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-planner/tests/planner_test.rs

@@ -9,9 +9,10 @@ fn test_create_tool_message_format() {
 
     assert!(matches!(msg.role, MessageRole::Assistant));
 
-    let parsed: serde_json::Value = serde_json::from_str(&msg.content).unwrap();
-    assert_eq!(parsed["tool"], "shell");
-    assert_eq!(parsed["args"]["command"], "ls -la");
+    assert_eq!(msg.tool_calls.len(), 1);
+    assert_eq!(msg.tool_calls[0].name, "shell");
+    assert_eq!(msg.tool_calls[0].input["command"], "ls -la");
+    assert!(!msg.tool_calls[0].id.is_empty());
 }
 
 #[test]