Updating tooling for jupytext + black break (#1191)

Author: jamesbraza

.pre-commit-config.yaml

@@ -25,14 +25,14 @@ repos:
       - id: mixed-line-ending
       - id: trailing-whitespace
   - repo: https://github.com/astral-sh/ruff-pre-commit
-    rev: v0.13.2
+    rev: v0.14.4
     hooks:
       - id: ruff-check
         args: [--fix, --exit-non-zero-on-fix]
   - repo: https://github.com/psf/black-pre-commit-mirror
-    rev: 25.9.0
+    rev: 25.11.0
     hooks:
-      - id: black
+      - id: black-jupyter
   - repo: https://github.com/rbubley/mirrors-prettier
     rev: v3.6.2
     hooks:
@@ -48,19 +48,19 @@ repos:
       - id: codespell
         additional_dependencies: [".[toml]"]
   - repo: https://github.com/crate-ci/typos
-    rev: v1.36.3
+    rev: v1.39.0
     hooks:
       - id: typos
   - repo: https://github.com/jumanjihouse/pre-commit-hooks
     rev: 3.0.0
     hooks:
       - id: check-mailmap
   - repo: https://github.com/henryiii/validate-pyproject-schema-store
-    rev: 2025.09.26
+    rev: 2025.11.04
     hooks:
       - id: validate-pyproject
   - repo: https://github.com/astral-sh/uv-pre-commit
-    rev: 0.8.22
+    rev: 0.9.8
     hooks:
       - id: uv-lock
   - repo: https://github.com/adamchainz/blacken-docs
@@ -74,19 +74,19 @@ repos:
       - id: nb-clean
         args: [--preserve-cell-outputs, --remove-empty-cells]
   - repo: https://github.com/jackdewinter/pymarkdown
-    rev: v0.9.32
+    rev: v0.9.33
     hooks:
       - id: pymarkdown
         exclude: docs/tutorials/
   - repo: https://github.com/mwouts/jupytext
-    rev: v1.17.3
+    rev: v1.18.1
     hooks:
       - id: jupytext
         args: [--to, md, --pipe, black]
-        additional_dependencies: [black]
+        additional_dependencies: [black<25.11.0] # Downpin for https://github.com/mwouts/jupytext/issues/1467
         files: ^docs/.*\.ipynb$
   - repo: https://github.com/jsh9/markdown-toc-creator
-    rev: 0.0.10
+    rev: 0.1.3
     hooks:
       - id: markdown-toc-creator
   - repo: local # Use local so we can inspect paperqa.version

README.md

@@ -16,6 +16,10 @@ question answering, summarization, and contradiction detection.
 
 <!--TOC-->
 
+---
+
+**Table of Contents**
+
 - [Quickstart](#quickstart)
   - [Example Output](#example-output)
 - [What is PaperQA2](#what-is-paperqa2)
@@ -56,6 +60,8 @@ question answering, summarization, and contradiction detection.
 - [Reproduction](#reproduction)
 - [Citation](#citation)
 
+---
+
 <!--TOC-->
 
 ## Quickstart

docs/tutorials/running_on_lfrqa.ipynb

@@ -361,7 +361,9 @@
     "os.makedirs(log_results_dir, exist_ok=True)\n",
     "\n",
     "\n",
-    "async def log_evaluation_to_json(lfrqa_question_evaluation: dict) -> None:  # noqa: RUF029\n",
+    "async def log_evaluation_to_json(  # noqa: RUF029\n",
+    "    lfrqa_question_evaluation: dict,\n",
+    ") -> None:\n",
     "    json_path = os.path.join(\n",
     "        log_results_dir, f\"{lfrqa_question_evaluation['qid']}.json\"\n",
     "    )\n",
@@ -409,7 +411,7 @@
     "\n",
     "\n",
     "if __name__ == \"__main__\":\n",
-    "    asyncio.run(evaluate())\n"
+    "    asyncio.run(evaluate())"
    ]
   },
   {
@@ -437,7 +439,7 @@
     "        data.append(json_data)\n",
     "\n",
     "results_df = pd.DataFrame(data).set_index(\"qid\")\n",
-    "results_df[\"winner\"].value_counts(normalize=True)\n"
+    "results_df[\"winner\"].value_counts(normalize=True)"
    ]
   }
  ],

docs/tutorials/running_on_lfrqa.md

@@ -5,7 +5,7 @@ jupyter:
       extension: .md
       format_name: markdown
       format_version: '1.3'
-      jupytext_version: 1.17.3
+      jupytext_version: 1.18.1
   kernelspec:
     display_name: .venv
     language: python
@@ -253,9 +253,9 @@ log_results_dir = os.path.join("data", "rag-qa-benchmarking", "results")
 os.makedirs(log_results_dir, exist_ok=True)
 
 
-async def log_evaluation_to_json(
+async def log_evaluation_to_json(  # noqa: RUF029
     lfrqa_question_evaluation: dict,
-) -> None:  # noqa: RUF029
+) -> None:
     json_path = os.path.join(
         log_results_dir, f"{lfrqa_question_evaluation['qid']}.json"
     )
@@ -306,7 +306,6 @@ if __name__ == "__main__":
     asyncio.run(evaluate())
 ```
 
-
 After running this, you can find the results in the `data/rag-qa-benchmarking/results` folder. Here is an example of how to read them:
 
 ```python

docs/tutorials/settings_tutorial.md

@@ -6,7 +6,7 @@ jupyter:
       extension: .md
       format_name: markdown
       format_version: '1.3'
-      jupytext_version: 1.17.3
+      jupytext_version: 1.18.1
   kernelspec:
     display_name: test
     language: python

pyproject.toml

@@ -135,6 +135,10 @@ skip = [
     "tests/stub_data/*",
 ]
 
+[tool.markdown_toc_creator]
+horizontal-rule-style = "prettier"
+proactive = false
+
 [tool.mypy]
 # Type-checks the interior of functions without type annotations.
 check_untyped_defs = true
@@ -220,7 +224,7 @@ max-line-length = 88  # Match ruff line-length
 # Files or directories matching the regular expression patterns are skipped.
 # The regex matches against base names, not paths. The default value ignores
 ignore-patterns = [
-    "version.py",  # setuptools-scm version files, SEE: https://github.com/pylint-dev/pylint/issues/10479
+    "^version\\.py$",  # Version files made by setuptools_scm, SEE: https://github.com/pylint-dev/pylint/issues/10479
 ]
 # Use multiple processes to speed up Pylint. Specifying 0 will auto-detect the
 # number of processors available to use, and will cap the count on Windows to
@@ -250,6 +254,7 @@ disable = [
     "global-statement",  # Rely on ruff PLW0603 for this
     "global-variable-not-assigned",  # Rely on ruff PLW0602 for this
     "import-outside-toplevel",  # Rely on ruff PLC0415 for this
+    "import-private-name",  # Rely on ruff PLC2701 for this
     "invalid-name",  # Don't care to enforce this
     "keyword-arg-before-vararg",  # Rely on ruff B026 for this
     "line-too-long",  # Rely on ruff E501 for this
@@ -289,7 +294,9 @@ disable = [
     "unused-argument",  # Rely on ruff ARG002 for this
     "unused-import",  # Rely on ruff F401 for this
     "unused-variable",  # Rely on ruff F841 for this
+    "unused-wildcard-import",  # Wildcard imports are convenient
     "use-sequence-for-iteration",  # Rely on ruff C0208 for this
+    "wildcard-import",  # Wildcard imports are convenient
     "wrong-import-order",  # Rely on ruff I001 for this
     "wrong-import-position",  # Rely on ruff E402 for this
 ]
@@ -367,11 +374,14 @@ preview = true
 explicit-preview-rules = true
 extend-select = [
     "ASYNC212",
+    "ASYNC240",
     "ASYNC250",
     "B901",
     "B903",
     "B909",
+    "B912",
     "CPY001",
+    "DOC102",
     "DOC201",
     "DOC202",
     "DOC402",
@@ -477,6 +487,7 @@ extend-select = [
     "RUF061",
     "RUF063",
     "RUF064",
+    "RUF065",
     "RUF102",
     "TC008",
     "UP042",
@@ -568,6 +579,7 @@ mypy-init-return = true
 [tool.ruff.lint.per-file-ignores]
 "**/tests/*.py" = [
     "N802",  # Tests function names can match class names
+    "PLC2701",  # Test can import private names if needed
     "PLR2004",  # Tests can have magic values
     "PLR6301",  # Test classes can ignore self
     "S101",  # Tests can have assertions

src/paperqa/agents/search.py

@@ -499,7 +499,8 @@ async def process_file(
 ) -> None:
 
     abs_file_path = (
-        pathlib.Path(settings.agent.index.paper_directory).absolute() / rel_file_path
+        pathlib.Path(settings.agent.index.paper_directory).absolute()  # noqa: ASYNC240
+        / rel_file_path
     )
     fallback_title = rel_file_path.name
     if settings.agent.index.use_absolute_paper_directory:

src/paperqa/clients/crossref.py

@@ -377,7 +377,7 @@ async def download_retracted_dataset(
             async for chunk in response.aiter_bytes(chunk_size=1024):
                 await f.write(chunk)
 
-        if os.path.getsize(str(retraction_data_path)) == 0:
+        if os.path.getsize(str(retraction_data_path)) == 0:  # noqa: ASYNC240
             raise RuntimeError("Retraction data is empty")
 
 

src/paperqa/contrib/openreview_paper_helper.py

@@ -122,7 +122,9 @@ async def _get_relevant_papers_chunk(self, question: str, chunk: str) -> list[An
 
     async def download_papers(self, submissions: list[Any]) -> None:
         """Download PDFs for given submissions."""
-        downloaded_papers = Path(self.settings.paper_directory).rglob("*.pdf")
+        downloaded_papers = Path(self.settings.paper_directory).rglob(  # noqa: ASYNC240
+            "*.pdf"
+        )
         downloaded_ids = [p.stem for p in downloaded_papers]
         logger.info("Downloading PDFs for relevant papers.")
         for submission in submissions:
@@ -151,7 +153,9 @@ async def aadd_docs(
     ) -> Docs:
         if docs is None:
             docs = Docs()
-        for doc_path in Path(self.settings.paper_directory).rglob("*.pdf"):
+        for doc_path in Path(self.settings.paper_directory).rglob(  # noqa: ASYNC240
+            "*.pdf"
+        ):
             sub = subs.get(doc_path.stem) if subs is not None else None
             if sub:
                 await docs.aadd(

tests/test_paperqa.py

@@ -61,7 +61,7 @@
 from paperqa.clients.journal_quality import JournalQualityPostProcessor
 from paperqa.core import (
     LLMContextTimeoutError,
-    _map_fxn_summary,  # noqa: PLC2701
+    _map_fxn_summary,
     llm_parse_json,
     map_fxn_summary,
 )