dsh-plugin-zen-useragent
让 provider 配置的 headers(如 User-Agent)真正到达 pi-ai 的 API 请求,并自动补全 opencode 身份头 —— 修复 OpenCode ZEN 免费模型 429(FreeUsageLimitError)与 400(MissingSessionID):把请求识别为 opencode 客户端而不是 deepseek-harness
1994 results
让 provider 配置的 headers(如 User-Agent)真正到达 pi-ai 的 API 请求,并自动补全 opencode 身份头 —— 修复 OpenCode ZEN 免费模型 429(FreeUsageLimitError)与 400(MissingSessionID):把请求识别为 opencode 客户端而不是 deepseek-harness
DeepSeek Harness vision enhancer: raises image limits to the official DeepSeek values, raises the per-model request image budget for DeepSeek-V4.1-Flash, and provides high-resolution tiled image reading via a dedicated tool.
Model router & cost optimizer for DeepSeek Harness: heuristic tier routing between cheap and strong models, automatic fallback on transient failures, and a per-session token/cache/cost panel in the composer dock.
DeepSeek Harness 插件:导入 claude-code / codex / reasonix / zcode 的聊天记录为 dsh 会话(含工作区绑定)。
Claude Code outputStyles-equivalent runtime output-style switching for DeepSeek Harness
Codex-style desktop pet for the DSH web GUI: a floating animated sprite driven by the agent's running state
DSH Web 会话头部大模型余量监控插件:当前模型额度徽标 + 全部提供方详情弹层 + 用量统计页签
CC Switch-style token consumption statistics for the DeepSeek Harness Web GUI: per-request usage log, real-consumption hero, request-time-bucketed trend chart, per-model peak/off-peak list pricing, per-project and per-model stats, and account balance.
Xiaomi MiMo text-to-speech controls for DeepSeek Harness Web assistant messages
Per-model token usage, cost estimation and DeepSeek account balance for the DeepSeek Harness Web settings panel.
DSH Windows default shell policy plugin: probe git-bash/MSYS2, switch bash/pwsh from the plugin config card, register the bash tool and trim the prompt tool surface. DSH Windows 默认 Shell 策略插件:探测 git-bash,配置面板切换 bash/pwsh,动态注册 bash 工具并裁剪提示词工具面
Floating notes for the dsh web GUI: keep commands, credentials, parameter values and other important snippets at hand while working, insert any note straight into the composer, and save any selected text (e.g. from an AI answer) as a note with one click
Solarized + Selenized themes for DeepSeek Harness: four faithful palettes (Solarized Dark/Light, Selenized Dark/Light) registered into DSH's theme runtime with a picker row in Settings, including the canonical syntax colors for markdown code blocks
A general-purpose knowledge base plugin for DeepSeek Harness (DSH): import documents (md/txt/json/yml/docx/pdf), organize them in folders, and search with FTS5. 通用知识库插件:文件导入、目录化管理、全文检索、知识库管理 UI。
Free vision plugin for DeepSeek Harness (dsh): image understanding for text-only models with free-tier providers (Qwen3-VL-Flash / DeepSeek-OCR / Doubao). 免费视觉插件:纯文本模型看图能力,优先免费模型(通义千问 / 硅基流动 / 豆包)。
将原作者 linshenkx 的 prompt-optimizer 移植到 DeepSeek Harness 的第三方插件
Custom convenience suite for the dsh web GUI: appearance, timeline, folders, prompts, session export/search, Mermaid, quote reply, usage analytics, local budget, key-free backups, and a Ctrl/Cmd+K command palette; dual-face plugin mounted without dsh source changes.
Xiaomi MiMo search + multimodal tools for DSH agents: mimo_search/vision/audio/video/asr/tts.
Auditable vision and cross-platform Computer Use runtime for DeepSeek Harness with source-preserving evidence.
Enhanced ACP server for DeepSeek Harness: block-level streaming, usage/stat telemetry (cache hit rate, token speed, input/output tokens, context length, turns, tool timing), model & reasoning-effort switching, and permission-preset control over the ACP wire (Zed-friendly)
Write in parallel, never overwrite — file claim / protection for concurrent DeepSeek Harness (DSH) sessions working the same workspace: claim/release, heartbeat stale takeover, and an async pending merge area (git 3-way merge)
dsh plugin: recognize attached images with the built-in Windows OCR engine (Windows.Media.Ocr) and send only the recognized text to the model. Text models never receive image bytes; vision passthrough is opt-in.
One memory layer for every AI tool and agent, packaged for DeepSeek Harness with startup context, prompt-time recall, Mem MCP tools, and DSH thread capture.
Tuning Engines CLI, MCP server, and Python agent runtime adapters for governed model, agent, skill, and MCP workflows. Fine-tune open-source LLMs, run inference, manage datasets/evaluations, and connect LangGraph or Temporal while Tuning Engines handles policy, audit, usage, and token economics.