205 results
DSH web plugin: a draggable ring-gauge dashboard pinned to the bottom-right that shows live model output speed (tok/s), with an expandable detail panel (per-step exact speed, TTFT, cache-hit rate, cache read/write, reasoning and input tokens, model, cumulative tokens).
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
Named subagent profiles with configurable model routing and reasoning for DeepSeek Harness
DSH plugin: keyboard shortcuts to switch models and reasoning effort levels
Hmm-Wait 思维链弹幕：监听模型思维链（reasoning）输出，当出现 hmm / wait / let me 等触发词时，在 dsh Web GUI 上弹出可配置的弹幕动画（方向 / 速度 / 抖动 / 样式均可调），并带官方设置面板开关。
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。
Top-right widget counting 'let me' / 'we' / 'let's' / 'I'll' across all reasoning chains of the current conversation.
Minimal epoch bootstrap, full-tool promotion, and hard handoff compaction for DeepSeek Harness
DSH plugin: floating HUD chat bar with live transcript, workspace/session/model/reasoning-effort switching, and Picture-in-Picture detach mode. Official bundle plugin.
Composable multi-model agent roles and legacy Luna/Sol reasoning routing for DeepSeek Harness
Structured context for DeepSeek Harness: split the conversation into typed sub-contexts (reasoning / tool calls / replies) and index them with a table of contents. 结构化 dsh 上下文:按类型拆分小上下文(思考/工具调用/正式回复),以结构化目录为索引。
FriendliAI serverless LLM adapter for DeepSeek Harness — OpenAI-compatible chat completions with dynamic model discovery and reasoning support
DeepSeek Harness relay plugin for reasoning-effort autofill, /models sync, and a capability-aware Fast toggle.
DSH plugin: deliver the real failure reason (e.g. RATE_LIMIT 429) to the parent agent when a background subagent fails, instead of an empty "Its closing message:"
DSH 模型流式缺陷修复：opencode 聚合端点上 muse-spark-1.2 / gpt-5.6-luna 不发送 finish_reason/[DONE]，导致 pi-ai 每次对话结尾报 "Stream ended without finish_reason"（TRANSPORT）并触发重试。本插件在 llm/stream waterfall 上把「已输出内容但结尾被截断」的 finish 改写为正常 stop，直连即可使用，无需代理。
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.
Local OpenAI-compatible model-server discovery + tiered reasoning-metadata resolution for DeepSeek Harness (dsh).
CodeBuddy OAuth, dynamic models, and reasoning controls for DeepSeek Harness
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。
Sliding-rheostat theme: model + reasoning-effort driven accent, glow and gear dock for the dsh web GUI
DSH harness bundle/plugin: tolerate OpenAI-compatible providers whose streaming responses omit finish_reason (e.g. the Snowflake Cortex gateway) so turns complete instead of failing with a TRANSPORT error.
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。
Offline DeepSeek request, tool-loop, reasoning_content, and SSE diagnostics for DSH
UltraCode agent preset for DeepSeek Harness 鈥?maximum-depth reasoning, plan 鈫?execute 鈫?verify, and parallel subagent orchestration, as a one-command-install mode.