Thanks to being unemployed, the last few months I've been experimenting a lot with coding agents, harnesses and most importantly, the workflows around them. Currently I'm refining what I think works best for me, which I'd call something like "issues/PR based LLM workflow", powered mainly by this action I'm building on top of the [Pi coding agent](https://pi.dev) SDK:... - Source: Hacker News / 1 day ago

If you haven't yet you should give a chance to https://pi.dev I've been using it exclusively (and extending it, see https://a.l3x.in/ai) for months with mainly GLM-4.7 then 5.1 and now 5.2 and I could hardly be any happier. I'm still working on a "Github/Forgejo first" based workflow but also quite happy with it already, basically most of my sessions run as a ci/cd job (triggered by "/pi" comments) and generate... - Source: Hacker News / 3 days ago

I like to use Pi (https://pi.dev/), and I recently got it to make an approval extension for itself. It has a lot of documentation built-in for the agent to modify the behavior of the app. I got it to display all proposed file change diffs and bash commands and made it so I can either approve the action or deny it with a message for it. It was surprisingly easy to tell it to modify things things the diff viewing... - Source: Hacker News / 3 days ago

For open source agents, like https://pi.dev, it is as easy as asking it to create a plugin to stop the session or ask for permission whenever the LLM is trying to execute a commit command. Then you add one line in AGENTS.md stating the LLM should never commit, push or perform any write git operation without explicit being asked to. So in the very rare case that the LLM bypass you instruction, you catch it... - Source: Hacker News / 4 days ago

Https://pi.dev specifically prides itself on having many extensions hook points. Is that one you've looked at? If so, it might be something they'd be willing to add a hook for if you open an issue. - Source: Hacker News / 10 days ago

Https://opencode.ai/ OpenCode was the first agent harness I used, and I have always like it. You can configure a wide variety of providers, but it's open source and has a number of core contributors. The other opinionated option is Pi (the Pi agent harness). This is a great lightweight option and also supports a number of providers. You can also use local model servers. - Source: Hacker News / 3 days ago

OpenCode with GLM 5.2 wrote custom Emacs Lisp to pinpoint within the file where the missing or extra bracket could be. It rewrote the custom code to check various parts of the file. Each of those is a tool use and many, many tokens burned. The next step is to turn those custom scripts written by the AI agent into a tool to speed up the process, or a skill that shows how to use other tools to speed up the process. - Source: dev.to / 6 days ago

I gave GLM-4.5-Air (106B, open weights) 12 coding tasks through opencode on my RTX 3090. It scored 0% — never edited a single file. - Source: dev.to / 7 days ago

Set up your stations. I work in two Ghostty terminals. The left side is for planning and viewing, the right for synchronous agents running through OpenCode. - Source: dev.to / 15 days ago

If you want to try it yourself: grab OpenCode, point it at OpenRouter, select GLM 5.2, and give it a real task instead of a benchmark. The z.ai docs have the rest of the details. - Source: dev.to / 16 days ago