Code

History

Commits on arm_github_runners to crates/eval/src35+
  1. Replace `async-watch` with a custom watch (#32245)Antonio Scandurra committed 1 year ago019a14b
  2. Store profile per thread (#31907)Ben Brandt committed 1 year ago709523b
  3. assistant: Partial fix for HTML entities in tools params (#32148)Oleksiy Syvokon committed 1 year ago3884de9
  4. agent: Generate a notification when reaching tool use limit (#31894)Danilo Leal committed 1 year ago63c1033
  5. Pass up intent with completion requests (#31710)Marshall Bowers committed 1 year agoa23ee61
  6. evals: Configurable number of max dialog turns (#31680)Oleksiy Syvokon committed 1 year agocb187b0
  7. Make language model deserialization more resilient (#31311)Richard Feldman committed 1 year ago00fd045
  8. Rename `assistant_settings` to `agent_settings` (#31513)Marshall Bowers committed 1 year ago8faeb34
  9. evals: Allow threads explorer to search for JSON files recursively (#31509)Oleksiy Syvokon committed 1 year ago61a40e2
  10. Use read-only access methods for read-only entity operations (#31479)Joseph T. Lyons committed 1 year agoc208532
  11. evals: Configurable judge model (#31282)Oleksiy Syvokon committed 1 year ago68a46c3
  12. eval: Don't read the model from the user settings (#31230)Marshall Bowers committed 1 year agocb52acb
  13. Handle new `refusal` stop reason from Claude 4 models (#31217)Marshall Bowers committed 1 year ago5c0b161
  14. chore: Make terminal_view own the TerminalSlashCommand (#31070)Piotr Osiewicz committed 1 year ago77dadfe
  15. Use `anyhow` more idiomatically (#31052)Kirill Bulatov committed 1 year ago16366cf
  16. Accept wrapped text content from LLM providers (#31048)Richard Feldman committed 1 year ago4bb04ce
  17. extension: Add debug_adapters to extension manifest (#30676)Piotr Osiewicz committed 1 year agoa092e2d
  18. eval: Count execution errors as failures (#30712)Oleksiy Syvokon committed 1 year ago6420df3
  19. agent: Overwrite files more cautiously (#30649)Oleksiy Syvokon committed 1 year ago255d8f7
  20. Have read_file support images (#30435)Richard Feldman committed 1 year ago8fdf309
  21. Add no_tools_enabled eval (#30537)Richard Feldman committed 1 year ago49887d6
  22. Wait to locate system-installed Node until the shell environment is loaded (#30416)Max Brunsfeld committed 1 year ago65b1396
  23. Include `EditAgent`'s raw output when inspecting thread (#30337)Antonio Scandurra committed 1 year ago1b593f6
  24. Reuse conversation cache when streaming edits (#30245)Antonio Scandurra committed 1 year ago9f6809a
  25. Fix agent reading and editing files over SSH (#30144)Antonio Scandurra committed 1 year ago89430a0
  26. evals: Enable Python LSP (#29987)Oleksiy Syvokon committed 1 year agoac00713
  27. Terminal tool improvements (#29924)Cole Miller committed 1 year agoc12e637
  28. context_store: Refactor state management (#29910)Bennet Bo Fenner committed 1 year ago9cb5ffa
  29. agent: Handle attempts to use hallucinated tools (#29946)Oleksiy Syvokon committed 1 year ago8199664
  30. agent: Remove unneeded tracking of request usage (#29894)Marshall Bowers committed 1 year ago3db4744
  31. agent eval: Fix `--model` arg and add `--provider` (#29883)Michael Sloan committed 1 year agobb82d9c
  32. Change cloud language model provider JSON protocol to surface errors and usage information (#29830)Max Brunsfeld committed 1 year agoc3d9cde
  33. Encourage editing over re-creating a file from scratch (#29870)Antonio Scandurra committed 1 year ago4d51602
  34. agent: Review edits in single-file editors (#29820)Agus Zubiaga committed 1 year ago6431630
  35. Add support for queuing status updates in cloud language model provider (#29818)Max Brunsfeld committed 1 year ago04772bf