Skip to main content
When a run doesn’t behave as expected, start with the lines the pipe writes at the top of its step log, then the report.

Read the plan

The pipe’s first real step, Resolve the verification plan, logs:
  • the mode and why it was picked, for example: auto, the repository is public, so the platform can check it out
  • the target: a deployed URL, or the port of an app in the pipe
  • the max-time the step needs, as “This configuration needs max-time of at least 85 on the step that runs it.” The number is in minutes. Set at least that much on the step: a pipe can’t read its step’s max-time, so it doesn’t check it
With the plan, the pipe warns about variables that don’t apply to the mode it runs in, and about conflicts such as a port in APP_URL that differs from APP_PORT. A warning means a setting was ignored, not that the run failed. Errors and warnings start with ERROR: and WARNING:, and each step of the pipe starts with a ▶ line.

Verbose logging

Set VERBOSE: "true" to log each tool call’s response, the prompt, the artifact list and the verdict details:

Common problems


Look at a run from your machine

With the IronBee CLI signed in to the same account, check a run on IronBee by its IRONBEE_JOB_ID:
See Verification jobs.

Session logs from your runner

When the verification ran inside the pipe, the step’s evidence artifacts include the session’s own logs. Each agent of the session has its own folder, sessions/<id>/agents/<agentId>/, and the main agent’s is agents/main/:
  • verdict.json holds that agent’s latest verdict.
  • actions.jsonl is its full event log.
If the agent stopped early, the report shows a banner and a Session end details list: the reason, the turns, errors and any blocked tool calls.

What’s next?

Evidence

Where the recording, screenshots, logs and report are.

Configuration

Every variable and output, with defaults.