Code

History

Commits on github-token to crates/eval/src/example.rs35+
  1. agent: Generate a notification when reaching tool use limit (#31894)Danilo Leal committed 1 year ago63c1033
  2. Pass up intent with completion requests (#31710)Marshall Bowers committed 1 year agoa23ee61
  3. evals: Configurable number of max dialog turns (#31680)Oleksiy Syvokon committed 1 year agocb187b0
  4. Rename `assistant_settings` to `agent_settings` (#31513)Marshall Bowers committed 1 year ago8faeb34
  5. Handle new `refusal` stop reason from Claude 4 models (#31217)Marshall Bowers committed 1 year ago5c0b161
  6. Use `anyhow` more idiomatically (#31052)Kirill Bulatov committed 1 year ago16366cf
  7. agent: Overwrite files more cautiously (#30649)Oleksiy Syvokon committed 1 year ago255d8f7
  8. agent: Handle attempts to use hallucinated tools (#29946)Oleksiy Syvokon committed 1 year ago8199664
  9. agent: Remove unneeded tracking of request usage (#29894)Marshall Bowers committed 1 year ago3db4744
  10. agent: Review edits in single-file editors (#29820)Agus Zubiaga committed 1 year ago6431630
  11. Support @-mentions in inline assists and when editing old agent panel messages (#29734)Cole Miller committed 1 year ago9547d42
  12. Introduce a new `StreamingEditFileTool` (#29733)Antonio Scandurra committed 1 year agof891dfb
  13. Code block evals (#29619)Richard Feldman committed 1 year agod700403
  14. agent: Enrich `grep` tool output with syntax information (#29601)Agus Zubiaga committed 1 year agofd17f2d
  15. agent: Cancel pending in-edit user message upon new message submit (#29565)Danilo Leal committed 1 year agobbe8d6a
  16. Restructure agent context (#29233)Michael Sloan committed 1 year ago17ecf94
  17. Treat invalid JSON in tool calls as failed tool calls (#29375)Richard Feldman committed 1 year ago720dfee
  18. eval: New `add_arg_to_trait_method` example (#29297)Agus Zubiaga committed 1 year ago45d3f51
  19. agent: Render diffs for the edit file tool (#29234)Danilo Leal committed 1 year ago8366cd0
  20. eval: Fine-grained assertions (#29246)Agus Zubiaga committed 1 year agoce1a674
  21. Rework eval to support interpretable scores and efficient repetitions (#29197)Max Brunsfeld committed 1 year ago36d02de
  22. Add new action to run agent eval (#29158)Nathan Sobo committed 1 year ago458ffaa
  23. Write `{result_count}.diff` and `last.diff` eval run outputs (#29181)Michael Sloan committed 1 year ago9249919
  24. Streaming tool calls (#29179)Richard Feldman committed 1 year ago4f2f9ff
  25. Agent eval: Copy `.rules` file into eval worktree for examples based on Zed (#29116)Michael Sloan committed 1 year ago0f3ac38
  26. debugger: More tidy up for SSH (#28993)Conrad Irwin committed 1 year ago9d35f03
  27. Start tracking tool failure rates in eval (#29122)Antonio Scandurra committed 1 year ago97ab098
  28. eval: Improve lang server idle detection (#29135)Agus Zubiaga committed 1 year agoceeae79
  29. Rename regex search tool to grep and accept an include glob pattern (#29100)Nathan Sobo committed 1 year ago107d8ca
  30. Default to fast model for thread summaries and titles + don't include system prompt / context / thinking segments (#29102)Michael Sloan committed 1 year agofbf7caf
  31. agent: Preserve thinking blocks between requests (#29055)Bennet Bo Fenner committed 1 year agobafc086
  32. Pretty tool inputs in eval output markdown + numbered assistant messages (#29082)Michael Sloan committed 1 year ago98ceffe
  33. Systematically optimize agentic editing performance (#28961)Nathan Sobo committed 1 year agobab2856
  34. agent: Attach thread ID and prompt ID to telemetry events (#29069)Marshall Bowers committed 1 year ago7abe2c9
  35. agent: Use default prompts from prompt library in system prompt (#28915)Michael Sloan committed 1 year ago502a0f6