Jev PR change request detection

Identify change requests in a code review comment

Read the current reviewer's comment to separate a concrete modification request from approval, explanation or a declined quoted suggestion. Preserve ambiguous attribution before acting on the comment.

PR change request detectionLive API
Try an example

The reviewer names a requested modification.

Source: API-collected workflow inspiration; original demonstration below

Source and example scope

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.

Classify the current reviewer comment.

Decision rules and labels
Change requestedNo change requestedReview
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

What the decision checks

This decision belongs before a patch-writing queue. It separates comments that ask for work from comments that acknowledge, explain or approve the current implementation.

Attribution matters. A reviewer can quote a previous change request to disagree with it. Read the surrounding stance instead of treating every imperative inside quotation marks as an instruction.

The jevable package demonstrates filtering review comments with a Jev test. This original example makes unresolved intent explicit and stops at a label; it does not connect to a repository or post a review reply.

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.

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 code review change requests.

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

    Add the information to check

    Read the current reviewer's comment to separate a concrete modification request from approval, explanation or a declined quoted suggestion.

  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 Change requested, No change requested, Review. 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 Review 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
Direct renameChange requested100%
Polite requestChange requested100%
ApprovalNo change requested100%
Quoted request rejectedNo change requested93.0%
Explanation onlyNo change requested97.0%
Missing comment contextReview96.0%

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

Code review change requests: six recorded examples

The downloads contain six original inputs, their expected labels and one recorded API observation per input revision. Disagreements stay visible.

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.

Replay options

Inspect saved outputs or request a new decision

View the code example
Two independent commands
# 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.
Scope of this demo

Where this decision fits

Useful scope

  • Filtering review notifications before drafting a response.
  • Testing polite requests that use question wording.
  • Keeping quoted but rejected suggestions out of a patch queue.

Outside this demonstration

  • Applying a change without reviewing its correctness or authorization.
  • Using the label to decide whether a pull request should merge.
Example FAQ

Using this example

The input contract and these limits define what the result means.

Is every question a change request?

No. A question can ask for an explanation or ask someone to modify code. The surrounding wording and reviewer stance distinguish those uses.

Will it identify the exact repair to make?

The output only says whether a change was requested. A separate step needs the code and review context to understand and evaluate the proposed repair.

Does the leading probability measure accuracy?

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.

Will a result change an external system?

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.

Test a different input

Edit the example above to see how a changed fact affects the decision, or open the Playground for another task.