Strip markdown decoration from model-emitted insight titles

Models wrap the title line despite the prompt — "**Title: A Day in the Woods**", "## Title: ...", bold around just the label — which made parse_title_body's bare "Title:" prefix match fall through to the fallbacks and leak asterisks into the stored title. strip_title_markdown trims bold/italic markers, heading hashes, backticks, and quotes from both ends; applied to the label line, the extracted title, both fallback paths, and generate_photo_title (which previously stripped only quotes). Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-06-11 22:18:43 -04:00
parent efd05db523
commit 3fa4fa8501
2 changed files with 54 additions and 13 deletions
@@ -33,30 +33,40 @@ use crate::utils::{earliest_fs_time, normalize_path};
 /// and labels the truncation via `found_header`.
 const LOCATION_HISTORY_DISPLAY_LIMIT: usize = 20;

+/// Strip common markdown decoration (bold/italic markers, heading hashes,
+/// backticks, quotes) from both ends of a model-emitted title. Models wrap
+/// the line despite the prompt: `**Title: A Day in the Woods**`,
+/// `## Title: ...`, `"..."`.
+pub(crate) fn strip_title_markdown(s: &str) -> &str {
+    s.trim_matches(|c: char| matches!(c, '*' | '_' | '`' | '#' | '"') || c.is_whitespace())
+}
+
 /// Parse a "Title: ...\n\n<body>" response into (title, body).
 /// Falls back to the first sentence as the title if the model didn't
 /// follow the format.
 pub(crate) fn parse_title_body(raw: &str) -> (String, String) {
    let trimmed = raw.trim();

-    // Try "Title: <title>\n\n<body>" or "Title: <title>\n<body>"
-    if let Some(rest) = trimmed
+    // Try "Title: <title>\n<body>", tolerating markdown decoration around
+    // the title line.
+    let (first_line, rest) = match trimmed.find('\n') {
+        Some(pos) => (&trimmed[..pos], trimmed[pos..].trim()),
+        None => (trimmed, ""),
+    };
+    let first_line = strip_title_markdown(first_line);
+    if let Some(t) = first_line
        .strip_prefix("Title:")
-        .or_else(|| trimmed.strip_prefix("title:"))
+        .or_else(|| first_line.strip_prefix("title:"))
    {
-        let rest = rest.trim_start();
-        if let Some(split_pos) = rest.find("\n\n").or_else(|| rest.find('\n')) {
-            let title = rest[..split_pos].trim();
-            let body = rest[split_pos..].trim();
-            if !title.is_empty() && !body.is_empty() {
-                return (title.to_string(), body.to_string());
-            }
+        let title = strip_title_markdown(t);
+        if !title.is_empty() && !rest.is_empty() {
+            return (title.to_string(), rest.to_string());
        }
    }

    // Fallback: first sentence (up to first `. ` or `.\n`) becomes the title
    if let Some(pos) = trimmed.find(". ").or_else(|| trimmed.find(".\n")) {
-        let title = &trimmed[..pos];
+        let title = strip_title_markdown(&trimmed[..pos]);
        let body = trimmed[pos + 1..].trim();
        if title.len() <= 100 && !body.is_empty() {
            return (title.to_string(), body.to_string());
@@ -65,7 +75,7 @@ pub(crate) fn parse_title_body(raw: &str) -> (String, String) {

    // Last resort: truncate to 60 chars for title, full text as body
    let title: String = trimmed.chars().take(60).collect();
-    let title = title.trim_end().to_string();
+    let title = strip_title_markdown(title.trim_end()).to_string();
    (title, trimmed.to_string())
 }

@@ -5126,6 +5136,28 @@ mod tests {
        assert_eq!(b, "Everyone gathered...");
    }

+    #[test]
+    fn parse_title_body_strips_bold_wrapper() {
+        let (t, b) = parse_title_body("**Title: A Day in the Woods**\n\nWe hiked the ridge trail.");
+        assert_eq!(t, "A Day in the Woods");
+        assert_eq!(b, "We hiked the ridge trail.");
+    }
+
+    #[test]
+    fn parse_title_body_strips_bold_label_only() {
+        // Bold around just the label: "**Title:** X"
+        let (t, b) = parse_title_body("**Title:** Garden Party\n\nEveryone gathered...");
+        assert_eq!(t, "Garden Party");
+        assert_eq!(b, "Everyone gathered...");
+    }
+
+    #[test]
+    fn parse_title_body_strips_heading_hashes() {
+        let (t, b) = parse_title_body("## Title: Morning Walk\nThe sun was rising...");
+        assert_eq!(t, "Morning Walk");
+        assert_eq!(b, "The sun was rising...");
+    }
+
    #[test]
    fn parse_title_body_fallback_first_sentence() {
        let (t, b) = parse_title_body("A warm summer day. We gathered at the park for a picnic.");
@@ -548,7 +548,16 @@ Capture the key moment or theme. Return ONLY the title, nothing else."#,
        let title = self
            .generate_with_images(&prompt, Some(system), None)
            .await?;
-        Ok(title.trim().trim_matches('"').to_string())
+        // Models decorate despite "Return ONLY the title": quotes, bold
+        // markers, sometimes a "Title:" label.
+        use crate::ai::insight_generator::strip_title_markdown;
+        let cleaned = strip_title_markdown(title.trim());
+        let cleaned = cleaned
+            .strip_prefix("Title:")
+            .or_else(|| cleaned.strip_prefix("title:"))
+            .map(strip_title_markdown)
+            .unwrap_or(cleaned);
+        Ok(cleaned.to_string())
    }

    /// Generate a summary for a single photo based on its context