[Bugfix] Fix --enable-prompt-tokens-details omitting zero cached tokens (#44383)

Signed-off-by: Sasindharan Sankar <sasindharansankar@email.com>
Co-authored-by: Sasindharan Sankar <sasindharansankar@email.com>
Co-authored-by: Chauncey <chaunceyjiang@gmail.com>
This commit is contained in:
sasindharan
2026-06-11 20:37:42 -07:00
committed by GitHub
co-authored by Sasindharan Sankar Chauncey
parent 2263f8a3de
commit 42ae5e7ac6
5 changed files with 61 additions and 9 deletions
@@ -58,9 +58,12 @@ async def test_single_completion(client: openai.AsyncOpenAI, model_name: str) ->
choice = completion.choices[0]
assert len(choice.text) >= 5
assert choice.finish_reason == "length"
assert completion.usage == openai.types.CompletionUsage(
completion_tokens=5, prompt_tokens=6, total_tokens=11
)
assert completion.usage is not None
assert completion.usage.completion_tokens == 5
assert completion.usage.prompt_tokens == 6
assert completion.usage.total_tokens == 11
assert completion.usage.prompt_tokens_details is not None
assert completion.usage.prompt_tokens_details.cached_tokens == 0
# test using token IDs
completion = await client.completions.create(