Skip to content

Agent Cache v0.7.0

Choose a tag to compare

View all tags
@KIvanow KIvanow released this 11 Jun 12:17
agent-cache-v0.7.0
461a522
This commit was signed with the committer’s verified signature.
KIvanow Kristiyan Ivanov
GPG key ID: 4BB27D5B662BC86B
Verified
Learn about vigilant mode.

Fixed

  • Vercel AI SDK adapter: tool definitions now included in cache key. Requests with identical messages but different tools no longer share cached responses. seed, stopSequences, responseFormat, and toolChoice are also part of the key now.
  • LlamaIndex adapter: tool definitions now included in cache key when tools is passed to prepareParams(). Only serializable metadata is used; the call closure is never serialized.

Changed

  • Cache keys changed for tool-using requests on Vercel and LlamaIndex adapters. Existing cached entries for those requests will be a one-time miss after upgrade — intended, as the prior entries were not safe to reuse across differing tool sets.
  • LlamaIndex prepareParams() now accepts a tools option. Omitting it falls back to messages-only keying (prior behavior).

Known limitations

  • LangChain adapter: tool-schema drift is not reflected in the cache key — the framework's BaseCache interface only exposes (prompt, llm_string). Documented limitation, unchanged.

Full Changelog: agent-cache-v0.6.1...agent-cache-v0.7.0

Full Changelog: v0.23.0...agent-cache-v0.7.0

Assets 2
Loading