Plugins

Raises Node's HTTP headers/body timeouts for the whole DSH process (default 30 min, proxy-aware) so Ollama and LM Studio models that stay silent while thinking or generating a large tool call are not cut off at 5 minutes; replaces the node_modules undici patch.

Per-provider concurrency gate on the llm/stream waterfall: holds surplus model requests in a FIFO queue inside DSH so main agent, subagents and compaction take turns on a single-slot local server (llama.cpp --parallel 1) instead of timing out; maxConcurrent / maxQueued / queueTimeoutMs.

Conversation-level multi-agent workbench for editable task planning, real child-session observation, plan-versus-runtime comparison, and evidence-backed recovery previews; tested with DSH 0.1.1-rc.2.

One Dark Pro theme plugin for DeepSeek Harness (DSH) Web UI. 为 DSH Web 界面打造的 One Dark Pro 暗色主题插件。

Adds a Spawnd.gg games cabinet to the DeepSeek Harness Web sidebar with search, sorting, hover previews, embedded play, and a minimized player.

Slash commands ported from other coding agents (setup, connect, install, trust, browse, doctor, status, model, memory, compact, resume, review, mcp, init, suggest, improve, refactor), a zero-dependency static scanner for plugin source, and an in-repo catalog of audited plugin report cards that cite file-and-line evidence.

语音输入插件 for Deepseek Harness

DSH 插件：可拖拽余额饼图 / 真实消耗 / 历史热力图 — balance pie with real spending & monthly heatmap for DeepSeek Harness.

Connect Feishu chats to DeepSeek Harness projects, conversations, replies, and scoped tool approvals over WebSocket.

Hard-stops further tool calls after a configurable per-session budget is reached.

Runs a parallel code review squad of read-only reviewer subagents (security, correctness, tests, style), each optionally on its own model, and aggregates one severity-grouped report from /review or a code_review tool call.

Turns DSH conversations into reviewable community feedback and, after confirmation, submits it to the official DeepSeek Harness Discussions.

Verifiable issue-to-PR delivery chain: an 11-stage pipeline (analysis, search, code understanding, hypothesis, planning, implementation, patch ledger, tests, review, failure classification, PR build) with 4 human review gates, GitHub/GitLab/CodeArts credential connections, a 5-page workbench and a draggable AI assistant panel.

Drive your real logged-in browser through OpenCLI — browser primitives plus 170+ site adapters as deterministic one-shot commands, with in-session adapter authoring, a write-approval gate and a settings management panel.

Diagnoses WSL port listening and Windows localhost forwarding, with a 3080/3081 uiPlaybook for the dsh web relay and launch token.

Converts Linux and Windows paths with /mnt/c caveats for WSL.

Shows a short Windows MessageBox or toast (BalloonTip) from WSL when a long task finishes.

Launches allowlisted Windows apps such as VS Code, Explorer, and browsers from WSL.

Probes nvidia-smi and GPU visibility inside WSL.

Uses a GitHub App to report open PRs and the latest Actions run for the current repo without returning secrets.

Reports the current WSL distro and warns about multi-distro setups.

Safe Git Credential Manager hints for WSL without exposing secrets.

Reads and writes the Windows clipboard from WSL.

Opens http(s) URLs from WSL in the Windows default browser.