Skip to main content

check

This tool on every surface: CLI · MCP · Python · JavaScript · Go · Java · .NET

Check a claim about a recorded session: a model with a fresh context — none of yours — reads the recording (each call, its result or error, and the screen and screenshot after it) through read-only tools, and answers passed, failed or inconclusive with the observations it rests on. These call app_check.

check​

def check(claim: str, record: str, model: str | None=None) -> dict

Ask an independent model whether claim holds in a recording.

record is the .zip a trace saved. The model reads only the recording, in a fresh context, and answers {status: passed | failed | inconclusive, summary, evidence, ...}. A model's judgment is not proof. model is "openai:" for one served through the OpenAI-compatible API (Ollama where mobium runs, unless MOBIUM_AI_BASE_URL names another server); None asks Claude through the Anthropic API, which needs a credential, is a paid call, and is not yet measured. Needs no device.

Examples​

Ask a model on this machine whether a claim holds in a recording​

v = device.check("After card 3 was tapped, it was shown face up as the Blue Morpho.", "card.zip", model="openai:qwen2.5:14b")
print(v["status"], v["summary"])