Sensor history use: 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 sensor's role and known history consumers. Compare retaining the series, slower reporting and exclusion review without changing settings or dropping stored data.
The useful question is what the history supports. A diagnostic series can matter to a support chart, while a high-volume display state may only need its current value.
Exclusion review has a stricter evidence requirement than no known consumer. The inventory must actually be complete, and the output is still a proposal for a person to inspect.
The linked helper reviews recorder churn and keeps protected dependencies in code. This fictional text exercise demonstrates the advisory reasoning; it does not connect to a recorder or change stored data.
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 sensor history use.

Provide the noncritical sensor's role and known history consumers.

Open the decision rules and keep the intended distinction between Retain, Slower reporting, Exclusion review, 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 Exclusion 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 |
|---|---|---|
| Required fine-grained chart | Retain | 94.0% |
| Coarser trend sufficient | Slower reporting | 100% |
| Current-state display only | Exclusion review | 100% |
| Diagnostic history still useful | Retain | 98.0% |
| Unexamined consumers | Review | 99.0% |
| Conflicting cadence needs | Review | 100% |
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. A documented consumer may require every transition. Frequency is context, not a reason by itself to remove history.
The model reads supplied facts and can be wrong or miss context. A real change needs dependency verification, retention policy and an authorized operator.
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.