Plugins

A dsh plugin that replaces the built-in llm-pi-ai and llm-deepseek adapters, the model selector and the Models settings page with self-maintained versions, tracks upstream @earendil-works/pi-ai, and adds quota/balance lookups plus a provider management UI

Automatic tier-based model routing for DeepSeek Harness: a virtual `smart` model classifies each request by difficulty (hard / normal / easy) and by vision need, then delegates it to the models you already configured. 三级难度 + 视觉自动路由，虚拟 smart 模型零配置接入。

XingTu 26 production-grade AI agent skills, packaged as a DeepSeek Harness (DSH) skills plugin — token compression, code review, safe refactor, migration, evidence review & more. 26 个生产级 SKILL.md 技能，DSH 一键安装即用。

Persistent, searchable, per-project memory for the DeepSeek Harness: decisions, rules, and sprint context in a queryable DuckDB file, rules enforced on every model request, with a full management UI in the Web Client

Context occupancy and account balance for the DeepSeek Harness Web Client: a session-header readout, a balance capability seam, and a DeepSeek provider

Keeps one reasoning-only turn from making an entire session unusable. When a turn produces no visible text and no tool call, the assistant message is persisted empty, the gateway then rejects every later request in that session with 'content or tool_calls must be set', and the session is dead with no way back through chat. This plugin registers a single llm/stream waterfall listener and, only when the turn carried nothing visible, injects a small text block immediately before the terminal finish, so the persisted message is never empty. Ships the fixture DSH's own mock cannot express (a strictly reasoning-only SSE server, since llm-mock-server forbids an empty successText and always appends text after reasoning), plus an end-to-end reproduction that replays a real persisted session through DSH's own serializeMessages. Preventive, not a repair. Zero dependencies, one file, no process or filesystem access.

Fills in what the official pi-ai adapter leaves out on the Models page: gateway reachability probing with latency, one-click pull of the gateway model catalog with checkbox write-back into settings, DeepSeek balance and provider quota shown in place, the protocol and endpoint each provider is actually wired to, and a model dropdown that lists only what works right now — a dead key, an empty balance or an exhausted quota is hidden until you fix it, and comes back on its own.

Trims historical images in outgoing chat requests down to a recent-image count, learns the provider per-prompt image cap from HTTP 400 responses, and retries with fewer images so image-heavy sessions keep working.

Declares per-model reasoning-effort ladders for third-party providers in the llm-pi-ai settings section, so DSH's stock thinking-intensity selector works on models the pi-ai catalog does not describe.

DeepSeek Harness plugin for querying LLM service provider usage: reads DeepSeek and Moonshot balances plus Kimi For Coding and OpenCode Go quota windows on the host and shows them in an always-visible card with three view modes, edge docking and a collapsed letter bubble.

Adds per-route context window and compaction threshold fields to the Models settings page and a vendor-aware thinking-effort picker to the composer, writing llm-pi-ai capacities, reasoningEfforts, and a compaction-basic patch row.

dsh (DeepSeek Harness) plugins for project-level persistent context: session archive with a mechanical index, memory consolidation (CONTEXT.md + MEMORY.md), low-frequency skill autolearn, and automatic handoff.

A web-search provider for the DeepSeek Harness, fully local no API key needed.

LLM provider plugin for the DeepSeek Harness (dsh): streams Claude through your Claude Code subscription (claude.ai OAuth credentials), no Anthropic API key required.

Turns DSH permissions into 9 selectable presets (3 sandbox modes x 4 approval tiers), with rule plus LLM risk classification across four risk levels, password-gated approval for high-risk operations, and a JSONL audit log.

Resume screening plugin for HR in DeepSeek Harness: ingest up to 100k Word/PDF/Excel resumes into one searchable library with skills / coarse categories / ingest time, auto-ingest & de-dupe new resumes, then screen by plain-language criteria — rule pre-filter in the database plus LLM fine-judge on the shortlisted few, CSV export.

Adds a markitdown tool that converts PDF, Word, Excel, PowerPoint, HTML, CSV, EPUB and URLs to Markdown, using a real Microsoft MarkItDown installation when one is reachable and a bundled dependency-free converter otherwise.

Measures what an llm-pi-ai endpoint really accepts — context window from its own model list, output-token limit and reasoning levels read out of its own range errors, image support from a generated test image — then reports declared values that contradict that evidence and rewrites them only after confirmation.

Agentic answer reviewer for DeepSeek Harness: each final assistant turn is re-reviewed by a separate LLM graded 1-100; below-threshold scores steer the agent back with concrete feedback. The score is shown as a chip on the answer's action row (green pass / red needs-work, with retry count and reason on hover). Live gate config over a 127.0.0.1 HTTP server, plus a collapsed dock above the composer and an optional right-sidebar tab via dsh-better-sidebar.

DSH 实时库文档：写代码前自动拉取项目安装版本的官方文档，消灭幻觉 API。零配置零 Key。Version-pinned live library docs for DeepSeek Harness — kill hallucinated APIs

dsh plugin: cron scheduling — bounded tasks with calendar & interval rules, delivered to live agents

CWL — Context Window Lifecycle for DeepSeek Harness: structured context eviction (arXiv:2606.11213). Graduated, deterministic, zero-LLM eviction of exploration/action episodes when context pressure exceeds budget — no summarization lossiness, no hallucina

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