feat: add custom provider batch size caps

[Helweg]

Summary

Add custom provider request batch-size caps so OpenAI-compatible endpoints with strict per-request input limits, such as text-embeddings-inference, can be used without rejecting larger indexer batches.

Changes

• add customProvider.maxBatchSize support and accept max_batch_size as a config alias
• split custom provider /embeddings requests into smaller sequential calls while preserving existing indexer token batching
• add config/provider tests and update README usage docs

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)

Additional targeted verification:

• npx vitest run tests/custom-provider.test.ts
• npx vitest run tests/config.test.ts
• npx vitest run tests/embeddings.test.ts

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 #39