Add judge-builder repo into sandbox for DBX Marketplace listing (#600)

As titled. This is nearly a direct copy of the existing `judge-builder`
repo here: https://github.com/databricks-solutions/judge-builder

Followed the guide for contributing
[here](https://github.com/databrickslabs/sandbox/blob/main/CONTRIBUTING.md).

- [x] Added code owners
- [x] Created the README in the expected format
- [x] Followed best practices for Databricks Apps on Marketplace
- [x] Completed a SDR (SDR-3817)

Author: smoorjani

CODEOWNERS

@@ -13,6 +13,7 @@ downstreams                @nfx @alexott
 feature-registry-app       @yang-chengg @mparkhe @mingyangge-db @stephanielu5
 go-libs                    @nfx @alexott
 ip_access_list_analyzer    @alexott
+judge-builder              @smoorjani @alkispoly-db
 ka-chat-bot                @taiga-db
 metascan                   @nfx @alexott
 runtime-packages           @nfx @alexott

judge-builder/.gitignore

@@ -0,0 +1,310 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*.pyc
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+develop-eggs/
+dist/
+# Note: client/build/ is checked in for Databricks Apps deployment
+downloads/
+eggs/
+.eggs/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/#use-with-ide
+.pdm.toml
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.env.local
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be added to the global gitignore or merged into this project gitignore.  For a PyCharm
+#  project, it is recommended to comment out the line below to share the project gitignore.
+.idea/
+
+# Node.js dependencies
+node_modules/
+npm-debug.log*
+yarn-debug.log*
+yarn-error.log*
+pnpm-debug.log*
+lerna-debug.log*
+
+# Runtime data
+pids
+*.pid
+*.seed
+*.pid.lock
+
+# Coverage directory used by tools like istanbul
+coverage/
+*.lcov
+
+# nyc test coverage
+.nyc_output
+
+# Grunt intermediate storage (https://gruntjs.com/creating-plugins#storing-task-files)
+.grunt
+
+# Bower dependency directory (https://bower.io/)
+bower_components
+
+# node-waf configuration
+.lock-wscript
+
+# Compiled binary addons (https://nodejs.org/api/addons.html)
+build/Release
+
+# Dependency directories
+jspm_packages/
+
+# Snowpack dependency directory (https://snowpack.dev/)
+web_modules/
+
+# TypeScript cache
+*.tsbuildinfo
+
+# Optional npm cache directory
+.npm
+
+# Optional eslint cache
+.eslintcache
+
+# Optional stylelint cache
+.stylelintcache
+
+# Microbundle cache
+.rpt2_cache/
+.rts2_cache_cjs/
+.rts2_cache_es/
+.rts2_cache_umd/
+
+# Optional REPL history
+.node_repl_history
+
+# Output of 'npm pack'
+*.tgz
+
+# Yarn Integrity file
+.yarn-integrity
+
+# dotenv environment variable files
+.env.development.local
+.env.test.local
+.env.production.local
+.env.local
+
+# parcel-bundler cache (https://parceljs.org/)
+.cache
+.parcel-cache
+
+# Next.js build output
+.next
+out
+
+# Nuxt.js build / generate output
+.nuxt
+dist
+
+# Gatsby files
+.cache/
+public
+
+# Vite build output
+dist
+dist-ssr
+*.local
+
+# Rollup build output
+dist/
+
+# Ruff 
+.ruff_cache/
+
+# Storybook build outputs
+.out
+.storybook-out
+storybook-static
+
+# Temporary folders
+tmp/
+temp/
+
+# Editor directories and files
+.vscode
+.vscode/*
+!.vscode/extensions.json
+.idea
+.DS_Store
+*.suo
+*.ntvs*
+*.njsproj
+*.sln
+*.sw?
+
+# OS generated files
+.DS_Store
+.DS_Store?
+._*
+.Spotlight-V100
+.Trashes
+ehthumbs.db
+Thumbs.db
+
+# Application specific
+mlruns/
+mlartifacts/
+
+# Databricks
+.databricks/
+
+# UV
+.uv/
+
+# Generated client
+client/src/client/
+
+# Generated requirements files (keep requirements.txt for deployment)
+dev-requirements.txt
+
+client/node_modules/
+client/package-lock.json
+.env.local
+tmp-deploy-logs.txt

judge-builder/CHANGELOG.md

@@ -0,0 +1,68 @@
+# CHANGELOG
+
+## 0.3.4 (2025-10-28)
+
+### Security Fixes
+
+- Fixed path traversal vulnerability in static file serving that could allow access to files outside the build directory
+- Restricted CORS middleware to development mode only (controlled by `DEPLOYMENT_MODE` environment variable)
+
+## 0.3.3 (2025-10-18)
+
+### Bug Fixes
+
+- Fixed alignment timeout issues in deployed environments by moving alignment to background tasks with polling
+
+## 0.3.2 (2025-10-17)
+
+### Improvements
+
+- Changed default alignment model back to databricks-hosted endpoint
+- Removed alignment model selector from judge creation form
+- Upgraded databricks-agents to >=1.8.0
+
+### Bug Fixes
+
+- Fixed duplicate traces being added to labeling sessions
+
+## 0.3.1 (2025-10-09)
+
+### Improvements
+
+- **Client Attribution**: Added monkey patch to set custom client name (`judge-builder-v{VERSION}`) in chat completions for better tracking and analytics
+
+## 0.3.0 (2025-10-03)
+
+### Features
+
+- **Alignment Model Selector**: Introduced a model selector for the alignment "teacher" model, allowing users to choose custom serving endpoints
+
+### Improvements
+
+- Made alignment limit clear with improved UI messaging about the 10-example requirement
+- Reduced logging bloat in judge builder and fixed watch.sh script
+- Fixed bug in iterative alignments where evaluations were not running on the full set of traces, causing incorrect cached results to be used
+
+## 0.2.1 (2025-09-24)
+
+### Improvements
+
+- Cache results of schema analysis to get potential output types
+
+## 0.2.0 (2025-09-23)
+
+### Features
+
+- **MLflow Integration**: Integrated `make_judge` and `align` functions from MLflow 3.4.0 for enhanced judge creation and alignment capabilities
+- **Expanded Judge Support**: Added support for judges over expectations or traces (e.g., correctness judges), extending beyond the original use cases
+- **Arbitrary Output Support**: Enhanced judge outputs to support arbitrary categorical values instead of being limited to just pass/fail binary outcomes
+
+### Improvements
+
+- Enhanced alignment visualization with improved metrics display and filtering options
+- Added version comparison indicators showing agreement/disagreement progression
+- Improved UI layout for better alignment results presentation
+
+## 0.1.0 (2025-08-26)
+
+Initial version of Judge Builder