Plugins

Official OpenAI account model connector for DeepSeek Harness

Make the model believe it is inside the Z.ai Code (Zhipu ZCode) agent environment: replaces the harness identity opener and injects a ZCode rules skeleton with a dynamic project section. 让模型认为自己处于智谱 ZCode Agent 环境。

Codex-style /reasoning command for DeepSeek Harness Web: select the reasoning effort of the current model from the slash menu

Composer polish: the model-select button shows a per-provider brand icon and collapses to icon-only under a narrow composer row (same mechanism as the built-in access-mode button), with a generic fallback icon for unrecognized/new providers.

ESLint Security SAST bundle and model-facing scan tool for DeepSeek Harness.

DSH plugin: inject per-model sampling parameters (top_p, top_k, min_p, repeat_penalty, presence_penalty, frequency_penalty) into every chat-completions request sent to a local llama.cpp / llama-server gateway.

智能体选择器：像模型选择器一样在输入框旁勾选委派目标+具体模型，把对话任务派给外部智能体（Codex CLI / WorkBuddy 内置模型活动价 automation 桥 / WorkBuddy 自定义模型直连 / Claude Code）执行，结果流回 DSH 对话。含 agent_dispatch 工具 + composer 两步下拉 + 设置面板 + 桥健康探活 + 反冒充出处凭证。

DSH session-log repair plugin: scan every stored session, detect a seq collision in the committed region or a torn trailing record, and repair it from a one-click Web UI, model tools, or the /dsh-session-log-repair command. Installing it also registers it

Unified management and invocation of external Agent CLIs in DSH, fully isolated from the user's native installs; preset Provider, model, reasoning effort, and permissions per CLI, callable directly or like native subagents.

OpenRouter free-models browser plugin (dual-face): fetch OpenRouter models, filter the free ones (price 0 or :free), list them newest-first in a Settings tab with local search and full model info, and create a ready-to-use DSH model config (settings.yaml

A minimal reasoning-effort ruler for the DSH composer: one hairline, a sliding marker, per-model memory, optimistic switching — and a streamlined model picker.

Persistent, searchable, per-project memory for the DeepSeek Harness: decisions, rules, and sprint context in a queryable DuckDB file, rules enforced on every model request, with a full management UI in the Web Client

Intelligent sub-agent orchestration for DeepSeek Harness, with model discovery, routing, planning, and parallel delegation.

Native desktop notifications for DeepSeek Harness (dsh): run completion, model questions, and approval requests on macOS, Linux, and Windows. Includes a web settings card consistent with the dsh web UI.

Keeps an unfinished task list visible across turns. DSH clears the todos projection at the start of every turn and expects the model to rewrite the whole list, so when a turn is interrupted the plan is durably in the session log but permanently gone from the UI — and todo_write is write-only, so neither the user nor the model can read it back. This plugin registers one ordinary session/event listener, remembers the last list per session, and when a turn/start arrives whose remembered list still has unfinished work, re-appends that list so the projection stops reporting an empty plan. No fork of tool-todo and no waterfall: a plugin cannot replace the projection (the registry throws on a stateVersion mismatch), so appending the event the fold reacts to is the reachable seam. Deliberately narrow — only unfinished lists, at most one event per turn start, fails open. Verified by a controlled A/B on real sessions: identical runs differing only in whether the plugin was installed, folded through the real projection definition. Zero dependencies.

Enforces your comment policy at write time, inside DeepSeek Harness. Reads the policy from your AGENTS.md or CLAUDE.md, blocks violating writes, and re-injects the policy verbatim so the model stops drifting from it.

Digests the images in a prompt with a vision model before admission, so any model — a text-only one included — can read them without the session ever switching models, and adds a describe_image tool for image paths.

Embeds external AI chat sites in a DSH side panel through the same-origin reverse proxy with per-site DOM adapters, and adds a composer button that either rewrites the draft with the host model or runs a two-round loop: compress the conversation, optimize, send to the embedded site, capture the reply, then finalize it into the composer.

Calls your own chat.deepseek.com account as a second model from DSH: ask a question, analyze a file's line range, and check login state, plus a runtime skill and a settings-page login panel.

Groups the model picker by provider: the menu lists sources first, and each source opens its models in a slide-in side panel (default) or inline below the title, switchable by double-clicking the source title.

Search and select models in the DeepSeek Harness WebUI with a native settings card.

Model channel manager: several provider/model candidates share one virtual route (roundrobin/<group>) with failover, retry, timeout and cooldown; a settings tab edits providers and groups, runs per-model speed tests and real single-model request tests, and a seven-day health panel aggregates latency, failures and upstream token usage (input, output, cache and reasoning).

Declares per-model reasoning-effort ladders for third-party providers in the llm-pi-ai settings section, so DSH's stock thinking-intensity selector works on models the pi-ai catalog does not describe.

Live token cost for every chat in the DSH Web UI: the chat, its subagents and the whole session tree, priced from a bundled models.dev snapshot of seven providers and 139 priced models, with cache read and write rates wherever the provider publishes them and DeepSeek from its own peak and off-peak table. Every finished answer carries its own price in the transcript, and a chat that is not currently open is priced from the log instead of disappearing. Spend is costed per interval from an append-only JSONL ledger in the project folder, so logged work keeps the tariff it was billed at. On top of it: budget-aware work plans packed against a money limit, routing scenarios that show which models are worth connecting, a generated plan document in English, Chinese or Russian, and a warning when spend belongs to no plan unit.