v1.3.0 focuses on long-running conversations and the model experience: it adds real long-context memory evaluations, a dynamic context-usage gauge, and per-model reasoning-effort controls. It also improves slash commands, global habits, and end-of-turn handling, while fixing streaming responses, repeated automatic compaction, MCP child-process shutdown, and several UI issues.
What's changed
Add headless memory-v1 eval dataset: compaction modes, retrieval, stage loading by @xuzhougeng in https://github.com/xuzhougeng/wisp-science/pull/809
Fix silent task failures and blank completions with DeepSeek/GLM (#798) by @xuzhougeng in https://github.com/xuzhougeng/wisp-science/pull/810
Add live memory eval and a copyable long-context demo by @xuzhougeng in https://github.com/xuzhougeng/wisp-science/pull/811
ui: replace native reasoning-effort select with in-menu option list by @xuzhougeng in https://github.com/xuzhougeng/wisp-science/pull/812
Make chat text follow the UI font size setting by @xuzhougeng in https://github.com/xuzhougeng/wisp-science/pull/813
memory: add global habits directly from settings by @xuzhougeng in https://github.com/xuzhougeng/wisp-science/pull/814
ui: edit reasoning effort per model row in the model picker by @xuzhougeng in https://github.com/xuzhougeng/wisp-science/pull/818
Hide follow-up suggestions as soon as the user sends by @xuzhougeng in https://github.com/xuzhougeng/wisp-science/pull/815
Default new DeepSeek profiles to deepseek-v4-flash by @xuzhougeng in https://github.com/xuzhougeng/wisp-science/pull/817
Animate conversation outline open and close by @xuzhougeng in https://github.com/xuzhougeng/wisp-science/pull/816
docs: name workflow engines (snakemake/nextflow/oxo-flow) in local-env-setup skill by @ShixiangWang in https://github.com/xuzhougeng/wisp-science/pull/819
seed: replace synthetic memory demo with a real recorded CLI session by @xuzhougeng in https://github.com/xuzhougeng/wisp-science/pull/820