scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-11-12 08:42:18 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 207

fix(github_copilot): surface copilot_usage token_details as cache token counts

Browse source
This commit is contained in:
Jeevan Babu Gotru 2026-10-27 09:46:48 -05:00 • committed by GitHub
parent cfe0100e1f
commit 5bf0f7706f
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
1 changed files with 53 additions and 1 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

54
litellm/llms/github_copilot/chat/transformation.py
View file

@ -28,6 +28,34 @@ if TYPE_CHECKING:
_DECODED_JSON: Final = TypeAdapter(object)
def copilot_cache_token_counts(usage: Mapping) -> tuple[int, int]:
copilot_usage: Final = usage.get("copilot_usage")
if not isinstance(copilot_usage, Mapping):
return 0, 0
token_details: Final = copilot_usage.get("token_details")
if not isinstance(token_details, list):
return 0, 0
cache_read: Final = sum(
entry["token_count"]
for entry in token_details
if isinstance(entry, Mapping)
and entry.get("token_type") == "cache_read"
and isinstance(entry.get("token_count"), int)
and not isinstance(entry.get("token_count"), bool)
and entry["token_count"] >= 0
)
cache_write: Final = sum(
entry["token_count"]
for entry in token_details
if isinstance(entry, Mapping)
and entry.get("token_type") == "cache_write"
and isinstance(entry.get("token_count"), int)
and not isinstance(entry.get("token_count"), bool)
and entry["token_count"] >= 0
)
return cache_read, cache_write
class GithubCopilotConfig(OpenAIConfig):
def __init__(
self,
@ -231,6 +259,17 @@ class GithubCopilotConfig(OpenAIConfig):
normalized["completion_tokens"] = usage["output_tokens"]
if "total_tokens" not in normalized:
normalized["total_tokens"] = normalized.get("prompt_tokens", 0) + normalized.get("completion_tokens", 0)
cache_read, cache_write = copilot_cache_token_counts(usage)
if cache_read and "cache_read_input_tokens" not in normalized:
normalized["cache_read_input_tokens"] = cache_read
if cache_write and "cache_creation_input_tokens" not in normalized:
normalized["cache_creation_input_tokens"] = cache_write
if cache_read:
existing_details: Final = normalized.get("prompt_tokens_details")
details: Final = dict(existing_details) if isinstance(existing_details, Mapping) else {}
if not details.get("cached_tokens"):
details["cached_tokens"] = cache_read
normalized["prompt_tokens_details"] = details
return normalized
@classmethod
@ -296,7 +335,11 @@ class GithubCopilotConfig(OpenAIConfig):
Repair the OpenAI-SDK-parsed response on the handler path that bypasses
transform_response. See: https://github.com/BerriAI/litellm/issues/30927
"""
return self._synthesize_choices_for_anthropic_native(parsed_response)
repaired: Final = self._synthesize_choices_for_anthropic_native(parsed_response)
usage: Final = repaired.get("usage")
if repaired.get("choices") and isinstance(usage, dict) and "copilot_usage" in usage:
return {**repaired, "usage": self._normalize_anthropic_usage(usage)}
return repaired
def transform_response(
self,
@ -337,6 +380,15 @@ class GithubCopilotConfig(OpenAIConfig):
headers=raw_response.headers,
content=json.dumps(synthesized).encode(),
)
else:
usage: Final = response_json.get("usage")
if isinstance(usage, dict) and "copilot_usage" in usage:
rewritten: Final = {**response_json, "usage": self._normalize_anthropic_usage(usage)}
raw_response = httpx.Response( # rebind-ok: replaces the raw body with the normalized usage payload
status_code=raw_response.status_code,
headers=raw_response.headers,
content=json.dumps(rewritten).encode(),
)
return super().transform_response(
model=model,