dsh-vision-patch
Per-model and per-route image-input (vision) checkboxes on the Models page's custom-provider cards, writing through the llm-pi-ai settings namespace.
226 results
Per-model and per-route image-input (vision) checkboxes on the Models page's custom-provider cards, writing through the llm-pi-ai settings namespace.
Grant official-style reasoning-effort selection to hand-declared pi-ai models (DeepSeek relays and the like) in the chat box
DSH 官方直连的 LLM 配置补强:模型发现(Models 页「获取可用模型」对 deepseek-official 生效)+ provider 卡片上的 DeepSeek 余额与可用性。零运行时依赖,不改动 DSH 安装。
DSH 模型插件:监控各服务商上游 /models,列出新增模型并勾选添加(检查只读、显式应用、不自动删除)。Monitor provider model catalogs and add newly released models to DeepSeek Harness.
Per-route context window, compaction threshold, and per-model thinking-effort controls for DSH models. · DSH 模型上下文窗口、压缩阈值与思考强度设置。
DeepSeek Harness plugin that serves every gpt-load model from one provider group, each model on its own wire protocol (OpenAI Chat Completions or Anthropic Messages), synced from /api/models
OpenCode Go models as a DeepSeek Harness provider, with session-affinity headers, a live model catalog, and a Web settings card
dsh web Settings section (Custom models): subagent delegation allow-list, plus per-model image-input / reasoning-effort mapping.
Full model-configuration editor for the DeepSeek Harness web Settings > Models page: every field the deployment's model-config schema declares, not just the handful the shipped UI exposes.
Google Antigravity (agy CLI) models for DeepSeek Harness — stream Gemini/Claude/GPT-OSS subscriptions into DSH with thinking, tool activity, token usage and in-GUI Google OAuth login.