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.
51 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.
Persistent global fetch proxy for DeepSeek Harness LLM requests (undici setGlobalDispatcher + EnvHttpProxyAgent), configured via the llm-proxy settings namespace
Custom HTTP/HTTPS proxy for DeepSeek Harness: routes every host-side fetch (LLM requests, model discovery, market, web search) through your proxy (Clash/mihomo/v2ray) without TUN mode, with a settings card for live host/port edits. 为 DeepSeek Harness 注入自定义 HTTP 代理,无需 TUN 模式,设置页可直接修改地址与端口。
JumpServer asset lookup for DeepSeek Harness: query assets via conversation using AccessKey/SecretKey signed requests
DeepSeek Harness 主动限速插件:按供应商令牌桶限速,超限延迟排队而非失败
Codex-style /btw for DeepSeek Harness: ask a side question answered by a conversation-seeded subagent, keeping the answer out of the main context
Safe model-request retry for DeepSeek Harness with exponential backoff, model-availability recovery, and configurable unknown-error limits.
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
ChatGPT 风格问题导航:胶囊轨道 + 刻度尺 + 贴边抽屉目录,悬浮 1 秒展开全部问题,搜索过滤 + 一键跳转
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.
Navigate to the latest and previous user questions in long DeepSeek Harness conversations.
DeepSeek Harness dynamic plugin: renders three clickable, editable follow-up question suggestions under every agent answer
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
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
DSH web bundle: codex-style Approve For Me — a reviewer model auto-approves low-risk escalation requests, and auto-rejects (or routes to the user) high-risk ones.
DSH web plugin: Codex-style /side side conversations. Open a temporary fork of the current chat in a floating panel — ask side questions without interrupting the main task or polluting its context.
DSH mega 系列:会话提问圆点导航条(question-nav 移植 · mgcn 族)
Readable thinking display for DeepSeek Harness: live per-paragraph summaries of the reasoning stream, rendered in the chat history where the 'Think' row is, with a user-chosen summary model (thinking disabled on summary requests).
HTTP 请求工具:发起请求返回状态码/响应头/响应体/耗时(Node fetch)