Code

History

Commits on arm_github_runners to crates/eval/src/instance.rs20
  1. Store profile per thread (#31907)Ben Brandt committed 1 year ago709523b
  2. Pass up intent with completion requests (#31710)Marshall Bowers committed 1 year agoa23ee61
  3. Make language model deserialization more resilient (#31311)Richard Feldman committed 1 year ago00fd045
  4. Use read-only access methods for read-only entity operations (#31479)Joseph T. Lyons committed 1 year agoc208532
  5. Use `anyhow` more idiomatically (#31052)Kirill Bulatov committed 1 year ago16366cf
  6. Accept wrapped text content from LLM providers (#31048)Richard Feldman committed 1 year ago4bb04ce
  7. agent: Overwrite files more cautiously (#30649)Oleksiy Syvokon committed 1 year ago255d8f7
  8. Have read_file support images (#30435)Richard Feldman committed 1 year ago8fdf309
  9. Include `EditAgent`'s raw output when inspecting thread (#30337)Antonio Scandurra committed 1 year ago1b593f6
  10. Reuse conversation cache when streaming edits (#30245)Antonio Scandurra committed 1 year ago9f6809a
  11. agent: Handle attempts to use hallucinated tools (#29946)Oleksiy Syvokon committed 1 year ago8199664
  12. Change cloud language model provider JSON protocol to surface errors and usage information (#29830)Max Brunsfeld committed 1 year agoc3d9cde
  13. Add support for queuing status updates in cloud language model provider (#29818)Max Brunsfeld committed 1 year ago04772bf
  14. Fix eval judging missing final response (#29638)Richard Feldman committed 1 year agoc8685dc
  15. agent: Add "max mode" toggle (#29549)Marshall Bowers committed 1 year agoce93961
  16. Refactor markdown formatting utilities to avoid building intermediate strings (#29511)Michael Sloan committed 1 year ago609c528
  17. Restructure agent context (#29233)Michael Sloan committed 1 year ago17ecf94
  18. Do not log unfinished tools use that are in the middle of streaming (#29275)Oleksiy Syvokon committed 1 year agof69aeb6
  19. eval: Write JSON-serialized thread (#29271)Oleksiy Syvokon committed 1 year ago76a78b5
  20. eval: Fine-grained assertions (#29246)Agus Zubiaga committed 1 year agoce1a674