dsh-llm-codex-app-server
DeepSeek Harness LLM provider backed by the locally authenticated Codex App Server
820 results
DeepSeek Harness LLM provider backed by the locally authenticated Codex App Server
DeepSeek Harness 第三方订阅接入插件:登录第三方订阅账户即可使用订阅内的模型(当前支持 OpenAI / ChatGPT 订阅,更多订阅服务规划中;支持图片理解与对话内图片生成、编辑)
DeepSeek Harness LLM provider for Codex models using managed ChatGPT OAuth
OpenTelemetry and Langfuse observability exporter for DeepSeek Harness: turn/step/tool/LLM spans, token and cost metrics, and sanitized LLM prompt/completion capture from the session/event stream, with async batching, bounded offline buffering, and retry with backoff.
Detect which conversation model your DeepSeek Harness account is served: score probe conversations' live chain-of-thought, cancel old-model probes in seconds, keep confident catches.
DSH web plugin: a usage statistics panel with per-day token trend, GitHub-style activity heatmap, cache hit-rate curve and per-model / per-provider breakdowns, replicating the reasonix usage stats feature.
Inject an x-session-id HTTP header onto every DeepSeek Harness LLM provider request, carrying the harness session id of that exact call; also covers whitelisted gateway fetches during tool execution.
DSH 插件:LLM 自动重试设置卡片——重试次数/退避/抖动与 25 个错误码可勾选(也能自己输入),可按 provider/model 单独设策略、回答被输出 token 上限截断时自动续写且提示词可改,内置重试观测面板,改完实时生效。
心虫 HeartFlow — AGI 第1层辨别门禁作为 DSH 插件: 47维纯规则判别 (heartflow_check/analyze/verdict/dimensions) + 工具调用后自动输出监督, fail-closed, 零LLM依赖
Provider fallback chain for the DeepSeek Harness LLM seam
DeepSeek Harness plugin: 在侧边栏展示当前 DSH 中配置的所有模型 Provider 的账号余额(余额面板 + 底部快捷入口)
A DeepSeek Harness plugin bundle for Telegram relay integration.
TradingAgents for DeepSeek Harness: the 14-role A-share multi-agent analysis pipeline (analysts → bull/bear debate → research manager → risk debate → trader) behind the /trading-agent command. · A股多智能体投研分析插件。
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。
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).
267 个即插即用的 AI 专家角色定义——从前端开发到区块链安全,从小红书运营到抖音策略(移植自 agency-agents-zh)
DSH host plugin — smart outbound HTTP(S) routing: named proxies (http/https/socks4/4a/5/5h), per-host/provider/plugin rules, direct-first fallback with health memory (global fetch + node http/https).
DeepSeek Harness (dsh) web plugin — Codex-style attachment expansion: PDF text-layer (pymupdf4llm/pdfjs), Office (docx/xlsx/pptx) to Markdown, TIFF/epub/odt/rtf, long-document spill to index cards, scanned-PDF OCR (tesseract.js + 8 cloud providers inc. DeepSeek Vision), and browser image to PNG. dsh-plugin for the DeepSeek Harness Web GUI.
Token-efficient catgirl persona runtime for DeepSeek Harness
Thin routing policy for DeepSeek Harness: keyword routing, allowlisted model switching, and isolated image generation. / DeepSeek Harness 薄路由策略:关键词路由、白名单模型切换和隔离生图。
Persistent global fetch proxy for DeepSeek Harness LLM requests (undici setGlobalDispatcher + EnvHttpProxyAgent), configured via the llm-proxy settings namespace
DSH performance plugin: llm/stream chunk coalescing (regular) and experimental trajectory-view replacement / chat rendering hints / runtime row management, with a Settings -> Plugins config card.
Real-time chain-of-thought trajectory profiling for DeepSeek Harness: live wording indicators, profile-family judgment, and per-session measurement records
DSH plugin: auto-fill metadata (context length, output cap, display name, input modalities) for custom-provider models from the Model Metadata Registry (models.dev).