Compare commits

..
Author SHA1 Message Date
beardthelion 08e62694cb test(node): pin createTask repo-ownership marker in the GraphQL authz fence 2026-11-07 14:59:35 -06:00
beardthelion 50e614a522 Merge remote-tracking branch 'origin/main' into fix/issue-496-create-task-repo-gate
# Conflicts:
#	crates/gitlawb-node/src/graphql/mutation.rs
2026-11-06 23:54:01 -06:00
Gravirei 2baaf27892 test(node): pin stored-verbatim repo_id on GraphQL gate arms
The REST deny/allow matrix reads each accepted task back and asserts the
stored repo_id is the supplied id; the GraphQL unknown/quarantined arms only
asserted no errors, so a GraphQL regression that dropped, normalized, or
rebound the id stayed green. Read those tasks back by the mutation's returned
id and assert the stored label matches.
2026-10-29 10:58:50 +06:00
Gravirei 10645adae9 fix(node): mirror AppError's 503 split and opaque INSERT in create_task
- db_error now sends pool-class failures to 503 db_unavailable like
  AppError::Db (db_unavailable made pub(crate)); query faults stay the opaque
  500. Unit tests cover the split and context-wrapped sqlx errors.
- Route the create_task INSERT through db_error instead of serializing
  e.to_string(); a REST fault-injection test pins the opaque envelope.
- The deny/allow matrix reads back the unknown and quarantined tasks to prove
  the id is stored verbatim, and drops no-leak asserts on the fixed forbidden
  envelope that could never carry the repo id.
2026-10-28 15:14:56 +06:00
Gravirei 37764c7ddb docs(node): stop claiming caller-scoped task reads in #496 gate comments
The create_task gate is a write gate. Unknown/quarantined repo ids are stored
verbatim, and the REST/GraphQL task-list paths are caller-independent on this
base, so the comments must not imply those ids are read-scoped to the
delegator/assignee. Describe only the enforced ownership check; note the
one-bit oracle split without asserting a read contract.
2026-10-27 08:10:40 +06:00
Gravirei be55f8bd46 fix(node): address P3 review on #496 gate — shared denial text, honest oracle wording, db-fault pins
- Give the REST and GraphQL copies of the create_task owner gate one denial
  sentence: add REPO_OWNER_ONLY_MESSAGE, used by require_repo_owner and the
  REST forbidden() envelope, and pin it from both surface tests.
- Carry the corrected one-bit-oracle wording into the GraphQL gate comment and
  the REST test docstring (drop the "oracle-free" claim).
- Fault-inject the gate's repo lookups: drop machine_id (get_repo_by_id) for
  REST and GraphQL, and quarantined (is_repo_quarantined) for REST, asserting
  the fixed opaque db_error envelope and no schema text.
2026-10-27 07:49:36 +06:00
Gravirei abc03d65c7 fix(node): address review on #496 gate — opaque lookup errors, no-persist asserts, GraphQL arm pins, honest oracle comment 2026-10-01 10:02:13 +06:00
Gravirei 64ef51d775 fix(node): owner-gate create_task repo_id against hosted repos (#496) 2026-09-29 13:28:21 +06:00
12 changed files with 709 additions and 1218 deletions

No files matched your search

+9 -56
View File
@@ -1,13 +1,12 @@
//! GET /api/v1/arweave/anchors — list Arweave ref-update anchors.
use axum::{
extract::{Extension, Query, State},
extract::{Query, State},
Json,
};
use serde::Deserialize;
use crate::db::normalize_owner_key;
use crate::error::{AppError, Result};
use crate::error::Result;
use crate::state::AppState;
#[derive(Debug, Deserialize)]
@@ -22,62 +21,17 @@ fn default_limit() -> i64 {
}
/// GET /api/v1/arweave/anchors
///
/// `?repo=<owner>/<name>` returns anchors for one repository and binds the
/// request to the canonical read-authorization path used by every other
/// repo-scoped read: the same `authorize_repo_read` helper, with the caller
/// identity attached. Missing repositories, quarantined mirrors, and signed
/// non-readers all collapse to the standard `404` (no existence oracle). The
/// unscoped listing is auth-only — the #121 contract — and does not admit
/// visibility filtering, which is the #136 stale-index class and explicitly
/// out of scope for this auth slice.
pub async fn list_anchors(
State(state): State<AppState>,
Query(q): Query<ListAnchorsQuery>,
auth: Option<Extension<crate::auth::AuthenticatedDid>>,
) -> Result<Json<serde_json::Value>> {
// The route's `optional_signature` layer is permissive (it admits unsigned
// legacy callers) so this in-handler check is the actual gate. A signed
// non-reader still passes this check and proceeds to the authz step below.
let caller = auth.as_ref().map(|e| e.0 .0.as_str());
if caller.is_none() {
return Err(AppError::Unauthorized(
"authentication required for anchor listing".into(),
));
}
// Clamp before the SQL query. A negative or non-numeric limit must not
// reach Postgres as `LIMIT -1` (which it rejects as a db error / 500) — the
// contract is the same default ceiling as the listing page itself.
let limit = q.limit.clamp(0, 200);
let anchors = if let Some(repo_slug) = q.repo.as_deref() {
// Parse the user-supplied "owner/name" through the same slug validator
// the sync path uses, so a malformed query is a 400, not a 500.
let (owner, name) = match crate::git::repo_store::validate_repo_slug(repo_slug) {
Ok(parts) => parts,
Err(e) => return Err(AppError::BadRequest(format!("invalid ?repo: {e}"))),
};
// Read gate. Returns `RepoNotFound` (→ 404) indistinguishably for
// missing repos, quarantined mirrors, and signed non-readers.
let (record, _rules) =
crate::api::authorize_repo_read(&state, owner, name, caller, "/").await?;
// Build the SQL filter from the canonical stored slug, NOT from the
// user-supplied `?repo=` string. Anchor rows are written as
// `{normalize_owner_key(owner_did)}/{name}` (the short form), so a
// request that passes authz with the full `did:key:…/name` form would
// match zero rows and return a false empty page. The gate already
// verified the repo is readable; `record.owner_did` is the canonical
// identity and `record.name` is the stored name.
let stored_slug = format!("{}/{}", normalize_owner_key(&record.owner_did), record.name);
state
.db
.list_arweave_anchors(Some(&stored_slug), limit)
.await?
} else {
// No scope → no repo-read decision. Auth-only.
state.db.list_arweave_anchors(None, limit).await?
};
let limit = q.limit.min(200);
// Bare `?` so connection-class sqlx failures downcast to `AppError::Db` and
// map to 503 `db_unavailable` (not 500 via `.map_err(AppError::Internal)`) (#251).
let anchors = state
.db
.list_arweave_anchors(q.repo.as_deref(), limit)
.await?;
Ok(Json(serde_json::json!({
"anchors": anchors,
@@ -106,7 +60,6 @@ mod closed_pool_tests {
.oneshot(
Request::builder()
.uri("/api/v1/arweave/anchors")
.extension(crate::auth::AuthenticatedDid("did:key:test".into()))
.body(axum::body::Body::empty())
.unwrap(),
)
+1 -10
View File
@@ -2133,15 +2133,7 @@ async fn gate_and_serve(
/// Returns all CIDs that have been pinned to the local IPFS node from git
/// objects received via push. Each entry includes the git SHA-256 hex, the
/// CIDv1 string, and the timestamp when it was pinned.
pub async fn list_pins(
State(state): State<AppState>,
auth: Option<Extension<crate::auth::AuthenticatedDid>>,
) -> Result<Json<serde_json::Value>> {
if auth.is_none() {
return Err(crate::error::AppError::Unauthorized(
"authentication required for pin listing".into(),
));
}
pub async fn list_pins(State(state): State<AppState>) -> Result<Json<serde_json::Value>> {
// Bare `?` so connection-class sqlx failures downcast to `AppError::Db` and
// map to 503 `db_unavailable` (not 500 via `.map_err(AppError::Internal)`) (#251).
let pins = state.db.list_pinned_cids().await?;
@@ -2434,7 +2426,6 @@ mod closed_pool_tests {
.oneshot(
Request::builder()
.uri("/api/v1/ipfs/pins")
.extension(crate::auth::AuthenticatedDid("did:key:test".into()))
.body(axum::body::Body::empty())
.unwrap(),
)
+18 -4
View File
@@ -80,15 +80,20 @@ pub(crate) fn did_matches(a: &str, b: &str) -> bool {
!ka.contains(':') && !kb.contains(':') && ka == kb
}
/// Client-facing denial shared by every repo-owner gate copy. `require_repo_owner`
/// renders it as `AppError::Forbidden`; a handler that emits its own
/// `(StatusCode, Json)` envelope instead of `AppError` (e.g.
/// `api::tasks::create_task`) must use this constant too, so two copies of one
/// gate cannot drift in observable output.
pub(crate) const REPO_OWNER_ONLY_MESSAGE: &str = "only the repo owner can perform this action";
/// 403 unless `caller` is the repo owner. Uses [`did_matches`] so the owner check
/// and the author check (close policy) share one normalization.
pub(crate) fn require_repo_owner(record: &RepoRecord, caller: &str) -> Result<()> {
if did_matches(caller, &record.owner_did) {
Ok(())
} else {
Err(AppError::Forbidden(
"only the repo owner can perform this action".into(),
))
Err(AppError::Forbidden(REPO_OWNER_ONLY_MESSAGE.into()))
}
}
@@ -242,6 +247,11 @@ mod authz_guard {
(events, "list_repo_events", "authorize_repo_read("),
// Bucket C — signer-self: the acting DID is matched/bound to auth.0
(tasks, "create_task", "did_matches("),
// #496: create_task is signer-self AND owner-when-repo-scoped — a
// repo_id naming a hosted repo admits tasks only from its owner.
// Both halves are pinned: the did_matches row guards the signer
// binding, this one the repo-ownership gate.
(tasks, "create_task", "require_repo_owner("),
(tasks, "claim_task", "did_matches("),
(tasks, "complete_task", "did_matches("),
(tasks, "fail_task", "did_matches("),
@@ -341,7 +351,11 @@ mod authz_guard {
(
"create_task",
"createTask",
&["require_signer(ctx)?", "did_matches("],
&[
"require_signer(ctx)?",
"did_matches(",
"require_repo_owner(",
],
),
(
"claim_task",
+4 -37
View File
@@ -3508,17 +3508,6 @@ pub struct ForkRepoRequest {
}
/// POST /api/v1/repos/:owner/:repo/fork
/// Argv for the fork's mirror clone, with `--` before the first positional (#374).
///
/// Both positionals here are server-derived paths rather than caller-supplied
/// URLs, so this is defence in depth rather than a reachable injection. It is
/// still the same argv contract as the other clone sites, and it is extracted for
/// the same reason: so the delimiter's placement is pinned by a test instead of
/// resting on review.
fn fork_clone_args<'a>(source: &'a str, dest: &'a str) -> [&'a str; 5] {
["clone", "--mirror", "--", source, dest]
}
pub async fn fork_repo(
State(state): State<AppState>,
Extension(auth): Extension<AuthenticatedDid>,
@@ -3604,10 +3593,12 @@ pub async fn fork_repo(
// Clone the source repo as a mirror
let output = std::process::Command::new("git")
.args(fork_clone_args(
.args([
"clone",
"--mirror",
source_path.to_str().unwrap_or(""),
disk_path.to_str().unwrap_or(""),
))
])
.output()
.map_err(|e| AppError::Git(format!("git clone --mirror failed: {e}")))?;
@@ -4074,30 +4065,6 @@ fn dedupe_canonical_repos(rows: Vec<(RepoRecord, i64)>) -> Vec<(RepoRecord, i64)
#[cfg(test)]
mod tests {
use super::*;
/// #374: the fork path builds its own `git clone --mirror` argv. Driven
/// through real git so a missing or misplaced `--` fails, matching the
/// coverage on the `gl clone`, `gl mirror`, and sync sinks.
#[test]
fn fork_clone_never_parses_the_source_as_a_git_option() {
let td = tempfile::TempDir::new().unwrap();
let dest = td.path().join("fork.git");
let injected = "--upload-pack=false";
let out = std::process::Command::new("git")
.env("LC_ALL", "C")
.args(fork_clone_args(injected, dest.to_str().unwrap()))
.output()
.unwrap();
let stderr = String::from_utf8_lossy(&out.stderr);
assert!(!out.status.success(), "an option-shaped source must fail");
assert!(
stderr.contains(&format!("repository '{injected}'")),
"git must name the source as the repository, not consume it as an option: {stderr}"
);
}
use crate::auth::caller_authorized_to_push;
use crate::error::AppError;
use gitlawb_core::identity::Keypair;
+92 -6
View File
@@ -30,6 +30,33 @@ fn forbidden(msg: &str) -> (StatusCode, Json<Value>) {
)
}
/// This module's error shape with an opaque body: the real error is logged
/// server-side and never serialized (#250), matching the envelope
/// `AppError::Db` renders. Also mirrors its status split: pool-class failures
/// are a retryable 503 `db_unavailable`, everything else the opaque 500
/// `db_error`, so a transient outage is not reported as permanent.
fn db_error(e: anyhow::Error) -> (StatusCode, Json<Value>) {
tracing::error!(error = %format!("{e:#}"), "task database error");
if let Some(sql) = e.chain().find_map(|c| c.downcast_ref::<sqlx::Error>()) {
if crate::error::db_unavailable(sql) {
return (
StatusCode::SERVICE_UNAVAILABLE,
Json(json!({
"error": crate::error::DB_UNAVAILABLE_CODE,
"message": crate::error::DB_UNAVAILABLE_MESSAGE,
})),
);
}
}
(
StatusCode::INTERNAL_SERVER_ERROR,
Json(json!({
"error": "db_error",
"message": crate::error::DB_ERROR_MESSAGE,
})),
)
}
// ── Request / response types ──────────────────────────────────────────────────
#[derive(Deserialize)]
@@ -101,6 +128,37 @@ pub async fn create_task(
if !crate::api::did_matches(&auth.0, &body.delegator_did) {
return Err(forbidden("delegator_did must be the authenticated signer"));
}
// #496: a caller-supplied repo_id must name a repo the caller owns. Without
// this, any signed caller can plant a task — payload and UCAN included —
// under a foreign repo id, where the named assignee can claim it. Resolve
// the id against hosted repos: a hosted, non-quarantined repo admits tasks
// only from its owner (403 otherwise). An id naming no hosted repo
// (unknown, or quarantined — which is hidden as if it did not exist, so
// 403ing it would confirm a real id) is stored verbatim as an opaque
// label: this is a write gate and does not bind an unresolved id to a
// repo. Task reads are caller-independent on this base (the list endpoints
// are not repo-scoped), before and after this change. The 403-vs-201 split
// between a hosted repo id and an unknown one is itself a one-bit oracle —
// a stranger holding a private repo's id learns it is hosted here — but
// denying foreign repos requires drawing exactly that line, and repo ids
// already surface via the task list on this base. Repo-less tasks are
// unaffected.
if let Some(repo_id) = body.repo_id.as_deref() {
let record = state.db.get_repo_by_id(repo_id).await.map_err(db_error)?;
if let Some(record) = record {
let quarantined = state
.db
.is_repo_quarantined(&record.id)
.await
.map_err(db_error)?;
if !quarantined && crate::api::require_repo_owner(&record, &auth.0).is_err() {
// Same denial text the GraphQL copy relays from
// `require_repo_owner`, so the two copies of this gate do not
// disagree in observable output.
return Err(forbidden(crate::api::REPO_OWNER_ONLY_MESSAGE));
}
}
}
let now = Utc::now().to_rfc3339();
let task = AgentTask {
id: Uuid::new_v4().to_string(),
@@ -117,12 +175,7 @@ pub async fn create_task(
updated_at: now,
deadline: body.deadline,
};
state.db.create_task(&task).await.map_err(|e| {
(
StatusCode::INTERNAL_SERVER_ERROR,
Json(json!({ "error": e.to_string() })),
)
})?;
state.db.create_task(&task).await.map_err(db_error)?;
Ok((StatusCode::CREATED, Json(task_to_json(&task))))
}
@@ -297,3 +350,36 @@ pub async fn fail_task(
});
Ok(Json(task_to_json(&task)))
}
#[cfg(test)]
mod tests {
use super::*;
/// The gate's DB helper must mirror `AppError::Db`: a pool-level failure is
/// the retryable 503 `db_unavailable`, a query fault the opaque 500.
#[test]
fn db_error_matches_app_error_status_split() {
let unavailable = db_error(anyhow::Error::from(sqlx::Error::PoolTimedOut));
assert_eq!(unavailable.0, StatusCode::SERVICE_UNAVAILABLE);
assert_eq!(unavailable.1 .0["error"], crate::error::DB_UNAVAILABLE_CODE);
assert_eq!(
unavailable.1 .0["message"],
crate::error::DB_UNAVAILABLE_MESSAGE
);
let query = db_error(anyhow::Error::from(sqlx::Error::Protocol(
"column \"machine_id\" does not exist".into(),
)));
assert_eq!(query.0, StatusCode::INTERNAL_SERVER_ERROR);
assert_eq!(query.1 .0["error"], "db_error");
assert_eq!(query.1 .0["message"], crate::error::DB_ERROR_MESSAGE);
assert!(!query.1 .0.to_string().contains("machine_id"));
}
/// `.context()` layers must not hide the sqlx error from the status split.
#[test]
fn db_error_sees_sqlx_through_context() {
let wrapped = anyhow::Error::from(sqlx::Error::PoolClosed).context("repo lookup failed");
assert_eq!(db_error(wrapped).0, StatusCode::SERVICE_UNAVAILABLE);
}
}
+1 -1
View File
@@ -101,7 +101,7 @@ pub const DB_ERROR_MESSAGE: &str = "a database error occurred";
/// Connection-level sqlx failures that mean the database is unreachable right
/// now (retryable, 503), as opposed to server-reported query errors.
fn db_unavailable(e: &sqlx::Error) -> bool {
pub(crate) fn db_unavailable(e: &sqlx::Error) -> bool {
matches!(
e,
sqlx::Error::PoolTimedOut
+220
View File
@@ -36,6 +36,33 @@ impl MutationRoot {
}
let delegator_did = caller.to_string();
let db = ctx.data_unchecked::<Arc<Db>>();
// #496: same write gate as the REST handler — a repo_id naming a
// hosted, non-quarantined repo admits tasks only from its owner, so a
// stranger cannot file under a foreign repo id. An id naming no hosted
// repo (unknown, or quarantined — hidden as if it did not exist) is
// stored verbatim as an opaque label; the gate does not bind an
// unresolved id to a repo. Task reads are caller-independent on this
// base (the tasks resolver is not repo-scoped), before and after this
// change. As in tasks.rs, the success-vs-denial split between a hosted
// repo id and an unknown one is itself a one-bit oracle — a stranger
// holding a private repo's id learns it is hosted here — but denying
// foreign repos requires drawing exactly that line.
if let Some(repo_id) = input.repo_id.as_deref() {
let record = db
.get_repo_by_id(repo_id)
.await
.map_err(crate::graphql::graphql_db_err)?;
if let Some(record) = record {
let quarantined = db
.is_repo_quarantined(&record.id)
.await
.map_err(crate::graphql::graphql_db_err)?;
if !quarantined {
crate::api::require_repo_owner(&record, caller)
.map_err(crate::graphql::graphql_app_err)?;
}
}
}
let now = Utc::now().to_rfc3339();
let task = AgentTask {
id: Uuid::new_v4().to_string(),
@@ -186,6 +213,22 @@ mod tests {
.join("; ")
}
/// The `id` scalar returned by a successful `createTask` mutation.
fn created_id(resp: &Response) -> String {
assert!(resp.errors.is_empty(), "graphql errors: {:?}", resp.errors);
let async_graphql::Value::Object(obj) = &resp.data else {
panic!("data not an object: {:?}", resp.data);
};
let async_graphql::Value::Object(task) = obj.get("createTask").expect("createTask key")
else {
panic!("createTask not an object");
};
let async_graphql::Value::String(id) = task.get("id").expect("id key") else {
panic!("id not a string");
};
id.clone()
}
/// N2: every GraphQL mutation requires a verified signer and binds the acting
/// DID to it. Unsigned is rejected; a signer other than the claimed actor is
/// rejected; the matching signer passes the auth gate.
@@ -353,4 +396,181 @@ mod tests {
errors(&resp)
);
}
/// #496 (GraphQL): createTask applies the same repo-ownership gate as the
/// REST handler — a stranger naming a hosted repo is rejected without
/// persisting anything, while the owner files. The quarantined and
/// unknown-id arms are pinned too, including that each accepted write
/// stores the supplied id verbatim, so this copy of the gate cannot regress
/// silently.
#[sqlx::test]
async fn create_task_rejects_foreign_repo_id(pool: PgPool) {
let state = crate::test_support::test_state(pool).await;
let owner = "did:key:zGQLTASKOWNERAAAAAAAAAAAAAAAAAAAAAAAAAA";
let stranger = "did:key:zGQLTASKSTRANGERBBBBBBBBBBBBBBBBBBBBBB";
let now = chrono::Utc::now();
let repo = crate::db::RepoRecord {
id: uuid::Uuid::new_v4().to_string(),
name: "gql-task-gate-repo".to_string(),
owner_did: owner.to_string(),
description: None,
is_public: true,
default_branch: "main".to_string(),
created_at: now,
updated_at: now,
disk_path: "/tmp/gql-task-gate-repo".to_string(),
forked_from: None,
machine_id: None,
};
state.db.create_repo(&repo).await.expect("seed repo");
let schema = state.graphql_schema.as_ref();
let q = |actor: &str| {
format!(
r#"mutation {{ createTask(delegatorDid: "{actor}", input: {{ kind: "build", capability: "repo:write", repoId: "{}" }}) {{ id }} }}"#,
repo.id
)
};
// Stranger signs as themselves (so the signer binding passes) but
// names the victim's repo → rejected by the ownership gate, leaking
// nothing about the repo.
let resp = schema
.execute(Request::new(q(stranger)).data(AuthenticatedDid(stranger.into())))
.await;
let errs = errors(&resp);
assert!(
errs.contains(crate::api::REPO_OWNER_ONLY_MESSAGE),
"a non-owner must not file under a foreign repo id (shared denial text): {errs}"
);
// The denial must not persist: no task row may carry the victim's
// repo id afterwards.
let stored = state
.db
.list_tasks(None, None, 50)
.await
.expect("list tasks");
assert!(
stored
.iter()
.all(|t| t.repo_id.as_deref() != Some(repo.id.as_str())),
"a denied write must not leave a task under the foreign repo id"
);
// The owner files under their own repo id.
let resp = schema
.execute(Request::new(q(owner)).data(AuthenticatedDid(owner.into())))
.await;
assert!(
errors(&resp).is_empty(),
"the owner should file against their repo: {}",
errors(&resp)
);
// Unknown repo ids stay accepted as opaque labels.
let q_unknown = format!(
r#"mutation {{ createTask(delegatorDid: "{stranger}", input: {{ kind: "build", capability: "repo:write", repoId: "no-such-repo-id" }}) {{ id }} }}"#
);
let resp = schema
.execute(Request::new(q_unknown).data(AuthenticatedDid(stranger.into())))
.await;
assert!(
errors(&resp).is_empty(),
"an id naming no hosted repo stays an opaque label: {}",
errors(&resp)
);
// Read back the row: the unresolved id must be stored verbatim, not
// dropped or rewritten to a repo it never named.
let stored = state
.db
.get_task(&created_id(&resp))
.await
.expect("get task")
.expect("task must be stored");
assert_eq!(
stored.repo_id.as_deref(),
Some("no-such-repo-id"),
"an unresolved id must be stored verbatim as a label"
);
// A quarantined repo id is treated as unknown (accepted, never a 403
// that would confirm the id names a real repo). This pins the
// `!quarantined` arm on this copy of the gate.
state
.db
.set_repo_quarantine(&repo.id, true)
.await
.expect("quarantine");
let resp = schema
.execute(Request::new(q(stranger)).data(AuthenticatedDid(stranger.into())))
.await;
assert!(
errors(&resp).is_empty(),
"a quarantined repo id must not 403 (existence oracle): {}",
errors(&resp)
);
// Read back the row: the quarantined id is stored verbatim as a label
// too, so the accepted write is not silently dropped.
let stored = state
.db
.get_task(&created_id(&resp))
.await
.expect("get task")
.expect("task must be stored");
assert_eq!(
stored.repo_id.as_deref(),
Some(repo.id.as_str()),
"a quarantined id must be stored verbatim as a label"
);
}
/// #496 (GraphQL): a repo-lookup fault in createTask's gate must stay
/// opaque. Dropping a column `get_repo_by_id` selects faults that lookup;
/// the resolver must return the fixed DB message and leak no schema text
/// (#250), as `create_task_db_error_message_is_opaque` pins for the
/// agent_tasks fault.
#[sqlx::test]
async fn create_task_gate_repo_lookup_fault_is_opaque(pool: PgPool) {
let state = crate::test_support::test_state(pool.clone()).await;
let owner = "did:key:zGQLTASKFAULTOWNERAAAAAAAAAAAAAAAAAAAAAAAA";
let now = chrono::Utc::now();
let repo = crate::db::RepoRecord {
id: uuid::Uuid::new_v4().to_string(),
name: "gql-task-gate-fault-repo".to_string(),
owner_did: owner.to_string(),
description: None,
is_public: true,
default_branch: "main".to_string(),
created_at: now,
updated_at: now,
disk_path: "/tmp/gql-task-gate-fault-repo".to_string(),
forked_from: None,
machine_id: None,
};
state.db.create_repo(&repo).await.expect("seed repo");
sqlx::query("ALTER TABLE repos DROP COLUMN machine_id")
.execute(&pool)
.await
.expect("drop machine_id");
let q = format!(
r#"mutation {{ createTask(delegatorDid: "{owner}", input: {{ kind: "build", capability: "repo:write", repoId: "{}" }}) {{ id }} }}"#,
repo.id
);
let resp = state
.graphql_schema
.execute(Request::new(&q).data(AuthenticatedDid(owner.into())))
.await;
let errs = errors(&resp);
assert!(
errs.contains(crate::graphql::GRAPHQL_DB_ERROR_MESSAGE),
"gate sqlx fault must be opaque: {errs}"
);
assert!(
!errs.contains("machine_id") && !errs.contains("column"),
"schema text leaked through the gate: {errs}"
);
}
}
+17 -708
View File
@@ -237,62 +237,35 @@ pub fn build_router(state: AppState) -> Router {
.layer(axum::Extension(push_limiter));
// ── IPFS content-addressed retrieval and pin listing ──────────────────
// Two independent sub-routers, then merged. They share a URL prefix family
// but have separate rate-limit policies and must not share a bucket.
//
// `/ipfs/{cid}` (CID resolver): carries `optional_signature` so `get_by_cid`
// sees the caller identity and can apply per-repo visibility (#110); anon
// callers stay anonymous and still read genuinely public content. The
// per-IP flood brake is layered on because the resolver is anon-reachable
// and each request can drive a full-history git walk — the brake is the
// outermost layer (rejects a flood before the walk-admission work), mirroring
// the push/create routers. The `IpRateLimiter` extension MUST be attached
// or `rate_limit_by_ip` is a silent no-op.
//
// `/api/v1/ipfs/pins` (pin listing): now carries `optional_signature` only
// (#121). The handler rejects requests without a verified `AuthenticatedDid`
// with 401. It does NOT carry the CID flood brake — `list_pins` is a single
// `list_pinned_cids()` call, no walk, and routing pins through the resolver's
// bucket would let `/ipfs/{cid}` traffic exhaust the bucket and 429 the
// pins endpoint, or let signed pin polling exhaust the bucket for legitimate
// CID reads. The two surfaces have separate availability contracts.
//
// Both sub-routers are built first with their own layer sets, then merged.
// This is the structure the prior routing guidance called for and the
// earlier 429 test for `/ipfs/{cid}` (test_support.rs) assumes.
// `/ipfs/{cid}` carries `optional_signature` so `get_by_cid` sees the caller
// identity and can apply per-repo visibility (#110); anonymous callers stay
// anonymous and still read genuinely public content. `/api/v1/ipfs/pins`
// stays unsigned — gating the pin index is tracked separately (#121).
// `/ipfs/{cid}` also carries a per-IP flood brake: it is anon-reachable and each
// request can drive a full-history git walk, so the per-IP rate limiter is the
// outermost layer (rejects a flood before the walk-admission work), mirroring the
// push/create routers. The extension MUST be attached or rate_limit_by_ip is a
// silent no-op. `/api/v1/ipfs/pins` (no walk) is merged in unbraked, as before.
let ipfs_limiter = rate_limit::IpRateLimiter {
limiter: state.ipfs_rate_limiter.clone(),
trust: state.push_limiter_trust,
};
let ipfs_cid_routes = Router::new()
let ipfs_routes = Router::new()
.route("/ipfs/{cid}", get(ipfs::get_by_cid))
.layer(middleware::from_fn_with_state(
auth::SignatureBodyLimit(SIGNED_BODY_LIMIT),
auth::optional_signature,
))
.layer(middleware::from_fn(rate_limit::rate_limit_by_ip))
.layer(axum::Extension(ipfs_limiter));
let ipfs_pins_routes = Router::new()
.route("/api/v1/ipfs/pins", get(ipfs::list_pins))
.layer(middleware::from_fn_with_state(
auth::SignatureBodyLimit(SIGNED_BODY_LIMIT),
auth::optional_signature,
));
let ipfs_routes = ipfs_cid_routes.merge(ipfs_pins_routes);
.layer(axum::Extension(ipfs_limiter))
.merge(Router::new().route("/api/v1/ipfs/pins", get(ipfs::list_pins)));
// ── Arweave permanent anchors ──────────────────────────────────────────
// `list_anchors` rejects callers without a verified `AuthenticatedDid`, so
// unsigned enumeration is denied. The same `optional_signature` layer used
// on the other read surfaces is applied here, closing the anonymous
// anchor-listing gap alongside `/api/v1/ipfs/pins`. The verify endpoint
// and its probe are deferred to the vertical slice with the uploader and
// a real provider contract.
let arweave_routes = Router::new()
.route("/api/v1/arweave/anchors", get(arweave::list_anchors))
.layer(middleware::from_fn_with_state(
auth::SignatureBodyLimit(SIGNED_BODY_LIMIT),
auth::optional_signature,
));
// List endpoint only (public; issue #134 tracks surfacing
// visibility rules on list). The verify endpoint and its probe
// are deferred to the vertical slice with the uploader and a
// real provider contract (reviewer 2, #26 split 2/4 round 5).
let arweave_routes = Router::new().route("/api/v1/arweave/anchors", get(arweave::list_anchors));
// ── Bounty routes (write — require HTTP Signature) ─────────────────
let bounty_write_routes = add_auth_layers(
@@ -699,667 +672,3 @@ async fn p2p_info(State(state): State<AppState>) -> Json<serde_json::Value> {
None => Json(json!({ "enabled": false })),
}
}
#[cfg(test)]
mod tests {
use super::*;
use axum::body::Body;
use axum::http::{Request, StatusCode};
use sqlx::PgPool;
use tower::ServiceExt;
use crate::db::RepoRecord;
use crate::test_support::test_state;
/// Regression: anonymous callers must not see the pin/anchor index (#121, #134).
#[sqlx::test]
async fn unsigned_get_pins_and_anchors_is_401_through_build_router(pool: PgPool) {
let state = test_state(pool).await;
// Seed identifiable rows so the denial oracle proves the 401 body omits
// them: a status-only check would stay green if a later change served
// the listing before the auth layer rejected.
state
.db
.record_pinned_cid("seeded-pin-oid", "bafyPIN-SECRET-DO-NOT-LEAK", None)
.await
.expect("seed pin");
let owner_did = "did:key:zSEEDOWNERAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA";
let repo = seed_repo_inline(owner_did, "seeded-repo");
state.db.create_repo(&repo).await.expect("seed repo");
state
.db
.record_arweave_anchor(&crate::db::RecordAnchorInput {
repo: "zSEEDOWNERAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA/seeded-repo",
owner_did,
ref_name: "refs/heads/secret",
old_sha: "0".repeat(64).as_str(),
new_sha: "1".repeat(64).as_str(),
cid: Some("bafytest"),
irys_tx_id: "irys-secret-tx-DO-NOT-LEAK",
arweave_url: "https://arweave.net/secret-tx",
node_did: "did:key:zNODE",
})
.await
.expect("seed anchor");
let router = build_router(state);
let pins = Request::builder()
.method("GET")
.uri("/api/v1/ipfs/pins?limit=50")
.body(Body::empty())
.unwrap();
let pins_resp = router.clone().oneshot(pins).await.unwrap();
assert_eq!(
pins_resp.status(),
StatusCode::UNAUTHORIZED,
"anonymous pin listing must be rejected"
);
let bytes = axum::body::to_bytes(pins_resp.into_body(), usize::MAX)
.await
.unwrap();
let body = String::from_utf8_lossy(&bytes);
assert!(
!body.contains("bafyPIN-SECRET-DO-NOT-LEAK"),
"the 401 body must not leak the seeded pin cid; body was: {body}"
);
let anchors = Request::builder()
.method("GET")
.uri("/api/v1/arweave/anchors?limit=50")
.body(Body::empty())
.unwrap();
let anchors_resp = router.oneshot(anchors).await.unwrap();
assert_eq!(
anchors_resp.status(),
StatusCode::UNAUTHORIZED,
"anonymous anchors listing must be rejected"
);
let bytes = axum::body::to_bytes(anchors_resp.into_body(), usize::MAX)
.await
.unwrap();
let body = String::from_utf8_lossy(&bytes);
assert!(
!body.contains("irys-secret-tx-DO-NOT-LEAK"),
"the 401 body must not leak the anchor's irys tx id; body was: {body}"
);
}
/// Regression: a real RFC-9421 signature produced exactly as `gl` does — built
/// with `gitlawb_core::http_sig::sign_request` over a GET, headers attached,
/// and sent through the actual `build_router` — is verified by the
/// `optional_signature` layer that wraps the pin/anchor routes, and the
/// handler returns 200. Pairs with the anonymous-denial test above; one
/// proves headers are required, the other proves a valid header is honored.
/// Without this test the unsigned-denial test would stay green even if the
/// `optional_signature` layer were never wired onto these routes, because
/// signed and unsigned requests would fail identically (#134 review).
#[sqlx::test]
async fn signed_get_pins_and_anchors_succeeds_through_build_router(pool: PgPool) {
use gitlawb_core::http_sig::sign_request;
use gitlawb_core::identity::Keypair;
let state = test_state(pool).await;
let router = build_router(state);
let kp = Keypair::generate();
let pins_path = "/api/v1/ipfs/pins";
let signed = sign_request(&kp, "GET", pins_path, b"");
let pins = Request::builder()
.method("GET")
.uri(pins_path)
.header("content-digest", signed.content_digest)
.header("signature-input", signed.signature_input)
.header("signature", signed.signature)
.body(Body::empty())
.unwrap();
let pins_resp = router.clone().oneshot(pins).await.unwrap();
assert_eq!(
pins_resp.status(),
StatusCode::OK,
"a valid signature on /api/v1/ipfs/pins must be honored through build_router"
);
let anchors_path = "/api/v1/arweave/anchors";
let signed = sign_request(&kp, "GET", anchors_path, b"");
let anchors = Request::builder()
.method("GET")
.uri(anchors_path)
.header("content-digest", signed.content_digest)
.header("signature-input", signed.signature_input)
.header("signature", signed.signature)
.body(Body::empty())
.unwrap();
let anchors_resp = router.oneshot(anchors).await.unwrap();
assert_eq!(
anchors_resp.status(),
StatusCode::OK,
"a valid signature on /api/v1/arweave/anchors must be honored through build_router"
);
}
/// Companion to the two regressions above: a request that *carries* signature
/// headers but whose signature does not verify (here, garbled) must be denied
/// with 401, not silently treated as anonymous and re-checked by the handler.
/// This pins the failure mode of the `optional_signature` layer: when the
/// caller claims to be signed, the layer must commit to verifying — there is
/// no fall-through path that lets a bad signature bypass auth.
#[sqlx::test]
async fn malformed_signature_on_pins_is_401_through_build_router(pool: PgPool) {
use gitlawb_core::http_sig::sign_request;
use gitlawb_core::identity::Keypair;
let state = test_state(pool).await;
let router = build_router(state);
let kp = Keypair::generate();
let path = "/api/v1/ipfs/pins";
let mut signed = sign_request(&kp, "GET", path, b"");
// Flip a character well inside the signature value (base64) so the header
// still parses but does not verify against the key.
let mut tampered = signed.signature.clone();
let mid = tampered.len() / 2;
let flipped = if tampered.as_bytes()[mid] == b'A' {
'B'
} else {
'A'
};
tampered.replace_range(mid..mid + 1, &flipped.to_string());
signed.signature = tampered;
let req = Request::builder()
.method("GET")
.uri(path)
.header("content-digest", signed.content_digest)
.header("signature-input", signed.signature_input)
.header("signature", signed.signature)
.body(Body::empty())
.unwrap();
let resp = router.oneshot(req).await.unwrap();
assert_eq!(
resp.status(),
StatusCode::UNAUTHORIZED,
"a malformed signature must be rejected by the auth layer, not silently accepted"
);
}
/// The same malformed-signature rejection must hold on the anchors route,
/// which carries its own `optional_signature` layer beside pins: a later
/// edit that dropped the layer here (but not on pins) would otherwise stay
/// green.
#[sqlx::test]
async fn malformed_signature_on_anchors_is_401_through_build_router(pool: PgPool) {
use gitlawb_core::http_sig::sign_request;
use gitlawb_core::identity::Keypair;
let state = test_state(pool).await;
let router = build_router(state);
let kp = Keypair::generate();
let path = "/api/v1/arweave/anchors";
let mut signed = sign_request(&kp, "GET", path, b"");
let mut tampered = signed.signature.clone();
let mid = tampered.len() / 2;
let flipped = if tampered.as_bytes()[mid] == b'A' {
'B'
} else {
'A'
};
tampered.replace_range(mid..mid + 1, &flipped.to_string());
signed.signature = tampered;
let req = Request::builder()
.method("GET")
.uri(path)
.header("content-digest", signed.content_digest)
.header("signature-input", signed.signature_input)
.header("signature", signed.signature)
.body(Body::empty())
.unwrap();
let resp = router.oneshot(req).await.unwrap();
assert_eq!(
resp.status(),
StatusCode::UNAUTHORIZED,
"a malformed signature must be rejected by the auth layer, not silently accepted"
);
}
// ── Scoped anchor contract (P1 follow-up: ?repo= must authorize_repo_read) ──
//
// The follow-up review (after the auth-layer wiring landed) found that a
// signed but unauthorized caller could still obtain scoped anchor metadata
// because the `?repo=` branch handed the user-supplied string straight to
// the SQL filter. These tests exercise the full production contract end to
// end: real RFC-9421 signature → `optional_signature` layer →
// `authorize_repo_read` → SQL. They fail closed if the authz call is moved
// after the query or removed entirely.
/// Inline repo seed for the scoped-anchor tests. Mirrors the shape in
/// `test_support::tests::seed_repo` without taking a cross-module private
/// helper as a dependency.
fn seed_repo_inline(owner_did: &str, name: &str) -> RepoRecord {
let now = chrono::Utc::now();
RepoRecord {
id: uuid::Uuid::new_v4().to_string(),
name: name.to_string(),
owner_did: owner_did.to_string(),
description: None,
is_public: true,
default_branch: "main".to_string(),
created_at: now,
updated_at: now,
disk_path: format!("/tmp/{name}"),
forked_from: None,
machine_id: None,
}
}
/// Unsigned scoped anchor request → 401, identical to the global anchor
/// 401 test. Proves the auth layer fires before any scope decision (no
/// existence oracle via the `?repo=` path either).
#[sqlx::test]
async fn unsigned_scoped_anchors_is_401_through_build_router(pool: PgPool) {
let state = test_state(pool).await;
// Seed an anchor under a repo the request claims to scope to, so the
// denial oracle proves the 401 body omits it rather than merely
// returning the right status over an empty table.
let owner_did = "did:key:zSCOPEDAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA";
let repo = seed_repo_inline(owner_did, "priv");
state.db.create_repo(&repo).await.expect("seed repo");
state
.db
.record_arweave_anchor(&crate::db::RecordAnchorInput {
repo: "zSCOPEDAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA/priv",
owner_did,
ref_name: "refs/heads/secret",
old_sha: "0".repeat(64).as_str(),
new_sha: "1".repeat(64).as_str(),
cid: Some("bafytest"),
irys_tx_id: "irys-scoped-secret-DO-NOT-LEAK",
arweave_url: "https://arweave.net/scoped-secret",
node_did: "did:key:zNODE",
})
.await
.expect("seed anchor");
let router = build_router(state);
let resp = router
.oneshot(
Request::builder()
.method("GET")
.uri("/api/v1/arweave/anchors?repo=did:key:zSCOPED%2Fpriv")
.body(Body::empty())
.unwrap(),
)
.await
.unwrap();
assert_eq!(
resp.status(),
StatusCode::UNAUTHORIZED,
"unsigned scoped anchor request must be 401, before any scope lookup"
);
let bytes = axum::body::to_bytes(resp.into_body(), usize::MAX)
.await
.unwrap();
let body = String::from_utf8_lossy(&bytes);
assert!(
!body.contains("irys-scoped-secret-DO-NOT-LEAK"),
"the 401 body must not leak the anchor's irys tx id; body was: {body}"
);
}
/// Signed owner on a private repo → 200, anchor metadata returned. Mirrors
/// the existing `list_webhooks_accepts_a_real_gl_signature_e2e` shape: real
/// signature, real middleware, real `authorize_repo_read`.
#[sqlx::test]
async fn signed_scoped_anchors_owner_succeeds_through_build_router(pool: PgPool) {
use gitlawb_core::http_sig::sign_request;
use gitlawb_core::identity::Keypair;
let kp = Keypair::generate();
let owner_did = kp.did().to_string();
let state = test_state(pool).await;
let mut repo = seed_repo_inline(&owner_did, "scoped-priv");
repo.is_public = false;
state.db.create_repo(&repo).await.expect("seed repo");
let short = owner_did.split(':').next_back().unwrap().to_string();
state
.db
.record_arweave_anchor(&crate::db::RecordAnchorInput {
repo: &format!("{short}/scoped-priv"),
owner_did: &owner_did,
ref_name: "refs/heads/main",
old_sha: "0".repeat(64).as_str(),
new_sha: "1".repeat(64).as_str(),
cid: Some("bafytest"),
irys_tx_id: "irys-owner-tx",
arweave_url: "https://arweave.net/owner-tx",
node_did: "did:key:zNODE",
})
.await
.expect("seed anchor");
let path = format!("/api/v1/arweave/anchors?repo={short}/scoped-priv");
let signed = sign_request(&kp, "GET", &path, b"");
let req = Request::builder()
.method("GET")
.uri(&path)
.header("content-digest", signed.content_digest)
.header("signature-input", signed.signature_input)
.header("signature", signed.signature)
.body(Body::empty())
.unwrap();
let router = build_router(state);
let resp = router.oneshot(req).await.unwrap();
assert_eq!(
resp.status(),
StatusCode::OK,
"the owner of a private repo must see their scoped anchors"
);
let bytes = axum::body::to_bytes(resp.into_body(), usize::MAX)
.await
.unwrap();
let body = String::from_utf8_lossy(&bytes);
assert!(
body.contains("irys-owner-tx"),
"owner must see the anchor's irys tx id; body was: {body}"
);
// Owner must see the ref name + new SHA so this is not just a count oracle.
assert!(
body.contains("refs/heads/main"),
"owner must see the ref name; body was: {body}"
);
// Sanity: a second test would need a different repo name to avoid
// colliding on `did:key:zSCOPED/scoped-priv` in the anchors table.
// Distinct repo names per test keep the rows queryable in isolation.
let _ = repo;
}
/// #121 R3: the SQL filter must use the canonical stored slug, not the
/// user-supplied `?repo=` string. Anchor rows are stored as
/// `{normalize_owner_key(owner_did)}/{name}` (the short form). Authz
/// passes for the full-DID form, but a literal `WHERE repo=$1` against
/// the full DID would match zero rows and return a false empty page,
/// breaking callers that legitimately use the full `did:key:…/name`
/// form in `?repo=`. RED before the fix: handler built the filter from
/// the raw `?repo=` string, so this query returned `anchors: []`.
#[sqlx::test]
async fn signed_scoped_anchors_full_did_form_matches_stored_slug_through_build_router(
pool: PgPool,
) {
use gitlawb_core::http_sig::sign_request;
use gitlawb_core::identity::Keypair;
let kp = Keypair::generate();
let owner_did = kp.did().to_string();
let state = test_state(pool).await;
let mut repo = seed_repo_inline(&owner_did, "scoped-did-form");
repo.is_public = false;
state.db.create_repo(&repo).await.expect("seed repo");
// Use the same slug-construction the writer uses
// (`db::normalize_owner_key`) so the test reader and the production
// writer can't drift if a future change moves the slug off the
// short-form. P3 (reviewer-3): the previous `split(':').next_back()`
// hand-rolled a third convention that agreed with the writer for
// `did:key` owners and diverged for every other method.
let short = crate::db::normalize_owner_key(&owner_did).to_string();
state
.db
.record_arweave_anchor(&crate::db::RecordAnchorInput {
repo: &format!("{short}/scoped-did-form"),
owner_did: &owner_did,
ref_name: "refs/heads/main",
old_sha: "0".repeat(64).as_str(),
new_sha: "1".repeat(64).as_str(),
cid: Some("bafytest"),
irys_tx_id: "irys-did-form-tx",
arweave_url: "https://arweave.net/did-form-tx",
node_did: "did:key:zNODE",
})
.await
.expect("seed anchor");
// P2 (reviewer-3): the previous suite only proved the authorized
// row is present. A correct filter must ALSO prove that anchors
// for OTHER repos do not leak into the response — the failure
// mode of the original bug was a cross-repo leak, not a
// fail-safe empty page. Seed a second repo (also under the
// same owner, so the authz test stays scoped) with its own
// irys_tx_id and assert it is absent from the body.
let other_owner = {
let kp2 = Keypair::generate();
kp2.did().to_string()
};
let mut other_repo = seed_repo_inline(&other_owner, "other-repo");
other_repo.is_public = true;
state
.db
.create_repo(&other_repo)
.await
.expect("seed other repo");
state
.db
.record_arweave_anchor(&crate::db::RecordAnchorInput {
repo: &format!(
"{}/other-repo",
crate::db::normalize_owner_key(&other_owner)
),
owner_did: &other_owner,
ref_name: "refs/heads/main",
old_sha: "0".repeat(64).as_str(),
new_sha: "2".repeat(64).as_str(),
cid: Some("bafyother"),
irys_tx_id: "irys-other-repo-tx",
arweave_url: "https://arweave.net/other-tx",
node_did: "did:key:zNODE",
})
.await
.expect("seed other anchor");
// The caller passes the FULL DID form in ?repo=. validate_repo_slug
// accepts it, authorize_repo_read resolves it, and the handler MUST
// then translate to the canonical stored slug (short form) before
// running the SQL — otherwise this returns 200 with anchors: [].
let path = format!("/api/v1/arweave/anchors?repo={owner_did}/scoped-did-form");
let signed = sign_request(&kp, "GET", &path, b"");
let req = Request::builder()
.method("GET")
.uri(&path)
.header("content-digest", signed.content_digest)
.header("signature-input", signed.signature_input)
.header("signature", signed.signature)
.body(Body::empty())
.unwrap();
let router = build_router(state);
let resp = router.oneshot(req).await.unwrap();
assert_eq!(
resp.status(),
StatusCode::OK,
"authz passed via the full DID form, so the response must be 200"
);
let bytes = axum::body::to_bytes(resp.into_body(), usize::MAX)
.await
.unwrap();
let body = String::from_utf8_lossy(&bytes);
assert!(
body.contains("irys-did-form-tx"),
"the SQL filter must use the stored short slug, not the full DID — \
a false-empty page would break callers that pass ?repo=did:key:…/name. \
body was: {body}"
);
assert!(
!body.contains("irys-other-repo-tx"),
"the scoped anchor filter must exclude other repos' anchors — \
a cross-repo leak would expose metadata of repos the caller \
did not authorize. body was: {body}"
);
let _ = repo;
}
/// Signed non-reader on a private repo → 404, anchor metadata MUST NOT
/// leak. This is the test that catches the "auth-but-no-authz" bug if
/// the gate is moved after the SQL query or removed entirely. The 404
/// is the standard `repo_not_found` shape — indistinguishable from the
/// missing-repo case below.
#[sqlx::test]
async fn signed_scoped_anchors_non_reader_is_404_no_leak_through_build_router(pool: PgPool) {
use gitlawb_core::http_sig::sign_request;
use gitlawb_core::identity::Keypair;
let owner_kp = Keypair::generate();
let stranger_kp = Keypair::generate();
let owner_did = owner_kp.did().to_string();
let stranger_did = stranger_kp.did().to_string();
let state = test_state(pool).await;
let mut repo = seed_repo_inline(&owner_did, "scoped-priv-nr");
repo.is_public = false;
state.db.create_repo(&repo).await.expect("seed repo");
let short_owner = owner_did.split(':').next_back().unwrap().to_string();
state
.db
.record_arweave_anchor(&crate::db::RecordAnchorInput {
repo: &format!("{short_owner}/scoped-priv-nr"),
owner_did: &owner_did,
ref_name: "refs/heads/secret",
old_sha: "2".repeat(64).as_str(),
new_sha: "3".repeat(64).as_str(),
cid: Some("bafytest"),
irys_tx_id: "irys-secret-tx-DO-NOT-LEAK",
arweave_url: "https://arweave.net/secret-tx",
node_did: "did:key:zNODE",
})
.await
.expect("seed anchor");
let _ = stranger_did; // signature carries the DID; this is just documentation
let path = format!("/api/v1/arweave/anchors?repo={short_owner}/scoped-priv-nr");
let signed = sign_request(&stranger_kp, "GET", &path, b"");
let req = Request::builder()
.method("GET")
.uri(&path)
.header("content-digest", signed.content_digest)
.header("signature-input", signed.signature_input)
.header("signature", signed.signature)
.body(Body::empty())
.unwrap();
let router = build_router(state);
let resp = router.oneshot(req).await.unwrap();
assert_eq!(
resp.status(),
StatusCode::NOT_FOUND,
"a signed non-reader must be 404 on a private repo's anchors"
);
let bytes = axum::body::to_bytes(resp.into_body(), usize::MAX)
.await
.unwrap();
let body = String::from_utf8_lossy(&bytes);
assert!(
!body.contains("irys-secret-tx-DO-NOT-LEAK"),
"the 404 body must not leak the anchor's irys tx id; body was: {body}"
);
assert!(
!body.contains("refs/heads/secret"),
"the 404 body must not leak the ref name; body was: {body}"
);
let v: serde_json::Value = serde_json::from_slice(&bytes).expect("json body");
assert_eq!(
v["error"], "repo_not_found",
"non-reader denial must carry the same error code as a missing repo"
);
}
/// Signed caller on a missing repo → 404, same shape as the non-reader
/// case. This is the indistinguishability half: a probe cannot tell
/// "private" from "absent" from the response.
#[sqlx::test]
async fn signed_scoped_anchors_missing_repo_is_404_through_build_router(pool: PgPool) {
use gitlawb_core::http_sig::sign_request;
use gitlawb_core::identity::Keypair;
let kp = Keypair::generate();
let state = test_state(pool).await;
let short = kp
.did()
.to_string()
.split(':')
.next_back()
.unwrap()
.to_string();
let path = format!("/api/v1/arweave/anchors?repo={short}/does-not-exist");
let signed = sign_request(&kp, "GET", &path, b"");
let req = Request::builder()
.method("GET")
.uri(&path)
.header("content-digest", signed.content_digest)
.header("signature-input", signed.signature_input)
.header("signature", signed.signature)
.body(Body::empty())
.unwrap();
let router = build_router(state);
let resp = router.oneshot(req).await.unwrap();
assert_eq!(
resp.status(),
StatusCode::NOT_FOUND,
"a missing repo must 404 indistinguishably from a non-readable private repo"
);
let bytes = axum::body::to_bytes(resp.into_body(), usize::MAX)
.await
.unwrap();
let v: serde_json::Value = serde_json::from_slice(&bytes).expect("json body");
assert_eq!(
v["error"], "repo_not_found",
"the 404 body must carry the standard repo_not_found error code"
);
}
/// `?limit=-1` must not crash as `LIMIT -1` (Postgres 500). It clamps to
/// zero and returns 200 with an empty list — the same shape as a valid
/// listing that happens to have no rows in the configured range.
#[sqlx::test]
async fn signed_anchors_negative_limit_clamps_to_zero_through_build_router(pool: PgPool) {
use gitlawb_core::http_sig::sign_request;
use gitlawb_core::identity::Keypair;
let kp = Keypair::generate();
let state = test_state(pool).await;
let path = "/api/v1/arweave/anchors?limit=-1";
let signed = sign_request(&kp, "GET", path, b"");
let req = Request::builder()
.method("GET")
.uri(path)
.header("content-digest", signed.content_digest)
.header("signature-input", signed.signature_input)
.header("signature", signed.signature)
.body(Body::empty())
.unwrap();
let router = build_router(state);
let resp = router.oneshot(req).await.unwrap();
assert_eq!(
resp.status(),
StatusCode::OK,
"?limit=-1 must clamp, not 500"
);
let bytes = axum::body::to_bytes(resp.into_body(), usize::MAX)
.await
.unwrap();
let v: serde_json::Value = serde_json::from_slice(&bytes).expect("json body");
assert_eq!(v["count"], 0, "clamped limit yields an empty list");
assert_eq!(v["anchors"].as_array().map(|a| a.len()), Some(0));
}
}
+1 -81
View File
@@ -701,7 +701,6 @@ async fn clone_repo(remote_url: &str, local_path: &Path, mode: MirrorMode) -> an
if mode == MirrorMode::Promisor {
args.push("--filter=blob:limit=10g");
}
args.push("--");
args.push(remote_url);
args.push(local_str);
@@ -730,10 +729,7 @@ async fn clone_repo(remote_url: &str, local_path: &Path, mode: MirrorMode) -> an
async fn fetch_repo(local_path: &Path, remote_url: &str, mode: MirrorMode) -> anyhow::Result<()> {
let local_str = local_path.to_str().unwrap_or(".");
git_run(&[
"-C", local_str, "remote", "set-url", "origin", "--", remote_url,
])
.await?;
git_run(&["-C", local_str, "remote", "set-url", "origin", remote_url]).await?;
match mode {
MirrorMode::Promisor => {
@@ -1010,82 +1006,6 @@ mod tests {
assert_eq!(probe, PromisorProbe::NotPromisor);
}
/// #374: `clone_repo` interpolates the peer's origin URL into a `git
/// clone --mirror` argument list. Without a `--` delimiter git parses a
/// remote beginning with `-` as an option instead of a repository.
///
/// The delimiter is what forces the same string to be a repository, and
/// git says so in its own words: it reports the whole argument as a
/// repository it cannot find. Undelimited, git consumes it as an option
/// and fails against the *destination* instead (`fatal: repository '<dest>' does not exist`),
/// never naming the injected string — which is why this assertion is RED
/// before the fix and GREEN after.
///
/// The payload is deliberately free of `:` and spaces: a colon would make
/// git read the argument as an ssh-style `host:path` URL and report a
/// hostname rather than a repository, which is a different code path.
#[tokio::test]
async fn clone_never_parses_a_remote_as_a_git_option() {
let td = TempDir::new().unwrap();
let dest = td.path().join("mirror.git");
let injected = "--upload-pack=false";
let err = clone_repo(injected, &dest, MirrorMode::Plain)
.await
.expect_err("a remote that is not a repository must fail the clone")
.to_string();
assert!(
err.contains(injected),
"git must report the argument as a repository, not consume it as an option: {err}"
);
}
/// #374: `fetch_repo` interpolates the peer's origin URL into
/// `git remote set-url`, a second argv construction with the same contract as
/// the clone. It needs its own proof: the clone test cannot reach this path.
///
/// The assertion is on stored state rather than on the error string, and that
/// is deliberate. `git_run` formats its failure as `git {args:?} failed:
/// {stderr}`, so the injected value is in the message via the debug-printed
/// argv whether or not the delimiter is present — asserting on containment
/// would pass with `--` deleted. Delimited, `set-url` succeeds and stores the
/// value verbatim; undelimited, git exits 129 with `unknown option` and leaves
/// the previous URL in place, so this goes red without the fix.
///
/// The fetch that follows the rewrite fails, because the stored URL is not a
/// repository. That is expected and ignored: the property under test is what
/// `set-url` wrote, not whether the subsequent fetch could succeed.
#[tokio::test]
async fn fetch_never_parses_a_remote_as_a_git_option() {
let td = TempDir::new().unwrap();
let local = td.path().join("mirror.git");
let local_str = local.to_str().unwrap();
let placeholder = "http://example.invalid/x.git";
assert!(Command::new("git")
.args(["init", "-q", "--bare", local_str])
.status()
.unwrap()
.success());
assert!(Command::new("git")
.args(["-C", local_str, "remote", "add", "origin", placeholder])
.status()
.unwrap()
.success());
let injected = "--upload-pack=false";
let _ = fetch_repo(&local, injected, MirrorMode::Plain).await;
assert_eq!(
git_config_get(local_str, "remote.origin.url")
.await
.as_deref(),
Some(injected),
"set-url must store an option-shaped remote verbatim, not reject it as an option"
);
}
#[tokio::test]
async fn probe_reports_unknown_on_git_error() {
// A path git cannot resolve as a repo at all (exit 128) is an indeterminate
+339 -175
View File
@@ -1036,6 +1036,345 @@ mod tests {
);
}
/// #496: create_task must reject a caller-supplied repo_id that names a
/// hosted repo the caller does not own. A stranger naming the victim's repo
/// gets 403, leaking nothing about the repo and persisting nothing; the
/// owner files (201). Repo-less tasks stay allowed; an id naming no hosted
/// repo (unknown, or quarantined, hidden as if it did not exist) is stored
/// verbatim as an opaque label, and the 403-vs-201 split between a hosted
/// id and an unknown one is itself a one-bit oracle. This is a write gate:
/// task reads are caller-independent and not repo-scoped on this base.
#[sqlx::test]
async fn create_task_rejects_foreign_repo_id(pool: PgPool) {
let owner = "did:key:zTASKREPOOWNERAAAAAAAAAAAAAAAAAAAAAAAAAA";
let stranger = "did:key:zTASKREPOSTRANGERBBBBBBBBBBBBBBBBBBBBBB";
let state = test_state(pool).await;
let repo = seed_repo(owner, "task-gate-repo");
state.db.create_repo(&repo).await.expect("seed repo");
let router = || {
Router::new()
.route(
"/api/v1/tasks",
axum::routing::post(crate::api::tasks::create_task),
)
.with_state(state.clone())
};
let post_as = |signer: &str, body: String| {
router().oneshot(signed_request_as(
signer,
Method::POST,
"/api/v1/tasks",
Body::from(body),
))
};
let body_with = |signer: &str, repo_id: Option<&str>| {
let repo_field = repo_id
.map(|id| format!(r#","repo_id":"{id}""#))
.unwrap_or_default();
format!(
r#"{{"kind":"build","capability":"repo:write","delegator_did":"{signer}"{repo_field}}}"#
)
};
let created_id = |bytes: &[u8]| -> String {
let v: serde_json::Value = serde_json::from_slice(bytes).expect("task json");
v["id"].as_str().expect("task id").to_string()
};
// Stranger filing under the victim's repo id → exact 403.
let resp = post_as(stranger, body_with(stranger, Some(&repo.id)))
.await
.unwrap();
assert_eq!(
resp.status(),
StatusCode::FORBIDDEN,
"a non-owner must not file tasks against a foreign repo id"
);
let bytes = axum::body::to_bytes(resp.into_body(), usize::MAX)
.await
.unwrap();
let text = String::from_utf8_lossy(&bytes);
assert!(
text.contains(r#""error":"forbidden""#),
"denial must keep the forbidden envelope: {text}"
);
assert!(
text.contains(crate::api::REPO_OWNER_ONLY_MESSAGE),
"denial must carry the shared owner-denial text (same as GraphQL): {text}"
);
// The denial must not persist: no task row may carry the victim's
// repo id afterwards — a 403 that still writes is the injection.
let stored = state
.db
.list_tasks(None, None, 50)
.await
.expect("list tasks");
assert!(
stored
.iter()
.all(|t| t.repo_id.as_deref() != Some(repo.id.as_str())),
"a denied write must not leave a task under the foreign repo id"
);
// Owner filing under their own repo id → 201.
let resp = post_as(owner, body_with(owner, Some(&repo.id)))
.await
.unwrap();
assert_eq!(
resp.status(),
StatusCode::CREATED,
"the owner must be able to file tasks against their repo"
);
// Repo-less task → 201 (unaffected).
let resp = post_as(stranger, body_with(stranger, None)).await.unwrap();
assert_eq!(
resp.status(),
StatusCode::CREATED,
"repo-less task creation must keep working"
);
// Unknown repo id → 201 as an opaque label.
let resp = post_as(stranger, body_with(stranger, Some("no-such-repo-id")))
.await
.unwrap();
assert_eq!(
resp.status(),
StatusCode::CREATED,
"an id naming no hosted repo stays an opaque label"
);
// Read back the row: the unresolved id must be stored verbatim, not
// dropped or rewritten to a repo it never named.
let bytes = axum::body::to_bytes(resp.into_body(), usize::MAX)
.await
.unwrap();
let task = state
.db
.get_task(&created_id(&bytes))
.await
.expect("get task")
.expect("task must be stored");
assert_eq!(
task.repo_id.as_deref(),
Some("no-such-repo-id"),
"an unresolved id must be stored verbatim as a label"
);
// Quarantined repo id → treated as unknown (201), never a 403 that
// would confirm the id names a real repo.
state
.db
.set_repo_quarantine(&repo.id, true)
.await
.expect("quarantine");
let resp = post_as(stranger, body_with(stranger, Some(&repo.id)))
.await
.unwrap();
assert_eq!(
resp.status(),
StatusCode::CREATED,
"a quarantined repo id must not 403 (existence oracle)"
);
// Read back the row: the quarantined id is stored verbatim as a label
// too, so the accepted write is not silently dropped.
let bytes = axum::body::to_bytes(resp.into_body(), usize::MAX)
.await
.unwrap();
let task = state
.db
.get_task(&created_id(&bytes))
.await
.expect("get task")
.expect("task must be stored");
assert_eq!(
task.repo_id.as_deref(),
Some(repo.id.as_str()),
"a quarantined id must be stored verbatim as a label"
);
}
/// #496 (REST): a repo-lookup fault in the create_task gate must render the
/// module's opaque `db_error` envelope, not the raw sqlx text. Dropping a
/// column `get_repo_by_id` selects faults that first lookup; the 500 body
/// stays fixed and names no column (#250/#226).
#[sqlx::test]
async fn create_task_gate_repo_lookup_fault_is_opaque(pool: PgPool) {
let owner = "did:key:zTASKFAULTOWNERAAAAAAAAAAAAAAAAAAAAAAAAA";
let state = test_state(pool.clone()).await;
let repo = seed_repo(owner, "task-gate-fault-repo");
state.db.create_repo(&repo).await.expect("seed repo");
let router = || {
Router::new()
.route(
"/api/v1/tasks",
axum::routing::post(crate::api::tasks::create_task),
)
.with_state(state.clone())
};
let body = format!(
r#"{{"kind":"build","capability":"repo:write","delegator_did":"{owner}","repo_id":"{}"}}"#,
repo.id
);
// Drop a column the lookup's SELECT names so get_repo_by_id faults.
sqlx::query("ALTER TABLE repos DROP COLUMN machine_id")
.execute(&pool)
.await
.expect("drop machine_id");
let resp = router()
.oneshot(signed_request_as(
owner,
Method::POST,
"/api/v1/tasks",
Body::from(body),
))
.await
.unwrap();
assert_eq!(
resp.status(),
StatusCode::INTERNAL_SERVER_ERROR,
"a faulted repo lookup must be a 500"
);
let bytes = axum::body::to_bytes(resp.into_body(), usize::MAX)
.await
.unwrap();
let text = String::from_utf8_lossy(&bytes);
assert!(
text.contains(r#""error":"db_error""#),
"gate DB fault must keep the opaque envelope: {text}"
);
assert!(
text.contains(crate::error::DB_ERROR_MESSAGE),
"gate DB fault must carry the fixed message: {text}"
);
assert!(
!text.contains("machine_id") && !text.contains("column"),
"schema text leaked through the gate: {text}"
);
}
/// #496 (REST): the gate's second lookup (`is_repo_quarantined`) runs through
/// the same opaque helper. Dropping the column only it selects leaves
/// `get_repo_by_id` succeeding, so this pins that second call site too.
#[sqlx::test]
async fn create_task_gate_quarantine_lookup_fault_is_opaque(pool: PgPool) {
let owner = "did:key:zTASKFAULT2OWNERAAAAAAAAAAAAAAAAAAAAAAAA";
let state = test_state(pool.clone()).await;
let repo = seed_repo(owner, "task-gate-fault2-repo");
state.db.create_repo(&repo).await.expect("seed repo");
let router = || {
Router::new()
.route(
"/api/v1/tasks",
axum::routing::post(crate::api::tasks::create_task),
)
.with_state(state.clone())
};
let body = format!(
r#"{{"kind":"build","capability":"repo:write","delegator_did":"{owner}","repo_id":"{}"}}"#,
repo.id
);
// `quarantined` is not in get_repo_by_id's SELECT, so that lookup still
// succeeds and the fault lands on is_repo_quarantined.
sqlx::query("ALTER TABLE repos DROP COLUMN quarantined")
.execute(&pool)
.await
.expect("drop quarantined");
let resp = router()
.oneshot(signed_request_as(
owner,
Method::POST,
"/api/v1/tasks",
Body::from(body),
))
.await
.unwrap();
assert_eq!(
resp.status(),
StatusCode::INTERNAL_SERVER_ERROR,
"a faulted quarantine lookup must be a 500"
);
let bytes = axum::body::to_bytes(resp.into_body(), usize::MAX)
.await
.unwrap();
let text = String::from_utf8_lossy(&bytes);
assert!(
text.contains(r#""error":"db_error""#),
"quarantine DB fault must keep the opaque envelope: {text}"
);
assert!(
text.contains(crate::error::DB_ERROR_MESSAGE),
"quarantine DB fault must carry the fixed message: {text}"
);
assert!(
!text.contains("quarantined") && !text.contains("column"),
"schema text leaked through the gate: {text}"
);
}
/// #496 (REST): the create_task INSERT goes through the same opaque helper,
/// so a write fault must not serialize sqlx text either. A repo-less task
/// reaches the INSERT without a gate lookup; dropping a column the INSERT
/// names faults it.
#[sqlx::test]
async fn create_task_insert_fault_is_opaque(pool: PgPool) {
let signer = "did:key:zTASKINSERTFAULTAAAAAAAAAAAAAAAAAAAAAAAA";
let state = test_state(pool.clone()).await;
let router = || {
Router::new()
.route(
"/api/v1/tasks",
axum::routing::post(crate::api::tasks::create_task),
)
.with_state(state.clone())
};
let body =
format!(r#"{{"kind":"build","capability":"repo:write","delegator_did":"{signer}"}}"#);
sqlx::query("ALTER TABLE agent_tasks DROP COLUMN status")
.execute(&pool)
.await
.expect("drop status");
let resp = router()
.oneshot(signed_request_as(
signer,
Method::POST,
"/api/v1/tasks",
Body::from(body),
))
.await
.unwrap();
assert_eq!(
resp.status(),
StatusCode::INTERNAL_SERVER_ERROR,
"a faulted INSERT must be a 500"
);
let bytes = axum::body::to_bytes(resp.into_body(), usize::MAX)
.await
.unwrap();
let text = String::from_utf8_lossy(&bytes);
assert!(
text.contains(r#""error":"db_error""#),
"INSERT fault must keep the opaque envelope: {text}"
);
assert!(
text.contains(crate::error::DB_ERROR_MESSAGE),
"INSERT fault must carry the fixed message: {text}"
);
assert!(
!text.contains("status") && !text.contains("column"),
"schema text leaked through the INSERT: {text}"
);
}
/// N3: get_tree gates on the REQUESTED subtree, not the repo root. A caller
/// denied a withheld subtree is rejected there (404) but passes the gate on a
/// non-withheld path (so the rejection is path-scoped, not repo-wide).
@@ -16560,181 +16899,6 @@ mod tests {
);
}
/// #134 R2 (split buckets): signed `/api/v1/ipfs/pins` polling must NOT debit
/// the CID resolver's per-IP flood brake. The pre-fix composition merged
/// pins under the same router as `/ipfs/{cid}`, so every signed pin
/// request consumed a token from `ipfs_rate_limiter` and a flood of pinned
/// traffic could 429 legitimate CID reads. RED before the split (pins
/// debited the bucket): a flood of pins followed by a CID request → 429
/// on the CID. GREEN after the split: the CID bucket is untouched.
#[sqlx::test]
async fn ipfs_pins_do_not_debit_the_cid_bucket(pool: PgPool) {
use gitlawb_core::http_sig::sign_request;
use gitlawb_core::identity::Keypair;
let kp = Keypair::generate();
let owner_did = kp.did().to_string();
let slug = owner_did.replace([':', '/'], "_");
let short = owner_did.split(':').next_back().unwrap().to_string();
let mut state = test_state(pool).await;
// Bucket size 2: any third /ipfs/{cid} request from the same IP would
// 429 if the bucket were touched by the preceding pin requests.
state.ipfs_rate_limiter = crate::rate_limit::RateLimiter::new(2, Duration::from_secs(3600));
state.ipfs_work_rate_limiter =
crate::rate_limit::RateLimiter::new(600, Duration::from_secs(3600));
state.push_limiter_trust = crate::rate_limit::TrustedProxy::XForwardedFor;
// Seed a public, walk-free CID so /ipfs/{cid} serves cheaply. This
// matters because the proof half of the test fires a real CID request
// and needs the route bucket to be the only thing that can 429 it.
let fx = seed_cid_repos(&slug, &short, &["pinsdebit"]);
let bare = std::path::PathBuf::from("/tmp")
.join(&slug)
.join("pinsdebit.git");
let repo = seed_repo(&owner_did, "pinsdebit");
state.db.create_repo(&repo).await.expect("seed repo");
let cid = pin_cid_for(&bare, &fx.public_oid, &state.db).await;
let router = crate::server::build_router(state);
let peer_ip = "203.0.113.50";
// Five signed pin requests — more than the bucket — all must 200 (the
// pins route has no rate limit; the bucket only charges /ipfs/{cid}).
let pins_path = "/api/v1/ipfs/pins";
let pins_signed = sign_request(&kp, "GET", pins_path, b"");
for i in 0..5 {
let req = Request::builder()
.method(Method::GET)
.uri(pins_path)
.header("content-digest", &pins_signed.content_digest)
.header("signature-input", &pins_signed.signature_input)
.header("signature", &pins_signed.signature)
.header("x-forwarded-for", peer_ip)
.body(Body::empty())
.unwrap();
let resp = router.clone().oneshot(req).await.unwrap();
assert_eq!(
resp.status(),
StatusCode::OK,
"pin request {i} must not be rate-limited even though the CID bucket is size 2"
);
}
// A subsequent /ipfs/{cid} request from the same IP must still serve
// 200 — the bucket was untouched by the pin traffic. (If pins had
// debited it, the bucket would be empty and the CID request would 429.)
let cid_path = format!("/ipfs/{cid}");
let cid_signed = sign_request(&kp, "GET", &cid_path, b"");
let req = Request::builder()
.method(Method::GET)
.uri(&cid_path)
.header("content-digest", cid_signed.content_digest)
.header("signature-input", cid_signed.signature_input)
.header("signature", cid_signed.signature)
.header("x-forwarded-for", peer_ip)
.body(Body::empty())
.unwrap();
let resp = router.oneshot(req).await.unwrap();
assert_eq!(
resp.status(),
StatusCode::OK,
"the CID bucket must still have tokens — pin traffic did not debit it"
);
}
/// #134 R2 (split buckets, second half): an EXHAUSTED CID bucket must
/// NOT block a valid signed `/api/v1/ipfs/pins` listing. The pre-fix
/// composition routed pins through the same middleware stack, so a CID
/// flood that exhausted the bucket would 429 the pins endpoint too. RED
/// before the split: a CID request that 429s the bucket makes the next
/// pin request 429 too. GREEN after the split: pins never see this
/// bucket and remain servable.
#[sqlx::test]
async fn ipfs_pins_survive_an_exhausted_cid_bucket(pool: PgPool) {
use gitlawb_core::http_sig::sign_request;
use gitlawb_core::identity::Keypair;
let kp = Keypair::generate();
let owner_did = kp.did().to_string();
let slug = owner_did.replace([':', '/'], "_");
let short = owner_did.split(':').next_back().unwrap().to_string();
let mut state = test_state(pool).await;
// Bucket size 1: the first /ipfs/{cid} request from the IP spends the
// only token; the second is 429 (proves exhaustion).
state.ipfs_rate_limiter = crate::rate_limit::RateLimiter::new(1, Duration::from_secs(3600));
state.ipfs_work_rate_limiter =
crate::rate_limit::RateLimiter::new(600, Duration::from_secs(3600));
state.push_limiter_trust = crate::rate_limit::TrustedProxy::XForwardedFor;
let fx = seed_cid_repos(&slug, &short, &["pinsexh"]);
let bare = std::path::PathBuf::from("/tmp")
.join(&slug)
.join("pinsexh.git");
let repo = seed_repo(&owner_did, "pinsexh");
state.db.create_repo(&repo).await.expect("seed repo");
let cid = pin_cid_for(&bare, &fx.public_oid, &state.db).await;
let router = crate::server::build_router(state);
let peer_ip = "203.0.113.60";
// First /ipfs/{cid} request — debits the single CID token, serves 200.
let cid_path = format!("/ipfs/{cid}");
let cid_signed = sign_request(&kp, "GET", &cid_path, b"");
let req = Request::builder()
.method(Method::GET)
.uri(&cid_path)
.header("content-digest", cid_signed.content_digest)
.header("signature-input", cid_signed.signature_input)
.header("signature", cid_signed.signature)
.header("x-forwarded-for", peer_ip)
.body(Body::empty())
.unwrap();
let resp = router.clone().oneshot(req).await.unwrap();
assert_eq!(
resp.status(),
StatusCode::OK,
"the first CID request spends the token and serves"
);
// Second /ipfs/{cid} request — bucket empty → 429 (proves the
// exhaustion is real and observable on this router). Re-sign because
// `SignedHeaders` holds owned `String`s.
let cid_signed_2 = sign_request(&kp, "GET", &cid_path, b"");
let req = Request::builder()
.method(Method::GET)
.uri(&cid_path)
.header("content-digest", cid_signed_2.content_digest)
.header("signature-input", cid_signed_2.signature_input)
.header("signature", cid_signed_2.signature)
.header("x-forwarded-for", peer_ip)
.body(Body::empty())
.unwrap();
let resp = router.clone().oneshot(req).await.unwrap();
assert_eq!(
resp.status(),
StatusCode::TOO_MANY_REQUESTS,
"the second CID request from the same IP is 429 — bucket exhausted"
);
// A signed /api/v1/ipfs/pins request from the SAME IP must still
// serve 200 — pins are auth-only and never see this bucket.
let pins_path = "/api/v1/ipfs/pins";
let pins_signed = sign_request(&kp, "GET", pins_path, b"");
let req = Request::builder()
.method(Method::GET)
.uri(pins_path)
.header("content-digest", pins_signed.content_digest)
.header("signature-input", pins_signed.signature_input)
.header("signature", pins_signed.signature)
.header("x-forwarded-for", peer_ip)
.body(Body::empty())
.unwrap();
let resp = router.oneshot(req).await.unwrap();
assert_eq!(
resp.status(),
StatusCode::OK,
"an exhausted CID bucket must not block a valid signed pin listing"
);
}
/// U5 (R6): the two buckets are independent — the WORK budget can be exhausted
/// (429) WITHOUT draining the ROUTE bucket. Through the production router, route
/// generous (5) but work tight (1): one request drives two legacy probes, so the
+5 -89
View File
@@ -163,8 +163,8 @@ pub fn setup_partial_clone(
if withheld_globs.is_empty() {
match branch {
Some(b) => git_global(&["clone", "-q", "--branch", b, "--", remote_url, dest_str])?,
None => git_global(&["clone", "-q", "--", remote_url, dest_str])?,
Some(b) => git_global(&["clone", "-q", "--branch", b, remote_url, dest_str])?,
None => git_global(&["clone", "-q", remote_url, dest_str])?,
}
return Ok(());
}
@@ -174,7 +174,6 @@ pub fn setup_partial_clone(
"-q",
"--filter=blob:none",
"--no-checkout",
"--",
remote_url,
dest_str,
])?;
@@ -389,7 +388,7 @@ async fn recover_encrypted_blobs(
let plaintext = match open_blob(&envelope, keypair) {
Ok(p) => p,
Err(e) => {
emit_warning(&format!("warning: could not decrypt {oid}: {e}"));
eprintln!("warning: could not decrypt {oid}: {e}");
continue;
}
};
@@ -407,9 +406,7 @@ async fn recover_encrypted_blobs(
recovered.push(p.clone());
}
} else {
emit_warning(&format!(
"warning: recovered blob {oid} hashed to {written}; discarding"
));
eprintln!("warning: recovered blob {oid} hashed to {written}; discarding");
}
}
Ok(recovered)
@@ -807,9 +804,7 @@ async fn recover_from_arweave(
recovered.push(p.clone());
}
} else {
emit_warning(&format!(
"warning: recovered blob {oid} hashed to {written}; discarding"
));
eprintln!("warning: recovered blob {oid} hashed to {written}; discarding");
}
}
Ok(recovered)
@@ -1095,85 +1090,6 @@ mod tests {
);
}
#[test]
fn setup_partial_clone_plain_without_withheld_paths() {
let (td, url) = bare_remote(&[("file.txt", b"hello\n")]);
let dest = td.path().join("dest");
setup_partial_clone(&dest, &url, &[], &[], None).unwrap();
assert!(dest.join("file.txt").exists());
}
#[test]
fn setup_partial_clone_with_branch_without_withheld_paths() {
let (td, url) = bare_remote(&[("file.txt", b"hello\n")]);
let branch_out = Command::new("git")
.args([
"-C",
td.path().join("origin").to_str().unwrap(),
"branch",
"--show-current",
])
.output()
.unwrap();
let branch = String::from_utf8(branch_out.stdout)
.unwrap()
.trim()
.to_string();
let dest = td.path().join("dest");
setup_partial_clone(&dest, &url, &[], &[], Some(&branch)).unwrap();
assert!(dest.join("file.txt").exists());
}
/// #374: every `setup_partial_clone` shape interpolates `remote_url` into a
/// `git clone` argv. The `--` delimiter is what forces an option-shaped
/// remote to be read as a repository rather than parsed as an option.
///
/// The assertion is on git's own words — `repository '<value>'`, single-quoted
/// — and not merely on the value appearing somewhere in the error. `git_global`
/// formats its failure as `git {args:?} failed: {stderr}`, so the injected
/// string is already present in the debug-printed argv whether or not the
/// delimiter is there; asserting on containment alone would pass with `--`
/// deleted. Undelimited, git consumes the value as an option, leaving the
/// destination as the only positional, and names *that* instead
/// (`repository '<dest>' does not exist`) — so this goes red without the fix.
///
/// The payload carries no `:` or space: a colon would make git read the
/// argument as an ssh-style `host:path` URL and report a hostname, which is a
/// different parse.
fn assert_option_shaped_remote_is_a_repository(withheld: &[String], branch: Option<&str>) {
let td = TempDir::new().unwrap();
let dest = td.path().join("dest");
let injected = "--upload-pack=false";
let err = setup_partial_clone(&dest, injected, withheld, &[], branch)
.expect_err("an option-shaped remote is not a repository and must fail")
.to_string();
assert!(
err.contains(&format!("repository '{injected}'")),
"git must name the argument as the repository, not consume it as an option: {err}"
);
}
#[test]
fn plain_clone_never_parses_a_remote_as_a_git_option() {
assert_option_shaped_remote_is_a_repository(&[], None);
}
#[test]
fn branch_clone_never_parses_a_remote_as_a_git_option() {
// Pins that `--branch <b>` stays ahead of the delimiter: if `--` were moved
// before `--branch`, git would read the branch name as a positional instead.
assert_option_shaped_remote_is_a_repository(&[], Some("main"));
}
#[test]
fn sparse_clone_never_parses_a_remote_as_a_git_option() {
// The withheld-globs arm is a separate argv construction
// (`--filter=blob:none --no-checkout`) and needs its own proof.
assert_option_shaped_remote_is_a_repository(&["/secret/**".to_string()], None);
}
#[test]
fn sparse_patterns_subtree_and_exact() {
assert_eq!(sparse_patterns("/secret/**"), vec!["/secret/".to_string()]);
+2 -51
View File
@@ -41,17 +41,6 @@ pub struct MirrorArgs {
pub dir: Option<PathBuf>,
}
/// Argv for the mirror clone, with `--` immediately before the first positional
/// so an option-shaped `source` cannot be parsed as a git option (#374).
///
/// This is a separate function purely so the delimiter's placement can be driven
/// through real git by a test. The production call keeps `.status()` rather than
/// `.output()`: a mirror clone of a large repo streams git's progress to the
/// user's terminal, and capturing it to assert on stderr here would swallow that.
fn mirror_clone_args(source: &str) -> [&str; 4] {
["clone", "--mirror", "--", source]
}
pub async fn run(args: MirrorArgs) -> Result<()> {
let source = args.source.trim_end_matches('/').to_string();
@@ -156,7 +145,7 @@ fn clone_mirror(source: &str, dest: &std::path::Path) -> Result<()> {
// bounded-runner rule governs node request handlers. Same spawn as before,
// only relocated into this helper.
let status = Command::new("git")
.args(mirror_clone_args(source))
.args(["clone", "--mirror", source])
.arg(dest)
.status()
.context("failed to run git clone — is git installed?")?;
@@ -197,43 +186,6 @@ pub fn extract_repo_name(url: &str) -> Option<String> {
mod tests {
use super::*;
/// #374: `gl mirror` interpolates the user-supplied source into a
/// `git clone --mirror` argv. `--` must sit immediately before the first
/// positional so an option-shaped source is read as a repository.
///
/// This drives the production argv through real git rather than asserting on
/// the array's contents, so it fails on a delimiter that is missing *or*
/// misplaced. It cannot go through `run()`: that loads an identity keypair and
/// contacts a node before reaching the clone, and its bail message interpolates
/// `{source}` unconditionally, so an assertion there would pass with `--` gone.
///
/// Asserting on git's single-quoted `repository '<value>'` is what makes this
/// red without the delimiter — undelimited, git consumes the value as an option
/// and names the destination as the repository instead.
#[test]
fn mirror_clone_never_parses_the_source_as_a_git_option() {
let td = tempfile::TempDir::new().unwrap();
let dest = td.path().join("mirror.git");
let injected = "--upload-pack=false";
let out = Command::new("git")
.env("LC_ALL", "C")
.args(mirror_clone_args(injected))
.arg(&dest)
.output()
.unwrap();
let stderr = String::from_utf8_lossy(&out.stderr);
assert!(
!out.status.success(),
"an option-shaped source is not a repository and must fail the clone"
);
assert!(
stderr.contains(&format!("repository '{injected}'")),
"git must name the source as the repository, not consume it as an option: {stderr}"
);
}
#[test]
fn test_extract_github_url() {
assert_eq!(
@@ -378,8 +330,7 @@ mod tests {
.create_async()
.await;
// The git subprocess argv is pinned separately by
// `mirror_clone_never_parses_the_source_as_a_git_option`; this covers the
// We can't easily test the git subprocess calls, but we can test the
// API error path by calling the create step directly via NodeClient.
let kp2 = gitlawb_core::identity::Keypair::generate();
let client = NodeClient::new(server.url(), Some(kp2));