CATEGORY
Verified manifests and exact versions in this category.
@gongshiyun/dsh-usage-dashboard
DeepSeek balance and usage statistics plugin: balance, current session/most recent usage, and remaining conversation counts for each model
dsh-response-meta
DSH web plugin: one live model and timing summary during every output
@dsh-external/dsh-llm-approver
LLM pre-review for sandbox-escalation approvals: an independent-context LLM gate answers sandbox escalation requests before they reach the user, falling back to the user on any failure.
dsh-token-optimizer
Deterministic, recoverable tool-result compression and cache-aware compaction for DeepSeek Harness
@dsh-external/dsh-openrouter-provider-badge
Displays the actual OpenRouter provider (such as StreamLake) and routed model above the statistics row for each conversation turn. Pure client-side plugin, compatible with DSH 0.1.1-rc.2 / 0.1.5-rc.1+.
@jcy2387/dsh-models-input-modalities
DeepSeek Harness Web plugin: per-model input-modality selector on the Models settings page for third-party (pi-ai) providers
dsh-llm-gateway-compat
OpenAI-compatible gateway adapter and dialect fixes for DeepSeek Harness
@wisexin/dsh-antigravity
Google Antigravity / Cloud Code Assist model provider for DeepSeek Harness (DSH Desktop Beta Compatible)
dsh-antigravity
Google Antigravity / Cloud Code Assist model provider for DeepSeek Harness
dsh-whale-widget-sankou
DSH 小鲸鱼余额挂件·三口皮肤版 — Modified version based on dsh-whale-widget: customizable “三口” character appearance, status, sound effects, and transparency animations, including angry and overfull reminders, plus voice interaction
dsh-peak-block
Liang Wenfeng time-based interception of official DeepSeek API requests: during Beijing-time weekday peak hours, 09:00–12:00 and 14:00–18:00, automatically intercepts model requests sent to the official provider `deepseek-official`. Requests can be switched to a third-party relay or a reserved local
dsh-cherry-provider-bridge
Synchronize a Cherry Studio custom provider into DeepSeek Harness
dsh-llm-approve-for-me
Sessionless LLM sandbox approval reviewer for DeepSeek Harness.
dsh-codex-reasoning-router
Composable multi-model agent roles and legacy Luna/Sol reasoning routing for DeepSeek Harness
dsh-loader-settlement-proof
Content-addressed evidence for recorded DSH Loader settlement
dsh-mascot-xiadie
Q版遐蝶余额小管家 — DeepSeek Harness web plugin: a floating character provides real-time updates on account balance and token usage; it can be dragged, and its image and character dialogue can be changed.
dsh-grok-image
DeepSeek Harness plugin: Grok Imagine image generation as a model tool (subscription)
dsh-missing-stop-heal
DeepSeek Harness plugin to heal third-party gateways that omit the stream terminal event (message_stop/done), which otherwise triggers repeated TRANSPORT retries in the dsh agent loop; scope is configurable per provider and per model.
dsh-plugin-cost
DeepSeek Harness cost tracker: per-turn & total token usage and billing (DeepSeek pricing, peak/off-peak aware), rendered in the chat UI.
dsh-commandcode-usage-inline
Inline Command Code plan usage badge in the DSH composer toolbar (5h/weekly window usage + remaining credits) with an upward detail popover; reuses the commandcode/report remote from @mars-sea/dsh-commandcode-provider.
@dsh-external/dsh-usage
DeepSeek usage panel: balance (API Key) + token usage (platform session token) dashboard, registered at Settings → DeepSeek Usage
@eduwork/dsh-oidc
Standards-based OIDC identity, enterprise API-key binding, declarative branding, and OpenAI-compatible model integration for DeepSeek Harness
dsh-runtime-observability
Runtime metrics and correlation API for DeepSeek Harness observability.
dsh-continue-on-limit
Auto-continue for the DeepSeek Harness Web GUI: when a small local model hits its output-token cap and the conversation shows the max-tokens notice, the plugin automatically sends a short "continue" message so the reply keeps flowing without a manual click.
@taylorswitiger/dsh-plan-bridge
Local multi-plan bridge for DeepSeek Harness: use your existing ChatGPT Codex, Claude, ZCode (GLM) and Qwen subscriptions through one loopback proxy, with a settings-page status card and one-click provisioning. No dsh core changes.
@ycp424c/dsh-luna-vision-bridge
DSH LLM adapter that transcribes native image attachments with Codex Luna before delegating to DeepSeek
dsh-tool-lipsync
FreeLipSync lip-sync talking video panel — an embedded DSH interface panel for uploading, text, audio, model selection, free generation, and recent generations. No Key or login required; does not consume model tokens.
dsh-plan-bridge
dsh-web-search-zai
Z.ai and Zhipu web search for DeepSeek Harness, with Coding Plan MCP quota, REST API billing, and bilingual settings.
dsh-token-speed
DSH web plugin: a draggable ring-gauge dashboard pinned to the bottom-right that shows live model output speed (tok/s), with an expandable detail panel (per-step exact speed, TTFT, cache-hit rate, cache read/write, reasoning and input tokens, model, cumulative tokens).
