GitHub user richardchen874-sys added a comment to the discussion: [Discussion] 
The selection of Agentic/Taskflow frame

HugeGraph's Agentic/Taskflow frame choice is really a per-stage routing 
problem: extraction, retrieval, reasoning, and fallback should not all share 
one cost profile.

I would keep provider, model, request type, prompt/output tokens, cached-token 
behavior, latency, retry count, and final billing bucket together in one event. 
That makes cost debugging and future routing decisions much easier.

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 hugegraph-ai, would the first win be 
user-facing cost transparency, internal spend debugging, or routing cheaper 
calls to cheaper models?

GitHub link: 
https://github.com/apache/hugegraph-ai/discussions/203#discussioncomment-17936098

----
This is an automatically sent email for [email protected].
To unsubscribe, please send an email to: [email protected]

Reply via email to