[
https://issues.apache.org/jira/browse/CAMEL-26960?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=18144723#comment-18144723
]
Claus Ibsen commented on CAMEL-26960:
-------------------------------------
Correction to the description: "Nothing checks that code" is not right. Since
CAMEL-24805, the Simple expressions of an answer are checked
({{AnswerChecks.checkSimple}} in camel-jbang-core). The AI panel and camel ask
ask the model once to correct them, and a note under the answer shows what is
left.
What is not checked today: unknown keys and options in YAML, {{camel.*}} keys
in properties, and endpoint options in URIs. This issue extends
{{AnswerChecks}} to those, so it builds on CAMEL-24805 instead of adding a new
mechanism.
Also found in the code:
* The answers of ACP agents are not checked, not even for Simple.
* The note is shown to the user, but it is not added to the model's history, so
the next answer can repeat the mistake.
> camel-jbang - Mark the mistakes in the code of AI answers, such as unknown
> options
> ----------------------------------------------------------------------------------
>
> Key: CAMEL-26960
> URL: https://issues.apache.org/jira/browse/CAMEL-26960
> Project: Camel
> Issue Type: Improvement
> Components: camel-jbang
> Reporter: Claus Ibsen
> Assignee: Claus Ibsen
> Priority: Major
> Fix For: 4.24.0
>
>
> The AI clients of the Camel CLI show code in their answers: YAML routes,
> application.properties lines, endpoint URIs. Nothing checks that code. A file
> the model writes goes through the validator, but code in an answer does not,
> and a beginner copies it.
> *Data* from a benchmark with a local model (Nov 13-14 2026, qwen3.6:35b-mlx,
> 5 example apps, 53 beginner questions in 3 rounds, so 159 answers per run):
> * Without an instruction: 6 unknown options in 4 answers.
> * With an instruction in the first message to look options up and to check
> every snippet with camel_validate_source: 32 unknown options in 14 answers.
> The model wrote 221 code blocks (84 without the instruction) and checked none
> of them. Its 3 calls of camel_validate_source checked the route file, not a
> snippet.
> Examples from the answers:
> * {{idempotentConsumer}} with {{messageIdCache}} and {{cacheName}} (the
> option is {{idempotentRepository}})
> * {{redeliveryPolicy}} with {{multiplier}} (the option is
> {{backOffMultiplier}})
> * {{camel.metrics-enabled}} (the key is {{camel.metrics.enabled}}),
> {{camel.tracing}}, {{camel.health.check-routes-on-startup}}
> * {{log:ERROR?level=ERROR&message=...}} (the log endpoint has no message
> option)
> * {{onException}} with the exception class as a YAML key
> * {{forceOpen}}, {{failureThreshold}} and {{openDuration}} on a circuit
> breaker
> *Proposal: mark the mistakes, do not change the answer.*
> * When an answer is complete, take its fenced code blocks (YAML, XML, Java,
> properties) and check them with the same checks as camel_validate_source with
> content.
> * Under each block with a problem, show one line per problem with the nearest
> valid names. For example: "multiplier is not an option of redeliveryPolicy;
> did you mean backOffMultiplier?"
> * Add the findings to the conversation, so the next answer does not repeat
> the mistake.
> * No extra model call. Always on.
> *Where*
> * The check itself goes in camel-jbang-core, next to camel_validate_source,
> so all clients share it.
> * camel ask: print the findings below the answer.
> * The AI panel: mark the blocks in the answer, for the built-in model and for
> ACP agents (their answers come in the same way).
> * External MCP clients never show Camel their answer. They can get a tool
> that checks the code blocks of a text. This can be a follow-up.
> *Fragments*
> Most code in an answer is a fragment, not a whole route. {{camel validate
> yaml}} finds {{messageIdCache}} in a whole route. But it refuses a bare
> {{redeliveryPolicy:}} block for its shape ("object found, array expected")
> before it checks the options. The check needs a fragment mode: check the
> block against the schema of its EIP, or wrap a list of steps in a route.
> *How to measure*
> The benchmark counts unknown options in answers. With this in place, no
> unknown option should be shown without a mark (32 in the run with the
> instruction).
> *Later, not in this issue:* a repair turn, where the model gets the findings
> and corrects its answer.
--
This message was sent by Atlassian Jira
(v10.3.26#10030026)