docs: add comprehensive project documentation and development guidelines

[dcramer]

Summary

• Added comprehensive CLAUDE.md development guidelines with mandatory pre-development reading requirements
• Created detailed documentation covering architecture, testing, development workflow, and scorer examples
• Established clear code standards, validation checklists, and common implementation patterns

Test plan

• Documentation files are properly formatted
• All links and references are accurate
• Code examples follow established patterns
• Guidelines align with current codebase structure

🤖 Generated with Claude Code

[codecov]

Codecov Report

All modified and coverable lines are covered by tests ✅

Project coverage is 84.50%. Comparing base (a9b1873) to head (09d75eb).
Report is 1 commits behind head on main.

✅ All tests successful. No failed tests found.

Additional details and impacted files

@@           Coverage Diff           @@
##             main      #21   +/-   ##
=======================================
  Coverage   84.50%   84.50%           
=======================================
  Files           4        4           
  Lines         400      400           
  Branches      115      115           
=======================================
  Hits          338      338           
  Misses         62       62           

Flag	Coverage Δ
unittests	84.50% <ø> (ø)

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

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.

🚀 New features to boost your workflow:

• 📦 JS Bundle Analysis: Save yourself from yourself by tracking and limiting bundle sizes in JS merges.

[Copilot]

Pull Request Overview

A comprehensive addition of project documentation, including development guidelines, architecture, testing standards, scorer examples, and provider transformations, plus minor package.json formatting cleanup.

• Consolidated the files array in package.json into a single line.
• Added detailed documentation covering testing requirements, development workflows, architecture overview, scorer patterns, provider transformations, and custom scorer examples.
• Introduced a top-level CLAUDE.md with mandatory pre-development reading and repository guidelines.

Reviewed Changes

Copilot reviewed 8 out of 8 changed files in this pull request and generated 1 comment.

Show a summary per file

File	Description
package.json	Condensed the "files" array to a single-line format
docs/testing.md	Added comprehensive testing standards and templates
docs/scorer-examples.md	Provided multiple scorer implementation examples
docs/provider-transformations.md	Documented tool call transformation patterns for various LLM providers
docs/development-guide.md	Outlined setup, workflow, and scorer creation steps
docs/custom-scorers.md	Showcased built-in and custom scorer usage examples
docs/architecture.md	Described core architecture, data flow, and extension points
CLAUDE.md	Introduced mandatory development guidelines and checklist

Comments suppressed due to low confidence (2)

docs/custom-scorers.md:20

• [nitpick] Usage of ToolCallScorer() here is inconsistent with other examples that pass scorer functions directly (e.g., [ExactMatchScorer]). Standardize on one pattern (function reference vs invocation) to avoid confusion.

scorers: [ToolCallScorer()]

docs/testing.md:99

• The example expects an error message of 'Missing required parameter', but elsewhere the thrown error is 'Expected value is required'. Update the test or error message to align examples with actual implementation.

  }).rejects.toThrow('Missing required parameter')