Plugins

Multi-source web search and fetch failover for DeepSeek Harness sessions: takes over the session searchProvider and fetchProvider seams and tries configured sources in a chosen order — TinyFish, Tavily and the official search as a fallback that always participates and can be repositioned but not removed. Multiple API keys per platform are spread round-robin, usage snapshots drive pre-flight exclusion of exhausted accounts, and per-request timeouts plus same-platform retry control failover granularity. Web fetching runs local HTTP first, then falls back to TinyFish Fetch server-side rendering and Tavily Extract, so pages still load when local egress is blocked by proxy or DNS policies. A per-platform panel shows key usage and plan limits. Install from npm with `dsh plugin --profile web add @tnnevol/dsh-failover-search`.

Browses Douyin in a dedicated browser with daily viewing limits, shared local persona and interests, native settings, diagnostics, usage tracking, and reports. Replies and shares use selected conversations; group replies require a mention or configured name. Public comments require separate opt-in.

Host-side DSH evaluation control plugin: injects one evaluation trial's variables, budget limits, session root and fork lineage into the agent process, routes its model calls through a host broker under a gateway lease, and writes a schema-versioned bundle descriptor for evidence attribution.

Zotero library tools via the local API (no API key, Zotero 7+): search items and collections, read metadata, abstracts and PDF full text (on-the-fly parsing when the cache misses), download attachments, and manage notes; API endpoint, target library and limits are configurable.

Password + TOTP two-factor authentication gateway for the dsh web UI: every HTTP request and WebSocket upgrade is refused until login, with per-source lockout, global rate limits and one-time backup codes.

Connects DSH to a local anet node through a stdio MCP client, with three skills and 14 tools to discover agents on the AgentNetwork, send, track and answer end-to-end encrypted A2A tasks, pay or decline priced skills within the operator's limits, read the local evidence chain and report the node state. Linux/macOS only; requires an anet 0.3.0+ node running locally.

Autonomous Douyin watching in a dedicated Edge browser on Windows (requires Node.js 22.13+): sampling decisions, frame storyboards, danmaku-aware comments, persona memory and a watch diary, all under daily viewing limits. Fork of LockyBee/dsh-douyin-agent — uninstall the upstream plugin before installing this one.

For the DeepSeek Harness native vision model deepseek-v4-flash-vision-exp, raises image admission limits to 32 MiB / 8192 px / 600 images and adds a highres_read tool that tiles large images, then returns the whole image plus 800x800 tiles through the host read_image tool.

ChatGPT Codex subscription chat: official OAuth, a Sol/Terra/Luna catalog with Fast rows, live usage limits, and optional search and view_image tools.

Resident Rust sidecar for Windows that folds shell-heavy tool calls into one warm worker: 11 tools (10 rust_* tools plus a native_help entry point; 5 resident, 6 activated on demand) for command execution, sha256-guarded file reads and writes, code indexing and search, session-log projection and resource sampling, served by a lane pool with soft RSS and CPU limits over 8 HTTP routes.

Adjust Agent Team's member count, task count, message size and teardown timeout.

DSH side of Blind Whale Farmer, a SMAPI mod in the same repo that lets an AI play Stardew Valley from a text game state through MCP tools: syncs play limits and extra instructions to the running game, adds an optional session preset or a single stardew gateway tool (both off by default), and sends "keep playing" when a Stardew session ends on a tool call that came back as plain text. Needs the mod installed in the game.

WeChat (Tencent iLink / ClawBot) channel for DeepSeek Harness: QR-code login, two-way text, image and file messaging, slash commands in WeChat including /cwd and /skills, approval and question cards answered from the chat, and reply sending that splits over-long answers and backs off on rate limits instead of dropping them. Only the account that scanned the login is admitted by default; messages from anyone else are ignored.

Keeps project decisions in plain markdown instead of chat history: one main document plus per-module documents, every entry carrying a file:line citation. The agent interviews you to turn open questions into settled decisions, and a five-dimension score (task complexity, extensibility, maintainability, code quality, reusability) is derived from the documents and shown on a button beside the model picker. A session can bind several projects; projects are sized small/medium/large, which widens the entry limits, and a reusable-pipeline section in the main document is injected when its trigger words appear.

Rate-limits LLM requests per provider and per model using a reservation-based token bucket, with queue or reject modes, plus gateway identity rules that rewrite user-agent and inject custom headers.

Adds a squeeze tool: the agent hands a long web page, a batch of pages, a text file or a text PDF (via pdftotext) plus one question to a helper model and gets back only the answer, so the material never enters the chat. A settings page picks up to three helper models from the DSH model list, each with a nickname, a fixed thinking level and a "when to use" note, with optional fallback and size limits taken from each model's context window.

Desktop notifications for DSH: a system toast, a per-kind chime and a tab-title marker when the agent needs you (approval, plan review, question) or a reply finishes in the background; errors, interrupts, usage limits and multi-agent workflow progress alert too. A host half adds SSE delivery, webhook push (WeCom/Feishu/DingTalk/generic), per-turn token/cache/TPS stats, plus three message-format presets (concise, detailed, custom); settings changes auto-save.

Tracks DSH's file reads, image views, and code edits in WakaTime, including exact counts of lines added and deleted by AI. Keeps activity tracking running while DSH responds, batches updates across files, and coordinates per-project reporting limits across parallel DSH processes. Automatically installs and updates wakatime-cli.

Firecrawl-backed web search provider for the built-in web_search tool, with a settings card for the API key and result limits.

The model switch for DSH: point it at any OpenAI-compatible endpoint, with curated free/cheap DeepSeek provider presets and automatic fallback when a free tier rate-limits you.

Automatically retries model failures (drops, timeouts, rate limits, 5xx) in-turn. Retry count, delays, backoff, fallback and more are configurable. Rate-limit backoff is capped and jittered, server retry hints are honored, and optional retry-until-success keeps going within a time ceiling. Every option is editable from the plugin config or the sidebar panel: retry count, initial and max delay, backoff factor and jitter, rate-limit delay window, retry-until-success ceiling, fallback trigger and switch cap, dead-route blacklist TTL, log file. When a route keeps failing it can switch to a pinned, allowlist-filtered, or catalog-picked alternate model route, with a 30-minute dead-route blacklist (auth failure, subscription expired, billing) and a stale-assembly guard that keeps retried requests on the switched route. Ships a right-sidebar panel with live retry state, route labels and incident counters, Chinese and English locale, and memory-only logging by default.

Finds wasted GitHub Actions runner time and proposes small, reviewable workflow patches, with explicit approval before any edit and a DSH settings page for analysis rules, history limits, storage, and cost estimation.

Predicts your next message after each turn and shows it as gray ghost text in the composer: Tab takes the whole line, Alt+Right takes one word at a time, Enter takes it and sends, Esc dismisses, and Alt+R asks the model again without repeating the old one. Typing a few characters completes from prompts already sent in the session, Up in an empty composer recalls the last one, and a plugin-page form sets the provider, model, reasoning effort, per-key toggles and generation limits.

Read-only DeepSeek web archive tools for DSH: list/download/search sessions, share-list, and a digest tool that compresses the 100-session history into one high-density page with activity bars and topic clusters. Write operations are intentionally not exposed (the web client rate-limits them). Requires the separately installed deepseek-ops Python client (github.com/Panniantong/deepseek-ops, by another author) with QR-code login; set scriptDir to its path.