プラグイン

Provider-aware account balance chip for the DSH sidebar, showing the active model provider balance for DeepSeek, OpenRouter, Moonshot/Kimi, Zhipu/GLM, and MiniMax, plus DeepSeek peak/off-peak status.

Cross-session TODO board as a draggable floating panel: tasks are grouped by working directory and reorderable by drag, each one carries a run mode (remind only, continue in the current session, or open a new session in the same directory), up to four attached images sent to the model as real image attachments, and an optional local time it may run at; two checkboxes track AI-done and user-verified, and the agent picks up the next unfinished task in that directory when it finishes one.

Replaces the native DSH reasoning-level option list in place with a draggable Off, Low, High, and Max slider while preserving the official model-selection flow.

Live2D avatar stage and desktop companion for DSH: bundled Haru sample, custom Cubism 2/3+ model loading with scale and position controls, a draggable in-page pet, an optional transparent always-on-top desktop pet window, per-conversation expression prompt control, and opt-in voice with self-hosted ASR/TTS.

Per-provider request headers in the DeepSeek Harness Models settings page, with per-conversation ${sessionId} expansion.

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

固定新会话默认模型与 Agent 预设模式，并支持按工作区独立绑定

Automatic model-tier routing for DeepSeek Harness: one user instruction enters, one tier decision comes out — complex intent is planned on the strong tier and implemented on the cheap tier, simple intent stays cheap throughout, with a deterministic guard and a TTL escalation fallback.

PK 2-10 models on the same prompt, files, and tools in DeepSeek Harness.

DeepSeek Harness plugin: expensive models plan and review, cheap models implement, a program loop keeps the factory inside budget.

dsh plugin: persistent whole-machine LLM usage ledger with a markdown /llm-stats report (GFM tables + emoji: tokens, cache hit, model/tool time, per-day bars)

DSH web plugin: a LiveBench tab in the Trajectory view (right of 对话/轨迹). Run LiveBench evaluations against every model configured in the DeepSeek Harness — pick provider/model, category, task, release and question range from dropdowns, watch progress, and

Reminders and task timing for DeepSeek Harness: interval alerts while the model runs and overdue alerts past the planned time, plus a persistent red decision alert when the model needs your input (in-app reminder cards with sound while you are in DSH, system toasts when you are away, configurable or keep-until-dismissed card dwell time, and clicking a card jumps to its session); plan time per session, count model runtime only, and report actual vs. planned when the task ends, with a task board and persistent local records.

Adds Token Market as an OpenAI-compatible model provider with DeepSeek V4 Pro, Kimi K3, and GLM-5.3.

Declare whether a configured third-party model accepts image (multimodal) input; writes the modality into the owning provider settings and verifies it through runtime model resolution.

DSH (DeepSeek Harness) 插件：为每个 LLM 模型配置默认推理等级（reasoningEffort），并在请求进入底层调用链前按路由规则自动补齐

Session-header button that previews and downloads the exact request frame DeepSeek Harness sends to the model: the full system prompt, the declared tools array, and the wire message array (system/user/assistant/tool-result) rebuilt from the session log via the same folds the agent loop reads.

Real-time DeepSeek API balance (official endpoint) and today-spend estimate (this DSH instance session-log usage x per-model price table) for the DSH web: composer dock strip, always-on floating badge, full settings dashboard (7-day trend, per-model cost, editable price table and polling, history rescan). The API key never leaves the host.

余额与费用：DeepSeek 余额、本次/日/周/月花费、各模型用量与实时单价。Balance and cost panel for DeepSeek Harness: balance, spend, per-model usage, live pricing.

Decides whether Python code is original or a derivative work: reports the longest identical expression span against an upstream tree, an exemption rationale per finding, and a risk list. Pure stdlib `ast` analysis — offline, no model calls.

Auto-switch DeepSeek models: routes every request to the vision model when images are present, to the pro model for complex tasks, and to the fast model otherwise; includes a switch_model tool for manual overrides.

PowerContext for DeepSeek Harness: WorkBuddy-style project memory and inspectable handoff workflows - bounded context recall before each model step, 19 pc_* tools for memory, handoff, experience and skills, with a Windows server watchdog for resident operation.

Dual-endpoint Zhipu BigModel GLM provider catalog (Coding Plan and ordinary API) with live model discovery, live-tested thinking-tier mapping, and a settings card for keys, endpoints and the default reasoning tier.

Auto-fills reasoning-efforts, context windows, output limits and image modality for models from unofficial (custom) providers, with data from models.dev. Also provides setting cards to control plugin's behavior.