Skip to content

fix(sdk): snapshot LLM metrics via Metrics.get_snapshot() (Q2 of #3341) #3397

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
malhotra5 merged 1 commit into from
May 27, 2026
+3 −12
Merged

fix(sdk): snapshot LLM metrics via Metrics.get_snapshot() (Q2 of #3341) #3397

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
15 changes: 3 additions & 12 deletions openhands-sdk/openhands/sdk/llm/llm.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -105,7 +105,7 @@
)
from openhands.sdk.llm.utils.image_resize import maybe_resize_messages_for_provider
from openhands.sdk.llm.utils.litellm_provider import infer_litellm_provider
from openhands.sdk.llm.utils.metrics import Metrics, MetricsSnapshot
from openhands.sdk.llm.utils.metrics import Metrics
from openhands.sdk.llm.utils.model_features import get_features
from openhands.sdk.llm.utils.retry_mixin import RetryMixin
from openhands.sdk.llm.utils.telemetry import Telemetry
Expand Down Expand Up @@ -757,15 +757,6 @@ async def _ahandle_error(
# Shared helpers for completion / acompletion / responses / aresponses
# =========================================================================

def _current_metrics_snapshot(self) -> MetricsSnapshot:
"""Snapshot current LLM metrics for an :class:`LLMResponse`."""
return MetricsSnapshot(
model_name=self.metrics.model_name,
accumulated_cost=self.metrics.accumulated_cost,
max_budget_per_task=self.metrics.max_budget_per_task,
accumulated_token_usage=self.metrics.accumulated_token_usage,
)

def _make_retry_decorator(
self,
) -> Callable[[Callable[..., Any]], Callable[..., Any]]:
Expand All @@ -785,7 +776,7 @@ def _build_completion_result(self, resp: ModelResponse) -> LLMResponse:
message = Message.from_llm_chat_message(first_choice["message"])
return LLMResponse(
message=message,
metrics=self._current_metrics_snapshot(),
metrics=self.metrics.get_snapshot(),
raw_response=resp,
)

Expand All @@ -795,7 +786,7 @@ def _build_responses_result(self, resp: ResponsesAPIResponse) -> LLMResponse:
message = Message.from_llm_responses_output(output_seq)
return LLMResponse(
message=message,
metrics=self._current_metrics_snapshot(),
metrics=self.metrics.get_snapshot(),
raw_response=resp,
)

Expand Down
Loading