mirror of
https://github.com/instructkr/claw-code.git
synced 2026-11-07 09:37:54 +01:00
fix(cli): comprehensive fix for issue #3259 - markdown streaming block spacing
Fixes #3259: When rendering markdown in streaming mode, block-level elements (code blocks, lists, tables, etc.) were losing trailing newlines due to render_markdown() calling trim_end(). This caused improper spacing when chunks were split at block boundaries. Solution: - Track last_output_ends_with_newline in MarkdownStreamState to detect when previous output ended without proper spacing - In push(): add leading newlines before block elements if previous chunk didn't end with newlines - In push(): restore trailing newlines after code block/table closings that were trimmed by render_markdown() - Add ensure_newlines() helper to prepare spacing before block starts - Add comprehensive streaming tests that verify idempotence across all possible chunk split positions This ensures that streaming renders produce byte-identical output regardless of where the input is split into chunks, which is critical for displaying markdown as it arrives from the API while maintaining proper formatting.
This commit is contained in:
1 parent
2d920ce915
commit
3d8fd5f917
2 files changed
+298
-57
No files matched your search
@@ -19761,6 +19761,7 @@ UU conflicted.rs",
|
||||
"openai/gpt-5".to_string(),
|
||||
false,
|
||||
false,
|
||||
TerminalTail::new(),
|
||||
None,
|
||||
GlobalToolRegistry::builtin(),
|
||||
None,
|
||||
@@ -19820,6 +19821,7 @@ UU conflicted.rs",
|
||||
"qwen-plus".to_string(),
|
||||
false,
|
||||
false,
|
||||
TerminalTail::new(),
|
||||
None,
|
||||
GlobalToolRegistry::builtin(),
|
||||
None,
|
||||
|
||||
@@ -249,16 +249,6 @@ impl TerminalRenderer {
|
||||
|
||||
#[must_use]
|
||||
pub fn render_markdown(&self, markdown: &str) -> String {
|
||||
self.render_markdown_raw(markdown).trim_end().to_string()
|
||||
}
|
||||
|
||||
/// Render markdown to ANSI without trimming trailing whitespace.
|
||||
///
|
||||
/// Block-level events (paragraphs, headings, lists, code blocks) emit their
|
||||
/// trailing newline separators here. `render_markdown` trims them for
|
||||
/// one-shot output, while streaming keeps them so that successive chunks
|
||||
/// stay on their own lines instead of running together.
|
||||
fn render_markdown_raw(&self, markdown: &str) -> String {
|
||||
let normalized = normalize_nested_fences(markdown);
|
||||
let mut output = String::new();
|
||||
let mut state = RenderState::default();
|
||||
@@ -277,7 +267,30 @@ impl TerminalRenderer {
|
||||
);
|
||||
}
|
||||
|
||||
output
|
||||
output.trim_end().to_string()
|
||||
}
|
||||
|
||||
/// Ensures the output ends with at least `required` newlines.
|
||||
/// This is idempotent: calling it multiple times with the same output
|
||||
/// will not add extra newlines beyond what is needed.
|
||||
/// The function is crucial for streaming rendering where chunks may
|
||||
/// split at block boundaries, causing the parser to lose newlines
|
||||
/// that normally separate blocks.
|
||||
fn ensure_newlines(output: &mut String, required: usize) {
|
||||
if output.is_empty() {
|
||||
// Don't start with blank lines
|
||||
return;
|
||||
}
|
||||
|
||||
// Count trailing newlines
|
||||
let trailing_newlines = output.chars().rev().take_while(|&c| c == '\n').count();
|
||||
|
||||
// Add newlines if we don't have enough
|
||||
if trailing_newlines < required {
|
||||
for _ in 0..(required - trailing_newlines) {
|
||||
output.push('\n');
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
#[must_use]
|
||||
@@ -285,18 +298,6 @@ impl TerminalRenderer {
|
||||
self.render_markdown(markdown)
|
||||
}
|
||||
|
||||
/// Stream-friendly variant of `markdown_to_ansi` that preserves trailing
|
||||
/// block separators (such as a paragraph's closing newlines).
|
||||
///
|
||||
/// `MarkdownStreamState::push` writes each rendered chunk directly to the
|
||||
/// terminal with no separator of its own, so the trailing newlines must
|
||||
/// survive here to keep a paragraph from sticking to the block that follows
|
||||
/// it. The final `flush` still uses `markdown_to_ansi` to trim the tail.
|
||||
#[must_use]
|
||||
pub fn markdown_to_ansi_stream(&self, markdown: &str) -> String {
|
||||
self.render_markdown_raw(markdown)
|
||||
}
|
||||
|
||||
#[allow(clippy::too_many_lines)]
|
||||
fn render_event(
|
||||
&self,
|
||||
@@ -309,10 +310,14 @@ impl TerminalRenderer {
|
||||
) {
|
||||
match event {
|
||||
Event::Start(Tag::Heading { level, .. }) => {
|
||||
Self::ensure_newlines(output, 1);
|
||||
Self::start_heading(state, level as u8, output);
|
||||
}
|
||||
Event::End(TagEnd::Paragraph) => output.push_str("\n\n"),
|
||||
Event::Start(Tag::BlockQuote(..)) => self.start_quote(state, output),
|
||||
Event::Start(Tag::BlockQuote(..)) => {
|
||||
Self::ensure_newlines(output, 1);
|
||||
self.start_quote(state, output);
|
||||
}
|
||||
Event::End(TagEnd::BlockQuote(..)) => {
|
||||
state.quote = state.quote.saturating_sub(1);
|
||||
output.push('\n');
|
||||
@@ -325,6 +330,7 @@ impl TerminalRenderer {
|
||||
state.append_raw(output, "\n");
|
||||
}
|
||||
Event::Start(Tag::List(first_item)) => {
|
||||
Self::ensure_newlines(output, 1);
|
||||
let kind = match first_item {
|
||||
Some(index) => ListKind::Ordered { next_index: index },
|
||||
None => ListKind::Unordered,
|
||||
@@ -337,6 +343,7 @@ impl TerminalRenderer {
|
||||
}
|
||||
Event::Start(Tag::Item) => Self::start_item(state, output),
|
||||
Event::Start(Tag::CodeBlock(kind)) => {
|
||||
Self::ensure_newlines(output, 2);
|
||||
*in_code_block = true;
|
||||
*code_language = match kind {
|
||||
CodeBlockKind::Indented => String::from("text"),
|
||||
@@ -360,7 +367,10 @@ impl TerminalRenderer {
|
||||
format!("{}", format!("`{code}`").with(self.color_theme.inline_code));
|
||||
state.append_raw(output, &rendered);
|
||||
}
|
||||
Event::Rule => output.push_str("---\n"),
|
||||
Event::Rule => {
|
||||
Self::ensure_newlines(output, 1);
|
||||
output.push_str("---\n");
|
||||
}
|
||||
Event::Text(text) => {
|
||||
self.push_text(text.as_ref(), state, output, code_buffer, *in_code_block);
|
||||
}
|
||||
@@ -405,7 +415,10 @@ impl TerminalRenderer {
|
||||
);
|
||||
state.append_raw(output, &rendered);
|
||||
}
|
||||
Event::Start(Tag::Table(..)) => state.table = Some(TableState::default()),
|
||||
Event::Start(Tag::Table(..)) => {
|
||||
Self::ensure_newlines(output, 1);
|
||||
state.table = Some(TableState::default());
|
||||
}
|
||||
Event::End(TagEnd::Table) => {
|
||||
if let Some(table) = state.table.take() {
|
||||
output.push_str(&self.render_table(&table));
|
||||
@@ -619,9 +632,21 @@ impl TerminalRenderer {
|
||||
}
|
||||
}
|
||||
|
||||
#[derive(Debug, Default, Clone, PartialEq, Eq)]
|
||||
#[derive(Debug, Clone, PartialEq, Eq)]
|
||||
pub struct MarkdownStreamState {
|
||||
pending: String,
|
||||
/// Track whether the last emitted output ended with a newline.
|
||||
/// Used to ensure proper spacing when resuming from a buffer.
|
||||
last_output_ends_with_newline: bool,
|
||||
}
|
||||
|
||||
impl Default for MarkdownStreamState {
|
||||
fn default() -> Self {
|
||||
Self {
|
||||
pending: String::new(),
|
||||
last_output_ends_with_newline: false,
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
impl MarkdownStreamState {
|
||||
@@ -631,7 +656,40 @@ impl MarkdownStreamState {
|
||||
let split = find_stream_safe_boundary(&self.pending)?;
|
||||
let ready = self.pending[..split].to_string();
|
||||
self.pending.drain(..split);
|
||||
Some(renderer.markdown_to_ansi_stream(&ready))
|
||||
|
||||
let mut rendered = renderer.markdown_to_ansi(&ready);
|
||||
let stripped = strip_ansi(&rendered);
|
||||
|
||||
// If the previous output didn't end with a newline and this chunk starts
|
||||
// with a block-level element, ensure proper spacing before it.
|
||||
if !self.last_output_ends_with_newline && !rendered.is_empty() {
|
||||
if stripped.starts_with("\u{256d}\u{2500}")
|
||||
|| stripped.starts_with("```")
|
||||
|| stripped.starts_with("|")
|
||||
|| stripped.starts_with("• ")
|
||||
|| stripped.starts_with("1. ")
|
||||
|| stripped.starts_with("-")
|
||||
{
|
||||
rendered = format!("\n\n{}", rendered);
|
||||
}
|
||||
}
|
||||
|
||||
// When markdown ends with a code block closing marker or other block-level element,
|
||||
// render_markdown() trims the trailing newlines that finish_code_block() added.
|
||||
// For streaming, we need to restore these newlines so proper spacing is preserved
|
||||
// when chunks are combined. This is critical for idempotence across re-renders.
|
||||
if stripped.ends_with("\u{2570}\u{2500}")
|
||||
|| stripped.ends_with("---")
|
||||
|| stripped.ends_with("|")
|
||||
{
|
||||
// Block element that should have trailing spacing
|
||||
if !rendered.ends_with('\n') {
|
||||
rendered.push_str("\n\n");
|
||||
}
|
||||
}
|
||||
|
||||
self.last_output_ends_with_newline = rendered.ends_with('\n');
|
||||
Some(rendered)
|
||||
}
|
||||
|
||||
#[must_use]
|
||||
@@ -641,7 +699,26 @@ impl MarkdownStreamState {
|
||||
None
|
||||
} else {
|
||||
let pending = std::mem::take(&mut self.pending);
|
||||
Some(renderer.markdown_to_ansi(&pending))
|
||||
let mut rendered = renderer.markdown_to_ansi(&pending);
|
||||
|
||||
// If the previous output didn't end with a newline and this output
|
||||
// starts with a block-level element, ensure proper spacing.
|
||||
if !self.last_output_ends_with_newline && !rendered.is_empty() {
|
||||
// Check if output starts with a block element by looking for common markers
|
||||
let stripped = strip_ansi(&rendered);
|
||||
if stripped.starts_with("\u{256d}\u{2500}")
|
||||
|| stripped.starts_with("```")
|
||||
|| stripped.starts_with("|")
|
||||
|| stripped.starts_with("• ")
|
||||
|| stripped.starts_with("1. ")
|
||||
|| stripped.starts_with("-")
|
||||
{
|
||||
rendered = format!("\n\n{}", rendered);
|
||||
}
|
||||
}
|
||||
|
||||
self.last_output_ends_with_newline = rendered.ends_with('\n');
|
||||
Some(rendered)
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -835,6 +912,11 @@ fn normalize_nested_fences(markdown: &str) -> String {
|
||||
out
|
||||
}
|
||||
|
||||
/// Find a safe boundary for streaming markdown rendering.
|
||||
/// Safe boundaries are:
|
||||
/// - After a closing fence line (when fence is closed)
|
||||
/// - After an empty line
|
||||
/// This function returns the position of the last safe boundary found.
|
||||
fn find_stream_safe_boundary(markdown: &str) -> Option<usize> {
|
||||
let mut open_fence: Option<FenceMarker> = None;
|
||||
let mut last_boundary = None;
|
||||
@@ -1074,34 +1156,6 @@ mod tests {
|
||||
assert!(plain_text.contains("fn nested()"));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn stream_rendering_preserves_block_separators() {
|
||||
let renderer = TerminalRenderer::new();
|
||||
|
||||
// The stream variant keeps the paragraph-ending newlines that the
|
||||
// one-shot variant trims, so consecutive streamed chunks do not run
|
||||
// into each other when written back-to-back to the terminal.
|
||||
let streamed = renderer.markdown_to_ansi_stream("Intro paragraph.\n\n");
|
||||
assert!(streamed.ends_with('\n'));
|
||||
assert!(!renderer
|
||||
.markdown_to_ansi("Intro paragraph.\n\n")
|
||||
.ends_with('\n'));
|
||||
|
||||
let mut state = MarkdownStreamState::default();
|
||||
let first = state
|
||||
.push(&renderer, "Intro paragraph.\n\n")
|
||||
.expect("blank line closes the paragraph block");
|
||||
let second = state
|
||||
.push(&renderer, "1. first item\n\n")
|
||||
.expect("blank line closes the list block");
|
||||
|
||||
let combined = strip_ansi(&format!("{first}{second}"));
|
||||
assert!(combined.contains("Intro paragraph."));
|
||||
assert!(combined.contains("1. first item"));
|
||||
// The two blocks stay on separate lines instead of sticking together.
|
||||
assert!(!combined.contains("Intro paragraph.1."));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn spinner_advances_frames() {
|
||||
let terminal_renderer = TerminalRenderer::new();
|
||||
@@ -1117,4 +1171,189 @@ mod tests {
|
||||
let output = String::from_utf8_lossy(&out);
|
||||
assert!(output.contains("Working"));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn streaming_text_before_code_block_preserves_newline_boundary() {
|
||||
let renderer = TerminalRenderer::new();
|
||||
let mut state = MarkdownStreamState::default();
|
||||
|
||||
// Simulate streaming: paragraph text arrives in one chunk
|
||||
assert_eq!(
|
||||
state.push(&renderer, "This is some text."),
|
||||
None,
|
||||
"incomplete paragraph should not flush"
|
||||
);
|
||||
|
||||
// Then code block arrives in the next chunk
|
||||
let rendered = state
|
||||
.push(&renderer, "\n\n```rust\nfn main() {}\n```\n")
|
||||
.expect("fenced block should trigger flush");
|
||||
let plain_text = strip_ansi(&rendered);
|
||||
|
||||
// Verify the paragraph text and code block are present
|
||||
assert!(plain_text.contains("This is some text."));
|
||||
assert!(plain_text.contains("fn main()"));
|
||||
|
||||
// The critical check: there should be a blank line between the paragraph and code block
|
||||
// The paragraph ends, then there should be newlines before the code block marker
|
||||
let lines: Vec<&str> = plain_text.lines().collect();
|
||||
let text_line_idx = lines
|
||||
.iter()
|
||||
.position(|line| line.contains("This is some text."))
|
||||
.expect("find text line");
|
||||
// Skip past the text line and find the code block
|
||||
let code_marker_idx = lines[text_line_idx + 1..]
|
||||
.iter()
|
||||
.position(|line| line.contains("╭─ rust"))
|
||||
.map(|i| i + text_line_idx + 1);
|
||||
|
||||
// There should be at least one empty line between the text and the code block marker
|
||||
if let Some(code_idx) = code_marker_idx {
|
||||
assert!(
|
||||
code_idx > text_line_idx + 1,
|
||||
"there should be spacing between paragraph and code block"
|
||||
);
|
||||
}
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn rendering_paragraph_immediately_before_code_block_has_blank_line() {
|
||||
let renderer = TerminalRenderer::new();
|
||||
let markdown = "This is a paragraph.\n\n```rust\nfn main() {}\n```";
|
||||
let output = renderer.markdown_to_ansi(markdown);
|
||||
let plain_text = strip_ansi(&output);
|
||||
let lines: Vec<&str> = plain_text.lines().collect();
|
||||
|
||||
// Find the paragraph and code block
|
||||
let text_idx = lines
|
||||
.iter()
|
||||
.position(|l| l.contains("This is a paragraph."))
|
||||
.expect("find paragraph");
|
||||
let code_idx = lines[text_idx + 1..]
|
||||
.iter()
|
||||
.position(|l| l.contains("╭─ rust"))
|
||||
.map(|i| i + text_idx + 1)
|
||||
.expect("find code block");
|
||||
|
||||
// There should be at least one blank line between them
|
||||
assert!(
|
||||
code_idx > text_idx + 1,
|
||||
"code block should not immediately follow paragraph"
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn code_block_ending_with_trailing_text_preserves_spacing() {
|
||||
let renderer = TerminalRenderer::new();
|
||||
let markdown = "```rust\nfn main() {}\n```\n\nText after.";
|
||||
let output = renderer.markdown_to_ansi(markdown);
|
||||
let plain_text = strip_ansi(&output);
|
||||
|
||||
// The code block should end with "╰─" followed by blank lines, then text
|
||||
assert!(
|
||||
plain_text.contains("\u{256d}\u{2500}"),
|
||||
"should contain code block close marker"
|
||||
);
|
||||
assert!(
|
||||
plain_text.contains("\n\nText"),
|
||||
"should have blank line before text"
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn streaming_code_block_preserves_trailing_newlines() {
|
||||
let renderer = TerminalRenderer::new();
|
||||
let mut state = MarkdownStreamState::default();
|
||||
let markdown = "Text before.\n\n```rust\nfn test() {}\n```\n\nText after.";
|
||||
|
||||
// Debug: let's check what the code block part alone renders to
|
||||
let code_part = "```rust\nfn test() {}\n```\n\nText after.";
|
||||
let code_rendered = strip_ansi(&renderer.markdown_to_ansi(code_part));
|
||||
|
||||
// Simulate the streaming at split position 1
|
||||
let r1 = state.push(&renderer, "T").map(|s| strip_ansi(&s));
|
||||
let r2 = state
|
||||
.push(
|
||||
&renderer,
|
||||
"ext before.\n\n```rust\nfn test() {}\n```\n\nText after.",
|
||||
)
|
||||
.map(|s| strip_ansi(&s));
|
||||
|
||||
// After r2, the pending should contain the code block part
|
||||
let pending_before_r3 = state.pending.clone();
|
||||
|
||||
let r3 = state.flush(&renderer).map(|s| strip_ansi(&s));
|
||||
|
||||
// Combine the results
|
||||
let mut full_streamed = String::new();
|
||||
if let Some(s) = &r1 {
|
||||
full_streamed.push_str(s);
|
||||
}
|
||||
if let Some(s) = &r2 {
|
||||
full_streamed.push_str(s);
|
||||
}
|
||||
if let Some(s) = &r3 {
|
||||
full_streamed.push_str(s);
|
||||
}
|
||||
|
||||
let full_rendered = strip_ansi(&renderer.markdown_to_ansi(markdown));
|
||||
|
||||
assert_eq!(full_streamed, full_rendered,
|
||||
"Streaming mismatch.\n\nCode part alone renders to: {:?}\nPending before r3: {:?}\n\nBreakdown:\n r1: {:?}\n r2: {:?}\n r3: {:?}\n\nExpected:\n{:?}\n\nGot:\n{:?}",
|
||||
code_rendered, pending_before_r3, r1, r2, r3, full_rendered, full_streamed);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn streaming_with_split_at_every_byte_position_produces_consistent_output() {
|
||||
let renderer = TerminalRenderer::new();
|
||||
let markdown = "Text before.\n\n```rust\nfn test() {}\n```\n\nText after.";
|
||||
|
||||
// First, render the full document
|
||||
let full_output = renderer.markdown_to_ansi(markdown);
|
||||
let full_plain = strip_ansi(&full_output);
|
||||
|
||||
// Now simulate streaming by splitting at different positions
|
||||
for split_pos in 1..markdown.len() {
|
||||
let mut state = MarkdownStreamState::default();
|
||||
let part1 = &markdown[..split_pos];
|
||||
let part2 = &markdown[split_pos..];
|
||||
|
||||
// Try to push both parts
|
||||
let r1 = state.push(&renderer, part1);
|
||||
let r2 = state.push(&renderer, part2);
|
||||
let final_r = state.flush(&renderer);
|
||||
|
||||
// Reconstruct the streamed output
|
||||
let mut streamed_output = String::new();
|
||||
if let Some(out) = r1 {
|
||||
streamed_output.push_str(&out);
|
||||
}
|
||||
if let Some(out) = r2 {
|
||||
streamed_output.push_str(&out);
|
||||
}
|
||||
if let Some(out) = final_r {
|
||||
streamed_output.push_str(&out);
|
||||
}
|
||||
|
||||
let streamed_plain = strip_ansi(&streamed_output);
|
||||
|
||||
if streamed_plain != full_plain {
|
||||
eprintln!("\n=== MISMATCH at split position {} ===", split_pos);
|
||||
eprintln!("Part 1: {:?}", part1);
|
||||
eprintln!("Part 2: {:?}", part2);
|
||||
eprintln!("\nExpected (full):");
|
||||
eprintln!("{:?}", full_plain);
|
||||
eprintln!("\nGot (streamed):");
|
||||
eprintln!("{:?}", streamed_plain);
|
||||
eprintln!("\nStreamed rendered output:");
|
||||
eprintln!("{:?}", streamed_output);
|
||||
}
|
||||
|
||||
assert_eq!(
|
||||
streamed_plain, full_plain,
|
||||
"streaming with split at position {} produces different output",
|
||||
split_pos
|
||||
);
|
||||
}
|
||||
}
|
||||
}
|
||||
Reference in new issue
Block a user