0x4007 commented 4 months ago

Overview

Similar to an old proposal for /ask.
The goal is to ask a context-aware question.
Feed the entire conversation context into ChatGPT4o.
Include any linked pull requests or issues and their entire conversation context.
Prioritize the issue specification to set the topic, then add comments.
Simplify comments by showing the username prepending the comment.
Divide conversations in the prompt using headers and footers.

Prompt Template

=== Start Project Specification === ubiquibot/plugins-wishlist #[Issue Number] ===

[GitHub issue specification body]

=== End Project Specification ===

=== Start Issue Conversation === ubiquibot/plugins-wishlist #[Issue Number] ===

[Comment ID] [Username]: [Comment]
[Comment ID] [Username]: [Comment]
...

=== End Issue Conversation ===

=== Start Linked Pull Request Conversation === ubiquibot/plugins-wishlist #[Pull Request Number] ===

[Comment ID] [Username]: [Comment]
[Comment ID] [Username]: [Comment]
...

=== End Linked Pull Request Conversation ===

=== Start Linked Pull Request Code Diff === ubiquibot/plugins-wishlist #[Pull Request Number] ===

- [Old Code]
+ [New Code]

=== End Linked Pull Request Code Diff ===

Example

=== Start Project Specification === ubiquibot/plugins-wishlist #29 ===

Add a new feature to support XYZ plugins.

=== End Project Specification ===

=== Start Issue Conversation === ubiquibot/plugins-wishlist #29 ===

2222517181 0x4007: We should consider adding support for plugins to enhance functionality.
2222517182 rndquu: I agree, this would be beneficial.
2222517184 gentlementlegen: Do we have any specific plugins in mind?

=== End Issue Conversation ===

=== Start Linked Pull Request Conversation === ubiquibot/plugins-wishlist #30 ===

2222517187 devuser1: Implemented basic support for plugins.
2222517189 devuser2: This looks good, but needs more testing.

=== End Linked Pull Request Conversation ===

=== Start Linked Pull Request Code Diff === ubiquibot/plugins-wishlist #30 ===

- // insert log
+ console.log("test");

=== End Linked Pull Request Code Diff ===

Notes

Include the org/repo/issue to help ChatGPT understand references to other issues/pulls.
Annotate comments with their IDs so that ChatGPT can produce outputs with links to other comments for references.

Keyrxng commented 4 months ago

Is this to replace /ask or is this a new plugin entirely @0x4007?

I refactored the old /ask plugin to V2 standards (slightly outdated again now). Can I refactor it to meet this spec or would you prefer another standalone?

0x4007 commented 4 months ago

Seems easier to redo we have a ton of new functions to borrow like how we authenticate and collect the comment data is totally different from the old version and new version.

Keyrxng commented 4 months ago

/start

ubiquibot[bot] commented 4 months ago




Deadline Sat, Jul 13, 10:35 AM UTC

Registered Wallet
0xAe5D1F192013db889b1e2115A370aB133f359765

Tips:

Use /wallet 0x0000...0000 if you want to update your registered payment wallet address.
Be sure to open a draft pull request as soon as possible to communicate updates on your progress.
Be sure to provide timely updates to us when requested, or you will be automatically unassigned from the task.

gentlementlegen commented 2 months ago

It seems that the user-activity-watcher ignores when a user opened a pull-request against an issue and considers there is no activity.

0x4007 commented 2 months ago

It seems that the user-activity-watcher ignores when a user opened a pull-request against an issue and considers there is no activity.

It's been two months since the last activity on that pull so it seems fine, except that it should've closed the pull

gentlementlegen commented 2 months ago

There was an issue opened for this case: https://github.com/ubiquibot/command-start-stop/issues/27

ubiquity-os-beta[bot] commented 3 weeks ago

[!NOTE] This output has been truncated due to the comment length limit.

[ 0.4125 WXDAI ]
@Keyrxng

Contributions Overview

View	Contribution	Count	Reward
Issue	Comment	1	0.4125
Review	Comment	29	0

[ 65.2335 WXDAI ]
@0x4007

Contributions Overview

View	Contribution	Count	Reward
Issue	Specification	1	46.53
Issue	Comment	2	2.3935
Review	Comment	32	16.31

[ 16.895 WXDAI ]
@gentlementlegen

Contributions Overview

View	Contribution	Count	Reward
Issue	Comment	2	1.819
Review	Comment	12	15.076

[ 0.462 WXDAI ]
@sshivaditya2019

Contributions Overview

View	Contribution	Count	Reward
Review	Comment	1	0.462

Keyrxng commented 3 weeks ago

@0x4007 Do you think you could assign me and re-gen the reward for implementing https://github.com/ubiquity-os-marketplace/command-ask/pull/1 please? idk if mentlegen can but I saw you had to bump rndquu' access earlier too.

So all permits generated since the 12 October are not claimable by contributors (and probably should be regenerated on demand once a new version of ubiquity-os/permit-generation is released).

actually never mind it makes sense to wait, sorry.

ubiquity-os-beta[bot] commented 3 weeks ago

@Keyrxng the deadline is at Wed, Oct 23, 7:35 AM UTC

ubiquity-os-beta[bot] commented 3 weeks ago

[ 200 WXDAI ]
@Keyrxng

Contributions Overview

View	Contribution	Count	Reward
Issue	Task	1	200
Issue	Comment	2	0
Review	Comment	29	0

Conversation Incentives

Comment	Formatting	Relevance
Is this to replace `/ask` or is this a new plugin entire…	0 content: content: p: score: 0 elementCount: 2 result: 0 regex: wordCount: 38 wordValue: 0 result: 0	0.8
@0x4007 Do you think you could assign me and re-gen the reward f…	0 content: content: p: score: 0 elementCount: 2 result: 0 regex: wordCount: 50 wordValue: 0 result: 0	0.7
Resolves https://github.com/ubiquibot/plugins-wishlist/issues/29…	12.5 content: content: p: score: 0 elementCount: 13 ul: score: 1 elementCount: 2 li: score: 0.5 elementCount: 9 a: score: 5 elementCount: 1 ol: score: 1 elementCount: 1 result: 12.5 regex: wordCount: 141 wordValue: 0 result: 0	0.8
Without it seeing it's own answers it may try to re-answer a pre…	0 content: content: p: score: 0 elementCount: 1 result: 0 regex: wordCount: 41 wordValue: 0 result: 0	0.7
Truthfully me either.The kernel does match using the regex pro…	0 content: content: p: score: 0 elementCount: 2 result: 0 regex: wordCount: 43 wordValue: 0 result: 0	0.6
While we have a 128k window I don't think it's going to be as ef…	0 content: content: p: score: 0 elementCount: 4 result: 0 regex: wordCount: 138 wordValue: 0 result: 0	0.9
I'm of a different mindset especially when linking to known 3rd …	0 content: content: p: score: 0 elementCount: 2 result: 0 regex: wordCount: 77 wordValue: 0 result: 0	0.5
Wasn't it the case originally that the kernel was matching the c…	0 content: content: p: score: 0 elementCount: 2 result: 0 regex: wordCount: 78 wordValue: 0 result: 0	0.7
Are you sure? In order to 'disable' they'd need to remove/commen…	0 content: content: p: score: 0 elementCount: 2 result: 0 regex: wordCount: 48 wordValue: 0 result: 0	0.6
just above it we return early if `!isPull` and we know i…	0 content: content: p: score: 0 elementCount: 1 result: 0 regex: wordCount: 23 wordValue: 0 result: 0	0.4
the `jest` import from `@jest/globals` isn't the…	0 content: content: p: score: 0 elementCount: 1 result: 0 regex: wordCount: 15 wordValue: 0 result: 0	0.5
Yeah it just means casting `issue_number` and `pull_…	0 content: content: p: score: 0 elementCount: 1 result: 0 regex: wordCount: 6 wordValue: 0 result: 0	0.4
see [this](https://github.com/ubiquity-os-marketplace/command-as…	10 content: content: p: score: 0 elementCount: 1 a: score: 5 elementCount: 2 result: 10 regex: wordCount: 31 wordValue: 0 result: 0	0.3
`@UbiquityOS ...` or `@ubiquityos ...`. Partner …	0 content: content: p: score: 0 elementCount: 1 result: 0 regex: wordCount: 21 wordValue: 0 result: 0	0.3
I caught those changes but thanks for the heads up	0 content: content: p: score: 0 elementCount: 1 result: 0 regex: wordCount: 10 wordValue: 0 result: 0	0.2
I referenced [conversation rewards](https://github.com/ubiquity-…	5 content: content: p: score: 0 elementCount: 2 a: score: 5 elementCount: 1 result: 5 regex: wordCount: 30 wordValue: 0 result: 0	0.3
It's a feature not a problem and wasn't it agreed we'd standardi…	0 content: content: p: score: 0 elementCount: 1 result: 0 regex: wordCount: 45 wordValue: 0 result: 0	0.4
I did not, I'll extract a 50k+ token prompt and I'll do some tes…	0 content: content: p: score: 0 elementCount: 1 result: 0 regex: wordCount: 21 wordValue: 0 result: 0	0.5
https://github.com/ubiquity-os-marketplace/command-ask/pull/1#di…	0 content: content: p: score: 0 elementCount: 2 result: 0 regex: wordCount: 44 wordValue: 0 result: 0	0.4
https://github.com/ubiquity-os-marketplace/automated-merging/pul…	0 content: content: p: score: 0 elementCount: 5 result: 0 regex: wordCount: 99 wordValue: 0 result: 0	0.4
https://github.com/ubiquity-os-marketplace/disqualifier/pull/15#…	0 content: content: p: score: 0 elementCount: 1 result: 0 regex: wordCount: 51 wordValue: 0 result: 0	0.3
I'll gather fresh QA tomorrow	0 content: content: p: score: 0 elementCount: 1 result: 0 regex: wordCount: 6 wordValue: 0 result: 0	0.1
@0x4007 fresh QA https://github.com/ubq-testing/bot-ai/issues/…	0 content: content: p: score: 0 elementCount: 4 result: 0 regex: wordCount: 78 wordValue: 0 result: 0	0.3
Shouldn't we rebrand this repo as I think it'll be doing more th…	2 content: content: p: score: 0 elementCount: 4 ul: score: 1 elementCount: 1 li: score: 0.5 elementCount: 2 result: 2 regex: wordCount: 107 wordValue: 0 result: 0	0.5
What are we calling this so I can update the references in `…	1.5 content: content: p: score: 0 elementCount: 2 ul: score: 1 elementCount: 1 li: score: 0.5 elementCount: 1 result: 1.5 regex: wordCount: 25 wordValue: 0 result: 0	0.4
o1 in my opinion is too slow compared to 4o, I'd prefer to use i…	0 content: content: p: score: 0 elementCount: 3 result: 0 regex: wordCount: 76 wordValue: 0 result: 0	0.7
Typically slash command type plugins have a `commands` e…	2 content: content: p: score: 0 elementCount: 3 ul: score: 1 elementCount: 1 li: score: 0.5 elementCount: 2 result: 2 regex: wordCount: 131 wordValue: 0 result: 0	0.6
I moved `UBIQUITY_OS_APP_SLUG` into `.env` so th…	0 content: content: p: score: 0 elementCount: 1 result: 0 regex: wordCount: 42 wordValue: 0 result: 0	0.7
Some recent additional QA that was built on top of this plugin:…	0 content: content: p: score: 0 elementCount: 3 result: 0 regex: wordCount: 69 wordValue: 0 result: 0	0.5
This PR should be merged separate from your feature. If required…	0 content: content: p: score: 0 elementCount: 2 result: 0 regex: wordCount: 31 wordValue: 0 result: 0	0.3
Realize I never pushed the branch to my repo which facilitated t…	0 content: content: p: score: 0 elementCount: 4 result: 0 regex: wordCount: 52 wordValue: 0 result: 0	0.2

[ 66.566 WXDAI ]
@0x4007

Contributions Overview

View	Contribution	Count	Reward
Issue	Specification	1	46.53
Issue	Comment	2	2.753
Review	Comment	32	17.283

Conversation Incentives

Comment	Formatting	Relevance	Reward
# Overview- Similar to an old proposal for `/ask`.- …	15.51 content: content: h1: score: 1 elementCount: 4 ul: score: 1 elementCount: 2 li: score: 0.5 elementCount: 9 p: score: 0 elementCount: 25 result: 10.5 regex: wordCount: 100 wordValue: 0.1 result: 5.01	1	46.53
Seems easier to redo we have a ton of new functions to borrow li…	1.9 content: content: p: score: 0 elementCount: 1 result: 0 regex: wordCount: 32 wordValue: 0.1 result: 1.9	0.9	1.71
It's been two months since the last activity on that pull so it …	1.49 content: content: p: score: 0 elementCount: 1 result: 0 regex: wordCount: 24 wordValue: 0.1 result: 1.49	0.7	1.043
```suggestionname: "command-gpt"```	0 content: content: {} result: 0 regex: wordCount: 0 wordValue: 0.1 result: 0	0.8	0
Definitely just ignore all bot comments as we do in conversation…	0.83 content: content: p: score: 0 elementCount: 1 result: 0 regex: wordCount: 12 wordValue: 0.1 result: 0.83	0.5	0.415
Will this be a problem? It is not clear to me if the kernel will…	1.33 content: content: p: score: 0 elementCount: 1 result: 0 regex: wordCount: 21 wordValue: 0.1 result: 1.33	0.4	0.532
Shouldn't this be fully removed instead of `never`?	0.59 content: content: p: score: 0 elementCount: 1 result: 0 regex: wordCount: 8 wordValue: 0.1 result: 0.59	0.6	0.354
Use a `string[]` as the buffer and `.join("\n")`…	0.88 content: content: p: score: 0 elementCount: 1 result: 0 regex: wordCount: 13 wordValue: 0.1 result: 0.88	0.7	0.616
It would be useful context to explain the purpose of the plugin,…	1.85 content: content: p: score: 0 elementCount: 1 result: 0 regex: wordCount: 31 wordValue: 0.1 result: 1.85	0.9	1.665
Why not all? Context length is not a problem anymore.	0.71 content: content: p: score: 0 elementCount: 1 result: 0 regex: wordCount: 10 wordValue: 0.1 result: 0.71	0.7	0.497
I think that recursion is not a problem due to generous context …	1 content: content: p: score: 0 elementCount: 1 result: 0 regex: wordCount: 15 wordValue: 0.1 result: 1	0.7	0.7
Just be sure to label the section with the org/repo name and Cha…	1.33 content: content: p: score: 0 elementCount: 1 result: 0 regex: wordCount: 21 wordValue: 0.1 result: 1.33	0.8	1.064
I prefer to exclude for now.	0.46 content: content: p: score: 0 elementCount: 1 result: 0 regex: wordCount: 6 wordValue: 0.1 result: 0.46	0.2	0.092
@gentlementlegen might know.	0.25 content: content: p: score: 0 elementCount: 1 result: 0 regex: wordCount: 3 wordValue: 0.1 result: 0.25	0.6	0.15
I prefer to try utilizing the most amount of context. We can mak…	1.06 content: content: p: score: 0 elementCount: 1 result: 0 regex: wordCount: 16 wordValue: 0.1 result: 1.06	0.6	0.636
I prefer maximizing signal to noise in the context of human comm…	2.25 content: content: p: score: 0 elementCount: 1 result: 0 regex: wordCount: 39 wordValue: 0.1 result: 2.25	0.7	1.575
`enabled` seems like a pointless config. Please remove t…	0.59 content: content: p: score: 0 elementCount: 1 result: 0 regex: wordCount: 8 wordValue: 0.1 result: 0.59	0.4	0.236
If it is not a pull shouldn't this revert or throw? Doesn't make…	1.54 content: content: p: score: 0 elementCount: 1 result: 0 regex: wordCount: 25 wordValue: 0.1 result: 1.54	0.5	0.77
You can recycle strings with a const in the beginning of this fi…	0.88 content: content: p: score: 0 elementCount: 1 result: 0 regex: wordCount: 13 wordValue: 0.1 result: 0.88	0.3	0.264
Why? Can't you just write the code to be in line with our styles?	1 content: content: p: score: 0 elementCount: 1 result: 0 regex: wordCount: 15 wordValue: 0.1 result: 1	0.2	0.2
```suggestionhttp.get("https://api.github.com/or…	0.71 content: content: p: score: 0 elementCount: 1 result: 0 regex: wordCount: 10 wordValue: 0.1 result: 0.71	0.4	0.284
Why not just use the correct object? Why cast as `any`?	0.71 content: content: p: score: 0 elementCount: 1 result: 0 regex: wordCount: 10 wordValue: 0.1 result: 0.71	0.3	0.213
```suggestioncontent: `You are a Git…	0.18 content: content: p: score: 0 elementCount: 1 result: 0 regex: wordCount: 2 wordValue: 0.1 result: 0.18	0.7	0.126
It's more natural to use it this way	0.65 content: content: p: score: 0 elementCount: 1 result: 0 regex: wordCount: 9 wordValue: 0.1 result: 0.65	0.5	0.325
Why don't you downgrade to 1.22.21 so you don't have this proble…	1.11 content: content: p: score: 0 elementCount: 1 result: 0 regex: wordCount: 17 wordValue: 0.1 result: 1.11	0.3	0.333
Did you test using the openai playground for optimizing the prom…	1.22 content: content: p: score: 0 elementCount: 1 result: 0 regex: wordCount: 19 wordValue: 0.1 result: 1.22	0.6	0.732
Empty string always seems wrong.	0.39 content: content: p: score: 0 elementCount: 1 result: 0 regex: wordCount: 5 wordValue: 0.1 result: 0.39	0.5	0.195
No it's not a problem for anybody except your yarn	0.77 content: content: p: score: 0 elementCount: 1 result: 0 regex: wordCount: 11 wordValue: 0.1 result: 0.77	0.4	0.308
I never agreed	0.25 content: content: p: score: 0 elementCount: 1 result: 0 regex: wordCount: 3 wordValue: 0.1 result: 0.25	0.3	0.075
Curious to see examples.	0.32 content: content: p: score: 0 elementCount: 1 result: 0 regex: wordCount: 4 wordValue: 0.1 result: 0.32	0.1	0.032
Maybe let's test in production but let's make it reply to @Ubiqu…	4.25 content: content: p: score: 0 elementCount: 1 ol: score: 1 elementCount: 1 li: score: 0.5 elementCount: 3 result: 2.5 regex: wordCount: 29 wordValue: 0.1 result: 1.75	0.4	3.2
Merge or delete this repo? @Keyrxng	0.46 content: content: p: score: 0 elementCount: 1 result: 0 regex: wordCount: 6 wordValue: 0.1 result: 0.46	0.2	0.092
Sure we can rename later	0.39 content: content: p: score: 0 elementCount: 1 result: 0 regex: wordCount: 5 wordValue: 0.1 result: 0.39	0.2	0.078
`command-ask` is fine for now. Your QA makes it look sta…	3.06 content: content: p: score: 0 elementCount: 3 hr: score: 0 elementCount: 1 result: 0 regex: wordCount: 56 wordValue: 0.1 result: 3.06	0.4	1.224
I think it's fine. A comment responding ten seconds later isn't …	1 content: content: p: score: 0 elementCount: 1 result: 0 regex: wordCount: 15 wordValue: 0.1 result: 1	0.3	0.3

[ 14.379 WXDAI ]
@gentlementlegen

Contributions Overview

View	Contribution	Count	Reward
Issue	Comment	2	1.331
Review	Comment	12	13.048

Conversation Incentives

Comment	Formatting	Relevance	Reward
It seems that the `user-activity-watcher` ignores when a…	1.33 content: content: p: score: 0 elementCount: 1 result: 0 regex: wordCount: 21 wordValue: 0.1 result: 1.33	0.5	0.665
There was an issue opened for this case: https://github.com/ubiq…	1.11 content: content: p: score: 0 elementCount: 1 result: 0 regex: wordCount: 17 wordValue: 0.1 result: 1.11	0.6	0.666
Would be nice to be able to configure the ChatGpt endpoint and m…	1.33 content: content: p: score: 0 elementCount: 1 result: 0 regex: wordCount: 21 wordValue: 0.1 result: 1.33	0.4	0.532
I think the kernel will have to be changed because currently plu…	4.06 content: content: p: score: 0 elementCount: 3 result: 0 regex: wordCount: 78 wordValue: 0.1 result: 4.06	0.8	3.248
Related PR for the fix is [here](https://github.com/ubiquity/ubi…	5.52 content: content: p: score: 0 elementCount: 1 a: score: 5 elementCount: 1 result: 5 regex: wordCount: 7 wordValue: 0.1 result: 0.52	0.5	5.26
Only `.dev.vars.example` is needed isn't it?	0.46 content: content: p: score: 0 elementCount: 1 result: 0 regex: wordCount: 6 wordValue: 0.1 result: 0.46	0.2	0.092
I made little changes on `workflow-delete` and `work…	1.17 content: content: p: score: 0 elementCount: 1 result: 0 regex: wordCount: 18 wordValue: 0.1 result: 1.17	0.1	0.117
It is missing the command definition, how can it run?	0.71 content: content: p: score: 0 elementCount: 1 result: 0 regex: wordCount: 10 wordValue: 0.1 result: 0.71	0.7	0.497
Shouldn't this be handle when we decode the env?	0.71 content: content: p: score: 0 elementCount: 1 result: 0 regex: wordCount: 10 wordValue: 0.1 result: 0.71	0.6	0.426
Should probably be camelCase	0.32 content: content: p: score: 0 elementCount: 1 result: 0 regex: wordCount: 4 wordValue: 0.1 result: 0.32	0.4	0.128
So how is that plugin used? I thought it would be something like…	0.88 content: content: p: score: 0 elementCount: 1 result: 0 regex: wordCount: 13 wordValue: 0.1 result: 0.88	0.3	0.264
I see. Any reason to do it that way instead of a command?	0.88 content: content: p: score: 0 elementCount: 1 result: 0 regex: wordCount: 13 wordValue: 0.1 result: 0.88	0.3	0.264
Do we need optional with the defaults? Also be careful not sure …	1.9 content: content: p: score: 0 elementCount: 1 result: 0 regex: wordCount: 32 wordValue: 0.1 result: 1.9	0.5	0.95
Because a check is done https://github.com/ubiquity-os-marketpla…	2.54 content: content: p: score: 0 elementCount: 2 result: 0 regex: wordCount: 45 wordValue: 0.1 result: 2.54	0.5	1.27

[ 0.77 WXDAI ]
@sshivaditya2019

Contributions Overview

View	Contribution	Count	Reward
Review	Comment	1	0.77

Conversation Incentives

Comment	Formatting	Relevance	Reward
@Keyrxng I think it would be a good idea for me to continue with…	1.54 content: content: p: score: 0 elementCount: 2 result: 0 regex: wordCount: 25 wordValue: 0.1 result: 1.54	0.5	0.77

Deadline	Sat, Jul 13, 10:35 AM UTC
Registered Wallet	0xAe5D1F192013db889b1e2115A370aB133f359765

ubiquity-os / plugins-wishlist

`/gpt` ask a context aware question #29

Overview

Prompt Template

Example

Notes

Tips:

@Keyrxng

Contributions Overview

@0x4007

Contributions Overview

@gentlementlegen

Contributions Overview

@sshivaditya2019

Contributions Overview

@Keyrxng

Contributions Overview

Conversation Incentives

@0x4007

Contributions Overview

Conversation Incentives

@gentlementlegen

Contributions Overview

Conversation Incentives

@sshivaditya2019

Contributions Overview

Conversation Incentives