Ask your agent to update the config!
@steipete
-
Codex Harness and Verifiable Stop Conditions for Model Control
By
–
At least if you use codex harness that should not be needed much anymore. If you provide a verify-able stop condition the model is quite relentless
-
Solving the lazy butt problem effectively
By
–
That’s exactly the lazy butt thing I’m trying to solve 🙂
-
Hooks enable trivial plugin development for custom setups
By
–
We have hooks, would be quite trivial to write a plugin that does this in your setup. If it’s useful, report back!
-
Call for Testing One-Line Code Change Before Default Rollout
By
–
It’s a one-liner in code – I need folks testing this and posting reports if that helps, before we change defaults or enable it for everyone. Please do and report back!
-
Submit PR or Issue Instead of Direct Pings
By
–
send a PR or at least writen an issue, I get far too many pings here
-
Making GPT More Agentic: Configuration Options
By
–
Try one of the options in my tweetstorm if you feel GPT is not agentic enough in the default settings.
-
Harnesses as Plugins: Custom SDK Integration Now Possible
By
–
Harnesses can now been plugins – meaning it'd be trivial to replace the default Pi harness with e.g. Anthropic’s SDK or another custom one. This won't magically allow Claude subscription, but it's useful to compare different implementations. Using codex as harness will likely
-
Native Codex as OpenClaw Harness Configuration and Thread Management
By
–
2) Native Codex as the OpenClaw harness: plugins.entries.codex.enabled = true
agents.defaults.model = "codex/gpt-5.4"
agents.defaults.embeddedHarness = { runtime: "codex", fallback: "none" } Codex owns threads, resume, compaction, app-server execution. https://
docs.openclaw.ai/plugins/codex-
harness
…