Fold anything verbose

prompt.md

@@ -26,11 +26,12 @@ changes, check that the result is aligned, clean, and pixel-perfect, and that
 included screenshots prove the intended result was achieved.
 
 The review must read at a glance: everything outside `<details>` blocks totals
-under 512 bytes. Keep only the assessment line, the section headings, and a
-one-line `@bot` instruction visible. Put each strength, each issue, and each
-recommendation in its own top-level `<details>` block, never inside a list item,
-with a `<summary>` of the `file:line` and a few words and the what, why, and how
-inside. The template's `**Reasoning:**` goes in a `<details>` block too.
+under 512 bytes. Only core information stays visible: the assessment line, the
+section headings, and a one-line `@bot` instruction. Anything verbose goes into
+a `<details>` block whose `<summary>` is a few words, such as the `file:line`
+and title of an issue with the what, why, and how inside; the same for each
+strength, each recommendation, the reasoning, and any compliance notes. Details
+blocks are top-level, never inside a list item, because Gitea breaks them there.
 
 For an `issue_comment` or `pull_request_review_comment` event, treat the `body`
 in the triggering comment payload below as the user's exact instruction.