mirror of
https://github.com/fawney19/Aether.git
synced 2026-10-10 19:29:50 +08:00
feat(routing): make routing profiles the sole scheduler policy source
Bootstrap an enabled system-default routing group from the legacy scheduler config keys on startup, resolve the default ordering config from that group before falling back to the legacy keys, and stop merging keep_priority_on_conversion with the legacy flag when a policy is resolved. Thread the policy-derived ordering config into candidate preselection so it no longer reads system config independently. Add per-API-format key priority overrides so a key serving several formats keeps independent ordering, matching the legacy global_priority_by_format semantics. Expose keep_priority_on_conversion in the routing profile editor and read the effective policy in the model routing preview, monitoring metrics and provider page badge.
This commit is contained in:
@@ -3,7 +3,7 @@ use aether_ai_serving::{
|
||||
AiCandidateRankingPort, AiRankableCandidateParts, AiRankingContextConfig,
|
||||
AiRankingSchedulingMode,
|
||||
};
|
||||
use aether_routing_core::{ResolvedRoutingPolicy, RoutingSchedulingMode, RoutingSetPriorityMode};
|
||||
use aether_routing_core::ResolvedRoutingPolicy;
|
||||
use async_trait::async_trait;
|
||||
use tokio::sync::Mutex;
|
||||
use tracing::warn;
|
||||
@@ -184,35 +184,16 @@ fn ai_ranking_scheduling_mode(mode: SchedulerSchedulingMode) -> AiRankingSchedul
|
||||
}
|
||||
}
|
||||
|
||||
/// Ordering config for a request. A resolved routing policy is authoritative
|
||||
/// and is never merged with legacy system-config values; without a policy the
|
||||
/// effective default (system-default routing group, then legacy keys) applies.
|
||||
pub(crate) async fn scheduler_ordering_config_for_routing_policy(
|
||||
state: PlannerAppState<'_>,
|
||||
routing_policy: Option<&ResolvedRoutingPolicy>,
|
||||
) -> SchedulerOrderingConfig {
|
||||
let system_config = read_scheduler_ordering_config_or_default(state).await;
|
||||
match routing_policy {
|
||||
Some(policy) => {
|
||||
let mut config = scheduler_ordering_config_from_routing_policy(policy);
|
||||
config.keep_priority_on_conversion |= system_config.keep_priority_on_conversion;
|
||||
config
|
||||
}
|
||||
None => system_config,
|
||||
}
|
||||
}
|
||||
|
||||
fn scheduler_ordering_config_from_routing_policy(
|
||||
policy: &ResolvedRoutingPolicy,
|
||||
) -> SchedulerOrderingConfig {
|
||||
SchedulerOrderingConfig {
|
||||
priority_mode: match policy.priority_mode {
|
||||
RoutingSetPriorityMode::Provider => SchedulerPriorityMode::Provider,
|
||||
RoutingSetPriorityMode::GlobalKey => SchedulerPriorityMode::GlobalKey,
|
||||
},
|
||||
scheduling_mode: match policy.scheduling_mode {
|
||||
RoutingSchedulingMode::FixedOrder => SchedulerSchedulingMode::FixedOrder,
|
||||
RoutingSchedulingMode::CacheAffinity => SchedulerSchedulingMode::CacheAffinity,
|
||||
RoutingSchedulingMode::LoadBalance => SchedulerSchedulingMode::LoadBalance,
|
||||
},
|
||||
keep_priority_on_conversion: policy.keep_priority_on_conversion,
|
||||
Some(policy) => SchedulerOrderingConfig::from_routing_policy(policy),
|
||||
None => read_scheduler_ordering_config_or_default(state).await,
|
||||
}
|
||||
}
|
||||
|
||||
@@ -231,14 +212,26 @@ fn routing_overlaid_candidate(
|
||||
let overlaid_key_priority = match kind {
|
||||
LocalExecutionCandidateKind::SingleKey => policy
|
||||
.ranking_overlay
|
||||
.key_priority_overrides
|
||||
.get(candidate.key_id.as_str()),
|
||||
.key_priority_override_matching_format(candidate.key_id.as_str(), |format| {
|
||||
crate::ai_serving::api_format_alias_matches(
|
||||
format,
|
||||
candidate.endpoint_api_format.as_str(),
|
||||
)
|
||||
})
|
||||
.or_else(|| {
|
||||
policy
|
||||
.ranking_overlay
|
||||
.key_priority_overrides
|
||||
.get(candidate.key_id.as_str())
|
||||
.copied()
|
||||
}),
|
||||
LocalExecutionCandidateKind::PoolGroup => policy
|
||||
.ranking_overlay
|
||||
.pool_priority_overrides
|
||||
.get(candidate.provider_id.as_str()),
|
||||
.get(candidate.provider_id.as_str())
|
||||
.copied(),
|
||||
};
|
||||
if let Some(overlaid_key_priority) = overlaid_key_priority.copied() {
|
||||
if let Some(overlaid_key_priority) = overlaid_key_priority {
|
||||
overlaid.key_internal_priority = overlaid_key_priority;
|
||||
overlaid.key_global_priority_for_format = Some(overlaid_key_priority);
|
||||
}
|
||||
@@ -396,7 +389,7 @@ mod tests {
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn routing_policy_inherits_global_conversion_priority_override() {
|
||||
async fn routing_policy_ignores_legacy_global_conversion_priority_override() {
|
||||
let data_state = GatewayDataState::default().with_system_config_values_for_tests([(
|
||||
"keep_priority_on_conversion".to_string(),
|
||||
json!(true),
|
||||
@@ -429,7 +422,10 @@ mod tests {
|
||||
ordering.scheduling_mode,
|
||||
crate::scheduler::config::SchedulerSchedulingMode::FixedOrder
|
||||
);
|
||||
assert!(ordering.keep_priority_on_conversion);
|
||||
assert!(
|
||||
!ordering.keep_priority_on_conversion,
|
||||
"a resolved routing policy must not inherit the legacy system-config flag"
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
|
||||
Reference in New Issue
Block a user