Source and example scope
Compare each saved result with its authored expectation. A disagreement remains in the fixture review; the call is not repeated to obtain a preferred label.
Describe the job and an account's capabilities and allowance status. Compare a suitable account with exhausted, restricted and unclear alternatives before routing work.
A capable account may have no usable allowance. An account with allowance may lack the modality needed for the task. The eligibility label needs both pieces of evidence.
Allowance is supplied as a status that ordinary code or an authorized account interface has already computed. Jev is not asked to count tokens, read a billing dashboard or estimate a remaining balance from a screenshot.
Eligible applies to this candidate and this task. Selecting the best account across several eligible candidates requires a separate objective, such as declared preference or verified total cost.
These fictional inputs and decision rules were written for this page. The linked X discussion provides background; the technical implementation follows TypeSafe's Choice contract.

Use the sample to understand the rule, then test your own input for account capability and quota.

Describe the job and an account's capabilities and allowance status.

Open the decision rules and keep the intended distinction between Eligible, Capability mismatch, Allowance unavailable, Unclear fit, Need evidence. 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 fit, Need evidence before using a result. The label is a decision about the supplied information, not an executed action.
| Original input | Observed label | Leading probability |
|---|---|---|
| Text job with allowance | Eligible | 100% |
| Image task on text account | Capability mismatch | 100% |
| Exhausted account | Allowance unavailable | 100% |
| Unclear capability | Capability mismatch | 67.0% |
| Restriction despite balance | Allowance unavailable | 100% |
| Missing allowance note | Need evidence | 78.0% |
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. 5 of 6 results matched the authored fixture expectations. For Unclear capability, the expectation was Unclear fit; the observed choice was Capability mismatch.Verified
Compare each saved result with its authored expectation. A disagreement remains in the fixture review; the call is not repeated to obtain a preferred label.
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.
npm install @typesafe-ai/sdk@0.6.0
# Set TYPESAFE_API_KEY privately in your shell.
node run-choice-sample.mjs samples.json case-1
python preview_choice_workflow.py samples.json saved-api-results.jsonThe rubric explains the decision; the application owns the next step.
No. It only satisfies the supplied capability and allowance conditions. Comparing eligible candidates needs a separate ranking objective.
Exact allowance arithmetic belongs in ordinary code. This example consumes a verified status and uses the model for the semantic capability match.
No. It is the model distribution for this one request. The six examples are functional checks with authored expectations, not a representative benchmark. Inspect disagreements and evaluate your own examples before using the label.
The window shows an error and supplies no fresh judgment. The downloadable runner sends one request without retries. Need evidence is a valid outcome about incomplete input; it does not stand in for a network or provider failure.
Edit the evidence above or use the Playground to test another bounded question.