dsh-plugin-clarify
Off-transcript clarification Host plugin for DeepSeek Harness
830 results
Off-transcript clarification Host plugin for DeepSeek Harness
DeepSeek Harness 批量并行子 Agent 调度插件:swarm_batch 工具(Kimi Code Swarm 模式移植)+ /swarm 命令 + 聊天内实时进度条。
生产级中文编剧创作与剧本诊断系统。覆盖概念超短片、短片、电影长片、剧集/连续剧、竖屏短剧/微短剧;强调主角驱动因果、场景价值转折、潜台词、中文自然度、故事状态机、人物知识边界、关系连续性、承诺-兑现、证据式QC、单调修复与长篇记忆快照。用于从零开发、续写、改戏、对白、剧本医生、结构诊断与长篇连续性维护。
Model-bound custom HTTP headers for LLM requests: llm/stream capture + ALS + fetch injection (soft-replacement: host half + settings.section UI)
Google Antigravity OAuth Gemini provider for DeepSeek Harness
ChatGPT Codex, xAI Grok, Zhipu GLM, AWS Kiro, Google Antigravity, Cursor, Ollama Cloud, Kimi, and GitHub Copilot subscription OAuth for DeepSeek Harness — PKCE / device-code / Google login, local Responses proxy, llm-pi-ai sync.
AiFP Cognitive Memory — persistent memory MCP server for AI assistants. Chinese-first retrieval with causal chains, Hebbian associations and graph diffusion. 记忆感知系统
三段式 RP 输入面板:台词/动作/心理分框填写,按模板组装后发送
Task planning with experience muscle-memory for DeepSeek Harness: condition-reflex recall of past solutions + LLM-driven capability matching + auto-persisted lessons. Zero keys, zero hard-coded paths.
DeepSeek Harness LLM provider for Codex models using managed ChatGPT OAuth
DeepSeek Harness plugin — manage an LLM-Wiki knowledge base from the agent: wiki_search / wiki_read / wiki_stats / wiki_validate / wiki_fix / wiki_errorbook / wiki_ingest
Cancelable auxiliary-model runtime for DeepSeek Harness with a provenance-preserving usage ledger outside official tokenUsage
Free Kilo Gateway and OpenCode Zen models for DeepSeek Harness (DSH) via native dsh-llm adapters.
提示词增强(DSH 通用插件):三种模式(基础/标准/专家)读取会话工作区项目上下文并调用 LLM 增强输入框提示词,支持结果对比确认、采用后撤回、失败模型回退链、按模型能力自动适配推理档位(网关不支持时自动去参重试)、待确认问答闭环(逐条回答后带答案重新增强)、组合行 config 可配置、可取消。Host 半提供 /api/prompt-enhance/enhance;浏览器半在 composer 工具行注册模式选择与 ✦ 按钮、对比面板与忙碌状态卡。随 harness 启动自动加载,无需手动重新加载。
DeepSeek usage monitor as a DeepSeek Harness (DSH) plugin: balance / day-month-all-time token & cost panels in the chat UI with drag-reorder config, plus an optional local usage proxy
DSH tool-call compatibility: strips sandbox_permissions/justification from tool-call arguments for third-party models (GPT etc.), and lets the user skip possibly-stuck tool calls with an LLM-facing notice.
MCP server that searches the Roblox DevForum and official creator docs so AI coding agents can debug Roblox games against real community and engine knowledge.
Optional local runtime dependencies for Chat2Skill plugin features.
分层长期记忆 MCP 服务器:本地 MiniLM 或 OpenAI 兼容嵌入 API,供 LLM Agent(DeepSeek Harness / Claude Code)做可语义检索的长期记忆
Cross-session long-term memory for AI agents — local Go service (~50MB RAM, SQLite-vec, verify-augmented) with bridges for DeepSeek Harness, Claude Code, Codex, Hermes, OpenClaw, opencode, pi, Reasonix.
DeepSeek Harness 自动审批插件:在 workspace-write 沙箱之上增加 Auto 档——确定性规则放行/拒绝,模糊操作由 LLM 裁决,危险操作转人工。保留工作区沙箱边界,不放宽为 full-access。
Expose a DeepSeek Harness agent over the Agent2Agent (A2A) protocol: agent card, JSON-RPC endpoint, LLM-powered replies, and a live status card.
DSH plugin: before answering a large question, show an estimate of tokens and DeepSeek API cost as an inline row in the Web chat stream, then update it with the actual usage after the answer.
让 DeepSeek Harness 自动重试商汤 429/QUOTA 等瞬时网关故障直到任务完成——启动时给所有 llm-pi-ai provider 热注入加固版 retryPolicy,运行中新增的 provider 也会自动补上,再也不用手动发「继续」。