dsh-more-models-thinking-level
Per-model reasoning effort declarations for GPT, Gemini and OpenAI-compatible providers in DeepSeek Harness
202 results
Per-model reasoning effort declarations for GPT, Gemini and OpenAI-compatible providers in DeepSeek Harness
DSH plugin: auto-detect and configure model capabilities (reasoningEfforts + input modalities) for llm-pi-ai. Successor to dsh-reasoning-efforts.
DSH Settings section to edit per-model input modalities (text/image) AND reasoningEfforts (incl. custom wire values), for all configured providers, models and modelOverrides at once — a companion to the lighter input-only WJZ-P plugin. Works on DSH Web and DSH Desktop.
DeepSeek Harness 推理强度与网关增强插件:自动为 llm-pi-ai 下所有模型补齐推理强度档位(off→max 全七档),并自动为 OpenCode Go 网关注入必需的 x-opencode-session 路由 Header,写入 settings 由 dsh 原生解析生效。
Adds a search field inside the model picker menu of the composer. Drop-in replacement for the native model seat, sharing the same per-session ModelDirectory so /model popup, the effort selector, and the /model command stay consistent.
DSH session model selector with search and reasoning-effort pane: shadows the native conversation.input.model seat (independent cordis client plugin).
Aggregate DSH plugin bundle — one install, five plugins: dsh-memarc (long-term memory + session archive), dsh-session-git (export/import sessions as committed JSON), dsh-session-branches (session fork tree), dsh-goal-auto-resume (re-arm unfinished goals), dsh-model-reasoning (per-model reasoning capability & effort editor). Declares dsh.bundle, so the whole repository installs as a single profile layer: no clone, no build.
Flash-only reasoning-effort routing for DeepSeek Harness: classifies each step by its shape and sets the DeepSeek flash model's reasoning effort to match. The model never changes; effort max is opt-in.
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。
Auto-adjust model reasoning effort per task: off/low/high/max with task classification, peak-pricing-period capping, countdown notices, and in-turn error escalation