# zeta2 cli: Cache at LLM request level \(\#42371\) · gitcafe/zed

[View on GitCafe](https://git.cafe/gitcafe/zed/commit/c748b177c4345c33438b43d66546fbd499570d22)

Repository: [gitcafe/zed](https://git.cafe/gitcafe/zed)

Visibility: public

Requested revision: c748b177c4345c33438b43d66546fbd499570d22

Requested commit: c748b177c4345c33438b43d66546fbd499570d22

Commit: c748b177c4345c33438b43d66546fbd499570d22

Tree: 296e5fcfef2027193394ccc5f39797c3d4fc815e

Author: Agus Zubiaga

Committer: GitHub

## Message

```
zeta2 cli: Cache at LLM request level (#42371)

We'll now cache LLM responses at the request level (by hash of
URL+contents) for both context and prediction. This way we don't need to
worry about mistakenly using the cache when we change the prompt or its
components.

Release Notes:

- N/A

---------

Co-authored-by: Oleksiy Syvokon <oleksiy.syvokon@gmail.com>
```

## Parents

- [ddf5937899087b03893c4f1038033781e4ac96e7](https://git.cafe/gitcafe/zed/commit/ddf5937899087b03893c4f1038033781e4ac96e7?format=markdown)

[Source at this commit](https://git.cafe/gitcafe/zed/tree/c748b177c4345c33438b43d66546fbd499570d22?format=markdown)