Plugins

Auto-migrate Codex desktop-pet skins into DSH: an animated corner pet that mirrors agent state (thinking, tool use, awaiting approval, failed, done), with per-session frosted-glass dialogs and a full settings panel.

A desktop dynamic island window for DSH (tested on Windows) that shows whether the agent is thinking, replying, running tools or waiting for approval; expanded, it shows plan progress, context and token usage, and lets you stop the task, approve permission requests and answer the agent's questions, with a separate usage window that estimates cost from DeepSeek's official prices. The island window needs an existing Electron runtime — reused from the dsh-orb plugin's downloaded runtime or pointed to by DSH_ISLAND_ELECTRON — and DSH Desktop 0.2.1-rc.5 on Windows; the package neither bundles nor downloads Electron.

Model switching and reasoning-effort control for DeepSeek Harness: set_model and list_models agent tools let the agent autonomously change its provider, model or thinking depth (reasoning effort) mid-task with a mandatory reason, a provider whitelist and a context-window token-pressure guard, the active model is injected into the runtime context, and Plan Mode auto-transition switches to a configured planning model on entering plan mode and restores the previous execution model on exit.

Prompt enhancement for the composer: an "✨ Enhance" button rewrites your draft prompt into a clearer, more structured version with first-principles thinking, grounded in session context, memory and recent conversation; asks clarifying questions in a card when key info is missing, then previews the result before applying it to the input.

Codex-style review of session file changes: per-turn cards (optionally taking over the shell edited cards) whose totals are the turn net diff, a review tab with syntax-highlighted diffs that never wrap, real line numbers, open-at-line and a draggable split, a hover preview of the whole file with three lines of context around each change, one-click per-turn revert, and the on-disk record size with a clear button in the review toolbar. Records are sharded per session, with content-addressed snapshot blobs that dedupe and are garbage collected. Light/dark presets follow the DSH theme, typography follows DSH and installed skins (or any font on the machine, with a px stepper), and a settings switch injects a think-in-Simplified-Chinese rule into the global AGENTS.md.

A thinking level stored per provider and model, so reasoning effort outlives the session it was set in and also reaches subagents, which dsh never asks. The in-session picker still wins, and a model with no row keeps its provider default.

Cross-session archive: overview workbench, folded timeline, subagent lineage, full-text search, rule+LLM summaries, ZIP export, live tracking. Native session-page embeds: turn rail, docked right panel (live mode, pinned to original session on switch), rename (official-synced), conclusion digest, health monitoring + persistent header chip (idle / active / tool-wait / stalled). dsh v0.1.2+: fuses with the official TurnNavigatorRail — vector-icon info chips (duration, tool calls, errors, thinking) plus lazy tool distribution inside the official preview card, right-click opens the workbench; the classic piano-key strip is on by default and delegates unloaded-turn jumps to the official auto-load engine; the official rail can be hidden entirely. Settings dialog section with 10 tunable behavior params.

Bridge dsh session status to the cc-pet desktop pet bubble: thinking, tool calls, and completion in real time.

Cristiano Ronaldo desktop pet for DeepSeek Harness: a chibi Portugal number 7 mascot in a bottom-right overlay whose animation follows the agent state — dribbling while tools run, thinking during a turn, waiting at approvals, diving on errors — and jumping in a SIU celebration with a host-process sound when a turn completes; it can be dragged, looks at the cursor on hover, dives on a triple click, and a settings panel manages several pets and imports custom spritesheets. It also runs as a borderless, always-on-top native Windows window that keeps living after the browser is closed: hovering shows the current workspace and conversation title, double-clicking opens the Harness page in Edge, and dragging, mouse-wheel resizing and a right-click menu work there too, sharing position, size and behaviour with the web panel. Pet sheets may use any cell resolution and scale preserving aspect ratio (atlas.scaling: smooth | pixelated). v2.2 adds a video route — feed it a clip (green screen or ordinary footage) and its real motion becomes the pet animations, via automatic backdrop sampling, chroma keying with spill suppression, motion-based segment splitting and union-bbox alignment; already-extracted PNG frames work too, with no video decoder installed, and the clip audio can be cut into per-action sounds. Pets can also be published to the community gallery under the DPSL-1.0 sharing declaration, and installed from it in one click. v2.3 adapts it to DSH 0.2 desktop clients — the celebration sound now falls back to spawning PowerShell when the host no longer provides the shell service — and makes a single click play a short, configurable taunt animation (`interactions.clickAnim`).

Model Capability Manager for DSH Web: thinking levels, context window, output caps, input modalities, gateway compat presets, EN/中文 UI.

Feishu/Lark IM channel for DeepSeek Harness agents with native thinking-process messages, approval cards, live goal and todo cards, workflow fan-out lines, session text search, and background job and subagent settlement notices. Access is bounded by the Feishu app's own visibility scope by design — anyone the app admits can drive the agent and answer its approvals unless the optional sender, group and approver allowlists are filled in.

Collapse noisy messages (Think, Bash, etc.) in conversations.

Use DeepSeek's web chat inside DSH: real chat history in the leftmost sidebar, a Chat/Work switch beside the agent mode, plus streaming answers, thinking, web search and file uploads.

Thinking levels, image input and image generation for third-party models in the official Models page; multiple keys per provider routed by model, automatic failover between keys on failure, per-route custom request headers, and balance display.

Fills missing context window, max tokens, thinking levels, and image input on custom DSH models from models.dev, and lists unmatched models for manual edits.

Plugin governance: new/updated plugins stage in a candidate area first, then hot-mount after startup — success promotes, failure auto-disables, repeated failures freeze, one-click safe mode, sidebar diagnostics panel (npm: `bsfeng-dsh-guardian`).

Browser notifications and a beep when a session turn ends, the agent asks a question or approval is pending; clicking the notification jumps to the session; remote trigger endpoint and SSE channel (npm: `bsfeng-dsh-notify`).

DeepSeek Harness 微信网关适配插件：复用 DeepSeekAdapter + 流式 think 标签转译

Tool-use visibility for dsh: an act wrapper and guard make every ordinary tool call carry a describe field (direct calls are rejected by default), the model narrates decisions in plain text, and live act cards with thinking, purpose, status and result show in a strip under the composer and, with the optional dsh-better-sidebar plugin, in a right-side digest panel. Also adds a background event tool for long tasks.

DSH plugin: smooths running-turn thinking and tool output across all Work details modes, with a capped following window in Compact/Standard and row-level pacing in Detailed/Verbose.

Ollama Cloud provider for DeepSeek Harness: adds the chat route on install, publishes each model's own thinking levels for the composer effort control, keeps the model list current from the endpoint (/api/tags and /api/show, cached for offline boots), reads the account allowance from /api/balance into the Models page and a sidebar row that hides itself when the endpoint reports none, and offers Ollama's web search and fetch as selectable DSH web providers.

Writes the harness agent live state (thinking, working, waiting, done, error) to a state file that a bundled Electron Live2D desktop pet polls, so the pet bubble and face follow what the agent is doing.

Keeps a pool of models and routes every agent step to one of them with its reasoning effort set — configured by clicking in the composer, no JSON needed. The router takes over the composer's model cell, so one control shows the session's model and reasoning effort alongside the router's own settings. Three authorization scopes (model / effort / full) where a manual pick only counts in the scope that owns it, and in effort scope the router is bound to the one model you choose. Task presets with per-model weights, vision routing for image steps, session signals (active todo, context pressure, token budget, subagent depth), and an optional semantic task classifier. Thinking stays on, because DeepSeek rejects a thinking-enabled request whose history contains a tool call made with thinking off.

OpenCode Go subscription chat for DSH with per-model Completions, Responses, or Anthropic protocol selection, model discovery, context, vision and thinking metadata, effort defaults, and usage meters.