fadb19340b
|
2025-04-01T06:37:35.270311
| 2015-08-07T09:15:24
|
99611925
|
{
"authors": [
"Reinmar",
"braver"
],
"license": "mit",
"license_source": "bigquery",
"license_type": "permissive",
"provenance": "gharchive-dolma-0000.json.gz:2762",
"repo": "SublimeLinter/SublimeLinter3",
"url": "https://github.com/SublimeLinter/SublimeLinter3/issues/310"
}
|
gharchive/issue
|
Different setting per folder
I have a project which consists of many submodules and each of them has its own JSHint and JSCS config files. In Sublime I want to have all these submodules as one projects (because they are rather small).
Is it possible to configure SublimeLinter3 so it uses different linter settings per folder? Or is it more a question about Sublime's than SublimeLinter's capabilities?
If I didn't miss anything and this is indeed impossible to achieve now, then could such feature be added to SublimeLinter or it doesn't seem to be feasible?
A linter executable will look for it's configuration starting from the file it is linting. So, this should "just work". If not, that's up to the linter, not SL.
|
2025-04-01T06:37:35.290062
| 2023-11-16T14:49:50
|
1997040887
|
{
"authors": [
"guilhem-barthes",
"oleobal"
],
"license": "Apache-2.0",
"license_source": "github-api",
"license_type": "permissive",
"provenance": "gharchive-dolma-0000.json.gz:2763",
"repo": "Substra/orchestrator",
"url": "https://github.com/Substra/orchestrator/pull/333"
}
|
gharchive/pull-request
|
chore: update orc certificates
Description
How has this been tested?
Checklist
[ ] changelog was updated with notable changes
[ ] documentation was updated
Thank you!
|
2025-04-01T06:37:35.314690
| 2023-01-20T15:17:45
|
1551025870
|
{
"authors": [
"BryceStevenWilley",
"plocket"
],
"license": "MIT",
"license_source": "github-api",
"license_type": "permissive",
"provenance": "gharchive-dolma-0000.json.gz:2764",
"repo": "SuffolkLITLab/docassemble-ALToolbox",
"url": "https://github.com/SuffolkLITLab/docassemble-ALToolbox/issues/141"
}
|
gharchive/issue
|
al_income.yml can't get past id: regular job employer if x.is_self_employed
"Interview order" for ALJob won't get past id: regular job employer if user selects that they are self-employed.
https://github.com/SuffolkLITLab/docassemble-ALToolbox/blob/main/docassemble/ALToolbox/data/questions/al_income.yml#L627
I think it'll be the same for ALItemizedJob.
https://github.com/SuffolkLITLab/docassemble-ALToolbox/blob/main/docassemble/ALToolbox/data/questions/al_income.yml#L158
Can't ask for x.employer.name.first because that may not be filled in
[Also, how many of those questions need to be required? For example, does the postal code and phone need to be required?]
I'm gonna mention this is the docs, but the reason for this is mentioned right above the line you linked for ALItemizedJob;
# NOTE: if `is_self_employed`, you need to set this yourself
Because in al_income, we only have access to the ALJob types. We need that job to be associated with some individual for us to actually be able to do anything with is_self_employed and the employer's name, which nothing in this module is.
In the ALAffidavit, the block that solves this is:
sets:
- x.jobs[i].employer.name.first
generic object: ALIndividual
code: |
if x.jobs[i].is_self_employed:
x.jobs[i].employer.address = x.address
x.jobs[i].employer.phone = x.phone_number
x.jobs[i].employer.name = x.name
Definitely not great, but there's not a good way around it IMO. Unless you have any ideas.
Can't ask for x.employer.name.first because that may not be filled in
That's explicitly why we define it right there; because it might not be filled in, we need to trigger a different code block (that needs to be provided by the user of this library) to fill it in when is_self_employed == True
how many of those questions need to be required? For example, does the postal code and phone need to be required?
Those are required for the Massachusetts form, and I'd guess that they'd be required elsewhere as well. Is replacing that screen not a good trade off there? Those attributes aren't defined in the code blocks, unlike the employer name.
I think I didn't describe the problem clearly enough. When a user reaches the screen I named, there's an option to check off that they are self employed. If they select that option, they cannot move on to the next question. Either we can't ask about self employment on the same page as the employer name or we need some other solution.
I'm not sure which file you are using for testing, but again, it's because users need to add a code block that sets x.employer.name.first, and that's noted in the file (and will be documented in the documentation). Adding that code block above in a user's file would fix it.
In case you were trying the demo (which I hadn't done a through fix on when updating the rest of the module), I fixed it in #145, if you want to try that out.
We had a quick conversation about this, and can be summarized as:
we should add a code block to AssemblyLine to make it easier for most of our users to have things work out of the box. Something like this:sets:
- x.jobs[i].employer.name.first
generic object: ALIndividual
code: |
if x.jobs[i].is_self_employed:
x.jobs[i].employer.address = x.address
x.jobs[i].employer.phone = x.phone_number
x.jobs[i].employer.name = x.name
if we can, the default code block in the demo, which sets just the employer's first name to "self-employed" and everything else to empty strings, might be a good default to just include in al_income.yml itself. We should see if that is actually a good default to have.
if not, we will document heavily in the file how to override that behavior.
@nonprofittechy @CaroRob we thought y'all might have an opinion on the second point above; specifically, that when we are asking about someone's employer at their job, if they say that they are self employed, the employer's name would be set to "self-employed", and the employer's contact information would be empty. That string, "self-employed", would likely appear verbatim on the form itself. Is this a good default to have, or are there cases where this would be a very bad default to have?
We were thinking this is a good default; our thought was that on a form where we are asking for someone's employment information, that person's information will be on the form somewhere else, and anyone reading the form would immediately look towards that info if in a question about someone's employer's information they had written "self-employed". Would appreciate y'all's opinions though.
This was merged, and fixed in https://github.com/SuffolkLITLab/docassemble-ALToolbox/commit/5f3f799374236384df6699a5ea8ec5bf7fbb90a5.
|
2025-04-01T06:37:35.403536
| 2022-10-17T06:38:59
|
1410995923
|
{
"authors": [
"TanushreeSG",
"asifbasha61",
"htvenkatesh"
],
"license": "MIT",
"license_source": "github-api",
"license_type": "permissive",
"provenance": "gharchive-dolma-0000.json.gz:2793",
"repo": "Sunbird-cQube/community",
"url": "https://github.com/Sunbird-cQube/community/issues/583"
}
|
gharchive/issue
|
Dashboard build issue when doing onpremise installation
Getting this error while doing onpremise installation
A variable in the config file has been repeated twice due to which angular failed build the code.
Modified the ansible env file and pushed the code to repo.
@asifbasha61 thanks, @TanushreeSG please recheck this issue and update it asap, as its a blocker
Retested again getting same error
@asifbasha61 pls check this wts the issue
@htvenkatesh @asifbasha61 It was a pull issue. I have retested again, now its working as expected.
|
2025-04-01T06:37:35.405999
| 2022-01-02T14:25:39
|
1092030785
|
{
"authors": [
"gzuidhof",
"jeremiahlee"
],
"license": "MIT",
"license_source": "github-api",
"license_type": "permissive",
"provenance": "gharchive-dolma-0000.json.gz:2794",
"repo": "SunderJS/sunder-worker-template",
"url": "https://github.com/SunderJS/sunder-worker-template/issues/5"
}
|
gharchive/issue
|
Cannot read favicon-32x32.png
I am unable to install this template. I have tried on 2 different MacBook Pros using npm v8.3.0 and v8.1.0 and node v17.3.0 and v16.12.0.
% wrangler generate testproject https://github.com/sunderjs/sunder-worker-template
🔧 Creating project called `testproject`...
Error: liquid: Cannot read file
with:
path=/Users/jeremiah/Projects/testproject/static/favicon-32x32.png
Error: tried running command:
/Users/jeremiah/Library/Caches/.wrangler/cargo-generate-0.5.0/cargo-generate generate --git https://github.com/sunderjs/sunder-worker-template --name testproject --force
exited with exit status: 1
/Users/jeremiah/Projects/testproject/static/favicon-32x32.png does exist in Finder.
Could you try again now? I re-added cargo-template.toml (link), I think that file was necessary to stop Cargo's templating system from trying to do string replacements in a .png file
I am no longer getting this error. Thanks!
|
2025-04-01T06:37:35.439806
| 2017-03-29T13:39:51
|
217879112
|
{
"authors": [
"SlightlyBearded",
"satindergrewal"
],
"license": "MIT",
"license_source": "github-api",
"license_type": "permissive",
"provenance": "gharchive-dolma-0000.json.gz:2795",
"repo": "SuperNETorg/Agama",
"url": "https://github.com/SuperNETorg/Agama/issues/80"
}
|
gharchive/issue
|
Agama beta won't load
So I just uninstalled Iguana and installed Agama and when I try to open it, I get a javascript error and the app won't open...
Duplicate of https://github.com/SuperNETorg/Agama/issues/74
|
2025-04-01T06:37:35.582488
| 2023-06-23T12:54:48
|
1771413671
|
{
"authors": [
"ManavMalhotra",
"shobhitexe"
],
"license": "MIT",
"license_source": "github-api",
"license_type": "permissive",
"provenance": "gharchive-dolma-0000.json.gz:2796",
"repo": "SurajPratap10/Imagine_AI",
"url": "https://github.com/SurajPratap10/Imagine_AI/issues/415"
}
|
gharchive/issue
|
[style]: Improving the homepage
What's the style idea?
Adding a little bit of margin and padding on the right and left can improve the user experience.
Add screenshots
This is the prototype but redesigning the content with proper call to action will improve it
Code of Conduct
[X] I agree to follow this project's Code of Conduct
I have developed a prototype it will take some time to implement in on the homepage
@SurajPratap10 Also In panic i deleted the forked repo 🥲🥲
@shobhitexe
I’ve fixed the conflicts but I still can’t see my code in the main branch. Can you explain why? I would really appreciate your help with this.
i will be merged when admin of project or maintainers approve your PR
@shobhitexe
I’ve fixed the conflicts but I still can’t see my code in the main branch. Can you explain why? I would really appreciate your help with this.
i will be merged when admin of project or maintainers approve your PR
In my PR it's showing PR closed
|
2025-04-01T06:37:35.585238
| 2023-07-06T11:56:51
|
1791414070
|
{
"authors": [
"Saimurugeshwari",
"SurajPratap10",
"killerraj369"
],
"license": "MIT",
"license_source": "github-api",
"license_type": "permissive",
"provenance": "gharchive-dolma-0000.json.gz:2797",
"repo": "SurajPratap10/Imagine_AI",
"url": "https://github.com/SurajPratap10/Imagine_AI/issues/547"
}
|
gharchive/issue
|
[style]: Want to Improve Imagin-AI Page and also spelling errors and aligning issues
What's the style idea?
We need to improve the Improve AI Page. There are some issues in this page.
Add screenshots
Add screenshots
Code of Conduct
[X] I agree to follow this project's Code of Conduct
Can I work on this under GSSOC 2023
Hi, @SurajPratap10 Please assign me this issue. I want to work on it.
Can I work on this under GSSOC 2023
One who raises the issue has authority to work on it.
|
2025-04-01T06:37:35.589737
| 2024-10-24T17:55:13
|
2612238196
|
{
"authors": [
"haseebzaki-07"
],
"license": "MIT",
"license_source": "github-api",
"license_type": "permissive",
"provenance": "gharchive-dolma-0000.json.gz:2798",
"repo": "SurajPratap10/Imagine_AI",
"url": "https://github.com/SurajPratap10/Imagine_AI/pull/1325"
}
|
gharchive/pull-request
|
Add contact us backend
Description
This PR adds the contact us implementation of the project .
Created nodemailer functionality to send the users thank you message along with their submitted feedback.
Stored their feedbacks in the database.
Fixes #1318
Screenshots
Checklist
[X] Tests have been added or updated to cover the changes
[X] Documentation has been updated to reflect the changes
[X] Code follows the established coding style guidelines
[X] All tests are passing
@SurajPratap10 maybe its because of the localhost url in the API call
hey @SurajPratap10 please finalize this PR
hey @SurajPratap10 please finalize this PR, its here for a long time!!
@SurajPratap10 Please check this PR
|
2025-04-01T06:37:35.601383
| 2022-08-15T09:37:46
|
1338762440
|
{
"authors": [
"AliReza1083",
"Susmita-Dey"
],
"license": "MIT",
"license_source": "github-api",
"license_type": "permissive",
"provenance": "gharchive-dolma-0000.json.gz:2799",
"repo": "Susmita-Dey/Sukoon",
"url": "https://github.com/Susmita-Dey/Sukoon/pull/231"
}
|
gharchive/pull-request
|
Update index.html
The changes that I've brought:
[x] Remove the extra Lines
- 2 or 3 lines
+ 1 line
@AliReza1083 Fix the merge conflicts
__
Summary: :hammer_and_wrench: This code needs a fix | Tags: Not reusable
@Susmita-Dey
is it fixed?
@Susmita-Dey is it fixed?
Yes
So, should I work with that issue right now (service section)?
@AliReza1083 The footer design is broken. I can't merge it in this way. Also, you haven't mentioned the issue no?
__
Summary: :hammer_and_wrench: This code needs a fix | Tags: Not reusable
Ok, let me do it again.
@AliReza1083
What's the issue number?
__
Summary: :question: I have a question
is it fixed?
I think right now the navbar is working fine as I checked the website.
I don't see any issue.
I just removed the extra lines.
@AliReza1083 Have you created issues before this PR?
__
Summary: :question: I have a question
No, I didn't
Don't accept this PR. hahaha
Please assign me to fix that service layout issues.
@AliReza1083 Sorry I can't merge your PR then. Closing this.
__
Summary: :hammer_and_wrench: This code needs a fix | Tags: Not reusable
Don't accept this PR. hahaha
Please assign me to fix that service layout issues.
Create an issue on your own with proper screenshot and changes you wanna make.
__
Tags: Not reusable
|
2025-04-01T06:37:35.614686
| 2017-09-05T07:25:17
|
255182933
|
{
"authors": [
"RobWin",
"alkemann",
"cascer1"
],
"license": "apache-2.0",
"license_source": "bigquery",
"license_type": "permissive",
"provenance": "gharchive-dolma-0000.json.gz:2800",
"repo": "Swagger2Markup/markup-document-builder",
"url": "https://github.com/Swagger2Markup/markup-document-builder/pull/26"
}
|
gharchive/pull-request
|
Render correct markdown for syntax highlight specification.
NB! Initial state of this Pull Request is NOT WORKING, but made at library authors request.
Thx.
I think you have to change test.md as well, so that two tests don't fail.
I did change test.md?
Strange. Two tests still fail:
Strange. Two tests still fail.
MarkupDocBuilderTest > testMarkdownCodeBlock FAILED
MarkupDocBuilderTest > testMarkdown FAILED
Yes. Like I said in the issue thread, I have been unable to successfully fix this and get the tests to past.
I have used your modifications as a base for PR #28
Since #28 is a working fix for this issue (confirmed with local build), I am closing this
|
2025-04-01T06:37:35.616780
| 2024-02-19T04:03:52
|
2141453784
|
{
"authors": [
"Feudalman",
"SAKURA-CAT"
],
"license": "Apache-2.0",
"license_source": "github-api",
"license_type": "permissive",
"provenance": "gharchive-dolma-0000.json.gz:2801",
"repo": "SwanHubX/SwanLab",
"url": "https://github.com/SwanHubX/SwanLab/issues/324"
}
|
gharchive/issue
|
[QUESTION] Keep sorting same as user input
🤔 Question description [Please make everyone to understand it]
Keep sorting same as user input.
Now supported
|
2025-04-01T06:37:35.646833
| 2015-02-17T06:19:56
|
57887780
|
{
"authors": [
"amcdnl",
"lookfirst"
],
"license": "MIT",
"license_source": "github-api",
"license_type": "permissive",
"provenance": "gharchive-dolma-0000.json.gz:2803",
"repo": "Swimlane/angular-systemjs-seed",
"url": "https://github.com/Swimlane/angular-systemjs-seed/issues/20"
}
|
gharchive/issue
|
gulp release
What sort of workflow are you planning for gulp release?
When I think of a release, I think of an artifact that is built that can be distributed to my servers. Something like a .tgz, .zip, .jar, .deb, .rpm. Right now, the system doesn't really do that. Can we improve on it?
I'd like to propose that we move the system.config.js and index.html into the src folder. These files are then copied into the dist folder. This allows for a gulp prod (which calls gulp release) to just point at the dist folder as the root of the application to serve things from. It also allows us to test the built application easily.
Thoughts?
Gulp release is the command the CI server calls for distro to prod. We use .net so it packages the files internally.
I've done all this in my project. Take a look if you'd like to port it back over. =)
I think a better approach would be to inject this into the app.js file . We probably also need to handle the system and config file cache busting too.
Yea, I agree. I'd like to get rid of the whole rewrite of the index.html thing. It is kind of ugly. =)
|
2025-04-01T06:37:35.808146
| 2016-01-20T02:02:13
|
127587543
|
{
"authors": [
"Sydriax",
"truell20"
],
"license": "MIT",
"license_source": "github-api",
"license_type": "permissive",
"provenance": "gharchive-dolma-0000.json.gz:2806",
"repo": "Sydriax/Halite",
"url": "https://github.com/Sydriax/Halite/issues/9"
}
|
gharchive/issue
|
Small Maps
Really small maps and games produce non-functional files.
@Sydriax Is this still a problem? How small?
|
2025-04-01T06:37:35.817280
| 2021-06-15T09:30:19
|
921198450
|
{
"authors": [
"GSadee",
"imajim"
],
"license": "MIT",
"license_source": "github-api",
"license_type": "permissive",
"provenance": "gharchive-dolma-0000.json.gz:2807",
"repo": "Sylius/InvoicingPlugin",
"url": "https://github.com/Sylius/InvoicingPlugin/issues/227"
}
|
gharchive/issue
|
use symfony mailer and twig inky and not swiftmailer
Hello
i would use the symfony compenent mailer with twig inky to replace swiftmailer. it's possible ?
thx ^^
Sylius issues should be used to report bugs, propose new features, discuss new functionalities. For everything else, please, use our Slack or stackoverflow 😃
|
2025-04-01T06:37:35.883114
| 2021-04-29T01:35:42
|
870534620
|
{
"authors": [
"benglines",
"dnltz",
"mithro"
],
"license": "isc",
"license_source": "bigquery",
"license_type": "permissive",
"provenance": "gharchive-dolma-0000.json.gz:2808",
"repo": "SymbiFlow/prjxray",
"url": "https://github.com/SymbiFlow/prjxray/issues/1658"
}
|
gharchive/issue
|
parts.yaml file not found when running settings script for board family
When trying to install Project X-Ray for the first time, I get the following error when running source settings/artix7.sh
Traceback (most recent call last):
File "/home/benglines/prjxray_test/utils/create_environment.py", line 66, in <module>
main()
File "/home/benglines/prjxray_test/utils/create_environment.py", line 59, in main
environment = get_environment_variables()
File "/home/benglines/prjxray_test/utils/create_environment.py", line 37, in get_environment_variables
part_info = get_part_information(db_root, part)
File "/home/benglines/prjxray_test/prjxray/util.py", line 44, in get_part_information
"Mapping file {} does not exists".format(filename)
AssertionError: Mapping file /home/benglines/prjxray_test/database/artix7/mapping/parts.yaml does not exists
I have also seen it complain about not finding a resources.yaml file (just like #1639), but I am not exactly sure why that happened nor how to recreate the error. Either way, I solved the issue in both cases by running make db-prepare-artix7, and then source settings/artix7.sh. The quick start guide suggest you do them in the opposite order.
This issue could be resolved by simply switching Step 6 and Step 7 in the quick start guide, so that the shell scripts run in the correct order i.e. running source/settings/artix7.sh after running make db-prepare-parts or make db-prepare-artix7.
Seems like we should set up the CI to use tuttest to run the commands in the README like we do for the symbiflow-examples repository.
@benglines - Thanks for reporting. Indeed, the script should be sourced after preparing the db.
@mithro - If I have a little bit time soon, I can try to add such a simple test.
|
2025-04-01T06:37:35.892095
| 2020-04-14T13:46:44
|
599586250
|
{
"authors": [
"litghost",
"rw1nkler"
],
"license": "ISC",
"license_source": "github-api",
"license_type": "permissive",
"provenance": "gharchive-dolma-0000.json.gz:2809",
"repo": "SymbiFlow/symbiflow-arch-defs",
"url": "https://github.com/SymbiFlow/symbiflow-arch-defs/pull/1419"
}
|
gharchive/pull-request
|
[DNM] Add techmap for BUFGMUX
This commit adds techmap for BUFGMUX.
The implementation is based on the [Xilinx documentation]
For the Nexys Video board test produces the same error as for OpenTitan design https://github.com/SymbiFlow/symbiflow-arch-defs/issues/1442#issuecomment-627411466. I will investigate why this errors occur.
Yeah, I thought that we have already merged new db - https://github.com/SymbiFlow/symbiflow-arch-defs/pull/1619
Can we merge that? @litghost
Can you simply incorporate the submodule bump in this PR, and that will test that the new prjxray-db solves your issue?
@litghost I believe that those CI failures are not related to this PR.
Xilinx Series 7 - Vendor Tools Tests fails due to no space left on the device error
Traceback (most recent call last):
File "/tmpfs/src/github/symbiflow-arch-defs-presubmit-xc7-vendor/xc/common/utils/prjxray_import_tile_capacity.py", line 90, in <module>
main()
File "/tmpfs/src/github/symbiflow-arch-defs-presubmit-xc7-vendor/xc/common/utils/prjxray_import_tile_capacity.py", line 86, in main
f.write(tile_str)
OSError: [Errno 28] No space left on device
VtR + SymbiFlow Architecture Definitions fails on:
Cannot route from BLK-TL-RIOPAD_M[0].IOI_ILOGIC0_O[0] (RR node: 1484735 type: SOURCE location: (114,109) class: 53 capacity: 1 fan-in: 0 fan-out: 1) to BLK-TL-RIOPAD_S[0].IOI_OLOGIC1_D1[0] (RR node: 1392164 type: SINK location: (114,67) class: 26 capacity: 1 fan-in: 1 fan-out: 0) -- no possible path
Failed to route connection from 'sw[15]' to '$iopadmap$top.led_15.t_inv' for net '$abc$1667$iopadmap$led[15]' (#16)
Could this be related to https://github.com/SymbiFlow/symbiflow-arch-defs/pull/1711?
|
2025-04-01T06:37:35.906156
| 2020-10-27T09:43:05
|
730282907
|
{
"authors": [
"acomodi",
"litghost",
"mithro",
"mkurc-ant"
],
"license": "ISC",
"license_source": "github-api",
"license_type": "permissive",
"provenance": "gharchive-dolma-0000.json.gz:2810",
"repo": "SymbiFlow/symbiflow-arch-defs",
"url": "https://github.com/SymbiFlow/symbiflow-arch-defs/pull/1729"
}
|
gharchive/pull-request
|
xc7 MMCM support
This pull requests adds support for MMCM block for Xilinx 7-series devices.
The supported features are:
Basic (integer) multiplier and divider control,
Fractional multiplier (CLKFBOUT) and divider (CLKOUT0) support,
Duty cycle control,
Phase shift control,
Bandwidth and compensation settings,
Local control input inverters (CLKINSEL, PSEN, PSINCDEC, PWRDWN, RST)
Startup wait enable/disable
Dynamic phase shift and dynamic reconfiguration are supported as well.
All the remaining MMCM functionality is not supported at the moment mostly due to missing bitstream documentation. This is tracked in https://github.com/SymbiFlow/prjxray/issues/1473
This PR also adds tests/examples for MMCM which are available under xc/xc7/tests/mmcm and can be run on hardware (some of them).
While disassembling Vivado bitstreams of MMCM designs I'm consistently getting these two unknown bits:
{ unknown_bit = "0040151c_30_19", unknown_segment = "0x00401500", unknown_segbit = "28_979" }
{ unknown_bit = "0040151c_31_28", unknown_segment = "0x00401500", unknown_segbit = "28_1020" }
While disassembling Vivado bitstreams of MMCM designs I'm consistently getting these two unknown bits:
{ unknown_bit = "0040151c_30_19", unknown_segment = "0x00401500", unknown_segbit = "28_979" }
{ unknown_bit = "0040151c_31_28", unknown_segment = "0x00401500", unknown_segbit = "28_1020" }
This doesn't surprise me too much. I disabled the compension features because they were initially causing me trouble, see here: https://github.com/SymbiFlow/prjxray/blob/91d91357b5077b12e578ac741322bea71c285b6a/fuzzers/031-cmt-mmcm/generate.py#L128-L131
Now that the basic MMCM features and pips are in, maybe it is time to go back and get the compension features working?
@litghost I've checked and currently the MMCM does not work in hardware when using SymbiFlow bitstream. It looks like the two unknown bits I mentioned before are required for it to work. I've tested Vivado and SymbiFlow bitstreams for the same design where the only difference between them was the latter missing these two bits. The Vivado bitstream works while the SymbiFlow doesn't.
This one solves the two missing bits: https://github.com/SymbiFlow/prjxray/pull/1491
@litghost Done. I'm now working on adding MMCM support to fasm2bels.
Latest error:
CMake Error at xc/xc7/tests/mmcm/CMakeLists.txt:46 (add_dependencies):
The dependency target "mmcm_random_case3_vivado_diff_fasm" of target
"all_xc7_mmcm_vivado_diff_fasm" does not exist.
@litghost Thanks for pointing out all the issues. So far I've managed to fix PLL NO_COUNT regression and MMCM DCP errors. A PR is in: https://github.com/SymbiFlow/symbiflow-xc-fasm2bels/pull/44
@litghost Thanks for pointing out all the issues. So far I've managed to fix PLL NO_COUNT regression and MMCM DCP errors. A PR is in: https://github.com/SymbiFlow/symbiflow-xc-fasm2bels/pull/44
Any reason this pull request was never landed?
@mithro As far as I remember this didn't land because there are some MMCM tests that fail due to incorrect BUFHCE route-throu handling in fasm2bels. I see two options:
We solve the BUFHCE issue in fasm2bels,
We simplify the failing tests so that they use eg. a single clock output which does not cause issues.
I've tested locally integration of this PR with https://github.com/SymbiFlow/symbiflow-xc-fasm2bels/pull/52 and the latter still fails on some designs each time at the same place in code:
Traceback (most recent call last):
File "/home/build/mkurc/symbiflow-arch-defs/env/conda/envs/symbiflow_arch_def_base/lib/python3.7/runpy.py", line 193, in _run_module_as_main
"__main__", mod_spec)
File "/home/build/mkurc/symbiflow-arch-defs/env/conda/envs/symbiflow_arch_def_base/lib/python3.7/runpy.py", line 85, in _run_code
exec(code, run_globals)
File "/home/build/mkurc/symbiflow-arch-defs/third_party/symbiflow-xc-fasm2bels/fasm2bels/__main__.py", line 15, in <module>
main()
File "/home/build/mkurc/symbiflow-arch-defs/third_party/symbiflow-xc-fasm2bels/fasm2bels/fasm2bels.py", line 489, in main
top.make_routes(allow_orphan_sinks=args.allow_orphan_sinks)
File "/home/build/mkurc/symbiflow-arch-defs/third_party/symbiflow-xc-fasm2bels/fasm2bels/models/verilog_modeling.py", line 2174, in make_routes
self.handle_post_route_cleanup()
File "/home/build/mkurc/symbiflow-arch-defs/third_party/symbiflow-xc-fasm2bels/fasm2bels/models/verilog_modeling.py", line 2347, in handle_post_route_cleanup
site.post_route_cleanup(self, site)
File "/home/build/mkurc/symbiflow-arch-defs/third_party/symbiflow-xc-fasm2bels/fasm2bels/models/clk_models.py", line 191, in cleanup_hrow
assert False, bufhce_i_wire_pkey
AssertionError: 1627284
So it looks like BUFHCE route-throu handling still fails for some cases.
xc7 tests fail on minilitex_ddr_arty with:
ERROR: [DRC RTRES-2] Global clock nets are using local routing resources: Global clock nets are using local routing resources. 1 net(s) have at least one node with COST_CODE_NAME equal to BOUNCEACROSS or INTENT_CODE_NAME equal to NODE_DOUBLE, NODE_HLONG, NODE_HQUAD, NODE_SINGLE, NODE_VLONG, or NODE_VQUAD. This situation occurs when a global clock net must enter a clock region where all global clock routing resources are occupied. Check the report from report_clock_utilization to determine which clock regions are traversed by the problem net and use floorplanning or other physical constraints to ensure a maximum of 12 global clock nets occupy each clock region. The problem net(s) are sys_clk.
ERROR: [Vivado 12-1345] Error(s) found during DRC. Bitgen not run.
I believe this error is not related to the change in fasm2bels, but it is a consequence of not handling the clock nets limits in a clock region, and this has not to do with fasm2bels, but with VPR.
If the MMCM test passed in the vendor tools CI I think we can go ahead and merge https://github.com/SymbiFlow/symbiflow-xc-fasm2bels/pull/52 and than update the fasm2bels version in this PR
@acomodi Ok, go ahead then with merging the fasm2bels PR.
I haven't looked in Vivado documentation what this DRC error means but it looks like that it is merely a warning that a clock uses a local route instead of a global one (because there are no more available).
|
2025-04-01T06:37:35.907856
| 2021-09-10T07:34:28
|
992969886
|
{
"authors": [
"acomodi"
],
"license": "ISC",
"license_source": "github-api",
"license_type": "permissive",
"provenance": "gharchive-dolma-0000.json.gz:2811",
"repo": "SymbiFlow/symbiflow-arch-defs",
"url": "https://github.com/SymbiFlow/symbiflow-arch-defs/pull/2265"
}
|
gharchive/pull-request
|
quicklogic: pin quicklogic_fasm python library
Signed-off-by: Alessandro Comodi<EMAIL_ADDRESS>
This actually will be pinned in the conda-lock file, which contains all the pip packages locked already (if the package is pinned in the requirements file)
|
2025-04-01T06:37:35.910861
| 2022-02-04T10:47:12
|
1124059129
|
{
"authors": [
"jakebeal"
],
"license": "MIT",
"license_source": "github-api",
"license_type": "permissive",
"provenance": "gharchive-dolma-0000.json.gz:2812",
"repo": "SynBioDex/SBOL-utilities",
"url": "https://github.com/SynBioDex/SBOL-utilities/issues/102"
}
|
gharchive/issue
|
Remove dependency on online validator/converter
pySBOL2 uses the SBOL online validator/converter at https://validator.sbolstandard.org/ for validation; we also use it for conversion to GenBank. Although this was stable for a long time, it has recently gone down, which is breaking lots of applications. Even if it goes up quickly again, this outage is painful.
Use of the online validator/converter also means SBOL utilities cannot be used offline and cannot convert confidential data to GenBank format.
The longer-term solution to this is going to be having native converters (see: https://github.com/nrnb/GoogleSummerOfCode/issues/183).
The near-term patch is to include a jar from https://github.com/SynBioDex/libSBOLj
First part of fix in progress at https://github.com/SynBioDex/pySBOL2/tree/offline-validation-conversion
Once this is updated, we can proceed to configuring sbol-utilities to use pySBOL2 in offline mode.
|
2025-04-01T06:37:35.913512
| 2021-02-19T20:04:49
|
871322573
|
{
"authors": [
"JMante1",
"danielfang97"
],
"license": "BSD-2-Clause",
"license_source": "github-api",
"license_type": "permissive",
"provenance": "gharchive-dolma-0000.json.gz:2813",
"repo": "SynBioHub/synbiohub3",
"url": "https://github.com/SynBioHub/synbiohub3/issues/31"
}
|
gharchive/issue
|
Some annotations don't render well
In particular source and target organism don't display well and data source and wasGeneratedby don't display at all. Examples of the use of these three can be found here: https://synbiohub.org/user/JMante/CIDAR_toolkit_KWK/CIDAR_toolkit_KWK_collection/1/a330d6f09b2bf4040d6012c515489e6e2674f626/share
closing this as this just has to do with the ontology issue
|
2025-04-01T06:37:36.022078
| 2023-04-15T14:33:44
|
1669434232
|
{
"authors": [
"feiranl",
"haowang-bioinfo"
],
"license": "CC-BY-4.0",
"license_source": "github-api",
"license_type": "permissive",
"provenance": "gharchive-dolma-0000.json.gz:2814",
"repo": "SysBioChalmers/Human-GEM",
"url": "https://github.com/SysBioChalmers/Human-GEM/pull/535"
}
|
gharchive/pull-request
|
feat: Add new reactions annotated for genes related to Glycolysis pathway
Main improvements in this PR:
Add 87 new mets, 68 new reactions for genes related to Glycolysis pathway according to the #507
I hereby confirm that I have:
[x] Tested my code on my own computer for running the model
[x] Selected develop as a target branch
[x] Any removed reactions and metabolites have been moved to the corresponding deprecated identifier lists
very good progress!
|
2025-04-01T06:37:36.024125
| 2022-04-13T08:07:00
|
1202911084
|
{
"authors": [
"KudoKhang",
"lkeab"
],
"license": "Apache-2.0",
"license_source": "github-api",
"license_type": "permissive",
"provenance": "gharchive-dolma-0000.json.gz:2815",
"repo": "SysCV/transfiner",
"url": "https://github.com/SysCV/transfiner/issues/9"
}
|
gharchive/issue
|
Error list image path
hi,
when i run code your code in Colab have error at line 106 demo/demo.py:
106| args.input = glob.glob(os.path.expanduser(args.input[0]))
it not return a list of image path. but if change:
106| args.input = [args.input[0] + '/' + name for name in os.listdir(args.input[0]) if name.endswith(('png', 'jpg', 'jpeg'))]
it work!
And the mask result not good as you said, can you tell me how to get a perfect result as your paper
This is script we recommend for visualization. Current checkpoint is a retrained beta version, we will update the final released checkpoints before CVPR.
|
2025-04-01T06:37:36.034529
| 2023-03-18T19:44:42
|
1630551706
|
{
"authors": [
"MarioHewardt",
"juju4"
],
"license": "MIT",
"license_source": "github-api",
"license_type": "permissive",
"provenance": "gharchive-dolma-0000.json.gz:2816",
"repo": "Sysinternals/SysmonForLinux",
"url": "https://github.com/Sysinternals/SysmonForLinux/issues/108"
}
|
gharchive/issue
|
[1.1.0] make package wrong version 0.0.0-0
Describe the bug
when building sysmon with newly release 1.1.0 code (git commit edc74fc41301d78ad9c9bedcc73f384cff2f7900), make package use a non-matching version aka 0.0.0-0 instead of 1.1.0-1.
previously worked as 1.0.0-1 (commit 9bca3734721a01cb2ac6e2e3adc40ecdcad3151e)
To Reproduce
following https://github.com/Sysinternals/SysmonForLinux/blob/main/BUILD.md#make-packages
make
make packages
Sysmon version
edc74fc41301d78ad9c9bedcc73f384cff2f7900
Distro/kernel version
tested on ubuntu 22.04 and 20.04
Sysmon configuration
N/A
Logs
(ubuntu 22.04)
https://github.com/juju4/ansible-sysmon/actions/runs/4456447238/jobs/7826904245#step:7:11077
changed: [instance] => (item={'c': 'make packages', 'chdir': '/var/_install/sysmon/build', 't': '/var/_install/sysmon/build/deb/sysmonforlinux_<IP_ADDRESS>-1_amd64.deb'}) => {
"ansible_loop_var": "item",
"changed": true,
"cmd": [
"make",
"packages"
],
"delta": "0:00:04.141773",
"end": "2023-03-18 17:18:57.896421",
"invocation": {
"module_args": {
"_raw_params": "make packages",
"_uses_shell": false,
"argv": null,
"chdir": "/var/_install/sysmon/build",
"creates": "/var/_install/sysmon/build/deb/sysmonforlinux_<IP_ADDRESS>-1_amd64.deb",
"executable": null,
"removes": null,
"stdin": null,
"stdin_add_newline": true,
"strip_empty_ends": true
}
},
"item": {
"c": "make packages",
"chdir": "/var/_install/sysmon/build",
"t": "/var/_install/sysmon/build/deb/sysmonforlinux_<IP_ADDRESS>-1_amd64.deb"
},
"msg": "",
"rc": 0,
"start": "2023-03-18 17:18:53.754648",
"stderr": "",
"stderr_lines": [],
"stdout": "[ 2%] Built target checkEBPFsizes\n[ 17%] Built target sysmonLogView\n[ 18%] Checking sysmonEBPFkern4.15_core.o\n\n[100%] Built target sysmon\ndpkg-deb: building package 'sysmonforlinux' in 'sysmonforlinux_0.0.0-0_amd64.deb'.\nNo rpmbuild found\n[100%] Built target packages",
"stdout_lines": [
"[ 2%] Built target checkEBPFsizes",
"[ 17%] Built target sysmonLogView",
"[ 18%] Checking sysmonEBPFkern4.15_core.o",
"",
"[100%] Built target sysmon",
"dpkg-deb: building package 'sysmonforlinux' in 'sysmonforlinux_0.0.0-0_amd64.deb'.",
"No rpmbuild found",
"[100%] Built target packages"
]
}
note that t is a for expected resulting file to be and from ansible role, not related to the build itself.
same on ubuntu 20.04: https://github.com/juju4/ansible-sysmon/actions/runs/4456447238/jobs/7826904285#step:7:14781
Expected behavior
build for current version or above, else could lead to mismatch from package manager
Hi - You can set env variable VERSION= and it will be respected in our build scripts. Does that work for you?
Does not seem so. still 0.0.0
https://github.com/juju4/ansible-sysmon/actions/runs/4519184319/jobs/7959525720#step:7:4929
like previously
https://github.com/juju4/ansible-sysmon/actions/runs/4463993537/jobs/7839727245#step:7:4935
note that I didn't change sysmon_build_version variable but only used for install of resulting package and ansible play's idempotence.
Still in an issue here
https://github.com/juju4/ansible-sysmon/actions/runs/6284397818/job/17065732603#step:7:5131
"stdout": "Consolidate compiler generated dependencies of target checkEBPFsizes\n[ 2%] Built target checkEBPFsizes\nConsolidate compiler generated dependencies of target sysmonLogView\n[ 17%] Built target sysmonLogView\n[ 18%] Checking sysmonEBPFkern4.15_core.o\n\nConsolidate compiler generated dependencies of target sysmon\n[100%] Built target sysmon\ndpkg-deb: building package 'sysmonforlinux' in 'sysmonforlinux_0.0.0-0_amd64.deb'.\nNo rpmbuild found\n[100%] Built target packages",
"stdout_lines": [
"Consolidate compiler generated dependencies of target checkEBPFsizes",
"[ 2%] Built target checkEBPFsizes",
"Consolidate compiler generated dependencies of target sysmonLogView",
"[ 17%] Built target sysmonLogView",
"[ 18%] Checking sysmonEBPFkern4.15_core.o",
"",
"Consolidate compiler generated dependencies of target sysmon",
"[100%] Built target sysmon",
"dpkg-deb: building package 'sysmonforlinux' in 'sysmonforlinux_0.0.0-0_amd64.deb'.",
"No rpmbuild found",
"[100%] Built target packages"
]
Not sure if there is something specific to Ansible but I just did the following which worked just fine:
~/SysmonForLinux$ rm -rf build
~/SysmonForLinux$ mkdir build
~/SysmonForLinux$ cd build/
~/SysmonForLinux/build$ export VERSION=**<IP_ADDRESS>**
~/SysmonForLinux/build$ cmake ..
~/SysmonForLinux/build$ make
...
...
...
[ 91%] Building C object CMakeFiles/sysmonUnitTests.dir/sysmonmsgop.c.o
[ 92%] Linking CXX executable sysmonUnitTests
[100%] Built target sysmonUnitTests
Scanning dependencies of target sysmonEBPFkern4.16
[100%] Built target sysmonEBPFkern4.16
Scanning dependencies of target sysmonEBPFkern5.6-
[100%] Built target sysmonEBPFkern5.6-
~/SysmonForLinux/build$ make packages
dpkg-deb: building package 'sysmonforlinux' in 'sysmonforlinux_**1.2.3-4**_amd64.deb'.
|
2025-04-01T06:37:36.076090
| 2021-05-26T18:31:30
|
902784424
|
{
"authors": [
"T-Troll",
"lowrck"
],
"license": "MIT",
"license_source": "github-api",
"license_type": "permissive",
"provenance": "gharchive-dolma-0000.json.gz:2817",
"repo": "T-Troll/alienfx-tools",
"url": "https://github.com/T-Troll/alienfx-tools/issues/13"
}
|
gharchive/issue
|
alienfx-ambient seems to crash the rgb controller for my dell g5 5500
so i managed to get the lighting zones for the lightbar mapped to names and even set up the ambient screen map how i wanted. it works for about 15-30 seconds but then the bar goes black and stays black no matter what i do. even starting AWCC doesn't allow changes to work. i don't know if this is a known issue or if i am unique but for now ambient is unusable. my guess is it issues commands too quickly and overwhelms the controller causing a unrecoverable crash to happen. well, it can recovery, though only after a system reboot. its a bummer but it looks like the ambient mode just can't be used right now.
Can i check you registry entries into HKCU/Software/AlienFX_sdk and HKCU/Software/Alienfxambient?
I check at my gear, and seems like it's not hardware hung, but MS alter DXGi capture into recent update. You can try to press "Reset" button into app to resume, or exit app and issue alienfx-cli set-all=255,0,0 command or so to check.
I will try to fix DXGi hung into new release, it's also nice if you confirm p.2
PS: There are 10fps limit into alienfx-ambient, so command rate is not so high (haptics use higher rate).
Check new release 1.1.8 - should be more stable now.
|
2025-04-01T06:37:36.104400
| 2019-01-04T20:39:05
|
396060089
|
{
"authors": [
"coveralls",
"jeremythuff"
],
"license": "MIT",
"license_source": "github-api",
"license_type": "permissive",
"provenance": "gharchive-dolma-0000.json.gz:2821",
"repo": "TAMULib/Cap",
"url": "https://github.com/TAMULib/Cap/pull/72"
}
|
gharchive/pull-request
|
[D01243] Check fixity of resource for list of resources not working
Resolves D-01243: Check fixity of resource for list of resources not working.
This PR addressed the issues by simplifying the process of obtaining a fixity report. The FixityReport has been removed from the IRContext and has become a first class citizen on the front end. Obtaining fixity both from a resource or for a resource contained within a parent container is all handled now within the same model.
Coverage increased (+0.07%) to 33.407% when pulling ca53cf42a0cbf96bc0c982906148209eed5c4da5 on D-01243 into b44dc8d04c3388a22d3530d8d728b9fae69a57cf on master.
|
2025-04-01T06:37:36.115750
| 2024-09-05T20:45:47
|
2508680111
|
{
"authors": [
"Lymah123",
"taniashiba"
],
"license": "Apache-2.0",
"license_source": "github-api",
"license_type": "permissive",
"provenance": "gharchive-dolma-0000.json.gz:2822",
"repo": "TBD54566975/developer.tbd.website",
"url": "https://github.com/TBD54566975/developer.tbd.website/issues/1585"
}
|
gharchive/issue
|
Change Word To Lowercase in VCs in DWNs Page
Change Word To Lowercase in VCs in DWNs Page
🚀 Goal
We want to ensure our website's documentation don't have any mistakes.
🤔 Background
This issue focuses specifically on fixing typos across our docs. Your contributions here make a difference!
🤝 How You Can Contribute
We've broken it down into specific typos for you to address. Every contribution counts!
🔑 Tasks and Acceptance Criteria
❗You must only assign yourself one task at a time to give everyone a chance to participate.❗
You may assign yourself your next task after your current task is reviewed & accepted.
Fix Typos in VCs in DWNS page
[ ] Make "From" lowercase for "Querying VC from DWN"
Make sure all tests are passing.
🌟 Resources
VCs in DWNs page
Docs, Developer Website
Getting Started
Comment ".take" on this issue to get assigned
Fork the repository and create a new branch for this task
Follow the tasks outlined above
Submit a pull request with your changes
Respond to any feedback during the review process
Questions?
If you have any questions or need clarification, please comment on this issue or join our Discord community.
Happy coding! 🎉
.take
|
2025-04-01T06:37:36.175467
| 2016-05-28T08:09:11
|
157327295
|
{
"authors": [
"THemming"
],
"license": "mit",
"license_source": "bigquery",
"license_type": "permissive",
"provenance": "gharchive-dolma-0000.json.gz:2823",
"repo": "THemming/harviewer-chrome-app",
"url": "https://github.com/THemming/harviewer-chrome-app/issues/18"
}
|
gharchive/issue
|
Add analytics permission in manifest
In preparation for collecting usage stats.
Does this also require a consent UI and a toggle option in the UI?
|
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.