Compare commits

..
Author SHA1 Message Date
beardthelion 5da280b6ff fix(node): propagate for-each-ref failures in resolve_issue_id 2026-09-10 23:08:58 -05:00
beardthelion f2b6cebdc1 fix(node): propagate for-each-ref failures in list_issues 2026-09-10 22:56:25 -05:00
beardthelion b5048f749f fix(node): read issue refs via cat-file --batch on stdin, resolve absence by enumeration 2026-09-10 22:00:08 -05:00
beardthelion 326f5e55ac fix(node): bound issue ref names and propagate rev-parse probe failures 2026-09-10 21:30:04 -05:00
beardthelion 4fa108160a fix(node): split absent ref from unreadable object in issue reads
get_issue folded every cat-file failure into Ok(None), so a corrupt or
unreadable object store looked identical to a missing issue. close_issue
then hit that None right after resolve_issue_id had proven the ref
exists and panicked on the expect.

A shared read_issue_blob helper now re-resolves the ref with rev-parse
(which does not read the object) when cat-file fails: unresolved means
genuinely absent (Ok(None)), resolved means a real read failure
(propagated as Err). list_issues applies the same split so a degraded
store errors the listing instead of silently under-reporting, and
close_issue treats a ref deleted between resolve and read as not-found
instead of panicking.

Closes #426.
2026-09-10 19:59:12 -05:00
3 changed files with 435 additions and 394 deletions

No files matched your search

+195
View File
@@ -449,3 +449,198 @@ mod lock_pool_shed_tests {
);
}
}
/// #426: end-to-end at the handler seam. A corrupt object store behind a
/// resolving issue ref used to look identical to an absent issue: get returned
/// a fake 404, close returned a fake 404 after releasing the write guard, and
/// list silently under-reported. All three must now surface a git error.
#[cfg(test)]
mod corrupt_store_tests {
use super::*;
use axum::response::IntoResponse;
use sqlx::PgPool;
use tempfile::TempDir;
fn seed_repo(owner_did: &str, name: &str) -> crate::db::RepoRecord {
let now = Utc::now();
crate::db::RepoRecord {
id: Uuid::new_v4().to_string(),
name: name.to_string(),
owner_did: owner_did.to_string(),
description: None,
is_public: true,
default_branch: "main".to_string(),
created_at: now,
updated_at: now,
disk_path: format!("/tmp/{name}"),
forked_from: None,
machine_id: None,
}
}
/// A state whose repo store roots in `repos_dir`, so the test can lay down
/// a real repo and then corrupt it without touching /tmp.
async fn state_with_repos_dir(pool: &PgPool, repos_dir: &std::path::Path) -> AppState {
let mut state = crate::test_support::test_state(pool.clone()).await;
state.repo_store =
crate::git::repo_store::RepoStore::for_testing(repos_dir.to_path_buf(), pool.clone());
state
}
/// Bare repo at the store's expected path, holding one issue ref.
fn bare_repo_with_issue(
repos_dir: &std::path::Path,
owner: &str,
name: &str,
) -> (std::path::PathBuf, String) {
let repo_path = repos_dir
.join(owner.replace([':', '/'], "_"))
.join(format!("{name}.git"));
std::fs::create_dir_all(&repo_path).unwrap();
let out = std::process::Command::new("git")
.args(["init", "--bare"])
.arg(&repo_path)
.output()
.unwrap();
assert!(out.status.success());
let issue_id = "aaaabbbb-0000-0000-0000-000000000000".to_string();
git_issues::create_issue(
&repo_path,
&issue_id,
&serde_json::json!({
"id": issue_id,
"title": "t",
"status": "open",
})
.to_string(),
)
.unwrap();
(repo_path, issue_id)
}
/// Delete the blob object behind the issue ref and put garbage in its
/// place: `cat-file` fails while `rev-parse` still resolves the ref.
fn corrupt_issue_object(repo_path: &std::path::Path, issue_id: &str) {
let out = std::process::Command::new("git")
.args(["rev-parse", &format!("refs/gitlawb/issues/{issue_id}")])
.current_dir(repo_path)
.output()
.unwrap();
let oid = String::from_utf8(out.stdout).unwrap().trim().to_string();
let obj = repo_path.join("objects").join(&oid[..2]).join(&oid[2..]);
std::fs::remove_file(&obj).unwrap();
std::fs::write(&obj, b"garbage").unwrap();
}
/// The regression: closing over a corrupt store used to return a fake 404
/// (or panic deeper in). It must reach the caller as a git 500, and the
/// handler must return rather than unwind.
#[sqlx::test]
async fn close_issue_on_corrupt_store_returns_git_error_not_panic(pool: PgPool) {
let owner = "did:key:zISSUECORRUPTCCCCCCCCCCCCCCCCCCCCCCCCC";
let dir = TempDir::new().unwrap();
let state = state_with_repos_dir(&pool, dir.path()).await;
state
.db
.create_repo(&seed_repo(owner, "corrupt-close"))
.await
.expect("seed repo");
let (repo_path, issue_id) = bare_repo_with_issue(dir.path(), owner, "corrupt-close");
corrupt_issue_object(&repo_path, &issue_id);
let err = close_issue(
State(state),
Extension(AuthenticatedDid(owner.to_string())),
Path((owner.to_string(), "corrupt-close".to_string(), issue_id)),
)
.await
.expect_err("a corrupt store must error, not panic or 404");
assert_eq!(
err.into_response().status(),
StatusCode::INTERNAL_SERVER_ERROR,
"a read failure is a git 500, not a fake not-found"
);
}
/// get on a corrupt store: 500, not the 404 the fold used to produce.
#[sqlx::test]
async fn get_issue_on_corrupt_store_returns_500_not_404(pool: PgPool) {
let owner = "did:key:zISSUECORRUPTGETDDDDDDDDDDDDDDDDDDDDDDD";
let dir = TempDir::new().unwrap();
let state = state_with_repos_dir(&pool, dir.path()).await;
state
.db
.create_repo(&seed_repo(owner, "corrupt-get"))
.await
.expect("seed repo");
let (repo_path, issue_id) = bare_repo_with_issue(dir.path(), owner, "corrupt-get");
corrupt_issue_object(&repo_path, &issue_id);
let err = get_issue(
State(state),
Path((owner.to_string(), "corrupt-get".to_string(), issue_id)),
None,
)
.await
.expect_err("a corrupt store must error, not 404");
assert_eq!(
err.into_response().status(),
StatusCode::INTERNAL_SERVER_ERROR,
);
}
/// list on a corrupt store must fail outright; a 200 that silently drops
/// the unreadable issue is the other half of the fold.
#[sqlx::test]
async fn list_issues_on_corrupt_store_returns_git_error(pool: PgPool) {
let owner = "did:key:zISSUECORRUPTLISTEEEEEEEEEEEEEEEEEEEEEE";
let dir = TempDir::new().unwrap();
let state = state_with_repos_dir(&pool, dir.path()).await;
state
.db
.create_repo(&seed_repo(owner, "corrupt-list"))
.await
.expect("seed repo");
let (repo_path, issue_id) = bare_repo_with_issue(dir.path(), owner, "corrupt-list");
corrupt_issue_object(&repo_path, &issue_id);
let err = list_issues(
State(state),
Path((owner.to_string(), "corrupt-list".to_string())),
None,
)
.await
.expect_err("a corrupt store must error, not under-report");
assert_eq!(
err.into_response().status(),
StatusCode::INTERNAL_SERVER_ERROR,
);
}
/// Must-not direction: a genuinely absent issue still gets the 404.
#[sqlx::test]
async fn get_issue_on_absent_ref_still_returns_404(pool: PgPool) {
let owner = "did:key:zISSUEABSENTFFFFFFFFFFFFFFFFFFFFFFFFFFF";
let dir = TempDir::new().unwrap();
let state = state_with_repos_dir(&pool, dir.path()).await;
state
.db
.create_repo(&seed_repo(owner, "absent-get"))
.await
.expect("seed repo");
bare_repo_with_issue(dir.path(), owner, "absent-get");
let err = get_issue(
State(state),
Path((
owner.to_string(),
"absent-get".to_string(),
"ffffffff-0000-0000-0000-000000000000".to_string(),
)),
None,
)
.await
.expect_err("a missing issue is still not-found");
assert_eq!(err.into_response().status(), StatusCode::NOT_FOUND);
}
}
+240 -27
View File
@@ -61,6 +61,119 @@ pub fn create_issue(repo_path: &Path, issue_id: &str, json: &str) -> Result<()>
Ok(())
}
/// Issue ids are UUIDs; refs under `refs/gitlawb/issues/` only ever carry
/// `[0-9a-zA-Z_-]` names. Anything else is not a value we pass to git.
fn issue_ref_name_is_safe(ref_name: &str) -> bool {
let Some(id) = ref_name.strip_prefix("refs/gitlawb/issues/") else {
return false;
};
!id.is_empty()
&& id
.chars()
.all(|c| c.is_ascii_alphanumeric() || c == '-' || c == '_')
}
/// Resolve a ref name without putting it on a command line: enumerate refs
/// (constant argv) and match in memory. A nonzero exit propagates, so "cannot
/// determine" is an error rather than a quiet `false`.
fn ref_name_resolves(repo_path: &Path, ref_name: &str) -> Result<bool> {
// allow-unbounded-git: failure-path existence recheck, module convention.
let out = Command::new("git")
.args(["for-each-ref", "--format=%(refname)"])
.current_dir(repo_path)
.output()
.context("failed to run git for-each-ref")?;
if !out.status.success() {
let stderr = String::from_utf8_lossy(&out.stderr);
anyhow::bail!("git for-each-ref failed: {}", stderr.trim());
}
let stdout = String::from_utf8_lossy(&out.stdout);
Ok(stdout.lines().any(|line| line.trim() == ref_name))
}
/// Read the blob behind an issue ref.
///
/// `Ok(None)` means the ref itself is absent. A ref that resolves but whose
/// object cannot be read (corrupt object, unreadable store, a mid-read gc) is
/// an error, not an absence (#426).
///
/// The ref name reaches git on stdin, never argv: `cat-file --batch` answers
/// `<oid> <type> <size>\n<body>\n` for a readable object and
/// `<spec> missing\n` for an absent ref or an unreadable object alike, so the
/// `missing` case is re-resolved by name enumeration to tell them apart.
fn read_issue_blob(repo_path: &Path, ref_name: &str) -> Result<Option<String>> {
if !issue_ref_name_is_safe(ref_name) {
anyhow::bail!("refusing issue ref outside the issues namespace: {ref_name}");
}
// allow-unbounded-git: this module's spawns predate the bounded runner and
// its callers run inside issue handlers that already hold the repo guard.
let mut child = Command::new("git")
.args(["cat-file", "--batch"])
.current_dir(repo_path)
.stdin(std::process::Stdio::piped())
.stdout(std::process::Stdio::piped())
.stderr(std::process::Stdio::piped())
.spawn()
.context("failed to spawn git cat-file --batch")?;
use std::io::Write;
// Reap the child even when the write fails so a stdin error cannot drop an
// unwaited Child and leak a zombie (#53).
let write_result = match child.stdin.take() {
Some(mut stdin) => stdin
.write_all(ref_name.as_bytes())
.and_then(|()| stdin.write_all(b"\n")),
None => Err(std::io::Error::new(
std::io::ErrorKind::BrokenPipe,
"git cat-file --batch stdin unavailable",
)),
};
let output = child
.wait_with_output()
.context("git cat-file --batch failed")?;
write_result.context("failed to write ref name to git cat-file stdin")?;
if !output.status.success() {
let stderr = String::from_utf8_lossy(&output.stderr);
anyhow::bail!("git cat-file --batch failed: {}", stderr.trim());
}
// "<spec> missing\n" covers an absent ref and an unreadable object; only a
// ref that still resolves is the error case.
let missing = format!("{ref_name} missing\n");
if output.stdout.as_slice() == missing.as_bytes() {
return match ref_name_resolves(repo_path, ref_name)? {
true => anyhow::bail!("issue ref resolves but its object is unreadable: {ref_name}"),
false => Ok(None),
};
}
// Header: "<oid> <type> <size>\n" then exactly <size> bytes plus a newline.
let header_end = output
.stdout
.iter()
.position(|b| *b == b'\n')
.context("unexpected git cat-file --batch output")?;
let header = String::from_utf8_lossy(&output.stdout[..header_end]);
let mut parts = header.split(' ');
parts.next();
let obj_type = parts.next().unwrap_or("");
if obj_type != "blob" {
anyhow::bail!("issue ref {ref_name} resolves to a non-blob object");
}
let size: usize = parts
.next()
.and_then(|s| s.parse().ok())
.context("unexpected git cat-file --batch header")?;
let body = &output.stdout[header_end + 1..];
anyhow::ensure!(
body.len() >= size,
"truncated git cat-file --batch body for {ref_name}"
);
Ok(Some(String::from_utf8_lossy(&body[..size]).to_string()))
}
/// List all issue refs and return their JSON content.
pub fn list_issues(repo_path: &Path) -> Result<Vec<String>> {
// List all refs under refs/gitlawb/issues/
@@ -74,9 +187,11 @@ pub fn list_issues(repo_path: &Path) -> Result<Vec<String>> {
.output()
.context("failed to run git for-each-ref")?;
// for-each-ref exits 0 with empty output when no refs match, so a nonzero
// exit is a real enumeration failure, not "no issues yet".
if !list_output.status.success() {
// No issues yet
return Ok(vec![]);
let stderr = String::from_utf8_lossy(&list_output.stderr);
anyhow::bail!("git for-each-ref failed: {}", stderr.trim());
}
let refs_str = String::from_utf8_lossy(&list_output.stdout);
@@ -88,16 +203,12 @@ pub fn list_issues(repo_path: &Path) -> Result<Vec<String>> {
continue;
}
// Read the blob content
let cat_output = Command::new("git")
.args(["cat-file", "blob", ref_name])
.current_dir(repo_path)
.output()
.context("failed to run git cat-file")?;
if cat_output.status.success() {
let content = String::from_utf8_lossy(&cat_output.stdout).to_string();
issues.push(content);
// Read the blob content. A ref that vanished between for-each-ref and
// here is skipped; a ref that resolves but fails to read propagates so
// a degraded object store errors the listing instead of under-reporting.
match read_issue_blob(repo_path, ref_name)? {
Some(content) => issues.push(content),
None => continue,
}
}
@@ -127,8 +238,12 @@ pub fn resolve_issue_id(repo_path: &Path, id_or_prefix: &str) -> Result<Option<S
.output()
.context("failed to run git for-each-ref")?;
// for-each-ref exits 0 with empty output when nothing matches, so a
// nonzero exit is a real enumeration failure (e.g. not a repo), not
// "issue not found".
if !list.status.success() {
return Ok(None);
let stderr = String::from_utf8_lossy(&list.stderr);
anyhow::bail!("git for-each-ref failed: {}", stderr.trim());
}
let output = String::from_utf8_lossy(&list.stdout);
@@ -161,8 +276,12 @@ pub fn close_issue(repo_path: &Path, issue_id: &str) -> Result<Option<String>> {
None => return Ok(None),
};
let raw = get_issue(repo_path, &full_id)?
.expect("ref existed in resolve but not in get — should be impossible");
// A ref that resolved and is now absent was deleted between the two calls;
// any other read failure propagates as an error rather than panic (#426).
let raw = match get_issue(repo_path, &full_id)? {
Some(raw) => raw,
None => return Ok(None),
};
let mut issue: serde_json::Value =
serde_json::from_str(&raw).context("invalid issue JSON in git ref")?;
@@ -181,18 +300,7 @@ pub fn get_issue(repo_path: &Path, issue_id: &str) -> Result<Option<String>> {
};
let ref_name = format!("refs/gitlawb/issues/{full_id}");
let cat_output = Command::new("git")
.args(["cat-file", "blob", &ref_name])
.current_dir(repo_path)
.output()
.context("failed to run git cat-file")?;
if !cat_output.status.success() {
return Ok(None);
}
let content = String::from_utf8_lossy(&cat_output.stdout).to_string();
Ok(Some(content))
read_issue_blob(repo_path, &ref_name)
}
#[cfg(test)]
@@ -294,4 +402,109 @@ mod tests {
let v: serde_json::Value = serde_json::from_str(&updated).unwrap();
assert_eq!(v["status"], "closed");
}
/// Overwrite the loose object behind an issue ref with garbage, so
/// `cat-file` fails while `rev-parse` still resolves the ref (#426).
fn corrupt_issue_object(dir: &TempDir, full_id: &str) {
let oid_out = Command::new("git")
.args(["rev-parse", &format!("refs/gitlawb/issues/{full_id}")])
.current_dir(dir.path())
.output()
.unwrap();
let oid = String::from_utf8(oid_out.stdout)
.unwrap()
.trim()
.to_string();
let obj = dir
.path()
.join(".git/objects")
.join(&oid[..2])
.join(&oid[2..]);
std::fs::remove_file(&obj).unwrap();
std::fs::write(&obj, b"garbage").unwrap();
}
#[test]
fn test_get_and_close_missing_issue_return_none() {
let dir = TempDir::new().unwrap();
init_repo(&dir);
assert_eq!(get_issue(dir.path(), "nosuch00").unwrap(), None);
assert_eq!(close_issue(dir.path(), "nosuch00").unwrap(), None);
}
// #426: a directory that is not a repo makes `cat-file --batch` exit
// nonzero; that failure is an error, not a quiet None.
#[test]
fn test_issue_read_on_non_repo_errors_instead_of_none() {
let dir = TempDir::new().unwrap();
let not_a_repo = dir.path().join("not-a-repo");
std::fs::create_dir_all(&not_a_repo).unwrap();
assert!(read_issue_blob(&not_a_repo, "refs/gitlawb/issues/deadbeef").is_err());
}
// #426: the ref name is constrained to the issues namespace and a safe
// charset before it is fed to git, even on stdin (a newline would smuggle
// a second `--batch` spec).
#[test]
fn test_issue_read_rejects_ref_outside_issues_namespace() {
let dir = TempDir::new().unwrap();
init_repo(&dir);
assert!(read_issue_blob(dir.path(), "refs/heads/main").is_err());
assert!(read_issue_blob(dir.path(), "refs/gitlawb/issues/../x").is_err());
}
// #426: a failed for-each-ref enumeration is an error, not an empty list.
#[test]
fn test_list_issues_on_non_repo_errors_instead_of_empty() {
let dir = TempDir::new().unwrap();
let not_a_repo = dir.path().join("not-a-repo");
std::fs::create_dir_all(&not_a_repo).unwrap();
assert!(list_issues(&not_a_repo).is_err());
}
// #426: the same enumeration failure inside resolve_issue_id must reach
// get_issue/close_issue as an error, not a "not found" None.
#[test]
fn test_get_and_close_on_non_repo_error_instead_of_none() {
let dir = TempDir::new().unwrap();
let not_a_repo = dir.path().join("not-a-repo");
std::fs::create_dir_all(&not_a_repo).unwrap();
assert!(get_issue(&not_a_repo, "nosuch00").is_err());
assert!(close_issue(&not_a_repo, "nosuch00").is_err());
}
// #426: a ref that resolves but whose object is corrupt is a read error,
// not an absent issue. `close_issue` used to `expect()` on that None and
// panic inside a request handler holding the write guard.
#[test]
fn test_corrupt_issue_object_errors_instead_of_panicking() {
let dir = TempDir::new().unwrap();
init_repo(&dir);
let full_id = "bad00000-0000-0000-0000-000000000000";
create_issue(dir.path(), full_id, r#"{"status":"open"}"#).unwrap();
corrupt_issue_object(&dir, full_id);
assert!(get_issue(dir.path(), full_id).is_err());
assert!(close_issue(dir.path(), full_id).is_err());
assert!(list_issues(dir.path()).is_err());
}
#[test]
fn test_list_issues_returns_all() {
let dir = TempDir::new().unwrap();
init_repo(&dir);
create_issue(
dir.path(),
"aaa00000-0000-0000-0000-000000000000",
r#"{"status":"open"}"#,
)
.unwrap();
create_issue(
dir.path(),
"bbb00000-0000-0000-0000-000000000000",
r#"{"status":"open"}"#,
)
.unwrap();
assert_eq!(list_issues(dir.path()).unwrap().len(), 2);
}
}
-367
View File
@@ -19,134 +19,6 @@ const MAX_ICAPTCHA_RETRIES: usize = 2;
/// response body, so it bounds a slow download and not just a slow handshake.
const TOTAL_REQUEST_TIMEOUT: std::time::Duration = std::time::Duration::from_secs(30);
/// Whether `url` would send a signed request off this machine in cleartext.
///
/// True only for `http://` to a non-loopback host. RFC 9421 signs the request
/// but does not encrypt it, so on a plaintext hop the `Signature` header and
/// the body are both readable, and a captured signature is replayable for its
/// freshness window against any host.
///
/// Loopback is decided from the parsed address rather than a string match, so
/// `127.0.0.2`, `[::1]` and an IPv4-mapped `[::ffff:127.0.0.1]` are all
/// recognised as this machine. A value that does not parse, or that is not
/// http(s), is not this guard's business and returns false: it fails later with
/// its own error, and naming it a TLS problem would misdirect the reader.
fn is_insecure_remote(url: &str) -> bool {
let Ok(parsed) = reqwest::Url::parse(url.trim()) else {
return false;
};
if parsed.scheme() != "http" {
return false;
}
let Some(host) = parsed.host_str() else {
return false;
};
let host = host.trim_end_matches('.').to_ascii_lowercase();
if host == "localhost" {
return false;
}
// host_str() keeps the brackets on an IPv6 literal.
let bare = host.trim_start_matches('[').trim_end_matches(']');
if let Ok(ip) = bare.parse::<std::net::IpAddr>() {
if ip.is_loopback() {
return false;
}
// An IPv4-mapped IPv6 literal hides a v4 loopback from is_loopback().
if let std::net::IpAddr::V6(v6) = ip {
if let Some(v4) = v6.to_ipv4_mapped() {
if v4.is_loopback() {
return false;
}
}
}
}
true
}
/// True when `no_proxy` covers `host`: a `*` entry, an exact match, or a
/// domain suffix match (`example.com` covers `a.example.com`). Entries match
/// case-insensitively, as DNS names are.
fn no_proxy_covers(host: &str, no_proxy: &str) -> bool {
no_proxy
.split(',')
.map(str::trim)
.map(|e| e.trim_start_matches('.').to_ascii_lowercase())
.filter(|e| !e.is_empty())
.any(|e| e == "*" || host == e || host.ends_with(&format!(".{e}")))
}
/// True when a plaintext request to a loopback `host` would still leave this
/// machine under the proxy env the client was built with. A configured proxy
/// without a NO_PROXY entry for the host carries the signed request
/// off-machine in cleartext, which is the leak this module guards against.
fn loopback_goes_off_machine(host: &str, proxy_env: &(bool, String)) -> bool {
proxy_env.0 && !no_proxy_covers(host, &proxy_env.1)
}
/// The normalized host when `url` is an `http://` loopback address, else None.
/// Same loopback rules as [`is_insecure_remote`].
fn loopback_http_host(url: &str) -> Option<String> {
let parsed = reqwest::Url::parse(url.trim()).ok()?;
if parsed.scheme() != "http" {
return None;
}
let host = parsed
.host_str()?
.trim_end_matches('.')
.to_ascii_lowercase();
if host == "localhost" {
return Some(host);
}
let bare = host
.trim_start_matches('[')
.trim_end_matches(']')
.to_string();
let ip = bare.parse::<std::net::IpAddr>().ok()?;
if ip.is_loopback() {
return Some(bare);
}
if let std::net::IpAddr::V6(v6) = ip {
if v6.to_ipv4_mapped().is_some_and(|v4| v4.is_loopback()) {
return Some(bare);
}
}
None
}
/// Refuse to sign a request destined for a cleartext hop off this machine
/// unless the operator has opted in. `GITLAWB_ALLOW_INSECURE_HTTP` exists for a
/// private LAN where the operator has decided that is acceptable; its presence
/// alone opts in, matching the variable git-remote-gitlawb's guard uses for
/// the same hop. This guard is stricter than the helper's in one respect: the
/// loopback exemption does not apply when a proxy would carry the request
/// off-machine anyway. `proxy_env` is the proxy state the client was built
/// with, so the guard judges the same routing the client will use.
fn ensure_signing_transport(
node_base: &str,
allow_insecure: bool,
proxy_env: &(bool, String),
) -> Result<()> {
let insecure = is_insecure_remote(node_base)
|| loopback_http_host(node_base).is_some_and(|h| loopback_goes_off_machine(&h, proxy_env));
if allow_insecure || !insecure {
return Ok(());
}
anyhow::bail!(
"refusing to send a signed request to {node_base} over plaintext http.\n\
The request is signed but not encrypted, so the Signature header and \
the body are readable by anyone on the path, and a captured signature \
can be replayed.\n\
Use https://, or set GITLAWB_ALLOW_INSECURE_HTTP=1 to accept the risk \
(for a trusted private network only)."
)
}
/// The operator opt-in for a plaintext remote, read at request time so a test
/// or shell can set it without rebuilding the client.
fn insecure_http_allowed() -> bool {
std::env::var_os("GITLAWB_ALLOW_INSECURE_HTTP").is_some()
}
/// Follow a redirect only when it stays on the origin that issued it AND re-issues the
/// identical request-target, and only for as long as the chain bound allows.
///
@@ -186,11 +58,6 @@ fn same_origin_redirect(attempt: reqwest::redirect::Attempt<'_>) -> reqwest::red
pub struct NodeClient {
inner: reqwest::Client,
/// Proxy env state captured at client build, so the transport guard judges
/// the same routing the client was built with. `(proxied, no_proxy)` where
/// `proxied` means HTTP_PROXY/ALL_PROXY was set and `no_proxy` is the raw
/// NO_PROXY value.
proxy_env: (bool, String),
pub node_url: String,
keypair: Option<Keypair>,
}
@@ -214,17 +81,10 @@ impl NodeClient {
.user_agent(format!("gl/{} gitlawb-cli", env!("CARGO_PKG_VERSION")))
.build()
.expect("failed to build HTTP client");
let proxied = ["HTTP_PROXY", "http_proxy", "ALL_PROXY", "all_proxy"]
.iter()
.any(|k| std::env::var_os(k).is_some_and(|v| !v.is_empty()));
let no_proxy = std::env::var("NO_PROXY")
.or_else(|_| std::env::var("no_proxy"))
.unwrap_or_default();
Self {
inner,
node_url: node_url.into(),
keypair,
proxy_env: (proxied, no_proxy),
}
}
@@ -255,7 +115,6 @@ impl NodeClient {
.keypair
.as_ref()
.context("get_signed requires an identity keypair")?;
ensure_signing_transport(&self.node_url, insecure_http_allowed(), &self.proxy_env)?;
let signed = sign_request(kp, "GET", path, b"");
let req = self
.inner
@@ -272,9 +131,6 @@ impl NodeClient {
/// to be authenticated. Mirrors the conditional signing of post/put/delete.
pub async fn get_maybe_signed(&self, path: &str) -> Result<reqwest::Response> {
let url = format!("{}{}", self.node_url, path);
if self.keypair.is_some() {
ensure_signing_transport(&self.node_url, insecure_http_allowed(), &self.proxy_env)?;
}
let mut req = self.inner.get(&url);
if let Some(kp) = &self.keypair {
let signed = sign_request(kp, "GET", path, b"");
@@ -351,9 +207,6 @@ impl NodeClient {
proof: Option<&str>,
) -> Result<reqwest::Response> {
let url = format!("{}{}", self.node_url, path);
if self.keypair.is_some() {
ensure_signing_transport(&self.node_url, insecure_http_allowed(), &self.proxy_env)?;
}
let mut req = self
.inner
.request(method.parse().expect("valid HTTP method"), &url)
@@ -1415,224 +1268,4 @@ mod tests {
let out = sanitize_node_msg("ok \u{0627}\u{200D}b");
assert_eq!(out, "ok \u{0627}\u{200D}b");
}
// ── #413 plaintext-remote signing guard ──────────────────────────────
/// Holds [`ICAPTCHA_ENV_LOCK`] while it points `GITLAWB_ALLOW_INSECURE_HTTP`
/// at `value` (or removes it), restoring the prior value on drop.
struct InsecureHttpEnv {
_lock: MutexGuard<'static, ()>,
prev: Option<OsString>,
}
impl InsecureHttpEnv {
fn set(value: Option<&str>) -> Self {
let lock = ICAPTCHA_ENV_LOCK.lock().unwrap();
let prev = std::env::var_os("GITLAWB_ALLOW_INSECURE_HTTP");
match value {
Some(v) => std::env::set_var("GITLAWB_ALLOW_INSECURE_HTTP", v),
None => std::env::remove_var("GITLAWB_ALLOW_INSECURE_HTTP"),
}
InsecureHttpEnv { _lock: lock, prev }
}
}
impl Drop for InsecureHttpEnv {
fn drop(&mut self) {
match self.prev.take() {
Some(v) => std::env::set_var("GITLAWB_ALLOW_INSECURE_HTTP", v),
None => std::env::remove_var("GITLAWB_ALLOW_INSECURE_HTTP"),
}
}
}
#[test]
fn insecure_remote_flags_only_plaintext_off_machine() {
// Loopback of every spelling is this machine and exempt.
for url in [
"http://localhost",
"http://localhost:7545",
"http://127.0.0.1:7545",
"http://127.0.0.2",
"http://[::1]",
"http://[::ffff:127.0.0.1]",
// https to anywhere is encrypted; the guard is not its business.
"https://node.gitlawb.com",
// Not a URL: unparseable input fails later with its own error.
"not a url",
] {
assert!(!is_insecure_remote(url), "{url} must not be flagged");
}
// Plaintext http off this machine is the flagged shape.
for url in [
"http://10.0.0.36:7777",
"http://node.example.com",
"http://[fd00::1]",
"http://127.0.0.1.evil.example",
] {
assert!(is_insecure_remote(url), "{url} must be flagged");
}
}
#[test]
fn signing_transport_refuses_plaintext_remote() {
let no_proxy_env = (false, String::new());
let err =
ensure_signing_transport("http://10.0.0.36:7777", false, &no_proxy_env).unwrap_err();
assert!(
err.to_string().contains("plaintext http")
&& err.to_string().contains("GITLAWB_ALLOW_INSECURE_HTTP"),
"the refusal names the risk and the opt-in: {err}"
);
// Opted in, loopback, and https all pass.
assert!(ensure_signing_transport("http://10.0.0.36:7777", true, &no_proxy_env).is_ok());
assert!(ensure_signing_transport("http://localhost:7545", false, &no_proxy_env).is_ok());
assert!(ensure_signing_transport("https://node.gitlawb.com", false, &no_proxy_env).is_ok());
}
/// A signed call against a plaintext remote errors out before any request
/// leaves; the refusal must beat the send. `.invalid` NXDOMAINs fast, so a
/// missed guard surfaces as a DNS error rather than a slow timeout.
#[tokio::test]
async fn get_signed_refuses_plaintext_remote_before_sending() {
let _env = InsecureHttpEnv::set(None);
let client = NodeClient::new("http://gl-nonexistent-node.invalid", Some(test_keypair()));
let err = client.get_signed("/api/v1/x").await.unwrap_err();
assert!(
err.to_string().contains("plaintext http"),
"expected the transport refusal, got: {err}"
);
}
/// With the opt-in set, the same call passes the guard and fails later on
/// the unresolvable host, proving the env var unblocks the send rather than
/// merely being read.
#[tokio::test]
async fn get_signed_proceeds_when_insecure_http_opted_in() {
let _env = InsecureHttpEnv::set(Some("1"));
let client = NodeClient::new("http://gl-nonexistent-node.invalid", Some(test_keypair()));
let err = client.get_signed("/api/v1/x").await.unwrap_err();
assert!(
!err.to_string().contains("plaintext http"),
"the opt-in should let the request attempt the hop, got: {err}"
);
}
/// Unsigned calls are not this guard's business: no keypair means no
/// signature to leak, and the request proceeds to its own failure.
#[tokio::test]
async fn unsigned_call_to_plaintext_remote_is_ungated() {
let _env = InsecureHttpEnv::set(None);
let client = NodeClient::new("http://gl-nonexistent-node.invalid", None);
let err = client.post("/api/v1/x", b"{}").await.unwrap_err();
assert!(
!err.to_string().contains("plaintext http"),
"an unsigned request should not hit the signing guard, got: {err}"
);
}
/// The opt-in is presence-based, matching the remote helper's read.
#[test]
fn insecure_http_allowed_reads_the_env_var() {
{
let _env = InsecureHttpEnv::set(Some("1"));
assert!(insecure_http_allowed());
}
{
let _env = InsecureHttpEnv::set(None);
assert!(!insecure_http_allowed());
}
}
#[test]
fn no_proxy_covers_matches_exact_suffix_and_star() {
assert!(no_proxy_covers("localhost", "localhost,127.0.0.1"));
assert!(no_proxy_covers("127.0.0.1", "localhost, 127.0.0.1"));
assert!(no_proxy_covers("a.example.com", ".example.com"));
assert!(no_proxy_covers("a.example.com", "example.com"));
assert!(no_proxy_covers("anything", "*"));
assert!(!no_proxy_covers("localhost", "127.0.0.1"));
assert!(!no_proxy_covers("127.0.0.1", ""));
assert!(!no_proxy_covers("notevil.com", "evil.com"));
}
/// Re-exec this test binary running exactly `child_test` under the given
/// env, and prove the child actually ran one test rather than filter-
/// matching nothing (a wrong `--exact` path exits 0 vacuously).
fn run_env_child(child_test: &str, envs: &[(&str, &str)]) {
let mut cmd = std::process::Command::new(std::env::current_exe().unwrap());
cmd.args(["--exact", child_test, "--nocapture"]);
// Clear any inherited proxy state first, then apply the case's env;
// env_remove after envs would silently undo a provided NO_PROXY.
for k in [
"HTTP_PROXY",
"http_proxy",
"ALL_PROXY",
"all_proxy",
"NO_PROXY",
"no_proxy",
"GITLAWB_ALLOW_INSECURE_HTTP",
] {
cmd.env_remove(k);
}
cmd.envs(envs.iter().copied());
let out = cmd.output().unwrap();
let stdout = String::from_utf8_lossy(&out.stdout);
assert!(
stdout.contains("1 passed"),
"the child must run the test, not exit green on a filter miss. \
stdout:\n{stdout}\nstderr:\n{}",
String::from_utf8_lossy(&out.stderr)
);
assert!(
out.status.success(),
"child failed: {}",
String::from_utf8_lossy(&out.stderr)
);
}
/// A proxied loopback plaintext hop must be refused. The env plumbing is
/// checked in a re-execed child so the process-global proxy vars never
/// touch sibling tests' reqwest clients.
#[tokio::test]
async fn proxied_loopback_http_is_refused() {
if std::env::var_os("GL_PROXY_CHILD").is_none() {
run_env_child(
"http::tests::proxied_loopback_http_is_refused",
&[
("GL_PROXY_CHILD", "1"),
("HTTP_PROXY", "http://10.9.9.9:3128"),
],
);
return;
}
let client = NodeClient::new("http://127.0.0.1:1", Some(test_keypair()));
let err = client.get_signed("/api/v1/x").await.unwrap_err();
assert!(
err.to_string().contains("plaintext http"),
"a proxy without NO_PROXY carries the signed request off-machine: {err}"
);
}
/// And NO_PROXY covering the host restores the loopback exemption.
#[tokio::test]
async fn proxied_loopback_with_no_proxy_is_allowed() {
if std::env::var_os("GL_PROXY_CHILD2").is_none() {
run_env_child(
"http::tests::proxied_loopback_with_no_proxy_is_allowed",
&[
("GL_PROXY_CHILD2", "1"),
("HTTP_PROXY", "http://10.9.9.9:3128"),
("NO_PROXY", "localhost,127.0.0.1"),
],
);
return;
}
let client = NodeClient::new("http://127.0.0.1:1", Some(test_keypair()));
let err = client.get_signed("/api/v1/x").await.unwrap_err();
assert!(
!err.to_string().contains("plaintext http"),
"NO_PROXY covering the host keeps the request on this machine: {err}"
);
}
}