Same agent Smaller bill. The tools and infrastructure to get more work from your AI. Fewer tokens. Less compute. Lower cost.
TypeScript agent-harnessagent-harness-engineeringai-engineeringai-observabilityamd-gpuclaude-codeclickhousecodexcoding-agentcoding-agentscursorgenaigpu-monitoringllm-observabilityllmopsnvidia-smiobservabilityopen-sourceopenaiopentelemetry
fix(google_ai_studio): add missing GEN_AI_USAGE_REASONING_TOKENS semconv (#1137)
Saivedant Hava2c403d28af4b
diff --git a/sdk/python/src/openlit/instrumentation/google_ai_studio/utils.py b/sdk/python/src/openlit/instrumentation/google_ai_studio/utils.pyindex 7ac127e2..5de255b5 100644--- a/sdk/python/src/openlit/instrumentation/google_ai_studio/utils.py+++ b/sdk/python/src/openlit/instrumentation/google_ai_studio/utils.py@@ -600,7 +600,8 @@ def common_chat_logic(and scope._reasoning_tokens > 0):scope._span.set_attribute(- "gen_ai.usage.reasoning_tokens", scope._reasoning_tokens+ SemanticConvention.GEN_AI_USAGE_REASONING_TOKENS,+ scope._reasoning_tokens,)# OTel cached token attributes (set even when 0)diff --git a/sdk/python/src/openlit/semcov/__init__.py b/sdk/python/src/openlit/semcov/__init__.pyindex 372663db..aaa7496e 100644--- a/sdk/python/src/openlit/semcov/__init__.py+++ b/sdk/python/src/openlit/semcov/__init__.py@@ -569,6 +569,7 @@ class SemanticConvention:GEN_AI_USAGE_COMPLETION_TOKENS_DETAILS_REASONING = ("gen_ai.usage.completion_tokens_details.reasoning_tokens")+ GEN_AI_USAGE_REASONING_TOKENS = "gen_ai.usage.reasoning_tokens"GEN_AI_USAGE_PROMPT_TOKENS_DETAILS_CACHE_READ = ("gen_ai.usage.prompt_tokens_details.cached_tokens")