fix: exclude TOC pages from pages_with_tables metadata

TOC detection routes through the table pipeline (detected as a table, then
formatted as a flat list with tab-aligned page numbers via
format_toc_as_list). That made TOC pages appear in LayoutComplexity's
pages_with_tables, which:

- Misleads downstream consumers that read this field as "this page has a
  data table".
- Trips the table-page guard in column detection, which switches to a
  different valley-detection threshold for table pages.

Add an is_table_of_contents check in compute_layout_complexity so TOC-shaped
detections don't count toward the table flag. The TOC still renders correctly
as a flat list — only the metadata classification changes.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

src/lib.rs

@@ -1782,19 +1782,29 @@ fn compute_layout_complexity(
                 markdown::filter_lines_to_band(lines, page, x_lo, x_hi)
             };
 
+            // TOC pages route through the table detector but render as flat
+            // lists. They aren't tables in any user-facing sense, so don't
+            // count them toward LayoutComplexity (would also trip the
+            // table-page guard in column detection below).
+            let has_real_table = |tables: &[tables::Table]| {
+                tables
+                    .iter()
+                    .any(|t| !tables::is_table_of_contents(&t.cells))
+            };
+
             let (rect_tables, _) = tables::detect_tables_from_rects(&band_items, &band_rects, page);
-            if !rect_tables.is_empty() {
+            if has_real_table(&rect_tables) {
                 found_table = true;
                 break;
             }
             let line_tables = tables::detect_tables_from_lines(&band_items, &band_lines, page);
-            if !line_tables.is_empty() {
+            if has_real_table(&line_tables) {
                 found_table = true;
                 break;
             }
             // Heuristic fallback for borderless tables
             let heuristic_tables = tables::detect_tables(&band_items, base_size, false);
-            if !heuristic_tables.is_empty() {
+            if has_real_table(&heuristic_tables) {
                 found_table = true;
                 break;
             }

src/tables/detect_heuristic.rs

@@ -581,8 +581,14 @@ fn detect_table_in_region(items: &[(usize, &TextItem)], mode: TableDetectionMode
     // Validation 1: some rows should have content in first column.
     // Use a lower threshold (25%) for tables with wrapped cells where
     // continuation lines leave the first column empty.
+    // Skip when cells form a narrow TOC pattern: hierarchical entries indented
+    // across multiple X levels leave the leftmost column sparse (only top-level
+    // chapters land there) but the structure is still a valid TOC. Narrow only
+    // (<=5 cols) — wide multi-column TOCs (e.g. 2-up indices) would render
+    // poorly through format_toc_as_list, which assumes one entry per row.
     let rows_with_first_col = cells.iter().filter(|row| !row[0].is_empty()).count();
-    if rows_with_first_col < rows.len() / 4 {
+    let is_narrow_toc = columns.len() <= 5 && is_table_of_contents(&cells);
+    if rows_with_first_col < rows.len() / 4 && !is_narrow_toc {
         log::debug!(
             "  validation 1 fail: {}/{} rows have first col",
             rows_with_first_col,
@@ -653,8 +659,12 @@ fn detect_table_in_region(items: &[(usize, &TextItem)], mode: TableDetectionMode
         return None;
     }
 
-    // Validation 8: Reject paragraph-like content falsely detected as tables
-    if is_paragraph_content(&cells) {
+    // Validation 8: Reject paragraph-like content falsely detected as tables.
+    // TOC pages with deep indentation (top-level chapters in col 0, subsections
+    // in cols 1-3, page numbers in last col) leave most cells empty and trip
+    // the paragraph heuristic; TOC shape is a safer signal here. Narrow only
+    // — see narrow-TOC rationale at validation 1.
+    if is_paragraph_content(&cells) && !is_narrow_toc {
         log::debug!("  validation 9 fail: paragraph content");
         return None;
     }
@@ -906,7 +916,7 @@ fn looks_like_number(s: &str) -> bool {
 /// Check if this looks like a Table of Contents (either style).
 ///
 /// Used by format.rs to render TOCs as flat lists instead of markdown tables.
-pub(super) fn is_table_of_contents(cells: &[Vec<String>]) -> bool {
+pub fn is_table_of_contents(cells: &[Vec<String>]) -> bool {
     is_dot_leader_toc(cells) || is_tabular_toc(cells)
 }
 
@@ -1601,6 +1611,62 @@ mod tests {
         );
     }
 
+    #[test]
+    fn is_table_of_contents_accepts_hierarchical_indented_toc() {
+        // Mythos system card pages 4-5: top-level chapters indent at col 0,
+        // subsections at cols 1-2, leaving col 0 mostly empty (only ~10% of
+        // rows). Validation 1 was rejecting these even though the structure
+        // is unambiguously a TOC.
+        let cells = vec![
+            vec!["Abstract".to_string(), String::new(), "3".to_string()],
+            vec![
+                "1 Introduction".to_string(),
+                String::new(),
+                "10".to_string(),
+            ],
+            vec![
+                String::new(),
+                "1.1 Model training".to_string(),
+                "11".to_string(),
+            ],
+            vec![
+                String::new(),
+                "1.1.1 Training data".to_string(),
+                "11".to_string(),
+            ],
+            vec![
+                String::new(),
+                "1.1.2 Crowd workers".to_string(),
+                "12".to_string(),
+            ],
+            vec![
+                String::new(),
+                "1.2 Release decision".to_string(),
+                "13".to_string(),
+            ],
+            vec![
+                "2 RSP evaluations".to_string(),
+                String::new(),
+                "16".to_string(),
+            ],
+            vec![
+                String::new(),
+                "2.1 RSP risk assessment".to_string(),
+                "16".to_string(),
+            ],
+            vec![String::new(), "2.1.1 Context".to_string(), "16".to_string()],
+            vec![
+                String::new(),
+                "2.2 CB evaluations".to_string(),
+                "20".to_string(),
+            ],
+        ];
+        assert!(
+            is_table_of_contents(&cells),
+            "hierarchical TOC with sparse col 0 should still be detected"
+        );
+    }
+
     #[test]
     fn is_table_of_contents_rejects_dotless_toc() {
         // Tabular TOC without leader dots: first column starts with dotted

src/tables/mod.rs

@@ -10,7 +10,7 @@ mod financial;
 mod format;
 mod grid;
 
-pub use detect_heuristic::detect_tables;
+pub use detect_heuristic::{detect_tables, is_table_of_contents};
 pub use detect_lines::detect_tables_from_lines;
 pub(crate) use detect_rects::cluster_rects;
 pub use detect_rects::{detect_tables_from_rects, RectHintRegion};