docs: document input schema processing

[MQ37]

closes #43

[Copilot]

Pull Request Overview

This PR updates the documentation for how the Actor input schema is processed, ensuring that it complies with JSON Schema standards and outlines the new processing rules.

• Updated the description of schema processing steps, including description truncation, enum length limits, required field marking, nested property building, and array item type inference.
• Provides detailed bullet points for each processing step.

Comments suppressed due to low confidence (2)

README.md:370

• [nitpick] It’s unclear how this new 'combined length' limit relates to the previous limit of 50 options. A brief note or cross-reference could help clarify the change.

+- **Enum fields** are truncated to a maximum combined length of 200 characters for all elements (as defined in `ACTOR_ENUM_MAX_LENGTH`).

README.md:373

• [nitpick] The priority order for inferring array item types could benefit from additional clarification or punctuation to improve readability.

+- **Array item types** are inferred when not explicitly defined in the schema, using a priority order: explicit type in items > prefill type > default value type > editor type.

[jirispilka]

Thanks