
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>
732 B
732 B
- All Goose packages (
goose
,goose-bench
,goose-cli
,goose-mcp
,goose-server
) were updated from version1.0.17
to1.0.18
inCargo.lock
. These updates ensure compatibility and consistency across related packages. - The
goose-app
version inui/desktop/package-lock.json
was also updated to1.0.18
, maintaining alignment with the backend and shared libraries. - In
App.tsx
, theuseConfig
hook was destructured to directly useaddExtension
instead of the olderaddExtensionToConfig
function. All occurrences of the old function name were updated, including inside effects and async calls, to use the new unified method. This change simplifies extension handling logic while preserving current behavior.