Sensor diagnostic roles: six recorded examples
The downloads contain six original inputs, their expected labels and one recorded API observation per input revision. Disagreements stay visible.
Read the sensor's described purpose to separate device or connection diagnostics from household and consumable measurements. Preserve unclear roles instead of using the unit or name alone.
A diagnostic reading explains the device or its connection. A primary reading explains a household condition or monitored consumable. The same device can expose both kinds.
The distinction is an organizational suggestion. A diagnostic entity can still matter to a person or an automation, so this label is not permission to hide it, stop recording it or disable it.
This original text-metadata exercise adapts a question in ha-gutcheck, linked by the source post. The inputs and conservative review outcomes are authored here. It does not connect to Home Assistant, change a device registry or operate equipment.

Use the sample to understand the rule, then test your own input for sensor diagnostic roles.

Read the sensor's described purpose to separate device or connection diagnostics from household and consumable measurements.

Open the decision rules and keep the intended distinction between Diagnostic, Primary, Unclear. Edit the choices only when testing your own rule.

Use a sample first, then try your own input. Compare the selected label with the other returned probabilities.

Review Unclear before using a result. The label is a decision about the supplied information, not an executed action.
| Original input | Observed label | Leading probability |
|---|---|---|
| Network signal | Diagnostic | 100% |
| Room temperature | Primary | 100% |
| Device uptime | Diagnostic | 100% |
| Filter life | Primary | 100% |
| Phone battery | Diagnostic | 78.0% |
| Undefined status | Diagnostic | 63.0% |
These are six original synthetic inputs, tested once per request revision. The percentage is the leading option probability, not measured accuracy. Authored expectations and any disagreements remain in the downloadable evidence. 4 of 6 results matched the authored fixture expectations. For Phone battery, the expectation was Unclear; the observed choice was Diagnostic. For Undefined status, the expectation was Unclear; the observed choice was Diagnostic.Verified
The downloads contain six original inputs, their expected labels and one recorded API observation per input revision. Disagreements stay visible.
The single-request SDK runner uses your private TYPESAFE_API_KEY. The offline consumer reads saved observations, checks request hashes and prints a pending output. It does not call the model or change any external system.
# Offline: inspect the downloaded saved observations. No API key is needed.
python preview_choice_workflow.py samples.json saved-api-results.json
# Optional live request: install the SDK and set TYPESAFE_API_KEY privately.
npm install @typesafe-ai/sdk@0.6.0
node run-choice-sample.mjs samples.json case-1
# The live response prints to the terminal; it does not update saved-api-results.json.The input contract and these limits define what the result means.
No. Signal strength and uptime may be useful. The label describes the information’s subject, not its importance or retention policy.
This disclosed contract treats consumable life as a household reading someone may monitor. It differs from the device’s firmware or network status.
It describes the distribution over the supplied choices for this request. These six synthetic examples are functional tests with authored expectations, not a production accuracy benchmark.
No. The demo displays a label and distribution. The downloadable consumer produces a pending preview packet. Application code and a separate authorization policy would control any real action.
Edit the example above to see how a changed fact affects the decision, or open the Playground for another task.