szabesz

Hello @maximus Thank you for the new version. I could not upgrade to it, so I uninstalled the module instead, but I guess you are interested in the error I got after upgrading from Context 1.1.9 to the latest. I am not sure if I will try to use Context 2 or not, as currently I am into Ryan's AI modules to learn how they can aid my workflow.

You can send one that you do need to me. My niece is coming this summer too, just post it to her address first please :D

It is from 2021. I do not see any trace of the new version having replaceable battery: https://www.logitech.com/en-us/shop/p/mx-keys-s As always, companies are so proud to be green: "15.87 kg CO2e carbon footprint." Yet they want to force me to buy a brand new unit if I want a better battery. Planned obsolescence: https://en.wikipedia.org/wiki/Planned_obsolescence at its finest. So we have less CO2 and more junk. But: https://www.nasa.gov/centers-and-facilities/goddard/carbon-dioxide-fertilization-greening-earth-study-finds/ "Studies have shown that plants acclimatize, or adjust, to rising carbon dioxide concentration and the fertilization effect diminishes over time." I must believe one study, but not the other one, and they will tell me which study to believe in. OK, I get that. So they want me to believe that while nature is recovering, that’s actually bad news, because their selected studies say so, and who am I to question their selected studies? I am just a dumb IT guy, and they know everything better, since they publish a lot of papers no one reads.

That's strange, as that's what I use and I like it. The only thing I do not like about it is the battery. There is no official replacement battery, which is a shame. I ordered my first third-party replacement for it two months ago and it was performing badly right from the beginning.

Wow, it even has an Fn1 key! ;)

Pretty good prompt engineering! Why have I never thought of this? :D

Thanks for sharing! I have not yet installed Agent Tools, but will surely start using it. And since I am also a MAMP Pro user, I am glad you saved me some troubleshooting time!

FYI https://processwire.com/talk/topic/30747-using-ai-to-migrate-your-migrations-tutorial-kind-of/ https://processwire.com/talk/topic/31575-using-config-migrations-with-an-existing-project/

That reminds me of: https://www.youtube.com/watch?v=fXpVEwEhamw

I would not expect Ryan to fix the SystemNotifications module anysoon, as ProcessWire User Activity does this and more.

The hardest bit...

Sure thing. If it were possible to code a module like that, I would be the first to do it. Jokes aside, anything that helps even a little is welcome, of course. Thanks for sharing!

Which should be addressed by planting forests and most importantly, letting nature heal. https://en.wikipedia.org/wiki/Biological_carbon_fixation "The process of biological carbon fixation plays a crucial role in the global carbon cycle, as it serves as the primary mechanism for removing CO2 from the atmosphere and incorporating it into living biomass. The primary production of organic compounds allows carbon to enter the biosphere. Carbon is considered essential for life as a base element for building organic compounds. The flow of carbon from the Earth's atmosphere, oceans and lithosphere into lifeforms and then back into the air, water and soil is one of the key biogeochemical cycles (or nutrient cycles). Understanding biological carbon fixation is essential for comprehending ecosystem dynamics, climate regulation, and the sustainability of life on Earth." Destroying natural habitats is something we should have stopped doing a long time ago. But it's not too late. I think we should concentrate on letting nature heal on its own by restoring (letting it restore) as much habitat as possible. We should just let Mother Nature do what she does best, without trying to play God by always trying to fix what we have screwed up by some sort of yet another artificial method we (most of the time) come up with.

Looks like Claude/Codex is good at introducing regressions/bugs in the core, or am I mistaken?

For this, I recommend: https://buildermethods.com/prd-creator Quote: "PRD Creator is just markdown — not Claude Code-specific. If you’re using Codex, Antigravity, Cursor, or another agentic tool, download the bm-prd-creator folder from the bm-skills repo and install it as a custom skill, command, or rule per your tool’s convention. The workflow is identical." These are the actual files: https://github.com/buildermethods/bm-skills/tree/main/plugins/bm-prd-creator/skills/bm-prd-creator You may also want to watch this from the author: https://youtu.be/g6VvvS46uCM

You are right. Ok. You are violating forum rules with this one too. "modules thread" Have you missed an apostrophe perhaps? I am asking this because "module's thread" would make more sense to me. Am I missing something perhaps? Anyway, I deleted my comment above. Cheers.

Thanks @maximus! It's a pity I can't give at least 5 likes to your post :)

Hello, I have not yet used Codex, but I've been using Claude Code for three weeks, but not yet for ProcessWire projects, but I will surely use it for ProcessWire projects too. I recommend watching some good tutorials first, like: https://youtu.be/uogzSxOw4LU Next, setup the MCP servers you need, I recommend https://context7.com/ and @Peter Knight's PromptWire, and any other MCP servers Context 7 cannot help with. For connecting to systems, I recommend composio.dev Also, do not forget: https://processwire.com/modules/agent-tools/ After you have setup Claude Code in Cursor (for example), just ask Claude whenever you need info on anything. And make full backups regularly, AI can screw things up fast... ;)

Those "top bar features" are welcome, and so are the "library and inputfield" additions/changes. Thanks @Peter Knight!

I do not strive for balance. I think that's just not a reality to achieve that. Maybe if you join some monks, then you can find it, but you'll need to give up everything else then. I focus on goals, and when I achieve one, well, that is satisfying. That might sound simple, but it's not. Of course, it's hard to stay focused, and it is also hard to keep the priorities. But I try not to miss the most important: family, health/sport, work, friends (in that order, and that's the order of importance, and not the order I spend time with/on, which is a different story..., but generally, I am just trying to be flexible with time as much as I can.) And when I am feeling blue, I just need to remind myself: https://youtu.be/uAzwji5Cfmk?list=RDuAzwji5Cfmk&t=24

Since it partially solves what Lister Pro is about, we cannot expect something like this in the core. Anyway, thank you @maximus for sharing this module, I will surely try it out.

You need an M5 Mac with 128GB RAM, I think (see: https://www.youtube.com/watch?v=SmuX-Al7DUs&t=173s) I have a M4 Pro Mac Mini with 24GB RAM. I cannot run anything more demanding than Qwen3-VL-8B, as the model must be kept in memory (you don’t want to wait for a model to load, I load it before starting to work on something and unload it at shutdown). I do not use Qwen3-VL-8B for coding, instead I use GLM, Gemini subsriptions (and recently, for that given project only, the client pays for Claude subscription so that I can use it). I also like the image descriptions Qwen3-VL-8B generates. IMHO, strangely, it is better than any other LLM I’ve ever tried in this use case. My only issue with Qwen3-VL-8B was that in chat mode it spits out emojis by default all the time, which I hate, but the “NEVER use emojis!” system prompt in LM Studio solved that.

This workflow would be really powerful, indeed. Using the MCP server as a tool, the agent could use it on its own, but also the developer could ask the LLM/agent in the console, as Adrian mentions:

I would give these (and related stats, listings) high priority. (BTW, why just 10?)

@psy Thanks! Note that the link above points to /talk/topic/13598-jsonld-schema-module/?do=getNewComment Is it that by mistake, perhaps? Another note is that I find it confusing that you edit the initial post and also clear the trace of its past state(s). This way it looks like information from 2016, but it is clearly not, and the discussion following the first post also looks odd and confusing to the newcomer.