Plugins

Adaptive reasoning slider skin that maps each model's available reasoning efforts onto a 0–30 visual intensity scale, with synchronized portraits, background, and interface colors.

Full-screen Changzhengji-themed boot animation for DSH with a six-step authorization sequence, seven built-in real-voice packs, two switchable emblems, five switchable character portraits, and an optional access-password gate.

Two-suit VTuber theme for Joi: Flowers and Library are separate token systems for light and dark, with a standing portrait and a whale girl napping on the headline of the new-session page, two chibi companions above the composer that follow the turn state, a duo sidebar mark, and a context meter shaped as a ripening mandarin; a third card returns the stock DeepSeek look with the plugin still installed.

DSH 工作区记忆画像：有证据、有版本、能解释变化；索引简报省 token、轮末本地召回、红线 / 审批队列 / 版本链 / 注入审计；零依赖、不出站。

Long-term memory scoped to the DSH workspace. A session opens with a one-line-per-memory index - bodies are fetched on demand by the `memory` tool, so the same character budget holds about three times as many entries - and when a turn ends a purely local search over the last user message pulls the matching memories into the next briefing at no model cost. Optional auto-capture distils a stretch of conversation into structured memories; in draft mode they wait in an approval queue instead of landing directly. A portrait layer keeps a workspace and a global picture, rewritten from the journal and the records, with the same draft-or-direct choice. Settings → Memory holds the archive, list and timeline views, a health check (duplicate clusters, stale entries, broken links), the supersede version chain with rollback, and a read-only scan that imports existing WorkBuddy / Qoder memory files.

Register models, assist with portraits, and select the Agent model from a secret-free catalog for DeepSeek Harness.

Portrait layout for desktop windows: navigation takes the full left column, the file/terminal panel moves above the conversation, and a draggable splitter sets its height; touch devices are unaffected.

TangSan mascot appearance layer for the DeepSeek Harness web GUI: wears a generated TangSan portrait as the GUI background (surface-token fade with opacity, blur, scrim and position controls), seats the matching square avatar as the sidebar and conversation brand mark, and edits it all from a Settings section; the host serves the artwork and config locally under /api/tangsan, and the config lives at $DSH_HOME/tangsan.json.

Portrait-adaptive communication skill: builds a live user portrait (proficiency, per-domain gaps, current state) from the conversation and calibrates every answer's depth, jargon density and step granularity to it; behavior-over-claims dumb-play detection; transparent profile snapshot export. MIT.

Floating desktop companion for DSH: a draggable character on the overlay — tap to charge energy, blinking and emotes, naps, synthesized WebAudio sounds and particle effects. Bring your own: any photo (pet, portrait, anime art) becomes a 2.5D cutout with hand-marked eyes, and 3D models (GLB, VRM, STL, OBJ, PLY) render as a real three.js turntable. Resize 30%-300%; data stays local.

Reach this Harness from your phone over a private network: a loopback-preserving gateway with one-time pairing codes, plus a portrait layout for narrow screens.

A WSLg-compatible DSH desktop pet reacts to agent activity, lets you message the active session, and loads Hatch-Pet v2 atlases or transparent portraits.

Make the AI remember how you think, not what you said: actively captures your principles, redlines, and working habits across sessions — with memory capacity, graceful decay, and human-readable reasoning for every entry. 0.7.0 brings an intuitive persona portrait with evidence tracing.