Unavailable entity triage: six recorded examples
The downloads contain six original inputs, their expected labels and one recorded API observation per input revision. Disagreements stay visible.
Provide the noncritical entity's role, current condition and device history. Separate expected inactivity from unexpected loss and a stale restored record without controlling devices or deleting entries.
Entity meaning matters. An optional playback attribute can disappear when a player is idle even while the device itself is working. A continuously reported status has a different expectation.
A stale-record suggestion requires explicit removal history. Time since the last update alone does not prove that a device was retired or that its data should be deleted.
The linked Home Assistant helper reviews unavailable entities with model and deterministic checks. This page is a fictional text adaptation for noncritical devices and performs no device control or configuration changes.
This is an independently authored text demonstration inspired by the linked X discussion. Its rules and synthetic inputs are ours. It does not reproduce the author’s application, verify reported outcomes, or perform an external action.

Use the sample to understand the rule, then test your own input for unavailable entity triage.

Provide the noncritical entity's role, current condition and device history.

Open the decision rules and keep the intended distinction between Expected, Investigate, Stale record, Review. 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 Review before using a result. The label is a decision about the supplied information, not an executed action.
| Original input | Observed label | Leading probability |
|---|---|---|
| Optional playback detail | Expected | 97.0% |
| Expected reporter missing | Investigate | 100% |
| Removed demo device | Stale record | 77.0% |
| Another expected idle detail | Expected | 98.0% |
| Unknown role | Review | 99.0% |
| Conflicting removal notes | Review | 97.0% |
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. 6 of 6 results matched the authored fixture expectations.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. It reads the fictional role and status facts you enter. It has no connection to a home network or device registry.
No. It identifies a record for review under the supplied history. Verify dependencies and backups before any real configuration change.
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.