v0.32.2
Mirrored from Ollama releases for archival readability. Support the source by reading on the original site.
What's Changed
- launch: keep Claude Code channels available by @hoyyeva in #17210
- cmd: remove dead agent prompt wrappers by @ParthSareen in #17227
- agent: reorder working directory instruction by @ParthSareen in #17228
- agent: clean up semantics, UX, DX, and procedural code by @ParthSareen in #17212
- agent: allow unlimited tool rounds for cloud models by default by @ParthSareen in #17217
- anthropic: close text block before starting thinking block by @hoyyeva in #17225
- agent: skills system by @ParthSareen in #17203
- llama.cpp update by @dhiltgen in #17186
- cmd: route root command server start through checkServerHeartbeat by @ParthSareen in #17245
- agent/tui: remove redundant context-window refreshes from event loop by @ParthSareen in #17241
- cmd: complete slash commands before submitting by @ParthSareen in #17230
- cmd: remove standalone agent command by @ParthSareen in #17229
- cmd/tui/chat: render bold emphasis consistently across markdown by @ParthSareen in #17224
- launch: update Hermes integration by @ParthSareen in #17202
- MLX update by @dhiltgen in #17189
- build: bump Linux toolchain to GCC 13 by @dhiltgen in #17244
- cuda: add CC 10.0 for linux in CUDA v12 by @dhiltgen in #17025
Full Changelog: v0.32.1...v0.32.2-rc0
Discussion (0)
Sign in to join the discussion. Free account, 30 seconds — email code or GitHub.
Sign in →No comments yet. Sign in and be the first to say something.