[Frontend] Support count_reasoning_tokens in the Streaming Parser Engine (#45802)
Signed-off-by: chaunceyjiang <chaunceyjiang@gmail.com> Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
This commit is contained in:
co-authored by
mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
parent
5cecfc0137
commit
ac2ae8798c
@@ -117,11 +117,16 @@ class PromptTokenUsageInfo(OpenAIBaseModel):
|
||||
request has no multimodal input."""
|
||||
|
||||
|
||||
class CompletionTokenUsageInfo(OpenAIBaseModel):
|
||||
reasoning_tokens: int = 0
|
||||
|
||||
|
||||
class UsageInfo(OpenAIBaseModel):
|
||||
prompt_tokens: int = 0
|
||||
total_tokens: int = 0
|
||||
completion_tokens: int | None = 0
|
||||
prompt_tokens_details: PromptTokenUsageInfo | None = None
|
||||
completion_tokens_details: CompletionTokenUsageInfo | None = None
|
||||
|
||||
|
||||
class PerRequestTimingMetrics(OpenAIBaseModel):
|
||||
|
||||
Reference in New Issue
Block a user