-
0.5.0 Stable
released this
2026-07-16 16:56:37 +00:00 | 56 commits to main since this releaseAdded
- Settings are grouped into collapsible sections (Missions / Appearance / CIPHER uplink);
the open/closed state is remembered. - The CIPHER endpoint is now an ordered fallback list instead of a single URL — the first
reachable one is used. One synced list covers the same local LLM server showing up as
localhostat your desk and as a LAN IP on the road. Existing single-endpoint settings
from 0.4.x migrate automatically. - New "Model thinking" toggle (off by default): CIPHER answers straight away instead of
deliberating. Models that always think (gpt-oss/harmony) are detected and the toggle
disables itself instead of promising something the request can't deliver. - The selected model's context length is shown when the endpoint reports it (LM Studio,
Ollama).
Downloads
-
Source code (ZIP)
0 downloads
-
Source code (TAR.GZ)
0 downloads
- Settings are grouped into collapsible sections (Missions / Appearance / CIPHER uplink);