dsh-agent-mode-switcher
DeepSeek Harness plugin: switch the current conversation's agent preset (mode) after the model finishes answering, and keep chatting in the same session
483 results
DeepSeek Harness plugin: switch the current conversation's agent preset (mode) after the model finishes answering, and keep chatting in the same session
DeepSeek Harness plugin: one sidebar Usage/Balance popover combining multi-provider accounts with peak/off-peak per-call billing.
Math_Agent: a math training/coaching agent preset for DeepSeek Harness, with a programmatic zero-leak output guard that never reveals answers
DSH agent preset 分发包:修复极简模式(minimal)预设中 persistent bash 工具约 3.5s 延迟返回的完成检测 bug,并同步 minimal-fast preset 到 ~/.dsh/.agent-presets/minimal-fast。
Register AllRouter as a DSH provider: one base URL and one key for Kimi K3, Claude, GPT, Grok, GLM, DeepSeek, MiniMax-H3. Switch models without managing separate providers; every call reports real cost.
GEO-first AI 搜索优化:为 AI 搜索引擎(ChatGPT/Claude/Perplexity/Gemini/AI Overviews)优化网站——citability 引用就绪评分、AI crawler 访问分析、llms.txt 生成、品牌提及扫描、Schema 标记、E-E-A-T 内容质量、5 并行子代理全审计。受 zubair-trabzada/geo-seo-claude(9.4k★ MIT)启发。
DSH plugin: session-header task estimator — estimated remaining time, token usage and per-model cost (≈CNY) with an optional LLM-powered estimate. / DSH 插件:会话标题栏任务估算窗口——预计剩余时间、token 用量与按模型花费估算(≈CNY),支持 LLM 智能估算。
聊天框语音输入按钮 for DeepSeek Harness: 点击麦克风说话,多引擎转写(智谱 GLM-ASR-2512 / 本地 faster-whisper / Gemini / OpenAI)自动填入输入框。一个按钮,所见即所得。
Gemini-style Material 3 Expressive theme for DeepSeek Harness Web (persistent bundle).
Live remaining balance and actual spend from the provider for the current API key, not a local token estimate.
DeepSeek Harness bundle for Google Generative AI and third-party OpenAI Responses providers.
Quota monitor for the DeepSeek Harness Web GUI: OpenCode Go plan usage + DeepSeek API balance/usage + MiniMax Token Plan, as a draggable bottom-left monitor window. P0: self-metered token ledger (llm/stream waterfall, own JSONL). P1: multi-provider abstractions (balance/windows kinds, presets, configurable parsers) and bundle-type packaging.
DSH plugin: /init slash command that generates an AGENTS.md guide for the current project with a two-stage model call
Academica scientific, healthcare, SEC, provider-market, reimbursement, and market-access MCP bundle for DeepSeek Harness and Pi.
Hot-disposable realtime voice Agent plugin for DeepSeek Harness WebUI and future WeChat Mini Program clients
Deterministic chemistry math for DeepSeek Harness (dsh): formula parsing with molar mass (nested parens, hydrates, ionic charges), mass/mole/particle conversions, solution concentration (molarity, dilution, percent) and pH/pOH/buffer math — zero runtime dependencies
DeepSeek Harness community plugin that raises an operating-system notification when one of your tasks finishes: an answered turn, a subagent run, a background job, a completed goal, or a settled workflow - with localized wording, per-source switches and a custom delivery command.
DSH harness bundle/plugin: tolerate OpenAI-compatible providers whose streaming responses omit finish_reason (e.g. the Snowflake Cortex gateway) so turns complete instead of failing with a TRANSPORT error.
Telegram notifications for DeepSeek Harness: ping you when a task finishes or the agent needs your input/approval. DeepSeek Harness 的 Telegram 通知插件。
Two-stage intent and evidence review, deterministic completion gates, and bounded repair for DeepSeek Harness agents
Agent JIT: a compiler/runtime that offloads deterministic execution paths from LLM agent loops.
DSH agent-fleet hygiene audit: credential-file permissions, embedded credentials in git remotes (masked), provider token-prefix literals. Read-only, zero-dependency, deterministic.
DeepSeek Harness plugin that bridges to external AI models (Codex, Claude, GPT, ...) for second-opinion code review, adversarial review, and task delegation.
User Message Minimap: a navigation rail for long DeepSeek Harness conversations