Yehowshua/ZIm
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Systematically optimize agentic editing performance (#28961)

Browse source 
Now that we've established a proper eval in tree, this PR is reboots of
our agent loop back to a set of minimal tools and simpler prompts. We
should aim to get this branch feeling subjectively competitive with
what's on main and then merge it, and build from there.

Let's invest in our eval and use it to drive better performance of the
agent loop. How you can help: Pick an example, and then make the outcome
faster or better. It's fine to even use your own subjective judgment, as
our evaluation criteria likely need tuning as well at this point. Focus
on making the agent work better in your own subjective experience first.
Let's focus on simple/practical improvements to make this thing work
better, then determine how we can craft our judgment criteria to lock
those improvements in.

Release Notes:

- N/A

---------

Co-authored-by: Max <max@zed.dev>
Co-authored-by: Antonio <antonio@zed.dev>
Co-authored-by: Agus <agus@zed.dev>
Co-authored-by: Richard <richard@zed.dev>
Co-authored-by: Max Brunsfeld <maxbrunsfeld@gmail.com>
Co-authored-by: Antonio Scandurra <me@as-cii.com>
Co-authored-by: Michael Sloan <mgsloan@gmail.com>
This commit is contained in:
Nathan Sobo 2025-04-18 20:47:59 -06:00 • committed by GitHub
parent 8102a16747
commit bab28560ef
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
68 changed files with 1575 additions and 478 deletions
Download patch file Download diff file Expand all files Collapse all files

6
crates/eval/examples/runtime_script_refactor/diff_criteria.md Normal file
View file

@ -0,0 +1,6 @@
1. **Added RuntimeCommands import and WebElement to page.py**
The changes add an import for `RuntimeCommands` and `WebElement` to `page.py`. The `execute_js_script` method is renamed to `execute_script` and enhanced to support execution in the context of a WebElement. The method now uses `RuntimeCommands` for script evaluation.
2. **Refactored Runtime-related commands from DomCommands to new RuntimeCommands class**
The changes move all Runtime-related command templates and methods from `DomCommands` in `dom.py` to a new `runtime.py` file. This includes `EVALUATE_TEMPLATE`, `CALL_FUNCTION_ON_TEMPLATE`, `GET_PROPERTIES`, and their associated methods. The DomCommands class now uses RuntimeCommands for JavaScript evaluation.
3. **Added Scripts constants and enhanced WebElement functionality**
The changes add a new `Scripts` class to `constants.py` containing JavaScript snippets for common operations. The `element.py` file is significantly enhanced with new methods for script execution, visibility checking, and improved click handling. New exceptions are added to `exceptions.py` for better error handling.