feat(gateway): harden failover and payload handling

Retry pre-response transport failures across candidates with an explicit stop policy, and propagate end-to-end timing into usage records and UI diagnostics.

Remove legacy body, import, cookie, PII, and tunnel replay caps while preserving optional operator-configured gateway limits.
This commit is contained in:
elky
2026-07-30 01:03:27 +08:00
parent a97acc07fc
commit a04673a90d
80 changed files with 3640 additions and 1236 deletions
+240 -7
View File
@@ -53,6 +53,20 @@ impl RequestDiagnostics {
inner.request_accepted_at
}
pub(crate) fn request_accepted_elapsed_ms(&self) -> Option<u64> {
self.request_accepted_at()
.map(|accepted_at| accepted_at.elapsed().as_millis().min(u128::from(u64::MAX)) as u64)
}
fn request_elapsed_ms_at(&self, observed_at: Instant) -> Option<u64> {
self.request_accepted_at().map(|accepted_at| {
observed_at
.saturating_duration_since(accepted_at)
.as_millis()
.min(u128::from(u64::MAX)) as u64
})
}
fn record_db_timing_ms(&self, operation: &'static str, elapsed_ms: u64) {
let Ok(mut inner) = self.inner.lock() else {
return;
@@ -151,9 +165,20 @@ pub(crate) async fn scope_request_diagnostics<F>(future: F) -> F::Output
where
F: Future,
{
REQUEST_DIAGNOSTICS
.scope(Arc::new(RequestDiagnostics::default()), future)
.await
scope_request_diagnostics_with(Some(Arc::new(RequestDiagnostics::default())), future).await
}
pub(crate) async fn scope_request_diagnostics_with<F>(
diagnostics: Option<Arc<RequestDiagnostics>>,
future: F,
) -> F::Output
where
F: Future,
{
match diagnostics {
Some(diagnostics) => REQUEST_DIAGNOSTICS.scope(diagnostics, future).await,
None => future.await,
}
}
pub(crate) fn current_request_diagnostics() -> Option<Arc<RequestDiagnostics>> {
@@ -199,23 +224,231 @@ pub(crate) fn attach_request_diagnostics_to_report_context(
report_context: Option<Value>,
diagnostics: Option<&Arc<RequestDiagnostics>>,
) -> Option<Value> {
let Some(db_timings_ms) = diagnostics.and_then(|diagnostics| diagnostics.db_timings_metadata())
else {
let db_timings_ms = diagnostics.and_then(|diagnostics| diagnostics.db_timings_metadata());
let end_to_end_time_ms =
diagnostics.and_then(|diagnostics| diagnostics.request_accepted_elapsed_ms());
if db_timings_ms.is_none() && end_to_end_time_ms.is_none() {
return report_context;
};
}
let mut object = match report_context {
Some(Value::Object(object)) => object,
Some(other) => Map::from_iter([("seed".to_string(), other)]),
None => Map::new(),
};
object.insert("db_timings_ms".to_string(), db_timings_ms);
if let Some(db_timings_ms) = db_timings_ms {
object.insert("db_timings_ms".to_string(), db_timings_ms);
}
if let Some(end_to_end_time_ms) = end_to_end_time_ms {
object.insert(
"end_to_end_time_ms".to_string(),
Value::from(end_to_end_time_ms),
);
}
Some(Value::Object(object))
}
pub(crate) fn attach_request_diagnostics_and_candidate_timing_to_report_context(
report_context: Option<Value>,
diagnostics: Option<&Arc<RequestDiagnostics>>,
candidate_elapsed_ms: Option<u64>,
candidate_ttfb_ms: Option<u64>,
) -> Option<Value> {
let end_to_end_time_ms =
diagnostics.and_then(|diagnostics| diagnostics.request_accepted_elapsed_ms());
let mut report_context =
attach_request_diagnostics_to_report_context(report_context, diagnostics);
let Some(end_to_end_first_byte_time_ms) =
end_to_end_first_byte_time_ms(end_to_end_time_ms, candidate_elapsed_ms, candidate_ttfb_ms)
else {
return report_context;
};
let object = report_context
.get_or_insert_with(|| Value::Object(Map::new()))
.as_object_mut()?;
object.insert(
"end_to_end_first_byte_time_ms".to_string(),
Value::from(end_to_end_first_byte_time_ms),
);
report_context
}
pub(crate) fn attach_request_diagnostics_and_candidate_start_timing_to_report_context(
report_context: Option<Value>,
diagnostics: Option<&Arc<RequestDiagnostics>>,
candidate_started_at: Option<Instant>,
candidate_ttfb_ms: Option<u64>,
) -> Option<Value> {
let end_to_end_time_ms =
diagnostics.and_then(|diagnostics| diagnostics.request_accepted_elapsed_ms());
let candidate_started_elapsed_ms = diagnostics
.zip(candidate_started_at)
.and_then(|(diagnostics, started_at)| diagnostics.request_elapsed_ms_at(started_at));
let mut report_context =
attach_request_diagnostics_to_report_context(report_context, diagnostics);
let Some(end_to_end_first_byte_time_ms) = end_to_end_first_byte_time_ms_from_candidate_start(
end_to_end_time_ms,
candidate_started_elapsed_ms,
candidate_ttfb_ms,
) else {
return report_context;
};
let object = report_context
.get_or_insert_with(|| Value::Object(Map::new()))
.as_object_mut()?;
object.insert(
"end_to_end_first_byte_time_ms".to_string(),
Value::from(end_to_end_first_byte_time_ms),
);
report_context
}
pub(crate) fn attach_current_request_diagnostics_and_candidate_timing_to_report_context(
report_context: Option<&Value>,
candidate_elapsed_ms: Option<u64>,
candidate_ttfb_ms: Option<u64>,
) -> Option<Value> {
let diagnostics = current_request_diagnostics();
attach_request_diagnostics_and_candidate_timing_to_report_context(
report_context.cloned(),
diagnostics.as_ref(),
candidate_elapsed_ms,
candidate_ttfb_ms,
)
}
pub(crate) fn attach_current_request_diagnostics_and_candidate_start_timing_to_report_context(
report_context: Option<&Value>,
candidate_started_at: Instant,
candidate_ttfb_ms: Option<u64>,
) -> Option<Value> {
let diagnostics = current_request_diagnostics();
attach_request_diagnostics_and_candidate_start_timing_to_report_context(
report_context.cloned(),
diagnostics.as_ref(),
Some(candidate_started_at),
candidate_ttfb_ms,
)
}
fn end_to_end_first_byte_time_ms(
end_to_end_time_ms: Option<u64>,
candidate_elapsed_ms: Option<u64>,
candidate_ttfb_ms: Option<u64>,
) -> Option<u64> {
let end_to_end_time_ms = end_to_end_time_ms?;
let candidate_elapsed_ms = candidate_elapsed_ms?;
let candidate_ttfb_ms = candidate_ttfb_ms?;
Some(
end_to_end_time_ms
.saturating_sub(candidate_elapsed_ms)
.saturating_add(candidate_ttfb_ms)
.min(end_to_end_time_ms),
)
}
fn end_to_end_first_byte_time_ms_from_candidate_start(
end_to_end_time_ms: Option<u64>,
candidate_started_elapsed_ms: Option<u64>,
candidate_ttfb_ms: Option<u64>,
) -> Option<u64> {
let end_to_end_time_ms = end_to_end_time_ms?;
let candidate_started_elapsed_ms = candidate_started_elapsed_ms?;
let candidate_ttfb_ms = candidate_ttfb_ms?;
Some(
candidate_started_elapsed_ms
.saturating_add(candidate_ttfb_ms)
.min(end_to_end_time_ms),
)
}
pub(crate) fn calibrate_candidate_first_byte_elapsed_ms(
candidate_elapsed_at_result_ms: u64,
execution_elapsed_ms: Option<u64>,
execution_ttfb_ms: Option<u64>,
) -> Option<u64> {
let execution_elapsed_ms = execution_elapsed_ms?;
let execution_ttfb_ms = execution_ttfb_ms?;
Some(
candidate_elapsed_at_result_ms
.saturating_sub(execution_elapsed_ms)
.saturating_add(execution_ttfb_ms)
.min(candidate_elapsed_at_result_ms),
)
}
pub(crate) fn attach_current_request_diagnostics_to_report_context(
report_context: Option<&Value>,
) -> Option<Value> {
let diagnostics = current_request_diagnostics()?;
attach_request_diagnostics_to_report_context(report_context.cloned(), Some(&diagnostics))
}
#[cfg(test)]
mod tests {
use std::sync::Arc;
use std::time::{Duration, Instant};
use serde_json::json;
use super::{
attach_request_diagnostics_and_candidate_start_timing_to_report_context,
calibrate_candidate_first_byte_elapsed_ms,
end_to_end_first_byte_time_ms_from_candidate_start, RequestDiagnostics,
};
#[test]
fn candidate_first_byte_calibration_includes_pre_transport_wait() {
assert_eq!(
calibrate_candidate_first_byte_elapsed_ms(826, Some(626), Some(120)),
Some(320)
);
}
#[test]
fn end_to_end_first_byte_matches_candidate_ttfb_without_prior_retry() {
assert_eq!(
end_to_end_first_byte_time_ms_from_candidate_start(Some(626), Some(0), Some(120)),
Some(120)
);
}
#[test]
fn end_to_end_first_byte_includes_time_spent_before_successful_retry() {
assert_eq!(
end_to_end_first_byte_time_ms_from_candidate_start(
Some(10_626),
Some(10_000),
Some(120),
),
Some(10_120)
);
}
#[test]
fn explicit_diagnostics_add_end_to_end_and_first_byte_timing() {
let diagnostics = Arc::new(RequestDiagnostics::default());
let accepted_at = Instant::now() - Duration::from_millis(1_000);
let candidate_started_at = accepted_at + Duration::from_millis(800);
diagnostics.record_request_accepted_at(accepted_at);
let context = attach_request_diagnostics_and_candidate_start_timing_to_report_context(
Some(json!({"candidate_index": 1})),
Some(&diagnostics),
Some(candidate_started_at),
Some(50),
)
.expect("diagnostics context should build");
let end_to_end = context["end_to_end_time_ms"]
.as_u64()
.expect("end-to-end timing should exist");
let first_byte = context["end_to_end_first_byte_time_ms"]
.as_u64()
.expect("first-byte timing should exist");
assert!(end_to_end >= 1_000);
assert_eq!(first_byte, 850);
}
}