fix(node): implement reconciliation sweep as durability backstop (#218)

.env.example

@@ -274,6 +274,13 @@ GITLAWB_TRUSTED_PROXY=
 # Enable automatic background sync from known peers
 GITLAWB_AUTO_SYNC=false
 
+# ── Reconciliation sweep ─────────────────────────────────────────────────
+# Periodic durability sweep: re-derives the public pin set and the withheld-blob
+# recovery set each hour and fills gaps so a dropped replication job never means
+# data loss. Defaults to true; set to false to disable the sweep even when a pin
+# backend (IPFS/Pinata) is configured.
+GITLAWB_RECONCILIATION_SWEEP=true
+
 # ── iCaptcha proof-of-intelligence gate ───────────────────────────────────
 # Optional gate on create_repo + register: require callers to present an
 # iCaptcha proof (X-ICaptcha-Proof header) earned at icaptcha.gitlawb.com.

README.md

@@ -347,6 +347,7 @@ Important node settings:
 | `GITLAWB_BOOTSTRAP_DISABLE_SEEDS` | Disable embedded seed peers for isolated dev/test networks. |
 | `GITLAWB_REQUIRE_SIGNED_PEER_WRITES` | Require signed peer announce/sync writes. |
 | `GITLAWB_AUTO_SYNC` | Enable automatic sync from known peers. |
+| `GITLAWB_RECONCILIATION_SWEEP` | Enable the hourly durability sweep that re-pins/backstops missing objects (default `true`; disabled when no IPFS/Pinata backend is configured). |
 | `GITLAWB_MAX_PACK_BYTES` | Max git pack body size for smart-HTTP routes. |
 | `GITLAWB_GIT_SERVICE_TIMEOUT_SECS` | Max seconds a served git upload-pack, receive-pack, or `info/refs` advertisement may run before it is aborted (504). Default 600. Also bounds the withheld-blob classification walk (on both the upload-pack serve and receive-pack replication paths) and the push-side pin-candidate discovery (`rev-list` / `cat-file`), each reaped via process-group teardown at the deadline. On the path-scoped upload-pack path the classification walk and the pack serve share ONE deadline, so this value bounds their combined duration rather than granting each stage a full budget: a walk that consumes it leaves the serve nothing and the clone gets a 504. Serving large path-scoped repos may therefore need a higher value than they did when each stage was budgeted separately. Accepted range is 1 to 3153600000 (100 years), since the node derives deadlines from this value and a larger one cannot be represented. |
 | `GITLAWB_GIT_ACQUIRE_TIMEOUT_SECS` | Max seconds the storage-acquisition phase (Tigris HEAD/GET, push advisory-lock) of a served git op may run before the request is shed with a 503, separate from the git-run timeout. The concurrency permit is released on expiry so a stalled backend cannot pin the pool. Default 30. |

crates/gitlawb-attest/src/attestation.rs

@@ -483,6 +483,37 @@ mod tests {
         assert!(matches!(err, Error::Signature(_)));
     }
 
+    /// The identity-point forgery must be rejected: the shared attestation
+    /// verifier is a cert-bound provenance gate, so accepting the weak-key
+    /// signature would let anyone mint a forged attestation that verifies.
+    /// Strict verification rejects small-order public keys and R (the identity
+    /// point here), which ordinary verification does not.
+    #[test]
+    fn verify_rejects_identity_point_forgery() {
+        let cert_hash = sample_cert_hash();
+        let mut att = dummy_attestation(&fresh(), cert_hash);
+
+        // Public key A = identity point (0,1); signature R = identity, S = 0.
+        // The equation `[S]B = R + [k]A` then holds for any k and any message.
+        let identity = [
+            1u8, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+            0, 0, 0, 0,
+        ];
+        let mut buf = Vec::with_capacity(34);
+        buf.extend_from_slice(&ED25519_MULTICODEC);
+        buf.extend_from_slice(&identity);
+        att.signer = format!(
+            "did:key:{}",
+            multibase::encode(multibase::Base::Base58Btc, &buf)
+        );
+        let mut sig = [0u8; 64];
+        sig[..32].copy_from_slice(&identity);
+        att.sig = B64U.encode(sig);
+
+        let err = att.verify_signature(cert_hash).unwrap_err();
+        assert!(matches!(err, Error::Signature(_)));
+    }
+
     /// A payload that happens to contain a `cert_hash` field of its own does
     /// not interfere with the outer binding: the attestation envelope's
     /// `cert_hash` is the only field consulted by `verify_signature`, and the

crates/gitlawb-core/src/identity.rs

@@ -77,6 +77,14 @@ impl Keypair {
 }
 
 /// Verify an Ed25519 signature.
+///
+/// Strict verification: rejects small-order `R` and small-order public keys
+/// (the identity point, and any point of low order). Ordinary `verify` accepts
+/// a signature forged with the identity point as the public key plus
+/// `R = identity, S = 0`, which verifies for *any* message. `identity::verify`
+/// is the shared primitive behind HTTP request authentication, UCANs, and
+/// certificates, so weak-key acceptance is an authentication bypass, not a
+/// malleability nuance.
 pub fn verify(verifying_key: &VerifyingKey, msg: &[u8], sig_bytes: &[u8; 64]) -> Result<()> {
     let sig = Signature::from_bytes(sig_bytes);
     verifying_key
@@ -208,6 +216,38 @@ mod tests {
         );
     }
 
+    /// The identity-point forgery: with public key A = identity, R = identity,
+    /// and S = 0, the equation `[S]B = R + [k]A` holds for every message,
+    /// because `[k]·identity = identity`. Ordinary (non-strict) Ed25519
+    /// verification accepts it, so the shared `verify` primitive must use
+    /// strict verification, which rejects small-order R and public keys.
+    #[test]
+    fn verify_rejects_identity_point_forgery() {
+        use ed25519_dalek::Verifier;
+        // The identity point (0,1) compresses to y = 1 with sign bit 0.
+        let identity = [
+            1u8, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+            0, 0, 0, 0,
+        ];
+        let vk = VerifyingKey::from_bytes(&identity).expect("identity point is on the curve");
+        let mut sig_bytes = [0u8; 64];
+        sig_bytes[..32].copy_from_slice(&identity);
+        let msg = b"arbitrary message the key owner never signed";
+
+        // Prove the forged signature satisfies the ordinary verification
+        // equation, so the strict check below is what actually defends the
+        // boundary (not a signature that was already invalid everywhere).
+        assert!(
+            vk.verify(msg, &Signature::from_bytes(&sig_bytes)).is_ok(),
+            "identity-point forgery must satisfy ordinary verification (this is why strict is needed)"
+        );
+
+        assert!(
+            verify(&vk, msg, &sig_bytes).is_err(),
+            "strict verification must reject the identity-point forgery"
+        );
+    }
+
     #[test]
     fn verify_rejects_weak_key_signature() {
         // Regression guard for strict verification: a signature forged under a

crates/gitlawb-node/src/api/ipfs.rs

@@ -680,14 +680,36 @@ pub async fn get_by_cid(
 
 /// GET /api/v1/ipfs/pins
 ///
-/// 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.
+/// Returns all CIDs that have been pinned from git objects received via push.
+/// Each entry includes the git SHA-256 hex, a CIDv1 string, and the timestamp
+/// when it was pinned.  For Pinata-only rows (no local IPFS pin), the `cid`
+/// field carries `pinata_cid` so CLI consumers see a usable value.
+///
+/// Rows with neither a local nor a Pinata CID are omitted so `cid` stays an
+/// always-string field. The raw `pinata_cid` is not surfaced under its own
+/// key, but it does appear as the `cid` value for Pinata-only rows; that is
+/// the intended fallback, so the field is always a real CIDv1, never node
+/// infrastructure detail beyond the CID itself.
 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?;
 
+    let pins: Vec<serde_json::Value> = pins
+        .into_iter()
+        .filter(|p| p.cid.is_some() || p.pinata_cid.is_some())
+        .map(|p| {
+            // Synthesize a usable CID from pinata_cid when this is a
+            // Pinata-only row (no local IPFS pin).
+            let display_cid = p.cid.clone().or_else(|| p.pinata_cid.clone());
+            serde_json::json!({
+                "sha256_hex": p.sha256_hex,
+                "cid": display_cid,
+                "pinned_at": p.pinned_at,
+            })
+        })
+        .collect();
+
     Ok(Json(serde_json::json!({
         "pins": pins,
         "count": pins.len(),

crates/gitlawb-node/src/api/repos.rs

@@ -1170,6 +1170,10 @@ async fn pin_new_objects_gated(
         object_list,
         db,
         crate::ipfs_pin::PIN_BATCH_BUDGET,
+        // The push path derives its object list at admission and holds a write
+        // lease, so no sweep-style batch snapshot crosses the dispatch boundary
+        // (see PolicyFence's doc).
+        None,
     )
     .await
 }
@@ -1227,7 +1231,14 @@ async fn pin_and_encrypt_objects(
                 &ctx.db,
                 repo_id,
                 &node_seed,
+                // The real git, not `ctx.git_bin`: tests point that at a fake
+                // walk git, and the seal reads must run the real one.
+                "git",
+                crate::ipfs_pin::PIN_BATCH_BUDGET,
                 &recipients,
+                // Push path: recipients derived at admission under a write lease,
+                // no sweep-style snapshot to fence (see PolicyFence's doc).
+                None,
             )
             .await;
 
@@ -2434,6 +2445,9 @@ async fn post_receive_replication_tail(
                         object_list,
                         &db_clone,
                         crate::ipfs_pin::PIN_BATCH_BUDGET,
+                        // Push path: no sweep-style batch snapshot to fence (see
+                        // PolicyFence's doc).
+                        None,
                     )
                     .await,
                 )

crates/gitlawb-node/src/config.rs

@@ -113,6 +113,17 @@ pub struct Config {
     #[arg(long, env = "GITLAWB_AUTO_SYNC", default_value_t = false)]
     pub auto_sync: bool,
 
+    /// Enable the periodic reconciliation sweep that re-derives pin/seal sets
+    /// and fills durability gaps.  Defaults to true; set to false to disable
+    /// the sweep even when a pin backend (IPFS/Pinata) is configured.
+    #[arg(
+        long,
+        env = "GITLAWB_RECONCILIATION_SWEEP",
+        default_value_t = true,
+        action = clap::ArgAction::Set
+    )]
+    pub reconciliation_sweep: bool,
+
     /// Irys URL for Arweave permanent anchoring.
     /// Leave empty to disable. Use https://devnet.irys.xyz for free devnet.
     #[arg(long, env = "GITLAWB_IRYS_URL", default_value = "")]