Jev commit diff support

Check whether a diff supports a commit-message claim

Provide one commit-message claim and the before-and-after diff. Compare visible support, contradiction and claims the diff cannot establish, such as unmeasured speed gains.

Does the supplied diff support this claim?Live API
Try an example

The added branch directly implements the stated check.

Source: Background discussion on X

Source and example scope

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.

Compare the one commit-message claim with the supplied diff only.

Decision rules and labels
SupportedContradictedNot establishedNeed evidence
A real response from the Jev API

Edit any input to explore a different decision. No request is sent until you run it.

Your next decision

Not run yet

Choose an example or write your own input, then run it to see the ranked choices.

Results are not stored by this site. Your submitted text is processed by the API provider.

The decision

A precise message can still disagree with the patch.

The null-check input includes the added branch, so the model can compare a concrete claim with concrete code. The timeout input supplies both values and makes the contradiction visible.

Not established differs from Contradicted. A renamed function does not demonstrate a speed improvement, and one changed endpoint does not prove that every endpoint checks authentication. Neither requires inventing an unseen result.

This is a review of supplied text. Run the relevant tests and inspect the full patch when correctness depends on behavior beyond these hunks.

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.

Illustration of checking a code change and reviewing a flagged line
Illustration of the decision flow.
How it works

Try the example in four steps

Use the sample to understand the rule, then test your own input for commit claim evidence.

  1. Illustration of adding the text or evidence for a decision

    Add the information to check

    Provide one commit-message claim and the before-and-after diff.

  2. Illustration of defining a question and its allowed choices

    Confirm the question and labels

    Open the decision rules and keep the intended distinction between Supported, Contradicted, Not established, Need evidence. Edit the choices only when testing your own rule.

  3. Illustration of sending one input and comparing the returned choices

    Run the decision

    Use a sample first, then try your own input. Compare the selected label with the other returned probabilities.

  4. Illustration of reviewing a result and an uncertain item before using it

    Review the next step

    Review Need evidence before using a result. The label is a decision about the supplied information, not an executed action.

Our API test

Recorded API observations

Recorded API observations
Original inputObserved labelLeading probability
Null check addedSupported87.0%
Timeout goes the other wayContradicted100%
Speed claim without a measurementNot established97.0%
Missing hunkNeed evidence99.0%
Removal shownSupported98.0%
Subset cannot prove global coverageNot established92.0%

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

Understand the results

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.

Using the result in your application

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.

Runnable offline example

Run one sample, then inspect the local packet

View the code example
Single-request replay
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.json
Scope of this demo

Where this decision fits

Useful scope

  • Reviewing a specific change claim against a short patch
  • Flagging unsupported global or performance claims
  • Keeping missing proof distinct from direct contradiction

Outside this demonstration

  • Executing tests or measuring runtime performance
  • Proving facts about code that was not supplied
  • Approving or merging a change without a reviewer
Example FAQ

Questions about commit diff support.

Input scope and downstream handling determine what the label can tell you.

How is this different from message specificity?

A specificity check asks whether a claim can be checked. This task supplies the code and asks whether that claim is supported.

Can a passing fixture replace the test suite?

No. The fixtures check this text-to-label workflow. They do not execute the supplied code or establish repository correctness.

Is the leading probability an accuracy measurement?

No. It is the distribution for this request. Six synthetic fixtures check the workflow and preserve disagreements; they are not a production benchmark.

What happens if the API request fails?

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.

Try your own commit diff support input

Edit the supplied evidence above, or open the Playground for a different decision rule.