thinking 8
为 DSH 的 pi-ai 第三方模型补充可配置的思考强度档位,并设置子 agent 默认思考强度。
dsh plugin add @hytime/dsh-thinking-effortThird-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
dsh plugin add dsh-better-reasoning-effortCodex-style tick-rail and thinking-process fold for the DeepSeek Harness web GUI: per-turn dashes, hover preview, click-to-scroll, eager history load, and collapsed Think/tool rows.
dsh plugin add @biggerboy123/dsh-conversation-anchorsDeepSeek Harness 插件:一键配置任意 OpenAI 兼容 API 并自动带思考模式,同时规避 developer 角色被第三方端点拒绝(content_filter)的问题。
dsh plugin add dsh-plugin-thinking-apiA native, model-aware effort slider with polished light, dark, and per-model colors for DeepSeek Harness
dsh plugin add dsh-native-reasoning-sliderdsh plugin: during long agent thinking, posts a hot-news or reminder message directly into the conversation stream.
dsh plugin add dsh-gap-feedDeepSeek Harness model selector upgrade: one-level model & reasoning-effort picker with 5 Liang tiers, custom model aliases, and peak/off-peak price countdown.
dsh plugin add dsh-model-selectorPer-model reasoning effort declarations for GPT, Gemini and OpenAI-compatible providers in DeepSeek Harness
dsh plugin add dsh-more-models-thinking-level