HISE Transformation to the new age

[Lindon]

OK here we go:

Easy-peasy one-shot Claude issues (perhaps):

https://github.com/christophhart/HISE/issues/869
https://github.com/christophhart/HISE/issues/739
https://github.com/christophhart/HISE/issues/762
https://github.com/christophhart/HISE/issues/761
https://github.com/christophhart/HISE/issues/625
https://github.com/christophhart/HISE/issues/863
https://github.com/christophhart/HISE/issues/769

Woah, smart brain of good looking German man(who like musical theatre) required:

https://forum.hise.audio/topic/14165/latest-version-of-hise-breaks-existing-presets/40?_=1771154413502
==== damn it I cant find the github issue number....possibly because there isnt one - so one of us is (to quote the Sex Pistols) a "Lazy Sod"...sorry

https://github.com/christophhart/HISE/issues/868
https://github.com/christophhart/HISE/issues/867
https://github.com/christophhart/HISE/issues/782
https://github.com/christophhart/HISE/issues/713

[Christoph Hart]

@Lindon yup good stuff, thanks. I'll try to explain Claude our plan, then give it this list of issues and let it categorize it into 3a or 3b without telling it your assessment. Then I'll do an assessment myself and we have three different evaluations per issue which should be a good enough "dataset" to distill a solution for step 2.

@David-Healey or anyone else reading this, you could also chime in with other findings of the bottomless pit of open issues from GH, the more assessments we have the better, it also expands the first column of the training data from Lindon's brain to a more generic "HISE developer" perspective - no pun intended Lindon :).

In the end we can also compare your assessments against mine and the AI suggestions and create a leaderboard in the who-can-take-over-if-I-get-hit-by-a-bus-category and a "who is actually a LLM disguised in a humanoid lifeform"-category...

[dannytaurus]

@Christoph-Hart When I fixed those bugs, and added small features or enhancements, I went for stuff that [1] had small surface area, [2] I was familiar with the feature, and [3] had been mentioned recently.

Bonus if there was a reproducible example included in the issue or a forum post.

It also helped that a lot of them were useful for my current work.

If something started to get complex or far-reaching I backed off and moved on to another issue. If I recall, some of the ScriptNode bugs were like this.

[dannytaurus]

@David-Healey said in HISE Transformation to the new age:

It's about time we got back to the master I think.

Agreed!

[Lindon]

@Christoph-Hart said in HISE Transformation to the new age:

"who is actually a LLM disguised in a humanoid lifeform"-category

oh I hope Im this.....!!

[Christoph Hart]

Alright, I just found out a feature of the CLI I'm using - whenever I said I use Claude Code I was lying. In fact I was using Opencode, which is the same thing but not tied to a certain model provider. Doesn't matter in the long run, but I just found a feature that we can somehow tie into that entire process: you can easily share the entire conversation history with the agent.

Eg, here's an example session of one of the earlier feature requests I added to HISE:

https://opncd.ai/share/aKO5yUQn

I can imagine that adding this link to a PR will help me track down the steps much better than just reading the final file changes, so for anything that isn't as trivial as this example this might be a very helpful piece of knowledge.

@dannytaurus I haven't touched Claude Code, but is there a similar feature over there in proprietary land?

[David Healey]

@Christoph-Hart said in HISE Transformation to the new age:

In fact I was using Opencode,

Which model are you using? I tried to use Claude with it but it seems anthropic are blocking it.

[Christoph Hart]

@David-Healey switched between all of the anthropic ones. I started using them through OpenRouter with the API key, but I blew through about 80USD worth of tokens within 2-3 hours, then went my way up the Claude subscription ladder up to the 200USD Claude Max subscription. It hasn't complained once about usage through a 3rd party client, but I also saw the headlines a few weeks back so maybe they just rolled this back to prevent backlash.

[David Healey]

@Christoph-Hart I get this message whenever I add a prompt

I'll check their github see if there is an issue there.

[Christoph Hart]

@David-Healey have you authorized opencode? Type opencode auth login, then select anthropic (there are two options, one for regular API usage and one for the plans), pick the one for the plan, paste the link in the browser, authorize it with your Claude subscription account, then paste back the stuff back into the terminal.

[David Healey]

@Christoph-Hart Yeah I've done that, I did it through the GUI interface.

[Christoph Hart]

@David-Healey have you selected the right model? The claude models show up both through the Zen and Claude provider so if you picked the Zen one it tries to spend non-existent API token money.

[David Healey]

@Christoph-Hart Aha you're totally correct, I didn't notice the little Z icon next to the model. All working now, thanks!

[David Healey]

This is slightly addictive. I'm getting Claude to allow us to style the MIDI Learn panel using LAF which is something I've wanted for ages.

-- Yes this design is hideous, I'm just testing it

[DanH]

@David-Healey I've set up OpenCode on my mac but the CLI version. Was advised that the Hise codebase is so massive that the desktop app would struggle to load the files. Simple tasks are taking a while via terminal / gpt 4. Can I check what your setup is pls?

[dannytaurus]

@David-Healey

[Lindon]

@dannytaurus said in HISE Transformation to the new age:

@David-Healey

damn it - there goes my T-shirt monopoly....

[David Healey]

@DanH said in HISE Transformation to the new age:

Can I check what your setup is pls?

I'm using Claude Code in the web, I have also set it up in Open Code but haven't had time to investigate the workflow there yet.

In the browser I just point Claude to my HISE github repo and select the branch I'm using. Then I tell it what I want and it creates a new branch for its changes.

[dannytaurus]

@DanH I use Claude Opus and Sonnet in the Cursor IDE (desktop app) with he whole HISE repo and it work great.

Cursor is good about sending the right amount of context and caching where it can.

[Christoph Hart]

Alright guys, I've been working on the automated workflow for handling issues. The idea is to give you a fixed set of guidelines that can classify issues / PRs into "contributor fixable" and "requires maintainer review".

Here's a nice summary of the proposed event flow:

https://gist.github.com/christoph-hart/394f9db01f97864e4c6ecd886c5e18ca

This will become part of the MCP server so if you're running a AI agent, you can simply launch the /contribute tool and it will guide you through the process. On the other side of the process it's me sitting around getting a nicely formatted PR that I can review quick and merge or reject with a comment or close altoghether.

I've tested this with a few real issues / PRs:

• one that I created myself, let the agent analyse and fix and then automerge: https://github.com/christophhart/HISE/pull/880 - the entire process from bug analysis to merge is handled by the MCP tool
• one that Dave created yesterday which went through the analysis without flagging concerns and thus got merged after a quick glance over the AI assessment: https://github.com/christophhart/HISE/pull/879
• one from David that the analysis (correctly) flagged as big fat no because it does affect the handling of script files in general: https://github.com/christophhart/HISE/pull/871

The response for the last one feels super icky because the AI starts talking to David like as if it would be a human, but I think if we iterate on this process it should streamline this entire procedure and vastly increase my PR merge speed.