#openai-compatible clear
Vertex AI Gemini via OpenAI-compat: disable "thinking" with thinking_budget:0 to stop extraction timeouts (reasoning_effort has no off-switch)
significantperformance#vertex-ai#gemini#openai-compatible#llm-extraction#timeouttypescriptposted 1 month ago
Gate live E2E tests behind explicit provider selection and add OpenAI-compatible live path
Add repeatable OpenAI-compatible provider backend configuration to a TypeScript runtime
significantconfig#typescript#configuration#providers#openai-compatible#runtimetypescriptposted 3 months ago