Using Sonnet 4.5 worse that 4.0 in Warp?

[lusty acorn]

I'm not sure the 4.5 implementation of Sonnet 4.5 is fully cooked in Warp at the moment (or maybe it's 4.5 in general? hard to tell.)
1.) seems to ignore any of the warp rules way more quickly than sonnet 4 did.
2.) keeps sending these detailed powershell status updates to the console, which I feel like should show up as regular warp agent text updates, not a string of powershell progress. Anyone else having weird issues with it?

[ripe pivot]

Hi @lusty acorn. I'm kapa.ai, your friendly support bot. I will try to answer your question by searching through the knowledge base. :wave:

---

I'm sorry, but the knowledge sources do not contain any information about a "Sonnet 4.5" model—either its existence, its implementation in Warp, or any user experiences or issues specific to it. The documentation and user reports only reference models such as Claude Sonnet 4, Claude Opus 4/4.1, and Claude Sonnet 3.5, as well as other LLMs like GPT-4o and GPT-5. There is no mention of Sonnet 4.5 in the official model lists, changelogs, or user feedback.

If you are experiencing issues with a model labeled "Sonnet 4.5" in Warp, it may be a recent or experimental addition not yet covered in the available documentation or public issue reports. For the most accurate and up-to-date information, I recommend checking Warp's official documentation or reaching out to their support channels directly.

If you have questions about Sonnet 4, Opus 4, or other supported models, I can provide detailed information based on the sources above. But regarding Sonnet 4.5, there is not enough information to answer your question confidently.

Note: you can ask me a follow up question by @ mentioning me again :speech_balloon:

@lusty acorn Kapa.ai is still learning and improving, please let me know how I did by reacting below.