Merge codex-security-s11-presence-discovery: honest presence/discovery state on apply failure (S11)

This commit is contained in:
2026-06-18 03:32:42 -04:00
4 changed files with 259 additions and 57 deletions
+7 -5
View File
@@ -955,13 +955,15 @@ fn update(state: &mut AppState, message: AppMessage) -> Task<AppMessage> {
state.friend_presence.insert(id, presence);
}
UiEvent::PresenceModeReverted { mode } => {
// The Discoverable time-box elapsed; core dropped us back to
// `mode` (Normal) and stopped publishing. Mirror + persist so the
// presence picker reflects it, and tell the user why it changed.
// Core corrected the committed presence mode. Mirror + persist so
// the picker reflects the discovery state the endpoint actually has.
state.config.presence_mode = mode;
state.config.save();
state.status_message =
"Discoverable timed out — back to Normal".to_string();
state.status_message = if mode == PresenceMode::Normal {
"Discoverable timed out — back to Normal".to_string()
} else {
format!("Presence mode stayed {mode}")
};
}
UiEvent::ShutdownComplete => {
if state.closing {
+4 -5
View File
@@ -124,11 +124,10 @@ pub enum UiEvent {
/// joinable gathering (with a one-click ticket). Emitted by the outbound ping
/// scheduler; absence of a recent event = treat as offline.
FriendPresence { id: EndpointId, presence: FriendPresence },
/// The Discoverable time-box elapsed (W7 P6): the core auto-reverted our presence
/// posture to the carried `mode` (always `Normal`) and stopped publishing. The
/// GUI must mirror + persist this so its presence picker stops showing
/// Discoverable. Distinct from a user-driven change so the GUI knows to update
/// without having issued the command itself.
/// Core corrected the committed presence posture. Usually the Discoverable
/// time-box elapsed and the core auto-reverted to `Normal`; on discovery apply
/// failure, this carries the previous truthful mode. The GUI must mirror +
/// persist this so its presence picker matches the endpoint's discovery state.
PresenceModeReverted { mode: PresenceMode },
/// Core finished orderly app shutdown and the GUI can exit.
ShutdownComplete,
+152 -37
View File
@@ -13,6 +13,7 @@ use crate::network::{
use crate::core::messages::{CoreCommand, UiEvent};
use crate::config::{NetworkMode, RecordingMode};
use crate::presence::PresenceMode;
use crate::audio::multitrack::MultitrackRecorder;
use iroh::{Endpoint, EndpointAddr, EndpointId, RelayMode, SecretKey, endpoint::presets, protocol::Router};
use iroh_gossip::net::Gossip;
@@ -69,10 +70,27 @@ const RECONNECT_GRACE: Duration = Duration::from_secs(45);
/// 48 kHz / 60 ms frame) while bounding malicious datagram copy/decode churn.
const MAX_OPUS_PAYLOAD: usize = 4000;
/// If the Discoverable time-box tries to revert but discovery service reconfiguration
/// fails, retry soon while keeping the UI in the still-possible publishing state.
const DISCOVERY_REVERT_RETRY: Duration = Duration::from_secs(60);
fn audio_datagram_len_ok(len: usize) -> bool {
(4..=4 + MAX_OPUS_PAYLOAD).contains(&len)
}
fn arm_discovery_retry(
discovery_deadline: &mut Option<tokio::time::Instant>,
now: tokio::time::Instant,
) {
let retry_deadline = now + DISCOVERY_REVERT_RETRY;
if discovery_deadline
.map(|current| current > retry_deadline)
.unwrap_or(true)
{
*discovery_deadline = Some(retry_deadline);
}
}
/// Per-peer reconnect grace timers (see [`RECONNECT_GRACE`]). Shared between the
/// room-event task (which arms one on a transient drop and cancels it on a
/// gossip rejoin) and the conn-event task (which cancels it when the audio link
@@ -466,12 +484,11 @@ impl NetStack {
/// `DnsAddressLookup`, mirroring the `N0` preset) is added when `plan.resolver`; the
/// n0 DNS *publisher* (`PkarrPublisher`) when `plan.publisher`.
///
/// Idempotent and reversible: it clears the whole service set and reinstalls exactly
/// what the plan wants, so flipping `publisher` off simply drops the publisher (its
/// republish task ends when the last clone is dropped, and the already-published
/// record TTL-expires within ~30s) without an endpoint rebuild and without disturbing
/// resolution. The brief clear→re-add window is a few synchronous calls; presence
/// toggles are rare, so a concurrent dial racing it is not a practical concern.
/// Idempotent and reversible: it builds the replacement services first, then clears
/// the service set and reinstalls exactly what the plan wants. Flipping `publisher`
/// off drops the publisher (its republish task ends when the last clone is dropped,
/// and the already-published record TTL-expires within ~30s) without an endpoint
/// rebuild and without disturbing resolution.
fn apply_discovery(
endpoint: &Endpoint,
memory_lookup: &iroh::address_lookup::memory::MemoryLookup,
@@ -482,16 +499,34 @@ fn apply_discovery(
pkarr::{PkarrPublisher, PkarrResolver},
};
let services = endpoint.address_lookup()?;
let pkarr_resolver = if plan.resolver {
Some(PkarrResolver::n0_dns().into_address_lookup(endpoint)?)
} else {
None
};
let dns_resolver = if plan.resolver {
Some(DnsAddressLookup::n0_dns().into_address_lookup(endpoint)?)
} else {
None
};
let publisher = if plan.publisher {
Some(PkarrPublisher::n0_dns().into_address_lookup(endpoint)?)
} else {
None
};
services.clear();
// Always keep the local, server-free lookup (this is what ticket/gossip dialing
// depends on — it must survive every posture, including DirectOnly).
services.add(memory_lookup.clone());
if plan.resolver {
services.add(PkarrResolver::n0_dns().into_address_lookup(endpoint)?);
services.add(DnsAddressLookup::n0_dns().into_address_lookup(endpoint)?);
if let Some(pkarr_resolver) = pkarr_resolver {
services.add(pkarr_resolver);
}
if plan.publisher {
services.add(PkarrPublisher::n0_dns().into_address_lookup(endpoint)?);
if let Some(dns_resolver) = dns_resolver {
services.add(dns_resolver);
}
if let Some(publisher) = publisher {
services.add(publisher);
}
Ok(())
}
@@ -851,22 +886,64 @@ async fn run_core_loop(
// W7 P6 time-box: Discoverable auto-reverts to Normal after DISCOVERY_TIMEBOX
// so a publish beacon never stands indefinitely. The branch is disabled
// (`if` guard) unless a deadline is armed; `unwrap_or_else` is unreachable
// belt-and-braces. On fire: stop publishing, drop to Normal, tell the GUI.
// belt-and-braces. On fire: stop publishing first, then commit Normal only
// if the endpoint's discovery services accepted the non-publishing plan.
_ = tokio::time::sleep_until(
discovery_deadline.unwrap_or_else(tokio::time::Instant::now),
), if discovery_deadline.is_some() => {
discovery_deadline = None;
*presence_mode.lock().unwrap() = crate::presence::PresenceMode::Normal;
let plan = crate::discovery::lookup_plan(network_mode, false);
if let Err(e) = apply_discovery(&net.endpoint, &net.memory_lookup, plan) {
crate::log_msg(&format!("discovery: time-box revert failed: {e:#}"));
let previous_mode = *presence_mode.lock().unwrap();
if previous_mode != PresenceMode::Discoverable {
discovery_deadline = None;
continue;
}
let requested_mode = PresenceMode::Normal;
let now = tokio::time::Instant::now();
let plan = crate::discovery::lookup_plan(
network_mode,
requested_mode.publishes_to_discovery(),
);
let apply_result = apply_discovery(&net.endpoint, &net.memory_lookup, plan);
let (committed_mode, transition_error) =
crate::discovery::resolve_presence_transition(
previous_mode,
requested_mode,
apply_result.is_ok(),
);
*presence_mode.lock().unwrap() = committed_mode;
discovery_deadline = if committed_mode == PresenceMode::Discoverable {
Some(now + DISCOVERY_REVERT_RETRY)
} else {
None
};
match apply_result {
Ok(()) => {
crate::log_msg(
"discovery: Discoverable time-box elapsed → reverting to Normal",
);
let _ = ui_tx
.send(UiEvent::PresenceModeReverted {
mode: PresenceMode::Normal,
})
.await;
}
Err(e) => {
crate::log_msg(&format!("discovery: time-box revert failed: {e:#}"));
if committed_mode != requested_mode {
let _ = ui_tx
.send(UiEvent::PresenceModeReverted {
mode: committed_mode,
})
.await;
}
if let Some(message) = transition_error {
let _ = ui_tx
.send(UiEvent::Error(format!("{message} ({e:#})")))
.await;
}
}
}
crate::log_msg("discovery: Discoverable time-box elapsed → reverting to Normal");
let _ = ui_tx
.send(UiEvent::PresenceModeReverted {
mode: crate::presence::PresenceMode::Normal,
})
.await;
continue;
}
};
@@ -1798,22 +1875,60 @@ async fn run_core_loop(
}
CoreCommand::SetPresenceMode(mode) => {
*presence_mode.lock().unwrap() = mode;
// W7 P6: re-apply n0 DNS discovery for the new posture (publish on iff
// Discoverable). Runtime — no endpoint rebuild; clears + reinstalls the
// address-lookup services. The resolver stays on regardless so we can
// still look up moved friends.
let plan = crate::discovery::lookup_plan(network_mode, mode.publishes_to_discovery());
if let Err(e) = apply_discovery(&net.endpoint, &net.memory_lookup, plan) {
crate::log_msg(&format!("discovery: apply failed: {e:#}"));
let previous_mode = *presence_mode.lock().unwrap();
let now = tokio::time::Instant::now();
if previous_mode == mode {
// Same-mode requests are no-ops for discovery wiring, but keep the
// existing UX: re-selecting Discoverable restarts the clock.
discovery_deadline = if mode == PresenceMode::Discoverable {
Some(now + crate::discovery::DISCOVERY_TIMEBOX)
} else {
None
};
continue;
}
// Arm (Discoverable) or cancel (any other posture) the auto-revert
// time-box. Re-selecting Discoverable restarts the clock.
discovery_deadline = if mode == crate::presence::PresenceMode::Discoverable {
Some(tokio::time::Instant::now() + crate::discovery::DISCOVERY_TIMEBOX)
// W7 P6/S11: re-apply n0 DNS discovery for the requested posture
// first, then commit the presence mode only if the endpoint accepted
// that discovery plan. This keeps the UI truthful when dropping the
// publisher fails.
let plan =
crate::discovery::lookup_plan(network_mode, mode.publishes_to_discovery());
let apply_result = apply_discovery(&net.endpoint, &net.memory_lookup, plan);
let (committed_mode, transition_error) =
crate::discovery::resolve_presence_transition(
previous_mode,
mode,
apply_result.is_ok(),
);
*presence_mode.lock().unwrap() = committed_mode;
if committed_mode == PresenceMode::Discoverable {
if apply_result.is_ok() && mode == PresenceMode::Discoverable {
discovery_deadline = Some(now + crate::discovery::DISCOVERY_TIMEBOX);
} else {
arm_discovery_retry(&mut discovery_deadline, now);
}
} else {
None
};
discovery_deadline = None;
}
if let Err(e) = apply_result {
crate::log_msg(&format!("discovery: apply failed: {e:#}"));
if committed_mode != mode {
let _ = ui_tx
.send(UiEvent::PresenceModeReverted {
mode: committed_mode,
})
.await;
}
if let Some(message) = transition_error {
let _ = ui_tx
.send(UiEvent::Error(format!("{message} ({e:#})")))
.await;
}
}
}
CoreCommand::SetRecordingMode(mode) => {
+96 -10
View File
@@ -8,14 +8,19 @@
//! The model (from `docs/contacts-plan.md` P6, decided 2026-06-16):
//! - **Resolving is always allowed on relay-capable modes** — a stationary friend
//! (typically in `Normal`) must be able to look up a friend who moved networks. A
//! resolve is a DNS query to n0 that publishes nothing; it only fires when a saved
//! address is stale and the dial falls through to discovery.
//! resolve is a DNS query to n0 that publishes nothing, but still exposes query
//! timing/source metadata to n0; it only fires when a saved address is stale and
//! the dial falls through to discovery.
//! - **Publishing is gated on `Discoverable`** and asymmetric: only the mover
//! publishes their address to n0 DNS; everyone else just looks it up.
//! - **Stopping publishing removes the local publisher service**; iroh does not
//! expose an explicit unpublish call here, so already-published pkarr records can
//! linger until their default ~30s TTL expires.
//! - **`DirectOnly` is the explicit no-server posture** — neither resolve nor publish
//! ever touches n0 there, regardless of the Discoverable toggle.
use crate::config::NetworkMode;
use crate::presence::PresenceMode;
use std::time::Duration;
/// How long `Discoverable` stays on before auto-reverting to `Normal`. Discovery is
@@ -46,12 +51,43 @@ pub fn lookup_plan(network_mode: NetworkMode, want_publish: bool) -> LookupPlan
match network_mode {
// The explicit serverless posture: no n0 contact at all, even to resolve.
// A Discoverable toggle here is intentionally inert.
NetworkMode::DirectOnly => LookupPlan { resolver: false, publisher: false },
NetworkMode::DirectOnly => LookupPlan {
resolver: false,
publisher: false,
},
// Relay-capable: always resolve (so a stationary friend can find a mover);
// publish only when the user opted into Discoverable.
NetworkMode::RelayNoDiscovery | NetworkMode::N0Full => {
LookupPlan { resolver: true, publisher: want_publish }
}
NetworkMode::RelayNoDiscovery | NetworkMode::N0Full => LookupPlan {
resolver: true,
publisher: want_publish,
},
}
}
/// Decide which presence mode may be committed after attempting to apply discovery
/// services for `requested`.
///
/// On failure, keep the previous mode: it is the only locally truthful state because
/// the endpoint's discovery services may still reflect the old posture. Same-mode
/// requests are no-ops from a presence-truth perspective and do not surface an error.
pub fn resolve_presence_transition(
previous: PresenceMode,
requested: PresenceMode,
apply_ok: bool,
) -> (PresenceMode, Option<String>) {
if previous == requested {
return (previous, None);
}
if apply_ok {
(requested, None)
} else {
(
previous,
Some(format!(
"Couldn't update discovery mode; keeping {previous}."
)),
)
}
}
@@ -64,12 +100,18 @@ mod tests {
for mode in [NetworkMode::RelayNoDiscovery, NetworkMode::N0Full] {
assert_eq!(
lookup_plan(mode, false),
LookupPlan { resolver: true, publisher: false },
LookupPlan {
resolver: true,
publisher: false
},
"{mode:?}: resolve always on, no publish when not Discoverable"
);
assert_eq!(
lookup_plan(mode, true),
LookupPlan { resolver: true, publisher: true },
LookupPlan {
resolver: true,
publisher: true
},
"{mode:?}: Discoverable adds publish on top of resolve"
);
}
@@ -79,12 +121,18 @@ mod tests {
fn direct_only_never_touches_n0_even_when_discoverable() {
assert_eq!(
lookup_plan(NetworkMode::DirectOnly, false),
LookupPlan { resolver: false, publisher: false }
LookupPlan {
resolver: false,
publisher: false
}
);
// The serverless posture overrides the Discoverable request entirely.
assert_eq!(
lookup_plan(NetworkMode::DirectOnly, true),
LookupPlan { resolver: false, publisher: false }
LookupPlan {
resolver: false,
publisher: false
}
);
}
@@ -92,4 +140,42 @@ mod tests {
fn timebox_is_thirty_minutes() {
assert_eq!(DISCOVERY_TIMEBOX, Duration::from_secs(1800));
}
#[test]
fn presence_transition_commits_requested_mode_after_successful_apply() {
assert_eq!(
resolve_presence_transition(PresenceMode::Normal, PresenceMode::Discoverable, true),
(PresenceMode::Discoverable, None)
);
}
#[test]
fn presence_transition_keeps_previous_mode_when_apply_fails() {
let (mode, err) =
resolve_presence_transition(PresenceMode::Normal, PresenceMode::Discoverable, false);
assert_eq!(mode, PresenceMode::Normal);
assert!(err.unwrap().contains("keeping Normal"));
}
#[test]
fn presence_transition_keeps_discoverable_when_off_transition_fails() {
let (mode, err) =
resolve_presence_transition(PresenceMode::Discoverable, PresenceMode::Normal, false);
assert_eq!(mode, PresenceMode::Discoverable);
assert!(err.unwrap().contains("keeping Discoverable"));
}
#[test]
fn presence_transition_same_mode_is_noop_without_error() {
assert_eq!(
resolve_presence_transition(
PresenceMode::Discoverable,
PresenceMode::Discoverable,
false
),
(PresenceMode::Discoverable, None)
);
}
}