AI-ML
Ollama v0.32.2
RESUMEN
What's Changed launch: keep Claude Code channels available by @hoyyeva in cmd: remove dead agent prompt wrappers by @ParthSareen in * agent: reorder working directory instruction by @ParthSareen in http
Descripción Detallada
What's Changed launch: keep Claude Code channels available by @hoyyeva in cmd: remove dead agent prompt wrappers by @ParthSareen in agent: reorder working directory instruction by @ParthSareen in agent: clean up semantics, UX, DX, and procedural code by @ParthSareen in agent: allow unlimited tool rounds for cloud models by default by @ParthSareen in anthropic: close text block before starting thinking block by @hoyyeva in agent: skills system by @ParthSareen in llama.cpp update by @dhiltgen in cmd: route root command server start through checkServerHeartbeat by @ParthSareen in agent/tui: remove redundant context-window refreshes from event loop by @ParthSareen in cmd: complete slash commands before submitting by @ParthSareen in cmd: remove standalone agent command by @ParthSareen in cmd/tui/chat: render bold emphasis consistently across markdown by @ParthSareen in launch
Explicación con IA
Genera un resumen en lenguaje claro de los cambios de este release.
Releases Relacionados
AI-ML
Ollama v0.32.3
## What's Changed * mlx update by @dhiltgen in https://github.com/ollama/ollama/pull/17332 * model/parsers: finalize incomplete GLM tool calls by @dhiltgen in https://github.com/ollama/ollama/pull/17250 * docs: update retirements by @mxyng in https://github.com/ollama/ollama/pull/17289 * model:
AI-ML
Ollama v0.32.1
## What's Changed - Improved Gemma 4 tool calling and multi-turn reasoning, including more reliable tool-response continuations - Fixed a recurrent MLX model cache leak that could increase memory use across requests, and improved cache snapshot performance - MLX text model loading now respects `O