Claus Ibsen created CAMEL-26416:
-----------------------------------
Summary: camel-jbang - AI tools: a field read is checked against
the fields of the JSON data files the routes read
Key: CAMEL-26416
URL: https://issues.apache.org/jira/browse/CAMEL-26416
Project: Camel
Issue Type: Improvement
Components: camel-jbang, camel-yaml-dsl
Reporter: Claus Ibsen
Assignee: Claus Ibsen
Fix For: 4.24.0
In the r24 run of the local-model benchmark (qwen3.6:35b on Ollama, Oct 29-30
2026), the model read fields that the data does not have. A field that is not
there is null, so nothing failed, and the logs were wrong:
* $\{body[lineCount]\} and $\{body[quantity]\} on an order, which has lines
(route-filter-and-multicast step 2, 2 runs). The read was in the direct: route
that a multicast sends the order to.
* $\{body[orderId]\} inside the split of the lines of an order: a line has sku,
qty and price (connect-http-client step 2).
The AI tools now read the fields of the JSON data the routes read: the files in
the directory a file consumer reads, and the file a resource: loads. Data whose
files do not all have one shape, or with more than 50 files, is left out. The
validator then checks a simple read of a field of the body after an unmarshal
of that data:
* in the route itself, and in the predicates of a filter or a choice;
* inside a split of a field that holds a list of objects, against the fields of
those objects. A field of the data that was split gets the advice to read it
before the split, into a variable;
* in a direct: or seda: route that every call of the file sends the same data
to.
The message names the fields the data has. None of the 85 reference route files
of the benchmark gets a report.
--
This message was sent by Atlassian Jira
(v10.3.26#10030026)
