Assistant CoreAssistant Core

Tracing

View per-message agent traces — LLM calls, token usage, and tool executions — to debug and analyze your assistant.

Tracing gives you an inside look at how your assistant produced each reply. For every assistant message, the platform records each LLM call and each tool execution, along with token usage, duration, and status.

Tracing is the fastest way to answer "why did the assistant respond like that?" and "what made this reply slow or expensive?".

What Is Tracing?

A single assistant reply is not always one LLM call. When the assistant uses tools (knowledge base, MCP, custom APIs, etc.), it runs a tool loop: call the model → run the requested tools → feed results back → call the model again, until it has a final answer.

Tracing records each step of that loop:

  • One LLM call entry per loop iteration (model, provider, tokens, duration, status).
  • One tool execution entry per tool the model invoked (arguments, result, duration, outcome).

This is built-in observability — no external setup required.

How to Open Traces

  1. Go to the Admin Panel and open Assistants.
  2. Open an assistant, then go to Conversations.
  3. Select a conversation to view its messages.
  4. On any assistant message, click the Trace pill (activity icon) to open the Agent Trace Details dialog.

Only assistant messages have traces. User messages don't trigger LLM or tool calls, so there is nothing to trace.

Summary Bar

The top of the dialog summarizes the whole reply at a glance:

MetricMeaning
Call(s)Number of LLM calls (loop iterations) for this message
TokensTotal tokens consumed across all calls
DurationTotal time spent generating the reply
Tool(s)Total number of tool executions across all calls

Reading an LLM Call

Each LLM call is shown as a card. The header shows the model, a status badge, and the Loop # (tool-loop iteration, starting at 0). Expand a card to see full details.

FieldMeaning
ModelThe chat model that handled this call (e.g. gpt-5.6-luna)
ProviderThe provider behind the model (e.g. openai, anthropic)
Statuscompleted, aborted, or error — see below
Loop #Tool-loop iteration index (0 = the first call)
TimeWhen the call was made
DurationHow long the call took

Token Breakdown

TokenMeaning
InputTokens sent to the model (prompt, history, context, tool results)
OutputTokens generated by the model
TotalInput + output
CachedInput tokens served from the provider's prompt cache (cheaper)
ReasoningInternal reasoning tokens, for models that think before answering

Cached and Reasoning only appear when they are greater than zero. Cached tokens lower cost; reasoning tokens are extra work the model does internally before producing the visible answer.

Tool Executions

When the assistant uses tools, the call card lists each tool execution. Each row shows the tool name, a type badge, and its duration. Expand a row for details:

DetailMeaning
ActionThe outcome of the tool call (see table below)
TimeWhen the tool ran
ArgsThe arguments the model passed to the tool (JSON)
ResultA summary of what the tool returned
ErrorThe error message, if the tool failed

Tool Types

BadgeWhat it is
builtinServer-side built-in tools (knowledge base, memory, web, etc.)
mcpTools provided through MCP (endpoints and MCP servers)
customYour own custom HTTP API tools

Tool Actions

ActionMeaning
REQLLMResult was sent back to the model to continue the loop
RESPONSETool produced the final response directly
NONETool ran but returned nothing to act on
ERRORTool failed — check the error message

Args and Result are sanitized and truncated for safety and readability — they are summaries, not the full raw payloads.

Trace Status

StatusMeaning
completedThe call finished normally
abortedThe call was stopped early (e.g. the user interrupted / barged in)
errorThe call failed — inspect the trace and tool errors for the cause

Common Use Cases

Debug a wrong answer — check which tools were called, what arguments were passed, and what each tool returned. A bad result or wrong arguments usually explains an off-topic reply.

Analyze cost — total tokens map directly to credit usage. Use traces to spot which messages are expensive and why. See Credits.

Diagnose slow replies — compare the duration of each loop iteration and each tool. A slow external tool or many loop iterations is often the bottleneck.

  • Tools & MCP — the tools that appear in your traces
  • AI Models — the models shown in each LLM call
  • Credits — how token usage maps to cost

On this page