Commit Graph
13 Commits
Author SHA1 Message Date
Ben Kunkle f7306171bf ep_cli: Integrate ep qa and ep repair into core ep loop (#47987)
Closes #ISSUE

Release Notes:

- N/A *or* Added/Fixed/Improved ...
2026-02-02 11:32:25 -05:00
Oleksiy Syvokon f5a2cf3124 ep: Don't log steps that took <500ms (#47371)
Release Notes:

- N/A
2026-01-22 12:17:55 +00:00
fc411f554f Fix edit history clearing bug in ep (#47017)
We were including changes due to Buffer.reload in the edit history.

Release Notes:

- N/A

---------

Co-authored-by: Oleksiy Syvokon <oleksiy.syvokon@gmail.com>
Co-authored-by: Agus Zubiaga <agus@zed.dev>
Co-authored-by: Ben Kunkle <ben@zed.dev>
Co-authored-by: Zed Zippy <234243425+zed-zippy[bot]@users.noreply.github.com>
2026-01-16 15:44:38 -08:00
Oleksiy Syvokon 2d13fa976a Add ep --failed=skip to exclude errored examples from output (#46453)
Release Notes:

- N/A
2026-01-09 14:45:08 +00:00
Max Brunsfeld d89ad6afd1 Fix EP CLI output flicker (#46313)
Release Notes:

- N/A
2026-01-08 17:08:24 +00:00
Oleksiy SyvokonandAgus Zubiaga e3904addbc ep: Add file deletion support in unified diff parsing (#46279)
- Replace `is_new_file: bool` with `FileStatus` enum
(Created/Modified/Deleted) in udiff.rs to properly track file status
through diff operations
- Handle deleted files in `apply_diff` by calling
`project.delete_file()`
- Fix diff serialization in reorder_patch.rs to output `+++ /dev/null`
for file deletions and parse both `--- /dev/null` and `+++ /dev/null`
correctly
- Add bounds check for edit ranges exceeding buffer length

Also includes edit_prediction_cli improvements:
- Track `context_range` and `editable_range` in ExampleBuffer for more
precise prompt formatting
- Export MAX_CONTEXT_TOKENS and MAX_REWRITE_TOKENS from zeta2
- Wait for buffer parsing before computing ranges
- Respect NO_COLOR env var and enable info-level logging


Release Notes:

- N/A

Co-authored-by: Agus Zubiaga <agus@zed.dev>
2026-01-07 18:54:22 +00:00
Oleksiy Syvokon 3b31ca513b ep: Fix incorrect example count in failure summary (#46257)
The 'X of Y examples failed' message was counting completed steps/tasks
instead of actual examples. For example, with 2 examples each going
through Load and Context steps, it would report '1 of 3' instead of '1
of 2'.

Release Notes:

- N/A
2026-01-07 14:09:33 +00:00
Agus Zubiaga 1006eae075 ep cli: Fix finalize counter (#46198)
Release Notes:

- N/A
2026-01-06 22:04:36 +00:00
Agus Zubiaga 4c5080f51c ep cli: Load captured examples from Snowflake (#46102)
Release Notes:

- N/A
2026-01-06 10:40:13 -03:00
Max Brunsfeld 5ba7ece91e Improve support for collecting edit prediction training and eval examples (#45914)
* Fix some bugs in capture of EP examples from running app
* Tweak markdown format for EP examples
    * Store repo and revision in TOML front matter
    * Represent cursor position using a comment line
* Allow multiple expected patches in evals
* Remove line-based scoring criteria for evals
* Add a `synthesize` subcommand to the EP cli that generates examples
from git commits

Release Notes:

- N/A
2026-01-03 16:08:35 -08:00
Agus Zubiaga 3e2f9aad36 edit prediction cli: Improve error handling (#44718)
We were panicking whenever something went wrong with an example in the
CLI. This can be very disruptive when running many examples, and e.g a
single request fails. Instead, if running more than one example, errors
will now be logged alongside instructions to explore and re-run the
example by itself.

<img width="1454" height="744" alt="CleanShot 2025-12-12 at 13 32 04@2x"
src="https://github.com/user-attachments/assets/87c59e64-08b9-4461-af5b-03af5de94152"></img>


You can still opt in to stop as soon as en error occurs with the new
`--failfast` argument.

Release Notes:

- N/A
2025-12-12 14:15:58 -03:00
Agus Zubiaga 3da021f14f edit prediction cli: Progress output cleanup (#44708)
- Limit status lines to 10 in case `max_parallelism` is specified with a
grater value
- Handle logging gracefully rather than writing over it when clearing
status lines

Release Notes:

- N/A
2025-12-12 14:03:08 +00:00
Agus Zubiaga 5513b181a4 edit prediction cli: Cargo-style progress output (#44675)
Release Notes:

- N/A
2025-12-12 09:43:16 -03:00