Add extensible tool system with code execution and web search

Introduces a tool registry architecture with sandboxed code execution, web search capabilities, and consent-based permission management. Enables safe, pluggable LLM tool integration with schema validation.

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>

crates/owlen-core/src/tools/mod.rs

@@ -0,0 +1,53 @@
+use std::collections::HashMap;
+
+use anyhow::Result;
+use async_trait::async_trait;
+use serde_json::Value;
+
+pub mod code_exec;
+pub mod registry;
+pub mod web_search;
+pub mod web_search_detailed;
+
+#[async_trait]
+pub trait Tool: Send + Sync {
+    fn name(&self) -> &'static str;
+    fn description(&self) -> &'static str;
+    fn schema(&self) -> Value;
+    fn requires_network(&self) -> bool {
+        false
+    }
+    fn requires_filesystem(&self) -> Vec<String> {
+        Vec::new()
+    }
+
+    async fn execute(&self, args: Value) -> Result<ToolResult>;
+}
+
+#[derive(Debug, Clone)]
+pub struct ToolResult {
+    pub success: bool,
+    pub output: Value,
+    pub duration: std::time::Duration,
+    pub metadata: HashMap<String, String>,
+}
+
+impl ToolResult {
+    pub fn success(output: Value) -> Self {
+        Self {
+            success: true,
+            output,
+            duration: std::time::Duration::from_millis(0),
+            metadata: HashMap::new(),
+        }
+    }
+
+    pub fn error(message: &str) -> Self {
+        Self {
+            success: false,
+            output: serde_json::json!({ "error": message }),
+            duration: std::time::Duration::from_millis(0),
+            metadata: HashMap::new(),
+        }
+    }
+}