fix(gateway): add provider key concurrency and cache affinity modes

This commit is contained in:
ZheFox
2026-09-01 08:06:58 +08:00
parent 36daba7a34
commit 9631b229b3
26 changed files with 1176 additions and 154 deletions
@@ -78,7 +78,9 @@ use crate::orchestration::{
LocalExecutionEffectContext, LocalHealthFailureEffect, LocalHealthSuccessEffect,
LocalOAuthInvalidationEffect, LocalOAuthSuccessEffect, LocalPoolErrorEffect,
};
use crate::provider_pool_demand::acquire_provider_pool_in_flight_guard;
use crate::provider_pool_demand::{
acquire_provider_pool_execution_guard, ProviderPoolInFlightAdmission,
};
use crate::request_candidate_runtime::{
ensure_execution_request_candidate_slot, record_local_request_candidate_extra_data,
record_local_request_candidate_status, record_local_request_candidate_status_snapshot,
@@ -1995,6 +1997,32 @@ async fn execute_execution_runtime_sync_impl(
.unwrap_or_else(|| "-".to_string());
let candidate_started_at = Instant::now();
let candidate_started_unix_secs = current_request_candidate_unix_ms();
let _provider_pool_in_flight_guard = match acquire_provider_pool_execution_guard(state, &plan)
.await?
{
ProviderPoolInFlightAdmission::Acquired(guard) => guard,
ProviderPoolInFlightAdmission::Saturated { limit } => {
if let Some(retry_scope) = retry_scope_out.as_deref_mut() {
*retry_scope = AiAttemptRetryScope::Candidate;
}
record_local_request_candidate_status(
state,
&plan,
report_context.as_ref(),
SchedulerRequestCandidateStatusUpdate {
status: RequestCandidateStatus::Skipped,
status_code: Some(StatusCode::TOO_MANY_REQUESTS.as_u16()),
error_type: Some("provider_key_concurrency_limit_reached".to_string()),
error_message: Some(format!("provider key concurrency limit reached: {limit}")),
latency_ms: Some(0),
started_at_unix_ms: Some(candidate_started_unix_secs),
finished_at_unix_ms: Some(candidate_started_unix_secs),
},
)
.await;
return Ok(None);
}
};
let lifecycle_seed = build_lifecycle_usage_seed(&plan, report_context.as_ref());
let usage_data = state.usage_lifecycle_data_state().as_ref().clone();
state
@@ -2024,14 +2052,6 @@ async fn execute_execution_runtime_sync_impl(
candidate_started_at,
);
let result = (async {
let _provider_pool_in_flight_guard = acquire_provider_pool_in_flight_guard(
state.runtime_state.clone(),
&plan.provider_id,
plan_request_id.as_str(),
plan_candidate_id.as_deref(),
key_id.as_str(),
)
.await;
record_sync_execution_active(
state,
&plan,