Prepare Covenant validation correction

When to use it

Prepare a bounded correction for a fully received model answer that failed validation. The correction stays within the original source set and scope. An uncertain provider call is not automatically repeated as a correction.

Add and configure

Add Prepare Covenant validation correction from the workflow step picker.
Give the step a recognisable name and connect its required inputs.
Set the options below. Nested names identify fields within an object or a list item.
Validate the recipe, inspect the test result, then run it on the intended data.

The step identifier used in the editor’s code view is covenant_correct.

Settings

Setting	Accepted value	Required	Default	What it controls
Max Corrections (`max_corrections`)	integer; minimum 0; maximum 5	No	1	Upper bound on correction attempts for the analysis plan.
Options (`options`)	object	No	Not specified	Options accepted by the selected domain operation. Use its documented shape; an open object is not a guarantee that every key has an effect.

Inputs and outputs

Direction	Port	Content	Required	Multiple records
Inputs	`in`	records	Yes	Yes
Outputs	`out`	records	Yes	Yes

Effects, testing, and recovery

Writes information inside Strive.

The declared preview behaviour is to skip this step. Configuration can affect preview behaviour; HTTP GET is a notable exception. Read dry runs before using a preview with live connections.

Duplicate prevention uses content identity. The step declares safe replay for its supported recovery path.

Execution bounds

Limit	Declared bound
max input bytes	6291456
max output bytes	6291456
max records	100
memory mb	256
timeout seconds	120

Recovery policy: ambiguous outcome: manual_resolution; cancellation: cooperative; errors: invalid_input, invalid_config, quota_exhausted, timeout, recovery_unsafe, upstream_rejected; max attempts: 1.

Example: Empty branch

Step settings:

{}

Expected output for this example:

[]

Check the result

Inspect the selected run’s status, counts, errors, and output records. An empty collection can be a valid result, and a completed step can contain per-record failures where the step defines that behaviour. Check the next step’s expected record shape before publishing or delivering the result.