fix: allowlist public system input projections

This commit is contained in:
2026-10-20 02:02:28 +09:00
parent e8dfb3e68d
commit cd0eb5eb00
9 changed files with 194 additions and 41 deletions
+4 -6
View File
@@ -1180,12 +1180,10 @@ pub enum Event {
},
/// One agent-injected system item committed to history.
///
/// Carries the JSON form of `session_store::SystemItem`. Covers
/// `Method::Notify` echoes, child-Worker lifecycle events from
/// `Method::WorkerEvent`, `@<path>` resolution payloads, and any future
/// Clients dispatch on the `kind` tag for typed rendering instead
/// of parsing free-text prefixes like `[Notification] …` or
/// `[File: …]`.
/// Carries the allowlisted JSON form of `session_store::PublicSystemItem`,
/// not the storage record. Its descriptive `kind` is independent from the
/// typed `presentation` used for notification, reminder, or context rendering.
/// Private Feature payloads and prompt provenance are never event data.
///
/// One event per `LogEntry::AnnotatedSystemItem` commit. Disk-side and
/// wire-side are 1:1.
+2 -1
View File
@@ -98,7 +98,8 @@ pub use segment::{
pub use segment_log::{LogEntry, RestoredState, SegmentOrigin, SessionExtension, collect_state};
pub use store::{Store, StoreError};
pub use system_item::{
PromptRenderProvenance, SystemItem, SystemReminder, SystemReminderSource, render_worker_event,
PromptRenderProvenance, PublicSystemItem, PublicSystemPresentation, SystemItem, SystemReminder,
SystemReminderSource, render_worker_event,
};
pub use uploaded_file::{
DEFAULT_MAX_FILES_PER_SUBMISSION, DEFAULT_MAX_SESSION_ARTIFACT_BYTES,
+5 -11
View File
@@ -1992,16 +1992,10 @@ fn system_entry(
provenance: SessionEntryProvenance,
derived_from: Vec<String>,
) -> SessionSnapshotEntry {
let mut data = serde_json::to_value(item).ok();
if let Some(serde_json::Value::Object(object)) = data.as_mut() {
object.remove("prompt_provenance");
}
let item_kind = data
.as_ref()
.and_then(|value| value.get("kind"))
.and_then(serde_json::Value::as_str)
.unwrap_or("system_item")
.to_owned();
let public = item.public_item();
let data = Some(serde_json::to_value(&public).expect("public system input is serializable"));
let item_kind = public.kind;
let content = public.body;
SessionSnapshotEntry {
entry_id,
timestamp,
@@ -2009,7 +2003,7 @@ fn system_entry(
derived_from,
data: SessionSnapshotEntryData::SystemItem {
item_kind,
content: item.history_text(),
content,
data,
},
}
+76
View File
@@ -197,7 +197,58 @@ pub enum SystemItem {
},
}
/// Allowlisted presentation data shared by live events and retained snapshots.
/// Private Feature payloads and render provenance never cross this boundary.
#[derive(Debug, Clone, Serialize, Deserialize)]
#[serde(deny_unknown_fields)]
pub struct PublicSystemItem {
pub kind: String,
pub body: String,
pub presentation: PublicSystemPresentation,
}
#[derive(Debug, Clone, Serialize, Deserialize)]
#[serde(tag = "kind", rename_all = "snake_case", deny_unknown_fields)]
pub enum PublicSystemPresentation {
Notification { message: String },
WorkerEvent { event: WorkerEvent },
Context,
TaskReminder,
Ignored,
}
impl SystemItem {
pub fn public_item(&self) -> PublicSystemItem {
let presentation = match self {
Self::Notification { message, .. } => PublicSystemPresentation::Notification {
message: message.clone(),
},
Self::WorkerEvent { event, .. } => PublicSystemPresentation::WorkerEvent {
event: event.clone(),
},
Self::TaskReminder { .. } => PublicSystemPresentation::TaskReminder,
Self::LegacyKnowledgeIgnored { .. } | Self::LegacyIgnored { .. } => {
PublicSystemPresentation::Ignored
}
Self::JournalStartup { .. }
| Self::ResidentSummaryRefresh { .. }
| Self::SubjectBehaviorRefresh { .. }
| Self::SkillActivation { .. }
| Self::FeatureInvocationResult { .. }
| Self::FileAttachment { .. }
| Self::Interrupt { .. } => PublicSystemPresentation::Context,
};
PublicSystemItem {
kind: self.kind_label().to_owned(),
body: if matches!(presentation, PublicSystemPresentation::Ignored) {
String::new()
} else {
self.history_text()
},
presentation,
}
}
/// Free-text body the LLM sees inside its `role:system` message
/// for this item. Returns the variant's stored `body` verbatim.
pub fn history_text(&self) -> String {
@@ -311,6 +362,31 @@ mod tests {
);
}
#[test]
fn public_system_input_decoder_rejects_private_fields_and_unknown_presentations() {
let valid = serde_json::json!({
"kind": "new-feature-label",
"body": "explicit public content",
"presentation": { "kind": "context" },
});
let public: PublicSystemItem = serde_json::from_value(valid.clone()).unwrap();
assert_eq!(public.body, "explicit public content");
for private_field in [
"payload",
"prompt_provenance",
"policy",
"snapshot",
"behavior_md",
] {
let mut malformed = valid.clone();
malformed[private_field] = serde_json::json!({ "private": true });
assert!(serde_json::from_value::<PublicSystemItem>(malformed).is_err());
}
let mut unknown = valid;
unknown["presentation"] = serde_json::json!({ "kind": "execute_feature_payload" });
assert!(serde_json::from_value::<PublicSystemItem>(unknown).is_err());
}
#[test]
fn frozen_subject_behavior_log_reads_old_counter_without_republishing_it() {
let old = r#"{"kind":"subject_behavior_refresh","body":"exact archived body","behavior_revision":7}"#;
+34 -20
View File
@@ -3013,7 +3013,8 @@ impl App {
/// `[File: …]` parsing path: each kind maps directly to a typed
/// block (`Block::Notify`, `Block::WorkerEvent`, …).
fn apply_system_item(&mut self, value: &serde_json::Value) {
let Ok(item) = serde_json::from_value::<session_store::SystemItem>(value.clone()) else {
let Ok(item) = serde_json::from_value::<session_store::PublicSystemItem>(value.clone())
else {
// Unknown / forward-compat shape: fall back to rendering the
// raw text payload (if any) as a generic system message.
if let Some(text) = value.get("body").and_then(|b| b.as_str()) {
@@ -3024,29 +3025,23 @@ impl App {
}
return;
};
match item {
session_store::SystemItem::Notification { message, .. } => {
let body = item.body;
match item.presentation {
session_store::PublicSystemPresentation::Notification { message } => {
self.blocks.push(Block::Notify { message });
}
session_store::SystemItem::WorkerEvent { event, .. } => {
session_store::PublicSystemPresentation::WorkerEvent { event } => {
self.blocks.push(Block::WorkerEvent { event });
}
session_store::SystemItem::FeatureInvocationResult { body, .. }
| session_store::SystemItem::FileAttachment { body, .. }
| session_store::SystemItem::SkillActivation { body, .. }
| session_store::SystemItem::JournalStartup { body, .. }
| session_store::SystemItem::ResidentSummaryRefresh { body, .. }
| session_store::SystemItem::SubjectBehaviorRefresh { body, .. }
| session_store::SystemItem::Interrupt { body, .. } => {
session_store::PublicSystemPresentation::Context => {
self.task_store.apply_system_message_text(&body);
self.blocks.push(Block::SystemMessage { text: body });
}
session_store::SystemItem::TaskReminder { body, .. } => {
session_store::PublicSystemPresentation::TaskReminder => {
self.task_store.apply_system_message_text(&body);
self.blocks.push(Block::TaskReminder { text: body });
}
session_store::SystemItem::LegacyIgnored { .. } => {}
session_store::SystemItem::LegacyKnowledgeIgnored { .. } => {}
session_store::PublicSystemPresentation::Ignored => {}
}
}
@@ -4450,12 +4445,12 @@ mod completion_flow_tests {
}
#[test]
fn live_legacy_workflow_system_item_is_ignored() {
fn retired_system_input_is_ignored() {
let mut app = App::new("test".into());
let item = serde_json::json!({
"kind": "workflow",
"slug": "build",
"body": "[Workflow /build]\nRun the build",
"kind": "retired_input",
"body": "",
"presentation": { "kind": "ignored" },
});
app.handle_worker_event(Event::SystemItem {
entry_id: None,
@@ -4861,12 +4856,30 @@ mod completion_flow_tests {
);
}
#[test]
fn feature_label_does_not_select_system_input_presentation() {
for label in ["journal_startup", "new-unregistered-feature"] {
let mut app = App::new("test".into());
app.handle_worker_event(Event::SystemItem {
entry_id: None,
item: serde_json::json!({
"kind": label,
"body": "explicit public content",
"presentation": { "kind": "context" },
}),
});
assert!(
matches!(app.blocks.as_slice(), [Block::SystemMessage { text }] if text == "explicit public content")
);
}
}
#[test]
fn live_system_item_notification_appends_notify_block() {
let mut app = App::new("test".into());
let item = serde_json::json!({
"kind": "notification",
"message": "hi",
"presentation": { "kind": "notification", "message": "hi" },
"body": "[Notification] hi",
});
app.handle_worker_event(Event::SystemItem {
@@ -4884,7 +4897,7 @@ mod completion_flow_tests {
let mut app = App::new("test".into());
let item = serde_json::json!({
"kind": "worker_event",
"event": { "kind": "turn_ended", "worker_name": "child" },
"presentation": { "kind": "worker_event", "event": { "kind": "turn_ended", "worker_name": "child" } },
"body": "[Notification] worker `child` finished a turn",
});
app.handle_worker_event(Event::SystemItem {
@@ -5285,6 +5298,7 @@ mod completion_flow_tests {
item: serde_json::json!({
"kind": "task_reminder",
"body": snapshot,
"presentation": { "kind": "task_reminder" },
}),
});
+70 -1
View File
@@ -90,7 +90,8 @@ pub fn live_log_entry_event(entry: LogEntry) -> Option<Event> {
}
LogEntry::AnnotatedSystemItem { entry, .. } => {
let entry_id = Some(entry.metadata.entry_id.0.clone());
let value = serde_json::to_value(&entry.item).expect("SystemItem is Serialize");
let value = serde_json::to_value(entry.item.public_item())
.expect("public system input is serializable");
Some(Event::SystemItem {
entry_id,
item: value,
@@ -370,6 +371,74 @@ mod tests {
}
}
#[test]
fn live_and_snapshot_system_projection_exclude_private_feature_fields() {
let provenance = session_store::PromptRenderProvenance {
workspace_id: Some("private-workspace".into()),
source_digest: "private-source".into(),
projection_digest: "private-projection".into(),
logical_name: "private-template".into(),
};
let items = [
session_store::SystemItem::SubjectBehaviorRefresh {
body: "displayed context".into(),
behavior_md: "private-raw-behavior".into(),
prompt_provenance: Some(provenance.clone()),
},
session_store::SystemItem::JournalStartup {
body: "displayed reference".into(),
snapshot: serde_json::json!({ "internal": "private-snapshot" }),
snapshot_sha256: "private-snapshot-digest".into(),
prompt_provenance: provenance,
},
];
for item in items {
let entry = LogEntry::AnnotatedSystemItem {
ts: 7,
entry: session_store::LoggedSystemHistoryEntry {
item,
metadata: session_store::LoggedSessionHistoryMetadata::legacy_unknown(),
},
extensions: vec![],
};
let persisted: LogEntry =
serde_json::from_slice(&serde_json::to_vec(&entry).unwrap()).unwrap();
let snapshot = session_store::public_snapshot::project_current_session_snapshot(&[
persisted.clone(),
]);
let Event::SystemItem {
entry_id,
item: live,
} = live_log_entry_event(persisted).unwrap()
else {
panic!("expected live system input");
};
let snapshot_entry = &snapshot.entries[0];
assert_eq!(entry_id.as_deref(), Some(snapshot_entry.entry_id.as_str()));
let protocol::SessionSnapshotEntryData::SystemItem {
data: Some(saved),
content,
..
} = &snapshot_entry.data
else {
panic!("expected canonical public system input");
};
assert_eq!(&live, saved);
let public: session_store::PublicSystemItem =
serde_json::from_value(live.clone()).unwrap();
assert_eq!(&public.body, content);
assert!(matches!(
public.presentation,
session_store::PublicSystemPresentation::Context
));
let encoded = serde_json::to_string(&snapshot).unwrap();
assert!(!encoded.contains("private-"));
assert!(live.get("prompt_provenance").is_none());
assert!(live.get("snapshot").is_none());
assert!(live.get("behavior_md").is_none());
}
}
#[test]
fn user_input_log_entry_maps_to_user_message_event() {
let segments = vec![protocol::Segment::text("hello from log")];
+1 -1
View File
@@ -3087,7 +3087,7 @@ async fn socket_worker_event_turn_ended_while_idle_auto_starts_turn() {
Ok(Some(Event::SystemItem { ref item, .. }))
if item.get("kind").and_then(|k| k.as_str()) == Some("worker_event")
&& item
.pointer("/event/worker_name")
.pointer("/presentation/event/worker_name")
.and_then(|v| v.as_str()) == Some("child") =>
{
saw_worker_event_echo = true;
File diff suppressed because one or more lines are too long
@@ -3943,6 +3943,7 @@ Deno.test("live system items reconcile with committed history by entry identity"
const item = {
kind: "resident_summary_refresh",
body: "Resident memory refresh",
presentation: { kind: "context" },
};
const event: Event = {
event: "system_item",