dsh-anchored-standard
Task-aware two-phase DeepSeek Harness preset: spec/react/weak first-request anchors (bash+read±edit/write), then the full Standard tool catalog after the first tool call.
49 results
Task-aware two-phase DeepSeek Harness preset: spec/react/weak first-request anchors (bash+read±edit/write), then the full Standard tool catalog after the first tool call.
题庄中小学 K12 真题检索、免费抽题、练习测验与智能组卷 DeepSeek Harness 插件。
Miraculous Standard — unified anchored agent preset for DeepSeek V4 Pro/Flash (official API & opencode-go). Minimal-exact two-tool first-request bootstrap, model-aware Pro/Flash paths, unified context gate, epoch-aware catalog management, rc7-ready shell handling.
Route DeepSeek Harness model-API requests through an HTTP/SOCKS proxy without modifying Harness source
Whitelist / blacklist / any-error retry policy for DeepSeek Harness, driving DSH's built-in LLM request retry mechanism.
Codex-style conversation outline for DeepSeek Harness: a floating panel listing every user question in the current conversation with search, load-older and click-to-jump (scroll + highlight). Bilingual zh-CN / en.
Persistent global fetch proxy for DeepSeek Harness LLM requests (undici setGlobalDispatcher + EnvHttpProxyAgent), configured via the llm-proxy settings namespace
Long-task gatekeeper for DeepSeek Harness: detects one-shot mammoth requests, asks whether to plan first, and scaffolds plan.md + a capped goal before the agent starts
DSH mega 系列:会话提问圆点导航条(question-nav 移植 · mgcn 族)
Ask a quick side question without interrupting the main conversation - a Claude Code /btw port for DeepSeek Harness (dsh). Type /btw <question> while the agent is working.
DSH Web 插件:在会话中列出我的问题并点击定位
Enforced pain-point-check guard plugin for DeepSeek Harness: after two non-converged experiments on one problem it injects the three questions, denies non-investigative tool calls until they are answered in the reply text, and blocks same-direction retries
Navigate to the latest and previous user questions in long DeepSeek Harness conversations.
DSH plugin that auto-retries failed API requests — when third-party APIs return errors (rate limiting, service unavailable, etc.), intercepts and retries to keep the conversation going. Supports auto/manual mode with configurable status codes and error codes.
DeepSeek Harness dynamic plugin: renders three clickable, editable follow-up question suggestions under every agent answer
Persian (Farsi) RTL fix for DeepSeek Harness: automatic per-paragraph direction and mixed-language detection (Persian text starting with English words), thinking cells, tool cells, user bubbles and question boxes.
Stops DeepSeek Harness from phoning home: disables every row that exports telemetry, attaches diagnostics to model requests, or records feedback for later upload
Free OpenCode Zen models in DeepSeek Harness through native HTTP requests. No OpenCode installation, login, API key, server, container, or LiteLLM is required.
Approve-for-me mode for DeepSeek Harness: an LLM safety reviewer auto-approves ordinary approval requests, while destructive high-risk commands still ask the human.
DSH web plugin: plays opencode sound effects on task completion/failure/input-request with a native Settings panel (45-sound pack, per-event picker + on/off switch, preview, volume).
Bounded all-error request retry plugin for DeepSeek Harness
DeepSeek Harness plugin: injects an [IMPORTANT] chain-of-thought rule block at the very top of the system prompt of every model request (English CoT starting with I'm, no 'Let me', direct verbs).
/btw slash command for DeepSeek Harness: ask a context-aware side question without touching the main conversation
HTTP 请求工具:发起请求返回状态码/响应头/响应体/耗时(Node fetch)