Skip to content

Cache LLM requests for cheaper re-runs #132

@alistairjcbrown

Description

@alistairjcbrown

Let quick fixes land and be run more frequently by caching LLM responses. We'll need to make sure the cache key is related to the content of the prompt so that it gets a cache miss as expected whenever it changes

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type

    Projects

    Status

    In Progress

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions