Plugins

Remotely control DeepSeek Harness sessions and workspaces from QQ (official Bot API v2, direct chat only): list and switch workspaces, create sessions, compact history, switch models, with streaming, markdown and approval forwarding. Access is not gated per user — anyone who can message the bot controls these sessions, using your model quota and file permissions.

Universal Model Context Protocol (MCP) bridge for DeepSeek Harness: connects agents to stdio/sse/websocket MCP servers with a 10k dormant scale engine, sub-millisecond BM25 tool search, dynamic token budgeting, and a real-time web UI dashboard.

TypeSafe Jev (System One decision model) as the jev_decide tool for DeepSeek Harness: noul, choice and score questions return calibrated probabilities; credentials reuse the DSH credential seam; 429/529 backoff retry built in.

Use the Jev (System One) decision-model paradigm with any OpenAI-compatible LLM — no TypeSafe key required. Registers a jev_decide tool that returns probability-distributed answers to typed questions (choice/score/boolean) in one call.

Visual goal lifecycle for the DSH web UI: a composer dock to create, multiline-edit, pause, resume, complete and clear session goals with live round progress, plus a phase-dot composer entry and a settings-page goal overview.

TypeSafe Jev as a first-class Cordis service and three model-visible tools for DeepSeek Harness — offline by default, egress disclosed, never default-on.

One-line clock context for DeepSeek Harness: a Current time timestamp reading (weekday, date, time, UTC offset, IANA timezone) opens every conversation turn and a Turn ended reading closes it, so the model always knows the time, date and idle gap across turns without asking.

Shows which graft index a dsh session is serving and whether it still matches the code, and gives the model graft_ask, graft_grep, graft_callers, graft_skeleton and graft_map as native tools.

Exposes OpenCode Zen free models to DeepSeek Harness with no API key, tracking Zen gateway changes.

Adds a 3D model library in its own conversation tab, where agents store models built from CadQuery scripts or supplied as tessellated meshes; the library previews them with three-cad-viewer, organises them into folders and exports them to 10 formats including STEP, BREP, STL and DXF.

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.

Lazy MCP gateway for DeepSeek Harness: one stable proxy tool instead of N tool schemas, servers connect on first use and idle out, metadata cached to disk.

Model picker for the DSH web composer that replaces the model seat: a search-first popup whose left column indexes the suppliers and scrolls the grouped list, with a favorites group pinned at the top, image icons separating native from bridged vision input, and a reasoning-effort panel opened from the right zone of the trigger.

Adds a reasoning-level editor with OpenAI and Anthropic protocol presets (llm-pi-ai), input-modality switches and a 1M/128K context and max-output preset to model rows in Settings.

Shipped with cc-safety-net-style mechanical safety-net rules appended; supports both no-model and model-assisted security review, in modes such as 自动审查 (auto-review) and 机械直通 (mechanical pass-through). P0–P4 deterministic-first permission gate with permissive tier, learning sedimentation and approval-history UI; hard-deny credentials and protected paths, auto-allow internal read-only tools.

Per-model system prompt injector for DeepSeek Harness: append custom prompt text to the END of the system prompt for locally configured models, matched by exact provider/model route or a provider-wide provider/* rule (both stack in order). A Settings page lists every configured provider and its models for per-route editing with instant effect, and rules persist to DSH_HOME so they survive restarts. Applies to main sessions, subagents, and workflow children alike.

Adds a settings page for declaring per-model reasoning efforts and vision support on pi-ai provider routes.

Stops a streaming model call when the same string repeats ten times in a row (threshold configurable), keeps the partial answer as a normal assistant message, and shows a stop notice with the workspace, session name and the repeated string. Repeat counts can vary by unit length through a piecewise table or a JavaScript module, and code regions (fenced, inline, indented) use a relaxed threshold.

Host-side guard that lets the write tool only create new files: when the target already exists it denies the call before execution and tells the model to use edit instead, applied to all sessions.

Supervisor-style workflow orchestration over top-level sessions: confirmation-gated batch dispatch, team workstreams, steering running tasks, idle-wait collection and live model-route discovery across 11 task_* tools plus a /tasks slash command.

Injects durable user-set must-do and must-not requirements into the model at conversation start.

ACP adapter that drives DeepSeek Harness from Obsidian Agent Client (and other ACP clients): list, resume, fork and delete sessions, switch the model per session, preview a one-line summary, import external ACP sessions, and pull Obsidian Agent Client conversations into dsh native session storage. Requires DSH >= 0.1.5-rc.3.

Tokenrhythm (基元律动) finance dashboard for DeepSeek Harness: account balance & expiring credits, category-filtered model price cards (with discounted prices), service status and platform key management; login via platform account or session cookie — credentials stay on the local host.

Drag-and-drop / paste / upload files and images; on non-multimodal models images are auto-described by a configured VLM.