dsh-model-autoconfig
dsh web 插件:自动配置模型思考档位与能力,并按 provider+model 记住最后选择的思考档位
117 results
dsh web 插件:自动配置模型思考档位与能力,并按 provider+model 记住最后选择的思考档位
DSH reasoning effort slider with 7 levels and cool visual effects
A DeepSeek Harness plugin with a vertical model list and an animated Three.js particle reasoning-effort control.
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。
Per-session subagent model picker for DeepSeek Harness with immutable child bindings
Host-only DSH foundation helpers: default workspace, resource inspection, and CLIProxyAPI catalog bridging.
DSH session model selector with search and reasoning-effort pane: shadows the native conversation.input.model seat (independent cordis client plugin).
Claude Code as a real, streaming dsh subagent: session-backed child, free model/effort choice per call, live model list from the CLI
DeepSeek Harness bundle for ZenTao MCP, task/bug workflows, reports, and verified formal effort recording.
A minimal reasoning-effort ruler for the DSH composer: one hairline, a sliding marker, per-model memory, optimistic switching — and a streamlined model picker.
Codex-style /reasoning command for DeepSeek Harness Web: select the reasoning effort of the current model from the slash menu
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
Choose default and per-name provider, model, and reasoning effort for newly created DeepSeek Harness Agent Teams teammates, with live team status and restart-safe route views.
Grant official-style reasoning-effort selection to hand-declared pi-ai models (DeepSeek relays and the like) in the chat box
DSH Effort Router(模型分流):按每一轮请求的难度自动选择模型与思考强度——简单问题走便宜快模型,难题才叫强模型。规则判定零 token,灰区交给一次小模型裁定,图片档强度随难度升降(low/high/max)。每轮请求级覆盖,不改你的会话选择与默认模型。
Cost policy for the DeepSeek Harness: per-call metering plus a local fuse that enforces budget, model and reasoning-effort limits before any token is spent.
dsh web Settings section (Custom models): subagent delegation allow-list, plus per-model image-input / reasoning-effort mapping.
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.
在 dsh 模型目录的每一行直接设置该模型的思考强度范围与支持的输入模态 (Per-model reasoning-effort range and accepted input modalities, right in the dsh Models catalog)
Command palette for DeepSeek Harness (Cmd+K) — new chat, jump to session, switch model and reasoning effort, permissions, slash commands, theme, language and settings, all from one fuzzy-searchable bar.
Capability metadata for hand-declared gateway models, resolved at runtime by bare model name (context window, output cap, reasoning levels, vision) — matched against the official DeepSeek route's catalog, the installed pi-ai catalog, opencode and models.dev, without writing to your settings.