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.
Auto-detect the current model vendor and show its balance or quota in the composer input row, with a settings page for custom endpoints.
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。
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。
Provider-folded model selector for the DSH Web composer with catalog-driven reasoning effort choices.
Single-model disable gate: hides denied models from every discovery path, blocks dispatch with an in-protocol error chunk, and exposes a settings-section UI for the denylist
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).
Zhipu AI BigModel and GLM Coding Plan LLM Provider model catalog plugin for DeepSeek Harness
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.
DeepSeek Harness plugin: provider sign-in, model catalog, and selection routing over a loopback-only /model-hub channel
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
Model-visible redaction plugin for DeepSeek Harness: redacts secrets from model input and output streams
DSH model management, synchronized model visibility, and OpenAI Responses web search.
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.
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。
xAI and Grok Coding Plan LLM Provider model catalog 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）。
Capability-aware reasoning controls and provider-native Fast mode for the DeepSeek Harness web composer
Global model command palette and provider/model configuration panel for DeepSeek Harness, with a visual provider catalog, startup OpenRouter free-model sync, selective request retries, loopback relays, online capacity presets, and optional media tools.
Semantic model routing plugin for DeepSeek Harness
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.
dsh plugin: keep llm-pi-ai provider routes' model lists in step with the pi.dev gateway, written through the official settings seam
Set image input and reasoning levels for third-party provider models.