Compare commits
7 Commits
feat/B1-he
...
feat/B3-co
| Author | SHA1 | Date | |
|---|---|---|---|
|
a9d7382be8
|
|||
|
cb9e7c7c2e
|
|||
|
2604b9f134
|
|||
|
178e3092d5
|
|||
|
46befde4cd
|
|||
|
cf87e156c5
|
|||
|
79073170ec
|
3
.gitignore
vendored
3
.gitignore
vendored
@@ -1,6 +1,9 @@
|
||||
/target
|
||||
/bench/node_modules
|
||||
/bench/dist
|
||||
/helexa.ai/node_modules
|
||||
/helexa.ai/dist
|
||||
helexa.ai/.env.local
|
||||
*.swp
|
||||
*.swo
|
||||
.idea/
|
||||
|
||||
4
Cargo.lock
generated
4
Cargo.lock
generated
@@ -2082,10 +2082,14 @@ dependencies = [
|
||||
"axum",
|
||||
"chrono",
|
||||
"clap",
|
||||
"cortex-core",
|
||||
"figment",
|
||||
"reqwest",
|
||||
"serde",
|
||||
"serde_json",
|
||||
"sha2",
|
||||
"sqlx",
|
||||
"subtle",
|
||||
"thiserror 2.0.18",
|
||||
"tokio",
|
||||
"tower-http",
|
||||
|
||||
@@ -90,3 +90,18 @@ account_id = "operator"
|
||||
key_id = "infra"
|
||||
# No hard_cap → uncapped operator infra key (own fleet, own use). Still
|
||||
# metered for visibility.
|
||||
|
||||
# -- Upstream (helexa mesh) entitlements client (#57) --------------------
|
||||
# When enabled, a bearer key NOT found in [[entitlements.keys]] above is
|
||||
# validated against the helexa-upstream authority (mesh accounts), and its
|
||||
# budget is reserved/settled there. Operator-local keys (incl. the infra
|
||||
# key) never leave this process. Fail-closed: if upstream is unreachable a
|
||||
# request is refused (503 + Retry-After), never served un-authorized.
|
||||
# Disabled by default — a standalone operator runs purely local.
|
||||
[upstream]
|
||||
enabled = false
|
||||
# url = "https://upstream.helexa.ai"
|
||||
# Shared client bearer this cortex presents (maps to an operator_id
|
||||
# upstream). Override via CORTEX_UPSTREAM__BEARER in prod.
|
||||
# bearer = "replace-with-operator-client-secret"
|
||||
# timeout_secs = 5
|
||||
|
||||
@@ -22,6 +22,36 @@ pub struct GatewayConfig {
|
||||
/// setups keep working until keys are configured.
|
||||
#[serde(default)]
|
||||
pub entitlements: EntitlementsConfig,
|
||||
/// helexa-upstream client (#57). When enabled, keys not found in the
|
||||
/// local `[entitlements]` config are validated against the mesh
|
||||
/// authority, and budget is reserved/settled there. Disabled by default
|
||||
/// — a single operator runs purely local.
|
||||
#[serde(default)]
|
||||
pub upstream: UpstreamClientConfig,
|
||||
}
|
||||
|
||||
/// `[upstream]` — the helexa-upstream authority client (#57). Locally
|
||||
/// unrecognised bearer keys are resolved against `url`'s `/authz/v1` surface
|
||||
/// (mesh accounts); local keys (operator + infra) never leave the process.
|
||||
#[derive(Debug, Clone, Serialize, Deserialize, Default)]
|
||||
pub struct UpstreamClientConfig {
|
||||
/// Enable the upstream fallthrough. Off → purely local entitlements.
|
||||
#[serde(default)]
|
||||
pub enabled: bool,
|
||||
/// Base URL of helexa-upstream (e.g. "https://upstream.helexa.ai").
|
||||
#[serde(default)]
|
||||
pub url: String,
|
||||
/// Shared client bearer this cortex presents to `/authz/v1` (maps to an
|
||||
/// operator_id upstream). Sent as `Authorization: Bearer <bearer>`.
|
||||
#[serde(default)]
|
||||
pub bearer: String,
|
||||
/// Per-call timeout (seconds) to upstream.
|
||||
#[serde(default = "default_upstream_timeout")]
|
||||
pub timeout_secs: u64,
|
||||
}
|
||||
|
||||
fn default_upstream_timeout() -> u64 {
|
||||
5
|
||||
}
|
||||
|
||||
/// `[entitlements]` — the local/static [`crate::entitlements::EntitlementProvider`]
|
||||
@@ -129,6 +159,7 @@ impl Default for GatewayConfig {
|
||||
neurons: vec![],
|
||||
models_config: default_models_path(),
|
||||
entitlements: EntitlementsConfig::default(),
|
||||
upstream: UpstreamClientConfig::default(),
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
@@ -81,12 +81,19 @@ pub struct BudgetSnapshot {
|
||||
pub reserved: u64,
|
||||
}
|
||||
|
||||
/// Authentication failure — the bearer key could not be resolved. Maps to
|
||||
/// `401 invalid_api_key` (#49/#63).
|
||||
/// Authentication failure — the bearer key could not be resolved.
|
||||
#[derive(Debug, thiserror::Error)]
|
||||
pub enum AuthError {
|
||||
/// The key is genuinely unknown → `401 invalid_api_key` (#49/#63).
|
||||
#[error("invalid or unknown API key")]
|
||||
InvalidKey,
|
||||
/// The authority that could resolve the key is unreachable (e.g. the
|
||||
/// helexa-upstream client failed, #57). Fail **closed** but distinctly:
|
||||
/// a transient outage must surface as `503 service_unavailable` +
|
||||
/// `Retry-After`, never `401` — a real key must not be rejected as
|
||||
/// invalid during an upstream blip.
|
||||
#[error("entitlement authority unavailable; retry in {retry_after_secs}s")]
|
||||
Unavailable { retry_after_secs: u64 },
|
||||
}
|
||||
|
||||
/// Why a reservation was refused. Carries enough for the caller to build the
|
||||
|
||||
@@ -22,7 +22,7 @@ use axum::http::header::AUTHORIZATION;
|
||||
use axum::http::{HeaderMap, HeaderValue};
|
||||
use axum::middleware::Next;
|
||||
use axum::response::Response;
|
||||
use cortex_core::entitlements::{HEADER_ACCOUNT_ID, HEADER_KEY_ID};
|
||||
use cortex_core::entitlements::{AuthError, HEADER_ACCOUNT_ID, HEADER_KEY_ID};
|
||||
use cortex_core::error_envelope::OpenAiError;
|
||||
use std::sync::Arc;
|
||||
|
||||
@@ -83,14 +83,25 @@ pub async fn require_principal(
|
||||
req.extensions_mut().insert(principal);
|
||||
next.run(req).await
|
||||
}
|
||||
// An unrecognized key only hard-fails when auth is *required*.
|
||||
// In allow-anonymous mode (the default) we must IGNORE it and
|
||||
// serve the request unauthenticated — otherwise the placeholder
|
||||
// keys that OpenAI-compatible clients send by default (opencode,
|
||||
// Open WebUI, Agent Zero, litellm) would all break, even though
|
||||
// the operator never opted into auth. Pre-#49 the bearer was
|
||||
// never inspected at all; this preserves that for require_auth=false.
|
||||
Err(_) => {
|
||||
// The entitlement authority is unreachable (upstream client
|
||||
// blip, #57). Fail **closed but distinct**: a transient outage
|
||||
// must not reject a real key as `401 invalid_api_key` — it's a
|
||||
// retryable `503`. This holds regardless of require_auth: we
|
||||
// can't safely serve a key we couldn't authorize.
|
||||
Err(AuthError::Unavailable { retry_after_secs }) => {
|
||||
envelope_response(OpenAiError::service_unavailable(
|
||||
"entitlement authority temporarily unavailable",
|
||||
Some(retry_after_secs),
|
||||
))
|
||||
}
|
||||
// A genuinely unrecognized key only hard-fails when auth is
|
||||
// *required*. In allow-anonymous mode (the default) we IGNORE it
|
||||
// and serve unauthenticated — otherwise the placeholder keys that
|
||||
// OpenAI-compatible clients send by default (opencode, Open WebUI,
|
||||
// Agent Zero, litellm) would all break though the operator never
|
||||
// opted into auth. Pre-#49 the bearer was never inspected; this
|
||||
// preserves that for require_auth=false.
|
||||
Err(AuthError::InvalidKey) => {
|
||||
if fleet.require_auth {
|
||||
unauthorized("invalid API key")
|
||||
} else {
|
||||
|
||||
112
crates/cortex-gateway/src/entitlements_chain.rs
Normal file
112
crates/cortex-gateway/src/entitlements_chain.rs
Normal file
@@ -0,0 +1,112 @@
|
||||
//! Chained entitlement provider (#57): operator-local keys first, mesh
|
||||
//! upstream for everything else.
|
||||
//!
|
||||
//! `resolve` tries the [`LocalEntitlementProvider`] (operator + infra keys —
|
||||
//! never a network hop); only a locally-unknown key falls through to
|
||||
//! [`UpstreamEntitlementProvider`]. Because the local provider treats an
|
||||
//! unconfigured principal as uncapped, reserve/settle/release/snapshot must
|
||||
//! **not** blindly hit local — they dispatch to whichever backend resolved
|
||||
//! that account, remembered in a map keyed by `account_id` (populated at
|
||||
//! resolve time).
|
||||
|
||||
use crate::entitlements_local::LocalEntitlementProvider;
|
||||
use crate::entitlements_upstream::UpstreamEntitlementProvider;
|
||||
use async_trait::async_trait;
|
||||
use cortex_core::entitlements::{
|
||||
AuthError, BudgetError, BudgetSnapshot, EntitlementProvider, Principal, Reservation,
|
||||
};
|
||||
use std::collections::HashMap;
|
||||
use tokio::sync::RwLock;
|
||||
|
||||
#[derive(Clone, Copy, Debug, PartialEq, Eq)]
|
||||
enum Backend {
|
||||
Local,
|
||||
Upstream,
|
||||
}
|
||||
|
||||
pub struct ChainedEntitlementProvider {
|
||||
local: LocalEntitlementProvider,
|
||||
upstream: UpstreamEntitlementProvider,
|
||||
/// account_id → which backend owns it, learned at resolve time.
|
||||
backends: RwLock<HashMap<String, Backend>>,
|
||||
}
|
||||
|
||||
impl ChainedEntitlementProvider {
|
||||
pub fn new(local: LocalEntitlementProvider, upstream: UpstreamEntitlementProvider) -> Self {
|
||||
Self {
|
||||
local,
|
||||
upstream,
|
||||
backends: RwLock::new(HashMap::new()),
|
||||
}
|
||||
}
|
||||
|
||||
async fn record(&self, account_id: &str, backend: Backend) {
|
||||
self.backends
|
||||
.write()
|
||||
.await
|
||||
.insert(account_id.to_string(), backend);
|
||||
}
|
||||
|
||||
/// The backend that owns `account_id`. Defaults to `Upstream` for an
|
||||
/// account never resolved this process-lifetime (a resolve always
|
||||
/// precedes reserve in a request, so this is just a safe fallback —
|
||||
/// upstream fails closed if the account is bogus).
|
||||
async fn backend_for(&self, account_id: &str) -> Backend {
|
||||
self.backends
|
||||
.read()
|
||||
.await
|
||||
.get(account_id)
|
||||
.copied()
|
||||
.unwrap_or(Backend::Upstream)
|
||||
}
|
||||
}
|
||||
|
||||
#[async_trait]
|
||||
impl EntitlementProvider for ChainedEntitlementProvider {
|
||||
async fn resolve(&self, api_key: &str) -> Result<Principal, AuthError> {
|
||||
match self.local.resolve(api_key).await {
|
||||
Ok(p) => {
|
||||
self.record(&p.account_id, Backend::Local).await;
|
||||
Ok(p)
|
||||
}
|
||||
Err(AuthError::InvalidKey) => {
|
||||
let p = self.upstream.resolve(api_key).await?;
|
||||
self.record(&p.account_id, Backend::Upstream).await;
|
||||
Ok(p)
|
||||
}
|
||||
Err(e) => Err(e),
|
||||
}
|
||||
}
|
||||
|
||||
async fn reserve(
|
||||
&self,
|
||||
principal: &Principal,
|
||||
max_tokens: u64,
|
||||
) -> Result<Reservation, BudgetError> {
|
||||
match self.backend_for(&principal.account_id).await {
|
||||
Backend::Local => self.local.reserve(principal, max_tokens).await,
|
||||
Backend::Upstream => self.upstream.reserve(principal, max_tokens).await,
|
||||
}
|
||||
}
|
||||
|
||||
async fn settle(&self, reservation: Reservation, actual_tokens: u64) {
|
||||
match self.backend_for(&reservation.principal.account_id).await {
|
||||
Backend::Local => self.local.settle(reservation, actual_tokens).await,
|
||||
Backend::Upstream => self.upstream.settle(reservation, actual_tokens).await,
|
||||
}
|
||||
}
|
||||
|
||||
async fn release(&self, reservation: Reservation) {
|
||||
match self.backend_for(&reservation.principal.account_id).await {
|
||||
Backend::Local => self.local.release(reservation).await,
|
||||
Backend::Upstream => self.upstream.release(reservation).await,
|
||||
}
|
||||
}
|
||||
|
||||
async fn snapshot(&self, principal: &Principal) -> Option<BudgetSnapshot> {
|
||||
match self.backend_for(&principal.account_id).await {
|
||||
Backend::Local => self.local.snapshot(principal).await,
|
||||
Backend::Upstream => self.upstream.snapshot(principal).await,
|
||||
}
|
||||
}
|
||||
}
|
||||
246
crates/cortex-gateway/src/entitlements_upstream.rs
Normal file
246
crates/cortex-gateway/src/entitlements_upstream.rs
Normal file
@@ -0,0 +1,246 @@
|
||||
//! helexa-upstream client (#57): an [`EntitlementProvider`] that resolves
|
||||
//! keys and reserves/settles budget against the mesh authority's
|
||||
//! `/authz/v1` surface (B2). It is "just another impl of the trait" — cortex
|
||||
//! enforcement (`auth.rs`, `metering.rs`) is unchanged.
|
||||
//!
|
||||
//! **Fail closed.** When upstream is unreachable, `resolve` returns
|
||||
//! [`AuthError::Unavailable`] (→ `503`, never `401`) and `reserve` refuses
|
||||
//! with a retryable [`BudgetError::RateLimited`] — a request is never served
|
||||
//! on an un-authorized key, and a real key is never rejected as invalid
|
||||
//! during a blip.
|
||||
|
||||
use async_trait::async_trait;
|
||||
use cortex_core::config::UpstreamClientConfig;
|
||||
use cortex_core::entitlements::{
|
||||
AuthError, BudgetError, BudgetSnapshot, EntitlementProvider, Principal, Reservation,
|
||||
};
|
||||
use serde::Deserialize;
|
||||
use std::time::Duration;
|
||||
|
||||
/// Retry-After (seconds) advertised when we fail closed on an upstream
|
||||
/// outage.
|
||||
const FAIL_CLOSED_RETRY_SECS: u64 = 5;
|
||||
|
||||
pub struct UpstreamEntitlementProvider {
|
||||
client: reqwest::Client,
|
||||
base_url: String,
|
||||
bearer: String,
|
||||
}
|
||||
|
||||
#[derive(Deserialize)]
|
||||
struct PrincipalDto {
|
||||
account_id: String,
|
||||
key_id: String,
|
||||
}
|
||||
#[derive(Deserialize)]
|
||||
struct SnapshotDto {
|
||||
hard_cap: Option<u64>,
|
||||
spent: u64,
|
||||
reserved: u64,
|
||||
}
|
||||
#[derive(Deserialize)]
|
||||
struct ResolveResp {
|
||||
principal: PrincipalDto,
|
||||
#[allow(dead_code)]
|
||||
snapshot: Option<SnapshotDto>,
|
||||
}
|
||||
#[derive(Deserialize)]
|
||||
struct ReserveResp {
|
||||
reservation_id: Option<i64>,
|
||||
rejected: Option<Rejection>,
|
||||
}
|
||||
#[derive(Deserialize)]
|
||||
#[serde(tag = "kind", rename_all = "snake_case")]
|
||||
enum Rejection {
|
||||
InsufficientQuota {
|
||||
requested: u64,
|
||||
available: u64,
|
||||
},
|
||||
RateLimited {
|
||||
requested: u64,
|
||||
available: u64,
|
||||
retry_after_secs: u64,
|
||||
},
|
||||
}
|
||||
|
||||
impl UpstreamEntitlementProvider {
|
||||
pub fn new(cfg: &UpstreamClientConfig) -> Self {
|
||||
let client = reqwest::Client::builder()
|
||||
.timeout(Duration::from_secs(cfg.timeout_secs))
|
||||
.build()
|
||||
.expect("failed to build upstream HTTP client");
|
||||
Self {
|
||||
client,
|
||||
base_url: cfg.url.trim_end_matches('/').to_string(),
|
||||
bearer: cfg.bearer.clone(),
|
||||
}
|
||||
}
|
||||
|
||||
fn url(&self, path: &str) -> String {
|
||||
format!("{}{}", self.base_url, path)
|
||||
}
|
||||
}
|
||||
|
||||
#[async_trait]
|
||||
impl EntitlementProvider for UpstreamEntitlementProvider {
|
||||
async fn resolve(&self, api_key: &str) -> Result<Principal, AuthError> {
|
||||
let resp = self
|
||||
.client
|
||||
.post(self.url("/authz/v1/resolve"))
|
||||
.bearer_auth(&self.bearer)
|
||||
.json(&serde_json::json!({ "api_key": api_key }))
|
||||
.send()
|
||||
.await;
|
||||
let resp = match resp {
|
||||
Ok(r) => r,
|
||||
Err(e) => {
|
||||
tracing::warn!(error = %e, "upstream resolve unreachable; failing closed");
|
||||
return Err(AuthError::Unavailable {
|
||||
retry_after_secs: FAIL_CLOSED_RETRY_SECS,
|
||||
});
|
||||
}
|
||||
};
|
||||
if resp.status().as_u16() == 401 {
|
||||
return Err(AuthError::InvalidKey);
|
||||
}
|
||||
if !resp.status().is_success() {
|
||||
return Err(AuthError::Unavailable {
|
||||
retry_after_secs: FAIL_CLOSED_RETRY_SECS,
|
||||
});
|
||||
}
|
||||
match resp.json::<ResolveResp>().await {
|
||||
Ok(r) => Ok(Principal {
|
||||
account_id: r.principal.account_id,
|
||||
key_id: r.principal.key_id,
|
||||
}),
|
||||
Err(e) => {
|
||||
tracing::warn!(error = %e, "upstream resolve: bad body; failing closed");
|
||||
Err(AuthError::Unavailable {
|
||||
retry_after_secs: FAIL_CLOSED_RETRY_SECS,
|
||||
})
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
async fn reserve(
|
||||
&self,
|
||||
principal: &Principal,
|
||||
max_tokens: u64,
|
||||
) -> Result<Reservation, BudgetError> {
|
||||
let fail_closed = || BudgetError::RateLimited {
|
||||
requested: max_tokens,
|
||||
available: 0,
|
||||
retry_after_secs: FAIL_CLOSED_RETRY_SECS,
|
||||
};
|
||||
let resp = self
|
||||
.client
|
||||
.post(self.url("/authz/v1/reserve"))
|
||||
.bearer_auth(&self.bearer)
|
||||
.json(&serde_json::json!({
|
||||
"account_id": principal.account_id,
|
||||
"key_id": principal.key_id,
|
||||
"max_tokens": max_tokens,
|
||||
}))
|
||||
.send()
|
||||
.await;
|
||||
let resp = match resp {
|
||||
Ok(r) if r.status().is_success() => r,
|
||||
Ok(r) => {
|
||||
tracing::warn!(status = %r.status(), "upstream reserve non-2xx; failing closed");
|
||||
return Err(fail_closed());
|
||||
}
|
||||
Err(e) => {
|
||||
tracing::warn!(error = %e, "upstream reserve unreachable; failing closed");
|
||||
return Err(fail_closed());
|
||||
}
|
||||
};
|
||||
match resp.json::<ReserveResp>().await {
|
||||
Ok(ReserveResp {
|
||||
reservation_id: Some(id),
|
||||
..
|
||||
}) => Ok(Reservation {
|
||||
id: id as u64,
|
||||
principal: principal.clone(),
|
||||
reserved: max_tokens,
|
||||
}),
|
||||
Ok(ReserveResp {
|
||||
rejected:
|
||||
Some(Rejection::InsufficientQuota {
|
||||
requested,
|
||||
available,
|
||||
}),
|
||||
..
|
||||
}) => Err(BudgetError::InsufficientQuota {
|
||||
requested,
|
||||
available,
|
||||
}),
|
||||
Ok(ReserveResp {
|
||||
rejected:
|
||||
Some(Rejection::RateLimited {
|
||||
requested,
|
||||
available,
|
||||
retry_after_secs,
|
||||
}),
|
||||
..
|
||||
}) => Err(BudgetError::RateLimited {
|
||||
requested,
|
||||
available,
|
||||
retry_after_secs,
|
||||
}),
|
||||
_ => Err(fail_closed()),
|
||||
}
|
||||
}
|
||||
|
||||
async fn settle(&self, reservation: Reservation, actual_tokens: u64) {
|
||||
// Best-effort; a lost settle is reaped by the upstream sweeper (B2).
|
||||
let _ = self
|
||||
.client
|
||||
.post(self.url("/authz/v1/settle"))
|
||||
.bearer_auth(&self.bearer)
|
||||
.json(&serde_json::json!({
|
||||
"reservation_id": reservation.id as i64,
|
||||
"actual_tokens": actual_tokens,
|
||||
}))
|
||||
.send()
|
||||
.await
|
||||
.inspect_err(
|
||||
|e| tracing::warn!(error = %e, "upstream settle failed (sweeper will reap)"),
|
||||
);
|
||||
}
|
||||
|
||||
async fn release(&self, reservation: Reservation) {
|
||||
let _ = self
|
||||
.client
|
||||
.post(self.url("/authz/v1/release"))
|
||||
.bearer_auth(&self.bearer)
|
||||
.json(&serde_json::json!({ "reservation_id": reservation.id as i64 }))
|
||||
.send()
|
||||
.await
|
||||
.inspect_err(
|
||||
|e| tracing::warn!(error = %e, "upstream release failed (sweeper will reap)"),
|
||||
);
|
||||
}
|
||||
|
||||
async fn snapshot(&self, principal: &Principal) -> Option<BudgetSnapshot> {
|
||||
let resp = self
|
||||
.client
|
||||
.post(self.url("/authz/v1/snapshot"))
|
||||
.bearer_auth(&self.bearer)
|
||||
.json(&serde_json::json!({
|
||||
"account_id": principal.account_id,
|
||||
"key_id": principal.key_id,
|
||||
}))
|
||||
.send()
|
||||
.await
|
||||
.ok()?;
|
||||
if !resp.status().is_success() {
|
||||
return None;
|
||||
}
|
||||
let dto = resp.json::<SnapshotDto>().await.ok()?;
|
||||
Some(BudgetSnapshot {
|
||||
hard_cap: dto.hard_cap,
|
||||
spent: dto.spent,
|
||||
reserved: dto.reserved,
|
||||
})
|
||||
}
|
||||
}
|
||||
@@ -1,6 +1,8 @@
|
||||
pub mod anthropic_sse;
|
||||
pub mod auth;
|
||||
pub mod entitlements_chain;
|
||||
pub mod entitlements_local;
|
||||
pub mod entitlements_upstream;
|
||||
pub mod error;
|
||||
pub mod evictor;
|
||||
pub mod handlers;
|
||||
|
||||
@@ -1,4 +1,6 @@
|
||||
use crate::entitlements_chain::ChainedEntitlementProvider;
|
||||
use crate::entitlements_local::LocalEntitlementProvider;
|
||||
use crate::entitlements_upstream::UpstreamEntitlementProvider;
|
||||
use cortex_core::catalogue::ModelCatalogue;
|
||||
use cortex_core::config::{EvictionSettings, GatewayConfig, NeuronEndpoint};
|
||||
use cortex_core::entitlements::EntitlementProvider;
|
||||
@@ -45,8 +47,20 @@ impl CortexState {
|
||||
|
||||
let catalogue = ModelCatalogue::load(&config.models_config);
|
||||
|
||||
let entitlements: Arc<dyn EntitlementProvider> =
|
||||
Arc::new(LocalEntitlementProvider::from_config(&config.entitlements));
|
||||
// Local provider always handles operator + infra keys. When the
|
||||
// upstream client is enabled (#57), wrap it in the chain so locally
|
||||
// unknown keys fall through to the mesh authority; otherwise stay
|
||||
// purely local.
|
||||
let local = LocalEntitlementProvider::from_config(&config.entitlements);
|
||||
let entitlements: Arc<dyn EntitlementProvider> = if config.upstream.enabled {
|
||||
tracing::info!(url = %config.upstream.url, "upstream entitlement client enabled");
|
||||
Arc::new(ChainedEntitlementProvider::new(
|
||||
local,
|
||||
UpstreamEntitlementProvider::new(&config.upstream),
|
||||
))
|
||||
} else {
|
||||
Arc::new(local)
|
||||
};
|
||||
|
||||
Self {
|
||||
nodes: RwLock::new(nodes),
|
||||
|
||||
@@ -57,6 +57,7 @@ async fn test_alias_resolves_in_chat_completions() {
|
||||
}],
|
||||
models_config: models_path.to_string_lossy().to_string(),
|
||||
entitlements: Default::default(),
|
||||
upstream: Default::default(),
|
||||
};
|
||||
|
||||
let fleet = Arc::new(CortexState::from_config(&config));
|
||||
@@ -143,6 +144,7 @@ async fn test_aliases_surface_in_v1_models() {
|
||||
}],
|
||||
models_config: models_path.to_string_lossy().to_string(),
|
||||
entitlements: Default::default(),
|
||||
upstream: Default::default(),
|
||||
};
|
||||
|
||||
let fleet = Arc::new(CortexState::from_config(&config));
|
||||
@@ -232,6 +234,7 @@ async fn test_alias_falls_through_for_unmapped_model() {
|
||||
}],
|
||||
models_config: models_path.to_string_lossy().to_string(),
|
||||
entitlements: Default::default(),
|
||||
upstream: Default::default(),
|
||||
};
|
||||
|
||||
let fleet = Arc::new(CortexState::from_config(&config));
|
||||
|
||||
@@ -105,6 +105,7 @@ async fn spawn_gateway(neuron_url: &str, entitlements: EntitlementsConfig) -> St
|
||||
}],
|
||||
models_config: "/dev/null".into(),
|
||||
entitlements,
|
||||
upstream: Default::default(),
|
||||
};
|
||||
|
||||
let fleet = Arc::new(CortexState::from_config(&config));
|
||||
|
||||
@@ -81,6 +81,7 @@ async fn spawn_gateway(neuron_url: &str, key: ApiKeyConfig) -> (Arc<CortexState>
|
||||
require_auth: true,
|
||||
keys: vec![key],
|
||||
},
|
||||
upstream: Default::default(),
|
||||
};
|
||||
let fleet = Arc::new(CortexState::from_config(&config));
|
||||
{
|
||||
|
||||
@@ -430,6 +430,7 @@ pub async fn spawn_gateway_with_state(mock_url: &str) -> (Arc<CortexState>, Stri
|
||||
}],
|
||||
models_config: "/dev/null".into(),
|
||||
entitlements: Default::default(),
|
||||
upstream: Default::default(),
|
||||
};
|
||||
|
||||
let fleet = Arc::new(CortexState::from_config(&config));
|
||||
|
||||
@@ -89,6 +89,7 @@ async fn error_response_no_healthy_nodes() {
|
||||
}],
|
||||
models_config: "/dev/null".into(),
|
||||
entitlements: Default::default(),
|
||||
upstream: Default::default(),
|
||||
};
|
||||
|
||||
let fleet = Arc::new(cortex_gateway::state::CortexState::from_config(&config));
|
||||
|
||||
@@ -72,6 +72,7 @@ fn make_fleet(endpoint: &str, defrag_after: u32) -> Arc<CortexState> {
|
||||
}],
|
||||
models_config: "/dev/null".into(),
|
||||
entitlements: Default::default(),
|
||||
upstream: Default::default(),
|
||||
};
|
||||
Arc::new(CortexState::from_config(&config))
|
||||
}
|
||||
|
||||
@@ -74,6 +74,7 @@ async fn fleet_with(big_healthy: bool, big_devices: usize) -> Arc<CortexState> {
|
||||
],
|
||||
models_config: cat.to_string_lossy().into_owned(),
|
||||
entitlements: Default::default(),
|
||||
upstream: Default::default(),
|
||||
};
|
||||
let fleet = Arc::new(CortexState::from_config(&config));
|
||||
{
|
||||
|
||||
@@ -72,6 +72,7 @@ async fn two_neuron_fleet(endpoint_a: &str, endpoint_b: &str) -> Arc<CortexState
|
||||
],
|
||||
models_config: "/dev/null".into(),
|
||||
entitlements: Default::default(),
|
||||
upstream: Default::default(),
|
||||
};
|
||||
Arc::new(CortexState::from_config(&config))
|
||||
}
|
||||
|
||||
@@ -53,6 +53,7 @@ async fn spawn_metered_gateway(neuron_url: &str) -> (Arc<CortexState>, String) {
|
||||
window: CapWindow::Balance,
|
||||
}],
|
||||
},
|
||||
upstream: Default::default(),
|
||||
};
|
||||
|
||||
let fleet = Arc::new(CortexState::from_config(&config));
|
||||
@@ -158,6 +159,7 @@ async fn anonymous_request_records_no_spend() {
|
||||
}],
|
||||
models_config: "/dev/null".into(),
|
||||
entitlements: EntitlementsConfig::default(),
|
||||
upstream: Default::default(),
|
||||
};
|
||||
let fleet = Arc::new(CortexState::from_config(&config));
|
||||
{
|
||||
|
||||
@@ -66,6 +66,7 @@ harness = "candle"
|
||||
}],
|
||||
models_config: cat_path.to_string_lossy().into_owned(),
|
||||
entitlements: Default::default(),
|
||||
upstream: Default::default(),
|
||||
};
|
||||
|
||||
let fleet = Arc::new(CortexState::from_config(&config));
|
||||
|
||||
@@ -55,6 +55,7 @@ capabilities = ["text"]
|
||||
}],
|
||||
models_config: cat_path.to_string_lossy().into_owned(),
|
||||
entitlements: Default::default(),
|
||||
upstream: Default::default(),
|
||||
};
|
||||
|
||||
let fleet = Arc::new(CortexState::from_config(&config));
|
||||
|
||||
@@ -32,6 +32,7 @@ async fn test_poller_discovers_models() {
|
||||
}],
|
||||
models_config: "/dev/null".into(),
|
||||
entitlements: Default::default(),
|
||||
upstream: Default::default(),
|
||||
};
|
||||
|
||||
let fleet = Arc::new(CortexState::from_config(&config));
|
||||
@@ -84,6 +85,7 @@ async fn test_poller_updates_gateway_models_endpoint() {
|
||||
}],
|
||||
models_config: "/dev/null".into(),
|
||||
entitlements: Default::default(),
|
||||
upstream: Default::default(),
|
||||
};
|
||||
|
||||
let fleet = Arc::new(CortexState::from_config(&config));
|
||||
@@ -156,6 +158,7 @@ async fn test_models_endpoint_unions_capabilities_across_nodes() {
|
||||
],
|
||||
models_config: "/dev/null".into(),
|
||||
entitlements: Default::default(),
|
||||
upstream: Default::default(),
|
||||
};
|
||||
|
||||
let fleet = Arc::new(CortexState::from_config(&config));
|
||||
@@ -219,6 +222,7 @@ async fn test_poller_marks_unreachable_node_unhealthy() {
|
||||
}],
|
||||
models_config: "/dev/null".into(),
|
||||
entitlements: Default::default(),
|
||||
upstream: Default::default(),
|
||||
};
|
||||
|
||||
let fleet = Arc::new(CortexState::from_config(&config));
|
||||
@@ -273,6 +277,7 @@ async fn test_poller_removes_stale_models() {
|
||||
}],
|
||||
models_config: "/dev/null".into(),
|
||||
entitlements: Default::default(),
|
||||
upstream: Default::default(),
|
||||
};
|
||||
|
||||
let fleet = Arc::new(CortexState::from_config(&config));
|
||||
@@ -304,6 +309,7 @@ async fn test_poller_removes_stale_models() {
|
||||
}],
|
||||
models_config: "/dev/null".into(),
|
||||
entitlements: Default::default(),
|
||||
upstream: Default::default(),
|
||||
};
|
||||
|
||||
let fleet2 = Arc::new(CortexState::from_config(&config2));
|
||||
@@ -386,6 +392,7 @@ async fn test_poller_captures_activation_from_health() {
|
||||
}],
|
||||
models_config: "/dev/null".into(),
|
||||
entitlements: Default::default(),
|
||||
upstream: Default::default(),
|
||||
};
|
||||
|
||||
let fleet = Arc::new(CortexState::from_config(&config));
|
||||
@@ -431,6 +438,7 @@ async fn test_poller_parses_recovering_status() {
|
||||
}],
|
||||
models_config: "/dev/null".into(),
|
||||
entitlements: Default::default(),
|
||||
upstream: Default::default(),
|
||||
};
|
||||
|
||||
let fleet = Arc::new(CortexState::from_config(&config));
|
||||
|
||||
@@ -75,6 +75,7 @@ async fn spawn_gateway(neuron: &str, context: usize) -> String {
|
||||
}],
|
||||
models_config: "/dev/null".into(),
|
||||
entitlements: Default::default(),
|
||||
upstream: Default::default(),
|
||||
};
|
||||
let fleet = Arc::new(CortexState::from_config(&config));
|
||||
{
|
||||
|
||||
@@ -118,6 +118,7 @@ async fn test_no_healthy_nodes() {
|
||||
}],
|
||||
models_config: "/dev/null".into(),
|
||||
entitlements: Default::default(),
|
||||
upstream: Default::default(),
|
||||
};
|
||||
let fleet = std::sync::Arc::new(cortex_gateway::state::CortexState::from_config(&config));
|
||||
|
||||
|
||||
105
crates/cortex-gateway/tests/upstream_chain.rs
Normal file
105
crates/cortex-gateway/tests/upstream_chain.rs
Normal file
@@ -0,0 +1,105 @@
|
||||
//! B3: the chained entitlement provider (local → upstream) and fail-closed
|
||||
//! semantics, exercised against a mock helexa-upstream `/authz/v1`.
|
||||
|
||||
use axum::{Json, Router, routing::post};
|
||||
use cortex_core::config::{ApiKeyConfig, EntitlementsConfig, UpstreamClientConfig};
|
||||
use cortex_core::entitlements::{AuthError, EntitlementProvider};
|
||||
use cortex_gateway::entitlements_chain::ChainedEntitlementProvider;
|
||||
use cortex_gateway::entitlements_local::LocalEntitlementProvider;
|
||||
use cortex_gateway::entitlements_upstream::UpstreamEntitlementProvider;
|
||||
use serde_json::{Value, json};
|
||||
use tokio::net::TcpListener;
|
||||
|
||||
/// Mock upstream: `mesh-key` resolves to a mesh account; anything else 401.
|
||||
/// reserve always grants reservation 1.
|
||||
async fn spawn_mock_upstream() -> String {
|
||||
async fn resolve(Json(body): Json<Value>) -> axum::response::Response {
|
||||
use axum::response::IntoResponse;
|
||||
if body["api_key"] == "mesh-key" {
|
||||
Json(json!({"principal": {"account_id": "mesh-acct", "key_id": "mesh-key-1"}}))
|
||||
.into_response()
|
||||
} else {
|
||||
(
|
||||
axum::http::StatusCode::UNAUTHORIZED,
|
||||
Json(json!({"error": {"code": "invalid_api_key"}})),
|
||||
)
|
||||
.into_response()
|
||||
}
|
||||
}
|
||||
async fn reserve() -> Json<Value> {
|
||||
Json(json!({ "reservation_id": 1 }))
|
||||
}
|
||||
let app = Router::new()
|
||||
.route("/authz/v1/resolve", post(resolve))
|
||||
.route("/authz/v1/reserve", post(reserve));
|
||||
let listener = TcpListener::bind("127.0.0.1:0").await.unwrap();
|
||||
let addr = listener.local_addr().unwrap();
|
||||
tokio::spawn(async move {
|
||||
axum::serve(listener, app).await.unwrap();
|
||||
});
|
||||
format!("http://{addr}")
|
||||
}
|
||||
|
||||
fn local_with_key() -> LocalEntitlementProvider {
|
||||
let cfg = EntitlementsConfig {
|
||||
require_auth: false,
|
||||
keys: vec![ApiKeyConfig {
|
||||
key: "local-key".into(),
|
||||
account_id: "op".into(),
|
||||
key_id: None,
|
||||
hard_cap: None,
|
||||
window: Default::default(),
|
||||
}],
|
||||
};
|
||||
LocalEntitlementProvider::from_config(&cfg)
|
||||
}
|
||||
|
||||
fn chain(local: LocalEntitlementProvider, url: &str) -> ChainedEntitlementProvider {
|
||||
let upstream = UpstreamEntitlementProvider::new(&UpstreamClientConfig {
|
||||
enabled: true,
|
||||
url: url.to_string(),
|
||||
bearer: "client-secret".into(),
|
||||
timeout_secs: 5,
|
||||
});
|
||||
ChainedEntitlementProvider::new(local, upstream)
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn local_key_resolves_locally() {
|
||||
let url = spawn_mock_upstream().await;
|
||||
let c = chain(local_with_key(), &url);
|
||||
let p = c.resolve("local-key").await.expect("local resolves");
|
||||
assert_eq!(p.account_id, "op");
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn unknown_key_falls_through_to_upstream() {
|
||||
let url = spawn_mock_upstream().await;
|
||||
let c = chain(local_with_key(), &url);
|
||||
let p = c.resolve("mesh-key").await.expect("upstream resolves");
|
||||
assert_eq!(p.account_id, "mesh-acct");
|
||||
assert_eq!(p.key_id, "mesh-key-1");
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn unknown_everywhere_is_invalid_key() {
|
||||
let url = spawn_mock_upstream().await;
|
||||
let c = chain(local_with_key(), &url);
|
||||
match c.resolve("nope").await {
|
||||
Err(AuthError::InvalidKey) => {}
|
||||
other => panic!("expected InvalidKey, got {other:?}"),
|
||||
}
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn upstream_unreachable_fails_closed_as_unavailable() {
|
||||
// No mock — point at a dead port. A locally-unknown key must surface
|
||||
// Unavailable (→ 503), never InvalidKey (→ 401).
|
||||
let c = chain(local_with_key(), "http://127.0.0.1:1");
|
||||
match c.resolve("some-mesh-key").await {
|
||||
Err(AuthError::Unavailable { retry_after_secs }) => assert!(retry_after_secs > 0),
|
||||
other => panic!("expected Unavailable, got {other:?}"),
|
||||
}
|
||||
// A local key still resolves without touching upstream.
|
||||
assert_eq!(c.resolve("local-key").await.unwrap().account_id, "op");
|
||||
}
|
||||
@@ -42,6 +42,12 @@ sqlx = { version = "0.8", default-features = false, features = [
|
||||
"uuid",
|
||||
] }
|
||||
uuid = { version = "1", features = ["v4", "serde"] }
|
||||
sha2 = "0.10"
|
||||
subtle = "2.6"
|
||||
|
||||
# cortex-core for the shared #63 OpenAiError envelope on the authz surface.
|
||||
cortex-core = { workspace = true }
|
||||
|
||||
[dev-dependencies]
|
||||
figment = { workspace = true, features = ["test"] }
|
||||
reqwest = { workspace = true }
|
||||
|
||||
284
crates/helexa-upstream/src/authz.rs
Normal file
284
crates/helexa-upstream/src/authz.rs
Normal file
@@ -0,0 +1,284 @@
|
||||
//! `/authz/v1` — the machine surface cortex's `UpstreamEntitlementProvider`
|
||||
//! (#57) consumes. It mirrors the `cortex_core::entitlements::EntitlementProvider`
|
||||
//! trait 1:1 (resolve / reserve / settle / release / snapshot) over the B1
|
||||
//! ledger.
|
||||
//!
|
||||
//! Contract notes for the cortex client:
|
||||
//! - A **non-2xx** response means the authority could not give an
|
||||
//! authoritative answer (bad caller auth, malformed request, server
|
||||
//! error) → the client should **fail closed**.
|
||||
//! - `reserve` returns **200** whether granted or budget-refused: the body
|
||||
//! carries either `reservation_id` or a `rejected` discriminant. A budget
|
||||
//! refusal is an authoritative answer, not a transport failure.
|
||||
//! - Rejections that are genuinely auth failures use the #63 `OpenAiError`
|
||||
//! envelope so they can be surfaced verbatim.
|
||||
|
||||
use crate::crypto::sha256;
|
||||
use crate::error::envelope_response;
|
||||
use crate::ledger::{self, LedgerError};
|
||||
use crate::state::AppState;
|
||||
use axum::extract::{Request, State};
|
||||
use axum::http::{StatusCode, header};
|
||||
use axum::middleware::Next;
|
||||
use axum::response::{IntoResponse, Response};
|
||||
use axum::routing::post;
|
||||
use axum::{Json, Router};
|
||||
use cortex_core::error_envelope::OpenAiError;
|
||||
use serde::{Deserialize, Serialize};
|
||||
use subtle::ConstantTimeEq;
|
||||
use uuid::Uuid;
|
||||
|
||||
/// The operator a validated client bearer identifies (served-usage
|
||||
/// attribution, #58). Inserted into request extensions by [`client_auth`].
|
||||
#[derive(Debug, Clone)]
|
||||
pub struct OperatorId(pub String);
|
||||
|
||||
/// Build the `/authz/v1` router with the client-auth layer applied.
|
||||
pub fn router(state: &AppState) -> Router<AppState> {
|
||||
Router::new()
|
||||
.route("/authz/v1/resolve", post(resolve))
|
||||
.route("/authz/v1/reserve", post(reserve))
|
||||
.route("/authz/v1/settle", post(settle))
|
||||
.route("/authz/v1/release", post(release))
|
||||
.route("/authz/v1/snapshot", post(snapshot))
|
||||
.layer(axum::middleware::from_fn_with_state(
|
||||
state.clone(),
|
||||
client_auth,
|
||||
))
|
||||
}
|
||||
|
||||
// ── client auth (shared bearer → operator_id) ───────────────────────
|
||||
|
||||
/// Validate the caller's `Authorization: Bearer` against the configured
|
||||
/// client tokens (constant-time) and stamp the `operator_id`. When no tokens
|
||||
/// are configured the surface is open (dev) and a synthetic operator is
|
||||
/// used.
|
||||
async fn client_auth(State(state): State<AppState>, mut req: Request, next: Next) -> Response {
|
||||
let tokens = &state.config.client_auth.tokens;
|
||||
if tokens.is_empty() {
|
||||
req.extensions_mut().insert(OperatorId("dev".into()));
|
||||
return next.run(req).await;
|
||||
}
|
||||
let presented = req
|
||||
.headers()
|
||||
.get(header::AUTHORIZATION)
|
||||
.and_then(|v| v.to_str().ok())
|
||||
.and_then(|v| v.strip_prefix("Bearer "))
|
||||
.map(str::trim)
|
||||
.unwrap_or("");
|
||||
let matched = tokens
|
||||
.iter()
|
||||
.find(|t| t.token.as_bytes().ct_eq(presented.as_bytes()).into());
|
||||
match matched {
|
||||
Some(t) => {
|
||||
req.extensions_mut()
|
||||
.insert(OperatorId(t.operator_id.clone()));
|
||||
next.run(req).await
|
||||
}
|
||||
None => envelope_response(OpenAiError::invalid_api_key(
|
||||
"missing or invalid client credentials",
|
||||
)),
|
||||
}
|
||||
}
|
||||
|
||||
// ── DTOs ────────────────────────────────────────────────────────────
|
||||
|
||||
#[derive(Deserialize)]
|
||||
struct ResolveReq {
|
||||
api_key: String,
|
||||
}
|
||||
|
||||
#[derive(Serialize)]
|
||||
struct PrincipalDto {
|
||||
account_id: String,
|
||||
key_id: String,
|
||||
}
|
||||
|
||||
#[derive(Serialize)]
|
||||
struct SnapshotDto {
|
||||
hard_cap: Option<i64>,
|
||||
spent: i64,
|
||||
reserved: i64,
|
||||
}
|
||||
|
||||
#[derive(Serialize)]
|
||||
struct ResolveResp {
|
||||
principal: PrincipalDto,
|
||||
snapshot: SnapshotDto,
|
||||
}
|
||||
|
||||
#[derive(Deserialize)]
|
||||
struct ReserveReq {
|
||||
account_id: String,
|
||||
key_id: String,
|
||||
max_tokens: i64,
|
||||
}
|
||||
|
||||
#[derive(Serialize, Default)]
|
||||
struct ReserveResp {
|
||||
#[serde(skip_serializing_if = "Option::is_none")]
|
||||
reservation_id: Option<i64>,
|
||||
#[serde(skip_serializing_if = "Option::is_none")]
|
||||
rejected: Option<Rejection>,
|
||||
}
|
||||
|
||||
#[derive(Serialize)]
|
||||
#[serde(tag = "kind", rename_all = "snake_case")]
|
||||
enum Rejection {
|
||||
InsufficientQuota {
|
||||
requested: i64,
|
||||
available: i64,
|
||||
},
|
||||
// Part of the frozen wire contract so the cortex client (#57) can map it
|
||||
// without a later breaking change. Not yet constructed: the B1 ledger
|
||||
// implements Balance caps only; rolling-window key sub-caps (which yield
|
||||
// this) land in a follow-up.
|
||||
#[allow(dead_code)]
|
||||
RateLimited {
|
||||
requested: i64,
|
||||
available: i64,
|
||||
retry_after_secs: u64,
|
||||
},
|
||||
}
|
||||
|
||||
#[derive(Deserialize)]
|
||||
struct SettleReq {
|
||||
reservation_id: i64,
|
||||
actual_tokens: i64,
|
||||
}
|
||||
|
||||
#[derive(Deserialize)]
|
||||
struct ReservationRef {
|
||||
reservation_id: i64,
|
||||
}
|
||||
|
||||
#[derive(Deserialize)]
|
||||
struct SnapshotReq {
|
||||
account_id: String,
|
||||
key_id: String,
|
||||
}
|
||||
|
||||
// ── handlers ────────────────────────────────────────────────────────
|
||||
|
||||
/// `POST /authz/v1/resolve` — bearer key → principal + snapshot, or
|
||||
/// `401 invalid_api_key` (also for a deactivated account: no clue).
|
||||
async fn resolve(State(state): State<AppState>, Json(req): Json<ResolveReq>) -> Response {
|
||||
match ledger::resolve_key(&state.pool, &sha256(&req.api_key)).await {
|
||||
Ok(Some(p)) => Json(ResolveResp {
|
||||
principal: PrincipalDto {
|
||||
account_id: p.account_id.to_string(),
|
||||
key_id: p.key_id.to_string(),
|
||||
},
|
||||
snapshot: SnapshotDto {
|
||||
hard_cap: Some(p.hard_cap),
|
||||
spent: p.key_spent,
|
||||
reserved: p.key_reserved,
|
||||
},
|
||||
})
|
||||
.into_response(),
|
||||
Ok(None) => envelope_response(OpenAiError::invalid_api_key("invalid or unknown API key")),
|
||||
Err(e) => {
|
||||
tracing::error!(error = %e, "resolve query failed");
|
||||
envelope_response(OpenAiError::service_unavailable("authority error", Some(5)))
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
/// `POST /authz/v1/reserve` — 200 with `reservation_id` (granted) or
|
||||
/// `rejected` (budget). Non-2xx only for bad input / server error.
|
||||
async fn reserve(State(state): State<AppState>, Json(req): Json<ReserveReq>) -> Response {
|
||||
let (Ok(account_id), Ok(key_id)) = (
|
||||
Uuid::parse_str(&req.account_id),
|
||||
Uuid::parse_str(&req.key_id),
|
||||
) else {
|
||||
return bad_request("account_id and key_id must be UUIDs");
|
||||
};
|
||||
match ledger::reserve(&state.pool, account_id, key_id, req.max_tokens).await {
|
||||
Ok(reservation_id) => Json(ReserveResp {
|
||||
reservation_id: Some(reservation_id),
|
||||
rejected: None,
|
||||
})
|
||||
.into_response(),
|
||||
Err(LedgerError::InsufficientQuota {
|
||||
requested,
|
||||
available,
|
||||
}) => Json(ReserveResp {
|
||||
reservation_id: None,
|
||||
rejected: Some(Rejection::InsufficientQuota {
|
||||
requested,
|
||||
available,
|
||||
}),
|
||||
})
|
||||
.into_response(),
|
||||
Err(LedgerError::AccountNotFound | LedgerError::KeyNotFound) => {
|
||||
// Resolve succeeded earlier; the principal vanished (archived /
|
||||
// deactivated). Treat as no budget — fail closed at the client.
|
||||
Json(ReserveResp {
|
||||
reservation_id: None,
|
||||
rejected: Some(Rejection::InsufficientQuota {
|
||||
requested: req.max_tokens,
|
||||
available: 0,
|
||||
}),
|
||||
})
|
||||
.into_response()
|
||||
}
|
||||
Err(LedgerError::Db(e)) => {
|
||||
tracing::error!(error = %e, "reserve failed");
|
||||
envelope_response(OpenAiError::service_unavailable("authority error", Some(5)))
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
/// `POST /authz/v1/settle` — idempotent; `204`.
|
||||
async fn settle(State(state): State<AppState>, Json(req): Json<SettleReq>) -> Response {
|
||||
match ledger::settle(&state.pool, req.reservation_id, req.actual_tokens).await {
|
||||
Ok(()) => StatusCode::NO_CONTENT.into_response(),
|
||||
Err(e) => {
|
||||
tracing::error!(error = %e, "settle failed");
|
||||
envelope_response(OpenAiError::service_unavailable("authority error", Some(5)))
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
/// `POST /authz/v1/release` — idempotent; `204`.
|
||||
async fn release(State(state): State<AppState>, Json(req): Json<ReservationRef>) -> Response {
|
||||
match ledger::release(&state.pool, req.reservation_id).await {
|
||||
Ok(()) => StatusCode::NO_CONTENT.into_response(),
|
||||
Err(e) => {
|
||||
tracing::error!(error = %e, "release failed");
|
||||
envelope_response(OpenAiError::service_unavailable("authority error", Some(5)))
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
/// `POST /authz/v1/snapshot` — `{hard_cap, spent, reserved}` or `404`.
|
||||
async fn snapshot(State(state): State<AppState>, Json(req): Json<SnapshotReq>) -> Response {
|
||||
let (Ok(account_id), Ok(key_id)) = (
|
||||
Uuid::parse_str(&req.account_id),
|
||||
Uuid::parse_str(&req.key_id),
|
||||
) else {
|
||||
return bad_request("account_id and key_id must be UUIDs");
|
||||
};
|
||||
match ledger::snapshot(&state.pool, account_id, key_id).await {
|
||||
Ok(Some((hard_cap, spent, reserved))) => Json(SnapshotDto {
|
||||
hard_cap: Some(hard_cap),
|
||||
spent,
|
||||
reserved,
|
||||
})
|
||||
.into_response(),
|
||||
Ok(None) => StatusCode::NOT_FOUND.into_response(),
|
||||
Err(e) => {
|
||||
tracing::error!(error = %e, "snapshot failed");
|
||||
envelope_response(OpenAiError::service_unavailable("authority error", Some(5)))
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
fn bad_request(msg: &str) -> Response {
|
||||
envelope_response(OpenAiError::new(
|
||||
400,
|
||||
"invalid_request_error",
|
||||
"invalid_request",
|
||||
msg,
|
||||
))
|
||||
}
|
||||
@@ -18,6 +18,50 @@ pub struct UpstreamConfig {
|
||||
pub grant: GrantSettings,
|
||||
#[serde(default)]
|
||||
pub abuse: AbuseSettings,
|
||||
#[serde(default)]
|
||||
pub client_auth: ClientAuthSettings,
|
||||
#[serde(default)]
|
||||
pub authz: AuthzSettings,
|
||||
}
|
||||
|
||||
/// `[client_auth]` — credentials operators' cortexes present to `/authz/v1`.
|
||||
/// Each token maps to an `operator_id` (served-usage attribution, #58). This
|
||||
/// transport credential is distinct from end-user API keys (which ride in
|
||||
/// the `resolve` body). v2 adds mTLS.
|
||||
#[derive(Debug, Clone, Serialize, Deserialize, Default)]
|
||||
pub struct ClientAuthSettings {
|
||||
/// When empty the authz surface is **open** (dev only; logged at warn).
|
||||
#[serde(default)]
|
||||
pub tokens: Vec<ClientToken>,
|
||||
}
|
||||
|
||||
#[derive(Debug, Clone, Serialize, Deserialize)]
|
||||
pub struct ClientToken {
|
||||
/// Shared bearer a cortex presents.
|
||||
pub token: String,
|
||||
/// Operator this token identifies.
|
||||
pub operator_id: String,
|
||||
}
|
||||
|
||||
/// `[authz]` — reservation lifecycle knobs.
|
||||
#[derive(Debug, Clone, Serialize, Deserialize)]
|
||||
pub struct AuthzSettings {
|
||||
/// Open reservations older than this are swept (released), self-healing
|
||||
/// a reservation whose settle/release from cortex was lost.
|
||||
#[serde(default = "default_reservation_ttl")]
|
||||
pub reservation_ttl_secs: u64,
|
||||
/// How often the sweeper runs.
|
||||
#[serde(default = "default_sweep_interval")]
|
||||
pub sweep_interval_secs: u64,
|
||||
}
|
||||
|
||||
impl Default for AuthzSettings {
|
||||
fn default() -> Self {
|
||||
Self {
|
||||
reservation_ttl_secs: default_reservation_ttl(),
|
||||
sweep_interval_secs: default_sweep_interval(),
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
#[derive(Debug, Clone, Serialize, Deserialize)]
|
||||
@@ -92,6 +136,12 @@ fn default_free_grant() -> i64 {
|
||||
fn default_fingerprint_threshold() -> i64 {
|
||||
5
|
||||
}
|
||||
fn default_reservation_ttl() -> u64 {
|
||||
120
|
||||
}
|
||||
fn default_sweep_interval() -> u64 {
|
||||
60
|
||||
}
|
||||
|
||||
impl UpstreamConfig {
|
||||
/// Load from a TOML file with `UPSTREAM_`-prefixed env overrides
|
||||
|
||||
12
crates/helexa-upstream/src/crypto.rs
Normal file
12
crates/helexa-upstream/src/crypto.rs
Normal file
@@ -0,0 +1,12 @@
|
||||
//! Hashing helpers. API keys and top-up codes are stored only as their
|
||||
//! sha256 (they are high-entropy secrets; sha256 is the fast, sufficient
|
||||
//! choice — argon2 is reserved for low-entropy passwords).
|
||||
|
||||
use sha2::{Digest, Sha256};
|
||||
|
||||
/// sha256 of `input`, as raw bytes (matches the `BYTEA` columns).
|
||||
pub fn sha256(input: &str) -> Vec<u8> {
|
||||
let mut h = Sha256::new();
|
||||
h.update(input.as_bytes());
|
||||
h.finalize().to_vec()
|
||||
}
|
||||
21
crates/helexa-upstream/src/error.rs
Normal file
21
crates/helexa-upstream/src/error.rs
Normal file
@@ -0,0 +1,21 @@
|
||||
//! Adapter from the shared, axum-agnostic
|
||||
//! [`cortex_core::error_envelope::OpenAiError`] (#60/#63) to an axum
|
||||
//! response, with `Retry-After`. The `/authz/v1` surface speaks the #63
|
||||
//! envelope so cortex (an OpenAI-compatible proxy) can forward rejections
|
||||
//! verbatim. (The future `/web/v1` surface uses a plain JSON error shape.)
|
||||
|
||||
use axum::http::{HeaderValue, StatusCode, header};
|
||||
use axum::response::{IntoResponse, Json, Response};
|
||||
use cortex_core::error_envelope::OpenAiError;
|
||||
|
||||
pub fn envelope_response(err: OpenAiError) -> Response {
|
||||
let status = StatusCode::from_u16(err.status).unwrap_or(StatusCode::INTERNAL_SERVER_ERROR);
|
||||
let retry_after = err.retry_after_secs;
|
||||
let mut response = (status, Json(err.body())).into_response();
|
||||
if let Some(secs) = retry_after
|
||||
&& let Ok(value) = HeaderValue::from_str(&secs.to_string())
|
||||
{
|
||||
response.headers_mut().insert(header::RETRY_AFTER, value);
|
||||
}
|
||||
response
|
||||
}
|
||||
@@ -20,6 +20,103 @@
|
||||
use sqlx::postgres::PgPool;
|
||||
use uuid::Uuid;
|
||||
|
||||
/// A bearer key resolved to its principal + a budget snapshot.
|
||||
#[derive(Debug, Clone)]
|
||||
pub struct ResolvedPrincipal {
|
||||
pub account_id: Uuid,
|
||||
pub key_id: Uuid,
|
||||
/// Effective per-key absolute cap (the key sub-cap; the account cap
|
||||
/// still binds at reserve time).
|
||||
pub hard_cap: i64,
|
||||
pub key_spent: i64,
|
||||
pub key_reserved: i64,
|
||||
}
|
||||
|
||||
/// Resolve a key by its `sha256` hash to its principal, or `None` when the
|
||||
/// key is unknown/archived **or its account is deactivated** (the silent
|
||||
/// abuse flag — indistinguishable from an unknown key, by design: no clue).
|
||||
pub async fn resolve_key(
|
||||
pool: &PgPool,
|
||||
key_hash: &[u8],
|
||||
) -> Result<Option<ResolvedPrincipal>, sqlx::Error> {
|
||||
let row = sqlx::query(
|
||||
"SELECT k.id AS key_id, k.account_id, k.limit_kind, k.limit_value, \
|
||||
k.key_spent, k.key_reserved, a.allocation_total \
|
||||
FROM api_keys k JOIN accounts a ON a.id = k.account_id \
|
||||
WHERE k.key_hash = $1 AND k.status = 'active' AND a.status = 'active'",
|
||||
)
|
||||
.bind(key_hash)
|
||||
.fetch_optional(pool)
|
||||
.await?;
|
||||
Ok(row.map(|r| {
|
||||
let total: i64 = sqlx::Row::get(&r, "allocation_total");
|
||||
let limit_kind: String = sqlx::Row::get(&r, "limit_kind");
|
||||
let limit_value: i64 = sqlx::Row::get(&r, "limit_value");
|
||||
ResolvedPrincipal {
|
||||
account_id: sqlx::Row::get(&r, "account_id"),
|
||||
key_id: sqlx::Row::get(&r, "key_id"),
|
||||
hard_cap: resolve_abs_cap(&limit_kind, limit_value, total),
|
||||
key_spent: sqlx::Row::get(&r, "key_spent"),
|
||||
key_reserved: sqlx::Row::get(&r, "key_reserved"),
|
||||
}
|
||||
}))
|
||||
}
|
||||
|
||||
/// Per-key budget snapshot `(hard_cap, spent, reserved)`, or `None` if the
|
||||
/// key/account isn't an active pair.
|
||||
pub async fn snapshot(
|
||||
pool: &PgPool,
|
||||
account_id: Uuid,
|
||||
key_id: Uuid,
|
||||
) -> Result<Option<(i64, i64, i64)>, sqlx::Error> {
|
||||
let row = sqlx::query(
|
||||
"SELECT k.limit_kind, k.limit_value, k.key_spent, k.key_reserved, a.allocation_total \
|
||||
FROM api_keys k JOIN accounts a ON a.id = k.account_id \
|
||||
WHERE k.id = $1 AND k.account_id = $2 AND k.status = 'active' AND a.status = 'active'",
|
||||
)
|
||||
.bind(key_id)
|
||||
.bind(account_id)
|
||||
.fetch_optional(pool)
|
||||
.await?;
|
||||
Ok(row.map(|r| {
|
||||
let total: i64 = sqlx::Row::get(&r, "allocation_total");
|
||||
let limit_kind: String = sqlx::Row::get(&r, "limit_kind");
|
||||
let limit_value: i64 = sqlx::Row::get(&r, "limit_value");
|
||||
let cap = resolve_abs_cap(&limit_kind, limit_value, total);
|
||||
(
|
||||
cap,
|
||||
sqlx::Row::get::<i64, _>(&r, "key_spent"),
|
||||
sqlx::Row::get::<i64, _>(&r, "key_reserved"),
|
||||
)
|
||||
}))
|
||||
}
|
||||
|
||||
/// Release every `open` reservation older than `max_age_secs`, returning
|
||||
/// each one's reserved tokens to its account and key in a single statement.
|
||||
/// The lost-settle self-heal. Returns the number swept.
|
||||
pub async fn sweep_stale(pool: &PgPool, max_age_secs: i64) -> Result<u64, sqlx::Error> {
|
||||
// Data-modifying CTEs: release stale rows, then fold their reserved sums
|
||||
// back into accounts and api_keys. All in one atomic statement.
|
||||
let result = sqlx::query(
|
||||
"WITH stale AS ( \
|
||||
UPDATE reservations SET state = 'released', settled_at = now() \
|
||||
WHERE state = 'open' AND created_at < now() - make_interval(secs => $1) \
|
||||
RETURNING account_id, key_id, reserved \
|
||||
), acct AS ( \
|
||||
UPDATE accounts a SET allocation_reserved = allocation_reserved - s.total \
|
||||
FROM (SELECT account_id, SUM(reserved) AS total FROM stale GROUP BY account_id) s \
|
||||
WHERE a.id = s.account_id \
|
||||
) \
|
||||
UPDATE api_keys k SET key_reserved = key_reserved - s.total \
|
||||
FROM (SELECT key_id, SUM(reserved) AS total FROM stale GROUP BY key_id) s \
|
||||
WHERE k.id = s.key_id",
|
||||
)
|
||||
.bind(max_age_secs as f64)
|
||||
.execute(pool)
|
||||
.await?;
|
||||
Ok(result.rows_affected())
|
||||
}
|
||||
|
||||
/// Resolve a key's per-key cap to an absolute token count.
|
||||
///
|
||||
/// `percent` is `floor(allocation_total * limit_value / 100)`; `hardcap` is
|
||||
|
||||
@@ -7,12 +7,16 @@
|
||||
//! of the `/authz/v1` surface; the helexa.ai frontend is a client of the
|
||||
//! `/web/v1` surface.
|
||||
//!
|
||||
//! B1 (this milestone) lands the crate skeleton, the full Postgres schema
|
||||
//! (`migrations/`), the reserve→settle ledger ([`ledger`]) with its
|
||||
//! no-overshoot guarantee, and `/health`.
|
||||
//! Landed so far: B1 — schema + reserve→settle [`ledger`] (no-overshoot) +
|
||||
//! `/health`. B2 — the `/authz/v1` [`authz`] surface (resolve/reserve/
|
||||
//! settle/release/snapshot) with shared-bearer client auth and a
|
||||
//! stale-reservation sweeper.
|
||||
|
||||
pub mod authz;
|
||||
pub mod config;
|
||||
pub mod crypto;
|
||||
pub mod db;
|
||||
pub mod error;
|
||||
pub mod handlers;
|
||||
pub mod ledger;
|
||||
pub mod state;
|
||||
@@ -20,22 +24,35 @@ pub mod state;
|
||||
use anyhow::Result;
|
||||
use config::UpstreamConfig;
|
||||
use state::AppState;
|
||||
use std::time::Duration;
|
||||
use tower_http::trace::TraceLayer;
|
||||
|
||||
/// Build the axum application.
|
||||
pub fn build_app(state: AppState) -> axum::Router {
|
||||
axum::Router::new()
|
||||
.merge(handlers::routes())
|
||||
.merge(authz::router(&state))
|
||||
.layer(TraceLayer::new_for_http())
|
||||
.with_state(state)
|
||||
}
|
||||
|
||||
/// Start the service: connect Postgres, run migrations, bind the listener.
|
||||
/// Start the service: connect Postgres, run migrations, spawn the
|
||||
/// reservation sweeper, bind the listener.
|
||||
pub async fn run(config: UpstreamConfig) -> Result<()> {
|
||||
let pool = db::connect_and_migrate(&config.db.url, config.db.max_connections).await?;
|
||||
let listen = config.server.listen.clone();
|
||||
let state = AppState::new(pool, config);
|
||||
|
||||
if state.config.client_auth.tokens.is_empty() {
|
||||
tracing::warn!(
|
||||
"no [client_auth] tokens configured — the /authz/v1 surface is OPEN (dev only)"
|
||||
);
|
||||
}
|
||||
|
||||
// Stale-reservation sweeper: releases open reservations whose
|
||||
// settle/release from cortex was lost, self-healing allocation_reserved.
|
||||
spawn_sweeper(&state);
|
||||
|
||||
let addr = listen.parse::<std::net::SocketAddr>()?;
|
||||
tracing::info!("helexa-upstream listening on {addr}");
|
||||
|
||||
@@ -43,3 +60,19 @@ pub async fn run(config: UpstreamConfig) -> Result<()> {
|
||||
axum::serve(listener, build_app(state)).await?;
|
||||
Ok(())
|
||||
}
|
||||
|
||||
fn spawn_sweeper(state: &AppState) {
|
||||
let pool = state.pool.clone();
|
||||
let ttl = state.config.authz.reservation_ttl_secs as i64;
|
||||
let interval = Duration::from_secs(state.config.authz.sweep_interval_secs);
|
||||
tokio::spawn(async move {
|
||||
loop {
|
||||
tokio::time::sleep(interval).await;
|
||||
match ledger::sweep_stale(&pool, ttl).await {
|
||||
Ok(n) if n > 0 => tracing::info!(swept = n, "released stale reservations"),
|
||||
Ok(_) => {}
|
||||
Err(e) => tracing::warn!(error = %e, "reservation sweep failed"),
|
||||
}
|
||||
}
|
||||
});
|
||||
}
|
||||
|
||||
240
crates/helexa-upstream/tests/authz_pg.rs
Normal file
240
crates/helexa-upstream/tests/authz_pg.rs
Normal file
@@ -0,0 +1,240 @@
|
||||
//! Integration tests for the `/authz/v1` surface against a real Postgres,
|
||||
//! driving the built axum app over HTTP. Gated on `UPSTREAM_TEST_DATABASE_URL`
|
||||
//! (skips cleanly when unset, so CI stays green without a DB):
|
||||
//!
|
||||
//! UPSTREAM_TEST_DATABASE_URL=postgres://helexa:helexa@localhost/helexa_test \
|
||||
//! cargo test -p helexa-upstream --test authz_pg
|
||||
|
||||
use helexa_upstream::config::{ClientToken, UpstreamConfig};
|
||||
use helexa_upstream::crypto::sha256;
|
||||
use helexa_upstream::db::connect_and_migrate;
|
||||
use helexa_upstream::state::AppState;
|
||||
use serde_json::{Value, json};
|
||||
use sqlx::Executor;
|
||||
use sqlx::Row;
|
||||
use sqlx::postgres::PgPool;
|
||||
use uuid::Uuid;
|
||||
|
||||
const CLIENT_TOKEN: &str = "test-operator-token";
|
||||
|
||||
async fn spawn_or_skip(test: &str) -> Option<(String, PgPool)> {
|
||||
let Ok(url) = std::env::var("UPSTREAM_TEST_DATABASE_URL") else {
|
||||
eprintln!("skipping {test}: UPSTREAM_TEST_DATABASE_URL not set");
|
||||
return None;
|
||||
};
|
||||
let pool = connect_and_migrate(&url, 16).await.expect("migrate");
|
||||
|
||||
let mut config = UpstreamConfig {
|
||||
server: Default::default(),
|
||||
db: helexa_upstream::config::DbSettings {
|
||||
url,
|
||||
max_connections: 16,
|
||||
},
|
||||
grant: Default::default(),
|
||||
abuse: Default::default(),
|
||||
client_auth: Default::default(),
|
||||
authz: Default::default(),
|
||||
};
|
||||
config.client_auth.tokens.push(ClientToken {
|
||||
token: CLIENT_TOKEN.into(),
|
||||
operator_id: "op-test".into(),
|
||||
});
|
||||
|
||||
let state = AppState::new(pool.clone(), config);
|
||||
let app = helexa_upstream::build_app(state);
|
||||
let listener = tokio::net::TcpListener::bind("127.0.0.1:0").await.unwrap();
|
||||
let addr = listener.local_addr().unwrap();
|
||||
tokio::spawn(async move {
|
||||
axum::serve(listener, app).await.unwrap();
|
||||
});
|
||||
Some((format!("http://{addr}"), pool))
|
||||
}
|
||||
|
||||
/// Seed an account with `total` allocation and an active key with raw value
|
||||
/// `raw` (percent=100). Optionally deactivate the account. Returns
|
||||
/// (account_id, key_id).
|
||||
async fn seed_key(pool: &PgPool, total: i64, raw: &str, deactivated: bool) -> (Uuid, Uuid) {
|
||||
let user_id: Uuid = pool
|
||||
.fetch_one(
|
||||
sqlx::query(
|
||||
"INSERT INTO users (email, password_hash, email_verified) VALUES ($1,'x',true) RETURNING id",
|
||||
)
|
||||
.bind(format!("u-{}@t.local", Uuid::new_v4())),
|
||||
)
|
||||
.await
|
||||
.unwrap()
|
||||
.get("id");
|
||||
let status = if deactivated { "deactivated" } else { "active" };
|
||||
let account_id: Uuid = pool
|
||||
.fetch_one(
|
||||
sqlx::query(
|
||||
"INSERT INTO accounts (owner_user_id, allocation_total, status) VALUES ($1,$2,$3) RETURNING id",
|
||||
)
|
||||
.bind(user_id)
|
||||
.bind(total)
|
||||
.bind(status),
|
||||
)
|
||||
.await
|
||||
.unwrap()
|
||||
.get("id");
|
||||
let key_id: Uuid = pool
|
||||
.fetch_one(
|
||||
sqlx::query(
|
||||
"INSERT INTO api_keys (account_id, key_hash, key_prefix, limit_kind, limit_value) \
|
||||
VALUES ($1,$2,'sk-test','percent',100) RETURNING id",
|
||||
)
|
||||
.bind(account_id)
|
||||
.bind(sha256(raw)),
|
||||
)
|
||||
.await
|
||||
.unwrap()
|
||||
.get("id");
|
||||
(account_id, key_id)
|
||||
}
|
||||
|
||||
fn client() -> reqwest::Client {
|
||||
reqwest::Client::new()
|
||||
}
|
||||
|
||||
async fn post(
|
||||
c: &reqwest::Client,
|
||||
url: String,
|
||||
body: Value,
|
||||
bearer: Option<&str>,
|
||||
) -> reqwest::Response {
|
||||
let mut req = c.post(url).json(&body);
|
||||
if let Some(b) = bearer {
|
||||
req = req.bearer_auth(b);
|
||||
}
|
||||
req.send().await.unwrap()
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn resolve_reserve_settle_round_trip() {
|
||||
let Some((base, pool)) = spawn_or_skip("resolve_reserve_settle_round_trip").await else {
|
||||
return;
|
||||
};
|
||||
let raw = format!("sk-{}", Uuid::new_v4());
|
||||
let (account_id, key_id) = seed_key(&pool, 1000, &raw, false).await;
|
||||
let c = client();
|
||||
|
||||
// resolve
|
||||
let r = post(
|
||||
&c,
|
||||
format!("{base}/authz/v1/resolve"),
|
||||
json!({"api_key": raw}),
|
||||
Some(CLIENT_TOKEN),
|
||||
)
|
||||
.await;
|
||||
assert_eq!(r.status(), 200);
|
||||
let body: Value = r.json().await.unwrap();
|
||||
assert_eq!(body["principal"]["account_id"], account_id.to_string());
|
||||
assert_eq!(body["principal"]["key_id"], key_id.to_string());
|
||||
assert_eq!(body["snapshot"]["hard_cap"], 1000);
|
||||
|
||||
// reserve 400
|
||||
let r = post(
|
||||
&c,
|
||||
format!("{base}/authz/v1/reserve"),
|
||||
json!({"account_id": account_id, "key_id": key_id, "max_tokens": 400}),
|
||||
Some(CLIENT_TOKEN),
|
||||
)
|
||||
.await;
|
||||
assert_eq!(r.status(), 200);
|
||||
let body: Value = r.json().await.unwrap();
|
||||
let rid = body["reservation_id"].as_i64().expect("granted");
|
||||
|
||||
// settle 150
|
||||
let r = post(
|
||||
&c,
|
||||
format!("{base}/authz/v1/settle"),
|
||||
json!({"reservation_id": rid, "actual_tokens": 150}),
|
||||
Some(CLIENT_TOKEN),
|
||||
)
|
||||
.await;
|
||||
assert_eq!(r.status(), 204);
|
||||
|
||||
// snapshot reflects spend
|
||||
let r = post(
|
||||
&c,
|
||||
format!("{base}/authz/v1/snapshot"),
|
||||
json!({"account_id": account_id, "key_id": key_id}),
|
||||
Some(CLIENT_TOKEN),
|
||||
)
|
||||
.await;
|
||||
let body: Value = r.json().await.unwrap();
|
||||
assert_eq!(body["spent"], 150);
|
||||
assert_eq!(body["reserved"], 0);
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn over_cap_reserve_is_rejected_not_errored() {
|
||||
let Some((base, pool)) = spawn_or_skip("over_cap_reserve_is_rejected_not_errored").await else {
|
||||
return;
|
||||
};
|
||||
let raw = format!("sk-{}", Uuid::new_v4());
|
||||
let (account_id, key_id) = seed_key(&pool, 100, &raw, false).await;
|
||||
let c = client();
|
||||
let r = post(
|
||||
&c,
|
||||
format!("{base}/authz/v1/reserve"),
|
||||
json!({"account_id": account_id, "key_id": key_id, "max_tokens": 999}),
|
||||
Some(CLIENT_TOKEN),
|
||||
)
|
||||
.await;
|
||||
assert_eq!(r.status(), 200, "budget refusal is an authoritative 200");
|
||||
let body: Value = r.json().await.unwrap();
|
||||
assert!(body["reservation_id"].is_null());
|
||||
assert_eq!(body["rejected"]["kind"], "insufficient_quota");
|
||||
assert_eq!(body["rejected"]["available"], 100);
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn deactivated_account_resolves_as_invalid_no_clue() {
|
||||
let Some((base, pool)) = spawn_or_skip("deactivated_account_resolves_as_invalid_no_clue").await
|
||||
else {
|
||||
return;
|
||||
};
|
||||
let raw = format!("sk-{}", Uuid::new_v4());
|
||||
seed_key(&pool, 1000, &raw, true).await; // deactivated
|
||||
let c = client();
|
||||
let r = post(
|
||||
&c,
|
||||
format!("{base}/authz/v1/resolve"),
|
||||
json!({"api_key": raw}),
|
||||
Some(CLIENT_TOKEN),
|
||||
)
|
||||
.await;
|
||||
// Indistinguishable from an unknown key.
|
||||
assert_eq!(r.status(), 401);
|
||||
let body: Value = r.json().await.unwrap();
|
||||
assert_eq!(body["error"]["code"], "invalid_api_key");
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn missing_client_auth_is_401_before_db() {
|
||||
let Some((base, pool)) = spawn_or_skip("missing_client_auth_is_401_before_db").await else {
|
||||
return;
|
||||
};
|
||||
let raw = format!("sk-{}", Uuid::new_v4());
|
||||
seed_key(&pool, 1000, &raw, false).await;
|
||||
let c = client();
|
||||
// No bearer → rejected by client_auth.
|
||||
let r = post(
|
||||
&c,
|
||||
format!("{base}/authz/v1/resolve"),
|
||||
json!({"api_key": raw}),
|
||||
None,
|
||||
)
|
||||
.await;
|
||||
assert_eq!(r.status(), 401);
|
||||
// Wrong bearer → also rejected.
|
||||
let r = post(
|
||||
&c,
|
||||
format!("{base}/authz/v1/resolve"),
|
||||
json!({"api_key": raw}),
|
||||
Some("wrong"),
|
||||
)
|
||||
.await;
|
||||
assert_eq!(r.status(), 401);
|
||||
}
|
||||
@@ -21,3 +21,17 @@ url = "postgres://helexa:helexa@localhost/helexa_upstream"
|
||||
# When this many accounts share one registration fingerprint, all are
|
||||
# silently deactivated (no notice to the user).
|
||||
# fingerprint_account_threshold = 5
|
||||
|
||||
# -- Client auth: credentials operators' cortexes present to /authz/v1.
|
||||
# Each token maps to an operator_id (served-usage attribution). When no
|
||||
# tokens are configured the authz surface is OPEN (dev only). Distinct from
|
||||
# end-user API keys, which ride inside the resolve request body.
|
||||
# [[client_auth.tokens]]
|
||||
# token = "replace-with-a-strong-shared-secret"
|
||||
# operator_id = "lair-cafe"
|
||||
|
||||
[authz]
|
||||
# Open reservations older than this are swept (released), self-healing a
|
||||
# reservation whose settle/release from a cortex was lost.
|
||||
# reservation_ttl_secs = 120
|
||||
# sweep_interval_secs = 60
|
||||
|
||||
20
helexa.ai/.env.example
Normal file
20
helexa.ai/.env.example
Normal file
@@ -0,0 +1,20 @@
|
||||
# helexa.ai frontend env. Copy to .env.local for local dev (gitignored).
|
||||
|
||||
# Mesh data-plane (helexa-router, OpenAI-compatible inference). In dev,
|
||||
# vite proxies /v1 and /health here.
|
||||
VITE_ROUTER_BASE_URL=http://localhost:8088
|
||||
|
||||
# Account control-plane (helexa-upstream). In dev, vite proxies /api here
|
||||
# (rewritten to /web/v1).
|
||||
VITE_ACCOUNT_BASE_URL=http://localhost:8090
|
||||
|
||||
# Public-beta banner.
|
||||
VITE_PUBLIC_BETA=true
|
||||
|
||||
# Models for the chat workspace (F3+).
|
||||
# VITE_ANON_MODEL=...
|
||||
# VITE_DEFAULT_MODEL=...
|
||||
|
||||
# Develop the account dashboard (F4) against an in-browser mock before the
|
||||
# upstream account API ships.
|
||||
# VITE_USE_MOCK_ACCOUNT_API=true
|
||||
6
helexa.ai/.gitignore
vendored
Normal file
6
helexa.ai/.gitignore
vendored
Normal file
@@ -0,0 +1,6 @@
|
||||
node_modules
|
||||
dist
|
||||
*.local
|
||||
.env.local
|
||||
.env.*.local
|
||||
*.tsbuildinfo
|
||||
34
helexa.ai/README.md
Normal file
34
helexa.ai/README.md
Normal file
@@ -0,0 +1,34 @@
|
||||
# helexa.ai
|
||||
|
||||
The public-beta frontend for the helexa mesh: a chat-first landing experience
|
||||
(anonymous + authenticated, with all chat history kept client-side in
|
||||
IndexedDB — no server-side history), a `/mission` page on European digital
|
||||
sovereignty, and full account self-service (register, recover, manage API
|
||||
keys, set per-key limits, redeem top-up codes) against `helexa-upstream`.
|
||||
|
||||
Vite + React (SWC) + TypeScript + react-bootstrap + react-router + react-i18next.
|
||||
Lives as a top-level folder in the cortex monorepo; it is **not** a Cargo crate.
|
||||
|
||||
## Develop
|
||||
|
||||
```sh
|
||||
cd helexa.ai
|
||||
npm install
|
||||
cp .env.example .env.local # adjust backend URLs
|
||||
npm run dev # vite dev server, proxies /v1+/health → router, /api → upstream
|
||||
```
|
||||
|
||||
Other scripts: `npm run build` (`tsc -b && vite build` → `dist/`), `npm run
|
||||
preview`, `npm run lint`, `npm run typecheck`.
|
||||
|
||||
In dev, `vite.config.ts` proxies the mesh data-plane (helexa-router) and the
|
||||
account control-plane (helexa-upstream) same-origin. Run a local router
|
||||
(`cargo run -p helexa-router`) for the chat path and a local helexa-upstream
|
||||
for the account path.
|
||||
|
||||
## Status
|
||||
|
||||
F0 scaffold. Theming + i18n (33 languages, usage-ordered selector), the
|
||||
`/mission` page, the chat workspace (Dexie + streaming), and the account
|
||||
dashboard land in subsequent phases — see
|
||||
`~/.claude/plans/we-need-to-plan-modular-graham.md`.
|
||||
23
helexa.ai/eslint.config.js
Normal file
23
helexa.ai/eslint.config.js
Normal file
@@ -0,0 +1,23 @@
|
||||
import js from "@eslint/js";
|
||||
import globals from "globals";
|
||||
import reactHooks from "eslint-plugin-react-hooks";
|
||||
import reactRefresh from "eslint-plugin-react-refresh";
|
||||
import tseslint from "typescript-eslint";
|
||||
import { defineConfig, globalIgnores } from "eslint/config";
|
||||
|
||||
export default defineConfig([
|
||||
globalIgnores(["dist"]),
|
||||
{
|
||||
files: ["**/*.{ts,tsx}"],
|
||||
extends: [
|
||||
js.configs.recommended,
|
||||
tseslint.configs.recommended,
|
||||
reactHooks.configs.flat.recommended,
|
||||
reactRefresh.configs.vite,
|
||||
],
|
||||
languageOptions: {
|
||||
ecmaVersion: 2020,
|
||||
globals: globals.browser,
|
||||
},
|
||||
},
|
||||
]);
|
||||
24
helexa.ai/index.html
Normal file
24
helexa.ai/index.html
Normal file
@@ -0,0 +1,24 @@
|
||||
<!doctype html>
|
||||
<html lang="en">
|
||||
<head>
|
||||
<meta charset="UTF-8" />
|
||||
<meta name="viewport" content="width=device-width, initial-scale=1.0" />
|
||||
<title>helexa.ai</title>
|
||||
<meta name="title" content="helexa.ai" />
|
||||
<meta
|
||||
name="description"
|
||||
content="helexa — near-frontier AI on a sovereign, operator-run mesh. Chat now; bring your own key."
|
||||
/>
|
||||
<meta property="og:type" content="website" />
|
||||
<meta property="og:url" content="https://helexa.ai/" />
|
||||
<meta property="og:title" content="helexa.ai" />
|
||||
<meta
|
||||
property="og:description"
|
||||
content="helexa — near-frontier AI on a sovereign, operator-run mesh."
|
||||
/>
|
||||
</head>
|
||||
<body>
|
||||
<div id="root"></div>
|
||||
<script type="module" src="/src/main.tsx"></script>
|
||||
</body>
|
||||
</html>
|
||||
4115
helexa.ai/package-lock.json
generated
Normal file
4115
helexa.ai/package-lock.json
generated
Normal file
File diff suppressed because it is too large
Load Diff
40
helexa.ai/package.json
Normal file
40
helexa.ai/package.json
Normal file
@@ -0,0 +1,40 @@
|
||||
{
|
||||
"name": "helexa.ai",
|
||||
"private": true,
|
||||
"version": "0.0.0",
|
||||
"type": "module",
|
||||
"scripts": {
|
||||
"dev": "vite",
|
||||
"build": "tsc -b && vite build",
|
||||
"preview": "vite preview",
|
||||
"lint": "eslint .",
|
||||
"typecheck": "tsc -b"
|
||||
},
|
||||
"dependencies": {
|
||||
"@fingerprintjs/fingerprintjs": "^4.6.2",
|
||||
"bootstrap": "^5.3.8",
|
||||
"dexie": "^4.2.0",
|
||||
"dexie-react-hooks": "^4.2.0",
|
||||
"i18next": "^25.7.1",
|
||||
"react": "^19.2.0",
|
||||
"react-bootstrap": "^2.10.10",
|
||||
"react-dom": "^19.2.0",
|
||||
"react-i18next": "^16.4.0",
|
||||
"react-icons": "^5.5.0",
|
||||
"react-router-dom": "^7.10.1"
|
||||
},
|
||||
"devDependencies": {
|
||||
"@eslint/js": "^9.39.1",
|
||||
"@types/node": "^24.10.1",
|
||||
"@types/react": "^19.2.5",
|
||||
"@types/react-dom": "^19.2.3",
|
||||
"@vitejs/plugin-react-swc": "^4.2.0",
|
||||
"eslint": "^9.39.1",
|
||||
"eslint-plugin-react-hooks": "^7.0.1",
|
||||
"eslint-plugin-react-refresh": "^0.4.24",
|
||||
"globals": "^16.5.0",
|
||||
"typescript": "~5.9.3",
|
||||
"typescript-eslint": "^8.46.4",
|
||||
"vite": "^7.2.0"
|
||||
}
|
||||
}
|
||||
12
helexa.ai/src/App.tsx
Normal file
12
helexa.ai/src/App.tsx
Normal file
@@ -0,0 +1,12 @@
|
||||
import { Container } from "react-bootstrap";
|
||||
|
||||
// F0 scaffold shell. Theming, i18n, routing, the chat workspace, mission
|
||||
// page and account dashboard land in the F1+ phases.
|
||||
export default function App() {
|
||||
return (
|
||||
<Container className="py-5">
|
||||
<h1 className="mb-2">helexa.ai</h1>
|
||||
<p className="text-muted">Public beta — coming online.</p>
|
||||
</Container>
|
||||
);
|
||||
}
|
||||
16
helexa.ai/src/index.css
Normal file
16
helexa.ai/src/index.css
Normal file
@@ -0,0 +1,16 @@
|
||||
/* Minimal reset; the full theme (CSS custom properties, light/dark, accent
|
||||
* palette) is ported from the reference site in F1. */
|
||||
:root {
|
||||
color-scheme: light dark;
|
||||
}
|
||||
|
||||
* {
|
||||
box-sizing: border-box;
|
||||
}
|
||||
|
||||
html,
|
||||
body,
|
||||
#root {
|
||||
margin: 0;
|
||||
min-height: 100vh;
|
||||
}
|
||||
11
helexa.ai/src/main.tsx
Normal file
11
helexa.ai/src/main.tsx
Normal file
@@ -0,0 +1,11 @@
|
||||
import { StrictMode } from "react";
|
||||
import { createRoot } from "react-dom/client";
|
||||
import "bootstrap/dist/css/bootstrap.min.css";
|
||||
import "./index.css";
|
||||
import App from "./App.tsx";
|
||||
|
||||
createRoot(document.getElementById("root")!).render(
|
||||
<StrictMode>
|
||||
<App />
|
||||
</StrictMode>,
|
||||
);
|
||||
28
helexa.ai/tsconfig.app.json
Normal file
28
helexa.ai/tsconfig.app.json
Normal file
@@ -0,0 +1,28 @@
|
||||
{
|
||||
"compilerOptions": {
|
||||
"tsBuildInfoFile": "./node_modules/.tmp/tsconfig.app.tsbuildinfo",
|
||||
"target": "ES2022",
|
||||
"useDefineForClassFields": true,
|
||||
"lib": ["ES2022", "DOM", "DOM.Iterable"],
|
||||
"module": "ESNext",
|
||||
"types": ["vite/client"],
|
||||
"skipLibCheck": true,
|
||||
|
||||
/* Bundler mode */
|
||||
"moduleResolution": "bundler",
|
||||
"allowImportingTsExtensions": true,
|
||||
"verbatimModuleSyntax": true,
|
||||
"moduleDetection": "force",
|
||||
"noEmit": true,
|
||||
"jsx": "react-jsx",
|
||||
|
||||
/* Linting */
|
||||
"strict": true,
|
||||
"noUnusedLocals": true,
|
||||
"noUnusedParameters": true,
|
||||
"erasableSyntaxOnly": true,
|
||||
"noFallthroughCasesInSwitch": true,
|
||||
"noUncheckedSideEffectImports": true
|
||||
},
|
||||
"include": ["src"]
|
||||
}
|
||||
7
helexa.ai/tsconfig.json
Normal file
7
helexa.ai/tsconfig.json
Normal file
@@ -0,0 +1,7 @@
|
||||
{
|
||||
"files": [],
|
||||
"references": [
|
||||
{ "path": "./tsconfig.app.json" },
|
||||
{ "path": "./tsconfig.node.json" }
|
||||
]
|
||||
}
|
||||
26
helexa.ai/tsconfig.node.json
Normal file
26
helexa.ai/tsconfig.node.json
Normal file
@@ -0,0 +1,26 @@
|
||||
{
|
||||
"compilerOptions": {
|
||||
"tsBuildInfoFile": "./node_modules/.tmp/tsconfig.node.tsbuildinfo",
|
||||
"target": "ES2023",
|
||||
"lib": ["ES2023"],
|
||||
"module": "ESNext",
|
||||
"types": ["node"],
|
||||
"skipLibCheck": true,
|
||||
|
||||
/* Bundler mode */
|
||||
"moduleResolution": "bundler",
|
||||
"allowImportingTsExtensions": true,
|
||||
"verbatimModuleSyntax": true,
|
||||
"moduleDetection": "force",
|
||||
"noEmit": true,
|
||||
|
||||
/* Linting */
|
||||
"strict": true,
|
||||
"noUnusedLocals": true,
|
||||
"noUnusedParameters": true,
|
||||
"erasableSyntaxOnly": true,
|
||||
"noFallthroughCasesInSwitch": true,
|
||||
"noUncheckedSideEffectImports": true
|
||||
},
|
||||
"include": ["vite.config.ts"]
|
||||
}
|
||||
29
helexa.ai/vite.config.ts
Normal file
29
helexa.ai/vite.config.ts
Normal file
@@ -0,0 +1,29 @@
|
||||
import { defineConfig, loadEnv } from "vite";
|
||||
import react from "@vitejs/plugin-react-swc";
|
||||
|
||||
// During `vite dev`, proxy the mesh data-plane (helexa-router, OpenAI-
|
||||
// compatible) and the account control-plane (helexa-upstream) so the SPA
|
||||
// talks to them same-origin without CORS. Targets are overridable via env.
|
||||
// VITE_ROUTER_BASE_URL — helexa-router (default http://localhost:8088)
|
||||
// VITE_ACCOUNT_BASE_URL — helexa-upstream (default http://localhost:8090)
|
||||
export default defineConfig(({ mode }) => {
|
||||
const env = loadEnv(mode, process.cwd(), "VITE_");
|
||||
const router = env.VITE_ROUTER_BASE_URL || "http://localhost:8088";
|
||||
const account = env.VITE_ACCOUNT_BASE_URL || "http://localhost:8090";
|
||||
return {
|
||||
plugins: [react()],
|
||||
server: {
|
||||
proxy: {
|
||||
"/v1": { target: router, changeOrigin: true },
|
||||
"/health": { target: router, changeOrigin: true },
|
||||
// The frontend calls /api/*; helexa-upstream serves /web/v1/*.
|
||||
"/api": {
|
||||
target: account,
|
||||
changeOrigin: true,
|
||||
rewrite: (p) => p.replace(/^\/api/, "/web/v1"),
|
||||
},
|
||||
},
|
||||
},
|
||||
build: { outDir: "dist" },
|
||||
};
|
||||
});
|
||||
Reference in New Issue
Block a user