AI Agents Module

The AI Agents module is agnostic to the library used. The SDK will instrument existing AI agents in certain frameworks or libraries (at the time of writing those are openai-agents in Python and Vercel AI in Javascript). You may need to manually annotate spans for other libraries.

Spans Conventions

For your AI agents data to show up in the Sentry AI Agents dashboard, at least one of the AI spans needs to be created and have well-defined names and data attributes. If the required data (marked with MUST or required) is missing, the data will not show up in the Agents dashbboard.

We try to follow v1.36.0 of the OpenTelemetry Semantic Conventions for Generative AI as close as possible. Being 100% compatible is not yet possible, because OpenTelemetry has "Span Events" which Sentry does not support. The input from/output to an AI model is stored in span events in OpenTelemetry. Since this is not possible in Sentry, we add this data onto span attributes as a list.

Invoke Agent Span

Describes AI agent invocation. Agent invocations represent operations that can include multiple model calls, or some auxiliary work that goes beyond transforming the model input and output.

• Span op SHOULD be "gen_ai.invoke_agent".
• Span name SHOULD be "invoke_agent {gen_ai.agent.name}". (e.g. "invoke_agent Weather Agent") [6]
• Attribute gen_ai.operation.name MUST be "invoke_agent".
• Attribute gen_ai.agent.name SHOULD be set to the agents name. (e.g. "Weather Agent")
• If relevant, the gen_ai.pipeline.name attribute SHOULD be set to the name of the AI workflow, pipeline or chain within which the agent operates. (e.g. "weather-pipeline")

Additional attributes on the span:

Request Data

Response Data

• [0]: Span attributes only allow primitive data types (like int, float, boolean, string). This means you need to use a stringified version of a list of dictionaries. Do NOT set the object/array [{"foo": "bar"}] but rather the string '[{"foo": "bar"}]' (must be parsable JSON).
• [1]: Messages use the format {role, parts} where parts is an array of typed objects: [{"role": "user", "parts": [{"type": "text", "content": "..."}]}]. The role must be "user", "assistant", "tool", or "system". For backwards compatibility, the legacy format {role, content} (e.g. [{"role": "user", "content": "..."}]) is also accepted.

AI Client Span

This span represents a request to an AI model or service that generates a response or requests a tool call based on the input prompt.

• Span op SHOULD be "gen_ai.{gen_ai.operation.name}". (e.g. "gen_ai.chat")
• Span name SHOULD be {gen_ai.operation.name} {gen_ai.request.model}". (e.g. "chat o3-mini")
• Attribute gen_ai.operation.name MUST be "chat", "embeddings", "generate_content" or "text_completion".
• Attribute gen_ai.provider.name MUST be the Generative AI product as identified by the client or server instrumentation. (e.g. "openai")
• Attribute gen_ai.request.model MUST be the requested model. (e.g. "gpt-4o")
• Attribute gen_ai.response.model MUST be the concrete response model. (e.g. "gpt-4o-2024-08-06")
• If the request originates from an agent, the gen_ai.agent.name attribute SHOULD be set to the name of the agent. (e.g. "Weather Agent")
• If relevant, the gen_ai.pipeline.name attribute SHOULD be set to the name of the AI workflow, pipeline or chain within which the agent operates. (e.g. "weather-pipeline")

Additional attributes on the span:

Request Data

Response Data

Token Usage Data

• [0]: Span attributes only allow primitive data types (like int, float, boolean, string). This means you need to use a stringified version of a list of dictionaries. Do NOT set the object/array [{"foo": "bar"}] but rather the string '[{"foo": "bar"}]' (must be parsable JSON).
• [1]: Messages use the format {role, parts} where parts is an array of typed objects: [{"role": "user", "parts": [{"type": "text", "content": "..."}]}]. The role must be "user", "assistant", "tool", or "system". For backwards compatibility, the legacy format {role, content} (e.g. [{"role": "user", "content": "..."}]) is also accepted.
• [2]: Cached tokens are a subset of input tokens; gen_ai.usage.input_tokens includes gen_ai.usage.cache_read.input_tokens.
• [3]: Reasoning tokens are a subset of output tokens; gen_ai.usage.output_tokens includes gen_ai.usage.reasoning.output_tokens.

Execute Tool Span

Describes a tool execution.

• Span op SHOULD be "gen_ai.execute_tool".
• Span name SHOULD be "execute_tool {gen_ai.tool.name}". (e.g. "execute_tool query_database")
• Attribute gen_ai.operation.name MUST be "execute_tool".
• Attribute gen_ai.tool.name SHOULD be set to the name of the tool. (e.g. "query_database")
• Attribute gen_ai.agent.name SHOULD be set to the name of the agent that invoked the tool. (e.g. "Weather Agent")
• If relevant, the gen_ai.pipeline.name attribute SHOULD be set to the name of the AI workflow, pipeline or chain within which the agent operates. (e.g. "weather-pipeline")

Additional attributes on the span:

Tool Data

[2]:

Cached tokens are a subset of input tokens; gen_ai.usage.input_tokens includes gen_ai.usage.input_tokens.cached.

[3]:

Reasoning tokens are a subset of output tokens; gen_ai.usage.output_tokens includes gen_ai.usage.output_tokens.reasoning.

[4]

The input list should include the most recent messages up to and including the most recent previous model response. The previous model response is identified with an "assistant" or "model" role in common frameworks. If there is no previous model response in the input list, then all input items which are not system instructions should be included. System instructions must be added in gen_ai.system_instructions, and are not included in the gen_ai.input.messages list.

[5]

Binary blobs in the input list should be replaced with the string "[Blob substitute]" in positions where binary data is expected in a given schema. Only binary blobs in positions where binary data is explicitly expected must be redacted. For example, in OpenAI Completions schema, only binary blobs in content blocks with type image_url, input_audio or file should be redacted.

[6]

In some agent libraries, the agent name is optional, and some do not provide the user an option to name their agents. In these cases, the span name SHOULD be "invoke_agent {call_id}", where call_id is some user-provided identifier for the agent invocation. For example, functionId in Vercel AI.

[7]

Image URLs in the data URL format in the input list should be replaced with the string "[Blob substitute]" in positions where binary data is expected. For example, data URLs like data:image/png;base64 will be redacted, but HTTP URLs like example.com/data?<a-base64-string> will not be.

See here for the regex used.