Trace Detail

Open a trace from the Trace Explorer to inspect a single request end to end. The detail view lays out the whole trace: a summary on the left, a chosen view on the right, and the timeline along the bottom. Use it to find which span was slow, which one errored, and why.

Trace summary

Until you select a span, the left panel shows the trace summary:

Trace ID, date, and total duration for the request.
Per-service time — each service in the trace with its share of the request time, so you can see where the request spent most of its time.
Errors — any errored spans, with a link to jump straight to the span.

When the trace contains GenAI spans, an AI summary appears here too — models, model and tool call counts, token usage, and the model-versus-tool time split. See AI Trace Observability.

Timeline

The timeline along the bottom is the waterfall of spans, ordered by start time and nested by parent. Each row shows the span’s service, operation name, an icon for its type, and a duration bar positioned by when it ran.

Expand or collapse a span to show or hide its children, or use Toggle Expand All.
Hide internal spans to cut framework noise and focus on the spans that cross a boundary.
Search within the trace using the filter box. Matching spans stay highlighted while the rest dim, and the match counter lets you step through hits with the next and previous arrows.

Select any row to open its detail in the left panel.

Span detail

Selecting a span replaces the summary with the span’s detail, organized into tabs. The tabs you see depend on the span’s type, so you only get what’s relevant:

Request and Response for HTTP spans — method, route, status, headers, and body.
Database for database spans — the statement and database attributes.
Message for messaging spans.
Conversation and Gen AI for LLM spans — the prompt and response transcript, token usage, finish reason, and tool calls. See AI Trace Observability.
Info for service, host, Kubernetes, and deployment metadata.
Events and Links when the span has them.
Attributes for the full attribute set, grouped by semantic-convention prefix.
JSON for the raw span.

Views

The toggle at the top right switches how the right panel presents the trace:

Service List lists the spans in a table — operation, type, and duration — for a flat, scannable view of everything in the trace.
Request Flow draws the trace as a service graph, so you can see how services called each other and where errors propagated.
AI Flow appears for traces with GenAI spans. It lays out the model and tool steps as a workflow graph. See AI Trace Observability.

Selecting a span in any view — or in the timeline — keeps the detail panel in sync.

Request logs and assistant

Two shortcuts sit in the trace header:

Request Logs opens the logs correlated with this trace, when logs are available, so you can move from a span to the log lines around it.
Ask Assistant hands the trace to the KloudMate assistant to help investigate bottlenecks or errors.