Plugins

Injects the current date and time into the runtime context on every turn, so the agent can read the time instead of inferring it.

Graft, forward and fork DSH sessions: read a slice of one session log, export it, fork at a turn boundary, or forward a selection into another session as a self-contained graft message.

Zhihu (知乎) for DeepSeek Harness: wraps the local pyzhihu-cli as 18 zhihu_* tools — 14 read-only (search, hot list, question, answer, user, feed, topic, notifications, collections) plus 4 publishing tools that are not registered until readOnly is turned off — with a web panel in the sidebar for login, config and lookups.

WebDAV server: turns a shared directory into a WebDAV service that Windows, macOS and Linux can mount as a local disk, with token authentication, optional read-only mode, configurable directory/port/token, and per-platform mounting guides built into the settings page.

Standing instructions edited in the DSH settings UI and injected into the system prompt of every subsequent turn.

Folds streaming reasoning and tool calls into collapsed step bars and collapses each finished turn into a single summary bar; step bars show native tool icons, filenames, edited line counts, and failure counts, finished turns restore duration, first-token time, token usage, generation speed, and cache hit metrics from recorded Session events, and preferences persist on the Host. Changes browser presentation only. Requires DSH 0.1.5-alpha.1.

Auditable token ledger for DeepSeek Harness: folds the durable session log into restart-safe totals, recomputes the same numbers from the raw logs and diffs them, and turns usage into a bill by workspace, session, model or vendor, exportable as CSV or JSON.

Turns DSH permissions into 9 selectable presets (3 sandbox modes x 4 approval tiers), with rule plus LLM risk classification across four risk levels, password-gated approval for high-risk operations, and a JSONL audit log.

Injects your own saved context entries as a Remember row after each user message, per turn or once per session, with a Settings editor and a manager page.

Forces a todo list at the start of every turn and rewrites it in full each time, so finished items stay listed instead of being replaced. The floating ball shows the complete history, including plans that were lost when you cut in mid-turn, so what got done and what got dropped is always clear. Adapts DSH kernel 0.2.2-rc.1.

Local-first HTML review and annotation workspace for coding agents: opens an isolated copy of a file in a browser editor, collects text edits, format changes and element/area comments, and returns a durable handoff the agent can claim and resolve.

Coding retrospect distilled memory for DSH: distills rejected solutions, pitfalls and constraints from each turn via a local LLM, tags them into MemOS (type:rejected_solution), and boosts weighted recall on coding tasks via agent/pre-step.

Custom script manager for DSH: turn verified operations into reusable scripts that run directly via /script or register as agent tools, with parameterized scripts, declared expected outcomes, and execution history.

Installs a skill-router skill that semantically searches a local skill corpus on demand, keeping the corpus out of the per-turn model catalog.

Image generation workbench and agent tool for DSH: one tool (ark9_generate_image) paints text-to-image and image-to-image via any OpenAI-compatible API. Channels are entirely user-configured - no bundled endpoint, you bring your own baseURL, key and model name (manual input supported). Agent-initiated generations are approval-gated by default: requests queue in the floating panel and nothing bills until you approve; approval is non-blocking (the agent replies "awaiting your approval" immediately, and results, denials or timeouts are injected back so the agent reports them in the next turn). Floating glass workbench with five tabs (Generate / Approvals / Prompts / History / About), aspect-ratio grid with quality-budget + 16px-alignment sizing, transparent background, batch up to 10 images as aggregated sub-tasks, prompt library with custom JSON sources fetched through a host proxy, persistent generation logs with one-click retry, multi-channel aggregation with per-channel model fetching, bilingual UI (zh/en), stroke-SVG icon set, config import/export. Registers as a Better Sidebar tab when dsh-better-sidebar is installed; stacks above the dsh-cua FAB when both are present.

Persistent memory for DeepSeek Harness with curated facts, automatic turn retention, and graph- and vector-ranked recall.

Session health-check: mechanically mines session logs into structured problem tickets (retry loops, tool-error clusters, interrupted turns, token waste) over the official session-query seam; works standalone.

Three independent language channels for model output — tool-call descriptions (every tool-call card title, including run_code in PTC-style presets), thinking, and replies — each set to follow the web GUI language, force a specific language, or turn off (default: only descriptions, following the GUI). One global runtime-context prompt directive on the host; the client half reports the GUI language; a Settings plugin card switches the modes.

Per-provider concurrency gate on the llm/stream waterfall: holds surplus model requests in a FIFO queue inside DSH so main agent, subagents and compaction take turns on a single-slot local server (llama.cpp --parallel 1) instead of timing out; maxConcurrent / maxQueued / queueTimeoutMs.

Uses a GitHub App to report open PRs and the latest Actions run for the current repo without returning secrets.

Turns completed DeepSeek Harness public-content work into a browser-local visual magazine with explicit updates and reviewed one-article sharing.

Consent-bound one-turn voice preview for DSH Web with a credential-free local synthetic demo, optional Qwen Audio, exact Session isolation, and explicit transcript-to-draft handoff without automatic submission.

Turn every idea into an image or video with Kling AI. In DeepSeek Harness, use natural language for text-to-image, image-to-image, text-to-video, image-to-video, reference-image creation, task tracking, and result previews.

Force the agent's chain-of-thought, planning, tool-invocation reasoning, and internal deliberation to stay in Chinese — the language constraint is injected at the top of the system prompt before every reasoning step, so it cannot be diluted by tool-returned content. A settings panel lets you edit the constraint text on the fly.