GitHub user richardchen874-sys added a comment to the discussion: [DISCUSS] New Agentic lakehouse module & built-in AI agent gateway
The agentic lakehouse module and AI agent gateway should be logged as a run-level decision, because model choice only matters if the task succeeds inside the latency and cost budget. I would log route choice, provider/model, tool-call support, latency, usage, and retry/fallback reason together. Agent failures are much easier to debug when the route decision is visible. I am working through similar issues while testing an OpenAI-compatible layer for official Chinese models, mainly around routing, cost visibility, and response-shape compatibility. For hudi, is the harder problem provider compatibility, routing quality, or keeping per-run cost predictable? GitHub link: https://github.com/apache/hudi/discussions/19264#discussioncomment-17792439 ---- This is an automatically sent email for [email protected]. To unsubscribe, please send an email to: [email protected]
