8 results
Third-party provider reasoning-effort AND input-modality settings for DeepSeek Harness: thinking levels and image-input support declared per model, auto-adapted from a model knowledge base + wire-protocol inference, edited right inside the official Models page card.
Explicit model input-modality selection for the DeepSeek Harness Web UI
DeepSeek Harness Web plugin: per-model input-modality selector on the Models settings page for third-party (pi-ai) providers
Mobile UI fixes for the DeepSeek Harness web profile: composer attachment upload, a restart row, input-modality switches, a narrow-screen drawer and settings tabs, a full-width model menu, a stuck-request network chip, and a throttled reaction to streaming message storms.
DSH Web UI model seat: 3-level quick slider (low/medium/high, each preconfigured with model + reasoning effort), advanced model/effort picker, modality icons, and per-provider usage/balance display. DSH 模型选择器增强：低中高三档快切滑块 + 高级选择 + 模态图标 + 供应商用量显示。
DeepSeek Harness (dsh) plugin: route one request to a modality-capable fallback model instead of forcing the whole session onto a single model.
OmniRoute model manager: searchable/filterable multi-select UI to control which OmniRoute models DSH uses, with modality discovery and OmniRoute-backed web search.
DSH 模型视觉开关：设置页「模型视觉」行，为 llm-pi-ai 自定义路由下手写声明的模型切换 input 视觉模态（settings.mutate 官方通道，热生效）。