Studio: strip invalid document citations that contain brackets

The invalid-citation regex stopped at the first closing bracket, so a
citation whose filename contained brackets left its tail (".pdf, p. 9]") in
the report. Match a balanced bracketed span so the whole invalid citation is
removed; valid citations stay protected by the earlier tokenization pass.

studio/backend/core/research_runs.py

@@ -42,7 +42,7 @@ _SOURCES_HEADING = re.compile(
 _NUMBERED_CITATION = re.compile(r"(?<!\^)\[(\d+)]")
 _AUTOLINK = re.compile(r"<(https?://[^>\s]+)>")
 _RAW_URL = re.compile(r"https?://[^\s<>]+")
-_DOCUMENT_CITATION = re.compile(r"\[Document:[^\]]+\]")
+_DOCUMENT_CITATION = re.compile(r"\[Document:(?:[^\[\]]+|\[[^\[\]]*\])*\]")
 # Wrapper delimiters used in the decision/synthesis prompts. Any occurrence inside
 # untrusted evidence is escaped so gathered content cannot close a block early.
 _PROMPT_DELIMITER_TAGS = re.compile(

studio/backend/tests/test_research_runs_hardening.py

@@ -111,6 +111,16 @@ def test_document_citation_strips_unknown_source():
     assert "not-a-real-file" not in out
 
 
+def test_document_citation_strips_unknown_source_with_brackets():
+    # An invalid citation whose filename contains brackets must be removed whole; the old regex
+    # stopped at the first ``]`` and left the tail (".pdf, p. 9]") behind.
+    report = "Ghost cite [Document: invented [final].pdf, p. 9] end."
+    out = _validate_report_document_sources(report, [{"filename": "real.pdf", "page": 1}])
+    assert "invented" not in out
+    assert ".pdf" not in out
+    assert out == "Ghost cite  end."
+
+
 def _make_payload(**overrides) -> CreateResearchRun:
     payload = {"threadId": "t1", "userMessageId": "u1", "inferenceRequest": {"model": "m"}}
     payload.update(overrides)