mirror of
https://github.com/Twigpine/node.git
synced 2026-11-08 17:55:53 -10:00
Compare commits
5
Commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
c805e35f40 | ||
|
|
a4026e84ff | ||
|
|
38bab4191b | ||
|
|
d84c445f94 | ||
|
|
42cc893fb3 |
No files matched your search
+1
-1
@@ -81,7 +81,7 @@ time once updated.
|
||||
|
||||
**Requirements:**
|
||||
- Rust stable (≥ 1.91) — install via [rustup](https://rustup.rs)
|
||||
- PostgreSQL — required for the node. Use the bundled `docker-compose.yml` for local dev.
|
||||
- PostgreSQL 16+ — required for the node (it uses `pg_input_is_valid`, which exists only on PostgreSQL 16 and later). Use the bundled `docker-compose.yml` for local dev.
|
||||
- Docker (optional, for full-stack local testing)
|
||||
|
||||
**Environment variables:**
|
||||
|
||||
@@ -53,6 +53,7 @@ Good today:
|
||||
|
||||
- Local or Docker node startup.
|
||||
- Postgres-backed repo metadata.
|
||||
- Bounded GraphQL queries with [repository pagination](docs/graphql-pagination.md).
|
||||
- Bare git repository storage.
|
||||
- Git smart-HTTP clone/fetch/push.
|
||||
- RFC 9421-signed writes.
|
||||
@@ -311,6 +312,7 @@ metadata local disk / optional S3
|
||||
| DID | A user, agent, or node identity derived from an Ed25519 public key. |
|
||||
| HTTP Signature | RFC 9421 signature proving control of the DID key for write requests. |
|
||||
| Ref certificate | Signed record of a ref update. Useful for audit and replication. |
|
||||
| Ref certificate versioning | The wire format is versioned; new certificates are currently issued as v1. `gl cert show <repo> <id> --verify` requires `--expect-node <did>`, and the queried node's self-reported DID is **not** accepted as a trust anchor. v2 is reserved for a future payload shape that carries the version inside the signed bytes; this client refuses to verify v2+ rather than guessing. |
|
||||
| UCAN | Delegation token for future capability-based workflows. |
|
||||
| Peer announce | Node-to-node HTTP announcement of DID + public URL. |
|
||||
| Gossipsub | libp2p topic for ref-update events. |
|
||||
|
||||
@@ -137,6 +137,11 @@ enum ShimMode {
|
||||
struct Shim {
|
||||
base_url: String,
|
||||
posts: Arc<AtomicUsize>,
|
||||
/// Advertisement (GET /info/refs) count. One `git fetch` performs exactly
|
||||
/// one advertisement, so tests assert this is EXACTLY one: any fetch-level
|
||||
/// retry that comes back re-advertises and goes red on the spot, which the
|
||||
/// lower-bound POST assertions alone cannot see (#275 round 6).
|
||||
gets: Arc<AtomicUsize>,
|
||||
stop: Arc<AtomicBool>,
|
||||
handle: Option<std::thread::JoinHandle<()>>,
|
||||
}
|
||||
@@ -166,15 +171,17 @@ fn start_shim(repo: PathBuf, mode: ShimMode) -> Shim {
|
||||
let addr = listener.local_addr().unwrap();
|
||||
let base_url = format!("http://{addr}");
|
||||
let posts = Arc::new(AtomicUsize::new(0));
|
||||
let gets = Arc::new(AtomicUsize::new(0));
|
||||
let stop = Arc::new(AtomicBool::new(false));
|
||||
|
||||
let posts_t = posts.clone();
|
||||
let gets_t = gets.clone();
|
||||
let stop_t = stop.clone();
|
||||
let handle = std::thread::spawn(move || {
|
||||
while !stop_t.load(Ordering::SeqCst) {
|
||||
match listener.accept() {
|
||||
Ok((stream, _)) => {
|
||||
handle_conn(stream, &repo, mode, &posts_t);
|
||||
handle_conn(stream, &repo, mode, &posts_t, &gets_t);
|
||||
}
|
||||
Err(ref e) if e.kind() == std::io::ErrorKind::WouldBlock => {
|
||||
std::thread::sleep(Duration::from_millis(5));
|
||||
@@ -187,6 +194,7 @@ fn start_shim(repo: PathBuf, mode: ShimMode) -> Shim {
|
||||
Shim {
|
||||
base_url,
|
||||
posts,
|
||||
gets,
|
||||
stop,
|
||||
handle: Some(handle),
|
||||
}
|
||||
@@ -212,7 +220,13 @@ fn normalize_accepted_stream(stream: &TcpStream) {
|
||||
stream.set_read_timeout(Some(Duration::from_secs(30))).ok();
|
||||
}
|
||||
|
||||
fn handle_conn(stream: TcpStream, repo: &Path, mode: ShimMode, posts: &AtomicUsize) {
|
||||
fn handle_conn(
|
||||
stream: TcpStream,
|
||||
repo: &Path,
|
||||
mode: ShimMode,
|
||||
posts: &AtomicUsize,
|
||||
gets: &AtomicUsize,
|
||||
) {
|
||||
normalize_accepted_stream(&stream);
|
||||
let mut reader = BufReader::new(stream);
|
||||
|
||||
@@ -263,6 +277,7 @@ fn handle_conn(stream: TcpStream, repo: &Path, mode: ShimMode, posts: &AtomicUsi
|
||||
receive_pack(repo, false, &body),
|
||||
)
|
||||
} else if method == "GET" && target.contains("/info/refs") {
|
||||
gets.fetch_add(1, Ordering::SeqCst);
|
||||
// v0 advertisement, wrapped exactly as the node's info_refs does.
|
||||
let adv = upload_pack(repo, true, b"");
|
||||
let mut wrapped = pkt(b"# service=git-upload-pack\n");
|
||||
@@ -1007,6 +1022,7 @@ fn shim_answers_a_connection_that_arrives_non_blocking() {
|
||||
|
||||
let server = std::thread::spawn(move || {
|
||||
let posts = AtomicUsize::new(0);
|
||||
let gets = AtomicUsize::new(0);
|
||||
let stream = loop {
|
||||
match listener.accept() {
|
||||
Ok((s, _)) => break s,
|
||||
@@ -1021,7 +1037,7 @@ fn shim_answers_a_connection_that_arrives_non_blocking() {
|
||||
// the assertions below run on every platform.
|
||||
stream.set_nonblocking(true).unwrap();
|
||||
accepted_tx.send(()).unwrap();
|
||||
handle_conn(stream, &repo, ShimMode::Normal, &posts);
|
||||
handle_conn(stream, &repo, ShimMode::Normal, &posts, &gets);
|
||||
});
|
||||
|
||||
let mut client = TcpStream::connect(addr).unwrap();
|
||||
@@ -1085,6 +1101,17 @@ fn real_git_multi_round_fetch_completes() {
|
||||
posts >= 2,
|
||||
"fixture did not force multi-round negotiation (observed {posts} POST(s)); the bridging path was not exercised"
|
||||
);
|
||||
// Exactly one advertisement: the POST bound above is a floor, so a
|
||||
// reintroduced fetch-level retry could satisfy it by running a second full
|
||||
// fetch instead of multi-round negotiation. Re-advertising is what a
|
||||
// second fetch cannot avoid, so this is the committed guard on the
|
||||
// retry's absence.
|
||||
let gets = shim.gets.load(Ordering::SeqCst);
|
||||
assert_eq!(
|
||||
gets, 1,
|
||||
"expected exactly one advertisement GET per fetch; {gets} means a \
|
||||
fetch-level retry is back"
|
||||
);
|
||||
|
||||
// The fetched tip is present and the clone's object graph is intact.
|
||||
let server_head = String::from_utf8(git(&server, &["rev-parse", "HEAD"])).unwrap();
|
||||
@@ -1177,6 +1204,17 @@ fn real_git_withheld_shaped_first_post() {
|
||||
"helper hung on a withheld-shaped response (should forward-and-terminate, not deadlock). stderr:\n{stderr}"
|
||||
);
|
||||
|
||||
// Exactly one advertisement, pass or fail: the POST assertions below are
|
||||
// floors, so a reintroduced fetch-level retry could mask the withheld
|
||||
// shape behind a second full fetch. A retry cannot avoid re-advertising,
|
||||
// so this is the committed guard on its absence.
|
||||
let gets = shim.gets.load(Ordering::SeqCst);
|
||||
assert_eq!(
|
||||
gets, 1,
|
||||
"expected exactly one advertisement GET per fetch; {gets} means a \
|
||||
fetch-level retry is back"
|
||||
);
|
||||
|
||||
if out.status.success() {
|
||||
// Real git accepted the mid-negotiation pack: the withheld multi-round
|
||||
// path works end to end with no extra handling.
|
||||
|
||||
@@ -52,6 +52,7 @@ pub async fn list_certs(
|
||||
"node_did": c.node_did,
|
||||
"signature": c.signature,
|
||||
"issued_at": c.issued_at,
|
||||
"version": c.version,
|
||||
})
|
||||
})
|
||||
.collect();
|
||||
@@ -92,5 +93,6 @@ pub async fn get_cert(
|
||||
"node_did": cert.node_did,
|
||||
"signature": cert.signature,
|
||||
"issued_at": cert.issued_at,
|
||||
"version": cert.version,
|
||||
})))
|
||||
}
|
||||
@@ -11,7 +11,8 @@ use crate::state::AppState;
|
||||
|
||||
/// Hard ceiling on rows any ref-update feed returns in one request. Shared by the
|
||||
/// shared collector's clamp and the per-handler request caps so they can't drift.
|
||||
const MAX_VISIBLE_REF_UPDATES: i64 = 200;
|
||||
/// `pub(crate)` so the GraphQL complexity meter can price against the same bound.
|
||||
pub(crate) const MAX_VISIBLE_REF_UPDATES: i64 = 200;
|
||||
|
||||
/// Collect up to `limit` ref-update rows visible to `caller`, newest first,
|
||||
/// paging past rows the feed gate drops. Filtering after a plain SQL `LIMIT`
|
||||
@@ -437,6 +438,7 @@ mod ref_updates_feed_tests {
|
||||
node_did: "did:key:z6MkNode".into(),
|
||||
signature: "sig".into(),
|
||||
issued_at: Utc::now().to_rfc3339(),
|
||||
version: 1,
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
@@ -8367,6 +8367,7 @@ mod tests {
|
||||
#[tokio::test]
|
||||
async fn get_by_cid_per_source_cap_sheds_same_source_admits_other() {
|
||||
let mut state = crate::test_support::test_state_lazy();
|
||||
state.db.pool().close().await;
|
||||
// Global pool has room; the per-source cap is 1.
|
||||
state.git_ipfs_walk_semaphore = Arc::new(Semaphore::new(8));
|
||||
state.git_ipfs_walk_per_caller = crate::rate_limit::PerCallerConcurrency::new(1, 100);
|
||||
@@ -8393,16 +8394,23 @@ mod tests {
|
||||
"a source at its per-source /ipfs walk cap must shed 503 with global capacity free"
|
||||
);
|
||||
|
||||
let bytes = axum::body::to_bytes(resp.into_body(), 1024).await.unwrap();
|
||||
let body: serde_json::Value = serde_json::from_slice(&bytes).unwrap();
|
||||
assert_eq!(body["error"], "overloaded");
|
||||
|
||||
// A DIFFERENT source is NOT shed by the per-source cap: it clears admission and
|
||||
// proceeds (then errors on the lazy DB, which is not a 503).
|
||||
// proceeds to the closed DB, which has a distinct db_unavailable error code.
|
||||
let resp = ipfs_router(state)
|
||||
.oneshot(get_cid(&cid, Some(other)))
|
||||
.await
|
||||
.unwrap();
|
||||
assert_ne!(
|
||||
resp.status(),
|
||||
StatusCode::SERVICE_UNAVAILABLE,
|
||||
"a different source must not be shed by the per-source cap"
|
||||
assert_eq!(resp.status(), StatusCode::SERVICE_UNAVAILABLE);
|
||||
let bytes = axum::body::to_bytes(resp.into_body(), 1024).await.unwrap();
|
||||
let body: serde_json::Value = serde_json::from_slice(&bytes).unwrap();
|
||||
assert_eq!(
|
||||
body["error"],
|
||||
crate::error::DB_UNAVAILABLE_CODE,
|
||||
"a different source must clear admission and reach the closed database"
|
||||
);
|
||||
}
|
||||
|
||||
|
||||
@@ -247,6 +247,40 @@ pub struct InfoRefsQuery {
|
||||
|
||||
// ── Handlers ──────────────────────────────────────────────────────────────
|
||||
|
||||
/// Validate a repository name at the create/fork write paths. The charset is
|
||||
/// restricted, and the length is bounded so every cursor the server emits
|
||||
/// parses back: `repo_cursor` embeds the name in a base64(JSON) cursor that
|
||||
/// `parse_repo_cursor` rejects over 4096 bytes (#465 4th round).
|
||||
///
|
||||
/// This is the API-side validator, and it deliberately differs from the
|
||||
/// stricter disk-side `validate_repo_name` in `git/repo_store.rs`: this one
|
||||
/// admits names the store rejects (empty, leading `-`, non-ASCII
|
||||
/// alphanumeric) and rejects `.`, which the store allows. The divergence
|
||||
/// predates this bound (#412 owns the fork half), so a store-rejected name
|
||||
/// still fails later at `repo_store.init` after the proof is spent. Do not
|
||||
/// "fix" the divergence here; the length bound below is the one that keeps
|
||||
/// emitted cursors parseable, and it is shared via `MAX_REPO_NAME_LEN` so the
|
||||
/// two validators cannot drift apart on length.
|
||||
fn validate_repo_name(name: &str) -> Result<()> {
|
||||
// Sanitize name: alphanumeric, hyphens, underscores only
|
||||
if !name
|
||||
.chars()
|
||||
.all(|c| c.is_alphanumeric() || c == '-' || c == '_')
|
||||
{
|
||||
return Err(AppError::BadRequest(
|
||||
"repo name must contain only alphanumeric characters, hyphens, and underscores".into(),
|
||||
));
|
||||
}
|
||||
// Byte length, not char count: the cursor budget is measured in bytes.
|
||||
if name.len() > crate::db::MAX_REPO_NAME_LEN {
|
||||
return Err(AppError::BadRequest(format!(
|
||||
"repo name must be at most {} bytes",
|
||||
crate::db::MAX_REPO_NAME_LEN
|
||||
)));
|
||||
}
|
||||
Ok(())
|
||||
}
|
||||
|
||||
/// POST /api/v1/repos
|
||||
/// Create a new repository. Requires HTTP Signature auth.
|
||||
pub async fn create_repo(
|
||||
@@ -261,16 +295,7 @@ pub async fn create_repo(
|
||||
// rejected request (bad name, already exists) never burns a valid proof.
|
||||
let proof = crate::icaptcha::verify_request(&headers, &auth.0)?;
|
||||
|
||||
// Sanitize name: alphanumeric, hyphens, underscores only
|
||||
if !req
|
||||
.name
|
||||
.chars()
|
||||
.all(|c| c.is_alphanumeric() || c == '-' || c == '_')
|
||||
{
|
||||
return Err(AppError::BadRequest(
|
||||
"repo name must contain only alphanumeric characters, hyphens, and underscores".into(),
|
||||
));
|
||||
}
|
||||
validate_repo_name(&req.name)?;
|
||||
|
||||
// default_branch is caller-supplied and becomes a PR's target_branch when the
|
||||
// PR omits one, which is interpolated into a git revision argument. Validate
|
||||
@@ -3774,15 +3799,7 @@ pub async fn fork_repo(
|
||||
let fork_name = req.name.unwrap_or_else(|| source.name.clone());
|
||||
let forker_did = auth.0;
|
||||
|
||||
// Validate fork name
|
||||
if !fork_name
|
||||
.chars()
|
||||
.all(|c| c.is_alphanumeric() || c == '-' || c == '_')
|
||||
{
|
||||
return Err(AppError::BadRequest(
|
||||
"repo name must contain only alphanumeric characters, hyphens, and underscores".into(),
|
||||
));
|
||||
}
|
||||
validate_repo_name(&fork_name)?;
|
||||
|
||||
// Same barrier every other repo-creation route goes through. The character
|
||||
// allowlist above is vacuously true on an empty name, and `repo_disk_path`
|
||||
@@ -5049,6 +5066,50 @@ mod tests {
|
||||
peer_mock.assert_async().await;
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn repo_name_validation_rejects_bad_charset_and_overlong_names() {
|
||||
assert!(validate_repo_name("ok-name_123").is_ok());
|
||||
assert!(validate_repo_name(&"a".repeat(crate::db::MAX_REPO_NAME_LEN)).is_ok());
|
||||
// The bound is in bytes: the cursor budget is measured in bytes.
|
||||
let overlong = "a".repeat(crate::db::MAX_REPO_NAME_LEN + 1);
|
||||
let err = validate_repo_name(&overlong).unwrap_err();
|
||||
assert!(
|
||||
matches!(err, AppError::BadRequest(_)),
|
||||
"overlong name must be a 400, got: {err:?}"
|
||||
);
|
||||
assert!(validate_repo_name("bad name!").is_err());
|
||||
// Empty names were already admissible before the length bound; the
|
||||
// bound does not change that.
|
||||
assert!(validate_repo_name("").is_ok());
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn create_repo_rejects_overlong_name_through_handler() {
|
||||
// Pins the wiring: `create_repo` must call `validate_repo_name`
|
||||
// before any database access. The lazy state never connects, so
|
||||
// deleting the call site would let the handler proceed to `get_repo`
|
||||
// and fail with a connection error instead of BadRequest.
|
||||
let state = crate::test_support::test_state_lazy();
|
||||
let overlong = "a".repeat(crate::db::MAX_REPO_NAME_LEN + 1);
|
||||
let err = create_repo(
|
||||
State(state),
|
||||
Extension(AuthenticatedDid(OWNER_DID.to_owned())),
|
||||
axum::http::HeaderMap::new(),
|
||||
Json(CreateRepoRequest {
|
||||
name: overlong,
|
||||
description: None,
|
||||
is_public: true,
|
||||
default_branch: "main".into(),
|
||||
}),
|
||||
)
|
||||
.await
|
||||
.unwrap_err();
|
||||
assert!(
|
||||
matches!(err, AppError::BadRequest(ref msg) if msg.contains("at most")),
|
||||
"overlong name through create_repo must be a 400, got: {err:?}"
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn upload_pack_request_finalizes_only_with_done_pktline() {
|
||||
let want = "0032want 1111111111111111111111111111111111111111\n";
|
||||
@@ -9179,6 +9240,7 @@ mod tests {
|
||||
/// A pkt-line receive-pack body carrying one branch-create ref update, so the
|
||||
/// handler's post-receive tail resolves a non-empty new-tip set (the delta
|
||||
/// scan's git stages run).
|
||||
#[cfg(unix)]
|
||||
fn ref_update_body(new_sha: &str) -> axum::body::Bytes {
|
||||
let line = format!("{ZERO_SHA} {new_sha} refs/heads/main");
|
||||
axum::body::Bytes::from(format!("{:04x}{}0000", line.len() + 4, line))
|
||||
@@ -11636,6 +11698,7 @@ mod tests {
|
||||
)
|
||||
}
|
||||
|
||||
#[cfg(unix)]
|
||||
fn f2a_log(log: &std::path::Path) -> String {
|
||||
std::fs::read_to_string(log).unwrap_or_default()
|
||||
}
|
||||
@@ -11643,6 +11706,7 @@ mod tests {
|
||||
/// Withheld-walk children run so far. `ls-tree` is the walk's signature child
|
||||
/// (`blob_paths` lists every reachable commit's tree); the delta scan and the
|
||||
/// full-scan fallback use `rev-list` / `cat-file` instead.
|
||||
#[cfg(unix)]
|
||||
fn f2a_walks(log: &std::path::Path) -> usize {
|
||||
f2a_log(log)
|
||||
.lines()
|
||||
@@ -11654,6 +11718,7 @@ mod tests {
|
||||
/// the withheld walk actually runs rather than taking the no-rule shortcut).
|
||||
/// The repo's on-disk path is passed to the tail directly, so no repo_store or
|
||||
/// receive-pack plumbing is involved.
|
||||
#[cfg(unix)]
|
||||
async fn f2a_state(
|
||||
pool: sqlx::PgPool,
|
||||
git_bin: &str,
|
||||
@@ -11685,6 +11750,7 @@ mod tests {
|
||||
(state, rec)
|
||||
}
|
||||
|
||||
#[cfg(unix)]
|
||||
fn f2a_update(ref_name: &str, new_sha: &str) -> Vec<RefUpdate> {
|
||||
vec![RefUpdate {
|
||||
old_sha: ZERO_SHA.to_string(),
|
||||
@@ -11693,6 +11759,7 @@ mod tests {
|
||||
}]
|
||||
}
|
||||
|
||||
#[cfg(unix)]
|
||||
const F2A_PUSHER: &str = "did:key:z6MkF2aPusherAAAAAAAAAAAAAAAAAAAAAAAAAA";
|
||||
|
||||
/// When publish durability is fenced, the tail must not run walks or take
|
||||
@@ -11805,6 +11872,7 @@ mod tests {
|
||||
}
|
||||
/// Poll `cond` until it holds, with a bound so a regression fails the test
|
||||
/// rather than hanging the suite.
|
||||
#[cfg(unix)]
|
||||
async fn f2a_wait_for(mut cond: impl FnMut() -> bool, what: &str) {
|
||||
let deadline = std::time::Instant::now() + std::time::Duration::from_secs(20);
|
||||
while !cond() {
|
||||
@@ -11819,6 +11887,7 @@ mod tests {
|
||||
/// A `rev-list --objects` line names the tips a DELTA scan was asked to resolve,
|
||||
/// so it attributes that scan to one push's tips. The withheld walk's own
|
||||
/// `rev-list --all` / `ls-tree` lines never carry a tip as an argument this way.
|
||||
#[cfg(unix)]
|
||||
fn f2a_delta_scanned(log: &std::path::Path, tip: &str) -> bool {
|
||||
f2a_log(log)
|
||||
.lines()
|
||||
@@ -11967,6 +12036,7 @@ mod tests {
|
||||
|
||||
/// Mount a Pinata upload endpoint that assigns every object the same CID, and
|
||||
/// point the state at it. Returns the server (kept alive by the caller) and CID.
|
||||
#[cfg(unix)]
|
||||
async fn f2a_pinata(state: &mut AppState) -> (mockito::ServerGuard, String) {
|
||||
let cid = "bafyf2acoalescedmapping".to_string();
|
||||
let mut server = mockito::Server::new_async().await;
|
||||
@@ -11986,6 +12056,7 @@ mod tests {
|
||||
|
||||
/// Poll the branch to CID table until the push's mapping lands (the Pinata
|
||||
/// worker is detached), bounded so a regression fails rather than hangs.
|
||||
#[cfg(unix)]
|
||||
async fn f2a_wait_for_branch_cid(
|
||||
db: &crate::db::Db,
|
||||
slug: &str,
|
||||
@@ -12005,6 +12076,7 @@ mod tests {
|
||||
}
|
||||
}
|
||||
|
||||
#[cfg(unix)]
|
||||
fn f2a_slug(rec: &crate::db::RepoRecord) -> String {
|
||||
format!(
|
||||
"{}/{}",
|
||||
@@ -12139,6 +12211,7 @@ mod tests {
|
||||
// and `z6p2fail`), and owner-only push is on by default, so the identity has to
|
||||
// follow the repo each push targets rather than being fixed for both.
|
||||
|
||||
#[cfg(unix)]
|
||||
fn p2_push(
|
||||
state: &AppState,
|
||||
owner: &str,
|
||||
@@ -12157,6 +12230,7 @@ mod tests {
|
||||
)
|
||||
}
|
||||
|
||||
#[cfg(unix)]
|
||||
fn p2_logged(log: &std::path::Path, prefix: &str) -> bool {
|
||||
f2a_log(log).lines().any(|l| l.starts_with(prefix))
|
||||
}
|
||||
@@ -13152,6 +13226,7 @@ exit 0
|
||||
/// runs exactly one `rev-list --all`, so this counts the walks that were attempted
|
||||
/// (the `ls-tree` counter above cannot: a walk whose enumeration fails never gets
|
||||
/// to `ls-tree`).
|
||||
#[cfg(unix)]
|
||||
fn f2b_walk_attempts(log: &std::path::Path) -> usize {
|
||||
f2a_log(log)
|
||||
.lines()
|
||||
|
||||
@@ -175,7 +175,7 @@ pub async fn create_task(
|
||||
updated_at: now,
|
||||
deadline: body.deadline,
|
||||
};
|
||||
state.db.create_task(&task).await.map_err(db_error)?;
|
||||
let task = state.db.create_task(&task).await.map_err(db_error)?;
|
||||
Ok((StatusCode::CREATED, Json(task_to_json(&task))))
|
||||
}
|
||||
|
||||
@@ -228,16 +228,28 @@ pub async fn claim_task(
|
||||
return Err(forbidden("assignee_did must be the authenticated signer"));
|
||||
}
|
||||
let task = state.db.claim_task(&id, &auth.0).await.map_err(|e| {
|
||||
if e.downcast_ref::<crate::db::TaskReservedForOtherAssignee>()
|
||||
.is_some()
|
||||
{
|
||||
return forbidden("task not claimable: reserved for another assignee");
|
||||
}
|
||||
(
|
||||
StatusCode::CONFLICT,
|
||||
Json(json!({ "error": e.to_string() })),
|
||||
)
|
||||
})?;
|
||||
let by_did = task
|
||||
.assignee_did
|
||||
.as_deref()
|
||||
.map(crate::db::trim_assignee_did)
|
||||
.filter(|s| !s.is_empty())
|
||||
.map(str::to_string)
|
||||
.unwrap_or_else(|| auth.0.clone());
|
||||
let _ = state.task_event_tx.send(TaskEventBroadcast {
|
||||
task_id: id,
|
||||
old_status: "pending".to_string(),
|
||||
new_status: "claimed".to_string(),
|
||||
by_did: auth.0,
|
||||
by_did,
|
||||
at: Utc::now().to_rfc3339(),
|
||||
});
|
||||
Ok(Json(task_to_json(&task)))
|
||||
@@ -272,14 +284,14 @@ pub async fn complete_task(
|
||||
})?;
|
||||
if !crate::api::did_matches(
|
||||
&auth.0,
|
||||
existing.assignee_did.as_deref().unwrap_or_default(),
|
||||
crate::db::trim_assignee_did(existing.assignee_did.as_deref().unwrap_or_default()),
|
||||
) {
|
||||
return Err(forbidden("only the task assignee can complete it"));
|
||||
}
|
||||
let by_did = auth.0;
|
||||
let task = state
|
||||
.db
|
||||
.finish_task(&id, "completed", body.result.as_deref())
|
||||
.finish_task(&id, "completed", body.result.as_deref(), &by_did)
|
||||
.await
|
||||
.map_err(|e| {
|
||||
(
|
||||
@@ -287,6 +299,13 @@ pub async fn complete_task(
|
||||
Json(json!({ "error": e.to_string() })),
|
||||
)
|
||||
})?;
|
||||
let by_did = task
|
||||
.assignee_did
|
||||
.as_deref()
|
||||
.map(crate::db::trim_assignee_did)
|
||||
.filter(|s| !s.is_empty())
|
||||
.map(str::to_string)
|
||||
.unwrap_or(by_did);
|
||||
let _ = state.task_event_tx.send(TaskEventBroadcast {
|
||||
task_id: id,
|
||||
old_status: "claimed".to_string(),
|
||||
@@ -325,7 +344,7 @@ pub async fn fail_task(
|
||||
})?;
|
||||
if !crate::api::did_matches(
|
||||
&auth.0,
|
||||
existing.assignee_did.as_deref().unwrap_or_default(),
|
||||
crate::db::trim_assignee_did(existing.assignee_did.as_deref().unwrap_or_default()),
|
||||
) {
|
||||
return Err(forbidden("only the task assignee can fail it"));
|
||||
}
|
||||
@@ -333,7 +352,7 @@ pub async fn fail_task(
|
||||
let reason = body.reason.unwrap_or_default();
|
||||
let task = state
|
||||
.db
|
||||
.finish_task(&id, "failed", Some(&reason))
|
||||
.finish_task(&id, "failed", Some(&reason), &by_did)
|
||||
.await
|
||||
.map_err(|e| {
|
||||
(
|
||||
@@ -341,6 +360,13 @@ pub async fn fail_task(
|
||||
Json(json!({ "error": e.to_string() })),
|
||||
)
|
||||
})?;
|
||||
let by_did = task
|
||||
.assignee_did
|
||||
.as_deref()
|
||||
.map(crate::db::trim_assignee_did)
|
||||
.filter(|s| !s.is_empty())
|
||||
.map(str::to_string)
|
||||
.unwrap_or(by_did);
|
||||
let _ = state.task_event_tx.send(TaskEventBroadcast {
|
||||
task_id: id,
|
||||
old_status: "claimed".to_string(),
|
||||
|
||||
+416
-10
@@ -11,6 +11,74 @@ use uuid::Uuid;
|
||||
use crate::db::RefCertificate;
|
||||
use crate::state::AppState;
|
||||
|
||||
/// Build the v1 signing payload — the EXACT bytes the node signs and
|
||||
/// gl's `verify_signature` reconstructs. This is the single source
|
||||
/// of truth shared by `issue_ref_certificate` and the frozen
|
||||
/// canonical-form tests below; drift here is what would break every
|
||||
/// existing cert.
|
||||
///
|
||||
/// Field order and key set are fixed: a default `serde_json::Value`
|
||||
/// serializes `Map<String, Value>` with sorted keys, so any change to
|
||||
/// the literal is observable as a different byte sequence on the
|
||||
/// wire.
|
||||
///
|
||||
/// v1 is the unversioned legacy shape: no `version` key in the signed
|
||||
/// JSON. From v2 onward the version belongs INSIDE the signed bytes
|
||||
/// (see `v2_signing_payload`): leaving it as an unsigned sibling
|
||||
/// would let a future v2 cert be downgraded to v1 and still verify
|
||||
/// cleanly, since the bytes would be identical.
|
||||
pub(crate) fn v1_signing_payload(
|
||||
repo_id: &str,
|
||||
ref_name: &str,
|
||||
old_sha: &str,
|
||||
new_sha: &str,
|
||||
pusher_did: &str,
|
||||
node_did: &str,
|
||||
issued_at: &str,
|
||||
) -> serde_json::Value {
|
||||
serde_json::json!({
|
||||
"repo_id": repo_id,
|
||||
"ref": ref_name,
|
||||
"old": old_sha,
|
||||
"new": new_sha,
|
||||
"pusher": pusher_did,
|
||||
"node": node_did,
|
||||
"ts": issued_at,
|
||||
})
|
||||
}
|
||||
|
||||
/// Build the v2 signing payload — the future shape for versioned
|
||||
/// certs. Identical to v1 except the wire `version` is part of the
|
||||
/// signed bytes, so stripping or flipping the `version` column
|
||||
/// invalidates the signature instead of verifying cleanly under the
|
||||
/// other version's path.
|
||||
///
|
||||
/// NOT yet issued: `issue_ref_certificate` still stamps v1 because
|
||||
/// the shipped `gl` verifier only supports v1. This builder exists
|
||||
/// to pin the downgrade-resistant shape now, before any v2 cert is
|
||||
/// ever signed.
|
||||
#[allow(dead_code)]
|
||||
pub(crate) fn v2_signing_payload(
|
||||
repo_id: &str,
|
||||
ref_name: &str,
|
||||
old_sha: &str,
|
||||
new_sha: &str,
|
||||
pusher_did: &str,
|
||||
node_did: &str,
|
||||
issued_at: &str,
|
||||
) -> serde_json::Value {
|
||||
serde_json::json!({
|
||||
"repo_id": repo_id,
|
||||
"ref": ref_name,
|
||||
"old": old_sha,
|
||||
"new": new_sha,
|
||||
"pusher": pusher_did,
|
||||
"node": node_did,
|
||||
"ts": issued_at,
|
||||
"version": 2,
|
||||
})
|
||||
}
|
||||
|
||||
/// Issue a signed ref-update certificate for a successful push.
|
||||
///
|
||||
/// Builds a canonical JSON payload, signs it with the node's Ed25519 key,
|
||||
@@ -26,16 +94,12 @@ pub async fn issue_ref_certificate(
|
||||
let node_did = state.node_did.to_string();
|
||||
let issued_at = Utc::now().to_rfc3339();
|
||||
|
||||
// Build the canonical signing payload.
|
||||
let payload = serde_json::json!({
|
||||
"repo_id": repo_id,
|
||||
"ref": ref_name,
|
||||
"old": old_sha,
|
||||
"new": new_sha,
|
||||
"pusher": pusher_did,
|
||||
"node": node_did,
|
||||
"ts": issued_at,
|
||||
});
|
||||
// Build the canonical signing payload via the shared builder so
|
||||
// the frozen-vector test below and the live signer cannot drift
|
||||
// apart — a regression in either side fails both.
|
||||
let payload = v1_signing_payload(
|
||||
repo_id, ref_name, old_sha, new_sha, pusher_did, &node_did, &issued_at,
|
||||
);
|
||||
let payload_bytes = serde_json::to_vec(&payload)?;
|
||||
|
||||
let signature = state.node_keypair.sign_b64(&payload_bytes);
|
||||
@@ -50,9 +114,351 @@ pub async fn issue_ref_certificate(
|
||||
node_did,
|
||||
signature,
|
||||
issued_at,
|
||||
// #26 Split PR 3: the wire-format version. New certs stamp
|
||||
// v1 — the pre-versioning 7-field payload with no `version`
|
||||
// key in the signed JSON — because the shipped `gl`
|
||||
// verifier only supports v1. Stamping v2 here would issue
|
||||
// certificates the shipped client refuses (round-3
|
||||
// finding: node pinned `version == 2` while gl pinned
|
||||
// "2 is refused", with nothing exercising the
|
||||
// composition). v2 is reserved for the future shape
|
||||
// defined by `v2_signing_payload`, which carries the
|
||||
// version INSIDE the signed bytes; land the v2 verify
|
||||
// path before stamping v2.
|
||||
version: 1,
|
||||
};
|
||||
|
||||
// Persist and return the row as it exists in the database (on a
|
||||
// conflict the existing row survives when it is newer).
|
||||
state.db.insert_ref_certificate(&cert).await
|
||||
}
|
||||
|
||||
#[cfg(test)]
|
||||
mod v1_payload_tests {
|
||||
//! #26 Split PR 3 — cert payload version compat.
|
||||
//!
|
||||
//! The v1 cert payload is the frozen canonical byte form the
|
||||
//! node signs. gl's `verify_signature` reconstructs the same
|
||||
//! payload and verifies. Any drift in field order, key set, or
|
||||
//! whitespace breaks every existing cert. The tests here pin
|
||||
//! the v1 payload shape, the round-trip, the cert id
|
||||
//! determinism per the v1 version, and the v2 read forward
|
||||
//! compat (an unknown version refuses to verify rather than
|
||||
//! guessing).
|
||||
//!
|
||||
//! Reviewer 1 finding: the live signer (`issue_ref_certificate`)
|
||||
//! and the frozen-vector test (`v1_payload_matches_frozen_canonical_form`)
|
||||
//! previously held two separate `serde_json::json!` literals,
|
||||
//! so a regression in the signer could not fail this test.
|
||||
//! Both now go through the shared `v1_signing_payload` builder.
|
||||
use super::{v1_signing_payload, v2_signing_payload};
|
||||
use crate::db::RefCertificate;
|
||||
use gitlawb_core::identity::Keypair;
|
||||
|
||||
/// v1 payload is the same shape the legacy code signed, byte
|
||||
/// for byte. Reverting this assertion to the v2 shape (which
|
||||
/// includes a `version` key) is what the versioned format
|
||||
/// forbids: an old client reading a v1 cert must not see a
|
||||
/// `version` key in the signed JSON.
|
||||
///
|
||||
/// The literal is built via the shared `v1_signing_payload`
|
||||
/// helper that `issue_ref_certificate` also uses, so the live
|
||||
/// signer and the frozen vector share one source of truth.
|
||||
#[test]
|
||||
fn v1_payload_matches_frozen_canonical_form() {
|
||||
let payload = v1_signing_payload(
|
||||
"repo-1",
|
||||
"refs/heads/main",
|
||||
&"0".repeat(40),
|
||||
&"a".repeat(40),
|
||||
"did:key:z6MkPusher",
|
||||
"did:key:z6MkNode",
|
||||
"2026-07-22T00:00:00+00:00",
|
||||
);
|
||||
let frozen = format!(
|
||||
r#"{{"new":"{}","node":"did:key:z6MkNode","old":"{}","pusher":"did:key:z6MkPusher","ref":"refs/heads/main","repo_id":"repo-1","ts":"2026-07-22T00:00:00+00:00"}}"#,
|
||||
"a".repeat(40),
|
||||
"0".repeat(40),
|
||||
);
|
||||
assert_eq!(serde_json::to_string(&payload).unwrap(), frozen);
|
||||
}
|
||||
|
||||
/// Round-trip: sign the v1 payload with a keypair, build a
|
||||
/// RefCertificate with version: 1, and verify the structure.
|
||||
/// This is the construction the live code does on every push.
|
||||
///
|
||||
/// Uses the shared builder for both halves so a regression in
|
||||
/// the live signer (adding/removing/renaming a field) cannot
|
||||
/// pass this test by accident.
|
||||
#[test]
|
||||
fn v1_ref_certificate_structure_is_well_formed() {
|
||||
let kp = Keypair::generate();
|
||||
let node_did = kp.did().as_str().to_string();
|
||||
let payload = v1_signing_payload(
|
||||
"repo-1",
|
||||
"refs/heads/main",
|
||||
&"0".repeat(40),
|
||||
&"a".repeat(40),
|
||||
"did:key:z6MkPusher",
|
||||
&node_did,
|
||||
"2026-07-22T00:00:00+00:00",
|
||||
);
|
||||
let payload_bytes = serde_json::to_vec(&payload).unwrap();
|
||||
let sig = kp.sign_b64(&payload_bytes);
|
||||
let cert = RefCertificate {
|
||||
id: "cert-id".into(),
|
||||
repo_id: "repo-1".into(),
|
||||
ref_name: "refs/heads/main".into(),
|
||||
old_sha: "0".repeat(40),
|
||||
new_sha: "a".repeat(40),
|
||||
pusher_did: "did:key:z6MkPusher".into(),
|
||||
node_did: node_did.clone(),
|
||||
signature: sig.clone(),
|
||||
issued_at: "2026-07-22T00:00:00+00:00".into(),
|
||||
version: 1,
|
||||
};
|
||||
assert_eq!(cert.version, 1, "new certs carry version: 1");
|
||||
// The signed payload reconstructs identically: gl's
|
||||
// verify_signature would build the same JSON, hash the
|
||||
// same bytes, and verify the same signature.
|
||||
let reconstructed = v1_signing_payload(
|
||||
&cert.repo_id,
|
||||
&cert.ref_name,
|
||||
&cert.old_sha,
|
||||
&cert.new_sha,
|
||||
&cert.pusher_did,
|
||||
&cert.node_did,
|
||||
&cert.issued_at,
|
||||
);
|
||||
let reconstructed_bytes = serde_json::to_vec(&reconstructed).unwrap();
|
||||
assert_eq!(
|
||||
reconstructed_bytes, payload_bytes,
|
||||
"the round-trip serialization must be byte-identical; \
|
||||
this is what makes gl's verify_signature succeed"
|
||||
);
|
||||
// Round 3 (P3 reviewer): byte-equality alone never calls
|
||||
// `identity::verify`, so a bad signature helper would pass.
|
||||
// Verify the computed signature against the reconstructed
|
||||
// bytes — the same check gl performs.
|
||||
let vk = node_did
|
||||
.parse::<gitlawb_core::did::Did>()
|
||||
.unwrap()
|
||||
.to_verifying_key()
|
||||
.unwrap();
|
||||
use base64::{engine::general_purpose::URL_SAFE_NO_PAD, Engine};
|
||||
let sig_bytes: [u8; 64] = URL_SAFE_NO_PAD
|
||||
.decode(&cert.signature)
|
||||
.unwrap()
|
||||
.try_into()
|
||||
.unwrap();
|
||||
gitlawb_core::identity::verify(&vk, &reconstructed_bytes, &sig_bytes)
|
||||
.expect("well-formed v1 cert signature must verify");
|
||||
}
|
||||
|
||||
/// Reviewer 1 finding: the live signer must share the
|
||||
/// canonical-form literal so a regression in either side
|
||||
/// fails both. This test pins the shared builder's output
|
||||
/// against the literal a future v2 byte stream would have
|
||||
/// to break — if someone adds a `version` key to
|
||||
/// `v1_signing_payload`, every existing cert breaks verify,
|
||||
/// and this test is one of the canaries that fires.
|
||||
#[test]
|
||||
fn v1_signing_payload_has_no_version_key() {
|
||||
let payload = v1_signing_payload(
|
||||
"repo-1",
|
||||
"refs/heads/main",
|
||||
"oldsha",
|
||||
"newsha",
|
||||
"did:key:z6MkPusher",
|
||||
"did:key:z6MkNode",
|
||||
"2026-07-22T00:00:00+00:00",
|
||||
);
|
||||
let obj = payload.as_object().expect("payload is a JSON object");
|
||||
assert!(
|
||||
!obj.contains_key("version"),
|
||||
"v1 signing payload must not carry a `version` key — adding \
|
||||
one changes the bytes and breaks every existing cert's \
|
||||
signature. v2 certs build a different payload, not this one"
|
||||
);
|
||||
// Pin the exact set so a future field addition is caught.
|
||||
let expected: std::collections::BTreeSet<&str> =
|
||||
["new", "node", "old", "pusher", "ref", "repo_id", "ts"]
|
||||
.into_iter()
|
||||
.collect();
|
||||
let actual: std::collections::BTreeSet<&str> = obj.keys().map(String::as_str).collect();
|
||||
assert_eq!(actual, expected, "v1 payload key set is frozen");
|
||||
}
|
||||
|
||||
/// Round 3 (P2 reviewer): from v2 onward the version belongs
|
||||
/// INSIDE the signed bytes. v1 stays the unversioned legacy
|
||||
/// shape; v2 carries `"version": 2` in the payload so a
|
||||
/// version flip without re-signing invalidates the signature
|
||||
/// instead of verifying cleanly under the other path.
|
||||
#[test]
|
||||
fn v2_signing_payload_binds_version_and_resists_downgrade() {
|
||||
let kp = Keypair::generate();
|
||||
let node_did = kp.did().as_str().to_string();
|
||||
let ts = "2026-07-22T00:00:00+00:00";
|
||||
let v1 = v1_signing_payload(
|
||||
"repo-1",
|
||||
"refs/heads/main",
|
||||
"oldsha",
|
||||
"newsha",
|
||||
"did:key:z6MkPusher",
|
||||
&node_did,
|
||||
ts,
|
||||
);
|
||||
let v2 = v2_signing_payload(
|
||||
"repo-1",
|
||||
"refs/heads/main",
|
||||
"oldsha",
|
||||
"newsha",
|
||||
"did:key:z6MkPusher",
|
||||
&node_did,
|
||||
ts,
|
||||
);
|
||||
let v2_obj = v2.as_object().expect("v2 payload is a JSON object");
|
||||
assert_eq!(
|
||||
v2_obj.get("version"),
|
||||
Some(&serde_json::json!(2)),
|
||||
"v2 payload must carry the version inside the signed bytes"
|
||||
);
|
||||
let v1_bytes = serde_json::to_vec(&v1).unwrap();
|
||||
let v2_bytes = serde_json::to_vec(&v2).unwrap();
|
||||
assert_ne!(
|
||||
v1_bytes, v2_bytes,
|
||||
"v1 and v2 payloads must differ, otherwise a version flip is cryptographically invisible"
|
||||
);
|
||||
|
||||
// A signature over v1 must NOT verify as v2 and vice versa.
|
||||
let vk = node_did
|
||||
.parse::<gitlawb_core::did::Did>()
|
||||
.unwrap()
|
||||
.to_verifying_key()
|
||||
.unwrap();
|
||||
use base64::{engine::general_purpose::URL_SAFE_NO_PAD, Engine};
|
||||
let sig_v1 = kp.sign_b64(&v1_bytes);
|
||||
let sig_v1_bytes: [u8; 64] = URL_SAFE_NO_PAD.decode(&sig_v1).unwrap().try_into().unwrap();
|
||||
assert!(
|
||||
gitlawb_core::identity::verify(&vk, &v1_bytes, &sig_v1_bytes).is_ok(),
|
||||
"v1 signature must verify under v1 bytes"
|
||||
);
|
||||
assert!(
|
||||
gitlawb_core::identity::verify(&vk, &v2_bytes, &sig_v1_bytes).is_err(),
|
||||
"a v1 signature presented as v2 (downgrade/upgrade flip) must not verify"
|
||||
);
|
||||
}
|
||||
|
||||
/// The live issuer stamps the version the shipped client can
|
||||
/// verify. The gl client refuses to verify v2 certs explicitly;
|
||||
/// this test pins that the version the ISSUING PATH claims
|
||||
/// agrees with the payload shape it actually signs.
|
||||
///
|
||||
/// Round 2: the prior form built a `RefCertificate` literal with
|
||||
/// `version: 1` and asserted `version == 1` — true no matter what the
|
||||
/// signer does, so flipping the issuer's version (or its payload shape)
|
||||
/// left it green. This one drives the actual
|
||||
/// `issue_ref_certificate` so a regression in the issuer flips the test.
|
||||
/// The DB row is created against `test_support::test_state`, which
|
||||
/// gives us a real `AppState` with a real node keypair.
|
||||
///
|
||||
/// Round 3: the issuer stamps v1 because the shipped `gl`
|
||||
/// verifier only supports v1 (stamping v2 shipped certs the
|
||||
/// client refuses). The binding to the live issuer is kept —
|
||||
/// flipping the stamp still turns this test red — without
|
||||
/// changing what production issues.
|
||||
#[sqlx::test]
|
||||
#[allow(clippy::async_yields_async)]
|
||||
async fn issuer_stamps_v1_over_v1_payload(pool: sqlx::PgPool) {
|
||||
let state = crate::test_support::test_state(pool.clone()).await;
|
||||
let repo_id = "repo-issuer-observe";
|
||||
let ref_name = "refs/heads/main";
|
||||
let old = "0".repeat(40);
|
||||
let new = "a".repeat(40);
|
||||
let pusher = "did:key:z6MkPusher";
|
||||
|
||||
// Drive the live issuer and read the persisted row back by
|
||||
// id, so the test covers the stored `version` column and
|
||||
// not just the in-process return value.
|
||||
let cert =
|
||||
crate::cert::issue_ref_certificate(&state, repo_id, ref_name, &old, &new, pusher)
|
||||
.await
|
||||
.expect("issue_ref_certificate must succeed");
|
||||
|
||||
// The cert returned by the issuer is the source of truth
|
||||
// for both the version claim and the signed bytes.
|
||||
assert_eq!(cert.repo_id, repo_id);
|
||||
assert_eq!(cert.ref_name, ref_name);
|
||||
|
||||
// Cross-check 1: the issuer's claimed version must match
|
||||
// what the live function stamps. This assertion is bound
|
||||
// to the live function, not a hand-built literal:
|
||||
// flipping the stamp in `issue_ref_certificate` breaks it
|
||||
// through the actual call path.
|
||||
assert_eq!(
|
||||
cert.version, 1,
|
||||
"the live issuer must stamp v1 until a v2 verifier ships; \
|
||||
flipping the stamp breaks this assertion through the actual call path"
|
||||
);
|
||||
|
||||
// Cross-check 1b: the persisted row carries the same stamp.
|
||||
let stored = state
|
||||
.db
|
||||
.get_ref_certificate(&cert.id)
|
||||
.await
|
||||
.expect("persisted cert must be readable")
|
||||
.expect("persisted cert must exist");
|
||||
assert_eq!(
|
||||
stored.version, cert.version,
|
||||
"the stored version column must match the issued claim"
|
||||
);
|
||||
|
||||
// Cross-check 2: the signature on the cert must verify
|
||||
// against the v1 payload builder's bytes, not against some
|
||||
// other shape the issuer might have introduced. This is
|
||||
// what gl's `verify_signature` does for a v1 cert: rebuild
|
||||
// the payload from the cert's own fields and verify the
|
||||
// signature. If the issuer ever signs a different shape
|
||||
// while still claiming v1, every shipped client breaks —
|
||||
// and so does this.
|
||||
let rebuilt = v1_signing_payload(
|
||||
&cert.repo_id,
|
||||
&cert.ref_name,
|
||||
&cert.old_sha,
|
||||
&cert.new_sha,
|
||||
&cert.pusher_did,
|
||||
&cert.node_did,
|
||||
&cert.issued_at,
|
||||
);
|
||||
let vk = cert
|
||||
.node_did
|
||||
.parse::<gitlawb_core::did::Did>()
|
||||
.unwrap()
|
||||
.to_verifying_key()
|
||||
.unwrap();
|
||||
use base64::{engine::general_purpose::URL_SAFE_NO_PAD, Engine};
|
||||
let sig_bytes: [u8; 64] = URL_SAFE_NO_PAD
|
||||
.decode(&cert.signature)
|
||||
.unwrap()
|
||||
.try_into()
|
||||
.unwrap();
|
||||
gitlawb_core::identity::verify(&vk, &serde_json::to_vec(&rebuilt).unwrap(), &sig_bytes)
|
||||
.expect("a v1 cert's signature must verify against the v1 payload shape");
|
||||
|
||||
// Cross-check 3: the v1 signed payload must NOT contain a
|
||||
// version key — v2 is the future shape that adds one inside
|
||||
// the signed bytes (see `v2_signing_payload`). The v1
|
||||
// payload (which the cert is signed over) is frozen at 7
|
||||
// fields. A change that adds `version` to the v1 payload
|
||||
// breaks every existing cert and this test.
|
||||
let obj = rebuilt
|
||||
.as_object()
|
||||
.expect("rebuilt v1 payload is a JSON object");
|
||||
assert!(
|
||||
!obj.contains_key("version"),
|
||||
"the v1 signing payload must not carry a version key — \
|
||||
adding one changes the bytes and breaks every existing \
|
||||
cert's signature"
|
||||
);
|
||||
}
|
||||
}
|
||||
@@ -6,6 +6,20 @@ use std::time::Duration;
|
||||
use tracing::info;
|
||||
use uuid::Uuid;
|
||||
|
||||
/// Maximum visible repositories per page, plus one internal look-ahead row.
|
||||
pub(crate) const MAX_VISIBLE_REPO_PAGE_SIZE: usize = 200;
|
||||
|
||||
/// Maximum repository name length in bytes. `repo_cursor` embeds the name in
|
||||
/// a base64(JSON) cursor that `parse_repo_cursor` rejects over 4096 bytes, so
|
||||
/// every write path must bound the name: a cursor the server emits must
|
||||
/// always parse back (#465 4th round). 100 bytes keeps the longest possible
|
||||
/// cursor an order of magnitude under the parse limit.
|
||||
pub(crate) const MAX_REPO_NAME_LEN: usize = 100;
|
||||
|
||||
/// Maximum agent tasks returned per query. Shared by the GraphQL `tasks`
|
||||
/// complexity meter and the resolver clamp so they can't drift.
|
||||
pub(crate) const MAX_VISIBLE_TASK_PAGE_SIZE: i64 = 200;
|
||||
|
||||
// ── Public data types ─────────────────────────────────────────────────────────
|
||||
|
||||
#[derive(Debug, Clone, Serialize, Deserialize)]
|
||||
@@ -278,6 +292,14 @@ pub struct RefCertificate {
|
||||
pub node_did: String,
|
||||
pub signature: String,
|
||||
pub issued_at: String,
|
||||
/// #26 Split PR 3 — the wire-format version of this cert. v1 is
|
||||
/// the pre-versioning 7-field payload (no `version` key in the
|
||||
/// signed bytes). v2+ is reserved for a new signed payload shape
|
||||
/// that carries the version inside the signed bytes; it is not
|
||||
/// v1 plus unsigned fields, because flipping this column must
|
||||
/// invalidate the signature. Clients refuse to verify versions
|
||||
/// they cannot represent rather than guessing.
|
||||
pub version: u32,
|
||||
}
|
||||
|
||||
#[derive(Debug, Clone, Serialize, Deserialize)]
|
||||
@@ -397,6 +419,17 @@ impl Db {
|
||||
Self { pool }
|
||||
}
|
||||
|
||||
/// Test-only: access the underlying Postgres connection pool.
|
||||
///
|
||||
/// The production accessor was removed on main (ed76adf) once every
|
||||
/// production caller had migrated to typed `Db` methods; this restores
|
||||
/// it for tests only, for the raw-SQL fixtures and closed-pool cases in
|
||||
/// this change that have no typed equivalent.
|
||||
#[cfg(test)]
|
||||
pub fn pool(&self) -> &PgPool {
|
||||
&self.pool
|
||||
}
|
||||
|
||||
/// Test-only: apply the full schema to a fresh pool. `#[sqlx::test]`
|
||||
/// provisions an empty per-test database, so DB-backed tests must run this
|
||||
/// before seeding. Reuses the production `migrate()` path (the advisory lock
|
||||
@@ -1358,6 +1391,32 @@ const MIGRATIONS: &[Migration] = &[
|
||||
name: "validate_repo_upstream_mirror_state",
|
||||
stmts: &["ALTER TABLE repos VALIDATE CONSTRAINT repos_mirror_state_valid"],
|
||||
},
|
||||
Migration {
|
||||
version: 37,
|
||||
name: "ref_certificates_version",
|
||||
stmts: &[
|
||||
// #26 Split PR 3 — certificate / CLI compatibility. The
|
||||
// ref-cert wire format is versioned so future fields can
|
||||
// be added without breaking old clients (which ignore
|
||||
// the field) or old servers (which default the column
|
||||
// to 1). New certificates are currently issued as v1,
|
||||
// which is byte-for-byte identical to the pre-versioning
|
||||
// shape: an old client reading a v1 cert from a new
|
||||
// server sees the same payload, the same signature, and
|
||||
// the same Ed25519 verify path. A new client reading an
|
||||
// old server sees `version` defaulted to 1 and verifies
|
||||
// against the v1 payload shape. v2 is reserved for a
|
||||
// future shape that carries the version inside the
|
||||
// signed bytes; it must not be stamped until a v2
|
||||
// verifier ships.
|
||||
//
|
||||
// DEFAULT 1 so an existing row reads as v1 without a
|
||||
// backfill migration. NOT NULL so a missing value is a
|
||||
// hard error at insert time rather than a silent v0 that
|
||||
// an old client would interpret as "no version field."
|
||||
"ALTER TABLE ref_certificates ADD COLUMN IF NOT EXISTS version INTEGER NOT NULL DEFAULT 1",
|
||||
],
|
||||
},
|
||||
];
|
||||
|
||||
/// Max distinct source repos recorded per pinned object (F1, #173 jatmn round 8).
|
||||
@@ -1560,6 +1619,16 @@ impl Db {
|
||||
machine_id: Option<&str>,
|
||||
quarantined: bool,
|
||||
) -> Result<()> {
|
||||
// Peer-supplied names are bound like the local write paths: an
|
||||
// unbounded name would make reposPage emit a cursor longer than the
|
||||
// 4096-byte parse limit, dead-ending pagination for every caller past
|
||||
// that row (#465 4th round). The sync caller drops the error and skips
|
||||
// the mirror.
|
||||
if name.len() > MAX_REPO_NAME_LEN {
|
||||
anyhow::bail!(
|
||||
"mirror repo name exceeds {MAX_REPO_NAME_LEN} bytes: refusing to register"
|
||||
);
|
||||
}
|
||||
let now = Utc::now().to_rfc3339();
|
||||
let id = format!("{owner_short}/{name}");
|
||||
// `quarantined` is set only on first insert (the admission decision).
|
||||
@@ -1851,6 +1920,73 @@ impl Db {
|
||||
Ok(rows.into_iter().map(row_to_repo).collect())
|
||||
}
|
||||
|
||||
/// A bounded, mirror-deduplicated page ordered by owner key and repository
|
||||
/// name. Apply root visibility before LIMIT: private rows must not consume
|
||||
/// page slots or influence continuation metadata. The root-rule predicate
|
||||
/// mirrors `visibility::listable_at_root`; a differential test pins it.
|
||||
/// Malformed reader JSON denies that repo to non-owners without failing the page.
|
||||
/// Cursors only select a position and never confer read authority.
|
||||
///
|
||||
/// Performance note: the page orders and keyset-filters on
|
||||
/// `(owner_key, name)` under `COLLATE "C"`, but the existing
|
||||
/// `idx_repos_owner_key_name` index is built on the database default
|
||||
/// collation and cannot serve that ordering, so each page sorts the full
|
||||
/// deduped repo set before the keyset filter applies: O(total repos) work
|
||||
/// per page. This is accepted (pages are capped at
|
||||
/// `MAX_VISIBLE_REPO_PAGE_SIZE` rows over a narrow projection). A
|
||||
/// C-collation expression index was deliberately not added in a migration:
|
||||
/// versions 27-35 are claimed by other in-flight branches (Gitlawb/node#384
|
||||
/// claims 27-35, #464 claims 27-28) and the runner keys applied migrations
|
||||
/// on the version integer alone, so a colliding entry would be silently
|
||||
/// skipped on whichever side merges second. Revisit once that range lands
|
||||
/// or clears.
|
||||
pub async fn list_visible_repos_page(
|
||||
&self,
|
||||
caller: Option<&str>,
|
||||
after: Option<(&str, &str)>,
|
||||
limit: usize,
|
||||
) -> Result<Vec<RepoRecord>> {
|
||||
let sql = format!(
|
||||
"{}
|
||||
SELECT d.id, d.name, d.owner_did, d.description, d.is_public,
|
||||
d.default_branch, d.created_at, d.updated_at, d.disk_path,
|
||||
d.forked_from, d.machine_id
|
||||
FROM deduped d
|
||||
LEFT JOIN LATERAL (
|
||||
SELECT reader_dids FROM visibility_rules v
|
||||
WHERE v.repo_id = d.id AND v.path_glob ~ '^/*([*][*])*$'
|
||||
ORDER BY v.path_glob DESC LIMIT 1
|
||||
) root_rule ON TRUE
|
||||
WHERE (
|
||||
($2::text IS NOT NULL AND ({key}) = $2)
|
||||
OR CASE WHEN root_rule.reader_dids IS NULL THEN d.is_public
|
||||
WHEN NOT pg_input_is_valid(root_rule.reader_dids, 'jsonb') THEN FALSE
|
||||
WHEN jsonb_typeof(root_rule.reader_dids::jsonb) = 'array' THEN
|
||||
COALESCE(root_rule.reader_dids::jsonb ? $3::text, FALSE)
|
||||
AND NOT EXISTS (
|
||||
SELECT 1 FROM jsonb_array_elements(root_rule.reader_dids::jsonb) reader
|
||||
WHERE jsonb_typeof(reader) <> 'string'
|
||||
)
|
||||
ELSE FALSE END
|
||||
)
|
||||
AND ($4::text IS NULL OR (({key}) COLLATE \"C\", d.name COLLATE \"C\") > ($4, $5::text))
|
||||
ORDER BY ({key}) COLLATE \"C\", d.name COLLATE \"C\"
|
||||
LIMIT $6",
|
||||
Self::dedup_cte(),
|
||||
key = OWNER_KEY_CASE_SQL,
|
||||
);
|
||||
let rows = sqlx::query(&sql)
|
||||
.bind(None::<&str>)
|
||||
.bind(caller.map(normalize_owner_key))
|
||||
.bind(caller)
|
||||
.bind(after.map(|(owner, _)| normalize_owner_key(owner)))
|
||||
.bind(after.map(|(_, name)| name))
|
||||
.bind(limit.min(MAX_VISIBLE_REPO_PAGE_SIZE + 1) as i64)
|
||||
.fetch_all(&self.pool)
|
||||
.await?;
|
||||
Ok(rows.into_iter().map(row_to_repo).collect())
|
||||
}
|
||||
|
||||
/// Repos currently quarantined (admitted as mirrors but withheld from every
|
||||
/// listing surface). `list_all_repos_deduped` excludes these (its `DEDUP_CTE`
|
||||
/// filters `quarantined = FALSE`), so a gate that resolves a slug against the
|
||||
@@ -2647,8 +2783,8 @@ impl Db {
|
||||
pub async fn insert_ref_certificate(&self, cert: &RefCertificate) -> Result<RefCertificate> {
|
||||
let row = sqlx::query(
|
||||
"INSERT INTO ref_certificates
|
||||
(id, repo_id, ref_name, old_sha, new_sha, pusher_did, node_did, signature, issued_at)
|
||||
VALUES ($1, $2, $3, $4, $5, $6, $7, $8, $9)
|
||||
(id, repo_id, ref_name, old_sha, new_sha, pusher_did, node_did, signature, issued_at, version)
|
||||
VALUES ($1, $2, $3, $4, $5, $6, $7, $8, $9, $10)
|
||||
ON CONFLICT (repo_id, ref_name) DO UPDATE SET
|
||||
old_sha = CASE WHEN EXCLUDED.issued_at > ref_certificates.issued_at
|
||||
THEN EXCLUDED.old_sha ELSE ref_certificates.old_sha END,
|
||||
@@ -2661,8 +2797,10 @@ impl Db {
|
||||
signature = CASE WHEN EXCLUDED.issued_at > ref_certificates.issued_at
|
||||
THEN EXCLUDED.signature ELSE ref_certificates.signature END,
|
||||
issued_at = CASE WHEN EXCLUDED.issued_at > ref_certificates.issued_at
|
||||
THEN EXCLUDED.issued_at ELSE ref_certificates.issued_at END
|
||||
RETURNING id, repo_id, ref_name, old_sha, new_sha, pusher_did, node_did, signature, issued_at",
|
||||
THEN EXCLUDED.issued_at ELSE ref_certificates.issued_at END,
|
||||
version = CASE WHEN EXCLUDED.issued_at > ref_certificates.issued_at
|
||||
THEN EXCLUDED.version ELSE ref_certificates.version END
|
||||
RETURNING id, repo_id, ref_name, old_sha, new_sha, pusher_did, node_did, signature, issued_at, version",
|
||||
)
|
||||
.bind(&cert.id)
|
||||
.bind(&cert.repo_id)
|
||||
@@ -2673,6 +2811,7 @@ impl Db {
|
||||
.bind(&cert.node_did)
|
||||
.bind(&cert.signature)
|
||||
.bind(&cert.issued_at)
|
||||
.bind(cert.version as i32)
|
||||
.fetch_one(&self.pool)
|
||||
.await?;
|
||||
Ok(row_to_cert(row))
|
||||
@@ -2687,7 +2826,7 @@ impl Db {
|
||||
// bounded even if a raw/negative value slips through the handler layer.
|
||||
let limit = limit.max(1);
|
||||
let rows = sqlx::query(
|
||||
"SELECT id, repo_id, ref_name, old_sha, new_sha, pusher_did, node_did, signature, issued_at
|
||||
"SELECT id, repo_id, ref_name, old_sha, new_sha, pusher_did, node_did, signature, issued_at, version
|
||||
FROM ref_certificates WHERE repo_id = $1 ORDER BY issued_at DESC LIMIT $2",
|
||||
)
|
||||
.bind(repo_id)
|
||||
@@ -2726,7 +2865,7 @@ impl Db {
|
||||
let pattern = format!("{}%", escaped_prefix);
|
||||
|
||||
let rows = sqlx::query(
|
||||
"SELECT id, repo_id, ref_name, old_sha, new_sha, pusher_did, node_did, signature, issued_at
|
||||
"SELECT id, repo_id, ref_name, old_sha, new_sha, pusher_did, node_did, signature, issued_at, version
|
||||
FROM ref_certificates WHERE repo_id = $1 AND id LIKE $2 ESCAPE '!' ORDER BY issued_at DESC LIMIT $3",
|
||||
)
|
||||
.bind(repo_id)
|
||||
@@ -2739,7 +2878,7 @@ impl Db {
|
||||
|
||||
pub async fn get_ref_certificate(&self, id: &str) -> Result<Option<RefCertificate>> {
|
||||
let row = sqlx::query(
|
||||
"SELECT id, repo_id, ref_name, old_sha, new_sha, pusher_did, node_did, signature, issued_at
|
||||
"SELECT id, repo_id, ref_name, old_sha, new_sha, pusher_did, node_did, signature, issued_at, version
|
||||
FROM ref_certificates WHERE id = $1",
|
||||
)
|
||||
.bind(id)
|
||||
@@ -4000,28 +4139,54 @@ impl Db {
|
||||
|
||||
// ── Agent Tasks ───────────────────────────────────────────────────────────────
|
||||
|
||||
/// Permanent authorization denial: the task is reserved for a different assignee.
|
||||
/// Handlers downcast this to return 403 (vs 409 for a lost claim race).
|
||||
#[derive(Debug, thiserror::Error)]
|
||||
#[error("task not claimable: reserved for another assignee")]
|
||||
pub struct TaskReservedForOtherAssignee;
|
||||
|
||||
/// ASCII whitespace treated as blank for assignee slots — must stay in sync with
|
||||
/// `BTRIM(assignee_did, E' \t\n\r')` in `claim_task`'s SQL open-slot check.
|
||||
const ASSIGNEE_BLANK: &[char] = &[' ', '\t', '\n', '\r'];
|
||||
|
||||
fn assignee_slot_blank(s: &str) -> bool {
|
||||
s.trim_matches(ASSIGNEE_BLANK).is_empty()
|
||||
}
|
||||
|
||||
/// Trim assignee DIDs for auth matching (same ASCII blank set as SQL/open checks).
|
||||
pub fn trim_assignee_did(s: &str) -> &str {
|
||||
s.trim_matches(ASSIGNEE_BLANK)
|
||||
}
|
||||
|
||||
impl Db {
|
||||
pub async fn create_task(&self, task: &AgentTask) -> Result<()> {
|
||||
/// Persist a task. Whitespace-only `assignee_did` is stored as `NULL` (open).
|
||||
/// Returns the normalized row shape so REST/GraphQL create responses match GET.
|
||||
pub async fn create_task(&self, task: &AgentTask) -> Result<AgentTask> {
|
||||
let mut stored = task.clone();
|
||||
stored.assignee_did = stored
|
||||
.assignee_did
|
||||
.take()
|
||||
.filter(|s| !assignee_slot_blank(s));
|
||||
sqlx::query(
|
||||
"INSERT INTO agent_tasks (id, repo_id, kind, status, delegator_did, assignee_did, capability, ucan_token, payload, result, created_at, updated_at, deadline)
|
||||
VALUES ($1,$2,$3,$4,$5,$6,$7,$8,$9,$10,$11,$12,$13)",
|
||||
)
|
||||
.bind(&task.id)
|
||||
.bind(&task.repo_id)
|
||||
.bind(&task.kind)
|
||||
.bind(&task.status)
|
||||
.bind(&task.delegator_did)
|
||||
.bind(&task.assignee_did)
|
||||
.bind(&task.capability)
|
||||
.bind(&task.ucan_token)
|
||||
.bind(&task.payload)
|
||||
.bind(&task.result)
|
||||
.bind(&task.created_at)
|
||||
.bind(&task.updated_at)
|
||||
.bind(&task.deadline)
|
||||
.bind(&stored.id)
|
||||
.bind(&stored.repo_id)
|
||||
.bind(&stored.kind)
|
||||
.bind(&stored.status)
|
||||
.bind(&stored.delegator_did)
|
||||
.bind(&stored.assignee_did)
|
||||
.bind(&stored.capability)
|
||||
.bind(&stored.ucan_token)
|
||||
.bind(&stored.payload)
|
||||
.bind(&stored.result)
|
||||
.bind(&stored.created_at)
|
||||
.bind(&stored.updated_at)
|
||||
.bind(&stored.deadline)
|
||||
.execute(&self.pool)
|
||||
.await?;
|
||||
Ok(())
|
||||
Ok(stored)
|
||||
}
|
||||
|
||||
pub async fn get_task(&self, id: &str) -> Result<Option<AgentTask>> {
|
||||
@@ -4078,38 +4243,102 @@ impl Db {
|
||||
Ok(rows.into_iter().map(row_to_task).collect())
|
||||
}
|
||||
|
||||
/// Claim a pending task for `assignee_did`.
|
||||
///
|
||||
/// If the task was created with a non-blank pre-set `assignee_did`, only that
|
||||
/// agent (DID-normalized via [`crate::api::did_matches`]) may claim it. Open
|
||||
/// tasks (`NULL` / blank) remain first-claimer-wins. A reserved claim keeps
|
||||
/// the **exact** stored DID form via `COALESCE($4, $2)` (no BTRIM rewrite) so
|
||||
/// exact-match list filters still work. The UPDATE also re-checks the
|
||||
/// assignee slot as defense-in-depth against a future writer racing the
|
||||
/// pre-check.
|
||||
pub async fn claim_task(&self, id: &str, assignee_did: &str) -> Result<AgentTask> {
|
||||
let now = Utc::now().to_rfc3339();
|
||||
// Denial path only needs status + assignee — do not load payload/UCAN
|
||||
// for a permissionless caller who will be rejected.
|
||||
let row = sqlx::query("SELECT status, assignee_did FROM agent_tasks WHERE id = $1")
|
||||
.bind(id)
|
||||
.fetch_optional(&self.pool)
|
||||
.await?
|
||||
.ok_or_else(|| anyhow::anyhow!("task not claimable: not found or already claimed"))?;
|
||||
let status: String = row.get("status");
|
||||
if status != "pending" {
|
||||
return Err(anyhow::anyhow!(
|
||||
"task not claimable: not found or already claimed"
|
||||
));
|
||||
}
|
||||
let stored: Option<String> = row.get("assignee_did");
|
||||
// Blank reservations are treated as open. Keep the exact stored string
|
||||
// for the UPDATE equality check and SET (do not BTRIM the reserved form).
|
||||
// Blank definition matches SQL `BTRIM(..., E' \t\n\r')` (not space-only).
|
||||
let reserved_exact = stored.as_deref().filter(|r| !assignee_slot_blank(r));
|
||||
if let Some(reserved) = reserved_exact {
|
||||
if !crate::api::did_matches(assignee_did, trim_assignee_did(reserved)) {
|
||||
return Err(TaskReservedForOtherAssignee.into());
|
||||
}
|
||||
}
|
||||
// Keep the exact reserved form ($4); only fill assignee on open claims ($2).
|
||||
// Treat blank stored values as open for the SQL slot check.
|
||||
let row = sqlx::query(
|
||||
"UPDATE agent_tasks SET status='claimed', assignee_did=$2, updated_at=$3
|
||||
"UPDATE agent_tasks SET status='claimed',
|
||||
assignee_did = COALESCE($4, $2),
|
||||
updated_at=$3
|
||||
WHERE id=$1 AND status='pending'
|
||||
AND (
|
||||
($4::text IS NULL AND (assignee_did IS NULL OR BTRIM(assignee_did, E' \t\n\r') = ''))
|
||||
OR assignee_did = $4
|
||||
)
|
||||
RETURNING id, repo_id, kind, status, delegator_did, assignee_did, capability, ucan_token, payload, result, created_at, updated_at, deadline",
|
||||
)
|
||||
.bind(id)
|
||||
.bind(assignee_did)
|
||||
.bind(&now)
|
||||
.bind(reserved_exact)
|
||||
.fetch_optional(&self.pool)
|
||||
.await?;
|
||||
row.map(row_to_task)
|
||||
.ok_or_else(|| anyhow::anyhow!("task not claimable: not found or already claimed"))
|
||||
}
|
||||
|
||||
/// Transition a claimed task to `new_status` (`completed` / `failed`).
|
||||
///
|
||||
/// `actor_did` must be the task's assignee (DID-normalized). The UPDATE
|
||||
/// binds the exact stored `assignee_did` so a concurrent reassignment /
|
||||
/// re-claim cannot finish under a check-then-act race in the handler.
|
||||
pub async fn finish_task(
|
||||
&self,
|
||||
id: &str,
|
||||
new_status: &str,
|
||||
result: Option<&str>,
|
||||
actor_did: &str,
|
||||
) -> Result<AgentTask> {
|
||||
let now = Utc::now().to_rfc3339();
|
||||
let existing = self
|
||||
.get_task(id)
|
||||
.await?
|
||||
.ok_or_else(|| anyhow::anyhow!("task not found or not in claimed state"))?;
|
||||
if existing.status != "claimed" {
|
||||
return Err(anyhow::anyhow!("task not found or not in claimed state"));
|
||||
}
|
||||
let Some(ref assigned) = existing.assignee_did else {
|
||||
return Err(anyhow::anyhow!("task not found or not in claimed state"));
|
||||
};
|
||||
// Trim matches claim_task so tab-padded stored values can finish.
|
||||
if !crate::api::did_matches(actor_did, trim_assignee_did(assigned)) {
|
||||
return Err(anyhow::anyhow!(
|
||||
"task not finishable: only the assignee may finish it"
|
||||
));
|
||||
}
|
||||
let row = sqlx::query(
|
||||
"UPDATE agent_tasks SET status=$2, result=$3, updated_at=$4
|
||||
WHERE id=$1 AND status='claimed'
|
||||
WHERE id=$1 AND status='claimed' AND assignee_did=$5
|
||||
RETURNING id, repo_id, kind, status, delegator_did, assignee_did, capability, ucan_token, payload, result, created_at, updated_at, deadline",
|
||||
)
|
||||
.bind(id)
|
||||
.bind(new_status)
|
||||
.bind(result)
|
||||
.bind(&now)
|
||||
.bind(assigned.as_str())
|
||||
.fetch_optional(&self.pool)
|
||||
.await?;
|
||||
row.map(row_to_task)
|
||||
@@ -4853,6 +5082,7 @@ fn row_to_cert(r: sqlx::postgres::PgRow) -> RefCertificate {
|
||||
node_did: r.get("node_did"),
|
||||
signature: r.get("signature"),
|
||||
issued_at: r.get("issued_at"),
|
||||
version: r.get::<i32, _>("version") as u32,
|
||||
}
|
||||
}
|
||||
|
||||
@@ -7561,6 +7791,7 @@ mod ref_certificate_tests {
|
||||
node_did: "did:key:zNODE".to_string(),
|
||||
signature: "sig".to_string(),
|
||||
issued_at: issued_at.to_string(),
|
||||
version: 1,
|
||||
}
|
||||
}
|
||||
|
||||
@@ -8234,6 +8465,130 @@ mod ref_certificate_tests {
|
||||
);
|
||||
}
|
||||
|
||||
/// #26 Split PR 3 (INV-7): an existing node past v1 gets the
|
||||
/// `ref_certificates.version` column from its OWN v37 entry, proven
|
||||
/// by dropping the column plus its `schema_migrations` row and
|
||||
/// re-running the real migration code. The migration is the only
|
||||
/// place the column is added (v37 — the v1 bundle no longer
|
||||
/// carries it), so a deletion of v37 must be visible as a missing
|
||||
/// column on a v27 node.
|
||||
///
|
||||
/// DEFAULT 1 is what makes an existing pre-v37 cert row read as
|
||||
/// v1 without a backfill migration. An upgraded node reads
|
||||
/// every legacy row as version 1 — the same payload the old
|
||||
/// code signed — so a v1 verify path on a new client still
|
||||
/// works against an upgraded database.
|
||||
///
|
||||
/// MUTATION (RED): delete the v37 entry from `MIGRATIONS` and the
|
||||
/// upgrade path leaves the column missing.
|
||||
#[sqlx::test]
|
||||
async fn v37_ref_certificates_version_applies_on_upgrade(pool: PgPool) {
|
||||
async fn version_column_default(pool: &PgPool) -> Option<String> {
|
||||
// fetch_optional (not fetch_one) so a missing column
|
||||
// returns Ok(None) instead of RowNotFound. The whole
|
||||
// point of the precondition assertion below is to
|
||||
// detect a missing column, and RowNotFound would mask
|
||||
// the difference between "the helper is wrong" and
|
||||
// "the migration is wrong".
|
||||
sqlx::query_scalar::<_, Option<String>>(
|
||||
"SELECT column_default
|
||||
FROM information_schema.columns
|
||||
WHERE table_name = 'ref_certificates'
|
||||
AND column_name = 'version'",
|
||||
)
|
||||
.fetch_optional(pool)
|
||||
.await
|
||||
.unwrap()
|
||||
.flatten()
|
||||
}
|
||||
|
||||
async fn seed_pre_v37_cert(pool: &PgPool) {
|
||||
// The pre-v37 schema has no `version` column, so a raw
|
||||
// INSERT omitting it is the legacy code path. The node
|
||||
// did not write a version value on v1..v27 — the field
|
||||
// did not exist.
|
||||
sqlx::query(
|
||||
"INSERT INTO ref_certificates
|
||||
(id, repo_id, ref_name, old_sha, new_sha,
|
||||
pusher_did, node_did, signature, issued_at)
|
||||
VALUES ($1, $2, $3, $4, $5, $6, $7, $8, $9)
|
||||
ON CONFLICT (repo_id, ref_name) DO NOTHING",
|
||||
)
|
||||
.bind("legacy-cert-1")
|
||||
.bind("legacy-repo")
|
||||
.bind("refs/heads/main")
|
||||
.bind("0000")
|
||||
.bind("1111")
|
||||
.bind("did:key:zLEGACYPUSHER")
|
||||
.bind("did:key:zLEGACYNODE")
|
||||
.bind("legacy-sig")
|
||||
.bind("2026-07-01T10:00:00+00:00")
|
||||
.execute(pool)
|
||||
.await
|
||||
.unwrap();
|
||||
}
|
||||
|
||||
async fn legacy_row_reads_as_v1(pool: &PgPool) -> i32 {
|
||||
// After v37 the legacy row (inserted without an explicit
|
||||
// version) reads back as 1 via the DEFAULT, not as 0 or
|
||||
// NULL — the latter would be a hard insert error under
|
||||
// NOT NULL DEFAULT, but the read-back is the actual
|
||||
// forward-compat property the v1 verify path relies on.
|
||||
sqlx::query_scalar::<_, i32>(
|
||||
"SELECT version FROM ref_certificates WHERE id = 'legacy-cert-1'",
|
||||
)
|
||||
.fetch_one(pool)
|
||||
.await
|
||||
.unwrap()
|
||||
}
|
||||
|
||||
// 1. Fresh chain: v37 has run, the column exists with DEFAULT 1.
|
||||
let db = Db::for_testing(pool.clone());
|
||||
db.run_migrations().await.unwrap();
|
||||
assert_eq!(
|
||||
version_column_default(&pool).await.as_deref(),
|
||||
Some("1"),
|
||||
"v37 must declare the version column with DEFAULT 1"
|
||||
);
|
||||
|
||||
// 2. Roll back to pre-v37: drop the column AND the v37 record.
|
||||
// The rollback is split into two statements because ALTER
|
||||
// TABLE ... DROP COLUMN and DELETE run in the same DDL
|
||||
// surface but the column drop must complete before the
|
||||
// next step reads schema_migrations.
|
||||
sqlx::query("ALTER TABLE ref_certificates DROP COLUMN version")
|
||||
.execute(&pool)
|
||||
.await
|
||||
.unwrap();
|
||||
sqlx::query("DELETE FROM schema_migrations WHERE version = 37")
|
||||
.execute(&pool)
|
||||
.await
|
||||
.unwrap();
|
||||
assert!(
|
||||
version_column_default(&pool).await.is_none(),
|
||||
"precondition: column removed and its migration record removed"
|
||||
);
|
||||
|
||||
// 3. Seed a legacy cert on the pre-v37 schema (no version
|
||||
// column ⇒ the INSERT must omit it).
|
||||
seed_pre_v37_cert(&pool).await;
|
||||
|
||||
// 4. Re-run migrations: v37 must re-add the column with
|
||||
// DEFAULT 1, and the legacy row must read back as 1.
|
||||
db.run_migrations().await.unwrap();
|
||||
assert_eq!(
|
||||
version_column_default(&pool).await.as_deref(),
|
||||
Some("1"),
|
||||
"v37 must recreate the version column with DEFAULT 1 on an upgrading node"
|
||||
);
|
||||
assert_eq!(
|
||||
legacy_row_reads_as_v1(&pool).await,
|
||||
1,
|
||||
"a pre-v37 cert row reads as version 1 after v37 runs, so the \
|
||||
v1 verify path on a new client still works against an upgraded database"
|
||||
);
|
||||
}
|
||||
|
||||
/// INV-7: upgrade-path test — seed a database at v9 with duplicate
|
||||
/// ref_certificates, then let the real v10 migration fire via
|
||||
/// run_migrations(). This exercises the migration code path rather than
|
||||
|
||||
@@ -118,7 +118,7 @@ impl RepoStore {
|
||||
/// Test-only: every guard from this store parks in `release` right before the
|
||||
/// `pg_advisory_unlock` await, until `gate` is notified. Dropping the future
|
||||
/// while it is parked reproduces a client disconnect inside `release`.
|
||||
#[cfg(test)]
|
||||
#[cfg(all(test, unix))]
|
||||
pub fn with_pre_unlock_gate(mut self, gate: Arc<tokio::sync::Notify>) -> Self {
|
||||
self.pre_unlock_gate = Some(gate);
|
||||
self
|
||||
@@ -126,7 +126,7 @@ impl RepoStore {
|
||||
|
||||
/// Test-only: how many write guards from this store have reached the Tigris upload
|
||||
/// site. See [`RepoWriteGuard::release`].
|
||||
#[cfg(test)]
|
||||
#[cfg(all(test, unix))]
|
||||
pub fn tigris_upload_site_reached(&self) -> usize {
|
||||
self.upload_site_reached
|
||||
.load(std::sync::atomic::Ordering::SeqCst)
|
||||
@@ -1717,8 +1717,11 @@ fn validate_repo_name(repo_name: &str) -> Result<()> {
|
||||
if repo_name.is_empty() {
|
||||
anyhow::bail!("repo_name is empty");
|
||||
}
|
||||
if repo_name.len() > 100 {
|
||||
anyhow::bail!("repo_name exceeds 100 chars");
|
||||
// Byte bound shared with the API-side validator via `MAX_REPO_NAME_LEN`:
|
||||
// the two validators differ on charset by design, but must not drift on
|
||||
// length, or an API-admitted name fails here after the proof is spent.
|
||||
if repo_name.len() > crate::db::MAX_REPO_NAME_LEN {
|
||||
anyhow::bail!("repo_name exceeds {} chars", crate::db::MAX_REPO_NAME_LEN);
|
||||
}
|
||||
// Repo names are `[A-Za-z0-9._-]+` minus path-traversal traps.
|
||||
if repo_name.contains("..") {
|
||||
|
||||
@@ -3,7 +3,7 @@ pub mod query;
|
||||
pub mod subscription;
|
||||
pub mod types;
|
||||
|
||||
use async_graphql::Schema;
|
||||
use async_graphql::{Schema, SchemaBuilder};
|
||||
use std::sync::Arc;
|
||||
|
||||
use crate::db::Db;
|
||||
@@ -14,6 +14,22 @@ use subscription::SubscriptionRoot;
|
||||
|
||||
pub type GitlawbSchema = Schema<QueryRoot, MutationRoot, SubscriptionRoot>;
|
||||
|
||||
// Keep ordinary schema discovery and application queries usable while
|
||||
// bounding validation work and the number of resolver selections per request.
|
||||
const GRAPHQL_MAX_COMPLEXITY: usize = 400;
|
||||
// The current public schema is shallow; this leaves headroom for composed
|
||||
// clients and the canonical getIntrospectionQuery without allowing
|
||||
// recursively nested documents to grow unchecked.
|
||||
const GRAPHQL_MAX_DEPTH: usize = 14;
|
||||
|
||||
fn apply_query_limits<Query, Mutation, Subscription>(
|
||||
builder: SchemaBuilder<Query, Mutation, Subscription>,
|
||||
) -> SchemaBuilder<Query, Mutation, Subscription> {
|
||||
builder
|
||||
.limit_complexity(GRAPHQL_MAX_COMPLEXITY)
|
||||
.limit_depth(GRAPHQL_MAX_DEPTH)
|
||||
}
|
||||
|
||||
/// Client-facing message for GraphQL resolver failures that wrap a real
|
||||
/// `sqlx::Error`. The real error is logged server-side; never put sqlx/Postgres
|
||||
/// detail in the GraphQL `errors` array (#250).
|
||||
@@ -81,7 +97,7 @@ pub fn build_schema(
|
||||
ref_update_tx: tokio::sync::broadcast::Sender<RefUpdateBroadcast>,
|
||||
task_event_tx: tokio::sync::broadcast::Sender<TaskEventBroadcast>,
|
||||
) -> GitlawbSchema {
|
||||
Schema::build(QueryRoot, MutationRoot, SubscriptionRoot)
|
||||
apply_query_limits(Schema::build(QueryRoot, MutationRoot, SubscriptionRoot))
|
||||
.data(db)
|
||||
.data(ref_update_tx)
|
||||
.data(task_event_tx)
|
||||
@@ -91,6 +107,10 @@ pub fn build_schema(
|
||||
#[cfg(test)]
|
||||
mod tests {
|
||||
use super::*;
|
||||
use crate::api::events::MAX_VISIBLE_REF_UPDATES;
|
||||
use crate::db::{MAX_VISIBLE_REPO_PAGE_SIZE, MAX_VISIBLE_TASK_PAGE_SIZE};
|
||||
use async_graphql::{EmptyMutation, EmptySubscription, Object, Value};
|
||||
use std::sync::atomic::{AtomicUsize, Ordering};
|
||||
|
||||
#[test]
|
||||
fn graphql_db_err_opaques_sqlx_chain() {
|
||||
@@ -160,6 +180,668 @@ mod tests {
|
||||
assert!(!err.message.contains("failed to open"));
|
||||
}
|
||||
|
||||
fn production_test_schema() -> GitlawbSchema {
|
||||
let pool = sqlx::postgres::PgPoolOptions::new()
|
||||
.connect_lazy("postgres://localhost/unused")
|
||||
.unwrap();
|
||||
production_test_schema_with_db(Arc::new(Db::for_testing(pool)))
|
||||
}
|
||||
|
||||
fn production_test_schema_with_db(db: Arc<Db>) -> GitlawbSchema {
|
||||
build_schema(
|
||||
db,
|
||||
tokio::sync::broadcast::channel(1).0,
|
||||
tokio::sync::broadcast::channel(1).0,
|
||||
)
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn ref_update_subscription_alias_budget() {
|
||||
assert_subscription_alias_budget("refUpdates { repo }").await;
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn task_event_subscription_alias_budget() {
|
||||
assert_subscription_alias_budget("taskEvents { taskId }").await;
|
||||
}
|
||||
|
||||
async fn assert_subscription_alias_budget(field: &str) {
|
||||
use futures::StreamExt;
|
||||
use std::time::Duration;
|
||||
let pool = sqlx::postgres::PgPoolOptions::new()
|
||||
.connect_lazy("postgres://localhost/unused")
|
||||
.unwrap();
|
||||
let (ref_tx, _) = tokio::sync::broadcast::channel(16);
|
||||
let (task_tx, _) = tokio::sync::broadcast::channel(16);
|
||||
let schema = build_schema(
|
||||
Arc::new(Db::for_testing(pool)),
|
||||
ref_tx.clone(),
|
||||
task_tx.clone(),
|
||||
);
|
||||
for count in [7, 8] {
|
||||
let fields = (0..count)
|
||||
.map(|n| format!("r{n}: {field}"))
|
||||
.collect::<Vec<_>>()
|
||||
.join(" ");
|
||||
let query = format!("subscription {{ {fields} }}");
|
||||
let mut responses = Box::pin(schema.execute_stream(query));
|
||||
if count == 8 {
|
||||
let response = tokio::time::timeout(Duration::from_secs(1), responses.next())
|
||||
.await
|
||||
.expect("over-budget subscriptions must reject before waiting for events")
|
||||
.expect("the validation error must be returned");
|
||||
assert_eq!(response.errors.len(), 1);
|
||||
assert_eq!(response.errors[0].message, "Query is too complex.");
|
||||
assert_eq!(ref_tx.receiver_count() + task_tx.receiver_count(), 0);
|
||||
continue;
|
||||
}
|
||||
// Poll the accepted operation far enough to register its receivers.
|
||||
assert!(
|
||||
tokio::time::timeout(Duration::from_millis(30), responses.next())
|
||||
.await
|
||||
.is_err()
|
||||
);
|
||||
assert_eq!(ref_tx.receiver_count() + task_tx.receiver_count(), 7);
|
||||
let _ = ref_tx.send(RefUpdateBroadcast {
|
||||
repo: "owner/repo".into(),
|
||||
ref_name: "refs/heads/main".into(),
|
||||
old_sha: "0".repeat(40),
|
||||
new_sha: "1".repeat(40),
|
||||
pusher_did: "did:key:test".into(),
|
||||
node_did: "did:key:node".into(),
|
||||
timestamp: "2026-01-01T00:00:00Z".into(),
|
||||
owner_did: "did:key:test".into(),
|
||||
});
|
||||
let _ = task_tx.send(TaskEventBroadcast {
|
||||
task_id: "task".into(),
|
||||
old_status: "pending".into(),
|
||||
new_status: "claimed".into(),
|
||||
by_did: "did:key:test".into(),
|
||||
at: "2026-01-01T00:00:00Z".into(),
|
||||
});
|
||||
let response = tokio::time::timeout(Duration::from_secs(1), responses.next())
|
||||
.await
|
||||
.unwrap()
|
||||
.unwrap();
|
||||
assert!(response.errors.is_empty(), "{:?}", response.errors);
|
||||
assert_ne!(response.data, Value::Null);
|
||||
drop(responses);
|
||||
assert_eq!(ref_tx.receiver_count() + task_tx.receiver_count(), 0);
|
||||
}
|
||||
}
|
||||
|
||||
#[sqlx::test]
|
||||
async fn production_mutation_budget_accepts_seven_and_rejects_eight(pool: sqlx::PgPool) {
|
||||
let db = Arc::new(Db::for_testing(pool));
|
||||
db.run_migrations().await.unwrap();
|
||||
let caller = "did:key:reviewer";
|
||||
let now = chrono::Utc::now().to_rfc3339();
|
||||
for index in 0..8 {
|
||||
db.create_task(&crate::db::AgentTask {
|
||||
id: format!("task-{index}"),
|
||||
repo_id: None,
|
||||
kind: "test".into(),
|
||||
status: "pending".into(),
|
||||
delegator_did: caller.into(),
|
||||
assignee_did: None,
|
||||
capability: "test".into(),
|
||||
ucan_token: None,
|
||||
payload: None,
|
||||
result: None,
|
||||
created_at: now.clone(),
|
||||
updated_at: now.clone(),
|
||||
deadline: None,
|
||||
})
|
||||
.await
|
||||
.unwrap();
|
||||
}
|
||||
let schema = production_test_schema_with_db(db.clone());
|
||||
for count in [8, 7] {
|
||||
let fields = (0..count)
|
||||
.map(|n| {
|
||||
format!("r{n}: claimTask(id: \"task-{n}\", assigneeDid: \"{caller}\") {{ id }}")
|
||||
})
|
||||
.collect::<Vec<_>>()
|
||||
.join(" ");
|
||||
let response = schema
|
||||
.execute(
|
||||
async_graphql::Request::new(format!("mutation {{ {fields} }}"))
|
||||
.data(crate::auth::AuthenticatedDid(caller.into())),
|
||||
)
|
||||
.await;
|
||||
if count == 8 {
|
||||
assert_eq!(response.errors.len(), 1);
|
||||
assert_eq!(response.errors[0].message, "Query is too complex.");
|
||||
assert_eq!(
|
||||
db.list_tasks(Some("pending"), None, 8).await.unwrap().len(),
|
||||
8
|
||||
);
|
||||
continue;
|
||||
}
|
||||
assert!(response.errors.is_empty(), "{:?}", response.errors);
|
||||
assert_eq!(
|
||||
response
|
||||
.data
|
||||
.into_json()
|
||||
.unwrap()
|
||||
.as_object()
|
||||
.unwrap()
|
||||
.len(),
|
||||
7
|
||||
);
|
||||
assert_eq!(
|
||||
db.list_tasks(Some("claimed"), Some(caller), 8)
|
||||
.await
|
||||
.unwrap()
|
||||
.len(),
|
||||
7
|
||||
);
|
||||
assert_eq!(
|
||||
db.get_task("task-7").await.unwrap().unwrap().status,
|
||||
"pending"
|
||||
);
|
||||
}
|
||||
}
|
||||
|
||||
#[sqlx::test]
|
||||
async fn production_list_cost_scales_with_the_same_alias_count(pool: sqlx::PgPool) {
|
||||
let db = Arc::new(Db::for_testing(pool));
|
||||
db.run_migrations().await.unwrap();
|
||||
let schema = production_test_schema_with_db(db);
|
||||
// Bounds are per-root named constants so the cases move with the
|
||||
// documented maximums instead of going stale as literals.
|
||||
for (field, selection, max) in [
|
||||
("refUpdates", "repo", MAX_VISIBLE_REF_UPDATES),
|
||||
("tasks", "id", MAX_VISIBLE_TASK_PAGE_SIZE),
|
||||
(
|
||||
"reposPage",
|
||||
"nodes { name }",
|
||||
MAX_VISIBLE_REPO_PAGE_SIZE as i64,
|
||||
),
|
||||
] {
|
||||
// Two aliases at the maximum always exceed the budget.
|
||||
let fields = (0..2)
|
||||
.map(|n| format!("r{n}: {field}(limit: {max}) {{ {selection} }}"))
|
||||
.collect::<Vec<_>>()
|
||||
.join(" ");
|
||||
let response = schema.execute(format!("{{ {fields} }}")).await;
|
||||
assert_eq!(response.errors.len(), 1);
|
||||
assert_eq!(response.errors[0].message, "Query is too complex.");
|
||||
|
||||
// At limit 1 two aliases fit for the row-priced roots; reposPage
|
||||
// prices the full corpus scan, so a single alias is the most that
|
||||
// fits under the budget.
|
||||
let aliases = if field == "reposPage" { 1 } else { 2 };
|
||||
let fields = (0..aliases)
|
||||
.map(|n| format!("r{n}: {field}(limit: 1) {{ {selection} }}"))
|
||||
.collect::<Vec<_>>()
|
||||
.join(" ");
|
||||
let response = schema.execute(format!("{{ {fields} }}")).await;
|
||||
assert!(response.errors.is_empty(), "{field}: {:?}", response.errors);
|
||||
assert_eq!(
|
||||
response
|
||||
.data
|
||||
.into_json()
|
||||
.unwrap()
|
||||
.as_object()
|
||||
.unwrap()
|
||||
.len(),
|
||||
aliases
|
||||
);
|
||||
}
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn production_limits_reject_mutation_aliases_and_large_lists() {
|
||||
let schema = production_test_schema();
|
||||
// Limits are derived from the MAX_* constants so the boundaries move
|
||||
// with the documented maximums instead of going stale as literals.
|
||||
for (prefix, count, field) in [
|
||||
("mutation", 8, "claimTask(id: \"missing\", assigneeDid: \"did:key:test\") { id }".to_owned()),
|
||||
("mutation", 8, "createTask(delegatorDid: \"did:key:test\", input: { kind: \"test\", capability: \"test\" }) { id }".to_owned()),
|
||||
("mutation", 8, "completeTask(id: \"missing\", byDid: \"did:key:test\", input: {}) { id }".to_owned()),
|
||||
("mutation", 8, "failTask(id: \"missing\", byDid: \"did:key:test\", input: {}) { id }".to_owned()),
|
||||
("query", 8, "task(id: \"missing\") { id }".to_owned()),
|
||||
("query", 2, format!("refUpdates(limit: {MAX_VISIBLE_REF_UPDATES}) {{ repo }}")),
|
||||
("query", 2, format!("tasks(limit: {MAX_VISIBLE_TASK_PAGE_SIZE}) {{ id }}")),
|
||||
("query", 2, format!("reposPage(limit: {MAX_VISIBLE_REPO_PAGE_SIZE}) {{ nodes {{ name }} }}")),
|
||||
("query", 8, "reposPage(limit: 1) { nodes { name } }".to_owned()),
|
||||
] {
|
||||
let fields = (0..count)
|
||||
.map(|n| format!("r{n}: {field}"))
|
||||
.collect::<Vec<_>>()
|
||||
.join(" ");
|
||||
let response = schema.execute(format!("{prefix} {{ {fields} }}")).await;
|
||||
assert_eq!(response.errors.len(), 1, "{:?}", response.errors);
|
||||
assert_eq!(response.errors[0].message, "Query is too complex.");
|
||||
}
|
||||
}
|
||||
|
||||
#[sqlx::test]
|
||||
async fn production_repos_page_serves_the_documented_maximum(pool: sqlx::PgPool) {
|
||||
let db = Arc::new(Db::for_testing(pool));
|
||||
db.run_migrations().await.unwrap();
|
||||
let schema = production_test_schema_with_db(db);
|
||||
for selection in [
|
||||
"nodes { name }",
|
||||
"nodes { name ownerDid } hasNextPage endCursor",
|
||||
] {
|
||||
let response = schema
|
||||
.execute(format!(
|
||||
"{{ reposPage(limit: {MAX_VISIBLE_REPO_PAGE_SIZE}) {{ {selection} }} }}"
|
||||
))
|
||||
.await;
|
||||
assert!(response.errors.is_empty(), "{:?}", response.errors);
|
||||
assert_eq!(
|
||||
response.data.into_json().unwrap()["reposPage"]["nodes"],
|
||||
serde_json::json!([])
|
||||
);
|
||||
}
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn seven_root_aliases_are_accepted() {
|
||||
struct Root(Arc<AtomicUsize>);
|
||||
#[Object]
|
||||
impl Root {
|
||||
#[graphql(complexity = "50 + child_complexity")]
|
||||
async fn repos(&self) -> Vec<Nested> {
|
||||
self.0.fetch_add(1, Ordering::Relaxed);
|
||||
vec![Nested]
|
||||
}
|
||||
}
|
||||
let calls = Arc::new(AtomicUsize::new(0));
|
||||
let schema = apply_query_limits(Schema::build(
|
||||
Root(calls.clone()),
|
||||
EmptyMutation,
|
||||
EmptySubscription,
|
||||
))
|
||||
.finish();
|
||||
let fields = (0..7)
|
||||
.map(|n| format!("r{n}: repos {{ value }}"))
|
||||
.collect::<Vec<_>>()
|
||||
.join(" ");
|
||||
let response = schema.execute(format!("{{ {fields} }}")).await;
|
||||
assert!(response.errors.is_empty(), "{:?}", response.errors);
|
||||
assert_eq!(calls.load(Ordering::Relaxed), 7);
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn expensive_root_aliases_are_rejected_before_database_access() {
|
||||
// Use the production builder with a lazy pool: rejection must precede DB access.
|
||||
let schema = production_test_schema();
|
||||
let fields = (0..8)
|
||||
.map(|n| format!("r{n}: repos {{ name }}"))
|
||||
.collect::<Vec<_>>()
|
||||
.join(" ");
|
||||
|
||||
let response = schema.execute(format!("{{ {fields} }}")).await;
|
||||
|
||||
assert_eq!(response.data, Value::Null);
|
||||
assert_eq!(response.errors.len(), 1);
|
||||
assert_eq!(response.errors[0].message, "Query is too complex.");
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn ordinary_schema_introspection_remains_available() {
|
||||
let schema = production_test_schema();
|
||||
let canonical_introspection = r#"
|
||||
query IntrospectionQuery {
|
||||
__schema {
|
||||
queryType { name }
|
||||
mutationType { name }
|
||||
subscriptionType { name }
|
||||
types {
|
||||
...FullType
|
||||
}
|
||||
directives {
|
||||
name
|
||||
description
|
||||
locations
|
||||
args {
|
||||
...InputValue
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
fragment FullType on __Type {
|
||||
kind
|
||||
name
|
||||
description
|
||||
fields(includeDeprecated: true) {
|
||||
name
|
||||
description
|
||||
args {
|
||||
...InputValue
|
||||
}
|
||||
type {
|
||||
...TypeRef
|
||||
}
|
||||
isDeprecated
|
||||
deprecationReason
|
||||
}
|
||||
inputFields {
|
||||
...InputValue
|
||||
}
|
||||
interfaces {
|
||||
...TypeRef
|
||||
}
|
||||
enumValues(includeDeprecated: true) {
|
||||
name
|
||||
description
|
||||
isDeprecated
|
||||
deprecationReason
|
||||
}
|
||||
possibleTypes {
|
||||
...TypeRef
|
||||
}
|
||||
}
|
||||
|
||||
fragment InputValue on __InputValue {
|
||||
name
|
||||
description
|
||||
type { ...TypeRef }
|
||||
defaultValue
|
||||
}
|
||||
|
||||
fragment TypeRef on __Type {
|
||||
kind
|
||||
name
|
||||
ofType {
|
||||
kind
|
||||
name
|
||||
ofType {
|
||||
kind
|
||||
name
|
||||
ofType {
|
||||
kind
|
||||
name
|
||||
ofType {
|
||||
kind
|
||||
name
|
||||
ofType {
|
||||
kind
|
||||
name
|
||||
ofType {
|
||||
kind
|
||||
name
|
||||
ofType {
|
||||
kind
|
||||
name
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
"#;
|
||||
let response = schema.execute(canonical_introspection).await;
|
||||
assert!(
|
||||
response.errors.is_empty(),
|
||||
"canonical introspection query failed against production schema: {:?}",
|
||||
response.errors
|
||||
);
|
||||
assert_ne!(response.data, Value::Null);
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn ref_updates_and_tasks_single_alias_max_limit_complexity_contract() {
|
||||
let pool = sqlx::postgres::PgPoolOptions::new()
|
||||
.connect_lazy("postgres://localhost/unused")
|
||||
.unwrap();
|
||||
pool.close().await;
|
||||
let (ref_tx, _) = tokio::sync::broadcast::channel(16);
|
||||
let (task_tx, _) = tokio::sync::broadcast::channel(16);
|
||||
let schema = build_schema(Arc::new(Db::for_testing(pool)), ref_tx, task_tx);
|
||||
|
||||
// refUpdates(limit: MAX_VISIBLE_REF_UPDATES):
|
||||
// Single-field selection has child_complexity 1 -> cost 100 + 200 + 1 = 301 <= 400.
|
||||
// It passes validation and reaches the resolver (which yields db error on lazy pool).
|
||||
let single_ref = schema
|
||||
.execute(format!(
|
||||
"{{ refUpdates(limit: {MAX_VISIBLE_REF_UPDATES}) {{ repo }} }}"
|
||||
))
|
||||
.await;
|
||||
assert!(
|
||||
!single_ref
|
||||
.errors
|
||||
.iter()
|
||||
.any(|e| e.message == "Query is too complex."),
|
||||
"single-field refUpdates at max limit must pass complexity validation: {:?}",
|
||||
single_ref.errors
|
||||
);
|
||||
assert!(
|
||||
single_ref
|
||||
.errors
|
||||
.iter()
|
||||
.any(|e| e.message == GRAPHQL_DB_ERROR_MESSAGE),
|
||||
"single-field refUpdates at max limit must reach the resolver: {:?}",
|
||||
single_ref.errors
|
||||
);
|
||||
|
||||
// Two-field selection has child_complexity 2 -> cost 100 + 200 + 2 = 302 <= 400.
|
||||
// The documented max-200 request stays reachable with multiple fields
|
||||
// (the old multiplicative price rejected it at 450); it passes
|
||||
// validation and reaches the resolver like the single-field case.
|
||||
let multi_ref = schema
|
||||
.execute(format!(
|
||||
"{{ refUpdates(limit: {MAX_VISIBLE_REF_UPDATES}) {{ repo refName }} }}"
|
||||
))
|
||||
.await;
|
||||
assert!(
|
||||
!multi_ref
|
||||
.errors
|
||||
.iter()
|
||||
.any(|e| e.message == "Query is too complex."),
|
||||
"two-field refUpdates at max limit must pass complexity validation: {:?}",
|
||||
multi_ref.errors
|
||||
);
|
||||
assert!(
|
||||
multi_ref
|
||||
.errors
|
||||
.iter()
|
||||
.any(|e| e.message == GRAPHQL_DB_ERROR_MESSAGE),
|
||||
"two-field refUpdates at max limit must reach the resolver: {:?}",
|
||||
multi_ref.errors
|
||||
);
|
||||
|
||||
// tasks(limit: MAX_VISIBLE_TASK_PAGE_SIZE):
|
||||
// Single-field selection has child_complexity 1, so the cost is
|
||||
// 50 + MAX_VISIBLE_TASK_PAGE_SIZE + 1 <= 400.
|
||||
// It passes validation and reaches the resolver.
|
||||
let single_task = schema
|
||||
.execute(format!(
|
||||
"{{ tasks(limit: {MAX_VISIBLE_TASK_PAGE_SIZE}) {{ id }} }}"
|
||||
))
|
||||
.await;
|
||||
assert!(
|
||||
!single_task
|
||||
.errors
|
||||
.iter()
|
||||
.any(|e| e.message == "Query is too complex."),
|
||||
"single-field tasks at the maximum page size must pass complexity validation: {:?}",
|
||||
single_task.errors
|
||||
);
|
||||
assert!(
|
||||
single_task
|
||||
.errors
|
||||
.iter()
|
||||
.any(|e| e.message == GRAPHQL_DB_ERROR_MESSAGE),
|
||||
"single-field tasks at the maximum page size must reach the resolver: {:?}",
|
||||
single_task.errors
|
||||
);
|
||||
|
||||
// Two-field selection has child_complexity 2, so the cost is
|
||||
// 50 + MAX_VISIBLE_TASK_PAGE_SIZE + 2 <= 400.
|
||||
// A request at the documented maximum stays reachable with multiple
|
||||
// fields (the old multiplicative price rejected it at 450); it passes
|
||||
// validation and reaches the resolver like the single-field case.
|
||||
let multi_task = schema
|
||||
.execute(format!(
|
||||
"{{ tasks(limit: {MAX_VISIBLE_TASK_PAGE_SIZE}) {{ id status }} }}"
|
||||
))
|
||||
.await;
|
||||
assert!(
|
||||
!multi_task
|
||||
.errors
|
||||
.iter()
|
||||
.any(|e| e.message == "Query is too complex."),
|
||||
"two-field tasks at the maximum page size must pass complexity validation: {:?}",
|
||||
multi_task.errors
|
||||
);
|
||||
assert!(
|
||||
multi_task
|
||||
.errors
|
||||
.iter()
|
||||
.any(|e| e.message == GRAPHQL_DB_ERROR_MESSAGE),
|
||||
"two-field tasks at the maximum page size must reach the resolver: {:?}",
|
||||
multi_task.errors
|
||||
);
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn two_repos_aliases_exceed_the_budget() {
|
||||
// `repos` is priced as the full page it scans
|
||||
// (50 + MAX_VISIBLE_REPO_PAGE_SIZE + child), so two `repos { name }`
|
||||
// aliases cost 2 * 251 = 502 > 400 and the document is rejected before
|
||||
// any resolver runs. If the price reverts to `50 + child_complexity`
|
||||
// the aliases cost 2 * 51 = 102, validation passes, and the failure
|
||||
// mode changes (resolver DB errors on the lazy pool): this test goes
|
||||
// red on revert.
|
||||
let schema = production_test_schema();
|
||||
let response = schema
|
||||
.execute("{ r0: repos { name } r1: repos { name } }")
|
||||
.await;
|
||||
assert_eq!(response.errors.len(), 1, "{:?}", response.errors);
|
||||
assert_eq!(response.errors[0].message, "Query is too complex.");
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn seven_repos_page_aliases_exceed_the_budget() {
|
||||
// `reposPage` is priced as the full corpus scan
|
||||
// (50 + MAX_VISIBLE_REPO_PAGE_SIZE + child_complexity), so seven
|
||||
// `reposPage(limit: 1) { nodes { name } }` aliases cost
|
||||
// 7 * (50 + 200 + 2) = 1764 > 400 and the document is rejected
|
||||
// before any resolver runs. Under the previous row-priced formula
|
||||
// the same aliases cost 7 * (50 + 1 + 2) = 371, validation passes,
|
||||
// and the failure mode changes (resolver DB errors on the lazy
|
||||
// pool): this test goes red on revert. Eight aliases are rejected
|
||||
// under both formulas, so seven is the load-bearing boundary.
|
||||
let schema = production_test_schema();
|
||||
let fields = (0..7)
|
||||
.map(|n| format!("r{n}: reposPage(limit: 1) {{ nodes {{ name }} }}"))
|
||||
.collect::<Vec<_>>()
|
||||
.join(" ");
|
||||
let response = schema.execute(format!("{{ {fields} }}")).await;
|
||||
assert_eq!(response.errors.len(), 1, "{:?}", response.errors);
|
||||
assert_eq!(response.errors[0].message, "Query is too complex.");
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn ref_updates_fixed_base_is_charged() {
|
||||
// The 100 base in the refUpdates complexity formula charges for the
|
||||
// collector's fixed work (loading the deduped repo set, the
|
||||
// quarantined set, and the visibility rules, then walking up to 16
|
||||
// keyset pages) even at limit: 1. Four aliases at limit: 1 cost
|
||||
// 4 * (100 + 1 + 1) = 408 > 400 and must be rejected. If the base
|
||||
// disappears, the cost drops to 4 * (1 + 1) = 8 and this test fails.
|
||||
let schema = production_test_schema();
|
||||
let fields = (0..4)
|
||||
.map(|n| format!("r{n}: refUpdates(limit: 1) {{ repo }}"))
|
||||
.collect::<Vec<_>>()
|
||||
.join(" ");
|
||||
let response = schema.execute(format!("{{ {fields} }}")).await;
|
||||
assert_eq!(response.errors.len(), 1, "{:?}", response.errors);
|
||||
assert_eq!(response.errors[0].message, "Query is too complex.");
|
||||
}
|
||||
|
||||
#[derive(Clone, Copy)]
|
||||
struct Nested;
|
||||
|
||||
#[Object]
|
||||
impl Nested {
|
||||
async fn child(&self) -> Nested {
|
||||
Nested
|
||||
}
|
||||
|
||||
async fn value(&self) -> i32 {
|
||||
1
|
||||
}
|
||||
}
|
||||
|
||||
struct CountingQuery(Arc<AtomicUsize>);
|
||||
|
||||
#[Object]
|
||||
impl CountingQuery {
|
||||
async fn nested(&self) -> Nested {
|
||||
self.0.fetch_add(1, Ordering::Relaxed);
|
||||
Nested
|
||||
}
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn query_depth_limit_accepts_fourteen_and_rejects_fifteen() {
|
||||
let calls = Arc::new(AtomicUsize::new(0));
|
||||
let schema = apply_query_limits(Schema::build(
|
||||
CountingQuery(Arc::clone(&calls)),
|
||||
EmptyMutation,
|
||||
EmptySubscription,
|
||||
))
|
||||
.finish();
|
||||
let query_at_depth = |depth: usize| {
|
||||
let selection = (2..depth).fold("value".to_string(), |selection, _| {
|
||||
format!("child {{ {selection} }}")
|
||||
});
|
||||
format!("{{ nested {{ {selection} }} }}")
|
||||
};
|
||||
|
||||
let accepted = schema.execute(query_at_depth(GRAPHQL_MAX_DEPTH)).await;
|
||||
|
||||
assert!(
|
||||
accepted.errors.is_empty(),
|
||||
"depth {GRAPHQL_MAX_DEPTH} should be accepted: {:?}",
|
||||
accepted.errors
|
||||
);
|
||||
assert_eq!(calls.swap(0, Ordering::Relaxed), 1);
|
||||
|
||||
let rejected = schema.execute(query_at_depth(GRAPHQL_MAX_DEPTH + 1)).await;
|
||||
|
||||
assert_eq!(rejected.data, Value::Null);
|
||||
assert_eq!(rejected.errors.len(), 1);
|
||||
assert_eq!(rejected.errors[0].message, "Query is nested too deep.");
|
||||
assert_eq!(calls.load(Ordering::Relaxed), 0);
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn production_schema_enforces_depth_limit() {
|
||||
let schema = production_test_schema();
|
||||
// Depth 14 is accepted through the production build_schema path.
|
||||
let of_types_14 = (0..9).fold("name".to_string(), |acc, _| format!("ofType {{ {acc} }}"));
|
||||
let query_14 =
|
||||
format!("{{ __schema {{ types {{ fields {{ type {{ {of_types_14} }} }} }} }} }}");
|
||||
let accepted = schema.execute(&query_14).await;
|
||||
assert!(accepted.errors.is_empty(), "{:?}", accepted.errors);
|
||||
|
||||
// Construct an introspection query of depth 15 using __schema.
|
||||
// 1: __schema
|
||||
// 2: types
|
||||
// 3: fields
|
||||
// 4: type
|
||||
// 5..14: ofType (10 times)
|
||||
// 15: name
|
||||
// Total depth = 15 > GRAPHQL_MAX_DEPTH (14).
|
||||
let of_types = (0..10).fold("name".to_string(), |acc, _| format!("ofType {{ {acc} }}"));
|
||||
let query = format!("{{ __schema {{ types {{ fields {{ type {{ {of_types} }} }} }} }} }}");
|
||||
|
||||
let rejected = schema.execute(&query).await;
|
||||
assert_eq!(rejected.data, async_graphql::Value::Null);
|
||||
assert_eq!(rejected.errors.len(), 1);
|
||||
assert_eq!(rejected.errors[0].message, "Query is nested too deep.");
|
||||
}
|
||||
|
||||
/// Every `.map_err(` in the GraphQL query/mutation resolvers must route
|
||||
/// through the opaque helpers, or discard the error (`|_|`). Same source-
|
||||
/// scrape pattern as `api::authz_guard` (#255 review).
|
||||
|
||||
@@ -22,6 +22,7 @@ pub struct MutationRoot;
|
||||
|
||||
#[Object]
|
||||
impl MutationRoot {
|
||||
#[graphql(complexity = "50 + child_complexity")]
|
||||
async fn create_task(
|
||||
&self,
|
||||
ctx: &Context<'_>,
|
||||
@@ -79,12 +80,17 @@ impl MutationRoot {
|
||||
updated_at: now,
|
||||
deadline: input.deadline,
|
||||
};
|
||||
db.create_task(&task)
|
||||
// Return the stored row, not the pre-insert input: create_task
|
||||
// normalizes the assignee (whitespace-only becomes NULL/open), and a
|
||||
// response that shows the raw input lies about the reservation.
|
||||
let stored = db
|
||||
.create_task(&task)
|
||||
.await
|
||||
.map_err(crate::graphql::graphql_db_err)?;
|
||||
Ok(AgentTaskType::from(task))
|
||||
Ok(AgentTaskType::from(stored))
|
||||
}
|
||||
|
||||
#[graphql(complexity = "50 + child_complexity")]
|
||||
async fn claim_task(
|
||||
&self,
|
||||
ctx: &Context<'_>,
|
||||
@@ -104,16 +110,25 @@ impl MutationRoot {
|
||||
.claim_task(&id, &assignee_did)
|
||||
.await
|
||||
.map_err(crate::graphql::graphql_db_err)?;
|
||||
// Report the stored assignee form like REST, so subscribers see the
|
||||
// same identity whichever API surface ran the transition.
|
||||
let by_did = task
|
||||
.assignee_did
|
||||
.as_deref()
|
||||
.map(crate::db::trim_assignee_did)
|
||||
.unwrap_or(assignee_did.as_str())
|
||||
.to_string();
|
||||
let _ = tx.send(TaskEventBroadcast {
|
||||
task_id: id,
|
||||
old_status: "pending".to_string(),
|
||||
new_status: "claimed".to_string(),
|
||||
by_did: assignee_did,
|
||||
by_did,
|
||||
at: Utc::now().to_rfc3339(),
|
||||
});
|
||||
Ok(AgentTaskType::from(task))
|
||||
}
|
||||
|
||||
#[graphql(complexity = "50 + child_complexity")]
|
||||
async fn complete_task(
|
||||
&self,
|
||||
ctx: &Context<'_>,
|
||||
@@ -137,15 +152,24 @@ impl MutationRoot {
|
||||
.await
|
||||
.map_err(crate::graphql::graphql_db_err)?
|
||||
.ok_or_else(|| async_graphql::Error::new("task not found"))?;
|
||||
if !crate::api::did_matches(caller, existing.assignee_did.as_deref().unwrap_or_default()) {
|
||||
if !crate::api::did_matches(
|
||||
caller,
|
||||
crate::db::trim_assignee_did(existing.assignee_did.as_deref().unwrap_or_default()),
|
||||
) {
|
||||
return Err(async_graphql::Error::new(
|
||||
"only the task assignee can complete it",
|
||||
));
|
||||
}
|
||||
let task = db
|
||||
.finish_task(&id, "completed", input.result.as_deref())
|
||||
.finish_task(&id, "completed", input.result.as_deref(), caller)
|
||||
.await
|
||||
.map_err(crate::graphql::graphql_db_err)?;
|
||||
let by_did = task
|
||||
.assignee_did
|
||||
.as_deref()
|
||||
.map(crate::db::trim_assignee_did)
|
||||
.unwrap_or(by_did.as_str())
|
||||
.to_string();
|
||||
let _ = tx.send(TaskEventBroadcast {
|
||||
task_id: id,
|
||||
old_status: "claimed".to_string(),
|
||||
@@ -156,6 +180,7 @@ impl MutationRoot {
|
||||
Ok(AgentTaskType::from(task))
|
||||
}
|
||||
|
||||
#[graphql(complexity = "50 + child_complexity")]
|
||||
async fn fail_task(
|
||||
&self,
|
||||
ctx: &Context<'_>,
|
||||
@@ -178,16 +203,25 @@ impl MutationRoot {
|
||||
.await
|
||||
.map_err(crate::graphql::graphql_db_err)?
|
||||
.ok_or_else(|| async_graphql::Error::new("task not found"))?;
|
||||
if !crate::api::did_matches(caller, existing.assignee_did.as_deref().unwrap_or_default()) {
|
||||
if !crate::api::did_matches(
|
||||
caller,
|
||||
crate::db::trim_assignee_did(existing.assignee_did.as_deref().unwrap_or_default()),
|
||||
) {
|
||||
return Err(async_graphql::Error::new(
|
||||
"only the task assignee can fail it",
|
||||
));
|
||||
}
|
||||
let reason = input.reason.unwrap_or_default();
|
||||
let task = db
|
||||
.finish_task(&id, "failed", Some(&reason))
|
||||
.finish_task(&id, "failed", Some(&reason), caller)
|
||||
.await
|
||||
.map_err(crate::graphql::graphql_db_err)?;
|
||||
let by_did = task
|
||||
.assignee_did
|
||||
.as_deref()
|
||||
.map(crate::db::trim_assignee_did)
|
||||
.unwrap_or(by_did.as_str())
|
||||
.to_string();
|
||||
let _ = tx.send(TaskEventBroadcast {
|
||||
task_id: id,
|
||||
old_status: "claimed".to_string(),
|
||||
@@ -573,4 +607,162 @@ mod tests {
|
||||
"schema text leaked through the gate: {errs}"
|
||||
);
|
||||
}
|
||||
|
||||
/// Pre-assigned GraphQL claimTask must reject a stranger (no UCAN leak)
|
||||
/// and admit the reserved assignee.
|
||||
#[sqlx::test]
|
||||
async fn claim_task_honors_preassigned_assignee(pool: PgPool) {
|
||||
let state = crate::test_support::test_state(pool).await;
|
||||
let reserved = "did:key:zGQLRESERVEDAAAAAAAAAAAAAAAAAAAAAAAAAAAA";
|
||||
let thief = "did:key:zGQLTHIEFBBBBBBBBBBBBBBBBBBBBBBBBBBBBBB";
|
||||
let now = chrono::Utc::now().to_rfc3339();
|
||||
let task = crate::db::AgentTask {
|
||||
id: "task-gql-reserved".into(),
|
||||
repo_id: None,
|
||||
kind: "build".into(),
|
||||
status: "pending".into(),
|
||||
delegator_did: "did:key:zGQLDELEGATORCCCCCCCCCCCCCCCCCCCCCCCCCC".into(),
|
||||
assignee_did: Some(reserved.into()),
|
||||
capability: "repo:write".into(),
|
||||
ucan_token: Some("gql-ucan-secret".into()),
|
||||
payload: None,
|
||||
result: None,
|
||||
created_at: now.clone(),
|
||||
updated_at: now,
|
||||
deadline: None,
|
||||
};
|
||||
state.db.create_task(&task).await.expect("seed");
|
||||
let schema = state.graphql_schema.as_ref();
|
||||
|
||||
let q = |actor: &str| {
|
||||
format!(
|
||||
r#"mutation {{ claimTask(id: "task-gql-reserved", assigneeDid: "{actor}") {{ id status ucanToken }} }}"#
|
||||
)
|
||||
};
|
||||
|
||||
let resp = schema
|
||||
.execute(Request::new(q(thief)).data(AuthenticatedDid(thief.into())))
|
||||
.await;
|
||||
let errs = errors(&resp);
|
||||
assert!(
|
||||
errs.contains("reserved"),
|
||||
"stranger claim must surface reserved deny distinctly: {errs}"
|
||||
);
|
||||
assert!(
|
||||
!errs.contains("gql-ucan-secret"),
|
||||
"UCAN must not leak in GraphQL errors: {errs}"
|
||||
);
|
||||
if let Ok(data) = resp.data.into_json() {
|
||||
let s = data.to_string();
|
||||
assert!(
|
||||
!s.contains("gql-ucan-secret"),
|
||||
"UCAN must not leak in GraphQL data on failed claim: {s}"
|
||||
);
|
||||
}
|
||||
// Parity with REST: failed steal must leave the row untouched.
|
||||
let still = state
|
||||
.db
|
||||
.get_task("task-gql-reserved")
|
||||
.await
|
||||
.expect("get")
|
||||
.expect("task exists");
|
||||
assert_eq!(
|
||||
still.status, "pending",
|
||||
"status must stay pending after steal"
|
||||
);
|
||||
assert_eq!(
|
||||
still.assignee_did.as_deref(),
|
||||
Some(reserved),
|
||||
"assignee_did must stay reserved after steal"
|
||||
);
|
||||
|
||||
let resp = schema
|
||||
.execute(Request::new(q(reserved)).data(AuthenticatedDid(reserved.into())))
|
||||
.await;
|
||||
assert!(
|
||||
errors(&resp).is_empty(),
|
||||
"reserved assignee must claim: {}",
|
||||
errors(&resp)
|
||||
);
|
||||
let data = resp.data.into_json().expect("json data");
|
||||
assert_eq!(data["claimTask"]["status"], "claimed");
|
||||
assert_eq!(data["claimTask"]["ucanToken"], "gql-ucan-secret");
|
||||
}
|
||||
|
||||
/// create_task normalizes a whitespace-only assignee to NULL (open task),
|
||||
/// so the create response must show the stored row, not echo the input: a
|
||||
/// client trusting the echoed "reservation" would believe a claimable task
|
||||
/// is reserved. Before the fix the response was built from the pre-insert
|
||||
/// struct and returned the padded input verbatim.
|
||||
#[sqlx::test]
|
||||
async fn create_task_reports_stored_assignee_not_input(pool: PgPool) {
|
||||
let state = crate::test_support::test_state(pool).await;
|
||||
let caller = "did:key:zGQLCREATORAAAAAAAAAAAAAAAAAAAAAAAAAAAAA";
|
||||
let schema = state.graphql_schema.as_ref();
|
||||
let q = format!(
|
||||
r#"mutation {{ createTask(delegatorDid: "{caller}", input: {{ kind: "build", capability: "repo:write", assigneeDid: " " }}) {{ id assigneeDid }} }}"#
|
||||
);
|
||||
let resp = schema
|
||||
.execute(Request::new(q).data(AuthenticatedDid(caller.into())))
|
||||
.await;
|
||||
let data = resp.data.into_json().expect("json data");
|
||||
assert!(
|
||||
data["createTask"]["assigneeDid"].is_null(),
|
||||
"whitespace-only assigneeDid must come back null (stored shape): {data}"
|
||||
);
|
||||
}
|
||||
|
||||
/// A task seeded with a whitespace-padded assignee must still be
|
||||
/// completable by that assignee over GraphQL: REST and Db::finish_task
|
||||
/// trim the stored value before comparing, and the GraphQL gate must do
|
||||
/// the same or padded reservations finish only through REST.
|
||||
#[sqlx::test]
|
||||
async fn graphql_finish_accepts_padded_stored_assignee(pool: PgPool) {
|
||||
let state = crate::test_support::test_state(pool).await;
|
||||
let assignee = "did:key:zGQLPADDEDAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA";
|
||||
let now = chrono::Utc::now().to_rfc3339();
|
||||
let task = crate::db::AgentTask {
|
||||
id: "task-gql-padded".into(),
|
||||
repo_id: None,
|
||||
kind: "build".into(),
|
||||
status: "pending".into(),
|
||||
delegator_did: "did:key:zGQLDELEGATORDDDDDDDDDDDDDDDDDDDDDDDDDD".into(),
|
||||
assignee_did: Some(format!("\t{assignee}\n")),
|
||||
capability: "repo:write".into(),
|
||||
ucan_token: None,
|
||||
payload: None,
|
||||
result: None,
|
||||
created_at: now.clone(),
|
||||
updated_at: now,
|
||||
deadline: None,
|
||||
};
|
||||
state.db.create_task(&task).await.expect("seed");
|
||||
let schema = state.graphql_schema.as_ref();
|
||||
|
||||
let claim = format!(
|
||||
r#"mutation {{ claimTask(id: "task-gql-padded", assigneeDid: "{assignee}") {{ id status }} }}"#
|
||||
);
|
||||
let resp = schema
|
||||
.execute(Request::new(claim).data(AuthenticatedDid(assignee.into())))
|
||||
.await;
|
||||
assert!(
|
||||
errors(&resp).is_empty(),
|
||||
"reserved assignee must claim a padded reservation: {}",
|
||||
errors(&resp)
|
||||
);
|
||||
|
||||
let finish = format!(
|
||||
r#"mutation {{ completeTask(id: "task-gql-padded", byDid: "{assignee}", input: {{}}) {{ id status }} }}"#
|
||||
);
|
||||
let resp = schema
|
||||
.execute(Request::new(finish).data(AuthenticatedDid(assignee.into())))
|
||||
.await;
|
||||
let errs = errors(&resp);
|
||||
assert!(
|
||||
errs.is_empty(),
|
||||
"assignee must complete a padded reservation: {errs}"
|
||||
);
|
||||
let data = resp.data.into_json().expect("json data");
|
||||
assert_eq!(data["completeTask"]["status"], "completed");
|
||||
}
|
||||
}
|
||||
@@ -1,57 +1,154 @@
|
||||
use async_graphql::{Context, Object, Result};
|
||||
use base64::{engine::general_purpose::URL_SAFE_NO_PAD, Engine};
|
||||
use std::sync::Arc;
|
||||
|
||||
use crate::db::Db;
|
||||
use crate::api::events::MAX_VISIBLE_REF_UPDATES;
|
||||
use crate::db::{Db, RepoRecord, MAX_VISIBLE_REPO_PAGE_SIZE, MAX_VISIBLE_TASK_PAGE_SIZE};
|
||||
|
||||
use super::types::{AgentTaskType, RefUpdateType, RepoType};
|
||||
use super::types::{AgentTaskType, RefUpdateType, RepoPageType, RepoType};
|
||||
|
||||
fn repo_type(repo: RepoRecord) -> RepoType {
|
||||
RepoType {
|
||||
name: repo.name,
|
||||
owner_did: repo.owner_did,
|
||||
description: repo.description,
|
||||
default_branch: repo.default_branch,
|
||||
created_at: repo.created_at.to_rfc3339(),
|
||||
}
|
||||
}
|
||||
|
||||
fn repo_cursor(repo: &RepoRecord) -> String {
|
||||
URL_SAFE_NO_PAD.encode(
|
||||
serde_json::to_vec(&(&repo.owner_did, &repo.name))
|
||||
.expect("a pair of strings is JSON serializable"),
|
||||
)
|
||||
}
|
||||
|
||||
fn parse_repo_cursor(cursor: &str) -> Result<(String, String)> {
|
||||
// A position contains only public response fields, not a database id or
|
||||
// authority. Every page re-evaluates visibility for the current caller.
|
||||
if cursor.len() > 4096 {
|
||||
return Err(async_graphql::Error::new("invalid repository cursor"));
|
||||
}
|
||||
let bytes = URL_SAFE_NO_PAD
|
||||
.decode(cursor)
|
||||
.map_err(|_| async_graphql::Error::new("invalid repository cursor"))?;
|
||||
let position: (String, String) = serde_json::from_slice(&bytes)
|
||||
.map_err(|_| async_graphql::Error::new("invalid repository cursor"))?;
|
||||
// PostgreSQL text cannot contain NUL. Reject it as malformed input before
|
||||
// binding either cursor component, rather than reporting a database error.
|
||||
if position.0.contains('\0') || position.1.contains('\0') {
|
||||
return Err(async_graphql::Error::new("invalid repository cursor"));
|
||||
}
|
||||
Ok(position)
|
||||
}
|
||||
|
||||
pub struct QueryRoot;
|
||||
|
||||
#[Object]
|
||||
impl QueryRoot {
|
||||
// DB-backed roots carry a base cost so aliases consume the request budget
|
||||
// even when each alias selects only one inexpensive response field.
|
||||
// `repos` performs the same full corpus scan as a max-size `reposPage`
|
||||
// (list_visible_repos_page with MAX_VISIBLE_REPO_PAGE_SIZE + 1), so it
|
||||
// is priced as the full page it is, not as a cheap alias.
|
||||
#[graphql(complexity = "50 + MAX_VISIBLE_REPO_PAGE_SIZE + child_complexity")]
|
||||
/// Complete visible repository list, up to the documented maximum number
|
||||
/// of entries. Larger lists must use reposPage; this field returns an
|
||||
/// error instead of truncating silently.
|
||||
async fn repos(&self, ctx: &Context<'_>) -> Result<Vec<RepoType>> {
|
||||
let db = ctx.data_unchecked::<Arc<Db>>();
|
||||
let repos = db
|
||||
.list_all_repos_deduped()
|
||||
.await
|
||||
.map_err(crate::graphql::graphql_db_err)?;
|
||||
|
||||
// Apply the same "/" visibility gate the REST/per-repo endpoints use so
|
||||
// this surface does not enumerate private repos (#97). The caller DID is
|
||||
// threaded onto the context by optional_signature; absent = anonymous.
|
||||
let caller = ctx
|
||||
.data::<crate::auth::AuthenticatedDid>()
|
||||
.ok()
|
||||
.map(|d| d.0.as_str());
|
||||
let ids: Vec<String> = repos.iter().map(|r| r.id.clone()).collect();
|
||||
let rules_by_repo = db
|
||||
.list_visibility_rules_for_repos(&ids)
|
||||
let mut repos = db
|
||||
.list_visible_repos_page(caller, None, MAX_VISIBLE_REPO_PAGE_SIZE + 1)
|
||||
.await
|
||||
.map_err(crate::graphql::graphql_db_err)?;
|
||||
|
||||
Ok(repos
|
||||
.into_iter()
|
||||
.filter(|r| {
|
||||
let rules = rules_by_repo.get(&r.id).map(Vec::as_slice).unwrap_or(&[]);
|
||||
crate::visibility::listable_at_root(rules, r.is_public, &r.owner_did, caller)
|
||||
})
|
||||
.map(|r| RepoType {
|
||||
name: r.name,
|
||||
owner_did: r.owner_did,
|
||||
description: r.description,
|
||||
default_branch: r.default_branch,
|
||||
created_at: r.created_at.to_rfc3339(),
|
||||
})
|
||||
.collect())
|
||||
if repos.len() > MAX_VISIBLE_REPO_PAGE_SIZE {
|
||||
return Err(async_graphql::Error::new(format!(
|
||||
"repository list exceeds {} entries; use reposPage with limit and after",
|
||||
MAX_VISIBLE_REPO_PAGE_SIZE
|
||||
)));
|
||||
}
|
||||
// Preserve the legacy activity ordering for complete, small lists.
|
||||
repos.sort_by_key(|repo| std::cmp::Reverse(repo.updated_at));
|
||||
Ok(repos.into_iter().map(repo_type).collect())
|
||||
}
|
||||
|
||||
/// Bounded visible repositories ordered by owner and name. Continue with
|
||||
/// endCursor while hasNextPage is true. Pages are not a database snapshot.
|
||||
// Every page sorts the full deduplicated corpus under COLLATE "C"
|
||||
// (list_visible_repos_page documents the accepted O(total repos) bound),
|
||||
// so the price charges the scan, not the emitted rows: a limit:1 page
|
||||
// costs the same as a max-size page, the way `repos` is priced.
|
||||
#[graphql(complexity = "50 + MAX_VISIBLE_REPO_PAGE_SIZE + child_complexity")]
|
||||
async fn repos_page(
|
||||
&self,
|
||||
ctx: &Context<'_>,
|
||||
#[graphql(
|
||||
default = 50,
|
||||
desc = "Page size from 1 to the documented maximum; other values are rejected."
|
||||
)]
|
||||
limit: i64,
|
||||
after: Option<String>,
|
||||
) -> Result<RepoPageType> {
|
||||
if !(1..=MAX_VISIBLE_REPO_PAGE_SIZE as i64).contains(&limit) {
|
||||
return Err(async_graphql::Error::new(format!(
|
||||
"limit must be between 1 and {}",
|
||||
MAX_VISIBLE_REPO_PAGE_SIZE
|
||||
)));
|
||||
}
|
||||
let after = after.as_deref().map(parse_repo_cursor).transpose()?;
|
||||
let caller = ctx
|
||||
.data::<crate::auth::AuthenticatedDid>()
|
||||
.ok()
|
||||
.map(|d| d.0.as_str());
|
||||
let db = ctx.data_unchecked::<Arc<Db>>();
|
||||
let mut repos = db
|
||||
.list_visible_repos_page(
|
||||
caller,
|
||||
after
|
||||
.as_ref()
|
||||
.map(|(owner, name)| (owner.as_str(), name.as_str())),
|
||||
limit as usize + 1,
|
||||
)
|
||||
.await
|
||||
.map_err(crate::graphql::graphql_db_err)?;
|
||||
let has_next_page = repos.len() > limit as usize;
|
||||
repos.truncate(limit as usize);
|
||||
let end_cursor = repos.last().map(repo_cursor);
|
||||
Ok(RepoPageType {
|
||||
nodes: repos.into_iter().map(repo_type).collect(),
|
||||
has_next_page,
|
||||
end_cursor,
|
||||
})
|
||||
}
|
||||
|
||||
// Complexity is additive with a base reflecting the collector's fixed scan:
|
||||
// every request loads the full deduped repo set, the quarantined set, and
|
||||
// the visibility rules, then walks up to max(limit, 2048) event rows past
|
||||
// withheld ones, regardless of `limit`. A multiplicative price both
|
||||
// undercharged limit:1 (51 for that fixed work) and made a request at the
|
||||
// documented maximum unreachable (two fields at max limit cost 450 > 400).
|
||||
//
|
||||
// Decision on the collector floor (review #465, 3rd round): the up-to-2048
|
||||
// walk is bounded constant overhead that does not scale with `limit`, so
|
||||
// it is priced in the fixed base, not the limit term; the limit term
|
||||
// prices only the emitted rows. Pricing the walk at face value in the base
|
||||
// would put every refUpdates query over the 400 budget and make the field
|
||||
// unusable, so the base prices that fixed scan as a lump sum instead.
|
||||
#[graphql(
|
||||
complexity = "100 + (limit.clamp(0, MAX_VISIBLE_REF_UPDATES) as usize) + child_complexity"
|
||||
)]
|
||||
async fn ref_updates(
|
||||
&self,
|
||||
ctx: &Context<'_>,
|
||||
repo: Option<String>,
|
||||
#[graphql(
|
||||
default = 20,
|
||||
desc = "Max 200; larger requests return the newest 200 rows (no continuation cursor)."
|
||||
desc = "Requests above the documented maximum return the newest rows up to that maximum (no continuation cursor)."
|
||||
)]
|
||||
limit: i64,
|
||||
) -> Result<Vec<RefUpdateType>> {
|
||||
@@ -105,6 +202,14 @@ impl QueryRoot {
|
||||
Ok(resolved)
|
||||
}
|
||||
|
||||
// Complexity is additive: list_tasks is a single LIMIT-bounded query whose
|
||||
// cost does not scale with the selected fields, so the price is the base
|
||||
// plus the clamped limit plus the child fields. A multiplicative price
|
||||
// made a request at the documented maximum unreachable (two fields at max
|
||||
// limit cost 450 > 400).
|
||||
#[graphql(
|
||||
complexity = "50 + (limit.clamp(0, MAX_VISIBLE_TASK_PAGE_SIZE) as usize) + child_complexity"
|
||||
)]
|
||||
async fn tasks(
|
||||
&self,
|
||||
ctx: &Context<'_>,
|
||||
@@ -112,7 +217,7 @@ impl QueryRoot {
|
||||
assignee_did: Option<String>,
|
||||
#[graphql(
|
||||
default = 50,
|
||||
desc = "Max 200; larger requests are clamped to 200 (no error). Negative values clamp to 0."
|
||||
desc = "Requests above the documented maximum are clamped to it (no error). Negative values clamp to 0."
|
||||
)]
|
||||
limit: i64,
|
||||
) -> Result<Vec<AgentTaskType>> {
|
||||
@@ -120,7 +225,7 @@ impl QueryRoot {
|
||||
// Clamp before SQL: a negative LIMIT is a client fault that Postgres
|
||||
// rejects with 2201W, which would otherwise trip the opaque DB path
|
||||
// and write an error-level log on every probe (#250 review).
|
||||
let limit = limit.clamp(0, 200);
|
||||
let limit = limit.clamp(0, MAX_VISIBLE_TASK_PAGE_SIZE);
|
||||
let tasks = db
|
||||
.list_tasks(status.as_deref(), assignee_did.as_deref(), limit)
|
||||
.await
|
||||
@@ -128,6 +233,7 @@ impl QueryRoot {
|
||||
Ok(tasks.into_iter().map(AgentTaskType::from).collect())
|
||||
}
|
||||
|
||||
#[graphql(complexity = "50 + child_complexity")]
|
||||
async fn task(&self, ctx: &Context<'_>, id: String) -> Result<Option<AgentTaskType>> {
|
||||
let db = ctx.data_unchecked::<Arc<Db>>();
|
||||
let t = db
|
||||
@@ -141,12 +247,642 @@ impl QueryRoot {
|
||||
#[cfg(test)]
|
||||
mod tests {
|
||||
use crate::db::{Db, ReceivedRefUpdate, RepoRecord};
|
||||
use base64::Engine;
|
||||
use chrono::Utc;
|
||||
use sqlx::PgPool;
|
||||
use std::sync::Arc;
|
||||
|
||||
const OWNER: &str = "did:key:z6MkOwner";
|
||||
|
||||
#[sqlx::test]
|
||||
async fn repos_legacy_rejects_overflow_and_pages_reach_every_visible_repo(pool: PgPool) {
|
||||
let db = db(pool).await;
|
||||
let total = crate::db::MAX_VISIBLE_REPO_PAGE_SIZE + 5;
|
||||
for index in 0..total {
|
||||
let name = format!("repo-{index:03}");
|
||||
db.create_repo(&repo(&name, OWNER, &name, true))
|
||||
.await
|
||||
.unwrap();
|
||||
}
|
||||
// The SQL helper itself must bound materialization, even for a caller
|
||||
// accidentally requesting an unlimited page.
|
||||
assert_eq!(
|
||||
db.list_visible_repos_page(None, None, usize::MAX)
|
||||
.await
|
||||
.unwrap()
|
||||
.len(),
|
||||
crate::db::MAX_VISIBLE_REPO_PAGE_SIZE + 1
|
||||
);
|
||||
let schema = schema(db);
|
||||
let legacy = anon(&schema, "{ repos { name } }").await;
|
||||
assert_eq!(legacy.errors.len(), 1);
|
||||
assert!(legacy.errors[0].message.contains("use reposPage"));
|
||||
assert_eq!(legacy.data, async_graphql::Value::Null);
|
||||
|
||||
let mut cursor = None;
|
||||
let mut names = Vec::new();
|
||||
loop {
|
||||
let response = schema.execute(
|
||||
async_graphql::Request::new(
|
||||
"query($after: String) { reposPage(limit: 50, after: $after) { nodes { name } hasNextPage endCursor } }",
|
||||
).variables(async_graphql::Variables::from_json(serde_json::json!({"after": cursor}))),
|
||||
).await;
|
||||
assert!(response.errors.is_empty(), "{:?}", response.errors);
|
||||
let json = response.data.into_json().unwrap();
|
||||
let page = &json["reposPage"];
|
||||
let rows = page["nodes"].as_array().unwrap();
|
||||
assert!(rows.len() <= 50);
|
||||
names.extend(
|
||||
rows.iter()
|
||||
.map(|row| row["name"].as_str().unwrap().to_owned()),
|
||||
);
|
||||
if !page["hasNextPage"].as_bool().unwrap() {
|
||||
break;
|
||||
}
|
||||
let next = page["endCursor"].as_str().unwrap().to_owned();
|
||||
assert_ne!(cursor.as_ref(), Some(&next));
|
||||
cursor = Some(next);
|
||||
assert!(names.len() <= crate::db::MAX_VISIBLE_REPO_PAGE_SIZE);
|
||||
}
|
||||
assert_eq!(
|
||||
names,
|
||||
(0..total)
|
||||
.map(|index| format!("repo-{index:03}"))
|
||||
.collect::<Vec<_>>()
|
||||
);
|
||||
}
|
||||
|
||||
#[sqlx::test]
|
||||
async fn repos_legacy_accepts_exactly_the_visible_bound(pool: PgPool) {
|
||||
let db = db(pool).await;
|
||||
let base_time = Utc::now();
|
||||
let total = crate::db::MAX_VISIBLE_REPO_PAGE_SIZE;
|
||||
for index in 0..total {
|
||||
let name = format!("repo-{index:03}");
|
||||
let mut r = repo(&name, OWNER, &name, true);
|
||||
// Anti-correlate updated_at with name, creation order, and index
|
||||
// so only ordering by updated_at DESC can satisfy the expectation.
|
||||
let offset = (index * 37) % total;
|
||||
r.updated_at = base_time + chrono::Duration::seconds(offset as i64);
|
||||
db.create_repo(&r).await.unwrap();
|
||||
}
|
||||
db.create_repo(&repo("hidden", OWNER, "hidden", false))
|
||||
.await
|
||||
.unwrap();
|
||||
let response = anon(&schema(db), "{ repos { name } }").await;
|
||||
assert!(response.errors.is_empty(), "{:?}", response.errors);
|
||||
let repos = response.data.into_json().unwrap()["repos"]
|
||||
.as_array()
|
||||
.unwrap()
|
||||
.clone();
|
||||
assert_eq!(repos.len(), total);
|
||||
let names: Vec<_> = repos.iter().filter_map(|r| r["name"].as_str()).collect();
|
||||
assert!(
|
||||
!names.contains(&"hidden"),
|
||||
"hidden repo must be excluded from legacy repos response"
|
||||
);
|
||||
let mut expected_indices = (0..total).collect::<Vec<_>>();
|
||||
expected_indices.sort_by_key(|&idx| std::cmp::Reverse((idx * 37) % total));
|
||||
let expected_names: Vec<String> = expected_indices
|
||||
.into_iter()
|
||||
.map(|index| format!("repo-{index:03}"))
|
||||
.collect();
|
||||
assert_eq!(
|
||||
names,
|
||||
expected_names
|
||||
.iter()
|
||||
.map(|s| s.as_str())
|
||||
.collect::<Vec<_>>(),
|
||||
"legacy repos must retain activity ordering (most recently updated first)"
|
||||
);
|
||||
}
|
||||
|
||||
#[sqlx::test]
|
||||
async fn repos_page_pagination_crosses_owner_boundary(pool: PgPool) {
|
||||
let db = db(pool).await;
|
||||
let owner1 = "did:key:z6MkaOwner1";
|
||||
let owner2 = "did:key:z6MkbOwner2";
|
||||
let earlier_owner = "did:web:example.com";
|
||||
// This owner sorts first only after did:key normalization. Its name
|
||||
// sorts past the first cursor, so an unqualified OR name predicate
|
||||
// would incorrectly serve it again on the next page.
|
||||
//
|
||||
// Rows are inserted out of order and not in reverse asserted order.
|
||||
// Assigned IDs do not track name order, and owner2 contains both
|
||||
// "B-repo" and "a-repo" whose byte order (B < a) differs from their
|
||||
// case-folded order (a < b), ensuring lower(d.name) cannot satisfy
|
||||
// the keyset query. Sized to 6 entries so the last page is full-sized
|
||||
// (limit 2), proving hasNextPage distinguishes a full terminal page.
|
||||
db.create_repo(&repo("r5", owner2, "c-repo", true))
|
||||
.await
|
||||
.unwrap();
|
||||
db.create_repo(&repo("r9", earlier_owner, "zz-repo", true))
|
||||
.await
|
||||
.unwrap();
|
||||
db.create_repo(&repo("r3", owner2, "B-repo", true))
|
||||
.await
|
||||
.unwrap();
|
||||
db.create_repo(&repo("r8", owner1, "z-repo", true))
|
||||
.await
|
||||
.unwrap();
|
||||
db.create_repo(&repo("r2", owner1, "b-repo", true))
|
||||
.await
|
||||
.unwrap();
|
||||
db.create_repo(&repo("r1", owner2, "a-repo", true))
|
||||
.await
|
||||
.unwrap();
|
||||
|
||||
let schema = schema(db);
|
||||
let page1_resp = anon(
|
||||
&schema,
|
||||
"{ reposPage(limit: 2) { nodes { name ownerDid } hasNextPage endCursor } }",
|
||||
)
|
||||
.await;
|
||||
assert!(page1_resp.errors.is_empty(), "{:?}", page1_resp.errors);
|
||||
let p1 = page1_resp.data.into_json().unwrap()["reposPage"].clone();
|
||||
assert_eq!(p1["hasNextPage"], true);
|
||||
assert_eq!(
|
||||
p1["nodes"],
|
||||
serde_json::json!([
|
||||
{"name": "zz-repo", "ownerDid": earlier_owner},
|
||||
{"name": "b-repo", "ownerDid": owner1},
|
||||
])
|
||||
);
|
||||
let cursor = p1["endCursor"].as_str().unwrap();
|
||||
|
||||
let page2_query = format!(
|
||||
"{{ reposPage(limit: 2, after: \"{cursor}\") {{ nodes {{ name ownerDid }} hasNextPage endCursor }} }}"
|
||||
);
|
||||
let page2_resp = anon(&schema, &page2_query).await;
|
||||
assert!(page2_resp.errors.is_empty(), "{:?}", page2_resp.errors);
|
||||
let p2 = page2_resp.data.into_json().unwrap()["reposPage"].clone();
|
||||
assert_eq!(p2["hasNextPage"], true);
|
||||
assert_eq!(
|
||||
p2["nodes"],
|
||||
serde_json::json!([
|
||||
{"name": "z-repo", "ownerDid": owner1},
|
||||
{"name": "B-repo", "ownerDid": owner2},
|
||||
])
|
||||
);
|
||||
let cursor = p2["endCursor"].as_str().unwrap();
|
||||
let page3_query = format!(
|
||||
"{{ reposPage(limit: 2, after: \"{cursor}\") {{ nodes {{ name ownerDid }} hasNextPage endCursor }} }}"
|
||||
);
|
||||
let page3_resp = anon(&schema, &page3_query).await;
|
||||
assert!(page3_resp.errors.is_empty(), "{:?}", page3_resp.errors);
|
||||
let p3 = page3_resp.data.into_json().unwrap()["reposPage"].clone();
|
||||
assert_eq!(p3["hasNextPage"], false);
|
||||
assert_eq!(
|
||||
p3["nodes"],
|
||||
serde_json::json!([
|
||||
{"name": "a-repo", "ownerDid": owner2},
|
||||
{"name": "c-repo", "ownerDid": owner2},
|
||||
])
|
||||
);
|
||||
}
|
||||
|
||||
#[sqlx::test]
|
||||
async fn repos_page_at_documented_maximum_distinguishes_terminal_page(pool: PgPool) {
|
||||
let db = db(pool).await;
|
||||
let total = crate::db::MAX_VISIBLE_REPO_PAGE_SIZE;
|
||||
for index in 0..total {
|
||||
let name = format!("repo-{index:03}");
|
||||
db.create_repo(&repo(&name, OWNER, &name, true))
|
||||
.await
|
||||
.unwrap();
|
||||
}
|
||||
let schema = schema(db.clone());
|
||||
let query =
|
||||
format!("{{ reposPage(limit: {total}) {{ nodes {{ name }} hasNextPage endCursor }} }}");
|
||||
let resp200 = anon(&schema, &query).await;
|
||||
assert!(resp200.errors.is_empty(), "{:?}", resp200.errors);
|
||||
let p200 = resp200.data.into_json().unwrap()["reposPage"].clone();
|
||||
assert_eq!(p200["hasNextPage"], false);
|
||||
let nodes200 = p200["nodes"].as_array().unwrap().clone();
|
||||
assert_eq!(nodes200.len(), total);
|
||||
|
||||
// Adding row 201 keeps page 1 content identical while flipping hasNextPage to true.
|
||||
let name201 = format!("repo-{total:03}");
|
||||
db.create_repo(&repo(&name201, OWNER, &name201, true))
|
||||
.await
|
||||
.unwrap();
|
||||
let resp201 = anon(&schema, &query).await;
|
||||
assert!(resp201.errors.is_empty(), "{:?}", resp201.errors);
|
||||
let p201 = resp201.data.into_json().unwrap()["reposPage"].clone();
|
||||
assert_eq!(p201["hasNextPage"], true);
|
||||
assert_eq!(p201["nodes"], p200["nodes"]);
|
||||
assert_eq!(p201["endCursor"], p200["endCursor"]);
|
||||
}
|
||||
|
||||
#[sqlx::test]
|
||||
async fn repos_page_visibility_matches_the_shared_gate(pool: PgPool) {
|
||||
use crate::db::VisibilityMode;
|
||||
let db = db(pool).await;
|
||||
let reader = "did:key:zReader";
|
||||
for (id, public) in [
|
||||
("open", true),
|
||||
("private", false),
|
||||
("root-deny", true),
|
||||
("root-reader", false),
|
||||
("subtree", true),
|
||||
("root-tie", true),
|
||||
("odd-star", true),
|
||||
("malformed-readers", true),
|
||||
("non-array-readers", true),
|
||||
("non-string-reader", true),
|
||||
("quarantined", true),
|
||||
] {
|
||||
db.create_repo(&repo(id, OWNER, id, public)).await.unwrap();
|
||||
}
|
||||
// Canonical and mirror copies must still collapse before pagination.
|
||||
db.create_repo(&repo("z6MkOwner/open", "z6MkOwner", "open", true))
|
||||
.await
|
||||
.unwrap();
|
||||
db.create_repo(&repo(
|
||||
"other-method",
|
||||
"did:web:z6MkOwner",
|
||||
"other-method",
|
||||
false,
|
||||
))
|
||||
.await
|
||||
.unwrap();
|
||||
db.set_repo_quarantine("quarantined", true).await.unwrap();
|
||||
for (id, glob, readers) in [
|
||||
("root-deny", "/", vec![]),
|
||||
("root-reader", "/**", vec![reader.to_owned()]),
|
||||
("subtree", "/secret/**", vec![]),
|
||||
("root-tie", "/", vec![reader.to_owned()]),
|
||||
("root-tie", "/**", vec![]),
|
||||
("odd-star", "/*", vec![]),
|
||||
("malformed-readers", "/", vec![]),
|
||||
("non-array-readers", "/", vec![]),
|
||||
("non-string-reader", "/", vec![]),
|
||||
] {
|
||||
db.set_visibility_rule(id, glob, VisibilityMode::B, &readers, OWNER)
|
||||
.await
|
||||
.unwrap();
|
||||
}
|
||||
// The typed setter cannot create malformed JSON, but existing TEXT rows
|
||||
// can contain it. Such a rule must deny this repo, not abort the page.
|
||||
// All three deny arms of the reader_dids predicate are pinned here:
|
||||
// (a) invalid JSON, (b) valid JSON that is not an array, (c) an array
|
||||
// containing a non-string member. The Rust gate parses reader_dids as
|
||||
// Vec<String> with unwrap_or_default(), so (b) and (c) also fail to
|
||||
// parse and deny; the SQL CASE must agree on every shape.
|
||||
let rows = sqlx::query("UPDATE visibility_rules SET reader_dids = $1 WHERE repo_id = $2")
|
||||
.bind("not JSON")
|
||||
.bind("malformed-readers")
|
||||
.execute(db.pool())
|
||||
.await
|
||||
.unwrap();
|
||||
assert_eq!(rows.rows_affected(), 1);
|
||||
let rows = sqlx::query("UPDATE visibility_rules SET reader_dids = $1 WHERE repo_id = $2")
|
||||
.bind("\"just-a-string\"")
|
||||
.bind("non-array-readers")
|
||||
.execute(db.pool())
|
||||
.await
|
||||
.unwrap();
|
||||
assert_eq!(rows.rows_affected(), 1);
|
||||
// The named reader is listed, but the non-string member poisons the
|
||||
// whole list: both sides must still deny them.
|
||||
let rows = sqlx::query("UPDATE visibility_rules SET reader_dids = $1 WHERE repo_id = $2")
|
||||
.bind("[\"did:key:zReader\", 42]")
|
||||
.bind("non-string-reader")
|
||||
.execute(db.pool())
|
||||
.await
|
||||
.unwrap();
|
||||
assert_eq!(rows.rows_affected(), 1);
|
||||
let all = db.list_all_repos_deduped().await.unwrap();
|
||||
for caller in [
|
||||
None,
|
||||
Some(OWNER),
|
||||
Some("z6MkOwner"),
|
||||
Some(reader),
|
||||
Some("zReader"),
|
||||
Some("did:web:z6MkOwner"),
|
||||
] {
|
||||
let mut expected = Vec::new();
|
||||
for record in &all {
|
||||
let rules = db.list_visibility_rules(&record.id).await.unwrap();
|
||||
if crate::visibility::listable_at_root(
|
||||
&rules,
|
||||
record.is_public,
|
||||
&record.owner_did,
|
||||
caller,
|
||||
) {
|
||||
expected.push(record.id.clone());
|
||||
}
|
||||
}
|
||||
expected.sort();
|
||||
let mut actual = db
|
||||
.list_visible_repos_page(caller, None, usize::MAX)
|
||||
.await
|
||||
.unwrap()
|
||||
.into_iter()
|
||||
.map(|record| record.id)
|
||||
.collect::<Vec<_>>();
|
||||
actual.sort();
|
||||
assert_eq!(actual, expected, "caller {caller:?}");
|
||||
}
|
||||
let schema = schema(db);
|
||||
for caller in [None, Some("did:key:zUnauthorized")] {
|
||||
let query = "{ repos { name } }";
|
||||
let response = match caller {
|
||||
None => anon(&schema, query).await,
|
||||
Some(caller) => authed(&schema, query, caller).await,
|
||||
};
|
||||
assert!(response.errors.is_empty(), "{:?}", response.errors);
|
||||
let mut names: Vec<String> = response.data.into_json().unwrap()["repos"]
|
||||
.as_array()
|
||||
.unwrap()
|
||||
.iter()
|
||||
.map(|repo| repo["name"].as_str().unwrap().to_owned())
|
||||
.collect();
|
||||
names.sort();
|
||||
assert_eq!(names, ["odd-star", "open", "subtree"]);
|
||||
}
|
||||
let query = "{ reposPage(limit: 1) { nodes { name ownerDid } hasNextPage endCursor } }";
|
||||
let response = anon(&schema, query).await;
|
||||
assert!(response.errors.is_empty(), "{:?}", response.errors);
|
||||
let json = response.data.into_json().unwrap();
|
||||
let page = &json["reposPage"];
|
||||
assert_eq!(
|
||||
page["nodes"],
|
||||
serde_json::json!([{"name": "odd-star", "ownerDid": OWNER}])
|
||||
);
|
||||
assert_eq!(page["hasNextPage"], true);
|
||||
let cursor = super::parse_repo_cursor(page["endCursor"].as_str().unwrap()).unwrap();
|
||||
assert_eq!(cursor, (OWNER.to_owned(), "odd-star".to_owned()));
|
||||
assert!(!json.to_string().contains("private"));
|
||||
assert!(!json.to_string().contains("quarantined"));
|
||||
|
||||
// Route-level check with unauthorized authenticated caller:
|
||||
// Excludes private, quarantined, and root-deny repos, matching anonymous behavior.
|
||||
let all_query = "{ reposPage(limit: 50) { nodes { name } hasNextPage } }";
|
||||
let unauth_response = authed(&schema, all_query, "did:key:zUnauthorized").await;
|
||||
assert!(
|
||||
unauth_response.errors.is_empty(),
|
||||
"{:?}",
|
||||
unauth_response.errors
|
||||
);
|
||||
let unauth_json = unauth_response.data.into_json().unwrap();
|
||||
let unauth_names: Vec<&str> = unauth_json["reposPage"]["nodes"]
|
||||
.as_array()
|
||||
.unwrap()
|
||||
.iter()
|
||||
.filter_map(|n| n["name"].as_str())
|
||||
.collect();
|
||||
assert_eq!(unauth_names, vec!["odd-star", "open", "subtree"]);
|
||||
let unauth_str = unauth_json.to_string();
|
||||
assert!(!unauth_str.contains("private"));
|
||||
assert!(!unauth_str.contains("quarantined"));
|
||||
assert!(!unauth_str.contains("root-deny"));
|
||||
assert!(!unauth_str.contains("root-reader"));
|
||||
assert!(!unauth_str.contains("root-tie"));
|
||||
|
||||
// Reader caller gets root-reader and root-tie, but still excludes private, quarantined, root-deny.
|
||||
let reader_response = authed(&schema, all_query, reader).await;
|
||||
assert!(
|
||||
reader_response.errors.is_empty(),
|
||||
"{:?}",
|
||||
reader_response.errors
|
||||
);
|
||||
let reader_json = reader_response.data.into_json().unwrap();
|
||||
let reader_names: Vec<&str> = reader_json["reposPage"]["nodes"]
|
||||
.as_array()
|
||||
.unwrap()
|
||||
.iter()
|
||||
.filter_map(|n| n["name"].as_str())
|
||||
.collect();
|
||||
assert_eq!(
|
||||
reader_names,
|
||||
vec!["odd-star", "open", "root-reader", "subtree"]
|
||||
);
|
||||
let reader_str = reader_json.to_string();
|
||||
assert!(!reader_str.contains("private"));
|
||||
assert!(!reader_str.contains("quarantined"));
|
||||
assert!(!reader_str.contains("root-deny"));
|
||||
assert!(!reader_str.contains("root-tie"));
|
||||
}
|
||||
|
||||
#[sqlx::test]
|
||||
async fn repos_page_rechecks_cursor_authority_and_exact_boundary(pool: PgPool) {
|
||||
let db = db(pool).await;
|
||||
let visible = repo("visible", OWNER, "a-visible", true);
|
||||
db.create_repo(&visible).await.unwrap();
|
||||
db.create_repo(&repo("hidden", OWNER, "z-private", false))
|
||||
.await
|
||||
.unwrap();
|
||||
let schema = schema(db);
|
||||
let first = anon(
|
||||
&schema,
|
||||
"{ reposPage(limit: 1) { nodes { name } hasNextPage endCursor } }",
|
||||
)
|
||||
.await;
|
||||
assert!(first.errors.is_empty());
|
||||
let first = first.data.into_json().unwrap();
|
||||
assert_eq!(first["reposPage"]["hasNextPage"], false);
|
||||
let query = format!(
|
||||
"{{ reposPage(limit: 1, after: \"{}\") {{ nodes {{ name }} hasNextPage endCursor }} }}",
|
||||
super::repo_cursor(&visible)
|
||||
);
|
||||
let owner = authed(&schema, &query, OWNER).await;
|
||||
assert!(owner.errors.is_empty());
|
||||
assert_eq!(
|
||||
owner.data.into_json().unwrap()["reposPage"]["nodes"][0]["name"],
|
||||
"z-private"
|
||||
);
|
||||
let anon = anon(&schema, &query).await;
|
||||
assert!(anon.errors.is_empty());
|
||||
assert_eq!(
|
||||
anon.data.into_json().unwrap()["reposPage"],
|
||||
serde_json::json!({
|
||||
"nodes": [], "hasNextPage": false, "endCursor": null
|
||||
})
|
||||
);
|
||||
let unauth = authed(&schema, &query, "did:key:zUnauthorized").await;
|
||||
assert!(unauth.errors.is_empty());
|
||||
assert_eq!(
|
||||
unauth.data.into_json().unwrap()["reposPage"],
|
||||
serde_json::json!({
|
||||
"nodes": [], "hasNextPage": false, "endCursor": null
|
||||
})
|
||||
);
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn repos_page_rejects_nul_cursors_before_database_access() {
|
||||
let pool = sqlx::postgres::PgPoolOptions::new()
|
||||
.connect_lazy("postgres://localhost/unused")
|
||||
.unwrap();
|
||||
let schema = schema(Arc::new(Db::for_testing(pool)));
|
||||
for position in [("did:key:zOwner\0", "repo"), ("did:key:zOwner", "repo\0")] {
|
||||
let cursor = super::URL_SAFE_NO_PAD.encode(serde_json::to_vec(&position).unwrap());
|
||||
let query = format!("{{ reposPage(after: \"{cursor}\") {{ hasNextPage }} }}");
|
||||
let response =
|
||||
tokio::time::timeout(std::time::Duration::from_secs(1), anon(&schema, &query))
|
||||
.await
|
||||
.expect("invalid cursors must be rejected without accessing the database");
|
||||
assert_eq!(response.errors.len(), 1);
|
||||
assert_eq!(response.errors[0].message, "invalid repository cursor");
|
||||
assert_eq!(response.data, async_graphql::Value::Null);
|
||||
}
|
||||
let position = ("did:key:zOwner", "repo");
|
||||
let cursor = super::URL_SAFE_NO_PAD.encode(serde_json::to_vec(&position).unwrap());
|
||||
assert_eq!(
|
||||
super::parse_repo_cursor(&cursor).unwrap(),
|
||||
(position.0.to_owned(), position.1.to_owned())
|
||||
);
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn repos_page_rejects_invalid_inputs_before_database_access() {
|
||||
let pool = sqlx::postgres::PgPoolOptions::new()
|
||||
.connect_lazy("postgres://localhost/unused")
|
||||
.unwrap();
|
||||
let schema = schema(Arc::new(Db::for_testing(pool)));
|
||||
let over_max = crate::db::MAX_VISIBLE_REPO_PAGE_SIZE + 1;
|
||||
let expected_limit_message = format!(
|
||||
"limit must be between 1 and {}",
|
||||
crate::db::MAX_VISIBLE_REPO_PAGE_SIZE
|
||||
);
|
||||
// Each input pins its own rejection message: the loop must not accept
|
||||
// either message for every query, or a misattributed message (e.g. the
|
||||
// limit arm returning "invalid repository cursor") stays invisible.
|
||||
for (query, expected_message) in [
|
||||
(
|
||||
"{ reposPage(limit: 0) { hasNextPage } }".to_owned(),
|
||||
expected_limit_message.clone(),
|
||||
),
|
||||
(
|
||||
"{ reposPage(limit: -1) { hasNextPage } }".to_owned(),
|
||||
expected_limit_message.clone(),
|
||||
),
|
||||
(
|
||||
format!("{{ reposPage(limit: {over_max}) {{ hasNextPage }} }}"),
|
||||
expected_limit_message.clone(),
|
||||
),
|
||||
(
|
||||
"{ reposPage(after: \"invalid!\") { hasNextPage } }".to_owned(),
|
||||
"invalid repository cursor".to_owned(),
|
||||
),
|
||||
] {
|
||||
let response =
|
||||
tokio::time::timeout(std::time::Duration::from_secs(1), anon(&schema, &query))
|
||||
.await
|
||||
.unwrap();
|
||||
assert_eq!(response.errors.len(), 1);
|
||||
assert_eq!(
|
||||
response.errors[0].message, expected_message,
|
||||
"wrong rejection message for query: {query}"
|
||||
);
|
||||
}
|
||||
// Valid base64 and valid cursor JSON: only the length guard rejects it.
|
||||
let oversized = super::URL_SAFE_NO_PAD
|
||||
.encode(serde_json::to_vec(&("did:key:reader", "a".repeat(3100))).unwrap());
|
||||
assert!(oversized.len() > 4096);
|
||||
assert!(serde_json::from_slice::<(String, String)>(
|
||||
&super::URL_SAFE_NO_PAD.decode(&oversized).unwrap()
|
||||
)
|
||||
.is_ok());
|
||||
assert!(super::parse_repo_cursor(&oversized).is_err());
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn parse_repo_cursor_rejects_wrong_shape_json() {
|
||||
// Valid base64 and valid JSON, but not a (String, String) pair: the
|
||||
// wrong-shape arm must report "invalid repository cursor", exactly,
|
||||
// before any database access.
|
||||
let pool = sqlx::postgres::PgPoolOptions::new()
|
||||
.connect_lazy("postgres://localhost/unused")
|
||||
.unwrap();
|
||||
let schema = schema(Arc::new(Db::for_testing(pool)));
|
||||
for payload in [
|
||||
serde_json::json!(["only-one"]),
|
||||
serde_json::json!(["a", "b", "c"]),
|
||||
serde_json::json!({"owner": "x", "name": "y"}),
|
||||
serde_json::json!(42),
|
||||
serde_json::json!(["a", 1]),
|
||||
] {
|
||||
let cursor = super::URL_SAFE_NO_PAD.encode(serde_json::to_vec(&payload).unwrap());
|
||||
let err = super::parse_repo_cursor(&cursor).unwrap_err();
|
||||
assert_eq!(err.message, "invalid repository cursor");
|
||||
let query = format!("{{ reposPage(after: \"{cursor}\") {{ hasNextPage }} }}");
|
||||
let response =
|
||||
tokio::time::timeout(std::time::Duration::from_secs(1), anon(&schema, &query))
|
||||
.await
|
||||
.expect("wrong-shape cursors must be rejected without accessing the database");
|
||||
assert_eq!(response.errors.len(), 1);
|
||||
assert_eq!(response.errors[0].message, "invalid repository cursor");
|
||||
assert_eq!(response.data, async_graphql::Value::Null);
|
||||
}
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn longest_repo_name_cursor_round_trips() {
|
||||
// #465 4th round: a cursor the server emits must always parse back.
|
||||
// Repo names are bounded at the create/fork/mirror write paths, so the
|
||||
// longest admissible name must produce a cursor under the 4096-byte
|
||||
// parse limit.
|
||||
let name = "a".repeat(crate::db::MAX_REPO_NAME_LEN);
|
||||
let record = repo("long", OWNER, &name, true);
|
||||
let cursor = super::repo_cursor(&record);
|
||||
assert!(
|
||||
cursor.len() <= 4096,
|
||||
"emitted cursor must stay under the parse limit: {}",
|
||||
cursor.len()
|
||||
);
|
||||
assert_eq!(
|
||||
super::parse_repo_cursor(&cursor).unwrap(),
|
||||
(OWNER.to_owned(), name)
|
||||
);
|
||||
}
|
||||
|
||||
/// A negative refUpdates(limit) must be accepted and clamped to zero rows,
|
||||
/// like tasks(limit: -1): the complexity formula's `limit.clamp(0, ...)`
|
||||
/// prices it at the floor and the shared collector returns before any
|
||||
/// database access. Mirrors tasks_negative_limit_clamped.
|
||||
#[tokio::test]
|
||||
async fn ref_updates_negative_limit_clamped() {
|
||||
let pool = sqlx::postgres::PgPoolOptions::new()
|
||||
.connect_lazy("postgres://localhost/unused")
|
||||
.unwrap();
|
||||
let schema = schema(Arc::new(Db::for_testing(pool)));
|
||||
let resp = tokio::time::timeout(
|
||||
std::time::Duration::from_secs(1),
|
||||
anon(&schema, "{ refUpdates(limit: -1) { repo } }"),
|
||||
)
|
||||
.await
|
||||
.expect("negative limit must clamp without accessing the database");
|
||||
assert!(
|
||||
resp.errors.is_empty(),
|
||||
"negative limit must clamp, not fail: {:?}",
|
||||
resp.errors
|
||||
);
|
||||
assert_eq!(count(&resp), 0);
|
||||
}
|
||||
|
||||
/// The mirror write path binds peer-supplied names verbatim, so it must
|
||||
/// enforce the same bound as the local write paths: an overlong peer name
|
||||
/// would otherwise make reposPage emit an unparseable cursor. The
|
||||
/// rejection happens before any database access.
|
||||
#[tokio::test]
|
||||
async fn mirror_repo_rejects_overlong_name() {
|
||||
let pool = sqlx::postgres::PgPoolOptions::new()
|
||||
.connect_lazy("postgres://localhost/unused")
|
||||
.unwrap();
|
||||
let db = Db::for_testing(pool);
|
||||
let name = "b".repeat(crate::db::MAX_REPO_NAME_LEN + 1);
|
||||
let err = db
|
||||
.upsert_mirror_repo("z6MkLong", &name, "/tmp/long", None, false)
|
||||
.await
|
||||
.unwrap_err();
|
||||
assert!(
|
||||
err.to_string().contains("exceeds"),
|
||||
"unexpected error: {err}"
|
||||
);
|
||||
}
|
||||
|
||||
async fn db(pool: PgPool) -> Arc<Db> {
|
||||
let db = Db::for_testing(pool);
|
||||
db.run_migrations().await.unwrap();
|
||||
@@ -475,12 +1211,13 @@ mod tests {
|
||||
assert_eq!(count_tasks(&resp), 0);
|
||||
}
|
||||
|
||||
/// #255: ceiling of the tasks(limit) clamp must be held (schema promises Max 200).
|
||||
/// #255: ceiling of the tasks(limit) clamp must be held (schema promises the
|
||||
/// documented maximum).
|
||||
#[sqlx::test]
|
||||
async fn tasks_limit_ceiling_clamped_to_200(pool: PgPool) {
|
||||
async fn tasks_limit_ceiling_clamped_to_max(pool: PgPool) {
|
||||
let db = db(pool).await;
|
||||
let now = Utc::now().to_rfc3339();
|
||||
for i in 0..201 {
|
||||
for i in 0..crate::db::MAX_VISIBLE_TASK_PAGE_SIZE + 1 {
|
||||
db.create_task(&crate::db::AgentTask {
|
||||
id: format!("task-ceil-{i}"),
|
||||
repo_id: None,
|
||||
@@ -501,7 +1238,49 @@ mod tests {
|
||||
}
|
||||
let schema = schema(db);
|
||||
let resp = anon(&schema, "{ tasks(limit: 5000) { id } }").await;
|
||||
assert_eq!(count_tasks(&resp), 200, "limit above 200 must clamp to 200");
|
||||
assert_eq!(
|
||||
count_tasks(&resp),
|
||||
crate::db::MAX_VISIBLE_TASK_PAGE_SIZE as usize,
|
||||
"limit above the maximum must clamp to MAX_VISIBLE_TASK_PAGE_SIZE"
|
||||
);
|
||||
}
|
||||
|
||||
/// A limit above MAX_VISIBLE_REF_UPDATES must reach the resolver clamped,
|
||||
/// not be rejected: the complexity formula clamps the priced limit (so the
|
||||
/// document passes validation) and the shared collector clamps the rows
|
||||
/// (so at most MAX_VISIBLE_REF_UPDATES come back). Removing the formula
|
||||
/// clamp prices the raw limit and rejects the document; removing the
|
||||
/// collector clamp returns unbounded rows. Mirrors
|
||||
/// tasks_limit_ceiling_clamped_to_max.
|
||||
#[sqlx::test]
|
||||
async fn ref_updates_limit_ceiling_clamped_to_max(pool: PgPool) {
|
||||
use crate::api::events::MAX_VISIBLE_REF_UPDATES;
|
||||
let db = db(pool).await;
|
||||
db.create_repo(&repo("r1", OWNER, "widget", true))
|
||||
.await
|
||||
.unwrap();
|
||||
let total = MAX_VISIBLE_REF_UPDATES as usize + 1;
|
||||
for i in 0..total {
|
||||
let mut row = ref_row(&format!("ceil{i}"), "z6MkOwner/widget");
|
||||
row.timestamp = format!("2026-07-01T10:{:02}:{:02}+00:00", i / 60, i % 60);
|
||||
db.insert_ref_update(&row).await.unwrap();
|
||||
}
|
||||
let schema = schema(db);
|
||||
let query = format!(
|
||||
"{{ refUpdates(limit: {}) {{ repo }} }}",
|
||||
MAX_VISIBLE_REF_UPDATES + 4800
|
||||
);
|
||||
let resp = anon(&schema, &query).await;
|
||||
assert!(
|
||||
resp.errors.is_empty(),
|
||||
"limit above the maximum must clamp, not fail: {:?}",
|
||||
resp.errors
|
||||
);
|
||||
assert_eq!(
|
||||
count(&resp),
|
||||
MAX_VISIBLE_REF_UPDATES as usize,
|
||||
"limit above the maximum must clamp to MAX_VISIBLE_REF_UPDATES"
|
||||
);
|
||||
}
|
||||
|
||||
fn count_tasks(resp: &async_graphql::Response) -> usize {
|
||||
|
||||
@@ -20,6 +20,7 @@ impl SubscriptionRoot {
|
||||
/// `if announce` block, `api/repos.rs`). This is a single-point invariant —
|
||||
/// any new sender to `ref_update_tx` MUST be `announce`-gated, or private-repo
|
||||
/// ref metadata leaks here to unauthenticated subscribers (#112/#114 class).
|
||||
#[graphql(complexity = "50 + child_complexity")]
|
||||
async fn ref_updates(
|
||||
&self,
|
||||
ctx: &Context<'_>,
|
||||
@@ -46,6 +47,7 @@ impl SubscriptionRoot {
|
||||
})
|
||||
}
|
||||
|
||||
#[graphql(complexity = "50 + child_complexity")]
|
||||
async fn task_events(
|
||||
&self,
|
||||
ctx: &Context<'_>,
|
||||
|
||||
@@ -11,6 +11,14 @@ pub struct RepoType {
|
||||
pub created_at: String,
|
||||
}
|
||||
|
||||
#[derive(SimpleObject)]
|
||||
pub struct RepoPageType {
|
||||
pub nodes: Vec<RepoType>,
|
||||
pub has_next_page: bool,
|
||||
/// Position after the last returned visible repository; null for an empty page.
|
||||
pub end_cursor: Option<String>,
|
||||
}
|
||||
|
||||
#[derive(SimpleObject, Clone)]
|
||||
pub struct AgentTaskType {
|
||||
pub id: String,
|
||||
|
||||
@@ -2638,6 +2638,7 @@ mod tests {
|
||||
/// type probe carries its oid on stdin rather than in argv, so an oid appears in
|
||||
/// the log only once an object has already got past its probe, and a healthy
|
||||
/// object costs two invocations to a faulting one's one.
|
||||
#[cfg(unix)]
|
||||
fn objects_attempted(log: &std::path::Path) -> usize {
|
||||
std::fs::read_to_string(log)
|
||||
.unwrap_or_default()
|
||||
|
||||
@@ -912,6 +912,7 @@ mod tests {
|
||||
/// probe carries its oid on stdin rather than in argv, so an oid appears in the log only
|
||||
/// once an object has already got past its probe, and a healthy object costs two
|
||||
/// invocations to a faulting one's one.
|
||||
#[cfg(unix)]
|
||||
fn objects_attempted(log: &std::path::Path) -> usize {
|
||||
std::fs::read_to_string(log)
|
||||
.unwrap_or_default()
|
||||
|
||||
@@ -1330,6 +1330,18 @@ mod tests {
|
||||
.await;
|
||||
}
|
||||
|
||||
/// Use a rooted path without a Windows drive prefix in the remote fixture.
|
||||
/// The destination still resolves on the temp directory's current drive,
|
||||
/// while the remote's relative path contains no illegal colon component.
|
||||
fn absolute_slug_path(path: &Path) -> String {
|
||||
assert!(path.is_absolute());
|
||||
path.components()
|
||||
.filter(|part| !matches!(part, std::path::Component::Prefix(_)))
|
||||
.collect::<std::path::PathBuf>()
|
||||
.to_string_lossy()
|
||||
.replace('\\', "/")
|
||||
}
|
||||
|
||||
#[sqlx::test]
|
||||
async fn process_batch_rejects_slug_escaping_repos_dir(pool: PgPool) {
|
||||
// The verified escape from #272: `PathBuf::join` discards everything
|
||||
@@ -1345,12 +1357,13 @@ mod tests {
|
||||
// fails on but leaves the parent it created, so assert on both.
|
||||
let outside = TempDir::new().unwrap();
|
||||
let escape_dir = outside.path().join("nest");
|
||||
let slug = format!("a/{}/escape", escape_dir.display());
|
||||
let escape_path = absolute_slug_path(&escape_dir);
|
||||
let slug = format!("a/{escape_path}/escape");
|
||||
let escape_target = escape_dir.join("escape.git");
|
||||
|
||||
// Serve the composed URL for real, so a run without the guard genuinely
|
||||
// clones outside the root rather than merely failing at git.
|
||||
let rel = format!("a{}/escape", escape_dir.display());
|
||||
let rel = format!("a{escape_path}/escape");
|
||||
let (_remote, peer_url) = rooted_remote(&[&rel]);
|
||||
|
||||
let did = "did:key:z6MkAttacker";
|
||||
@@ -1470,6 +1483,7 @@ mod tests {
|
||||
// ── canonical containment before the git call (issue #272) ───────────────
|
||||
|
||||
/// Every ref in `repo`, as one string, for a before/after comparison.
|
||||
#[cfg(unix)]
|
||||
fn refs_of(repo: &Path) -> String {
|
||||
let out = Command::new("git")
|
||||
.args(["-C", repo.to_str().unwrap(), "for-each-ref"])
|
||||
@@ -1802,6 +1816,7 @@ mod tests {
|
||||
/// starvation tests is fixed rather than dependent on how fast the loop
|
||||
/// runs. Two rows enqueued in the same microsecond would otherwise order
|
||||
/// arbitrarily.
|
||||
#[cfg(unix)]
|
||||
async fn enqueue_at(db: &Db, pool: &PgPool, repo: &str, did: &str, enqueued_at: &str) {
|
||||
enqueue(db, repo, did).await;
|
||||
sqlx::query("UPDATE sync_queue SET enqueued_at = $1 WHERE repo = $2")
|
||||
@@ -1995,7 +2010,8 @@ mod tests {
|
||||
|
||||
let outside = TempDir::new().unwrap();
|
||||
let escape_dir = outside.path().join("nest");
|
||||
let slug = format!("a/{}/gitlawb-probe", escape_dir.display());
|
||||
let escape_path = absolute_slug_path(&escape_dir);
|
||||
let slug = format!("a/{escape_path}/gitlawb-probe");
|
||||
let escape_target = escape_dir.join("gitlawb-probe.git");
|
||||
|
||||
// Two things this fixture must get right or the test is green for the
|
||||
@@ -2006,7 +2022,7 @@ mod tests {
|
||||
// run without the guard genuinely clones outside the root instead of
|
||||
// just failing at git. Db::upsert_peer cannot seed this row: it gates on
|
||||
// is_public_http_url, which rejects file://.
|
||||
let rel = format!("a{}/gitlawb-probe", escape_dir.display());
|
||||
let rel = format!("a{escape_path}/gitlawb-probe");
|
||||
let (_remote, peer_url) = rooted_remote(&[&rel]);
|
||||
let did = "did:key:z6MkAttacker";
|
||||
seed_local_peer(&pool, did, &peer_url).await;
|
||||
|
||||
@@ -0,0 +1,75 @@
|
||||
//! Native Git fixtures shared by timing tests on Unix and Windows.
|
||||
|
||||
use std::ops::Deref;
|
||||
use std::path::{Path, PathBuf};
|
||||
use std::sync::OnceLock;
|
||||
|
||||
/// The fixture delays or hangs in its own process, so the production watchdog
|
||||
/// can terminate it without depending on a shell or descendant process support.
|
||||
pub(super) enum Behavior<'a> {
|
||||
Delay(u64),
|
||||
Hang,
|
||||
HangOid(&'a str),
|
||||
HangRepo(&'a str),
|
||||
LogTypes(&'a Path),
|
||||
}
|
||||
|
||||
pub(super) struct GitShim {
|
||||
_directory: tempfile::TempDir,
|
||||
executable: PathBuf,
|
||||
}
|
||||
|
||||
impl Deref for GitShim {
|
||||
type Target = Path;
|
||||
|
||||
fn deref(&self) -> &Path {
|
||||
&self.executable
|
||||
}
|
||||
}
|
||||
|
||||
pub(super) fn create(name: &str, behavior: Behavior<'_>) -> GitShim {
|
||||
static COMPILED: OnceLock<tempfile::TempDir> = OnceLock::new();
|
||||
let compiled = COMPILED.get_or_init(|| {
|
||||
let directory = tempfile::tempdir().expect("native Git fixture directory");
|
||||
let source = directory.path().join("git_shim.rs");
|
||||
std::fs::write(&source, include_str!("../tests/fixtures/git_shim.rs"))
|
||||
.expect("write native Git fixture source");
|
||||
let executable = directory
|
||||
.path()
|
||||
.join(format!("git-shim{}", std::env::consts::EXE_SUFFIX));
|
||||
let output =
|
||||
std::process::Command::new(std::env::var_os("RUSTC").unwrap_or_else(|| "rustc".into()))
|
||||
.arg("--edition=2021")
|
||||
.arg("-Dwarnings")
|
||||
.arg(&source)
|
||||
.arg("-o")
|
||||
.arg(executable)
|
||||
.output()
|
||||
.expect("compile native Git fixture with the installed Rust toolchain");
|
||||
assert!(
|
||||
output.status.success(),
|
||||
"{}",
|
||||
String::from_utf8_lossy(&output.stderr)
|
||||
);
|
||||
directory
|
||||
});
|
||||
let directory = tempfile::Builder::new()
|
||||
.prefix(name)
|
||||
.tempdir()
|
||||
.expect("Git fixture instance");
|
||||
let file_name = format!("git-shim{}", std::env::consts::EXE_SUFFIX);
|
||||
let executable = directory.path().join(&file_name);
|
||||
std::fs::copy(compiled.path().join(file_name), &executable).expect("copy native Git fixture");
|
||||
let config = match behavior {
|
||||
Behavior::Delay(milliseconds) => format!("delay\n{milliseconds}"),
|
||||
Behavior::Hang => "hang\n".to_owned(),
|
||||
Behavior::HangOid(oid) => format!("hang-oid\n{oid}"),
|
||||
Behavior::HangRepo(repo) => format!("hang-repo\n{repo}"),
|
||||
Behavior::LogTypes(path) => format!("log-types\n{}", path.display()),
|
||||
};
|
||||
std::fs::write(directory.path().join("config"), config).expect("configure native Git fixture");
|
||||
GitShim {
|
||||
_directory: directory,
|
||||
executable,
|
||||
}
|
||||
}
|
||||
@@ -28,6 +28,9 @@ use gitlawb_core::identity::Keypair;
|
||||
use crate::auth::AuthenticatedDid;
|
||||
use crate::state::AppState;
|
||||
|
||||
#[path = "test_git_shim.rs"]
|
||||
mod git_shim;
|
||||
|
||||
/// Build an [`AppState`] over a real, migrated Postgres pool (from `#[sqlx::test]`).
|
||||
/// Runs the schema migrations first, because the per-test database starts empty.
|
||||
///
|
||||
@@ -559,11 +562,12 @@ mod tests {
|
||||
/// #174 (SC1, load-bearing): a saturated READ pool must NOT shed an
|
||||
/// authenticated push — the write pool is a separate budget. Read pool at zero,
|
||||
/// write pool with capacity: the push proceeds PAST admission (it then errors on
|
||||
/// the placeholder DB, but crucially it is not a 503). Route git-receive-pack
|
||||
/// the closed DB, with db_unavailable rather than overloaded). Route git-receive-pack
|
||||
/// back to the read pool and this goes red — that is the isolation proof.
|
||||
#[tokio::test]
|
||||
async fn git_receive_pack_not_shed_by_exhausted_read_pool() {
|
||||
let mut state = test_state_lazy();
|
||||
state.db.pool().close().await;
|
||||
// Read pool exhausted as if a flood of anonymous clones held every slot.
|
||||
state.git_read_semaphore = Arc::new(tokio::sync::Semaphore::new(0));
|
||||
// Write pool keeps its default capacity from test_state_lazy.
|
||||
@@ -585,10 +589,13 @@ mod tests {
|
||||
.await
|
||||
.unwrap();
|
||||
|
||||
assert_ne!(
|
||||
resp.status(),
|
||||
StatusCode::SERVICE_UNAVAILABLE,
|
||||
"an exhausted READ pool must not shed a push — the write pool is a separate budget (#174)"
|
||||
assert_eq!(resp.status(), StatusCode::SERVICE_UNAVAILABLE);
|
||||
let bytes = axum::body::to_bytes(resp.into_body(), 1024).await.unwrap();
|
||||
let body: serde_json::Value = serde_json::from_slice(&bytes).unwrap();
|
||||
assert_eq!(
|
||||
body["error"],
|
||||
crate::error::DB_UNAVAILABLE_CODE,
|
||||
"the push must clear admission and reach the deliberately closed database"
|
||||
);
|
||||
}
|
||||
|
||||
@@ -1526,6 +1533,451 @@ mod tests {
|
||||
);
|
||||
}
|
||||
|
||||
/// Pre-assigned tasks must not be stealable: a stranger claiming a pending
|
||||
/// task reserved for another agent must fail, and must not receive the
|
||||
/// UCAN. The reserved assignee still claims successfully.
|
||||
#[sqlx::test]
|
||||
async fn claim_task_honors_preassigned_assignee(pool: PgPool) {
|
||||
let delegator = "did:key:zCLAIMDELEGATORAAAAAAAAAAAAAAAAAAAAAAAAA";
|
||||
let reserved = "did:key:zCLAIMRESERVEDBBBBBBBBBBBBBBBBBBBBBBBBBBB";
|
||||
let thief = "did:key:zCLAIMTHIEFCCCCCCCCCCCCCCCCCCCCCCCCCCCCC";
|
||||
let state = test_state(pool).await;
|
||||
let mut task = seed_task("task-reserved", delegator);
|
||||
task.assignee_did = Some(reserved.to_string());
|
||||
task.ucan_token = Some("ucan-secret-for-reserved-only".into());
|
||||
state.db.create_task(&task).await.expect("seed");
|
||||
|
||||
let router = || {
|
||||
Router::new()
|
||||
.route(
|
||||
"/api/v1/tasks/{id}/claim",
|
||||
axum::routing::post(crate::api::tasks::claim_task),
|
||||
)
|
||||
.with_state(state.clone())
|
||||
};
|
||||
let uri = "/api/v1/tasks/task-reserved/claim";
|
||||
|
||||
// Thief signs as themselves and asks to claim — must fail, UCAN stays put.
|
||||
let resp = router()
|
||||
.oneshot(signed_request_as(
|
||||
thief,
|
||||
Method::POST,
|
||||
uri,
|
||||
Body::from(format!(r#"{{"assignee_did":"{thief}"}}"#)),
|
||||
))
|
||||
.await
|
||||
.unwrap();
|
||||
assert_eq!(
|
||||
resp.status(),
|
||||
StatusCode::FORBIDDEN,
|
||||
"stranger must not steal a pre-assigned task, got {}",
|
||||
resp.status()
|
||||
);
|
||||
let body = axum::body::to_bytes(resp.into_body(), usize::MAX)
|
||||
.await
|
||||
.unwrap();
|
||||
let text = String::from_utf8_lossy(&body);
|
||||
assert!(
|
||||
!text.contains("ucan-secret-for-reserved-only"),
|
||||
"UCAN must not leak on a failed steal: {text}"
|
||||
);
|
||||
let still = state.db.get_task("task-reserved").await.unwrap().unwrap();
|
||||
assert_eq!(still.status, "pending");
|
||||
assert_eq!(still.assignee_did.as_deref(), Some(reserved));
|
||||
|
||||
// Reserved assignee claims successfully and receives the UCAN.
|
||||
let resp = router()
|
||||
.oneshot(signed_request_as(
|
||||
reserved,
|
||||
Method::POST,
|
||||
uri,
|
||||
Body::from(format!(r#"{{"assignee_did":"{reserved}"}}"#)),
|
||||
))
|
||||
.await
|
||||
.unwrap();
|
||||
assert!(
|
||||
resp.status().is_success(),
|
||||
"reserved assignee must claim, got {}",
|
||||
resp.status()
|
||||
);
|
||||
let body = axum::body::to_bytes(resp.into_body(), usize::MAX)
|
||||
.await
|
||||
.unwrap();
|
||||
let text = String::from_utf8_lossy(&body);
|
||||
assert!(
|
||||
text.contains("ucan-secret-for-reserved-only"),
|
||||
"reserved assignee must receive UCAN: {text}"
|
||||
);
|
||||
assert!(text.contains("\"status\":\"claimed\"") || text.contains("claimed"));
|
||||
}
|
||||
|
||||
/// Open (unassigned) pending tasks remain first-claimer-wins after the
|
||||
/// pre-assignment gate.
|
||||
#[sqlx::test]
|
||||
async fn claim_task_open_still_first_claimer_wins(pool: PgPool) {
|
||||
let delegator = "did:key:zOPENDELEGATORAAAAAAAAAAAAAAAAAAAAAAAAAA";
|
||||
let claimer = "did:key:zOPENCLAIMERBBBBBBBBBBBBBBBBBBBBBBBBBBBB";
|
||||
let state = test_state(pool).await;
|
||||
state
|
||||
.db
|
||||
.create_task(&seed_task("task-open", delegator))
|
||||
.await
|
||||
.expect("seed");
|
||||
|
||||
let router = Router::new()
|
||||
.route(
|
||||
"/api/v1/tasks/{id}/claim",
|
||||
axum::routing::post(crate::api::tasks::claim_task),
|
||||
)
|
||||
.with_state(state.clone());
|
||||
let resp = router
|
||||
.oneshot(signed_request_as(
|
||||
claimer,
|
||||
Method::POST,
|
||||
"/api/v1/tasks/task-open/claim",
|
||||
Body::from(format!(r#"{{"assignee_did":"{claimer}"}}"#)),
|
||||
))
|
||||
.await
|
||||
.unwrap();
|
||||
assert!(
|
||||
resp.status().is_success(),
|
||||
"open task must still be claimable, got {}",
|
||||
resp.status()
|
||||
);
|
||||
let got = state.db.get_task("task-open").await.unwrap().unwrap();
|
||||
assert_eq!(got.status, "claimed");
|
||||
assert_eq!(got.assignee_did.as_deref(), Some(claimer));
|
||||
}
|
||||
|
||||
/// ASCII-blank assignees (`ASSIGNEE_BLANK`: space, tab, LF, CR) must be open
|
||||
/// at the claim SQL blank branch. Seeds via raw INSERT so create_task
|
||||
/// normalization is not in the path.
|
||||
#[sqlx::test]
|
||||
async fn claim_task_ascii_blank_reservations_are_open(pool: PgPool) {
|
||||
let delegator = "did:key:zBLANKDELEGATORAAAAAAAAAAAAAAAAAAAAAAAAA";
|
||||
let claimer = "did:key:zBLANKCLAIMERBBBBBBBBBBBBBBBBBBBBBBBBBBBB";
|
||||
let state = test_state(pool.clone()).await;
|
||||
let now = chrono::Utc::now().to_rfc3339();
|
||||
for (id, blank) in [
|
||||
("task-blank-empty", ""),
|
||||
("task-blank-tab", "\t"),
|
||||
("task-blank-space", " "),
|
||||
("task-blank-lf", "\n"),
|
||||
("task-blank-cr", "\r"),
|
||||
] {
|
||||
sqlx::query(
|
||||
"INSERT INTO agent_tasks (id, repo_id, kind, status, delegator_did, assignee_did, capability, ucan_token, payload, result, created_at, updated_at, deadline)
|
||||
VALUES ($1,NULL,'build','pending',$2,$3,'repo:write',NULL,NULL,NULL,$4,$4,NULL)",
|
||||
)
|
||||
.bind(id)
|
||||
.bind(delegator)
|
||||
.bind(blank)
|
||||
.bind(&now)
|
||||
.execute(&pool)
|
||||
.await
|
||||
.unwrap_or_else(|e| panic!("seed {id}: {e}"));
|
||||
|
||||
let claimed = state
|
||||
.db
|
||||
.claim_task(id, claimer)
|
||||
.await
|
||||
.unwrap_or_else(|e| panic!("{id} must be open: {e}"));
|
||||
assert_eq!(claimed.status, "claimed", "{id}");
|
||||
assert_eq!(claimed.assignee_did.as_deref(), Some(claimer), "{id}");
|
||||
}
|
||||
}
|
||||
|
||||
/// create_task must null whitespace-only assignees and return that shape
|
||||
/// (fail-on-remove for the blank filter).
|
||||
#[sqlx::test]
|
||||
async fn create_task_normalizes_whitespace_assignee(pool: PgPool) {
|
||||
let delegator = "did:key:zCREATENORMDELEGAAAAAAAAAAAAAAAAAAAAAAAA";
|
||||
let state = test_state(pool).await;
|
||||
let mut task = seed_task("task-create-norm", delegator);
|
||||
task.assignee_did = Some(" \t\n ".into());
|
||||
let stored = state.db.create_task(&task).await.expect("create");
|
||||
assert!(
|
||||
stored.assignee_did.is_none(),
|
||||
"create_task must return normalized NULL assignee, got {:?}",
|
||||
stored.assignee_did
|
||||
);
|
||||
let got = state
|
||||
.db
|
||||
.get_task("task-create-norm")
|
||||
.await
|
||||
.unwrap()
|
||||
.unwrap();
|
||||
assert!(got.assignee_did.is_none(), "row must store NULL assignee");
|
||||
}
|
||||
|
||||
/// Claiming a reserved task must keep the stored DID form so exact-match
|
||||
/// list filters still find it. Also covers bare→full claim + list by bare
|
||||
/// (claimer full DID must not be required for list equality).
|
||||
#[sqlx::test]
|
||||
async fn claim_task_keeps_stored_assignee_did_form(pool: PgPool) {
|
||||
let delegator = "did:key:zFORMDELEGATORAAAAAAAAAAAAAAAAAAAAAAAAAA";
|
||||
let bare = "zFORMRESERVEDBBBBBBBBBBBBBBBBBBBBBBBBBBB";
|
||||
let full = format!("did:key:{bare}");
|
||||
let state = test_state(pool).await;
|
||||
let mut task = seed_task("task-form", delegator);
|
||||
task.assignee_did = Some(bare.to_string());
|
||||
state.db.create_task(&task).await.expect("seed");
|
||||
|
||||
let claimed = state
|
||||
.db
|
||||
.claim_task("task-form", &full)
|
||||
.await
|
||||
.expect("claim with full DID");
|
||||
assert_eq!(
|
||||
claimed.assignee_did.as_deref(),
|
||||
Some(bare),
|
||||
"reserved claim must keep the stored bare-key form"
|
||||
);
|
||||
let listed_bare = state
|
||||
.db
|
||||
.list_tasks(Some("claimed"), Some(bare), 10)
|
||||
.await
|
||||
.unwrap();
|
||||
assert!(
|
||||
listed_bare.iter().any(|t| t.id == "task-form"),
|
||||
"delegator filtering by bare key must still find the task"
|
||||
);
|
||||
let listed_full = state
|
||||
.db
|
||||
.list_tasks(Some("claimed"), Some(&full), 10)
|
||||
.await
|
||||
.unwrap();
|
||||
assert!(
|
||||
!listed_full.iter().any(|t| t.id == "task-form"),
|
||||
"exact list by claimer's full DID must miss the bare stored form"
|
||||
);
|
||||
}
|
||||
|
||||
/// Padded non-blank reservation must survive claim unchanged (exact form).
|
||||
#[sqlx::test]
|
||||
async fn claim_task_keeps_padded_reservation_exact(pool: PgPool) {
|
||||
let delegator = "did:key:zPADDELEGATORAAAAAAAAAAAAAAAAAAAAAAAAAAA";
|
||||
let key = "zPADRESERVEDBBBBBBBBBBBBBBBBBBBBBBBBBBBB";
|
||||
let padded = format!(" {key}\t");
|
||||
let full = format!("did:key:{key}");
|
||||
let state = test_state(pool.clone()).await;
|
||||
let now = chrono::Utc::now().to_rfc3339();
|
||||
sqlx::query(
|
||||
"INSERT INTO agent_tasks (id, repo_id, kind, status, delegator_did, assignee_did, capability, ucan_token, payload, result, created_at, updated_at, deadline)
|
||||
VALUES ($1,NULL,'build','pending',$2,$3,'repo:write',NULL,NULL,NULL,$4,$4,NULL)",
|
||||
)
|
||||
.bind("task-padded")
|
||||
.bind(delegator)
|
||||
.bind(&padded)
|
||||
.bind(&now)
|
||||
.execute(&pool)
|
||||
.await
|
||||
.expect("seed padded");
|
||||
|
||||
let claimed = state
|
||||
.db
|
||||
.claim_task("task-padded", &full)
|
||||
.await
|
||||
.expect("claim padded reservation");
|
||||
assert_eq!(
|
||||
claimed.assignee_did.as_deref(),
|
||||
Some(padded.as_str()),
|
||||
"claim must not BTRIM a non-blank reservation"
|
||||
);
|
||||
let listed = state
|
||||
.db
|
||||
.list_tasks(Some("claimed"), Some(&padded), 10)
|
||||
.await
|
||||
.unwrap();
|
||||
assert!(
|
||||
listed.iter().any(|t| t.id == "task-padded"),
|
||||
"exact list by original padded form must still find the task"
|
||||
);
|
||||
|
||||
let finished = state
|
||||
.db
|
||||
.finish_task("task-padded", "completed", None, &full)
|
||||
.await
|
||||
.expect("padded assignee must finish after trim match");
|
||||
assert_eq!(finished.status, "completed");
|
||||
}
|
||||
|
||||
/// Direct coverage for the DB-layer finish_task assignee Rust gate (handlers
|
||||
/// 403 before calling in, so HTTP tests alone leave this unproven).
|
||||
#[sqlx::test]
|
||||
async fn finish_task_rejects_non_assignee_at_db(pool: PgPool) {
|
||||
let delegator = "did:key:zFINISHDELEGATORAAAAAAAAAAAAAAAAAAAAAAAA";
|
||||
let assignee = "did:key:zFINISHASSIGNEEBBBBBBBBBBBBBBBBBBBBBBBBB";
|
||||
let stranger = "did:key:zFINISHSTRANGERCCCCCCCCCCCCCCCCCCCCCCCCC";
|
||||
let state = test_state(pool).await;
|
||||
state
|
||||
.db
|
||||
.create_task(&seed_task("task-finish-gate", delegator))
|
||||
.await
|
||||
.expect("seed");
|
||||
state
|
||||
.db
|
||||
.claim_task("task-finish-gate", assignee)
|
||||
.await
|
||||
.expect("claim");
|
||||
|
||||
let err = state
|
||||
.db
|
||||
.finish_task("task-finish-gate", "completed", None, stranger)
|
||||
.await
|
||||
.expect_err("stranger must not finish");
|
||||
assert!(
|
||||
err.to_string().contains("assignee") || err.to_string().contains("finishable"),
|
||||
"expected assignee denial, got {err}"
|
||||
);
|
||||
let still = state
|
||||
.db
|
||||
.get_task("task-finish-gate")
|
||||
.await
|
||||
.unwrap()
|
||||
.unwrap();
|
||||
assert_eq!(
|
||||
still.status, "claimed",
|
||||
"row must stay claimed after denial"
|
||||
);
|
||||
|
||||
let done = state
|
||||
.db
|
||||
.finish_task("task-finish-gate", "completed", None, assignee)
|
||||
.await
|
||||
.expect("assignee finishes");
|
||||
assert_eq!(done.status, "completed");
|
||||
}
|
||||
|
||||
/// Fail-on-remove for `finish_task`'s `AND assignee_did=$5`: a concurrent writer
|
||||
/// that changes the stored assignee between the production read and UPDATE must
|
||||
/// leave the task claimed (production `Db::finish_task` path).
|
||||
#[sqlx::test]
|
||||
async fn finish_task_sql_assignee_predicate_is_load_bearing(pool: PgPool) {
|
||||
let delegator = "did:key:zFINISHSQLDELEGAAAAAAAAAAAAAAAAAAAAAAAAA";
|
||||
let assignee = "did:key:zFINISHSQLASSIGNBBBBBBBBBBBBBBBBBBBBBBBB";
|
||||
let other = "did:key:zFINISHSQLOTHERCCCCCCCCCCCCCCCCCCCCCCCCC";
|
||||
let state = test_state(pool.clone()).await;
|
||||
let id = "task-finish-sql";
|
||||
state
|
||||
.db
|
||||
.create_task(&seed_task(id, delegator))
|
||||
.await
|
||||
.expect("seed");
|
||||
state.db.claim_task(id, assignee).await.expect("claim");
|
||||
|
||||
let pool_bg = pool.clone();
|
||||
let id_bg = id.to_string();
|
||||
let other_bg = other.to_string();
|
||||
let (locked_tx, locked_rx) = tokio::sync::oneshot::channel();
|
||||
let hog = tokio::spawn(async move {
|
||||
let mut tx = pool_bg.begin().await.expect("begin");
|
||||
sqlx::query("SELECT assignee_did FROM agent_tasks WHERE id = $1 FOR UPDATE")
|
||||
.bind(&id_bg)
|
||||
.fetch_one(&mut *tx)
|
||||
.await
|
||||
.expect("lock row");
|
||||
locked_tx.send(()).ok();
|
||||
tokio::time::sleep(std::time::Duration::from_millis(50)).await;
|
||||
sqlx::query(
|
||||
"UPDATE agent_tasks SET assignee_did = $2 WHERE id = $1 AND status = 'claimed'",
|
||||
)
|
||||
.bind(&id_bg)
|
||||
.bind(&other_bg)
|
||||
.execute(&mut *tx)
|
||||
.await
|
||||
.expect("race assignee");
|
||||
tx.commit().await.expect("commit");
|
||||
});
|
||||
locked_rx.await.expect("row lock held before finish");
|
||||
|
||||
let err = state
|
||||
.db
|
||||
.finish_task(id, "completed", None, assignee)
|
||||
.await
|
||||
.expect_err("assignee slot race must fail production finish_task");
|
||||
hog.await.expect("hog task");
|
||||
|
||||
assert!(
|
||||
err.to_string().contains("not in claimed state"),
|
||||
"expected finish denial, got {err}"
|
||||
);
|
||||
let still = state.db.get_task(id).await.unwrap().unwrap();
|
||||
assert_eq!(still.status, "claimed");
|
||||
assert_eq!(still.assignee_did.as_deref(), Some(other));
|
||||
}
|
||||
|
||||
/// Fail-on-remove for the claim UPDATE assignee-slot re-check: a concurrent
|
||||
/// writer that changes `assignee_did` after the pre-read must block claim.
|
||||
#[sqlx::test]
|
||||
async fn claim_task_update_assignee_slot_recheck_is_load_bearing(pool: PgPool) {
|
||||
let delegator = "did:key:zCLAIMSLOTDELEGAAAAAAAAAAAAAAAAAAAAAAAAA";
|
||||
let reserved = "did:key:zCLAIMSLOTASSIGNEEBBBBBBBBBBBBBBBBBBBBBBBBB";
|
||||
let other = "did:key:zCLAIMSLOTOTHERCCCCCCCCCCCCCCCCCCCCCCCCC";
|
||||
let state = test_state(pool.clone()).await;
|
||||
let id = "task-claim-slot";
|
||||
let now = chrono::Utc::now().to_rfc3339();
|
||||
sqlx::query(
|
||||
"INSERT INTO agent_tasks
|
||||
(id, repo_id, kind, status, delegator_did, assignee_did, capability,
|
||||
ucan_token, payload, result, created_at, updated_at, deadline)
|
||||
VALUES ($1, NULL, 'build', 'pending', $2, $3, 'repo:write',
|
||||
NULL, NULL, NULL, $4, $4, NULL)",
|
||||
)
|
||||
.bind(id)
|
||||
.bind(delegator)
|
||||
.bind(reserved)
|
||||
.bind(&now)
|
||||
.execute(&pool)
|
||||
.await
|
||||
.expect("seed reserved");
|
||||
|
||||
let pool_bg = pool.clone();
|
||||
let id_bg = id.to_string();
|
||||
let other_bg = other.to_string();
|
||||
let (locked_tx, locked_rx) = tokio::sync::oneshot::channel();
|
||||
let hog = tokio::spawn(async move {
|
||||
let mut tx = pool_bg.begin().await.expect("begin");
|
||||
sqlx::query("SELECT assignee_did FROM agent_tasks WHERE id = $1 FOR UPDATE")
|
||||
.bind(&id_bg)
|
||||
.fetch_one(&mut *tx)
|
||||
.await
|
||||
.expect("lock row");
|
||||
locked_tx.send(()).ok();
|
||||
tokio::time::sleep(std::time::Duration::from_millis(50)).await;
|
||||
sqlx::query(
|
||||
"UPDATE agent_tasks SET assignee_did = $2 WHERE id = $1 AND status = 'pending'",
|
||||
)
|
||||
.bind(&id_bg)
|
||||
.bind(&other_bg)
|
||||
.execute(&mut *tx)
|
||||
.await
|
||||
.expect("race assignee");
|
||||
tx.commit().await.expect("commit");
|
||||
});
|
||||
locked_rx.await.expect("row lock held before claim");
|
||||
|
||||
let err = state
|
||||
.db
|
||||
.claim_task(id, reserved)
|
||||
.await
|
||||
.expect_err("assignee slot race must fail production claim_task");
|
||||
hog.await.expect("hog task");
|
||||
|
||||
assert!(
|
||||
err.to_string().contains("not found or already claimed"),
|
||||
"expected SQL re-check denial, got {err}"
|
||||
);
|
||||
assert!(
|
||||
err.downcast_ref::<crate::db::TaskReservedForOtherAssignee>()
|
||||
.is_none(),
|
||||
"must prove the UPDATE predicate, not the Rust pre-check: {err}"
|
||||
);
|
||||
let still = state.db.get_task(id).await.unwrap().unwrap();
|
||||
assert_eq!(still.status, "pending");
|
||||
assert_eq!(still.assignee_did.as_deref(), Some(other));
|
||||
}
|
||||
|
||||
/// Adversarial-review GATE-2 (create_pr): opening a PR requires read access.
|
||||
/// A non-reader is denied on a private repo before any PR is created; the
|
||||
/// owner is allowed.
|
||||
@@ -4693,6 +5145,7 @@ mod tests {
|
||||
node_did: owner.to_string(),
|
||||
signature: "sig".to_string(),
|
||||
issued_at: Utc::now().to_rfc3339(),
|
||||
version: 1,
|
||||
})
|
||||
.await
|
||||
.expect("seed private cert");
|
||||
@@ -10749,14 +11202,10 @@ mod tests {
|
||||
seed_legacy_pin(&pool, &bare, &fx.public_oid, Some(&repo.id)).await;
|
||||
|
||||
// A git that takes 300ms per invocation (the read makes two: type, then content).
|
||||
let slow_git = std::env::temp_dir().join(format!("gl-slow-git-{short}"));
|
||||
std::fs::write(&slow_git, "#!/bin/sh\nsleep 0.3\nexec git \"$@\"\n").expect("write shim");
|
||||
#[cfg(unix)]
|
||||
{
|
||||
use std::os::unix::fs::PermissionsExt;
|
||||
std::fs::set_permissions(&slow_git, std::fs::Permissions::from_mode(0o755))
|
||||
.expect("chmod shim");
|
||||
}
|
||||
let slow_git = git_shim::create(
|
||||
&format!("gl-slow-git-{short}"),
|
||||
git_shim::Behavior::Delay(300),
|
||||
);
|
||||
|
||||
let ticks = std::sync::Arc::new(AtomicUsize::new(0));
|
||||
let ticker = {
|
||||
@@ -11703,19 +12152,6 @@ mod tests {
|
||||
);
|
||||
}
|
||||
|
||||
/// Write an executable `git` stand-in and return its path.
|
||||
fn write_git_shim(name: &str, script: &str) -> std::path::PathBuf {
|
||||
let path = std::env::temp_dir().join(name);
|
||||
std::fs::write(&path, script).expect("write the git shim");
|
||||
#[cfg(unix)]
|
||||
{
|
||||
use std::os::unix::fs::PermissionsExt;
|
||||
std::fs::set_permissions(&path, std::fs::Permissions::from_mode(0o755))
|
||||
.expect("chmod the git shim");
|
||||
}
|
||||
path
|
||||
}
|
||||
|
||||
/// F6 scenario 1 (#173 round 13): one hung candidate must not starve the rows behind
|
||||
/// it in the same pass. `DiscoveryCtx` is loaded once per pass, so before the per-row
|
||||
/// slice every source-less row in a pass shared ONE deadline: the first row's wedged
|
||||
@@ -11755,23 +12191,9 @@ mod tests {
|
||||
|
||||
// The type stage feeds the oid on STDIN (`cat-file --batch-check`) and the
|
||||
// content stage puts it in argv, so the stand-in has to look in both places.
|
||||
let git_bin = write_git_shim(
|
||||
let git_bin = git_shim::create(
|
||||
&format!("gl-hung-git-{short}"),
|
||||
&format!(
|
||||
"#!/bin/sh\n\
|
||||
if [ \"$2\" = \"--batch-check\" ]; then\n\
|
||||
\x20 oid=$(cat)\n\
|
||||
\x20 case \"$oid\" in\n\
|
||||
\x20 {hung_oid}) sleep 30; exit 1 ;;\n\
|
||||
\x20 esac\n\
|
||||
\x20 printf '%s\\n' \"$oid\" | git \"$@\"\n\
|
||||
\x20 exit $?\n\
|
||||
fi\n\
|
||||
case \"$*\" in\n\
|
||||
\x20 *{hung_oid}*) sleep 30; exit 1 ;;\n\
|
||||
esac\n\
|
||||
exec git \"$@\"\n"
|
||||
),
|
||||
git_shim::Behavior::HangOid(&hung_oid),
|
||||
);
|
||||
|
||||
let stats = tokio::time::timeout(
|
||||
@@ -11856,10 +12278,7 @@ mod tests {
|
||||
|
||||
// Wedges on every invocation, so no row can ever be repaired and the only
|
||||
// question left is what each one COSTS.
|
||||
let git_bin = write_git_shim(
|
||||
&format!("gl-spent-git-{short}"),
|
||||
"#!/bin/sh\nsleep 30\nexit 1\n",
|
||||
);
|
||||
let git_bin = git_shim::create(&format!("gl-spent-git-{short}"), git_shim::Behavior::Hang);
|
||||
|
||||
let stats = tokio::time::timeout(
|
||||
std::time::Duration::from_secs(60),
|
||||
@@ -12463,10 +12882,7 @@ mod tests {
|
||||
seed_legacy_pin(&pool, &src, oid, None).await;
|
||||
}
|
||||
|
||||
let git_bin = write_git_shim(
|
||||
&format!("gl-starve-git-{short}"),
|
||||
"#!/bin/sh\nsleep 30\nexit 1\n",
|
||||
);
|
||||
let git_bin = git_shim::create(&format!("gl-starve-git-{short}"), git_shim::Behavior::Hang);
|
||||
|
||||
tokio::time::timeout(
|
||||
std::time::Duration::from_secs(120),
|
||||
@@ -12534,9 +12950,9 @@ mod tests {
|
||||
let (raw_cid, provider_cid) = seed_legacy_pin(&pool, &src, &fx.public_oid, None).await;
|
||||
|
||||
// Wedges only inside the position-nine repo, which the sweep enters by cwd.
|
||||
let git_bin = write_git_shim(
|
||||
let git_bin = git_shim::create(
|
||||
&format!("gl-mid-git-{short}"),
|
||||
"#!/bin/sh\ncase \"$(pwd)\" in\n */midcand9.git) sleep 30; exit 1 ;;\nesac\nexec git \"$@\"\n",
|
||||
git_shim::Behavior::HangRepo("midcand9.git"),
|
||||
);
|
||||
|
||||
let first = tokio::time::timeout(
|
||||
@@ -12698,19 +13114,9 @@ mod tests {
|
||||
|
||||
let log = std::env::temp_dir().join(format!("gl-ali-log-{short}"));
|
||||
let _ = std::fs::remove_file(&log);
|
||||
let git_bin = write_git_shim(
|
||||
let git_bin = git_shim::create(
|
||||
&format!("gl-ali-git-{short}"),
|
||||
&format!(
|
||||
"#!/bin/sh\n\
|
||||
if [ \"$2\" = \"--batch-check\" ]; then\n\
|
||||
\x20 oid=$(cat)\n\
|
||||
\x20 printf '%s %s\\n' \"$oid\" \"$(basename $(pwd))\" >> {log}\n\
|
||||
\x20 printf '%s\\n' \"$oid\" | git \"$@\"\n\
|
||||
\x20 exit $?\n\
|
||||
fi\n\
|
||||
exec git \"$@\"\n",
|
||||
log = log.display()
|
||||
),
|
||||
git_shim::Behavior::LogTypes(&log),
|
||||
);
|
||||
|
||||
let mut traversal = crate::ipfs_pin::DiscoveryTraversalState::default();
|
||||
@@ -17252,6 +17658,7 @@ mod tests {
|
||||
node_did: "did:key:zNode".into(),
|
||||
signature: "sig".into(),
|
||||
issued_at: "2026-01-01T00:00:00Z".into(),
|
||||
version: 1,
|
||||
};
|
||||
state.db.insert_ref_certificate(&cert).await.unwrap();
|
||||
|
||||
@@ -17287,6 +17694,7 @@ mod tests {
|
||||
node_did: "did:key:zNode".into(),
|
||||
signature: "sig".into(),
|
||||
issued_at: "2026-01-01T00:00:00Z".into(),
|
||||
version: 1,
|
||||
};
|
||||
state.db.insert_ref_certificate(&cert).await.unwrap();
|
||||
|
||||
@@ -18026,6 +18434,7 @@ mod tests {
|
||||
node_did: "did:key:zNode".into(),
|
||||
signature: "sig".into(),
|
||||
issued_at: "2026-01-01T00:00:00Z".into(),
|
||||
version: 1,
|
||||
};
|
||||
state.db.insert_ref_certificate(&cert).await.unwrap();
|
||||
|
||||
@@ -19700,6 +20109,7 @@ mod tests {
|
||||
node_did: "did:key:zNODE".into(),
|
||||
signature: "sig".into(),
|
||||
issued_at: issued_at.to_string(),
|
||||
version: 1,
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
+59
@@ -0,0 +1,59 @@
|
||||
use std::io::{Read, Write};
|
||||
use std::process::{Command, Stdio};
|
||||
use std::time::Duration;
|
||||
|
||||
fn main() -> std::io::Result<()> {
|
||||
let executable = std::env::current_exe()?;
|
||||
let config = std::fs::read_to_string(executable.parent().unwrap().join("config"))?;
|
||||
let (mode, parameter) = config.split_once('\n').unwrap_or((&config, ""));
|
||||
let args: Vec<_> = std::env::args_os().skip(1).collect();
|
||||
if mode == "delay" {
|
||||
std::thread::sleep(Duration::from_millis(parameter.parse().unwrap()));
|
||||
}
|
||||
let batch = args.get(1).is_some_and(|arg| arg == "--batch-check");
|
||||
let input = if batch {
|
||||
let mut bytes = Vec::new();
|
||||
std::io::stdin().read_to_end(&mut bytes)?;
|
||||
Some(bytes)
|
||||
} else {
|
||||
None
|
||||
};
|
||||
let cwd = std::env::current_dir()?;
|
||||
let hang = mode == "hang"
|
||||
|| (mode == "hang-repo" && cwd.file_name().is_some_and(|name| name == parameter))
|
||||
|| (mode == "hang-oid"
|
||||
&& (args.iter().any(|arg| arg == parameter)
|
||||
|| input
|
||||
.as_ref()
|
||||
.is_some_and(|bytes| String::from_utf8_lossy(bytes).trim() == parameter)));
|
||||
if hang {
|
||||
std::thread::sleep(Duration::from_secs(30));
|
||||
std::process::exit(1);
|
||||
}
|
||||
if mode == "log-types" && batch {
|
||||
let mut log = std::fs::OpenOptions::new()
|
||||
.create(true)
|
||||
.append(true)
|
||||
.open(parameter)?;
|
||||
writeln!(
|
||||
log,
|
||||
"{} {}",
|
||||
String::from_utf8_lossy(input.as_ref().unwrap()).trim(),
|
||||
cwd.file_name().unwrap().to_string_lossy()
|
||||
)?;
|
||||
}
|
||||
let mut child = Command::new("git")
|
||||
.args(&args)
|
||||
.stdin(if input.is_some() {
|
||||
Stdio::piped()
|
||||
} else {
|
||||
Stdio::inherit()
|
||||
})
|
||||
.stdout(Stdio::inherit())
|
||||
.stderr(Stdio::inherit())
|
||||
.spawn()?;
|
||||
if let Some(bytes) = input {
|
||||
child.stdin.take().unwrap().write_all(&bytes)?;
|
||||
}
|
||||
std::process::exit(child.wait()?.code().unwrap_or(1));
|
||||
}
|
||||
+541
-21
@@ -4,6 +4,7 @@
|
||||
|
||||
use anyhow::{Context, Result};
|
||||
use clap::{Args, Subcommand};
|
||||
use serde_json::Value;
|
||||
use std::path::PathBuf;
|
||||
|
||||
use crate::http::NodeClient;
|
||||
@@ -34,7 +35,12 @@ pub enum CertCmd {
|
||||
#[arg(long)]
|
||||
dir: Option<PathBuf>,
|
||||
},
|
||||
/// Show a specific ref certificate and verify its signature
|
||||
/// Show a specific ref certificate and verify its signature.
|
||||
///
|
||||
/// `--verify` requires `--expect-node <did>`: the queried node's
|
||||
/// self-reported DID is not a trust anchor, because a node serving a
|
||||
/// forged certificate also controls its own self-report. Callers
|
||||
/// must name the issuer they trust.
|
||||
Show {
|
||||
/// Repository in <owner>/<repo> or <repo> format
|
||||
repo: String,
|
||||
@@ -49,13 +55,17 @@ pub enum CertCmd {
|
||||
#[arg(long)]
|
||||
dir: Option<PathBuf>,
|
||||
/// Exit non-zero unless the Ed25519 signature verifies AND the
|
||||
/// issuing node matches the queried node (or --expect-node)
|
||||
/// issuing node matches --expect-node (which --verify requires:
|
||||
/// without a caller-supplied anchor there is no trusted issuer to
|
||||
/// verify against)
|
||||
#[arg(long)]
|
||||
verify: bool,
|
||||
/// Expected issuing node DID for --verify. A valid signature alone
|
||||
/// only proves the cert is internally consistent — signed by whatever
|
||||
/// key it names — so --verify also anchors the issuer to a DID you
|
||||
/// trust: this value when given, else the queried node's DID.
|
||||
/// trust. The queried node's self-reported DID is deliberately NOT
|
||||
/// accepted as a fallback anchor: the node that served the cert can
|
||||
/// serve a matching self-report.
|
||||
#[arg(long, requires = "verify")]
|
||||
expect_node: Option<String>,
|
||||
},
|
||||
@@ -152,6 +162,24 @@ async fn cmd_show(
|
||||
let node_did = cert["node_did"].as_str().unwrap_or("?");
|
||||
let signature = cert["signature"].as_str().unwrap_or("?");
|
||||
let issued_at = cert["issued_at"].as_str().unwrap_or("?");
|
||||
// #26 Split PR 3: read the wire-format version. A MISSING key
|
||||
// selects legacy v1 (an old server that predates the field).
|
||||
// A PRESENT value must be a JSON integer that fits in u32 and
|
||||
// names a version this client supports — otherwise the response
|
||||
// declares a format we cannot represent and we refuse to verify
|
||||
// rather than guess the payload shape. Reviewer 2 finding:
|
||||
// collapsing `null`, a string, a float, or an overflow integer
|
||||
// onto v1 would let a well-signed v1 signature pass `--verify`
|
||||
// against a server that explicitly said "version 2 (or 99, or
|
||||
// 4294967297)" — that is the exact mismatch the field exists
|
||||
// to prevent. parse_cert_version is the load-bearing parser
|
||||
// that distinguishes missing-key (legacy v1) from invalid-value
|
||||
// (unsupported).
|
||||
let parsed_version = parse_cert_version(cert.get("version"));
|
||||
let version_display: String = match &parsed_version {
|
||||
Ok(v) => v.to_string(),
|
||||
Err(reason) => format!("unsupported ({reason})"),
|
||||
};
|
||||
|
||||
println!("Ref Certificate: {cert_id}");
|
||||
println!(" Ref: {ref_name}");
|
||||
@@ -160,6 +188,7 @@ async fn cmd_show(
|
||||
println!(" Pusher: {pusher}");
|
||||
println!(" Node DID: {node_did}");
|
||||
println!(" Issued at: {issued_at}");
|
||||
println!(" Version: {version_display}");
|
||||
println!(" Signature: {signature}");
|
||||
println!();
|
||||
|
||||
@@ -169,9 +198,31 @@ async fn cmd_show(
|
||||
// This proves the cert is internally authentic — signed by the key it
|
||||
// names; the node-DID comparison below covers *which* node that is.
|
||||
let repo_id = cert["repo_id"].as_str().unwrap_or("");
|
||||
let verdict = verify_signature(
|
||||
repo_id, ref_name, old_sha, new_sha, pusher, node_did, issued_at, signature,
|
||||
);
|
||||
let verdict = match parsed_version {
|
||||
// v1 is the only version this client verifies. The v1
|
||||
// signed payload is the 7-field canonical form with no
|
||||
// `version` key — see gitlawb-node/src/cert.rs. A future
|
||||
// v2+ cert has a different signed payload shape (the
|
||||
// version field becomes part of the signed JSON per
|
||||
// `v2_signing_payload`), so a v2+ cert from a server this
|
||||
// client does not know about must NOT be silently verified
|
||||
// as v1.
|
||||
// Reviewer 2: refuse rather than guess; the client and
|
||||
// server must agree on the version.
|
||||
// parse_cert_version admits exactly one Ok value: 1 (missing key and
|
||||
// integer 1 both land there; 2, floats, strings, overflow and every
|
||||
// other spelling come back Err with their own reason). A separate
|
||||
// `Ok(v != 1)` arm existed here and was DEAD CODE — a test aimed at it
|
||||
// could never catch drift in this match (review round 2) — so the
|
||||
// match now mirrors the parser's real contract, which the
|
||||
// `parse_cert_version_truth_table` test pins.
|
||||
Ok(_) => verify_signature(
|
||||
repo_id, ref_name, old_sha, new_sha, pusher, node_did, issued_at, signature,
|
||||
),
|
||||
Err(ref reason) => Err(format!(
|
||||
"cert declared a version this client cannot represent ({reason}); refusing to verify"
|
||||
)),
|
||||
};
|
||||
|
||||
println!("Signature verification:");
|
||||
match &verdict {
|
||||
@@ -181,7 +232,11 @@ async fn cmd_show(
|
||||
);
|
||||
}
|
||||
Err(reason) => {
|
||||
println!(" INVALID — {reason}");
|
||||
// A version refusal means no cryptographic check ran, so it must
|
||||
// not print as an INVALID signature: operators and log scrapers
|
||||
// would read that as a failed Ed25519 verification. INVALID is
|
||||
// reserved for failures out of verify_signature itself.
|
||||
println!(" {} — {reason}", signature_verdict_label(&parsed_version));
|
||||
}
|
||||
}
|
||||
|
||||
@@ -198,29 +253,39 @@ async fn cmd_show(
|
||||
},
|
||||
Err(e) => Err(e.to_string()),
|
||||
};
|
||||
let current_node_did = current.as_ref().ok().cloned();
|
||||
for line in did_check_report(¤t, node_did) {
|
||||
println!("{line}");
|
||||
}
|
||||
|
||||
if require_valid {
|
||||
if let Err(reason) = verdict {
|
||||
anyhow::bail!("certificate signature did not verify: {reason}");
|
||||
// Round 3: do not claim the signature failed when it was
|
||||
// never checked. A version refusal means the payload
|
||||
// shape is unknown, so no signature verification ran.
|
||||
anyhow::bail!("certificate could not be verified: {reason}");
|
||||
}
|
||||
// A valid signature proves internal consistency only: the payload was
|
||||
// signed by whatever key the certificate itself names. A hostile
|
||||
// source can mint a keypair, put its DID in node_did, and self-sign.
|
||||
// --verify therefore also anchors the issuer to a trusted DID:
|
||||
// --expect-node when given, else the DID of the node being queried.
|
||||
let expected = expect_node.as_deref().or(current_node_did.as_deref());
|
||||
match expected {
|
||||
// --verify therefore also anchors the issuer — and the anchor must be
|
||||
// a DID the CALLER trusts, which is exactly what --expect-node is.
|
||||
// The DID the queried node reports at `/` is NOT an anchor: the same
|
||||
// node that served a forged certificate can serve a matching
|
||||
// self-report, and with that fallback a wholly forged cert printed
|
||||
// VALID and exited 0 (review round 2, demonstrated by execution). So
|
||||
// --verify without --expect-node refuses to claim a trusted issuer at
|
||||
// all, rather than laundering the server's self-assertion into one.
|
||||
match expect_node.as_deref() {
|
||||
Some(expected) if expected == node_did => {}
|
||||
Some(expected) => anyhow::bail!(
|
||||
"certificate is signed by {node_did}, but the expected issuer is {expected} — \
|
||||
a valid signature alone proves internal consistency, not a trusted issuer"
|
||||
),
|
||||
None => anyhow::bail!(
|
||||
"cannot anchor the issuer: node info is unreachable and no --expect-node was given"
|
||||
"--verify needs --expect-node <did> to anchor the issuer: the signature is \
|
||||
valid, but it only proves the cert is self-consistent with the DID it \
|
||||
names ({node_did}); the queried node's self-reported DID is not a trust \
|
||||
anchor"
|
||||
),
|
||||
}
|
||||
}
|
||||
@@ -268,6 +333,18 @@ fn did_check_report(current: &std::result::Result<String, String>, node_did: &st
|
||||
}
|
||||
}
|
||||
|
||||
/// The stdout label for a failed verification verdict. A `parsed_version`
|
||||
/// error means `verify_signature` never ran, so the refusal must print as
|
||||
/// UNSUPPORTED VERSION rather than INVALID, which operators and log
|
||||
/// scrapers would read as a failed Ed25519 check.
|
||||
fn signature_verdict_label(parsed_version: &std::result::Result<u32, String>) -> &'static str {
|
||||
if parsed_version.is_err() {
|
||||
"UNSUPPORTED VERSION"
|
||||
} else {
|
||||
"INVALID"
|
||||
}
|
||||
}
|
||||
|
||||
/// Rebuild the node's canonical signing payload (field order must match
|
||||
/// gitlawb-node/src/cert.rs::issue_ref_certificate exactly) and verify the
|
||||
/// certificate's Ed25519 signature against the key embedded in `node_did`.
|
||||
@@ -314,6 +391,65 @@ fn verify_signature(
|
||||
.map_err(|_| "Ed25519 signature does not match the signed payload".to_string())
|
||||
}
|
||||
|
||||
/// Parse the wire-format `version` field of a certificate response.
|
||||
///
|
||||
/// Semantics (Reviewer 2):
|
||||
/// - MISSING key (`None`) → `Ok(1)`. An old server predates the field, so
|
||||
/// the cert is by definition the v1 (pre-versioning) shape; the v1
|
||||
/// verify path is the only path that can possibly match the bytes.
|
||||
/// - PRESENT key must be a JSON integer that fits losslessly in `u32`
|
||||
/// and equals a version this client supports. `null`, a string,
|
||||
/// a float, an overflow integer, or any version other than 1 all
|
||||
/// yield `Err`. Collapsing any of these onto v1 would let a
|
||||
/// well-signed v1 signature pass `--verify` against a response
|
||||
/// that explicitly declared a format this client cannot represent
|
||||
/// — which is exactly the mismatch the version field exists to
|
||||
/// prevent.
|
||||
///
|
||||
/// The supported-version set is hard-coded to `{1}` because PR 3 ships
|
||||
/// only v1 verification; bump this set (and the verdict branch) when
|
||||
/// v2 verification lands.
|
||||
fn parse_cert_version(value: Option<&Value>) -> Result<u32, String> {
|
||||
let v = match value {
|
||||
None => return Ok(1),
|
||||
Some(v) => v,
|
||||
};
|
||||
|
||||
// serde_json::Value::as_u64 rejects strings, floats, booleans,
|
||||
// nulls, arrays, and objects — but it silently truncates floats
|
||||
// that are whole numbers (e.g. 2.0 → 2). We must reject floats
|
||||
// explicitly so a server cannot smuggle a v2 cert through the
|
||||
// float shape.
|
||||
if v.is_f64() {
|
||||
return Err(format!(
|
||||
"version is a JSON number with a fractional part ({v}); expected an integer"
|
||||
));
|
||||
}
|
||||
|
||||
let n = v.as_u64().ok_or_else(|| {
|
||||
// null / string / bool / array / object — anything that is
|
||||
// not a JSON integer.
|
||||
format!("version is {v}; expected a JSON integer")
|
||||
})?;
|
||||
|
||||
// Lossy narrowing: refuse anything that does not fit in u32.
|
||||
// u32::MAX is 4_294_967_295; serde_json only goes up to u64.
|
||||
if n > u32::MAX as u64 {
|
||||
return Err(format!(
|
||||
"version {n} does not fit in u32 (max {})",
|
||||
u32::MAX
|
||||
));
|
||||
}
|
||||
|
||||
let n = n as u32;
|
||||
if n != 1 {
|
||||
return Err(format!(
|
||||
"this client supports cert version 1 only; server returned {n}"
|
||||
));
|
||||
}
|
||||
Ok(1)
|
||||
}
|
||||
|
||||
async fn resolve_cert_id(client: &NodeClient, owner: &str, name: &str, id: &str) -> Result<String> {
|
||||
if id.len() >= 36 {
|
||||
return Ok(id.to_string());
|
||||
@@ -811,7 +947,15 @@ mod tests {
|
||||
let mut server = mockito::Server::new_async().await;
|
||||
let (cert, _root) = cert_server(&mut server, &id, &body, Some(&info)).await;
|
||||
|
||||
let got = cmd_show("alice/r".to_string(), id, server.url(), None, true, None).await;
|
||||
let got = cmd_show(
|
||||
"alice/r".to_string(),
|
||||
id,
|
||||
server.url(),
|
||||
None,
|
||||
true,
|
||||
Some(kp.did().as_str().to_string()),
|
||||
)
|
||||
.await;
|
||||
assert!(got.is_ok(), "valid sig + matching issuer must pass");
|
||||
cert.assert_async().await;
|
||||
}
|
||||
@@ -827,10 +971,17 @@ mod tests {
|
||||
let mut server = mockito::Server::new_async().await;
|
||||
let (cert, _root) = cert_server(&mut server, &id, &body, Some(&info)).await;
|
||||
|
||||
let err = cmd_show("alice/r".to_string(), id, server.url(), None, true, None)
|
||||
.await
|
||||
.unwrap_err()
|
||||
.to_string();
|
||||
let err = cmd_show(
|
||||
"alice/r".to_string(),
|
||||
id,
|
||||
server.url(),
|
||||
None,
|
||||
true,
|
||||
Some(other.did().as_str().to_string()),
|
||||
)
|
||||
.await
|
||||
.unwrap_err()
|
||||
.to_string();
|
||||
assert!(err.contains("expected issuer"), "got: {err}");
|
||||
cert.assert_async().await;
|
||||
}
|
||||
@@ -848,7 +999,7 @@ mod tests {
|
||||
.await
|
||||
.unwrap_err()
|
||||
.to_string();
|
||||
assert!(err.contains("cannot anchor the issuer"), "got: {err}");
|
||||
assert!(err.contains("--expect-node"), "got: {err}");
|
||||
cert.assert_async().await;
|
||||
}
|
||||
|
||||
@@ -889,7 +1040,7 @@ mod tests {
|
||||
.await
|
||||
.unwrap_err()
|
||||
.to_string();
|
||||
assert!(err.contains("signature did not verify"), "got: {err}");
|
||||
assert!(err.contains("does not match"), "got: {err}");
|
||||
cert.assert_async().await;
|
||||
}
|
||||
|
||||
@@ -973,4 +1124,373 @@ mod tests {
|
||||
assert!(report.contains("verify offline"), "got: {report}");
|
||||
assert!(!report.contains("WARNING"), "got: {report}");
|
||||
}
|
||||
|
||||
/// #26 Split PR 3: a missing `version` field on a cert defaults
|
||||
/// to 1, so an old server's response is forward-compatible with
|
||||
/// a new client. The v1 verify path is taken, and a
|
||||
/// well-signed v1 cert round-trips through `verify_signature`.
|
||||
///
|
||||
/// Reviewer 1 finding: the previous shape only parsed the field
|
||||
/// and never called `verify_signature`, so the test could not
|
||||
/// fail if the verdict branch was wired to the wrong path. This
|
||||
/// version signs and verifies the full round-trip.
|
||||
#[test]
|
||||
fn missing_version_defaults_to_1_and_verifies() {
|
||||
let kp = gitlawb_core::identity::Keypair::generate();
|
||||
let node_did = kp.did().as_str().to_string();
|
||||
let payload = serde_json::json!({
|
||||
"repo_id": "repo-1",
|
||||
"ref": "refs/heads/main",
|
||||
"old": "0".repeat(40),
|
||||
"new": "a".repeat(40),
|
||||
"pusher": "did:key:z6MkPusher",
|
||||
"node": node_did,
|
||||
"ts": "2026-07-22T00:00:00+00:00",
|
||||
});
|
||||
let sig = kp.sign_b64(&serde_json::to_vec(&payload).unwrap());
|
||||
|
||||
// Simulate the JSON a v1 server returns: no `version` key.
|
||||
let cert_json = serde_json::json!({
|
||||
"id": "test-id",
|
||||
"repo_id": "repo-1",
|
||||
"ref_name": "refs/heads/main",
|
||||
"old_sha": "0".repeat(40),
|
||||
"new_sha": "a".repeat(40),
|
||||
"pusher_did": "did:key:z6MkPusher",
|
||||
"node_did": node_did,
|
||||
"signature": sig.clone(),
|
||||
"issued_at": "2026-07-22T00:00:00+00:00",
|
||||
// no `version` field
|
||||
});
|
||||
|
||||
// Forward-compat: the parse yields v1 (the only version this
|
||||
// client verifies), and the verdict arm matching Ok(1) feeds
|
||||
// the v1 payload through verify_signature end to end.
|
||||
assert_eq!(parse_cert_version(cert_json.get("version")).unwrap(), 1);
|
||||
let verdict = verify_signature(
|
||||
"repo-1",
|
||||
"refs/heads/main",
|
||||
&"0".repeat(40),
|
||||
&"a".repeat(40),
|
||||
"did:key:z6MkPusher",
|
||||
&node_did,
|
||||
"2026-07-22T00:00:00+00:00",
|
||||
&sig,
|
||||
);
|
||||
assert!(
|
||||
verdict.is_ok(),
|
||||
"missing version must take the v1 verify path: {verdict:?}"
|
||||
);
|
||||
}
|
||||
|
||||
/// #26 Split PR 3: an explicit `version: 1` on a cert is the v1
|
||||
/// verify path. A v1 cert with an explicit version verifies the
|
||||
/// same as a v1 cert without one — round-trip through
|
||||
/// `verify_signature`.
|
||||
#[test]
|
||||
fn explicit_version_1_takes_v1_path() {
|
||||
let kp = gitlawb_core::identity::Keypair::generate();
|
||||
let node_did = kp.did().as_str().to_string();
|
||||
let payload = serde_json::json!({
|
||||
"repo_id": "repo-1",
|
||||
"ref": "refs/heads/main",
|
||||
"old": "0".repeat(40),
|
||||
"new": "a".repeat(40),
|
||||
"pusher": "did:key:z6MkPusher",
|
||||
"node": node_did,
|
||||
"ts": "2026-07-22T00:00:00+00:00",
|
||||
});
|
||||
let sig = kp.sign_b64(&serde_json::to_vec(&payload).unwrap());
|
||||
|
||||
// Simulate a v1 cert with an explicit `version: 1` field.
|
||||
let cert_json = serde_json::json!({
|
||||
"id": "test-id",
|
||||
"repo_id": "repo-1",
|
||||
"ref_name": "refs/heads/main",
|
||||
"old_sha": "0".repeat(40),
|
||||
"new_sha": "a".repeat(40),
|
||||
"pusher_did": "did:key:z6MkPusher",
|
||||
"node_did": node_did,
|
||||
"signature": sig.clone(),
|
||||
"issued_at": "2026-07-22T00:00:00+00:00",
|
||||
"version": 1,
|
||||
});
|
||||
|
||||
// The parse arms the Ok(1) verdict branch, which calls
|
||||
// verify_signature on the v1 payload. A signature mismatch
|
||||
// here would mean the verdict branch was wired to the
|
||||
// wrong path or the payload drifted.
|
||||
assert_eq!(parse_cert_version(cert_json.get("version")).unwrap(), 1);
|
||||
let verdict = verify_signature(
|
||||
"repo-1",
|
||||
"refs/heads/main",
|
||||
&"0".repeat(40),
|
||||
&"a".repeat(40),
|
||||
"did:key:z6MkPusher",
|
||||
&node_did,
|
||||
"2026-07-22T00:00:00+00:00",
|
||||
&sig,
|
||||
);
|
||||
assert!(
|
||||
verdict.is_ok(),
|
||||
"explicit version: 1 must take the v1 verify path: {verdict:?}"
|
||||
);
|
||||
}
|
||||
|
||||
/// #26 Split PR 3 + Reviewer 2: parse_cert_version is the
|
||||
/// load-bearing gate that distinguishes a missing-key (legacy
|
||||
/// server) from a present-but-malformed value. The four cases
|
||||
/// below pin every cell of that truth table; collapsing any
|
||||
/// pair would let a server advertise "version 2" (or 99, or
|
||||
/// 4294967297, or "two") while the client runs the v1
|
||||
/// signature path on a different signed payload — a hostile
|
||||
/// misconfiguration that `--verify` must not silently accept.
|
||||
#[test]
|
||||
fn parse_cert_version_truth_table() {
|
||||
// MISSING key → legacy v1 (the v1 path is the only one that
|
||||
// could match pre-versioning bytes).
|
||||
assert_eq!(
|
||||
parse_cert_version(None).unwrap(),
|
||||
1,
|
||||
"a missing version field is the legacy v1 path"
|
||||
);
|
||||
|
||||
// Explicit 1 → v1.
|
||||
assert_eq!(
|
||||
parse_cert_version(Some(&serde_json::json!(1))).unwrap(),
|
||||
1,
|
||||
"explicit version 1 is the v1 path"
|
||||
);
|
||||
|
||||
// Explicit 2 → Err, NOT Ok(1). Reviewer 2: a v1 signature
|
||||
// must not verify against a server that said "version 2".
|
||||
assert!(
|
||||
parse_cert_version(Some(&serde_json::json!(2))).is_err(),
|
||||
"explicit version 2 must not collapse to v1"
|
||||
);
|
||||
|
||||
// u32 overflow (2^32 + 1) → Err, NOT Ok(1). The previous
|
||||
// `.map(|v| v as u32)` silently truncated this to 1.
|
||||
let overflow = serde_json::json!(u64::from(u32::MAX) + 1);
|
||||
assert!(
|
||||
parse_cert_version(Some(&overflow)).is_err(),
|
||||
"a version that overflows u32 must not truncate to 1"
|
||||
);
|
||||
|
||||
// Non-numeric: a string, a float, null, bool — every shape
|
||||
// that is not a JSON integer is rejected. None of these
|
||||
// may collapse to v1.
|
||||
for bad in [
|
||||
serde_json::json!("two"),
|
||||
serde_json::json!(2.0), // serde_json::Value::is_f64 is true for this
|
||||
serde_json::json!(2.5), // obviously fractional
|
||||
serde_json::json!(true),
|
||||
serde_json::json!(null),
|
||||
serde_json::json!([2]),
|
||||
serde_json::json!({"v": 2}),
|
||||
] {
|
||||
assert!(
|
||||
parse_cert_version(Some(&bad)).is_err(),
|
||||
"non-integer version {bad} must not collapse to v1"
|
||||
);
|
||||
}
|
||||
}
|
||||
|
||||
/// A version refusal must not print as INVALID — no cryptographic
|
||||
/// check ran, so labelling it INVALID would tell operators an Ed25519
|
||||
/// verification failed when the payload shape was the disqualifier.
|
||||
/// Removing the label branch fails this test.
|
||||
#[test]
|
||||
fn signature_verdict_label_distinguishes_refusal_from_bad_signature() {
|
||||
assert_eq!(
|
||||
signature_verdict_label(&Err("version 2 not supported".to_string())),
|
||||
"UNSUPPORTED VERSION"
|
||||
);
|
||||
assert_eq!(signature_verdict_label(&Ok(1)), "INVALID");
|
||||
}
|
||||
|
||||
/// #26 Split PR 3, round 2: a `version: 2` certificate must fail
|
||||
/// `--verify` THROUGH `cmd_show` itself, not through a copy of its
|
||||
/// match. The prior form of this test duplicated the verdict match in
|
||||
/// the test body and aimed at an `Ok(v != 1)` arm the real parser can
|
||||
/// never produce, so gutting `cmd_show`'s rejection kept every test
|
||||
/// green (demonstrated by the reviewer by execution). Driving the
|
||||
/// command end to end is what makes this a guard: the mock serves a
|
||||
/// cert whose SIGNATURE IS VALID for v1 bytes but which declares
|
||||
/// version 2, and the command must exit Err with the version named —
|
||||
/// the v1 verify path must not launder it through.
|
||||
#[tokio::test]
|
||||
async fn cmd_show_verify_rejects_v2_even_with_valid_v1_signature() {
|
||||
let kp = gitlawb_core::identity::Keypair::generate();
|
||||
let node_did = kp.did().as_str().to_string();
|
||||
|
||||
// Sign a v1-shaped payload so the ONLY disqualifier is the version.
|
||||
let payload = serde_json::json!({
|
||||
"repo_id": "repo-1",
|
||||
"ref": "refs/heads/main",
|
||||
"old": "0".repeat(40),
|
||||
"new": "a".repeat(40),
|
||||
"pusher": "did:key:z6MkPusher",
|
||||
"node": node_did,
|
||||
"ts": "2026-07-22T00:00:00+00:00",
|
||||
});
|
||||
let sig = kp.sign_b64(&serde_json::to_vec(&payload).unwrap());
|
||||
|
||||
let cert_json = serde_json::json!({
|
||||
"id": "0123456789abcdef0123456789abcdef0123",
|
||||
"repo_id": "repo-1",
|
||||
"ref_name": "refs/heads/main",
|
||||
"old_sha": "0".repeat(40),
|
||||
"new_sha": "a".repeat(40),
|
||||
"pusher_did": "did:key:z6MkPusher",
|
||||
"node_did": node_did,
|
||||
"signature": sig,
|
||||
"issued_at": "2026-07-22T00:00:00+00:00",
|
||||
"version": 2,
|
||||
});
|
||||
|
||||
let mut server = mockito::Server::new_async().await;
|
||||
// 36-char id short-circuits resolve_cert_id; "owner/repo" input
|
||||
// short-circuits resolve_repo — the cert GET is the only required
|
||||
// route. `/` may be probed for the contextual DID line; serving it
|
||||
// keeps the test about the verdict, not about network noise.
|
||||
let _cert = server
|
||||
.mock(
|
||||
"GET",
|
||||
"/api/v1/repos/o/r/certs/0123456789abcdef0123456789abcdef0123",
|
||||
)
|
||||
.with_status(200)
|
||||
.with_header("content-type", "application/json")
|
||||
.with_body(cert_json.to_string())
|
||||
.create_async()
|
||||
.await;
|
||||
let _root = server
|
||||
.mock("GET", "/")
|
||||
.with_status(200)
|
||||
.with_header("content-type", "application/json")
|
||||
.with_body(serde_json::json!({ "did": node_did }).to_string())
|
||||
.create_async()
|
||||
.await;
|
||||
|
||||
let err = cmd_show(
|
||||
"o/r".to_string(),
|
||||
"0123456789abcdef0123456789abcdef0123".to_string(),
|
||||
server.url(),
|
||||
None,
|
||||
true,
|
||||
Some(node_did.clone()),
|
||||
)
|
||||
.await
|
||||
.expect_err("a version-2 cert must fail --verify even with a valid v1 signature");
|
||||
let msg = format!("{err:#}");
|
||||
assert!(
|
||||
msg.contains("version"),
|
||||
"the failure must name the version mismatch, not a generic invalid signature: {msg}"
|
||||
);
|
||||
}
|
||||
|
||||
/// Round 2's second demonstrated escape: with no --expect-node, the old
|
||||
/// fallback anchored the issuer to the DID the QUERIED NODE reports at
|
||||
/// `/` — which a forger controls along with the cert, so a wholly forged
|
||||
/// self-signed certificate passed --verify with exit 0. `cmd_show` with
|
||||
/// --verify and no --expect-node must now refuse to claim a trusted
|
||||
/// issuer, even when the served cert's signature is valid and the node's
|
||||
/// self-report matches it.
|
||||
#[tokio::test]
|
||||
async fn cmd_show_verify_without_expect_node_refuses_self_asserted_anchor() {
|
||||
let kp = gitlawb_core::identity::Keypair::generate();
|
||||
let node_did = kp.did().as_str().to_string();
|
||||
let payload = serde_json::json!({
|
||||
"repo_id": "repo-1",
|
||||
"ref": "refs/heads/main",
|
||||
"old": "0".repeat(40),
|
||||
"new": "a".repeat(40),
|
||||
"pusher": "did:key:z6MkPusher",
|
||||
"node": node_did,
|
||||
"ts": "2026-07-22T00:00:00+00:00",
|
||||
});
|
||||
let sig = kp.sign_b64(&serde_json::to_vec(&payload).unwrap());
|
||||
let cert_json = serde_json::json!({
|
||||
"id": "0123456789abcdef0123456789abcdef0123",
|
||||
"repo_id": "repo-1",
|
||||
"ref_name": "refs/heads/main",
|
||||
"old_sha": "0".repeat(40),
|
||||
"new_sha": "a".repeat(40),
|
||||
"pusher_did": "did:key:z6MkPusher",
|
||||
"node_did": node_did,
|
||||
"signature": sig,
|
||||
"issued_at": "2026-07-22T00:00:00+00:00",
|
||||
});
|
||||
|
||||
let mut server = mockito::Server::new_async().await;
|
||||
// P3 (reviewer round 2): both mocks are required to be
|
||||
// hit for the test to mean anything. `mockito 1.7`'s
|
||||
// `assert_on_drop` is off by default, so the previous
|
||||
// `_cert` and `_root` bindings would silently let a
|
||||
// regression that skipped the root fetch pass.
|
||||
// `.expect(2)` pins each mock's call count (the cert mock
|
||||
// is hit twice because the test runs `cmd_show` twice) and
|
||||
// `.assert_async()` at the end fires if any are unmet.
|
||||
let cert_mock = server
|
||||
.mock(
|
||||
"GET",
|
||||
"/api/v1/repos/o/r/certs/0123456789abcdef0123456789abcdef0123",
|
||||
)
|
||||
.with_status(200)
|
||||
.with_header("content-type", "application/json")
|
||||
.with_body(cert_json.to_string())
|
||||
.expect(2)
|
||||
.create_async()
|
||||
.await;
|
||||
// The forger's matching self-report — the exact shape
|
||||
// that used to convert into a trust anchor. The guard's
|
||||
// whole point is to make the test FAIL if a future
|
||||
// regression stops calling `/` here: `.expect(2)` +
|
||||
// `.assert_async()` makes that dependency visible.
|
||||
let root_mock = server
|
||||
.mock("GET", "/")
|
||||
.with_status(200)
|
||||
.with_header("content-type", "application/json")
|
||||
.with_body(serde_json::json!({ "did": node_did }).to_string())
|
||||
.expect(2)
|
||||
.create_async()
|
||||
.await;
|
||||
|
||||
let err = cmd_show(
|
||||
"o/r".to_string(),
|
||||
"0123456789abcdef0123456789abcdef0123".to_string(),
|
||||
server.url(),
|
||||
None,
|
||||
true,
|
||||
None,
|
||||
)
|
||||
.await
|
||||
.expect_err("--verify without --expect-node must not mint a trust anchor from the node's self-report");
|
||||
let msg = format!("{err:#}");
|
||||
assert!(
|
||||
msg.contains("--expect-node"),
|
||||
"the refusal must tell the caller how to anchor trust: {msg}"
|
||||
);
|
||||
|
||||
// Positive control: the same cert with the DID explicitly trusted
|
||||
// passes, so the guard is about the anchor, not the signature.
|
||||
cmd_show(
|
||||
"o/r".to_string(),
|
||||
"0123456789abcdef0123456789abcdef0123".to_string(),
|
||||
server.url(),
|
||||
None,
|
||||
true,
|
||||
Some(node_did),
|
||||
)
|
||||
.await
|
||||
.expect("explicitly anchored --verify of a valid v1 cert must pass");
|
||||
|
||||
// P3 (reviewer round 2): confirm the mocks were actually
|
||||
// hit. Without this, a regression that skipped the cert or
|
||||
// root fetches would still produce a passing test (the
|
||||
// `expect_err` arm succeeds, the positive control succeeds)
|
||||
// and the test would mean nothing.
|
||||
cert_mock.assert_async().await;
|
||||
root_mock.assert_async().await;
|
||||
}
|
||||
}
|
||||
+177
-36
@@ -3,7 +3,7 @@
|
||||
//! Checks:
|
||||
//! 1. Identity — ~/.gitlawb/identity.pem exists, DID parseable
|
||||
//! 2. Registration — ~/.gitlawb/ucan.json exists (registered with a node)
|
||||
//! 3. GITLAWB_NODE — env var is set to a non-localhost URL
|
||||
//! 3. GITLAWB_NODE — env var points at a public node (unset is advisory)
|
||||
//! 4. Node — GITLAWB_NODE is reachable (default: https://node.twigpine.com)
|
||||
//! 5. git helper — git-remote-gitlawb is in PATH
|
||||
//! 6. git — git is installed
|
||||
@@ -80,7 +80,6 @@ pub async fn run(args: DoctorArgs) -> Result<()> {
|
||||
});
|
||||
|
||||
let mut checks = Vec::new();
|
||||
let mut all_ok = true;
|
||||
|
||||
// ── 1. Identity ───────────────────────────────────────────────────────
|
||||
let pem_path = dir.join("identity.pem");
|
||||
@@ -141,32 +140,16 @@ pub async fn run(args: DoctorArgs) -> Result<()> {
|
||||
}
|
||||
|
||||
// ── 3. GITLAWB_NODE env var ───────────────────────────────────────────
|
||||
match std::env::var("GITLAWB_NODE") {
|
||||
// A loopback host is a legitimate setup (self-hosted node, dev
|
||||
// harness) — the connectivity check below fails loudly if it is not
|
||||
// actually reachable, so don't red-flag the configuration itself.
|
||||
Ok(v) if is_loopback_url(&v) => {
|
||||
checks.push(Check::pass(
|
||||
"GITLAWB_NODE",
|
||||
format!(
|
||||
"{v} (local node — intentional for self-hosting/dev; unset to target the public network)"
|
||||
),
|
||||
));
|
||||
}
|
||||
Ok(v) if !v.is_empty() => {
|
||||
checks.push(Check::pass("GITLAWB_NODE", v.to_string()));
|
||||
}
|
||||
_ => {
|
||||
checks.push(Check::fail(
|
||||
"GITLAWB_NODE",
|
||||
"not set — git-remote-gitlawb will fall back to http://127.0.0.1:7545",
|
||||
"export GITLAWB_NODE=https://node.twigpine.com",
|
||||
));
|
||||
}
|
||||
}
|
||||
checks.push(gitlawb_node_env_check(
|
||||
std::env::var("GITLAWB_NODE").ok().as_deref(),
|
||||
));
|
||||
|
||||
// ── 4. Node connectivity ──────────────────────────────────────────────
|
||||
let client = NodeClient::new(&args.node, None);
|
||||
// GITLAWB_NODE="" binds args.node to "" through clap, and check 3 groups
|
||||
// empty with unset. The probe must apply the same normalization or it
|
||||
// would dial "" and Fail while the env row only Warns.
|
||||
let node_url = effective_node_url(&args.node);
|
||||
let client = NodeClient::new(node_url, None);
|
||||
match client.get("/").await {
|
||||
Ok(resp) if resp.status().is_success() => {
|
||||
let info = resp.json::<serde_json::Value>().await.unwrap_or_default();
|
||||
@@ -175,7 +158,7 @@ pub async fn run(args: DoctorArgs) -> Result<()> {
|
||||
let short_did = did.chars().take(30).collect::<String>();
|
||||
checks.push(Check::pass(
|
||||
"node",
|
||||
format!("{} — v{version} ({short_did}…)", args.node),
|
||||
format!("{} — v{version} ({short_did}…)", node_url),
|
||||
));
|
||||
// Capability drift: a node newer than this CLI may require features
|
||||
// (RFC 9421 signing, iCaptcha) the CLI doesn't speak.
|
||||
@@ -194,14 +177,14 @@ pub async fn run(args: DoctorArgs) -> Result<()> {
|
||||
Ok(resp) => {
|
||||
checks.push(Check::fail(
|
||||
"node",
|
||||
format!("{} returned HTTP {}", args.node, resp.status()),
|
||||
format!("{} returned HTTP {}", node_url, resp.status()),
|
||||
"check GITLAWB_NODE env var or try gl register --node <url>",
|
||||
));
|
||||
}
|
||||
Err(e) => {
|
||||
checks.push(Check::fail(
|
||||
"node",
|
||||
format!("{} unreachable: {e}", args.node),
|
||||
format!("{} unreachable: {e}", node_url),
|
||||
"check your internet connection or set GITLAWB_NODE",
|
||||
));
|
||||
}
|
||||
@@ -285,23 +268,21 @@ pub async fn run(args: DoctorArgs) -> Result<()> {
|
||||
CheckState::Fail => "✗",
|
||||
};
|
||||
println!(" {icon} {:<24} {}", check.label, check.detail);
|
||||
if matches!(check.state, CheckState::Fail) {
|
||||
all_ok = false;
|
||||
}
|
||||
}
|
||||
|
||||
println!();
|
||||
|
||||
let has_failures_now = has_failures(&checks);
|
||||
let has_issues = checks
|
||||
.iter()
|
||||
.any(|c| matches!(c.state, CheckState::Fail | CheckState::Warn));
|
||||
if !has_issues {
|
||||
println!("Everything looks good. Run `gl quickstart` to create your first repo.");
|
||||
} else {
|
||||
if all_ok {
|
||||
println!("Setup looks good with some warnings:");
|
||||
} else {
|
||||
if has_failures_now {
|
||||
println!("Some checks failed. Suggested fixes:");
|
||||
} else {
|
||||
println!("Setup looks good with some warnings:");
|
||||
}
|
||||
for check in &checks {
|
||||
if matches!(check.state, CheckState::Fail | CheckState::Warn) {
|
||||
@@ -311,14 +292,75 @@ pub async fn run(args: DoctorArgs) -> Result<()> {
|
||||
}
|
||||
}
|
||||
println!();
|
||||
if !all_ok {
|
||||
if has_failures_now {
|
||||
println!("Run `gl quickstart` for a guided setup.");
|
||||
}
|
||||
}
|
||||
|
||||
// #357: a non-zero exit is the only signal scripting and CI have. Warn-only
|
||||
// rows stay exit 0 (iCaptcha offline, version drift, shell-alias shadowing
|
||||
// are all non-fatal); Fail-class rows (identity, registration, node
|
||||
// reachable, git-remote-gitlawb present, git present) flip to exit 1.
|
||||
// Direct `process::exit` rather than returning Err: the prose above is the
|
||||
// user-facing summary, and an anyhow Error frame would just duplicate it.
|
||||
if has_failures(&checks) {
|
||||
std::process::exit(1);
|
||||
}
|
||||
|
||||
Ok(())
|
||||
}
|
||||
|
||||
/// Classify the `GITLAWB_NODE` env var for `gl doctor`. Extracted so unit
|
||||
/// tests can pin the Warn tier directly (#357): an unset env is advisory, not
|
||||
/// a failure, because `--node` defaults to `https://node.twigpine.com` and the
|
||||
/// CLI works without it. Flipping this back to `Check::fail` must break a
|
||||
/// test, not just change prose.
|
||||
fn gitlawb_node_env_check(env_val: Option<&str>) -> Check {
|
||||
match env_val {
|
||||
// A loopback host is a legitimate setup (self-hosted node, dev
|
||||
// harness) — the connectivity check below fails loudly if it is not
|
||||
// actually reachable, so don't red-flag the configuration itself.
|
||||
Some(v) if is_loopback_url(v) => Check::pass(
|
||||
"GITLAWB_NODE",
|
||||
format!(
|
||||
"{v} (local node — intentional for self-hosting/dev; unset to target the public network)"
|
||||
),
|
||||
),
|
||||
Some(v) if !v.is_empty() => Check::pass("GITLAWB_NODE", v.to_string()),
|
||||
// `--node` defaults to `https://node.twigpine.com` and the CLI works
|
||||
// fine without the variable, so an unset env is advisory, not a
|
||||
// failure. Warn-class keeps the exit code 0 for a stock working
|
||||
// install; this used to be Fail, which the obvious "return non-zero
|
||||
// on any failure" change would have flipped to exit 1 on every
|
||||
// default-config install (#357).
|
||||
_ => Check::warn(
|
||||
"GITLAWB_NODE",
|
||||
"not set — git-remote-gitlawb will fall back to http://127.0.0.1:7545",
|
||||
format!("export GITLAWB_NODE={PUBLIC_NODE}"),
|
||||
),
|
||||
}
|
||||
}
|
||||
|
||||
/// The URL the connectivity probe should dial. `GITLAWB_NODE` set but empty
|
||||
/// (or whitespace-only) binds `args.node` to `""` through clap rather than
|
||||
/// to the `default_value`, and check 3 already groups empty with unset, so
|
||||
/// the probe applies the same normalization: an empty effective URL means
|
||||
/// the public node, same as unset.
|
||||
fn effective_node_url(node: &str) -> &str {
|
||||
if node.trim().is_empty() {
|
||||
PUBLIC_NODE
|
||||
} else {
|
||||
node
|
||||
}
|
||||
}
|
||||
|
||||
/// True when at least one check is Fail-class. Warn-only runs (iCaptcha offline,
|
||||
/// version drift, shell-alias shadowing, GITLAWB_NODE unset) keep exit 0;
|
||||
/// this is the gating predicate for #357's exit-status fix.
|
||||
fn has_failures(checks: &[Check]) -> bool {
|
||||
checks.iter().any(|c| matches!(c.state, CheckState::Fail))
|
||||
}
|
||||
|
||||
/// Check if a binary name exists anywhere on PATH.
|
||||
/// True when the rc file contains a real `unalias` command naming `gl` —
|
||||
/// not a comment, and not a longer word like `unalias global`. Ordering
|
||||
@@ -644,4 +686,103 @@ mod tests {
|
||||
assert!(matches!(check.state, CheckState::Ok));
|
||||
assert!(check.detail.contains("GitHub API returned HTTP 403"));
|
||||
}
|
||||
|
||||
/// #357: an all-Ok run does not flip the exit code to non-zero — a healthy
|
||||
/// install must keep returning 0 so scripts like `gl doctor && gl push`
|
||||
/// keep working.
|
||||
#[test]
|
||||
fn exit_predicate_is_false_for_all_ok() {
|
||||
let checks = vec![
|
||||
Check::pass("identity", "ok"),
|
||||
Check::pass("registration", "ok"),
|
||||
Check::pass("git", "ok"),
|
||||
];
|
||||
assert!(!has_failures(&checks));
|
||||
}
|
||||
|
||||
/// #357: Warn-class rows (iCaptcha offline, version drift, shell-alias
|
||||
/// shadowing, GITLAWB_NODE unset on a default-config install) are NOT
|
||||
/// exit-status failures — they are still printed to the user but the
|
||||
/// process exits 0. This is the rule that the previous "any
|
||||
/// Fail-or-Warn row → exit 1" change would have broken for stock
|
||||
/// installs that simply have not set the env var.
|
||||
#[test]
|
||||
fn exit_predicate_is_false_for_warn_only() {
|
||||
let checks = vec![
|
||||
Check::pass("identity", "ok"),
|
||||
Check::warn("GITLAWB_NODE", "unset", "export GITLAWB_NODE=..."),
|
||||
Check::warn("iCaptcha", "offline", "check connectivity"),
|
||||
Check::warn("version", "drift", "upgrade"),
|
||||
Check::warn("shell alias", "omz git plugin", "unalias gl"),
|
||||
];
|
||||
assert!(!has_failures(&checks));
|
||||
}
|
||||
|
||||
/// #357: a single Fail-class row trips the exit code. The set of Fail
|
||||
/// rows is whatever `run` writes through `Check::fail`: identity missing
|
||||
/// or unparseable, registration missing/malformed, node unreachable,
|
||||
/// git-remote-gitlawb absent, git absent.
|
||||
#[test]
|
||||
fn exit_predicate_is_true_when_a_fail_row_is_present() {
|
||||
let checks = vec![
|
||||
Check::pass("registration", "ok"),
|
||||
Check::fail("identity", "missing", "gl identity new"),
|
||||
Check::pass("git", "ok"),
|
||||
];
|
||||
assert!(has_failures(&checks));
|
||||
|
||||
let mixed_warns = vec![
|
||||
Check::pass("identity", "ok"),
|
||||
Check::warn("GITLAWB_NODE", "unset", "export"),
|
||||
Check::fail("node", "unreachable", "check network"),
|
||||
Check::warn("iCaptcha", "offline", "check"),
|
||||
];
|
||||
assert!(has_failures(&mixed_warns));
|
||||
}
|
||||
|
||||
/// #357: `GITLAWB_NODE` unset must be Warn, not Fail. This pins the
|
||||
/// re-tier so flipping it back to `Check::fail` breaks the suite — the
|
||||
/// previous `has_failures`-only tests built their own `Check::warn` rows
|
||||
/// and could not see the re-tier at all.
|
||||
#[test]
|
||||
fn gitlawb_node_env_unset_is_warn() {
|
||||
let check = gitlawb_node_env_check(None);
|
||||
assert!(matches!(check.state, CheckState::Warn));
|
||||
assert!(check.detail.contains("not set"));
|
||||
let empty = gitlawb_node_env_check(Some(""));
|
||||
assert!(matches!(empty.state, CheckState::Warn));
|
||||
}
|
||||
|
||||
/// `GITLAWB_NODE=""` binds `args.node` to `""` through clap, and check 3
|
||||
/// groups empty with unset. The probe must dial the same URL unset
|
||||
/// would — removing the normalization makes check 4 probe `""` and Fail
|
||||
/// while the env row only Warns, so an empty env install exits 1.
|
||||
#[test]
|
||||
fn effective_node_url_treats_empty_and_blank_as_unset() {
|
||||
assert_eq!(effective_node_url(""), PUBLIC_NODE);
|
||||
assert_eq!(effective_node_url(" "), PUBLIC_NODE);
|
||||
assert_eq!(effective_node_url("\t\n"), PUBLIC_NODE);
|
||||
assert_eq!(
|
||||
effective_node_url("http://127.0.0.1:7545"),
|
||||
"http://127.0.0.1:7545"
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn gitlawb_node_env_set_is_pass() {
|
||||
let check = gitlawb_node_env_check(Some("https://node.twigpine.com"));
|
||||
assert!(matches!(check.state, CheckState::Ok));
|
||||
assert!(check.detail.contains("https://node.twigpine.com"));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn gitlawb_node_env_loopback_is_pass() {
|
||||
for url in ["http://127.0.0.1:7545", "http://localhost:7545"] {
|
||||
let check = gitlawb_node_env_check(Some(url));
|
||||
assert!(
|
||||
matches!(check.state, CheckState::Ok),
|
||||
"loopback {url} must be Ok, not Warn/Fail"
|
||||
);
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,48 @@
|
||||
//! #357: pin the `gl doctor` exit-code wiring, not just the predicate.
|
||||
//!
|
||||
//! The unit tests for `has_failures` never touch `std::process::exit(1)` or
|
||||
//! the `GITLAWB_NODE` Warn tier. Deleting the exit gate outright kept
|
||||
//! `cargo test -p gl doctor::` green, so this binary probe is the only thing
|
||||
//! that breaks when the wiring is gutted.
|
||||
|
||||
use std::process::Command;
|
||||
|
||||
#[test]
|
||||
fn doctor_exits_nonzero_when_fail_rows_present() {
|
||||
let dir = tempfile::tempdir().expect("temp dir");
|
||||
// Use an unroutable node so the "node unreachable" check is Fail-class.
|
||||
// The temp dir has no identity.pem / ucan.json, so identity + registration
|
||||
// are also Fail — at least one Fail must flip the process to exit 1.
|
||||
let bin = env!("CARGO_BIN_EXE_gl");
|
||||
let output = Command::new(bin)
|
||||
.args([
|
||||
"doctor",
|
||||
"--dir",
|
||||
dir.path().to_str().unwrap(),
|
||||
"--node",
|
||||
"http://127.0.0.1:1",
|
||||
])
|
||||
// Inherit PATH but neutralize GITLAWB_NODE so the test is deterministic
|
||||
// across machines that have it set (otherwise it would be Pass).
|
||||
.env_remove("GITLAWB_NODE")
|
||||
// iCaptcha probes a real URL by default; keep it unreachable too so
|
||||
// it stays Warn and does not affect the Fail gating.
|
||||
.env("GITLAWB_ICAPTCHA_URL", "http://127.0.0.1:1")
|
||||
.output()
|
||||
.expect("run gl doctor");
|
||||
|
||||
// The command should have exited 1 because at least one Fail row exists.
|
||||
// If the `std::process::exit(1)` gate is removed, this becomes 0 and the
|
||||
// test fails — that is the regression it pins.
|
||||
assert!(
|
||||
!output.status.success(),
|
||||
"gl doctor must exit non-zero when Fail rows are present; stdout: {}\nstderr: {}",
|
||||
String::from_utf8_lossy(&output.stdout),
|
||||
String::from_utf8_lossy(&output.stderr)
|
||||
);
|
||||
assert_eq!(
|
||||
output.status.code(),
|
||||
Some(1),
|
||||
"exit code must be 1, not some other non-zero"
|
||||
);
|
||||
}
|
||||
@@ -8,6 +8,7 @@ Step-by-step guide to staking $GITLAWB, registering your node on-chain, and earn
|
||||
|
||||
- A wallet with at least **10,000 $GITLAWB** (minimum stake) plus a small amount of ETH on Base for gas
|
||||
- Docker or Rust 1.91+ (for running the node process)
|
||||
- PostgreSQL 16+ — the node uses `pg_input_is_valid`, which exists only on PostgreSQL 16 and later. The bundled `docker-compose.yml` pins `postgres:16-alpine`; if you supply your own `DATABASE_URL`, the server must be 16+.
|
||||
- A public HTTP URL (your-host.com) — can be a VPS, Fly.io app, or anything reachable. A Fly.io config is provided at `infra/fly/fly.toml` (deploy from the repo root with `fly deploy -c infra/fly/fly.toml`)
|
||||
|
||||
---
|
||||
|
||||
@@ -0,0 +1,76 @@
|
||||
# GraphQL repository pagination
|
||||
|
||||
`repos` returns the complete visible repository list when it contains at most
|
||||
200 entries. Larger lists return a GraphQL error directing the caller to
|
||||
`reposPage`; they are never silently truncated.
|
||||
|
||||
Use `reposPage` for larger lists:
|
||||
|
||||
```graphql
|
||||
query Repositories($after: String) {
|
||||
reposPage(limit: 50, after: $after) {
|
||||
nodes {
|
||||
name
|
||||
ownerDid
|
||||
}
|
||||
hasNextPage
|
||||
endCursor
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
Start with `after: null`. When `hasNextPage` is true, pass the returned
|
||||
`endCursor` as `after` on the next request. Stop when `hasNextPage` is false.
|
||||
An empty page has a null `endCursor`. The default limit is 50 and the maximum
|
||||
page size is 200; limits below 1 or above 200 are rejected (see Query budgets
|
||||
below). Malformed cursors, including decoded owner or name strings containing
|
||||
NUL, return `invalid repository cursor` before database access.
|
||||
|
||||
Pages are ordered by normalized owner DID and repository name. Visibility and
|
||||
mirror deduplication are applied in the database before limiting the page;
|
||||
hidden and quarantined repositories do not occupy page slots or create a
|
||||
continuation signal. Cursors contain a position from the last returned visible
|
||||
repository, not a permission grant. Each request checks the current caller's
|
||||
visibility independently. Keep the same caller while traversing a list.
|
||||
Malformed reader lists in a repository's root visibility rule deny access to
|
||||
non-owners for that repository while other visible repositories remain listable.
|
||||
|
||||
Pagination is not a snapshot: concurrent renames, ownership changes, or visibility
|
||||
changes can alter subsequent pages. Treat cursors as opaque and restart from the
|
||||
first page when a fresh complete traversal is needed. Small legacy `repos`
|
||||
queries retain their activity ordering.
|
||||
|
||||
## Query budgets
|
||||
|
||||
Every GraphQL document is validated against two budgets before any resolver
|
||||
runs. Both apply per document (per request), not per client: `/graphql` has
|
||||
no per-caller rate limiting, so a rejected document can always be retried
|
||||
smaller. The constants live in `crates/gitlawb-node/src/graphql/mod.rs`.
|
||||
|
||||
- **Complexity budget: 400 per document** (`GRAPHQL_MAX_COMPLEXITY`). Each
|
||||
root field carries a base cost plus the clamped page size plus the selected
|
||||
child fields:
|
||||
- `repos`: 50 + `MAX_VISIBLE_REPO_PAGE_SIZE` + child fields. `repos`
|
||||
always scans the full visible corpus, so it is priced as the full page
|
||||
it is.
|
||||
- `reposPage`: 50 + `MAX_VISIBLE_REPO_PAGE_SIZE` + child fields. Every
|
||||
page request sorts the full deduplicated corpus, so the price does not
|
||||
depend on `limit`: seven `reposPage(limit: 1)` aliases cost the same as
|
||||
seven max-size pages.
|
||||
- `refUpdates`: 100 + clamped `limit` (`MAX_VISIBLE_REF_UPDATES`) + child
|
||||
fields. The 100 base covers the collector's fixed scan (the deduplicated
|
||||
repo set, the quarantined set, the visibility rules, and the bounded
|
||||
up-to-2048-row walk past withheld rows); the limit term prices only the
|
||||
rows returned.
|
||||
- `tasks`: 50 + clamped `limit` (`MAX_VISIBLE_TASK_PAGE_SIZE`) + child
|
||||
fields.
|
||||
- `task`, mutations, subscriptions: 50 + child fields.
|
||||
|
||||
A document whose total exceeds 400 is rejected with
|
||||
`Query is too complex.` before any resolver runs, so an over-budget
|
||||
document needs fewer aliases or fewer child fields. A smaller `limit` does
|
||||
not help `reposPage` or `repos`: both are priced at the full
|
||||
`MAX_VISIBLE_REPO_PAGE_SIZE` scan regardless of `limit`.
|
||||
|
||||
- **Depth cap: 14 per document** (`GRAPHQL_MAX_DEPTH`). Documents nested
|
||||
deeper than 14 selections are rejected with `Query is nested too deep.`
|
||||
Reference in new issue
Block a user