Systematically optimize agentic editing performance (#28961)
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:
parent
8102a16747
commit
bab28560ef
68 changed files with 1575 additions and 478 deletions
|
@ -15,6 +15,7 @@ To get a project-wide diagnostic summary:
|
|||
{}
|
||||
</example>
|
||||
|
||||
IMPORTANT: When you're done making changes, you **MUST** get the **project** diagnostics (input: `{}`) at the end of your edits so you can fix any problems you might have introduced. **DO NOT** tell the user you're done before doing this!
|
||||
|
||||
You may only attempt to fix these up to 3 times. If you have tried 3 times to fix them, and there are still problems remaining, you must not continue trying to fix them, and must instead tell the user that there are problems remaining - and ask if the user would like you to attempt to solve them further.
|
||||
<guidelines>
|
||||
- If you think you can fix a diagnostic, make 1-2 attempts and then give up.
|
||||
- Don't remove code you've generated just because you can't fix an error. The user can help you fix it.
|
||||
</guidelines>
|
||||
|
|
Loading…
Add table
Add a link
Reference in a new issue