Only apply #:when and #:unless refactoring to multi-body loops

[Copilot]

The when-expression-in-for-loop-to-when-keyword and unless-expression-in-for-loop-to-unless-keyword rules were refactoring single-statement loops, which doesn't meaningfully reduce indentation or improve readability.

Changes

• Added #:when (>= (length (attribute body)) 2) guard to both refactoring rules to require at least 2 body forms
• Updated existing tests to use multi-body examples
• Added no-change-test cases to verify single-body loops are not refactored

Example

This will not be refactored anymore:

(for ([v (in-list vs)])
  (unless (good? v)
    (raise-arguments-error ...)))

This will still be refactored:

(for ([v (in-list vs)])
  (unless (good? v)
    (displayln "checking")
    (raise-arguments-error ...)))
;; →
(for ([v (in-list vs)]
      #:unless (good? v))
  (displayln "checking")
  (raise-arguments-error ...))

Original prompt

---

This section details on the original issue you should resolve

<issue_title>Only use #:when and #:unless with multi-body loops</issue_title> <issue_description>Often, the unless-expression-in-for-loop-to-unless-keyword rule (and its corresponding when-based rule) rewrites this:

(for ([v (in-list vs)])
  (unless (good? v)
    (raise-arguments-error ...)))

to this:

(for ([v (in-list vs)]
      #:unless (good? v))
  (raise-arguments-error ...))

I don't think that's an improvement. I think these rules should only remove a when or unless from a loop if it has more than one body form inside it.</issue_description>

Comments on the Issue (you are @copilot in this section)

• Fixes jackfirth/resyntax#765

---

💡 You can make Copilot smarter by setting up custom instructions, customizing its development environment and configuring Model Context Protocol (MCP) servers. Learn more Copilot coding agent tips in the docs.