103 results
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
Enhanced DSH subagent tools with per-call model and reasoning-effort selection
DSH web plugin: splits the composer model selector into two independent controls — a searchable, favorite-marking model dropdown and a reasoning-effort slider — plus Ctrl+P (cycle favorite models) and Ctrl+T (cycle reasoning effort) shortcuts.
Save and switch model and reasoning-effort presets in the DeepSeek Harness composer.
DeepSeek Harness plugin: direct multimodal image transfer declarations + per-session image clearing, reasoning-effort auto-fill, and progressive Figma MCP bridging (design-to-code + AI-driven design).
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: keyboard shortcuts to switch models and reasoning effort levels
DSH plugin: floating HUD chat bar with live transcript, workspace/session/model/reasoning-effort switching, and Picture-in-Picture detach mode. Official bundle plugin.
DeepSeek Harness relay plugin for reasoning-effort autofill, /models sync, and a capability-aware Fast toggle.
Personal usage analytics & activity dashboard for the DeepSeek Harness (dsh) web GUI: token totals, session activity, GitHub-style contribution heatmap, model / reasoning-effort / tool / skill / plugin rankings, streaks and insights. Aggregates real session events through ctx.sessionPersistence; no dsh core changes, no prompt content leaves the machine.
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.
CodeBuddy (copilot.tencent.com) provider bundle for DeepSeek Harness (dsh): 18 models (DeepSeek, GLM, Kimi, MiniMax, Hunyuan, auto) with adjustable reasoning efforts, CodeBuddy web search / web fetch backends for the stock dsh tools, and a settings card in the Web UI.
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
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。
Effort bars for DeepSeek Harness — click signal-style sticks next to the model button to switch the reasoning effort instantly; the model menu opens straight to the searchable list.
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.
DSH plugin: when a provider's model sync returns only ids, automatically fill display name, context window, max output tokens, reasoning efforts, and input modalities from the models.dev catalog (cached, TTL-refreshed), and surface a settings page with toggles, refresh, and a fill report.
Custom DSH task board fork with per-task provider, model, and reasoning-effort pins.
在 DSH 已打开子代理的 Header 展示 provider、model 和 reasoning effort
DSH plugin that replaces the official Models settings page: provider management, per-model reasoning effort, retry overrides, drag reorder, credential status, upstream model sync, and fixed model deletion
Per-model reasoning effort declarations for GPT, Gemini and OpenAI-compatible providers in DeepSeek Harness
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