Plugins

On-demand memory for DeepSeek Harness: session logs are distilled into layered markdown (a summary, an index and per-topic files), and a mem_query tool returns only the matched entries rather than the whole index. Nothing is injected per turn, there are no dependencies, and every entry keeps a source pointer back to the conversation it came from.

Adds DSH restart and stop controls with token-aware reconnect and policy-based recovery for interrupted web sessions.

Plan-usage pet for the DSH web GUI: a floating skeletal-animated character reports quota in a speech bubble, auto-matching the configured provider (OpenCode Go, Command Code, DeepSeek) to show a plan percentage or an account balance, and falling back to local token stats when the provider API is unavailable; draggable, wheel-scalable (90-260px), synthesized click sounds, loopback-only routes.

Session usage statistics panel: token and request stats at day/hour/minute granularity, an activity heatmap, bottom-bar session info takeover with per-turn cost chips, and cost estimation under multi-condition time-segmented pricing. Re-implemented from HaoyueQin/dsh-usage-statistics-panel with extensions.

Per-turn token usage, request composition and cost breakdown panel for the DeepSeek Harness Web GUI.

Global token totals across every local DSH conversation, de-duplicated by message id, with custom date ranges and per-provider monthly quota tracking.

DSH (DeepSeek Harness) Web GUI plugin: global model token usage stats as a dedicated "Token 用量" page in Settings — incremental session-file scanning with a persistent fold cache, date-range picker with presets, model/provider filters, per-day and per-mode

Fuse v1.2.1 — an all-in-one UI design + code style plugin (the upgraded ui-aesthetics skill): design tokens in theme.json (with the brand color as the single source of truth) + code style in code-style.json + dsh-fuse-english fence page-level rendering +

DeepSeek Harness Web GUI plugin: real-time spend for the current session, priced from per-model token rates and shown as a pill under the composer

DSH 会话管理插件（dshm）：设置页「会话管理」面板 + 3082 端口上的完整 dshm 界面（会话列表/全文搜索/每步 token 趋势/导出/归档）。

统一管理十种 IM 机器人及飞书、钉钉个人账号授权，并接入本机 DeepSeek Harness。

DSH plugin: sync model settings, plugin manifests, patch layers and lockfiles across devices through a private Git repository (manual push/pull; https+token or ssh public-key auth).

XingTu 26 production-grade AI agent skills, packaged as a DeepSeek Harness (DSH) skills plugin — token compression, code review, safe refactor, migration, evidence review & more. 26 个生产级 SKILL.md 技能，DSH 一键安装即用。

Global real-time Token HUD for DeepSeek Harness Web: draggable floating window showing live output tok/s, cumulative tokens, and per-session running/retrying status across all DSH sessions.

Brick — a restrained, token-only theme layer for DeepSeek Harness Web. Warm plaster neutrals, mortar hairlines, one fired-clay accent, and a Settings on/off switch. 一切皆插件，每一块砖都可承重。

RTK (Reusable Token Kompressor) tool for DeepSeek Harness — token-optimized CLI proxy exposing read/ls/git/grep/err/test/json and more through the standard shell sandbox.

Dynamic capability gating for DeepSeek Harness that reduces token usage by exposing large MCP/plugin toolsets only when an agent needs them.

NPM registry management for DeepSeek Harness: query package info, list versions, search packages, and publish/deprecate packages — registry info via HTTP API, publish via the npm CLI with optional token injection, plus a web settings panel

Context occupancy and account balance for the DeepSeek Harness Web Client: a session-header readout, a balance capability seam, and a DeepSeek provider

Adds a View URL page to Settings showing the running session tokenized Web address plus a stable fixed address that survives desktop restarts and is reachable from other devices on the same LAN.

Model channel manager: several provider/model candidates share one virtual route (roundrobin/<group>) with failover, retry, timeout and cooldown; a settings tab edits providers and groups, runs per-model speed tests and real single-model request tests, and a seven-day health panel aggregates latency, failures and upstream token usage (input, output, cache and reasoning).

Composer readouts for the DeepSeek Harness: CJK-weighted draft token count, session spend at official peak/idle rates, context occupancy, and what the same usage would have cost on the costliest other model; client-only, with no host half and no credential access.

Live token cost for every chat in the DSH Web UI: the chat, its subagents and the whole session tree, priced from a bundled models.dev snapshot of seven providers and 139 priced models, with cache read and write rates wherever the provider publishes them and DeepSeek from its own peak and off-peak table. Every finished answer carries its own price in the transcript, and a chat that is not currently open is priced from the log instead of disappearing. Spend is costed per interval from an append-only JSONL ledger in the project folder, so logged work keeps the tariff it was billed at. On top of it: budget-aware work plans packed against a money limit, routing scenarios that show which models are worth connecting, a generated plan document in English, Chinese or Russian, and a warning when spend belongs to no plan unit.

Video-style turn navigation for the Web UI: full-map progress bar with hover preview cards (tools/files/tokens), drag scrub, ⌘K in-conversation search, ⌘↑/⌘↓ stepping, Esc-return. Event-log powered — works beyond the loaded window. Dual-half plugin on the official composer.dock slot.