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 +1,164 @@
use crate::ai_serving::planner::common::{
CLAUDE_CHAT_STREAM_PLAN_KIND, CLAUDE_CHAT_SYNC_PLAN_KIND, CLAUDE_CLI_STREAM_PLAN_KIND,
CLAUDE_CLI_SYNC_PLAN_KIND, GEMINI_CHAT_STREAM_PLAN_KIND, GEMINI_CHAT_SYNC_PLAN_KIND,
GEMINI_CLI_STREAM_PLAN_KIND, GEMINI_CLI_SYNC_PLAN_KIND, GEMINI_FILES_DELETE_PLAN_KIND,
GEMINI_FILES_DOWNLOAD_PLAN_KIND, GEMINI_FILES_GET_PLAN_KIND, GEMINI_FILES_LIST_PLAN_KIND,
GEMINI_VIDEO_CANCEL_SYNC_PLAN_KIND, GEMINI_VIDEO_CREATE_SYNC_PLAN_KIND,
OPENAI_CHAT_STREAM_PLAN_KIND, OPENAI_CHAT_SYNC_PLAN_KIND, OPENAI_IMAGE_STREAM_PLAN_KIND,
OPENAI_IMAGE_SYNC_PLAN_KIND, OPENAI_RESPONSES_COMPACT_STREAM_PLAN_KIND,
OPENAI_RESPONSES_COMPACT_SYNC_PLAN_KIND, OPENAI_RESPONSES_STREAM_PLAN_KIND,
OPENAI_RESPONSES_SYNC_PLAN_KIND, OPENAI_VIDEO_CANCEL_SYNC_PLAN_KIND,
OPENAI_VIDEO_CONTENT_PLAN_KIND, OPENAI_VIDEO_CREATE_SYNC_PLAN_KIND,
OPENAI_VIDEO_DELETE_SYNC_PLAN_KIND, OPENAI_VIDEO_REMIX_SYNC_PLAN_KIND,
};
use crate::ai_serving::planner::plan_builders::{
build_gemini_stream_plan_from_decision, build_gemini_sync_plan_from_decision,
build_openai_chat_stream_plan_from_decision, build_openai_chat_sync_plan_from_decision,
build_openai_responses_stream_plan_from_decision,
build_openai_responses_sync_plan_from_decision, build_passthrough_stream_plan_from_decision,
build_passthrough_sync_plan_from_decision, build_standard_stream_plan_from_decision,
build_standard_sync_plan_from_decision,
};
use crate::ai_serving::planner::route::{
resolve_execution_runtime_stream_plan_kind as resolve_stream_plan_kind,
resolve_execution_runtime_sync_plan_kind as resolve_sync_plan_kind,
};
use crate::ai_serving::GatewayControlDecision;
use crate::{AiExecutionDecision, AiExecutionPlanPayload, AppState, GatewayError};
use aether_ai_serving::{
build_ai_stream_execution_plan_payload, build_ai_sync_execution_plan_payload,
};
pub(crate) async fn maybe_build_sync_plan_payload_impl(
state: &AppState,
parts: &http::request::Parts,
trace_id: &str,
decision: &GatewayControlDecision,
body_json: &serde_json::Value,
body_base64: Option<&str>,
body_is_empty: bool,
) -> Result<Option<AiExecutionPlanPayload>, GatewayError> {
let Some(plan_kind) = resolve_sync_plan_kind(parts, decision) else {
return Ok(None);
};
let Some(payload) = super::maybe_build_sync_decision_payload(
state,
parts,
trace_id,
decision,
body_json,
body_base64,
body_is_empty,
)
.await?
else {
return Ok(None);
};
build_sync_plan_payload_from_decision(parts, body_json, plan_kind, payload)
}
pub(crate) async fn maybe_build_stream_plan_payload_impl(
state: &AppState,
parts: &http::request::Parts,
trace_id: &str,
decision: &GatewayControlDecision,
body_json: &serde_json::Value,
body_base64: Option<&str>,
) -> Result<Option<AiExecutionPlanPayload>, GatewayError> {
let Some(plan_kind) = resolve_stream_plan_kind(parts, decision) else {
return Ok(None);
};
let Some(payload) = super::maybe_build_stream_decision_payload(
state,
parts,
trace_id,
decision,
body_json,
body_base64,
)
.await?
else {
return Ok(None);
};
build_stream_plan_payload_from_decision(parts, body_json, plan_kind, payload)
}
fn build_sync_plan_payload_from_decision(
parts: &http::request::Parts,
body_json: &serde_json::Value,
plan_kind: &str,
mut payload: AiExecutionDecision,
) -> Result<Option<AiExecutionPlanPayload>, GatewayError> {
let auth_context = payload.auth_context.take();
let plan_and_report = match plan_kind {
OPENAI_CHAT_SYNC_PLAN_KIND => {
build_openai_chat_sync_plan_from_decision(parts, body_json, payload)?
}
OPENAI_RESPONSES_SYNC_PLAN_KIND => {
build_openai_responses_sync_plan_from_decision(parts, body_json, payload, false)?
}
OPENAI_IMAGE_SYNC_PLAN_KIND => build_passthrough_sync_plan_from_decision(parts, payload)?,
OPENAI_RESPONSES_COMPACT_SYNC_PLAN_KIND => {
build_openai_responses_sync_plan_from_decision(parts, body_json, payload, true)?
}
CLAUDE_CHAT_SYNC_PLAN_KIND | CLAUDE_CLI_SYNC_PLAN_KIND => {
build_standard_sync_plan_from_decision(parts, body_json, payload)?
}
GEMINI_CHAT_SYNC_PLAN_KIND | GEMINI_CLI_SYNC_PLAN_KIND => {
build_gemini_sync_plan_from_decision(parts, body_json, payload)?
}
OPENAI_VIDEO_CREATE_SYNC_PLAN_KIND
| OPENAI_VIDEO_REMIX_SYNC_PLAN_KIND
| OPENAI_VIDEO_CANCEL_SYNC_PLAN_KIND
| OPENAI_VIDEO_DELETE_SYNC_PLAN_KIND
| GEMINI_VIDEO_CREATE_SYNC_PLAN_KIND
| GEMINI_VIDEO_CANCEL_SYNC_PLAN_KIND
| GEMINI_FILES_LIST_PLAN_KIND
| GEMINI_FILES_GET_PLAN_KIND
| GEMINI_FILES_DELETE_PLAN_KIND => {
build_passthrough_sync_plan_from_decision(parts, payload)?
}
_ => None,
};
Ok(plan_and_report
.map(|value| build_ai_sync_execution_plan_payload(plan_kind, value, auth_context)))
}
fn build_stream_plan_payload_from_decision(
parts: &http::request::Parts,
body_json: &serde_json::Value,
plan_kind: &str,
mut payload: AiExecutionDecision,
) -> Result<Option<AiExecutionPlanPayload>, GatewayError> {
let auth_context = payload.auth_context.take();
let plan_and_report = match plan_kind {
OPENAI_CHAT_STREAM_PLAN_KIND => {
build_openai_chat_stream_plan_from_decision(parts, body_json, payload)?
}
OPENAI_RESPONSES_STREAM_PLAN_KIND => {
build_openai_responses_stream_plan_from_decision(parts, body_json, payload, false)?
}
OPENAI_IMAGE_STREAM_PLAN_KIND => {
build_standard_stream_plan_from_decision(parts, body_json, payload, false)?
}
OPENAI_RESPONSES_COMPACT_STREAM_PLAN_KIND => {
build_openai_responses_stream_plan_from_decision(parts, body_json, payload, true)?
}
CLAUDE_CHAT_STREAM_PLAN_KIND | CLAUDE_CLI_STREAM_PLAN_KIND => {
build_standard_stream_plan_from_decision(parts, body_json, payload, true)?
}
GEMINI_CHAT_STREAM_PLAN_KIND | GEMINI_CLI_STREAM_PLAN_KIND => {
build_gemini_stream_plan_from_decision(parts, body_json, payload)?
}
OPENAI_VIDEO_CONTENT_PLAN_KIND | GEMINI_FILES_DOWNLOAD_PLAN_KIND => {
build_passthrough_stream_plan_from_decision(parts, payload)?
}
_ => None,
};
Ok(plan_and_report
.map(|value| build_ai_stream_execution_plan_payload(plan_kind, value, auth_context)))
}
@@ -0,0 +1,26 @@
mod control_plan;
mod stream;
mod sync;
pub(crate) use self::control_plan::{
maybe_build_stream_plan_payload_impl, maybe_build_sync_plan_payload_impl,
};
pub(crate) use self::stream::maybe_build_stream_decision_payload;
pub(crate) use self::sync::maybe_build_sync_decision_payload;
pub(crate) use super::passthrough::{
maybe_build_stream_local_same_format_provider_decision_payload,
maybe_build_sync_local_same_format_provider_decision_payload,
};
pub(crate) use super::specialized::{
maybe_build_stream_local_gemini_files_decision_payload,
maybe_build_stream_local_image_decision_payload,
maybe_build_sync_local_gemini_files_decision_payload,
maybe_build_sync_local_image_decision_payload, maybe_build_sync_local_video_decision_payload,
};
pub(crate) use super::standard::{
maybe_build_stream_local_decision_payload,
maybe_build_stream_local_openai_responses_decision_payload,
maybe_build_stream_local_standard_decision_payload, maybe_build_sync_local_decision_payload,
maybe_build_sync_local_openai_responses_decision_payload,
maybe_build_sync_local_standard_decision_payload,
};
@@ -0,0 +1,188 @@
use aether_ai_serving::{
build_ai_execution_decision_from_plan, run_ai_stream_decision_path,
AiExecutionDecisionFromPlanParts, AiStreamDecisionPathPort, AiStreamDecisionStep,
};
use async_trait::async_trait;
use crate::ai_serving::planner::common::{
EXECUTION_RUNTIME_STREAM_DECISION_ACTION, OPENAI_VIDEO_CONTENT_PLAN_KIND,
};
use crate::ai_serving::planner::route::{
is_matching_stream_request, resolve_execution_runtime_stream_plan_kind,
};
use crate::ai_serving::{resolve_decision_execution_runtime_auth_context, GatewayControlDecision};
use crate::{AiExecutionDecision, AppState, GatewayError};
pub(crate) async fn maybe_build_stream_decision_payload(
state: &AppState,
parts: &http::request::Parts,
trace_id: &str,
decision: &GatewayControlDecision,
body_json: &serde_json::Value,
body_base64: Option<&str>,
) -> Result<Option<AiExecutionDecision>, GatewayError> {
let Some(plan_kind) = resolve_execution_runtime_stream_plan_kind(parts, decision) else {
return Ok(None);
};
if !is_matching_stream_request(plan_kind, parts, body_json, body_base64) {
return Ok(None);
}
let port = GatewayStreamDecisionPathPort {
state,
parts,
trace_id,
decision,
body_json,
body_base64,
plan_kind,
};
run_ai_stream_decision_path(&port).await
}
struct GatewayStreamDecisionPathPort<'a> {
state: &'a AppState,
parts: &'a http::request::Parts,
trace_id: &'a str,
decision: &'a GatewayControlDecision,
body_json: &'a serde_json::Value,
body_base64: Option<&'a str>,
plan_kind: &'a str,
}
#[async_trait]
impl AiStreamDecisionPathPort for GatewayStreamDecisionPathPort<'_> {
type Decision = AiExecutionDecision;
type Error = GatewayError;
async fn build_stream_decision_step(
&self,
step: AiStreamDecisionStep,
) -> Result<Option<Self::Decision>, Self::Error> {
match step {
AiStreamDecisionStep::LocalVideoContent => {
maybe_build_local_video_task_content_stream_decision_payload(
self.state,
self.parts,
self.trace_id,
self.decision,
self.plan_kind,
)
.await
}
AiStreamDecisionStep::LocalImage => {
super::maybe_build_stream_local_image_decision_payload(
self.state,
self.parts,
self.body_json,
self.body_base64,
self.trace_id,
self.decision,
self.plan_kind,
)
.await
}
AiStreamDecisionStep::LocalOpenAiChat => {
super::maybe_build_stream_local_decision_payload(
self.state,
self.parts,
self.trace_id,
self.decision,
self.body_json,
self.plan_kind,
)
.await
}
AiStreamDecisionStep::LocalOpenAiResponses => {
super::maybe_build_stream_local_openai_responses_decision_payload(
self.state,
self.parts,
self.trace_id,
self.decision,
self.body_json,
self.plan_kind,
)
.await
}
AiStreamDecisionStep::LocalStandardFamily => {
super::maybe_build_stream_local_standard_decision_payload(
self.state,
self.parts,
self.trace_id,
self.decision,
self.body_json,
self.plan_kind,
)
.await
}
AiStreamDecisionStep::LocalSameFormatProvider => {
super::maybe_build_stream_local_same_format_provider_decision_payload(
self.state,
self.parts,
self.trace_id,
self.decision,
self.body_json,
self.plan_kind,
)
.await
}
AiStreamDecisionStep::LocalGeminiFiles => {
super::maybe_build_stream_local_gemini_files_decision_payload(
self.state,
self.parts,
self.trace_id,
self.decision,
self.plan_kind,
)
.await
}
}
}
}
async fn maybe_build_local_video_task_content_stream_decision_payload(
state: &AppState,
parts: &http::request::Parts,
trace_id: &str,
decision: &GatewayControlDecision,
plan_kind: &str,
) -> Result<Option<AiExecutionDecision>, GatewayError> {
if plan_kind != OPENAI_VIDEO_CONTENT_PLAN_KIND
|| decision.route_family.as_deref() != Some("openai")
{
return Ok(None);
}
let _ = state
.hydrate_video_task_for_route(decision.route_family.as_deref(), parts.uri.path())
.await?;
let Some(action) = state.video_tasks.prepare_openai_content_stream_action(
parts.uri.path(),
parts.uri.query(),
trace_id,
) else {
return Ok(None);
};
let crate::video_tasks::LocalVideoTaskContentAction::StreamPlan(plan) = action else {
return Ok(None);
};
let plan = *plan;
Ok(Some(build_ai_execution_decision_from_plan(
AiExecutionDecisionFromPlanParts {
action: EXECUTION_RUNTIME_STREAM_DECISION_ACTION.to_string(),
decision_kind: Some(plan_kind.to_string()),
request_id: None,
upstream_base_url: None,
include_auth_pair: false,
plan,
report_kind: None,
report_context: None,
auth_context: resolve_decision_execution_runtime_auth_context(decision),
},
)))
}
@@ -0,0 +1,257 @@
use aether_ai_serving::{
build_ai_execution_decision_from_plan, infer_ai_upstream_base_url, run_ai_sync_decision_path,
AiExecutionDecisionFromPlanParts, AiSyncDecisionPathPort, AiSyncDecisionStep,
};
use async_trait::async_trait;
use tracing::debug;
use crate::ai_serving::planner::common::{
EXECUTION_RUNTIME_SYNC_DECISION_ACTION, GEMINI_FILES_DELETE_PLAN_KIND,
GEMINI_FILES_GET_PLAN_KIND, GEMINI_FILES_LIST_PLAN_KIND, GEMINI_VIDEO_CANCEL_SYNC_PLAN_KIND,
OPENAI_VIDEO_CANCEL_SYNC_PLAN_KIND, OPENAI_VIDEO_DELETE_SYNC_PLAN_KIND,
OPENAI_VIDEO_REMIX_SYNC_PLAN_KIND,
};
use crate::ai_serving::planner::route::resolve_execution_runtime_sync_plan_kind;
use crate::ai_serving::{
build_execution_runtime_auth_context, resolve_execution_runtime_auth_context,
GatewayControlDecision,
};
use crate::{AiExecutionDecision, AppState, GatewayError};
pub(crate) async fn maybe_build_sync_decision_payload(
state: &AppState,
parts: &http::request::Parts,
trace_id: &str,
decision: &GatewayControlDecision,
body_json: &serde_json::Value,
body_base64: Option<&str>,
body_is_empty: bool,
) -> Result<Option<AiExecutionDecision>, GatewayError> {
let Some(plan_kind) = resolve_execution_runtime_sync_plan_kind(parts, decision) else {
return Ok(None);
};
let port = GatewaySyncDecisionPathPort {
state,
parts,
trace_id,
decision,
body_json,
body_base64,
body_is_empty,
plan_kind,
};
run_ai_sync_decision_path(&port).await
}
struct GatewaySyncDecisionPathPort<'a> {
state: &'a AppState,
parts: &'a http::request::Parts,
trace_id: &'a str,
decision: &'a GatewayControlDecision,
body_json: &'a serde_json::Value,
body_base64: Option<&'a str>,
body_is_empty: bool,
plan_kind: &'a str,
}
#[async_trait]
impl AiSyncDecisionPathPort for GatewaySyncDecisionPathPort<'_> {
type Decision = AiExecutionDecision;
type Error = GatewayError;
fn sync_decision_step_enabled(&self, step: AiSyncDecisionStep) -> bool {
if step == AiSyncDecisionStep::LocalGeminiFiles {
return matches!(
self.plan_kind,
GEMINI_FILES_LIST_PLAN_KIND
| GEMINI_FILES_GET_PLAN_KIND
| GEMINI_FILES_DELETE_PLAN_KIND
);
}
true
}
async fn build_sync_decision_step(
&self,
step: AiSyncDecisionStep,
) -> Result<Option<Self::Decision>, Self::Error> {
match step {
AiSyncDecisionStep::VideoTaskFollowUp => {
maybe_build_local_video_task_follow_up_sync_decision_payload(
self.state,
self.parts,
self.body_json,
self.trace_id,
self.decision,
self.plan_kind,
)
.await
}
AiSyncDecisionStep::LocalVideo => {
super::maybe_build_sync_local_video_decision_payload(
self.state,
self.parts,
self.body_json,
self.trace_id,
self.decision,
self.plan_kind,
)
.await
}
AiSyncDecisionStep::LocalImage => {
super::maybe_build_sync_local_image_decision_payload(
self.state,
self.parts,
self.body_json,
self.body_base64,
self.trace_id,
self.decision,
self.plan_kind,
)
.await
}
AiSyncDecisionStep::LocalOpenAiChat => {
super::maybe_build_sync_local_decision_payload(
self.state,
self.parts,
self.trace_id,
self.decision,
self.body_json,
self.plan_kind,
)
.await
}
AiSyncDecisionStep::LocalOpenAiResponses => {
super::maybe_build_sync_local_openai_responses_decision_payload(
self.state,
self.parts,
self.trace_id,
self.decision,
self.body_json,
self.plan_kind,
)
.await
}
AiSyncDecisionStep::LocalStandardFamily => {
super::maybe_build_sync_local_standard_decision_payload(
self.state,
self.parts,
self.trace_id,
self.decision,
self.body_json,
self.plan_kind,
)
.await
}
AiSyncDecisionStep::LocalSameFormatProvider => {
super::maybe_build_sync_local_same_format_provider_decision_payload(
self.state,
self.parts,
self.trace_id,
self.decision,
self.body_json,
self.plan_kind,
)
.await
}
AiSyncDecisionStep::LocalGeminiFiles => {
super::maybe_build_sync_local_gemini_files_decision_payload(
self.state,
self.parts,
self.body_json,
self.body_base64,
self.body_is_empty,
self.trace_id,
self.decision,
self.plan_kind,
)
.await
}
}
}
}
async fn maybe_build_local_video_task_follow_up_sync_decision_payload(
state: &AppState,
parts: &http::request::Parts,
body_json: &serde_json::Value,
trace_id: &str,
decision: &GatewayControlDecision,
plan_kind: &str,
) -> Result<Option<AiExecutionDecision>, GatewayError> {
if !matches!(
plan_kind,
OPENAI_VIDEO_REMIX_SYNC_PLAN_KIND
| OPENAI_VIDEO_CANCEL_SYNC_PLAN_KIND
| OPENAI_VIDEO_DELETE_SYNC_PLAN_KIND
| GEMINI_VIDEO_CANCEL_SYNC_PLAN_KIND
) {
return Ok(None);
}
let _ = state
.hydrate_video_task_for_route(decision.route_family.as_deref(), parts.uri.path())
.await?;
let auth_context = resolve_execution_runtime_auth_context(
state,
decision,
&parts.headers,
&parts.uri,
trace_id,
)
.await?;
let Some(auth_context) = auth_context else {
return Ok(None);
};
let Some(follow_up) = state.video_tasks.prepare_follow_up_sync_plan(
plan_kind,
parts.uri.path(),
Some(body_json),
Some(&auth_context),
trace_id,
) else {
return Ok(None);
};
let aether_video_tasks_core::LocalVideoTaskFollowUpPlan {
plan,
report_kind,
report_context,
} = follow_up;
let upstream_base_url = infer_ai_upstream_base_url(&plan.url);
debug!(
event_name = "local_video_follow_up_sync_decision_payload_built",
log_type = "debug",
trace_id = %trace_id,
request_id = %trace_id,
candidate_id = ?plan.candidate_id,
provider_id = %plan.provider_id,
endpoint_id = %plan.endpoint_id,
key_id = %plan.key_id,
plan_kind,
downstream_path = %parts.uri.path(),
provider_api_format = %plan.provider_api_format,
client_api_format = %plan.client_api_format,
upstream_base_url = ?upstream_base_url,
upstream_url = %plan.url,
"gateway built local video follow-up sync decision payload"
);
Ok(Some(build_ai_execution_decision_from_plan(
AiExecutionDecisionFromPlanParts {
action: EXECUTION_RUNTIME_SYNC_DECISION_ACTION.to_string(),
decision_kind: Some(plan_kind.to_string()),
request_id: Some(trace_id.to_string()),
upstream_base_url,
include_auth_pair: true,
plan,
report_kind,
report_context,
auth_context: Some(build_execution_runtime_auth_context(&auth_context)),
},
)))
}