dsh-openai-codex
OpenAI Codex (ChatGPT subscription) authentication and LLM provider for deepseek-harness
621 results
OpenAI Codex (ChatGPT subscription) authentication and LLM provider for deepseek-harness
Native DSH settings page for daily provider usage, subscription quotas, and API price estimates.
Per-model reasoning effort declarations for GPT, Gemini and OpenAI-compatible providers in DeepSeek Harness
DSH 插件(用量中心):常驻用量卡片 · 多提供方用量/余额查询(OpenCode Go 订阅 + DeepSeek 余额 + Command Code 订阅/余额,对齐 cc-switch 查询语义)
Use a SuperGrok / X Premium subscription inside DeepSeek Harness. Device-code OAuth, grok-bridge token reuse, no xAI API key. Works in headless, web, and any TUI.
CodeBuddy/WorkBuddy models bundle for DeepSeek Harness (dsh): reads the local desktop login and serves the CodeBuddy subscription as a native provider route in the model picker
Multi-Model Fusion Orchestrator (MoA) over registered DeepSeek Harness LLM providers: conductor-led fan-out, evidence ledger, verify/synthesize loop, zero training.
TokenLab provider bundle for DeepSeek Harness with native Responses, Messages and Chat routing plus multimodal and async tools.
Provider-scoped HTTP/HTTPS forward proxy middleware for DeepSeek Harness LLM requests
One-shot Grok CLI subagent provider for DeepSeek Harness
Multi-provider third-party web search for the DeepSeek Harness: routes the native web_search tool through a configurable provider fallback chain, with an isolated provider settings page.
Per-provider request headers in the DeepSeek Harness Models settings page, with per-conversation ${sessionId} expansion.
Replacement session-title provider for DeepSeek Harness: compresses oversized first prompts instead of failing, and gates weak prompts.
DeepSeek Harness bundle for MotoMoto's OpenAI-compatible endpoint: a pi-ai provider route plus a status card in Settings - Plugins.
LLM provider plugin for the DeepSeek Harness (dsh): streams Claude (Sonnet/Haiku/Opus) through your Claude Code subscription (claude.ai OAuth credentials), no Anthropic API key required.
Configure Responses reasoning mode and summary per provider/model in DeepSeek Harness
统计本机全部 DSH 会话的历史 token 总消耗,按 message.id 去重,支持按天/模型/Provider/项目分组。Global token-usage totals across all DSH conversations.
Provider-based inline context picker for DeepSeek Harness
Declare whether a configured third-party model accepts image (multimodal) input; writes the modality into the owning provider settings and verifies it through runtime model resolution.
Exa web search provider for the DeepSeek Harness ctx.web seam, with Dynamic Highlights on by default, an /exa command to change highlights, search type and result count at runtime, and an exa_search tool that owns its own result cap.
DSH/Cordis Web plugin: a zoomable relation graph of every loaded plugin - dependencies, resolved providers, and Loader-tree nesting - as a Settings tab next to 'Plugin list'.
Zhipu BigModel/GLM provider toolkit for DeepSeek Harness: dual-endpoint model catalog (Coding Plan + ordinary API), verified thinking-level mapping, live model discovery
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.
Six-tier web search provider for the ctx.web seam: free local scraping with a billing-guarded official fallback (allowOfficial, default off), a tier-capable web_search_deep tool a preset cannot shadow, and a settings card.