From a56a928b0ccaee75c1549255d555324b21305ec3 Mon Sep 17 00:00:00 2001
From: iris <2+iris@noreply.localhost>
Date: Sun, 6 Sep 2026 18:28:57 -0400
Subject: [PATCH] client-core: the transcript's own markdown shapes, and the
 streaming property as a property

split_blocks was tested on the shapes it was written against. These are
the ones a real reply contains -- a fence with blank lines in it, a `---`
inside a fence, a nested list, a fence directly under a heading, a table,
a quote -- plus the property RowBlocks::apply_delta actually depends on,
checked at every character boundary of a message that has all of them:
growing a message may rewrite its last block and never an earlier one, or
common_prefix must say so. No defect found; the split already held.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
---
 client-core/src/markdown_blocks.rs | 91 ++++++++++++++++++++++++++++++
 1 file changed, 91 insertions(+)

diff --git a/client-core/src/markdown_blocks.rs b/client-core/src/markdown_blocks.rs
index 9eb4a93..9df6596 100644
--- a/client-core/src/markdown_blocks.rs
+++ b/client-core/src/markdown_blocks.rs
@@ -231,4 +231,95 @@ mod tests {
             vec![BlockKind::Paragraph, BlockKind::Other, BlockKind::Paragraph]
         );
     }
+
+    /// The shapes a real transcript actually contains, each checked for
+    /// the one property the streaming fast path needs: the *number* of
+    /// blocks and every earlier block's source stay put while the message
+    /// grows. A fence's own blank lines, a `---` inside one, a nested
+    /// list and a table are all places where a naive line-based split
+    /// would break the message into more pieces than there are blocks.
+    #[test]
+    fn the_transcripts_own_block_shapes_survive_a_split() {
+        let fence_with_blanks = "Intro.\n\n```rust\nfn a() {}\n\nfn b() {}\n```\n\nAfter.";
+        assert_eq!(
+            kinds(fence_with_blanks),
+            vec![BlockKind::Paragraph, BlockKind::Code, BlockKind::Paragraph],
+            "a blank line inside a fence is not a block boundary"
+        );
+        assert_eq!(
+            kinds("```\n---\n```"),
+            vec![BlockKind::Code],
+            "a thematic break inside a fence is code, not a break"
+        );
+        assert_eq!(
+            kinds("- a\n  - a1\n  - a2\n- b"),
+            vec![BlockKind::List],
+            "a nested list is one top-level block"
+        );
+        assert_eq!(
+            kinds("## Heading\n```sh\nls\n```"),
+            vec![BlockKind::Heading, BlockKind::Code],
+            "a fence directly under a heading, with no blank line"
+        );
+        assert_eq!(
+            kinds("| a | b |\n|---|---|\n| 1 | 2 |"),
+            vec![BlockKind::Table]
+        );
+        assert_eq!(
+            kinds("> quoted\n> more\n\nplain"),
+            vec![BlockKind::Quote, BlockKind::Paragraph]
+        );
+    }
+
+    /// `apply_delta`'s precondition, stated as the property rather than
+    /// the arithmetic: for every prefix of a realistic streamed message,
+    /// the blocks before the last one must be exactly the blocks the
+    /// previous prefix had. Where markdown breaks that (the `---` case
+    /// above), `common_prefix` has to *say* so -- which is what the
+    /// `>= len - 1` assertion below checks: the split may rewrite the
+    /// last block, never an earlier one, or `RowBlocks::apply_delta`
+    /// would keep a widget whose text is no longer what it holds.
+    #[test]
+    fn every_prefix_of_a_streamed_message_keeps_all_but_its_last_block() {
+        let full = "# Report\n\nFirst finding, at some length.\n\n```rust\nfn main() {\n\n                        println!(\"hi\");\n}\n```\n\n- one\n  - nested\n- two\n\n| a | b |\n                    |---|---|\n| 1 | 2 |\n\n> and a closing quote.";
+        // Every character boundary, so a delta landing mid-word and one
+        // landing exactly on a fence's closing backtick are both covered.
+        let mut prev = Vec::new();
+        for end in full.char_indices().map(|(i, _)| i).chain([full.len()]) {
+            let now = split_blocks(&full[..end]);
+            let common = common_prefix(&prev, &now);
+            assert!(
+                prev.is_empty() || common + 1 >= prev.len(),
+                "at {end} bytes the split rewrote block {common} of {}, not just the last one:\n                 before={prev:#?}\nafter={now:#?}",
+                prev.len()
+            );
+            prev = now;
+        }
+    }
+
+    /// The half a growing message cannot show: a fence that never closes.
+    /// The stream ends there and the block must still be the code block
+    /// it has been all along, not re-split into paragraphs.
+    #[test]
+    fn a_stream_that_ends_inside_a_fence_still_ends_with_one_code_block() {
+        let src = "Here is the patch:\n\n```diff\n- old line\n+ new line";
+        let blocks = split_blocks(src);
+        assert_eq!(
+            blocks.iter().map(|b| b.kind).collect::<Vec<_>>(),
+            vec![BlockKind::Paragraph, BlockKind::Code]
+        );
+        assert_eq!(blocks[1].source, "```diff\n- old line\n+ new line");
+    }
+
+    /// A delta that closes a fence changes the *last* block only, so the
+    /// fast path takes it -- the case the module doc says is the reason
+    /// `common_prefix` is a comparison.
+    #[test]
+    fn the_delta_that_closes_a_fence_changes_only_the_last_block() {
+        let before = split_blocks("Text.\n\n```\ncode\n");
+        let after = split_blocks("Text.\n\n```\ncode\n```");
+        assert_eq!(before.len(), after.len());
+        assert_eq!(common_prefix(&before, &after), 1);
+        assert_ne!(before[1], after[1]);
+    }
 }