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/code_exec.rs

@@ -0,0 +1,147 @@
+use std::sync::Arc;
+use std::time::Instant;
+
+use anyhow::{anyhow, Context, Result};
+use async_trait::async_trait;
+use serde_json::{json, Value};
+
+use super::{Tool, ToolResult};
+use crate::sandbox::{SandboxConfig, SandboxedProcess};
+
+pub struct CodeExecTool {
+    allowed_languages: Arc<Vec<String>>,
+}
+
+impl CodeExecTool {
+    pub fn new(allowed_languages: Vec<String>) -> Self {
+        Self {
+            allowed_languages: Arc::new(allowed_languages),
+        }
+    }
+}
+
+#[async_trait]
+impl Tool for CodeExecTool {
+    fn name(&self) -> &'static str {
+        "code_exec"
+    }
+
+    fn description(&self) -> &'static str {
+        "Execute code snippets within a sandboxed environment"
+    }
+
+    fn schema(&self) -> Value {
+        json!({
+            "type": "object",
+            "properties": {
+                "language": {
+                    "type": "string",
+                    "enum": self.allowed_languages.as_slice(),
+                    "description": "Language of the code block"
+                },
+                "code": {
+                    "type": "string",
+                    "minLength": 1,
+                    "maxLength": 10000,
+                    "description": "Code to execute"
+                },
+                "timeout": {
+                    "type": "integer",
+                    "minimum": 1,
+                    "maximum": 300,
+                    "default": 30,
+                    "description": "Execution timeout in seconds"
+                }
+            },
+            "required": ["language", "code"],
+            "additionalProperties": false
+        })
+    }
+
+    async fn execute(&self, args: Value) -> Result<ToolResult> {
+        let start = Instant::now();
+
+        let language = args
+            .get("language")
+            .and_then(Value::as_str)
+            .context("Missing language parameter")?;
+        let code = args
+            .get("code")
+            .and_then(Value::as_str)
+            .context("Missing code parameter")?;
+        let timeout = args.get("timeout").and_then(Value::as_u64).unwrap_or(30);
+
+        if !self.allowed_languages.iter().any(|lang| lang == language) {
+            return Err(anyhow!("Language '{}' not permitted", language));
+        }
+
+        let (command, command_args) = match language {
+            "python" => (
+                "python3".to_string(),
+                vec!["-c".to_string(), code.to_string()],
+            ),
+            "javascript" => ("node".to_string(), vec!["-e".to_string(), code.to_string()]),
+            "bash" => ("bash".to_string(), vec!["-c".to_string(), code.to_string()]),
+            "rust" => {
+                let mut result =
+                    ToolResult::error("Rust execution is not yet supported in the sandbox");
+                result.duration = start.elapsed();
+                return Ok(result);
+            }
+            other => return Err(anyhow!("Unsupported language: {}", other)),
+        };
+
+        let sandbox_config = SandboxConfig {
+            allow_network: false,
+            timeout_seconds: timeout,
+            ..Default::default()
+        };
+
+        let sandbox_result = tokio::task::spawn_blocking(move || -> Result<_> {
+            let sandbox = SandboxedProcess::new(sandbox_config)?;
+            let arg_refs: Vec<&str> = command_args.iter().map(|s| s.as_str()).collect();
+            sandbox.execute(&command, &arg_refs)
+        })
+        .await
+        .context("Sandbox execution task failed")??;
+
+        let mut result = if sandbox_result.exit_code == 0 {
+            ToolResult::success(json!({
+                "stdout": sandbox_result.stdout,
+                "stderr": sandbox_result.stderr,
+                "exit_code": sandbox_result.exit_code,
+                "timed_out": sandbox_result.was_timeout,
+            }))
+        } else {
+            let error_msg = if sandbox_result.was_timeout {
+                format!(
+                    "Execution timed out after {} seconds (exit code {}): {}",
+                    timeout, sandbox_result.exit_code, sandbox_result.stderr
+                )
+            } else {
+                format!(
+                    "Execution failed with status {}: {}",
+                    sandbox_result.exit_code, sandbox_result.stderr
+                )
+            };
+            let mut err_result = ToolResult::error(&error_msg);
+            err_result.output = json!({
+                "stdout": sandbox_result.stdout,
+                "stderr": sandbox_result.stderr,
+                "exit_code": sandbox_result.exit_code,
+                "timed_out": sandbox_result.was_timeout,
+            });
+            err_result
+        };
+
+        result.duration = start.elapsed();
+        result
+            .metadata
+            .insert("language".to_string(), language.to_string());
+        result
+            .metadata
+            .insert("timeout_seconds".to_string(), timeout.to_string());
+
+        Ok(result)
+    }
+}

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(),
+        }
+    }
+}

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

@@ -0,0 +1,53 @@
+use std::collections::HashMap;
+use std::sync::Arc;
+
+use anyhow::{Context, Result};
+use serde_json::Value;
+
+use super::Tool;
+
+pub struct ToolRegistry {
+    tools: HashMap<String, Arc<dyn Tool>>,
+}
+
+impl Default for ToolRegistry {
+    fn default() -> Self {
+        Self::new()
+    }
+}
+
+impl ToolRegistry {
+    pub fn new() -> Self {
+        Self {
+            tools: HashMap::new(),
+        }
+    }
+
+    pub fn register<T>(&mut self, tool: T)
+    where
+        T: Tool + 'static,
+    {
+        let tool: Arc<dyn Tool> = Arc::new(tool);
+        let name = tool.name().to_string();
+        self.tools.insert(name, tool);
+    }
+
+    pub fn get(&self, name: &str) -> Option<Arc<dyn Tool>> {
+        self.tools.get(name).cloned()
+    }
+
+    pub fn all(&self) -> Vec<Arc<dyn Tool>> {
+        self.tools.values().cloned().collect()
+    }
+
+    pub async fn execute(&self, name: &str, args: Value) -> Result<super::ToolResult> {
+        let tool = self
+            .get(name)
+            .with_context(|| format!("Tool not registered: {}", name))?;
+        tool.execute(args).await
+    }
+
+    pub fn tools(&self) -> Vec<String> {
+        self.tools.keys().cloned().collect()
+    }
+}

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

@@ -0,0 +1,153 @@
+use std::sync::{Arc, Mutex};
+use std::time::Instant;
+
+use anyhow::{Context, Result};
+use async_trait::async_trait;
+use serde_json::{json, Value};
+
+use super::{Tool, ToolResult};
+use crate::consent::ConsentManager;
+use crate::credentials::CredentialManager;
+use crate::encryption::VaultHandle;
+
+pub struct WebSearchTool {
+    consent_manager: Arc<Mutex<ConsentManager>>,
+    _credential_manager: Option<Arc<CredentialManager>>,
+    browser: duckduckgo::browser::Browser,
+}
+
+impl WebSearchTool {
+    pub fn new(
+        consent_manager: Arc<Mutex<ConsentManager>>,
+        credential_manager: Option<Arc<CredentialManager>>,
+        _vault: Option<Arc<Mutex<VaultHandle>>>,
+    ) -> Self {
+        // Create a reqwest client compatible with duckduckgo crate (v0.11)
+        let client = reqwest_011::Client::new();
+        let browser = duckduckgo::browser::Browser::new(client);
+
+        Self {
+            consent_manager,
+            _credential_manager: credential_manager,
+            browser,
+        }
+    }
+}
+
+#[async_trait]
+impl Tool for WebSearchTool {
+    fn name(&self) -> &'static str {
+        "web_search"
+    }
+
+    fn description(&self) -> &'static str {
+        "Search the web for information using DuckDuckGo API"
+    }
+
+    fn schema(&self) -> Value {
+        json!({
+            "type": "object",
+            "properties": {
+                "query": {
+                    "type": "string",
+                    "minLength": 1,
+                    "maxLength": 500,
+                    "description": "Search query"
+                },
+                "max_results": {
+                    "type": "integer",
+                    "minimum": 1,
+                    "maximum": 10,
+                    "default": 5,
+                    "description": "Maximum number of results"
+                }
+            },
+            "required": ["query"],
+            "additionalProperties": false
+        })
+    }
+
+    fn requires_network(&self) -> bool {
+        true
+    }
+
+    async fn execute(&self, args: Value) -> Result<ToolResult> {
+        let start = Instant::now();
+
+        // Check if consent has been granted (non-blocking check)
+        // Consent should have been granted via TUI dialog before tool execution
+        {
+            let consent = self
+                .consent_manager
+                .lock()
+                .expect("Consent manager mutex poisoned");
+
+            if !consent.has_consent(self.name()) {
+                return Ok(ToolResult::error(
+                    "Consent not granted for web search. This should have been handled by the TUI.",
+                ));
+            }
+        }
+
+        let query = args
+            .get("query")
+            .and_then(Value::as_str)
+            .context("Missing query parameter")?;
+        let max_results = args.get("max_results").and_then(Value::as_u64).unwrap_or(5) as usize;
+
+        let user_agent = duckduckgo::user_agents::get("firefox").unwrap_or(
+            "Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:91.0) Gecko/20100101 Firefox/91.0",
+        );
+
+        // Detect if this is a news query - use news endpoint for better snippets
+        let is_news_query = query.to_lowercase().contains("news")
+            || query.to_lowercase().contains("latest")
+            || query.to_lowercase().contains("today")
+            || query.to_lowercase().contains("recent");
+
+        let mut formatted_results = Vec::new();
+
+        if is_news_query {
+            // Use news endpoint which returns excerpts/snippets
+            let news_results = self
+                .browser
+                .news(query, "wt-wt", false, Some(max_results), user_agent)
+                .await
+                .context("DuckDuckGo news search failed")?;
+
+            for result in news_results {
+                formatted_results.push(json!({
+                    "title": result.title,
+                    "url": result.url,
+                    "snippet": result.body,  // news has body/excerpt
+                    "source": result.source,
+                    "date": result.date
+                }));
+            }
+        } else {
+            // Use lite search for general queries (fast but no snippets)
+            let search_results = self
+                .browser
+                .lite_search(query, "wt-wt", Some(max_results), user_agent)
+                .await
+                .context("DuckDuckGo search failed")?;
+
+            for result in search_results {
+                formatted_results.push(json!({
+                    "title": result.title,
+                    "url": result.url,
+                    "snippet": result.snippet
+                }));
+            }
+        }
+
+        let mut result = ToolResult::success(json!({
+            "query": query,
+            "results": formatted_results,
+            "total_found": formatted_results.len()
+        }));
+        result.duration = start.elapsed();
+
+        Ok(result)
+    }
+}

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

@@ -0,0 +1,130 @@
+use std::sync::{Arc, Mutex};
+use std::time::Instant;
+
+use anyhow::{Context, Result};
+use async_trait::async_trait;
+use serde_json::{json, Value};
+
+use super::{Tool, ToolResult};
+use crate::consent::ConsentManager;
+use crate::credentials::CredentialManager;
+use crate::encryption::VaultHandle;
+
+pub struct WebSearchDetailedTool {
+    consent_manager: Arc<Mutex<ConsentManager>>,
+    _credential_manager: Option<Arc<CredentialManager>>,
+    browser: duckduckgo::browser::Browser,
+}
+
+impl WebSearchDetailedTool {
+    pub fn new(
+        consent_manager: Arc<Mutex<ConsentManager>>,
+        credential_manager: Option<Arc<CredentialManager>>,
+        _vault: Option<Arc<Mutex<VaultHandle>>>,
+    ) -> Self {
+        // Create a reqwest client compatible with duckduckgo crate (v0.11)
+        let client = reqwest_011::Client::new();
+        let browser = duckduckgo::browser::Browser::new(client);
+
+        Self {
+            consent_manager,
+            _credential_manager: credential_manager,
+            browser,
+        }
+    }
+}
+
+#[async_trait]
+impl Tool for WebSearchDetailedTool {
+    fn name(&self) -> &'static str {
+        "web_search_detailed"
+    }
+
+    fn description(&self) -> &'static str {
+        "Search for recent articles and web content with detailed snippets and descriptions. \
+         Returns results with publication dates, sources, and full text excerpts. \
+         Best for finding recent information, articles, and detailed context about topics."
+    }
+
+    fn schema(&self) -> Value {
+        json!({
+            "type": "object",
+            "properties": {
+                "query": {
+                    "type": "string",
+                    "minLength": 1,
+                    "maxLength": 500,
+                    "description": "Search query"
+                },
+                "max_results": {
+                    "type": "integer",
+                    "minimum": 1,
+                    "maximum": 10,
+                    "default": 5,
+                    "description": "Maximum number of results"
+                }
+            },
+            "required": ["query"],
+            "additionalProperties": false
+        })
+    }
+
+    fn requires_network(&self) -> bool {
+        true
+    }
+
+    async fn execute(&self, args: Value) -> Result<ToolResult> {
+        let start = Instant::now();
+
+        // Check if consent has been granted (non-blocking check)
+        // Consent should have been granted via TUI dialog before tool execution
+        {
+            let consent = self
+                .consent_manager
+                .lock()
+                .expect("Consent manager mutex poisoned");
+
+            if !consent.has_consent(self.name()) {
+                return Ok(ToolResult::error("Consent not granted for detailed web search. This should have been handled by the TUI."));
+            }
+        }
+
+        let query = args
+            .get("query")
+            .and_then(Value::as_str)
+            .context("Missing query parameter")?;
+        let max_results = args.get("max_results").and_then(Value::as_u64).unwrap_or(5) as usize;
+
+        let user_agent = duckduckgo::user_agents::get("firefox").unwrap_or(
+            "Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:91.0) Gecko/20100101 Firefox/91.0",
+        );
+
+        // Use news endpoint which provides detailed results with full snippets
+        // Even for non-news queries, this often returns recent articles and content with good descriptions
+        let news_results = self
+            .browser
+            .news(query, "wt-wt", false, Some(max_results), user_agent)
+            .await
+            .context("DuckDuckGo detailed search failed")?;
+
+        let mut formatted_results = Vec::new();
+        for result in news_results {
+            formatted_results.push(json!({
+                "title": result.title,
+                "url": result.url,
+                "snippet": result.body,  // news endpoint includes full excerpts
+                "source": result.source,
+                "date": result.date
+            }));
+        }
+
+        let mut result = ToolResult::success(json!({
+            "query": query,
+            "results": formatted_results,
+            "total_found": formatted_results.len()
+        }));
+        result.duration = start.elapsed();
+
+        Ok(result)
+    }
+}