Skip to content

fix: handle missing usage object in OpenAIClient #15

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 2 commits into from
Jan 5, 2026
Merged

fix: handle missing usage object in OpenAIClient #15

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
9bdd750
fix: improve token tracking in OpenAIClient to handle missing usage a…
lakshyaag Jan 5, 2026
4393a72
feat: enhance OpenAIClient to support additional usage tracking for P…
lakshyaag Jan 5, 2026
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
32 changes: 25 additions & 7 deletions rlm/clients/openai.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -13,6 +13,7 @@
# Load API keys from environment variables
DEFAULT_OPENAI_API_KEY = os.getenv("OPENAI_API_KEY")
DEFAULT_OPENROUTER_API_KEY = os.getenv("OPENROUTER_API_KEY")
DEFAULT_PRIME_INTELLECT_BASE_URL = "https://api.pinference.ai/api/v1/"


class OpenAIClient(BaseLM):
Expand Down Expand Up @@ -58,7 +59,13 @@ def completion(self, prompt: str | list[dict[str, Any]], model: str | None = Non
if not model:
raise ValueError("Model name is required for OpenAI client.")

response = self.client.chat.completions.create(model=model, messages=messages)
extra_body = {}
if self.client.base_url == DEFAULT_PRIME_INTELLECT_BASE_URL:
extra_body["usage"] = {"include": True}

response = self.client.chat.completions.create(
model=model, messages=messages, extra_body=extra_body
)
self._track_cost(response, model)
return response.choices[0].message.content

Expand All @@ -76,19 +83,30 @@ async def acompletion(
if not model:
raise ValueError("Model name is required for OpenAI client.")

response = await self.async_client.chat.completions.create(model=model, messages=messages)
extra_body = {}
if self.base_url == DEFAULT_PRIME_INTELLECT_BASE_URL:
extra_body["usage"] = {"include": True}

response = await self.async_client.chat.completions.create(
model=model, messages=messages, extra_body=extra_body
)
self._track_cost(response, model)
return response.choices[0].message.content

def _track_cost(self, response: openai.ChatCompletion, model: str):
self.model_call_counts[model] += 1
self.model_input_tokens[model] += response.usage.prompt_tokens
self.model_output_tokens[model] += response.usage.completion_tokens
self.model_total_tokens[model] += response.usage.total_tokens

usage = getattr(response, "usage", None)
if usage is None:
raise ValueError("No usage data received. Tracking tokens not possible.")

self.model_input_tokens[model] += usage.prompt_tokens
self.model_output_tokens[model] += usage.completion_tokens
self.model_total_tokens[model] += usage.total_tokens

# Track last call for handler to read
self.last_prompt_tokens = response.usage.prompt_tokens
self.last_completion_tokens = response.usage.completion_tokens
self.last_prompt_tokens = usage.prompt_tokens
self.last_completion_tokens = usage.completion_tokens

def get_usage_summary(self) -> UsageSummary:
model_summaries = {}
Expand Down