feat: add remote repository command

CHANGELOG.md

@@ -0,0 +1,20 @@
+# Changelog
+
+All notable changes to this project will be documented in this file.
+
+## 1.7.0 - 2026-02-09
+
+Added
+- `--repo` to process a remote git repository in a temporary directory.
+- `--repo-branch` to checkout a branch or tag when using `--repo`.
+- `--repo-commit` to checkout a specific commit when using `--repo`.
+- Repository integration tests covering clone, cleanup, and commit checkout.
+
+Changed
+- Error handling now uses typed `AppError` variants (via `thiserror`), removing string-based checks for clipboard and config errors.
+- When `--repo-commit` is used, cloning no longer uses `--depth 1` to ensure the commit is available.
+- Documentation updated with a remote-repo usage example.
+- Applied a formatting pass to keep code style consistent.
+
+Fixed
+- CLI now prevents using `--repo` and `--dir` together.

Cargo.toml

@@ -22,6 +22,7 @@ ignore = "0.4.23"
 serde = { version = "1.0.228", features = ["derive"] }
 serde_yaml = "0.9.34"
 walkdir = "2.5.0"
+tempfile = "3.19.1"
+thiserror = "1.0"
 
 [dev-dependencies]
-tempfile = "3.19.1"

README.md

@@ -7,6 +7,7 @@ A command-line tool to combine files from a directory into a single file for AI
 ## Features
 
 - Combines multiple text files into one output file
+- Can process a remote git repository in a temporary directory
 - Supports configuration via CLI options **and config files** (YAML)
 - Filters files by:
   - Size
@@ -80,21 +81,25 @@ fyai
 
 ```
 USAGE:
-    fyai [OPTIONS]
+    fyai [OPTIONS] [SUBCOMMAND]
 
 OPTIONS:
     -d, --dir <DIR>                Sets the input directory [default: .]
     -o, --output <FILE>            Sets the output file [default: fyai.txt]
+        --repo <URL>               Clone a git repository (e.g., GitHub/GitLab) into a temporary directory before processing
+        --repo-branch <BRANCH>     Branch or tag to checkout when using --repo
+        --repo-commit <COMMIT>     Commit SHA to checkout when using --repo
         --include-dirs <DIRS>      Comma-separated list of directories to include (e.g., src,docs)
     -x, --exclude-dirs <DIRS>      Comma-separated list of directories to exclude (e.g., node_modules,dist)
         --include-files <FILES>    Comma-separated list of files to include (e.g., README.md,main.rs)
         --exclude-files <FILES>    Comma-separated list of files to exclude (e.g., LICENSE,config.json)
         --include-ext <EXT>        Comma-separated list of file extensions to include (e.g., txt,md)
     -e, --exclude-ext <EXT>        Comma-separated list of file extensions to exclude (e.g., log,tmp)
-    -n, --min-size <BYTES>         Exclude files smaller than this size in bytes (default: 51200)
+    -n, --min-size <BYTES>         Exclude files smaller than this size in bytes
     -m, --max-size <BYTES>         Exclude files larger than this size in bytes
         --respect-gitignore <BOOL> Whether to respect .gitignore rules (true/false) [default: true]
         --tree-only                Only output the project directory tree, no file contents
+    -t, --test                     Run in test mode
     -h, --help                     Print help information
     -V, --version                  Print version information
 
@@ -104,6 +109,9 @@ CONFIG FILE SUPPORT:
     Global config: ~/.config/fyai.yaml (used if no local config found)
     CLI options override config file values.
     See README for details and examples.
+
+SUBCOMMANDS:
+    init    Generate a template fyai.yaml config file
 ```
 
 ### Examples
@@ -155,6 +163,24 @@ CONFIG FILE SUPPORT:
   fyai --respect-gitignore false
   ```
 
+- Run against a remote GitHub/GitLab repository without leaving the clone on disk:
+
+  ```bash
+  fyai --repo https://github.com/owner/repo.git --repo-branch main
+  ```
+
+- Run against a specific commit:
+
+  ```bash
+  fyai --repo https://github.com/owner/repo.git --repo-commit 1234abcd
+  ```
+
+- Generate a config template:
+
+  ```bash
+  fyai init
+  ```
+
 ## Output Format
 
 The combined file includes headers for each source file:
@@ -179,6 +205,10 @@ Contributions are welcome! Please:
 
 This project is licensed under the MIT License.
 
+## Changelog
+
+See `CHANGELOG.md` for release notes.
+
 ## Acknowledgments
 
 - Built with [Rust](https://www.rust-lang.org/)

src/cli.rs

@@ -20,6 +20,26 @@ pub fn create_commands() -> Command {
                 .help("Sets the output file")
                 .default_value("fyai.txt"),
         )
+        .arg(
+            Arg::new("repo")
+                .long("repo")
+                .value_name("URL")
+                .help("Clone a git repository (GitHub/GitLab) into a temporary directory before processing").conflicts_with("directory"),
+        )
+        .arg(
+            Arg::new("repo_branch")
+                .long("repo-branch")
+                .value_name("BRANCH")
+                .help("Branch or tag to checkout when using --repo")
+                .requires("repo"),
+        )
+        .arg(
+            Arg::new("repo_commit")
+                .long("repo-commit")
+                .value_name("COMMIT")
+                .help("Commit SHA to checkout when using --repo")
+                .requires("repo"),
+        )
         .arg(
             Arg::new("include_dirs")
                 .long("include-dirs")

src/clipboard.rs

@@ -1,19 +1,21 @@
 use clipboard::{ClipboardContext, ClipboardProvider};
 use std::fs::File;
-use std::io::{self, Error, Read};
+use std::io::Read;
 use std::path::Path;
 
+use crate::error::{AppError, AppResult};
+
 /// Copies the contents of the specified file to the system clipboard.
-pub fn copy_to_clipboard(output_path: &Path) -> io::Result<()> {
+pub fn copy_to_clipboard(output_path: &Path) -> AppResult<()> {
     let mut output_contents = String::new();
     File::open(output_path)?.read_to_string(&mut output_contents)?;
 
     let mut clipboard: ClipboardContext =
-        ClipboardProvider::new().map_err(|e| Error::other(format!("Clipboard error: {}", e)))?;
+        ClipboardProvider::new().map_err(|e| AppError::Clipboard(e.to_string()))?;
 
     clipboard
         .set_contents(output_contents)
-        .map_err(|e| Error::other(format!("Clipboard error: {}", e)))?;
+        .map_err(|e| AppError::Clipboard(e.to_string()))?;
 
     Ok(())
 }

src/config.rs

@@ -1,8 +1,9 @@
 use serde::{Deserialize, Serialize};
 use std::fs;
-use std::io;
 use std::path::{Path, PathBuf};
 
+use crate::error::{AppError, AppResult};
+
 /// Main config struct used throughout the app.
 #[derive(Debug, PartialEq, Clone)]
 pub struct Config {
@@ -39,14 +40,13 @@ pub struct FileConfig {
 
 impl FileConfig {
     /// Load config from a YAML file path.
-    pub fn from_path<P: AsRef<Path>>(path: P) -> io::Result<Self> {
-        let content = fs::read_to_string(path)?;
-        let config: FileConfig = serde_yaml::from_str(&content).map_err(|e| {
-            io::Error::new(
-                io::ErrorKind::InvalidData,
-                format!("YAML parse error: {}", e),
-            )
-        })?;
+    pub fn from_path<P: AsRef<Path>>(path: P) -> AppResult<Self> {
+        let content = fs::read_to_string(path.as_ref())?;
+        let config: FileConfig =
+            serde_yaml::from_str(&content).map_err(|e| AppError::YamlParse {
+                path: path.as_ref().to_path_buf(),
+                source: e,
+            })?;
         Ok(config)
     }
 }
@@ -127,7 +127,7 @@ pub fn merge_config(file: FileConfig, cli: Config, explicit: ExplicitFlags) -> C
 /// Returns both the built `Config` and an `ExplicitFlags` struct that indicates
 /// which CLI values were actually provided on the command line (as opposed to
 /// being left as clap defaults).
-pub fn config_from_matches(matches: clap::ArgMatches) -> std::io::Result<(Config, ExplicitFlags)> {
+pub fn config_from_matches(matches: clap::ArgMatches) -> AppResult<(Config, ExplicitFlags)> {
     let directory_set = match matches.try_get_one::<String>("directory") {
         Ok(Some(_)) => true,
         Ok(None) => false,
@@ -151,24 +151,14 @@ pub fn config_from_matches(matches: clap::ArgMatches) -> std::io::Result<(Config
 
     let directory = matches
         .try_get_one::<String>("directory")
-        .map_err(|e| {
-            std::io::Error::new(
-                std::io::ErrorKind::InvalidInput,
-                format!("Missing directory: {}", e),
-            )
-        })?
-        .ok_or_else(|| std::io::Error::new(std::io::ErrorKind::InvalidInput, "Missing directory"))?
+        .map_err(|_| AppError::MissingDirectory)?
+        .ok_or(AppError::MissingDirectory)?
         .into();
 
     let output = matches
         .try_get_one::<String>("output")
-        .map_err(|e| {
-            std::io::Error::new(
-                io::ErrorKind::InvalidInput,
-                format!("Missing output: {}", e),
-            )
-        })?
-        .ok_or_else(|| std::io::Error::new(std::io::ErrorKind::InvalidInput, "Missing output"))?
+        .map_err(|_| AppError::MissingOutput)?
+        .ok_or(AppError::MissingOutput)?
         .into();
 
     let include_dirs = match matches.try_get_one::<String>("include_dirs") {
@@ -234,17 +224,13 @@ pub fn config_from_matches(matches: clap::ArgMatches) -> std::io::Result<(Config
     };
 
     let min_size = match matches.try_get_one::<String>("min_size") {
-        Ok(Some(s)) => Some(s.parse::<u64>().map_err(|_| {
-            std::io::Error::new(std::io::ErrorKind::InvalidInput, "Invalid min-size")
-        })?),
+        Ok(Some(s)) => Some(s.parse::<u64>().map_err(|_| AppError::InvalidMinSize)?),
         Ok(None) => None,
         Err(_) => None,
     };
 
     let max_size = match matches.try_get_one::<String>("max_size") {
-        Ok(Some(s)) => Some(s.parse::<u64>().map_err(|_| {
-            std::io::Error::new(std::io::ErrorKind::InvalidInput, "Invalid max-size")
-        })?),
+        Ok(Some(s)) => Some(s.parse::<u64>().map_err(|_| AppError::InvalidMaxSize)?),
         Ok(None) => None,
         Err(_) => None,
     };

src/error.rs

@@ -0,0 +1,49 @@
+use std::io;
+use std::path::PathBuf;
+
+use thiserror::Error;
+
+pub type AppResult<T> = Result<T, AppError>;
+
+#[derive(Debug, Error)]
+pub enum AppError {
+    #[error(transparent)]
+    Io(#[from] io::Error),
+
+    #[error("Clipboard error: {0}")]
+    Clipboard(String),
+
+    #[error("YAML parse error in {path}: {source}")]
+    YamlParse {
+        path: PathBuf,
+        #[source]
+        source: serde_yaml::Error,
+    },
+
+    #[error("Missing directory")]
+    MissingDirectory,
+
+    #[error("Missing output")]
+    MissingOutput,
+
+    #[error("Invalid min-size")]
+    InvalidMinSize,
+
+    #[error("Invalid max-size")]
+    InvalidMaxSize,
+
+    #[error("Config file already exists at {path}. Use --force to overwrite.")]
+    ConfigAlreadyExists { path: String },
+
+    #[error("Failed to run git clone: {0}")]
+    GitCloneExec(#[source] io::Error),
+
+    #[error("git clone failed: {0}")]
+    GitCloneFailed(String),
+
+    #[error("Failed to run git checkout: {0}")]
+    GitCheckoutExec(#[source] io::Error),
+
+    #[error("git checkout failed: {0}")]
+    GitCheckoutFailed(String),
+}