fix(deps): downgrade Next.js to 16.0.10 to fix turbopack hashing regression

Closes #509, #508

Docs: added rc.8 and rc.9 sprint summary to CHANGELOG.md

.gitignore

@@ -89,6 +89,7 @@ docs/*
 !docs/MCP-SERVER.md
 !docs/CLI-TOOLS.md
 
+
 # open-sse tests
 open-sse/test/*
 

CHANGELOG.md

@@ -6,9 +6,37 @@
 
 ---
 
-## [3.0.0-rc.5] — 2026-03-22 _(What's New vs v2.9.5 — will be released as v3.0.0)_
+## [3.0.0-rc.9] — 2026-03-23
 
-> **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 · 832 tests passing.
+### ✨ New Features
+
+- **T29** — Vertex AI SA JSON Executor: implemented using the `jose` library to handle JWT/Service Account auth, along with configurable regions in the UI and automatic partner model URL building.
+- **T42** — Image generation aspect ratio mapping: created `sizeMapper` logic for generic OpenAI formats (`size`), added native `imagen3` handling, and updated NanoBanana endpoints to utilize mapped aspect ratios automatically.
+- **T38** — Centralized model specifications: `modelSpecs.ts` created for limits and parameters per model.
+
+### 🔧 Improvements
+
+- **T40** — OpenCode CLI tools integration: native `opencode-zen` and `opencode-go` integration completed in earlier PR.
+
+---
+
+## [3.0.0-rc.8] — 2026-03-23
+
+### 🔧 Bug Fixes & Improvements (Fallback, Quota & Budget)
+
+- **T24** — `503` cooldown await fix + `406` mapping: mapped `406 Not Acceptable` to `503 Service Unavailable` with proper cooldown intervals.
+- **T25** — Provider validation fallback: graceful fallback to standard validation models when a specific `validationModelId` is not present.
+- **T36** — `403` vs `429` provider handling refinement: extracted into `errorClassifier.ts` to properly segregate hard permissions failures (`403`) from rate limits (`429`).
+- **T39** — Endpoint Fallback for `fetchAvailableModels`: implemented a tri-tier mechanism (`/models` -> `/v1/models` -> local generic catalog) + `list_models_catalog` MCP tool updates to reflect `source` and `warning`.
+- **T33** — Thinking level to budget conversion: translates qualitative thinking levels into precise budget allocations.
+- **T41** — Background task auto redirect: routes heavy background evaluation tasks to flash/efficient models automatically.
+- **T23** — Intelligent quota reset fallback: accurately extracts `x-ratelimit-reset` / `retry-after` header values or maps static cooldowns.
+
+---
+
+## [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 · 15 sub2api gap improvements (T01–T15 complete).
 
 ### 🆕 New Providers
 
@@ -111,6 +139,43 @@ 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)
+
+- **T01** — `requested_model` column in `call_logs` (migration 009): track which model the client originally requested vs the actual routed model. Enables fallback rate analytics.
+- **T02** — Strip empty text blocks from nested `tool_result.content`: prevents Anthropic 400 errors (`text content blocks must be non-empty`) when Claude Code chains tool results.
+- **T03** — Parse `x-codex-5h-*` / `x-codex-7d-*` headers: `parseCodexQuotaHeaders()` + `getCodexResetTime()` extract Codex quota windows for precise cooldown scheduling instead of generic 5-min fallback.
+- **T04** — `X-Session-Id` header for external sticky routing: `extractExternalSessionId()` in `sessionManager.ts` reads `x-session-id` / `x-omniroute-session` headers with `ext:` prefix to avoid collision with internal SHA-256 session IDs. Nginx-compatible (hyphenated header).
+- **T06** — Account deactivated → permanent block: `isAccountDeactivated()` in `accountFallback.ts` detects 401 deactivation signals and applies a 1-year cooldown to prevent retrying permanently dead accounts.
+- **T07** — X-Forwarded-For IP validation: new `src/lib/ipUtils.ts` with `extractClientIp()` and `getClientIpFromRequest()` — skips `unknown`/non-IP entries in `X-Forwarded-For` chains (Nginx/proxy-forwarded requests).
+- **T10** — Credits exhausted → distinct fallback: `isCreditsExhausted()` in `accountFallback.ts` returns 1h cooldown with `creditsExhausted` flag, distinct from generic 429 rate limiting.
+- **T11** — `max` reasoning effort → 131072 budget tokens: `EFFORT_BUDGETS` and `THINKING_LEVEL_MAP` updated; reverse mapping now returns `"max"` for full-budget responses. Unit test updated.
+- **T12** — MiniMax M2.7 pricing entries added: `minimax-m2.7`, `MiniMax-M2.7`, `minimax-m2.7-highspeed` added to pricing table (sub2api PR #1120). M2.5/GLM-4.7/GLM-5/Kimi pricing already existed.
+- **T15** — Array content normalization: `normalizeContentToString()` helper in `openai-to-claude.ts` correctly collapses array-formatted system/tool messages to string before sending to Anthropic.
+
+### 🧪 Tests
+
+- Test suite: **832 tests, 0 failures** (unchanged from rc.5)
+
+---
+
 ## [3.0.0-rc.5] - 2026-03-22
 
 ### ✨ New Features

docs/openapi.yaml

@@ -1,7 +1,7 @@
 openapi: 3.1.0
 info:
   title: OmniRoute API
-  version: 3.0.0-rc.5
+  version: 3.0.0-rc.9
   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/config/providerRegistry.ts

@@ -1241,6 +1241,68 @@ export const REGISTRY: Record<string, RegistryEntry> = {
     ],
   },
 
+  puter: {
+    id: "puter",
+    alias: "pu",
+    format: "openai",
+    executor: "puter",
+    // OpenAI-compatible gateway with 500+ models (GPT, Claude, Gemini, Grok, DeepSeek, Qwen…)
+    // Auth: Bearer <puter_auth_token> from puter.com/dashboard → Copy Auth Token
+    // Model IDs use provider/model-name format for non-OpenAI models.
+    // Only chat completions (incl. streaming) are available via REST.
+    // Image gen, TTS, STT, video are puter.js SDK-only (browser).
+    baseUrl: "https://api.puter.com/puterai/openai/v1/chat/completions",
+    authType: "apikey",
+    authHeader: "bearer",
+    models: [
+      // OpenAI — use bare IDs
+      { id: "gpt-4o-mini", name: "GPT-4o Mini (🆓 Puter)" },
+      { id: "gpt-4o", name: "GPT-4o (Puter)" },
+      { id: "gpt-4.1", name: "GPT-4.1 (Puter)" },
+      { id: "gpt-4.1-mini", name: "GPT-4.1 Mini (Puter)" },
+      { id: "gpt-5-nano", name: "GPT-5 Nano (Puter)" },
+      { id: "gpt-5-mini", name: "GPT-5 Mini (Puter)" },
+      { id: "gpt-5", name: "GPT-5 (Puter)" },
+      { id: "o3-mini", name: "OpenAI o3-mini (Puter)" },
+      { id: "o3", name: "OpenAI o3 (Puter)" },
+      { id: "o4-mini", name: "OpenAI o4-mini (Puter)" },
+      // Anthropic Claude — use bare IDs (confirmed working)
+      { id: "claude-haiku-4-5", name: "Claude Haiku 4.5 (Puter)" },
+      { id: "claude-sonnet-4-5", name: "Claude Sonnet 4.5 (Puter)" },
+      { id: "claude-opus-4-5", name: "Claude Opus 4.5 (Puter)" },
+      { id: "claude-sonnet-4", name: "Claude Sonnet 4 (Puter)" },
+      { id: "claude-opus-4", name: "Claude Opus 4 (Puter)" },
+      // Google Gemini — use google/ prefix (confirmed working)
+      { id: "google/gemini-2.0-flash", name: "Gemini 2.0 Flash (Puter)" },
+      { id: "google/gemini-2.5-flash", name: "Gemini 2.5 Flash (Puter)" },
+      { id: "google/gemini-2.5-pro", name: "Gemini 2.5 Pro (Puter)" },
+      { id: "google/gemini-3-flash", name: "Gemini 3 Flash (Puter)" },
+      { id: "google/gemini-3-pro", name: "Gemini 3 Pro (Puter)" },
+      // DeepSeek — use deepseek/ prefix (confirmed working)
+      { id: "deepseek/deepseek-chat", name: "DeepSeek Chat (Puter)" },
+      { id: "deepseek/deepseek-r1", name: "DeepSeek R1 (Puter)" },
+      { id: "deepseek/deepseek-v3.2", name: "DeepSeek V3.2 (Puter)" },
+      // xAI Grok — use x-ai/ prefix
+      { id: "x-ai/grok-3", name: "Grok 3 (Puter)" },
+      { id: "x-ai/grok-3-mini", name: "Grok 3 Mini (Puter)" },
+      { id: "x-ai/grok-4", name: "Grok 4 (Puter)" },
+      { id: "x-ai/grok-4-fast", name: "Grok 4 Fast (Puter)" },
+      // Meta Llama — bare IDs (confirmed ✅)
+      { id: "llama-4-scout", name: "Llama 4 Scout (Puter)" },
+      { id: "llama-4-maverick", name: "Llama 4 Maverick (Puter)" },
+      { id: "llama-3.3-70b-instruct", name: "Llama 3.3 70B (Puter)" },
+      // Mistral — bare IDs (confirmed ✅)
+      { id: "mistral-small-latest", name: "Mistral Small (Puter)" },
+      { id: "mistral-medium-latest", name: "Mistral Medium (Puter)" },
+      { id: "open-mistral-nemo", name: "Mistral Nemo (Puter)" },
+      // Qwen — use qwen/ prefix (confirmed ✅)
+      { id: "qwen/qwen3-235b-a22b", name: "Qwen3 235B (Puter)" },
+      { id: "qwen/qwen3-32b", name: "Qwen3 32B (Puter)" },
+      { id: "qwen/qwen3-coder", name: "Qwen3 Coder 480B (Puter)" },
+    ],
+    passthroughModels: true, // 500+ models available — users can type any Puter model ID
+  },
+
   "cloudflare-ai": {
     id: "cloudflare-ai",
     alias: "cf",

open-sse/executors/codex.ts

@@ -3,6 +3,112 @@ 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.
+ * Ref: sub2api PR #357 (feat(oauth): persist usage snapshots and window cooldown)
+ */
+export interface CodexQuotaSnapshot {
+  usage5h: number; // tokens used in 5h window
+  limit5h: number; // token limit for 5h window
+  resetAt5h: string | null; // ISO timestamp when 5h window resets
+  usage7d: number; // tokens used in 7d window
+  limit7d: number; // token limit for 7d window
+  resetAt7d: string | null; // ISO timestamp when 7d window resets
+}
+
+/**
+ * T03: Parse Codex-specific quota headers from a provider response.
+ * Returns null if none of the relevant headers are present.
+ *
+ * Extracts:
+ *   x-codex-5h-usage / x-codex-5h-limit / x-codex-5h-reset-at
+ *   x-codex-7d-usage / x-codex-7d-limit / x-codex-7d-reset-at
+ */
+export function parseCodexQuotaHeaders(headers: Headers): CodexQuotaSnapshot | null {
+  const usage5h = headers.get("x-codex-5h-usage");
+  const limit5h = headers.get("x-codex-5h-limit");
+  const resetAt5h = headers.get("x-codex-5h-reset-at");
+  const usage7d = headers.get("x-codex-7d-usage");
+  const limit7d = headers.get("x-codex-7d-limit");
+  const resetAt7d = headers.get("x-codex-7d-reset-at");
+
+  // Return null if none of the quota headers are present (not a quota-aware response)
+  if (!usage5h && !limit5h && !resetAt5h && !usage7d && !limit7d && !resetAt7d) {
+    return null;
+  }
+
+  return {
+    usage5h: usage5h ? parseFloat(usage5h) : 0,
+    limit5h: limit5h ? parseFloat(limit5h) : Infinity,
+    resetAt5h: resetAt5h ?? null,
+    usage7d: usage7d ? parseFloat(usage7d) : 0,
+    limit7d: limit7d ? parseFloat(limit7d) : Infinity,
+    resetAt7d: resetAt7d ?? null,
+  };
+}
+
+/**
+ * T03: Get the soonest quota reset time from a CodexQuotaSnapshot.
+ * 7d window takes priority (wider window, harder limit) but we use whichever
+ * is further in the future to avoid releasing the block too early.
+ *
+ * @returns Unix timestamp (ms) of the soonest effective reset, or null
+ */
+export function getCodexResetTime(quota: CodexQuotaSnapshot): number | null {
+  const times: number[] = [];
+  if (quota.resetAt7d) {
+    const t = new Date(quota.resetAt7d).getTime();
+    if (!isNaN(t) && t > Date.now()) times.push(t);
+  }
+  if (quota.resetAt5h) {
+    const t = new Date(quota.resetAt5h).getTime();
+    if (!isNaN(t) && t > Date.now()) times.push(t);
+  }
+  if (times.length === 0) return null;
+  return Math.max(...times); // Use furthest-out reset to avoid premature unblock
+}
+
 // Ordered list of effort levels from lowest to highest
 const EFFORT_ORDER = ["none", "low", "medium", "high", "xhigh"] as const;
 type EffortLevel = (typeof EFFORT_ORDER)[number];

open-sse/executors/index.ts

@@ -9,6 +9,7 @@ import { DefaultExecutor } from "./default.ts";
 import { PollinationsExecutor } from "./pollinations.ts";
 import { CloudflareAIExecutor } from "./cloudflare-ai.ts";
 import { OpencodeExecutor } from "./opencode.ts";
+import { PuterExecutor } from "./puter.ts";
 
 const executors = {
   antigravity: new AntigravityExecutor(),
@@ -25,6 +26,8 @@ const executors = {
   cf: new CloudflareAIExecutor(), // Alias
   "opencode-zen": new OpencodeExecutor("opencode-zen"),
   "opencode-go": new OpencodeExecutor("opencode-go"),
+  puter: new PuterExecutor(),
+  pu: new PuterExecutor(), // Alias
 };
 
 const defaultCache = new Map();
@@ -51,3 +54,4 @@ export { DefaultExecutor } from "./default.ts";
 export { PollinationsExecutor } from "./pollinations.ts";
 export { CloudflareAIExecutor } from "./cloudflare-ai.ts";
 export { OpencodeExecutor } from "./opencode.ts";
+export { PuterExecutor } from "./puter.ts";

open-sse/executors/puter.ts

@@ -0,0 +1,59 @@
+import { BaseExecutor } from "./base.ts";
+import { PROVIDERS } from "../config/constants.ts";
+
+/**
+ * PuterExecutor — OpenAI-compatible proxy for Puter AI.
+ *
+ * Puter exposes 500+ models (GPT, Claude, Gemini, Grok, DeepSeek, Qwen, Mistral...)
+ * through a single OpenAI-compatible REST endpoint.
+ *
+ * Endpoint: https://api.puter.com/puterai/openai/v1/chat/completions
+ * Auth:     Bearer <puter_auth_token>  (from puter.com/dashboard → Copy Auth Token)
+ * Docs:     https://docs.puter.com/AI/
+ *
+ * Model ID examples:
+ *   OpenAI:   "gpt-4o-mini", "gpt-4o", "gpt-4.1"
+ *   Claude:   "claude-sonnet-4-5", "claude-opus-4", "claude-haiku-4-5"
+ *   Gemini:   "google/gemini-2.0-flash", "google/gemini-2.5-pro"
+ *   DeepSeek: "deepseek/deepseek-chat", "deepseek/deepseek-r1"
+ *   Grok:     "x-ai/grok-3", "x-ai/grok-4"
+ *   Mistral:  "mistralai/mistral-small-3.2"
+ *   Meta:     "meta-llama/llama-3.3-70b-instruct"
+ *
+ * Note: Image generation, TTS, STT, and video are puter.js SDK-only features.
+ * Only text chat completions (with streaming SSE) are available via REST.
+ */
+export class PuterExecutor extends BaseExecutor {
+  constructor() {
+    super("puter", PROVIDERS["puter"] || { format: "openai" });
+  }
+
+  buildUrl(_model: string, _stream: boolean, _urlIndex = 0, _credentials = null): string {
+    return "https://api.puter.com/puterai/openai/v1/chat/completions";
+  }
+
+  buildHeaders(credentials: any, stream = true): Record<string, string> {
+    const headers: Record<string, string> = {
+      "Content-Type": "application/json",
+    };
+
+    const key = credentials?.apiKey || credentials?.accessToken;
+    if (key) {
+      headers["Authorization"] = `Bearer ${key}`;
+    }
+
+    if (stream) {
+      headers["Accept"] = "text/event-stream";
+    }
+
+    return headers;
+  }
+
+  transformRequest(model: string, body: any, _stream: boolean, _credentials: any): any {
+    // Puter accepts model IDs directly from its catalog.
+    // No transformation required — model string is passed as-is.
+    return body;
+  }
+}
+
+export default PuterExecutor;

open-sse/services/accountFallback.ts

@@ -8,6 +8,46 @@ import {
 } from "../config/constants.ts";
 import { getProviderCategory } from "../config/providerRegistry.ts";
 
+// T06 (sub2api PR #1037): Signals that indicate permanent account deactivation.
+// When a 401 body contains these strings, the account is permanently dead
+// and should NOT be retried after token refresh.
+export const ACCOUNT_DEACTIVATED_SIGNALS = [
+  "account_deactivated",
+  "account has been deactivated",
+  "account has been disabled",
+  "your account has been suspended",
+  "this account is deactivated",
+];
+
+// T10 (sub2api PR #1169): Signals that indicate billing credits are exhausted.
+// Distinct from rate-limit 429 — the account won't recover until credits are added.
+export const CREDITS_EXHAUSTED_SIGNALS = [
+  "insufficient_quota",
+  "billing_hard_limit_reached",
+  "exceeded your current quota",
+  "credit_balance_too_low",
+  "your credit balance is too low",
+  "credits exhausted",
+  "out of credits",
+  "payment required",
+];
+
+/**
+ * T06: Returns true if response body indicates the account is permanently deactivated.
+ */
+export function isAccountDeactivated(errorText: string): boolean {
+  const lower = String(errorText || "").toLowerCase();
+  return ACCOUNT_DEACTIVATED_SIGNALS.some((sig) => lower.includes(sig));
+}
+
+/**
+ * T10: Returns true if response body indicates credits/quota are permanently exhausted.
+ */
+export function isCreditsExhausted(errorText: string): boolean {
+  const lower = String(errorText || "").toLowerCase();
+  return CREDITS_EXHAUSTED_SIGNALS.some((sig) => lower.includes(sig));
+}
+
 // ─── Provider Profile Helper ────────────────────────────────────────────────
 
 /**
@@ -201,6 +241,14 @@ export function classifyErrorText(errorText) {
   ) {
     return RateLimitReason.QUOTA_EXHAUSTED;
   }
+  // T10: credits_exhausted signals
+  if (isCreditsExhausted(errorText)) {
+    return RateLimitReason.QUOTA_EXHAUSTED;
+  }
+  // T06: account_deactivated signals
+  if (isAccountDeactivated(errorText)) {
+    return RateLimitReason.AUTH_ERROR;
+  }
   if (
     lower.includes("rate limit") ||
     lower.includes("too many requests") ||
@@ -301,6 +349,26 @@ export function checkFallbackError(
     const errorStr = typeof errorText === "string" ? errorText : JSON.stringify(errorText);
     const lowerError = errorStr.toLowerCase();
 
+    // T06 (sub2api #1037): Permanent account deactivation — do NOT retry, mark as permanent failure
+    if (isAccountDeactivated(errorStr)) {
+      return {
+        shouldFallback: true,
+        cooldownMs: 365 * 24 * 60 * 60 * 1000, // 1 year = effectively permanent
+        reason: RateLimitReason.AUTH_ERROR,
+        permanent: true,
+      };
+    }
+
+    // T10 (sub2api #1169): Credits/quota exhausted — long cooldown, distinct from rate limit
+    if (isCreditsExhausted(errorStr)) {
+      return {
+        shouldFallback: true,
+        cooldownMs: COOLDOWN_MS.paymentRequired ?? 3600 * 1000, // 1h cooldown
+        reason: RateLimitReason.QUOTA_EXHAUSTED,
+        creditsExhausted: true,
+      };
+    }
+
     if (lowerError.includes("no credentials")) {
       return {
         shouldFallback: true,

open-sse/services/sessionManager.ts

@@ -173,6 +173,95 @@ 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 (${maxSessions}). ` +
+      `Please close unused sessions or wait for them to expire.`,
+    limit: maxSessions,
+    current,
+  };
+}
+
+/**
+ * T04: Extract an external session ID from request headers.
+ * Accepts both hyphenated and underscore forms for Nginx compatibility.
+ * Nginx drops headers with underscores by default — use `underscores_in_headers on`
+ * in nginx.conf, or use X-Session-Id (hyphenated) which passes cleanly.
+ *
+ * Ref: sub2api README + PR #634
+ *
+ * @param headers - Request headers (Headers object or plain object with .get())
+ * @returns External session ID with "ext:" prefix, or null
+ */
+export function extractExternalSessionId(
+  headers: Headers | { get?: (n: string) => string | null } | null | undefined
+): string | null {
+  if (!headers || typeof (headers as Headers).get !== "function") return null;
+  const h = headers as Headers;
+  const raw =
+    h.get("x-session-id") ?? // Preferred: hyphenated (passes through Nginx)
+    h.get("x-omniroute-session") ?? // OmniRoute-specific form
+    h.get("session-id") ?? // Bare session-id
+    null;
+  if (!raw || !raw.trim()) return null;
+  // Prefix "ext:" to ensure no collision with internal SHA-256 hash IDs
+  return `ext:${raw.trim().slice(0, 64)}`; // max 64 chars to avoid abuse
 }
 
 // ─── Internal Helpers ───────────────────────────────────────────────────────

open-sse/services/thinkingBudget.ts

@@ -19,6 +19,8 @@ export const EFFORT_BUDGETS = {
   low: 1024,
   medium: 10240,
   high: 131072,
+  max: 131072, // T11: Claude "max" / "xhigh" — full budget
+  xhigh: 131072, // T11: explicit alias used internally
 };
 
 // thinkingLevel string → budget token mapping
@@ -28,6 +30,8 @@ export const THINKING_LEVEL_MAP = {
   low: 1024,
   medium: 10240,
   high: 131072,
+  max: 131072, // T11: max = full Claude budget (sub2api: xhigh)
+  xhigh: 131072, // T11: explicit xhigh alias
 };
 
 // Default config (passthrough = backward compatible)
@@ -198,7 +202,7 @@ function setCustomBudget(body, budget) {
     };
   }
 
-  // OpenAI reasoning_effort mapping
+  // OpenAI reasoning_effort mapping (T11: add 'max' tier for full budget)
   if (result.reasoning_effort !== undefined || result.reasoning !== undefined) {
     if (budget <= 0) {
       delete result.reasoning_effort;
@@ -207,8 +211,10 @@ function setCustomBudget(body, budget) {
       result.reasoning_effort = "low";
     } else if (budget <= 10240) {
       result.reasoning_effort = "medium";
-    } else {
+    } else if (budget < 131072) {
       result.reasoning_effort = "high";
+    } else {
+      result.reasoning_effort = "max"; // T11: full budget → "max"
     }
   }
 

open-sse/translator/request/openai-to-claude.ts

@@ -27,6 +27,60 @@ type ClaudeTool = {
   defer_loading?: boolean;
 };
 
+/**
+ * T02: Recursively strips empty text blocks from content arrays.
+ * Anthropic returns 400 "text content blocks must be non-empty" if any
+ * text block has text: "". Must also recurse into nested tool_result.content.
+ * Ref: sub2api PR #1212
+ */
+export function stripEmptyTextBlocks(content: unknown[] | undefined): unknown[] {
+  if (!Array.isArray(content)) return content ?? [];
+  return content
+    .filter((block: unknown) => {
+      if (
+        block &&
+        typeof block === "object" &&
+        (block as Record<string, unknown>).type === "text"
+      ) {
+        const text = (block as Record<string, unknown>).text;
+        if (text === "" || text == null) return false;
+      }
+      return true;
+    })
+    .map((block: unknown) => {
+      if (
+        block &&
+        typeof block === "object" &&
+        (block as Record<string, unknown>).type === "tool_result" &&
+        Array.isArray((block as Record<string, unknown>).content)
+      ) {
+        // Recurse into nested tool_result.content
+        return {
+          ...(block as Record<string, unknown>),
+          content: stripEmptyTextBlocks((block as Record<string, unknown>).content as unknown[]),
+        };
+      }
+      return block;
+    });
+}
+
+/**
+ * T15: Normalize content to string form.
+ * Handles both string and array-of-blocks forms (Cursor, Codex 2.x, etc.).
+ * Ref: sub2api PR #1197
+ */
+export function normalizeContentToString(content: string | unknown[] | null | undefined): string {
+  if (!content) return "";
+  if (typeof content === "string") return content;
+  if (Array.isArray(content)) {
+    return (content as Array<Record<string, unknown>>)
+      .filter((b) => b.type === "text")
+      .map((b) => String(b.text ?? ""))
+      .join("\n");
+  }
+  return "";
+}
+
 // Convert OpenAI request to Claude format
 export function openaiToClaudeRequest(model, body, stream) {
   // Check if tool prefix should be disabled (configured per-provider or global)
@@ -61,11 +115,11 @@ export function openaiToClaudeRequest(model, body, stream) {
   const systemParts = [];
 
   if (body.messages && Array.isArray(body.messages)) {
-    // Extract system messages
+    // Extract system messages (T15: handle both string and array content)
     for (const msg of body.messages) {
       if (msg.role === "system") {
         systemParts.push(
-          typeof msg.content === "string" ? msg.content : extractTextContent(msg.content)
+          typeof msg.content === "string" ? msg.content : normalizeContentToString(msg.content)
         );
       }
     }
@@ -270,10 +324,14 @@ function getContentBlocksFromMessage(msg, toolNameMap = new Map(), disableToolPr
   const blocks = [];
 
   if (msg.role === "tool") {
+    // T02: Strip empty text blocks from nested tool_result content to avoid Anthropic 400
+    const toolContent = Array.isArray(msg.content)
+      ? stripEmptyTextBlocks(msg.content)
+      : msg.content;
     blocks.push({
       type: "tool_result",
       tool_use_id: msg.tool_call_id,
-      content: msg.content,
+      content: toolContent,
     });
   } else if (msg.role === "user") {
     if (typeof msg.content === "string") {
@@ -287,10 +345,14 @@ function getContentBlocksFromMessage(msg, toolNameMap = new Map(), disableToolPr
         } else if (part.type === "tool_result") {
           // Skip tool_result with no tool_use_id (would be useless and may cause errors)
           if (!part.tool_use_id) continue;
+          // T02: strip empty text blocks from nested content before passing to Anthropic
+          const resultContent = Array.isArray(part.content)
+            ? stripEmptyTextBlocks(part.content)
+            : part.content;
           blocks.push({
             type: "tool_result",
             tool_use_id: part.tool_use_id,
-            content: part.content,
+            content: resultContent,
             ...(part.is_error && { is_error: part.is_error }),
           });
         } else if (part.type === "image_url") {

package-lock.json

@@ -1,12 +1,12 @@
 {
   "name": "omniroute",
-  "version": "3.0.0-rc.5",
+  "version": "3.0.0-rc.9",
   "lockfileVersion": 3,
   "requires": true,
   "packages": {
     "": {
       "name": "omniroute",
-      "version": "3.0.0-rc.5",
+      "version": "3.0.0-rc.9",
       "hasInstallScript": true,
       "license": "MIT",
       "workspaces": [
@@ -28,7 +28,7 @@
         "jose": "^6.1.3",
         "lowdb": "^7.0.1",
         "monaco-editor": "^0.55.1",
-        "next": "^16.1.6",
+        "next": "^16.0.10",
         "next-intl": "^4.8.3",
         "node-machine-id": "^1.1.12",
         "open": "^11.0.0",
@@ -61,7 +61,7 @@
         "concurrently": "^9.2.1",
         "cross-env": "^10.1.0",
         "eslint": "^9.39.2",
-        "eslint-config-next": "16.1.6",
+        "eslint-config-next": "^16.0.10",
         "husky": "^9.1.7",
         "lint-staged": "^16.2.7",
         "prettier": "^3.8.1",
@@ -2567,15 +2567,15 @@
       }
     },
     "node_modules/@next/env": {
-      "version": "16.1.7",
-      "resolved": "https://registry.npmjs.org/@next/env/-/env-16.1.7.tgz",
-      "integrity": "sha512-rJJbIdJB/RQr2F1nylZr/PJzamvNNhfr3brdKP6s/GW850jbtR70QlSfFselvIBbcPUOlQwBakexjFzqLzF6pg==",
+      "version": "16.0.10",
+      "resolved": "https://registry.npmjs.org/@next/env/-/env-16.0.10.tgz",
+      "integrity": "sha512-8tuaQkyDVgeONQ1MeT9Mkk8pQmZapMKFh5B+OrFUlG3rVmYTXcXlBetBgTurKXGaIZvkoqRT9JL5K3phXcgang==",
       "license": "MIT"
     },
     "node_modules/@next/eslint-plugin-next": {
-      "version": "16.1.6",
-      "resolved": "https://registry.npmjs.org/@next/eslint-plugin-next/-/eslint-plugin-next-16.1.6.tgz",
-      "integrity": "sha512-/Qq3PTagA6+nYVfryAtQ7/9FEr/6YVyvOtl6rZnGsbReGLf0jZU6gkpr1FuChAQpvV46a78p4cmHOVP8mbfSMQ==",
+      "version": "16.0.10",
+      "resolved": "https://registry.npmjs.org/@next/eslint-plugin-next/-/eslint-plugin-next-16.0.10.tgz",
+      "integrity": "sha512-b2NlWN70bbPLmfyoLvvidPKWENBYYIe017ZGUpElvQjDytCWgxPJx7L9juxHt0xHvNVA08ZHJdOyhGzon/KJuw==",
       "dev": true,
       "license": "MIT",
       "dependencies": {
@@ -2583,9 +2583,9 @@
       }
     },
     "node_modules/@next/swc-darwin-arm64": {
-      "version": "16.1.7",
-      "resolved": "https://registry.npmjs.org/@next/swc-darwin-arm64/-/swc-darwin-arm64-16.1.7.tgz",
-      "integrity": "sha512-b2wWIE8sABdyafc4IM8r5Y/dS6kD80JRtOGrUiKTsACFQfWWgUQ2NwoUX1yjFMXVsAwcQeNpnucF2ZrujsBBPg==",
+      "version": "16.0.10",
+      "resolved": "https://registry.npmjs.org/@next/swc-darwin-arm64/-/swc-darwin-arm64-16.0.10.tgz",
+      "integrity": "sha512-4XgdKtdVsaflErz+B5XeG0T5PeXKDdruDf3CRpnhN+8UebNa5N2H58+3GDgpn/9GBurrQ1uWW768FfscwYkJRg==",
       "cpu": [
         "arm64"
       ],
@@ -2599,9 +2599,9 @@
       }
     },
     "node_modules/@next/swc-darwin-x64": {
-      "version": "16.1.7",
-      "resolved": "https://registry.npmjs.org/@next/swc-darwin-x64/-/swc-darwin-x64-16.1.7.tgz",
-      "integrity": "sha512-zcnVaaZulS1WL0Ss38R5Q6D2gz7MtBu8GZLPfK+73D/hp4GFMrC2sudLky1QibfV7h6RJBJs/gOFvYP0X7UVlQ==",
+      "version": "16.0.10",
+      "resolved": "https://registry.npmjs.org/@next/swc-darwin-x64/-/swc-darwin-x64-16.0.10.tgz",
+      "integrity": "sha512-spbEObMvRKkQ3CkYVOME+ocPDFo5UqHb8EMTS78/0mQ+O1nqE8toHJVioZo4TvebATxgA8XMTHHrScPrn68OGw==",
       "cpu": [
         "x64"
       ],
@@ -2615,12 +2615,15 @@
       }
     },
     "node_modules/@next/swc-linux-arm64-gnu": {
-      "version": "16.1.7",
-      "resolved": "https://registry.npmjs.org/@next/swc-linux-arm64-gnu/-/swc-linux-arm64-gnu-16.1.7.tgz",
-      "integrity": "sha512-2ant89Lux/Q3VyC8vNVg7uBaFVP9SwoK2jJOOR0L8TQnX8CAYnh4uctAScy2Hwj2dgjVHqHLORQZJ2wH6VxhSQ==",
+      "version": "16.0.10",
+      "resolved": "https://registry.npmjs.org/@next/swc-linux-arm64-gnu/-/swc-linux-arm64-gnu-16.0.10.tgz",
+      "integrity": "sha512-uQtWE3X0iGB8apTIskOMi2w/MKONrPOUCi5yLO+v3O8Mb5c7K4Q5KD1jvTpTF5gJKa3VH/ijKjKUq9O9UhwOYw==",
       "cpu": [
         "arm64"
       ],
+      "libc": [
+        "glibc"
+      ],
       "license": "MIT",
       "optional": true,
       "os": [
@@ -2631,12 +2634,15 @@
       }
     },
     "node_modules/@next/swc-linux-arm64-musl": {
-      "version": "16.1.7",
-      "resolved": "https://registry.npmjs.org/@next/swc-linux-arm64-musl/-/swc-linux-arm64-musl-16.1.7.tgz",
-      "integrity": "sha512-uufcze7LYv0FQg9GnNeZ3/whYfo+1Q3HnQpm16o6Uyi0OVzLlk2ZWoY7j07KADZFY8qwDbsmFnMQP3p3+Ftprw==",
+      "version": "16.0.10",
+      "resolved": "https://registry.npmjs.org/@next/swc-linux-arm64-musl/-/swc-linux-arm64-musl-16.0.10.tgz",
+      "integrity": "sha512-llA+hiDTrYvyWI21Z0L1GiXwjQaanPVQQwru5peOgtooeJ8qx3tlqRV2P7uH2pKQaUfHxI/WVarvI5oYgGxaTw==",
       "cpu": [
         "arm64"
       ],
+      "libc": [
+        "musl"
+      ],
       "license": "MIT",
       "optional": true,
       "os": [
@@ -2647,12 +2653,15 @@
       }
     },
     "node_modules/@next/swc-linux-x64-gnu": {
-      "version": "16.1.7",
-      "resolved": "https://registry.npmjs.org/@next/swc-linux-x64-gnu/-/swc-linux-x64-gnu-16.1.7.tgz",
-      "integrity": "sha512-KWVf2gxYvHtvuT+c4MBOGxuse5TD7DsMFYSxVxRBnOzok/xryNeQSjXgxSv9QpIVlaGzEn/pIuI6Koosx8CGWA==",
+      "version": "16.0.10",
+      "resolved": "https://registry.npmjs.org/@next/swc-linux-x64-gnu/-/swc-linux-x64-gnu-16.0.10.tgz",
+      "integrity": "sha512-AK2q5H0+a9nsXbeZ3FZdMtbtu9jxW4R/NgzZ6+lrTm3d6Zb7jYrWcgjcpM1k8uuqlSy4xIyPR2YiuUr+wXsavA==",
       "cpu": [
         "x64"
       ],
+      "libc": [
+        "glibc"
+      ],
       "license": "MIT",
       "optional": true,
       "os": [
@@ -2663,12 +2672,15 @@
       }
     },
     "node_modules/@next/swc-linux-x64-musl": {
-      "version": "16.1.7",
-      "resolved": "https://registry.npmjs.org/@next/swc-linux-x64-musl/-/swc-linux-x64-musl-16.1.7.tgz",
-      "integrity": "sha512-HguhaGwsGr1YAGs68uRKc4aGWxLET+NevJskOcCAwXbwj0fYX0RgZW2gsOCzr9S11CSQPIkxmoSbuVaBp4Z3dA==",
+      "version": "16.0.10",
+      "resolved": "https://registry.npmjs.org/@next/swc-linux-x64-musl/-/swc-linux-x64-musl-16.0.10.tgz",
+      "integrity": "sha512-1TDG9PDKivNw5550S111gsO4RGennLVl9cipPhtkXIFVwo31YZ73nEbLjNC8qG3SgTz/QZyYyaFYMeY4BKZR/g==",
       "cpu": [
         "x64"
       ],
+      "libc": [
+        "musl"
+      ],
       "license": "MIT",
       "optional": true,
       "os": [
@@ -2679,9 +2691,9 @@
       }
     },
     "node_modules/@next/swc-win32-arm64-msvc": {
-      "version": "16.1.7",
-      "resolved": "https://registry.npmjs.org/@next/swc-win32-arm64-msvc/-/swc-win32-arm64-msvc-16.1.7.tgz",
-      "integrity": "sha512-S0n3KrDJokKTeFyM/vGGGR8+pCmXYrjNTk2ZozOL1C/JFdfUIL9O1ATaJOl5r2POe56iRChbsszrjMAdWSv7kQ==",
+      "version": "16.0.10",
+      "resolved": "https://registry.npmjs.org/@next/swc-win32-arm64-msvc/-/swc-win32-arm64-msvc-16.0.10.tgz",
+      "integrity": "sha512-aEZIS4Hh32xdJQbHz121pyuVZniSNoqDVx1yIr2hy+ZwJGipeqnMZBJHyMxv2tiuAXGx6/xpTcQJ6btIiBjgmg==",
       "cpu": [
         "arm64"
       ],
@@ -2695,9 +2707,9 @@
       }
     },
     "node_modules/@next/swc-win32-x64-msvc": {
-      "version": "16.1.7",
-      "resolved": "https://registry.npmjs.org/@next/swc-win32-x64-msvc/-/swc-win32-x64-msvc-16.1.7.tgz",
-      "integrity": "sha512-mwgtg8CNZGYm06LeEd+bNnOUfwOyNem/rOiP14Lsz+AnUY92Zq/LXwtebtUiaeVkhbroRCQ0c8GlR4UT1U+0yg==",
+      "version": "16.0.10",
+      "resolved": "https://registry.npmjs.org/@next/swc-win32-x64-msvc/-/swc-win32-x64-msvc-16.0.10.tgz",
+      "integrity": "sha512-E+njfCoFLb01RAFEnGZn6ERoOqhK1Gl3Lfz1Kjnj0Ulfu7oJbuMyvBKNj/bw8XZnenHDASlygTjZICQW+rYW1Q==",
       "cpu": [
         "x64"
       ],
@@ -7522,6 +7534,7 @@
       "version": "2.9.19",
       "resolved": "https://registry.npmjs.org/baseline-browser-mapping/-/baseline-browser-mapping-2.9.19.tgz",
       "integrity": "sha512-ipDqC8FrAl/76p2SSWKSI+H9tFwm7vYqXQrItCuiVPt26Km0jS+NzSsBWAaBusvSbQcfJG+JitdMm+wZAgTYqg==",
+      "dev": true,
       "license": "Apache-2.0",
       "bin": {
         "baseline-browser-mapping": "dist/cli.js"
@@ -9705,13 +9718,13 @@
       }
     },
     "node_modules/eslint-config-next": {
-      "version": "16.1.6",
-      "resolved": "https://registry.npmjs.org/eslint-config-next/-/eslint-config-next-16.1.6.tgz",
-      "integrity": "sha512-vKq40io2B0XtkkNDYyleATwblNt8xuh3FWp8SpSz3pt7P01OkBFlKsJZ2mWt5WsCySlDQLckb1zMY9yE9Qy0LA==",
+      "version": "16.0.10",
+      "resolved": "https://registry.npmjs.org/eslint-config-next/-/eslint-config-next-16.0.10.tgz",
+      "integrity": "sha512-BxouZUm0I45K4yjOOIzj24nTi0H2cGo0y7xUmk+Po/PYtJXFBYVDS1BguE7t28efXjKdcN0tmiLivxQy//SsZg==",
       "dev": true,
       "license": "MIT",
       "dependencies": {
-        "@next/eslint-plugin-next": "16.1.6",
+        "@next/eslint-plugin-next": "16.0.10",
         "eslint-import-resolver-node": "^0.3.6",
         "eslint-import-resolver-typescript": "^3.5.2",
         "eslint-plugin-import": "^2.32.0",
@@ -14658,14 +14671,13 @@
       }
     },
     "node_modules/next": {
-      "version": "16.1.7",
-      "resolved": "https://registry.npmjs.org/next/-/next-16.1.7.tgz",
-      "integrity": "sha512-WM0L7WrSvKwoLegLYr6V+mz+RIofqQgVAfHhMp9a88ms0cFX8iX9ew+snpWlSBwpkURJOUdvCEt3uLl3NNzvWg==",
+      "version": "16.0.10",
+      "resolved": "https://registry.npmjs.org/next/-/next-16.0.10.tgz",
+      "integrity": "sha512-RtWh5PUgI+vxlV3HdR+IfWA1UUHu0+Ram/JBO4vWB54cVPentCD0e+lxyAYEsDTqGGMg7qpjhKh6dc6aW7W/sA==",
       "license": "MIT",
       "dependencies": {
-        "@next/env": "16.1.7",
+        "@next/env": "16.0.10",
         "@swc/helpers": "0.5.15",
-        "baseline-browser-mapping": "^2.9.19",
         "caniuse-lite": "^1.0.30001579",
         "postcss": "8.4.31",
         "styled-jsx": "5.1.6"
@@ -14677,14 +14689,14 @@
         "node": ">=20.9.0"
       },
       "optionalDependencies": {
-        "@next/swc-darwin-arm64": "16.1.7",
-        "@next/swc-darwin-x64": "16.1.7",
-        "@next/swc-linux-arm64-gnu": "16.1.7",
-        "@next/swc-linux-arm64-musl": "16.1.7",
-        "@next/swc-linux-x64-gnu": "16.1.7",
-        "@next/swc-linux-x64-musl": "16.1.7",
-        "@next/swc-win32-arm64-msvc": "16.1.7",
-        "@next/swc-win32-x64-msvc": "16.1.7",
+        "@next/swc-darwin-arm64": "16.0.10",
+        "@next/swc-darwin-x64": "16.0.10",
+        "@next/swc-linux-arm64-gnu": "16.0.10",
+        "@next/swc-linux-arm64-musl": "16.0.10",
+        "@next/swc-linux-x64-gnu": "16.0.10",
+        "@next/swc-linux-x64-musl": "16.0.10",
+        "@next/swc-win32-arm64-msvc": "16.0.10",
+        "@next/swc-win32-x64-msvc": "16.0.10",
         "sharp": "^0.34.4"
       },
       "peerDependencies": {

package.json

@@ -1,6 +1,6 @@
 {
   "name": "omniroute",
-  "version": "3.0.0-rc.5",
+  "version": "3.0.0-rc.9",
   "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": {
@@ -96,7 +96,7 @@
     "jose": "^6.1.3",
     "lowdb": "^7.0.1",
     "monaco-editor": "^0.55.1",
-    "next": "^16.1.6",
+    "next": "^16.0.10",
     "next-intl": "^4.8.3",
     "node-machine-id": "^1.1.12",
     "open": "^11.0.0",
@@ -125,7 +125,7 @@
     "concurrently": "^9.2.1",
     "cross-env": "^10.1.0",
     "eslint": "^9.39.2",
-    "eslint-config-next": "16.1.6",
+    "eslint-config-next": "^16.0.10",
     "husky": "^9.1.7",
     "lint-staged": "^16.2.7",
     "prettier": "^3.8.1",

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/migrations/009_requested_model.sql

@@ -0,0 +1,9 @@
+-- Migration 009: Add requested_model to call_logs for billing transparency
+-- Tracks the model the client *asked* for vs the model that was *actually routed*.
+-- Needed when a combo falls back: requested_model ≠ model in call_logs.
+-- Ref: sub2api commits 0b845c25 + 4edcfe1f (T01 sub2api gap analysis)
+ALTER TABLE call_logs ADD COLUMN requested_model TEXT DEFAULT NULL;
+
+-- Index for filtering/aggregating by requested_model in Analytics
+CREATE INDEX IF NOT EXISTS idx_call_logs_requested_model
+  ON call_logs(requested_model);

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/ipUtils.ts

@@ -0,0 +1,56 @@
+import { isIP } from "node:net";
+
+/**
+ * T07: Extract the real client IP from X-Forwarded-For header.
+ * Skips invalid entries like "unknown" or empty strings.
+ * Falls back to remoteAddress if no valid IP found.
+ * Ref: sub2api PR #1135
+ *
+ * @param xForwardedFor - Value of the X-Forwarded-For header (may be CSV)
+ * @param remoteAddress - Fallback from the raw socket (req.socket.remoteAddress)
+ * @returns The first valid IP address found, or "unknown"
+ */
+export function extractClientIp(
+  xForwardedFor: string | null | undefined,
+  remoteAddress: string | undefined
+): string {
+  if (xForwardedFor) {
+    const entries = xForwardedFor.split(",");
+    for (const entry of entries) {
+      const trimmed = entry.trim();
+      if (trimmed && isIP(trimmed) !== 0) {
+        return trimmed; // First valid IP wins
+      }
+    }
+  }
+  return remoteAddress?.trim() ?? "unknown";
+}
+
+/**
+ * Extract client IP from a Request or NextRequest object.
+ * Checks X-Forwarded-For, X-Real-IP, CF-Connecting-IP, then socket.
+ */
+export function getClientIpFromRequest(req: {
+  headers?: Headers | { get?: (n: string) => string | null };
+  socket?: { remoteAddress?: string };
+  ip?: string;
+}): string {
+  // Helper to get header value from either Headers object or plain object
+  const getHeader = (name: string): string | null => {
+    if (!req.headers) return null;
+    if (typeof (req.headers as Headers).get === "function") {
+      return (req.headers as Headers).get(name);
+    }
+    return null;
+  };
+
+  // Priority: CF-Connecting-IP (Cloudflare) > X-Forwarded-For > X-Real-IP > socket
+  const cfIp = getHeader("cf-connecting-ip");
+  if (cfIp && isIP(cfIp.trim()) !== 0) return cfIp.trim();
+
+  const xff = getHeader("x-forwarded-for");
+  const realIp = getHeader("x-real-ip");
+  const remoteAddress = req.ip ?? req.socket?.remoteAddress;
+
+  return extractClientIp(xff ?? realIp, remoteAddress);
+}

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);
+    });
+  });
+}

src/lib/usage/callLogs.ts

@@ -180,6 +180,7 @@ export async function saveCallLog(entry: any) {
       path: entry.path || "/v1/chat/completions",
       status: entry.status || 0,
       model: entry.model || "-",
+      requestedModel: entry.requestedModel || null, // T01: model the client asked for
       provider: entry.provider || "-",
       account,
       connectionId: entry.connectionId || null,
@@ -205,10 +206,10 @@ export async function saveCallLog(entry: any) {
     const db = getDbInstance();
     db.prepare(
       `
-      INSERT INTO call_logs (id, timestamp, method, path, status, model, provider,
+      INSERT INTO call_logs (id, timestamp, method, path, status, model, requested_model, provider,
         account, connection_id, duration, tokens_in, tokens_out, request_type, source_format, target_format,
         api_key_id, api_key_name, combo_name, request_body, response_body, error)
-      VALUES (@id, @timestamp, @method, @path, @status, @model, @provider,
+      VALUES (@id, @timestamp, @method, @path, @status, @model, @requestedModel, @provider,
         @account, @connectionId, @duration, @tokensIn, @tokensOut, @requestType, @sourceFormat, @targetFormat,
         @apiKeyId, @apiKeyName, @comboName, @requestBody, @responseBody, @error)
     `
@@ -374,6 +375,7 @@ export async function getCallLogs(filter: any = {}) {
       path: toStringOrNull(l.path),
       status: toNumber(l.status),
       model: toStringOrNull(l.model),
+      requestedModel: toStringOrNull(l.requested_model), // T01: original model from client
       provider: toStringOrNull(l.provider),
       account: toStringOrNull(l.account),
       duration: toNumber(l.duration),

src/shared/constants/pricing.ts

@@ -802,6 +802,30 @@ export const DEFAULT_PRICING = {
       reasoning: 1.8,
       cache_creation: 0.3,
     },
+    // T12: MiniMax M2.7 — new default model (sub2api PR #1120)
+    // Upgraded from M2.5, same API endpoint api.minimax.io
+    // Pricing estimated, check https://platform.minimaxi.com/document/Price
+    "minimax-m2.7": {
+      input: 0.4,
+      output: 1.6,
+      cached: 0.2,
+      reasoning: 2.4,
+      cache_creation: 0.4,
+    },
+    "MiniMax-M2.7": {
+      input: 0.4,
+      output: 1.6,
+      cached: 0.2,
+      reasoning: 2.4,
+      cache_creation: 0.4,
+    },
+    "minimax-m2.7-highspeed": {
+      input: 0.4,
+      output: 1.6,
+      cached: 0.2,
+      reasoning: 2.4,
+      cache_creation: 0.4,
+    },
   },
 
   // ─── Free-tier API Key Providers (nominal $0 pricing) ───

src/shared/constants/providers.ts

@@ -546,6 +546,20 @@ export const APIKEY_PROVIDERS = {
     freeNote:
       "No API key needed — access GPT-5, Claude, Gemini, DeepSeek V3, Llama 4 free (1 req/15s)",
   },
+  puter: {
+    id: "puter",
+    alias: "pu",
+    name: "Puter AI",
+    icon: "cloud_circle",
+    color: "#6366F1",
+    textIcon: "PU",
+    website: "https://puter.com",
+    hasFree: true,
+    freeNote:
+      "500+ models (GPT-5, Claude Opus 4, Gemini 3 Pro, Grok 4, DeepSeek V3...) — Users pay via free Puter account",
+    passthroughModels: true,
+    authHint: "Get token at puter.com/dashboard → Copy Auth Token",
+  },
   "cloudflare-ai": {
     id: "cloudflare-ai",
     alias: "cf",

tests/unit/thinking-budget.test.mjs

@@ -101,7 +101,8 @@ test("CUSTOM: sets OpenAI reasoning_effort from budget", () => {
     reasoning_effort: "low",
   };
   const result = applyThinkingBudget(body);
-  assert.equal(result.reasoning_effort, "high");
+  // T11 (sub2api gap): full budget (131072) now maps to "max" instead of "high"
+  assert.equal(result.reasoning_effort, "max");
   setThinkingBudgetConfig(DEFAULT_THINKING_CONFIG);
 });