Compare commits

...
4 Commits
Author SHA1 Message Date
ZyyandCodex d89db84a77 chore(release): v3.35.1
Co-authored-by: Codex <noreply@openai.com>
2026-10-29 13:09:42 +08:00
ZyyandCodex 6504761ce4 fix(responses): keep slow websocket uploads alive
Track inbound byte progress before WebSocket decoding so active uploads do not trip the heartbeat timeout. Reuse Axum handshake validation and report actual receive idle time.

Cover successive slow uploads and stalled partial frames, and document the downstream liveness contract.

Validation: 652 API and gateway tests passed; production API check, strict workspace Clippy, and formatting passed.

Co-authored-by: Codex <noreply@openai.com>
2026-10-29 13:03:06 +08:00
ZyyandCodex 5877b0cb2f fix(openai): tolerate session affinity storage jitter
Raise the session affinity storage budget to 500ms while keeping cyber policy operations on a separate 100ms budget. Preserve fail-closed binding behavior and cover delayed admission and timeout rejection before upstream sending.

Refs #549

Co-authored-by: Codex <noreply@openai.com>
2026-10-29 12:04:09 +08:00
ZyyandCodex 958e13c370 fix(errors): standardize client messages and correct error mappings
Return non-retryable client version errors and correct provider error types.
Keep safe user messages separate from operational diagnostics.
Unify error wording and document the conventions in the development skill.

Co-authored-by: Codex <noreply@openai.com>
2026-10-29 01:57:31 +08:00
105 changed files with 1674 additions and 684 deletions
+21
View File
@@ -17,6 +17,7 @@ description: Codex Proxy RS 开发、修复、排障、代码审查和文档修
| 开发、排查或审查插件接入、宿主 SDK、Runtime、扩展接口或独立网关插件;目标在 `backend/crates/gateway-plugin/`、`modules/plugins/` | 完整读取[插件职责边界](references/plugin-boundaries.md)及所用 [SDK](../../../backend/crates/gateway-plugin/sdk/README.md) 类型与能力合同;宿主维护自身合同、资源与稳定性,插件业务错误在插件侧修复,不在宿主、SDK 或 Runtime 中补偿;独立插件开发、排查、审查另用 [cpr-plugin-dev](../cpr-plugin-dev/SKILL.md) |
| 开发、排查或审查服务端接口、路由、调度、账号与用量规则、持久化、后台任务或协议行为;目标是 `backend/` 中的实现、配置、迁移,或 Rust 源码 | [Workspace 边界](../../../docs/architecture.md#3-workspace-边界)的模块与依赖规则、所属模块及[后端自审](../../../docs/architecture.md#后端自审);Rust 使用 `$rust-best-practices` 和下方后端注释要求,宿主 Rust 同时读取 [Rust 模块组织约定](../../../docs/architecture.md#32-rust-模块组织约定) |
| 修改页面接口调用,或开发、排查、审查面向管理端或模型客户端的 HTTP/WS API 合同 | [API](../../../docs/api.md)对应章节;优先复用已有接口,核对调用方 → 服务端解析 → 实际查询或执行,不能只凭前端类型认定参数生效;按实际改动叠加前后端规范 |
| 新增、修改或审查客户端可见错误、失败提示、后台任务状态文案 | 下方[错误文案](#错误文案),并按实际出口核对[错误与诊断三层边界](../../../docs/architecture.md#错误与诊断三层边界) |
| 模块或调用链变更 | [Workspace 边界](../../../docs/architecture.md#3-workspace-边界)及所属模块章节,不通读整份架构 |
| 新增、调整、清理或审查测试 | 下方[测试维护](#测试维护),按当前行为、职责归属与已有覆盖判断保留、合并或删除 |
| 修改部署行为、`deploy/` 配置或数据库迁移 | 按范围读取[部署](../../../deploy/README.md)、[迁移](../../../backend/migrations/README.md)对应章节 |
@@ -55,3 +56,23 @@ description: Codex Proxy RS 开发、修复、排障、代码审查和文档修
- 每个 Rust 文件顶层使用简短的中文 `//!` 注释说明文件职责,覆盖生产源码、测试与构建脚本;测试文件说明测试范围或辅助用途,生成文件同步维护生成器
- 注释不使用中文或英文句号,多句说明按语义分行;保留 URL、版本号、标识符和代码示例中有语义的点号
- 文件说明聚焦当前功能与职责边界,局部注释解释原因和约束,避免复述代码或记录修改经过
## 错误文案
适用于项目自定义的客户端提示,包括 HTTP、WS、SSE 和任务失败状态;原始上游错误与内部诊断遵守[三层边界](../../../docs/architecture.md#错误与诊断三层边界),不为统一外观翻译、截短或改写
- 管理端自定义提示统一中文,模型 API 自定义提示统一英文;英文句首大写、句末使用句号,API、Codex 等缩写及专有名词保持正确大小写,中文短提示不加句末句号
- 默认一句说明具体问题,确有必要才补第二句处理办法,不设机械字数限制;明确字段、对象或限制,避免只说「请求不合法」或堆叠内部术语
- 处理办法必须明确且适用;不把「请稍后重试」「联系管理员」作为统一后缀,不罗列尚未确认的网络、权限、磁盘等可能原因,不对执行结果未知的操作笼统建议重试
- 机器码、状态与结构化字段负责程序判断,文案供人阅读;只改措辞时保留分类、重试和账号处置语义,先核对现有调用方是否依赖消息文本
- 在拥有错误事实的模块提供安全提示,保留独立的内部原因链;不在响应出口批量首字母大写、翻译或裁剪任意消息,以免改写上游原文
| 场景 | 文案示例 |
| --- | --- |
| 日费用额度耗尽 | `Daily spending limit reached.` |
| 请求过大 | `Request too large. Reduce the input size.` |
| 客户端过旧 | `Codex CLI is outdated. Upgrade to 0.152.0 or later.` |
| 名称为空 | `请输入 API Key 名称` |
| 更新包校验失败 | `更新包校验失败,请重新下载` |
审查时沿实际出口检查语言、大小写、标点、长度和处理建议;复用现有行为测试核对错误码及敏感信息边界,不为逐条文案建立重复的快照或字符串清单测试
+2
View File
@@ -1743,6 +1743,8 @@ dependencies = [
"http",
"http-body",
"http-body-util",
"hyper",
"hyper-util",
"regex",
"secrecy",
"serde",
+13 -1
View File
@@ -68,6 +68,7 @@ pub struct AdminError {
kind: AdminErrorKind,
message: String,
source: Option<gateway_core::error::ErrorSource>,
sensitive_context_redacted: bool,
}
impl AdminError {
@@ -77,6 +78,7 @@ impl AdminError {
kind,
message: message.into(),
source: None,
sensitive_context_redacted: false,
}
}
@@ -86,9 +88,19 @@ impl AdminError {
self
}
#[must_use]
pub fn redact_sensitive_context(mut self) -> Self {
self.sensitive_context_redacted = true;
self
}
#[must_use]
pub fn error_details(&self) -> Option<gateway_core::error::ErrorDetails> {
gateway_core::error::ErrorDetails::capture(self.source.as_ref(), None, false)
gateway_core::error::ErrorDetails::capture(
self.source.as_ref(),
None,
self.sensitive_context_redacted,
)
}
#[must_use]
@@ -72,7 +72,7 @@ pub fn account_quota_forecasts(
},
extrapolated: false,
source: None,
unavailable_reason: Some("没有可统计的周/月额度窗口,请先刷新账号额度。"),
unavailable_reason: Some("缺少周/月额度窗口,请刷新账号额度"),
low_sample: false,
incomplete_cost: false,
incomplete_tokens: false,
@@ -138,30 +138,27 @@ impl AccountQuotaForecast {
self.incomplete_tokens = usage.is_some_and(|usage| usage.missing_token_count > 0);
let method = sample.map_or(QuotaForecastMethod::Cumulative, |sample| sample.method);
let Some(start) = start.filter(|start| *start <= now && now < reset_at) else {
self.unavailable_reason = Some("额度窗口已过期或边界无效,请刷新账号额度后重试。");
self.unavailable_reason = Some("额度窗口已过期或无效,请刷新账号额度");
return;
};
if !observed_at.is_some_and(|observed| start <= observed && observed <= now) {
self.unavailable_reason = Some("缺少本周期的额度快照,请先刷新账号额度。");
self.unavailable_reason = Some("缺少本周期的额度快照,请刷新账号额度");
return;
}
if sample.is_some_and(|sample| sample.discontinuous) {
self.unavailable_reason =
Some("额度观测出现回落或累计记录不连续,正在重新积累配对样本。");
self.unavailable_reason = Some("额度回落或记录不连续,正在重新积累配对样本");
return;
}
if account_added_at > start && method == QuotaForecastMethod::Cumulative {
self.unavailable_reason = Some(
"本周期开始时的记录不完整,正在积累至少 5 个百分点的配对观测,无需等待下次重置。",
);
self.unavailable_reason = Some("周期初记录不完整,正在积累至少 5 个百分点的配对观测");
return;
}
let Some(percent) = percent else {
self.unavailable_reason = Some("已用比例未知,请刷新额度后查看预测。");
self.unavailable_reason = Some("已用比例未知,请刷新账号额度");
return;
};
let Some(usage) = usage.filter(|usage| usage.request_count > 0) else {
self.unavailable_reason = Some("本周期没有网关用量记录,暂时无法预测额度。");
self.unavailable_reason = Some("本周期没有网关用量记录,无法预测额度");
return;
};
let Some(sample) = sample.filter(|sample| {
@@ -172,8 +169,7 @@ impl AccountQuotaForecast {
&& sample.sampled_percent >= MIN_USED_PERCENT
&& sample.sampled_percent <= percent
}) else {
self.unavailable_reason =
Some("有效额度进度不足 5 个百分点或采样边界无效,请继续积累用量。");
self.unavailable_reason = Some("有效额度进度不足 5 个百分点或采样边界无效");
return;
};
self.low_sample = sample.sampled_percent < LOW_SAMPLE_PERCENT
@@ -196,7 +192,7 @@ impl AccountQuotaForecast {
.and_then(|(used, remaining)| estimate(used + remaining, factor));
self.unavailable_reason = if self.estimated_tokens.is_none() && self.estimated_usd.is_none()
{
Some("本周期暂无可用于估算的 Token 或费用数据,请积累用量后重试。")
Some("本周期缺少可用于估算的 Token 或费用数据")
} else {
None
};
@@ -148,7 +148,7 @@ pub trait ProviderAdmin: Send + Sync {
> {
Err(gateway_core::settings::privacy::PrivacyError {
rule_index: 0,
reason: "Provider 不支持隐私策略",
reason: "该服务商不支持隐私策略",
})
}
@@ -161,7 +161,7 @@ pub trait ProviderAdmin: Send + Sync {
> {
Err(gateway_core::settings::privacy::PrivacyError {
rule_index: 0,
reason: "Provider 不支持隐私策略",
reason: "该服务商不支持隐私策略",
})
}
@@ -38,11 +38,13 @@ pub enum SystemOperationErrorKind {
}
/// 不泄漏路径、命令行或发布凭据的系统操作错误
#[derive(Debug, Clone, PartialEq, Eq, thiserror::Error)]
#[error("system operation failed: {message}")]
#[derive(Debug, Clone, thiserror::Error)]
#[error("{message}")]
pub struct SystemOperationError {
kind: SystemOperationErrorKind,
message: String,
source: Option<gateway_core::error::ErrorSource>,
sensitive_context_redacted: bool,
}
impl SystemOperationError {
@@ -51,9 +53,37 @@ impl SystemOperationError {
Self {
kind,
message: message.into(),
source: None,
sensitive_context_redacted: false,
}
}
#[must_use]
pub fn with_source(mut self, source: impl Into<gateway_core::error::ErrorSource>) -> Self {
self.source = Some(source.into());
self
}
#[must_use]
pub fn redact_sensitive_context(mut self) -> Self {
self.sensitive_context_redacted = true;
self
}
#[must_use]
pub const fn sensitive_context_redacted(&self) -> bool {
self.sensitive_context_redacted
}
#[must_use]
pub fn error_details(&self) -> Option<gateway_core::error::ErrorDetails> {
gateway_core::error::ErrorDetails::capture(
self.source.as_ref(),
None,
self.sensitive_context_redacted,
)
}
#[must_use]
pub const fn kind(&self) -> SystemOperationErrorKind {
self.kind
@@ -116,14 +116,14 @@ pub trait AccountsService: Send + Sync {
&self,
_account_id: &ProviderAccountId,
) -> Result<AccountPersonalInfo, AdminError> {
Err(AdminError::invalid("当前 Provider 不支持个人信息"))
Err(AdminError::invalid("该服务商不支持个人信息查询"))
}
async fn profile_avatar(
&self,
_account_id: &ProviderAccountId,
) -> Result<ProviderProfileAvatar, AdminError> {
Err(AdminError::invalid("当前 Provider 不支持账号头像"))
Err(AdminError::invalid("该服务商不支持账号头像"))
}
async fn reset_credit_automation_status(
@@ -154,7 +154,7 @@ pub trait AccountsService: Send + Sync {
_context: &MutationContext,
_account_id: ProviderAccountId,
) -> Result<ProviderResetCredits, AdminError> {
Err(AdminError::invalid("当前 Provider 不支持重置额度"))
Err(AdminError::invalid("该服务商不支持额度重置"))
}
async fn consume_reset_credit(
@@ -162,7 +162,7 @@ pub trait AccountsService: Send + Sync {
_context: &MutationContext,
_command: ConsumeProviderResetCredit,
) -> Result<ProviderResetCreditResult, AdminError> {
Err(AdminError::invalid("当前 Provider 不支持重置额度"))
Err(AdminError::invalid("该服务商不支持额度重置"))
}
async fn models(
@@ -315,7 +315,7 @@ impl DefaultAccountsService {
.load_account(account_id.as_str(), runtime)
.await
.map_err(|error| map_store_error(error, "provider account"))?
.ok_or_else(|| AdminError::not_found("Provider 账号不存在"))
.ok_or_else(|| AdminError::not_found("服务商账号不存在"))
}
async fn provider_for_account(
@@ -564,7 +564,7 @@ impl AccountsService for DefaultAccountsService {
.zip(quotas)
.map(|(mut item, quota)| {
let id = ProviderAccountId::new(item.account.id.clone())
.map_err(|_| AdminError::invalid("Provider 账号 ID 不合法"))?;
.map_err(|_| AdminError::invalid("服务商账号 ID 不合法"))?;
let capabilities = providers
.require(&item.account.provider_kind)
.map(|provider| {
@@ -743,7 +743,7 @@ impl AccountsService for DefaultAccountsService {
command: UpdateAccount,
) -> Result<AccountUpdateResult, AdminError> {
let account_id = ProviderAccountId::new(command.account_id.clone())
.map_err(|_| AdminError::invalid("Provider 账号 ID 不合法"))?;
.map_err(|_| AdminError::invalid("服务商账号 ID 不合法"))?;
let (_, provider) = self.provider_for_account(&account_id).await?;
let enabled = command.enabled;
let result = self
@@ -771,7 +771,7 @@ impl AccountsService for DefaultAccountsService {
.iter()
.map(|id| {
ProviderAccountId::new(id.clone())
.map_err(|_| AdminError::invalid("Provider 账号 ID 不合法"))
.map_err(|_| AdminError::invalid("服务商账号 ID 不合法"))
})
.collect::<Result<Vec<_>, _>>()?;
let mut providers = BTreeMap::<
@@ -326,17 +326,15 @@ impl DefaultBackupService {
/// 校验存储配置;空串视为非法,Secret 缺省表示保留旧值
fn validate_storage(command: &UpdateBackupStorageCommand) -> Result<(), AdminError> {
validate_endpoint(&command.endpoint)?;
validate_nonempty("region", &command.region)?;
validate_nonempty("bucket", &command.bucket)?;
validate_nonempty("accessKeyId", &command.access_key_id)?;
validate_nonempty("存储区域", &command.region)?;
validate_nonempty("存储桶名称", &command.bucket)?;
validate_nonempty("访问密钥 ID", &command.access_key_id)?;
if let Some(secret) = command.secret_access_key.as_ref() {
let value = secret.expose_secret();
if value.is_empty() {
return Err(AdminError::bad_request(
"secretAccessKey 不能为空字符串;缺省表示保留旧值",
));
return Err(AdminError::bad_request("访问密钥不能为空"));
}
validate_length("secretAccessKey", value, 512)?;
validate_length("访问密钥", value, 512)?;
}
crate::model::backup::normalize_prefix(&command.prefix).map_err(map_backup_error)?;
Ok(())
@@ -344,17 +342,15 @@ fn validate_storage(command: &UpdateBackupStorageCommand) -> Result<(), AdminErr
fn validate_endpoint(value: &str) -> Result<(), AdminError> {
if value.is_empty() {
return Err(AdminError::bad_request("endpoint 不能为空"));
return Err(AdminError::bad_request("备份存储地址不能为空"));
}
if !value.starts_with("https://") {
return Err(AdminError::bad_request(
"endpoint 必须使用 HTTPS;仅测试或显式开发配置允许 HTTP",
));
return Err(AdminError::bad_request("备份存储地址必须使用 HTTPS"));
}
if value.contains('@') || value.bytes().any(|byte| byte.is_ascii_control()) {
return Err(AdminError::bad_request("endpoint 格式非法"));
return Err(AdminError::bad_request("备份存储地址格式不合法"));
}
validate_length("endpoint", value, 2048)
validate_length("备份存储地址", value, 2048)
}
fn validate_nonempty(field: &str, value: &str) -> Result<(), AdminError> {
@@ -94,7 +94,7 @@ impl ClientKeyService for DefaultClientKeyService {
.get_client_key(id)
.await
.map_err(|error| map_store_error(error, "client API key"))?
.ok_or_else(|| AdminError::not_found("Client API Key 不存在"))
.ok_or_else(|| AdminError::not_found("API Key 不存在"))
}
async fn budget(&self, id: &ClientApiKeyId) -> Result<ClientBudgetStatus, AdminError> {
@@ -149,7 +149,7 @@ impl ClientKeyService for DefaultClientKeyService {
.reveal_client_key(id)
.await
.map_err(|error| map_store_error(error, "client API key"))?
.ok_or_else(|| AdminError::not_found("Client API Key 不存在"))
.ok_or_else(|| AdminError::not_found("API Key 不存在"))
}
async fn create(
@@ -158,7 +158,7 @@ impl ClientKeyService for DefaultClientKeyService {
command: CreateClientKey,
) -> Result<CreatedClientKey, AdminError> {
crate::model::client_keys::validate_group_ids(&command.group_ids)
.map_err(|_| AdminError::invalid("Client API Key 分组不合法"))?;
.map_err(|_| AdminError::invalid("API Key 分组不合法"))?;
for (provider, profile) in &command.request_profile_overrides {
self.providers
.require(provider)
@@ -202,7 +202,7 @@ impl ClientKeyService for DefaultClientKeyService {
command: UpdateClientKey,
) -> Result<ClientKeyMutation, AdminError> {
crate::model::client_keys::validate_group_ids(&command.group_ids)
.map_err(|_| AdminError::invalid("Client API Key 分组不合法"))?;
.map_err(|_| AdminError::invalid("API Key 分组不合法"))?;
for (provider, profile) in &command.request_profile_override_updates {
if let Some(profile) = profile {
self.providers
@@ -277,9 +277,7 @@ fn validate_cursor(query: &ClientKeyListQuery) -> Result<(), AdminError> {
return Ok(());
};
if cursor.sort != query.sort {
return Err(AdminError::invalid(
"Client API Key 游标排序与查询条件不一致",
));
return Err(AdminError::invalid("分页游标与排序条件不一致"));
}
let matches = matches!(
(cursor.sort.field, &cursor.value),
@@ -300,7 +298,7 @@ fn validate_cursor(query: &ClientKeyListQuery) -> Result<(), AdminError> {
if matches {
Ok(())
} else {
Err(AdminError::invalid("Client API Key 游标不合法"))
Err(AdminError::invalid("API Key 分页游标不合法"))
}
}
@@ -65,7 +65,7 @@ pub(super) async fn required_credential(
.credential_details(provider_kind, account_id)
.await
.map_err(|error| map_store_error(error, resource))?
.ok_or_else(|| AdminError::not_found("Provider 凭据不存在"))
.ok_or_else(|| AdminError::not_found("服务商凭据不存在"))
}
pub(super) async fn required_plugin_credential(
@@ -77,7 +77,7 @@ pub(super) async fn required_plugin_credential(
.credential_details_by_id(account_id)
.await
.map_err(|error| map_store_error(error, resource))?
.ok_or_else(|| AdminError::not_found("Provider 凭据不存在"))
.ok_or_else(|| AdminError::not_found("服务商凭据不存在"))
}
pub(super) async fn import_proxy_binding(
@@ -156,7 +156,7 @@ pub(super) fn validate_prepared_import(
.iter()
.any(|credential| credential.provider_kind != *provider_kind)
{
return Err(AdminError::conflict("Provider 准备结果与请求范围不一致"));
return Err(AdminError::conflict("服务商返回的凭据与请求范围不符"));
}
Ok(())
}
@@ -176,7 +176,7 @@ pub(super) fn validate_prepared_rotation_facts(
if facts.account_id.as_str() != account.id.as_str()
|| facts.provider_kind != account.provider_kind
{
return Err(AdminError::conflict("Provider 准备结果与当前凭据不一致"));
return Err(AdminError::conflict("凭据处理结果与当前凭据不符"));
}
Ok(())
}
@@ -42,15 +42,17 @@ pub(super) fn map_provider_error(
ProviderAdminErrorKind::BadGateway => AdminErrorKind::BadGateway,
ProviderAdminErrorKind::Internal => AdminErrorKind::Internal,
};
let message = match kind {
AdminErrorKind::Invalid => "Provider 请求不合法",
AdminErrorKind::NotFound => "Provider 资源不存在",
AdminErrorKind::Conflict => "Provider 资源状态冲突,请刷新后重试",
AdminErrorKind::BadGateway => "上游服务请求失败",
AdminErrorKind::UpstreamResultUnknown => "上游执行结果未知,请刷新状态后再决定是否重试",
AdminErrorKind::Unavailable => "Provider 服务暂不可用",
AdminErrorKind::Internal => "服务内部错误",
_ => "Provider 操作失败",
let message = match error.kind() {
ProviderAdminErrorKind::Invalid => "服务商请求参数不合法",
ProviderAdminErrorKind::Unsupported => "该服务商不支持此操作",
ProviderAdminErrorKind::NotFound => "服务商资源不存在",
ProviderAdminErrorKind::Conflict => "服务商资源状态冲突,请刷新后重试",
ProviderAdminErrorKind::BadGateway => "上游服务请求失败",
ProviderAdminErrorKind::Ambiguous => "上游执行结果未知,请刷新状态后再决定是否重试",
ProviderAdminErrorKind::Unavailable | ProviderAdminErrorKind::CredentialRefreshRequired => {
"服务商暂不可用"
}
ProviderAdminErrorKind::Internal => "服务内部错误",
};
AdminError::new(kind, error.public_message().unwrap_or(message)).with_source(OperationFailure {
operation: resource,
@@ -104,7 +104,7 @@ impl PluginAccountAccess for DefaultPluginAccountAccess {
.load_credential_for_plugin(account_id)
.await
.map_err(|error| map_store_error(error, "plugin credential"))?
.ok_or_else(|| AdminError::not_found("Provider 凭据不存在"))?;
.ok_or_else(|| AdminError::not_found("服务商凭据不存在"))?;
Ok(PluginAccountCredential {
account: credential.account,
provider_material: credential.provider_material,
@@ -71,7 +71,7 @@ impl PluginsService {
validate_update_policy(&binding)?;
let PluginUpdateSource::Github { repository } = &binding.source else {
return Err(AdminError::invalid(
"该来源不提供 Release 更新查询,请显式选择并安装插件包",
"该来源不支持更新查询,请手动安装插件包",
));
};
let (tag, allow_prerelease) = match &binding.policy {
@@ -356,9 +356,7 @@ fn validate_update_policy(binding: &PluginSourceBinding) -> Result<(), AdminErro
if !matches!(binding.source, PluginUpdateSource::Github { .. })
&& !matches!(binding.policy, PluginUpdatePolicy::Manual {})
{
return Err(AdminError::invalid(
"只有 GitHub 来源支持 Release 更新检查策略",
));
return Err(AdminError::invalid("仅 GitHub 来源支持发行版本更新检查"));
}
if let PluginUpdatePolicy::Pinned { tag, .. } = &binding.policy
&& (tag.is_empty()
@@ -366,7 +364,7 @@ fn validate_update_policy(binding: &PluginSourceBinding) -> Result<(), AdminErro
|| tag.chars().any(char::is_control)
|| tag.trim() != tag)
{
return Err(AdminError::invalid("固定 Release tag 不合法"));
return Err(AdminError::invalid("固定版本标签不合法"));
}
Ok(())
}
@@ -47,14 +47,14 @@ pub trait SettingsService: Send + Sync {
&self,
_provider: &str,
) -> Result<gateway_core::account::OpaqueProviderData, AdminError> {
Err(AdminError::invalid("当前 Provider 不支持客户端身份配置"))
Err(AdminError::invalid("该服务商不支持客户端身份配置"))
}
async fn preview_client_profile(
&self,
_provider: &str,
_configuration: Option<&gateway_core::account::OpaqueProviderData>,
) -> Result<gateway_core::account::OpaqueProviderData, AdminError> {
Err(AdminError::invalid("当前 Provider 不支持客户端身份配置"))
Err(AdminError::invalid("该服务商不支持客户端身份配置"))
}
async fn load(&self) -> Result<RuntimeSettings, AdminError>;
async fn replace(
@@ -86,7 +86,7 @@ impl DefaultSettingsService {
provider: &str,
) -> Result<std::sync::Arc<dyn crate::ports::provider::ProviderAdmin>, AdminError> {
let kind = gateway_core::routing::ProviderKind::new(provider)
.map_err(|_| AdminError::invalid("Provider 不合法"))?;
.map_err(|_| AdminError::invalid("服务商无效"))?;
self.providers
.require(&kind)
.map_err(|error| super::map_provider_error(error, "client profile"))
@@ -170,7 +170,7 @@ impl SettingsService for DefaultSettingsService {
.keys()
.any(|provider| !providers.contains_key(provider))
{
return Err(AdminError::invalid("Provider 不支持价目管理"));
return Err(AdminError::invalid("该服务商不支持价目管理"));
}
let mut current = self.pricing_source.fetch().await?;
if current != command.preview {
@@ -242,7 +242,7 @@ impl SettingsService for DefaultSettingsService {
|| model.chars().any(char::is_control)
})
{
return Err(AdminError::invalid("Provider、模型 ID 或批量数量不合法"));
return Err(AdminError::invalid("服务商、模型 ID 或批量数量不合法"));
}
if command.change == PricingChange::Delete
&& command.models.iter().any(|model| {
@@ -146,12 +146,11 @@ fn map_system_error(error: SystemOperationError) -> AdminError {
SystemOperationErrorKind::Upstream => AdminErrorKind::BadGateway,
SystemOperationErrorKind::Internal => AdminErrorKind::Internal,
};
let message = match kind {
AdminErrorKind::Invalid => "系统操作请求不合法",
AdminErrorKind::Conflict => error.message(),
AdminErrorKind::BadGateway => "系统更新服务请求失败",
AdminErrorKind::Internal => "系统操作失败",
_ => "系统操作失败",
let failure = AdminError::new(kind, error.message());
let failure = if error.sensitive_context_redacted() {
failure.redact_sensitive_context()
} else {
failure
};
AdminError::new(kind, message)
failure.with_source(error)
}
@@ -24,9 +24,9 @@ impl DefaultUsageDataService {
reason: reason.into(),
};
let kind = ProviderKind::new(input.provider.clone())
.map_err(|_| UsageDataError::invalid("Provider 无效"))?;
.map_err(|_| UsageDataError::invalid("服务商无效"))?;
let Ok(provider) = self.providers.require(&kind) else {
return Ok(unavailable("Provider 没有可用的计价规则"));
return Ok(unavailable("服务商没有可用的计价规则"));
};
let tokens = &input.tokens;
let price = match &input.price {
@@ -61,9 +61,9 @@ impl DefaultUsageDataService {
ProviderAdminErrorKind::Unsupported | ProviderAdminErrorKind::Invalid
) =>
{
return Ok(unavailable("Provider 不支持该计价输入"));
return Ok(unavailable("服务商不支持该计价输入"));
}
Err(_) => return Err(UsageDataError::unavailable("Provider 计价失败")),
Err(_) => return Err(UsageDataError::unavailable("服务商计价失败")),
};
Ok(UsagePricingResult::Estimated {
id: input.id,
@@ -3088,7 +3088,7 @@ async fn accounts_refresh_should_not_expose_the_provider_failure_message() {
.expect_err("Provider preparation must fail");
assert_eq!(error.kind(), gateway_admin::model::AdminErrorKind::Conflict);
assert_eq!(error.to_string(), "Provider 资源状态冲突,请刷新后重试");
assert_eq!(error.to_string(), "服务商资源状态冲突,请刷新后重试");
assert!(!error.to_string().contains(upstream_message));
assert_eq!(
recorded(&events),
@@ -16,11 +16,15 @@ use gateway_admin::{
struct RecordingSystemOperations {
target: Mutex<Option<Option<String>>>,
channel: Mutex<Option<gateway_admin::model::system::SystemUpdateChannel>>,
failure: Option<SystemOperationError>,
}
#[async_trait]
impl SystemOperations for RecordingSystemOperations {
async fn version(&self) -> Result<SystemVersion, SystemOperationError> {
if let Some(error) = &self.failure {
return Err(error.clone());
}
Ok(SystemVersion {
version: "1.0.0".to_owned(),
git_sha: "unknown".to_owned(),
@@ -119,6 +123,33 @@ impl SystemOperations for RecordingSystemOperations {
}
}
#[tokio::test]
async fn system_failure_should_preserve_safe_message_source_and_redaction_marker() {
let operations = std::sync::Arc::new(RecordingSystemOperations {
failure: Some(
SystemOperationError::new(
gateway_admin::ports::system::SystemOperationErrorKind::Upstream,
"更新包下载失败",
)
.with_source(std::io::Error::other("native transport diagnostic"))
.redact_sensitive_context(),
),
..RecordingSystemOperations::default()
});
let services = super::AdminHarness::new().system(operations).build().await;
let error = services.system().version().await.expect_err("host failure");
assert_eq!(
error.kind(),
gateway_admin::model::AdminErrorKind::BadGateway
);
assert_eq!(error.message(), "更新包下载失败");
assert!(!format!("{error} {error:?}").contains("native transport diagnostic"));
let details = error.error_details().expect("host error details");
assert!(details.as_str().contains("native transport diagnostic"));
let details: serde_json::Value = serde_json::from_str(details.as_str()).expect("details JSON");
assert_eq!(details["redacted"], true);
}
#[tokio::test]
async fn system_update_should_normalize_blank_target_to_latest() {
let operations = std::sync::Arc::new(RecordingSystemOperations::default());
+4 -1
View File
@@ -25,13 +25,16 @@ gateway-admin = { path = "../gateway-admin" }
gateway-core = { path = "../gateway-core" }
gateway-protocol = { path = "../gateway-protocol" }
headers = "0.4.1"
hyper = { version = "=1.11.1", default-features = false }
hyper-util = { version = "=0.1.21", default-features = false, features = ["tokio"] }
regex = "1.13.1"
secrecy = "0.10"
serde = { version = "1.0.228", features = ["derive"] }
serde_json = { version = "1.0.150", features = ["arbitrary_precision", "preserve_order"] }
sha2 = "0.11.0"
thiserror = "2.0.18"
tokio = { version = "1.52.3", default-features = false, features = ["macros", "rt", "sync", "time"] }
tokio = { version = "1.52.3", default-features = false, features = ["io-util", "macros", "rt", "sync", "time"] }
tokio-tungstenite = { version = "0.29.0", default-features = false, features = ["handshake"] }
tower = { version = "0.5.3", features = ["util"] }
tower-http = { version = "0.7.0", features = ["compression-gzip", "cors", "fs", "request-id", "timeout", "trace"] }
tracing = "0.1.44"
@@ -1066,13 +1066,28 @@ fn mutation_response(
}
fn map_wire_error(error: WireValidationError) -> AdminError {
match error.field() {
"cursor" => AdminError::bad_request("Client API Key 游标不合法"),
let message = match error.field() {
"cursor" => "API Key 分页游标不合法",
"clientKeyRevealNotFound" | "clientKeyMutationNotFound" => {
AdminError::not_found("Client API Key 不存在")
return AdminError::not_found("API Key 不存在");
}
_ => AdminError::bad_request("Client API Key 请求不合法"),
}
"id" => "API Key ID 不能为空",
"name" => "API Key 名称不能为空",
"label" => "API Key 标签不能为空",
"customKey" => "自定义 API Key 仅支持英文字母、数字和英文符号",
"groupIds" => "账号分组无效、重复或数量超限",
"maxConcurrency" => "并发请求上限超出支持范围",
"requestsPerMinute" => "每分钟请求上限超出支持范围",
"dailyLimitUsd" => "每日美元限额须非负,整数和小数各最多 10 位",
"weeklyLimitUsd" => "每周美元限额须非负,整数和小数各最多 10 位",
"providerRequestProfileOverrides" => "API Key 客户端身份配置无效或字段冲突",
"limit" => "每页数量须为 1 至 65535",
"search" => "搜索内容过长或包含控制字符",
"sortBy" => "排序字段不受支持",
"sortDirection" => "排序方向必须为 asc(升序)或 desc(降序)",
_ => "API Key 请求参数不合法",
};
AdminError::bad_request(message)
}
fn map_service_error(error: gateway_admin::model::AdminError) -> AdminError {
@@ -581,13 +581,13 @@ fn wire_model_mappings(mappings: DomainModelMappings) -> ModelMappings {
fn map_wire_error(error: WireValidationError) -> AdminError {
let message = match error.field() {
"settingsRefreshConcurrencyOverflow" => "refreshConcurrency 不合法".to_owned(),
"settingsMaxConcurrencyOverflow" => "maxConcurrentPerAccount 不合法".to_owned(),
"settingsUsageRetentionOverflow" => "usageRetentionDays 不合法".to_owned(),
"settingsOpsRetentionOverflow" => "opsEventRetentionDays 不合法".to_owned(),
"settingsAuditRetentionOverflow" => "auditRetentionDays 不合法".to_owned(),
"requestLocation" => "请求位置不合法,请检查国家代码、地区和城市".to_owned(),
"providerRequestProfiles" => "Provider 请求画像格式不合法或字段冲突".to_owned(),
"settingsRefreshConcurrencyOverflow" => "刷新并发数不合法".to_owned(),
"settingsMaxConcurrencyOverflow" => "单账号并发上限不合法".to_owned(),
"settingsUsageRetentionOverflow" => "用量记录保留天数不合法".to_owned(),
"settingsOpsRetentionOverflow" => "运维事件保留天数不合法".to_owned(),
"settingsAuditRetentionOverflow" => "审计记录保留天数不合法".to_owned(),
"requestLocation" => "请求位置的国家代码、地区或城市不合法".to_owned(),
"providerRequestProfiles" => "服务商客户端身份配置无效或字段冲突".to_owned(),
"minCodexDesktopVersion" => "Codex Desktop 最低版本格式不合法".to_owned(),
"minCodexCliVersion" => "Codex CLI 最低版本格式不合法".to_owned(),
field => format!("{field} 字段不合法"),
@@ -33,7 +33,8 @@ pub fn openai_error_response(
}
}
/// Codex 将这两个容量码视为不可重试;仅在交付边界转换,内部仍保留真实上游事实
/// 无重试提示的容量拒绝及旧版 Codex 限流错误需要可重试投影
/// 仅在交付边界转换,内部仍保留真实上游事实
pub(super) fn client_error_code(code: &str) -> &str {
match code {
"server_is_overloaded" | "slow_down" => "server_error",
@@ -83,7 +84,7 @@ pub fn protocol_error_response(status: StatusCode, body: ProtocolErrorBody) -> R
pub fn missing_client_api_key_response() -> (StatusCode, Json<Value>) {
openai_error_response(
StatusCode::UNAUTHORIZED,
"Missing or invalid API key",
"Missing or invalid API key.",
"invalid_request_error",
"invalid_api_key",
)
@@ -93,7 +94,7 @@ pub fn missing_client_api_key_response() -> (StatusCode, Json<Value>) {
pub fn runtime_unavailable_response() -> (StatusCode, Json<Value>) {
openai_error_response(
StatusCode::SERVICE_UNAVAILABLE,
"Gateway runtime configuration is temporarily unavailable",
"Gateway configuration is temporarily unavailable.",
"server_error",
"runtime_configuration_unavailable",
)
@@ -110,7 +111,7 @@ pub fn client_version_rejection_response(
let (message, code, current_version) = match rejection.current() {
Some(current) => (
format!(
"{client_label} {current} is below the minimum required version {}. Upgrade {client_label} and retry.",
"{client_label} {current} is outdated. Upgrade to {} or later.",
rejection.min()
),
"client_version_too_old",
@@ -118,15 +119,15 @@ pub fn client_version_rejection_response(
),
None => (
format!(
"A valid {client_label} version is required. Upgrade to version {} or newer and retry.",
rejection.min()
"Cannot read the {client_label} version. Check the User-Agent and version headers."
),
"client_version_unavailable",
None,
),
};
// Codex 将 400 视为不可重试的请求错误,426 则会触发 WS 回退和 HTTP 重试
(
StatusCode::UPGRADE_REQUIRED,
StatusCode::BAD_REQUEST,
Json(json!({
"error": {
"message": message,
@@ -144,7 +145,7 @@ pub fn client_version_rejection_response(
pub fn model_not_found_response() -> (StatusCode, Json<Value>) {
openai_error_response(
StatusCode::NOT_FOUND,
"The requested model does not exist or is not available",
"The requested model does not exist or is not available.",
"invalid_request_error",
"model_not_found",
)
@@ -124,7 +124,7 @@ async fn image_operation(
.map_err(|_| {
GatewayError::new(
GatewayErrorKind::Internal,
"OpenAI protocol identifier is invalid",
"OpenAI protocol identifier is invalid.",
)
})?
.with_context(context);
@@ -26,7 +26,7 @@ pub(super) async fn normalize_edit_body(
return Ok(body);
}
if headers.get_all(CONTENT_TYPE).iter().count() != 1 {
return Err(invalid("Image edit requires a single Content-Type header"));
return Err(invalid("Image edit requires a single Content-Type header."));
}
let mut request = Request::new(Body::from(body));
@@ -35,7 +35,7 @@ pub(super) async fn normalize_edit_body(
DefaultBodyLimit::disable().apply(&mut request);
let mut multipart = Multipart::from_request(request, &())
.await
.map_err(|_| invalid("Image edit multipart boundary is invalid"))?;
.map_err(|_| invalid("Image edit multipart boundary is invalid."))?;
let mut body = Vec::new();
let mut serializer = serde_json::Serializer::new(&mut body);
// 直接序列化字段,避免经过 Map 后覆盖同名参数
@@ -44,17 +44,17 @@ pub(super) async fn normalize_edit_body(
while let Some(field) = multipart
.next_field()
.await
.map_err(|_| invalid("Image edit multipart body is invalid"))?
.map_err(|_| invalid("Image edit multipart body is invalid."))?
{
let name = field
.name()
.ok_or_else(|| invalid("Image edit multipart fields must have names"))?
.ok_or_else(|| invalid("Image edit multipart fields must have names."))?
.to_owned();
let is_file = field.file_name().is_some();
let bytes = field
.bytes()
.await
.map_err(|_| invalid("Image edit multipart field is invalid"))?;
.map_err(|_| invalid("Image edit multipart field is invalid."))?;
if matches!(name.as_str(), "image" | "image[]") {
// 按表单中的出现顺序追加,多图顺序参与编辑语义
images.push(image_reference(&bytes)?);
@@ -65,7 +65,7 @@ pub(super) async fn normalize_edit_body(
} else {
if is_file {
return Err(invalid(
"Only image, image[] and mask may contain image files",
"Only image, image[] and mask may contain image files.",
));
}
scalar_field(&name, &bytes)?
@@ -76,7 +76,7 @@ pub(super) async fn normalize_edit_body(
}
if images.is_empty() {
return Err(invalid(
"Image edit multipart requires an image or image[] upload",
"Image edit multipart requires an image or image[] upload.",
));
}
fields
@@ -92,14 +92,14 @@ fn scalar_field(name: &str, bytes: &[u8]) -> Result<Value, GatewayError> {
match name {
"n" | "output_compression" | "partial_images" => serde_json::from_slice::<Number>(bytes)
.map(Value::Number)
.map_err(|_| invalid("Image edit numeric fields must contain JSON numbers")),
.map_err(|_| invalid("Image edit numeric fields must contain JSON numbers.")),
"stream" => serde_json::from_slice::<bool>(bytes)
.map(Value::Bool)
.map_err(|_| invalid("Image edit stream field must contain a JSON boolean")),
.map_err(|_| invalid("Image edit stream field must contain a JSON boolean.")),
// 其余表单字段保留名称与文本值,不因字段尚未识别而丢弃或拒绝
_ => {
let text = std::str::from_utf8(bytes)
.map_err(|_| invalid("Image edit text fields must be valid UTF-8"))?;
.map_err(|_| invalid("Image edit text fields must be valid UTF-8."))?;
Ok(Value::String(text.to_owned()))
}
}
@@ -114,7 +114,7 @@ fn image_reference(bytes: &[u8]) -> Result<Value, GatewayError> {
} else if bytes.starts_with(b"RIFF") && bytes.get(8..12) == Some(b"WEBP") {
"image/webp"
} else {
return Err(invalid("Image edit uploads must be PNG, JPEG or WebP"));
return Err(invalid("Image edit uploads must be PNG, JPEG or WebP."));
};
Ok(json!({ "image_url": format!("data:{mime};base64,{}", STANDARD.encode(bytes)) }))
}
@@ -126,6 +126,6 @@ fn invalid(message: &'static str) -> GatewayError {
fn encode_error(_: serde_json::Error) -> GatewayError {
GatewayError::new(
GatewayErrorKind::Internal,
"Could not encode image edit JSON",
"Could not encode image edit JSON.",
)
}
@@ -70,7 +70,7 @@ pub(crate) async fn live_call(
return live_error_response(
LiveErrorShape::Live,
StatusCode::BAD_REQUEST,
"Codex live call request has an invalid model",
"Codex live call request has an invalid model.",
"invalid_request",
);
}
@@ -184,7 +184,7 @@ async fn read_call_body(
Box::new(live_error_response(
LiveErrorShape::Live,
StatusCode::PAYLOAD_TOO_LARGE,
"Codex live request body too large",
"Codex live request body too large.",
"invalid_request",
))
})?;
@@ -194,7 +194,7 @@ async fn read_call_body(
Box::new(live_error_response(
LiveErrorShape::Live,
StatusCode::BAD_REQUEST,
"Codex live multipart body is invalid",
"Codex live multipart body is invalid.",
"invalid_request",
))
})?;
@@ -205,7 +205,7 @@ async fn read_call_body(
Box::new(live_error_response(
LiveErrorShape::Live,
StatusCode::BAD_REQUEST,
"Codex live multipart body is invalid",
"Codex live multipart body is invalid.",
"invalid_request",
))
})?
@@ -218,7 +218,7 @@ async fn read_call_body(
Box::new(live_error_response(
LiveErrorShape::Live,
StatusCode::BAD_REQUEST,
"Codex live multipart body is invalid",
"Codex live multipart body is invalid.",
"invalid_request",
))
})?;
@@ -229,7 +229,7 @@ async fn read_call_body(
Box::new(live_error_response(
LiveErrorShape::Live,
StatusCode::BAD_REQUEST,
"Codex live multipart body is invalid",
"Codex live multipart body is invalid.",
"invalid_request",
))
})?;
@@ -237,7 +237,7 @@ async fn read_call_body(
Box::new(live_error_response(
LiveErrorShape::Live,
StatusCode::BAD_REQUEST,
"Codex live session field must contain valid JSON",
"Codex live session field must contain valid JSON.",
"invalid_request",
))
})?;
@@ -251,7 +251,7 @@ async fn read_call_body(
None => Err(Box::new(live_error_response(
LiveErrorShape::Live,
StatusCode::BAD_REQUEST,
"Codex live multipart body requires an sdp field",
"Codex live multipart body requires an sdp field.",
"invalid_request",
))),
}
@@ -121,7 +121,7 @@ async fn sip_unsupported() -> Response {
pub(crate) fn realtime_unsupported_response(capability: &str) -> Response {
openai_error_response(
StatusCode::NOT_IMPLEMENTED,
&format!("{capability} are not supported by the Codex OAuth upstream"),
&format!("Unsupported by Codex OAuth: {capability}."),
"not_supported_error",
"realtime_capability_not_supported",
)
@@ -168,7 +168,7 @@ pub(crate) fn live_call_operation(
Box::new(live_error_response(
LiveErrorShape::Live,
StatusCode::BAD_REQUEST,
"Codex live call request is invalid",
"Codex live call request is invalid.",
"invalid_request",
))
};
@@ -251,7 +251,7 @@ pub(crate) fn encode_call_request(
))
};
if sdp.trim().is_empty() {
return Err(invalid("Codex live call request requires an SDP offer"));
return Err(invalid("Codex live call request requires an SDP offer."));
}
let mut payload = serde_json::Map::new();
payload.insert("sdp".to_owned(), Value::String(sdp.to_owned()));
@@ -260,7 +260,7 @@ pub(crate) fn encode_call_request(
}
serde_json::to_vec(&payload)
.map(Bytes::from)
.map_err(|_| invalid("Codex live call request is invalid"))
.map_err(|_| invalid("Codex live call request is invalid."))
}
/// 共用响应身份与传输边界;Live 原始正文另保留上游 Content-Type
@@ -310,7 +310,7 @@ pub(crate) fn normalize_call_request(
Box::new(live_error_response(
LiveErrorShape::Live,
StatusCode::BAD_REQUEST,
"Codex live call request requires a UTF-8 SDP offer",
"Codex live call request requires a UTF-8 SDP offer.",
"invalid_request",
))
})?;
@@ -149,7 +149,7 @@ fn upgrade_required_response() -> Response {
let mut response = live_error_response(
LiveErrorShape::Realtime,
StatusCode::UPGRADE_REQUIRED,
"WebSocket upgrade required",
"WebSocket upgrade required.",
"websocket_upgrade_required",
);
response.headers_mut().insert(
@@ -246,7 +246,7 @@ pub(crate) fn error_response(error: MiddlewareError) -> Response {
MiddlewareError::Rejected | MiddlewareError::Remote { rejected: true, .. } => {
openai_error_response(
StatusCode::FORBIDDEN,
"Request rejected by middleware",
"Request rejected by middleware.",
"invalid_request_error",
"middleware_rejected",
)
@@ -255,7 +255,7 @@ pub(crate) fn error_response(error: MiddlewareError) -> Response {
MiddlewareError::Fault | MiddlewareError::Remote { .. } | MiddlewareError::InvalidState => {
openai_error_response(
StatusCode::BAD_GATEWAY,
"Request middleware failed",
"Request middleware failed.",
"server_error",
"middleware_failed",
)
@@ -72,7 +72,7 @@ async fn models_response(
{
return openai_error_response(
StatusCode::BAD_REQUEST,
"Invalid client_version",
"Invalid client_version.",
"invalid_request_error",
"invalid_client_version",
)
@@ -134,7 +134,7 @@ async fn models_response(
fn catalog_unavailable_response() -> Response {
openai_error_response(
StatusCode::SERVICE_UNAVAILABLE,
"Model catalog is temporarily unavailable",
"Model catalog is temporarily unavailable.",
"server_error",
"model_catalog_unavailable",
)
@@ -984,7 +984,7 @@ impl MiddlewareBody for StreamingExecutionBody {
MiddlewareError::Engine(error) => gateway_error_from_engine(&error),
_ => GatewayError::new(
GatewayErrorKind::Internal,
"gateway response stream could not be delivered",
"Gateway response stream could not be delivered.",
),
};
self.push_stream_error(error);
@@ -1068,6 +1068,6 @@ fn done_frame() -> MiddlewareFrame {
fn invalid_execution_stream() -> MiddlewareError {
MiddlewareError::Gateway(GatewayError::new(
GatewayErrorKind::Internal,
"gateway response stream violated its execution lifecycle",
"Gateway response stream violated its execution lifecycle.",
))
}
@@ -137,7 +137,7 @@ async fn stream_failure(response: Response, error_encoder: Option<fn(&Value) ->
raw_message.unwrap_or_else(|| {
status
.canonical_reason()
.unwrap_or("Response stream failed")
.unwrap_or("Response stream failed.")
}),
)
});
@@ -4,8 +4,9 @@ use super::{
frame::*,
pump::run_pump,
state::{ConnectionCommand, ConnectionStats},
transport::Socket,
};
use axum::extract::ws::{CloseFrame, Message, Utf8Bytes, WebSocket, close_code};
use axum::extract::ws::{CloseFrame, Message, Utf8Bytes, close_code};
use futures::{Sink, Stream};
use gateway_core::{
engine::middleware::{FrozenMiddlewarePlan, MiddlewareHeader},
@@ -21,7 +22,7 @@ use std::{
time::Duration,
};
use tokio::{
sync::{mpsc, oneshot},
sync::{mpsc, oneshot, watch},
task::JoinHandle,
time::{Instant, timeout},
};
@@ -38,19 +39,21 @@ pub struct ResponsesWebSocketConnection {
exited: oneshot::Receiver<PumpExitReason>,
pump_task: Option<JoinHandle<()>>,
stats: Arc<ConnectionStats>,
activity: watch::Sender<Instant>,
config: ConnectionConfig,
exit_reason: Option<PumpExitReason>,
}
impl ResponsesWebSocketConnection {
pub(in super::super) fn new(
socket: WebSocket,
socket: Socket,
connection_id: String,
cancellation: CancellationToken,
middleware: Option<FrozenMiddlewarePlan>,
headers: Arc<[MiddlewareHeader]>,
) -> Self {
spawn_connection(
socket.activity.clone(),
socket,
Arc::<str>::from(connection_id),
cancellation,
@@ -278,8 +281,7 @@ impl ResponsesWebSocketConnection {
pub(in super::super) fn log_summary(&self, request_count: u64) {
let connection_age_ms = self.age().as_millis();
let read_idle_ms = connection_age_ms
.saturating_sub(u128::from(self.stats.last_read_ms.load(Ordering::Relaxed)));
let read_idle_ms = self.activity.borrow().elapsed().as_millis();
let write_idle_ms = connection_age_ms
.saturating_sub(u128::from(self.stats.last_write_ms.load(Ordering::Relaxed)));
tracing::info!(
@@ -319,7 +321,9 @@ impl Drop for ResponsesWebSocketConnection {
/// 为 WebSocket transport 启动包含冻结中间件计划的单 owner pump
/// cancellation 必须属于本连接,连接退出或句柄释放时会取消它
/// activity 仅由 transport 的实际入站字节或 pump 的完整消息更新,不能由写入刷新
pub fn spawn_connection<S, E>(
activity: watch::Sender<Instant>,
socket: S,
connection_id: Arc<str>,
cancellation: CancellationToken,
@@ -342,6 +346,7 @@ where
.unwrap_or_default();
let pump_task = tokio::spawn(run_pump(
socket,
activity.clone(),
command_rx,
incoming_tx,
exit_tx,
@@ -366,6 +371,7 @@ where
exited: exit_rx,
pump_task: Some(pump_task),
stats,
activity,
config,
exit_reason: None,
}
@@ -5,9 +5,12 @@ mod handle;
mod middleware;
mod pump;
mod state;
mod transport;
pub use frame::{
ConnectionConfig, ConnectionEvent, ConnectionWriteError, FramePhase, PumpExitReason,
WriteContext, WriteOutcome,
};
pub use handle::{ResponsesWebSocketConnection, spawn_connection};
pub(super) use transport::Socket;
pub(crate) use transport::Upgrade;
@@ -26,6 +26,7 @@ use tokio::{
#[expect(clippy::too_many_arguments)]
pub(super) async fn run_pump<S, E>(
socket: S,
activity: watch::Sender<Instant>,
commands: mpsc::Receiver<ConnectionCommand>,
incoming: mpsc::Sender<PendingConnectionEvent>,
exited: oneshot::Sender<PumpExitReason>,
@@ -58,7 +59,7 @@ pub(super) async fn run_pump<S, E>(
let (writer, mut reader) = socket.split();
let writer = Arc::new(middleware::Writer::new(writer, context.clone()));
let sender: Arc<dyn contract::Sender> = writer.clone();
let (activity, received_activity) = watch::channel(());
let received_activity = activity.subscribe();
// 心跳独立于业务写入等待,但共享唯一 writer,避免长写入或排队阻止失联检测
let reason = tokio::select! {
biased;
@@ -81,7 +82,7 @@ async fn read_connection<S, E>(
socket: &mut S,
incoming: &mpsc::Sender<PendingConnectionEvent>,
sender: Arc<dyn contract::Sender>,
activity: &watch::Sender<()>,
activity: &watch::Sender<Instant>,
context: &PumpContext,
) -> PumpExitReason
where
@@ -106,10 +107,9 @@ where
}
}
message = socket.next() => {
if matches!(&message, Some(Ok(_))) { context.stats.record_read(context.opened_at); }
if matches!(&message, Some(Ok(message)) if !matches!(message, Message::Close(_))) {
if matches!(&message, Some(Ok(_))) {
// 链路活动以真实入站为准,插件丢弃消息不应抹掉对端已经响应的事实
activity.send_replace(());
activity.send_replace(Instant::now());
}
let message = match message {
Some(Ok(message)) => match middleware::transform(message, contract::Direction::Incoming, sender.clone(), context).await {
@@ -201,7 +201,7 @@ where
async fn heartbeat_connection<S, E>(
writer: Arc<middleware::Writer<S>>,
mut activity: watch::Receiver<()>,
mut activity: watch::Receiver<Instant>,
context: &PumpContext,
) -> PumpExitReason
where
@@ -30,18 +30,10 @@ pub(super) struct ConnectionStats {
pub(super) ping_received_count: AtomicU64,
pub(super) ping_written_count: AtomicU64,
pub(super) pong_received_count: AtomicU64,
pub(super) last_read_ms: AtomicU64,
pub(super) last_write_ms: AtomicU64,
}
impl ConnectionStats {
pub(super) fn record_read(&self, opened_at: Instant) {
self.last_read_ms.store(
u64::try_from(opened_at.elapsed().as_millis()).unwrap_or(u64::MAX),
Ordering::Relaxed,
);
}
pub(super) fn record_write(&self, opened_at: Instant) {
self.last_write_ms.store(
u64::try_from(opened_at.elapsed().as_millis()).unwrap_or(u64::MAX),
@@ -0,0 +1,204 @@
//! 保留 Axum 握手校验,在 WS 消息解码前记录下游真实接收进度
use std::{
io,
pin::Pin,
task::{Context, Poll},
};
use axum::{
extract::{
FromRequestParts,
ws::{self, Message},
},
http::{HeaderValue, StatusCode, Version, header, request::Parts},
response::{IntoResponse, Response},
};
use futures::{Sink, Stream, ready};
use hyper::upgrade::{OnUpgrade, Upgraded};
use hyper_util::rt::TokioIo;
use tokio::{
io::{AsyncRead, AsyncWrite, ReadBuf},
sync::watch,
time::Instant,
};
use tokio_tungstenite::{
WebSocketStream,
tungstenite::{
self,
protocol::{Role, WebSocketConfig},
},
};
pub(crate) struct Upgrade {
pending: OnUpgrade,
key: Option<HeaderValue>,
}
impl<S: Send + Sync> FromRequestParts<S> for Upgrade {
type Rejection = ws::rejection::WebSocketUpgradeRejection;
async fn from_request_parts(parts: &mut Parts, state: &S) -> Result<Self, Self::Rejection> {
let pending = parts.extensions.get::<OnUpgrade>().cloned();
// Axum 的 WebSocket 不暴露底层 I/O;只复用其握手校验,由本层接管唯一升级流
let _validated = ws::WebSocketUpgrade::from_request_parts(parts, state).await?;
let pending = pending.expect("Axum validated the presence of OnUpgrade");
let key = (parts.version <= Version::HTTP_11)
.then(|| parts.headers.get(header::SEC_WEBSOCKET_KEY).cloned())
.flatten();
Ok(Self { pending, key })
}
}
impl Upgrade {
pub(in super::super) fn on_upgrade<F, Fut>(self, callback: F) -> Response
where
F: FnOnce(Socket) -> Fut + Send + 'static,
Fut: Future<Output = ()> + Send + 'static,
{
tokio::spawn(async move {
let Ok(upgraded) = self.pending.await else {
return;
};
let (activity, _) = watch::channel(Instant::now());
let io = Receiving {
inner: TokioIo::new(upgraded),
activity: activity.clone(),
};
// 与原生 Responses 升级保持一致,不引入消息或帧长度上限
let config = WebSocketConfig::default()
.max_message_size(None)
.max_frame_size(None);
let inner = WebSocketStream::from_raw_socket(io, Role::Server, Some(config)).await;
callback(Socket { inner, activity }).await;
});
if let Some(key) = self.key {
(
StatusCode::SWITCHING_PROTOCOLS,
[
(header::CONNECTION, "upgrade".to_owned()),
(header::UPGRADE, "websocket".to_owned()),
(
header::SEC_WEBSOCKET_ACCEPT,
tungstenite::handshake::derive_accept_key(key.as_bytes()),
),
],
)
.into_response()
} else {
StatusCode::OK.into_response()
}
}
}
struct Receiving {
inner: TokioIo<Upgraded>,
activity: watch::Sender<Instant>,
}
impl AsyncRead for Receiving {
fn poll_read(
mut self: Pin<&mut Self>,
cx: &mut Context<'_>,
buffer: &mut ReadBuf<'_>,
) -> Poll<io::Result<()>> {
let before = buffer.filled().len();
let result = Pin::new(&mut self.inner).poll_read(cx, buffer);
if buffer.filled().len() > before {
// 完整消息尚未收齐时,客户端可能仍在发送、暂时无法读取 Ping
self.activity.send_replace(Instant::now());
}
result
}
}
impl AsyncWrite for Receiving {
fn poll_write(
mut self: Pin<&mut Self>,
cx: &mut Context<'_>,
buffer: &[u8],
) -> Poll<io::Result<usize>> {
Pin::new(&mut self.inner).poll_write(cx, buffer)
}
fn poll_flush(mut self: Pin<&mut Self>, cx: &mut Context<'_>) -> Poll<io::Result<()>> {
Pin::new(&mut self.inner).poll_flush(cx)
}
fn poll_shutdown(mut self: Pin<&mut Self>, cx: &mut Context<'_>) -> Poll<io::Result<()>> {
Pin::new(&mut self.inner).poll_shutdown(cx)
}
}
pub(in super::super) struct Socket {
inner: WebSocketStream<Receiving>,
pub(super) activity: watch::Sender<Instant>,
}
impl Stream for Socket {
type Item = Result<Message, axum::Error>;
fn poll_next(mut self: Pin<&mut Self>, cx: &mut Context<'_>) -> Poll<Option<Self::Item>> {
loop {
let message = match ready!(Pin::new(&mut self.inner).poll_next(cx)) {
Some(Ok(message)) => message,
Some(Err(error)) => return Poll::Ready(Some(Err(axum::Error::new(error)))),
None => return Poll::Ready(None),
};
let message = match message {
tungstenite::Message::Text(text) => Message::Text(
ws::Utf8Bytes::try_from(bytes::Bytes::from(text)).map_err(axum::Error::new)?,
),
tungstenite::Message::Binary(data) => Message::Binary(data),
tungstenite::Message::Ping(data) => Message::Ping(data),
tungstenite::Message::Pong(data) => Message::Pong(data),
tungstenite::Message::Close(frame) => {
Message::Close(frame.map(|frame| ws::CloseFrame {
code: frame.code.into(),
reason: frame.reason.to_string().into(),
}))
}
tungstenite::Message::Frame(_) => continue,
};
return Poll::Ready(Some(Ok(message)));
}
}
}
impl Sink<Message> for Socket {
type Error = axum::Error;
fn poll_ready(mut self: Pin<&mut Self>, cx: &mut Context<'_>) -> Poll<Result<(), Self::Error>> {
Pin::new(&mut self.inner)
.poll_ready(cx)
.map_err(axum::Error::new)
}
fn start_send(mut self: Pin<&mut Self>, message: Message) -> Result<(), Self::Error> {
let message = match message {
Message::Text(text) => tungstenite::Message::Text(
tungstenite::Utf8Bytes::try_from(bytes::Bytes::from(text))
.map_err(axum::Error::new)?,
),
Message::Binary(data) => tungstenite::Message::Binary(data),
Message::Ping(data) => tungstenite::Message::Ping(data),
Message::Pong(data) => tungstenite::Message::Pong(data),
Message::Close(frame) => {
tungstenite::Message::Close(frame.map(|frame| tungstenite::protocol::CloseFrame {
code: frame.code.into(),
reason: frame.reason.to_string().into(),
}))
}
};
Pin::new(&mut self.inner)
.start_send(message)
.map_err(axum::Error::new)
}
fn poll_flush(mut self: Pin<&mut Self>, cx: &mut Context<'_>) -> Poll<Result<(), Self::Error>> {
Pin::new(&mut self.inner)
.poll_flush(cx)
.map_err(axum::Error::new)
}
fn poll_close(mut self: Pin<&mut Self>, cx: &mut Context<'_>) -> Poll<Result<(), Self::Error>> {
Pin::new(&mut self.inner)
.poll_close(cx)
.map_err(axum::Error::new)
}
}
@@ -400,13 +400,13 @@ fn middleware_gateway_error(error: MiddlewareError) -> GatewayError {
MiddlewareError::Rejected | MiddlewareError::Remote { rejected: true, .. } => {
GatewayError::new(
GatewayErrorKind::PolicyDenied,
"request middleware rejected the request",
"Request middleware rejected the request.",
)
}
MiddlewareError::Fault | MiddlewareError::Remote { .. } | MiddlewareError::InvalidState => {
GatewayError::new(
GatewayErrorKind::Internal,
"request middleware returned an invalid response",
"Request middleware returned an invalid response.",
)
}
}
@@ -779,7 +779,7 @@ pub(super) async fn send_control(
connection,
&GatewayError::new(
GatewayErrorKind::InvalidRequest,
"No upstream WebSocket connection is available for control messages",
"No upstream WebSocket connection is available for control messages.",
),
request_id,
)
@@ -11,11 +11,7 @@ use std::{
};
use axum::{
extract::{
Extension, State,
connect_info::ConnectInfo,
ws::{WebSocket, WebSocketUpgrade},
},
extract::{Extension, State, connect_info::ConnectInfo},
http::{HeaderMap, StatusCode},
response::{IntoResponse, Response},
};
@@ -45,7 +41,9 @@ use crate::{
use super::{
request::OpenAiRequestHeaders, request_client_context, validation::ResponseValidationFacts,
};
use connection::{ConnectionEvent, FramePhase, ResponsesWebSocketConnection, WriteContext};
use connection::{
ConnectionEvent, FramePhase, ResponsesWebSocketConnection, Socket, Upgrade, WriteContext,
};
use forward::{
ConnectionReplaySnapshot, ForwardOutcome, execution_response, forward_control_event,
forward_response, new_replay_capture, send_control, send_gateway_error, send_middleware_error,
@@ -54,7 +52,7 @@ use forward::{
pub use protocol::{ResponseCreateFrameError, decode_response_create_with_context};
use protocol::{connection_limit_event, is_response_create};
const TEXT_FRAMES_ONLY: &str = "Responses WebSocket accepts text frames only";
const TEXT_FRAMES_ONLY: &str = "Responses WebSocket accepts text frames only.";
const CONNECTION_LIMIT_CLOSE_REASON: &str = "Responses websocket connection limit reached";
/// 将已认证的 `GET /v1/responses` 升级为 Responses WebSocket
@@ -64,7 +62,7 @@ pub(crate) async fn responses_websocket(
middleware: Option<Extension<FrozenMiddlewarePlan>>,
lifetime: Option<Extension<Arc<crate::middleware::CallLifetime>>>,
headers: HeaderMap,
websocket: WebSocketUpgrade,
websocket: Upgrade,
) -> Response {
let service = state.openai().clone();
let client = match authenticate_client(&service, &headers).await {
@@ -104,7 +102,7 @@ impl ResponsesWebSocketAdapter {
#[expect(clippy::too_many_arguments)]
fn upgrade_with_client_context(
&self,
websocket: WebSocketUpgrade,
websocket: Upgrade,
client: AuthenticatedClient,
client_ip: Option<IpAddr>,
user_agent: Option<String>,
@@ -138,15 +136,10 @@ impl ResponsesWebSocketAdapter {
middleware,
};
let origin = crate::middleware::current();
websocket
// 覆盖 axum/tungstenite 的私有 64 MiB message 与 16 MiB frame 默认值
// Responses JSON 的协议可接受性由上游决定,代理不另设 wire 长度上限
.max_message_size(usize::MAX)
.max_frame_size(usize::MAX)
.on_upgrade(move |socket| async move {
let _lifetime = lifetime;
crate::middleware::scope(origin, serve_responses_websocket(socket, session)).await;
})
websocket.on_upgrade(move |socket| async move {
let _lifetime = lifetime;
crate::middleware::scope(origin, serve_responses_websocket(socket, session)).await;
})
}
}
@@ -163,7 +156,7 @@ struct ResponsesWebSocketSession {
middleware: Option<FrozenMiddlewarePlan>,
}
async fn serve_responses_websocket(socket: WebSocket, session: ResponsesWebSocketSession) {
async fn serve_responses_websocket(socket: Socket, session: ResponsesWebSocketSession) {
let ResponsesWebSocketSession {
service,
client,
@@ -288,13 +281,13 @@ async fn serve_responses_websocket(socket: WebSocket, session: ResponsesWebSocke
let current = execution.request_settings().ok_or_else(|| {
gateway_core::error::GatewayError::new(
gateway_core::error::GatewayErrorKind::Internal,
"runtime snapshot is unavailable",
"Gateway configuration is unavailable.",
)
})?;
let rebased = settings.rebase(current.snapshot()).map_err(|_| {
gateway_core::error::GatewayError::new(
gateway_core::error::GatewayErrorKind::InvalidRequest,
"request settings are invalid",
"Request settings are invalid.",
)
})?;
client = client.with_request_settings(rebased);
@@ -65,7 +65,7 @@ fn search_operation(body: Bytes, headers: &HeaderMap) -> Result<Operation, Gatew
.map_err(|_| {
GatewayError::new(
GatewayErrorKind::Internal,
"OpenAI protocol identifier is invalid",
"OpenAI protocol identifier is invalid.",
)
})?
.with_context(context);
@@ -101,7 +101,7 @@ impl OpenAiService {
.map_err(|_| {
GatewayError::new(
GatewayErrorKind::ModelNotFound,
"requested model was not found",
"Requested model was not found.",
)
})?;
let previous_response_id = match metadata.continuation() {
@@ -142,7 +142,7 @@ impl OpenAiService {
let provider = ProviderKind::new("openai").map_err(|_| {
GatewayError::new(
GatewayErrorKind::Internal,
"OpenAI provider identifier is invalid",
"OpenAI provider identifier is invalid.",
)
})?;
self.execution
@@ -63,7 +63,7 @@ async fn usage_response(
if Query::<UsageQuery>::try_from_uri(&uri).is_err() {
return openai_error_response(
StatusCode::BAD_REQUEST,
"Usage query does not accept query parameters",
"Usage query does not accept query parameters.",
"invalid_request_error",
"invalid_usage_query",
)
@@ -80,7 +80,7 @@ async fn usage_response(
Err(_) => {
return openai_error_response(
StatusCode::SERVICE_UNAVAILABLE,
"Key usage is temporarily unavailable",
"Key usage is temporarily unavailable.",
"server_error",
"usage_unavailable",
)
+9 -9
View File
@@ -73,18 +73,18 @@ async fn count_tokens(
};
let provider = match ProviderKind::new(provider) {
Ok(provider) => provider,
Err(_) => return invalid_request("provider identifier is invalid"),
Err(_) => return invalid_request("Provider identifier is invalid."),
};
let model = match UpstreamModelId::new(model) {
Ok(model) => model,
Err(_) => return invalid_request("provider model identifier is invalid"),
Err(_) => return invalid_request("Provider model identifier is invalid."),
};
if serde_json::from_slice::<serde::de::IgnoredAny>(&body).is_err() {
return invalid_request("token count request must be valid JSON");
return invalid_request("Token count request must be valid JSON.");
}
let payload = match RawJsonPayload::new(TOKEN_COUNT_PROTOCOL, body) {
Ok(payload) => payload,
Err(_) => return invalid_request("token count request is invalid"),
Err(_) => return invalid_request("Token count request is invalid."),
};
let (client_ip, user_agent) = request_client_context(
&headers,
@@ -124,12 +124,12 @@ async fn provider_http(
body: Bytes,
) -> Response {
if method == Method::GET && !body.is_empty() {
return invalid_request("GET provider HTTP operations cannot carry a request body");
return invalid_request("GET provider HTTP operations cannot carry a request body.");
}
let method = match method {
Method::GET => ProviderHttpMethod::Get,
Method::POST => ProviderHttpMethod::Post,
_ => return invalid_request("provider HTTP method is unsupported"),
_ => return invalid_request("Provider HTTP method is unsupported."),
};
let service = state.openai();
let client = match authenticate_client(service, &headers).await {
@@ -138,7 +138,7 @@ async fn provider_http(
};
let provider = match ProviderKind::new(provider) {
Ok(provider) => provider,
Err(_) => return invalid_request("provider identifier is invalid"),
Err(_) => return invalid_request("Provider identifier is invalid."),
};
let connection_options = headers
.get_all(header::CONNECTION)
@@ -158,7 +158,7 @@ async fn provider_http(
.collect();
let payload = match RawHttpPayload::new(PROVIDER_HTTP_PROTOCOL, body) {
Ok(payload) => payload,
Err(_) => return invalid_request("provider HTTP request is invalid"),
Err(_) => return invalid_request("Provider HTTP request is invalid."),
};
let operation = match ProviderHttpRequest::new(
endpoint,
@@ -168,7 +168,7 @@ async fn provider_http(
payload,
) {
Ok(request) => Operation::ProviderHttp(request),
Err(_) => return invalid_request("provider HTTP request is invalid"),
Err(_) => return invalid_request("Provider HTTP request is invalid."),
};
let (client_ip, user_agent) = request_client_context(
&headers,
@@ -69,7 +69,7 @@ mod personal_info {
fn personal_info_response_preserves_unknown_subscription_and_profile_error() {
let response = AccountPersonalInfoData::from((
AccountPersonalInfo {
profile: Err(AdminError::unavailable("Provider 服务暂不可用")),
profile: Err(AdminError::unavailable("服务商暂不可用")),
subscription: None,
},
gateway_api::TimePresenter::new(Default::default()),
@@ -78,7 +78,7 @@ mod personal_info {
serde_json::to_value(response).unwrap(),
json!({
"profile": null,
"profileError": "Provider 服务暂不可用",
"profileError": "服务商暂不可用",
"subscription": null,
})
);
@@ -171,6 +171,70 @@ async fn malformed_admin_query_should_use_a_safe_bad_request_envelope() {
);
}
#[tokio::test]
async fn client_key_validation_should_identify_the_invalid_field_without_echoing_values() {
let fixture = AdminTestFixture::new().await;
fixture.auth.insert_session("valid-session");
let secret = "private-key-must-not-leak\n";
for (field, value, message) in [
("name", json!(" "), "API Key 名称不能为空"),
(
"customKey",
json!(secret),
"自定义 API Key 仅支持英文字母、数字和英文符号",
),
(
"dailyLimitUsd",
json!("-1"),
"每日美元限额须非负,整数和小数各最多 10 位",
),
(
"weeklyLimitUsd",
json!("0.00000000001"),
"每周美元限额须非负,整数和小数各最多 10 位",
),
(
"maxConcurrency",
json!(u64::MAX),
"并发请求上限超出支持范围",
),
] {
for path in [
"/api/admin/client-keys/create",
"/api/admin/client-keys/update",
] {
if path.ends_with("/update") && field == "customKey" {
continue;
}
let mut payload = json!({
"name": "key",
"groupIds": [],
"maxConcurrency": 0,
"requestsPerMinute": 0,
});
if path.ends_with("/update") {
payload["id"] = json!("key_existing");
}
payload[field] = value.clone();
let mut request = request(Method::POST, path, Body::from(payload.to_string()));
request
.headers_mut()
.insert(header::COOKIE, SESSION_COOKIE.parse().unwrap());
request
.headers_mut()
.insert(header::CONTENT_TYPE, "application/json".parse().unwrap());
let response = app(fixture.state()).oneshot(request).await.unwrap();
let (status, _, body) = response_json(response).await;
assert_eq!(status, StatusCode::BAD_REQUEST);
assert_eq!(
body,
json!({"code": 40001, "message": message, "data": null})
);
assert!(!body.to_string().contains(secret.trim()));
}
}
}
#[tokio::test]
async fn invalid_time_range_should_use_its_published_business_code() {
let fixture = AdminTestFixture::new().await;
@@ -445,8 +509,10 @@ mod provider {
let fixture = AdminTestFixture::new().await;
fixture.auth.insert_session("valid-session");
for (kind, status, code, message) in [
(Kind::Invalid, 400, 40001, "服务商请求参数不合法"),
(Kind::Unsupported, 400, 40001, "该服务商不支持此操作"),
(Kind::BadGateway, 502, 50201, "上游服务请求失败"),
(Kind::Unavailable, 503, 50301, "Provider 服务暂不可用"),
(Kind::Unavailable, 503, 50301, "服务商暂不可用"),
(
Kind::Ambiguous,
502,
@@ -562,9 +562,12 @@ async fn http_settings_freeze_before_plan_resolution_and_apply_before_admission(
.unwrap();
assert_eq!(
response.status(),
StatusCode::UPGRADE_REQUIRED,
StatusCode::BAD_REQUEST,
"request changes must not alter the published baseline"
);
let body: serde_json::Value =
serde_json::from_slice(&response.into_body().collect().await.unwrap().to_bytes()).unwrap();
assert_eq!(body["error"]["code"], "client_version_too_old");
assert_eq!(
snapshots
.acquire()
@@ -357,7 +357,7 @@ fn local_provider_capacity_exhaustion_should_map_to_service_unavailable() {
);
assert_eq!(
projected.safe_message(),
"all eligible upstream accounts are temporarily busy"
"All eligible upstream accounts are temporarily busy."
);
}
@@ -389,7 +389,7 @@ fn no_eligible_provider_account_should_preserve_safe_provider_detail() {
);
assert_eq!(
gateway.safe_message(),
"no upstream provider is currently available for this request"
"No upstream provider is currently available for this request."
);
}
@@ -407,7 +407,7 @@ fn provider_infrastructure_failure_should_have_a_distinct_client_contract() {
);
assert_eq!(
projected.safe_message(),
"provider account infrastructure is temporarily unavailable"
"Upstream accounts are temporarily inaccessible."
);
}
@@ -422,7 +422,7 @@ fn no_eligible_provider_account_should_map_to_service_unavailable() {
assert_eq!(projected.kind(), GatewayErrorKind::NoAvailableProvider);
assert_eq!(
projected.safe_message(),
"no upstream provider is currently available for this request"
"No upstream provider is currently available for this request."
);
}
@@ -479,7 +479,7 @@ fn engine_provider_credential_failures_should_not_impersonate_client_auth_failur
assert_eq!(mapped.kind(), GatewayErrorKind::UpstreamUnavailable);
assert_eq!(
mapped.safe_message(),
"upstream authentication resource is unavailable"
"The upstream account cannot access the service."
);
}
}
@@ -550,7 +550,7 @@ fn engine_provider_runtime_failures_should_collapse_to_safe_unavailability() {
let projected = gateway_error_from_engine(&error);
assert_eq!(projected.kind(), GatewayErrorKind::UpstreamUnavailable);
assert_eq!(projected.safe_message(), "upstream service is unavailable");
assert_eq!(projected.safe_message(), "Upstream service is unavailable.");
}
}
@@ -560,13 +560,13 @@ fn engine_store_error_should_collapse_to_safe_internal_error() {
let projected = gateway_error_from_engine(&error);
assert_eq!(projected.kind(), GatewayErrorKind::Internal);
assert_eq!(projected.safe_message(), "request execution failed");
assert_eq!(projected.safe_message(), "Request execution failed.");
}
#[test]
fn openai_error_response_should_preserve_only_safe_contract_fields() {
let (status, body) = openai_error_response(
StatusCode::BAD_GATEWAY,
"upstream service is unavailable",
"Upstream service is unavailable.",
"server_error",
"upstream_unavailable",
);
@@ -577,7 +577,7 @@ fn openai_error_response_should_preserve_only_safe_contract_fields() {
StatusCode::BAD_GATEWAY,
serde_json::json!({
"error": {
"message": "upstream service is unavailable",
"message": "Upstream service is unavailable.",
"type": "server_error",
"code": "upstream_unavailable"
}
@@ -767,12 +767,12 @@ mod model_routing {
(
"missing-model",
BTreeMap::new(),
"the requested model was not found in the provider catalogs available to this API key; check the model name",
"Model unavailable for this API key. Check the model name.",
),
(
"model-a",
BTreeMap::from([("model-a".to_owned(), "missing-target".to_owned())]),
"the requested model maps to an upstream model that was not found in the provider catalogs available to this API key; check the configured model mapping",
"Mapped model unavailable for this API key. Check the model mapping.",
),
] {
for stream in [false, true] {
@@ -446,7 +446,7 @@ async fn models_should_reject_recognized_cli_below_configured_min() {
.await
.expect("list models response");
assert_eq!(response.status(), StatusCode::UPGRADE_REQUIRED);
assert_eq!(response.status(), StatusCode::BAD_REQUEST);
let body = to_bytes(response.into_body(), usize::MAX)
.await
.expect("read version rejection body");
@@ -470,7 +470,7 @@ async fn models_should_reject_recognized_cli_with_invalid_version() {
.await
.expect("list models response");
assert_eq!(response.status(), StatusCode::UPGRADE_REQUIRED);
assert_eq!(response.status(), StatusCode::BAD_REQUEST);
let body = to_bytes(response.into_body(), usize::MAX)
.await
.expect("read version rejection body");
@@ -495,7 +495,7 @@ async fn models_should_reject_desktop_below_its_configured_min() {
.await
.expect("list models response");
assert_eq!(response.status(), StatusCode::UPGRADE_REQUIRED);
assert_eq!(response.status(), StatusCode::BAD_REQUEST);
let body = to_bytes(response.into_body(), usize::MAX)
.await
.expect("read version rejection body");
@@ -2406,7 +2406,7 @@ async fn atomic_uncommitted_upstream_failure_batch_should_be_forwarded_once() {
assert_eq!(body.matches("event: response.failed").count(), 1);
assert!(body.contains(std::str::from_utf8(&raw_created).expect("created frame")));
assert!(body.contains(std::str::from_utf8(&raw_failure).expect("failure frame")));
assert!(!body.contains("upstream capacity is temporarily unavailable"));
assert!(!body.contains("Upstream capacity is temporarily unavailable."));
assert!(body.ends_with("data: [DONE]\n\n"));
assert_eq!(trace.snapshot(), vec!["next_event", "commit", "next_error"]);
}
@@ -3000,7 +3000,7 @@ async fn official_core_clients_should_be_version_checked_before_starting_respons
assert!(String::from_utf8_lossy(&body).contains("event: response.completed\n"));
assert!(trace.snapshot().contains(&"commit"));
} else {
assert_eq!(status, StatusCode::UPGRADE_REQUIRED, "{product}/{version}");
assert_eq!(status, StatusCode::BAD_REQUEST, "{product}/{version}");
let value: Value = serde_json::from_slice(&body).unwrap();
assert_eq!(value["error"]["code"], "client_version_too_old");
assert_eq!(value["error"]["current_version"], version);
@@ -3071,7 +3071,7 @@ async fn chatgpt_remote_responses_should_only_skip_missing_desktop_versions() {
let body = to_bytes(response.into_body(), usize::MAX).await.unwrap();
if let Some(code) = expected_code {
let value: Value = serde_json::from_slice(&body).unwrap();
assert_eq!(status, StatusCode::UPGRADE_REQUIRED, "{name} {version:?}");
assert_eq!(status, StatusCode::BAD_REQUEST, "{name} {version:?}");
assert_eq!(value["error"]["code"], code);
assert!(execution.session.lock().unwrap().is_some());
} else {
@@ -66,6 +66,7 @@ async fn client_close_does_not_flush_a_retained_sender_with_an_inflight_write()
dropped: Arc::new(AtomicBool::new(false)),
};
let mut connection = spawn_connection(
tokio::sync::watch::channel(tokio::time::Instant::now()).0,
socket,
Arc::from("retained-writer"),
CancellationToken::new(),
@@ -1,6 +1,7 @@
//! Responses WebSocket 连接生命周期与多轮请求边界测试
mod middleware;
mod transport;
use std::{
fmt,
@@ -311,6 +312,7 @@ fn test_connection(stall_writes: bool) -> PumpHarness {
dropped: Arc::clone(&dropped),
};
let connection = spawn_connection(
tokio::sync::watch::channel(tokio::time::Instant::now()).0,
socket,
Arc::from("ws_test"),
cancellation.clone(),
@@ -0,0 +1,181 @@
//! 实际 HTTP 升级及 WS 编解码下,慢速上传与半帧停传的心跳边界
use std::{
io,
pin::Pin,
sync::{Arc, atomic::Ordering},
task::{Context, Poll},
time::Duration,
};
use futures::{SinkExt, StreamExt, ready};
use hyper_util::rt::TokioIo;
use serde_json::{Value, json};
use tokio::{
io::{AsyncRead, AsyncWrite, AsyncWriteExt, DuplexStream, ReadBuf},
time::{Instant, Sleep},
};
use tokio_tungstenite::{
WebSocketStream, client_async,
tungstenite::{Message, client::IntoClientRequest},
};
use tower::ServiceExt;
use super::{CrossingLimitExecution, CrossingLimitTrace, api_router, authenticated_client};
struct SlowUpload {
inner: DuplexStream,
slow: bool,
next_write: Option<Pin<Box<Sleep>>>,
}
impl AsyncRead for SlowUpload {
fn poll_read(
mut self: Pin<&mut Self>,
cx: &mut Context<'_>,
buffer: &mut ReadBuf<'_>,
) -> Poll<io::Result<()>> {
Pin::new(&mut self.inner).poll_read(cx, buffer)
}
}
impl AsyncWrite for SlowUpload {
fn poll_write(
mut self: Pin<&mut Self>,
cx: &mut Context<'_>,
buffer: &[u8],
) -> Poll<io::Result<usize>> {
if self.slow {
if let Some(delay) = self.next_write.as_mut() {
ready!(delay.as_mut().poll(cx));
}
let size = ready!(
Pin::new(&mut self.inner).poll_write(cx, &buffer[..buffer.len().min(4096)])
)?;
self.next_write = Some(Box::pin(tokio::time::sleep(Duration::from_secs(1))));
Poll::Ready(Ok(size))
} else {
Pin::new(&mut self.inner).poll_write(cx, buffer)
}
}
fn poll_flush(mut self: Pin<&mut Self>, cx: &mut Context<'_>) -> Poll<io::Result<()>> {
Pin::new(&mut self.inner).poll_flush(cx)
}
fn poll_shutdown(mut self: Pin<&mut Self>, cx: &mut Context<'_>) -> Poll<io::Result<()>> {
Pin::new(&mut self.inner).poll_shutdown(cx)
}
}
async fn connect() -> (WebSocketStream<SlowUpload>, Arc<CrossingLimitTrace>) {
let trace = Arc::new(CrossingLimitTrace::default());
let app = api_router(Arc::new(CrossingLimitExecution {
client: authenticated_client("sk_ws_crossing_limit"),
trace: trace.clone(),
}))
.await;
let (client, server) = tokio::io::duplex(65536);
tokio::spawn(async move {
hyper::server::conn::http1::Builder::new()
.serve_connection(
TokioIo::new(server),
hyper::service::service_fn(move |request| app.clone().oneshot(request)),
)
.with_upgrades()
.await
.expect("serve Responses upgrade");
});
let mut request = "ws://localhost/v1/responses".into_client_request().unwrap();
request.headers_mut().insert(
http::header::AUTHORIZATION,
"Bearer sk_ws_crossing_limit".parse().unwrap(),
);
let (socket, response) = client_async(
request,
SlowUpload {
inner: client,
slow: false,
next_write: None,
},
)
.await
.unwrap();
assert_eq!(response.status(), http::StatusCode::SWITCHING_PROTOCOLS);
(socket, trace)
}
async fn receive_event(socket: &mut WebSocketStream<SlowUpload>, expected: &str) {
tokio::time::timeout(Duration::from_secs(2), async {
loop {
let message = socket
.next()
.await
.expect("connection stays open")
.expect("valid frame");
if let Message::Text(text) = message {
let event: Value = serde_json::from_str(&text).unwrap();
if event["type"] == expected {
break;
}
assert_eq!(event["type"], "response.metadata");
} else {
assert!(matches!(message, Message::Ping(_)));
}
}
})
.await
.expect("receive response after upload");
}
#[tokio::test(start_paused = true)]
async fn slow_unfragmented_uploads_survive_heartbeats_on_first_and_later_requests() {
let (mut socket, trace) = connect().await;
let input = "x".repeat(320 * 1024);
for round in 1..=2 {
let started = Instant::now();
socket.get_mut().slow = true;
// 对齐 Codex 的发送语义:整个 send 完成前不读 Ping,也不主动发送 Pong
tokio::time::timeout(
Duration::from_secs(100),
socket.send(Message::Text(
json!({"type": "response.create", "model": "model-a", "input": input})
.to_string()
.into(),
)),
)
.await
.expect("upload completes")
.expect("heartbeat must not interrupt an active upload");
assert!(started.elapsed() >= Duration::from_secs(80));
socket.get_mut().slow = false;
receive_event(&mut socket, "response.created").await;
assert_eq!(trace.starts.load(Ordering::Acquire), round);
trace.release_terminal.notify_one();
receive_event(&mut socket, "response.completed").await;
}
assert_eq!(
*trace.inputs.lock().unwrap(),
vec![json!(input), json!(input)]
);
socket.close(None).await.unwrap();
}
#[tokio::test(start_paused = true)]
async fn stalled_partial_frame_without_pongs_still_releases_the_connection() {
let (mut socket, trace) = connect().await;
// 已掩码的文本帧声明 4096 字节,只交付一个字节,之后不再收发
socket
.get_mut()
.write_all(&[0x81, 0xfe, 0x10, 0x00, 0, 0, 0, 0, b'x'])
.await
.unwrap();
tokio::time::sleep(Duration::from_secs(56)).await;
let error = socket
.get_mut()
.write_all(b"x")
.await
.expect_err("idle partial frame must be closed");
assert_eq!(error.kind(), io::ErrorKind::BrokenPipe);
assert_eq!(trace.starts.load(Ordering::Acquire), 0);
}
@@ -266,7 +266,7 @@ async fn non_structured_bodies_use_safe_fallback_without_losing_status_or_ids()
assert_eq!(
error["error"],
json!({
"message": "upstream service is unavailable",
"message": "Upstream service is unavailable.",
"code": "upstream_unavailable",
"type": "server_error",
})
@@ -365,7 +365,10 @@ async fn provider_failure_facts_survive_without_a_complete_http_response() {
"observed-turn-state"
);
assert!(error["headers"].get("x-oai-request-id").is_none());
assert_eq!(error["error"]["message"], "upstream service is unavailable");
assert_eq!(
error["error"]["message"],
"Upstream service is unavailable."
);
}
#[tokio::test]
@@ -1241,7 +1241,7 @@ async fn official_core_version_gate_should_run_before_websocket_upgrade() {
else {
panic!("expected an HTTP version rejection");
};
assert_eq!(response.status(), StatusCode::UPGRADE_REQUIRED);
assert_eq!(response.status(), StatusCode::BAD_REQUEST);
let value: Value = serde_json::from_slice(response.body().as_deref().unwrap()).unwrap();
assert_eq!(value["error"]["code"], "client_version_too_old");
assert_eq!(value["error"]["current_version"], "0.158.0");
@@ -385,11 +385,11 @@ impl QueueRejection {
match self {
Self::Full => crate::error::GatewayError::new(
crate::error::GatewayErrorKind::ConcurrencyQueueFull,
"concurrency wait queue is full",
"Request queue is full.",
),
Self::Timeout => crate::error::GatewayError::new(
crate::error::GatewayErrorKind::ConcurrencyQueueTimeout,
"concurrency wait deadline elapsed",
"Request queue wait timed out.",
),
}
}
@@ -1059,7 +1059,7 @@ where
let Some(candidate) = self.plan.candidates().get(self.candidate_index).cloned() else {
let error = GatewayError::new(
GatewayErrorKind::NoAvailableProvider,
"no upstream Provider is available",
"No upstream service is available.",
);
self.finish_failure(FailureFinalization {
outcome: ExecutionOutcome::Failed,
@@ -1365,7 +1365,7 @@ where
self.record_provider_failure(candidate.provider().clone());
let error = GatewayError::new(
GatewayErrorKind::Internal,
"provider metadata did not match the frozen candidate",
"Provider metadata did not match the frozen candidate.",
);
self.finish_failure(FailureFinalization {
outcome: ExecutionOutcome::Failed,
@@ -1399,7 +1399,7 @@ where
drop(stream);
let error = GatewayError::new(
GatewayErrorKind::Internal,
"provider selected an account outside the frozen client scope",
"Provider selected an account outside the frozen client scope.",
);
self.finish_failure(FailureFinalization {
outcome: ExecutionOutcome::Failed,
@@ -1422,7 +1422,7 @@ where
drop(stream);
let error = GatewayError::new(
GatewayErrorKind::Internal,
"provider did not use the required account",
"Provider did not use the required account.",
);
self.finish_failure(FailureFinalization {
outcome: ExecutionOutcome::Failed,
@@ -1448,7 +1448,7 @@ where
drop(stream);
let error = GatewayError::new(
GatewayErrorKind::Internal,
"native continuation binding did not match selected account",
"Native continuation binding did not match selected account.",
);
self.finish_failure(FailureFinalization {
outcome: ExecutionOutcome::Failed,
@@ -2401,11 +2401,11 @@ where
} else {
ExecutionOutcome::Failed
},
GatewayError::new(GatewayErrorKind::Timeout, "request deadline elapsed"),
GatewayError::new(GatewayErrorKind::Timeout, "Request deadline elapsed."),
),
_ => (
ExecutionOutcome::Failed,
GatewayError::new(GatewayErrorKind::Internal, "request execution failed"),
GatewayError::new(GatewayErrorKind::Internal, "Request execution failed."),
),
};
let send_state = if self.attempts == 0 {
@@ -196,7 +196,7 @@ impl PreparedRootExecution {
.map_err(|_| {
GatewayError::new(
GatewayErrorKind::InvalidRequest,
"execution settings are invalid",
"Execution settings are invalid.",
)
})?;
self.client.policy = settings.apply_policy(self.client.policy.clone());
@@ -224,7 +224,7 @@ impl PreparedRootExecution {
let started_at = SystemTime::now();
let deadline_at = Deadline::from_timeout(started_at, client.execution_timeout())
.ok_or_else(|| {
GatewayError::new(GatewayErrorKind::Internal, "system clock is invalid")
GatewayError::new(GatewayErrorKind::Internal, "System clock is invalid.")
})?;
let execution_effects = Arc::new(ExecutionEffects::default());
let execution_effects_baseline = execution_effects.epoch();
@@ -411,7 +411,7 @@ pub trait ExecutionService: Send + Sync {
Box::pin(async {
Err(GatewayError::new(
GatewayErrorKind::Unauthorized,
"plugin model entry is unavailable",
"Plugin model entry is unavailable.",
))
})
}
@@ -505,6 +505,7 @@ pub(super) fn duration_ms(duration: Duration) -> u64 {
}
pub(super) fn new_request_id() -> Result<ModelRequestId, GatewayError> {
ModelRequestId::new(format!("req_{}", Uuid::now_v7().simple()))
.map_err(|_| GatewayError::new(GatewayErrorKind::Internal, "failed to allocate request ID"))
ModelRequestId::new(format!("req_{}", Uuid::now_v7().simple())).map_err(|_| {
GatewayError::new(GatewayErrorKind::Internal, "Failed to allocate request ID.")
})
}
@@ -9,15 +9,15 @@ use crate::{
pub(super) fn authentication_gateway_error(error: ClientAuthenticationError) -> GatewayError {
match error {
ClientAuthenticationError::InvalidKey => {
GatewayError::new(GatewayErrorKind::Unauthorized, "client API key is invalid")
GatewayError::new(GatewayErrorKind::Unauthorized, "Client API key is invalid.")
}
ClientAuthenticationError::SnapshotUnavailable => GatewayError::new(
GatewayErrorKind::Internal,
"runtime snapshot is unavailable",
"Gateway configuration is unavailable.",
),
ClientAuthenticationError::ProviderUnavailable => GatewayError::new(
GatewayErrorKind::Internal,
"frontend authentication provider is unavailable",
"Client authentication service is unavailable.",
),
}
}
@@ -30,24 +30,24 @@ pub(super) fn map_routing_error(error: crate::validation::RoutingError) -> Gatew
} => GatewayError::new(
GatewayErrorKind::ModelNotFound,
if model == mapped_model {
"the requested model was not found in the provider catalogs available to this API key; check the model name"
"Model unavailable for this API key. Check the model name."
} else {
"the requested model maps to an upstream model that was not found in the provider catalogs available to this API key; check the configured model mapping"
"Mapped model unavailable for this API key. Check the model mapping."
},
),
crate::validation::RoutingError::NoCapableProvider { .. }
| crate::validation::RoutingError::NoCapableProviderEndpoint { .. }
| crate::validation::RoutingError::EmptyAccountScope => GatewayError::new(
GatewayErrorKind::NoAvailableProvider,
"no provider can execute this request",
"No provider can execute this request.",
),
crate::validation::RoutingError::UnsupportedProviderEndpoint { .. } => GatewayError::new(
GatewayErrorKind::Unsupported,
"the selected provider does not support this operation",
"The selected provider does not support this operation.",
),
_ => GatewayError::new(
GatewayErrorKind::Internal,
"runtime routing configuration is invalid",
"Runtime routing configuration is invalid.",
),
}
}
@@ -55,23 +55,23 @@ pub(super) fn map_routing_error(error: crate::validation::RoutingError) -> Gatew
pub fn gateway_error_from_engine(error: &EngineError) -> GatewayError {
match error {
EngineError::Cancelled => {
GatewayError::new(GatewayErrorKind::Cancelled, "request was cancelled")
GatewayError::new(GatewayErrorKind::Cancelled, "Request was cancelled.")
}
EngineError::Deadline => {
GatewayError::new(GatewayErrorKind::Timeout, "request deadline elapsed")
GatewayError::new(GatewayErrorKind::Timeout, "Request deadline elapsed.")
}
EngineError::Provider(provider) => GatewayError::from_provider(provider),
EngineError::EmptyRoutingPlan | EngineError::ProviderNotRegistered { .. } => {
GatewayError::new(
GatewayErrorKind::NoAvailableProvider,
"no provider is available",
"No provider is available.",
)
}
EngineError::Store(source) => {
GatewayError::new(GatewayErrorKind::Internal, "request execution failed")
GatewayError::new(GatewayErrorKind::Internal, "Request execution failed.")
.with_source(source.clone())
}
_ => GatewayError::new(GatewayErrorKind::Internal, "request execution failed"),
_ => GatewayError::new(GatewayErrorKind::Internal, "Request execution failed."),
}
}
@@ -122,7 +122,7 @@ impl NestedExecutionGraph {
{
return Err(GatewayError::new(
GatewayErrorKind::ConcurrencyQueueFull,
"nested model execution concurrency is exhausted",
"Nested model execution concurrency is exhausted.",
));
}
if self
@@ -135,7 +135,7 @@ impl NestedExecutionGraph {
self.active.fetch_sub(1, Ordering::AcqRel);
return Err(GatewayError::new(
GatewayErrorKind::PolicyDenied,
"nested model execution budget is exhausted",
"Nested model execution budget is exhausted.",
));
}
Ok(NestedExecutionPermit {
@@ -333,7 +333,7 @@ impl DefaultExecutionService {
let authentication = client.authentication.clone().ok_or_else(|| {
GatewayError::new(
GatewayErrorKind::Internal,
"bound execution identity cannot enter the public start path",
"Bound execution identity cannot enter the public start path.",
)
})?;
let authentication = match client.settings.clone() {
@@ -418,13 +418,13 @@ impl DefaultExecutionService {
if authorization.cancellation.is_cancelled() {
return Err(GatewayError::new(
GatewayErrorKind::Cancelled,
"parent request was cancelled",
"Parent request was cancelled.",
));
}
if authorization.deadline_at.is_elapsed() {
return Err(GatewayError::new(
GatewayErrorKind::Timeout,
"request deadline elapsed",
"Request deadline elapsed.",
));
}
let account_group_ids = authorization
@@ -501,7 +501,7 @@ impl DefaultExecutionService {
if !authorization.account_scope.provider_kinds().contains(&provider) {
return Err(GatewayError::new(
GatewayErrorKind::PolicyDenied,
"nested provider is outside the frozen account scope",
"Nested provider is outside the frozen account scope.",
));
}
routing_context.required_provider = Some(provider);
@@ -532,21 +532,21 @@ impl DefaultExecutionService {
.map_err(|_| {
GatewayError::new(
GatewayErrorKind::Internal,
"model routing policy failed",
"Model routing policy failed.",
)
})? {
ModelRouteDecision::Unhandled => {}
ModelRouteDecision::Reject => {
return Err(GatewayError::new(
GatewayErrorKind::PolicyDenied,
"model routing policy rejected the request",
"Model routing policy rejected the request.",
));
}
ModelRouteDecision::Route { provider, model } => {
if provider.is_none() && model.is_none() {
return Err(GatewayError::new(
GatewayErrorKind::Internal,
"model routing policy returned an empty target",
"Model routing policy returned an empty target.",
));
}
if let Some(provider) = provider {
@@ -561,7 +561,7 @@ impl DefaultExecutionService {
{
return Err(GatewayError::new(
GatewayErrorKind::PolicyDenied,
"model routing policy exceeded the frozen provider scope",
"Model routing policy exceeded the frozen provider scope.",
));
}
target_context.required_provider = Some(provider);
@@ -601,26 +601,26 @@ impl DefaultExecutionService {
Err(error)
if error.kind() == NativeContinuationStoreErrorKind::OwnershipMismatch =>
{
return Err(GatewayError::new(GatewayErrorKind::PolicyDenied, "continuation does not belong to this client API key"));
return Err(GatewayError::new(GatewayErrorKind::PolicyDenied, "Continuation does not belong to this client API key."));
}
Err(error) => {
tracing::warn!(request_id = request_id.as_str(), %error, "Continuation affinity 记录无效,已拒绝续接");
return Err(GatewayError::new(GatewayErrorKind::Internal, "continuation state is invalid"));
return Err(GatewayError::new(GatewayErrorKind::Internal, "Continuation state is invalid."));
}
},
_ = timeout => None,
};
Some(match pin {
Some(pin) if !pin.matches_client(request.client.policy.key_id()) => {
return Err(GatewayError::new(GatewayErrorKind::PolicyDenied, "continuation does not belong to this client API key"));
return Err(GatewayError::new(GatewayErrorKind::PolicyDenied, "Continuation does not belong to this client API key."));
}
Some(pin) if !authorization.account_scope.allows(pin.account()) => {
return Err(GatewayError::new(GatewayErrorKind::PolicyDenied, "continuation account is outside the client account scope"));
return Err(GatewayError::new(GatewayErrorKind::PolicyDenied, "Continuation account is outside the client account scope."));
}
Some(pin)
if !plan.candidates().iter().any(|candidate| candidate.provider() == pin.provider()) =>
{
return Err(GatewayError::new(GatewayErrorKind::NoAvailableProvider, "continuation provider is not available"));
return Err(GatewayError::new(GatewayErrorKind::NoAvailableProvider, "Continuation provider is not available."));
}
Some(pin) => {
attach_continuation_session_state(&mut request.operation, &pin);
@@ -728,7 +728,7 @@ impl DefaultExecutionService {
let permit = authorization.nested_permit.take().ok_or_else(|| {
GatewayError::new(
GatewayErrorKind::Internal,
"nested execution admission is unavailable",
"Nested execution admission is unavailable.",
)
})?;
(ExecutionAdmission::Nested(permit), None)
@@ -953,19 +953,19 @@ impl DefaultExecutionService {
.ok_or_else(|| {
GatewayError::new(
GatewayErrorKind::PolicyDenied,
"parent model request is not active",
"Parent model request is not active.",
)
})?;
if authority.cancellation.is_cancelled() {
return Err(GatewayError::new(
GatewayErrorKind::Cancelled,
"parent request was cancelled",
"Parent request was cancelled.",
));
}
if authority.deadline_at.is_elapsed() {
return Err(GatewayError::new(
GatewayErrorKind::Timeout,
"parent request deadline elapsed",
"Parent request deadline elapsed.",
));
}
Ok(authority)
@@ -989,7 +989,7 @@ impl DefaultExecutionService {
if parent.extension_scope.len() >= ExtensionCallScope::MAXIMUM_DEPTH {
return Err(GatewayError::new(
GatewayErrorKind::PolicyDenied,
"nested model execution depth is exhausted",
"Nested model execution depth is exhausted.",
));
}
let extension_scope = parent
@@ -998,7 +998,7 @@ impl DefaultExecutionService {
.ok_or_else(|| {
GatewayError::new(
GatewayErrorKind::PolicyDenied,
"recursive plugin model execution is not allowed",
"Recursive plugin model execution is not allowed.",
)
})?;
let (account_scope, required_provider) = restrict_model_execution_scope(
@@ -1057,7 +1057,7 @@ impl DefaultExecutionService {
refresh.refresh().await.map_err(|_| {
GatewayError::new(
GatewayErrorKind::Internal,
"current runtime snapshot is unavailable",
"Gateway configuration is unavailable.",
)
})?;
}
@@ -1068,7 +1068,7 @@ impl DefaultExecutionService {
.map_err(|_| {
GatewayError::new(
GatewayErrorKind::Internal,
"current runtime snapshot is unavailable",
"Gateway configuration is unavailable.",
)
})?;
let policy = snapshot
@@ -1077,11 +1077,14 @@ impl DefaultExecutionService {
.ok_or_else(|| {
GatewayError::new(
GatewayErrorKind::Unauthorized,
"client API key no longer exists",
"Client API key no longer exists.",
)
})?;
policy.authorize().map_err(|_| {
GatewayError::new(GatewayErrorKind::PolicyDenied, "client API key is disabled")
GatewayError::new(
GatewayErrorKind::PolicyDenied,
"Client API key is disabled.",
)
})?;
Ok(AuthenticatedClient {
policy: match &settings {
@@ -1112,13 +1115,13 @@ impl DefaultExecutionService {
if cancellation.is_cancelled() {
return Err(GatewayError::new(
GatewayErrorKind::Cancelled,
"bound plugin invocation was cancelled",
"Bound plugin invocation was cancelled.",
));
}
if extension_scope.len() >= ExtensionCallScope::MAXIMUM_DEPTH {
return Err(GatewayError::new(
GatewayErrorKind::PolicyDenied,
"plugin model execution depth exceeded",
"Plugin model execution depth exceeded.",
));
}
let extension_scope = extension_scope
@@ -1126,13 +1129,13 @@ impl DefaultExecutionService {
.ok_or_else(|| {
GatewayError::new(
GatewayErrorKind::PolicyDenied,
"plugin model execution scope is recursive",
"Plugin model execution scope is recursive.",
)
})?;
let now = SystemTime::now();
let deadline_at =
Deadline::from_timeout(now, client.execution_timeout()).ok_or_else(|| {
GatewayError::new(GatewayErrorKind::Internal, "system clock is invalid")
GatewayError::new(GatewayErrorKind::Internal, "System clock is invalid.")
})?;
let (account_scope, required_provider) = restrict_model_execution_scope(
client.policy.account_scope().as_ref(),
@@ -1194,13 +1197,13 @@ impl DefaultExecutionService {
if !parent.account_scope.provider_kinds().contains(&provider) {
return Err(GatewayError::new(
GatewayErrorKind::PolicyDenied,
"affinity provider is outside the frozen authorization scope",
"Affinity provider is outside the frozen authorization scope.",
));
}
let affinity = self.session_affinity.as_ref().ok_or_else(|| {
GatewayError::new(
GatewayErrorKind::PolicyDenied,
"provider session affinity is unavailable",
"Provider session affinity is unavailable.",
)
})?;
let account = {
@@ -1211,15 +1214,15 @@ impl DefaultExecutionService {
result = load => result.map_err(|error| match error.kind() {
ProviderStoreErrorKind::Unavailable => GatewayError::new(
GatewayErrorKind::ProviderInfrastructureUnavailable,
"provider session affinity is temporarily unavailable",
"Provider session affinity is temporarily unavailable.",
),
ProviderStoreErrorKind::InvalidData | ProviderStoreErrorKind::Conflict => {
GatewayError::new(GatewayErrorKind::Internal, "provider session affinity is invalid")
GatewayError::new(GatewayErrorKind::Internal, "Provider session affinity is invalid.")
}
})?,
_ = timeout => return Err(GatewayError::new(
GatewayErrorKind::ProviderInfrastructureUnavailable,
"provider session affinity lookup timed out",
"Provider session affinity lookup timed out.",
)),
}
};
@@ -1261,7 +1264,7 @@ impl DefaultExecutionService {
if remaining.is_zero() {
return Err(GatewayError::new(
GatewayErrorKind::Timeout,
"request deadline elapsed",
"Request deadline elapsed.",
));
}
// 在发送原子准入之前接管取消清理,覆盖 Redis 已取得租约但返回尚未被观察的窗口
@@ -1280,9 +1283,9 @@ impl DefaultExecutionService {
let cancelled = cancellation.cancelled().fuse();
pin_mut!(acquire, timeout, cancelled);
let decision = select_biased! {
() = cancelled => return Err(GatewayError::new(GatewayErrorKind::Cancelled, "request admission was cancelled")),
result = acquire => result.map_err(|source| GatewayError::new(GatewayErrorKind::NoAvailableProvider, "request admission is temporarily unavailable").with_source(source))?,
_ = timeout => return Err(GatewayError::new(GatewayErrorKind::Timeout, "request deadline elapsed")),
() = cancelled => return Err(GatewayError::new(GatewayErrorKind::Cancelled, "Request admission was cancelled.")),
result = acquire => result.map_err(|source| GatewayError::new(GatewayErrorKind::NoAvailableProvider, "Request admission is temporarily unavailable.").with_source(source))?,
_ = timeout => return Err(GatewayError::new(GatewayErrorKind::Timeout, "Request deadline elapsed.")),
};
match decision {
ClientAdmissionDecision::Granted => {
@@ -1307,7 +1310,7 @@ impl DefaultExecutionService {
if reason == ClientAdmissionRejection::RateLimited || policy.max_waiting == 0 {
return Err(GatewayError::new(
GatewayErrorKind::RateLimited,
"request exceeds client API key limits",
"Request exceeds client API key limits.",
));
}
if waiting.elapsed().is_zero()
@@ -1345,12 +1348,12 @@ impl DefaultExecutionService {
.map_err(|_| {
GatewayError::new(
GatewayErrorKind::Internal,
"runtime snapshot is unavailable",
"Gateway configuration is unavailable.",
)
})?;
let public_model =
PublicModelId::new(upstream_model.as_str().to_owned()).map_err(|_| {
GatewayError::new(GatewayErrorKind::Unsupported, "requested model is invalid")
GatewayError::new(GatewayErrorKind::Unsupported, "Requested model is invalid.")
})?;
let routing_context = RoutingContext {
required_provider: Some(provider_kind),
@@ -1361,11 +1364,11 @@ impl DefaultExecutionService {
.map_err(map_routing_error)?;
let started_at = SystemTime::now();
let deadline_at = started_at.checked_add(DIAGNOSTIC_TIMEOUT).ok_or_else(|| {
GatewayError::new(GatewayErrorKind::Internal, "system clock is invalid")
GatewayError::new(GatewayErrorKind::Internal, "System clock is invalid.")
})?;
let request_id = new_request_id()?;
let actor = ClientApiKeyId::new("admin_connection_test")
.map_err(|_| GatewayError::new(GatewayErrorKind::Internal, "invalid admin actor"))?;
.map_err(|_| GatewayError::new(GatewayErrorKind::Internal, "Invalid admin actor."))?;
let new_request = NewModelRequest {
id: request_id,
client_api_key_name_snapshot: None,
@@ -1742,7 +1745,7 @@ impl ClientIdentityPort for DefaultExecutionService {
let cancelled = cancellation.cancelled().fuse();
pin_mut!(cancelled);
select_biased! {
() = cancelled => Err(GatewayError::new(GatewayErrorKind::Cancelled, "client verification was cancelled")),
() = cancelled => Err(GatewayError::new(GatewayErrorKind::Cancelled, "Client verification was cancelled.")),
result = verification => result.map_err(authentication_gateway_error),
}
}
@@ -1768,9 +1771,9 @@ impl NestedModelExecutionPort for DefaultExecutionService {
.fuse();
pin_mut!(cancelled, timeout, catalog);
let models = select_biased! {
() = cancelled => return Err(GatewayError::new(GatewayErrorKind::Cancelled, "model catalog call was cancelled")),
() = timeout => return Err(GatewayError::new(GatewayErrorKind::Timeout, "model catalog deadline elapsed")),
result = catalog => result.map_err(|_| GatewayError::new(GatewayErrorKind::Internal, "model catalog is unavailable"))?,
() = cancelled => return Err(GatewayError::new(GatewayErrorKind::Cancelled, "Model catalog call was cancelled.")),
() = timeout => return Err(GatewayError::new(GatewayErrorKind::Timeout, "Model catalog deadline elapsed.")),
result = catalog => result.map_err(|_| GatewayError::new(GatewayErrorKind::Internal, "Model catalog is unavailable."))?,
};
Ok(models
.into_iter()
@@ -1850,13 +1853,13 @@ fn restrict_model_execution_scope(
if !parent_scope.allows(parent_account) {
return Err(GatewayError::new(
GatewayErrorKind::PolicyDenied,
"parent attempt account is outside the frozen account scope",
"Parent attempt account is outside the frozen account scope.",
));
}
if account == Some(parent_account) {
return Err(GatewayError::new(
GatewayErrorKind::PolicyDenied,
"nested execution cannot wait for the parent attempt account",
"Nested execution cannot wait for the parent attempt account.",
));
}
account_scope = account_scope.excluding_account(parent_account.clone());
@@ -1866,7 +1869,7 @@ fn restrict_model_execution_scope(
if !account_scope.allows(account) {
return Err(GatewayError::new(
GatewayErrorKind::PolicyDenied,
"model account is outside the frozen authorization scope",
"Model account is outside the frozen authorization scope.",
));
}
let account_provider = account_scope
@@ -1875,7 +1878,7 @@ fn restrict_model_execution_scope(
.ok_or_else(|| {
GatewayError::new(
GatewayErrorKind::PolicyDenied,
"model account is unavailable in the frozen snapshot",
"Model account is unavailable in the frozen snapshot.",
)
})?;
if provider
@@ -1884,7 +1887,7 @@ fn restrict_model_execution_scope(
{
return Err(GatewayError::new(
GatewayErrorKind::PolicyDenied,
"model provider and account do not match",
"Model provider and account do not match.",
));
}
Some(account_provider)
@@ -1898,7 +1901,7 @@ fn restrict_model_execution_scope(
{
return Err(GatewayError::new(
GatewayErrorKind::PolicyDenied,
"model provider is outside the frozen authorization scope",
"Model provider is outside the frozen authorization scope.",
));
}
Ok((Arc::new(account_scope), required_provider))
@@ -12,7 +12,7 @@ pub(super) fn check_image_generation(
if !allowed && operation.image_generation_requested() {
return Err(GatewayError::new(
GatewayErrorKind::PolicyDenied,
"Image generation is not allowed by the API key's account groups",
"Image generation is not allowed by the API key's account groups.",
)
.with_client_code("image_generation_disabled"));
}
+19 -18
View File
@@ -1203,62 +1203,63 @@ impl GatewayError {
#[must_use]
pub fn from_provider(error: &ProviderError) -> Self {
let gateway = match error.kind() {
ProviderErrorKind::InvalidRequest => {
Self::new(GatewayErrorKind::InvalidRequest, "invalid upstream request")
}
ProviderErrorKind::InvalidRequest => Self::new(
GatewayErrorKind::InvalidRequest,
"Invalid upstream request.",
),
ProviderErrorKind::SessionPolicyRestricted => Self::new(
GatewayErrorKind::InvalidRequest,
"session policy excludes all eligible accounts",
"No accounts are available under this conversation's restrictions.",
),
ProviderErrorKind::ContinuationRecoveryRequired => Self::new(
GatewayErrorKind::InvalidRequest,
"conversation continuation must be rebuilt",
"Previous response unavailable. Resend the full conversation history.",
),
ProviderErrorKind::Unsupported => Self::new(
GatewayErrorKind::Unsupported,
"requested capability is unsupported",
"Requested capability is unsupported.",
),
ProviderErrorKind::Unauthorized | ProviderErrorKind::PermissionDenied => Self::new(
GatewayErrorKind::UpstreamUnavailable,
"upstream authentication resource is unavailable",
"The upstream account cannot access the service.",
),
ProviderErrorKind::RequestPolicyDenied => Self::new(
GatewayErrorKind::PolicyDenied,
"request policy rejected the request",
"Request policy rejected the request.",
),
ProviderErrorKind::RateLimited | ProviderErrorKind::QuotaExhausted => Self::new(
GatewayErrorKind::RateLimited,
"upstream capacity is temporarily unavailable",
"Upstream capacity is temporarily unavailable.",
),
ProviderErrorKind::ConcurrencyQueueFull => Self::new(
GatewayErrorKind::ConcurrencyQueueFull,
"concurrency wait queue is full",
"Request queue is full.",
),
ProviderErrorKind::ConcurrencyQueueTimeout => Self::new(
GatewayErrorKind::ConcurrencyQueueTimeout,
"concurrency wait deadline elapsed",
"Request queue wait timed out.",
),
ProviderErrorKind::AccountCapacityUnavailable => Self::new(
GatewayErrorKind::AccountCapacityUnavailable,
"all eligible upstream accounts are temporarily busy",
"All eligible upstream accounts are temporarily busy.",
),
ProviderErrorKind::NoEligibleAccount => Self::new(
GatewayErrorKind::NoAvailableProvider,
"no upstream provider is currently available for this request",
"No upstream provider is currently available for this request.",
),
ProviderErrorKind::ProviderInfrastructureUnavailable => Self::new(
GatewayErrorKind::ProviderInfrastructureUnavailable,
"provider account infrastructure is temporarily unavailable",
"Upstream accounts are temporarily inaccessible.",
),
ProviderErrorKind::Timeout => {
Self::new(GatewayErrorKind::Timeout, "upstream request timed out")
Self::new(GatewayErrorKind::Timeout, "Upstream request timed out.")
}
ProviderErrorKind::MessageTooBig => Self::new(
GatewayErrorKind::MessageTooBig,
"upstream rejected the request because the message is too large",
"Request too large. Reduce the input size.",
),
ProviderErrorKind::Cancelled => {
Self::new(GatewayErrorKind::Cancelled, "request was cancelled")
Self::new(GatewayErrorKind::Cancelled, "Request was cancelled.")
}
ProviderErrorKind::Transport
| ProviderErrorKind::Protocol
@@ -1266,7 +1267,7 @@ impl GatewayError {
| ProviderErrorKind::UpstreamCapacityUnavailable
| ProviderErrorKind::ProcessTerminated => Self::new(
GatewayErrorKind::UpstreamUnavailable,
"upstream service is unavailable",
"Upstream service is unavailable.",
),
};
let gateway = match error.diagnostic() {
+7 -7
View File
@@ -37,26 +37,26 @@ impl CancellationReason {
#[must_use]
pub const fn message(self) -> &'static str {
match self {
Self::Requested => "request was cancelled",
Self::Requested => "Request was cancelled.",
Self::Lease {
kind: RequestLeaseKind::ClientAdmission,
failure,
} => match failure {
LeaseFailure::Lost => "request was cancelled: client admission lease was lost",
LeaseFailure::Lost => "Request was cancelled: client admission lease was lost.",
LeaseFailure::RenewalTimedOut => {
"request was cancelled: client admission lease renewal timed out"
"Request was cancelled: client admission lease renewal timed out."
}
LeaseFailure::Expired => "request was cancelled: client admission lease expired",
LeaseFailure::Expired => "Request was cancelled: client admission lease expired.",
},
Self::Lease {
kind: RequestLeaseKind::Credential,
failure,
} => match failure {
LeaseFailure::Lost => "request was cancelled: credential lease was lost",
LeaseFailure::Lost => "Request was cancelled: credential lease was lost.",
LeaseFailure::RenewalTimedOut => {
"request was cancelled: credential lease renewal timed out"
"Request was cancelled: credential lease renewal timed out."
}
LeaseFailure::Expired => "request was cancelled: credential lease expired",
LeaseFailure::Expired => "Request was cancelled: credential lease expired.",
},
}
}
@@ -3776,7 +3776,7 @@ fn known_catalog_should_reject_a_model_that_the_provider_did_not_publish() {
(error.kind(), error.client_message()),
(
GatewayErrorKind::ModelNotFound,
"the requested model was not found in the provider catalogs available to this API key; check the model name",
"Model unavailable for this API key. Check the model name.",
)
);
let rejections = store.entry_rejections.lock().unwrap();
@@ -280,7 +280,7 @@ fn gateway_error_should_keep_client_visible_upstream_fields_out_of_safe_diagnost
assert_eq!(
gateway.safe_message(),
"upstream capacity is temporarily unavailable"
"Upstream capacity is temporarily unavailable."
);
assert_eq!(gateway.client_message(), message);
assert_eq!(gateway.client_error_code(), Some("quota_exhausted"));
@@ -304,7 +304,7 @@ fn continuation_recovery_should_keep_its_internal_classification_and_client_cont
assert_eq!(error.kind().as_str(), "continuation_recovery_required");
assert_eq!(
gateway.safe_message(),
"conversation continuation must be rebuilt"
"Previous response unavailable. Resend the full conversation history."
);
assert_eq!(
gateway.client_error_code(),
@@ -329,7 +329,7 @@ fn message_too_big_should_map_to_a_request_scoped_client_contract() {
assert_eq!(gateway.kind().as_str(), "message_too_big");
assert_eq!(
gateway.safe_message(),
"upstream rejected the request because the message is too large"
"Request too large. Reduce the input size."
);
assert_eq!(gateway.client_error_code(), Some("message_too_big"));
assert_eq!(gateway.client_error_type(), Some("invalid_request_error"));
+1
View File
@@ -160,6 +160,7 @@ impl HostBundle {
lease: Arc<dyn WorkerLeaderLeasePort>,
diagnostics: Arc<dyn gateway_core::diagnostics::OperationalDiagnostics>,
) -> Result<(), HostError> {
self.system.set_diagnostics(Arc::clone(&diagnostics));
self.workers.start(plan, lease, diagnostics)?;
Ok(())
}
@@ -22,7 +22,7 @@ pub(crate) fn extract_release(
temp_dir: &Path,
) -> Result<ExtractedRelease, OperationError> {
let file = fs::File::open(archive_path)
.map_err(|error| internal(format!("failed to open release archive: {error}")))?;
.map_err(|error| internal("无法打开更新包").with_source(error))?;
let decoder = flate2::read::GzDecoder::new(file);
let mut archive = tar::Archive::new(decoder);
let binary_path = temp_dir.join(APP_BINARY_NAME);
@@ -37,61 +37,55 @@ pub(crate) fn extract_release(
for entry in archive
.entries()
.map_err(|error| internal(format!("failed to read release archive: {error}")))?
.map_err(|error| internal("无法读取更新包").with_source(error))?
{
let mut entry =
entry.map_err(|error| internal(format!("invalid archive entry: {error}")))?;
entry.map_err(|error| internal("更新包内容损坏,请重新下载").with_source(error))?;
let path = entry
.path()
.map_err(|error| internal(format!("invalid archive path: {error}")))?
.map_err(|error| internal("更新包中的文件路径无效").with_source(error))?
.into_owned();
if unsafe_archive_path(&path) {
return Err(invalid("release archive contains an unsafe path"));
return Err(invalid("更新包包含不安全的文件路径,已停止更新"));
}
let official_relative = official_plugin_relative_path(&path)?;
if !entry.header().entry_type().is_file() {
if official_relative.is_some() {
return Err(invalid(
"release archive contains a non-file official plugin asset",
));
return Err(invalid("更新包中的官方插件资源不是普通文件"));
}
continue;
}
file_count = file_count.saturating_add(1);
extracted_size = extracted_size.saturating_add(entry.header().size().unwrap_or(u64::MAX));
if file_count > MAX_ARCHIVE_FILES || extracted_size > MAX_EXTRACTED_SIZE {
return Err(invalid("release archive expands beyond safety limits"));
return Err(invalid("更新包解压后的大小或文件数量超出限制"));
}
if path.file_name().is_some_and(|name| name == APP_BINARY_NAME) {
if found_binary {
return Err(invalid("release archive contains duplicate binaries"));
return Err(invalid("更新包包含重复的程序文件"));
}
entry
.unpack(&binary_path)
.map_err(|error| internal(format!("failed to extract binary: {error}")))?;
.map_err(|error| internal("无法解压程序文件").with_source(error))?;
found_binary = true;
continue;
}
if let Some(relative) = official_relative {
if !official_files.insert(relative.clone()) {
return Err(invalid(
"release archive contains a duplicate official plugin asset",
));
return Err(invalid("更新包包含重复的官方插件文件"));
}
fs::create_dir_all(&official_plugins_dir).map_err(|error| {
internal(format!("failed to create official plugin dir: {error}"))
})?;
fs::create_dir_all(&official_plugins_dir)
.map_err(|error| internal("无法创建官方插件目录").with_source(error))?;
let target = official_plugins_dir.join(&relative);
entry.unpack(&target).map_err(|error| {
internal(format!("failed to extract official plugin asset: {error}"))
})?;
entry
.unpack(&target)
.map_err(|error| internal("无法解压官方插件文件").with_source(error))?;
#[cfg(unix)]
{
use std::os::unix::fs::PermissionsExt as _;
fs::set_permissions(&target, fs::Permissions::from_mode(0o444)).map_err(
|error| internal(format!("failed to protect official plugin asset: {error}")),
)?;
fs::set_permissions(&target, fs::Permissions::from_mode(0o444))
.map_err(|error| internal("无法设置官方插件文件权限").with_source(error))?;
}
found_official_manifest |= relative == Path::new("plugin-release-manifest.json");
continue;
@@ -102,29 +96,26 @@ pub(crate) fn extract_release(
}
let target = web_dist_dir.join(relative);
if let Some(parent) = target.parent() {
fs::create_dir_all(parent).map_err(|error| {
internal(format!("failed to create web asset dir: {error}"))
})?;
fs::create_dir_all(parent)
.map_err(|error| internal("无法创建管理页面目录").with_source(error))?;
}
entry
.unpack(&target)
.map_err(|error| internal(format!("failed to extract web asset: {error}")))?;
.map_err(|error| internal("无法解压管理页面文件").with_source(error))?;
found_web = true;
}
}
if !found_binary {
return Err(invalid("release archive does not contain codex-proxy-rs"));
return Err(invalid("更新包缺少网关程序文件"));
}
if !found_official_manifest {
return Err(invalid(
"release archive does not contain the official plugin manifest",
));
return Err(invalid("更新包缺少官方插件发行清单"));
}
#[cfg(unix)]
{
use std::os::unix::fs::PermissionsExt as _;
fs::set_permissions(&binary_path, fs::Permissions::from_mode(0o755))
.map_err(|error| internal(format!("failed to chmod binary: {error}")))?;
.map_err(|error| internal("无法设置程序执行权限").with_source(error))?;
}
Ok(ExtractedRelease {
binary_path,
@@ -187,9 +178,7 @@ fn official_plugin_relative_path(path: &Path) -> Result<Option<PathBuf>, Operati
return Ok(None);
}
if relative.len() != 1 {
return Err(invalid(
"release archive contains a nested official plugin asset",
));
return Err(invalid("更新包中的官方插件目录结构不符合要求"));
}
let file_name = relative[0];
let is_manifest = file_name == "plugin-release-manifest.json";
@@ -197,9 +186,7 @@ fn official_plugin_relative_path(path: &Path) -> Result<Option<PathBuf>, Operati
.to_str()
.is_some_and(|value| value.ends_with(".tar.gz"));
if !is_manifest && !is_archive {
return Err(invalid(
"release archive contains an unexpected official plugin asset",
));
return Err(invalid("更新包包含不支持的官方插件文件类型"));
}
return Ok(Some(PathBuf::from(file_name)));
}
@@ -130,7 +130,7 @@ impl SystemUpdateConfig {
}
env::current_exe()
.and_then(fs::canonicalize)
.map_err(|error| internal(format!("failed to resolve executable: {error}")))
.map_err(|error| internal("无法确定当前程序位置").with_source(error))
}
pub(crate) fn official_plugins_dir(&self) -> Result<PathBuf, OperationError> {
@@ -138,7 +138,7 @@ impl SystemUpdateConfig {
let parent = executable
.parent()
.filter(|path| !path.as_os_str().is_empty())
.ok_or_else(|| internal("failed to resolve official plugin release directory"))?;
.ok_or_else(|| internal("无法确定官方插件安装目录"))?;
Ok(parent.join("plugins").join("official"))
}
@@ -146,7 +146,7 @@ impl SystemUpdateConfig {
self.web_dist_dir
.as_deref()
.filter(|path| !path.as_os_str().is_empty())
.ok_or_else(|| conflict("web assets directory is not configured"))
.ok_or_else(|| conflict("尚未配置管理页面文件目录,无法在线更新"))
}
}
@@ -0,0 +1,57 @@
//! 更新 owner 消费失败时记录受控详情,初始化和关闭阶段保持尽力写入
use std::sync::{Arc, OnceLock};
use gateway_core::diagnostics::{OperationalDiagnostics, OperationalFailure};
use super::OperationError;
#[derive(Clone, Default)]
pub(super) struct Diagnostics(Arc<OnceLock<Arc<dyn OperationalDiagnostics>>>);
impl Diagnostics {
pub(super) fn bind(&self, diagnostics: Arc<dyn OperationalDiagnostics>) {
let _ = self.0.set(diagnostics);
}
pub(super) async fn record(
&self,
operation: &'static str,
correlation_id: Option<&str>,
error: &OperationError,
) {
let Some(diagnostics) = self.0.get() else {
return;
};
let mut failure = OperationalFailure::new(
"system_update",
operation,
"system_operation_failed",
error.message(),
);
failure.correlation_id = correlation_id.map(str::to_owned);
failure.details = error.error_details();
if diagnostics.record_failure(failure).await.is_err() {
tracing::warn!(operation, "系统操作诊断记录失败");
}
}
pub(super) fn record_on_drop(
&self,
operation: &'static str,
correlation_id: Option<String>,
error: OperationError,
) {
// 析构不能等待异步存储,运行时已关闭时沿用诊断尽力写入的合同
if self.0.get().is_some()
&& let Ok(runtime) = tokio::runtime::Handle::try_current()
{
let diagnostics = self.clone();
drop(runtime.spawn(async move {
diagnostics
.record(operation, correlation_id.as_deref(), &error)
.await;
}));
}
}
}
@@ -25,7 +25,7 @@ pub(crate) async fn download_file(
) -> Result<(), OperationError> {
validate_download_url(url, api_base)?;
if expected_size == 0 || expected_size > MAX_DOWNLOAD_SIZE {
return Err(invalid("release archive size is invalid"));
return Err(invalid("更新包大小无效或超出限制"));
}
let client = download_client(api_base, Duration::from_secs(120))?;
let response = client
@@ -33,32 +33,32 @@ pub(crate) async fn download_file(
.header(reqwest::header::ACCEPT_ENCODING, "identity")
.send()
.await
.map_err(|error| upstream(format!("release download failed: {error}")))?;
.map_err(|error| super::error::http("更新包下载失败", error))?;
if !response.status().is_success() {
return Err(upstream(format!(
"release download failed with {}",
response.status()
"更新包下载失败(HTTP {})",
response.status().as_u16()
)));
}
if response
.content_length()
.is_some_and(|size| size != expected_size)
{
return Err(upstream("downloaded size does not match release metadata"));
return Err(upstream("下载文件大小与发行信息不一致"));
}
let mut file = fs::File::create(destination)
.map_err(|error| super::internal(format!("failed to create download file: {error}")))?;
.map_err(|error| super::internal("无法创建下载文件").with_source(error))?;
let mut stream = response.bytes_stream();
let mut downloaded = 0_u64;
let mut next_progress = 10_u8;
while let Some(chunk) = stream.next().await {
let chunk = chunk.map_err(|error| upstream(format!("download stream failed: {error}")))?;
let chunk = chunk.map_err(|error| super::error::http("更新包下载中断", error))?;
downloaded = downloaded.saturating_add(u64::try_from(chunk.len()).unwrap_or(u64::MAX));
if downloaded > expected_size {
return Err(invalid("download exceeds declared release size"));
return Err(invalid("下载文件超过发行信息声明的大小,已停止更新"));
}
file.write_all(&chunk)
.map_err(|error| super::internal(format!("failed to write download: {error}")))?;
.map_err(|error| super::internal("无法保存下载内容").with_source(error))?;
let percent = download_percent(downloaded, expected_size);
if percent >= next_progress || downloaded == expected_size {
events.emit_progress(
@@ -74,9 +74,9 @@ pub(crate) async fn download_file(
}
}
file.sync_all()
.map_err(|error| super::internal(format!("failed to sync download: {error}")))?;
.map_err(|error| super::internal("无法完成下载文件写入").with_source(error))?;
if downloaded != expected_size {
return Err(upstream("downloaded size does not match release metadata"));
return Err(upstream("下载文件大小与发行信息不一致"));
}
Ok(())
}
@@ -90,7 +90,7 @@ pub(crate) async fn verify_checksum(
) -> Result<(), OperationError> {
validate_download_url(checksum_url, api_base)?;
if checksum_size == 0 || checksum_size > MAX_CHECKSUM_SIZE {
return Err(invalid("release checksum size is invalid"));
return Err(invalid("校验文件大小无效或超出限制"));
}
let client = download_client(api_base, Duration::from_secs(30))?;
let response = client
@@ -98,27 +98,27 @@ pub(crate) async fn verify_checksum(
.header(reqwest::header::ACCEPT_ENCODING, "identity")
.send()
.await
.map_err(|error| upstream(format!("checksum download failed: {error}")))?;
.map_err(|error| super::error::http("校验文件下载失败", error))?;
if !response.status().is_success() {
return Err(upstream(format!(
"checksum download failed with {}",
response.status()
"校验文件下载失败(HTTP {})",
response.status().as_u16()
)));
}
let bytes = response
.bytes()
.await
.map_err(|error| upstream(format!("checksum read failed: {error}")))?;
.map_err(|error| super::error::http("校验文件读取失败", error))?;
if bytes.len() > MAX_CHECKSUM_SIZE as usize || bytes.len() as u64 != checksum_size {
return Err(invalid("checksum document size is invalid"));
return Err(invalid("校验文件大小与发行信息不一致"));
}
let body =
std::str::from_utf8(&bytes).map_err(|_| invalid("checksum document is not UTF-8"))?;
std::str::from_utf8(&bytes).map_err(|_| invalid("校验文件编码无效,无法校验更新包"))?;
let expected = checksum_for(body, file_name)
.ok_or_else(|| upstream("release checksum entry is missing"))?;
.ok_or_else(|| upstream("校验文件中缺少当前更新包的校验值"))?;
let actual = sha256_file(file_path)?;
if !expected.eq_ignore_ascii_case(&actual) {
return Err(upstream("release checksum mismatch"));
return Err(upstream("更新包校验失败,请重新下载"));
}
Ok(())
}
@@ -137,13 +137,13 @@ fn checksum_for(body: &str, file_name: &str) -> Option<String> {
fn sha256_file(path: &Path) -> Result<String, OperationError> {
let mut file = fs::File::open(path)
.map_err(|error| super::internal(format!("failed to open checksum file: {error}")))?;
.map_err(|error| super::internal("无法打开待校验文件").with_source(error))?;
let mut hasher = sha2::Sha256::new();
let mut buffer = [0_u8; 64 * 1024];
loop {
let read = file
.read(&mut buffer)
.map_err(|error| super::internal(format!("failed to read checksum file: {error}")))?;
.map_err(|error| super::internal("无法读取待校验文件").with_source(error))?;
if read == 0 {
break;
}
@@ -16,6 +16,16 @@ pub(super) fn upstream(message: impl Into<String>) -> OperationError {
SystemOperationError::new(SystemOperationErrorKind::Upstream, message)
}
pub(super) fn http(message: &'static str, source: reqwest::Error) -> OperationError {
let failure = upstream(message);
let failure = if source.url().is_some() {
failure.redact_sensitive_context()
} else {
failure
};
failure.with_source(source.without_url())
}
pub(super) fn internal(message: impl Into<String>) -> OperationError {
SystemOperationError::new(SystemOperationErrorKind::Internal, message)
}
@@ -52,8 +52,7 @@ impl ReleaseFiles {
}
fn read_error(error: io::Error) -> OperationError {
tracing::warn!(error = %error, "核对系统安装文件失败");
internal("无法核对安装文件,请检查文件完整性与读取权限")
internal("无法核对安装文件").with_source(error)
}
fn hash_directory(path: &Path) -> io::Result<String> {
@@ -2,6 +2,7 @@
mod archive;
mod config;
mod diagnostics;
mod download;
mod error;
mod events;
@@ -44,6 +44,7 @@ pub struct ProcessSystemOperations {
operation_lock: Arc<AsyncMutex<Option<OperationFileLock>>>,
release_cache: Arc<ReleaseCache>,
running_files: Arc<Result<ReleaseFiles, OperationError>>,
diagnostics: super::diagnostics::Diagnostics,
}
impl ProcessSystemOperations {
@@ -62,13 +63,22 @@ impl ProcessSystemOperations {
operation_lock: Arc::new(AsyncMutex::new(None)),
release_cache: Arc::new(ReleaseCache::default()),
running_files,
diagnostics: super::diagnostics::Diagnostics::default(),
}
}
/// Store 就绪后绑定受控诊断端口,不改变 Host 的初始化顺序
pub fn set_diagnostics(
&self,
diagnostics: Arc<dyn gateway_core::diagnostics::OperationalDiagnostics>,
) {
self.diagnostics.bind(diagnostics);
}
fn lock_operation(&self) -> Result<OwnedMutexGuard<Option<OperationFileLock>>, OperationError> {
let operation = Arc::clone(&self.operation_lock)
.try_lock_owned()
.map_err(|_| conflict("system operation is already running"))?;
.map_err(|_| conflict("已有系统操作正在执行"))?;
if operation.is_some() {
return Err(conflict("服务正在重启"));
}
@@ -95,7 +105,7 @@ impl ProcessSystemOperations {
let selected = self.resolve_channel(channel)?;
if let Err(error) = validate_update_target(&self.config.version, &target, selected) {
self.events
.error_terminal(None, Some("preflight"), error.to_string());
.error_terminal(None, Some("preflight"), error.message().to_owned());
return Err(error);
}
let status = self.reconcile_installation()?;
@@ -109,6 +119,7 @@ impl ProcessSystemOperations {
&target,
&self.config.version,
file_lock,
self.diagnostics.clone(),
)?;
let accepted = SystemOperationAccepted::Update {
operation_id: operation_id.clone(),
@@ -125,7 +136,18 @@ impl ProcessSystemOperations {
() = service.cancellation.cancelled() => Err(conflict("服务关闭,更新已中断")),
result = service.perform_update_inner(&target, selected, &operation_id, preflight.as_ref()) => result,
};
if let Err(error) = operation.complete(&result) {
let completion = operation.complete(&result);
if let Err(error) = &result {
service
.diagnostics
.record("install", Some(&operation_id), error)
.await;
}
if let Err(error) = completion {
service
.diagnostics
.record("persist_update_status", Some(&operation_id), &error)
.await;
tracing::warn!(error = %error, "系统更新终态落盘失败");
return;
}
@@ -138,7 +160,7 @@ impl ProcessSystemOperations {
Err(error) => service.events.error_terminal(
Some(&operation_id),
Some("failed"),
error.to_string(),
error.message().to_owned(),
),
}
}));
@@ -156,7 +178,7 @@ impl ProcessSystemOperations {
.config
.update_repository
.as_deref()
.ok_or_else(|| conflict("update repository is not configured"))?;
.ok_or_else(|| conflict("未配置更新仓库 CPR_UPDATE_REPOSITORY"))?;
self.events.info(
Some(operation_id),
Some("release"),
@@ -211,22 +233,22 @@ impl ProcessSystemOperations {
self.events
.info(Some(operation_id), Some("verify"), "正在校验更新资源");
if archive.size == 0 || archive.size > MAX_DOWNLOAD_SIZE {
return Err(invalid("release archive size is invalid"));
return Err(invalid("更新包大小无效或超出限制"));
}
let checksum = release
.assets
.iter()
.find(|asset| asset.name == "checksums.txt")
.ok_or_else(|| upstream("release checksums.txt is required"))?;
.ok_or_else(|| upstream("发行版本缺少 checksums.txt 校验文件,无法安全更新"))?;
if checksum.size == 0 || checksum.size > MAX_CHECKSUM_SIZE {
return Err(invalid("release checksum size is invalid"));
return Err(invalid("校验文件大小无效或超出限制"));
}
self.events
.info(Some(operation_id), Some("prepare"), "正在创建临时更新目录");
fs::create_dir_all(&self.config.update_temp_dir)
.map_err(|error| internal(format!("failed to prepare update temp dir: {error}")))?;
.map_err(|error| internal("无法创建更新临时目录").with_source(error))?;
let temp_root = fs::canonicalize(&self.config.update_temp_dir)
.map_err(|error| internal(format!("failed to resolve update temp dir: {error}")))?;
.map_err(|error| internal("无法确定更新临时目录位置").with_source(error))?;
let temp = UpdateTempDir::create(&temp_root)?;
let archive_path = temp.path().join(&archive.name);
self.events
@@ -283,7 +305,7 @@ impl ProcessSystemOperations {
self.config.web_dist_dir()?,
extracted,
)?;
let mut applied = AppliedReleaseGuard::new(&self.config);
let mut applied = AppliedReleaseGuard::new(&self.config, &self.diagnostics);
let applied_manifest = read_release_manifest(&self.config.official_plugins_dir()?)?;
if applied_manifest.as_ref() != release_manifest.as_ref() {
return Err(applied.rollback(conflict("已应用的更新候选与预检候选不一致")));
@@ -368,12 +390,15 @@ impl SystemOperations for ProcessSystemOperations {
.await
{
Ok(detail) => Ok(detail),
Err(error) => Ok(base_update_detail(
&self.config,
channel,
self.config.update_support_error(),
Some(error.to_string()),
)),
Err(error) => {
self.diagnostics.record("check_release", None, &error).await;
Ok(base_update_detail(
&self.config,
channel,
self.config.update_support_error(),
Some(error.message().to_owned()),
))
}
}
}
@@ -454,7 +479,7 @@ impl SystemOperations for ProcessSystemOperations {
)?;
let result = match rollback_release(&self.config) {
Ok(()) => {
let mut applied = AppliedReleaseGuard::new(&self.config);
let mut applied = AppliedReleaseGuard::new(&self.config, &self.diagnostics);
let result = match read_release_manifest(&self.config.official_plugins_dir()?) {
Ok(manifest) if manifest.as_ref() == release_manifest.as_ref() => {
preflight.confirm_revision(plugin_revision).await
@@ -478,24 +503,28 @@ impl SystemOperations for ProcessSystemOperations {
SystemOperationKind::Rollback,
None,
None,
result.as_ref().err().map(ToString::to_string),
result
.as_ref()
.err()
.map(|error| error.message().to_owned()),
)?;
match &result {
Ok(()) => self.events.success_terminal(
Some(&operation_id),
Some("done"),
"previous release restored",
"上一版本已恢复,请重启服务",
),
Err(error) => self.events.error_terminal(
Some(&operation_id),
Some("failed"),
error.message().to_owned(),
),
Err(error) => {
self.events
.error_terminal(Some(&operation_id), Some("failed"), error.to_string())
}
}
drop(file_lock);
result?;
Ok(SystemOperationAccepted::Rollback {
operation_id,
message: "回滚完成,请重启服务。".to_owned(),
message: "回滚完成,请重启服务".to_owned(),
need_restart: true,
})
}
@@ -513,7 +542,7 @@ impl SystemOperations for ProcessSystemOperations {
// 载入半成品产物
let mut operation = self.lock_operation()?;
if !self.config.self_restart_enabled {
return Err(conflict("self restart is disabled"));
return Err(conflict("当前部署未启用在线重启"));
}
let file_lock = OperationFileLock::acquire(&self.config.update_lock_file)?;
let candidate = self.installed_restart_candidate()?;
@@ -555,36 +584,40 @@ impl SystemOperations for ProcessSystemOperations {
fn read_release_manifest(directory: &Path) -> Result<Arc<[u8]>, OperationError> {
let path = directory.join(OFFICIAL_PLUGIN_MANIFEST);
let metadata = fs::symlink_metadata(&path)
.map_err(|error| invalid(format!("official plugin manifest is unavailable: {error}")))?;
.map_err(|error| invalid("无法访问官方插件发行清单").with_source(error))?;
if !metadata.file_type().is_file() || metadata.file_type().is_symlink() {
return Err(invalid("official plugin manifest is not a regular file"));
return Err(invalid("官方插件发行清单必须是普通文件"));
}
if metadata.len() == 0 || metadata.len() > MAX_OFFICIAL_PLUGIN_MANIFEST_SIZE {
return Err(invalid("official plugin manifest size is invalid"));
return Err(invalid("官方插件发行清单大小无效或超出限制"));
}
fs::read(path)
.map(Arc::<[u8]>::from)
.map_err(|error| invalid(format!("official plugin manifest cannot be read: {error}")))
.map_err(|error| invalid("无法读取官方插件发行清单").with_source(error))
}
fn restore_applied_release(config: &SystemUpdateConfig, cause: OperationError) -> OperationError {
match rollback_release(config) {
Ok(()) => cause,
Err(error) => internal(format!(
"release verification failed and restoring the previous files failed: {error}"
)),
Err(error) => internal("更新校验失败,且无法恢复原文件")
.with_source(gateway_core::error::ErrorSource::new(cause).with_cleanup(error)),
}
}
struct AppliedReleaseGuard<'a> {
config: &'a SystemUpdateConfig,
diagnostics: &'a super::diagnostics::Diagnostics,
armed: bool,
}
impl<'a> AppliedReleaseGuard<'a> {
const fn new(config: &'a SystemUpdateConfig) -> Self {
const fn new(
config: &'a SystemUpdateConfig,
diagnostics: &'a super::diagnostics::Diagnostics,
) -> Self {
Self {
config,
diagnostics,
armed: true,
}
}
@@ -605,6 +638,8 @@ impl Drop for AppliedReleaseGuard<'_> {
&& let Err(error) = rollback_release(self.config)
{
tracing::error!(error = %error, "系统发行物临界区取消后的恢复失败");
self.diagnostics
.record_on_drop("restore_cancelled_installation", None, error);
}
}
}
@@ -13,19 +13,15 @@ const DEFAULT_RESTART_DELAY_MS: u64 = 1_200;
pub(crate) fn spawn_replacement(config: &SystemUpdateConfig) -> Result<(), OperationError> {
let executable = config.executable_path()?;
let metadata = fs::metadata(&executable)
.map_err(|error| internal(format!("failed to schedule replacement process: {error}")))?;
.map_err(|error| internal("无法启动替换进程").with_source(error))?;
if !metadata.is_file() {
return Err(internal(
"failed to schedule replacement process: executable is not a file",
));
return Err(internal("当前程序不是普通文件,无法在线重启"));
}
#[cfg(unix)]
{
use std::os::unix::fs::PermissionsExt as _;
if metadata.permissions().mode() & 0o111 == 0 {
return Err(internal(
"failed to schedule replacement process: executable is not executable",
));
return Err(internal("当前程序没有执行权限,无法在线重启"));
}
}
@@ -58,5 +54,5 @@ pub(crate) fn spawn_replacement(config: &SystemUpdateConfig) -> Result<(), Opera
command
.spawn()
.map(|_| ())
.map_err(|error| internal(format!("failed to schedule replacement process: {error}")))
.map_err(|error| internal("无法启动替换进程").with_source(error))
}
@@ -60,7 +60,7 @@ impl ReleaseCache {
let repository = config
.update_repository
.as_deref()
.ok_or_else(|| conflict("update repository is not configured"))?;
.ok_or_else(|| conflict("未配置更新仓库 CPR_UPDATE_REPOSITORY"))?;
validate_repository(repository)?;
validate_api_base(&config.github_api_base).map_err(conflict)?;
let key = format!("{}|{}", config.release_cache_key(), channel.as_str());
@@ -127,12 +127,12 @@ pub(crate) async fn fetch_latest(
validate_repository(repository)?;
let base = api_base.trim_end_matches('/');
let current = semver::Version::parse(&normalize_version(current_version))
.map_err(|_| invalid("current version is invalid"))?;
.map_err(|_| invalid("当前版本号无效,无法检查更新"))?;
let client = reqwest::Client::builder()
.timeout(Duration::from_secs(30))
.redirect(reqwest::redirect::Policy::none())
.build()
.map_err(|error| upstream(format!("failed to create release client: {error}")))?;
.map_err(|error| super::error::http("无法初始化发行查询连接", error))?;
// 所有发行线先过滤再排序,避免更高大版本或其他实验遮住仍可安装的更新
let mut latest: Option<(semver::Version, GitHubRelease)> = None;
@@ -184,17 +184,17 @@ async fn fetch_release_json<T: serde::de::DeserializeOwned>(
.header(reqwest::header::USER_AGENT, APP_BINARY_NAME)
.send()
.await
.map_err(|error| upstream(format!("GitHub release check failed: {error}")))?;
.map_err(|error| super::error::http("无法查询 GitHub 发行版本", error))?;
if !response.status().is_success() {
return Err(upstream(format!(
"GitHub release check failed with {}",
response.status()
"GitHub 发行查询失败(HTTP {})",
response.status().as_u16()
)));
}
response
.json::<T>()
.await
.map_err(|error| upstream(format!("invalid GitHub release response: {error}")))
.map_err(|error| super::error::http("GitHub 发行信息格式无效", error))
}
pub(crate) fn detail_from_release(
@@ -227,10 +227,10 @@ pub(crate) fn detail_from_release(
}
pub(crate) fn confirmed_target(target: Option<String>) -> Result<String, OperationError> {
let target = target.ok_or_else(|| conflict("target version must be confirmed"))?;
let target = target.ok_or_else(|| conflict("请先确认目标版本"))?;
let target = normalize_version(&target);
if target.is_empty() || semver::Version::parse(&target).is_err() {
return Err(invalid("target version is invalid"));
return Err(invalid("目标版本号格式无效"));
}
Ok(target)
}
@@ -258,7 +258,7 @@ pub(crate) fn select_archive<'a>(
})
.ok_or_else(|| {
conflict(format!(
"no compatible release archive for {}/{}",
"当前发行版本没有适用于 {}/{} 的更新包",
env::consts::OS,
env::consts::ARCH
))
@@ -268,20 +268,20 @@ pub(crate) fn select_archive<'a>(
/// 校验 GitHub Release 资产 URL 及其重定向目标是否位于受信任边界内
pub fn validate_download_url(raw: &str, api_base: &str) -> Result<(), OperationError> {
let url = reqwest::Url::parse(raw)
.map_err(|error| invalid(format!("invalid download URL: {error}")))?;
.map_err(|error| invalid("更新文件下载地址格式无效").with_source(error))?;
if local_download_allowed(&url, api_base) {
return Ok(());
}
if url.scheme() != "https" {
return Err(invalid("only HTTPS release downloads are allowed"));
return Err(invalid("更新文件必须通过 HTTPS 下载"));
}
let host = url
.host_str()
.ok_or_else(|| invalid("download URL is missing host"))?;
.ok_or_else(|| invalid("更新文件下载地址缺少主机名"))?;
if github_download_host_allowed(host) {
Ok(())
} else {
Err(invalid("release download host is not trusted"))
Err(invalid("更新文件下载地址不在受信任的发行站点范围内"))
}
}
@@ -302,7 +302,7 @@ pub(crate) fn download_client(
}
}))
.build()
.map_err(|error| upstream(format!("failed to create download client: {error}")))
.map_err(|error| super::error::http("无法初始化下载连接", error))
}
pub(crate) fn validate_repository(repository: &str) -> Result<(), OperationError> {
@@ -315,30 +315,30 @@ pub(crate) fn validate_repository(repository: &str) -> Result<(), OperationError
|| !owner.chars().all(repository_character)
|| !name.chars().all(repository_character)
{
return Err(conflict("update repository must use owner/repository"));
return Err(conflict("更新仓库格式应为 owner/repository"));
}
Ok(())
}
pub(crate) fn validate_api_base(raw: &str) -> Result<(), String> {
let url = reqwest::Url::parse(raw).map_err(|error| format!("invalid API base: {error}"))?;
let url = reqwest::Url::parse(raw).map_err(|_| "发行查询地址格式无效".to_owned())?;
if !url.username().is_empty()
|| url.password().is_some()
|| url.query().is_some()
|| url.fragment().is_some()
{
return Err("API base must not include credentials, query, or fragment".to_owned());
return Err("发行查询地址不能包含认证信息、查询参数或片段".to_owned());
}
if url.path().trim_end_matches('/') != "/repos" {
return Err("API base path must be /repos".to_owned());
return Err("发行查询地址的路径必须为 /repos".to_owned());
}
if url_host_is_loopback(&url) {
return matches!(url.scheme(), "http" | "https")
.then_some(())
.ok_or_else(|| "loopback API base must use HTTP or HTTPS".to_owned());
.ok_or_else(|| "本地发行查询地址必须使用 HTTP 或 HTTPS".to_owned());
}
if url.scheme() != "https" || url.host_str() != Some("api.github.com") {
return Err("API base must be https://api.github.com/repos".to_owned());
return Err("发行查询地址必须为 https://api.github.com/repos".to_owned());
}
Ok(())
}
@@ -409,7 +409,7 @@ pub(crate) fn validate_update_target(
let current = semver::Version::parse(&normalize_version(current))
.map_err(|_| conflict("当前版本格式无效"))?;
let target = semver::Version::parse(&normalize_version(target))
.map_err(|_| invalid("target version is invalid"))?;
.map_err(|_| invalid("目标版本号格式无效"))?;
if !update_target_allowed(&current, &target, channel) {
return Err(conflict(
"所选通道不允许此目标,或目标涉及跨实验线、跨大版本、降级",
@@ -494,13 +494,13 @@ impl SystemUpdateConfig {
return Some("检查更新需要配置 CPR_UPDATE_REPOSITORY".to_owned());
};
if let Err(error) = validate_repository(repository) {
return Some(error.to_string());
return Some(error.message().to_owned());
}
if let Err(error) = validate_api_base(&self.github_api_base) {
return Some(error);
}
if let Err(error) = self.web_dist_dir() {
return Some(error.to_string());
return Some(error.message().to_owned());
}
None
}
@@ -71,29 +71,27 @@ impl OperationFileLock {
.parent()
.filter(|parent| !parent.as_os_str().is_empty())
{
fs::create_dir_all(parent).map_err(|error| {
internal(format!("failed to create update lock directory: {error}"))
})?;
fs::create_dir_all(parent)
.map_err(|error| internal("无法创建更新锁目录").with_source(error))?;
}
match Self::try_create(path) {
Ok(()) => Ok(Self { path: path.into() }),
Err(error) if error.kind() == io::ErrorKind::AlreadyExists => {
if !stale_lock(path)? {
return Err(conflict("system update already running"));
return Err(conflict("系统更新正在执行"));
}
fs::remove_file(path).map_err(|error| {
internal(format!("failed to remove stale update lock: {error}"))
})?;
fs::remove_file(path)
.map_err(|error| internal("无法清理过期更新锁").with_source(error))?;
Self::try_create(path).map_err(|error| {
if error.kind() == io::ErrorKind::AlreadyExists {
conflict("system update already running")
conflict("系统更新正在执行")
} else {
internal(format!("failed to create update lock: {error}"))
internal("无法创建更新锁").with_source(error)
}
})?;
Ok(Self { path: path.into() })
}
Err(error) => Err(internal(format!("failed to create update lock: {error}"))),
Err(error) => Err(internal("无法创建更新锁").with_source(error)),
}
}
@@ -137,13 +135,11 @@ impl UpdateTempDir {
Ok(()) => return Ok(Self { path }),
Err(error) if error.kind() == io::ErrorKind::AlreadyExists => continue,
Err(error) => {
return Err(internal(format!(
"failed to create update temp directory: {error}"
)));
return Err(internal("无法创建更新临时目录").with_source(error));
}
}
}
Err(internal("failed to create unique update temp directory"))
Err(internal("无法分配更新临时目录"))
}
pub(crate) fn path(&self) -> &Path {
@@ -168,6 +164,7 @@ pub(crate) struct UpdateOperation {
target: String,
completed: bool,
_file_lock: OperationFileLock,
diagnostics: super::diagnostics::Diagnostics,
}
impl UpdateOperation {
@@ -177,6 +174,7 @@ impl UpdateOperation {
target: &str,
current_version: &str,
file_lock: OperationFileLock,
diagnostics: super::diagnostics::Diagnostics,
) -> Result<Self, OperationError> {
set_running(
path,
@@ -191,6 +189,7 @@ impl UpdateOperation {
target: target.to_owned(),
completed: false,
_file_lock: file_lock,
diagnostics,
})
}
@@ -204,7 +203,10 @@ impl UpdateOperation {
SystemOperationKind::Update,
result.as_ref().ok().map(|_| self.target.clone()),
result.as_ref().ok().cloned(),
result.as_ref().err().map(ToString::to_string),
result
.as_ref()
.err()
.map(|error| error.message().to_owned()),
)?;
self.completed = true;
Ok(())
@@ -224,6 +226,11 @@ impl Drop for UpdateOperation {
)
{
tracing::warn!(error = %error, "收敛中断的系统更新状态失败");
self.diagnostics.record_on_drop(
"persist_interrupted_update",
Some(self.operation_id.clone()),
error,
);
}
}
}
@@ -277,7 +284,7 @@ pub(crate) fn set_running(
kind: Some(kind.into()),
status: PersistedStatus::Running,
target_version: target_version.map(ToOwned::to_owned),
message: Some("operation running".to_owned()),
message: Some("操作正在执行".to_owned()),
error: None,
started_at: Some(Utc::now().to_rfc3339()),
finished_at: None,
@@ -303,7 +310,7 @@ pub(crate) fn finish(
state.operation.error = Some(error);
} else {
state.operation.status = PersistedStatus::Succeeded;
state.operation.message = Some("operation succeeded".to_owned());
state.operation.message = Some("操作已完成".to_owned());
state.operation.error = None;
match kind {
SystemOperationKind::Update => {
@@ -398,11 +405,11 @@ pub(crate) fn reconcile_installation(
fn stale_lock(path: &Path) -> Result<bool, OperationError> {
let modified = fs::metadata(path)
.and_then(|metadata| metadata.modified())
.map_err(|error| internal(format!("failed to read update lock timestamp: {error}")))?;
.map_err(|error| internal("无法读取更新锁时间").with_source(error))?;
modified
.elapsed()
.map(|age| age > Duration::from_secs(30 * 60))
.map_err(|error| internal(format!("failed to calculate update lock age: {error}")))
.map_err(|error| internal("无法检查更新锁是否过期").with_source(error))
}
fn read_persisted(path: &Path) -> Result<PersistedState, OperationError> {
@@ -410,8 +417,8 @@ fn read_persisted(path: &Path) -> Result<PersistedState, OperationError> {
return Ok(PersistedState::default());
}
let data = fs::read_to_string(path)
.map_err(|error| internal(format!("failed to read update state: {error}")))?;
serde_json::from_str(&data).map_err(|error| internal(format!("invalid update state: {error}")))
.map_err(|error| internal("无法读取系统更新状态").with_source(error))?;
serde_json::from_str(&data).map_err(|error| internal("系统更新状态文件损坏").with_source(error))
}
fn write_persisted(path: &Path, state: &PersistedState) -> Result<(), OperationError> {
@@ -419,12 +426,11 @@ fn write_persisted(path: &Path, state: &PersistedState) -> Result<(), OperationE
.parent()
.filter(|parent| !parent.as_os_str().is_empty())
{
fs::create_dir_all(parent).map_err(|error| {
internal(format!("failed to create update state directory: {error}"))
})?;
fs::create_dir_all(parent)
.map_err(|error| internal("无法创建系统更新状态目录").with_source(error))?;
}
let data = serde_json::to_vec_pretty(state)
.map_err(|error| internal(format!("failed to encode update state: {error}")))?;
.map_err(|error| internal("无法生成系统更新状态").with_source(error))?;
let temporary = temporary_path(path);
let result = (|| {
let mut file = fs::OpenOptions::new()
@@ -438,7 +444,7 @@ fn write_persisted(path: &Path, state: &PersistedState) -> Result<(), OperationE
if result.is_err() {
let _ = fs::remove_file(&temporary);
}
result.map_err(|error| internal(format!("failed to write update state: {error}")))
result.map_err(|error| internal("无法保存系统更新状态").with_source(error))
}
fn temporary_path(path: &Path) -> PathBuf {
@@ -1,10 +1,12 @@
//! 二进制与 Web 制品的交易式替换、跨文件系统移动与回滚
use std::fmt;
use std::error::Error;
use std::fs;
use std::io;
use std::path::{Path, PathBuf};
use gateway_core::error::ErrorSource;
use super::archive::ExtractedRelease;
use super::{OperationError, SystemUpdateConfig, conflict, internal};
@@ -15,18 +17,15 @@ pub(crate) fn replace_release_files(
) -> Result<(), OperationError> {
let official_plugins = official_plugins_dir(executable)?;
if !official_plugins.exists() {
fs::create_dir_all(&official_plugins).map_err(|error| {
internal(format!(
"failed to prepare official plugin rollback directory: {error}"
))
})?;
fs::create_dir_all(&official_plugins)
.map_err(|error| internal("无法创建官方插件备份目录").with_source(error))?;
}
let official_backup = backup_path_for(&official_plugins);
replace_dir(
&official_plugins,
&official_backup,
&extracted.official_plugins_dir,
"official plugin assets",
"官方插件文件",
)?;
if let Err(error) = protect_official_plugins(&official_plugins) {
let mut rollback = Vec::new();
@@ -36,7 +35,7 @@ pub(crate) fn replace_release_files(
restore_dir(&official_plugins, &official_backup),
);
return Err(error_with_rollback(
"failed to protect official plugin assets",
"无法设置官方插件文件权限",
error,
rollback,
));
@@ -45,18 +44,14 @@ pub(crate) fn replace_release_files(
let web_backup = backup_path_for(web_dist);
let web_replaced = match extracted.web_dist_dir {
Some(new_web) => {
if let Err(error) = replace_dir(web_dist, &web_backup, &new_web, "web assets") {
if let Err(error) = replace_dir(web_dist, &web_backup, &new_web, "管理页面文件") {
let mut rollback = Vec::new();
collect_rollback_error(
&mut rollback,
"restore official plugin assets",
restore_dir(&official_plugins, &official_backup),
);
return Err(error_with_rollback(
"failed to replace web assets",
error,
rollback,
));
return Err(error_with_rollback("无法替换管理页面文件", error, rollback));
}
true
}
@@ -80,11 +75,7 @@ pub(crate) fn replace_release_files(
"restore official plugin assets",
restore_dir(&official_plugins, &official_backup),
);
return Err(error_with_rollback(
"failed to remove old binary backup",
error,
rollback,
));
return Err(error_with_rollback("无法移除旧的程序备份", error, rollback));
}
if let Err(error) = move_file(executable, &binary_backup) {
let mut rollback = Vec::new();
@@ -100,7 +91,7 @@ pub(crate) fn replace_release_files(
"restore official plugin assets",
restore_dir(&official_plugins, &official_backup),
);
return Err(error_with_rollback("binary backup failed", error, rollback));
return Err(error_with_rollback("无法备份程序文件", error, rollback));
}
if let Err(error) = move_file(&extracted.binary_path, executable) {
let mut rollback = Vec::new();
@@ -128,11 +119,7 @@ pub(crate) fn replace_release_files(
"restore official plugin assets",
restore_dir(&official_plugins, &official_backup),
);
return Err(error_with_rollback(
"binary replace failed",
error,
rollback,
));
return Err(error_with_rollback("无法替换程序文件", error, rollback));
}
Ok(())
}
@@ -142,10 +129,10 @@ pub(crate) fn rollback_release(config: &SystemUpdateConfig) -> Result<(), Operat
let executable = config.executable_path()?;
let binary_backup = backup_path_for(&executable);
if !binary_backup.exists() {
return Err(conflict("no binary backup found for rollback"));
return Err(conflict("没有可用于回滚的程序备份"));
}
swap_file(&executable, &binary_backup)
.map_err(|error| internal(format!("binary rollback failed: {error}")))?;
.map_err(|error| internal("程序文件回滚失败").with_source(error))?;
let web_backup = backup_path_for(web_dist);
if web_backup.exists()
@@ -157,7 +144,7 @@ pub(crate) fn rollback_release(config: &SystemUpdateConfig) -> Result<(), Operat
"restore binary after web rollback failure",
swap_file(&executable, &binary_backup),
);
return Err(error_with_rollback("web rollback failed", error, rollback));
return Err(error_with_rollback("管理页面文件回滚失败", error, rollback));
}
let official_plugins = config.official_plugins_dir()?;
let official_backup = backup_path_for(&official_plugins);
@@ -177,11 +164,7 @@ pub(crate) fn rollback_release(config: &SystemUpdateConfig) -> Result<(), Operat
"restore binary after official plugin rollback failure",
swap_file(&executable, &binary_backup),
);
return Err(error_with_rollback(
"official plugin rollback failed",
error,
rollback,
));
return Err(error_with_rollback("官方插件文件回滚失败", error, rollback));
}
Ok(())
}
@@ -199,7 +182,7 @@ fn official_plugins_dir(executable: &Path) -> Result<PathBuf, OperationError> {
.parent()
.filter(|path| !path.as_os_str().is_empty())
.map(|path| path.join("plugins").join("official"))
.ok_or_else(|| internal("failed to resolve official plugin release directory"))
.ok_or_else(|| internal("无法确定官方插件安装目录"))
}
fn replace_dir(
@@ -210,11 +193,11 @@ fn replace_dir(
) -> Result<(), OperationError> {
if backup.exists() {
remove_dir_all(backup)
.map_err(|error| internal(format!("failed to remove old {label} backup: {error}")))?;
.map_err(|error| internal(format!("无法移除旧的{label}备份")).with_source(error))?;
}
if current.exists() {
move_dir(current, backup)
.map_err(|error| internal(format!("failed to backup {label}: {error}")))?;
.map_err(|error| internal(format!("无法备份{label}")).with_source(error))?;
}
if let Err(error) = move_dir(replacement, current) {
let mut rollback = Vec::new();
@@ -225,11 +208,7 @@ fn replace_dir(
restore_dir(current, backup),
);
}
return Err(error_with_rollback(
"failed to replace directory contents",
error,
rollback,
));
return Err(error_with_rollback("无法替换安装目录内容", error, rollback));
}
Ok(())
}
@@ -391,14 +370,13 @@ fn collect_rollback_error(errors: &mut Vec<String>, action: &'static str, result
fn error_with_rollback(
context: &'static str,
error: impl fmt::Display,
error: impl Error + Send + Sync + 'static,
rollback_errors: Vec<String>,
) -> OperationError {
if rollback_errors.is_empty() {
return internal(format!("{context}: {error}"));
return internal(context).with_source(error);
}
internal(format!(
"{context}: {error}; rollback failed: {}",
rollback_errors.join("; ")
))
internal(format!("{context},且无法恢复原文件")).with_source(
ErrorSource::new(error).with_cleanup(io::Error::other(rollback_errors.join("; "))),
)
}
@@ -2,6 +2,76 @@
use super::*;
#[tokio::test]
async fn download_failure_should_not_publish_download_url_in_events_or_status() {
for diagnostics_result in [None, Some(false), Some(true)] {
let server = MockServer::start().await;
let fixture = Fixture::new();
fixture
.mount_custom_release(
&server,
&format!("{}/archive?token=private-download-sentinel", server.uri()),
None,
)
.await;
Mock::given(method("GET"))
.and(path("/archive"))
.respond_with(
ResponseTemplate::new(302)
.insert_header("location", "https://untrusted.example/archive"),
)
.mount(&server)
.await;
let service = fixture.service(&server);
let diagnostics = Arc::new(RecordingDiagnostics {
reject: diagnostics_result == Some(true),
..RecordingDiagnostics::default()
});
if diagnostics_result.is_some() {
service.set_diagnostics(diagnostics.clone());
}
let events = service.update_events();
let status = complete_update(&service, TARGET_VERSION).await;
assert_eq!(status.operation.status, SystemOperationStatus::Failed);
assert_eq!(status.operation.error.as_deref(), Some("更新包下载失败"));
let events = events.collect::<Vec<_>>().await;
let terminal = events.last().expect("terminal event");
assert!(terminal.terminal);
assert_eq!(
Some(terminal.message.as_str()),
status.operation.error.as_deref()
);
assert!(
events
.iter()
.all(|event| !event.message.contains("private-download-sentinel"))
);
assert!(
!fs::read_to_string(fixture.state())
.expect("persisted state")
.contains("private-download-sentinel")
);
if diagnostics_result.is_some() {
let failures = diagnostics.failures.lock().expect("diagnostic failures");
assert_eq!(failures.len(), 1);
let failure = &failures[0];
assert_eq!(failure.operation, "install");
assert_eq!(failure.correlation_id, status.operation.operation_id);
let details = failure.details.as_ref().expect("download failure details");
assert!(!details.as_str().contains("private-download-sentinel"));
assert!(!details.as_str().contains(&server.uri()));
let details: serde_json::Value =
serde_json::from_str(details.as_str()).expect("details JSON");
assert_eq!(details["redacted"], true);
assert!(
details["causes"]["messages"]
.as_array()
.is_some_and(|messages| !messages.is_empty())
);
}
}
}
#[tokio::test]
async fn update_events_should_close_after_terminal_update_log() {
let fixture = Fixture::new();
@@ -144,6 +214,11 @@ async fn terminal_event_should_only_be_visible_after_status_is_persisted() {
let status = service.update_status().await.expect("terminal status");
assert_eq!(status.operation.status, SystemOperationStatus::Failed);
assert!(status.operation.finished_at.is_some());
assert_eq!(event.message, "更新包校验失败,请重新下载");
assert_eq!(
status.operation.error.as_deref(),
Some(event.message.as_str())
);
return;
}
}
@@ -45,6 +45,32 @@ const OLD_RELEASE_MANIFEST: &str = r#"{"gateway_version":"1.0.0"}"#;
const TARGET_VERSION: &str = "1.9.9";
const CROSS_MAJOR_VERSION: &str = "2.0.0";
#[derive(Default)]
struct RecordingDiagnostics {
failures: std::sync::Mutex<Vec<gateway_core::diagnostics::OperationalFailure>>,
reject: bool,
}
#[async_trait::async_trait]
impl gateway_core::diagnostics::OperationalDiagnostics for RecordingDiagnostics {
async fn record_failure(
&self,
failure: gateway_core::diagnostics::OperationalFailure,
) -> Result<(), gateway_core::error::StoreError> {
self.failures
.lock()
.expect("diagnostic failures")
.push(failure);
if self.reject {
Err(gateway_core::error::StoreError::new(
gateway_core::error::StoreErrorKind::Unavailable,
))
} else {
Ok(())
}
}
}
struct AllowingUpdatePreflight;
#[async_trait::async_trait]
impl gateway_admin::ports::system::SystemRestartPreflight for AllowingUpdatePreflight {
@@ -2,6 +2,32 @@
use super::*;
#[tokio::test]
async fn update_detail_should_record_decode_failure_while_returning_safe_warning() {
let server = MockServer::start().await;
Mock::given(method("GET"))
.and(path("/repos/owner/repository/releases"))
.respond_with(ResponseTemplate::new(200).set_body_string("not release JSON"))
.mount(&server)
.await;
let fixture = Fixture::new();
let service = fixture.service(&server);
let diagnostics = Arc::new(RecordingDiagnostics::default());
service.set_diagnostics(diagnostics.clone());
let detail = service
.update_detail(true, None)
.await
.expect("failure detail");
assert_eq!(detail.warning.as_deref(), Some("GitHub 发行信息格式无效"));
let failures = diagnostics.failures.lock().expect("diagnostic failures");
assert_eq!(failures.len(), 1);
assert_eq!(failures[0].operation, "check_release");
let details = failures[0].details.as_ref().expect("decoding details");
assert!(details.as_str().contains("expected ident"));
assert!(!details.as_str().contains(&server.uri()));
}
#[tokio::test]
async fn update_detail_should_report_refresh_failure_and_clear_previous_update() {
let server = MockServer::start().await;
@@ -18,7 +44,10 @@ async fn update_detail_should_report_refresh_failure_and_clear_previous_update()
.await
.expect("failure detail");
assert!(!detail.has_update);
assert!(detail.warning.is_some());
assert_eq!(
detail.warning.as_deref(),
Some("GitHub 发行查询失败(HTTP 404)")
);
assert!(!detail.cached);
assert_eq!(detail.latest_version, "1.0.0");
assert!(detail.notes.is_none());
@@ -2,6 +2,27 @@
use super::*;
#[tokio::test]
async fn invalid_update_state_should_keep_raw_details_out_of_public_error() {
use std::error::Error as _;
let fixture = Fixture::new();
fs::write(
fixture.state(),
r#"{"operation":{"status":"private-state-sentinel"}}"#,
)
.expect("invalid state");
let service = fixture.service_for_url("http://127.0.0.1:1/repos");
let error = service.update_status().await.expect_err("invalid state");
assert_eq!(error.kind(), SystemOperationErrorKind::Internal);
assert_eq!(error.message(), "系统更新状态文件损坏");
assert!(!format!("{error} {error:?}").contains("private-state-sentinel"));
let source = error.source().expect("state decoding error");
assert!(source.is::<serde_json::Error>());
assert!(source.to_string().contains("private-state-sentinel"));
}
#[tokio::test]
async fn update_status_should_reconcile_manual_deployment_without_reusing_legacy_success() {
let fixture = Fixture::new();
@@ -86,7 +86,7 @@ pub(super) async fn invoke(
() = context.cancellation().cancelled() => return Err(MiddlewareError::Fault),
() = context.deadline().wait() => return Err(gateway_core::error::GatewayError::new(
gateway_core::error::GatewayErrorKind::Timeout,
"request deadline elapsed",
"Request deadline elapsed.",
).into()),
reply = ports.session.call(
HANDLE_METHOD,
@@ -137,7 +137,7 @@ pub(super) async fn invoke(
() = context.cancellation().cancelled() => return Err(MiddlewareError::Fault),
() = context.deadline().wait() => return Err(gateway_core::error::GatewayError::new(
gateway_core::error::GatewayErrorKind::Timeout,
"request deadline elapsed",
"Request deadline elapsed.",
).into()),
result = invocation_ports.session.call_stream(
HANDLE_METHOD,
@@ -154,7 +154,7 @@ pub(crate) fn rpc_middleware(error: crate::RpcError) -> MiddlewareError {
return MiddlewareError::Gateway(
GatewayError::new(
GatewayErrorKind::MiddlewareCapacityUnavailable,
"Request middleware is temporarily busy",
"Request middleware is temporarily busy.",
)
.with_source(gateway_core::error::ErrorSource::new(error)),
);
@@ -170,11 +170,11 @@ impl PgClientBudgetStore {
)
.bind(key_id.as_str()).bind(ids).fetch_optional(&self.pool).await
.map_err(|source| unavailable().with_source(source))?
.ok_or_else(|| GatewayError::new(GatewayErrorKind::Unauthorized, "client API key no longer exists"))?;
.ok_or_else(|| GatewayError::new(GatewayErrorKind::Unauthorized, "Client API key no longer exists."))?;
if !row.get::<bool, _>("enabled") {
return Err(GatewayError::new(
GatewayErrorKind::PolicyDenied,
"client API key is disabled",
"Client API key is disabled.",
));
}
let parse = |field: &str| -> Result<Decimal, GatewayError> {
@@ -238,21 +238,22 @@ impl PgClientBudgetStore {
let daily_exceeded = limits.daily_usd != Decimal::ZERO && daily >= limits.daily_usd;
let weekly_exceeded = limits.weekly_usd != Decimal::ZERO && weekly >= limits.weekly_usd;
if daily_exceeded || weekly_exceeded {
let reset = if weekly_exceeded {
weekly_end
let (reset, code, message) = if weekly_exceeded {
(
weekly_end,
"key_weekly_budget_exceeded",
"Weekly spending limit reached.",
)
} else {
daily_end
(
daily_end,
"key_daily_budget_exceeded",
"Daily spending limit reached.",
)
};
return Err(GatewayError::new(
GatewayErrorKind::RateLimited,
"client API key budget is exhausted",
)
.with_client_code(if weekly_exceeded {
"key_weekly_budget_exceeded"
} else {
"key_daily_budget_exceeded"
})
.with_retry_after((reset - now).to_std().unwrap_or(Duration::from_secs(1))));
return Err(GatewayError::new(GatewayErrorKind::RateLimited, message)
.with_client_code(code)
.with_retry_after((reset - now).to_std().unwrap_or(Duration::from_secs(1))));
}
}
// 首次使用或窗口到期才写入;与重置、结算保持相同锁序
@@ -270,7 +271,7 @@ impl PgClientBudgetStore {
.ok_or_else(|| {
GatewayError::new(
GatewayErrorKind::Unauthorized,
"client API key no longer exists",
"Client API key no longer exists.",
)
})?;
advance_windows(&mut tx, key_id.as_str(), now, now, self.timezone)
@@ -478,7 +479,7 @@ pub(super) async fn load_client_key_budgets(
pub(super) fn unavailable() -> GatewayError {
GatewayError::new(
GatewayErrorKind::ProviderInfrastructureUnavailable,
"client budget service is temporarily unavailable",
"Client budget service is temporarily unavailable.",
)
.with_client_code("key_budget_unavailable")
}
@@ -45,7 +45,9 @@ const CLOUDFLARE_CHALLENGE_BACKOFF: [Duration; 4] = [
Duration::from_secs(120),
];
const CLOUDFLARE_PATH_BLOCK_THRESHOLD: u32 = 3;
const SESSION_AFFINITY_TIMEOUT: Duration = Duration::from_millis(100);
// 绑定失败会阻止发送,预算容纳短暂调度抖动;可丢失的策略排除记录保持独立预算
const SESSION_AFFINITY_TIMEOUT: Duration = Duration::from_millis(500);
const CYBER_POLICY_TIMEOUT: Duration = Duration::from_millis(100);
const CYBER_POLICY_SESSION_TTL: Duration = Duration::from_secs(60 * 60);
const MAX_ACCOUNT_SNAPSHOT_RETRIES: u32 = 3;
const COOLDOWN_READ_CONCURRENCY: usize = 128;
@@ -1141,7 +1143,7 @@ impl CodexCredentialSelector {
) -> Option<CodexCyberPolicyScope> {
let key = key?.clone();
let state = match tokio::time::timeout(
SESSION_AFFINITY_TIMEOUT,
CYBER_POLICY_TIMEOUT,
self.session_exclusions.load(&self.provider_kind, &key),
)
.await
@@ -1153,7 +1155,7 @@ impl CodexCredentialSelector {
}
Err(_) => {
tracing::warn!(
timeout_ms = SESSION_AFFINITY_TIMEOUT.as_millis(),
timeout_ms = CYBER_POLICY_TIMEOUT.as_millis(),
"OpenAI cyber policy state read timed out"
);
None
@@ -1171,7 +1173,7 @@ impl CodexCredentialSelector {
return;
};
match tokio::time::timeout(
SESSION_AFFINITY_TIMEOUT,
CYBER_POLICY_TIMEOUT,
self.session_exclusions.record_failure(
&self.provider_kind,
&scope.key,
@@ -1192,7 +1194,7 @@ impl CodexCredentialSelector {
Err(_) => {
tracing::warn!(
account_id = %account.id(),
timeout_ms = SESSION_AFFINITY_TIMEOUT.as_millis(),
timeout_ms = CYBER_POLICY_TIMEOUT.as_millis(),
"OpenAI cyber policy exclusion write timed out"
);
}
@@ -1207,7 +1209,7 @@ impl CodexCredentialSelector {
return;
};
match tokio::time::timeout(
SESSION_AFFINITY_TIMEOUT,
CYBER_POLICY_TIMEOUT,
self.session_exclusions
.clear(&self.provider_kind, &scope.key, state.revision()),
)
@@ -1219,7 +1221,7 @@ impl CodexCredentialSelector {
}
Err(_) => {
tracing::warn!(
timeout_ms = SESSION_AFFINITY_TIMEOUT.as_millis(),
timeout_ms = CYBER_POLICY_TIMEOUT.as_millis(),
"OpenAI cyber policy exclusion clear timed out"
);
}
@@ -794,7 +794,14 @@ pub(super) fn map_client_error(
ProviderErrorKind::InvalidRequest,
UpstreamSendState::NotSent,
)
.with_retry_prohibited(),
.with_retry_prohibited()
.with_client_visible_upstream_error(
ClientVisibleUpstreamError::new(
"A gateway privacy rule could not process this request.",
Some("privacy_policy_rejected".to_owned()),
Some("invalid_request_error".to_owned()),
),
),
)
}
CodexClientError::ConnectionBudgetExhausted => MappedProviderFailure::plain(
@@ -971,7 +978,7 @@ pub(super) fn map_client_error(
}
/// 在消费 transport 错误前提取可持久化事实,不能使用可能携带 URL/凭据的 Display
fn client_diagnostic(error: &CodexClientError) -> Option<ProviderDiagnostic> {
pub(super) fn client_diagnostic(error: &CodexClientError) -> Option<ProviderDiagnostic> {
let (stage, code, message) = match error {
CodexClientError::ConnectionBudgetExhausted => (
"connect",
@@ -1300,9 +1307,13 @@ pub(super) fn websocket_client_visible_error(
.map_or_else(
|| {
if message_too_big {
"upstream websocket message too big".to_owned()
"The upstream WebSocket message is too large.".to_owned()
} else if let Some(code) = close.code() {
format!(
"The upstream WebSocket closed before the response completed (code {code})."
)
} else {
close.to_string()
"The upstream WebSocket closed before the response completed.".to_owned()
}
},
str::to_owned,
@@ -69,10 +69,10 @@ impl LiveClaimError {
fn message(self) -> &'static str {
match self {
Self::Missing => "codex live call not found",
Self::Busy => "codex live call already has a sideband connection",
Self::OwnerMismatch => "codex live call is outside the current API key scope",
Self::Invalid => "invalid codex live call id",
Self::Missing => "The voice call was not found or has expired.",
Self::Busy => "The voice call already has an active event connection.",
Self::OwnerMismatch => "This API key cannot access the voice call.",
Self::Invalid => "The voice call ID is invalid.",
}
}
}
@@ -562,23 +562,29 @@ impl CodexLiveGateway {
.store()
.get_account(account_id)
.await
.map_err(|_| credential_unavailable("codex live pinned account is unavailable"))?
.ok_or_else(|| credential_unavailable("codex live pinned account is unavailable"))?;
.map_err(|_| credential_unavailable("The account for this voice call is unavailable."))?
.ok_or_else(|| {
credential_unavailable("The account for this voice call is unavailable.")
})?;
if account.authentication_kind() != CODEX_AUTHENTICATION_KIND_OAUTH {
return Err(LiveGatewayError::new(
LiveGatewayErrorKind::Unsupported,
"codex live requires an OAuth codex account",
"Voice calls require an OpenAI OAuth account.",
));
}
let credential = self
.repository
.load_runtime_credential(&account)
.await
.map_err(|_| credential_unavailable("codex live pinned credential is unavailable"))?;
.map_err(|_| {
credential_unavailable("The credentials for this voice call are unavailable.")
})?;
let authorization = credential
.authentication
.authorization_header()
.map_err(|_| credential_unavailable("codex live pinned credential is unusable"))?;
.map_err(|_| {
credential_unavailable("The credentials for this voice call are invalid.")
})?;
Ok((account, authorization, credential.installation_id))
}
@@ -608,9 +614,9 @@ fn map_sideband_dial_error(error: CodexWebSocketExchangeError) -> LiveGatewayErr
)
.with_upstream(upstream.status_code, body)
}
other => LiveGatewayError::new(
LiveGatewayErrorKind::UpstreamUnavailable,
format!("codex live sideband upstream unavailable: {other}"),
other => local_live_error(
CodexClientError::WebSocket(other),
"The voice connection could not be established.",
),
}
}
@@ -637,13 +643,23 @@ fn map_live_http_error(error: CodexClientError) -> LiveGatewayError {
),
)
.with_upstream(status.as_u16(), Some(Bytes::from(body))),
other => LiveGatewayError::new(
LiveGatewayErrorKind::UpstreamUnavailable,
format!("codex live upstream call failed: {other}"),
),
other => local_live_error(other, "The voice call request could not be completed."),
}
}
fn local_live_error(error: CodexClientError, message: &'static str) -> LiveGatewayError {
// 本地传输异常可能包含 URL 或代理上下文;客户端提示与现有安全诊断各自保留
if let Some(diagnostic) = super::failure::client_diagnostic(&error) {
tracing::warn!(
stage = diagnostic.stage(),
code = diagnostic.code(),
detail = diagnostic.as_str(),
"Codex Live request failed"
);
}
LiveGatewayError::new(LiveGatewayErrorKind::UpstreamUnavailable, message)
}
impl LiveGateway for CodexLiveGateway {
fn open_sideband<'a>(
&'a self,
@@ -667,7 +683,7 @@ impl LiveGateway for CodexLiveGateway {
if !account.enabled() {
return Err(LiveGatewayError::new(
LiveGatewayErrorKind::OwnerMismatch,
"codex live pinned account is disabled",
"The account for this voice call is disabled.",
));
}
let endpoint = Self::sideband_endpoint(request.style, request.call_id);
@@ -732,7 +748,7 @@ impl LiveGateway for CodexLiveGateway {
.map_err(|_| {
LiveGatewayError::new(
LiveGatewayErrorKind::CredentialUnavailable,
"codex live hangup account client is unavailable",
"The account connection for this voice call is unavailable.",
)
})?;
let request_id = Uuid::new_v4().to_string();
@@ -789,9 +789,16 @@ fn selection_failure(error: &CredentialSelectionError) -> ProviderError {
ProviderDiagnostic::new(error.to_string()).with_classification("account_selection", code)
});
let mapped = match error {
CredentialSelectionError::Cancelled => provider_error(ProviderErrorKind::Cancelled, UpstreamSendState::NotSent).with_retry_prohibited(),
CredentialSelectionError::ContinuationOwnerChanged => continuation_replay_required_error("scope_unavailable"),
CredentialSelectionError::SessionBound(error) => selection_failure(error).with_retry_prohibited(),
CredentialSelectionError::Cancelled => {
provider_error(ProviderErrorKind::Cancelled, UpstreamSendState::NotSent)
.with_retry_prohibited()
}
CredentialSelectionError::ContinuationOwnerChanged => {
continuation_replay_required_error("scope_unavailable")
}
CredentialSelectionError::SessionBound(error) => {
selection_failure(error).with_retry_prohibited()
}
CredentialSelectionError::QueueRejected(error) => {
provider_error(error.provider_kind(), UpstreamSendState::NotSent)
}
@@ -811,7 +818,7 @@ fn selection_failure(error: &CredentialSelectionError) -> ProviderError {
)
.with_retry_prohibited()
.with_client_visible_upstream_error(ClientVisibleUpstreamError::new(
"No account is available for this session because of an earlier upstream cyber_policy rejection. Do not repeatedly retry this session. This does not indicate an account ban or a service-wide outage.",
"No account is available for this session after an upstream cyber policy rejection.",
Some("cyber_policy".to_owned()),
Some("invalid_request_error".to_owned()),
)),
@@ -824,7 +831,7 @@ fn selection_failure(error: &CredentialSelectionError) -> ProviderError {
UpstreamSendState::NotSent,
)
.with_client_visible_upstream_error(ClientVisibleUpstreamError::new(
"All eligible accounts have exhausted their quota. Retry after quota resets or add an available account.",
"All eligible accounts have exhausted their quota.",
Some("usage_limit_reached".to_owned()),
Some("usage_limit_reached".to_owned()),
)),
@@ -844,14 +851,15 @@ fn selection_failure(error: &CredentialSelectionError) -> ProviderError {
ProviderErrorKind::ProviderInfrastructureUnavailable,
UpstreamSendState::NotSent,
),
CredentialSelectionError::PolicyRejected | CredentialSelectionError::PolicyFiltered => provider_error(
ProviderErrorKind::RequestPolicyDenied,
UpstreamSendState::NotSent,
),
CredentialSelectionError::PolicyUnavailable => provider_error(
ProviderErrorKind::Unavailable,
UpstreamSendState::NotSent,
),
CredentialSelectionError::PolicyRejected | CredentialSelectionError::PolicyFiltered => {
provider_error(
ProviderErrorKind::RequestPolicyDenied,
UpstreamSendState::NotSent,
)
}
CredentialSelectionError::PolicyUnavailable => {
provider_error(ProviderErrorKind::Unavailable, UpstreamSendState::NotSent)
}
};
match diagnostic {
Some(diagnostic) => mapped.with_diagnostic(diagnostic),
@@ -524,7 +524,8 @@ impl ResponsesSseFailure {
pub(crate) fn from_raw_event(event: &str, raw_body: &str, value: &Value) -> Self {
Self {
event: event.to_string(),
message: failure_message(value).unwrap_or_else(|| "Codex upstream SSE failed".into()),
message: failure_message(value)
.unwrap_or_else(|| "The upstream response stream failed.".into()),
upstream_code: failure_code(value),
upstream_message: failure_message(value),
upstream_type: failure_type(value),
@@ -145,7 +145,7 @@ async fn account_client_preparation_keeps_ca_read_cause_without_exposing_path()
assert!(diagnostic.as_str().contains("OS cause:"));
assert!(!diagnostic.as_str().contains("PRIVATE_"));
let gateway = gateway_core::error::GatewayError::from_provider(&snapshot);
assert_eq!(gateway.safe_message(), "upstream service is unavailable");
assert_eq!(gateway.safe_message(), "Upstream service is unavailable.");
assert_eq!(gateway.diagnostic(), Some(diagnostic));
}
@@ -217,6 +217,18 @@ async fn privacy_rejection_is_not_sent_and_cannot_retry_or_rotate() {
assert_eq!(error.kind(), ProviderErrorKind::InvalidRequest);
assert_eq!(error.send_state(), UpstreamSendState::NotSent);
assert!(error.retry_is_prohibited());
let visible = error.client_visible_upstream_error().unwrap();
assert_eq!(visible.code(), Some("privacy_policy_rejected"));
assert_eq!(visible.error_type(), Some("invalid_request_error"));
assert_eq!(
visible.message(),
"A gateway privacy rule could not process this request."
);
assert!(!visible.message().contains("$.input"));
assert_eq!(
error.diagnostic().unwrap().code(),
Some("privacy_policy_rejected")
);
assert!(server.received_requests().await.unwrap().is_empty());
}
@@ -2,6 +2,71 @@
use super::*;
#[tokio::test]
async fn session_affinity_storage_tolerates_delays_but_rejects_expired_requests_before_sending() {
for (delay_ms, should_succeed) in [(250, true), (750, false)] {
let store = Arc::new(MemoryAccountStore::default());
create_account(&store, "acct_subagent_a").await;
let affinity = Arc::new(MemorySessionAffinity::with_operation_delay(
Duration::from_millis(delay_ms),
));
let server = MockServer::start().await;
Mock::given(method("POST"))
.and(path("/codex/responses"))
.respond_with(
ResponseTemplate::new(200).set_body_raw(
format!("event: response.created\ndata: {{\"type\":\"response.created\",\"response\":{{\"id\":\"resp_scope_capture\",\"status\":\"in_progress\"}}}}\n\n{CAPTURE_COMPLETED_SSE}"),
"text/event-stream",
),
)
.expect(if should_succeed { 1 } else { 0 })
.mount(&server)
.await;
let provider = provider_with_affinity_and_base_url(&store, affinity.clone(), server.uri());
// 只推进存储等待的虚拟时间,网络交付恢复真实时钟,避免依赖宿主调度速度
tokio::time::pause();
let result = provider
.execute(
planned_request("openai", turn_request("delayed-session", "delayed-turn")),
context("req_affinity_delay", CancellationToken::new()),
)
.await;
tokio::time::resume();
if should_succeed {
let mut stream = result.expect("delayed binding and turn association must succeed");
assert_eq!(
stream.metadata().provider_account_id().as_str(),
"acct_subagent_a"
);
assert_eq!(affinity.binding_count(), 1);
assert_eq!(affinity.alias_ttls().len(), 1);
let mut completed = false;
while let Some(event) = stream.next().await {
completed |= event
.unwrap()
.canonical_facts()
.iter()
.any(|event| matches!(event, GatewayEvent::Completed(_)));
}
assert!(completed, "admitted request must complete through upstream");
} else {
let error = result
.err()
.expect("expired storage wait must reject the request");
assert_eq!(
error.kind(),
ProviderErrorKind::ProviderInfrastructureUnavailable
);
assert_eq!(error.send_state(), UpstreamSendState::NotSent);
assert!(error.retry_is_prohibited());
assert_eq!(affinity.binding_count(), 0);
}
server.verify().await;
}
}
#[tokio::test]
async fn cyber_policy_session_exclusion_has_actionable_non_retryable_error() {
let store = Arc::new(MemoryAccountStore::default());
@@ -63,7 +128,10 @@ async fn cyber_policy_session_exclusion_has_actionable_non_retryable_error() {
.client_visible_upstream_error()
.expect("actionable client message");
assert_eq!(visible.code(), Some("cyber_policy"));
assert!(visible.message().contains("Do not repeatedly retry"));
assert_eq!(
visible.message(),
"No account is available for this session after an upstream cyber policy rejection."
);
assert_eq!(server.received_requests().await.unwrap().len(), 1);
// 可见但不属于固定账号范围的候选不能掩盖会话限制
create_account(&store, "acct_subagent_b").await;
@@ -310,6 +310,74 @@ async fn live_sideband_rejects_disabled_account_even_before_scope_refresh() {
}
}
#[tokio::test]
async fn live_proxy_failures_return_actionable_errors_and_release_the_call_claim() {
use gateway_core::{account::OutboundProxy, live::LiveHangupRequest};
use tokio::{io::AsyncWriteExt, net::TcpListener};
let (provider, store, _upstream) = bootstrap().await;
let proxy = TcpListener::bind("127.0.0.1:0").await.unwrap();
store.set_egress(
ACCOUNT,
Some(OutboundProxy::parse(&format!("http://{}", proxy.local_addr().unwrap())).unwrap()),
None,
);
let proxy_task = tokio::spawn(async move {
for _ in 0..3 {
let (mut socket, _) = proxy.accept().await.unwrap();
let head = read_live_head(&mut socket).await;
assert!(head.starts_with("CONNECT api.openai.com:443 "));
socket
.write_all(b"HTTP/1.1 407 Proxy Authentication Required\r\nContent-Length: 0\r\nConnection: close\r\n\r\n")
.await
.unwrap();
}
});
let gateway = provider.live_gateway().unwrap();
let key = ClientApiKeyId::new("key_openai_contract").unwrap();
let allowed = scope(AccountModelAccess::default());
// 拨号失败释放 claim;第二次仍须到达代理,不能被本地 busy 拦住
for _ in 0..2 {
let error = gateway
.open_sideband(LiveSidebandRequest {
call_id: CALL,
client_api_key_id: &key,
account_scope: &allowed,
style: LiveSidebandStyle::Live,
protocol_headers: Vec::new(),
subprotocols: Vec::new(),
})
.await
.unwrap_err();
assert_eq!(error.kind(), LiveGatewayErrorKind::UpstreamUnavailable);
assert_eq!(error.status(), 503);
assert_eq!(
error.message(),
"The voice connection could not be established."
);
assert!(!error.message().contains("407"));
assert!(error.body().is_none());
}
let error = gateway
.hangup(LiveHangupRequest {
call_id: CALL,
client_api_key_id: &key,
content_type: None,
body: Bytes::new(),
protocol_headers: Vec::new(),
})
.await
.unwrap_err();
assert_eq!(error.status(), 503);
assert_eq!(
error.message(),
"The voice call request could not be completed."
);
assert!(!error.message().contains("api.openai.com"));
assert!(error.body().is_none());
proxy_task.await.unwrap();
}
#[tokio::test]
async fn live_bootstrap_rejects_missing_planned_model_before_upstream_send() {
let store = Arc::new(MemoryAccountStore::default());
@@ -785,6 +785,7 @@ impl ProviderLeasePort for TestLeaseCoordinator {
#[derive(Default)]
pub(crate) struct MemorySessionAffinity {
operation_delay: Duration,
initial_claim_barrier: Option<Arc<tokio::sync::Barrier>>,
aliases: Mutex<BTreeMap<(String, String), gateway_core::provider_ports::ProviderSessionAlias>>,
bindings:
@@ -795,6 +796,19 @@ pub(crate) struct MemorySessionAffinity {
}
impl MemorySessionAffinity {
pub(crate) fn with_operation_delay(operation_delay: Duration) -> Self {
Self {
operation_delay,
..Self::default()
}
}
async fn delay_operation(&self) {
if !self.operation_delay.is_zero() {
tokio::time::sleep(self.operation_delay).await;
}
}
pub(crate) fn with_initial_claim_barrier(participants: usize) -> Self {
Self {
initial_claim_barrier: Some(Arc::new(tokio::sync::Barrier::new(participants))),
@@ -865,6 +879,7 @@ impl ProviderSessionAffinityPort for MemorySessionAffinity {
Result<Option<gateway_core::provider_ports::ProviderSessionBinding>, ProviderStoreError>,
> {
Box::pin(async move {
self.delay_operation().await;
self.lookups
.lock()
.expect("lookups")
@@ -893,6 +908,7 @@ impl ProviderSessionAffinityPort for MemorySessionAffinity {
Result<Option<gateway_core::provider_ports::ProviderSessionBinding>, ProviderStoreError>,
> {
Box::pin(async move {
self.delay_operation().await;
// 让并发首请求都读到空绑定,再验证发送前的原子认领冲突
if expected.is_none()
&& let Some(barrier) = &self.initial_claim_barrier
@@ -931,6 +947,7 @@ impl ProviderSessionAffinityPort for MemorySessionAffinity {
Result<Option<gateway_core::provider_ports::ProviderSessionAlias>, ProviderStoreError>,
> {
Box::pin(async move {
self.delay_operation().await;
Ok(self
.aliases
.lock()
@@ -950,6 +967,7 @@ impl ProviderSessionAffinityPort for MemorySessionAffinity {
ttl: Duration,
) -> BoxFuture<'a, Result<bool, ProviderStoreError>> {
Box::pin(async move {
self.delay_operation().await;
let mut aliases = self.aliases.lock().unwrap();
let current = aliases
.entry((
@@ -434,19 +434,19 @@ fn selection_failure(error: &GrokSessionSelectorError) -> ProviderError {
GrokSessionSelectorError::CapacityUnavailable { retry_after } => (
ProviderErrorKind::AccountCapacityUnavailable,
*retry_after,
"account is at its concurrency limit".to_owned(),
"The available accounts are busy.".to_owned(),
"account_capacity_busy",
),
GrokSessionSelectorError::NoEligibleSession => (
ProviderErrorKind::NoEligibleAccount,
None,
"no account is eligible for the requested model".to_owned(),
"No account is available for the requested model.".to_owned(),
"no_eligible_account",
),
GrokSessionSelectorError::Unavailable(_) => (
ProviderErrorKind::ProviderInfrastructureUnavailable,
None,
"account scheduling state is temporarily unreadable".to_owned(),
"Account selection is temporarily unavailable.".to_owned(),
"account_selector_unavailable",
),
GrokSessionSelectorError::PolicyRejected => {
@@ -489,20 +489,20 @@ fn selection_failure(error: &GrokSessionSelectorError) -> ProviderError {
pub(super) fn cooling_down_message(retry_after: Option<Duration>) -> String {
match retry_after {
Some(retry_after) => format!(
"account is cooling down after an upstream failure; retry in {}s",
"The account is temporarily unavailable after an upstream failure; retry in {} seconds.",
retry_after.as_secs().saturating_add(1)
),
None => "account is cooling down after an upstream failure".to_owned(),
None => "The account is temporarily unavailable after an upstream failure.".to_owned(),
}
}
pub(super) fn model_cooling_down_message(retry_after: Option<Duration>) -> String {
match retry_after {
Some(retry_after) => format!(
"all eligible accounts are cooling down for this model; retry in {}s",
"All eligible accounts are temporarily unavailable for this model; retry in {} seconds.",
retry_after.as_secs().saturating_add(1)
),
None => "all eligible accounts are cooling down for this model".to_owned(),
None => "All eligible accounts are temporarily unavailable for this model.".to_owned(),
}
}
@@ -1201,7 +1201,11 @@ fn incomplete_finish_reason(response: &Value) -> FinishReason {
fn upstream_event_error(value: &Value) -> ProviderError {
let code = upstream_error_field(value, "code");
let error_type = upstream_error_field(value, "type");
// 顶层 type 是 SSE 事件名,只有错误对象内的 type 才属于上游错误事实
let error_type = value
.pointer("/error/type")
.or_else(|| value.pointer("/response/error/type"))
.and_then(Value::as_str);
let message = upstream_error_field(value, "message");
let kind = if classify_grok_quota_failure(code, error_type, message).is_some() {
ProviderErrorKind::QuotaExhausted
@@ -1229,12 +1233,7 @@ fn upstream_event_error(value: &Value) -> ProviderError {
.and_then(|value| u16::try_from(value).ok())
.filter(|value| (400..=599).contains(value)),
code: code.map(str::to_owned),
// 顶层 type 是 SSE 事件名,只有错误对象内的 type 才属于上游错误事实
error_type: value
.pointer("/error/type")
.or_else(|| value.pointer("/response/error/type"))
.and_then(Value::as_str)
.map(str::to_owned),
error_type: error_type.map(str::to_owned),
message: message.map(str::to_owned),
});
if let Some(code) = code {
@@ -317,19 +317,19 @@ impl fmt::Debug for GrokResponsesRequest {
#[derive(Debug, thiserror::Error, Clone, Copy, PartialEq, Eq)]
pub enum GrokRequestEncodeError {
/// 数据面只接受 OpenAI adapter 保留的原始 Responses object
#[error("Grok Build request is missing its OpenAI protocol payload")]
#[error("The OpenAI request payload is missing.")]
InvalidProtocolPayload,
/// Grok Build 不支持 Codex 的非生成预热语义
#[error("Grok Build does not support non-generating prewarm requests (generate=false)")]
#[error("Grok Build does not support prewarm requests (generate=false).")]
UnsupportedPrewarm,
/// JSON 序列化意外失败
#[error("Grok Build request serialization failed")]
Serialization,
/// Responses 兼容字段无法安全归一化
#[error("Grok Build request normalization failed")]
#[error("The request could not be converted to the Grok Build format.")]
InvalidRequestNormalization,
/// 请求中的具体字段无法安全转换为 Grok Build 接受的形态
#[error("Grok Build request field `{field}` could not be normalized safely")]
#[error("The request field `{field}` could not be converted to the Grok Build format.")]
InvalidRequestField { field: &'static str },
}
@@ -3316,7 +3316,7 @@ async fn selection_failures_carry_a_distinguishable_client_error_code() {
assert_eq!(transport.calls.load(Ordering::SeqCst), 0);
if expected_code == "account_cooling_down" {
assert!(
detail.message().contains("retry in 13s"),
detail.message().contains("retry in 13 seconds."),
"{}",
detail.message()
);
@@ -4178,7 +4178,7 @@ async fn provider_should_expose_safe_request_normalization_field_before_selectio
detail.error_type()
)),
Some((
"Grok Build request field `tools` could not be normalized safely",
"The request field `tools` could not be converted to the Grok Build format.",
Some("invalid_request_normalization"),
Some("invalid_request_error"),
)),
@@ -1544,36 +1544,52 @@ fn decoder_should_classify_incomplete_reasons_and_preserve_native_wire() {
}
#[test]
fn decoder_should_classify_failed_event_without_retaining_body() {
let body = concat!(
"event: response.created\n",
"data: {\"type\":\"response.created\",\"response\":{\"id\":\"resp_1\"}}\n\n",
"event: response.failed\n",
"data: {\"type\":\"response.failed\",\"error\":{\"code\":\"rate_limit_exceeded\",\"type\":\"server_error\",\"message\":\"secret\"}}\n\n",
);
let error = GrokCanonicalDecoder::new("fallback")
.push(body.as_bytes())
.expect_err("failed response must surface");
fn decoder_should_preserve_structured_failure_fields_and_hide_raw_debug() {
for (event, expected_error_type) in [
(
serde_json::json!({"type":"response.failed","error":{"code":"rate_limit_exceeded","type":"server_error","message":"secret"}}),
Some("server_error"),
),
(
serde_json::json!({"type":"response.failed","response":{"error":{"code":"rate_limit_exceeded","type":"provider_specific_error","message":"secret"}}}),
Some("provider_specific_error"),
),
(
serde_json::json!({"type":"response.failed","response":{"error":{"code":"rate_limit_exceeded","message":"secret"}}}),
None,
),
(
serde_json::json!({"type":"error","code":"rate_limit_exceeded","message":"secret"}),
None,
),
] {
let body = format!(
"event: {}\ndata: {event}\n\n",
event["type"].as_str().unwrap()
);
let error = GrokCanonicalDecoder::new("fallback")
.push(body.as_bytes())
.expect_err("failed response must surface");
assert_eq!(
error.kind(),
gateway_core::error::ProviderErrorKind::RateLimited
);
assert_eq!(
error.upstream_code().map(|code| code.as_str()),
Some("rate_limit_exceeded")
);
let visible = error
.client_visible_upstream_error()
.expect("structured upstream message is client-visible");
assert_eq!(visible.message(), "secret");
assert_eq!(visible.code(), Some("rate_limit_exceeded"));
assert_eq!(visible.error_type(), Some("server_error"));
let raw: serde_json::Value =
serde_json::from_str(error.raw_upstream_error().unwrap().as_str()).unwrap();
assert_eq!(raw["error"]["message"], "secret");
assert_eq!(raw["error"]["code"], "rate_limit_exceeded");
assert!(!format!("{error:?}").contains("secret"));
assert_eq!(
error.kind(),
gateway_core::error::ProviderErrorKind::RateLimited
);
assert_eq!(
error.upstream_code().map(|code| code.as_str()),
Some("rate_limit_exceeded")
);
let visible = error
.client_visible_upstream_error()
.expect("structured upstream message is client-visible");
assert_eq!(visible.message(), "secret");
assert_eq!(visible.code(), Some("rate_limit_exceeded"));
assert_eq!(visible.error_type(), expected_error_type);
let raw: serde_json::Value =
serde_json::from_str(error.raw_upstream_error().unwrap().as_str()).unwrap();
assert_eq!(raw, event);
assert!(!format!("{error:?}").contains("secret"));
}
}
#[test]

Some files were not shown because too many files have changed in this diff Show More