IVYXSTUDIO · IVY AGENT

CSV Quality Report

ivy.agent.csv-quality-report · v1.0.0

ivyx

Checks every row of an orders CSV against a schema and writes a report of the rows with problems and the valid rows per country, with no model involved.

Steps

In the order the agent's file lists them, each with where its inputs come from and the values the file fixes. A branch or a loop is a step too.

01
Read the CSV
ivy.node.csv-read
Reads a CSV file, or CSV text, into rows with the column names and row count.
takes
path from the agent's input
returns
row_count
Ivy Node
02
Check every row
ivy.node.rows-validate
Checks every row against a JSON Schema and splits the rows into valid ones and invalid ones with their problems.
takes
rows from step 1
set
schema {"type":"object","required":["order_id","customer","quantity","unit_price","status"],"properties":{"order_id":{"type"...
returns
error_count, invalid_rows
Ivy Node
03
Count valid rows per country
ivy.node.table-aggregate
Groups rows and sums, averages, counts or takes the minimum or maximum of one column, optionally by month, year or day of a date column.
takes
rows from step 2, valid_rows
set
group_by country
op count
returns
by_country
Ivy Node
04
Lay out the problem rows
ivy.node.markdown-table
Formats rows as a Markdown table, with the columns in the order given or as they first appear.
takes
rows from step 2, invalid_rows
set
columns ["order_id","customer","problems"]
Ivy Node
05
Lay out the country counts
ivy.node.markdown-table
Formats rows as a Markdown table, with the columns in the order given or as they first appear.
takes
rows from step 3
Ivy Node
06
Assemble the report
ivy.node.template-render
Fills {{ name }} placeholders in a text template from a mapping, and reports which names were missing.
takes
values.file from the agent's input, path
values.error_count from step 2, error_count
values.row_count from step 1, row_count
values.problems from step 4, markdown
values.by_country from step 5, markdown
set
template # CSV quality report File: {{ file }} {{ error_count }} of {{ row_count }} rows have a problem. ## Rows with problems...
on_missing empty
returns
report
Ivy Node
07
Write the report
ivy.node.file-write
Writes text to a file, creating its folder, and returns the absolute path and the number of bytes written.
takes
text from step 6
set
path reports/csv-quality.md
overwrite true
returns
path
Ivy Node

Nodes it brings

Adding this agent in IVYX Studio adds these nodes with it. A node your workspace already has is kept as it is, even at another version.

What it touches

Collected from what each of its nodes declares, plus the model call when a step is a model turn. A declaration is the author's statement, and it is what policy rules select on.

Writes files

Inputs

Field	Type	Description
pathrequired	string	Path to the orders CSV, with the columns order_id, customer, country, quantity, unit_price and status.

Outputs

Field	Type	Description
row_count	integer	How many rows the file has.
error_count	integer	How many rows had a problem.
invalid_rows	array	The rows with problems, each with its problems as one sentence.
by_country	array	The valid rows counted per country.
report	string	The report that was written.
path	string	The file the report was written to.

Tests

2 of 2 test cases passed on Oct 4, 2026, in the publisher's own environment, before this version was published. The registry keeps that record; it does not run the cases again.

Requires: python:3.9

four-bad-rows
Six orders, four with a problem: a missing quantity, a negative one, an unknown status and a missing customer.
given
path data/showcase/orders.csv
expects
row_count equals 6
error_count equals 4
report matches O-1002[\s\S]*O-1003[\s\S]*O-1004[\s\S]*O-1006
path matches reports/csv-quality\.md$
clean-file
A clean file has no problem row and still counts its countries.
given
path data/showcase/orders-clean.csv
expects
row_count equals 3
error_count equals 0
report matches 0 of 3 rows