feat(chunks): aggiunge parser.py con markdown-it-py

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

chunks/parser.py

@@ -0,0 +1,16 @@
+from __future__ import annotations
+from markdown_it import MarkdownIt
+from markdown_it.token import Token
+
+
+def parse(source: str) -> tuple[list[Token], list[str]]:
+    """Parsa Markdown in token stream con source map.
+
+    Returns:
+        tokens: lista Token con .map = [start_line, end_line] (0-indexed, end escluso)
+        lines:  righe sorgente (0-indexed) per ricostruzione testo esatto
+    """
+    md = MarkdownIt().enable("table")
+    tokens = md.parse(source)
+    lines = source.splitlines()
+    return tokens, lines