bab28560ef
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>
739 B
739 B
Get errors and warnings for the project or a specific file.
This tool can be invoked after a series of edits to determine if further edits are necessary, or if the user asks to fix errors or warnings in their codebase.
When a path is provided, shows all diagnostics for that specific file. When no path is provided, shows a summary of error and warning counts for all files in the project.
To get diagnostics for a specific file: { "path": "src/main.rs" }To get a project-wide diagnostic summary: {}
- 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.