FAQ ❔
Does Testronaut need a headless browser?
Testronaut runs headless by default. You do not need to open a browser window unless you enable debugging or visualization.
How do I track token consumption?
Each mission starts with a 20-turn default budget. Mission reports show token usage so you can assess how efficiently the agent completed the journey. See Turn Limits and Overrides and Usage & Costs.
How do I take a screenshot?
Add a natural-language instruction such as:
Take a screenshot.
Screenshots appear in reports and are stored under:
<outputDir>/screenshots/run_<runId>/
Use --no-screenshots when screenshots are not wanted.
Which LLM providers and models are supported?
Testronaut CLI v1.10.0 supports:
- OpenAI: GPT-5.6 Sol, Terra, and Luna; GPT-5.5; and legacy GPT/o-series models.
- Google Gemini: Gemini 3.8 Flash, 3.7 Flash, 3.6 Flash, 3.5 Flash-Lite, 3.1 Pro Preview, and legacy Gemini 2.5 models.
- Anthropic Claude: Claude Sonnet 5, Opus 5, and Haiku 4.5.
Run testronaut --init to see the catalog in your installed CLI. Provider access, lifecycle status, pricing, and rate limits remain controlled by the provider.
Where is project configuration stored?
The canonical project file is testronaut-config.json. Use:
testronaut config
testronaut config --json
to inspect resolved values and their sources without printing the session token.
Is the CLI free?
Yes. The Testronaut CLI is open source. Mission Control plans cover hosted report capacity, stored MFA configurations, hosted inboxes, and team collaboration. See Plans & Feature Availability.
Can Testronaut test MFA and email verification?
Yes. Testronaut can retrieve stored TOTP codes, poll a hosted inbox for short email codes, safely open allowlisted invitation or magic-login links, or pause for human input.