feat: sub2api T05/T08/T09/T13/T14 + bump to 3.0.0-rc.7

CHANGELOG.md

@@ -6,9 +6,9 @@
 
 ---
 
-## [3.0.0-rc.6] — 2026-03-23 _(What's New vs v2.9.5 — will be released as v3.0.0)_
+## [3.0.0-rc.7] — 2026-03-23 _(What's New vs v2.9.5 — will be released as v3.0.0)_
 
-> **Upgrade from v2.9.5:** 16 issues resolved · 2 community PRs merged · 2 new providers · 7 new API endpoints · 3 new features · DB migration 008+009 · 832 tests passing · 10 sub2api gap improvements.
+> **Upgrade from v2.9.5:** 16 issues resolved · 2 community PRs merged · 2 new providers · 7 new API endpoints · 3 new features · DB migration 008+009 · 832 tests passing · 15 sub2api gap improvements (T01–T15 complete).
 
 ### 🆕 New Providers
 
@@ -111,6 +111,22 @@ OmniRoute now automatically refreshes model lists for connected providers every
 
 ---
 
+## [3.0.0-rc.7] - 2026-03-23
+
+### 🔧 Improvements (sub2api Gap Analysis — T05, T08, T09, T13, T14)
+
+- **T05** — Rate-limit DB persistence: `setConnectionRateLimitUntil()`, `isConnectionRateLimited()`, `getRateLimitedConnections()` in `providers.ts`. The existing `rate_limited_until` column is now exposed as a dedicated API — OAuth token refresh must NOT touch this field to prevent rate-limit loops.
+- **T08** — Per-API-key session limit: `max_sessions INTEGER DEFAULT 0` added to `api_keys` via auto-migration. `sessionManager.ts` gains `registerKeySession()`, `unregisterKeySession()`, `checkSessionLimit()`, and `getActiveSessionCountForKey()`. Callers in `chatCore.js` can enforce the limit and decrement on `req.close`.
+- **T09** — Codex vs Spark rate-limit scopes: `getCodexModelScope()` and `getCodexRateLimitKey()` in `codex.ts`. Standard models (`gpt-5.x-codex`, `codex-mini`) get scope `"codex"`; spark models (`codex-spark*`) get scope `"spark"`. Rate-limit keys should be `${accountId}:${scope}` so exhausting one pool doesn't block the other.
+- **T13** — Stale quota display fix: `getEffectiveQuotaUsage(used, resetAt)` returns `0` when the reset window has passed; `formatResetCountdown(resetAt)` returns a human-readable countdown string (e.g. `"2h 35m"`). Both exported from `providers.ts` + `localDb.ts` for dashboard consumption.
+- **T14** — Proxy fast-fail: new `src/lib/proxyHealth.ts` with `isProxyReachable(proxyUrl, timeoutMs=2000)` (TCP check, ≤2s instead of 30s timeout), `getCachedProxyHealth()`, `invalidateProxyHealth()`, and `getAllProxyHealthStatuses()`. Results cached 30s by default; configurable via `PROXY_FAST_FAIL_TIMEOUT_MS` / `PROXY_HEALTH_CACHE_TTL_MS`.
+
+### 🧪 Tests
+
+- Test suite: **832 tests, 0 failures**
+
+---
+
 ## [3.0.0-rc.6] - 2026-03-23
 
 ### 🔧 Bug Fixes & Improvements (sub2api Gap Analysis — T01–T15)

docs/openapi.yaml

@@ -1,7 +1,7 @@
 openapi: 3.1.0
 info:
   title: OmniRoute API
-  version: 3.0.0-rc.6
+  version: 3.0.0-rc.7
   description: |
     OmniRoute is a local-first AI API proxy router. It provides an OpenAI-compatible
     endpoint that routes requests to multiple AI providers with load balancing,

open-sse/executors/codex.ts

@@ -3,6 +3,46 @@ import { CODEX_DEFAULT_INSTRUCTIONS } from "../config/codexInstructions.ts";
 import { PROVIDERS } from "../config/constants.ts";
 import { refreshCodexToken } from "../services/tokenRefresh.ts";
 
+// ─── T09: Codex vs Spark Scope-Aware Rate Limiting ────────────────────────
+// Codex has two independent quota pools: "codex" (standard) and "spark" (premium).
+// Exhausting one should NOT block requests to the other.
+// Ref: sub2api PR #1129 (feat(openai): split codex spark rate limiting from codex)
+
+/**
+ * Maps model name substrings to their rate-limit scope.
+ * Checked in order — first match wins.
+ */
+const CODEX_SCOPE_PATTERNS: Array<{ pattern: string; scope: "codex" | "spark" }> = [
+  { pattern: "codex-spark", scope: "spark" },
+  { pattern: "spark", scope: "spark" },
+  { pattern: "codex", scope: "codex" },
+  { pattern: "gpt-5", scope: "codex" }, // gpt-5.2-codex, gpt-5.3-codex, etc.
+];
+
+/**
+ * T09: Determine the rate-limit scope for a Codex model.
+ * Use this key as the suffix for per-scope rate limit state:
+ *   `${accountId}:${getModelScope(model)}`
+ *
+ * @param model - The Codex model ID (e.g. "gpt-5.3-codex", "codex-spark-mini")
+ * @returns "codex" | "spark"
+ */
+export function getCodexModelScope(model: string): "codex" | "spark" {
+  const lower = model.toLowerCase();
+  for (const { pattern, scope } of CODEX_SCOPE_PATTERNS) {
+    if (lower.includes(pattern)) return scope;
+  }
+  return "codex"; // default scope
+}
+
+/**
+ * T09: Get the scope-keyed rate limit identifier for an account+model combination.
+ * Use this as the key for rateLimitState maps to ensure scope isolation.
+ */
+export function getCodexRateLimitKey(accountId: string, model: string): string {
+  return `${accountId}:${getCodexModelScope(model)}`;
+}
+
 /**
  * T03: Parsed quota snapshot from Codex response headers.
  * Codex includes per-account usage windows that allow precise reset scheduling.

open-sse/services/sessionManager.ts

@@ -173,6 +173,69 @@ export function getActiveSessions(): Array<SessionEntry & { sessionId: string; a
  */
 export function clearSessions(): void {
   sessions.clear();
+  activeSessionsByKey.clear();
+}
+
+// ─── T08: Per-API-Key Session Limit ─────────────────────────────────────────
+// Tracks concurrent sticky sessions per API key and enforces max_sessions limits.
+// Ref: sub2api PR #634 (fix: stabilize session hash + add user-level session limit)
+
+// Map: apiKeyId → Set<sessionId>
+const activeSessionsByKey = new Map<string, Set<string>>();
+
+/**
+ * T08: Get the number of currently active sessions for an API key.
+ * @param apiKeyId - The API key's UUID from the database
+ */
+export function getActiveSessionCountForKey(apiKeyId: string): number {
+  return activeSessionsByKey.get(apiKeyId)?.size ?? 0;
+}
+
+/**
+ * T08: Register a session as belonging to an API key.
+ * Call this after session creation is allowed (i.e., limit check passed).
+ */
+export function registerKeySession(apiKeyId: string, sessionId: string): void {
+  if (!activeSessionsByKey.has(apiKeyId)) {
+    activeSessionsByKey.set(apiKeyId, new Set());
+  }
+  activeSessionsByKey.get(apiKeyId)!.add(sessionId);
+}
+
+/**
+ * T08: Unregister a session from an API key's active set.
+ * Call this when the request closes or the session TTL expires.
+ */
+export function unregisterKeySession(apiKeyId: string, sessionId: string): void {
+  activeSessionsByKey.get(apiKeyId)?.delete(sessionId);
+  // Clean up empty sets to avoid memory leaks
+  if (activeSessionsByKey.get(apiKeyId)?.size === 0) {
+    activeSessionsByKey.delete(apiKeyId);
+  }
+}
+
+/**
+ * T08: Check whether adding a new session would exceed the key's max_sessions limit.
+ * Returns null if allowed, or an error object to return as a 429 response.
+ *
+ * @param apiKeyId - The API key's UUID
+ * @param maxSessions - The limit from the DB (0 = unlimited)
+ */
+export function checkSessionLimit(
+  apiKeyId: string,
+  maxSessions: number
+): { code: "SESSION_LIMIT_EXCEEDED"; message: string; limit: number; current: number } | null {
+  if (!maxSessions || maxSessions <= 0) return null; // unlimited
+  const current = getActiveSessionCountForKey(apiKeyId);
+  if (current < maxSessions) return null;
+  return {
+    code: "SESSION_LIMIT_EXCEEDED",
+    message:
+      `You have reached the maximum number of active sessions (${maxSessions}). ` +
+      `Please close unused sessions or wait for them to expire.`,
+    limit: maxSessions,
+    current,
+  };
 }
 
 /**

package.json

@@ -1,6 +1,6 @@
 {
   "name": "omniroute",
-  "version": "3.0.0-rc.6",
+  "version": "3.0.0-rc.7",
   "description": "Smart AI Router with auto fallback — route to FREE & cheap models, zero downtime. Works with Cursor, Cline, Claude Desktop, Codex, and any OpenAI-compatible tool.",
   "type": "module",
   "bin": {

src/lib/db/apiKeys.ts

@@ -40,6 +40,8 @@ interface ApiKeyMetadata {
   accessSchedule: AccessSchedule | null;
   maxRequestsPerDay: number | null;
   maxRequestsPerMinute: number | null;
+  // T08: Per-key max concurrent sticky sessions (0 = unlimited)
+  maxSessions: number;
 }
 
 interface ApiKeyRow extends JsonRecord {
@@ -197,6 +199,11 @@ function ensureApiKeysColumns(db: ApiKeysDbLike) {
       db.exec("ALTER TABLE api_keys ADD COLUMN max_requests_per_minute INTEGER");
       console.log("[DB] Added api_keys.max_requests_per_minute column");
     }
+    // T08: max concurrent sticky sessions per key (0 = unlimited)
+    if (!columnNames.has("max_sessions")) {
+      db.exec("ALTER TABLE api_keys ADD COLUMN max_sessions INTEGER NOT NULL DEFAULT 0");
+      console.log("[DB] Added api_keys.max_sessions column");
+    }
     _schemaChecked = true;
   } catch (error) {
     const message = error instanceof Error ? error.message : String(error);
@@ -222,7 +229,7 @@ function getPreparedStatements(db: ApiKeysDbLike): ApiKeysStatements {
     _stmtGetKeyById = db.prepare<ApiKeyRow>("SELECT * FROM api_keys WHERE id = ?");
     _stmtValidateKey = db.prepare<JsonRecord>("SELECT 1 FROM api_keys WHERE key = ?");
     _stmtGetKeyMetadata = db.prepare<ApiKeyRow>(
-      "SELECT id, name, machine_id, allowed_models, allowed_connections, no_log, auto_resolve, is_active, access_schedule, max_requests_per_day, max_requests_per_minute FROM api_keys WHERE key = ?"
+      "SELECT id, name, machine_id, allowed_models, allowed_connections, no_log, auto_resolve, is_active, access_schedule, max_requests_per_day, max_requests_per_minute, max_sessions FROM api_keys WHERE key = ?"
     );
     _stmtInsertKey = db.prepare(
       "INSERT INTO api_keys (id, name, key, machine_id, allowed_models, no_log, created_at) VALUES (?, ?, ?, ?, ?, ?, ?)"
@@ -418,6 +425,8 @@ export async function updateApiKeyPermissions(
         accessSchedule?: AccessSchedule | null;
         maxRequestsPerDay?: number | null;
         maxRequestsPerMinute?: number | null;
+        // T08: max concurrent sessions for this key (0 = unlimited)
+        maxSessions?: number | null;
       }
 ) {
   const db = getDbInstance() as ApiKeysDbLike;
@@ -436,6 +445,7 @@ export async function updateApiKeyPermissions(
           accessSchedule: update.accessSchedule,
           maxRequestsPerDay: update.maxRequestsPerDay,
           maxRequestsPerMinute: update.maxRequestsPerMinute,
+          maxSessions: (update as { maxSessions?: number | null }).maxSessions,
         };
 
   if (
@@ -447,7 +457,8 @@ export async function updateApiKeyPermissions(
     normalized.isActive === undefined &&
     normalized.accessSchedule === undefined &&
     normalized.maxRequestsPerDay === undefined &&
-    normalized.maxRequestsPerMinute === undefined
+    normalized.maxRequestsPerMinute === undefined &&
+    (normalized as Record<string, unknown>).maxSessions === undefined
   ) {
     return false;
   }
@@ -464,6 +475,7 @@ export async function updateApiKeyPermissions(
     accessSchedule?: string | null;
     maxRequestsPerDay?: number | null;
     maxRequestsPerMinute?: number | null;
+    maxSessions?: number;
   } = { id };
 
   if (normalized.name !== undefined) {
@@ -514,6 +526,12 @@ export async function updateApiKeyPermissions(
     params.maxRequestsPerMinute = normalized.maxRequestsPerMinute;
   }
 
+  const maxSessionsUpdate = (normalized as Record<string, unknown>).maxSessions;
+  if (maxSessionsUpdate !== undefined) {
+    updates.push("max_sessions = @maxSessions");
+    params.maxSessions = typeof maxSessionsUpdate === "number" ? Math.max(0, maxSessionsUpdate) : 0;
+  }
+
   const result = db.prepare(`UPDATE api_keys SET ${updates.join(", ")} WHERE id = @id`).run(params);
 
   if (result.changes === 0) return false;
@@ -605,6 +623,8 @@ export async function getApiKeyMetadata(
   const rawMaxRPD = record.max_requests_per_day ?? record.maxRequestsPerDay;
   const rawMaxRPM = record.max_requests_per_minute ?? record.maxRequestsPerMinute;
 
+  const rawMaxSessions = record.max_sessions ?? record.maxSessions;
+
   const metadata: ApiKeyMetadata = {
     id: metadataId,
     name: metadataName,
@@ -619,6 +639,8 @@ export async function getApiKeyMetadata(
     accessSchedule: parseAccessSchedule(record.access_schedule ?? record.accessSchedule),
     maxRequestsPerDay: typeof rawMaxRPD === "number" && rawMaxRPD > 0 ? rawMaxRPD : null,
     maxRequestsPerMinute: typeof rawMaxRPM === "number" && rawMaxRPM > 0 ? rawMaxRPM : null,
+    // T08: max concurrent sessions; 0 = unlimited (default & backward-compatible)
+    maxSessions: typeof rawMaxSessions === "number" && rawMaxSessions > 0 ? rawMaxSessions : 0,
   };
 
   if (!metadata.id) {

src/lib/db/providers.ts

@@ -513,3 +513,98 @@ export async function deleteProviderNode(id: string) {
   backupDbFile("pre-write");
   return rowToCamel(existing);
 }
+
+// ──────────────── T05: Rate-Limit DB Persistence ──────────────────────────
+// Allows rate-limit state to survive token refresh without being accidentally
+// cleared. DB column rate_limited_until already exists in schema.
+// Ref: sub2api PR #1218 (fix(openai): prevent rescheduling rate-limited accounts)
+
+/**
+ * T05: Persist when a connection is rate-limited, directly in DB.
+ * This survives token refresh — OAuth flows must NOT override this field.
+ *
+ * @param connectionId - The provider_connections.id
+ * @param until - Epoch ms when the rate limit expires (null to clear)
+ */
+export function setConnectionRateLimitUntil(connectionId: string, until: number | null): void {
+  const db = getDbInstance() as unknown as DbLike;
+  db.prepare(
+    "UPDATE provider_connections SET rate_limited_until = ?, updated_at = ? WHERE id = ?"
+  ).run(until, new Date().toISOString(), connectionId);
+  invalidateDbCache("connections");
+}
+
+/**
+ * T05: Check if a connection is currently rate-limited (DB-backed).
+ * Use this before account selection to skip transiently rate-limited accounts.
+ *
+ * @returns true if rate_limited_until is set and in the future
+ */
+export function isConnectionRateLimited(connectionId: string): boolean {
+  const db = getDbInstance() as unknown as DbLike;
+  const row = db
+    .prepare("SELECT rate_limited_until FROM provider_connections WHERE id = ?")
+    .get(connectionId) as { rate_limited_until?: number | null } | undefined;
+  if (!row?.rate_limited_until) return false;
+  return Date.now() < row.rate_limited_until;
+}
+
+/**
+ * T05: Get all connections for a provider that are currently rate-limited.
+ * Returns an array of { id, rateLimitedUntil } for dashboard display.
+ */
+export function getRateLimitedConnections(
+  provider: string
+): Array<{ id: string; rateLimitedUntil: number }> {
+  const db = getDbInstance() as unknown as DbLike;
+  const now = Date.now();
+  const rows = db
+    .prepare(
+      "SELECT id, rate_limited_until FROM provider_connections WHERE provider = ? AND rate_limited_until > ?"
+    )
+    .all(provider, now) as Array<{ id: string; rate_limited_until: number }>;
+  return rows.map((r) => ({ id: r.id, rateLimitedUntil: r.rate_limited_until }));
+}
+
+// ──────────────── T13: Stale Quota Display Fix ─────────────────────────────
+// Codex/Claude quotas display stale cumulative usage after the window resets.
+// By comparing resetAt timestamp to now(), we can show 0 when window has passed.
+// Ref: sub2api PR #1171 (fix: quota display shows stale cumulative usage after reset)
+
+/**
+ * T13: Get effective quota usage, zeroing it out if the window has already reset.
+ *
+ * @param used - Stored usage value (tokens used in the window)
+ * @param resetAt - ISO-8601 string or epoch ms when the window resets, or null
+ * @returns Effective usage: 0 if window expired, original value otherwise
+ */
+export function getEffectiveQuotaUsage(
+  used: number,
+  resetAt: string | number | null | undefined
+): number {
+  if (!resetAt) return used;
+  const resetTime = typeof resetAt === "number" ? resetAt : new Date(resetAt).getTime();
+  if (isNaN(resetTime)) return used;
+  // Window has passed — display should show 0 (pending next snapshot)
+  if (Date.now() >= resetTime) return 0;
+  return used;
+}
+
+/**
+ * T13: Format a reset countdown as a human-readable string: "2h 35m" or "4m 30s".
+ * Returns null if resetAt is in the past or not set.
+ */
+export function formatResetCountdown(resetAt: string | number | null | undefined): string | null {
+  if (!resetAt) return null;
+  const resetTime = typeof resetAt === "number" ? resetAt : new Date(resetAt).getTime();
+  if (isNaN(resetTime)) return null;
+  const diffMs = resetTime - Date.now();
+  if (diffMs <= 0) return null;
+  const totalSeconds = Math.floor(diffMs / 1000);
+  const hours = Math.floor(totalSeconds / 3600);
+  const minutes = Math.floor((totalSeconds % 3600) / 60);
+  const seconds = totalSeconds % 60;
+  if (hours > 0) return `${hours}h ${minutes}m`;
+  if (minutes > 0) return `${minutes}m ${seconds}s`;
+  return `${seconds}s`;
+}

src/lib/localDb.ts

@@ -23,6 +23,15 @@ export {
   createProviderNode,
   updateProviderNode,
   deleteProviderNode,
+
+  // T05: Rate-limit DB persistence (survives token refresh)
+  setConnectionRateLimitUntil,
+  isConnectionRateLimited,
+  getRateLimitedConnections,
+
+  // T13: Stale quota display fix (zero out usage after window resets)
+  getEffectiveQuotaUsage,
+  formatResetCountdown,
 } from "./db/providers";
 
 export {

src/lib/proxyHealth.ts

@@ -0,0 +1,140 @@
+/**
+ * T14: Proxy Fast-Fail — TCP health check with in-memory cache.
+ *
+ * When a configured HTTP/SOCKS5 proxy is unreachable, every request
+ * through OmniRoute used to wait for the full PROXY_TIMEOUT_MS (30s)
+ * before failing. This module detects dead proxies in <2s via a quick
+ * TCP connection check, caching the result to avoid overhead per request.
+ *
+ * Ref: sub2api PR #1167 (fix: proxy-fast-fail)
+ */
+
+import { createConnection } from "node:net";
+
+// Configurable via env vars
+const FAST_FAIL_TIMEOUT_MS = parseInt(process.env.PROXY_FAST_FAIL_TIMEOUT_MS ?? "2000", 10);
+const HEALTH_CACHE_TTL_MS = parseInt(process.env.PROXY_HEALTH_CACHE_TTL_MS ?? "30000", 10);
+
+interface ProxyHealthEntry {
+  healthy: boolean;
+  checkedAt: number;
+  ttlMs: number;
+}
+
+// In-memory cache: proxyUrl → health entry
+const proxyHealthCache = new Map<string, ProxyHealthEntry>();
+
+/**
+ * T14: Perform a fast TCP check to see if a proxy host:port is reachable.
+ * Results are cached for `cacheTtlMs` (default 30s) to avoid checking every request.
+ *
+ * @param proxyUrl - Full proxy URL, e.g. http://user:pass@1.2.3.4:8080
+ * @param timeoutMs - TCP connection timeout (default 2000ms)
+ * @param cacheTtlMs - How long to cache the health result (default 30000ms)
+ * @returns true if proxy TCP port is open, false otherwise
+ */
+export async function isProxyReachable(
+  proxyUrl: string,
+  timeoutMs = FAST_FAIL_TIMEOUT_MS,
+  cacheTtlMs = HEALTH_CACHE_TTL_MS
+): Promise<boolean> {
+  const cached = proxyHealthCache.get(proxyUrl);
+  if (cached && Date.now() - cached.checkedAt < cached.ttlMs) {
+    return cached.healthy;
+  }
+
+  let url: URL;
+  try {
+    url = new URL(proxyUrl);
+  } catch {
+    // Malformed URL — treat as unreachable
+    proxyHealthCache.set(proxyUrl, {
+      healthy: false,
+      checkedAt: Date.now(),
+      ttlMs: cacheTtlMs,
+    });
+    return false;
+  }
+
+  const host = url.hostname;
+  const port = parseInt(url.port || defaultPortForScheme(url.protocol), 10);
+
+  if (!host || isNaN(port)) {
+    proxyHealthCache.set(proxyUrl, {
+      healthy: false,
+      checkedAt: Date.now(),
+      ttlMs: cacheTtlMs,
+    });
+    return false;
+  }
+
+  const healthy = await tcpCheck(host, port, timeoutMs);
+  proxyHealthCache.set(proxyUrl, { healthy, checkedAt: Date.now(), ttlMs: cacheTtlMs });
+  return healthy;
+}
+
+/**
+ * Get the cached health status of a proxy without re-checking.
+ * Returns null if there is no cached entry.
+ */
+export function getCachedProxyHealth(proxyUrl: string): boolean | null {
+  const cached = proxyHealthCache.get(proxyUrl);
+  if (!cached) return null;
+  if (Date.now() - cached.checkedAt >= cached.ttlMs) return null; // stale
+  return cached.healthy;
+}
+
+/**
+ * Invalidate the cached health for a proxy URL (force re-check on next call).
+ */
+export function invalidateProxyHealth(proxyUrl: string): void {
+  proxyHealthCache.delete(proxyUrl);
+}
+
+/**
+ * Get all currently cached proxy health entries (for dashboard display).
+ */
+export function getAllProxyHealthStatuses(): Array<{
+  proxyUrl: string;
+  healthy: boolean;
+  checkedAt: number;
+  stale: boolean;
+}> {
+  const now = Date.now();
+  return [...proxyHealthCache.entries()].map(([proxyUrl, entry]) => ({
+    proxyUrl,
+    healthy: entry.healthy,
+    checkedAt: entry.checkedAt,
+    stale: now - entry.checkedAt >= entry.ttlMs,
+  }));
+}
+
+// ─── Internals ────────────────────────────────────────────────────────────────
+
+function defaultPortForScheme(protocol: string): string {
+  switch (protocol.replace(":", "").toLowerCase()) {
+    case "https":
+      return "443";
+    case "socks5":
+    case "socks5h":
+      return "1080";
+    case "http":
+    default:
+      return "8080";
+  }
+}
+
+function tcpCheck(host: string, port: number, timeoutMs: number): Promise<boolean> {
+  return new Promise<boolean>((resolve) => {
+    const socket = createConnection({ host, port }, () => {
+      socket.destroy();
+      resolve(true);
+    });
+    socket.setTimeout(timeoutMs);
+    socket.on("error", () => resolve(false));
+    socket.on("timeout", () => {
+      socket.destroy();
+      resolve(false);
+    });
+  });
+}