fix: store tool calls structurally for proper API roundtripping

The agent would stop mid-task because native tool calls were stored as
inline JSON text in Message.content. When sent back to the Anthropic API
via convert_messages(), they went as plain text instead of structured
tool_use/tool_result blocks. The model would occasionally get confused
and emit text describing what it wanted to do instead of invoking the
tool mechanism.

Changes:
- Add MessageToolCall struct and tool_calls/tool_result_id fields to Message
- Add id field to core ToolCall struct to preserve provider tool call IDs
- Update Anthropic convert_messages() to emit tool_use and tool_result blocks
- Add ToolResult variant to AnthropicContent enum
- Store tool calls structurally in tool message construction (not inline JSON)
- Fix add_message() to preserve empty-content messages with tool_calls
- Fix check_duplicate_in_previous_message() to check structured tool_calls
- Generate valid IDs for JSON fallback tool calls (Anthropic pattern requirement)
- Update planner create_tool_message() to use structured tool calls

crates/g3-core/tests/tool_execution_test.rs

@@ -29,6 +29,7 @@ fn make_tool_call(tool: &str, args: serde_json::Value) -> ToolCall {
     ToolCall {
         tool: tool.to_string(),
         args,
+        id: String::new(),
     }
 }