Plugins

Session-memory autopilot: watches DSH sessions and extracts OKF entries in-process through the harness LLM (ctx.llm, deepseek-official by default) at idle, commit, compaction and end checkpoints, storing them via the vault MCP server.

Project-level Local Context Engine for DeepSeek Harness: retrieval/compression/prioritization over history, code, files, user preferences and agent trajectories, producing a dynamic context window for any LLM.

Adds a handoff button to every assistant message that writes an LLM-summarized handoff document of the current conversation into the workspace handoff/ directory.

Governs multi-model access, monthly credits, manual/quality/credit/auto routing, failure rerouting, and usage auditing for DSH.

Command Code LLM provider plugin adapted for DSH-Desktop 0.7.1: registers a commandcode route, with a live model catalog, reasoning-effort support, and real-time plan usage display.

Qwen Token Plan CN Responses provider for DeepSeek Harness via the OpenAI Responses API, with Qwen server-side tools, DSH local function tools, text/reasoning/tool-call multi-turn history, persisted image attachments, and a per-release official model catalog snapshot.

LLM request retry plugin for DeepSeek Harness: when a model request fails with a configured HTTP status code, machine code, or provider field=value match, it sleeps for the per-rule delay and re-issues the request automatically, so subscription quota and rate-limit errors (429 / insufficient_quota) do not interrupt a run.

DeepSeek Harness plugin that aggressively saves tokens without affecting task quality: lossless head/tail truncation of tool results (default), grep-result folding, pressure-triggered dsh-compaction-basic delegation, and an LLM-summary CompactionEngine subclass for the aggressive mode. Saves 97.6% of input tokens on an 8-scenario synthetic suite, with all reductions routed through dsh event flow so model-visible = logged stays intact.

Mounted owner of the LLM Providers Settings page: provider cards, drag-reorder card order, and picker sort.

Resident Web overlay seat with its own assistant session: chat, images, reminders, a duty heartbeat, and on-demand read-only task reference.

Provider health dashboard as a Settings page: read-only per-provider status, health (time-decayed from recent errors), thinking capability, max tokens and latest error, sourced from the llm-pi-ai config and the compat-healer error log.

AI-generated curiosity & trivia plugin for the dsh web GUI (Curio in the English UI): 「开始探奇」 generates a fresh batch of unexpected knowledge (excluding everything already seen), each item unfolds into two deeper layers plus similar knowledge points, and 「探奇清单」 keeps the full history (batch, items, layers, similar points) in browser storage. Reuses the host LLM channel with zero config; when no model is available, a DeepSeek API key can be pasted into the panel. Output language follows the DSH UI language (zh/en).

Use local MLX-LM or MLX-VLM models in DeepSeek Harness through a loopback OpenAI-compatible provider, with optional DSH-owned server startup.

Tracks DeepSeek Harness LLM token usage and cost (CNY, peak/off-peak pricing) with a settings dashboard, agent tools, HTTP API and persistent storage.

Codex-style right-edge workspace for the dsh web UI: file tree with preview tabs (Markdown/source), an embedded browser (direct/proxy iframe), and a side chat streaming from the host LLM — all as switchable tabs in the native details column.

Reusable LLM configuration profile library exposed to browser consumers as a Remote

Free anonymous OpenCode Zen models inside DeepSeek Harness (DSH): native LlmAdapter, no API key, no child process; optional Go sidecar included

dsh plugin: keep llm-pi-ai provider routes' model lists in step with the pi.dev gateway, written through the official settings seam

Provider-scoped HTTP/HTTPS forward proxy for DeepSeek Harness: configure independent proxy URLs and enable/disable switches per LLM provider, with environment-variable references for proxy credentials and model discovery routing.

Permanent memory plugin for DSH with vector search, LLM reflection, and knowledge pages.

OAuth sign-in for 9 subscription LLM providers (Claude, Codex, Grok, Antigravity, OpenRouter, Agnes AI, Qwen, Spark, ERNIE) with zero-config login and usage dashboards.

Control panel for local LLM inference servers in the DSH web view: service registry with health checks and stop controls, named parameter profiles for llama.cpp, SGLang and vLLM with pre-save KV/VRAM validation, GPU detection, and tok/s benchmarks.

DSH plugin: auto-detect and configure model capabilities (reasoningEfforts + input modalities) for llm-pi-ai. Successor to dsh-reasoning-efforts.

Streaming speech-to-text for DeepSeek Harness using AllModels.io.