chore(bench): wire make bench, add pytest-benchmark, record baseline

[plind-junior]

the benchmark suite was implemented but unrunnable out of the box: pytest-benchmark wasn't in the [dev] extras, and the bench_*.py filenames don't match pytest's default python_files glob, so the documented invocation collected zero tests.

• add pytest-benchmark to the [dev] optional-dependencies
• add a make bench target that folds in the python_files override
• record the first baseline (medians at 1k/10k) in benchmarks/README.md and flip its status from "not implemented yet" to implemented
• gitignore the bench.json / .benchmarks run artifacts

What changed

Why

What might break

VEP

Tests

• make check passes locally (lint + mypy + pytest)
• New / changed behaviour has a test
• CHANGELOG.md updated under ## [Unreleased]

[coderabbitai]

Important

Review skipped

Auto reviews are disabled on base/target branches other than the default branch.

Please check the settings in the CodeRabbit UI or the .coderabbit.yaml file in this repository. To trigger a single review, invoke the @coderabbitai review command.

⚙️ Run configuration

Configuration used: defaults

Review profile: CHILL

Plan: Pro Plus

Run ID: 2ae3b3d8-ac91-4985-b18e-03a8dbd9792a

You can disable this status message by setting the reviews.review_status to false in the CodeRabbit configuration file.

Use the checkbox below for a quick retry:

• 🔍 Trigger review

✨ Finishing Touches

🧪 Generate unit tests (beta)

• Create PR with unit tests
• Commit unit tests in branch chore/benchmarks

---

Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out.

❤️ Share

• X
• Mastodon
• Reddit
• LinkedIn

_{Comment @coderabbitai help to get the list of available commands.}

[Copilot]

Pull request overview

This PR makes the existing benchmark suite runnable out of the box. Previously the suite couldn't be executed as documented: pytest-benchmark was missing from the [dev] extras, and the bench_*.py filenames don't match pytest's default python_files glob, so the documented invocation collected zero tests. The change wires up tooling and records a first baseline, fitting under the 0.3 "operational maturity" milestone in ROADMAP.md.

Changes:

• Add pytest-benchmark>=5,<6 to the [dev] optional dependencies.
• Add a make bench target (with the python_files collection override and JSON output), and update .PHONY, help text, and clean.
• Update benchmarks/README.md to mark the suite implemented and record baseline medians; gitignore bench.json and .benchmarks/.

Reviewed changes

Copilot reviewed 3 out of 4 changed files in this pull request and generated 3 comments.

File	Description
pyproject.toml	Adds pytest-benchmark to the [dev] extras so benchmarks install with dev setup.
Makefile	Adds a bench target with the required python_files override, plus help/.PHONY/clean updates.
benchmarks/README.md	Flips status to implemented and records a baseline; however the invocation section still describes the pre-PR state and contradicts these changes, and the recorded version (vouch 1.0.0) doesn't match the project version 0.0.1.
.gitignore	Ignores benchmark run artifacts (bench.json, .benchmarks/).

The Makefile, pyproject.toml, and .gitignore changes are consistent with each other. The remaining concerns are documentation inconsistencies in benchmarks/README.md where the newly-added text still says pytest-benchmark isn't in [dev] and that make bench isn't wired (both fixed by this PR), and the baseline environment references a nonexistent vouch 1.0.0.

---

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

[plind-junior]

@copilot resolve the merge conflicts in this pull request

[Copilot]

@copilot resolve the merge conflicts in this pull request

Resolved by merging origin/test into this branch and fixing the Makefile conflict in commit dd6529b.