@ztlovelsw/dsh-model-profile
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。
108 results
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
DeepSeek Harness relay plugin for reasoning-effort autofill, /models sync, and a capability-aware Fast toggle.
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。
Task contracts, approval gates, checkpoints, verification evidence, and best-effort rollback for DeepSeek Harness
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.
DSH 自定义模型思考等级管理、渠道重试策略与偏好记忆插件:原生设计语言、全档位思考配置、渠道级重试控制与无感隔离式跨会话偏好记忆。
Sliding-rheostat theme: model + reasoning-effort driven accent, glow and gear dock for the dsh web GUI
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。
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。
DeepSeek Harness plugin: the Models+ settings page — a fully plugin-owned model/provider UI with per-model extension fields (reasoning efforts, input modalities, compat flags) and models.dev metadata prefill
OpenAI-completions-compatible adapter for custom gateways (vLLM / LM Studio / self-hosted proxies): always role:"system", enable_thinking / chat_template_kwargs / reasoning_effort driven by the llm-pi-ai model config, and a </think> split on the receive side — no pi-ai behavior guessing.
Model and reasoning-effort switcher: composer seat with an Off/Max effort slider over session.models / session.selectModel
DeepSeek 中转站(OpenAI 兼容网关)思考强度适配插件:让 UI 出现 Off/Low/High/Max 推理等级选项,并按中转站格式发送 reasoning_effort / thinking
DSH plugin: floating HUD chat bar with live transcript, workspace/session/model/reasoning-effort switching, and Picture-in-Picture detach mode. Official bundle plugin.
Notched reasoning-effort slider grouped with the model picker for DeepSeek Harness — native DSH styling, adaptive theming (light/dark + theme plugins), i18n (en/fr/zh), realtime drag. 100% modular, zero core changes.
Add configurable thinking-strength (reasoning effort) levels to custom llm-pi-ai providers in DeepSeek Harness
DeepSeek Harness web UI plugin: floating API token usage, context pressure, reasoning-effort control, and cost estimation with official peak/off-peak pricing.
Correctly activate DeepSeek v4 flash on the Volcano Ark plan API for DeepSeek Harness: default config injection (ark provider + reasoningEfforts + reasoningEffort=max) plus an ark_plan_doctor self-check tool.
Automatically add reasoning-level controls to compatible DSH provider models.
DSH Web UI model seat: 3-level quick slider (low/medium/high, each preconfigured with model + reasoning effort), advanced model/effort picker, modality icons, and per-provider usage/balance display. DSH 模型选择器增强:低中高三档快切滑块 + 高级选择 + 模态图标 + 供应商用量显示。
Configure model input capabilities and reasoning efforts for DeepSeek Harness
Per-stage model routing for dsh-TUI: let subagents run on a different provider/model/reasoning-effort, configured in /settings (model-switch namespace), status via /model-switch.