feat: add LaTeX (.tex, .bib) to readable and prose extensions

LaTeX source files and BibTeX bibliographies are prose-rich content that
benefits from both palace mining and entity detection. Adds the two
extensions to the two extension lists most relevant to them, each with a
matching test.

- ``mempalace/miner.py:READABLE_EXTENSIONS`` — ``.tex`` / ``.bib`` join the
  mining allowlist (parallel to the Swift/Kotlin PR #1368 and the PHP
  ecosystem PR #1819).

- ``mempalace/entity_detector.py:PROSE_EXTENSIONS`` — ``.tex`` / ``.bib``
  also join the *preferred* entity-detection bucket alongside ``.md`` /
  ``.rst`` / ``.csv``, NOT the broader code-file fallback. The reason
  ``PROSE_EXTENSIONS`` exists separately is documented in-code:
  programming-language files have lots of capitalized identifiers (class
  names, function names) that produce false-positive person matches.
  LaTeX/BibTeX don't have that problem — they're typesetting languages
  for prose documents. ``.bib`` in particular is almost entirely author
  names, one of the highest real-entity densities of any file type the
  detector scans.

Tests follow the patterns established by the prior extension PRs:
``tests/test_miner.py::test_scan_project_includes_latex_files`` mirrors
the Swift/Kotlin scan tests, and
``tests/test_entity_detector.py::test_scan_for_detection_includes_latex_prose``
mirrors ``test_scan_for_detection_finds_prose``. The existing
``test_prose_extensions`` was extended to assert the two new entries.

Full env-cleared suite: 3216 passed, 20 skipped. ``ruff check .`` and
``ruff format --check .`` both clean.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01KC5Qsknh2zFRtRvVyjXiTA

mempalace/entity_detector.py

@@ -215,6 +215,8 @@ PROSE_EXTENSIONS = {
     ".md",
     ".rst",
     ".csv",
+    ".tex",
+    ".bib",
 }
 
 READABLE_EXTENSIONS = {

mempalace/miner.py

@@ -133,6 +133,8 @@ READABLE_EXTENSIONS = {
     ".csv",
     ".sql",
     ".toml",
+    ".tex",
+    ".bib",
     # C# / .NET
     ".cs",
     ".csproj",

tests/test_entity_detector.py

@@ -531,6 +531,24 @@ def test_scan_for_detection_skips_git_dir(tmp_path):
     assert not any(".git" in f for f in file_strs)
 
 
+def test_scan_for_detection_includes_latex_prose(tmp_path):
+    # .tex and .bib are prose-heavy (author names, abstracts, citations) and
+    # belong in the preferred PROSE_EXTENSIONS bucket alongside .md / .rst,
+    # not the code-file fallback. .bib in particular is almost entirely
+    # author names — high entity density per byte.
+    (tmp_path / "paper.tex").write_text(
+        "\\documentclass{article}\\author{Leslie Lamport}\\begin{document}Body.\\end{document}"
+    )
+    (tmp_path / "refs.bib").write_text(
+        "@article{l86, author={Leslie Lamport}, title={LaTeX}, year={1986}}"
+    )
+    (tmp_path / "code.py").write_text("import os")
+    files = scan_for_detection(str(tmp_path))
+    extensions = {os.path.splitext(str(f))[1] for f in files}
+    assert ".tex" in extensions
+    assert ".bib" in extensions
+
+
 # ── module-level constants ──────────────────────────────────────────────
 
 
@@ -543,6 +561,8 @@ def test_stopwords_contains_common_words():
 def test_prose_extensions():
     assert ".txt" in PROSE_EXTENSIONS
     assert ".md" in PROSE_EXTENSIONS
+    assert ".tex" in PROSE_EXTENSIONS
+    assert ".bib" in PROSE_EXTENSIONS
 
 
 # ── _print_entity_list ─────────────────────────────────────────────────

tests/test_miner.py

@@ -349,6 +349,20 @@ def test_scan_project_includes_kotlin_files():
         ]
 
 
+def test_scan_project_includes_latex_files():
+    with tempfile.TemporaryDirectory() as tmpdir:
+        project_root = Path(tmpdir).resolve()
+        write_file(
+            project_root / "main.tex",
+            "\\documentclass{article}\n\\begin{document}\nHello, world.\n\\end{document}\n" * 20,
+        )
+        write_file(
+            project_root / "refs.bib",
+            "@article{lamport1986, author={Leslie Lamport}, title={LaTeX}, year={1986}}\n" * 20,
+        )
+        assert scanned_files(project_root) == ["main.tex", "refs.bib"]
+
+
 def test_scan_project_respects_gitignore():
     tmpdir = tempfile.mkdtemp()
     try: