Plugins
Browse, filter, and install DeepSeek-Harness plugins.
432 plugins found
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.
dsh-plugin-offline-reasoning-translator
fotlim/dsh-plugin-offline-reasoning-translator
Translates the English reasoning text of DSH sessions into Chinese on this machine, using a local Marian NMT model (ONNX, about 108 MiB) that you download once from the plugin panel (Hugging Face or the hf-mirror.com mirror). No API key and no network request at translation time; identifiers, code spans and URLs are masked so they come back unchanged.
dsh-model-tabs
lycorisradiatax/dsh-model-tabs
A zero-config composer model picker with one provider per tab, independent scrolling per provider, cross-provider search with provider badges and reasoning-effort chips; selections stay in sync with the built-in /model dialog.
dsh-effort-menu
xuanfenglajiao/dsh-effort-menu
Replaces the composer model menu with a recent-models list, a searchable all-providers flyout and a draggable reasoning-effort slider; a Manage models row at the bottom of the flyout opens the Models settings directly. It takes over the composer model slot, so install only one model-menu plugin.
dsh-plugin-dlidl
phoenixyun/dsh-plugin-dlidl
Danmaku and live-chat overlays for DSH: stream reasoning and answers as a right-hand chat timeline (bottom anchored, per-row fade, adjustable lifetime) or as Bilibili-style flying bullets across the whole window; mode-specific settings, content filters, and semantic edit announcements while files are being written.
dsh-codex-model-picker
caidows/dsh-codex-model-picker
Codex-style composer model picker: a card showing the current model and a draggable slider that sets reasoning effort, with one stop per level the model advertises and an Off stop when the provider supports it. The slider snaps only to whole stops and updates the effort label while dragging; selecting a model or effort still goes through the session model directory, so it stays in sync with the rest of the composer.
dsh-prompt-boost-model
amyaxy/dsh-prompt-boost-model
Prompt enhancement for the DSH composer, with a model picker that lists the models the host actually offers: a Boost button beside the composer sends the current draft to a model on the Host, shows the rewrite in a before/after overlay, and replaces the draft only when you confirm. While boosting, the button glyph becomes a spinning arc; once a rewrite is applied the same button becomes an in-place Undo that restores the original draft and then returns to its idle state. Settings hold the enable switch, a provider/model choice rendered as a grouped dropdown built from the live provider list (including configurable providers that are not set up yet) rather than free-text fields, temperature, output limit, timeout and optional custom instructions. Empty or reasoning-only model answers are reported with their real cause instead of a generic failure, and the Host endpoint only answers loopback requests from the same origin.
dsh-execution-narration
101011001101q/dsh-execution-narration
Translates the agent's English execution narration into Simplified Chinese in place; the final answer, tool records and reasoning stay as they are, so the official reasoning-translation plugin keeps working alongside it. Whether a step is narration is decided by a render-time structural signal, not by English phrasing, and with no signal available it translates nothing automatically. Fenced code, inline code, URLs and file paths are masked before the request. Uses the host's translator service (Bing by default, no API key).
dsh-auto-router
dakouchiya/dsh-auto-router
Routes model and reasoning effort per turn: a cheap classifier reads each request and picks one of five tiers, a supervisor model re-routes on tool errors and checkpoints, and upgrading to the stronger model waits for confirmation.
dsh-fish
zingzheng/dsh-fish
A reasoning-style row above the DSH composer with a stock watchlist and a host-backed TXT/EPUB reader; reading progress is shared across browsers.
dsh-model-pool
pure-cow-horse/dsh-model-pool
Merges your configured, runtime-registered and locally cached models into one panel, probes and minimal-request tests them, pulls each channel's upstream /v1/models catalog, and chains the keepers into named schemes. A virtual ModelPool provider fails over at request time with per-model cooldowns, exponential backoff, image-request avoidance for text-only models, and a 10-minute memory for rejected reasoning levels. Adds a token ledger by day and model with CSV export, and 21 regression probes. Not a fork of dsh-llm-fallbacks.
dsh-reasoning-adapter
hatiaa/dsh-reasoning-adapter
Gives hand-declared models on custom or relay routes a vendor-matched reasoning-effort picker: detects Claude, GPT, DeepSeek, GLM, Kimi, Qwen, Gemini, Grok, Doubao or MiMo from the model id, display name or endpoint host, fills in only the levels that vendor accepts plus the pi-ai compat fields its request format needs, and writes them into the profile config so the Models page reasoning switch turns on. Models you edit or switch off are left alone, and a Models page card hands them back on request.
dsh-unified-model
elfgzp/dsh-unified-model
Writes one model and reasoning effort into every session at once from a control beside the composer model picker, since the shipped picker only changes the session you are in. Sessions that already match are skipped, subagent sessions follow their parent instead of being written, and the same selection can be pinned as the default for new sessions.
dsh-tlpro-models
dungcsnd1133/dsh-tlpro-models
Declares two model routes in the llm-pi-ai settings section — a TLPro gateway and Z.ai's GLM-5.3 endpoint — with per-model context windows, output caps and reasoning-effort ladders, so the stock model picker can select and tune them. Requires your own TLPRO_API_KEY and a Z.ai coding-plan ZAI_API_KEY; the patch replaces the whole llm-pi-ai row config.
dsh-stellar-effort
wangtheme-coder/dsh-stellar-effort
Adds a reasoning-effort rail above the DSH composer: drag or use the keyboard to preview and submit the levels the current model exposes (Off through Max), while a procedurally rendered micro-universe contracts and collapses into a black hole as effort rises. Levels go through the DSH model-selection interface, so the rail shows the level DSH confirms, and the plugin writes only to $DSH_HOME/stellar-effort/.
dsh-effort-dial-plus
ikun1031/dsh-effort-dial-plus
A merge of the dsh-effort-dial card structure and the reasoning-slider gradient/particle effects: a Codex-style reasoning-effort card in the composer with one control for model and effort, per-level accent colors, a quota line on the top level, and a blue-purple gradient with drifting particles. It takes over the composer model slot, so it cannot be enabled alongside dsh-effort-dial or reasoning-slider.
dsh-opencode-routing
2869949486/dsh-opencode-routing
OpenCode Go control panel: an account pool that rotates A-to-B when a key runs out or stops authenticating, per-account 5-hour/weekly/monthly allowance, per-model spend with remaining quota, capability tags (image, video, text-only, tools, reasoning), a live OpenCode-vs-official cost comparison, and quota routing that falls back to a DeepSeek official subscription on an upstream limit or degradation, then returns after 10 stable minutes - shown as a current-route banner, a status card and desktop switch notices, in 10 UI languages.