feat(release): v2.0.3 — deferred tools cache_control fix, quota system hardening

fix: harden quota system — code review fixes + build fix

.gitignore

@@ -117,3 +117,8 @@ icon.iconset/
 
 # VS Code Extension (independent Git repo)
 vscode-extension/
+
+# SQLite residual files
+*.sqlite-shm
+*.sqlite-wal
+*.sqlite-journal

CHANGELOG.md

@@ -7,6 +7,49 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ---
 
+## [2.0.3] — 2026-03-05
+
+> ### 🐛 Bug Fixes & Quota System Hardening
+
+### 🐛 Bug Fixes
+
+- **#215 — Deferred tools 400 error** — Skip `cache_control` on tools with `defer_loading=true` when assigning prompt caching to the last tool. Previously, the API rejected requests with 400 when MCP tools (Playwright, etc.) had deferred loading enabled. Fix applied in both `claudeHelper.ts` and `openai-to-claude.ts` translation layers. PR #216 by @DavyMassoneto
+- **Stale compiled schemas.js** — Deleted stale compiled `schemas.js` (912 lines) that shadowed the TypeScript `.ts` source, causing `cloudSyncActionSchema` warnings in the dashboard. PR #216 by @DavyMassoneto
+- **#202 — False quota exhaustion** — Fixed empty API responses (`{}`) creating quota objects with `utilization ?? 0` = 0% remaining, incorrectly marking accounts as exhausted. Added `hasUtilization()` guard. PR #214 by @DavyMassoneto
+- **Invalid date crash** — `parseDate()` now validates dates before comparison, handling `Invalid Date` from malformed `resetAt` values gracefully. PR #214 by @DavyMassoneto
+- **`total=0` false infinite quota** — `normalizeQuotas` now defaults to 0% remaining when `total` is zero (was incorrectly reporting 100%). PR #214 by @DavyMassoneto
+- **Tailwind v4 build failure** — Tailwind v4 scanned `*.sqlite-shm`/`.sqlite-wal` binary files, triggering "Invalid code point" errors. Added `@source not` exclusions in `globals.css`. PR #214 by @DavyMassoneto
+
+### ✨ Improvements
+
+- **Quota-aware account selection** — All load-balancing strategies (sticky, round-robin, p2c, random, least-used, cost-optimized, fill-first) now prioritize accounts with available quota over exhausted ones. PR #214 by @DavyMassoneto
+- **Concurrent refresh protection** — `tickRunning` flag prevents overlapping background quota refresh ticks; `refreshingSet` deduplicates per-connection refreshes. Thundering herd prevention with `MAX_CONCURRENT_REFRESHES=5`. PR #214 by @DavyMassoneto
+- **`clearModelUnavailability` on success** — Model unavailability is now cleared on every successful request, not only on fallback paths. PR #214 by @DavyMassoneto
+- **Centralized `anthropic-version`** — Hardcoded `anthropic-version` header (3 occurrences) centralized into `CLAUDE_CONFIG.apiVersion`. PR #214 by @DavyMassoneto
+- **Extracted `safePercentage()` utility** — Shared percentage validation function extracted to `src/shared/utils/formatting.ts`, eliminating duplication between backend and frontend. PR #214 by @DavyMassoneto
+- **`isRecord()` type guard** — Replaces inline `typeof` chain in usage API route. PR #214 by @DavyMassoneto
+
+### 📁 Files Changed
+
+| File                                                                                  | Change                                                     |
+| ------------------------------------------------------------------------------------- | ---------------------------------------------------------- |
+| `open-sse/translator/helpers/claudeHelper.ts`                                         | Skip `cache_control` on deferred tools                     |
+| `open-sse/translator/request/openai-to-claude.ts`                                     | Same fix in translator layer                               |
+| `src/shared/validation/schemas.js`                                                    | **DELETED** — stale compiled JS                            |
+| `.gitignore`                                                                          | Exclude Tailwind binary scanning                           |
+| `open-sse/services/usage.ts`                                                          | Legacy endpoint fallback logging                           |
+| `src/domain/quotaCache.ts`                                                            | **NEW** — Core quota cache with hardening                  |
+| `src/shared/utils/formatting.ts`                                                      | **NEW** — `safePercentage()` utility                       |
+| `src/instrumentation.ts`                                                              | Startup log for quota cache                                |
+| `src/sse/handlers/chat.ts`                                                            | `clearModelUnavailability` + `markAccountExhaustedFrom429` |
+| `src/sse/services/auth.ts`                                                            | Quota-aware account selection                              |
+| `src/app/globals.css`                                                                 | Tailwind `@source not` exclusions                          |
+| `src/app/api/usage/[connectionId]/route.ts`                                           | `isRecord()` type guard                                    |
+| `src/app/(dashboard)/dashboard/usage/components/ProviderLimits/ProviderLimitCard.tsx` | Use `remainingPercentage` directly                         |
+| `src/app/(dashboard)/dashboard/usage/components/ProviderLimits/utils.tsx`             | Use shared `safePercentage()`                              |
+
+---
+
 ## [2.0.2] — 2026-03-05
 
 > ### 🐛 Bug Fixes & ✨ Endpoint-Aware Model Management

open-sse/services/usage.ts

@@ -3,6 +3,7 @@
  */
 
 import { PROVIDERS } from "../config/constants.ts";
+import { safePercentage } from "@/shared/utils/formatting";
 
 // GitHub API config
 const GITHUB_CONFIG = {
@@ -34,6 +35,7 @@ const CLAUDE_CONFIG = {
   oauthUsageUrl: "https://api.anthropic.com/api/oauth/usage",
   usageUrl: "https://api.anthropic.com/v1/organizations/{org_id}/usage",
   settingsUrl: "https://api.anthropic.com/v1/settings",
+  apiVersion: "2023-06-01",
 };
 
 type JsonRecord = Record<string, unknown>;
@@ -469,7 +471,7 @@ async function getClaudeUsage(accessToken) {
       headers: {
         Authorization: `Bearer ${accessToken}`,
         "anthropic-beta": "oauth-2025-04-20",
-        "anthropic-version": "2023-06-01",
+        "anthropic-version": CLAUDE_CONFIG.apiVersion,
       },
     });
 
@@ -477,36 +479,34 @@ async function getClaudeUsage(accessToken) {
       const data = await oauthResponse.json();
       const quotas: Record<string, any> = {};
 
-      // utilization = percentage USED (e.g., 22 means 22% used, 78% remaining)
+      // utilization = percentage REMAINING (e.g., 90 means 90% remaining, 10% used)
+      const hasUtilization = (window: any) =>
+        window && typeof window === "object" && safePercentage(window.utilization) !== undefined;
+
       const createQuotaObject = (window: any) => {
-        const used = window?.utilization ?? 0;
-        const remaining = 100 - used;
+        const remaining = safePercentage(window.utilization) as number;
+        const used = 100 - remaining;
         return {
           used,
           total: 100,
           remaining,
-          resetAt: parseResetTime(window?.resets_at),
+          resetAt: parseResetTime(window.resets_at),
           remainingPercentage: remaining,
           unlimited: false,
         };
       };
 
-      if (data.five_hour && typeof data.five_hour === "object") {
+      if (hasUtilization(data.five_hour)) {
         quotas["session (5h)"] = createQuotaObject(data.five_hour);
       }
 
-      if (data.seven_day && typeof data.seven_day === "object") {
+      if (hasUtilization(data.seven_day)) {
         quotas["weekly (7d)"] = createQuotaObject(data.seven_day);
       }
 
       // Parse model-specific weekly windows (e.g., seven_day_sonnet, seven_day_opus)
       for (const [key, value] of Object.entries(data)) {
-        if (
-          key.startsWith("seven_day_") &&
-          key !== "seven_day" &&
-          value &&
-          typeof value === "object"
-        ) {
+        if (key.startsWith("seven_day_") && key !== "seven_day" && hasUtilization(value)) {
           const modelName = key.replace("seven_day_", "");
           quotas[`weekly ${modelName} (7d)`] = createQuotaObject(value);
         }
@@ -519,7 +519,10 @@ async function getClaudeUsage(accessToken) {
       };
     }
 
-    // Fallback: Try legacy settings/org endpoint (for API key users with org admin access)
+    // Fallback: OAuth endpoint returned non-OK, try legacy settings/org endpoint
+    console.warn(
+      `[Claude Usage] OAuth endpoint returned ${oauthResponse.status}, falling back to legacy`
+    );
     return await getClaudeUsageLegacy(accessToken);
   } catch (error) {
     return { message: `Claude connected. Unable to fetch usage: ${(error as any).message}` };
@@ -536,7 +539,7 @@ async function getClaudeUsageLegacy(accessToken) {
       method: "GET",
       headers: {
         Authorization: `Bearer ${accessToken}`,
-        "anthropic-version": "2023-06-01",
+        "anthropic-version": CLAUDE_CONFIG.apiVersion,
       },
     });
 
@@ -550,7 +553,7 @@ async function getClaudeUsageLegacy(accessToken) {
             method: "GET",
             headers: {
               Authorization: `Bearer ${accessToken}`,
-              "anthropic-version": "2023-06-01",
+              "anthropic-version": CLAUDE_CONFIG.apiVersion,
             },
           }
         );

open-sse/translator/helpers/claudeHelper.ts

@@ -185,15 +185,19 @@ export function prepareClaudeRequest(body, provider = null) {
     }
   }
 
-  // 3. Tools: remove all cache_control, add only to last tool with ttl 1h
+  // 3. Tools: remove all cache_control, add only to last non-deferred tool with ttl 1h
+  // Tools with defer_loading=true cannot have cache_control (API rejects it)
   if (body.tools && Array.isArray(body.tools)) {
-    body.tools = body.tools.map((tool, i) => {
+    body.tools = body.tools.map((tool) => {
       const { cache_control, ...rest } = tool;
-      if (i === body.tools.length - 1) {
-        return { ...rest, cache_control: { type: "ephemeral", ttl: "1h" } };
-      }
       return rest;
     });
+    for (let i = body.tools.length - 1; i >= 0; i--) {
+      if (!body.tools[i].defer_loading) {
+        body.tools[i].cache_control = { type: "ephemeral", ttl: "1h" };
+        break;
+      }
+    }
   }
 
   return body;

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

@@ -175,8 +175,13 @@ export function openaiToClaudeRequest(model, body, stream) {
       };
     });
 
-    if (result.tools.length > 0) {
-      result.tools[result.tools.length - 1].cache_control = { type: "ephemeral", ttl: "1h" };
+    // Add cache_control to last tool that doesn't have defer_loading
+    // Tools with defer_loading=true cannot have cache_control (API rejects it)
+    for (let i = result.tools.length - 1; i >= 0; i--) {
+      if (!result.tools[i].defer_loading) {
+        result.tools[i].cache_control = { type: "ephemeral", ttl: "1h" };
+        break;
+      }
     }
   }
 

package.json

@@ -1,6 +1,6 @@
 {
   "name": "omniroute",
-  "version": "2.0.2",
+  "version": "2.0.3",
   "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/app/(dashboard)/dashboard/usage/components/ProviderLimits/ProviderLimitCard.tsx

@@ -150,10 +150,9 @@ export default function ProviderLimitCard({
       {!loading && !error && !message && quotas?.length > 0 && (
         <div className="space-y-4">
           {quotas.map((quota, index) => {
-            // For Antigravity, use remainingPercentage if available, otherwise calculate
             const percentage =
               quota.remainingPercentage !== undefined
-                ? Math.round(((quota.total - quota.used) / quota.total) * 100)
+                ? Math.round(quota.remainingPercentage)
                 : calculatePercentage(quota.used, quota.total);
             const unlimited = quota.total === 0 || quota.total === null;
 

src/app/(dashboard)/dashboard/usage/components/ProviderLimits/utils.tsx

@@ -1,4 +1,5 @@
 import { getModelsByProviderId } from "@omniroute/open-sse/config/providerModels.ts";
+import { safePercentage } from "@/shared/utils/formatting";
 
 /**
  * Format ISO date string to countdown format (inspired by vscode-antigravity-cockpit)
@@ -110,7 +111,7 @@ export function parseQuotaData(provider, data) {
               used: quota.used || 0,
               total: quota.total || 0,
               resetAt: quota.resetAt || null,
-              remainingPercentage: quota.remainingPercentage,
+              remainingPercentage: safePercentage(quota.remainingPercentage),
             });
           });
         }
@@ -159,7 +160,7 @@ export function parseQuotaData(provider, data) {
               used: quota.used || 0,
               total: quota.total || 0,
               resetAt: quota.resetAt || null,
-              remainingPercentage: quota.remainingPercentage,
+              remainingPercentage: safePercentage(quota.remainingPercentage),
             });
           });
         }

src/app/api/usage/[connectionId]/route.ts

@@ -4,6 +4,11 @@ import { getUsageForProvider } from "@omniroute/open-sse/services/usage.ts";
 import { getExecutor } from "@omniroute/open-sse/executors/index.ts";
 import { syncToCloud } from "@/lib/cloudSync";
 import { runWithProxyContext } from "@omniroute/open-sse/utils/proxyFetch.ts";
+import { setQuotaCache } from "@/domain/quotaCache";
+
+function isRecord(value: unknown): value is Record<string, any> {
+  return value !== null && typeof value === "object" && !Array.isArray(value);
+}
 
 /**
  * Sync to cloud if enabled
@@ -147,6 +152,12 @@ export async function GET(request: Request, { params }: { params: Promise<{ conn
     const usage = await runWithProxyContext(proxyInfo?.proxy || null, () =>
       getUsageForProvider(connection)
     );
+
+    // Populate quota cache for quota-aware account selection
+    if (isRecord(usage?.quotas)) {
+      setQuotaCache(connectionId, connection.provider, usage.quotas);
+    }
+
     return Response.json(usage);
   } catch (error) {
     console.error("[Usage API] Error fetching usage:", error);

src/app/globals.css

@@ -6,6 +6,9 @@
    directives ensure all utility classes in route groups are included. */
 @source "../app/(dashboard)";
 @source "../../open-sse";
+@source not "../../*.sqlite*";
+@source not "../../.claude*";
+@source not "../../.claude-memory";
 
 @custom-variant dark (&:where(.dark, .dark *));
 

src/domain/quotaCache.ts

@@ -0,0 +1,264 @@
+/**
+ * Quota Cache — Domain Layer
+ *
+ * In-memory cache of provider quota data per connectionId.
+ * Populated by:
+ *   - Dashboard usage endpoint (GET /api/usage/[connectionId])
+ *   - 429 responses marking account as exhausted
+ *
+ * Background refresh runs every 1 minute:
+ *   - Active accounts (quota > 0%): refetch every 5 minutes
+ *   - Exhausted accounts: refetch every 5 minutes (or immediately after resetAt passes)
+ *
+ * @module domain/quotaCache
+ */
+
+import { getUsageForProvider } from "@omniroute/open-sse/services/usage.ts";
+import { getProviderConnectionById, resolveProxyForConnection } from "@/lib/localDb";
+import { runWithProxyContext } from "@omniroute/open-sse/utils/proxyFetch.ts";
+import { safePercentage } from "@/shared/utils/formatting";
+
+// ─── Types ──────────────────────────────────────────────────────────────────
+
+interface QuotaInfo {
+  remainingPercentage: number;
+  resetAt: string | null;
+}
+
+interface QuotaCacheEntry {
+  connectionId: string;
+  provider: string;
+  quotas: Record<string, QuotaInfo>;
+  fetchedAt: number;
+  exhausted: boolean;
+  nextResetAt: string | null;
+}
+
+// ─── Constants ──────────────────────────────────────────────────────────────
+
+const ACTIVE_TTL_MS = 5 * 60 * 1000; // 5 minutes for active accounts
+const EXHAUSTED_TTL_MS = 5 * 60 * 1000; // 5 minutes for 429-sourced entries (no resetAt)
+const EXHAUSTED_REFRESH_MS = 5 * 60 * 1000; // 5 minutes: recheck exhausted accounts (aligned with TTL)
+const REFRESH_INTERVAL_MS = 60 * 1000; // Background tick every 1 minute
+
+// ─── State ──────────────────────────────────────────────────────────────────
+
+const cache = new Map<string, QuotaCacheEntry>();
+const MAX_CONCURRENT_REFRESHES = 5;
+let refreshTimer: ReturnType<typeof setInterval> | null = null;
+let tickRunning = false;
+
+// ─── Helpers ────────────────────────────────────────────────────────────────
+
+function isExhausted(quotas: Record<string, QuotaInfo>): boolean {
+  const entries = Object.values(quotas);
+  if (entries.length === 0) return false;
+  return entries.every((q) => q.remainingPercentage <= 0);
+}
+
+function parseDate(value: string): number | null {
+  const ms = new Date(value).getTime();
+  return Number.isNaN(ms) ? null : ms;
+}
+
+function earliestResetAt(quotas: Record<string, QuotaInfo>): string | null {
+  let earliest: string | null = null;
+  let earliestMs = Infinity;
+  for (const q of Object.values(quotas)) {
+    if (!q.resetAt) continue;
+    const ms = parseDate(q.resetAt);
+    if (ms !== null && ms < earliestMs) {
+      earliestMs = ms;
+      earliest = q.resetAt;
+    }
+  }
+  return earliest;
+}
+
+function normalizeQuotas(rawQuotas: Record<string, any>): Record<string, QuotaInfo> {
+  const result: Record<string, QuotaInfo> = {};
+  for (const [key, q] of Object.entries(rawQuotas)) {
+    if (q && typeof q === "object") {
+      result[key] = {
+        remainingPercentage:
+          safePercentage(q.remainingPercentage) ??
+          (q.total > 0 ? Math.round(((q.total - (q.used || 0)) / q.total) * 100) : 0),
+        resetAt: q.resetAt || null,
+      };
+    }
+  }
+  return result;
+}
+
+// ─── Public API ─────────────────────────────────────────────────────────────
+
+/**
+ * Store quota data for a connection (called by usage endpoint and background refresh).
+ */
+export function setQuotaCache(
+  connectionId: string,
+  provider: string,
+  rawQuotas: Record<string, any>
+) {
+  const quotas = normalizeQuotas(rawQuotas);
+  const exhausted = isExhausted(quotas);
+  cache.set(connectionId, {
+    connectionId,
+    provider,
+    quotas,
+    fetchedAt: Date.now(),
+    exhausted,
+    nextResetAt: exhausted ? earliestResetAt(quotas) : null,
+  });
+}
+
+/**
+ * Get cached quota entry (returns null if not cached).
+ */
+export function getQuotaCache(connectionId: string): QuotaCacheEntry | null {
+  return cache.get(connectionId) || null;
+}
+
+/**
+ * Check if an account's quota is exhausted based on cached data.
+ * Returns false if no cache entry exists (unknown = assume available).
+ */
+export function isAccountQuotaExhausted(connectionId: string): boolean {
+  const entry = cache.get(connectionId);
+  if (!entry) return false;
+  if (!entry.exhausted) return false;
+
+  // If resetAt has passed, assume available until refresh confirms
+  if (entry.nextResetAt) {
+    const resetMs = parseDate(entry.nextResetAt);
+    if (resetMs !== null && resetMs <= Date.now()) return false;
+  }
+
+  // Exhausted entries without resetAt expire after fixed TTL
+  const age = Date.now() - entry.fetchedAt;
+  if (!entry.nextResetAt && age > EXHAUSTED_TTL_MS) return false;
+
+  return true;
+}
+
+/**
+ * Mark an account as quota-exhausted from a 429 response (no quota data available).
+ * Uses 5-minute fixed TTL since we don't know the actual resetAt.
+ */
+export function markAccountExhaustedFrom429(connectionId: string, provider: string) {
+  cache.set(connectionId, {
+    connectionId,
+    provider,
+    quotas: {},
+    fetchedAt: Date.now(),
+    exhausted: true,
+    nextResetAt: null,
+  });
+}
+
+// ─── Background Refresh ─────────────────────────────────────────────────────
+
+const refreshingSet = new Set<string>();
+
+async function refreshEntry(entry: QuotaCacheEntry) {
+  if (refreshingSet.has(entry.connectionId)) return;
+  refreshingSet.add(entry.connectionId);
+
+  try {
+    const connection = await getProviderConnectionById(entry.connectionId);
+    if (!connection || connection.authType !== "oauth" || !connection.isActive) {
+      cache.delete(entry.connectionId);
+      return;
+    }
+
+    const proxyInfo = await resolveProxyForConnection(entry.connectionId);
+    const usage = await runWithProxyContext(proxyInfo?.proxy || null, () =>
+      getUsageForProvider(connection)
+    );
+
+    if (usage?.quotas) {
+      setQuotaCache(entry.connectionId, entry.provider, usage.quotas);
+    }
+  } catch (err) {
+    console.warn(
+      `[QuotaCache] Refresh failed for ${entry.connectionId.slice(0, 8)}:`,
+      (err as any)?.message || err
+    );
+  } finally {
+    refreshingSet.delete(entry.connectionId);
+  }
+}
+
+function needsRefresh(entry: QuotaCacheEntry, now: number): boolean {
+  const age = now - entry.fetchedAt;
+  if (entry.exhausted) {
+    if (entry.nextResetAt) {
+      const resetMs = parseDate(entry.nextResetAt);
+      if (resetMs !== null && resetMs <= now) return true;
+    }
+    return age >= EXHAUSTED_REFRESH_MS;
+  }
+  return age >= ACTIVE_TTL_MS;
+}
+
+async function backgroundRefreshTick() {
+  if (tickRunning) return;
+  tickRunning = true;
+
+  try {
+    const now = Date.now();
+    const pending = [...cache.values()].filter((e) => needsRefresh(e, now));
+
+    // Refresh in batches to avoid thundering herd
+    for (let i = 0; i < pending.length; i += MAX_CONCURRENT_REFRESHES) {
+      const batch = pending.slice(i, i + MAX_CONCURRENT_REFRESHES);
+      await Promise.allSettled(batch.map(refreshEntry));
+    }
+  } finally {
+    tickRunning = false;
+  }
+}
+
+/**
+ * Start the background refresh timer.
+ */
+export function startBackgroundRefresh() {
+  if (refreshTimer) return;
+  refreshTimer = setInterval(backgroundRefreshTick, REFRESH_INTERVAL_MS);
+  refreshTimer?.unref?.();
+}
+
+/**
+ * Stop the background refresh timer.
+ */
+export function stopBackgroundRefresh() {
+  if (refreshTimer) {
+    clearInterval(refreshTimer);
+    refreshTimer = null;
+  }
+}
+
+/**
+ * Get cache stats (for debugging/dashboard).
+ */
+export function getQuotaCacheStats() {
+  const entries: Array<{
+    connectionId: string;
+    provider: string;
+    exhausted: boolean;
+    nextResetAt: string | null;
+    ageMs: number;
+  }> = [];
+
+  for (const entry of cache.values()) {
+    entries.push({
+      connectionId: entry.connectionId.slice(0, 8) + "...",
+      provider: entry.provider,
+      exhausted: entry.exhausted,
+      nextResetAt: entry.nextResetAt,
+      ageMs: Date.now() - entry.fetchedAt,
+    });
+  }
+
+  return { total: cache.size, entries };
+}

src/instrumentation.ts

@@ -39,6 +39,13 @@ export async function register() {
     const { initApiBridgeServer } = await import("@/lib/apiBridgeServer");
     initApiBridgeServer();
 
+    // Quota cache: start background refresh for quota-aware account selection
+    // Dynamic import required — quotaCache depends on better-sqlite3 (Node-only),
+    // and instrumentation.ts is bundled for all runtimes including Edge.
+    const { startBackgroundRefresh } = await import("@/domain/quotaCache");
+    startBackgroundRefresh();
+    console.log("[STARTUP] Quota cache background refresh started");
+
     // Compliance: Initialize audit_log table + cleanup expired logs
     try {
       const { initAuditLog, cleanupExpiredLogs } = await import("@/lib/compliance/index");

src/shared/utils/formatting.ts

@@ -148,3 +148,11 @@ export function truncateUrl(url, max = 50) {
     return url.length > max ? url.slice(0, max) + "…" : url;
   }
 }
+
+/**
+ * Safely extract a finite number, returning undefined for invalid values.
+ * Used by quota normalization in both backend (quotaCache) and frontend (ProviderLimits).
+ */
+export function safePercentage(value: unknown): number | undefined {
+  return typeof value === "number" && isFinite(value) ? value : undefined;
+}

src/shared/validation/schemas.js

@@ -1,912 +0,0 @@
-"use strict";
-Object.defineProperty(exports, "__esModule", { value: true });
-exports.dbBackupRestoreSchema =
-  exports.testComboSchema =
-  exports.updateComboSchema =
-  exports.cloudSyncActionSchema =
-  exports.cloudModelAliasUpdateSchema =
-  exports.cloudResolveAliasSchema =
-  exports.cloudCredentialUpdateSchema =
-  exports.kiroSocialExchangeSchema =
-  exports.kiroImportSchema =
-  exports.cursorImportSchema =
-  exports.oauthPollSchema =
-  exports.oauthExchangeSchema =
-  exports.translatorTranslateSchema =
-  exports.translatorSendSchema =
-  exports.translatorSaveSchema =
-  exports.translatorDetectSchema =
-  exports.testProxySchema =
-  exports.updateProxyConfigSchema =
-  exports.removeModelAliasSchema =
-  exports.addModelAliasSchema =
-  exports.updateModelAliasesSchema =
-  exports.updateIpFilterSchema =
-  exports.updateThinkingBudgetSchema =
-  exports.updateSystemPromptSchema =
-  exports.updateRequireLoginSchema =
-  exports.updateComboDefaultsSchema =
-  exports.resetStatsActionSchema =
-  exports.jsonObjectSchema =
-  exports.updateResilienceSchema =
-  exports.toggleRateLimitSchema =
-  exports.updatePricingSchema =
-  exports.providerModelMutationSchema =
-  exports.clearModelAvailabilitySchema =
-  exports.updateModelAliasSchema =
-  exports.removeFallbackSchema =
-  exports.registerFallbackSchema =
-  exports.policyActionSchema =
-  exports.setBudgetSchema =
-  exports.v1CountTokensSchema =
-  exports.providerChatCompletionSchema =
-  exports.v1RerankSchema =
-  exports.v1ModerationSchema =
-  exports.v1AudioSpeechSchema =
-  exports.v1ImageGenerationSchema =
-  exports.v1EmbeddingsSchema =
-  exports.loginSchema =
-  exports.updateSettingsSchema =
-  exports.createComboSchema =
-  exports.createKeySchema =
-  exports.createProviderSchema =
-    void 0;
-exports.guideSettingsSaveSchema =
-  exports.codexProfileIdSchema =
-  exports.codexProfileNameSchema =
-  exports.cliModelConfigSchema =
-  exports.cliSettingsEnvSchema =
-  exports.cliBackupMutationSchema =
-  exports.cliMitmAliasUpdateSchema =
-  exports.cliMitmStopSchema =
-  exports.cliMitmStartSchema =
-  exports.v1betaGeminiGenerateSchema =
-  exports.validateProviderApiKeySchema =
-  exports.providersBatchTestSchema =
-  exports.updateProviderConnectionSchema =
-  exports.providerNodeValidateSchema =
-  exports.updateProviderNodeSchema =
-  exports.createProviderNodeSchema =
-  exports.updateKeyPermissionsSchema =
-  exports.evalRunSuiteSchema =
-    void 0;
-exports.validateBody = validateBody;
-var zod_1 = require("zod");
-// ──── Provider Schemas ────
-exports.createProviderSchema = zod_1.z.object({
-  provider: zod_1.z.string().min(1).max(100),
-  apiKey: zod_1.z.string().min(1).max(10000),
-  name: zod_1.z.string().min(1).max(200),
-  priority: zod_1.z.number().int().min(1).max(100).optional(),
-  globalPriority: zod_1.z.number().int().min(1).max(100).nullable().optional(),
-  defaultModel: zod_1.z.string().max(200).nullable().optional(),
-  testStatus: zod_1.z.string().max(50).optional(),
-});
-// ──── API Key Schemas ────
-exports.createKeySchema = zod_1.z.object({
-  name: zod_1.z.string().min(1, "Name is required").max(200),
-});
-// ──── Combo Schemas ────
-// A model entry can be a plain string (legacy) or an object with weight
-var comboModelEntry = zod_1.z.union([
-  zod_1.z.string(),
-  zod_1.z.object({
-    model: zod_1.z.string().min(1),
-    weight: zod_1.z.number().min(0).max(100).default(0),
-  }),
-]);
-// Per-combo config overrides
-var comboConfigSchema = zod_1.z
-  .object({
-    maxRetries: zod_1.z.number().int().min(0).max(10).optional(),
-    retryDelayMs: zod_1.z.number().int().min(0).max(60000).optional(),
-    timeoutMs: zod_1.z.number().int().min(1000).max(600000).optional(),
-    healthCheckEnabled: zod_1.z.boolean().optional(),
-  })
-  .optional();
-var comboStrategySchema = zod_1.z.enum([
-  "priority",
-  "weighted",
-  "round-robin",
-  "random",
-  "least-used",
-  "cost-optimized",
-]);
-var comboRuntimeConfigSchema = zod_1.z
-  .object({
-    strategy: comboStrategySchema.optional(),
-    maxRetries: zod_1.z.coerce.number().int().min(0).max(10).optional(),
-    retryDelayMs: zod_1.z.coerce.number().int().min(0).max(60000).optional(),
-    timeoutMs: zod_1.z.coerce.number().int().min(1000).max(600000).optional(),
-    concurrencyPerModel: zod_1.z.coerce.number().int().min(1).max(20).optional(),
-    queueTimeoutMs: zod_1.z.coerce.number().int().min(1000).max(120000).optional(),
-    healthCheckEnabled: zod_1.z.boolean().optional(),
-    healthCheckTimeoutMs: zod_1.z.coerce.number().int().min(100).max(30000).optional(),
-    maxComboDepth: zod_1.z.coerce.number().int().min(1).max(10).optional(),
-    trackMetrics: zod_1.z.boolean().optional(),
-  })
-  .strict();
-exports.createComboSchema = zod_1.z.object({
-  name: zod_1.z
-    .string()
-    .min(1, "Name is required")
-    .max(100)
-    .regex(/^[a-zA-Z0-9_/.-]+$/, "Name can only contain letters, numbers, -, _, / and ."),
-  models: zod_1.z.array(comboModelEntry).optional().default([]),
-  strategy: comboStrategySchema.optional().default("priority"),
-  config: comboConfigSchema,
-});
-// ──── Settings Schemas ────
-// FASE-01: Removed .passthrough() — only explicitly listed fields are accepted
-exports.updateSettingsSchema = zod_1.z.object({
-  newPassword: zod_1.z.string().min(1).max(200).optional(),
-  currentPassword: zod_1.z.string().max(200).optional(),
-  theme: zod_1.z.string().max(50).optional(),
-  language: zod_1.z.string().max(10).optional(),
-  requireLogin: zod_1.z.boolean().optional(),
-  enableRequestLogs: zod_1.z.boolean().optional(),
-  enableSocks5Proxy: zod_1.z.boolean().optional(),
-  instanceName: zod_1.z.string().max(100).optional(),
-  corsOrigins: zod_1.z.string().max(500).optional(),
-  logRetentionDays: zod_1.z.number().int().min(1).max(365).optional(),
-  cloudUrl: zod_1.z.string().max(500).optional(),
-  baseUrl: zod_1.z.string().max(500).optional(),
-  setupComplete: zod_1.z.boolean().optional(),
-  requireAuthForModels: zod_1.z.boolean().optional(),
-  blockedProviders: zod_1.z.array(zod_1.z.string().max(100)).optional(),
-  hideHealthCheckLogs: zod_1.z.boolean().optional(),
-  // Routing settings (#134)
-  fallbackStrategy: zod_1.z
-    .enum(["fill-first", "round-robin", "p2c", "random", "least-used", "cost-optimized"])
-    .optional(),
-  wildcardAliases: zod_1.z
-    .array(zod_1.z.object({ pattern: zod_1.z.string(), target: zod_1.z.string() }))
-    .optional(),
-  stickyRoundRobinLimit: zod_1.z.number().int().min(0).max(1000).optional(),
-});
-// ──── Auth Schemas ────
-exports.loginSchema = zod_1.z.object({
-  password: zod_1.z.string().min(1, "Password is required").max(200),
-});
-// ──── API Route Payload Schemas (T06) ────
-var modelIdSchema = zod_1.z.string().trim().min(1, "Model is required").max(200);
-var nonEmptyStringSchema = zod_1.z.string().trim().min(1, "Field is required");
-var embeddingTokenArraySchema = zod_1.z
-  .array(zod_1.z.number().int().min(0))
-  .min(1, "input token array must contain at least one item");
-var embeddingInputSchema = zod_1.z.union([
-  nonEmptyStringSchema,
-  zod_1.z.array(nonEmptyStringSchema).min(1, "input must contain at least one item"),
-  embeddingTokenArraySchema,
-  zod_1.z.array(embeddingTokenArraySchema).min(1, "input must contain at least one item"),
-]);
-var chatMessageSchema = zod_1.z
-  .object({
-    role: zod_1.z.string().trim().min(1, "messages[].role is required"),
-    content: zod_1.z
-      .union([nonEmptyStringSchema, zod_1.z.array(zod_1.z.unknown()).min(1), zod_1.z.null()])
-      .optional(),
-  })
-  .catchall(zod_1.z.unknown());
-var countTokensMessageSchema = zod_1.z
-  .object({
-    content: zod_1.z.union([
-      nonEmptyStringSchema,
-      zod_1.z
-        .array(
-          zod_1.z
-            .object({
-              type: zod_1.z.string().optional(),
-              text: zod_1.z.string().optional(),
-            })
-            .catchall(zod_1.z.unknown())
-        )
-        .min(1, "messages[].content must contain at least one item"),
-    ]),
-  })
-  .catchall(zod_1.z.unknown());
-exports.v1EmbeddingsSchema = zod_1.z
-  .object({
-    model: modelIdSchema,
-    input: embeddingInputSchema,
-    dimensions: zod_1.z.coerce.number().int().positive().optional(),
-    encoding_format: zod_1.z.enum(["float", "base64"]).optional(),
-  })
-  .catchall(zod_1.z.unknown());
-exports.v1ImageGenerationSchema = zod_1.z
-  .object({
-    model: modelIdSchema,
-    prompt: nonEmptyStringSchema,
-  })
-  .catchall(zod_1.z.unknown());
-exports.v1AudioSpeechSchema = zod_1.z
-  .object({
-    model: modelIdSchema,
-    input: nonEmptyStringSchema,
-  })
-  .catchall(zod_1.z.unknown());
-exports.v1ModerationSchema = zod_1.z
-  .object({
-    model: modelIdSchema.optional(),
-    input: zod_1.z.unknown().refine(function (value) {
-      if (value === undefined || value === null) return false;
-      if (typeof value === "string") return value.trim().length > 0;
-      if (Array.isArray(value)) return value.length > 0;
-      return true;
-    }, "Input is required"),
-  })
-  .catchall(zod_1.z.unknown());
-exports.v1RerankSchema = zod_1.z
-  .object({
-    model: modelIdSchema,
-    query: nonEmptyStringSchema,
-    documents: zod_1.z.array(zod_1.z.unknown()).min(1, "documents must contain at least one item"),
-  })
-  .catchall(zod_1.z.unknown());
-exports.providerChatCompletionSchema = zod_1.z
-  .object({
-    model: modelIdSchema,
-    messages: zod_1.z.array(chatMessageSchema).min(1).optional(),
-    input: zod_1.z
-      .union([nonEmptyStringSchema, zod_1.z.array(zod_1.z.unknown()).min(1)])
-      .optional(),
-    prompt: nonEmptyStringSchema.optional(),
-  })
-  .catchall(zod_1.z.unknown())
-  .superRefine(function (value, ctx) {
-    if (value.messages === undefined && value.input === undefined && value.prompt === undefined) {
-      ctx.addIssue({
-        code: zod_1.z.ZodIssueCode.custom,
-        message: "messages, input or prompt is required",
-        path: [],
-      });
-    }
-  });
-exports.v1CountTokensSchema = zod_1.z
-  .object({
-    messages: zod_1.z
-      .array(countTokensMessageSchema)
-      .min(1, "messages must contain at least one item"),
-  })
-  .catchall(zod_1.z.unknown());
-exports.setBudgetSchema = zod_1.z.object({
-  apiKeyId: zod_1.z.string().trim().min(1, "apiKeyId is required"),
-  dailyLimitUsd: zod_1.z.coerce.number().positive("dailyLimitUsd must be greater than zero"),
-  monthlyLimitUsd: zod_1.z.coerce
-    .number()
-    .positive("monthlyLimitUsd must be greater than zero")
-    .optional(),
-  warningThreshold: zod_1.z.coerce.number().min(0).max(1).optional(),
-});
-exports.policyActionSchema = zod_1.z
-  .object({
-    action: zod_1.z.enum(["unlock"]),
-    identifier: zod_1.z.string().trim().min(1).optional(),
-  })
-  .superRefine(function (value, ctx) {
-    if (value.action === "unlock" && !value.identifier) {
-      ctx.addIssue({
-        code: zod_1.z.ZodIssueCode.custom,
-        message: "identifier is required for unlock action",
-        path: ["identifier"],
-      });
-    }
-  });
-var fallbackChainEntrySchema = zod_1.z
-  .object({
-    provider: zod_1.z.string().trim().min(1, "provider is required"),
-    priority: zod_1.z.number().int().min(1).max(100).optional(),
-    enabled: zod_1.z.boolean().optional(),
-  })
-  .catchall(zod_1.z.unknown());
-exports.registerFallbackSchema = zod_1.z.object({
-  model: modelIdSchema,
-  chain: zod_1.z.array(fallbackChainEntrySchema).min(1, "chain must contain at least one provider"),
-});
-exports.removeFallbackSchema = zod_1.z.object({
-  model: modelIdSchema,
-});
-exports.updateModelAliasSchema = zod_1.z.object({
-  model: modelIdSchema,
-  alias: zod_1.z.string().trim().min(1, "Alias is required").max(200),
-});
-exports.clearModelAvailabilitySchema = zod_1.z.object({
-  provider: zod_1.z.string().trim().min(1, "provider is required").max(120),
-  model: modelIdSchema,
-});
-exports.providerModelMutationSchema = zod_1.z.object({
-  provider: zod_1.z.string().trim().min(1, "provider is required").max(120),
-  modelId: zod_1.z.string().trim().min(1, "modelId is required").max(240),
-  modelName: zod_1.z.string().trim().max(240).optional(),
-  source: zod_1.z.string().trim().max(80).optional(),
-});
-var pricingFieldsSchema = zod_1.z
-  .object({
-    input: zod_1.z.number().min(0).optional(),
-    output: zod_1.z.number().min(0).optional(),
-    cached: zod_1.z.number().min(0).optional(),
-    reasoning: zod_1.z.number().min(0).optional(),
-    cache_creation: zod_1.z.number().min(0).optional(),
-  })
-  .strict();
-exports.updatePricingSchema = zod_1.z.record(
-  zod_1.z.string().trim().min(1),
-  zod_1.z.record(zod_1.z.string().trim().min(1), pricingFieldsSchema)
-);
-exports.toggleRateLimitSchema = zod_1.z.object({
-  connectionId: zod_1.z.string().trim().min(1, "connectionId is required"),
-  enabled: zod_1.z.boolean(),
-});
-var resilienceProfileSchema = zod_1.z.object({
-  transientCooldown: zod_1.z.number().min(0),
-  rateLimitCooldown: zod_1.z.number().min(0),
-  maxBackoffLevel: zod_1.z.number().int().min(0),
-  circuitBreakerThreshold: zod_1.z.number().int().min(0),
-  circuitBreakerReset: zod_1.z.number().min(0),
-});
-var resilienceDefaultsSchema = zod_1.z
-  .object({
-    requestsPerMinute: zod_1.z.number().int().min(1).optional(),
-    minTimeBetweenRequests: zod_1.z.number().int().min(1).optional(),
-    concurrentRequests: zod_1.z.number().int().min(1).optional(),
-  })
-  .strict();
-exports.updateResilienceSchema = zod_1.z
-  .object({
-    profiles: zod_1.z
-      .object({
-        oauth: resilienceProfileSchema.optional(),
-        apikey: resilienceProfileSchema.optional(),
-      })
-      .strict()
-      .optional(),
-    defaults: resilienceDefaultsSchema.optional(),
-  })
-  .superRefine(function (value, ctx) {
-    if (!value.profiles && !value.defaults) {
-      ctx.addIssue({
-        code: zod_1.z.ZodIssueCode.custom,
-        message: "Must provide profiles or defaults",
-        path: [],
-      });
-    }
-  });
-exports.jsonObjectSchema = zod_1.z.record(zod_1.z.string(), zod_1.z.unknown());
-exports.resetStatsActionSchema = zod_1.z.object({
-  action: zod_1.z.literal("reset-stats"),
-});
-exports.updateComboDefaultsSchema = zod_1.z
-  .object({
-    comboDefaults: comboRuntimeConfigSchema.optional(),
-    providerOverrides: zod_1.z
-      .record(zod_1.z.string().trim().min(1), comboRuntimeConfigSchema)
-      .optional(),
-  })
-  .superRefine(function (value, ctx) {
-    if (!value.comboDefaults && !value.providerOverrides) {
-      ctx.addIssue({
-        code: zod_1.z.ZodIssueCode.custom,
-        message: "Nothing to update",
-        path: [],
-      });
-    }
-  });
-exports.updateRequireLoginSchema = zod_1.z
-  .object({
-    requireLogin: zod_1.z.boolean().optional(),
-    password: zod_1.z.string().min(4, "Password must be at least 4 characters").optional(),
-  })
-  .superRefine(function (value, ctx) {
-    if (value.requireLogin === undefined && !value.password) {
-      ctx.addIssue({
-        code: zod_1.z.ZodIssueCode.custom,
-        message: "No valid fields to update",
-        path: [],
-      });
-    }
-  });
-exports.updateSystemPromptSchema = zod_1.z
-  .object({
-    prompt: zod_1.z.string().max(50000).optional(),
-    enabled: zod_1.z.boolean().optional(),
-  })
-  .strict()
-  .superRefine(function (value, ctx) {
-    if (value.prompt === undefined && value.enabled === undefined) {
-      ctx.addIssue({
-        code: zod_1.z.ZodIssueCode.custom,
-        message: "No valid fields to update",
-        path: [],
-      });
-    }
-  });
-exports.updateThinkingBudgetSchema = zod_1.z
-  .object({
-    mode: zod_1.z.enum(["passthrough", "auto", "custom", "adaptive"]).optional(),
-    customBudget: zod_1.z.coerce.number().int().min(0).max(131072).optional(),
-    effortLevel: zod_1.z.enum(["none", "low", "medium", "high"]).optional(),
-    baseBudget: zod_1.z.coerce.number().int().min(0).max(131072).optional(),
-    complexityMultiplier: zod_1.z.coerce.number().min(0).optional(),
-  })
-  .strict()
-  .superRefine(function (value, ctx) {
-    if (
-      value.mode === undefined &&
-      value.customBudget === undefined &&
-      value.effortLevel === undefined &&
-      value.baseBudget === undefined &&
-      value.complexityMultiplier === undefined
-    ) {
-      ctx.addIssue({
-        code: zod_1.z.ZodIssueCode.custom,
-        message: "No valid fields to update",
-        path: [],
-      });
-    }
-  });
-var ipFilterModeSchema = zod_1.z.enum(["blacklist", "whitelist"]);
-var tempBanSchema = zod_1.z.object({
-  ip: zod_1.z.string().trim().min(1),
-  durationMs: zod_1.z.coerce.number().int().min(1).optional(),
-  reason: zod_1.z.string().max(200).optional(),
-});
-exports.updateIpFilterSchema = zod_1.z
-  .object({
-    enabled: zod_1.z.boolean().optional(),
-    mode: ipFilterModeSchema.optional(),
-    blacklist: zod_1.z.array(zod_1.z.string()).optional(),
-    whitelist: zod_1.z.array(zod_1.z.string()).optional(),
-    addBlacklist: zod_1.z.string().optional(),
-    removeBlacklist: zod_1.z.string().optional(),
-    addWhitelist: zod_1.z.string().optional(),
-    removeWhitelist: zod_1.z.string().optional(),
-    tempBan: tempBanSchema.optional(),
-    removeBan: zod_1.z.string().optional(),
-  })
-  .strict()
-  .superRefine(function (value, ctx) {
-    if (Object.keys(value).length === 0) {
-      ctx.addIssue({
-        code: zod_1.z.ZodIssueCode.custom,
-        message: "No valid fields to update",
-        path: [],
-      });
-    }
-  });
-exports.updateModelAliasesSchema = zod_1.z.object({
-  aliases: zod_1.z.record(zod_1.z.string().trim().min(1), zod_1.z.string().trim().min(1)),
-});
-exports.addModelAliasSchema = zod_1.z.object({
-  from: zod_1.z.string().trim().min(1),
-  to: zod_1.z.string().trim().min(1),
-});
-exports.removeModelAliasSchema = zod_1.z.object({
-  from: zod_1.z.string().trim().min(1),
-});
-var proxyConfigSchema = zod_1.z
-  .object({
-    type: zod_1.z
-      .preprocess(
-        function (value) {
-          return typeof value === "string" ? value.trim().toLowerCase() : value;
-        },
-        zod_1.z.enum(["http", "https", "socks5"])
-      )
-      .optional(),
-    host: zod_1.z.string().trim().min(1).optional(),
-    port: zod_1.z.coerce.number().int().min(1).max(65535).optional(),
-    username: zod_1.z.string().optional(),
-    password: zod_1.z.string().optional(),
-  })
-  .strict();
-exports.updateProxyConfigSchema = zod_1.z
-  .object({
-    proxy: proxyConfigSchema.nullable().optional(),
-    global: proxyConfigSchema.nullable().optional(),
-    providers: zod_1.z
-      .record(zod_1.z.string().trim().min(1), proxyConfigSchema.nullable())
-      .optional(),
-    combos: zod_1.z.record(zod_1.z.string().trim().min(1), proxyConfigSchema.nullable()).optional(),
-    keys: zod_1.z.record(zod_1.z.string().trim().min(1), proxyConfigSchema.nullable()).optional(),
-    level: zod_1.z.enum(["global", "provider", "combo", "key"]).optional(),
-    id: zod_1.z.string().optional(),
-  })
-  .strict()
-  .superRefine(function (value, ctx) {
-    var _a;
-    var hasPayload =
-      value.proxy !== undefined ||
-      value.global !== undefined ||
-      value.providers !== undefined ||
-      value.combos !== undefined ||
-      value.keys !== undefined ||
-      value.level !== undefined;
-    if (!hasPayload) {
-      ctx.addIssue({
-        code: zod_1.z.ZodIssueCode.custom,
-        message: "No valid fields to update",
-        path: [],
-      });
-    }
-    if (value.level !== undefined && value.proxy === undefined) {
-      ctx.addIssue({
-        code: zod_1.z.ZodIssueCode.custom,
-        message: "proxy is required when level is provided",
-        path: ["proxy"],
-      });
-    }
-    if (
-      value.level &&
-      value.level !== "global" &&
-      !((_a = value.id) === null || _a === void 0 ? void 0 : _a.trim())
-    ) {
-      ctx.addIssue({
-        code: zod_1.z.ZodIssueCode.custom,
-        message: "id is required for provider/combo/key level updates",
-        path: ["id"],
-      });
-    }
-  });
-exports.testProxySchema = zod_1.z.object({
-  proxy: zod_1.z.object({
-    type: zod_1.z.string().optional(),
-    host: zod_1.z.string().trim().min(1, "proxy.host is required"),
-    port: zod_1.z.union([zod_1.z.string(), zod_1.z.number()]),
-    username: zod_1.z.string().optional(),
-    password: zod_1.z.string().optional(),
-  }),
-});
-var jsonRecordSchema = zod_1.z.record(zod_1.z.string(), zod_1.z.unknown());
-var nonEmptyJsonRecordSchema = jsonRecordSchema.refine(function (value) {
-  return Object.keys(value).length > 0;
-}, "Body must be a non-empty object");
-var translatorLogFileSchema = zod_1.z.enum([
-  "1_req_client.json",
-  "2_req_source.json",
-  "3_req_openai.json",
-  "4_req_target.json",
-  "5_res_provider.txt",
-]);
-exports.translatorDetectSchema = zod_1.z.object({
-  body: nonEmptyJsonRecordSchema,
-});
-exports.translatorSaveSchema = zod_1.z.object({
-  file: translatorLogFileSchema,
-  content: zod_1.z.string().min(1, "Content is required").max(1000000, "Content is too large"),
-});
-exports.translatorSendSchema = zod_1.z.object({
-  provider: zod_1.z.string().trim().min(1, "Provider is required"),
-  body: nonEmptyJsonRecordSchema,
-});
-exports.translatorTranslateSchema = zod_1.z
-  .object({
-    step: zod_1.z.union([zod_1.z.number().int().min(1).max(4), zod_1.z.literal("direct")]),
-    provider: zod_1.z.string().trim().min(1).optional(),
-    body: nonEmptyJsonRecordSchema,
-    sourceFormat: zod_1.z.string().optional(),
-    targetFormat: zod_1.z.string().optional(),
-  })
-  .superRefine(function (value, ctx) {
-    if (value.step !== "direct" && !value.provider) {
-      ctx.addIssue({
-        code: zod_1.z.ZodIssueCode.custom,
-        message: "Step and provider are required",
-        path: ["provider"],
-      });
-    }
-  });
-exports.oauthExchangeSchema = zod_1.z.object({
-  code: zod_1.z.string().trim().min(1),
-  redirectUri: zod_1.z.string().trim().min(1),
-  codeVerifier: zod_1.z.string().trim().min(1),
-  state: zod_1.z.string().optional(),
-});
-exports.oauthPollSchema = zod_1.z.object({
-  deviceCode: zod_1.z.string().trim().min(1),
-  codeVerifier: zod_1.z.string().optional(),
-  extraData: zod_1.z.unknown().optional(),
-});
-exports.cursorImportSchema = zod_1.z.object({
-  accessToken: zod_1.z.string().trim().min(1, "Access token is required"),
-  machineId: zod_1.z.string().trim().min(1, "Machine ID is required"),
-});
-exports.kiroImportSchema = zod_1.z.object({
-  refreshToken: zod_1.z.string().trim().min(1, "Refresh token is required"),
-});
-exports.kiroSocialExchangeSchema = zod_1.z.object({
-  code: zod_1.z.string().trim().min(1, "Code is required"),
-  codeVerifier: zod_1.z.string().trim().min(1, "Code verifier is required"),
-  provider: zod_1.z.enum(["google", "github"]),
-});
-exports.cloudCredentialUpdateSchema = zod_1.z.object({
-  provider: zod_1.z.string().trim().min(1, "Provider is required"),
-  credentials: zod_1.z
-    .object({
-      accessToken: zod_1.z.string().optional(),
-      refreshToken: zod_1.z.string().optional(),
-      expiresIn: zod_1.z.coerce.number().positive().optional(),
-    })
-    .strict()
-    .superRefine(function (value, ctx) {
-      if (
-        value.accessToken === undefined &&
-        value.refreshToken === undefined &&
-        value.expiresIn === undefined
-      ) {
-        ctx.addIssue({
-          code: zod_1.z.ZodIssueCode.custom,
-          message: "At least one credential field must be provided",
-          path: [],
-        });
-      }
-    }),
-});
-exports.cloudResolveAliasSchema = zod_1.z.object({
-  alias: zod_1.z.string().trim().min(1, "Missing alias"),
-});
-exports.cloudModelAliasUpdateSchema = zod_1.z.object({
-  model: zod_1.z.string().trim().min(1, "Model and alias required"),
-  alias: zod_1.z.string().trim().min(1, "Model and alias required"),
-});
-exports.cloudSyncActionSchema = zod_1.z.object({
-  action: zod_1.z.enum(["enable", "sync", "disable"]),
-});
-exports.updateComboSchema = zod_1.z
-  .object({
-    name: zod_1.z
-      .string()
-      .min(1, "Name is required")
-      .max(100)
-      .regex(/^[a-zA-Z0-9_/.-]+$/, "Name can only contain letters, numbers, -, _, / and .")
-      .optional(),
-    models: zod_1.z.array(comboModelEntry).optional(),
-    strategy: comboStrategySchema.optional(),
-    config: comboRuntimeConfigSchema.optional(),
-    isActive: zod_1.z.boolean().optional(),
-  })
-  .superRefine(function (value, ctx) {
-    if (
-      value.name === undefined &&
-      value.models === undefined &&
-      value.strategy === undefined &&
-      value.config === undefined &&
-      value.isActive === undefined
-    ) {
-      ctx.addIssue({
-        code: zod_1.z.ZodIssueCode.custom,
-        message: "No valid fields to update",
-        path: [],
-      });
-    }
-  });
-exports.testComboSchema = zod_1.z.object({
-  comboName: zod_1.z.string().trim().min(1, "comboName is required"),
-});
-exports.dbBackupRestoreSchema = zod_1.z.object({
-  backupId: zod_1.z.string().trim().min(1, "backupId is required"),
-});
-exports.evalRunSuiteSchema = zod_1.z.object({
-  suiteId: zod_1.z.string().trim().min(1, "suiteId is required"),
-  outputs: zod_1.z.record(zod_1.z.string(), zod_1.z.unknown()),
-});
-exports.updateKeyPermissionsSchema = zod_1.z
-  .object({
-    allowedModels: zod_1.z.array(zod_1.z.string().trim().min(1)).max(1000).optional(),
-    noLog: zod_1.z.boolean().optional(),
-  })
-  .superRefine(function (value, ctx) {
-    if (value.allowedModels === undefined && value.noLog === undefined) {
-      ctx.addIssue({
-        code: zod_1.z.ZodIssueCode.custom,
-        message: "No valid fields to update",
-        path: [],
-      });
-    }
-  });
-exports.createProviderNodeSchema = zod_1.z
-  .object({
-    name: zod_1.z.string().trim().min(1, "Name is required"),
-    prefix: zod_1.z.string().trim().min(1, "Prefix is required"),
-    apiType: zod_1.z.enum(["chat", "responses"]).optional(),
-    baseUrl: zod_1.z.string().trim().min(1).optional(),
-    type: zod_1.z.enum(["openai-compatible", "anthropic-compatible"]).optional(),
-  })
-  .superRefine(function (value, ctx) {
-    var nodeType = value.type || "openai-compatible";
-    if (nodeType === "openai-compatible" && !value.apiType) {
-      ctx.addIssue({
-        code: zod_1.z.ZodIssueCode.custom,
-        message: "Invalid OpenAI compatible API type",
-        path: ["apiType"],
-      });
-    }
-  });
-exports.updateProviderNodeSchema = zod_1.z.object({
-  name: zod_1.z.string().trim().min(1, "Name is required"),
-  prefix: zod_1.z.string().trim().min(1, "Prefix is required"),
-  apiType: zod_1.z.enum(["chat", "responses"]).optional(),
-  baseUrl: zod_1.z.string().trim().min(1, "Base URL is required"),
-});
-exports.providerNodeValidateSchema = zod_1.z.object({
-  baseUrl: zod_1.z.string().trim().min(1, "Base URL and API key required"),
-  apiKey: zod_1.z.string().trim().min(1, "Base URL and API key required"),
-  type: zod_1.z.enum(["openai-compatible", "anthropic-compatible"]).optional(),
-});
-exports.updateProviderConnectionSchema = zod_1.z
-  .object({
-    name: zod_1.z.string().max(200).optional(),
-    priority: zod_1.z.coerce.number().int().min(1).max(100).optional(),
-    globalPriority: zod_1.z
-      .union([zod_1.z.coerce.number().int().min(1).max(100), zod_1.z.null()])
-      .optional(),
-    defaultModel: zod_1.z.union([zod_1.z.string().max(200), zod_1.z.null()]).optional(),
-    isActive: zod_1.z.boolean().optional(),
-    apiKey: zod_1.z.string().max(10000).optional(),
-    testStatus: zod_1.z.string().max(50).optional(),
-    lastError: zod_1.z.union([zod_1.z.string(), zod_1.z.null()]).optional(),
-    lastErrorAt: zod_1.z.union([zod_1.z.string(), zod_1.z.null()]).optional(),
-    lastErrorType: zod_1.z.union([zod_1.z.string(), zod_1.z.null()]).optional(),
-    lastErrorSource: zod_1.z.union([zod_1.z.string(), zod_1.z.null()]).optional(),
-    errorCode: zod_1.z.union([zod_1.z.string(), zod_1.z.null()]).optional(),
-    rateLimitedUntil: zod_1.z.union([zod_1.z.string(), zod_1.z.null()]).optional(),
-    lastTested: zod_1.z.union([zod_1.z.string(), zod_1.z.null()]).optional(),
-    healthCheckInterval: zod_1.z.coerce.number().int().min(0).optional(),
-  })
-  .superRefine(function (value, ctx) {
-    if (Object.keys(value).length === 0) {
-      ctx.addIssue({
-        code: zod_1.z.ZodIssueCode.custom,
-        message: "No valid fields to update",
-        path: [],
-      });
-    }
-  });
-exports.providersBatchTestSchema = zod_1.z
-  .object({
-    mode: zod_1.z.enum(["provider", "oauth", "free", "apikey", "compatible", "all"]),
-    providerId: zod_1.z.string().trim().min(1).optional(),
-  })
-  .superRefine(function (value, ctx) {
-    if (value.mode === "provider" && !value.providerId) {
-      ctx.addIssue({
-        code: zod_1.z.ZodIssueCode.custom,
-        message: "providerId is required when mode=provider",
-        path: ["providerId"],
-      });
-    }
-  });
-exports.validateProviderApiKeySchema = zod_1.z.object({
-  provider: zod_1.z.string().trim().min(1, "Provider and API key required"),
-  apiKey: zod_1.z.string().trim().min(1, "Provider and API key required"),
-});
-var geminiPartSchema = zod_1.z
-  .object({
-    text: zod_1.z.string().optional(),
-  })
-  .catchall(zod_1.z.unknown());
-var geminiContentSchema = zod_1.z
-  .object({
-    role: zod_1.z.string().optional(),
-    parts: zod_1.z.array(geminiPartSchema).optional(),
-  })
-  .catchall(zod_1.z.unknown());
-exports.v1betaGeminiGenerateSchema = zod_1.z
-  .object({
-    contents: zod_1.z.array(geminiContentSchema).optional(),
-    systemInstruction: zod_1.z
-      .object({
-        parts: zod_1.z.array(geminiPartSchema).optional(),
-      })
-      .catchall(zod_1.z.unknown())
-      .optional(),
-    generationConfig: zod_1.z
-      .object({
-        stream: zod_1.z.boolean().optional(),
-        maxOutputTokens: zod_1.z.coerce.number().int().min(1).optional(),
-        temperature: zod_1.z.coerce.number().optional(),
-        topP: zod_1.z.coerce.number().optional(),
-      })
-      .catchall(zod_1.z.unknown())
-      .optional(),
-  })
-  .catchall(zod_1.z.unknown())
-  .superRefine(function (value, ctx) {
-    if (!value.contents && !value.systemInstruction) {
-      ctx.addIssue({
-        code: zod_1.z.ZodIssueCode.custom,
-        message: "contents or systemInstruction is required",
-        path: [],
-      });
-    }
-  });
-exports.cliMitmStartSchema = zod_1.z.object({
-  apiKey: zod_1.z.string().trim().min(1, "Missing apiKey"),
-  sudoPassword: zod_1.z.string().optional(),
-});
-exports.cliMitmStopSchema = zod_1.z.object({
-  sudoPassword: zod_1.z.string().optional(),
-});
-exports.cliMitmAliasUpdateSchema = zod_1.z.object({
-  tool: zod_1.z.string().trim().min(1, "tool and mappings required"),
-  mappings: zod_1.z.record(zod_1.z.string(), zod_1.z.string().optional()),
-});
-exports.cliBackupMutationSchema = zod_1.z
-  .object({
-    tool: zod_1.z.string().trim().min(1).optional(),
-    toolId: zod_1.z.string().trim().min(1).optional(),
-    backupId: zod_1.z.string().trim().min(1, "tool and backupId are required"),
-  })
-  .superRefine(function (value, ctx) {
-    if (!value.tool && !value.toolId) {
-      ctx.addIssue({
-        code: zod_1.z.ZodIssueCode.custom,
-        message: "tool and backupId are required",
-        path: ["tool"],
-      });
-    }
-  });
-var envKeySchema = zod_1.z
-  .string()
-  .trim()
-  .min(1, "Environment key is required")
-  .max(120)
-  .regex(/^[A-Z_][A-Z0-9_]*$/, "Invalid environment key format");
-var envValueSchema = zod_1.z
-  .union([zod_1.z.string(), zod_1.z.number(), zod_1.z.boolean()])
-  .transform(function (value) {
-    return String(value);
-  })
-  .refine(function (value) {
-    return value.length > 0;
-  }, "Environment value is required")
-  .refine(function (value) {
-    return value.length <= 10000;
-  }, "Environment value is too long");
-exports.cliSettingsEnvSchema = zod_1.z.object({
-  env: zod_1.z.record(envKeySchema, envValueSchema).refine(function (value) {
-    return Object.keys(value).length > 0;
-  }, "env must contain at least one key"),
-});
-exports.cliModelConfigSchema = zod_1.z.object({
-  baseUrl: zod_1.z.string().trim().min(1, "baseUrl and model are required"),
-  apiKey: zod_1.z.string().optional(),
-  model: zod_1.z.string().trim().min(1, "baseUrl and model are required"),
-});
-exports.codexProfileNameSchema = zod_1.z.object({
-  name: zod_1.z.string().trim().min(1, "Profile name is required"),
-});
-exports.codexProfileIdSchema = zod_1.z.object({
-  profileId: zod_1.z.string().trim().min(1, "profileId is required"),
-});
-exports.guideSettingsSaveSchema = zod_1.z.object({
-  baseUrl: zod_1.z.string().trim().min(1).optional(),
-  apiKey: zod_1.z.string().optional(),
-  model: zod_1.z.string().trim().min(1, "Model is required"),
-});
-// ──── Helper ────
-/**
- * Parse and validate request body with a Zod schema.
- * Returns { success: true, data } or { success: false, error }.
- */
-function validateBody(schema, body) {
-  var _a;
-  var result = schema.safeParse(body);
-  if (result.success) {
-    return { success: true, data: result.data };
-  }
-  var issues = Array.isArray((_a = result.error) === null || _a === void 0 ? void 0 : _a.issues)
-    ? result.error.issues
-    : [];
-  return {
-    success: false,
-    error: {
-      message: "Invalid request",
-      details: issues.map(function (e) {
-        return {
-          field: e.path.join("."),
-          message: e.message,
-        };
-      }),
-    },
-  };
-}

src/sse/handlers/chat.ts

@@ -31,7 +31,12 @@ import { sanitizeRequest } from "../../shared/utils/inputSanitizer";
 
 // Pipeline integration — wired modules
 import { getCircuitBreaker, CircuitBreakerOpenError } from "../../shared/utils/circuitBreaker";
-import { isModelAvailable, setModelUnavailable } from "../../domain/modelAvailability";
+import {
+  isModelAvailable,
+  setModelUnavailable,
+  clearModelUnavailability,
+} from "../../domain/modelAvailability";
+import { markAccountExhaustedFrom429 } from "../../domain/quotaCache";
 import { RequestTelemetry, recordTelemetry } from "../../shared/utils/requestTelemetry";
 import { generateRequestId } from "../../shared/utils/requestId";
 import { recordCost } from "../../domain/costRules";
@@ -127,7 +132,10 @@ export async function handleChat(request: any, clientRawRequest: any = null) {
   telemetry.startPhase("policy");
   const policy = await enforceApiKeyPolicy(request, modelStr);
   if (policy.rejection) {
-    log.warn("POLICY", `API key policy rejected: ${modelStr} (key=${policy.apiKeyInfo?.id || "unknown"})`);
+    log.warn(
+      "POLICY",
+      `API key policy rejected: ${modelStr} (key=${policy.apiKeyInfo?.id || "unknown"})`
+    );
     return policy.rejection;
   }
   const apiKeyInfo = policy.apiKeyInfo;
@@ -243,6 +251,13 @@ async function handleSingleModelChat(
     const credentials = await getProviderCredentials(provider, excludeConnectionId);
 
     if (!credentials || credentials.allRateLimited) {
+      if (lastStatus === 429 || lastStatus === 503) {
+        setModelUnavailable(provider, model, 60000, `HTTP ${lastStatus}`);
+        log.info(
+          "AVAILABILITY",
+          `${provider}/${model} marked unavailable — all accounts exhausted (HTTP ${lastStatus})`
+        );
+      }
       return handleNoCredentials(
         credentials,
         excludeConnectionId,
@@ -296,22 +311,19 @@ async function handleSingleModelChat(
     });
 
     if (result.success) {
+      clearModelUnavailability(provider, model);
       recordCostIfNeeded(apiKeyInfo, result);
       if (telemetry) telemetry.startPhase("finalize");
       if (telemetry) telemetry.endPhase();
       return result.response;
     }
 
-    // Pipeline: Mark model unavailable on repeated failures
-    if (result.status === 429 || result.status === 503) {
-      setModelUnavailable(provider, model, 60000, `HTTP ${result.status}`);
-      log.info(
-        "AVAILABILITY",
-        `${provider}/${model} marked unavailable for 60s (HTTP ${result.status})`
-      );
+    // 6. Mark account as quota-exhausted on 429 response
+    if (result.status === 429) {
+      markAccountExhaustedFrom429(credentials.connectionId, provider);
     }
 
-    // 6. Fallback to next account
+    // 7. Fallback to next account
     const { shouldFallback } = await markAccountUnavailable(
       credentials.connectionId,
       result.status,

src/sse/services/auth.ts

@@ -4,6 +4,7 @@ import {
   updateProviderConnection,
   getSettings,
 } from "@/lib/localDb";
+import { isAccountQuotaExhausted } from "@/domain/quotaCache";
 import {
   isAccountUnavailable,
   getUnavailableUntil,
@@ -197,6 +198,19 @@ export async function getProviderCredentials(
       return null;
     }
 
+    // Quota-aware: prioritize accounts with available quota
+    const withQuota = availableConnections.filter((c) => !isAccountQuotaExhausted(c.id));
+    const exhaustedQuota = availableConnections.filter((c) => isAccountQuotaExhausted(c.id));
+    const orderedConnections =
+      withQuota.length > 0 ? [...withQuota, ...exhaustedQuota] : availableConnections;
+
+    if (exhaustedQuota.length > 0) {
+      log.debug(
+        "AUTH",
+        `${provider} | quota-aware: ${withQuota.length} with quota, ${exhaustedQuota.length} exhausted`
+      );
+    }
+
     const settings = await getSettings();
     const strategy = settings.fallbackStrategy || "fill-first";
 
@@ -205,7 +219,7 @@ export async function getProviderCredentials(
       const stickyLimit = toNumber((settings as Record<string, unknown>).stickyRoundRobinLimit, 3);
 
       // Sort by lastUsed (most recent first) to find current candidate
-      const byRecency = [...availableConnections].sort((a: any, b: any) => {
+      const byRecency = [...orderedConnections].sort((a: any, b: any) => {
         if (!a.lastUsedAt && !b.lastUsedAt) return (a.priority || 999) - (b.priority || 999);
         if (!a.lastUsedAt) return 1;
         if (!b.lastUsedAt) return -1;
@@ -225,7 +239,7 @@ export async function getProviderCredentials(
         });
       } else {
         // Pick the least recently used (excluding current if possible)
-        const sortedByOldest = [...availableConnections].sort((a: any, b: any) => {
+        const sortedByOldest = [...orderedConnections].sort((a: any, b: any) => {
           if (!a.lastUsedAt && !b.lastUsedAt) return (a.priority || 999) - (b.priority || 999);
           if (!a.lastUsedAt) return -1;
           if (!b.lastUsedAt) return 1;
@@ -242,14 +256,14 @@ export async function getProviderCredentials(
       }
     } else if (strategy === "p2c") {
       // Power of Two Choices: pick 2 random, choose the one with fewer failures
-      if (availableConnections.length <= 2) {
-        connection = availableConnections[0];
+      if (orderedConnections.length <= 2) {
+        connection = orderedConnections[0];
       } else {
-        const i = Math.floor(Math.random() * availableConnections.length);
-        let j = Math.floor(Math.random() * (availableConnections.length - 1));
+        const i = Math.floor(Math.random() * orderedConnections.length);
+        let j = Math.floor(Math.random() * (orderedConnections.length - 1));
         if (j >= i) j++;
-        const a = availableConnections[i];
-        const b = availableConnections[j];
+        const a = orderedConnections[i];
+        const b = orderedConnections[j];
         // Prefer the one with fewer consecutive uses / better health
         const scoreA = (a.consecutiveUseCount || 0) + (a.lastError ? 10 : 0);
         const scoreB = (b.consecutiveUseCount || 0) + (b.lastError ? 10 : 0);
@@ -257,11 +271,11 @@ export async function getProviderCredentials(
       }
     } else if (strategy === "random") {
       // Random: Fisher-Yates-inspired random pick
-      const idx = Math.floor(Math.random() * availableConnections.length);
-      connection = availableConnections[idx];
+      const idx = Math.floor(Math.random() * orderedConnections.length);
+      connection = orderedConnections[idx];
     } else if (strategy === "least-used") {
       // Least Used: pick the one with oldest lastUsedAt
-      const sorted = [...availableConnections].sort((a, b) => {
+      const sorted = [...orderedConnections].sort((a, b) => {
         if (!a.lastUsedAt && !b.lastUsedAt) return (a.priority || 999) - (b.priority || 999);
         if (!a.lastUsedAt) return -1;
         if (!b.lastUsedAt) return 1;
@@ -271,13 +285,13 @@ export async function getProviderCredentials(
     } else if (strategy === "cost-optimized") {
       // Cost Optimized: sort by priority ascending (lower = cheaper/preferred)
       // Future: can be enhanced with actual cost data per provider
-      const sorted = [...availableConnections].sort(
+      const sorted = [...orderedConnections].sort(
         (a, b) => (a.priority || 999) - (b.priority || 999)
       );
       connection = sorted[0];
     } else {
       // Default: fill-first (already sorted by priority in getProviderConnections)
-      connection = availableConnections[0];
+      connection = orderedConnections[0];
     }
 
     return {