miniblog.

I certainly see the appeal of an LLM system with full context and tool use (OpenClaw), but the lethal trifecta puts me off deploying it. I do like the idea of an agent with a heartbeat though. A bunch of nice cron-style workflows can be built on top.

Further tinkering with diagnostics, following feedback! * Two lines of context above and below now. * The caret is included in the line below where possible. * Syntax highlighting of keywords. I kinda feel that smart context sizing would be better. What do you think so far?

I'm experimenting with diagnostics formatting. * I've added a left margin, showing both the file name and line numbers * I'm showing one line of context above/below the offending line. * I'm using grey for comments. What do you think? Is there anything you'd change?