Code

History

Commits on debug-shell to crates/eval/src/instance.rs22
  1. agent: Fix issue with Anthropic thinking models (#33317)Bennet Bo Fenner committed 1 year ago7be57ba
  2. agent: Less disruptive changed file notification (#31693)Oleksiy Syvokon committed 1 year ago6df4c53
  3. Store profile per thread (#31907)Ben Brandt committed 1 year ago709523b
  4. Pass up intent with completion requests (#31710)Marshall Bowers committed 1 year agoa23ee61
  5. Make language model deserialization more resilient (#31311)Richard Feldman committed 1 year ago00fd045
  6. Use read-only access methods for read-only entity operations (#31479)Joseph T. Lyons committed 1 year agoc208532
  7. Use `anyhow` more idiomatically (#31052)Kirill Bulatov committed 1 year ago16366cf
  8. Accept wrapped text content from LLM providers (#31048)Richard Feldman committed 1 year ago4bb04ce
  9. agent: Overwrite files more cautiously (#30649)Oleksiy Syvokon committed 1 year ago255d8f7
  10. Have read_file support images (#30435)Richard Feldman committed 1 year ago8fdf309
  11. Include `EditAgent`'s raw output when inspecting thread (#30337)Antonio Scandurra committed 1 year ago1b593f6
  12. Reuse conversation cache when streaming edits (#30245)Antonio Scandurra committed 1 year ago9f6809a
  13. agent: Handle attempts to use hallucinated tools (#29946)Oleksiy Syvokon committed 1 year ago8199664
  14. Change cloud language model provider JSON protocol to surface errors and usage information (#29830)Max Brunsfeld committed 1 year agoc3d9cde
  15. Add support for queuing status updates in cloud language model provider (#29818)Max Brunsfeld committed 1 year ago04772bf
  16. Fix eval judging missing final response (#29638)Richard Feldman committed 1 year agoc8685dc
  17. agent: Add "max mode" toggle (#29549)Marshall Bowers committed 1 year agoce93961
  18. Refactor markdown formatting utilities to avoid building intermediate strings (#29511)Michael Sloan committed 1 year ago609c528
  19. Restructure agent context (#29233)Michael Sloan committed 1 year ago17ecf94
  20. Do not log unfinished tools use that are in the middle of streaming (#29275)Oleksiy Syvokon committed 1 year agof69aeb6
  21. eval: Write JSON-serialized thread (#29271)Oleksiy Syvokon committed 1 year ago76a78b5
  22. eval: Fine-grained assertions (#29246)Agus Zubiaga committed 1 year agoce1a674