Jev tool result kind

Classify what a tool actually returned

Read the returned content to distinguish an actual failure, path listing, source text, run log and lookup facts. Classify the output rather than relying on the command's name.

Which kind of content is in this result?Live API
Try an example

An actual failure takes priority over log format.

Source: API-collected workflow inspiration; original demonstration below

Source and example scope

The API-collected roundup links the cited project. Its pinned source defines the decision adapted here. These synthetic inputs and explicit missing-context outcomes are original to this demonstration. The window returns a label; it does not run the linked application, execute its downstream actions or verify its performance claims.

Classify the result, not the command name.

Decision rules and labels
FailurePath listingSource textRun logLookup dataNeed result
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 source file containing ERROR is different from a command reporting an error.

The build preset reports a real resolution failure inside a log, so Failure takes priority. The source-text preset contains ERROR in a string literal and explicitly states that no command ran. The word alone cannot establish a failed operation.

Search hits can include code fragments while still being a Path listing. An inventory lookup can return structured facts without being a source-file excerpt. The supplied role helps distinguish those cases; a command name by itself is insufficient.

The pinned context.compact decision first classifies the content of a tool result. It separately asks whether the result is still needed. This original demonstration only covers content type and adds explicit ambiguity handling; it does not compact context, delete output or validate an MCP response schema.

The API-collected roundup links the cited project. Its pinned source defines the decision adapted here. These synthetic inputs and explicit missing-context outcomes are original to this demonstration. The window returns a label; it does not run the linked application, execute its downstream actions or verify its performance claims.

Illustration of one spreadsheet row producing two separate classification results
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 tool result types.

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

    Add the information to check

    Read the returned content to distinguish an actual failure, path listing, source text, run log and lookup facts.

  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 Failure, Path listing, Source text, Run log, Lookup data. 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 result 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
Failure inside a build logFailure99.0%
Search hitsPath listing99.0%
Source with a quoted errorSource text100%
Execution progressRun log100%
Returned lookup valuesLookup data100%
Result missingNeed result100%

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

Replay the saved synthetic requests to inspect each recorded decision

Replay the saved synthetic requests to inspect each recorded decision. Authored expectations and model disagreements remain available; these examples are not a production accuracy benchmark.

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

  • Labeling captured tool results
  • Separating actual errors from quoted strings
  • Distinguishing search hits from full source excerpts

Outside this demonstration

  • Executing the displayed commands
  • Choosing which results to discard
  • Validating a transport envelope or response schema
Example FAQ

Questions about tool result kind.

Input scope and downstream handling determine what this judgment means.

Does the result type decide whether to keep the text?

No. Retention depends on the task and future evidence needs. A short failure and a long source excerpt can both remain important.

What happens with inseparably mixed content?

Choose Need result under this page’s rule when a role and dominant type cannot be established. An actual reported failure still takes priority over its log formatting.

Is the leading probability an accuracy measurement?

No. It is one value in the returned distribution over this request’s choices. The six synthetic fixtures have authored expectations; they do not measure production accuracy.

What happens on an API failure?

The window displays an error without a fresh judgment. An incomplete-input outcome describes the supplied evidence and is not used as a fallback for provider failure.

Try your own tool result kind input

Edit the input above, or open the Playground to explore another decision.