Плагины

Marks models in use by other running sessions in the DSH model menu, and restores the remembered reasoning effort and group collapse state for each model.

Aggregated status badges on collapsed sidebar groups in DSH: a folded folder row shows in-progress / awaiting-approval / done / scheduled / review-pending counts, with numbers and hover detail. (sidebar badge / group status / aggregate)

A small pet in the corner of the interface that reads the real event stream instead of guessing: it drifts when idle, speeds up while the agent is thinking, draws a flowing line per running tool call, turns red and shakes with the error summary on a failure, and celebrates a turn that ran longer than ten seconds. The same widget is the at-a-glance busy and error indicator, so there is no spinner to stare at. The host half folds real harness events into a snapshot and the client half only draws it; it performs no content recognition, and it positions itself away from the composer so it never sits over what you are typing.

Small DeepSeek Harness affordances for everyday actions — locate the current session from the sidebar header (Cmd/Ctrl+Shift+D), copy a session ID from the session row menu (Cmd/Ctrl+Shift+C), open links in the system default program including localhost, open or copy inline code from a context menu, open changed-file cards with a local IDE or reveal them in the file manager, swap Enter with Cmd/Ctrl+Enter, recall sent messages with Up/Down, and show the current workspace name inside the header open button; every one of them has its own switch in a Flow settings page.

Sidebar layout fix for the DSH Web UI: caps and scrolls the plugin-action area, shrinks the inline pairing QR code and tightens the brand row, so the workspace and session list stays clickable when footer plugins grow tall.

Chinese summaries for the dsh-skill-mcp-panel skill cards: each expanded card gets a short Chinese overview, a category tag and a few bullet points, while the English description the panel already renders is folded behind a "原文" toggle. Skills missing from the bundled map are translated on demand by the host with your current default model and cached on disk, keyed by a hash of the original text, so a new skill needs no manual entry. Skills whose own description is already Chinese are skipped.

Selection comments and quoted conversations (dsh划词评论 / dsh-huaci-pinglun), based on the MIT-licensed BangBang-03/dsh-client-ui-quote 0.11.1 with attached textarea measurement, border-aware height and long-text scrolling.

Unified install for DS Bot and the Codex-style sidebar: one package that mounts both and fixes their layout conflicts (composer alignment, sidebar footer, account entry, conversation width).

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.

Connects TypeSafe/Jev, Cloudflare/Clef, Nace/Drex, self-hosted Laya, and custom decision providers through one interface for agent and plugin classification, filtering, scoring, and image-object localization with structured results.

Subagent model control: a Jev classifier labels each turn, and the subagent request itself is rewritten to the provider, model and reasoning effort that the label maps to, at the agent/request hook; a per-session inherit/auto/manual selector, one prompt per role injected ahead of the task, and offline replay of past verdicts.

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.