> For the complete documentation index, see [llms.txt](https://docs.testvibe.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.testvibe.com/ai-generation/review-generation-progress.md). # Review Generation Progress 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](/ai-generation/choose-agent-and-model.md) for the generation timeout setting. For execution environment issues, see [Troubleshoot runners](/runners/troubleshooting-runners.md). ## After Completion When generation succeeds, continue to [Read generated output](/ai-generation/read-generated-output.md). When it fails, continue to [Troubleshoot failed generation](/ai-generation/troubleshoot-failed-generation.md). --- # Agent Instructions This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com. ## Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter: ``` GET https://docs.testvibe.com/ai-generation/review-generation-progress.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.