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.
Provide the next task's context dependencies and access after a proposed switch. Check whether required evidence remains available or is missing, without assuming that a model change retains the conversation.
The decision checks whether the next turn can read its required evidence after a switch. A cached request can still omit the approved outline, and a fresh request can explicitly include it.
No context dependency applies only when the supplied next task is independent. Unclear access preserves unresolved transfer notes instead of treating a proposed migration as completed.
This example does not measure cache savings or select a cheaper model. Its source discusses continuity concerns in model routing; the demonstration inspects the evidence available to one candidate route.
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 model-switch context access.

Provide the next task's context dependencies and access after a proposed switch.

Open the decision rules and keep the intended distinction between Context retained, Context missing, No context dependency, Unclear access, 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 Context missing, Unclear access, 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 |
|---|---|---|
| Context transferred | Context retained | 99.0% |
| Outline omitted | Context missing | 100% |
| Independent task | No context dependency | 100% |
| Transfer unresolved | Unclear access | 99.0% |
| Cache is not evidence | Context missing | 100% |
| No next-task requirement | Need evidence | 98.0% |
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
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. Access to required evidence and provider cache behavior are different properties. This input establishes only the first.
Yes, under this rubric, when the task explicitly requires no earlier evidence. Capability, cost and policy still need their own checks.
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.