dsh-llm-codex-app-server
DeepSeek Harness LLM provider backed by the locally authenticated Codex App Server
864 results
DeepSeek Harness LLM provider backed by the locally authenticated Codex App Server
Global Qoder subscription adapter for the DeepSeek Harness LLM seam
DSH plugin: start/stop a local llama.cpp llama-server from the settings → plugins page — two model slots (A/B) with per-slot model-file selection, eight editable launch-parameter groups (text/vision × fast/long × 2 slots), and one shared DSH provider carrying both slots' models with four thinking-effort levels.
Cache-stable progressive tool discovery and dispatch for DeepSeek Harness
LLM-as-a-Verifier for DeepSeek Harness: fine-grained reward, Probabilistic Pivot Tournament best-of-N selection, and per-step progress tracking as agent tools.
TeamFlow 团队研发流水线(TypeScript):需求→PRD→设计→架构→技术方案→并行开发→QA→验收;backlog 持久化 + 断点续跑 + 完成汇报 + 防假交付;Web 团队工作台(conversation.view tab + 拖拽看板)
Google Antigravity OAuth Gemini provider for DeepSeek Harness
see_image tool for DSH: route image files to a configurable vision model (OpenAI-compatible API) and relay its description back to a text-only model
DSH 模型代理插件:按模型走代理(Clash 等),有官方出站代理包时复用其传输层,设置页实时生效。
Persistent global fetch proxy for DeepSeek Harness LLM requests (undici setGlobalDispatcher + EnvHttpProxyAgent), configured via the llm-proxy settings namespace
DSH plugin: pipes oversized command output through the external rtk CLI and hands the model RTK's condensed output instead of the raw text (a tools/post-execute result transformer).
Seamless API-key rotation for DeepSeek Harness LLM providers when subscription limits are hit
OpenCode Zen free models provider for dsh
Cut token cost without cutting model intelligence — a DeepSeek Harness (dsh) bundle plugin: structure-aware compression + TOON-style lossless encoding first + reversible spill-to-disk + real-time dashboard.
为 DeepSeek Harness 开发的「建议提示词」插件:单个 bundle 集成了宿主生成插件与 Web 输入框幽灵文字界面。每个 agent 回合完成后,通过一次有界的辅助 LLM 调用在会话日志中写入一条建议的下一条提示词;Web 端把它渲染为输入框内的幽灵占位文字,通过可配置的快捷键(默认 Tab)采纳进草稿。
Interactive multi-agent council and prompt arena for DeepSeek Harness
Use the locally installed Claude Code CLI as a DeepSeek Harness LLM provider — no API key, native tool calls through an MCP bridge
QQ Bot IM channel plugin for deepseek-harness (dsh)
Claude Code-style @path imports for DSH: expands @imports in AGENTS.md/CLAUDE.md and injects the referenced files into model context at session start
Cline free models provider for dsh: scan the Cline model catalog dynamically and serve the :free models through the harness LLM seam
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
Prompt enhancement plugin for DeepSeek Harness: an "✨ Enhance" composer button that rewrites prompts with first-principles thinking using session context, and asks clarifying questions when key info is missing.
DeepSeek Harness 批量并行子 Agent 调度插件:swarm_batch 工具(Kimi Code Swarm 模式移植)+ /swarm 命令 + 聊天内实时进度条。
Provider-level web search+fetch pool for DeepSeek Harness: bypass the official LLM search channel (0 model tokens), failover/rotate across Exa/Tavily/Jina/Firecrawl/Serper/SerpApi/SearXNG/DDG/Brave with quota-aware circuit breaking, multi-key rotation, and a GUI settings page.