Skip to content

fix(telemetry): export cache token metrics as strings #1000

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

Open
wants to merge 1 commit into
base: main
Choose a base branch
from
Open

fix(telemetry): export cache token metrics as strings #1000

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
28 changes: 14 additions & 14 deletions src/strands/telemetry/tracer.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -289,13 +289,13 @@ def end_model_invoke_span(
error: Optional exception if the model call failed.
"""
attributes: Dict[str, AttributeValue] = {
"gen_ai.usage.prompt_tokens": usage["inputTokens"],
"gen_ai.usage.input_tokens": usage["inputTokens"],
"gen_ai.usage.completion_tokens": usage["outputTokens"],
"gen_ai.usage.output_tokens": usage["outputTokens"],
"gen_ai.usage.total_tokens": usage["totalTokens"],
"gen_ai.usage.cache_read_input_tokens": usage.get("cacheReadInputTokens", 0),
"gen_ai.usage.cache_write_input_tokens": usage.get("cacheWriteInputTokens", 0),
"gen_ai.usage.prompt_tokens": str(usage["inputTokens"]),
"gen_ai.usage.input_tokens": str(usage["inputTokens"]),
"gen_ai.usage.completion_tokens": str(usage["outputTokens"]),
"gen_ai.usage.output_tokens": str(usage["outputTokens"]),
"gen_ai.usage.total_tokens": str(usage["totalTokens"]),
"gen_ai.usage.cache_read_input_tokens": str(usage.get("cacheReadInputTokens", 0)),
"gen_ai.usage.cache_write_input_tokens": str(usage.get("cacheWriteInputTokens", 0)),
}

if self.use_latest_genai_conventions:
Expand Down Expand Up @@ -607,13 +607,13 @@ def end_agent_span(
accumulated_usage = response.metrics.accumulated_usage
attributes.update(
{
"gen_ai.usage.prompt_tokens": accumulated_usage["inputTokens"],
"gen_ai.usage.completion_tokens": accumulated_usage["outputTokens"],
"gen_ai.usage.input_tokens": accumulated_usage["inputTokens"],
"gen_ai.usage.output_tokens": accumulated_usage["outputTokens"],
"gen_ai.usage.total_tokens": accumulated_usage["totalTokens"],
"gen_ai.usage.cache_read_input_tokens": accumulated_usage.get("cacheReadInputTokens", 0),
"gen_ai.usage.cache_write_input_tokens": accumulated_usage.get("cacheWriteInputTokens", 0),
"gen_ai.usage.prompt_tokens": str(accumulated_usage["inputTokens"]),
"gen_ai.usage.completion_tokens": str(accumulated_usage["outputTokens"]),
"gen_ai.usage.input_tokens": str(accumulated_usage["inputTokens"]),
"gen_ai.usage.output_tokens": str(accumulated_usage["outputTokens"]),
"gen_ai.usage.total_tokens": str(accumulated_usage["totalTokens"]),
"gen_ai.usage.cache_read_input_tokens": str(accumulated_usage.get("cacheReadInputTokens", 0)),
"gen_ai.usage.cache_write_input_tokens": str(accumulated_usage.get("cacheWriteInputTokens", 0)),
}
)

Expand Down
84 changes: 42 additions & 42 deletions tests/strands/telemetry/test_tracer.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -209,13 +209,13 @@ def test_end_model_invoke_span(mock_span):

tracer.end_model_invoke_span(mock_span, message, usage, stop_reason)

mock_span.set_attribute.assert_any_call("gen_ai.usage.prompt_tokens", 10)
mock_span.set_attribute.assert_any_call("gen_ai.usage.input_tokens", 10)
mock_span.set_attribute.assert_any_call("gen_ai.usage.completion_tokens", 20)
mock_span.set_attribute.assert_any_call("gen_ai.usage.output_tokens", 20)
mock_span.set_attribute.assert_any_call("gen_ai.usage.total_tokens", 30)
mock_span.set_attribute.assert_any_call("gen_ai.usage.cache_read_input_tokens", 0)
mock_span.set_attribute.assert_any_call("gen_ai.usage.cache_write_input_tokens", 0)
mock_span.set_attribute.assert_any_call("gen_ai.usage.prompt_tokens", "10")
mock_span.set_attribute.assert_any_call("gen_ai.usage.input_tokens", "10")
mock_span.set_attribute.assert_any_call("gen_ai.usage.completion_tokens", "20")
mock_span.set_attribute.assert_any_call("gen_ai.usage.output_tokens", "20")
mock_span.set_attribute.assert_any_call("gen_ai.usage.total_tokens", "30")
mock_span.set_attribute.assert_any_call("gen_ai.usage.cache_read_input_tokens", "0")
mock_span.set_attribute.assert_any_call("gen_ai.usage.cache_write_input_tokens", "0")
mock_span.add_event.assert_called_with(
"gen_ai.choice",
attributes={"message": json.dumps(message["content"]), "finish_reason": "end_turn"},
Expand All @@ -235,13 +235,13 @@ def test_end_model_invoke_span_latest_conventions(mock_span):

tracer.end_model_invoke_span(mock_span, message, usage, stop_reason)

mock_span.set_attribute.assert_any_call("gen_ai.usage.prompt_tokens", 10)
mock_span.set_attribute.assert_any_call("gen_ai.usage.input_tokens", 10)
mock_span.set_attribute.assert_any_call("gen_ai.usage.completion_tokens", 20)
mock_span.set_attribute.assert_any_call("gen_ai.usage.output_tokens", 20)
mock_span.set_attribute.assert_any_call("gen_ai.usage.total_tokens", 30)
mock_span.set_attribute.assert_any_call("gen_ai.usage.cache_read_input_tokens", 0)
mock_span.set_attribute.assert_any_call("gen_ai.usage.cache_write_input_tokens", 0)
mock_span.set_attribute.assert_any_call("gen_ai.usage.prompt_tokens", "10")
mock_span.set_attribute.assert_any_call("gen_ai.usage.input_tokens", "10")
mock_span.set_attribute.assert_any_call("gen_ai.usage.completion_tokens", "20")
mock_span.set_attribute.assert_any_call("gen_ai.usage.output_tokens", "20")
mock_span.set_attribute.assert_any_call("gen_ai.usage.total_tokens", "30")
mock_span.set_attribute.assert_any_call("gen_ai.usage.cache_read_input_tokens", "0")
mock_span.set_attribute.assert_any_call("gen_ai.usage.cache_write_input_tokens", "0")
mock_span.add_event.assert_called_with(
"gen_ai.client.inference.operation.details",
attributes={
Expand Down Expand Up @@ -698,13 +698,13 @@ def test_end_agent_span(mock_span):

tracer.end_agent_span(mock_span, mock_response)

mock_span.set_attribute.assert_any_call("gen_ai.usage.prompt_tokens", 50)
mock_span.set_attribute.assert_any_call("gen_ai.usage.input_tokens", 50)
mock_span.set_attribute.assert_any_call("gen_ai.usage.completion_tokens", 100)
mock_span.set_attribute.assert_any_call("gen_ai.usage.output_tokens", 100)
mock_span.set_attribute.assert_any_call("gen_ai.usage.total_tokens", 150)
mock_span.set_attribute.assert_any_call("gen_ai.usage.cache_read_input_tokens", 0)
mock_span.set_attribute.assert_any_call("gen_ai.usage.cache_write_input_tokens", 0)
mock_span.set_attribute.assert_any_call("gen_ai.usage.prompt_tokens", "50")
mock_span.set_attribute.assert_any_call("gen_ai.usage.input_tokens", "50")
mock_span.set_attribute.assert_any_call("gen_ai.usage.completion_tokens", "100")
mock_span.set_attribute.assert_any_call("gen_ai.usage.output_tokens", "100")
mock_span.set_attribute.assert_any_call("gen_ai.usage.total_tokens", "150")
mock_span.set_attribute.assert_any_call("gen_ai.usage.cache_read_input_tokens", "0")
mock_span.set_attribute.assert_any_call("gen_ai.usage.cache_write_input_tokens", "0")
mock_span.add_event.assert_any_call(
"gen_ai.choice",
attributes={"message": "Agent response", "finish_reason": "end_turn"},
Expand All @@ -729,13 +729,13 @@ def test_end_agent_span_latest_conventions(mock_span):

tracer.end_agent_span(mock_span, mock_response)

mock_span.set_attribute.assert_any_call("gen_ai.usage.prompt_tokens", 50)
mock_span.set_attribute.assert_any_call("gen_ai.usage.input_tokens", 50)
mock_span.set_attribute.assert_any_call("gen_ai.usage.completion_tokens", 100)
mock_span.set_attribute.assert_any_call("gen_ai.usage.output_tokens", 100)
mock_span.set_attribute.assert_any_call("gen_ai.usage.total_tokens", 150)
mock_span.set_attribute.assert_any_call("gen_ai.usage.cache_read_input_tokens", 0)
mock_span.set_attribute.assert_any_call("gen_ai.usage.cache_write_input_tokens", 0)
mock_span.set_attribute.assert_any_call("gen_ai.usage.prompt_tokens", "50")
mock_span.set_attribute.assert_any_call("gen_ai.usage.input_tokens", "50")
mock_span.set_attribute.assert_any_call("gen_ai.usage.completion_tokens", "100")
mock_span.set_attribute.assert_any_call("gen_ai.usage.output_tokens", "100")
mock_span.set_attribute.assert_any_call("gen_ai.usage.total_tokens", "150")
mock_span.set_attribute.assert_any_call("gen_ai.usage.cache_read_input_tokens", "0")
mock_span.set_attribute.assert_any_call("gen_ai.usage.cache_write_input_tokens", "0")
mock_span.add_event.assert_called_with(
"gen_ai.client.inference.operation.details",
attributes={
Expand Down Expand Up @@ -769,13 +769,13 @@ def test_end_model_invoke_span_with_cache_metrics(mock_span):

tracer.end_model_invoke_span(mock_span, message, usage, stop_reason)

mock_span.set_attribute.assert_any_call("gen_ai.usage.prompt_tokens", 10)
mock_span.set_attribute.assert_any_call("gen_ai.usage.input_tokens", 10)
mock_span.set_attribute.assert_any_call("gen_ai.usage.completion_tokens", 20)
mock_span.set_attribute.assert_any_call("gen_ai.usage.output_tokens", 20)
mock_span.set_attribute.assert_any_call("gen_ai.usage.total_tokens", 30)
mock_span.set_attribute.assert_any_call("gen_ai.usage.cache_read_input_tokens", 5)
mock_span.set_attribute.assert_any_call("gen_ai.usage.cache_write_input_tokens", 3)
mock_span.set_attribute.assert_any_call("gen_ai.usage.prompt_tokens", "10")
mock_span.set_attribute.assert_any_call("gen_ai.usage.input_tokens", "10")
mock_span.set_attribute.assert_any_call("gen_ai.usage.completion_tokens", "20")
mock_span.set_attribute.assert_any_call("gen_ai.usage.output_tokens", "20")
mock_span.set_attribute.assert_any_call("gen_ai.usage.total_tokens", "30")
mock_span.set_attribute.assert_any_call("gen_ai.usage.cache_read_input_tokens", "5")
mock_span.set_attribute.assert_any_call("gen_ai.usage.cache_write_input_tokens", "3")
mock_span.set_status.assert_called_once_with(StatusCode.OK)
mock_span.end.assert_called_once()

Expand All @@ -801,13 +801,13 @@ def test_end_agent_span_with_cache_metrics(mock_span):

tracer.end_agent_span(mock_span, mock_response)

mock_span.set_attribute.assert_any_call("gen_ai.usage.prompt_tokens", 50)
mock_span.set_attribute.assert_any_call("gen_ai.usage.input_tokens", 50)
mock_span.set_attribute.assert_any_call("gen_ai.usage.completion_tokens", 100)
mock_span.set_attribute.assert_any_call("gen_ai.usage.output_tokens", 100)
mock_span.set_attribute.assert_any_call("gen_ai.usage.total_tokens", 150)
mock_span.set_attribute.assert_any_call("gen_ai.usage.cache_read_input_tokens", 25)
mock_span.set_attribute.assert_any_call("gen_ai.usage.cache_write_input_tokens", 10)
mock_span.set_attribute.assert_any_call("gen_ai.usage.prompt_tokens", "50")
mock_span.set_attribute.assert_any_call("gen_ai.usage.input_tokens", "50")
mock_span.set_attribute.assert_any_call("gen_ai.usage.completion_tokens", "100")
mock_span.set_attribute.assert_any_call("gen_ai.usage.output_tokens", "100")
mock_span.set_attribute.assert_any_call("gen_ai.usage.total_tokens", "150")
mock_span.set_attribute.assert_any_call("gen_ai.usage.cache_read_input_tokens", "25")
mock_span.set_attribute.assert_any_call("gen_ai.usage.cache_write_input_tokens", "10")
mock_span.set_status.assert_called_once_with(StatusCode.OK)
mock_span.end.assert_called_once()

Expand Down