feat: import Chinese-localized Buzz source snapshot
Docker image / Build (linux/amd64) (push) Has been cancelled
Docker image / Build (linux/arm64) (push) Has been cancelled
Docker image / Merge release multi-arch manifest (push) Has been cancelled
Docker image / Merge debug multi-arch manifest (push) Has been cancelled
Docker image / Build public push gateway (linux/amd64) (push) Has been cancelled
Docker image / Build public push gateway (linux/arm64) (push) Has been cancelled
Docker image / Publish public push gateway image (push) Has been cancelled
Sprig image / Build (linux/amd64) (push) Has been cancelled
Sprig image / Build (linux/arm64) (push) Has been cancelled
Sprig image / Merge multi-arch manifest (push) Has been cancelled
Harbor Buzz Orchestra / Python tests and lint (push) Has been cancelled
CI / Detect Changed Paths (push) Has been cancelled
CI / Rust Lint (push) Has been cancelled
CI / Unit Tests (push) Has been cancelled
CI / Desktop Core (push) Has been cancelled
CI / Desktop Smoke E2E (1) (push) Has been cancelled
CI / Desktop Smoke E2E (2) (push) Has been cancelled
CI / Desktop Smoke E2E (3) (push) Has been cancelled
CI / Desktop Smoke E2E (4) (push) Has been cancelled
CI / Desktop (push) Has been cancelled
CI / Desktop E2E Relay (push) Has been cancelled
CI / Desktop E2E Integration (1/2) (push) Has been cancelled
CI / Desktop E2E Integration (2/2) (push) Has been cancelled
CI / Desktop E2E Integration (push) Has been cancelled
CI / Backend Integration (relay e2e) (push) Has been cancelled
CI / Relay E2E (push) Has been cancelled
CI / Web (push) Has been cancelled
CI / Mobile (push) Has been cancelled
CI / Security (push) Has been cancelled
CI / Dead Token Reference Guard (push) Has been cancelled
CI / Server Cross-Compile (aarch64-unknown-linux-musl) (push) Has been cancelled
CI / Server Cross-Compile (x86_64-unknown-linux-musl) (push) Has been cancelled
CI / Windows Rust (x86_64-pc-windows-msvc) (push) Has been cancelled
CI / Desktop Build (macOS) (push) Has been cancelled
helm chart / lint + unittest + render matrix (push) Has been cancelled
helm chart / install on kind (gated) (push) Has been cancelled
helm chart / publish chart to GHCR (push) Has been cancelled
Mesh Lifecycle / Relay-Driven Mesh Lifecycle Smoke (push) Has been cancelled
Sprig / Build (aarch64-unknown-linux-musl) (push) Has been cancelled
Sprig / Build (x86_64-unknown-linux-musl) (push) Has been cancelled
Sprig / Publish rolling release (push) Has been cancelled
Sprig / Publish tagged release (push) Has been cancelled

Signed-off-by: cls_宁波本机 <908705107@qq.com>
This commit is contained in:
2026-08-13 18:34:25 +08:00
parent 61c3fa1df9
commit 9dfa06ffee
3785 changed files with 1085458 additions and 2 deletions
+22
View File
@@ -0,0 +1,22 @@
[package]
name = "buzz-audit"
version.workspace = true
edition.workspace = true
rust-version.workspace = true
license.workspace = true
repository.workspace = true
description = "Hash-chain audit log for Buzz"
[dependencies]
buzz-core = { workspace = true }
sqlx = { workspace = true }
tokio = { workspace = true }
serde = { workspace = true }
serde_json = { workspace = true }
uuid = { workspace = true }
chrono = { workspace = true }
tracing = { workspace = true }
thiserror = { workspace = true }
sha2 = { workspace = true }
hex = { workspace = true }
futures-util = { workspace = true }
+100
View File
@@ -0,0 +1,100 @@
use serde::{Deserialize, Serialize};
use std::fmt;
use std::str::FromStr;
/// Audit action recorded for each event in the log.
#[derive(Debug, Clone, PartialEq, Eq, Serialize, Deserialize)]
#[serde(rename_all = "snake_case")]
pub enum AuditAction {
/// A Nostr event was created.
EventCreated,
/// A Nostr event was deleted.
EventDeleted,
/// A channel was created.
ChannelCreated,
/// A channel's metadata was updated.
ChannelUpdated,
/// A channel was deleted.
ChannelDeleted,
/// A member was added to a channel.
MemberAdded,
/// A member was removed from a channel.
MemberRemoved,
/// A client successfully authenticated.
AuthSuccess,
/// A client authentication attempt failed.
AuthFailure,
/// A client exceeded the rate limit.
RateLimitExceeded,
/// A media file was uploaded via the Blossom endpoint.
MediaUploaded,
}
impl AuditAction {
/// Stable string representation used in hash computation and DB storage.
pub fn as_str(&self) -> &'static str {
match self {
Self::EventCreated => "event_created",
Self::EventDeleted => "event_deleted",
Self::ChannelCreated => "channel_created",
Self::ChannelUpdated => "channel_updated",
Self::ChannelDeleted => "channel_deleted",
Self::MemberAdded => "member_added",
Self::MemberRemoved => "member_removed",
Self::AuthSuccess => "auth_success",
Self::AuthFailure => "auth_failure",
Self::RateLimitExceeded => "rate_limit_exceeded",
Self::MediaUploaded => "media_uploaded",
}
}
const ALL: &'static [Self] = &[
Self::EventCreated,
Self::EventDeleted,
Self::ChannelCreated,
Self::ChannelUpdated,
Self::ChannelDeleted,
Self::MemberAdded,
Self::MemberRemoved,
Self::AuthSuccess,
Self::AuthFailure,
Self::RateLimitExceeded,
Self::MediaUploaded,
];
}
impl fmt::Display for AuditAction {
fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
f.write_str(self.as_str())
}
}
impl FromStr for AuditAction {
type Err = String;
fn from_str(s: &str) -> Result<Self, Self::Err> {
Self::ALL
.iter()
.find(|a| a.as_str() == s)
.cloned()
.ok_or_else(|| format!("unknown audit action: {s:?}"))
}
}
#[cfg(test)]
mod tests {
use super::*;
#[test]
fn roundtrip_all_variants() {
for action in AuditAction::ALL {
let parsed: AuditAction = action.to_string().parse().unwrap();
assert_eq!(&parsed, action);
}
}
#[test]
fn unknown_action_returns_err() {
assert!("totally_bogus".parse::<AuditAction>().is_err());
}
}
+72
View File
@@ -0,0 +1,72 @@
use buzz_core::CommunityId;
use chrono::{DateTime, Utc};
use serde::{Deserialize, Serialize};
use uuid::Uuid;
use crate::action::AuditAction;
/// A materialised audit log entry as stored in `audit_log`.
///
/// Rows are keyed `(community_id, seq)`: `seq` is monotonic *within one
/// community*, and `prev_hash` chains to the previous entry *of the same
/// community*. The chain is independent per tenant.
#[derive(Debug, Clone, PartialEq, Eq, Serialize, Deserialize)]
pub struct AuditEntry {
/// Server-resolved community this entry belongs to. Leads the primary key.
pub community_id: Uuid,
/// Sequence number, monotonic within `community_id` (starts at 1).
pub seq: i64,
/// SHA-256 of this entry's fields including `community_id` and `prev_hash`.
pub hash: Vec<u8>,
/// SHA-256 of the previous entry in *this community's* chain, or `None` for
/// the community's first entry (hashed as [`crate::hash::GENESIS_HASH`]).
pub prev_hash: Option<Vec<u8>>,
/// Action that was performed.
pub action: AuditAction,
/// Raw bytes of the actor's Nostr pubkey, if the action has one.
pub actor_pubkey: Option<Vec<u8>>,
/// Generic identifier of the object acted upon (event id hex, channel UUID,
/// media sha256, …), if any. The relay resolves it under `community_id`;
/// it never names an object in another community.
pub object_id: Option<String>,
/// Arbitrary JSON context. **Included in the hash** (serialized with sorted
/// keys for determinism) so tampering with it is detectable.
pub detail: serde_json::Value,
/// When the entry was recorded.
pub created_at: DateTime<Utc>,
}
/// Input for appending a new audit entry. `seq`, `prev_hash`, `hash`, and
/// `created_at` are assigned by [`crate::service::AuditService::log`].
///
/// `community_id` is the **server-resolved** tenant (from the request's
/// `TenantContext`), never a client-supplied value — the same provenance rule
/// the whole multi-tenant model rests on.
///
/// Not `Serialize`/`Deserialize`: this is an in-process input struct (consumed
/// by `AuditService::log`, threaded through the in-memory audit sink), never
/// crossing a wire or DB boundary as a whole. Keeping it non-deserializable
/// reinforces the fence — there is no path by which a client-supplied blob
/// becomes a `NewAuditEntry` (and thus a `CommunityId`).
#[derive(Debug, Clone, PartialEq, Eq)]
pub struct NewAuditEntry {
/// Server-resolved community this entry belongs to. Typed as [`CommunityId`]
/// (not a raw `Uuid`) so the provenance rule is visible in the signature:
/// the only ways to obtain one are host resolution or a server-scoped DB
/// row — never a value parsed from client input.
pub community_id: CommunityId,
/// Action that was performed.
pub action: AuditAction,
/// Raw bytes of the actor's Nostr pubkey, if the action has one.
pub actor_pubkey: Option<Vec<u8>>,
/// Generic identifier of the object acted upon, if any.
pub object_id: Option<String>,
/// Arbitrary JSON context included in the hash.
///
/// **Never bearer-token material.** This field is opaque to the audit
/// crate and persisted verbatim; callers must not write tokens, passwords,
/// or other secrets here. `AuthSuccess`/`AuthFailure` entries carry only
/// outcome metadata — the token has no slot in this type, and `detail` must
/// not become one.
pub detail: serde_json::Value,
}
+108
View File
@@ -0,0 +1,108 @@
use thiserror::Error;
/// Errors that can occur during audit log operations.
///
/// These are **operator-internal** diagnostics (logged by the audit worker, or
/// returned to an operator-scoped verification call) — they are never relayed to
/// a client on the wire. Even so, no variant embeds a `community_id` or any
/// cross-community object identifier: a `seq` is per-community and meaningless
/// without its chain, and hashes are opaque. An error raised while verifying
/// community A's chain therefore cannot reveal a fact about community B.
#[derive(Debug, Error)]
pub enum AuditError {
/// A database operation failed.
#[error("database error: {0}")]
Database(#[from] sqlx::Error),
/// The `prev_hash` of an entry does not match the hash of the preceding
/// entry in the same community's chain.
#[error(
"hash chain integrity violation at seq {seq}: prev_hash does not match preceding entry"
)]
ChainViolation {
/// Per-community sequence number of the offending entry.
seq: i64,
},
/// The stored hash of an entry does not match the recomputed hash.
#[error("hash mismatch at seq {seq}: stored hash does not match recomputed hash")]
HashMismatch {
/// Per-community sequence number of the offending entry.
seq: i64,
},
/// An unrecognised action string was found in the database.
#[error("unknown audit action in database")]
UnknownAction,
/// A JSON serialization error occurred (e.g. while canonicalising `detail`).
#[error("serialization error: {0}")]
Serialization(#[from] serde_json::Error),
}
#[cfg(test)]
mod tests {
use super::*;
/// The sanitization obligation for the conformance `audit_log` row: an error
/// raised while verifying or appending to one community's chain must not let
/// its rendered text become a cross-community identifier — no `community_id`,
/// no constraint name. Only `seq` may appear, and `seq` is per-community and
/// meaningless without the chain it indexes.
///
/// This is the *complement* to the structural fence in the variant
/// definitions above: those variants simply have no `community_id` field, so
/// there is no slot to leak one from. This test pins the observable form —
/// if anyone adds a `community_id` to a variant and threads it into the
/// `#[error(...)]` format string, the assertion below reds.
#[test]
fn audit_error_text_carries_no_community_id_or_constraint() {
// A concrete community whose chain is "being verified" when these errors
// fire. If its id leaked into any error text, the error would identify a
// specific tenant.
let community = uuid::Uuid::new_v4();
let community_str = community.to_string();
let community_simple = community.simple().to_string();
// The variants the audit crate constructs itself with chain-derived data.
let domain_errors = [
AuditError::ChainViolation { seq: 7 },
AuditError::HashMismatch { seq: 42 },
AuditError::UnknownAction,
];
for err in &domain_errors {
let text = err.to_string();
// No form of the community id may appear.
assert!(
!text.contains(&community_str) && !text.contains(&community_simple),
"audit error text leaked a community_id: {text:?}"
);
// No Postgres constraint/PK names that would reveal schema shape or
// the existence of a cross-community key.
for needle in [
"community_id",
"audit_log_pkey",
"constraint",
"communities",
] {
assert!(
!text.to_ascii_lowercase().contains(needle),
"audit error text leaked a constraint/identifier '{needle}': {text:?}"
);
}
}
// The two chain-integrity variants must still carry their per-community
// `seq` (the diagnostic is useless without it) — proves the assertion
// above isn't vacuously passing on empty strings.
assert!(AuditError::ChainViolation { seq: 7 }
.to_string()
.contains('7'));
assert!(AuditError::HashMismatch { seq: 42 }
.to_string()
.contains("42"));
}
}
+272
View File
@@ -0,0 +1,272 @@
use chrono::{DateTime, SubsecRound, Utc};
use sha2::{Digest, Sha256};
use crate::entry::AuditEntry;
use crate::error::AuditError;
/// The 32-byte sentinel hashed in place of `prev_hash` for a community's first
/// entry. Stored as `prev_hash = NULL`; hashed as all-zero bytes.
pub const GENESIS_HASH: [u8; 32] = [0u8; 32];
/// Reduce a timestamp to the precision the audit store round-trips.
///
/// `audit_log.created_at` is `TIMESTAMPTZ`, which Postgres keeps at microsecond
/// resolution. [`compute_hash`] covers `created_at.to_rfc3339()`, and that
/// string's sub-second digit count follows the value (chrono emits 0, 3, 6 or 9
/// digits), so a timestamp carrying nanoseconds hashes to a digest that can
/// never be recomputed from the stored row — the entry is written with one
/// preimage and verified against another.
///
/// Every `created_at` must therefore pass through here *before* it is hashed
/// and stored, so the in-memory entry and the row are byte-identical.
pub fn to_storage_precision(created_at: DateTime<Utc>) -> DateTime<Utc> {
created_at.trunc_subsecs(6)
}
/// SHA-256 over the entry's identity, chain, and context fields.
///
/// Field order is fixed — changing it invalidates all existing chains. The
/// `community_id` is hashed first so chain identity carries the tenant: an entry
/// cannot be lifted out of one community's chain and re-verified inside another.
///
/// `created_at` is normalized through [`to_storage_precision`] here rather than
/// hashed as given. Write paths truncate before storing so the row matches the
/// in-memory entry, but normalizing again at the single point that consumes the
/// value means no future caller can reintroduce the write/read preimage split
/// by forgetting to. Values already at storage precision are unaffected —
/// truncation is idempotent — so this does not change any digest.
///
/// `detail` is serialized via [`canonical_json`] (sorted keys) so the hash is
/// stable across machines and Rust versions. A serialization failure is a hard
/// error, never silently hashed as empty.
pub fn compute_hash(entry: &AuditEntry) -> Result<[u8; 32], AuditError> {
let mut hasher = Sha256::new();
// Tenant binding: community_id leads the hash.
hasher.update(entry.community_id.as_bytes());
hasher.update(entry.seq.to_be_bytes());
hasher.update(
to_storage_precision(entry.created_at)
.to_rfc3339()
.as_bytes(),
);
hasher.update(entry.action.as_str().as_bytes());
match &entry.actor_pubkey {
Some(pk) => {
hasher.update([1u8]); // presence tag — distinguishes Some(empty) from None
hasher.update(pk);
}
None => hasher.update([0u8]),
}
match &entry.object_id {
Some(id) => {
hasher.update([1u8]);
hasher.update(id.as_bytes());
}
None => hasher.update([0u8]),
}
hasher.update(canonical_json(&entry.detail)?.as_bytes());
match &entry.prev_hash {
Some(h) => hasher.update(h),
None => hasher.update(GENESIS_HASH),
}
Ok(hasher.finalize().into())
}
/// Serialize a JSON value with sorted object keys for deterministic output.
///
/// Propagates any scalar serialization error rather than substituting a
/// placeholder — a hash must never silently stand in an empty value for a real
/// payload.
fn canonical_json(value: &serde_json::Value) -> Result<String, serde_json::Error> {
use serde_json::Value;
use std::collections::BTreeMap;
match value {
Value::Object(map) => {
let sorted: BTreeMap<&str, &Value> = map.iter().map(|(k, v)| (k.as_str(), v)).collect();
let mut out = String::from("{");
let mut first = true;
for (k, v) in &sorted {
if !first {
out.push(',');
}
first = false;
out.push_str(&serde_json::to_string(k)?);
out.push(':');
out.push_str(&canonical_json(v)?);
}
out.push('}');
Ok(out)
}
Value::Array(arr) => {
let mut out = String::from("[");
let mut first = true;
for v in arr {
if !first {
out.push(',');
}
first = false;
out.push_str(&canonical_json(v)?);
}
out.push(']');
Ok(out)
}
other => serde_json::to_string(other),
}
}
#[cfg(test)]
mod tests {
use super::*;
use crate::{action::AuditAction, entry::AuditEntry};
use chrono::Utc;
use uuid::Uuid;
fn sample_entry() -> AuditEntry {
AuditEntry {
community_id: Uuid::from_u128(1),
seq: 1,
hash: Vec::new(),
prev_hash: None,
action: AuditAction::EventCreated,
actor_pubkey: Some(vec![0xab; 32]),
object_id: Some("abc123".into()),
detail: serde_json::Value::Null,
created_at: chrono::DateTime::parse_from_rfc3339("2026-01-01T00:00:00Z")
.unwrap()
.with_timezone(&Utc),
}
}
/// A wall-clock instant carrying sub-microsecond digits, like `Utc::now()`
/// returns on Linux (`clock_gettime`, nanosecond resolution).
fn nanosecond_instant() -> chrono::DateTime<Utc> {
chrono::DateTime::from_timestamp_nanos(1_700_000_000_123_456_789)
}
/// What Postgres hands back for a `TIMESTAMPTZ`: microsecond resolution.
fn after_database_round_trip(ts: chrono::DateTime<Utc>) -> chrono::DateTime<Utc> {
ts.trunc_subsecs(6)
}
#[test]
fn deterministic() {
let entry = sample_entry();
assert_eq!(compute_hash(&entry).unwrap(), compute_hash(&entry).unwrap());
assert_eq!(compute_hash(&entry).unwrap().len(), 32);
}
#[test]
fn storage_precision_drops_sub_microsecond_digits() {
let stored = to_storage_precision(nanosecond_instant());
assert_eq!(stored.timestamp_subsec_nanos(), 123_456_000);
// Idempotent, so a stored value re-read from Postgres is unchanged.
assert_eq!(stored, after_database_round_trip(stored));
}
#[test]
fn rfc3339_sub_second_width_follows_the_value() {
// The underlying trap, pinned on the preimage rather than the digest:
// chrono emits 0/3/6/9 fractional digits depending on the value, so a
// nanosecond timestamp and its microsecond truncation are *different
// strings*. Hashing the untruncated value therefore produces a digest
// that cannot be recomputed from the stored row — which is what made
// every entry fail `verify_chain` with `HashMismatch`.
let ns = nanosecond_instant();
assert_eq!(ns.to_rfc3339(), "2023-11-14T22:13:20.123456789+00:00");
assert_eq!(
after_database_round_trip(ns).to_rfc3339(),
"2023-11-14T22:13:20.123456+00:00"
);
assert_ne!(ns.to_rfc3339(), after_database_round_trip(ns).to_rfc3339());
}
#[test]
fn compute_hash_normalizes_sub_microsecond_timestamps() {
// The enforcement point: even handed an untruncated `created_at`,
// `compute_hash` digests the storage-precision value, so a write path
// that forgot to truncate cannot split the write/read preimage.
let ns = nanosecond_instant();
let mut written = sample_entry();
written.created_at = ns;
let mut read_back = sample_entry();
read_back.created_at = after_database_round_trip(ns);
assert_eq!(
compute_hash(&written).unwrap(),
compute_hash(&read_back).unwrap()
);
}
#[test]
fn storage_precision_timestamps_survive_a_database_round_trip() {
// The invariant the write path must hold: hash what will be stored, so
// recomputing from the row reproduces the digest.
let mut written = sample_entry();
written.created_at = to_storage_precision(nanosecond_instant());
let mut read_back = written.clone();
read_back.created_at = after_database_round_trip(read_back.created_at);
assert_eq!(
compute_hash(&written).unwrap(),
compute_hash(&read_back).unwrap()
);
}
#[test]
fn community_id_is_part_of_identity() {
// The whole point: the same logical entry in two communities hashes
// differently, so a row can't be replayed across chains.
let a = sample_entry();
let mut b = a.clone();
b.community_id = Uuid::from_u128(2);
assert_ne!(compute_hash(&a).unwrap(), compute_hash(&b).unwrap());
}
#[test]
fn sensitive_to_each_field() {
let base = sample_entry();
let h0 = compute_hash(&base).unwrap();
let mut e = base.clone();
e.seq = 2;
assert_ne!(h0, compute_hash(&e).unwrap());
let mut e = base.clone();
e.action = AuditAction::EventDeleted;
assert_ne!(h0, compute_hash(&e).unwrap());
let mut e = base.clone();
e.actor_pubkey = Some(vec![0xcd; 32]);
assert_ne!(h0, compute_hash(&e).unwrap());
let mut e = base.clone();
e.object_id = Some("different".into());
assert_ne!(h0, compute_hash(&e).unwrap());
let mut e = base.clone();
e.detail = serde_json::json!({"key": "value"});
assert_ne!(h0, compute_hash(&e).unwrap());
let mut e = base.clone();
e.prev_hash = Some(vec![0xff; 32]);
assert_ne!(h0, compute_hash(&e).unwrap());
}
#[test]
fn presence_tag_distinguishes_none_from_empty() {
// Some(empty) must not collide with None — the presence tag prevents it.
let mut none = sample_entry();
none.actor_pubkey = None;
let mut empty = sample_entry();
empty.actor_pubkey = Some(Vec::new());
assert_ne!(compute_hash(&none).unwrap(), compute_hash(&empty).unwrap());
}
#[test]
fn canonical_json_key_order_is_stable() {
let a = serde_json::json!({"z": 1, "a": 2, "m": 3});
let b = serde_json::json!({"a": 2, "m": 3, "z": 1});
assert_eq!(canonical_json(&a).unwrap(), canonical_json(&b).unwrap());
}
}
+35
View File
@@ -0,0 +1,35 @@
#![deny(unsafe_code)]
#![warn(missing_docs)]
//! Tamper-evident, **per-community** hash-chain audit log.
//!
//! Each community owns an independent chain: rows are keyed `(community_id, seq)`,
//! `seq` is monotonic *within a community*, and each entry chains to the previous
//! entry *of the same community* via SHA-256. The `community_id` is folded into the
//! hash, so a row lifted out of one community's chain can never verify inside
//! another's — chain identity carries the tenant. This is the audit half of the
//! non-interference floor (`auditHeads[c]` in `MultiTenantRelay.tla`): an audit
//! observation reveals only its own community's head.
//!
//! Writes for a given community are serialized by a **per-community** Postgres
//! advisory lock, so the chain stays consistent across relay processes without one
//! global lock serializing (and timing-coupling) every tenant.
//!
//! The `audit_log` table is owned by the consolidated `0001` migration — this crate
//! is pure chain logic and ships no DDL.
/// Audit action types recorded in the log.
pub mod action;
/// Audit log entry types (stored and input).
pub mod entry;
/// Error types for audit operations.
pub mod error;
/// SHA-256 hash computation for audit entries.
pub mod hash;
/// Audit log service — append and verify entries.
pub mod service;
pub use action::AuditAction;
pub use entry::{AuditEntry, NewAuditEntry};
pub use error::AuditError;
pub use hash::{compute_hash, GENESIS_HASH};
pub use service::AuditService;
+527
View File
@@ -0,0 +1,527 @@
use chrono::{DateTime, Utc};
use futures_util::FutureExt as _;
use sqlx::{Acquire, PgPool, Row};
use tracing::{debug, instrument, warn};
use uuid::Uuid;
use buzz_core::CommunityId;
use crate::{
action::AuditAction,
entry::{AuditEntry, NewAuditEntry},
error::AuditError,
hash::{compute_hash, to_storage_precision},
};
/// The `created_at` stamped on a new entry.
///
/// Reduced to the precision Postgres round-trips before it is hashed — see
/// [`to_storage_precision`]. Split out from [`AuditService::log_inner`] so the
/// invariant is testable without a database.
fn log_timestamp() -> DateTime<Utc> {
to_storage_precision(Utc::now())
}
/// Per-community advisory lock key. Derived in Postgres from the community UUID
/// so two communities never serialize each other's audit writes (which would be
/// both a throughput bottleneck and a cross-tenant timing oracle). The lock is
/// taken with `pg_advisory_lock(hashtextextended(...))` — see [`AuditService::log`].
const AUDIT_LOCK_NAMESPACE: &str = "buzz_audit:";
/// Append-only, per-community hash-chain audit log backed by Postgres.
///
/// Each community has an independent chain keyed `(community_id, seq)`. Writes
/// for one community are serialized by a per-community advisory lock so the chain
/// stays consistent across relay processes; different communities proceed in
/// parallel.
pub struct AuditService {
pool: PgPool,
}
impl AuditService {
/// Creates a new `AuditService` using the given connection pool.
pub fn new(pool: PgPool) -> Self {
Self { pool }
}
/// Append a new entry to the calling community's chain.
///
/// Serialized per-community via `pg_advisory_lock`. Postgres advisory locks
/// are session-scoped, so we acquire before the transaction and release
/// after commit (or on any error path).
#[instrument(skip(self, entry), fields(action = %entry.action))]
pub async fn log(&self, entry: NewAuditEntry) -> Result<AuditEntry, AuditError> {
let mut conn = self.pool.acquire().await?;
// Per-community advisory lock: hash the namespaced community id to an
// i64 lock key inside Postgres. Communities lock independently.
let lock_key = format!("{AUDIT_LOCK_NAMESPACE}{}", entry.community_id);
sqlx::query("SELECT pg_advisory_lock(hashtextextended($1, 0))")
.bind(&lock_key)
.execute(&mut *conn)
.await?;
// Run the chain append and release the lock regardless of outcome.
// catch_unwind so a panic still releases the lock before the connection
// returns to the pool.
let result = std::panic::AssertUnwindSafe(self.log_inner(&mut conn, entry))
.catch_unwind()
.await;
let _ = sqlx::query("SELECT pg_advisory_unlock(hashtextextended($1, 0))")
.bind(&lock_key)
.execute(&mut *conn)
.await;
match result {
Ok(inner_result) => inner_result,
Err(panic_payload) => std::panic::resume_unwind(panic_payload),
}
}
async fn log_inner(
&self,
conn: &mut sqlx::pool::PoolConnection<sqlx::Postgres>,
entry: NewAuditEntry,
) -> Result<AuditEntry, AuditError> {
let mut tx = conn.begin().await?;
// The stored row keys on the raw UUID; the typed `CommunityId` on the
// input is the provenance fence, dereferenced here at the DB boundary.
let community_id = *entry.community_id.as_uuid();
// Head of THIS community's chain — scoped by community_id.
let head = sqlx::query(
"SELECT seq, hash FROM audit_log
WHERE community_id = $1
ORDER BY seq DESC LIMIT 1",
)
.bind(community_id)
.fetch_optional(&mut *tx)
.await?;
let (prev_seq, prev_hash): (i64, Option<Vec<u8>>) = match head {
Some(row) => (
row.get::<i64, _>("seq"),
Some(row.get::<Vec<u8>, _>("hash")),
),
None => (0, None), // community's first entry
};
let seq = prev_seq + 1;
let created_at: DateTime<Utc> = log_timestamp();
let mut audit_entry = AuditEntry {
community_id,
seq,
hash: Vec::new(),
prev_hash,
action: entry.action,
actor_pubkey: entry.actor_pubkey,
object_id: entry.object_id,
detail: entry.detail,
created_at,
};
audit_entry.hash = compute_hash(&audit_entry)?.to_vec();
debug!(seq, "writing audit entry");
sqlx::query(
r#"
INSERT INTO audit_log
(community_id, seq, hash, prev_hash, action, actor_pubkey, object_id, detail, created_at)
VALUES ($1, $2, $3, $4, $5, $6, $7, $8, $9)
"#,
)
.bind(audit_entry.community_id)
.bind(audit_entry.seq)
.bind(&audit_entry.hash)
.bind(audit_entry.prev_hash.as_deref())
.bind(audit_entry.action.as_str())
.bind(audit_entry.actor_pubkey.as_deref())
.bind(audit_entry.object_id.as_deref())
.bind(&audit_entry.detail)
.bind(audit_entry.created_at)
.execute(&mut *tx)
.await?;
tx.commit().await?;
Ok(audit_entry)
}
/// Verify the hash chain for one community over `[from_seq, to_seq]`.
///
/// Reads exactly that community's chain — it can never observe another
/// community's entries or head. Returns `Ok(false)` if the range is empty,
/// `Ok(true)` if the segment is internally consistent.
#[instrument(skip(self))]
pub async fn verify_chain(
&self,
community: CommunityId,
from_seq: i64,
to_seq: i64,
) -> Result<bool, AuditError> {
let rows = sqlx::query(
r#"
SELECT community_id, seq, hash, prev_hash, action, actor_pubkey,
object_id, detail, created_at
FROM audit_log
WHERE community_id = $1 AND seq BETWEEN $2 AND $3
ORDER BY seq ASC
"#,
)
.bind(community.as_uuid())
.bind(from_seq)
.bind(to_seq)
.fetch_all(&self.pool)
.await?;
if rows.is_empty() {
return Ok(false);
}
let mut expected_prev: Option<Vec<u8>> = None;
for row in &rows {
let entry = row_to_audit_entry(row)?;
if let Some(ref expected) = expected_prev {
// The previous entry's hash must equal this entry's prev_hash.
if entry.prev_hash.as_deref() != Some(expected.as_slice()) {
return Err(AuditError::ChainViolation { seq: entry.seq });
}
}
let computed = compute_hash(&entry)?;
if computed.as_slice() != entry.hash.as_slice() {
return Err(AuditError::HashMismatch { seq: entry.seq });
}
expected_prev = Some(entry.hash);
}
Ok(true)
}
/// Returns up to `limit` entries from one community's chain starting at
/// `from_seq`, ordered by sequence number. Scoped to `community` — never
/// returns another community's rows.
#[instrument(skip(self))]
pub async fn get_entries(
&self,
community: CommunityId,
from_seq: i64,
limit: i64,
) -> Result<Vec<AuditEntry>, AuditError> {
let rows = sqlx::query(
r#"
SELECT community_id, seq, hash, prev_hash, action, actor_pubkey,
object_id, detail, created_at
FROM audit_log
WHERE community_id = $1 AND seq >= $2
ORDER BY seq ASC
LIMIT $3
"#,
)
.bind(community.as_uuid())
.bind(from_seq)
.bind(limit)
.fetch_all(&self.pool)
.await?;
rows.iter().map(row_to_audit_entry).collect()
}
}
fn row_to_audit_entry(row: &sqlx::postgres::PgRow) -> Result<AuditEntry, AuditError> {
let action_str: String = row.get("action");
let action: AuditAction = action_str.parse().map_err(|_| {
warn!("unknown action in audit log");
AuditError::UnknownAction
})?;
Ok(AuditEntry {
community_id: row.get::<Uuid, _>("community_id"),
seq: row.get("seq"),
hash: row.get("hash"),
prev_hash: row.get("prev_hash"),
action,
actor_pubkey: row.get("actor_pubkey"),
object_id: row.get("object_id"),
detail: row.get("detail"),
created_at: row.get("created_at"),
})
}
#[cfg(test)]
mod tests {
use super::*;
use crate::action::AuditAction;
use crate::entry::NewAuditEntry;
use chrono::SubsecRound;
use std::sync::OnceLock;
use tokio::sync::Mutex;
use uuid::Uuid;
// The per-community advisory lock means different communities don't contend,
// but tests share one table; serialize them so seq assertions are stable.
static DB_LOCK: OnceLock<Mutex<()>> = OnceLock::new();
fn db_lock() -> &'static Mutex<()> {
DB_LOCK.get_or_init(|| Mutex::new(()))
}
async fn test_pool() -> Option<PgPool> {
let url = std::env::var("DATABASE_URL")
.unwrap_or_else(|_| "postgres://buzz:buzz_dev@localhost:5432/buzz".into());
PgPool::connect(&url).await.ok()
}
/// Runs without Postgres, so a regression here is caught by `just
/// test-unit` rather than only by the `#[ignore]` chain tests below.
#[test]
fn log_timestamp_carries_no_sub_microsecond_digits() {
let ts = log_timestamp();
assert_eq!(
ts,
ts.trunc_subsecs(6),
"created_at is hashed and then stored in a TIMESTAMPTZ column; \
sub-microsecond digits make every entry fail verify_chain"
);
}
/// A `community_id` known to exist in `communities` (FK target). Inserts a
/// throwaway community row with a unique host and returns its id.
async fn make_community(pool: &PgPool) -> Uuid {
let id = Uuid::new_v4();
let host = format!("test-{id}.example");
sqlx::query("INSERT INTO communities (id, host) VALUES ($1, $2)")
.bind(id)
.bind(host)
.execute(pool)
.await
.expect("insert test community");
id
}
fn new_entry(community_id: Uuid, action: AuditAction) -> NewAuditEntry {
NewAuditEntry {
community_id: CommunityId::from_uuid(community_id),
action,
actor_pubkey: Some(vec![0xab; 32]),
object_id: Some(format!("obj_{}", Uuid::new_v4())),
detail: serde_json::json!({"test": true}),
}
}
#[tokio::test]
#[ignore = "requires Postgres"]
async fn community_chain_starts_at_seq_1_with_null_prev() {
let _g = db_lock().lock().await;
let Some(pool) = test_pool().await else {
return;
};
let svc = AuditService::new(pool.clone());
let c = make_community(&pool).await;
let e = svc
.log(new_entry(c, AuditAction::EventCreated))
.await
.unwrap();
assert_eq!(e.seq, 1, "first entry in a community starts at seq 1");
assert!(e.prev_hash.is_none(), "genesis entry has NULL prev_hash");
assert_eq!(e.hash.len(), 32);
assert_eq!(e.community_id, c);
}
#[tokio::test]
#[ignore = "requires Postgres"]
async fn chain_links_within_one_community() {
let _g = db_lock().lock().await;
let Some(pool) = test_pool().await else {
return;
};
let svc = AuditService::new(pool.clone());
let c = make_community(&pool).await;
let e1 = svc
.log(new_entry(c, AuditAction::EventCreated))
.await
.unwrap();
let e2 = svc
.log(new_entry(c, AuditAction::ChannelCreated))
.await
.unwrap();
let e3 = svc
.log(new_entry(c, AuditAction::MemberAdded))
.await
.unwrap();
assert_eq!(e1.seq, 1);
assert_eq!(e2.seq, 2);
assert_eq!(e3.seq, 3);
assert!(e1.prev_hash.is_none());
assert_eq!(e2.prev_hash.as_deref(), Some(e1.hash.as_slice()));
assert_eq!(e3.prev_hash.as_deref(), Some(e2.hash.as_slice()));
assert!(svc
.verify_chain(CommunityId::from_uuid(c), 1, 3)
.await
.unwrap());
}
/// THE isolation property: two communities keep independent chains. Each
/// starts at seq 1; interleaving writes does not link them; verifying one
/// never traverses the other.
#[tokio::test]
#[ignore = "requires Postgres"]
async fn chains_are_independent_per_community() {
let _g = db_lock().lock().await;
let Some(pool) = test_pool().await else {
return;
};
let svc = AuditService::new(pool.clone());
let a = make_community(&pool).await;
let b = make_community(&pool).await;
// Interleave A and B writes.
let a1 = svc
.log(new_entry(a, AuditAction::EventCreated))
.await
.unwrap();
let b1 = svc
.log(new_entry(b, AuditAction::EventCreated))
.await
.unwrap();
let a2 = svc
.log(new_entry(a, AuditAction::ChannelCreated))
.await
.unwrap();
let b2 = svc
.log(new_entry(b, AuditAction::ChannelCreated))
.await
.unwrap();
// Each community's seq is independent and starts at 1.
assert_eq!((a1.seq, a2.seq), (1, 2));
assert_eq!((b1.seq, b2.seq), (1, 2));
// A's chain links only within A; B's only within B. A2 must NOT chain to
// B1 even though B1 was written between A1 and A2.
assert_eq!(a2.prev_hash.as_deref(), Some(a1.hash.as_slice()));
assert_eq!(b2.prev_hash.as_deref(), Some(b1.hash.as_slice()));
assert_ne!(a2.prev_hash, b1.prev_hash);
// Verifying A's chain traverses only A; same for B.
assert!(svc
.verify_chain(CommunityId::from_uuid(a), 1, 2)
.await
.unwrap());
assert!(svc
.verify_chain(CommunityId::from_uuid(b), 1, 2)
.await
.unwrap());
// get_entries scoped to A returns only A's rows.
let a_rows = svc
.get_entries(CommunityId::from_uuid(a), 1, 100)
.await
.unwrap();
assert!(
a_rows.iter().all(|e| e.community_id == a),
"A read leaked another community"
);
assert_eq!(a_rows.len(), 2);
}
#[tokio::test]
#[ignore = "requires Postgres"]
async fn verify_detects_tampering_within_a_community() {
let _g = db_lock().lock().await;
let Some(pool) = test_pool().await else {
return;
};
let svc = AuditService::new(pool.clone());
let c = make_community(&pool).await;
svc.log(new_entry(c, AuditAction::EventCreated))
.await
.unwrap();
let e2 = svc
.log(new_entry(c, AuditAction::EventDeleted))
.await
.unwrap();
svc.log(new_entry(c, AuditAction::ChannelDeleted))
.await
.unwrap();
// Tamper with e2's stored actor_pubkey.
let tampered: Vec<u8> = vec![0xff; 32];
sqlx::query("UPDATE audit_log SET actor_pubkey = $1 WHERE community_id = $2 AND seq = $3")
.bind(tampered)
.bind(c)
.bind(e2.seq)
.execute(&pool)
.await
.unwrap();
let r = svc.verify_chain(CommunityId::from_uuid(c), 1, 3).await;
assert!(matches!(r, Err(AuditError::HashMismatch { seq }) if seq == e2.seq));
}
/// A row forged with another community's id cannot pass verification against
/// the chain it was stamped for, because community_id is hashed in. (Models
/// "a row can't be replayed across chains and still verify".)
#[tokio::test]
#[ignore = "requires Postgres"]
async fn cross_community_row_does_not_verify() {
let _g = db_lock().lock().await;
let Some(pool) = test_pool().await else {
return;
};
let svc = AuditService::new(pool.clone());
let a = make_community(&pool).await;
let b = make_community(&pool).await;
let a1 = svc
.log(new_entry(a, AuditAction::EventCreated))
.await
.unwrap();
// Forge: copy A's seq-1 row's hash into B's chain at seq 1.
sqlx::query(
"INSERT INTO audit_log (community_id, seq, hash, prev_hash, action, actor_pubkey, object_id, detail, created_at)
VALUES ($1, 1, $2, NULL, $3, $4, $5, $6, NOW())",
)
.bind(b)
.bind(&a1.hash) // A's hash, which was computed over community_id = A
.bind(a1.action.as_str())
.bind(a1.actor_pubkey.as_deref())
.bind(a1.object_id.as_deref())
.bind(&a1.detail)
.execute(&pool)
.await
.unwrap();
// Verifying B's chain recomputes the hash with community_id = B, which
// won't match A's stored hash → HashMismatch. The forge is rejected.
let r = svc.verify_chain(CommunityId::from_uuid(b), 1, 1).await;
assert!(matches!(r, Err(AuditError::HashMismatch { seq: 1 })));
}
#[tokio::test]
#[ignore = "requires Postgres"]
async fn verify_empty_range_is_false() {
let _g = db_lock().lock().await;
let Some(pool) = test_pool().await else {
return;
};
let svc = AuditService::new(pool.clone());
let c = make_community(&pool).await;
// No entries for this fresh community.
assert!(!svc
.verify_chain(CommunityId::from_uuid(c), 1, 100)
.await
.unwrap());
}
}