feat(gateway): unify background task runtime and storage

This commit is contained in:
fawney19
2026-05-09 21:19:29 +08:00
parent 4a64d078f3
commit 209322b499
64 changed files with 4595 additions and 273 deletions
@@ -1,11 +1,10 @@
use crate::handlers::admin::provider::delete_task::run_admin_provider_delete_task;
use crate::handlers::admin::provider::shared::paths::{
admin_provider_delete_task_parts, admin_provider_id_for_manage_path,
};
use crate::handlers::admin::provider::shared::support::build_admin_provider_delete_task_payload;
use crate::handlers::admin::request::{AdminAppState, AdminRequestContext};
use crate::handlers::admin::shared::attach_admin_audit_response;
use crate::{GatewayError, LocalProviderDeleteTaskState};
use crate::GatewayError;
use axum::{
body::Body,
http,
@@ -13,8 +12,6 @@ use axum::{
Json,
};
use serde_json::json;
use tracing::warn;
use uuid::Uuid;
fn build_admin_provider_not_found_response(detail: impl Into<String>) -> Response<Body> {
(
@@ -60,52 +57,18 @@ pub(crate) async fn maybe_build_local_admin_provider_delete_task_response(
"Provider 不存在",
)));
};
let Some(provider) = state
.read_provider_catalog_providers_by_ids(std::slice::from_ref(&provider_id))
.await?
.into_iter()
.next()
let Some(task_id) =
crate::task_runtime::submit_provider_delete_task(state, &provider_id, Some("admin"))
.await?
else {
return Ok(Some(build_admin_provider_not_found_response(
"提供商不存在",
)));
};
let task_id = Uuid::new_v4().simple().to_string()[..16].to_string();
let pending_task = LocalProviderDeleteTaskState {
task_id: task_id.clone(),
provider_id: provider.id.clone(),
status: "pending".to_string(),
stage: "queued".to_string(),
total_keys: 0,
deleted_keys: 0,
total_endpoints: 0,
deleted_endpoints: 0,
message: "delete task submitted".to_string(),
};
state.put_provider_delete_task(pending_task.clone());
if let Err(err) = state
.run_admin_provider_delete_task(&provider.id, &task_id)
.await
{
warn!(
"gateway admin provider delete task failed for provider {}: {:?}",
provider.id, err
);
state.put_provider_delete_task(LocalProviderDeleteTaskState {
task_id: task_id.clone(),
provider_id: provider.id.clone(),
status: "failed".to_string(),
stage: "failed".to_string(),
total_keys: 0,
deleted_keys: 0,
total_endpoints: 0,
deleted_endpoints: 0,
message: format!("provider delete failed: {err:?}"),
});
}
return Ok(Some(attach_admin_audit_response(
Json(json!({
"task_id": task_id,
"run_id": task_id,
"status": "pending",
"message": "删除任务已提交,提供商已进入后台删除队列",
}))
@@ -113,7 +76,7 @@ pub(crate) async fn maybe_build_local_admin_provider_delete_task_response(
"admin_provider_delete_queued",
"delete_provider",
"provider",
&provider.id,
&provider_id,
)));
}
@@ -15,7 +15,14 @@ use crate::handlers::admin::provider::oauth::state::{
};
use crate::handlers::admin::provider::shared::paths::admin_provider_oauth_batch_import_task_provider_id;
use crate::handlers::admin::request::{AdminAppState, AdminRequestContext};
use crate::task_runtime::{
append_event_with_logging, now_unix_secs, task_definition, update_run_status,
upsert_run_with_logging, TASK_KEY_PROVIDER_OAUTH_BATCH_IMPORT,
};
use crate::GatewayError;
use aether_data_contracts::repository::background_tasks::{
BackgroundTaskKind, BackgroundTaskStatus, UpsertBackgroundTaskRun,
};
use axum::{
body::Bytes,
http,
@@ -133,11 +140,7 @@ pub(in super::super) async fn handle_admin_provider_oauth_start_batch_import_tas
}
let task_id = Uuid::new_v4().to_string();
let created_at = SystemTime::now()
.duration_since(UNIX_EPOCH)
.ok()
.map(|duration| duration.as_secs())
.unwrap_or(0);
let created_at = now_unix_secs();
let submitted_state = build_admin_provider_oauth_batch_task_state(
&task_id,
&provider_id,
@@ -167,6 +170,50 @@ pub(in super::super) async fn handle_admin_provider_oauth_start_batch_import_tas
));
}
if state.has_background_task_data_writer() {
let max_attempts = task_definition(TASK_KEY_PROVIDER_OAUTH_BATCH_IMPORT)
.map(|item| item.retry_policy.max_attempts)
.unwrap_or(1);
let run = UpsertBackgroundTaskRun {
id: task_id.clone(),
task_key: TASK_KEY_PROVIDER_OAUTH_BATCH_IMPORT.to_string(),
kind: BackgroundTaskKind::OnDemand,
trigger: "manual".to_string(),
status: BackgroundTaskStatus::Queued,
attempt: 1,
max_attempts,
owner_instance: Some(state.app().tunnel.local_instance_id().to_string()),
progress_percent: 0,
progress_message: Some("provider oauth batch import queued".to_string()),
payload_json: Some(json!({
"provider_id": provider_id.clone(),
"provider_type": provider_type.clone(),
"total": total,
})),
result_json: None,
error_message: None,
cancel_requested: false,
created_by: Some("admin".to_string()),
created_at_unix_secs: created_at,
started_at_unix_secs: None,
finished_at_unix_secs: None,
updated_at_unix_secs: created_at,
};
let _ = upsert_run_with_logging(state.app(), run).await;
append_event_with_logging(
state.app(),
&task_id,
"queued",
"provider oauth batch import queued",
Some(json!({
"provider_id": provider_id.clone(),
"provider_type": provider_type.clone(),
"total": total,
})),
)
.await;
}
let task_state = state.cloned_app();
let task_id_for_worker = task_id.clone();
let provider_id_for_worker = provider_id.clone();
@@ -201,6 +248,27 @@ pub(in super::super) async fn handle_admin_provider_oauth_start_batch_import_tas
.save_provider_oauth_batch_task_payload(&task_id_for_worker, &processing_state)
.await;
let _ = update_run_status(
&task_state,
&task_id_for_worker,
BackgroundTaskStatus::Running,
Some(1),
Some("provider oauth batch import started".to_string()),
None,
None,
Some(started_at),
None,
)
.await;
append_event_with_logging(
&task_state,
&task_id_for_worker,
"running",
"provider oauth batch import started",
None,
)
.await;
let mut progress_reporter = BatchTaskProgressReporter {
app: task_state.clone(),
task_id: task_id_for_worker.clone(),
@@ -270,6 +338,34 @@ pub(in super::super) async fn handle_admin_provider_oauth_start_batch_import_tas
let _ = AdminAppState::new(&task_state)
.save_provider_oauth_batch_task_payload(&task_id_for_worker, &completed_state)
.await;
let _ = update_run_status(
&task_state,
&task_id_for_worker,
BackgroundTaskStatus::Succeeded,
Some(100),
Some(message),
Some(json!({
"provider_id": provider_id_for_worker,
"provider_type": provider_type_for_worker,
"total": outcome.total,
"success": outcome.success,
"failed": outcome.failed,
"created_count": created_count,
"replaced_count": replaced_count,
})),
None,
None,
Some(finished_at),
)
.await;
append_event_with_logging(
&task_state,
&task_id_for_worker,
"succeeded",
"provider oauth batch import completed",
None,
)
.await;
}
Err(err) => {
let finished_at = SystemTime::now()
@@ -299,6 +395,26 @@ pub(in super::super) async fn handle_admin_provider_oauth_start_batch_import_tas
let _ = AdminAppState::new(&task_state)
.save_provider_oauth_batch_task_payload(&task_id_for_worker, &failed_state)
.await;
let _ = update_run_status(
&task_state,
&task_id_for_worker,
BackgroundTaskStatus::Failed,
Some(100),
Some("provider oauth batch import failed".to_string()),
None,
Some(error_message.clone()),
None,
Some(finished_at),
)
.await;
append_event_with_logging(
&task_state,
&task_id_for_worker,
"failed",
"provider oauth batch import failed",
Some(json!({ "error": error_message.clone() })),
)
.await;
tracing::warn!(
task_id = %task_id_for_worker,
provider_id = %provider_id_for_worker,
@@ -4,6 +4,7 @@ use super::quota::codex::refresh_codex_provider_quota_locally;
use super::quota::kiro::refresh_kiro_provider_quota_locally;
use crate::handlers::admin::request::AdminAppState;
use crate::provider_key_auth::provider_key_is_oauth_managed;
use crate::task_runtime::{spawn_fire_and_forget, TASK_KEY_PROVIDER_OAUTH_ACCOUNT_REFRESH};
use crate::{AppState, GatewayError};
use aether_contracts::ProxySnapshot;
use aether_data_contracts::repository::provider_catalog::{
@@ -170,7 +171,7 @@ pub(crate) fn spawn_provider_oauth_account_state_refresh_after_update(
key_id: String,
proxy_override: Option<ProxySnapshot>,
) {
tokio::spawn(async move {
spawn_fire_and_forget(TASK_KEY_PROVIDER_OAUTH_ACCOUNT_REFRESH, async move {
let _ = refresh_provider_oauth_account_state_after_update(
&AdminAppState::new(&app),
&provider,
@@ -1,5 +1,6 @@
use super::actions::admin_provider_ops_local_action_response;
use crate::handlers::admin::request::AdminAppState;
use crate::task_runtime::{spawn_fire_and_forget, TASK_KEY_PROVIDER_BALANCE_REFRESH};
use serde_json::{json, Value};
use std::collections::HashSet;
use std::time::Duration;
@@ -130,7 +131,7 @@ pub(super) async fn spawn_admin_provider_ops_balance_refresh(
let app = state.cloned_app();
let provider_id = provider_id.to_string();
tokio::spawn(async move {
spawn_fire_and_forget(TASK_KEY_PROVIDER_BALANCE_REFRESH, async move {
let permit = match tokio::time::timeout(
Duration::from_secs(5),
ADMIN_PROVIDER_OPS_BALANCE_REFRESH_SEMAPHORE.acquire(),