feat: grep_files as a tool (#4820)

Add `grep_files` to be able to perform more action in parallel

codex-rs/core/src/tools/handlers/grep_files.rs

@@ -0,0 +1,272 @@
+use std::path::Path;
+use std::time::Duration;
+
+use async_trait::async_trait;
+use serde::Deserialize;
+use tokio::process::Command;
+use tokio::time::timeout;
+
+use crate::function_tool::FunctionCallError;
+use crate::tools::context::ToolInvocation;
+use crate::tools::context::ToolOutput;
+use crate::tools::context::ToolPayload;
+use crate::tools::registry::ToolHandler;
+use crate::tools::registry::ToolKind;
+
+pub struct GrepFilesHandler;
+
+const DEFAULT_LIMIT: usize = 100;
+const MAX_LIMIT: usize = 2000;
+const COMMAND_TIMEOUT: Duration = Duration::from_secs(30);
+
+fn default_limit() -> usize {
+    DEFAULT_LIMIT
+}
+
+#[derive(Deserialize)]
+struct GrepFilesArgs {
+    pattern: String,
+    #[serde(default)]
+    include: Option<String>,
+    #[serde(default)]
+    path: Option<String>,
+    #[serde(default = "default_limit")]
+    limit: usize,
+}
+
+#[async_trait]
+impl ToolHandler for GrepFilesHandler {
+    fn kind(&self) -> ToolKind {
+        ToolKind::Function
+    }
+
+    async fn handle(&self, invocation: ToolInvocation) -> Result<ToolOutput, FunctionCallError> {
+        let ToolInvocation { payload, turn, .. } = invocation;
+
+        let arguments = match payload {
+            ToolPayload::Function { arguments } => arguments,
+            _ => {
+                return Err(FunctionCallError::RespondToModel(
+                    "grep_files handler received unsupported payload".to_string(),
+                ));
+            }
+        };
+
+        let args: GrepFilesArgs = serde_json::from_str(&arguments).map_err(|err| {
+            FunctionCallError::RespondToModel(format!(
+                "failed to parse function arguments: {err:?}"
+            ))
+        })?;
+
+        let pattern = args.pattern.trim();
+        if pattern.is_empty() {
+            return Err(FunctionCallError::RespondToModel(
+                "pattern must not be empty".to_string(),
+            ));
+        }
+
+        if args.limit == 0 {
+            return Err(FunctionCallError::RespondToModel(
+                "limit must be greater than zero".to_string(),
+            ));
+        }
+
+        let limit = args.limit.min(MAX_LIMIT);
+        let search_path = turn.resolve_path(args.path.clone());
+
+        verify_path_exists(&search_path).await?;
+
+        let include = args.include.as_deref().map(str::trim).and_then(|val| {
+            if val.is_empty() {
+                None
+            } else {
+                Some(val.to_string())
+            }
+        });
+
+        let search_results =
+            run_rg_search(pattern, include.as_deref(), &search_path, limit, &turn.cwd).await?;
+
+        if search_results.is_empty() {
+            Ok(ToolOutput::Function {
+                content: "No matches found.".to_string(),
+                success: Some(false),
+            })
+        } else {
+            Ok(ToolOutput::Function {
+                content: search_results.join("\n"),
+                success: Some(true),
+            })
+        }
+    }
+}
+
+async fn verify_path_exists(path: &Path) -> Result<(), FunctionCallError> {
+    tokio::fs::metadata(path).await.map_err(|err| {
+        FunctionCallError::RespondToModel(format!("unable to access `{}`: {err}", path.display()))
+    })?;
+    Ok(())
+}
+
+async fn run_rg_search(
+    pattern: &str,
+    include: Option<&str>,
+    search_path: &Path,
+    limit: usize,
+    cwd: &Path,
+) -> Result<Vec<String>, FunctionCallError> {
+    let mut command = Command::new("rg");
+    command
+        .current_dir(cwd)
+        .arg("--files-with-matches")
+        .arg("--sortr=modified")
+        .arg("--regexp")
+        .arg(pattern)
+        .arg("--no-messages");
+
+    if let Some(glob) = include {
+        command.arg("--glob").arg(glob);
+    }
+
+    command.arg("--").arg(search_path);
+
+    let output = timeout(COMMAND_TIMEOUT, command.output())
+        .await
+        .map_err(|_| {
+            FunctionCallError::RespondToModel("rg timed out after 30 seconds".to_string())
+        })?
+        .map_err(|err| {
+            FunctionCallError::RespondToModel(format!(
+                "failed to launch rg: {err}. Ensure ripgrep is installed and on PATH."
+            ))
+        })?;
+
+    match output.status.code() {
+        Some(0) => Ok(parse_results(&output.stdout, limit)),
+        Some(1) => Ok(Vec::new()),
+        _ => {
+            let stderr = String::from_utf8_lossy(&output.stderr);
+            Err(FunctionCallError::RespondToModel(format!(
+                "rg failed: {stderr}"
+            )))
+        }
+    }
+}
+
+fn parse_results(stdout: &[u8], limit: usize) -> Vec<String> {
+    let mut results = Vec::new();
+    for line in stdout.split(|byte| *byte == b'\n') {
+        if line.is_empty() {
+            continue;
+        }
+        if let Ok(text) = std::str::from_utf8(line) {
+            if text.is_empty() {
+                continue;
+            }
+            results.push(text.to_string());
+            if results.len() == limit {
+                break;
+            }
+        }
+    }
+    results
+}
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+    use std::process::Command as StdCommand;
+    use tempfile::tempdir;
+
+    #[test]
+    fn parses_basic_results() {
+        let stdout = b"/tmp/file_a.rs\n/tmp/file_b.rs\n";
+        let parsed = parse_results(stdout, 10);
+        assert_eq!(
+            parsed,
+            vec!["/tmp/file_a.rs".to_string(), "/tmp/file_b.rs".to_string()]
+        );
+    }
+
+    #[test]
+    fn parse_truncates_after_limit() {
+        let stdout = b"/tmp/file_a.rs\n/tmp/file_b.rs\n/tmp/file_c.rs\n";
+        let parsed = parse_results(stdout, 2);
+        assert_eq!(
+            parsed,
+            vec!["/tmp/file_a.rs".to_string(), "/tmp/file_b.rs".to_string()]
+        );
+    }
+
+    #[tokio::test]
+    async fn run_search_returns_results() -> anyhow::Result<()> {
+        if !rg_available() {
+            return Ok(());
+        }
+        let temp = tempdir().expect("create temp dir");
+        let dir = temp.path();
+        std::fs::write(dir.join("match_one.txt"), "alpha beta gamma").unwrap();
+        std::fs::write(dir.join("match_two.txt"), "alpha delta").unwrap();
+        std::fs::write(dir.join("other.txt"), "omega").unwrap();
+
+        let results = run_rg_search("alpha", None, dir, 10, dir).await?;
+        assert_eq!(results.len(), 2);
+        assert!(results.iter().any(|path| path.ends_with("match_one.txt")));
+        assert!(results.iter().any(|path| path.ends_with("match_two.txt")));
+        Ok(())
+    }
+
+    #[tokio::test]
+    async fn run_search_with_glob_filter() -> anyhow::Result<()> {
+        if !rg_available() {
+            return Ok(());
+        }
+        let temp = tempdir().expect("create temp dir");
+        let dir = temp.path();
+        std::fs::write(dir.join("match_one.rs"), "alpha beta gamma").unwrap();
+        std::fs::write(dir.join("match_two.txt"), "alpha delta").unwrap();
+
+        let results = run_rg_search("alpha", Some("*.rs"), dir, 10, dir).await?;
+        assert_eq!(results.len(), 1);
+        assert!(results.iter().all(|path| path.ends_with("match_one.rs")));
+        Ok(())
+    }
+
+    #[tokio::test]
+    async fn run_search_respects_limit() -> anyhow::Result<()> {
+        if !rg_available() {
+            return Ok(());
+        }
+        let temp = tempdir().expect("create temp dir");
+        let dir = temp.path();
+        std::fs::write(dir.join("one.txt"), "alpha one").unwrap();
+        std::fs::write(dir.join("two.txt"), "alpha two").unwrap();
+        std::fs::write(dir.join("three.txt"), "alpha three").unwrap();
+
+        let results = run_rg_search("alpha", None, dir, 2, dir).await?;
+        assert_eq!(results.len(), 2);
+        Ok(())
+    }
+
+    #[tokio::test]
+    async fn run_search_handles_no_matches() -> anyhow::Result<()> {
+        if !rg_available() {
+            return Ok(());
+        }
+        let temp = tempdir().expect("create temp dir");
+        let dir = temp.path();
+        std::fs::write(dir.join("one.txt"), "omega").unwrap();
+
+        let results = run_rg_search("alpha", None, dir, 5, dir).await?;
+        assert!(results.is_empty());
+        Ok(())
+    }
+
+    fn rg_available() -> bool {
+        StdCommand::new("rg")
+            .arg("--version")
+            .output()
+            .map(|output| output.status.success())
+            .unwrap_or(false)
+    }
+}

codex-rs/core/src/tools/handlers/mod.rs

@@ -1,5 +1,6 @@
 pub mod apply_patch;
 mod exec_stream;
+mod grep_files;
 mod list_dir;
 mod mcp;
 mod plan;
@@ -13,6 +14,7 @@ pub use plan::PLAN_TOOL;
 
 pub use apply_patch::ApplyPatchHandler;
 pub use exec_stream::ExecStreamHandler;
+pub use grep_files::GrepFilesHandler;
 pub use list_dir::ListDirHandler;
 pub use mcp::McpHandler;
 pub use plan::PlanHandler;

codex-rs/core/src/tools/spec.rs

@@ -320,6 +320,56 @@ fn create_test_sync_tool() -> ToolSpec {
     })
 }
 
+fn create_grep_files_tool() -> ToolSpec {
+    let mut properties = BTreeMap::new();
+    properties.insert(
+        "pattern".to_string(),
+        JsonSchema::String {
+            description: Some("Regular expression pattern to search for.".to_string()),
+        },
+    );
+    properties.insert(
+        "include".to_string(),
+        JsonSchema::String {
+            description: Some(
+                "Optional glob that limits which files are searched (e.g. \"*.rs\" or \
+                 \"*.{ts,tsx}\")."
+                    .to_string(),
+            ),
+        },
+    );
+    properties.insert(
+        "path".to_string(),
+        JsonSchema::String {
+            description: Some(
+                "Directory or file path to search. Defaults to the session's working directory."
+                    .to_string(),
+            ),
+        },
+    );
+    properties.insert(
+        "limit".to_string(),
+        JsonSchema::Number {
+            description: Some(
+                "Maximum number of file paths to return (defaults to 100).".to_string(),
+            ),
+        },
+    );
+
+    ToolSpec::Function(ResponsesApiTool {
+        name: "grep_files".to_string(),
+        description: "Finds files whose contents match the pattern and lists them by modification \
+                      time."
+            .to_string(),
+        strict: false,
+        parameters: JsonSchema::Object {
+            properties,
+            required: Some(vec!["pattern".to_string()]),
+            additional_properties: Some(false.into()),
+        },
+    })
+}
+
 fn create_read_file_tool() -> ToolSpec {
     let mut properties = BTreeMap::new();
     properties.insert(
@@ -610,6 +660,7 @@ pub(crate) fn build_specs(
     use crate::exec_command::create_write_stdin_tool_for_responses_api;
     use crate::tools::handlers::ApplyPatchHandler;
     use crate::tools::handlers::ExecStreamHandler;
+    use crate::tools::handlers::GrepFilesHandler;
     use crate::tools::handlers::ListDirHandler;
     use crate::tools::handlers::McpHandler;
     use crate::tools::handlers::PlanHandler;
@@ -678,8 +729,16 @@ pub(crate) fn build_specs(
 
     if config
         .experimental_supported_tools
-        .iter()
-        .any(|tool| tool == "read_file")
+        .contains(&"grep_files".to_string())
+    {
+        let grep_files_handler = Arc::new(GrepFilesHandler);
+        builder.push_spec_with_parallel_support(create_grep_files_tool(), true);
+        builder.register_handler("grep_files", grep_files_handler);
+    }
+
+    if config
+        .experimental_supported_tools
+        .contains(&"read_file".to_string())
     {
         let read_file_handler = Arc::new(ReadFileHandler);
         builder.push_spec_with_parallel_support(create_read_file_tool(), true);
@@ -698,8 +757,7 @@ pub(crate) fn build_specs(
 
     if config
         .experimental_supported_tools
-        .iter()
-        .any(|tool| tool == "test_sync_tool")
+        .contains(&"test_sync_tool".to_string())
     {
         let test_sync_handler = Arc::new(TestSyncHandler);
         builder.push_spec_with_parallel_support(create_test_sync_tool(), true);
@@ -841,8 +899,9 @@ mod tests {
         let (tools, _) = build_specs(&config, None).build();
 
         assert!(!find_tool(&tools, "unified_exec").supports_parallel_tool_calls);
-        assert!(find_tool(&tools, "read_file").supports_parallel_tool_calls);
+        assert!(find_tool(&tools, "grep_files").supports_parallel_tool_calls);
         assert!(find_tool(&tools, "list_dir").supports_parallel_tool_calls);
+        assert!(find_tool(&tools, "read_file").supports_parallel_tool_calls);
     }
 
     #[test]
@@ -870,6 +929,11 @@ mod tests {
                 .iter()
                 .any(|tool| tool_name(&tool.spec) == "read_file")
         );
+        assert!(
+            tools
+                .iter()
+                .any(|tool| tool_name(&tool.spec) == "grep_files")
+        );
         assert!(tools.iter().any(|tool| tool_name(&tool.spec) == "list_dir"));
     }