25 results
Per-model capability declaration for DeepSeek Harness: reasoning-effort levels (with wire spellings) and request modalities (text/image) for OpenAI-compatible providers — one settings section, no YAML hand-editing.
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)
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
Human-AI collaborative prototyping for DSH, Codex and MCP agents, from product clarification to editable Excalidraw wireframes and verified frontend generation.
pi-web-access for the DeepSeek Harness: multi-provider web search with automatic fallback (SearXNG → Tavily → Brave → keyless DuckDuckGo) plus URL content extraction, wired into the web seam so the built-in web_search tool is powered by piwa. Search engine toggle and API keys are configurable from the DSH settings page.
Mobile responsive shell (single-column layout, drawer sidebar, overlay details) and WireGuard remote enhancements for the DeepSeek Harness web GUI
Per-project runtime environments for DeepSeek Harness: auto-adopt or create a project-local Python venv (.venv_local/python) and wire in the toolchains/env vars for the runtimes each project uses.
The public-apis catalog wired into DeepSeek Harness: search 1716 free public APIs by keyword/category/auth/HTTPS/CORS so the agent can discover and call any of them.
电线线径选择
Three Ark presets (ark/ark-code/ark-cordis) and a side-channel CLI for DeepSeek Harness: frozen minimal wire surface with on-demand instructions, skills, tools, and MCP.
Unattended full-access (yolo) mode for the DeepSeek Harness: a human-only /yolo switch arms danger-full-access + never-approval for long autonomous runs, with a best-effort catastrophic-command tripwire guard, optional time-boxed expiry, and idle/denial notifications (desktop / webhook / email)
DSH bundle: wire the Butler Memory MCP server (agent tools) and add a Web memory panel (view/search/candidates)
Safety-gated WireGuard and VLESS Reality operations for DeepSeek Harness
DeepSeek Harness plugin that serves every gpt-load model from one provider group, each model on its own wire protocol (OpenAI Chat Completions or Anthropic Messages), synced from /api/models
Mchose wireless mouse battery + connection-mode indicator in the DSH sidebar (WebHID)
Multi-provider LLM configuration for the DeepSeek Harness LLM seam: declare any number of providers, each with its own endpoint, credential and per-model parameters, across the OpenAI Chat, OpenAI Responses, Anthropic Messages and Google Gemini wire formats.
Neutralize tool calls with invalid JSON arguments on the wire, so one malformed model generation cannot brick a session against strict OpenAI-compatible servers (vLLM et al).
DeepSeek Harness relay: mirror the home dsh web UI to the public internet through an outbound wire trunk (cloud relay + out-of-tree host plugin).
DSH LLM provider hub with a native model-configuration panel, gateway routes, model catalogs and live model discovery. Supports three wire protocols, custom User-Agent, model overrides and live routing without hand-editing settings.yaml.
A self-contained desktop pet plugin for DeepSeek Harness: Codex-style frame-animated pet living on your desktop, with its own affinity state machine, pet registry (Codex pet.json compatible), activity bubbles wired to harness sessions, decorations, and a settings-page card. No web pet required.
DeepSeek Harness plugin that captures the raw HTTP request and response bodies of model provider calls, shows the request body as a collapsible size-annotated JSON tree in a Conversation View tab and on a loopback viewer page, and assembles SSE responses back into reasoning, content and tool calls.
Third-party provider reasoning-effort AND input-modality settings for DeepSeek Harness: thinking levels and image-input support declared per model, auto-adapted from a model knowledge base + wire-protocol inference, edited right inside the official Models
A configurable branch-role guard for AI coding agents (DSH / Claude Code / Codex / OpenCode / Antigravity / Pi / CodeBuddy / ZCode / Cursor) — zero-config defaults (develop+main) out of the box, deep-merge override, per-client native hooks via gitflow-gua
Preview and download the exact request frame (system prompt + tools + wire messages) that DeepSeek Harness sends to the model.