@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。
65 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。
Unified image understanding plugin for DeepSeek Harness (DSH). Visual twin adapter for native thumbnails + auto-analysis on any text-only model (incl. pi-ai providers); privacy/smart/strict routing; local tools (scan/OCR×4 engines (windows/macos/paddle/rapid)/crop/palette/compare/batch); document-to-image (pdf/word/excel/ppt); local photo editing (image_edit: resize/rotate/filter/composite/watermark/background-remove/upscale etc, pure CPU); optional external VLM bridge.
One-click context window matching and selective bulk configuration for DeepSeek Harness models, with source references and manual management.
ChatGPT (Codex + Sign-in-with-ChatGPT), xAI Grok, Zhipu GLM, AWS Kiro, Google Antigravity, Cursor, Ollama Cloud, Kimi Code Plan, Devin, Cline, Command Code, and OpenCode Go subscription OAuth / API keys for DeepSeek Harness — PKCE / device-code / Google login, local proxy, llm-pi-ai sync.
DeepSeek Harness plugin: make a custom llm-pi-ai provider route masquerade as Claude Code / Codex — spoofed client-identity headers, plus an opt-in request-body fingerprint for relays that gate on the body.
让 provider 配置的 headers(如 User-Agent)真正到达 pi-ai 的 API 请求,自动补全 opencode 身份头(ses_/msg_ 会话与请求 ID 格式),并在向 OpenCode Zen 网关发送的请求 body.tools 里补上网关必需的 bash 工具 —— 把请求识别为 opencode 客户端而不是 deepseek-harness,修复 OpenCode ZEN 免费模型 429(FreeUsageLimitError)、400(MissingSessionID/MissingHeader)、403(Generation.FreeTierError)
Model Capability Manager for DSH Web: per-model thinking levels, context window, output caps, input modalities, gateway compat, route defaults, one-click presets, EN/中文 UI.
Model Pro — DSH plugin for llm-pi-ai provider lifecycle: create/edit, custom headers, enable/disable with uninstall-restore safety, smart routing, composites, observability, and per-model connectivity tests
Generic LLM gateway model provider plugin for DeepSeek Harness: mounts newapi / LiteLLM / Higress / any OpenAI-compatible gateway as provider routes, auto-discovers the model list, enriches every model with models.dev parameters, and dispatches each model over its native wire protocol (OpenAI / Anthropic / Gemini) via the pi-ai SDK
让 DeepSeek Harness 自动重试商汤 429/QUOTA 等瞬时网关故障直到任务完成——启动时给所有 llm-pi-ai provider 热注入加固版 retryPolicy,运行中新增的 provider 也会自动补上,再也不用手动发「继续」。
Per-model reasoning-effort and vision capability editor for DSH pi-ai provider profiles.
DSH web plugin: 为自定义模型(OpenAI-compatible pi-ai provider)增加思考强度(reasoning effort)配置 —— 设置页新增「思考强度」分区,按模型配置思考级别与线格式、按 provider 配置默认思考强度,直接写入 llm-pi-ai 设置,composer 模型选择器随即生效。
DeepSeek vision bridge for the dsh web GUI: route image attachments to a vision model (pi-ai / llama.cpp Qwen3-VL) and continue the conversation with the text description on a text-only LLM (DeepSeek)
Sync opencode-go models from https://models.opencode.ai/api.json into llm-pi-ai provider opencode-go-autosync (one-click create/update in settings).
Google Anti Gravity and Cloud Code Assist Coding Plan LLM Provider plugin 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思考等级(reasoning efforts),并按 models.dev 预设/批量同步思考等级与上下文容量,写入 llm-pi-ai 设置命名空间。
Declare per-model reasoning efforts, image input, and openai-completions dialect on hand-declared llm-pi-ai routes. Writes the official namespace; does not intercept llm/stream or replace the Models page.
Sync cc-switch provider profiles (Claude Code / Codex relays) into DeepSeek Harness as llm-pi-ai routes, credentials stored via the DSH credential seam.
Zhipu AI BigModel and GLM Coding Plan LLM Provider model catalog plugin for DeepSeek Harness
DeepSeek Harness (dsh) bundle that routes the harness through the OpenLLM gateway — an `openllm` provider on the in-box pi-ai adapter (via the local daemon gateway) plus the OpenLLM MCP server. Pure config; install OpenLLM first (see README).
Sync CommandCode plan models (goat/pro/max) from the official models API + GOAT plan catalog into llm-pi-ai providers commandcode-<plan>-autosync (one-click create/update in settings).
在 Settings 面板中为自定义 pi-ai 模型编辑推理等级(reasoningEfforts),支持多选、拖拽、复制粘贴,自动保存。
xAI and Grok Coding Plan LLM Provider model catalog plugin for DeepSeek Harness
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。