v0.23.0#
These are the release notes for gptme version v0.23.0.
Contributors#
Thanks to everyone who contributed to this release:
@0xbrayo, @erikbjare, @jrmi
Changelog#
Changes since v0.22.0:
📦 gptme#
✨ Features (6)#
🐛 Fixes (11)#
Click to expand
fix: prompt to reinforce correct placement of filename parameter in patch tool (#252) (
01541af0)fix: trigger tool detection only on complete lines, for performance and to fix nested codeblocks in tooluse (#251) (
5a228d4e)fix: fixed prompt for python tool (
64f94916)fix: fixes to computer use (
1de06c67)fix: switch to new Claude 3.5 models in evals, improve detection of results folders (
6aec2313)fix: switch to duckduckgo as default search engine with lynx browser (#237) (
ce7afb8f)fix: fixed running evals in docker (
5ac3914b)fix: added metadata for new haiku model (
85647562)fix: fix including files specified in gptme.toml (
381dbc8f)fix: updated READMEs about gptme.vim (
f7913bbc)fix: removed debug logging in gptme.vim (
25c998c4)
🔨 Misc (12)#
Click to expand
chore: bump version to 0.23.0 (
9010fede)chore: committed caches for contributor info used in changelog generation (
9dee5548)docs: improved server/computer use docs (
501008a3)refactor: move get_workspace_prompt into prompts.py, add TODO comments (
639e4cb1)docs: updated
gptme --helpoutput, fix command ordering (da90e33c)docs: minor improvements to server docs (
f6589de1)docs: updated server docs with better structure and mention of gptme-webui (
c32f64db)docs(README): moved the use cases section above the developer/in-progress sections (
0c0163d0)docs(README): rewrote use cases section (
a517d8f3)docs: add link to SWE-Bench PR (
970fc47e)docs: improved arewetiny intro text (
3f5aa840)docs: fixed gptme.vim docs (
9ca2e083)
(excluded 3 less relevant commits)
Full Changelog: https://github.com/gptme/gptme/compare/v0.22.0…v0.23.0