fix: paragraph-aware newline chunking (#1726)

Thanks @tyler6204

Co-authored-by: Tyler Yust <64381258+tyler6204@users.noreply.github.com>
This commit is contained in:
Peter Steinberger
2026-01-25 13:24:00 +00:00
parent c3f5b4c416
commit 0130ecd800
17 changed files with 39 additions and 24 deletions

View File

@@ -344,6 +344,11 @@ describe("chunkMarkdownTextWithMode", () => {
expect(chunkMarkdownTextWithMode(text, 1000, "newline")).toEqual([text]);
});
it("defers long markdown paragraphs to markdown chunking in newline mode", () => {
const text = `\`\`\`js\n${"const a = 1;\n".repeat(20)}\`\`\``;
expect(chunkMarkdownTextWithMode(text, 40, "newline")).toEqual(chunkMarkdownText(text, 40));
});
it("does not split on blank lines inside a fenced code block", () => {
const text = "```python\ndef my_function():\n x = 1\n\n y = 2\n return x + y\n```";
expect(chunkMarkdownTextWithMode(text, 1000, "newline")).toEqual([text]);