fix: improve first-run indexing diagnostics

[Helweg]

Summary

Fixes the confusing first-run indexing failure reported in issue #58 by making auto provider selection safer and surfacing failed embedding batches directly in tool output.

Changes

• prefer GitHub Copilot before other built-in providers during embeddingProvider: \"auto\" detection
• switch the built-in Google default model to gemini-embedding-001, which matches the Gemini API path used by the provider
• expose failed embedding batch warnings and failed-batches path in index_codebase / index_status

Testing

How were these changes tested?

• Unit tests added/updated
• Manual testing performed
• Build passes (npm run build)
• Typecheck passes (npm run typecheck)
• Tests pass (npm run test:run)
• Lint passes (npm run lint)

Release Labels

• Added at least one release category label (feature, bug, performance, documentation, dependencies, refactor, test, chore, or skip-changelog)
• Added at most one semver label (semver:major, semver:minor, semver:patch) when needed

Related Issues

Fixes #58