Debugger next step: 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 paused state and investigation goal. Compare Step into, Step over, Step out and a configured breakpoint before issuing any debugger command.
This demo recommends one navigation command from the supplied state. It does not attach to a process, inspect variables or run an expression.
An explicit evidence goal distinguishes commands that would otherwise all be technically available. Keep the paused line, stack context and prerequisites together.
The linked debugger strategy uses Jev for bounded action selection and another model for generated parameters. This page covers only the navigation subset and does not reproduce that agent.
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 debugger next step.

Describe the paused state and investigation goal.

Open the decision rules and keep the intended distinction between Step into, Step over, Step out, Continue, 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 |
|---|---|---|
| Inspect parser internals | Step into | 100% |
| Observe known helper result | Step over | 100% |
| Return to caller | Step out | 100% |
| Reach known breakpoint | Continue | 100% |
| No investigation goal | Review | 100% |
| Missing breakpoint | Review | 99.0% |
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.
No. It normally executes the call without stepping through its internals, then pauses at the next relevant point. This page only selects the label.
This exercise chooses how to gather another observation. Confirming a cause or ending an investigation needs a separate evidence contract.
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.