Плагины
Находите, фильтруйте и устанавливайте плагины DeepSeek-Harness.
Найдено плагинов: 472
dsh-connect-loomy
hxgh776/dsh-connect-loomy
Connects the locally signed-in Loomy (iFlytek) desktop account to DeepSeek Harness: chat models with reasoning and tool calls executed locally by DSH, plus a read-only credits dashboard (total balance, daily allowance, available balance). Reuses the Loomy app's own session file without copying or storing credentials; doctor and probe CLIs included. Windows x64.
online_model_discovery
dhllib/online_model_discovery
Adds live model discovery and per-model reasoning-effort editing for third-party pi-ai providers, and automatically fills compat switches for models missing from the bundled catalog, fixing 400 errors caused by an unsupported developer role.
dsh-team-switch-place
zrrrrrrr77/dsh-team-switch-place
Puts the Agent Teams switch above the model and reasoning rows in the composer menu, out of mis-tap range. UI-only, no tokens; Tab lands on the reasoning row.
dsh-model-fallback
carlcn2003/dsh-model-fallback
Primary and multi-level backup model failover router for DSH, with cross-provider reasoning-effort clamping, exponential cooldown, per-turn recovery, and a settings panel.
dsh-composer-model-controls
timxiang-948/dsh-composer-model-controls
Reasoning-effort control for the DSH composer — an adaptive effort slider whose track and composer border tint with the level, plus Shift+Tab cycling; the built-in model menu stays untouched.
dsh-chat-spacing
imcaibaicai/dsh-chat-spacing
Unifies the conversation flow gap and the indent, margins, card borders and radii of expanded reasoning and tool bodies through CSS variables, with one live stepper per knob in Settings → General.
dsh-search-pull
studentbuilding-studio/dsh-search-pull
Pushes the agent to search the web before answering instead of relying on memory — especially for library choice, version and error questions, where reusing an existing open-source solution beats reasoning from scratch.
dsh-chat-reply-coach
ximing-chat/dsh-chat-reply-coach
A DSH plugin that generates high-EQ reply suggestions based on chat context, with reasoning and strategy.
dsh-mode-switcher
qrak/dsh-mode-switcher
Adds a Plan/Build switch to the composer chip and to the Tab key, keeping a separate model and reasoning effort per mode and restoring them on every toggle, /plan, and plan approval.
dsh-longtask-guard
zhangyahao/dsh-longtask-guard
Externalizes oversized assistant and tool messages in long sessions into project files while keeping a recent window, and archives reasoning from empty turns as a visible message so long tasks do not stall on context size.
dsh-project-hub
shipinlei/dsh-project-hub
Project workbench for DSH: groups sessions by project (workspace) in a panel with project cards and session lists, applies a project's default preset, model and reasoning effort to new sessions, scopes memory per project on request, previews AGENTS.md/CLAUDE.md read-only, and groups the sidebar by project at startup.
dsh-nanogpt
taxah92/dsh-nanogpt
NanoGPT PRO subscription models for DeepSeek Harness: a curated model picker with ×1/×2 rate badges, reasoning levels and the remaining weekly quota, without spending the subscription allowance.
dsh-prompt-polish
minus77/dsh-prompt-polish
Polishes the composer draft: opening the panel optimizes once with the default template, replacing the draft shows a line-by-line diff first, and a 9-second undo sits on the entry pill. Five templates (basics, structure, examples, reasoning, iteration) switch without spending a call; history and version chains stay on this machine, and the UI follows the Harness language.
dsh-question-bubbles
3341284397-max/dsh-question-bubbles
Surfaces the questions a model almost asks but never voices — bubbles above the whale widget pick them up from the reasoning stream in real time, and you can answer one in place so it is folded into the next step without interrupting the run. Supports a prompt-marker protocol that lets the model mark its own doubts, five languages, DSH light and dark themes, and depends on dsh-whale-widget for placement.
dsh-chinese-reasoning
yingshuozhang/dsh-chinese-reasoning
Makes a DeepSeek Harness agent reason in Simplified Chinese: each turn it appends one runtime-context instruction at the end of the conversation, and it can keep a stable declaration in the system prompt as well. Settings pick Simplified Chinese or off, and whether that declaration is included.
dsh-gpt-adapter
lxjmaster/dsh-gpt-adapter
DeepSeek Harness plugin for GPT models and Codex instructions, skills, plugin resources, and MCP configuration.
dsh-thinking-channel-guard
laoyingfuhuole/dsh-thinking-channel-guard
Moves reasoning that a provider leaks into the visible text channel back into the reasoning channel, and emits a text block when a whole turn of answer text lands only in the reasoning channel. Catches three shapes: `<thinking>`-tagged text, text that continues a reasoning tail which ended mid-token, and an answer-only reasoning turn that stops. Healthy streams pass through unchanged, block order is preserved, and each of the four rules can be switched off in one JSON config.
dsh-doom-loop-guard
dixiewithheart/dsh-doom-loop-guard
Detects repetitive loops in an agent's reasoning output and records, nudges, or cuts them, with a history report. Defaults to a nudge (a reminder injected into the next request); cutting and auto-resuming is opt-in, and should not be combined with another plugin's cutting such as dsh-loop-rescue. Needs DSH 0.2.1+ and Node.js 22.15+.
dsh-session-wake
waning-sun/dsh-session-wake
Wakes a DSH conversation on demand and hands work to it: pick one or more sessions to auto-wake when DSH starts, give each session its own provider, model and reasoning effort, and let the agent call another conversation with the session_task tool — it wakes that session, delivers the content, waits for it to finish and brings the answer back. Also ships list_sessions and wake_session tools plus a settings page titled 会话唤醒; no QQ or bridge dependency. The three tools are available to every agent and can reach any session in the profile; the auto-wake list is empty by default, a session's boot prompt is delivered at every DSH start, and session_task waits up to 300 seconds by default.
dsh-model-radar
chip-g0202/dsh-model-radar
Runs a four-task, 150-point model intelligence benchmark inside DeepSeek Harness (Qin 60, Pompeii 45, Pelican 22.5, Candy 22.5): each selected model × reasoning-effort pair executes every task in its own isolated subagent session, Qin and Pelican are graded by the selected judge model against rubrics, Pompeii and Candy programmatically, and batches keep scores, artifacts and cost. Adds a 0–1000 real-world performance score per model × effort computed from local session logs across seven dimensions (output speed, first-token latency, reasoning speed, tool cadence, tool latency, tool success rate, cache hit), with baseline deltas and controlled speed runs, plus a sidebar page with ranking, performance, history and settings views. Each batch spends real tokens of the candidate and judge models, and candidate subagents get file and bash tools inside an isolated run directory.
DSH-Translate
light-cheng/dsh-translate
Bilingual reasoning, selection translation, composer polish, an offline English–Chinese dictionary with IPA, pronunciation and a vocabulary notebook for DeepSeek Harness. Instant selection translation is on by default and, on the cloud engine, sends the selected text to the model; pronunciation audio is fetched from Youdao when clicked or hovered; the bundled dictionary data (ECDICT and ipa-dict) is GPL-3.0.
dsh-model-effort-chips
dreamaniax/dsh-model-effort-chips
Splits the composer model seat into a model chip and a reasoning-effort chip: the effort chip opens a draggable, wheel-adjustable slider, and the panel behind it animates 36 canvas effects across 12 categories.
dsh-model-quick-selector
arrosam/dsh-model-quick-selector
Adds a quick-select model list to the DSH composer model button: a settings icon on the Model row of the model menu opens a dialog to pick and reorder favourite models, dragging vertically on the model button switches between them on release, and dragging left or right steps the reasoning effort; the menu's reasoning-effort row also gets a draggable slider (based on Microqian2th/dsh-codex-effort-slider). Text follows the DSH language setting (English / Chinese).
dsh-chinese-thinking-mode
qiao-fang/dsh-chinese-thinking-mode
Delivers one required user-role runtime context that makes the agent reason in Simplified Chinese and keep a whale-loli in-thinking persona (calls itself 本鱼, lazy-arrogant tone) in both reasoning and the final reply, while proper nouns, identifiers, paths, commands, URLs and error text stay verbatim; persona, extra proper nouns and context order are configurable. Enabled by default for every agent in the profile, subagents included.