Code

History

Commits on diff-perf-experiments to crates/eval/src/instance.rs35+
  1. eval: Port to agent2 (#40704)Bennet Fenner committed 1 year agoc60343a
  2. Remove agent1 code (#40495)Bennet Fenner committed 1 year ago3f13191
  3. Use `into_owned` over `to_string` for `Cow<str>` (#39024)Lukas Wirth committed 1 year ago72948e1
  4. Represent relative paths using a dedicated, separator-agnostic type (#38744)Max Brunsfeld committed 1 year ago03f9cf4
  5. Fix `clippy::println_empty_string`, `clippy::while_let_on_iterator`, `clippy::while_let_on_iterator` lint style violations (#36613)Umesh Yadav committed 1 year agoec8106d
  6. Fix `clippy::redundant_clone` lint violations (#36558)tidely committed 1 year ago7bdc99a
  7. lints: A bunch of extra style lint fixes (#36568)Piotr Osiewicz committed 1 year agocf7c64d
  8. Another batch of lint fixes (#36521)Piotr Osiewicz committed 1 year ago6825715
  9. Auto-fix clippy::collapsible_if violations (#36428)Piotr Osiewicz committed 1 year ago8f56738
  10. Fix clippy::needless_borrow lint violations (#36444)Piotr Osiewicz committed 1 year ago9e0e233
  11. Start separating authentication from connection to collab (#35471)Antonio Scandurra committed 1 year agof888f3f
  12. Update Agent panel to work with `CloudUserStore` (#35436)Marshall Bowers committed 1 year ago72d354d
  13. agent: Disable thinking when using inline assistant/edit file tool (#34141)Bennet Bo Fenner committed 1 year ago41fe2a2
  14. agent: Improve error handling and retry for zed-provided models (#33565)Michael Sloan committed 1 year agod497f52
  15. agent: Fix issue with Anthropic thinking models (#33317)Bennet Bo Fenner committed 1 year ago7be57ba
  16. agent: Less disruptive changed file notification (#31693)Oleksiy Syvokon committed 1 year ago6df4c53
  17. Store profile per thread (#31907)Ben Brandt committed 1 year ago709523b
  18. Pass up intent with completion requests (#31710)Marshall Bowers committed 1 year agoa23ee61
  19. Make language model deserialization more resilient (#31311)Richard Feldman committed 1 year ago00fd045
  20. Use read-only access methods for read-only entity operations (#31479)Joseph T. Lyons committed 1 year agoc208532
  21. Use `anyhow` more idiomatically (#31052)Kirill Bulatov committed 1 year ago16366cf
  22. Accept wrapped text content from LLM providers (#31048)Richard Feldman committed 1 year ago4bb04ce
  23. agent: Overwrite files more cautiously (#30649)Oleksiy Syvokon committed 1 year ago255d8f7
  24. Have read_file support images (#30435)Richard Feldman committed 1 year ago8fdf309
  25. Include `EditAgent`'s raw output when inspecting thread (#30337)Antonio Scandurra committed 1 year ago1b593f6
  26. Reuse conversation cache when streaming edits (#30245)Antonio Scandurra committed 1 year ago9f6809a
  27. agent: Handle attempts to use hallucinated tools (#29946)Oleksiy Syvokon committed 1 year ago8199664
  28. Change cloud language model provider JSON protocol to surface errors and usage information (#29830)Max Brunsfeld committed 1 year agoc3d9cde
  29. Add support for queuing status updates in cloud language model provider (#29818)Max Brunsfeld committed 1 year ago04772bf
  30. Fix eval judging missing final response (#29638)Richard Feldman committed 1 year agoc8685dc
  31. agent: Add "max mode" toggle (#29549)Marshall Bowers committed 1 year agoce93961
  32. Refactor markdown formatting utilities to avoid building intermediate strings (#29511)Michael Sloan committed 1 year ago609c528
  33. Restructure agent context (#29233)Michael Sloan committed 1 year ago17ecf94
  34. Do not log unfinished tools use that are in the middle of streaming (#29275)Oleksiy Syvokon committed 1 year agof69aeb6
  35. eval: Write JSON-serialized thread (#29271)Oleksiy Syvokon committed 1 year ago76a78b5