207 results
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
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.
A calmer reading view for DeepSeek Harness: native process details, live reasoning, and clean final answers.
Limit the expanded thinking block to a bounded scroll window in the DSH web conversation.
KISS's Law (Weiwen's Law) universal causal engine (white-box presentation). DeepSeek Harness (Cordis) plugin implementation.
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.
Animated reasoning-level slider for DeepSeek Harness model selection.
DSH web 插件：折叠思考过程直接输出回答内容；在会话输入框上方增加会话活动状态条，展示 Think / Edit / Bash / Read，可展开与收起。 / DSH web plugin: folds the thinking process so answers render directly, and adds a session-activity status bar above the composer showing Think / Edit / Bash / Read, expandable and collapsible.
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。
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.
FriendliAI serverless LLM adapter for DeepSeek Harness — OpenAI-compatible chat completions with dynamic model discovery and reasoning support
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