Code

History

Commits on make-adding-folder-paths-mutating to crates/edit_prediction/src35+
  1. Track additional metrics in settled (#52938)Ben Kunkle committed 7 months ago7597666
  2. Add onboarding for parallel agents (#52940)Danilo Leal committed 7 months agoa0d0195
  3. language_models: Refactor deps and extract cloud (#53270)Agus Zubiaga committed 7 months ago98c17ca
  4. Consolidate prompt formatting logic into `zeta_prompt` (#53079)Ben Kunkle committed 7 months agof0df393
  5. Maintain root repo common dir path as a field on Worktree (#53023)Max Brunsfeld committed 7 months ago20f7308
  6. language_model: Decouple from Zed-specific implementation details (#52913)Jakub Konka committed 7 months ago29609d3
  7. ep: Move pure diffing functions to zeta_prompt:udiff (#52959)Oleksiy Syvokon committed 7 months ago66ea4b8
  8. Fix license check triggering on worktree root entry changes (#52902)Kirill Bulatov committed 7 months ago43ea97a
  9. Require multibuffer excerpts to be ordered and nonoverlapping (#52364)Cole Miller committed 7 months ago2a15bf6
  10. worktree: Close single-file worktrees when file is deleted (#49366)Daniel Strobusch committed 7 months ago03c5d37
  11. ep: Only fetch experiments if `cx.is_staff` (#52739)Ben Kunkle committed 7 months agoc332be8
  12. Strong app state (#52602)Mikayla Maki committed 7 months ago8cdae31
  13. Remove Sweep Integration (#52348)Ben Kunkle committed 7 months agof31b069
  14. Swap arrayvec crate for heapless to use LenT optimization (#47101)Gnome! committed 7 months agoaabc967
  15. Omit large edits from ep history (#51938)Ben Kunkle committed 7 months ago1c80e27
  16. ep: Fix e2e_latency tracking (#51852)Oleksiy Syvokon committed 8 months ago7cf7dca
  17. Fix shared database test isolation (#51809)Mikayla Maki committed 8 months ago67d7f99
  18. ep: Add two new prompt formats (#51836)Oleksiy Syvokon committed 8 months ago090ef79
  19. Add stream_options.include_usage for OpenAI-compatible API token usage (#45812)Elier committed 8 months ago905d28c
  20. ep: Track e2e latency (#51678)Ben Kunkle committed 8 months ago52fb089
  21. ep: Ensure prompt is always within token limit (#51529)Ben Kunkle committed 8 months ago8a7daea
  22. ep: Ensure predictions are not refreshed while following (#51489)Ben Kunkle committed 8 months ago8fc880e
  23. ep: Error indication when Mercury free tier limit reached (#51447)Ben Kunkle committed 8 months agob0cc006
  24. ep: Avoid including collaborator edits in edit history sent to model (#51343)Ben Kunkle committed 8 months agodf8bafd
  25. language_model: Centralize LlmApiToken to a singleton (#51225)Tom Houlé committed 8 months ago9fb57b0
  26. Prevent remote edits from triggering edit predictions when collaborating (#51196)Lukas Wirth committed 8 months agob21f4a3
  27. ep: Include diagnostics in `ZetaPromptInput` (#51141)Ben Kunkle committed 8 months ago1475774
  28. zeta: Allow the server to select the editable and context ranges more flexibly (#50975)Max Brunsfeld committed 8 months ago2bd5c21
  29. ep: Skip context retrieval when already performed (#51100)Oleksiy Syvokon committed 8 months agob54716d
  30. ep: Add `<|no-edit|>` command to hashlines format (#51103)Ben Kunkle committed 8 months agoe9c691a
  31. ep: Unify code in `parse_output` and `zeta_prompt` (#50958)Oleksiy Syvokon committed 8 months ago4b3660b
  32. Refresh LLM API token on organization change (#50931)Neel committed 8 months agodc0e41f
  33. zeta: Add variable edit format (#50850)Max Brunsfeld committed 8 months ago61d9696
  34. zeta2: Don't remove redundant excerpts on the client (#50886)Ben Kunkle committed 8 months agoda9d548
  35. ep: Indicate active experiment (#50870)Ben Kunkle committed 8 months agoc5f3a1d