124 results
DeepSeek Harness plugin: when a request fails with a model error before any output, it falls through the configured provider groups' models (then the next selected provider) until one works; transient failures retry with backoff under a liveness watchdog, dead turns self-resume with a templated continue wake-up, and an optional full-auto mode auto-answers permission/confirm/plan approvals with an AUTO-MODE.md audit trail. Adds its own Settings tab.
Model pricing and capability board for DeepSeek Harness: compare per-1M-token prices, find the cheapest route, and see coding/agentic/vision tags for every LLM you can connect — in the DSH settings UI.
xAI and Grok Coding Plan LLM Provider model catalog plugin for DeepSeek Harness
DeepSeek Harness plugin: provider sign-in, model catalog, and selection routing over a loopback-only /model-hub channel
DSH 插件：给所有非官方（自定义）提供商的模型自动填充模型信息，包括：推理级别、最大上下文、输出上限与图片模态，数据来自 models.dev。
One-click / auto model sync for DeepSeek Harness providers — reconciles stored model lists against each provider's /v1/models endpoint, with a Settings page toggle and conversation-open auto-sync.
Capability-aware reasoning controls and provider-native Fast mode for the DeepSeek Harness web composer
Model-visible redaction plugin for DeepSeek Harness: redacts secrets from model input and output streams
DSH 模型中心插件：免费模型目录 / 真免费实测 / 价格余额 / 一键切换 / 用量统计 — Model center plugin for DeepSeek Harness
DeepSeek Harness 插件：按工作阶段自动路由模型（对话/规划用 flash，实施用 pro）。
模型路由网关：一个端点连接 290+ AI 提供商（90+ 免费、1200+ 模型），Claude Code/Codex/Cursor/Cline/Copilot 全兼容——配额感知自动回退、19 种路由策略、RTK+Caveman 叠加压缩省 15-95% token、免费层聚合预算（~1.5B tokens/月）、MCP/A2A、本地优先。受 diegosouzapw/OmniRoute（51k★ MIT）启发。
DeepSeek Harness 的增强模型选择器：单层菜单（搜索 + 分组）+ 底部内联推理强度（Effort）滑杆。
Show a hover hint with a model's full configuration (input types, context window, max tokens, protocol, base URL, credential env, …) over each model in the DeepSeek Harness web model picker, read from ~/.dsh/settings.yaml.
dsh plugin: keep llm-pi-ai provider routes' model lists in step with the pi.dev gateway, written through the official settings seam
Vendor logo seat in the DSH web composer: shows which provider serves the current model (DeepSeek / OpenAI / Anthropic / OpenCode / ...), live from the official per-session ModelDirectory.
Set image input and reasoning levels for third-party provider models.
DSH WebUI 模型下拉菜单实时搜索框：给 composer 的模型选择菜单注入一个可打字过滤的搜索框（不抢座位、不改共享服务，跨版本可用）
Provider-folded model selector for the DSH Web composer with catalog-driven reasoning effort choices.
DSH 自定义模型思考等级管理、渠道重试策略与偏好记忆插件：原生设计语言、全档位思考配置、渠道级重试控制与无感隔离式跨会话偏好记忆。
Provider-first model selector for the DeepSeek Harness model seat: pick a provider, then a model from that provider — current model always shows Model · Provider; search and hardening (v0.3.2, verified against DSH 0.1.1-rc.2).
DeepSeek Harness plugin: control which models appear in the model selector — per-model switches, provider-level batch toggles, and search. Hiding a model never touches your provider config or running sessions.
Zhipu AI BigModel and GLM Coding Plan LLM Provider model catalog plugin for DeepSeek Harness
Semantic model routing plugin for DeepSeek Harness
DSH model management, synchronized model visibility, and OpenAI Responses web search.