Review Generation Progress

Follow queued, running, finalizing, succeeded, failed, and cancelled generation states.

The generation progress view shows what TestVibe and the cloud test session are doing while the AI agent works.

Use it to understand whether generation is waiting, actively working, finalizing output, or blocked.

Common States

State	What it usually means
Queued	TestVibe accepted the run, but a cloud test session has not started it yet.
Setting up	The cloud test session is preparing dependencies, browser tools, and configuration.
Running	The agent is generating or validating output.
Awaiting you	The agent asked a question — answer it in the drawer to continue.
Finalizing	Generation work is done and TestVibe is collecting files, status, or artifacts.
Succeeded	Generation completed and output should be available.
Failed	Generation could not complete successfully.
Cancelled	The run was stopped before it finished.

Overview

The overview summarizes the full generation run. It may show:

• status

• run details link

• generated path

• target site

• reasoning effort and generation config used

• section counts

• duration or credit usage when available

Use the overview when you want the whole-run status rather than a single scenario.

How The Assistant Works Through A Generation

A cloud generation moves through the same phases every time:

Phase	What is happening
Exploring the app	The assistant opens the target site and probes the UI the feature describes.
Writing the test	The assistant authors the Playwright code for each scenario.
Verifying · run N	The assistant replays what it wrote against the live site. A failed verification loops back to Writing the test and tries again.
Final verification	After every scenario is recorded, TestVibe runs the whole assembled spec end-to-end. Recording every step is not the same as the finished test passing a real run — this is the check that proves it does.

A feature only reaches generated status once final verification passes. There is no way to skip this check.

What The Assistant Learned

When generation succeeds, look for the What the Assistant learned card. It lists app-specific behavior the agent discovered while exploring — timing quirks, how a particular control behaves, or navigation it had to work around. It explains why the generated test is built the way it is, not just what it does.

Sections And Steps

For Gherkin features, progress may be organized by:

Section	What it means
Background	Shared setup for scenarios in the feature.
Scenario	One concrete behavior being generated.
Scenario Outline	A scenario pattern generated with example values.
Steps	Individual actions or assertions inside a section.

Section progress helps you see whether the agent is working through the feature or stuck on a particular part.

Each Gherkin step shows credit, time, and tool-call counts; click a step to expand its tool-call detail.

A step or section that did not run always carries a plain-language reason — TestVibe never leaves a block red with no explanation.

Live Preview And Evidence

When available, generation may show:

Evidence	How it helps
Screenshot preview	Shows what the browser or agent saw during generation.
Trace link	Opens deeper Playwright debugging evidence in the built-in trace viewer.
Verification video	Shows the final end-to-end verification run.
Generated path	Shows where output is being saved in your project.
Run details link	Opens lower-level run logs when you need them.

Once a generation completes, its trace is captured whether the final verification passed or failed, so the trace-viewer link is available on completed generations either way — alongside the verification video.

If Progress Looks Stuck

Use this order:

1. Check whether the status is queued or setting up.

2. If queued, give TestVibe a moment to start a cloud test session.

3. If setting up, give the session time to install dependencies.

4. If running for a long time, open the run details link if available.

5. If failed, read the failure message before editing the feature.

A generation that hits the generation timeout, runs out of credits, or is otherwise cut off says so plainly — the summary explains what stopped it rather than leaving the run stuck with no explanation. See Choose an Agent and Model for the generation timeout setting.

For execution environment issues, see Troubleshoot runners.

After Completion

When generation succeeds, continue to Read generated output. When it fails, continue to Troubleshoot failed generation.