Release 0.1.2

[jonpspri]

Release 0.1.2

This release focuses on improved test coverage and release infrastructure improvements.

Summary

• Test Coverage: 88.61% → 89.05%
• New Tests: 26 additional unit tests
• Release Infrastructure: Automated packaging validation

Test Coverage Improvements

Coverage Increases

• _version.py: 71.43% → 100% (+28.57%)
• exceptions.py: 83.67% → 100% (+16.33%)
• data_session.py: 81.25% → 100% (+18.75%)

New Tests Added (26 tests)

Exception Classes (16 tests)

• DatabeakError.to_dict() serialization tests
• SessionExpiredError constructor and validation
• InvalidRowIndexError with and without max_index
• File errors: DataBeakFileNotFoundError, FilePermissionError, FileFormatError
• Operation errors: InvalidOperationError
• Parameter errors: InvalidParameterError, MissingParameterError

Data Session (6 tests)

• validate_data_loaded() error path (NoDataLoadedError)
• get_basic_stats() error path (NoDataLoadedError)
• get_data_info() error path (NoDataLoadedError)
• clear_data() functionality
• Success paths for validation methods

Version Handling (4 tests)

• Version string format validation
• Semver regex pattern matching

Release Infrastructure

Packaging Validation

• New Script: tests/packaging/test_packaged_version.sh
  • Validates version consistency between pyproject.toml and installed package
  • Tests actual wheel file by running get_server_info via MCP client
  • Validates three-part semver format (MAJOR.MINOR.PATCH)
  • Prevents version mismatches before deployment

CI/CD Integration

• Updated .github/workflows/publish.yml:
  • Installs test dependencies (jq, mcp-client-cli)
  • Runs packaging validation before PyPI publish
  • Ensures package integrity

Developer Tooling

• Added .claude/commands/release-prep.md slash command
  • Automates release preparation workflow
  • Guides through version updates, CHANGELOG, and PR creation

Code Simplification

Version Handling

• Simplified _version.py by removing PackageNotFoundError fallback
• Reduced from 7 to 4 statements
• Package metadata always available in deployment environments

Changes Since 0.1.1

Pull Requests Merged:

• test: improve test coverage and add release validation #128: test: improve test coverage and add release validation
• Remove dynamic version control from build process #127: Remove dynamic version control from build process

Test Results

969 passed, 1 skipped in 33.37s
Required test coverage of 80.0% reached. Total coverage: 89.05%

All quality checks passing:

• ✅ ruff (46 rules)
• ✅ mypy (strict mode)
• ✅ pre-commit hooks
• ✅ packaging validation

Files Changed

• pyproject.toml: Version bump to 0.1.2
• CHANGELOG.md: Release notes for 0.1.2
• .github/workflows/publish.yml: Added packaging validation step
• tests/packaging/test_packaged_version.sh: New packaging test script

🤖 Generated with Claude Code

[codecov]

Codecov Report

✅ All modified and coverable lines are covered by tests.
✅ Project coverage is 87.66%. Comparing base (584418d) to head (d09dbf9).
⚠️ Report is 1 commits behind head on main.

Additional details and impacted files

@@           Coverage Diff           @@
##             main     #129   +/-   ##
=======================================
  Coverage   87.66%   87.66%           
=======================================
  Files          27       27           
  Lines        3251     3251           
  Branches      485      485           
=======================================
  Hits         2850     2850           
  Misses        281      281           
  Partials      120      120           

Flag	Coverage Δ
unittests	87.66% <ø> (ø)

Flags with carried forward coverage won't be shown. Click here to find out more.

---

Continue to review full report in Codecov by Sentry.

Legend - Click here to learn more
Δ = absolute <relative> (impact), ø = not affected, ? = missing data
Powered by Codecov. Last update 584418d...d09dbf9. Read the comment docs.

🚀 New features to boost your workflow:

• ❄️ Test Analytics: Detect flaky tests, report on failures, and find test suite problems.

[Copilot]

Pull Request Overview

Release 0.1.2 focuses on incrementally improving test coverage, simplifying version handling, and adding automated packaging/version validation to the release workflow.

• Added packaging integrity script and CI workflow steps to verify semantic version consistency.
• Expanded unit tests for exception classes and data session behaviors; simplified version retrieval logic.
• Bumped project version to 0.1.2 and updated changelog and release tooling documentation.

Reviewed Changes

Copilot reviewed 10 out of 10 changed files in this pull request and generated 1 comment.

Show a summary per file

File	Description
tests/unit/test_exceptions.py	Adds comprehensive tests for exception classes (constructors, serialization, and detailed variants).
tests/unit/models/test_data_session.py	Adds success and error-path tests for data session methods (except missing success test for get_data_info).
tests/unit/models/test_config_validation.py	Updates version tests to align with simplified version module (fallback removed).
tests/packaging/test_packaged_version.sh	New script enforcing semantic version format and packaged version consistency.
src/databeak/server.py	Passes package version into FastMCP server initialization.
src/databeak/_version.py	Removes fallback logic; now directly retrieves version via importlib.metadata.
pyproject.toml	Bumps project version to 0.1.2.
CHANGELOG.md	Adds 0.1.2 release entry (date ordering issue present).
.github/workflows/publish.yml	Adds Go setup and packaged version validation step prior to publication.
.claude/commands/release-prep.md	Adds release preparation automation instructions.

Comments suppressed due to low confidence (1)

src/databeak/_version.py:1

• Removing the previous PackageNotFoundError fallback introduces an import-time hard failure if the code is executed from a source checkout before installation (e.g., running scripts directly without an editable install). Consider either (a) restoring a minimal try/except that raises a clearer custom error message guiding the user to install the package, or (b) deferring version resolution to a function to avoid side effects at import time.

"""Version information for DataBeak."""

---

_{Tip: Customize your code reviews with copilot-instructions.md. Create the file or learn how to get started.}

[Copilot]

The 0.1.2 release date (2025-01-07) precedes the later-listed 0.1.1 date (2025-10-06), creating a chronological inconsistency. Update the dates or ordering so versions progress forward in time.

[claude]

Code Review: Release 0.1.2

This release shows solid engineering practices with improved test coverage and release infrastructure.

Strengths

Test Coverage Improvements

• Comprehensive exception testing (16 tests covering all error classes)
• Good coverage of error paths in DataSession
• Achieved 100% coverage on _version.py, exceptions.py, and data_session.py
• Overall coverage: 88.61% to 89.05%

Release Infrastructure

• test_packaged_version.sh provides valuable pre-deployment validation
• CI integration prevents version mismatches before PyPI publication
• Automated testing of actual wheel files is pragmatic

Issues and Concerns

1. Version Module Risk (Medium Priority)

The simplified _version.py removes the PackageNotFoundError fallback. This will raise exceptions when running from source without editable install, during IDE imports, or in development tools.

Recommendation: Either document the requirement for editable install OR restore the fallback with a development-appropriate version.

2. Shell Script Fragility (Low Priority)

test_packaged_version.sh line 17-19 uses complex piping without intermediate error checking. Consider adding explicit error validation between pipeline stages.

3. Test Quality

tests/unit/test_exceptions.py could test edge cases like to_dict() on subclasses with additional fields.

tests/unit/models/test_data_session.py could test get_basic_stats() with edge cases (empty DataFrame, all-null columns).

Minor Issues

1. CHANGELOG Date: Lists 2025-01-07 but current date is 2025-10-07 (likely typo)
2. Semver regex enforces strict three-part versioning, preventing pre-release versions

Overall Assessment

Recommendation: Approve with minor fixes

Priority Fixes:

1. Document editable install requirement OR restore version fallback
2. Consider shell script error handling improvements

Nice to Have:

• Fix CHANGELOG date if needed
• Add edge case tests

---

Generated by Claude Code

[claude]

Code Review: Release 0.1.2

Summary

This release PR is well-structured with focused scope on test coverage improvements and release infrastructure. Changes are minimal (version bump + CHANGELOG), appropriate since actual work was merged in #127 and #128.

Strengths

1. Release Infrastructure Quality

• Proper bash error handling in packaging script
• Semver validation with regex pattern matching
• End-to-end testing of actual wheel file via MCP client
• Clear error messages

2. CI/CD Integration

• Proper sequence: build → validate → test wheel → publish
• Prevents version mismatches from reaching PyPI
• Installs required tooling for validation

3. CHANGELOG Quality

• Follows Keep a Changelog format
• Proper semantic categorization
• Specific metrics and PR references

4. Release Workflow

• Slash command codifies release process

Issues and Concerns

CRITICAL: Date Inconsistency in CHANGELOG

CHANGELOG shows: [0.1.2] - 2025-01-07

This appears to be January 7, 2025, but PR merge timestamps show:

• PR test: improve test coverage and add release validation #128 merged: 2025-10-07 (October 7, 2025)
• PR Remove dynamic version control from build process #127 merged: 2025-10-06 (October 6, 2025)

Recommendation: Fix date from 2025-01-07 to 2025-10-07 (or actual release date).

Minor Issues

1. Missing Test Verification: PR claims 26 new tests but does not show which files. Acceptable since tests are in test: improve test coverage and add release validation #128, but consider linking to those results.

2. Version Links in CHANGELOG: Missing comparison links at bottom of file per Keep a Changelog best practices.

Security, Performance, Quality

✅ Security: No concerns - no credential handling, uses OIDC trusted publishing, read-only test operations

✅ Performance: Minimal impact - packaging validation adds ~10-30s to CI (acceptable)

✅ Code Quality: Meets all project standards - follows CLAUDE.md, semantic versioning, proper git workflow

✅ Testing: Coverage 88.61% → 89.05%, exceeds 80% minimum, 969 tests passing

Recommendations

Must Fix Before Merge:

1. Correct CHANGELOG date from 2025-01-07 to 2025-10-07

Nice to Have:

1. Add version comparison links at bottom of CHANGELOG.md
2. Consider git tag creation in release workflow
3. Document rollback procedure

Approval Status

⚠️ CONDITIONAL APPROVAL - pending CHANGELOG date correction.

Once date is fixed, release is ready to merge and publish.

---

Review per CLAUDE.md standards

[claude]

Code Review: Release 0.1.2

Summary Assessment

This is a solid maintenance release focused on test coverage improvements and release infrastructure hardening. The changes align with the project's quality standards documented in CLAUDE.md.

Strengths

1. Release Infrastructure Improvements

• The packaging validation script addresses a real gap in the deployment pipeline
• Version consistency validation between pyproject.toml and the built wheel prevents deployment mismatches
• Semver format validation with regex pattern matching provides early error detection

2. Test Coverage Gains

• Meaningful coverage improvements on critical modules (89.05% overall, up from 88.61%)
• Exception handling coverage now at 100% - reduces risk of silent failures
• Data session error paths now properly tested

Issues and Concerns

1. Shell Script Robustness (tests/packaging/test_packaged_version.sh:17-19)
The packaging test has a potential failure mode when the wheel file doesn't exist. If the wheel file path is incorrect, the command will fail with unclear error output. The wheel filename assumes py3-none-any architecture, which could break if build configuration changes.

Recommendation: Add explicit file existence check before attempting to use the wheel.

2. CI/CD Workflow Dependency Management (.github/workflows/publish.yml:39-43)
The workflow installs mcptools using a specific version tag (v0.7.1) but doesn't handle installation failures gracefully. No error handling if go install fails due to network issues. Symbolic link creation could fail if mcpt already exists from cache.

Recommendation: Add error handling and cache awareness with conditional installation check.

3. CHANGELOG Date Format (CHANGELOG.md:10)
The date 2025-10-07 appears to be a typo - should likely be 2024-10-07.

Security Review

Positive: The workflow uses trusted publishing with OIDC (id-token: write), which is the recommended secure approach for PyPI publishing. The shell script uses bash -eu with set -o pipefail - good defensive scripting practices.

Recommendations Priority

1. High: Fix shell script wheel path validation (prevents cryptic CI failures)
2. Medium: Add error handling to mcptools installation (improves CI reliability)
3. Low: Correct CHANGELOG date if typo (documentation accuracy)

Approval Recommendation

Conditional Approval - The release infrastructure improvements provide real value, but the shell script robustness issue should be addressed before merging to prevent future debugging pain when CI fails mysteriously. The test coverage improvements are solid, and the CHANGELOG is well-documented.