Span
The fundamental unit of distributed tracing, representing a single operation or step within a complete trace. It contains metadata such as inputs and outputs, timing, status, and parent-child relationships, enabling precise identification of where issues occur.
Core Facts
Timeline (last 90 days)
A span is the smallest unit of work in distributed tracing, representing an operation with a start time, end time, and metadata, and multiple spans are combined into a trace through parent-child relationships or links.
In LLM applications, a single user question typically corresponds to one trace, and the internal model calls, vector retrievals, and tool executions are each a child span.
Storing high-dimensional embedding vectors (such as 768- or 1536-dimensional float arrays) in span attributes bloats the payload, increases serialization overhead, exhausts the memory of downstream storage engines, and is unreadable to humans.
OTel的核心数据模型是Span——代表一次操作的结构化记录，包含名称、起止时间、状态、属性（attributes）以及与其他span的父子关系；Trace由一组共享同一trace ID的span构成的有向无环图。
The trace structure displayed in Phoenix is essentially a tree of Spans, where each Span represents a discrete operation and records the start time, end time, input parameters, and return values.
Snapshotting key configuration and permission scopes as Span attributes into traces is an effective means of guarding against configuration drift issues.
Mainstream tracing frameworks such as OpenTelemetry generate Spans by instrumenting code and can only record what is explicitly specified to be recorded.
In agent scenarios, a complete agent task should be treated as a single Trace, with each LLM call, tool call, and memory retrieval being a Span.
AI Agent的会话本质上是独立的运行时上下文，在初始化阶段完成工具注册并将工具注册表固定为启动时的快照，存续会话无法动态感知配置变更
All Facts (10)
In agent scenarios, a complete agent task should be treated as a single Trace, with each LLM call, tool call, and memory retrieval being a Span.
65%Unverified事件日志中的事件天然对应分布式追踪中的Span概念，每个事件可携带TraceID和SpanID来还原完整的因果链路
85%UnverifiedA span is the smallest unit of work in distributed tracing, representing an operation with a start time, end time, and metadata, and multiple spans are combined into a trace through parent-child relationships or links.
50%UnverifiedStoring high-dimensional embedding vectors (such as 768- or 1536-dimensional float arrays) in span attributes bloats the payload, increases serialization overhead, exhausts the memory of downstream storage engines, and is unreadable to humans.
50%UnverifiedIn LLM applications, a single user question typically corresponds to one trace, and the internal model calls, vector retrievals, and tool executions are each a child span.
50%UnverifiedOTel的核心数据模型是Span——代表一次操作的结构化记录，包含名称、起止时间、状态、属性（attributes）以及与其他span的父子关系；Trace由一组共享同一trace ID的span构成的有向无环图。
50%UnverifiedThe trace structure displayed in Phoenix is essentially a tree of Spans, where each Span represents a discrete operation and records the start time, end time, input parameters, and return values.
50%UnverifiedMainstream tracing frameworks such as OpenTelemetry generate Spans by instrumenting code and can only record what is explicitly specified to be recorded.
50%UnverifiedSnapshotting key configuration and permission scopes as Span attributes into traces is an effective means of guarding against configuration drift issues.
50%UnverifiedAI Agent的会话本质上是独立的运行时上下文，在初始化阶段完成工具注册并将工具注册表固定为启动时的快照，存续会话无法动态感知配置变更
50%