Skip to content

fix: resolve type mismatch regarding usage summary #55

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
alexzhang13 merged 1 commit into from
Jan 19, 2026
Merged

fix: resolve type mismatch regarding usage summary #55

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
4 changes: 2 additions & 2 deletions rlm/clients/base_lm.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,7 +1,7 @@
from abc import ABC, abstractmethod
from typing import Any

from rlm.core.types import UsageSummary
from rlm.core.types import ModelUsageSummary, UsageSummary


class BaseLM(ABC):
Expand All @@ -28,6 +28,6 @@ def get_usage_summary(self) -> UsageSummary:
raise NotImplementedError

@abstractmethod
def get_last_usage(self) -> UsageSummary:
def get_last_usage(self) -> ModelUsageSummary:
"""Get the last cost summary of the model."""
raise NotImplementedError
12 changes: 8 additions & 4 deletions rlm/core/lm_handler.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -51,10 +51,12 @@ def _handle_single(self, request: LMRequest, handler: "LMHandler") -> LMResponse
content = client.completion(request.prompt)
end_time = time.perf_counter()

usage_summary = client.get_last_usage()
model_usage = client.get_last_usage()
root_model = request.model or client.model_name
usage_summary = UsageSummary(model_usage_summaries={root_model: model_usage})
return LMResponse.success_response(
chat_completion=RLMChatCompletion(
root_model=request.model or client.model_name,
root_model=root_model,
prompt=request.prompt,
response=content,
usage_summary=usage_summary,
Expand All @@ -76,11 +78,13 @@ async def run_all():
end_time = time.perf_counter()

total_time = end_time - start_time
usage_summary = client.get_last_usage()
model_usage = client.get_last_usage()
root_model = request.model or client.model_name
usage_summary = UsageSummary(model_usage_summaries={root_model: model_usage})

chat_completions = [
RLMChatCompletion(
root_model=request.model or client.model_name,
root_model=root_model,
prompt=prompt,
response=content,
usage_summary=usage_summary,
Expand Down