Created GitHub CI from GitLab CI. #4
Conversation
There was a problem hiding this comment.
Pull request overview
Adds a GitHub Actions CI workflow intended to mirror the existing GitLab CI pipeline for this repo.
Changes:
- Introduces a multi-job GitHub Actions workflow to build/install the package and validate imports.
- Adds formatting, docs build, unit tests, script-based tests, and coverage generation jobs.
- Uploads artifacts for formatter output, docs site, and coverage reports.
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
.github/workflows/ci.yml
Outdated
| continue-on-error: true | ||
| steps: |
There was a problem hiding this comment.
continue-on-error: true at the job level will mark the job successful for any failure (including tool installation/network errors), which is broader than the GitLab behavior (allow failure only for formatter/lint findings). Consider removing job-level continue-on-error and instead handling the formatter exit code in the script so only the expected “lint errors” exit code is allowed while other non-zero exit codes fail the job.
.github/workflows/ci.yml
Outdated
| source .venv/bin/activate | ||
| pip install --upgrade hatch | ||
| pip install --upgrade hatch-mkdocs | ||
| (hatch fmt | tee fmt.out && echo "lint_errors 0" > metrics.txt) || (cat fmt.out | grep -e 'Found .* errors' | sed 's/Found \(.*\) errors.*/lint_errors \1/' > metrics.txt) |
There was a problem hiding this comment.
This uses hatch fmt | tee fmt.out but doesn’t enable pipefail. In GitHub Actions, tee returning 0 can mask a non-zero hatch fmt exit code, causing formatting failures to be treated as success and lint_errors 0 to be written. Add set -o pipefail (or capture PIPESTATUS[0]) so the formatter failure is detected reliably.
| python -m venv --upgrade-deps .venv | ||
| source .venv/bin/activate | ||
| pip install . | ||
| python -c "import chathpc.app; print(chathpc.app.__doc__)" |
There was a problem hiding this comment.
pip install . will attempt to install project dependencies. The current pyproject.toml includes a git+ssh://[email protected]/... dependency (codellama), which generally fails on GitHub-hosted runners unless an SSH key/agent is configured. To make this CI runnable for contributors/forks, either switch that dependency to HTTPS (preferred) or add an SSH setup step (e.g., ssh-agent with a deploy key) before installing.
| python -m venv --upgrade-deps .venv | ||
| source .venv/bin/activate | ||
| pip install . | ||
| ./scripts/test_commands.sh |
There was a problem hiding this comment.
Same issue as the Build job: this pip install . will try to resolve the git+ssh://... dependency (codellama) and can fail on GitHub runners without SSH credentials. Consider switching the dependency to HTTPS or configuring SSH before installing.
☂️ Python Coverage
Overall Coverage
New FilesNo new covered files... Modified FilesNo covered modified files...
|
Test Results29 tests 29 ✅ 4s ⏱️ Results for commit 6633b03. ♻️ This comment has been updated with latest results. |
…g and output formatting
- Add permissions for writing to pull requests - Add sticky PR comments for format check results - Add coverage summary to step summary with percentage calculation
Format resultsMetrics Formatter output (last 200 lines) |
No description provided.