Open
Conversation
- Replace pytest-benchmark with pytest-codspeed in test dependencies - Rewrite benchmark tests to use @pytest.mark.benchmark decorator - Add full process lifecycle benchmark (init + run + destroy) - Parameterize benchmarks across AsyncioConnector and ZMQConnector - Replace GitHub Actions workflow with CodSpeed integration Co-authored-by: toby-coleman <13170610+toby-coleman@users.noreply.github.com> Agent-Logs-Url: https://github.com/plugboard-dev/plugboard/sessions/b8d70f1d-7f6f-412b-9452-e70611a349de
Copilot
AI
changed the title
[WIP] Enhance benchmarking tests using codspeed
ci: Improve benchmarking tests with CodSpeed
Mar 25, 2026
toby-coleman
requested changes
Mar 25, 2026
…tion - test_benchmark_process_run now uses benchmark.pedantic with setup to only time process.run(), excluding init - Added RayConnector/RayProcess to both benchmark test parametrizations - Added Ray env vars to CI workflow for benchmark tests Co-authored-by: toby-coleman <13170610+toby-coleman@users.noreply.github.com> Agent-Logs-Url: https://github.com/plugboard-dev/plugboard/sessions/2d017dc2-a948-4b46-8c61-c42be32507a4
Contributor
Author
|
Just as a heads up, I was blocked by some firewall rules while working on your feedback. Expand below for details. Warning Firewall rules blocked me from connecting to one or more addresses (expand for details)I tried to connect to the following addresses, but was blocked by firewall rules:
If you need me to access, download, or install something from one of these locations, you can either:
|
Congrats! CodSpeed is installed 🎉
You will start to see performance impacts in the reports once the benchmarks are run from your default branch.
|
Codecov Report✅ All modified and coverable lines are covered by tests. 📢 Thoughts on this report? Let us know! |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Replace
pytest-benchmarkwithpytest-codspeedfor benchmarking, extend test coverage to full process lifecycle, and parameterize across connector types.Changes
pyproject.toml: Swappytest-benchmark→pytest-codspeed>=4.3.0tests/benchmark/test_benchmarking.py:test_benchmark_process_run— benchmarks onlyprocess.run()(init excluded viabenchmark.pedanticwith setup)test_benchmark_process_lifecycle— benchmarks full init → run → destroy using@pytest.mark.benchmarkAsyncioConnector/LocalProcess,ZMQConnector/LocalProcess, andRayConnector/RayProcess.github/workflows/benchmarks.yaml: Replace manual checkout-both-branches-and-compare workflow withCodSpeedHQ/action@v4. Addspushtomainandworkflow_dispatchtriggers for baseline tracking and backtesting. Uses OIDC auth (id-token: write). AddsRAY_ENABLE_UV_RUN_RUNTIME_ENVandPLUGBOARD_IO_READ_TIMEOUTenv vars for Ray-based benchmarks.uv.lock: Updated to reflect dependency changeOriginal prompt
⚡ Quickly spin up Copilot coding agent tasks from anywhere on your macOS or Windows machine with Raycast.