Files
ragflow/internal/entity/models/volcengine.go
Hz_ 944d726284 fix(go-models): record provider token usage (#17423)
## Summary

- Parse chat, embedding, and rerank usage from provider responses
- Record usage with the correct model type even when no usage sink is
provided
- Cover SiliconFlow, Aliyun, Huawei Cloud, Qiniu, and VolcEngine
response formats
2026-07-27 17:16:50 +08:00

25 KiB