feat: findings refinement, new scanners, and deployment tooling (#6)

compliance-agent/src/pipeline/git.rs

@@ -1,17 +1,80 @@
 use std::path::{Path, PathBuf};
 
-use git2::{FetchOptions, Repository};
+use git2::{Cred, FetchOptions, RemoteCallbacks, Repository};
 
 use crate::error::AgentError;
 
+/// Credentials for accessing a private repository
+#[derive(Debug, Clone, Default)]
+pub struct RepoCredentials {
+    /// Path to the SSH private key (for SSH URLs)
+    pub ssh_key_path: Option<String>,
+    /// Auth token / password (for HTTPS URLs)
+    pub auth_token: Option<String>,
+    /// Username for HTTPS auth (defaults to "x-access-token")
+    pub auth_username: Option<String>,
+}
+
+impl RepoCredentials {
+    pub(crate) fn make_callbacks(&self) -> RemoteCallbacks<'_> {
+        let mut callbacks = RemoteCallbacks::new();
+        let ssh_key = self.ssh_key_path.clone();
+        let token = self.auth_token.clone();
+        let username = self.auth_username.clone();
+
+        callbacks.credentials(move |_url, username_from_url, allowed_types| {
+            // SSH key authentication
+            if allowed_types.contains(git2::CredentialType::SSH_KEY) {
+                if let Some(ref key_path) = ssh_key {
+                    let key = Path::new(key_path);
+                    if key.exists() {
+                        let user = username_from_url.unwrap_or("git");
+                        return Cred::ssh_key(user, None, key, None);
+                    }
+                }
+            }
+
+            // HTTPS userpass authentication
+            if allowed_types.contains(git2::CredentialType::USER_PASS_PLAINTEXT) {
+                if let Some(ref tok) = token {
+                    let user = username.as_deref().unwrap_or("x-access-token");
+                    return Cred::userpass_plaintext(user, tok);
+                }
+            }
+
+            Cred::default()
+        });
+
+        callbacks
+    }
+
+    fn fetch_options(&self) -> FetchOptions<'_> {
+        let mut fetch_opts = FetchOptions::new();
+        if self.has_credentials() {
+            fetch_opts.remote_callbacks(self.make_callbacks());
+        }
+        fetch_opts
+    }
+
+    fn has_credentials(&self) -> bool {
+        self.ssh_key_path
+            .as_ref()
+            .map(|p| Path::new(p).exists())
+            .unwrap_or(false)
+            || self.auth_token.is_some()
+    }
+}
+
 pub struct GitOps {
     base_path: PathBuf,
+    credentials: RepoCredentials,
 }
 
 impl GitOps {
-    pub fn new(base_path: &str) -> Self {
+    pub fn new(base_path: &str, credentials: RepoCredentials) -> Self {
         Self {
             base_path: PathBuf::from(base_path),
+            credentials,
         }
     }
 
@@ -22,17 +85,25 @@ impl GitOps {
             self.fetch(&repo_path)?;
         } else {
             std::fs::create_dir_all(&repo_path)?;
-            Repository::clone(git_url, &repo_path)?;
+            self.clone_repo(git_url, &repo_path)?;
             tracing::info!("Cloned {git_url} to {}", repo_path.display());
         }
 
         Ok(repo_path)
     }
 
+    fn clone_repo(&self, git_url: &str, repo_path: &Path) -> Result<(), AgentError> {
+        let mut builder = git2::build::RepoBuilder::new();
+        let fetch_opts = self.credentials.fetch_options();
+        builder.fetch_options(fetch_opts);
+        builder.clone(git_url, repo_path)?;
+        Ok(())
+    }
+
     fn fetch(&self, repo_path: &Path) -> Result<(), AgentError> {
         let repo = Repository::open(repo_path)?;
         let mut remote = repo.find_remote("origin")?;
-        let mut fetch_opts = FetchOptions::new();
+        let mut fetch_opts = self.credentials.fetch_options();
         remote.fetch(&[] as &[&str], Some(&mut fetch_opts), None)?;
 
         // Fast-forward to origin/HEAD
@@ -48,6 +119,15 @@ impl GitOps {
         Ok(())
     }
 
+    /// Test that we can access a remote repository (used during add validation)
+    pub fn test_access(git_url: &str, credentials: &RepoCredentials) -> Result<(), AgentError> {
+        let mut remote = git2::Remote::create_detached(git_url)?;
+        let callbacks = credentials.make_callbacks();
+        remote.connect_auth(git2::Direction::Fetch, Some(callbacks), None)?;
+        remote.disconnect()?;
+        Ok(())
+    }
+
     pub fn get_head_sha(repo_path: &Path) -> Result<String, AgentError> {
         let repo = Repository::open(repo_path)?;
         let head = repo.head()?;
@@ -63,6 +143,62 @@ impl GitOps {
         }
     }
 
+    /// Extract structured diff content between two commits
+    pub fn get_diff_content(
+        repo_path: &Path,
+        old_sha: &str,
+        new_sha: &str,
+    ) -> Result<Vec<DiffFile>, AgentError> {
+        let repo = Repository::open(repo_path)?;
+        let old_commit = repo.find_commit(git2::Oid::from_str(old_sha)?)?;
+        let new_commit = repo.find_commit(git2::Oid::from_str(new_sha)?)?;
+
+        let old_tree = old_commit.tree()?;
+        let new_tree = new_commit.tree()?;
+
+        let diff = repo.diff_tree_to_tree(Some(&old_tree), Some(&new_tree), None)?;
+
+        let mut diff_files: Vec<DiffFile> = Vec::new();
+
+        diff.print(git2::DiffFormat::Patch, |delta, _hunk, line| {
+            let file_path = delta
+                .new_file()
+                .path()
+                .map(|p| p.to_string_lossy().to_string())
+                .unwrap_or_default();
+
+            // Find or create the DiffFile entry
+            let idx = if let Some(pos) = diff_files.iter().position(|f| f.path == file_path) {
+                pos
+            } else {
+                diff_files.push(DiffFile {
+                    path: file_path,
+                    hunks: String::new(),
+                });
+                diff_files.len() - 1
+            };
+            let diff_file = &mut diff_files[idx];
+
+            let prefix = match line.origin() {
+                '+' => "+",
+                '-' => "-",
+                ' ' => " ",
+                _ => "",
+            };
+
+            let content = std::str::from_utf8(line.content()).unwrap_or("");
+            diff_file.hunks.push_str(prefix);
+            diff_file.hunks.push_str(content);
+
+            true
+        })?;
+
+        // Filter out binary files and very large diffs
+        diff_files.retain(|f| !f.hunks.is_empty() && f.hunks.len() < 50_000);
+
+        Ok(diff_files)
+    }
+
     #[allow(dead_code)]
     pub fn get_changed_files(
         repo_path: &Path,
@@ -94,3 +230,10 @@ impl GitOps {
         Ok(files)
     }
 }
+
+/// A file changed between two commits with its diff content
+#[derive(Debug, Clone)]
+pub struct DiffFile {
+    pub path: String,
+    pub hunks: String,
+}