Plugins

TOTP-only access control for personal DeepSeek Harness Web instances, with in-app QR enrollment, single-use recovery codes, live protection controls and lock-all revocation of page access.

After official llm-retry (n/5) gives up, keep retrying transient API failures (timeout, transport, rate-limit, 5xx, dropped SSE) on the same open step until success, cancel, or pause; AUTH, QUOTA, and user Stop are never retried.

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

Web UI for capturing and reviewing raw LLM requests, streamed responses, token usage and tool calls.

Smart session titles for DSH: after each conversation turn an independent auxiliary LLM call summarizes the full user+assistant transcript into a title that follows the session's real topic instead of echoing the first message; the first message is titled instantly, failed built-in titles auto-retry on later turns, manual renames are never overwritten, and subagent/fork sessions are skipped.

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

A DeepSeek Harness provider backed by the official GitHub Copilot SDK and CLI

夏尔 Ciel — DeepSeek Harness 的规划前顾问：第二个知识广博的模型在动手前提供方向、先例、陷阱与验证清单（主意，不是步骤）。命名灵感：转生史莱姆的大贤者夏尔。Settings → 夏尔 Ciel 独立页面可配。

dsh-plugin: quality-first topic memory for dsh — a topic keeps the starting question, conclusion, impact and dependencies, not the process; local-first git-traced OKF bundle, budgeted LLM-free injection

Token-cost pipeline for DeepSeek Harness: pressure-aware layered compaction (lossless projection below 40% context pressure, LLM summarization above), per-agent tool allowlisting, long-text-to-image with vision summarization, and a /token-status command tracking pressure, tiers, and saved tokens.

Multi-role parallel argumentation for DeepSeek Harness: runs the real Codex and Claude CLIs in parallel, has the DSH model (Judge) write a third-party verdict back into the conversation, plus Obsidian-style single-agent direct chat and per-role model config.

Anime subscription manager for DeepSeek Harness: Bangumi metadata lookup, nyaa/dmhy torrent search, qBittorrent auto-download with RSS-based new-episode polling, local media-library dedup, and a calendar/progress sidebar GUI with 11 LLM tools (bangumi_lookup / bangumi_search / bangumi_subscribe / bangumi_unsubscribe / bangumi_list / bangumi_progress / bangumi_calendar / qb_status / qb_configure / qb_add_torrent / library_scan).

Scans the whole C drive and classifies every large folder into A/B/C/D/E/P (safe cache / relocatable / junction-movable / abandoned software / config-memory redline / personal files), then deletes, moves, or redirects on demand — with strong redline protection, dry-run preview and undo. Unknown software decided by LLM fallback + human confirmation.

Context trimmer: lists the current session's context entries with role, preview and ≈token estimate (cl100k), highlights over-threshold items, and removes selected entries exactly without LLM summarization.

Coding retrospect distilled memory for DSH: distills rejected solutions, pitfalls and constraints from each turn via a local LLM, tags them into MemOS (type:rejected_solution), and boosts weighted recall on coding tasks via agent/pre-step.

Auto-renames DSH sessions with LLM-summarized titles: runs after the first prompt and on /handoff, or manually via a header button or /autotitle, with configurable title language and max title bytes.

DeepSeek Harness (dsh) plugin that registers Lynkr — a self-hosted, multi-provider LLM tier-routing gateway — as a custom OpenAI-compatible provider in settings.yaml.

Per-workspace custom system prompts for DeepSeek Harness (DSH): set one active prompt per workspace, captured into a session at creation time, editable from a session-header dialog. 给 DeepSeek Harness 的「工作区自定义提示词」插件：每个工作区一条生效提示词，新建会话时固化注入，会话头部弹窗增删改查。

Cross-session knowledge for DeepSeek Harness: ctx.knowledge service + knowledge_* tools, SQLite FTS5 trigram retrieval (CJK substring) with L1 query expansion. V1.11 contract (write/update/search/list/delete + budget + events + error codes).

Local and remote SSH terminals for DeepSeek Harness Web with three permission levels, human approval for risky AI commands, and encrypted credential storage.

ServerChan3 (Server酱) push notifications when a turn finishes — title, model, project directory, git branch, status and a reply excerpt, with subagent filtering and fire-and-forget delivery.

Jimu (积木): domain-based orchestration plugin for DeepSeek Harness — domain_plan confirmation, per-domain sub-agents with hand-off, and automatic LLM audit.

Turns a Xiaohongshu, Douyin, TikTok, YouTube or X link into text: transcript with timecodes, on-screen text, a description and OCR of every image, caption and metadata. Mounts the hosted MCP server over streamable HTTP.

Memory consolidation tuning for dsh-mneme (autoDream enabled, schema-max output budget, deepseek-chat route) plus the llm-deepseek reasoning-effort fix, an MCP bridge to the auditable seed-society agent runtime, and six yogacara seed skills.