602 results
Provider badge icon beside the composer model selector: DeepSeek whale SVG, bold GO/ZEN wordmarks for OpenCode Go/Zen, blocky initials otherwise. Client-only DSH plugin. · DSH 客户端插件：在模型选择器旁显示当前 provider 图标（DeepSeek 鲸鱼 / OpenCode GO·ZEN 字标）。
Multi-level provider fallback for same-named models in the DeepSeek Harness
DSH web plugin: provider quota/balance badges — composer chip beside the context meter plus per-row badges on the Models settings page (GLM/Kimi/OpenCode/DeepSeek/Moonshot/xAI + Sub2API gateway auto-detect)
Adds a model parameter to the subagent tool so the model picks the subagent's provider/model per call
LLMTR AI gateway provider for the DeepSeek Harness LLM seam: 170+ chat models and Türkiye-hosted LLMs behind one OpenAI-compatible key
Custom DSH task board fork with per-task provider, model, and reasoning-effort pins.
Local web fetch provider: fetches web pages and summarizes/parses them with the local Ollama model before returning to the agent
Provider-neutral task lifecycle and idempotent event ledger for DeepSeek Harness and Aifred
Kimi (Kimi Code account) integration bundle for DeepSeek Harness: provider route, models, device-code login and auto token refresh (npm: dsh-kimi-provider)
DSH plugin: exposes per-provider balance / coding-plan usage (5h window + weekly) in a status bar pinned to the native session-stats row.
DeepSeek Harness plugin: fingerprint the provider, model id, sampling, offered tool schemas, and system-prompt prefix of each request, and diff the live card against a pinned one through the modelprint_check tool
Multiple API keys per provider for DeepSeek Harness: keep a pool of keys with notes, switch the active key right from Settings → API 密钥, and every switch really takes effect on the next model call.
请求管理插件（bundle）：按全局配置管理 Agent→LLM 请求——「请求额外间隔」（每个请求发送前固定多等 N 毫秒，0=不介入）、重试次数覆盖（留空=沿用 provider 默认）、拦截「请求失败」（终态失败后挂起等待人工决议：重试原地重发同一请求 / 放弃按原生路径终结）。入口为会话头部 utilities 槽位的「请求管理」按钮；设置跨会话全局生效，按值决定是否介入；界面跟随 dsh 语言中英切换。
在 DSH 已打开子代理的 Header 展示 provider、model 和 reasoning effort
DeepSeek Harness (dsh) plugin that registers Lynkr — a self-hosted, multi-provider LLM tier-routing gateway — as a custom OpenAI-compatible provider in settings.yaml.
DSH plugin: one-click account balance & quota panel for multiple AI providers (DeepSeek, Zhipu GLM, Z.ai, Moonshot, MiniMax, StepFun, SiliconFlow, OpenRouter, xAI).
Local-first DeepSeek Harness plugin marketplace with GitHub and dshfind providers
Locally maintained web search plugin for DeepSeek Harness with free and API-backed providers.
DSH plugin: OAuth sign-in for Claude, Codex, Grok, Antigravity, OpenRouter, Agnes AI, Qwen, Spark, ERNIE — expose subscription LLMs as DeepSeek Harness providers
Managed local fingerprint relays so DSH can reach providers that gate on the client's TLS fingerprint
DSH plugin that replaces the official Models settings page: provider management, per-model reasoning effort, retry overrides, drag reorder, credential status, upstream model sync, and fixed model deletion
穷鬼模式（Poor Mode）：钱包优先的 DSH agent preset，供应商感知的分时省钱。先分析用户意图与任务复杂度，复杂任务让用户选择「立即执行」或「闲时执行」——按当前供应商的实际计费规则判断：DeepSeek 峰谷价闲时半价；固定计价的平台则退化为纯延后队列。支持 ~/.dsh/poor-mode-providers.json 自定义任意平台的分时规则。基于 dsh-liangshen 的 preset 同步架构。
dsh web 插件：自动配置模型思考档位与能力，并按 provider+model 记住最后选择的思考档位
Native ChatGPT OAuth controls for DeepSeek Harness's built-in OpenAI Codex provider