Source and example scope
Replay the saved synthetic requests and compare each observed label with its authored expectation. Any disagreement stays visible; the model is not rerun to obtain a preferred answer.
Describe the code addition with all secret values removed. Compare an embedded credential, environment lookup and nonfunctional placeholder before a local scanner handles the file.
The fixtures contain descriptions, variable names and explicit placeholders. The embedded-token case says that a value was written into code, but removes that value before the request. Do the same with your own input.
This page cannot establish whether a credential is real, active or exposed elsewhere. An environment lookup is only a statement about the supplied snippet; it does not prove that the application handles the resulting value safely.
Keep deterministic secret scanning close to the repository and let your own policy decide what blocks a commit. This original Choice demo provides a contextual review label and does not reproduce the source hook or its blocking behavior.
These six synthetic inputs and Choice rules are original demonstrations. The API-collected X post links to jev-commit, whose pinned README describes related checks using Noul questions. This page is not that hook, does not execute Git, and does not reproduce its measurements or credential-blocking policy.

Use the sample to understand the rule, then test your own input for redacted credential review.

Describe the code addition with all secret values removed.

Open the decision rules and keep the intended distinction between Credential literal, Environment lookup, Placeholder, No credential cue, 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 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 |
|---|---|---|
| Embedded token described | Credential literal | 99.0% |
| Environment variable read | Environment lookup | 100% |
| Explicit example | Placeholder | 100% |
| Ordinary constant | No credential cue | 99.0% |
| Unknown variable source | Need evidence | 98.0% |
| Private key described | Credential literal | 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
Replay the saved synthetic requests and compare each observed label with its authored expectation. Any disagreement stays visible; the model is not rerun to obtain a preferred answer.
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.jsonInput scope and downstream handling determine what the label can tell you.
No. Remove the value locally and describe how it appears in the added code. The provided examples never need a real key.
No. It describes the supplied line only. The application could still expose the value later, and that behavior is outside this input.
No. It is the distribution for this request. Six synthetic fixtures check the workflow and preserve disagreements; they are not a production benchmark.
The window shows an error and returns no fresh judgment. The replay runner makes one request without retries. A missing-evidence label is about the input, not a substitute for an API failure.
Edit the supplied evidence above, or open the Playground for a different decision rule.