Plugins

Conversation font-size controls for the Web UI: a stepper in the composer row, keyboard shortcuts, and Ctrl+wheel zoom, all writing through the theme service setFontSize.

Next-step suggestions for the DSH composer: after each completed turn, one auxiliary call on the session's current model returns 3 clickable follow-up suggestions above the input box, and clicking one fills the draft.

Shows local glossary definitions when hovering over terms in chat messages.

Adds a session status pill to the composer dock that expands into a panel of turn, token, performance and context readings.

Adds two visual pages to DSH Settings. MCP servers are kept as a JSON source of truth that rewrites the profile patch managed block, with YAML validation and timestamped backups, plus import of a pasted mcpServers JSON that first lists what will be added or overwritten. Thinking unlock probes each OpenAI-compatible gateway for the reasoning efforts it really declares and writes the per-level config back while leaving other hand-written YAML byte ranges untouched; the available model list syncs from a separate button that previews additions and removals, then writes levels and models in one atomic pass, and can also run on the page schedule.

Connect multiple decision providers and models through one interface: Jev via TypeSafe, Clef via Cloudflare, Drex via Nace, Decider via meraGPT, self-hosted Laya, and compatible custom providers. Agents and plugins can classify content, filter candidates, score against criteria, or locate objects in images, then use structured results in their workflows.

Claude-style Git branch and PR composer bar for DeepSeek Harness: quick branch switcher, native diff drawer integration, and adaptive PR creation with Actions CI status.

Skill manager page in the DSH Web Settings panel, at the same level as Plugins: lists every skill the installation serves with its own summary, source and disk footprint, and removes any of them into a recoverable trash.

You.com web search and page-fetch providers for DeepSeek Harness, returning source lists and extracted page text through a configurable API key and endpoint.

DeepSeek Harness: ds-llm-manage. 模型管理（收藏、置顶、探活），熟练度排序，故障自动切换，防止长任务中途中断

Export DeepSeek Harness (dsh) sessions as readable Markdown. Pick individual messages from one session, or merge several into a single .md / split them into a ZIP.

Image generation for DeepSeek Harness through an OpenAI-compatible relay (configured for `api.ykh.ai` / `gpt-image-2`).

Customs declaration document consistency check: field-level findings with rule IDs.

作文量表评分核对（按评分项、原文定位与分值算术核对评分自洽，仅提示差异，不作出定性结论）

安全隐患台账→《工贸企业重大事故隐患判定标准》（应急管理部令第10号）条款映射提示（仅提示差异，不作出定性结论）

Aquaculture input register completeness and withdrawal-period date check: deterministic findings with rule IDs.

项目全流程文件链条核对（按环节先后与金额口径核对链条自洽，仅提示差异，不作出定性结论）

Checks an FMEA worksheet for element completeness and for the arithmetic that follows from it - severity, occurrence and detection against the resulting risk priority number - following published FMEA method standards. Reports inconsistencies; it does not judge whether the ratings themselves are appropriate.

预测准确率考核核对（按准确率、门槛与考核单价核对考核费用的算术自洽，仅提示差异，不作出定性结论）

应急预案要素齐备性与条款级页码定位（依据 GB/T 29639-2020 等公开文件，仅提示差异，不作出定性结论）

控制图常数与过程能力指数核对（按 GB/T 4091 的常规控制图常数表核对控制限与 Cp/Cpk 的自洽性，仅提示差异，不作出定性结论）

应急演练脚本核对（按阶段、响应分级、指挥与资源要素核对脚本齐备，仅提示差异，不作出定性结论）

审稿意见逐条回应覆盖核对（按意见与回应一一对应核对覆盖完整性，仅提示差异，不作出定性结论）

Checks a medical-record front sheet for field completeness and for internal logical contradictions between its fields, against 国卫办医发〔2016〕24号 and other published documents. Lists what is missing or inconsistent for a human to review; it does not assess clinical correctness.