Single-element lists like [1] were being incorrectly unwrapped to "1"
in unstructured content while multi-element lists remained as lists.
This created inconsistent behavior where the structure was lost for
single items.
This fix ensures lists always preserve their structure in unstructured
content regardless of length, making behavior consistent and predictable.
Also removes pretty-printing from JSON serialization for more compact
output across tools, prompts, and resources.
Fixes#1064🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
Implements comprehensive notification system for tools, resources, and prompts with automatic client updates and flexible message handlers.
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Add pydantic_core.to_json() serialization for non-string prompt arguments
- Update type annotations to accept dict[str, Any] instead of dict[str, str]
- Add focused tests covering specific scenarios:
* Client always serializes non-string args regardless of server types
* Integration with server-side type conversion
* Client serialization error with specific PydanticSerializationError
* Server deserialization error with specific McpError match
This ensures MCP protocol compliance while maintaining developer experience
with typed arguments.
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
Added comprehensive elicitation support including:
- Client-side handler infrastructure following sampling pattern
- Server-side Context.elicit() method with type safety and validation
- Support for primitive types (str, int, float, bool) with automatic wrapping
- Support for dataclasses and other complex types
- Pattern matching with AcceptedElicitation, DeclinedElicitation, CancelledElicitation
- Comprehensive atomic test coverage for all scenarios
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
