Plugins

Cross-session memory plugin for DSH (v0.6.1, npm @asherliner/dsh-memory-connect): auto-extraction, SQLite FTS5 indexing, RRF semantic recall injected into the system prompt every turn, scheduled maintenance, LLM-powered consolidation via ctx.llm, context explosion prevention, and global Soul identity via ~/.dsh/soul.md. v0.5.0 added temporal context graph (valid_from/valid_until/supersedes, append-only corrections via reviseMemory), trust model (recalled history injected as untrusted reference, current instruction always wins), turn-end summarization. v0.6.0 added local semantic embeddings (BAAI/bge-small-zh-v1.5 via embed_server.py, cosine + RRF fusion with FTS5, no cloud calls, ~232 msgs/sec on CPU). v0.6.1 fixed ~ expansion in path config. Zero-config install.

Settings card for the DSH LLM auto-retry engine: tune retry count, backoff and jitter live from Settings -> General, with configurable retryableCodes chips - defaults add INVALID_REQUEST so OpenAI-style HTTP 400 reasoning_text errors in thinking mode get retried automatically.

Local Claude Code provider for DeepSeek Harness — runs your installed claude CLI as an LLM provider

Live llmtrim savings dashboard in the DSH web UI: Settings page with paid, would-have-cost, saved-today and saved-this-week cards plus per-model breakdown, and a configurable rotating or static stats strip under the composer.

DeepSeek Harness (dsh) plugin that exports a session as a self-contained, replayable HTML file — full transcript, faithful tool cards, and playback at the original timing.

FriendliAI serverless LLM adapter for DeepSeek Harness — OpenAI-compatible chat completions with dynamic model discovery and reasoning support

Declarative multi-agent pipeline executor for DeepSeek Harness (dsh): runs a manifest of confined role dispatches with mechanical gates and a machine-written evidence ledger. dsh 声明式多角色流水线执行器：按 manifest 派发受限子代理、机械门禁、机器写证据账本。

DeepSeek Harness (dsh) plugin that snapshots your workspace at every turn into a shadow git repository, so you can restore the files to any earlier turn. Your own .git is never touched, and plain directories work too.

Per-project LLM token usage and RMB cost in the DSH Web sidebar, split by input (cache miss), cache hit, and output with model price auto-pricing.

System parameter adjustment UI: grouped settings page for timeouts, parallelism, LLM retry policy, model params, web search, permissions and presets; safe profile-config editing with line-level YAML matching and post-write validation.

Rewrite the current composer draft through an auxiliary LLM call without sending a message.

MCP client hub (stdio / Streamable HTTP / SSE) with a web console for DeepSeek Harness — manage MCP servers, agent skills, slash commands, project & global memory, and prompt sections.

为原生 DeepSeek Harness 接入飞书 CodeM 模型。Use Feishu CodeM as the LLM provider for DeepSeek Harness (DSH) .

明眸 VisionBridge - 自研视觉桥：瞎子模型收图时自动调用视觉模型识别，把识别文字喂回主模型，无感、可配置、升级不丢

Control your DeepSeek Harness agent from Feishu/Lark: DM a task, a DSH agent runs it with your LLM, and the answer comes back to the chat. Image understanding, image generation round-trip, feishu_send tools, resident launcher. Powered by lark-cli.

DeepSeek Harness (dsh) plugin for wallpaper theming — upload images from the Settings page, pick one, and the whole dsh web UI renders over it with an adjustable readability mask and blur.

DeepSeek Harness plugin: serve LLM calls with the OAuth tokens your local Codex CLI and Claude Code already hold, instead of a separately configured API key.

DeepSeek Harness 插件 — 通过读取企划书 / 半成品软件 / 资料预估特定模型的 token 消耗量并实时按各家定价计费

DeepSeek Harness 文字冒险/推理游戏插件:海龟汤、侦探推理、密室逃脱、剧本杀、时间循环、王国议会、单人跑团。确定性内核保证公平,LLM 担任主持人(GM)与 NPC;真相封存于引擎,永不进入模型上下文。

Per-plugin usage budgets and cost caps on the llm/stream waterfall: per-model usage accounting, session and monthly budgets with warn/block transitions, latency windows, and a carbon-footprint estimate.

Scrape URLs to LLM-ready Markdown and search the web via the Firecrawl Cloud API.

DeepSeek Harness (dsh) plugin for machine-wide token usage statistics — a Settings page with totals, a contribution heatmap, streaks, and a per-model breakdown. Reads session logs from every dsh home; no cost estimates.

LLMTR AI gateway provider for the DeepSeek Harness LLM seam: 170+ chat models and Türkiye-hosted LLMs behind one OpenAI-compatible key