refactor ai serving modules and crates

This commit is contained in:
fawney19
2026-05-02 13:23:54 +08:00
parent 4fc7cecf30
commit c130d0e2c9
309 changed files with 21549 additions and 14265 deletions
@@ -0,0 +1,192 @@
use tracing::warn;
use crate::ai_serving::planner::common::extract_requested_model_from_request;
use crate::ai_serving::planner::runtime_miss::{
apply_local_runtime_candidate_evaluation_progress_preserving_candidate_signal,
apply_local_runtime_candidate_terminal_reason, set_local_runtime_miss_diagnostic_reason,
};
use crate::ai_serving::planner::spec_metadata::{
build_stream_plan_from_requested_model_family, build_sync_plan_from_requested_model_family,
local_same_format_provider_spec_metadata,
};
pub(crate) use crate::ai_serving::{
resolve_local_same_format_stream_spec as resolve_stream_spec,
resolve_local_same_format_sync_spec as resolve_sync_spec,
};
use super::{
materialize_local_same_format_provider_candidate_attempts,
maybe_build_local_same_format_provider_decision_payload_for_candidate,
resolve_local_same_format_provider_decision_input, AiStreamAttempt, AiSyncAttempt, AppState,
GatewayControlDecision, GatewayError, LocalSameFormatProviderSpec,
};
pub(crate) async fn build_local_sync_plan_and_reports(
state: &AppState,
parts: &http::request::Parts,
trace_id: &str,
decision: &GatewayControlDecision,
body_json: &serde_json::Value,
spec: LocalSameFormatProviderSpec,
) -> Result<Vec<AiSyncAttempt>, GatewayError> {
let spec_metadata = local_same_format_provider_spec_metadata(spec);
let requested_model_family = spec_metadata
.requested_model_family
.expect("same-format provider spec metadata should include requested-model family");
let Some(input) = resolve_local_same_format_provider_decision_input(
state, parts, trace_id, decision, body_json, spec,
)
.await
else {
set_local_runtime_miss_diagnostic_reason(
state,
trace_id,
decision,
spec_metadata.decision_kind,
extract_requested_model_from_request(parts, body_json, requested_model_family)
.as_deref(),
"decision_input_unavailable",
);
return Ok(Vec::new());
};
set_local_runtime_miss_diagnostic_reason(
state,
trace_id,
decision,
spec_metadata.decision_kind,
Some(input.requested_model.as_str()),
"candidate_evaluation_incomplete",
);
let (attempts, candidate_count) = materialize_local_same_format_provider_candidate_attempts(
state, trace_id, &input, body_json, spec,
)
.await?;
apply_local_runtime_candidate_evaluation_progress_preserving_candidate_signal(
state,
trace_id,
candidate_count,
);
if candidate_count == 0 {
return Ok(Vec::new());
}
let mut plans = Vec::new();
for attempt in attempts {
let Some(payload) = maybe_build_local_same_format_provider_decision_payload_for_candidate(
state, parts, trace_id, body_json, &input, attempt, spec,
)
.await
else {
continue;
};
let built = build_sync_plan_from_requested_model_family(
requested_model_family,
parts,
body_json,
payload,
);
match built {
Ok(Some(value)) => plans.push(value),
Ok(None) => {}
Err(err) => {
warn!(
trace_id = %trace_id,
api_format = spec_metadata.api_format,
error = ?err,
"gateway local same-format sync decision plan build failed"
);
}
}
}
apply_local_runtime_candidate_terminal_reason(state, trace_id, "no_local_sync_plans");
Ok(plans)
}
pub(crate) async fn build_local_stream_plan_and_reports(
state: &AppState,
parts: &http::request::Parts,
trace_id: &str,
decision: &GatewayControlDecision,
body_json: &serde_json::Value,
spec: LocalSameFormatProviderSpec,
) -> Result<Vec<AiStreamAttempt>, GatewayError> {
let spec_metadata = local_same_format_provider_spec_metadata(spec);
let requested_model_family = spec_metadata
.requested_model_family
.expect("same-format provider spec metadata should include requested-model family");
let Some(input) = resolve_local_same_format_provider_decision_input(
state, parts, trace_id, decision, body_json, spec,
)
.await
else {
set_local_runtime_miss_diagnostic_reason(
state,
trace_id,
decision,
spec_metadata.decision_kind,
extract_requested_model_from_request(parts, body_json, requested_model_family)
.as_deref(),
"decision_input_unavailable",
);
return Ok(Vec::new());
};
set_local_runtime_miss_diagnostic_reason(
state,
trace_id,
decision,
spec_metadata.decision_kind,
Some(input.requested_model.as_str()),
"candidate_evaluation_incomplete",
);
let (attempts, candidate_count) = materialize_local_same_format_provider_candidate_attempts(
state, trace_id, &input, body_json, spec,
)
.await?;
apply_local_runtime_candidate_evaluation_progress_preserving_candidate_signal(
state,
trace_id,
candidate_count,
);
if candidate_count == 0 {
return Ok(Vec::new());
}
let mut plans = Vec::new();
for attempt in attempts {
let Some(payload) = maybe_build_local_same_format_provider_decision_payload_for_candidate(
state, parts, trace_id, body_json, &input, attempt, spec,
)
.await
else {
continue;
};
let built = build_stream_plan_from_requested_model_family(
requested_model_family,
parts,
body_json,
payload,
);
match built {
Ok(Some(value)) => plans.push(value),
Ok(None) => {}
Err(err) => {
warn!(
trace_id = %trace_id,
api_format = spec_metadata.api_format,
error = ?err,
"gateway local same-format stream decision plan build failed"
);
}
}
}
apply_local_runtime_candidate_terminal_reason(state, trace_id, "no_local_stream_plans");
Ok(plans)
}