fix(wiki): exclude URL-shaped bibkeys from claim parsing

_parse_claims now skips matches where bibkey contains spaces or starts
with "http", preventing Markdown hyperlinks like [text](https://...) from
being misidentified as citations. Add two tests.

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

tests/wiki/test_compile.py

@@ -121,6 +121,20 @@ def test_parse_claims_multiple() -> None:
     assert len(claims) == 2
 
 
+def test_parse_claims_ignores_markdown_links() -> None:
+    """Markdown hyperlinks like [text](https://example.com) are NOT parsed as claims."""
+    md = "See the [related work](https://example.com) for details."
+    claims = _parse_claims(md)
+    assert claims == []
+
+
+def test_parse_claims_ignores_multi_word_bibkey() -> None:
+    """Multi-word 'bibkeys' (spaces inside) are not treated as real citations."""
+    md = "Some text [not a bibkey here] and more."
+    claims = _parse_claims(md)
+    assert claims == []
+
+
 # ---------------------------------------------------------------------------
 # _run_grounding_guard
 # ---------------------------------------------------------------------------