Plugins

Zero-token DuckDuckGo search provider for the DeepSeek Harness (DSH) web seam — local headless browser, no API key, no model billing

One settings page that lists every subscription sign-in the harness can offer and walks you through it — ChatGPT (Codex), Claude, GitHub Copilot, OpenRouter, Kimi and xAI — reading the list from the authorization seam instead of hardcoding providers, and showing credential records no registered flow claims any more.

Ren'Py galgame production workbench: a host-side project service (write gateway plus git snapshots, a dialogue/scene dialect parser, derived progress, human-only review stamps, pinned-SDK validation and playtest, local publish) behind one seam, driven by an embedded web panel and agent tools.

DSH web plugin: multi-vendor web_search / web_fetch providers for the ctx.web seam (Tavily, Firecrawl, extensible) — works with any LLM provider.

Keeps an unfinished task list visible across turns. DSH clears the todos projection at the start of every turn and expects the model to rewrite the whole list, so when a turn is interrupted the plan is durably in the session log but permanently gone from the UI — and todo_write is write-only, so neither the user nor the model can read it back. This plugin registers one ordinary session/event listener, remembers the last list per session, and when a turn/start arrives whose remembered list still has unfinished work, re-appends that list so the projection stops reporting an empty plan. No fork of tool-todo and no waterfall: a plugin cannot replace the projection (the registry throws on a stateVersion mismatch), so appending the event the fold reacts to is the reachable seam. Deliberately narrow — only unfinished lists, at most one event per turn start, fails open. Verified by a controlled A/B on real sessions: identical runs differing only in whether the plugin was installed, folded through the real projection definition. Zero dependencies.

Workspace session monitor: aggregates per-session pending/running/completed state into a sidebar footer badge and a floating per-workspace panel, so switching between workspaces never hides a forgotten session; an additive core seam (upstream-seam.patch)

Kimi Coding web search and web fetch providers for the DeepSeek Harness — one coding-plan key fills both ctx.web seams (POST /v1/search and /v1/fetch), a settings card in the GUI stores it via the credentials service, and the fallback chain reads the Kimi CLI config for zero-setup installs.

Web search provider for the ctx.web seam that routes the DeepSeek web_search tool through a LiteLLM proxy using the OpenAI Responses API, reusing LITELLM_API_KEY.

Session health-check: mechanically mines session logs into structured problem tickets (retry loops, tool-error clusters, interrupted turns, token waste) over the official session-query seam; works standalone.

Zhipu GLM web search provider: registers as `glm` on the ctx.web seam and runs the native web_search server tool through GLM's Anthropic-compatible API (Coding Plan billing).

DeepSeek account balance in the sidebar footer plus spend per session, today, this month and all time, priced by a configurable time-of-day price table per currency (DeepSeek CNY/USD defaults included). Two read-only remote methods, no host routes, key read through the host credentials seam on every call, egress only to the configured provider origin.

pi-web-access for the DeepSeek Harness: multi-provider web search with automatic fallback (SearXNG → Tavily → Brave → keyless DuckDuckGo) plus URL content extraction, wired into the web seam so the built-in web_search tool is powered by piwa. Search engin

Cline free models provider for dsh: scan the Cline model catalog dynamically and serve the :free models through the harness LLM seam

Low-intrusion Settings presentation layer for DSH: group plugins, hide single settings / whole plugins, search settings, and restore hidden items — entirely through DSH's additive client-slot + settings-namespace seams.

SearXNG-backed web search provider for the DeepSeek Harness web capability seam (ctx.web) — self-hosted metasearch, no API key, no model turn per search

Exa search provider for the dsh-web seam: the web_search tool sends queries to Exa's /search API and returns the results as sources, in dsh web, dsh-TUI and headless runs. Needs an Exa API key (EXA_API_KEY, the credential store or a key file read on every search). web_fetch is unchanged and there is no UI.

Phone push for DeepSeek Harness: hooks the question seam in-process so a pending question reaches your phone through an ntfy relay; an answer sent from the phone is fed back to the agent as a user message, which requires `tool-ask-user` to run in `mode: timed` — with the shipped default (`mode: legacy`) only the notification is delivered.

Outbound route pool for DeepSeek Harness. Ships 15 seed routes plus a 20-entry candidate pool covering 7 target kinds (GitHub raw/codeload/main, npm registry, PyPI index, HuggingFace, general). Routes are verified before use: upstream IP lists go through a TLS handshake with full certificate-chain validation (a bare TCP check can be answered locally and report dead IPs as healthy), and failures advance a cooldown ladder of 2/5/15 minutes with the fastest healthy route picked per target kind. Routes are applied by rewriting the URL with one of four rules (prefix, registry, index, host-replace), reaching git, pip, npm, pnpm, gh, curl and wget through three paths: the shell seam (download commands the model runs through the bash tool are intercepted and rewritten automatically; commands wrapped by the pwsh tool, and fetches made by the host itself or the renderer, are not covered), two registered tools the model can call directly (line_pool_status, line_pool_run), and child-process spawn. Multi-line commands keep their line breaks and only the download segment is touched. URLs carrying credentials (user:token@host) are never rewritten, so tokens are not forwarded to third-party mirrors. No global config is modified. A sidebar panel lists every route with latency, failure reason and cooldown countdown, supports per-route retest and enable/disable, and shows live TUN/proxy status from network-adapter and loopback port checks. The candidate pool is re-verified every 24 hours so newly usable routes are added and dead ones dropped. 570 tests, 87% line coverage.

Tencent Yuanbao Search provider for the ctx.web seam: one direct Search API request per query returns portable title, URL, snippet and ISO-8601 date, with credentials resolved per search and no auxiliary model turn. Requires a Tencent Cloud WSA API key.

Context observability and control for DeepSeek Harness: cross-session token analytics, session-level budget/prompt/tool controls, and optional agent scaffolds. It reuses the official tokenMeter, compaction, systemPrompt, and tools.restrict seams; monitoring is read-only.

Publishes the desktop shell's file-path bridge as the host-path seam the composer reads, so files and folders dropped into the composer become @path references instead of uploaded copies (images still upload through the native image channel).

Registers a Tavily search provider for the ctx.web seam and switches web_search to it, with a comma-separated apiKey list that rotates on 401/403/429/5xx and transport errors.

OpenCode CLI inside DeepSeek Harness: an `opencode` delegation tool, a /opencode command, and an `opencode` LLM provider route — all over the ctx.subprocess seam, with `opencode models` discovery.

The /JevLoop control panel for moqi: gates and API key from dsh-jev-loop, rendered through moqi's tuiHost seam.