xrk-v3-api
Skill140 starsChanged 8 months agoMITView on GitHub
当你需要对接/调试标准 LLM 网关 `/v1/chat/completions`、`/v1/responses`、`/v1/messages` 与 SSE 时使用。
In this repository43 other files it gives its agents.
- AGENTS.mdAGENTS.md
- docs/agents.mdAGENTS.md
- .cursor/rules/vibe-learn-craft.mdcCursor rule
- .cursor/rules/xrk-core-code.mdcCursor rule
- .cursor/rules/xrk-dev-requirements.mdcCursor rule
- .cursor/rules/xrk-infrastructure.mdcCursor rule
- .cursor/rules/xrk-project.mdcCursor rule
- .cursor/rules/xrk-third-party-plugins.mdcCursor rule
- accessibility-complianceSkill
- design-system-patternsSkill
- fronted-designSkill
- immersive-short-videoSkill
- interaction-designSkill
- mobile-android-designSkill
- mobile-ios-designSkill
- react-native-designSkill
- responsive-designSkill
- ui-ux-pro-maxSkill
- visual-design-foundationsSkill
- web-component-designSkill
- xrk-agent-runtimeSkill
- xrk-ai-workflowSkill
- xrk-app-devSkill
- xrk-authSkill
- xrk-coding-styleSkill
- xrk-configSkill
- xrk-crawlSkill
- xrk-dockerSkill
- xrk-docsSkill
- xrk-github-researchSkill
- xrk-http-apiSkill
- xrk-infrastructureSkill
- xrk-llmSkill
- xrk-mcpSkill
- xrk-node-runtimeSkill
- xrk-pluginsSkill
- xrk-project-overviewSkill
- xrk-rendererSkill
- xrk-runtime-utilSkill
- xrk-subserverSkill
- xrk-system-coreSkill
- xrk-taskerSkill
- xrk-www-compatSkill
The file
Files
实现
core/system-Core/http/ai.js:仅标准运营商路由core/system-Core/lib/ai-gateway/:协议转换
对外网关(仅这些)
POST /v1/chat/completions·/openai/v1/chat/completionsGET /v1/models·/v1/models/:id(及/openai/v1/...)POST /v1/messages(Anthropic)POST /v1/responses·/openai/v1/responsesGET /v1/responses/:id→ 404(store=false)
已移除:/api/v3/*、/api/ai/stream。控制台 LLM 目录在 ai-workspace:GET /api/ai/models。
约定
model= provider key;Chat SSE 含[DONE]。- Responses:不持久化;忽略
previous_response_id。 /v1/*、/openai/v1/*使用systemAuth: 'ai.v1'。
排障
401 → docs/AUTH.md;无 provider → ai-workflow.yaml。
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

