* fix: Remove invalid colon in bash else statement
- Fix bash syntax error in auto-version workflow
- Remove Python-style colon from else statement
- Resolves exit code 127 in version bump determination
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
* feat: Add Docker build combinations for non-versioning prefixes
- Add support for prefix+docker combinations (docs+docker:, chore+docker:, etc.)
- Enable Docker build for non-versioning changes when requested
- Add repository_dispatch trigger for Docker workflow
- Update Docker tagging for PR-based builds (pr-X, main-sha)
- Update PR template with new prefix options
This allows contributors to force Docker builds for documentation,
maintenance, and other non-versioning changes when needed.
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
* docs: Add comprehensive PR prefix and automation documentation
- Update CONTRIBUTING.md with detailed PR prefix system explanation
- Add automation workflow documentation to docs/contributing/workflows.md
- Create new user-friendly contributing guide at docs/user-guides/contributing-guide.md
- Include Mermaid diagrams for workflow visualization
- Document Docker testing combinations and image tagging strategy
- Add best practices and common mistakes to avoid
This provides clear guidance for contributors on using the automated
versioning and Docker build system effectively.
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
---------
Co-authored-by: Patryk Ciechanski <patryk.ciechanski@inetum.com>
Co-authored-by: Claude <noreply@anthropic.com>
Major improvements to thinking capabilities and API integration:
- Remove all output token limits for future-proof responses
- Add 5-level thinking mode system: minimal, low, medium, high, max
- Migrate from google-generativeai to google-genai library
- Implement native thinkingBudget support for Gemini 2.5 Pro
- Set medium thinking as default for all tools, max for think_deeper
🧠 Thinking Modes:
- minimal (128 tokens) - simple tasks
- low (2048 tokens) - basic reasoning
- medium (8192 tokens) - default for most tools
- high (16384 tokens) - complex analysis
- max (32768 tokens) - default for think_deeper
🔧 Technical Changes:
- Complete migration to google-genai>=1.19.0
- Remove google-generativeai dependency
- Add ThinkingConfig with thinking_budget parameter
- Update all tools to support thinking_mode parameter
- Comprehensive test suite with 37 passing unit tests
- CI-friendly testing (no API key required for unit tests)
- Live integration tests for API verification
🧪 Testing & CI:
- Add GitHub Actions workflow with multi-Python support
- Unit tests use mocks, no API key required
- Live integration tests optional with API key
- Contributing guide with development setup
- All tests pass without external dependencies
🐛 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
