[Bugfix][Responses API] Complete cache-write token accounting (#60973)
Signed-off-by: Kay Yan <kay.yan@daocloud.io> Co-authored-by: Codex <noreply@openai.com>
This commit is contained in:
@@ -881,7 +881,7 @@ class OpenAIServingResponses(GenerateBaseServing):
|
||||
output_tokens=num_generated_tokens,
|
||||
total_tokens=num_prompt_tokens + num_generated_tokens,
|
||||
input_tokens_details=InputTokensDetails(
|
||||
cache_write_tokens=getattr(context, "num_cache_creation_tokens", 0),
|
||||
cache_write_tokens=context.num_cache_creation_tokens,
|
||||
cached_tokens=num_cached_tokens,
|
||||
input_tokens_per_turn=[
|
||||
turn.input_tokens for turn in context.all_turn_metrics
|
||||
|
||||
Reference in New Issue
Block a user