Working with logs

The Logs page lets you investigate Flow and Agent executions. Runtype executions and external executions reported through the OpenTelemetry Protocol (OTLP) produce log entries with step-by-step details that you can inspect. External executions sent through POST /v1/executions/ingest remain visible in Runs and remain available for eval capture. This JSON compatibility path does not produce structural Logs or trace records. For the OTLP migration path, see Reporting telemetry from an external agent.

View execution details

Select a row in the Logs list to open its execution details. The details view contains the following areas:

• Timeline: Shows each step in execution order with its status and duration.
• Step inspector: Lets you select a step and inspect its full input, output, and configuration.
• Token usage: Shows input and output tokens for prompt steps.
• Context window: Shows estimated input tokens for agent turns. It splits them into the system prompt, tool definitions, record context, conversation history, tool results, and current message. It classifies the total by absolute token count as Typical range, Elevated, or Very high. These estimates can differ from billed tokens.
• Trace: Shows a tree of iterations, tool calls, and model turns. When context estimates are available, the Context per iteration chart shows one stacked column per iteration. It uses the same categories and colors as the Context window bar. When all iterations share an Elevated threshold, a dashed line marks that threshold.

Agent executions

Agent logs show recorded iterations, tool calls, tool results, and reasoning output. Use the trace to inspect tool selection and the final response.

Tool-call details retain parameter names and values that are not protected. The logs do not retain values injected for protected parameters. They replace those values with [REDACTED] and identify the parameters as secure.

Capture an agent execution as an eval case

To capture an execution, follow these steps:

1. Open an agent execution.
2. Click Add to eval.
3. Select the target eval. If no eval targets the agent, select the option to create a default eval when you save.
4. Select the Fork point that the eval grades as the next step.
5. Click Add to eval.

The case freezes the conversation before the selected action and grades the agent’s next step. If the run has no tool calls, the eval grades the agent’s reply. The dialog reports Fully replayable when it captures all recorded tool outputs. It reports Partially replayable when it truncates a tool output, and the case still grades the next step. For more information, see Managing eval suites.

Search and filter logs

Use search and filters to find executions in your log history.

Filter logs

Use the following filters:

• Type: Shows entries for Flow, Agent, Tool, Batch, System, Model, Schedule, or Audit.
• Status: Shows executions with Completed, Failed, Running, Queued, or Cancelled status.
• Time range: Limits results to a specific time window.

Search logs

Type keywords in the search field to search titles, step names, Flow names, Record names, tool names, model names, and error messages. Use field-specific queries such as stepName:Analyze or model:gpt-4.

Use live mode

Click Live in the Logs view to show new executions as they start and complete. Use live mode to test a Flow or monitor a scheduled batch run.

Live mode pauses automatically when you review older entries. It resumes when you return to the end of the list.

When live mode is on, the Logs view shows a context strip with up to three pills for executions with the newest activity. Each pill includes a mini context bar and its band label. Click a pill to open that execution’s details.

Export logs

Click Export to download entries in your current filtered view as JSON or CSV. JSON exports include each entry’s available fields. CSV exports include timestamps, levels, types, statuses, titles, Flow and step names, durations, token totals, estimated costs, and errors.

Debug failed executions

When a Flow or Agent execution fails, the Logs page shows the failed step and its error details.

Identify the failed step

Open a failed execution. In the Timeline, find the step with an error status. Select that step in the Step inspector to review its error message and input.

Review common failure patterns

The following table lists common failure patterns and fixes:

Re-run after a fix

After you fix the issue, run the Flow manually from Flows. If the Flow uses a Schedule, wait for its next scheduled execution.

Next steps

Use the following pages to continue:

• Debugging flows: troubleshoot Flow execution errors
• Flow execution failures: review common failure patterns
• What are logs?: learn what Logs captures