Run or inspect local Release-Green checks for a specific code revision or combined pull request candidate. Report blocking failures, diagnostic differences, and missing evidence, compare against the base revision, and identify remaining CI checks.
中文简介正在准备中。当前显示英语简介。
Repair confirmed failures in CI, the automated build and test process, starting with the base branch. Then prepare affected pull requests individually, recording checks for the exact code candidate and unresolved issues for owner review.
中文简介正在准备中。当前显示英语简介。
Configure Codex CLI to connect through OmniRoute on Linux, macOS, or Windows. The workflow detects the operating system and shell, creates configuration files and seven profiles, sets environment variables, and verifies the setup.
中文简介正在准备中。当前显示英语简介。
Manage API key authentication and session tokens. Start here to authenticate requests via Bearer token, obtain session cookies, and configure login requirements for the OmniRoute API.
中文简介正在准备中。当前显示原文说明。
管理将OmniRoute事件发送到外部的Webhook，可设置请求完成、失败和配额超限通知，并处理通知地址验证、测试发送、投递历史查询与重试管理。
Create and run automated tests that score LLM answers against expected outputs or judging criteria. Monitor progress, inspect individual results, compare models on the same tests, and use score thresholds in CI, an automated checking workflow.
中文简介正在准备中。当前显示英语简介。
Connect AI agents to OmniRoute through MCP, a protocol for accessing tools. Use tools for request routing, memory, cache, providers, and audits, with three connection methods and permission scopes that control which operations are available.
中文简介正在准备中。当前显示英语简介。
Find agent skills on GitHub, score their relevance using rule-based checks, scan for malware and embedded secrets, and import them into supported agent directories, including Hermes, Claude Code, Gemini CLI, and OpenCode.
中文简介正在准备中。当前显示英语简介。
Synchronize OmniRoute configuration, provider connections, and settings with cloud storage. Manage authentication for the cloud worker, a remote service, along with its credentials and remote backup destinations.
中文简介正在准备中。当前显示英语简介。
Create, list, rotate, and revoke OmniRoute API keys. Control per-key scopes, spending limits, and expiration. Keys gate access to all proxy and management endpoints.
中文简介正在准备中。当前显示原文说明。
Create and manage secure tunnels that make OmniRoute accessible over the internet. Use ngrok, Cloudflare Tunnel, or a custom tunnel to share access with remote agents and automated build and test pipelines.
中文简介正在准备中。当前显示英语简介。
Configure prompt compression, which shortens text sent to AI models, through the OmniRoute command line. Adjust RTK filters, Caveman rules, and combined compression modes, then preview the results using real prompts.
中文简介正在准备中。当前显示英语简介。
Create, list, rotate, and revoke OmniRoute API keys from the CLI. Manage OAuth flows for provider authentication and inspect key scopes and expiration.
中文简介正在准备中。当前显示原文说明。
Keep coding changes small by questioning unnecessary work and reusing existing code, standard libraries, and native platform features. Apply this approach to implementation, bug fixes, reviews, and dependency choices while preserving validation, security, and accessibility.
中文简介正在准备中。当前显示英语简介。
Manage provider connections, API keys, OAuth flows, and connection tests via the REST API. List, add, update, remove, and test AI provider integrations across OmniRoute's 375-provider catalog.
中文简介正在准备中。当前显示原文说明。
通过命令行启动、停止和重启 OmniRoute 服务器，指定端口，配置后台运行、自动恢复和系统托盘显示，并打开管理面板。
通过命令行向OmniRoute的A2A服务器发送任务，查看执行历史和日志，监控或取消任务，并交互测试智能体之间的通信。
Review AI call logs by provider, model, time range, status, and cost. Aggregate token usage, export logs, configure budgets, and inspect response times and prompt cache statistics to understand usage and performance.
中文简介正在准备中。当前显示英语简介。
Create, list, switch, and delete model routing combinations from the command line. Request suggestions using task descriptions, cost limits, and response time limits, with an option to explain recommendations or activate a suggested setup.
中文简介正在准备中。当前显示英语简介。
Query available AI models across all configured providers. List models, resolve model aliases, and browse the full model catalog including provider-specific variants.
中文简介正在准备中。当前显示原文说明。
Submit groups of AI requests as batch jobs with the OmniRoute command line. Manage input files, monitor or cancel jobs, save results and errors, and incorporate batch processing into automated build and deployment workflows.
中文简介正在准备中。当前显示英语简介。
Configure compression for command output, prose, and chat history before sending them to AI providers. Choose suitable engines, adjust language rules, and preview compressed text and reported savings before enabling a mode.
中文简介正在准备中。当前显示英语简介。
Manage Omni Skills, plugins, and persistent memory from the command line. Find and install skills, run them with supplied input, inspect execution history, and maintain saved information alongside plugin installations.
中文简介正在准备中。当前显示英语简介。
Query OmniRoute through A2A, a protocol for communication between agents. Get provider and model recommendations, check remaining quotas, find providers with required features, estimate request costs, and review system health.
中文简介正在准备中。当前显示英语简介。