Skip to content

Fix: Prevent cache token overwrite by last chunk in streaming usage #10284

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Apr 26, 2025
Merged

Fix: Prevent cache token overwrite by last chunk in streaming usage #10284

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
10 changes: 8 additions & 2 deletions litellm/litellm_core_utils/streaming_chunk_builder_utils.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -348,11 +348,17 @@ def calculate_usage(
and usage_chunk_dict["completion_tokens"] > 0
):
completion_tokens = usage_chunk_dict["completion_tokens"]
if usage_chunk_dict["cache_creation_input_tokens"] is not None:
if usage_chunk_dict["cache_creation_input_tokens"] is not None and (
usage_chunk_dict["cache_creation_input_tokens"] > 0
or cache_creation_input_tokens is None
):
cache_creation_input_tokens = usage_chunk_dict[
"cache_creation_input_tokens"
]
if usage_chunk_dict["cache_read_input_tokens"] is not None:
if usage_chunk_dict["cache_read_input_tokens"] is not None and (
usage_chunk_dict["cache_read_input_tokens"] > 0
or cache_read_input_tokens is None
):
cache_read_input_tokens = usage_chunk_dict[
"cache_read_input_tokens"
]
Expand Down
89 changes: 89 additions & 0 deletions tests/litellm/litellm_core_utils/test_streaming_chunk_builder_utils.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -16,6 +16,8 @@
Function,
ModelResponseStream,
StreamingChoices,
Usage,
PromptTokensDetails,
)


Expand Down Expand Up @@ -153,3 +155,90 @@ def test_get_combined_tool_content():
type="function",
),
]


def test_cache_read_input_tokens_retained():
chunk1 = ModelResponseStream(
id="chatcmpl-95aabb85-c39f-443d-ae96-0370c404d70c",
created=1745513206,
model="claude-3-7-sonnet-20250219",
object="chat.completion.chunk",
system_fingerprint=None,
choices=[
StreamingChoices(
finish_reason=None,
index=0,
delta=Delta(
provider_specific_fields=None,
content="",
role=None,
function_call=None,
tool_calls=None,
audio=None,
),
logprobs=None,
)
],
provider_specific_fields=None,
stream_options={"include_usage": True},
usage=Usage(
completion_tokens=5,
prompt_tokens=11779,
total_tokens=11784,
completion_tokens_details=None,
prompt_tokens_details=PromptTokensDetails(
audio_tokens=None, cached_tokens=11775
),
cache_creation_input_tokens=4,
cache_read_input_tokens=11775,
),
)

chunk2 = ModelResponseStream(
id="chatcmpl-95aabb85-c39f-443d-ae96-0370c404d70c",
created=1745513207,
model="claude-3-7-sonnet-20250219",
object="chat.completion.chunk",
system_fingerprint=None,
choices=[
StreamingChoices(
finish_reason="stop",
index=0,
delta=Delta(
provider_specific_fields=None,
content=None,
role=None,
function_call=None,
tool_calls=None,
audio=None,
),
logprobs=None,
)
],
provider_specific_fields=None,
stream_options={"include_usage": True},
usage=Usage(
completion_tokens=214,
prompt_tokens=0,
total_tokens=214,
completion_tokens_details=None,
prompt_tokens_details=PromptTokensDetails(
audio_tokens=None, cached_tokens=0
),
cache_creation_input_tokens=0,
cache_read_input_tokens=0,
),
)

# Use dictionaries directly instead of ModelResponseStream
chunks = [chunk1, chunk2]
processor = ChunkProcessor(chunks=chunks)

usage = processor.calculate_usage(
chunks=chunks,
model="claude-3-7-sonnet",
completion_output="",
)

assert usage.cache_creation_input_tokens == 4
assert usage.cache_read_input_tokens == 11775
Loading