Files
Aether/apps/aether-gateway/src/api/ai/registry.rs
T
AAEE86 71b54070e8 feat(gateway): Codex/OpenAI Responses WebSocket 代理模式
在 /v1/responses 上支持 WebSocket 升级,把客户端帧中继到上游 Codex /
OpenAI Responses WebSocket 端点,同时保持既有的路由、鉴权、配额与用量
语义:

- 路由与准入:control/route/ai.rs 识别 WebSocket 升级请求;
  websocket/ingress.rs 复用 API Key 鉴权、IP 规则与并发许可,并引入
  独立的 WebSocket 连接许可
- 中继:websocket/responses/* 按 connection / session / turn 分层,
  帧解析归一化、socket 写入有界、continuation 保持调度亲和性
- 配额:orchestration/codex_quota_breaker.rs 在账号配额耗尽时熔断并
  自动恢复,不再直接断开客户端连接
- 用量:每个 turn 的终态用量落库,request_metadata 记录
  websocket_mode / websocket_transport,管理端与 usage 视图暴露
  is_websocket
- 管理端:provider 可配置 Responses WebSocket 开关
2026-08-17 14:50:33 +08:00

169 lines
5.9 KiB
Rust

use axum::body::Body;
use axum::extract::Request;
use axum::http::{header, HeaderValue, Response, StatusCode};
use axum::routing::{any, get, post};
use axum::Router;
use super::{aliyun, claude, doubao, gemini, jina, openai};
use crate::api::response::build_local_http_error_response_with_request_path;
use crate::headers::extract_or_generate_trace_id;
use crate::{
handlers::proxy::{proxy_request, responses_websocket},
state::AppState,
GatewayError,
};
// Router registration patterns live here so AI public ingress has a single mount registry.
// They intentionally stay separate from manifest-facing route inventories in constants.rs,
// which describe operational compatibility surfaces rather than the concrete axum mount list.
const AI_POST_ROUTE_PATTERNS: &[&str] = &[
"/v1/chat/completions",
"/v1/embeddings",
"/v1/rerank",
"/v1/responses",
"/v1/responses/compact",
"/v1/alpha/search",
"/v1/images/generations",
"/v1/images/edits",
"/v1/interactions",
"/v1beta/interactions",
"/v1internal:loadCodeAssist",
"/v1internal:fetchAvailableModels",
"/v1internal:retrieveUserQuotaSummary",
"/v1internal:fetchUserInfo",
"/v1internal:fetchAdminControls",
"/v1internal:setUserSettings",
"/v1internal:listExperiments",
"/v1internal:recordCodeAssistMetrics",
"/v1internal:writeTrajectoryAcls",
"/v1internal:streamGenerateContent",
];
const CLAUDE_POST_ROUTE_PATTERNS: &[&str] = &["/v1/messages", "/v1/messages/count_tokens"];
const AI_ANY_ROUTE_PATTERNS: &[&str] = &[
"/v1/models/{*gemini_path}",
"/v1beta/models/{*gemini_path}",
"/v1beta/operations",
"/v1beta/operations/{*operation_path}",
"/v1/videos",
"/v1/videos/{*video_path}",
"/upload/v1beta/files",
"/v1beta/files",
"/v1beta/files/{*file_path}",
];
pub(crate) fn mount_ai_routes(mut router: Router<AppState>) -> Router<AppState> {
for path in AI_POST_ROUTE_PATTERNS {
router = if *path == "/v1/responses" {
router.route(path, get(responses_websocket).post(proxy_request))
} else {
router.route(path, post(proxy_request))
};
}
for path in CLAUDE_POST_ROUTE_PATTERNS {
router = router.route(
path,
post(proxy_request).fallback(claude_method_not_allowed),
);
}
for path in AI_ANY_ROUTE_PATTERNS {
router = router.route(path, any(proxy_request));
}
router
}
async fn claude_method_not_allowed(request: Request) -> Result<Response<Body>, GatewayError> {
let trace_id = extract_or_generate_trace_id(request.headers());
let mut response = build_local_http_error_response_with_request_path(
&trace_id,
None,
Some(request.uri().path()),
StatusCode::METHOD_NOT_ALLOWED,
"Method not allowed",
)?;
response
.headers_mut()
.insert(header::ALLOW, HeaderValue::from_static("POST"));
Ok(response)
}
pub(crate) fn public_api_format_local_path(api_format: &str) -> &'static str {
let normalized = api_format.trim().to_ascii_lowercase();
openai::local_path(&normalized)
.or_else(|| claude::local_path(&normalized))
.or_else(|| gemini::local_path(&normalized))
.or_else(|| jina::local_path(&normalized))
.or_else(|| doubao::local_path(&normalized))
.or_else(|| aliyun::local_path(&normalized))
.unwrap_or("/")
}
pub(crate) fn normalize_admin_endpoint_signature(api_format: &str) -> Option<&'static str> {
let normalized = api_format.trim().to_ascii_lowercase();
openai::normalized_signature(&normalized)
.or_else(|| claude::normalized_signature(&normalized))
.or_else(|| gemini::normalized_signature(&normalized))
.or_else(|| jina::normalized_signature(&normalized))
.or_else(|| doubao::normalized_signature(&normalized))
.or_else(|| aliyun::normalized_signature(&normalized))
}
pub(crate) fn admin_endpoint_signature_parts(
api_format: &str,
) -> Option<(&'static str, &'static str, &'static str)> {
let normalized = normalize_admin_endpoint_signature(api_format)?;
let (api_family, endpoint_kind) = normalized.split_once(':')?;
Some((normalized, api_family, endpoint_kind))
}
pub(crate) fn admin_default_body_rules_for_signature(
api_format: &str,
provider_type: Option<&str>,
) -> Option<(String, Vec<serde_json::Value>)> {
let normalized_api_format = normalize_admin_endpoint_signature(api_format)?.to_string();
let _ = provider_type;
Some((normalized_api_format, Vec::new()))
}
#[cfg(test)]
mod tests {
use super::{admin_endpoint_signature_parts, public_api_format_local_path};
#[test]
fn supports_data_api_endpoint_signatures_and_public_paths() {
for (api_format, family, kind, path) in [
("openai:embedding", "openai", "embedding", "/v1/embeddings"),
(
"gemini:interactions",
"gemini",
"interactions",
"/v1/interactions",
),
(
"gemini:embedding",
"gemini",
"embedding",
"/v1beta/models/{model}:{action}",
),
("jina:embedding", "jina", "embedding", "/v1/embeddings"),
("doubao:embedding", "doubao", "embedding", "/v1/embeddings"),
(
"aliyun:multimodal_embedding",
"aliyun",
"multimodal_embedding",
"/api/v1/services/embeddings/multimodal-embedding/multimodal-embedding",
),
("openai:rerank", "openai", "rerank", "/v1/rerank"),
("openai:search", "openai", "search", "/v1/alpha/search"),
("jina:rerank", "jina", "rerank", "/v1/rerank"),
] {
assert_eq!(
admin_endpoint_signature_parts(api_format),
Some((api_format, family, kind))
);
assert_eq!(public_api_format_local_path(api_format), path);
}
}
}