dsh-model-thinking
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。
773 results
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。
DSH plugin: the /douyin command opens the Douyin web app in the default browser
多功能 DSH 插件:① 为 OpenAI 兼容第三方模型声明 Codex 风格推理档位并钉住默认档位;② 引用目录(附加文件夹)——为会话添加可读写的白名单文件夹,注册 refdir_list/read/write/edit/grep 工具。安装一次,按模块持续扩展。
Deploy the ArchGraph ARGO toolchain, skills, and rules (schema, scripts, argo-init skill, global rule) with one command.
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).
DSH subagent provider that delegates tasks to the OpenAI Codex CLI (codex exec), exposing the subagent_codex tool
OpenSpec change orchestration plugin for AI coding agents (Claude Code, Codex, ZCode, DeepSeek Harness, OpenCode)
把 Codex(OpenAI Codex CLI / Desktop)的 MCP、技能、全局配置、记忆以适配 DSH 的形式迁移进 DeepSeek Harness(DSH 插件)
Cross-platform Web UI launcher plugin for DeepSeek Harness: webui_start/stop/status/open model tools, a /webui slash command and a Settings-page launch card.
DSH plugin: VSCode-style uncommitted changes sidebar for the DeepSeek Harness web GUI — staged / unstaged / untracked files, per-file diffs and open-in-editor, docked to the right of the conversation page
DSH plugin: renders images inline in DeepSeek Harness Web chat and gives text-only models vision — cloud multimodal API first, local Qwen3-VL fallback.
dsh-polyglot — the model switch for DSH: one generic OpenAI-compatible ctx.llm adapter, curated free/cheap DeepSeek provider presets, and automatic provider fallback when a free tier rate-limits you
DeepSeek Harness plugin: OpenCode GO 套餐用量(三窗口额度 + DSH 按模型 token/金额统计 + 输入框迷你条)
Host-level vision bridge for text-only models: analyze_image tool (Ollama local / Xiaomi MiMo cloud / any OpenAI-compatible endpoint) returning structured evidence.
DeepSeek Harness plugin: auto-repairs an invalid messages array (orphaned tool_calls / tool messages) to stop 400 INVALID_REQUEST session lock-ups.
Eyes for text-only DeepSeek on DeepSeek Harness: image understanding via Antigravity IDE quota (default, flash/pro), OpenAI-compatible VLM endpoints, Gemini API, or local Ollama — model-invokable vision tool, wrapper adapters for deepseek/opencode-go, evidence memory, and a polished client panel.
分层长期记忆 MCP 服务器:本地 MiniLM 或 OpenAI 兼容嵌入 API,供 LLM Agent(DeepSeek Harness / Claude Code)做可语义检索的长期记忆
Workspace-bound arbitrary file upload, reading, OCR, and rendering for DeepSeek Harness.
Unified web search provider for DeepSeek Harness (ctx.web): 11 backends — Exa + Parallel + DDG + SearXNG (keyless), DeepSeek + Anthropic + OpenAI + Brave + Tavily + Serper + Mojeek (key-gated via Settings credentials). Registers provider id "unified" for zero-config web_search tool.
Multi-channel IM bridge for DeepSeek Harness: Feishu, Telegram, DingTalk, Slack, Discord — persistent sessions, true streaming, slash commands
Image preview in the dsh session: read_image tool results render as a small thumbnail by default and open full-size in the built-in lightbox on click
Open WSL Linux paths from DeepSeek Harness chat in Windows Explorer or the default Windows app.
Manage OpenCode Zen free-tier and Go-tier models in settings.yaml: live model listings from opencode.ai, configured-versus-live drift per route, add/remove through four agent tools plus an OpenCode Models settings section.
Academic Paper Search bridge for DeepSeek Harness: verified multi-source literature search over the existing MCP server.