[calebhwin]

Thank you! It's currently based on task lineage, exact match of task descriptions, and an optional user-provided cache_control argument that can control whether results or plans are cached.

One use-case for this is conversations: So for example if I invoke /chat/completions with [{"role": "user", "content": "Go to google.com"}] and later with [{"role": "user", "content": "Go to google.com"}, {"role": "user", "content": "Search for gorilla vs 100 human"}] then we cache the browser state from the first invocation so it can be quickly restored (or reuse the browser if not evicted).

Caching will get much more sophisticated in a future version, it's the piece we're most actively working on.