mirror of
https://github.com/fawney19/Aether.git
synced 2026-10-11 11:49:50 +08:00
feat: add routing profile scheduling policies
This commit is contained in:
@@ -1,4 +1,5 @@
|
||||
use crate::ai_serving::build_request_trace_proxy_value;
|
||||
use crate::ai_serving::planner::decision_input::apply_provider_request_routing_policy_to_decision;
|
||||
use crate::ai_serving::planner::report_context::{
|
||||
build_local_execution_report_context, LocalExecutionReportContextParts,
|
||||
};
|
||||
@@ -10,7 +11,7 @@ use crate::ai_serving::transport::{
|
||||
resolve_transport_execution_timeouts, resolve_transport_profile,
|
||||
};
|
||||
use crate::ai_serving::{ai_local_execution_contract_for_formats, PlannerAppState};
|
||||
use crate::{AiExecutionDecision, AppState};
|
||||
use crate::{AiExecutionDecision, AppState, GatewayError};
|
||||
|
||||
use super::request::resolve_local_video_create_candidate_payload_parts;
|
||||
use super::support::{LocalVideoCreateCandidateAttempt, LocalVideoCreateDecisionInput};
|
||||
@@ -24,14 +25,17 @@ pub(super) async fn maybe_build_local_video_create_decision_payload_for_candidat
|
||||
input: &LocalVideoCreateDecisionInput,
|
||||
attempt: LocalVideoCreateCandidateAttempt,
|
||||
spec: LocalVideoCreateSpec,
|
||||
) -> Option<AiExecutionDecision> {
|
||||
) -> Result<Option<AiExecutionDecision>, GatewayError> {
|
||||
let spec_metadata = local_video_create_spec_metadata(spec);
|
||||
let planner_state = PlannerAppState::new(state);
|
||||
let attempt_identity = attempt.attempt_identity();
|
||||
let resolved = resolve_local_video_create_candidate_payload_parts(
|
||||
let Some(resolved) = resolve_local_video_create_candidate_payload_parts(
|
||||
state, parts, body_json, trace_id, input, &attempt, spec,
|
||||
)
|
||||
.await?;
|
||||
.await
|
||||
else {
|
||||
return Ok(None);
|
||||
};
|
||||
let LocalVideoCreateCandidateAttempt {
|
||||
eligible,
|
||||
candidate_id,
|
||||
@@ -50,6 +54,7 @@ pub(super) async fn maybe_build_local_video_create_decision_payload_for_candidat
|
||||
if let Some(proxy_value) = build_request_trace_proxy_value(Some(&transport), proxy.as_ref()) {
|
||||
extra_fields.insert("proxy".to_string(), proxy_value);
|
||||
}
|
||||
let effective_headers = input.effective_headers(&parts.headers);
|
||||
let report_context = build_local_execution_report_context(LocalExecutionReportContextParts {
|
||||
auth_context: &input.auth_context,
|
||||
request_id: trace_id,
|
||||
@@ -75,7 +80,7 @@ pub(super) async fn maybe_build_local_video_create_decision_payload_for_candidat
|
||||
body_rules: transport.endpoint.body_rules.as_ref(),
|
||||
provider_request_method: None,
|
||||
provider_request_headers: None,
|
||||
original_headers: &parts.headers,
|
||||
original_headers: effective_headers,
|
||||
request_path: Some(parts.uri.path()),
|
||||
request_query_string: parts.uri.query(),
|
||||
request_origin: Some(crate::ai_serving::request_origin_from_parts(parts)),
|
||||
@@ -99,45 +104,45 @@ pub(super) async fn maybe_build_local_video_create_decision_payload_for_candidat
|
||||
upstream_url,
|
||||
} = resolved;
|
||||
|
||||
Some(build_ai_execution_decision_response(
|
||||
AiExecutionDecisionResponseParts {
|
||||
decision_is_stream: false,
|
||||
decision_kind: spec_metadata.decision_kind.to_string(),
|
||||
execution_strategy,
|
||||
conversion_mode,
|
||||
request_id: trace_id.to_string(),
|
||||
candidate_id: candidate_id.clone(),
|
||||
provider_name: transport.provider.name.clone(),
|
||||
provider_id: candidate.provider_id.clone(),
|
||||
endpoint_id: candidate.endpoint_id.clone(),
|
||||
key_id: candidate.key_id.clone(),
|
||||
upstream_base_url: transport.endpoint.base_url.clone(),
|
||||
upstream_url,
|
||||
provider_request_method: Some(parts.method.to_string()),
|
||||
auth_header: Some(auth_header),
|
||||
auth_value: Some(auth_value),
|
||||
provider_api_format: spec_metadata.api_format.to_string(),
|
||||
client_api_format: spec_metadata.api_format.to_string(),
|
||||
model_name: input.requested_model.clone(),
|
||||
mapped_model,
|
||||
prompt_cache_key: None,
|
||||
provider_request_headers,
|
||||
provider_request_body: Some(provider_request_body),
|
||||
provider_request_body_base64: None,
|
||||
content_type: parts
|
||||
.headers
|
||||
.get(http::header::CONTENT_TYPE)
|
||||
.and_then(|value| value.to_str().ok())
|
||||
.map(str::trim)
|
||||
.filter(|value| !value.is_empty())
|
||||
.map(ToOwned::to_owned),
|
||||
proxy,
|
||||
transport_profile,
|
||||
timeouts: resolve_transport_execution_timeouts(&transport),
|
||||
upstream_is_stream: false,
|
||||
report_kind: spec_metadata.report_kind.map(ToOwned::to_owned),
|
||||
report_context: Some(report_context),
|
||||
auth_context: input.auth_context.clone(),
|
||||
},
|
||||
))
|
||||
let mut decision = build_ai_execution_decision_response(AiExecutionDecisionResponseParts {
|
||||
decision_is_stream: false,
|
||||
decision_kind: spec_metadata.decision_kind.to_string(),
|
||||
execution_strategy,
|
||||
conversion_mode,
|
||||
request_id: trace_id.to_string(),
|
||||
candidate_id: candidate_id.clone(),
|
||||
provider_name: transport.provider.name.clone(),
|
||||
provider_id: candidate.provider_id.clone(),
|
||||
endpoint_id: candidate.endpoint_id.clone(),
|
||||
key_id: candidate.key_id.clone(),
|
||||
upstream_base_url: transport.endpoint.base_url.clone(),
|
||||
upstream_url,
|
||||
provider_request_method: Some(parts.method.to_string()),
|
||||
auth_header: Some(auth_header),
|
||||
auth_value: Some(auth_value),
|
||||
provider_api_format: spec_metadata.api_format.to_string(),
|
||||
client_api_format: spec_metadata.api_format.to_string(),
|
||||
model_name: input.requested_model.clone(),
|
||||
mapped_model,
|
||||
prompt_cache_key: None,
|
||||
provider_request_headers,
|
||||
provider_request_body: Some(provider_request_body),
|
||||
provider_request_body_base64: None,
|
||||
content_type: parts
|
||||
.headers
|
||||
.get(http::header::CONTENT_TYPE)
|
||||
.and_then(|value| value.to_str().ok())
|
||||
.map(str::trim)
|
||||
.filter(|value| !value.is_empty())
|
||||
.map(ToOwned::to_owned),
|
||||
proxy,
|
||||
transport_profile,
|
||||
timeouts: resolve_transport_execution_timeouts(&transport),
|
||||
upstream_is_stream: false,
|
||||
report_kind: spec_metadata.report_kind.map(ToOwned::to_owned),
|
||||
report_context: Some(report_context),
|
||||
auth_context: input.auth_context.clone(),
|
||||
});
|
||||
apply_provider_request_routing_policy_to_decision(input, &mut decision)?;
|
||||
Ok(Some(decision))
|
||||
}
|
||||
|
||||
@@ -41,6 +41,7 @@ pub(super) async fn resolve_local_video_create_candidate_payload_parts(
|
||||
let spec_metadata = local_video_create_spec_metadata(spec);
|
||||
let candidate = &attempt.eligible.candidate;
|
||||
let transport = &attempt.eligible.transport;
|
||||
let effective_headers = input.effective_headers(&parts.headers);
|
||||
|
||||
let provider_family = provider_video_create_family(spec.family);
|
||||
let transport_unsupported_reason = video_create_transport_unsupported_reason(
|
||||
@@ -124,7 +125,7 @@ pub(super) async fn resolve_local_video_create_candidate_payload_parts(
|
||||
provider_family,
|
||||
&mapped_model,
|
||||
transport.endpoint.body_rules.as_ref(),
|
||||
Some(&parts.headers),
|
||||
Some(effective_headers),
|
||||
) else {
|
||||
mark_skipped_local_video_candidate_with_failure_diagnostic(
|
||||
state,
|
||||
@@ -146,7 +147,7 @@ pub(super) async fn resolve_local_video_create_candidate_payload_parts(
|
||||
|
||||
let Some(provider_request_headers) =
|
||||
build_video_create_headers(ProviderVideoCreateHeadersInput {
|
||||
headers: &parts.headers,
|
||||
headers: effective_headers,
|
||||
auth_header: &auth_header,
|
||||
auth_value: &auth_value,
|
||||
header_rules: transport.endpoint.header_rules.as_ref(),
|
||||
|
||||
@@ -15,6 +15,7 @@ use crate::ai_serving::planner::candidate_metadata::{
|
||||
use crate::ai_serving::planner::candidate_resolution::SkippedLocalExecutionCandidate;
|
||||
use crate::ai_serving::planner::common::extract_requested_model_from_request;
|
||||
use crate::ai_serving::planner::decision_input::{
|
||||
attach_routing_policy_to_local_requested_model_input,
|
||||
build_local_requested_model_decision_input, resolve_local_authenticated_decision_input,
|
||||
};
|
||||
use crate::ai_serving::planner::materialization_policy::{
|
||||
@@ -41,19 +42,21 @@ pub(super) async fn resolve_local_video_create_decision_input(
|
||||
decision: &GatewayControlDecision,
|
||||
body_json: &serde_json::Value,
|
||||
spec: LocalVideoCreateSpec,
|
||||
) -> Option<LocalVideoCreateDecisionInput> {
|
||||
) -> Result<Option<LocalVideoCreateDecisionInput>, GatewayError> {
|
||||
let spec_metadata = local_video_create_spec_metadata(spec);
|
||||
let Some(auth_context) = resolve_local_video_create_auth_context(decision, spec.family) else {
|
||||
return None;
|
||||
return Ok(None);
|
||||
};
|
||||
|
||||
let requested_model = extract_requested_model_from_request(
|
||||
let Some(requested_model) = extract_requested_model_from_request(
|
||||
parts,
|
||||
body_json,
|
||||
spec_metadata
|
||||
.requested_model_family
|
||||
.expect("video specs should declare requested-model family"),
|
||||
)?;
|
||||
) else {
|
||||
return Ok(None);
|
||||
};
|
||||
|
||||
let resolved_input = match resolve_local_authenticated_decision_input(
|
||||
state,
|
||||
@@ -64,7 +67,7 @@ pub(super) async fn resolve_local_video_create_decision_input(
|
||||
.await
|
||||
{
|
||||
Ok(Some(resolved_input)) => resolved_input,
|
||||
Ok(None) => return None,
|
||||
Ok(None) => return Ok(None),
|
||||
Err(err) => {
|
||||
warn!(
|
||||
trace_id = %trace_id,
|
||||
@@ -72,14 +75,31 @@ pub(super) async fn resolve_local_video_create_decision_input(
|
||||
error = ?err,
|
||||
"gateway local video decision auth snapshot read failed"
|
||||
);
|
||||
return None;
|
||||
return Err(err);
|
||||
}
|
||||
};
|
||||
|
||||
let mut input = build_local_requested_model_decision_input(resolved_input, requested_model);
|
||||
input.request_auth_channel = decision.request_auth_channel.clone();
|
||||
input.client_session_affinity = client_session_affinity_from_parts(parts, Some(body_json));
|
||||
Some(input)
|
||||
if let Err(err) = attach_routing_policy_to_local_requested_model_input(
|
||||
state,
|
||||
parts,
|
||||
&mut input,
|
||||
body_json,
|
||||
spec_metadata.api_format,
|
||||
)
|
||||
.await
|
||||
{
|
||||
warn!(
|
||||
trace_id = %trace_id,
|
||||
decision_kind = spec_metadata.decision_kind,
|
||||
error = ?err,
|
||||
"gateway local video decision routing profile resolution failed"
|
||||
);
|
||||
return Err(err);
|
||||
}
|
||||
Ok(Some(input))
|
||||
}
|
||||
|
||||
fn resolve_local_video_create_auth_context(
|
||||
@@ -196,6 +216,7 @@ pub(super) async fn build_local_video_create_candidate_attempt_source<'a>(
|
||||
Some(&input.auth_snapshot),
|
||||
input.client_session_affinity.as_ref(),
|
||||
input.required_capabilities.as_ref(),
|
||||
input.routing_policy.as_ref(),
|
||||
sticky_session_token.as_deref(),
|
||||
input.request_auth_channel.as_deref(),
|
||||
persistence_policy,
|
||||
@@ -261,6 +282,7 @@ async fn materialize_local_video_create_candidate_attempts(
|
||||
Some(&input.auth_snapshot),
|
||||
input.client_session_affinity.as_ref(),
|
||||
input.required_capabilities.as_ref(),
|
||||
input.routing_policy.as_ref(),
|
||||
sticky_session_token.as_deref(),
|
||||
input.request_auth_channel.as_deref(),
|
||||
persistence_policy,
|
||||
|
||||
Reference in New Issue
Block a user