Story spoiler check: six recorded examples
The downloads contain six original inputs, their expected labels and one recorded API observation per input revision. Disagreements stay visible.
Provide fictional story facts, the reader's progress and a comment. Identify a concrete later-event disclosure while keeping already-reached events and vague reactions separate from spoilers.
This example supplies its own fictional story facts. It does not rely on the model remembering a real film, book or game.
The progress boundary changes the result without changing the comment. Provide that boundary explicitly instead of treating every plot reference as a spoiler.
The source-linked blocker checks concrete plot disclosures. This original text adaptation adds a supplied progress boundary and does not hide comments or install an extension.
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 story spoiler check.

Provide fictional story facts, the reader's progress and a comment.

Open the decision rules and keep the intended distinction between Later-event spoiler, No later-event disclosure, 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 |
|---|---|---|
| Later culprit revealed | Later-event spoiler | 99.0% |
| Already known event | No later-event disclosure | 98.0% |
| Vague reaction | No later-event disclosure | 87.0% |
| Unknown progress | Review | 92.0% |
| Unresolved pronoun | Review | 67.0% |
| Embedded instruction | Later-event spoiler | 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.
Under this narrow rule, a reaction without a concrete event is not a later-event disclosure. A stricter community policy could choose a different contract.
It compares with the supplied story facts. It does not verify an external source or establish the canon of a real work.
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.