You can just use it through Claude Code, so you get to keep the system prompt and tooling you are used to.

3rd party models are a drop-in replacement with `ANTHROPIC_BASE_URL` in Claude Code, something people seem to miss right now. And contrary to what Anthropic might like to have you think, you don't need Opus 4.7 to run the harness to get similar performance.

https://api-docs.deepseek.com/quick_start/agent_integrations...

Is there an easier way to manage multiple models?

Also, great example of why you don't take a terminal that requires login as your daily workhorse. It never ends well.

That was a mistake they made initially, but iirc they got rid of it after a while.

If you block internet access to Warp, it refuses to start. That's all I need to know about it.

I've been using all Kimi K2.6, gpt-5.4 and now Deepseek v4 (thought not extensively yet) in Claude Code and I can say it works much better than you'd expect. It looks like the system prompt and tools are pulling a lot of weight. Maybe the current models are good enough that you don't need them to be trained for a specific harness.

FWIW, works great in Claude Code.

https://api-docs.deepseek.com/guides/coding_agents#integrate...

This might be the opposite of staying nimble as my workflows are quite tied to Claude Code specifically, however I've been experimenting with using OpenAI models in CC and it works surprisingly well.

Added support for Kimi in https://github.com/raine/claude-code-proxy and it does appear to work surprisingly well with Claude Code, although the usage limit for the entry tier doesn't seem as generous as I'd have expected.

- Way more accurate, especially with technical jargon. Try saying JSON as part of a sentence to macOS dictation and see what comes out.

- macOS dictation mutes other sounds while it's running. This is a deal-breaker for me.

Why doesn't OpenAI introduce $100/mo plan? Surely many would switch in a heartbeat

Maybe because they don't want to lose money even faster than Anthropic is?

Is that also why they allow to use their subscriptions in OpenClaw and 3rd party harnesses?

For a container-based sandbox in tmux, see workmux and its sandboxing feature.

The added isolation does come with some friction though, which is kind of by design.

Conflicts are not a problem at all in my experience.

My setup is that I run `/merge`[1] , which will first have the agent rebase changes on base, and on conflicts, it's instructed to understand both sides before resolving, which helps it merge them cleanly. I haven't resolved conflicts manually in months and also haven't had any issues with agents resolving them incorrectly. A solved problem as far as I'm concerned.

[1]: https://workmux.raine.dev/guide/workflows#direct-merge

> it's instructed to understand both sides before resolving. This is the crux of the issue. You are delegating the resolution of conflicts to an agent, which is fine, but doesnt solve the core issue that there's no scalable way to actually do this. It is far from a solved problem lol, just because your agents havent had issues resolving them.