Plugins

Installs an image-input checkbox into the Models catalog so a custom model can declare image input and receive images directly; includes an optional BYO vision relay.

Requires DSH 0.1.5-rc.2+. Dialog-style model picker for the DSH Web UI: fuzzy search, collapsible provider groups, favorites with a favorites-only filter, and a thinking-level dropdown, replacing the built-in model selector with official UI primitives and DSW tokens.

Zero-touch runtime telemetry for DSH: every session auto-writes task, model tier, tools, failures, duration, status into a human-readable journal with a stats section (pure observer — no tools, no LLM calls, no injection).

模型回合结束后用 LLM 生成 3 条批判性跟进建议，点击即发送 | After a model turn, an LLM generates 3 critical follow-up suggestions shown as click-to-send chips

让 DeepSeek Harness 的第三方 API 支持低、中、高等推理强度，并可为每次子 Agent 调用选择模型｜Add Low, Medium, High, and other reasoning levels to third-party APIs, with model selection for each subagent call

DSH port of TaskPlane: dependency-ordered waves run in parallel git-worktree lanes, with task packets, cross-model review, and crash recovery.

Automatic provider/model fallback chains for DeepSeek Harness agents when LLM requests keep failing (retry exhausted, auth, quota, rate limit)

Shows DeepSeek balance and estimated daily spend, merges external vision-call JSONL records, and adds a per-session dashboard with model statistics, TTFT, cache rate, call logs, cost estimates, filters, and CSV export.

The model switch for DSH: point it at any OpenAI-compatible endpoint, with curated free/cheap DeepSeek provider presets and automatic fallback when a free tier rate-limits you.

Import local Codex, Grok, Claude, OpenCode, and CC Switch logins into DSH; pick sources and enable models in Settings.

Adaptive model routing: per-request complexity classification with automatic provider routing.

Native LLM-provider vision bridge: images pasted in the chat are described by a vision model (Qwen3-VL via pi-ai/llama.cpp) and the text description is fed to text-only DeepSeek for the reply — image admission, routing and compaction all run through harness-native mechanisms, with an LRU description cache and 503 retry.

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.

SQLite memory entries, a calendar with due-time reminders, and cron-scheduled agent tasks, with 13 model tools and a bilingual zh/en UI.

Custom modes / assistant manager: give each mode its own system prompt in the settings page — a custom prompt that is a plain file the agent loop re-reads before every model step, so an edit applies to the running session on its next step — and start it from the official standard / PTC / minimal / Cordis composition, toggling the plugin rows it mounts one by one (a custom plugin composition per mode), renaming it as you like. Several assistants coexist with their own prompts, so one machine can keep a coding assistant, a chat companion and a roleplay (RP) persona side by side — a multi-agent setup you pick from per new session. Rows left untouched stay byte-identical to the shipped ones, platform conditions included.

Lists the Markdown documents, images and video that already exist anywhere in the session workspace in the DSH sidebar, ranked by relevance to the current conversation: recent messages are matched locally against document title, summary and body with IDF weighting, with no model calls and no network. Because the list is scanned from the workspace instead of remembered, restarting DSH or starting a new session does not empty it. Images and video preview in place, with relative-path images resolved and video streamed over HTTP Range. A references bar under the preview header shows which documents cite the one being previewed and which it cites, with one click to jump between them. The same ranking is exposed to the agent as a knit_docs tool, which returns the most relevant documents along with the passage that matched in each, where one is found.

Role-based multi-agent team for DeepSeek Harness. The /team command assembles up to 12 specialist subagents (product, architect, researcher, UI, backend, frontend, database, security, reviewer, QA, DevOps, docs) and runs a nine-phase gated pipeline (clarify, research, design, spec review, plan approval, implement, review, test, deliver) over a shared workspace of artifacts (SPEC, PLAN, TASKS, STATE, REVIEW, TEST). Quality gates are enforced by plugin code rather than requested in prompts: an unfinished task cannot be marked completed, quality findings must be adjudicated by the reviewer or QA role, and coverage gaps or rework over budget appear live in the overlay and in /team status. Ships a live team overlay (phases, roster with per-role models, task DAG, artifact preview, decision buttons), a persistent-team mode that resumes across sessions, and per-run token and time accounting. Zero runtime dependencies, no build step.

Multi-language codebase intelligence for MCP-compatible IDEs, the CLI and DeepSeek Harness: chat, search, audit, refactor, and board-ready reports from local code.

Per-workspace MCP scoping for the DeepSeek Harness — decide which MCP servers a session may see from the directory it was opened in.

DeepSeek Harness client plugin: adds an 'Invert selection' button to the fetch-models dialog of the Models settings section, so only the rows that are already in the model list stay checked on a second fetch + add pass.

Unofficial DeepSeek Harness settings panel for Command Code: credits, usage windows, and model-catalog sync.

Configurable send and newline keys, a composer context menu with three sources (leave it to DSH and other plugins / browser menu / plugin-styled custom menu), a quick-command panel with categorized prompt lists where each prompt can append on every send or only on the first message of a session, a create-and-move row at the bottom of each category, a prompt optimizer that rewrites the draft with a separate model call, settings-panel size memory, and automatic x-opencode-session header injection for OpenCode routes. Prompt lists live in a global ~/.dsh/quick-prompts.json that is independent of the session and the project.

Automatic approval and review for tool calls that need approval: keyword buckets match red lines without context, then a judge model classifies what was requested and sends it to allow, reject or a human according to the matching row and risk level; a judgment that never ran always goes to a human, and rejections tell the model why.

Multi-language codebase intelligence for DeepSeek Harness and MCP-compatible IDEs: chat, search, audit, refactor, and board-ready reports from local code.