Plugins

Two-tier model router for DeepSeek Harness — LLM-Judge routing, multi-model fallback chains, exponential-backoff failover, and task-level orchestration (DSH adaptation of pi-shift-router)

deepseek harness manim数学插件

DeepSeek Harness plugin: per-request thinking-mode switch (enable_thinking) for Qwen3-family models on OpenAI-compatible endpoints

SearXNG-backed web search provider for the DeepSeek Harness web capability seam (ctx.web) — self-hosted metasearch, no API key, no model turn per search

Recurring/scheduled tasks (轮询任务/定时任务) plugin for DeepSeek Harness: cron-driven polling jobs as real sessions, natural-language creation, model tools (polling_create/list/edit/delete/trigger) and a web UI. Install-and-go via `dsh plugin add`.

DeepSeek usage monitor for DeepSeek Harness: account balance query and token usage summary as model-callable tools.

A DeepSeek Harness plugin: model-facing reload_plugin tool that restarts one Cordis Loader entry (by entry id, module name, or MCP serverName) without touching sibling entries — respawns mcp-client server processes

DeepSeek Harness plugin bundle: qwen_vision (Qwen-VL image understanding) and qwen_generate (Qwen-Image text-to-image) tools for text-only models

Inspect and manage the live instruction chain and project skills for the current dsh session, with in-place creation and editing — what you see is what the model gets

Request Context Profiler for DeepSeek Harness — see what changed between model requests, and how cache reuse changed with it.

DeepSee: DeepSeek Harness vision, multi-model routing, and Gemini visual self-checks before delivery

Plug-in vision for text-only DeepSeek Harness (dsh) models: a `vision` tool with built-in cheap/free VLM presets, multi-image batch analysis, paste-to-hint image admission, and a web settings page with hot-reload.

Browser Web Speech API voice input: zero server, zero keys, zero model downloads (Edge=Azure, Chrome=Google speech).

Reusable Markdown prompt profiles for DeepSeek Harness with per-turn model selection, argument substitution, and state restoration.

Telemetry backend exporting turns, model steps, and tool calls to yiTrace.

Cross-session memory for the model: full-text search all past sessions (SQLite FTS5 via ctx.sessionQuery) and bring the strongest matching excerpts back into the current context.

Compaction for local models that actually fires and never bricks the session. OpenAI-compatible proxy + DeepSeek Harness engine.

Manual model probe for DeepSeek Harness: a session-view tab where you pick provider, API type, model and route, then send one real raw HTTP request over openai-completions, openai-responses or anthropic-messages — streaming or not — and read latency, TTFT, HTTP status, token usage and a three-layer diagnosis chain (API request / model response / strict check) on one screen, with errors in plain language.

Model-autonomous context compaction for DeepSeek Harness: a mind_map tool surveys the agent context surface (stable seq ids, roles, token weights, clear-boundary markers, the clear-mind playbook), a clear_mind tool replaces a chosen conversation-history span with a model-written checkpoint through the native compaction transaction, call and result pairs self-collapse into one-line tombstones, and a proactive reminder nudges the model when the context grows long or a turn runs too many steps.

Model-driven context compaction for DeepSeek Harness. The agent decides when and what to compress, commits durable session-log replacements, and ships reversible tool-result compression with byte-exact hash retrieval.

Model switching and reasoning-effort control for DeepSeek Harness: set_model and list_models agent tools let the agent autonomously change its provider, model or thinking depth (reasoning effort) mid-task with a mandatory reason, a provider whitelist and a context-window token-pressure guard, the active model is injected into the runtime context, and Plan Mode auto-transition switches to a configured planning model on entering plan mode and restores the previous execution model on exit.

Registers the Xunfei Loomy cloud channel as an OpenAI-compatible supplier in dsh-router, adding model listing and streaming chat completions.

Shows the DeepSeek account balance as a row in the sidebar footer with a refresh button, and opens a popover with the balance card, daily token and estimated-cost charts over a 7/30-day window, a per-model table, and a link to the platform usage page. The balance comes from the official /user/balance endpoint; usage is aggregated from local DSH session logs and priced with the published peak/off-peak rate card in CNY, so it is labelled an estimate and its scope is stated on the panel.

Replaces the chat input model picker with a provider-grouped, collapsible list: groups models by provider, folds vision-bridge mirror providers back into their upstream, and carries the reasoning-effort options each model declares in settings. Tested on DSH Desktop only; the DSH web build is untested.