Plugins

Turns the composer's reasoning-effort menu into a draggable slider and takes over the stock model-and-reasoning-level chip. Dragging follows the pointer continuously; releasing snaps to the nearest level and submits one session update per drag. The track draws its own fill, tick marks and white knob, only the highest levels (xhigh, max, ultra) get a flowing brand-colour gradient, and both ends carry the lowest and highest level names. The same card expands into the official model list. Arrow keys step one level, PageUp and PageDown two, Home and End jump to the ends, and each move submits. A generation counter on the directory object discards late responses, and reduced-motion turns the animations off. All data comes from the stock modelDirectories directory; no new capabilities are added.

Shows the provider behind a session's current model as a compact badge in the DSH Web composer tool row, left of the model selector.

Annotates every subagent with the model route it actually ran on: a badge line in each parent-catalog row and a readout in a child session's own header.

Select text in the DSH web client and a translate button appears at the end of the selection; clicking it translates that text in place. Translation goes through the host llm service, so it reuses the model the current session already has selected and needs no separate API key; an OpenAI-compatible endpoint can be configured instead. The result opens in a popover that stays inside the viewport, with one-click copy, a row of language buttons for instant retranslation, and smart Chinese-to-English / other-to-Chinese as the default. Configuration is stored host-side and its API key is never sent to the browser.

Replaces the chat model picker with a collapsible provider-grouped list (640x720 max) that shows each model name, provider name, provider ID and exact model ID, plus a manually managed uncommon list and a separate favorites list. Classification is user-driven only: no usage tracking and no auto-sorting. Search covers model name, model ID, provider name, provider ID and account notes.

Select a passage in a DSH conversation and read a plain-language explanation in a floating panel, which carries the surrounding message as the context. Three explanation depths (plain / general / pro) that re-explain on the spot when switched; optional web search and local file lookup (the model decides by default, and a button can force one lookup that reports only what is new); follow-up questions; and a button that hands the whole exchange to a new session in standby mode - the background is queued without waking the model or spending tokens. Settings live on the host in settings.json, and nothing is written until you press save. The repository also ships an OpenAI-compatible endpoint and a browser extension (source).

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.

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.

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.

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.

Removes sandbox_permissions / justification arguments that cannot widen the call's current sandbox mode, so calls no longer fail with 'sandbox escalation to "workspace-write" is not strictly wider than this call's current "danger-full-access" mode'. GPT models tend to fill these optional fields on every call and pick workspace-write, which is narrower than danger-full-access. Runs in tools/pre-execute: compares the requested mode with the mode the session's sandbox policy resolves, and drops the fields when the request is the same or narrower (also drops a lone justification). Also understands the values GPT carries over from Codex's own shell tool: null, empty and use_default are treated as no request, and in a danger-full-access session any value (including require_escalated) is dropped because nothing is wider. Real widening requests, unknown modes and tools that do not advertise DSH's escalation schema are left to DSH core. Never widens permissions. Configurable tool list (default bash, pwsh, write, edit, run_code). Zero dependencies.

Talk to DeepSeek Harness from Feishu / Lark. A chat maps to a DSH session, messages become turns and answers are pushed back as cards; questions, permission requests, model switches and conversation switches are interactive cards, and inbound files and images are downloaded into the workspace.

Bridges DeepSeek Harness sessions to Feishu/Lark, Telegram and DingTalk: each chat is bound to a resumable DSH session, replies stream back as cards, and a task-end card reports the model, token usage, step count and duration. Question and permission-approval cards are answerable from the chat, and a web settings pane configures the per-channel credentials.

A /review command that hands the current change set to a reviewer subagent pinned to the model you choose, with one continuing reviewer session per chat.

Skill center: browse and manage local Agent Skills, and search, preview and install skills from the ClawHub, ModelScope and QwenPaw marketplaces in one merged view with source and category filters; ships a `skill_hub` tool so the agent can install skills itself.

Agent skill and tool for querying multi-platform model account balances: DeepSeek, Doubao / Volcengine, Qwen / Alibaba Cloud, Hunyuan / Tencent Cloud, and custom HTTP endpoints. Read-only, with 60s cache.

Speaker button left of the model selector in the composer tool row — one click scrolls to the start of your newest question, marks it with a blinking caret and reads from there through the newest agent reply (dsh-tts, browser voice as fallback); press-and-hold the icon and then click anywhere on the page to pick another reading start position; press-and-drag-up opens a vertical mixer for in-page media volume and system output volume.

Vision through NVIDIA NIM: mounts the bundled stdio MCP server as mcp__opencode_eyes_nvidia__describe_image, which describes an image with any of seven hosted vision models (MiniMax-M3 by default) and rotates several API keys.

Eyes for text-only models: mounts the bundled stdio MCP server as mcp__opencode_eyes__describe_image, which sends an image file to StepFun step-3.7-flash and returns a detailed description.

Observes consecutive identical tool failures and optionally pauses before the next model step, preserving original results and successful repeats, with an in-chat report in DSH Web.

Runs /single-turn and /multi-turn answers in isolated sub-agents so results stay in the current chat and never enter the main model context.

Replaces the composer model seat with a search-first picker and adds a model management page: create and edit llm-pi-ai channels, choose which of an endpoint's models exist, and declare per-model thinking ladders and capabilities.

Reuses the local model proxy of a logged-in XiaoyiWork desktop app (Windows only) so its models appear in DeepSeek Harness without a separate API key.