Plugins

Chrome DevTools Protocol Plugin for DeepSeek Harness. Use chrome-remote-interface to connect to and control Chrome via CDP. The connection includes a graphical interface.

Web search provider for the ctx.web seam that routes the DeepSeek web_search tool through a LiteLLM proxy using the OpenAI Responses API, reusing LITELLM_API_KEY.

Answers hard questions by staging a formal debate: two adversarial subagents argue opposite sides with research, then the main agent rules on the transcript through the debate_open, debate_round, and debate_verdict tools.

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.

Session handoff for DeepSeek Harness: the session menu creates a successor session that rebuilds the old session's memory, tasks and rules through an eight-section takeover packet, with light context via on-demand transcript readback.

Pin and unpin sessions to the top of the Web sidebar with a dedicated pinned panel, archive section, and native three-dot menu integration.

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.

Gemini-styled skin restyling the conversation ground, sidebar rows, hero greeting and composer through one stylesheet over the --dsw-* tokens, with light and dark both covered.

DeepSeek Harness plugin that aggressively saves tokens without affecting task quality: lossless head/tail truncation of tool results (default), grep-result folding, pressure-triggered dsh-compaction-basic delegation, and an LLM-summary CompactionEngine subclass for the aggressive mode. Saves 97.6% of input tokens on an 8-scenario synthetic suite, with all reductions routed through dsh event flow so model-visible = logged stays intact.

Drive your real logged-in browser through OpenCLI — browser primitives plus 170+ site adapters as deterministic one-shot commands, with in-session adapter authoring, a write-approval gate and a settings management panel.

Annotate on selection, persist through refresh; send the notes with your message and the model answers each one.

Routes DeepSeek Harness outbound traffic through a local Clash proxy, with automatic fallback to direct when the proxy is off.

Zhipu GLM web search provider: registers as `glm` on the ctx.web seam and runs the native web_search server tool through GLM's Anthropic-compatible API (Coding Plan billing).

DeepSeek Harness rate-limiting plugin that prevents API 429 errors during long-running tasks, with task retrospectives.

Provider-first three-level model selector for the DSH Web model seat: pick a provider, then a model from that provider, with inline search on both levels, failed-provider retry rows, and a Model · Provider trigger.

Routes the harness through the OpenLLM gateway: a pure-config Cordis patch that adds an `openllm` provider to the in-box pi-ai adapter pointed at the local daemon (`127.0.0.1:8787/v1`, no API key held by dsh) and registers the `openllm mcp` stdio server (openllm, claude-context, supermemory tool groups).

Web search for DeepSeek Harness through Z.ai or Zhipu, with Coding Plan MCP quota and REST API billing modes, a native bilingual settings card, and support for reusing an existing ZAI_API_KEY.

Provider/model-aware adaptive pacing and visible rate-limit retries for DeepSeek Harness free models.

A permanent DSH plugin that bundles a developer workbench, an in-session conversation tree, and a plugin manager: build and run an LVAL project, browse its code, and keep per-program version snapshots with rollback; edit, retry, or branch any message in place, with message micro-versions; a feature manager plus a global-plugin library whose entries each carry an enable tier; cross-dialogue memory, one-shot temporary chats, and model collaboration; five network-permission tiers, mixed-model routing, a security audit, and browser control through a companion extension.

Augmentor for DeepSeek Harness: DSH plugin + Chrome extension that drives the user's real browser from any DSH session — live page snapshot, click, type, tabs — with save-to-workspace chat sessions.

Three-layer skill management for DeepSeek Harness: a library pool, per-workspace enablement whitelists, and per-session picks, with a Web settings panel, a conversation-embedded view, a skill file browser/editor, zip and folder import, and engine-load validation.

Type /tabs to pick a browser tab (via chrome-devtools-mcp) and auto-fill its URL into the composer.

HTTP network debugging toolset for DeepSeek Harness: a general-purpose HTTP client with SSRF/private-network protection, per-session request history with replay, response inspection and HAR export - three dsh tools plus a zero-dependency CLI.

Runs headless-style tasks through the live dsh web process (POST /x/headless + GET status + SSE events) so CLI-invoked sessions appear in the Web UI in real time.