Plugins

ChatGPT account sign-in for DeepSeek Harness through a Codex browser OAuth flow with no API key and no workspace selection: subscribes the login to pi-ai's Codex provider, lets you set the global default Codex model and reasoning effort for new sessions, refreshes the model list from the signed-in account's own catalog endpoint, and shows the five-hour and weekly usage windows in the composer.

All seven Kimi ask/review/challenge/rescue/pursue/swarm/swarm-write providers through the local Kimi Code CLI, with managed hooks, jobs, budgets, and artifacts; also supports Claude Code and Codex.

Unified multi-provider web search and fetch: BYOK key pools, health monitoring, and deterministic fallback.

Research-only trading workbench bundle: typed market-data provider seam with a CSV reference provider, multi-timeframe indicator regime snapshot and OHLCV tools, interactive chart cards in dsh web with provenance-gated model annotations, and a risk-guard denying execution-shaped tool calls at tools/pre-execute.

Runs your logged-in Claude Code CLI as a dsh model provider: live model list, session resume, approval relay, rewind, memory panel and remote SSH workspaces.

A drawer panel for the DSH web UI with a paginated list of free LLMs; one-click or batch writes each as a custom model provider into Settings, plus a local multi-key rotation proxy.

Tencent CodeBuddy model provider for DeepSeek Harness that signs in with browser OAuth instead of an API key, lists the CodeBuddy model catalog with the context, output, tool-calling, reasoning and image capabilities of each model, keeps multiple accounts with automatic failover to the next usable one, shows remaining quota in the composer with a token and credit usage panel, and completes automatable CodeBuddy growth tasks per account with an execution log. Install from npm with `dsh plugin --profile web add @tnnevol/dsh-codebuddy`.

DeepSeek Harness provider that runs the subprocess seam inside a remote Upstash Box

Classifies pending tool calls with Jev (TypeSafe AI's non-generative decision model) on tools/pre-execute — confident high-risk calls are denied, ambiguous ones escalated to approval — and auto-approves clearly-granted reversible calls on approval/request behind argument-evidence gating. Also subclasses the session-reference resolver so snapshots keep Jev-scored messages instead of dropping oldest-first. Degrades to stock behavior on any provider failure; shadow mode with a /jev-stats command; TypeSafe or OpenRouter endpoints; 64 tests.

Google Antigravity / Cloud Code Assist model provider with quota management and model selector.

Multi-provider usage stats framework (v2 adapter contract): persistent capsule plus detail panel; DeepSeek official (interval-bookkeeping daily usage derivation with a peak/valley countdown badge, working even without an official usage endpoint) and OpenCode Go built in; any other data source joins by dropping in a single mjs adapter file, hot-swappable from the settings page, with API keys kept on the host.

Free conversational ChatGPT Web (GPT 5.6 Luna) model provider for DeepSeek Harness with streaming Markdown.

DeepTrace — deterministic agent reports from session logs (daily/weekly/monthly/yearly/custom): cost & token breakdown, 8 insight rules, collaboration review, live provider balance, PDF/PNG/HTML export; read-only, never rewrites history.

Local + online music player for DeepSeek Harness: multi-root library, NetEase / QQ Music / KuGou / Navidrome, synced playlists and lyrics, audio cache, EBU R128 leveling, 10-band EQ with AutoEQ headphone curves, smart crossfade, in-list search, and tag / cover editing. Online sources keep login cookies and tokens in ~/.dsh/music/providers.json (mode 0600); ticking Save password for Navidrome writes that password there in plain text.

Image generation and image reading for DSH: an Images page in the sidebar, labelled 图像 in Chinese (one row per model, 10 ratios, 1K–4K sizes, a contact sheet with detail cards, zoom, reuse and delete), three preset providers plus custom endpoints — one needs no key at all — and a vision-review skill. A pasted key is written to ~/.dsh/secrets/media-tools.env (mode 600) and only sent to the provider you picked. The page follows the harness language (Chinese or English). Requires Python 3.9+ (generation runs through scripts/generate.py); the page needs desktop DSH 0.2.1+.

Connects Qoder subscriptions to DeepSeek Harness, supporting Global and China regions, multimodal input, and tool calls.

TinyFish-backed web search provider for the built-in web_search tool: each search is one GET to the TinyFish Search API, no model call.

Terminal-native TUI frontend for DeepSeek Harness that presents sessions, models, plugins, jobs, subagents, todos, and provider configuration through Harness capabilities while preserving real terminal scrollback.

Registers ChatGPT Codex, Claude, Grok and Antigravity subscriptions as DeepSeek Harness LLM providers through OAuth, so no API key is needed for them.

Connects a Doubao account to DeepSeek Harness as a model provider after a single browser QR sign-in — live model discovery from Doubao web and desktop menus with inline composer billing multipliers and per-model thinking ladders, 「工作任务」 task-mode models spending paid quota, chain-of-thought reasoning streaming, Seedream image generation preferring original uncropped assets over watermarked variants, native DSH token usage and session stats tracking, and a live remaining-quota panel. Windows x64 only, since the session is sealed with DPAPI. Windows x64 only, since the session is sealed with DPAPI.

Factory (Droid) subscription quota as native DSH model providers, with three protocol routes, your own API key through a loopback gateway, and a settings page for connection status, quota, per-model token statistics and key switching.

Free model provider plugin for DSH with 20+ models including Gemini, MiMo, GLM, etc.

Ollama provider for DeepSeek Harness with model management, health checks, rule-based local routing, and cloud fallback.

Provider-independent DSH document parsing powered by MinerU, with native background jobs, immutable results, and safe request coalescing.