5 Commits

Author SHA1 Message Date
Florian BRUNIAUX 1d857914d6 feat: add local LLM analysis, filter improvements, and testing scripts
Add smart code analysis with local LLM integration (rtk smart command),
improve filter.rs formatting and readability, and add comprehensive
testing utilities.

Key changes:
- local_llm.rs: Ultra-compact code summaries for LLM contexts
- filter.rs: Better formatting, enhanced comment/docstring detection
- main.rs: Integrate smart command routing
- config.rs: Code formatting improvements
- .gitignore: Exclude claudedocs/ directory
- scripts/rtk-economics.sh: Token savings analysis
- scripts/test-all.sh: Comprehensive test runner
- scripts/test-aristote.sh: Project-specific test suite

Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
2026-02-02 08:43:19 +01:00
patrick szymkowiak b8bbfb87b4 Merge pull request #12 from FlorianBruniaux/feat/all-features
feat: CI/CD automation (versioning, benchmarks, README auto-update)
2026-01-29 16:54:50 +01:00
Florian BRUNIAUX 22c3017ed5 feat: add CI/CD automation (release management and automated metrics)
## Release automation
- Add release-please workflow for automatic semantic versioning
- Configure release.yml to only trigger on tags (avoid double-release)

## Benchmark automation
- Extend benchmark.yml with README auto-update
- Add permissions for contents and pull-requests writes
- Auto-create PR with updated metrics via peter-evans/create-pull-request
- Add scripts/update-readme-metrics.sh for CI integration

## Verification
- ✅ Workflows ready for CI/CD pipeline
- ✅ No breaking changes to existing functionality

Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
2026-01-29 16:45:17 +01:00
Florian BRUNIAUX b868987f6f feat: add Modern JS Stack commands to benchmark script
Add benchmarks for the 6 new commands in scripts/benchmark.sh:
- tsc: TypeScript compiler error grouping
- prettier: Format checker with file filtering
- lint: ESLint/Biome grouped violations
- next: Next.js build metrics extraction
- playwright: E2E test failure filtering
- prisma: Prisma CLI without ASCII art

All benchmarks are conditional (skip if tools not available or
not applicable to current project). Tests only run on projects
with package.json and relevant configuration files.

Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
2026-01-29 11:44:52 +01:00
Patrick szymkowiak 50f501c92a adding benchmark 2026-01-28 23:03:49 +01:00