History

Commits on git-job-queue-debug-ui to crates/edit_prediction/src35+

agent_ui: Unify draft and background threads into retained threads (#53737)Nathan Sobo committed 7 months ago55e4713
edit_prediction: Disable training data collection based on organization configuration (#53639)Marshall Bowers committed 7 months agoeb76db4
ep: Add LCS-based recall (#53509)Oleksiy Syvokon committed 7 months agoc788dc5
Track additional metrics in settled (#52938)Ben Kunkle committed 7 months ago7597666
Add onboarding for parallel agents (#52940)Danilo Leal committed 7 months agoa0d0195
language_models: Refactor deps and extract cloud (#53270)Agus Zubiaga committed 7 months ago98c17ca
Consolidate prompt formatting logic into `zeta_prompt` (#53079)Ben Kunkle committed 7 months agof0df393
Maintain root repo common dir path as a field on Worktree (#53023)Max Brunsfeld committed 7 months ago20f7308
language_model: Decouple from Zed-specific implementation details (#52913)Jakub Konka committed 7 months ago29609d3
ep: Move pure diffing functions to zeta_prompt:udiff (#52959)Oleksiy Syvokon committed 7 months ago66ea4b8
Fix license check triggering on worktree root entry changes (#52902)Kirill Bulatov committed 7 months ago43ea97a
Require multibuffer excerpts to be ordered and nonoverlapping (#52364)Cole Miller committed 7 months ago2a15bf6
worktree: Close single-file worktrees when file is deleted (#49366)Daniel Strobusch committed 7 months ago03c5d37
ep: Only fetch experiments if `cx.is_staff` (#52739)Ben Kunkle committed 7 months agoc332be8
Strong app state (#52602)Mikayla Maki committed 7 months ago8cdae31
Remove Sweep Integration (#52348)Ben Kunkle committed 7 months agof31b069
Swap arrayvec crate for heapless to use LenT optimization (#47101)Gnome! committed 7 months agoaabc967
Omit large edits from ep history (#51938)Ben Kunkle committed 8 months ago1c80e27
ep: Fix e2e_latency tracking (#51852)Oleksiy Syvokon committed 8 months ago7cf7dca
Fix shared database test isolation (#51809)Mikayla Maki committed 8 months ago67d7f99
ep: Add two new prompt formats (#51836)Oleksiy Syvokon committed 8 months ago090ef79
Add stream_options.include_usage for OpenAI-compatible API token usage (#45812)Elier committed 8 months ago905d28c
ep: Track e2e latency (#51678)Ben Kunkle committed 8 months ago52fb089
ep: Ensure prompt is always within token limit (#51529)Ben Kunkle committed 8 months ago8a7daea
ep: Ensure predictions are not refreshed while following (#51489)Ben Kunkle committed 8 months ago8fc880e
ep: Error indication when Mercury free tier limit reached (#51447)Ben Kunkle committed 8 months agob0cc006
ep: Avoid including collaborator edits in edit history sent to model (#51343)Ben Kunkle committed 8 months agodf8bafd
language_model: Centralize LlmApiToken to a singleton (#51225)Tom Houlé committed 8 months ago9fb57b0
Prevent remote edits from triggering edit predictions when collaborating (#51196)Lukas Wirth committed 8 months agob21f4a3
ep: Include diagnostics in `ZetaPromptInput` (#51141)Ben Kunkle committed 8 months ago1475774
zeta: Allow the server to select the editable and context ranges more flexibly (#50975)Max Brunsfeld committed 8 months ago2bd5c21
ep: Skip context retrieval when already performed (#51100)Oleksiy Syvokon committed 8 months agob54716d
ep: Add `<|no-edit|>` command to hashlines format (#51103)Ben Kunkle committed 8 months agoe9c691a
ep: Unify code in `parse_output` and `zeta_prompt` (#50958)Oleksiy Syvokon committed 8 months ago4b3660b
Refresh LLM API token on organization change (#50931)Neel committed 8 months agodc0e41f