Semantic Conventions for GenAI agent and framework spans

Status: Development

Generative AI models can be trained to use tools to access real-time information or suggest a real-world action. For example, a model can leverage a database retrieval tool to access specific information, like a customer’s purchase history, so it can generate tailored shopping recommendations. Alternatively, based on a user’s query, a model can make various API calls to send an email response to a colleague or complete a financial transaction on your behalf. To do so, the model must not only have access to a set of external tools, it needs the ability to plan and execute any task in a self-directed fashion. This combination of reasoning, logic, and access to external information that are all connected to a Generative AI model invokes the concept of an agent.

This document defines semantic conventions for GenAI agent calls that are defined by this whitepaper.

It MAY be applicable to agent operations that are performed by the GenAI framework locally.

The semantic conventions for GenAI agents extend and override the semantic conventions for Gen AI Spans.

Spans

Create agent span

Status:

Describes GenAI agent creation and is usually applicable when working with remote agent services.

The gen_ai.operation.name SHOULD be create_agent.

Span name SHOULD be create_agent {gen_ai.agent.name}. Semantic conventions for individual GenAI systems and frameworks MAY specify different span name format.

Span kind SHOULD be CLIENT.

Span status SHOULD follow the Recording Errors document.

Attribute	Type	Description	Examples	Requirement Level	Stability
gen_ai.operation.name	string	The name of the operation being performed. [1]	chat; generate_content; text_completion	Required
gen_ai.system	string	The Generative AI product as identified by the client or server instrumentation. [2]	openai	Required
error.type	string	Describes a class of error the operation ended with. [3]	timeout; java.net.UnknownHostException; server_certificate_invalid; 500	Conditionally Required if the operation ended in an error
gen_ai.agent.description	string	Free-form description of the GenAI agent provided by the application.	Helps with math problems; Generates fiction stories	Conditionally Required If provided by the application.
gen_ai.agent.id	string	The unique identifier of the GenAI agent.	asst_5j66UpCpwteGg4YSxUnt7lPY	Conditionally Required if applicable.
gen_ai.agent.name	string	Human-readable name of the GenAI agent provided by the application.	Math Tutor; Fiction Writer	Conditionally Required If provided by the application.
gen_ai.request.model	string	The name of the GenAI model a request is being made to. [4]	gpt-4	Conditionally Required If available.
server.port	int	GenAI server port. [5]	80; 8080; 443	Conditionally Required If server.address is set.
server.address	string	GenAI server address. [6]	example.com; 10.1.2.80; /tmp/my.sock	Recommended

[1] gen_ai.operation.name: If one of the predefined values applies, but specific system uses a different name it’s RECOMMENDED to document it in the semantic conventions for specific GenAI system and use system-specific name in the instrumentation. If a different name is not documented, instrumentation libraries SHOULD use applicable predefined value.

[2] gen_ai.system: The gen_ai.system describes a family of GenAI models with specific model identified by gen_ai.request.model and gen_ai.response.model attributes.

The actual GenAI product may differ from the one identified by the client. Multiple systems, including Azure OpenAI and Gemini, are accessible by OpenAI client libraries. In such cases, the gen_ai.system is set to openai based on the instrumentation’s best knowledge, instead of the actual system. The server.address attribute may help identify the actual system in use for openai.

For custom model, a custom friendly name SHOULD be used. If none of these options apply, the gen_ai.system SHOULD be set to _OTHER.

[3] error.type: The error.type SHOULD match the error code returned by the Generative AI provider or the client library, the canonical name of exception that occurred, or another low-cardinality error identifier. Instrumentations SHOULD document the list of errors they report.

[4] gen_ai.request.model: The name of the GenAI model a request is being made to. If the model is supplied by a vendor, then the value must be the exact name of the model requested. If the model is a fine-tuned custom model, the value should have a more specific name than the base model that’s been fine-tuned.

[5] server.port: When observed from the client side, and when communicating through an intermediary, server.port SHOULD represent the server port behind any intermediaries, for example proxies, if it’s available.

[6] server.address: When observed from the client side, and when communicating through an intermediary, server.address SHOULD represent the server address behind any intermediaries, for example proxies, if it’s available.

error.type has the following list of well-known values. If one of them applies, then the respective value MUST be used; otherwise, a custom value MAY be used.

Value	Description	Stability
_OTHER	A fallback error value to be used when the instrumentation doesn’t define a custom value.

gen_ai.operation.name has the following list of well-known values. If one of them applies, then the respective value MUST be used; otherwise, a custom value MAY be used.

Value	Description	Stability
chat	Chat completion operation such as OpenAI Chat API
create_agent	Create GenAI agent
embeddings	Embeddings operation such as OpenAI Create embeddings API
execute_tool	Execute a tool
generate_content	Multimodal content generation operation such as Gemini Generate Content
text_completion	Text completions operation such as OpenAI Completions API (Legacy)

gen_ai.system has the following list of well-known values. If one of them applies, then the respective value MUST be used; otherwise, a custom value MAY be used.

Value	Description	Stability
anthropic	Anthropic
aws.bedrock	AWS Bedrock
az.ai.inference	Azure AI Inference
az.ai.openai	Azure OpenAI
cohere	Cohere
deepseek	DeepSeek
gcp.gemini	Gemini [7]
gcp.gen_ai	Any Google generative AI endpoint [8]
gcp.vertex_ai	Vertex AI [9]
groq	Groq
ibm.watsonx.ai	IBM Watsonx AI
mistral_ai	Mistral AI
openai	OpenAI
perplexity	Perplexity
xai	xAI

[7]: This refers to the ‘generativelanguage.googleapis.com’ endpoint. Also known as the AI Studio API. May use common attributes prefixed with ‘gcp.gen_ai.’.

[8]: May be used when specific backend is unknown. May use common attributes prefixed with ‘gcp.gen_ai.’.

[9]: This refers to the ‘aiplatform.googleapis.com’ endpoint. May use common attributes prefixed with ‘gcp.gen_ai.’.

Agent execute tool span

If you are using some tools in your agent, refer to Execute Tool Span.