feat(routing): consolidate scheduling strategy configuration

This commit is contained in:
fawney
2026-09-03 11:05:59 +08:00
parent e8d9877b79
commit 2cb4d554aa
88 changed files with 1836 additions and 3635 deletions
@@ -17,6 +17,7 @@ use crate::ai_serving::{
resolve_gemini_files_sync_spec as resolve_sync_spec, LocalGeminiFilesSpec,
};
use crate::{AiExecutionDecision, AppState, GatewayError};
use aether_routing_core::RoutingExecutionPolicy;
use self::decision::maybe_build_local_gemini_files_decision_payload_for_candidate;
use self::support::{
@@ -174,6 +175,13 @@ pub(crate) async fn build_local_gemini_files_stream_attempt_source_for_kind<'a>(
#[async_trait]
impl LocalExecutionAttemptSource<AiSyncAttempt> for LocalGeminiFilesSyncAttemptSource<'_> {
fn routing_execution_policy(&self) -> Option<RoutingExecutionPolicy> {
self.input
.routing_policy
.as_ref()
.map(|policy| policy.execution_policy)
}
async fn next_execution_attempt(&mut self) -> Result<Option<AiSyncAttempt>, GatewayError> {
while let Some(attempt) = self.candidates.next_attempt().await? {
match self.build_sync_attempt(attempt).await? {
@@ -212,6 +220,13 @@ impl LocalExecutionAttemptSource<AiSyncAttempt> for LocalGeminiFilesSyncAttemptS
#[async_trait]
impl LocalExecutionAttemptSource<AiStreamAttempt> for LocalGeminiFilesStreamAttemptSource<'_> {
fn routing_execution_policy(&self) -> Option<RoutingExecutionPolicy> {
self.input
.routing_policy
.as_ref()
.map(|policy| policy.execution_policy)
}
async fn next_execution_attempt(&mut self) -> Result<Option<AiStreamAttempt>, GatewayError> {
while let Some(attempt) = self.candidates.next_attempt().await? {
match self.build_stream_attempt(attempt).await? {
@@ -26,7 +26,6 @@ use crate::ai_serving::{
};
use crate::client_session_affinity::client_session_affinity_from_parts;
use crate::clock::current_unix_secs;
use crate::scheduler::config::SchedulerOrderingConfig;
use crate::{AppState, GatewayError};
pub(super) use crate::ai_serving::planner::candidate_materialization::LocalExecutionCandidateAttempt as LocalGeminiFilesCandidateAttempt;
@@ -109,10 +108,9 @@ pub(super) async fn materialize_local_gemini_files_candidate_attempts(
Some(&input.auth_snapshot),
input.client_session_affinity.as_ref(),
current_unix_secs(),
input
.routing_policy
.as_ref()
.map(SchedulerOrderingConfig::from_routing_policy),
crate::ai_serving::planner::candidate_ranking::scheduler_ordering_config_for_routing_policy(
input.routing_policy.as_ref(),
),
)
.await?;
let outcome = materialize_local_execution_candidates_with_serving(
@@ -186,10 +184,9 @@ pub(super) async fn build_local_gemini_files_candidate_attempt_source<'a>(
Some(&input.auth_snapshot),
input.client_session_affinity.as_ref(),
current_unix_secs(),
input
.routing_policy
.as_ref()
.map(SchedulerOrderingConfig::from_routing_policy),
crate::ai_serving::planner::candidate_ranking::scheduler_ordering_config_for_routing_policy(
input.routing_policy.as_ref(),
),
)
.await?;
Ok(build_local_execution_candidate_attempt_source_with_serving(
@@ -19,6 +19,7 @@ use crate::ai_serving::{
resolve_local_image_sync_spec as resolve_sync_spec,
};
use crate::{AiExecutionDecision, AppState, GatewayError};
use aether_routing_core::RoutingExecutionPolicy;
use self::decision::maybe_build_local_openai_image_decision_payload_for_candidate;
use self::support::{
@@ -252,6 +253,13 @@ pub(crate) async fn build_local_image_stream_attempt_source_for_kind<'a>(
#[async_trait]
impl LocalExecutionAttemptSource<AiSyncAttempt> for LocalOpenAiImageSyncAttemptSource<'_> {
fn routing_execution_policy(&self) -> Option<RoutingExecutionPolicy> {
self.input
.routing_policy
.as_ref()
.map(|policy| policy.execution_policy)
}
async fn next_execution_attempt(&mut self) -> Result<Option<AiSyncAttempt>, GatewayError> {
while let Some(attempt) = self.candidates.next_attempt().await? {
match self.build_sync_attempt(attempt).await? {
@@ -290,6 +298,13 @@ impl LocalExecutionAttemptSource<AiSyncAttempt> for LocalOpenAiImageSyncAttemptS
#[async_trait]
impl LocalExecutionAttemptSource<AiStreamAttempt> for LocalOpenAiImageStreamAttemptSource<'_> {
fn routing_execution_policy(&self) -> Option<RoutingExecutionPolicy> {
self.input
.routing_policy
.as_ref()
.map(|policy| policy.execution_policy)
}
async fn next_execution_attempt(&mut self) -> Result<Option<AiStreamAttempt>, GatewayError> {
while let Some(attempt) = self.candidates.next_attempt().await? {
match self.build_stream_attempt(attempt).await? {
@@ -27,7 +27,6 @@ use crate::ai_serving::{
};
use crate::client_session_affinity::client_session_affinity_from_parts;
use crate::clock::current_unix_secs;
use crate::scheduler::config::SchedulerOrderingConfig;
use crate::{AppState, GatewayError};
use aether_scheduler_core::SchedulerMinimalCandidateSelectionCandidate;
@@ -128,10 +127,9 @@ pub(super) async fn list_local_openai_image_candidate_attempts(
input.client_session_affinity.as_ref(),
current_unix_secs(),
false,
input
.routing_policy
.as_ref()
.map(SchedulerOrderingConfig::from_routing_policy),
crate::ai_serving::planner::candidate_ranking::scheduler_ordering_config_for_routing_policy(
input.routing_policy.as_ref(),
),
)
.await
{
@@ -206,10 +204,9 @@ pub(super) async fn build_local_openai_image_candidate_attempt_source<'a>(
input.client_session_affinity.as_ref(),
current_unix_secs(),
false,
input
.routing_policy
.as_ref()
.map(SchedulerOrderingConfig::from_routing_policy),
crate::ai_serving::planner::candidate_ranking::scheduler_ordering_config_for_routing_policy(
input.routing_policy.as_ref(),
),
)
.await
{
@@ -16,6 +16,7 @@ use crate::ai_serving::{
LocalVideoCreateSpec,
};
use crate::{AiExecutionDecision, AppState, GatewayError};
use aether_routing_core::RoutingExecutionPolicy;
use self::decision::maybe_build_local_video_create_decision_payload_for_candidate;
use self::support::{
@@ -104,6 +105,13 @@ pub(crate) async fn build_local_video_sync_attempt_source_for_kind<'a>(
#[async_trait]
impl LocalExecutionAttemptSource<AiSyncAttempt> for LocalVideoCreateSyncAttemptSource<'_> {
fn routing_execution_policy(&self) -> Option<RoutingExecutionPolicy> {
self.input
.routing_policy
.as_ref()
.map(|policy| policy.execution_policy)
}
async fn next_execution_attempt(&mut self) -> Result<Option<AiSyncAttempt>, GatewayError> {
while let Some(attempt) = self.candidates.next_attempt().await? {
match self.build_sync_attempt(attempt).await? {
@@ -29,7 +29,6 @@ use crate::ai_serving::{
};
use crate::client_session_affinity::client_session_affinity_from_parts;
use crate::clock::current_unix_secs;
use crate::scheduler::config::SchedulerOrderingConfig;
use crate::{AppState, GatewayError};
pub(super) use crate::ai_serving::planner::candidate_materialization::LocalExecutionCandidateAttempt as LocalVideoCreateCandidateAttempt;
@@ -134,10 +133,9 @@ pub(super) async fn list_local_video_create_candidate_attempts(
input.client_session_affinity.as_ref(),
current_unix_secs(),
false,
input
.routing_policy
.as_ref()
.map(SchedulerOrderingConfig::from_routing_policy),
crate::ai_serving::planner::candidate_ranking::scheduler_ordering_config_for_routing_policy(
input.routing_policy.as_ref(),
),
)
.await
{
@@ -195,10 +193,9 @@ pub(super) async fn build_local_video_create_candidate_attempt_source<'a>(
input.client_session_affinity.as_ref(),
current_unix_secs(),
false,
input
.routing_policy
.as_ref()
.map(SchedulerOrderingConfig::from_routing_policy),
crate::ai_serving::planner::candidate_ranking::scheduler_ordering_config_for_routing_policy(
input.routing_policy.as_ref(),
),
)
.await
{