Search recency windows: six recorded examples
The downloads contain six original inputs, their expected labels and one recorded API observation per input revision. Disagreements stay visible.
Describe the requested recency to choose day, week, month or anytime. Keep unsupported exact windows and conflicting constraints separate instead of silently rounding them to a different period.
A query can contain dates for different reasons. Searching about an old event does not necessarily mean searching for pages published during that event. The input must make the intended freshness requirement clear.
This label only prepares a search parameter. The application must check that the selected search provider supports it and validate the dates of returned results. No search runs in this example.
This original text demonstration adapts a decision in a repository linked by the cited X post. The examples and explicit uncertainty outcomes are ours. The post is a directory reference, not proof that its author built every linked project. No third-party benchmark, business outcome or external action is reproduced.

Use the sample to understand the rule, then test your own input for search recency windows.

Describe the requested recency to choose day, week, month or anytime.

Open the decision rules and keep the intended distinction between Day, Week, Month, Anytime, Unsupported. 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 uncertain or unexpected results before using a result. The label is a decision about the supplied information, not an executed action.
| Original input | Observed label | Leading probability |
|---|---|---|
| Last day | Day | 100% |
| Weekly update | Week | 100% |
| Monthly reading | Month | 100% |
| Historical subject | Anytime | 100% |
| Exact two days | Unsupported | 99.0% |
| No request | Unsupported | 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.
Clarify the desired period or define a policy before using it. The fixed window menu should not silently promise an interval the user did not specify.
No. The output is only a proposed parameter. The provider and result-date checks determine what is actually returned.
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.