1329 lines · 46.8 KB · Rust
RawDownload
use action_log::ActionLog;use agent_client_protocol::{self as acp, ToolCallUpdateFields};use anyhow::{Context as _, Result, anyhow};use futures::FutureExt as _;use gpui::{App, Entity, SharedString, Task};use indoc::formatdoc;use language::Point;use language_model::{LanguageModelImage, LanguageModelImageExt, LanguageModelToolResultContent};use project::{AgentLocation, ImageItem, Project, WorktreeSettings, image_store};use schemars::JsonSchema;use serde::{Deserialize, Serialize};use settings::Settings;use std::sync::Arc;use util::markdown::MarkdownCodeBlock; fn tool_content_err(e: impl std::fmt::Display) -> LanguageModelToolResultContent {    LanguageModelToolResultContent::from(e.to_string())} use super::tool_permissions::{    ResolvedProjectPath, authorize_symlink_access, canonicalize_worktree_roots,    resolve_project_path,};use crate::{AgentTool, ToolCallEventStream, ToolInput, outline}; /// Reads the content of the given file in the project.////// - Never attempt to read a path that hasn't been previously mentioned./// - For large files, this tool returns a file outline with symbol names and line numbers instead of the full content.///   This outline IS a successful response - use the line numbers to read specific sections with start_line/end_line.///   Do NOT retry reading the same file without line numbers if you receive an outline./// - This tool supports reading image files. Supported formats: PNG, JPEG, WebP, GIF, BMP, TIFF.///   Image files are returned as visual content that you can analyze directly.#[derive(Debug, Serialize, Deserialize, JsonSchema)]pub struct ReadFileToolInput {    /// The relative path of the file to read.    ///    /// This path should never be absolute, and the first component of the path should always be a root directory in a project.    ///    /// <example>    /// If the project has the following root directories:    ///    /// - /a/b/directory1    /// - /c/d/directory2    ///    /// If you want to access `file.txt` in `directory1`, you should use the path `directory1/file.txt`.    /// If you want to access `file.txt` in `directory2`, you should use the path `directory2/file.txt`.    /// </example>    pub path: String,    /// Optional line number to start reading on (1-based index)    #[serde(default)]    pub start_line: Option<u32>,    /// Optional line number to end reading on (1-based index, inclusive)    #[serde(default)]    pub end_line: Option<u32>,} pub struct ReadFileTool {    project: Entity<Project>,    action_log: Entity<ActionLog>,    update_agent_location: bool,} impl ReadFileTool {    pub fn new(        project: Entity<Project>,        action_log: Entity<ActionLog>,        update_agent_location: bool,    ) -> Self {        Self {            project,            action_log,            update_agent_location,        }    }} impl AgentTool for ReadFileTool {    type Input = ReadFileToolInput;    type Output = LanguageModelToolResultContent;     const NAME: &'static str = "read_file";     fn kind() -> acp::ToolKind {        acp::ToolKind::Read    }     fn initial_title(        &self,        input: Result<Self::Input, serde_json::Value>,        cx: &mut App,    ) -> SharedString {        if let Ok(input) = input            && let Some(project_path) = self.project.read(cx).find_project_path(&input.path, cx)            && let Some(path) = self                .project                .read(cx)                .short_full_path_for_project_path(&project_path, cx)        {            match (input.start_line, input.end_line) {                (Some(start), Some(end)) => {                    format!("Read file `{path}` (lines {}-{})", start, end,)                }                (Some(start), None) => {                    format!("Read file `{path}` (from line {})", start)                }                _ => format!("Read file `{path}`"),            }            .into()        } else {            "Read file".into()        }    }     fn run(        self: Arc<Self>,        input: ToolInput<Self::Input>,        event_stream: ToolCallEventStream,        cx: &mut App,    ) -> Task<Result<LanguageModelToolResultContent, LanguageModelToolResultContent>> {        let project = self.project.clone();        let action_log = self.action_log.clone();        cx.spawn(async move |cx| {            let input = input                .recv()                .await                .map_err(tool_content_err)?;            let fs = project.read_with(cx, |project, _cx| project.fs().clone());            let canonical_roots = canonicalize_worktree_roots(&project, &fs, cx).await;             let (project_path, symlink_canonical_target) =                project.read_with(cx, |project, cx| {                    let resolved =                        resolve_project_path(project, &input.path, &canonical_roots, cx)?;                    anyhow::Ok(match resolved {                        ResolvedProjectPath::Safe(path) => (path, None),                        ResolvedProjectPath::SymlinkEscape {                            project_path,                            canonical_target,                        } => (project_path, Some(canonical_target)),                    })                }).map_err(tool_content_err)?;             let abs_path = project                .read_with(cx, |project, cx| {                    project.absolute_path(&project_path, cx)                })                .ok_or_else(|| {                    anyhow!("Failed to convert {} to absolute path", &input.path)                }).map_err(tool_content_err)?;             // Check settings exclusions synchronously            project.read_with(cx, |_project, cx| {                let global_settings = WorktreeSettings::get_global(cx);                if global_settings.is_path_excluded(&project_path.path) {                    anyhow::bail!(                        "Cannot read file because its path matches the global `file_scan_exclusions` setting: {}",                        &input.path                    );                }                 if global_settings.is_path_private(&project_path.path) {                    anyhow::bail!(                        "Cannot read file because its path matches the global `private_files` setting: {}",                        &input.path                    );                }                 let worktree_settings = WorktreeSettings::get(Some((&project_path).into()), cx);                if worktree_settings.is_path_excluded(&project_path.path) {                    anyhow::bail!(                        "Cannot read file because its path matches the worktree `file_scan_exclusions` setting: {}",                        &input.path                    );                }                 if worktree_settings.is_path_private(&project_path.path) {                    anyhow::bail!(                        "Cannot read file because its path matches the worktree `private_files` setting: {}",                        &input.path                    );                }                 anyhow::Ok(())            }).map_err(tool_content_err)?;             if let Some(canonical_target) = &symlink_canonical_target {                let authorize = cx.update(|cx| {                    authorize_symlink_access(                        Self::NAME,                        &input.path,                        canonical_target,                        &event_stream,                        cx,                    )                });                authorize.await.map_err(tool_content_err)?;            }             let file_path = input.path.clone();             cx.update(|_cx| {                event_stream.update_fields(ToolCallUpdateFields::new().locations(vec![                    acp::ToolCallLocation::new(&abs_path)                        .line(input.start_line.map(|line| line.saturating_sub(1))),                ]));            });             let is_image = project.read_with(cx, |_project, cx| {                image_store::is_image_file(&project, &project_path, cx)            });             if is_image {                let image_entity: Entity<ImageItem> = cx                    .update(|cx| {                        self.project.update(cx, |project, cx| {                            project.open_image(project_path.clone(), cx)                        })                    })                    .await.map_err(tool_content_err)?;                 let image =                    image_entity.read_with(cx, |image_item, _| Arc::clone(&image_item.image));                 let language_model_image = cx                    .update(|cx| LanguageModelImage::from_image(image, cx))                    .await                    .context("processing image")                    .map_err(tool_content_err)?;                 event_stream.update_fields(ToolCallUpdateFields::new().content(vec![                    acp::ToolCallContent::Content(acp::Content::new(acp::ContentBlock::Image(                        acp::ImageContent::new(language_model_image.source.clone(), "image/png"),                    ))),                ]));                 return Ok(language_model_image.into());            }             let open_buffer_task = project.update(cx, |project, cx| {                project.open_buffer(project_path.clone(), cx)            });             let buffer = futures::select! {                result = open_buffer_task.fuse() => result.map_err(tool_content_err)?,                _ = event_stream.cancelled_by_user().fuse() => {                    return Err(tool_content_err("File read cancelled by user"));                }            };            if buffer.read_with(cx, |buffer, _| {                buffer                    .file()                    .as_ref()                    .is_none_or(|file| !file.disk_state().exists())            }) {                return Err(tool_content_err(format!("{file_path} not found")));            }             let mut anchor = None;             // Check if specific line ranges are provided            let result = if input.start_line.is_some() || input.end_line.is_some() {                let result = buffer.read_with(cx, |buffer, _cx| {                    // .max(1) because despite instructions to be 1-indexed, sometimes the model passes 0.                    let start = input.start_line.unwrap_or(1).max(1);                    let start_row = start - 1;                    if start_row <= buffer.max_point().row {                        let column = buffer.line_indent_for_row(start_row).raw_len();                        anchor = Some(buffer.anchor_before(Point::new(start_row, column)));                    }                     let mut end_row = input.end_line.unwrap_or(u32::MAX);                    if end_row <= start_row {                        end_row = start_row + 1; // read at least one lines                    }                    let start = buffer.anchor_before(Point::new(start_row, 0));                    let end = buffer.anchor_before(Point::new(end_row, 0));                    buffer.text_for_range(start..end).collect::<String>()                });                 action_log.update(cx, |log, cx| {                    log.buffer_read(buffer.clone(), cx);                });                 Ok(result.into())            } else {                // No line ranges specified, so check file size to see if it's too big.                let buffer_content = outline::get_buffer_content_or_outline(                    buffer.clone(),                    Some(&abs_path.to_string_lossy()),                    cx,                )                .await.map_err(tool_content_err)?;                 action_log.update(cx, |log, cx| {                    log.buffer_read(buffer.clone(), cx);                });                 if buffer_content.is_outline {                    Ok(formatdoc! {"                        SUCCESS: File outline retrieved. This file is too large to read all at once, so the outline below shows the file's structure with line numbers.                         IMPORTANT: Do NOT retry this call without line numbers - you will get the same outline.                        Instead, use the line numbers below to read specific sections by calling this tool again with start_line and end_line parameters.                         {}                         NEXT STEPS: To read a specific symbol's implementation, call read_file with the same path plus start_line and end_line from the outline above.                        For example, to read a function shown as [L100-150], use start_line: 100 and end_line: 150.", buffer_content.text                    }                    .into())                } else {                    Ok(buffer_content.text.into())                }            };             project.update(cx, |project, cx| {                if self.update_agent_location {                    project.set_agent_location(                        Some(AgentLocation {                            buffer: buffer.downgrade(),                            position: anchor.unwrap_or_else(|| {                                text::Anchor::min_for_buffer(buffer.read(cx).remote_id())                            }),                        }),                        cx,                    );                }                if let Ok(LanguageModelToolResultContent::Text(text)) = &result {                    let text: &str = text;                    let markdown = MarkdownCodeBlock {                        tag: &input.path,                        text,                    }                    .to_string();                    event_stream.update_fields(ToolCallUpdateFields::new().content(vec![                        acp::ToolCallContent::Content(acp::Content::new(markdown)),                    ]));                }            });             result        })    }} #[cfg(test)]mod test {    use super::*;    use agent_client_protocol as acp;    use fs::Fs as _;    use gpui::{AppContext, TestAppContext, UpdateGlobal as _};    use project::{FakeFs, Project};    use serde_json::json;    use settings::SettingsStore;    use std::path::PathBuf;    use std::sync::Arc;    use util::path;     #[gpui::test]    async fn test_read_nonexistent_file(cx: &mut TestAppContext) {        init_test(cx);         let fs = FakeFs::new(cx.executor());        fs.insert_tree(path!("/root"), json!({})).await;        let project = Project::test(fs.clone(), [path!("/root").as_ref()], cx).await;        let action_log = cx.new(|_| ActionLog::new(project.clone()));        let tool = Arc::new(ReadFileTool::new(project, action_log, true));        let (event_stream, _) = ToolCallEventStream::test();         let result = cx            .update(|cx| {                let input = ReadFileToolInput {                    path: "root/nonexistent_file.txt".to_string(),                    start_line: None,                    end_line: None,                };                tool.run(ToolInput::resolved(input), event_stream, cx)            })            .await;        assert_eq!(            error_text(result.unwrap_err()),            "root/nonexistent_file.txt not found"        );    }     #[gpui::test]    async fn test_read_small_file(cx: &mut TestAppContext) {        init_test(cx);         let fs = FakeFs::new(cx.executor());        fs.insert_tree(            path!("/root"),            json!({                "small_file.txt": "This is a small file content"            }),        )        .await;        let project = Project::test(fs.clone(), [path!("/root").as_ref()], cx).await;        let action_log = cx.new(|_| ActionLog::new(project.clone()));        let tool = Arc::new(ReadFileTool::new(project, action_log, true));        let result = cx            .update(|cx| {                let input = ReadFileToolInput {                    path: "root/small_file.txt".into(),                    start_line: None,                    end_line: None,                };                tool.run(                    ToolInput::resolved(input),                    ToolCallEventStream::test().0,                    cx,                )            })            .await;        assert_eq!(result.unwrap(), "This is a small file content".into());    }     #[gpui::test]    async fn test_read_large_file(cx: &mut TestAppContext) {        init_test(cx);         let fs = FakeFs::new(cx.executor());        fs.insert_tree(            path!("/root"),            json!({                "large_file.rs": (0..1000).map(|i| format!("struct Test{} {{\n    a: u32,\n    b: usize,\n}}", i)).collect::<Vec<_>>().join("\n")            }),        )        .await;        let project = Project::test(fs.clone(), [path!("/root").as_ref()], cx).await;        let language_registry = project.read_with(cx, |project, _| project.languages().clone());        language_registry.add(language::rust_lang());        let action_log = cx.new(|_| ActionLog::new(project.clone()));        let tool = Arc::new(ReadFileTool::new(project, action_log, true));        let result = cx            .update(|cx| {                let input = ReadFileToolInput {                    path: "root/large_file.rs".into(),                    start_line: None,                    end_line: None,                };                tool.clone().run(                    ToolInput::resolved(input),                    ToolCallEventStream::test().0,                    cx,                )            })            .await            .unwrap();        let content = result.to_str().unwrap();         assert_eq!(            content.lines().skip(7).take(6).collect::<Vec<_>>(),            vec![                "struct Test0 [L1-4]",                " a [L2]",                " b [L3]",                "struct Test1 [L5-8]",                " a [L6]",                " b [L7]",            ]        );         let result = cx            .update(|cx| {                let input = ReadFileToolInput {                    path: "root/large_file.rs".into(),                    start_line: None,                    end_line: None,                };                tool.run(                    ToolInput::resolved(input),                    ToolCallEventStream::test().0,                    cx,                )            })            .await            .unwrap();        let content = result.to_str().unwrap();        let expected_content = (0..1000)            .flat_map(|i| {                vec![                    format!("struct Test{} [L{}-{}]", i, i * 4 + 1, i * 4 + 4),                    format!(" a [L{}]", i * 4 + 2),                    format!(" b [L{}]", i * 4 + 3),                ]            })            .collect::<Vec<_>>();        pretty_assertions::assert_eq!(            content                .lines()                .skip(7)                .take(expected_content.len())                .collect::<Vec<_>>(),            expected_content        );    }     #[gpui::test]

Lines 1–500 of 1329.