dsh-model-reasoning
DSH 插件:给所有非官方(自定义)提供商的模型自动填充模型信息,包括:推理级别、最大上下文、输出上限与图片模态,数据来自 models.dev。
183 results
DSH 插件:给所有非官方(自定义)提供商的模型自动填充模型信息,包括:推理级别、最大上下文、输出上限与图片模态,数据来自 models.dev。
Readable thinking display for DeepSeek Harness: live per-paragraph summaries of the reasoning stream, rendered in the chat history where the 'Think' row is, with a user-chosen summary model (thinking disabled on summary requests).
Save and switch model and reasoning-effort presets in the DeepSeek Harness composer.
Codex-style turn folding: collapse each group of reasoning + tool-call nodes (between visible outputs) into a single disclosure unit
Provider-folded model selector for the DSH Web composer with catalog-driven reasoning effort choices.
Auto-expand every Think row, including after switching sessions. Header switch to turn it on or off.
DeepSeek Harness plugin that steers reasoning toward Simplified Chinese and translates eligible reasoning blocks.
DSH plugin: keyboard shortcuts to switch models and reasoning effort levels
DeepSeek Harness plugin that enhances custom provider setup by auto-discovering models and auto-populating contextWindow, maxTokens, vision, and reasoning capabilities from models.dev
Top-right widget counting 'let me' / 'we' / 'let's' / 'I'll' across all reasoning chains of the current conversation.
DSH Web GUI 模型能力配置:在「设置 → 模型」的模型目录编辑器内,为每个已配置的模型直接设置是否支持图像与思考等级(reasoning efforts),写入 llm-pi-ai 设置命名空间。
增强的模型设置页插件:为自定义模型提供每模型推理强度(reasoningEfforts)编辑,OpenAI 兼容网关可直接勾选 low/medium/high 等档位;聊天模型选择器随之显示 Effort 菜单。
DSH plugin: fixes compaction failure on local qwen3.8-27b gateways — xhigh thinking burns the entire output token budget, so thinking is off for compaction-only, with the model's non-thinking sampling parameters
DSH plugin: detect long model thinking chains, segment them, and show per-segment summaries live in the chat UI, with a settings page.
DeepSeek Harness relay plugin for reasoning-effort autofill, /models sync, and a capability-aware Fast toggle.
A full-screen interactive terminal UI for the DeepSeek Harness agent runtime — live streaming, reasoning blocks, tool cards, sessions, permissions, plan mode, and a full slash-command suite. The web UI, reimagined for the terminal.
Configure the default provider, model and reasoning effort for new subagents from the Web settings page; optionally apply changes to existing idle subagents. · DSH 插件:在设置页可视化配置 subagent 默认的提供商、模型与思考等级,新创建的 subagent 立即生效,可选的让空闲 subagent 也跟随新设置。
Minimal epoch bootstrap, full-tool promotion, and hard handoff compaction for DeepSeek Harness
DSH 温暖极简模式:官方 minimal 等价 composition,加一条固定工作目录确认首轮。
Black-first Matrix hacker skin for DeepSeek Harness (DSH) Web with efficient displayed-text code rain and readable provider reasoning.
Matrix rain for expanded thinking in DeepSeek Harness Web
滑动变祖 · 马圣皮肤:an opt-in adaptive reasoning slider skin for DeepSeek Harness
Offline DeepSeek request, tool-loop, reasoning_content, and SSE diagnostics for DSH
Ranked subagent delegation for DeepSeek Harness: role-based model routing with failover, per-route reasoning effort, fork delegation, transparent model labels, and a visual route editor in Settings.