@hytime/dsh-thinking-effort
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。
55 results
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。
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.
Per-model capability declaration for DeepSeek Harness: reasoning-effort levels (with wire spellings) and request modalities (text/image) for OpenAI-compatible providers — one settings section, no YAML hand-editing.
Reasoning effort settings and per-call subagent model routing for DeepSeek Harness custom providers
Codex-style reasoning-effort slider embedded in the DSH model selector
DeepSeek Harness composer model seat: model picker plus a three-stop reasoning bar (小难梁 / 梁子 / 梁圣)
Enhanced ACP server for DeepSeek Harness: block-level streaming, usage/stat telemetry (cache hit rate, token speed, input/output tokens, context length, turns, tool timing), model & reasoning-effort switching, and permission-preset control over the ACP wire (Zed-friendly)
Global model request headers plus image input, reasoning, and DeepSeek system-role compatibility for custom providers
A compact per-model reasoning effort editor for DeepSeek Harness custom providers.
DeepSeek Harness 前端插件:梁系强度滑动条 —— 用 6 档滑块替换输入框的模型与推理等级按钮(小难梁/牢梁/梁子/梁圣/梁神/梁祖),悬停时在进度条上方显示对应档位形象图,切换带交叉淡入淡出渐变
DeepSeek Harness 统一推理等级插件:一个 llm-reasoning 设置项动态配置 DSH 所有模型的默认推理等级(思考等级)——自动为手写声明的模型补齐推理能力、按路由设置默认等级(仅当全部模型支持)、同步 DeepSeek 官方路由,改设置即生效。
DeepSeek Harness plugin that enhances custom provider setup by auto-discovering models and auto-populating contextWindow, maxTokens, vision, and reasoning capabilities from models.dev
Unified ModelID routing for DeepSeek Harness: one logical model id over multiple providers, first-token failover with cooldown, health-aware ranking, fallback reasoning efforts, purpose-based simple/complex task split, per-tier reasoning effort, and a settings-page management panel.
DSH plugin (NInfer engine only): fixes compaction failure on local qwen3.8-27b gateways served by NInfer — xhigh thinking burns the entire output token budget, so thinking is off for compaction-only, with the model's non-thinking sampling parameters; the same idea applies to other launch methods
Capability-aware reasoning effort slider for the DeepSeek Harness web model selector.
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。
第三方模型思考努力度配置(DeepSeek Harness 插件):在设置页为模型声明 reasoningEfforts 档位、路由默认档位与 Anthropic token 预算,写入 llm-pi-ai 命名空间;档位调节复用原生模型框 Effort 面板。
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。
DeepSeek Harness 实用工具箱:便签、API 余额与费用、推理等级、删除会话、对话节点导航条、轻拟物皮肤(monorepo,可一键安装全家桶)
Sliding-rheostat theme: model + reasoning-effort driven accent, glow and gear dock for the dsh web GUI
Provider-folded model selector for the DSH Web composer with catalog-driven reasoning effort choices.
DeepSeek Harness 插件:在 Web GUI 中选择模型的推理程度(reasoning effort)。按当前模型的适配器目录展示可选档位(如 Off / High / Max),一键写入会话的模型选择。
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。
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