Merge remote-tracking branch 'origin/master' into gitea/feature/end

Resolved conflicts taking origin/master (v0.5.55) as canonical, with local features re-applied: - runtime log level (LOG_LEVEL env + dashboard Settings → Logging, applied immediately and persisted across restarts) - free/noAuth provider enable/disable toggle via providerStrategies.enabled - parallel model testing (Test All Models / Test Selected Keys)
2026-08-17 00:38:31 +07:00
parent e7470e955e
commit 7e45ead2ac
557 changed files with 53396 additions and 6935 deletions
--- a/open-sse/services/usage/claude.js
+++ b/open-sse/services/usage/claude.js
@@ -19,7 +19,43 @@ const CLAUDE_CONFIG = {
 const OAUTH_429_COOLDOWN_MS = 180000;
 const oauthCooldown = new Map();

-export async function getClaudeUsage(accessToken, proxyOptions = null) {
+// Dedup + short TTL cache per access token. Many tabs / many accounts / auto-refresh
+// all funnel through here; without this each call hits Anthropic and triggers 429.
+const USAGE_CACHE_TTL_MS = 300000;
+const usageCache = new Map(); // token -> { promise } | { result, expiresAt }
+
+export async function getClaudeUsage(accessToken, proxyOptions = null, options = {}) {
+  const force = options?.force === true;
+
+  // Serve in-flight or fresh cached result (skip on manual force)
+  if (!force && accessToken) {
+    const hit = usageCache.get(accessToken);
+    if (hit?.promise) return hit.promise;
+    if (hit && hit.expiresAt > Date.now()) return hit.result;
+  }
+
+  const stale = (!force && accessToken && usageCache.get(accessToken)?.result) || null;
+
+  const promise = (async () => {
+    const result = await fetchClaudeUsageRaw(accessToken, proxyOptions);
+    // Only cache real quota data, not soft-failure {message: ...} payloads
+    if (accessToken && result?.quotas) {
+      usageCache.set(accessToken, {
+        result,
+        expiresAt: Date.now() + USAGE_CACHE_TTL_MS,
+      });
+      return result;
+    }
+    // Soft failure (429/error): prefer the last good read over a transient error
+    if (stale) return stale;
+    return result;
+  })();
+
+  if (accessToken) usageCache.set(accessToken, { promise });
+  return promise;
+}
+
+async function fetchClaudeUsageRaw(accessToken, proxyOptions = null) {
  try {
    // Skip OAuth usage call while this token is cooling down from a recent 429
    const cooldownUntil = oauthCooldown.get(accessToken);
--- a/open-sse/services/usage/codebuddy-cn.js
+++ b/open-sse/services/usage/codebuddy-cn.js
@@ -43,17 +43,17 @@ function refillCadence(acc) {
  return "Monthly";
 }

-export async function getCodeBuddyCnUsage(accessToken, apiKey, providerSpecificData, proxyOptions = null) {
+async function getCodeBuddyUsage(providerId, accessToken, apiKey, providerSpecificData, proxyOptions = null) {
  const token = accessToken || apiKey;
  if (!token) {
-    return { message: "CodeBuddy CN credential not available." };
+    return { message: `CodeBuddy (${providerId}) credential not available.` };
  }

  try {
-    const response = await proxyAwareFetch(U(PROVIDER_ID).url, {
+    const response = await proxyAwareFetch(U(providerId).url, {
      method: "POST",
      headers: {
-        ...(PROVIDERS[PROVIDER_ID]?.headers || {}),
+        ...(PROVIDERS[providerId]?.headers || {}),
        Authorization: `Bearer ${token}`,
        "Content-Type": "application/json",
        Accept: "application/json",
@@ -129,10 +129,18 @@ export async function getCodeBuddyCnUsage(accessToken, apiKey, providerSpecificD
    });

    const basePkg = refills[0] || accounts[0] || {};
-    const plan = basePkg.PackageName || basePkg.SubProductName || "CodeBuddy CN";
+    const plan = basePkg.PackageName || basePkg.SubProductName || "CodeBuddy";

    return { plan, quotas };
  } catch (error) {
-    return { message: `CodeBuddy CN error: ${error.message}` };
+    return { message: `CodeBuddy (${providerId}) error: ${error.message}` };
  }
 }
+
+export async function getCodeBuddyCnUsage(accessToken, apiKey, providerSpecificData, proxyOptions = null) {
+  return getCodeBuddyUsage(PROVIDER_ID, accessToken, apiKey, providerSpecificData, proxyOptions);
+}
+
+export async function getCodeBuddyIntlUsage(accessToken, apiKey, providerSpecificData, proxyOptions = null) {
+  return getCodeBuddyUsage("codebuddy-intl", accessToken, apiKey, providerSpecificData, proxyOptions);
+}
--- a/open-sse/services/usage/deepseek.js
+++ b/open-sse/services/usage/deepseek.js
@@ -0,0 +1,112 @@
+/**
+ * DeepSeek usage — GET https://api.deepseek.com/user/balance
+ * Auth: Bearer <apiKey>
+ */
+
+import { proxyAwareFetch } from "../../utils/proxyFetch.js";
+import { toFiniteNumber } from "./shared.js";
+
+const BALANCE_URL = "https://api.deepseek.com/user/balance";
+
+function parseBalanceInfos(data) {
+  const list = Array.isArray(data?.balance_infos) ? data.balance_infos : [];
+  const results = [];
+  for (const item of list) {
+    if (!item || typeof item !== "object") continue;
+    const currency =
+      typeof item.currency === "string" ? item.currency.toUpperCase() : "";
+    if (!currency) continue;
+    const totalBalance = toFiniteNumber(
+      item.total_balance ?? item.totalBalance,
+      0,
+    );
+    results.push({
+      currency,
+      totalBalance,
+      grantedBalance: toFiniteNumber(
+        item.granted_balance ?? item.grantedBalance,
+        0,
+      ),
+      toppedUpBalance: toFiniteNumber(
+        item.topped_up_balance ?? item.toppedUpBalance,
+        0,
+      ),
+    });
+  }
+  return results;
+}
+
+/**
+ * @param {string|null|undefined} apiKey
+ * @param {object|null} proxyOptions
+ */
+export async function getDeepseekUsage(apiKey = null, proxyOptions = null) {
+  if (!apiKey || typeof apiKey !== "string" || !apiKey.trim()) {
+    return { message: "DeepSeek API key not available. Add a key to view usage." };
+  }
+
+  try {
+    const response = await proxyAwareFetch(
+      BALANCE_URL,
+      {
+        method: "GET",
+        headers: {
+          Authorization: `Bearer ${apiKey.trim()}`,
+          "Content-Type": "application/json",
+          Accept: "application/json",
+        },
+      },
+      proxyOptions,
+    );
+
+    if (response.status === 401 || response.status === 403) {
+      return {
+        plan: "DeepSeek",
+        message: "DeepSeek authentication failed. Check the API key.",
+      };
+    }
+
+    if (!response.ok) {
+      const errText = await response.text().catch(() => "");
+      return {
+        plan: "DeepSeek",
+        message: `DeepSeek balance API error (${response.status})${errText ? `: ${errText.slice(0, 120)}` : ""}`,
+      };
+    }
+
+    const data = await response.json().catch(() => null);
+    if (!data || typeof data !== "object") {
+      return { message: "DeepSeek balance response was not JSON." };
+    }
+
+    const balances = parseBalanceInfos(data);
+    if (balances.length === 0) {
+      return {
+        plan: "DeepSeek",
+        message: "DeepSeek connected. No balance data returned.",
+      };
+    }
+
+    const isAvailable = data.is_available === true || data.isAvailable === true;
+    const quotas = {};
+    for (const b of balances) {
+      const total = Math.max(0, b.totalBalance);
+      // Credit pot: show full remaining against current balance; never set absolute
+      // `remaining` — QuotaTable treats it as a 0–100 percentage.
+      quotas[`Balance (${b.currency})`] = {
+        used: 0,
+        total,
+        remainingPercentage: total > 0 ? 100 : 0,
+        resetAt: null,
+        unlimited: total > 0,
+      };
+    }
+
+    return {
+      plan: isAvailable ? "DeepSeek" : "DeepSeek (Insufficient Balance)",
+      quotas,
+    };
+  } catch (error) {
+    return { message: `DeepSeek error: ${error.message}` };
+  }
+}
--- a/open-sse/services/usage/google.js
+++ b/open-sse/services/usage/google.js
@@ -2,15 +2,15 @@
 * Google usage handlers (Gemini CLI + Antigravity)
 */

-import { CLIENT_METADATA, getPlatformUserAgent } from "../../config/appConstants.js";
-import { ANTIGRAVITY_OAUTH_CLIENT } from "../../providers/shared.js";
+import { CLIENT_METADATA } from "../../config/appConstants.js";
+import { ANTIGRAVITY_IDE_USER_AGENT, ANTIGRAVITY_IDE_VERSION, ANTIGRAVITY_OAUTH_CLIENT } from "../../providers/shared.js";
 import { U, parseResetTime, normalizeCloudCodeProjectId, fetchWithTimeout } from "./shared.js";

 // Antigravity API config (from Quotio) — urls from registry, oauth client + dynamic UA kept here
 const ANTIGRAVITY_CONFIG = {
  ...U("antigravity"),
  ...ANTIGRAVITY_OAUTH_CLIENT,
-  userAgent: getPlatformUserAgent(),
+  userAgent: ANTIGRAVITY_IDE_USER_AGENT,
 };

 /**
@@ -129,8 +129,7 @@ export async function getAntigravityUsage(accessToken, providerSpecificData, pro
        "User-Agent": ANTIGRAVITY_CONFIG.userAgent,
        "Content-Type": "application/json",
        "X-Client-Name": "antigravity",
-        "X-Client-Version": "1.107.0",
-        "x-request-source": "local", // MITM bypass
+        "X-Client-Version": ANTIGRAVITY_IDE_VERSION,
      },
      body: JSON.stringify({
        ...(projectId ? { project: projectId } : {})
@@ -162,7 +161,12 @@ export async function getAntigravityUsage(accessToken, providerSpecificData, pro
    if (data.models) {
      // Filter only recommended/important models (must match PROVIDER_MODELS ag ids)
      const importantModels = [
-        'gemini-3-flash-agent',
+        'gemini-3.7-flash-high',
+        'gemini-3.7-flash-medium',
+        'gemini-3.7-flash-low',
+        'gemini-3.6-flash-high',
+        'gemini-3.6-flash-medium',
+        'gemini-3.6-flash-low',
        'gemini-3.5-flash-low',
        'gemini-3.5-flash-extra-low',
        'gemini-pro-agent',
@@ -170,10 +174,8 @@ export async function getAntigravityUsage(accessToken, providerSpecificData, pro
        'claude-sonnet-4-6',
        'claude-opus-4-6-thinking',
        'gpt-oss-120b-medium',
-        'gemini-3-flash',
        // Image generation models
        'gemini-3.1-flash-image',
-        'gemini-3-pro-image',
      ];

      for (const [modelKey, info] of Object.entries(data.models)) {
@@ -229,7 +231,6 @@ async function getAntigravitySubscriptionInfo(accessToken, proxyOptions = null)
        "Authorization": `Bearer ${accessToken}`,
        "User-Agent": ANTIGRAVITY_CONFIG.userAgent,
        "Content-Type": "application/json",
-        "x-request-source": "local", // MITM bypass
      },
      body: JSON.stringify({ metadata: CLIENT_METADATA, mode: 1 }),
    }, 10000, proxyOptions);
--- a/open-sse/services/usage/grok-cli.js
+++ b/open-sse/services/usage/grok-cli.js
@@ -0,0 +1,424 @@
+/**
+ * Grok CLI / Grok Build usage handler
+ *
+ * Source of truth: official grok-shell/grok-pager traffic to cli-chat-proxy.grok.com
+ *   GET /v1/billing?format=credits
+ *   GET /v1/user?include=subscription
+ *
+ * Observed billing shape (protobuf-json style `{ val: number }`):
+ * {
+ *   config: {
+ *     currentPeriod: { type: "USAGE_PERIOD_TYPE_WEEKLY", start, end },
+ *     onDemandCap: { val },
+ *     onDemandUsed: { val },
+ *     prepaidBalance: { val },
+ *     isUnifiedBillingUser: true,
+ *     billingPeriodStart, billingPeriodEnd
+ *   }
+ * }
+ *
+ * Exhausted free/promo accounts return cap=0/used=0/prepaid=0 and chat 402s with
+ * personal-team-blocked:spending-limit. Paid/sub accounts surface non-zero cap
+ * or prepaidBalance; richer credit fields are parsed opportunistically if present.
+ */
+
+import { proxyAwareFetch } from "../../utils/proxyFetch.js";
+import { U, parseResetTime, toFiniteNumber } from "./shared.js";
+import {
+  GROK_CLI_CLIENT_IDENTIFIER,
+  GROK_CLI_USER_AGENT,
+  GROK_CLI_VERSION,
+} from "../../config/grokCli.js";
+import { decodeGrokCreditsFrame } from "./grokCliQuotaFrame.js";
+
+const USAGE = U("grok-cli");
+const BILLING_URL = USAGE.url || "https://cli-chat-proxy.grok.com/v1/billing?format=credits";
+const USER_URL = USAGE.userUrl || "https://cli-chat-proxy.grok.com/v1/user?include=subscription";
+
+// SuperGrok weekly pool.
+const GRPC_CREDITS_URL =
+  "https://grok.com/grok_api_v2.GrokBuildBilling/GetGrokCreditsConfig";
+// Empty gRPC-web request frame (flag 0 + length 0). Without it upstream returns
+// grpc-status 13 "Missing request message." with a 0-byte body.
+const GRPC_WEB_EMPTY_REQUEST_FRAME = Buffer.from([0, 0, 0, 0, 0]);
+
+/** Unwrap protobuf-json `{ val: n }` or plain numbers/strings. */
+function unwrapVal(value, fallback = 0) {
+  if (value == null) return fallback;
+  if (typeof value === "object" && !Array.isArray(value) && "val" in value) {
+    return toFiniteNumber(value.val, fallback);
+  }
+  return toFiniteNumber(value, fallback);
+}
+
+function buildGrokCliHeaders(accessToken, providerSpecificData = {}) {
+  const psd = providerSpecificData || {};
+  const headers = {
+    Authorization: `Bearer ${accessToken}`,
+    Accept: "application/json",
+    "User-Agent": GROK_CLI_USER_AGENT,
+    "x-xai-token-auth": "xai-grok-cli",
+    "x-grok-client-identifier": GROK_CLI_CLIENT_IDENTIFIER,
+    "x-grok-client-version": GROK_CLI_VERSION,
+    "x-grok-client-mode": "headless",
+  };
+  const email = psd.email;
+  const userId = psd.userId || psd.principalId;
+  if (email) headers["x-email"] = email;
+  if (userId) headers["x-userid"] = userId;
+  return headers;
+}
+
+function subscriptionTier(user, config) {
+  const rawTier =
+    user?.subscriptionTier ??
+    user?.subscription_tier ??
+    user?.subscription?.tier ??
+    config?.subscriptionTier ??
+    config?.subscription_tier;
+  return typeof rawTier === "string" ? rawTier.trim() : "";
+}
+
+function resolvePlan(user, config) {
+  const tier = subscriptionTier(user, config);
+  if (tier) {
+    return tier
+      .replace(/[_-]+/g, " ")
+      .replace(/\b\w/g, (c) => c.toUpperCase());
+  }
+  if (user?.hasGrokCodeAccess === true) return "Grok Code";
+  if (config?.isUnifiedBillingUser === true) return "Grok Build";
+  return "Grok Build";
+}
+
+// Display only; upstream remains authoritative for access and quota enforcement.
+function planFromAccessToken(accessToken) {
+  try {
+    const payload = JSON.parse(Buffer.from(accessToken.split(".")[1], "base64url"));
+    return {
+      0: "Free",
+      1: "SuperGrok",
+      2: "X Basic",
+      3: "X Premium",
+      4: "X Premium Plus",
+      5: "SuperGrok Heavy",
+      6: "SuperGrok Lite",
+    }[payload.tier] || "";
+  } catch {
+    return "";
+  }
+}
+
+function makeQuota({ used, total, resetAt, unlimited = false }) {
+  const safeTotal = Math.max(0, toFiniteNumber(total, 0));
+  const safeUsed = Math.max(0, toFiniteNumber(used, 0));
+  // Do NOT set absolute `remaining` — QuotaTable's getRemainingPercentage treats
+  // `remaining` as a 0–100 percentage (same trap as Qoder credits).
+  if (unlimited || safeTotal === 0) {
+    return {
+      used: safeUsed,
+      total: 0,
+      remainingPercentage: unlimited ? 100 : 0,
+      resetAt: resetAt || null,
+      unlimited: true,
+    };
+  }
+  const remaining = Math.max(0, safeTotal - safeUsed);
+  const remainingPercentage = (remaining / safeTotal) * 100;
+  return {
+    used: safeUsed,
+    total: safeTotal,
+    remainingPercentage,
+    resetAt: resetAt || null,
+    unlimited: false,
+  };
+}
+
+/**
+ * Map billing JSON → normalized quotas object for the dashboard.
+ * Returns { quotas, periodEnd, exhaustedHint } or empty quotas when nothing usable.
+ */
+export function parseGrokCliBilling(billing, user = null) {
+  const root = billing && typeof billing === "object" ? billing : {};
+  const config =
+    root.config && typeof root.config === "object" && !Array.isArray(root.config)
+      ? root.config
+      : root;
+
+  const periodEnd =
+    parseResetTime(config.billingPeriodEnd) ||
+    parseResetTime(config.billing_period_end) ||
+    parseResetTime(config.currentPeriod?.end) ||
+    parseResetTime(config.resetAt || config.resetsAt || config.periodEnd) ||
+    parseResetTime(root.billingPeriodEnd) ||
+    parseResetTime(root.billing_period_end) ||
+    parseResetTime(root.resetAt || root.resetsAt || root.periodEnd) ||
+    null;
+
+  const quotas = {};
+  const tier = subscriptionTier(user, config);
+  const subscriptionAccess = Boolean(tier) && !/^(free|none|null)$/i.test(tier);
+
+  // Current Grok Build responses expose included monthly usage at top level.
+  const monthlyLimit = unwrapVal(
+    config.monthlyLimit ?? config.monthly_limit ?? root.monthlyLimit ?? root.monthly_limit,
+    NaN,
+  );
+  const includedUsed = unwrapVal(
+    config.includedUsed ?? config.included_used ?? root.includedUsed ?? root.included_used,
+    NaN,
+  );
+  const totalUsed = unwrapVal(
+    config.totalUsed ?? config.total_used ?? root.totalUsed ?? root.total_used,
+    NaN,
+  );
+  if (Number.isFinite(monthlyLimit) && monthlyLimit > 0) {
+    quotas["Monthly included"] = makeQuota({
+      used: Number.isFinite(includedUsed)
+        ? includedUsed
+        : Number.isFinite(totalUsed)
+          ? totalUsed
+          : 0,
+      total: monthlyLimit,
+      resetAt: periodEnd,
+    });
+  }
+
+  // Primary: on-demand spending window (subscription / promo credits)
+  const onDemandCap = unwrapVal(config.onDemandCap ?? root.onDemandCap, NaN);
+  const onDemandUsed = unwrapVal(config.onDemandUsed ?? root.onDemandUsed, NaN);
+  if (Number.isFinite(onDemandCap) && onDemandCap > 0) {
+    const used = Number.isFinite(onDemandUsed) ? Math.max(0, onDemandUsed) : 0;
+    quotas["On-demand"] = makeQuota({
+      used,
+      total: onDemandCap,
+      resetAt: periodEnd,
+    });
+  } else if (
+    !subscriptionAccess &&
+    Number.isFinite(onDemandCap) &&
+    onDemandCap === 0 &&
+    Number.isFinite(onDemandUsed)
+  ) {
+    // Cap 0 is the exhausted free/promo state (chat returns 402 spending-limit).
+    // UI treats total===0 as unlimited, so use a synthetic 1/1 depleted row.
+    quotas["On-demand"] = {
+      used: 1,
+      total: 1,
+      remainingPercentage: 0,
+      resetAt: periodEnd,
+      unlimited: false,
+    };
+  }
+
+  // Prepaid top-up balance (remaining credits; no fixed allotment known)
+  const prepaid = unwrapVal(config.prepaidBalance ?? root.prepaidBalance, NaN);
+  if (Number.isFinite(prepaid) && prepaid > 0) {
+    // Show full bar against the current balance (0 spent of this remaining pot).
+    quotas["Prepaid"] = {
+      used: 0,
+      total: prepaid,
+      remainingPercentage: 100,
+      resetAt: null,
+      unlimited: false,
+    };
+  }
+
+  // SuperGrok weekly shared-pool usage (subscription tier). creditUsagePercent is
+  // the single total used %; productUsage is a breakdown legend, NOT independent
+  // quotas — never split it into separate bars.
+  const usedPct = unwrapVal(
+    config.creditUsagePercent ?? config.credit_usage_percent ?? root.creditUsagePercent,
+    NaN,
+  );
+  if (Number.isFinite(usedPct) && usedPct >= 0) {
+    quotas["Weekly SuperGrok"] = makeQuota({
+      used: Math.max(0, Math.min(100, usedPct)),
+      total: 100,
+      resetAt: periodEnd,
+    });
+  }
+
+  // Opportunistic richer credit envelopes (future / other account types)
+  const creditBags = [
+    root.credits,
+    root.creditBalance,
+    root.usage,
+    config.credits,
+    config.includedCredits,
+    config.subscriptionCredits,
+  ].filter((bag) => bag && typeof bag === "object" && !Array.isArray(bag));
+
+  for (const bag of creditBags) {
+    const total = unwrapVal(
+      bag.total ?? bag.limit ?? bag.cap ?? bag.allocation ?? bag.amount,
+      NaN,
+    );
+    const used = unwrapVal(bag.used ?? bag.spent ?? bag.consumed, NaN);
+    const remaining = unwrapVal(bag.remaining ?? bag.balance ?? bag.left, NaN);
+    if (Number.isFinite(total) && total > 0) {
+      const resolvedUsed = Number.isFinite(used)
+        ? used
+        : Number.isFinite(remaining)
+          ? Math.max(0, total - remaining)
+          : 0;
+      if (!quotas.Credits) {
+        quotas.Credits = makeQuota({
+          used: resolvedUsed,
+          total,
+          resetAt: parseResetTime(bag.resetAt || bag.resetsAt || bag.end) || periodEnd,
+        });
+      }
+    } else if (Number.isFinite(remaining) && remaining >= 0 && !quotas.Credits) {
+      quotas.Credits = {
+        used: 0,
+        total: remaining > 0 ? remaining : 1,
+        remainingPercentage: remaining > 0 ? 100 : 0,
+        resetAt: periodEnd,
+        unlimited: false,
+      };
+    }
+  }
+
+  // Exhausted when every finite quota bar is at 0% remaining
+  const exhausted =
+    Object.keys(quotas).length > 0 &&
+    Object.values(quotas).every(
+      (q) => q.unlimited !== true && (q.remainingPercentage ?? 100) <= 0,
+    );
+
+  return {
+    plan: resolvePlan(user, config),
+    quotas,
+    periodEnd,
+    exhausted,
+    subscriptionAccess,
+    rawConfig: config,
+  };
+}
+
+/**
+ * Live SuperGrok weekly pool via gRPC-web GetGrokCreditsConfig.
+ * Fail-open: any network/auth/parse failure returns null.
+ * @returns {{ percentUsed: number, resetAt: string|null } | null}
+ */
+export async function fetchGrokCliCreditsConfig(accessToken, proxyOptions = null) {
+  if (!accessToken) return null;
+  try {
+    const res = await proxyAwareFetch(
+      GRPC_CREDITS_URL,
+      {
+        method: "POST",
+        headers: {
+          Authorization: `Bearer ${accessToken}`,
+          "Content-Type": "application/grpc-web+proto",
+          "X-Grpc-Web": "1",
+          Accept: "application/grpc-web+proto",
+        },
+        body: GRPC_WEB_EMPTY_REQUEST_FRAME,
+      },
+      proxyOptions,
+    );
+    if (!res?.ok) return null;
+    const arrayBuffer = await res.arrayBuffer().catch(() => null);
+    if (!arrayBuffer) return null;
+    return decodeGrokCreditsFrame(Buffer.from(arrayBuffer));
+  } catch {
+    return null;
+  }
+}
+
+function quotasFromGrpcCredits(decoded) {
+  if (!decoded || !Number.isFinite(decoded.percentUsed)) return null;
+  // Round for bar display (fixed32 ratio * 100 can be 34.999… for 0.35)
+  const used = Math.round(Math.max(0, Math.min(100, decoded.percentUsed)));
+  return {
+    "Weekly SuperGrok": makeQuota({
+      used,
+      total: 100,
+      resetAt: decoded.resetAt || null,
+    }),
+  };
+}
+
+/**
+ * @param {string} accessToken
+ * @param {object|null} providerSpecificData
+ * @param {object|null} proxyOptions
+ */
+export async function getGrokCliUsage(accessToken, providerSpecificData = null, proxyOptions = null) {
+  if (!accessToken) {
+    return { message: "Grok CLI access token not available." };
+  }
+
+  const headers = buildGrokCliHeaders(accessToken, providerSpecificData);
+
+  try {
+    // Fetch billing + user profile in parallel (same pattern as official CLI startup)
+    const [billingRes, userRes] = await Promise.all([
+      proxyAwareFetch(
+        BILLING_URL,
+        { method: "GET", headers },
+        proxyOptions,
+      ),
+      proxyAwareFetch(
+        USER_URL,
+        { method: "GET", headers },
+        proxyOptions,
+      ).catch(() => null),
+    ]);
+
+    if (billingRes.status === 401 || billingRes.status === 403) {
+      return { message: "Grok CLI authentication expired. Please re-authorize." };
+    }
+
+    if (!billingRes.ok) {
+      const errText = await billingRes.text().catch(() => "");
+      const trimmed = errText ? `: ${errText.slice(0, 200)}` : "";
+      return { message: `Grok CLI billing API error (${billingRes.status})${trimmed}` };
+    }
+
+    const billing = await billingRes.json().catch(() => null);
+    if (!billing || typeof billing !== "object") {
+      return { message: "Grok CLI billing response was not JSON." };
+    }
+
+    let user = null;
+    if (userRes?.ok) {
+      user = await userRes.json().catch(() => null);
+    }
+
+    const parsed = parseGrokCliBilling(billing, user);
+    parsed.plan = planFromAccessToken(accessToken) || parsed.plan;
+
+    if (!parsed.quotas || Object.keys(parsed.quotas).length === 0) {
+      // Paid SuperGrok often returns cap=0 over REST but exposes the shared
+      // weekly pool on GetGrokCreditsConfig — try that before giving up.
+      const grpc = await fetchGrokCliCreditsConfig(accessToken, proxyOptions);
+      const grpcQuotas = quotasFromGrpcCredits(grpc);
+      if (grpcQuotas) {
+        return {
+          plan: parsed.plan,
+          quotas: grpcQuotas,
+        };
+      }
+      return {
+        plan: parsed.plan,
+        message: parsed.subscriptionAccess
+          ? "Subscription access is active; Grok does not expose a numeric included quota."
+          : "Grok Build connected, but no credit allotment was returned. Free promo may be exhausted.",
+        quotas: {},
+      };
+    }
+
+    // Dashboard hides QuotaTable whenever `message` is set, so only attach a
+    // message when there are no quota rows to render. Depleted accounts keep
+    // the 0% On-demand bar without a blocking message.
+    return {
+      plan: parsed.plan,
+      quotas: parsed.quotas,
+    };
+  } catch (error) {
+    return { message: `Grok CLI usage error: ${error.message}` };
+  }
+}
--- a/open-sse/services/usage/grokCliQuotaFrame.js
+++ b/open-sse/services/usage/grokCliQuotaFrame.js
@@ -0,0 +1,191 @@
+/**
+ * gRPC-web frame decoder for xAI GetGrokCreditsConfig
+ * (grok_api_v2.GrokBuildBilling/GetGrokCreditsConfig).
+ *
+ * Real response shape (live capture 2026-07-20):
+ *   top-level field 1 (length-delimited) — nested credits info
+ *     subfield 1  (fixed32 float)            — usage ratio 0..1
+ *     subfield 5  (Timestamp{seconds,nanos}) — credit-pool reset time
+ *
+ * Fail-open: any malformed buffer returns null, never throws.
+ */
+
+const FIELD_CREDITS_INFO = 1;
+const CREDITS_FIELD_USAGE_RATIO = 1;
+const CREDITS_FIELD_RESET_TIMESTAMP = 5;
+const TIMESTAMP_FIELD_SECONDS = 1;
+const TIMESTAMP_FIELD_NANOS = 2;
+
+const WIRE_TYPE_VARINT = 0;
+const WIRE_TYPE_FIXED64 = 1;
+const WIRE_TYPE_LENGTH_DELIMITED = 2;
+const WIRE_TYPE_FIXED32 = 5;
+
+const GRPC_WEB_TRAILER_FLAG_BIT = 0x80;
+const MAX_VARINT_SHIFT_BITS = 70n;
+
+/**
+ * Validate a gRPC-web frame header at `offset`.
+ * @returns {{ flag: number, payloadStart: number, payloadLength: number } | null}
+ */
+export function probeFrameHeader(buffer, offset = 0) {
+  if (!Buffer.isBuffer(buffer) || offset < 0 || buffer.length - offset < 5) return null;
+  const flag = buffer[offset];
+  if (flag !== 0x00 && flag !== 0x01 && flag !== 0x80 && flag !== 0x81) return null;
+  const payloadStart = offset + 5;
+  const payloadLength = buffer.readUInt32BE(offset + 1);
+  if (payloadLength > buffer.length - payloadStart) return null;
+  return { flag, payloadStart, payloadLength };
+}
+
+function readVarint(buffer, offset) {
+  let result = 0n;
+  let shift = 0n;
+  let pos = offset;
+  for (;;) {
+    if (pos >= buffer.length) return null;
+    const byte = buffer[pos];
+    result |= BigInt(byte & 0x7f) << shift;
+    pos += 1;
+    if ((byte & 0x80) === 0) break;
+    shift += 7n;
+    if (shift > MAX_VARINT_SHIFT_BITS) return null;
+  }
+  return { value: Number(result), next: pos };
+}
+
+function readLengthDelimitedField(buffer, offset) {
+  const lengthResult = readVarint(buffer, offset);
+  if (!lengthResult) return null;
+  const { value: length, next: bodyStart } = lengthResult;
+  if (length < 0 || bodyStart + length > buffer.length) return null;
+  return {
+    field: { wireType: WIRE_TYPE_LENGTH_DELIMITED, bytes: buffer.subarray(bodyStart, bodyStart + length) },
+    next: bodyStart + length,
+  };
+}
+
+function readFixedWidthField(buffer, offset, width, wireType) {
+  if (offset + width > buffer.length) return null;
+  return {
+    field: { wireType, bytes: buffer.subarray(offset, offset + width) },
+    next: offset + width,
+  };
+}
+
+function readField(buffer, offset) {
+  const tagResult = readVarint(buffer, offset);
+  if (!tagResult) return null;
+  const fieldNumber = tagResult.value >>> 3;
+  const wireType = tagResult.value & 0x7;
+  if (fieldNumber === 0) return null;
+
+  if (wireType === WIRE_TYPE_VARINT) {
+    const valueResult = readVarint(buffer, tagResult.next);
+    if (!valueResult) return null;
+    return {
+      fieldNumber,
+      field: { wireType: WIRE_TYPE_VARINT, value: valueResult.value },
+      next: valueResult.next,
+    };
+  }
+  if (wireType === WIRE_TYPE_LENGTH_DELIMITED) {
+    const result = readLengthDelimitedField(buffer, tagResult.next);
+    return result ? { fieldNumber, field: result.field, next: result.next } : null;
+  }
+  if (wireType === WIRE_TYPE_FIXED64) {
+    const result = readFixedWidthField(buffer, tagResult.next, 8, WIRE_TYPE_FIXED64);
+    return result ? { fieldNumber, field: result.field, next: result.next } : null;
+  }
+  if (wireType === WIRE_TYPE_FIXED32) {
+    const result = readFixedWidthField(buffer, tagResult.next, 4, WIRE_TYPE_FIXED32);
+    return result ? { fieldNumber, field: result.field, next: result.next } : null;
+  }
+  return null;
+}
+
+function decodeFields(buffer) {
+  const fields = new Map();
+  let offset = 0;
+  while (offset < buffer.length) {
+    const result = readField(buffer, offset);
+    if (!result) return null;
+    fields.set(result.fieldNumber, result.field);
+    offset = result.next;
+  }
+  return fields;
+}
+
+function findDataFramePayload(buffer) {
+  let offset = 0;
+  while (offset < buffer.length) {
+    const frame = probeFrameHeader(buffer, offset);
+    if (!frame) return null;
+    const frameEnd = frame.payloadStart + frame.payloadLength;
+    const isTrailer = (frame.flag & GRPC_WEB_TRAILER_FLAG_BIT) !== 0;
+    if (!isTrailer) {
+      return buffer.subarray(frame.payloadStart, frameEnd);
+    }
+    offset = frameEnd;
+  }
+  return null;
+}
+
+function extractNestedMessage(field) {
+  if (!field || field.wireType !== WIRE_TYPE_LENGTH_DELIMITED) return null;
+  return decodeFields(field.bytes);
+}
+
+function extractUsageRatio(field) {
+  if (!field) return 0; // proto3 omission = 0% used
+  if (field.wireType === WIRE_TYPE_FIXED32) return field.bytes.readFloatLE(0);
+  if (field.wireType === WIRE_TYPE_FIXED64) return field.bytes.readDoubleLE(0);
+  return null;
+}
+
+function extractResetAt(field) {
+  if (!field || field.wireType !== WIRE_TYPE_LENGTH_DELIMITED) return null;
+
+  const timestampFields = decodeFields(field.bytes);
+  if (!timestampFields) return null;
+
+  const secondsField = timestampFields.get(TIMESTAMP_FIELD_SECONDS);
+  const nanosField = timestampFields.get(TIMESTAMP_FIELD_NANOS);
+  const seconds = secondsField?.wireType === WIRE_TYPE_VARINT ? secondsField.value : 0;
+  const nanos = nanosField?.wireType === WIRE_TYPE_VARINT ? nanosField.value : 0;
+
+  const millis = seconds * 1000 + Math.round(nanos / 1_000_000);
+  const parsed = new Date(millis);
+  return Number.isNaN(parsed.getTime()) ? null : parsed.toISOString();
+}
+
+/**
+ * Decode GetGrokCreditsConfig response → `{ percentUsed: 0-100, resetAt }` or null.
+ * @param {Buffer} buffer
+ * @returns {{ percentUsed: number, resetAt: string|null } | null}
+ */
+export function decodeGrokCreditsFrame(buffer) {
+  if (!buffer || !Buffer.isBuffer(buffer) || buffer.length === 0) return null;
+
+  try {
+    const framed = probeFrameHeader(buffer, 0) !== null;
+    const payload = framed ? findDataFramePayload(buffer) : buffer;
+    if (!payload) return null;
+
+    const topLevelFields = decodeFields(payload);
+    if (!topLevelFields) return null;
+
+    const creditsInfo = extractNestedMessage(topLevelFields.get(FIELD_CREDITS_INFO));
+    if (!creditsInfo) return null;
+
+    const usageRatio = extractUsageRatio(creditsInfo.get(CREDITS_FIELD_USAGE_RATIO));
+    if (usageRatio === null || !Number.isFinite(usageRatio) || usageRatio < 0) return null;
+
+    return {
+      percentUsed: Math.min(100, usageRatio * 100),
+      resetAt: extractResetAt(creditsInfo.get(CREDITS_FIELD_RESET_TIMESTAMP)),
+    };
+  } catch {
+    return null;
+  }
+}
--- a/open-sse/services/usage/kimi.js
+++ b/open-sse/services/usage/kimi.js
@@ -0,0 +1,211 @@
+/**
+ * Kimi Coding usage — GET /v1/usages
+ *
+ * Dual auth (single provider id `kimi`):
+ *   - apiKey present → x-api-key only (platform / coding API key)
+ *   - else accessToken → Bearer + X-Msh-* (device-code OAuth)
+ *
+ * Note: chat messages use combined x-api-key; /usages OAuth is Bearer.
+ * 403 permission_denied is NOT auth-expired — account lacks usage feature / sub.
+ */
+
+import { proxyAwareFetch } from "../../utils/proxyFetch.js";
+import { parseResetTime, toFiniteNumber } from "./shared.js";
+import { buildKimiHeaders } from "../../config/appConstants.js";
+
+const USAGE_URL = "https://api.kimi.com/coding/v1/usages";
+
+const PLAN_LEVELS = {
+  LEVEL_BASIC: "Moderato",
+  LEVEL_INTERMEDIATE: "Allegretto",
+  LEVEL_ADVANCED: "Allegro",
+  LEVEL_STANDARD: "Vivace",
+};
+
+function getKimiPlanName(level) {
+  if (!level) return "";
+  const key = String(level);
+  if (PLAN_LEVELS[key]) return PLAN_LEVELS[key];
+  return key.replace(/^LEVEL_/, "").toLowerCase();
+}
+
+/** Best-effort extract human message from Kimi error JSON (403 body is Connect-RPC-ish). */
+export function formatKimiUsageError(status, responseText) {
+  let parsed = null;
+  try {
+    parsed = JSON.parse(responseText || "");
+  } catch {
+    /* plain text */
+  }
+
+  const detail0 = Array.isArray(parsed?.details) ? parsed.details[0] : null;
+  const debug = detail0?.debug || parsed?.debug || null;
+  const reason = debug?.reason || parsed?.reason || "";
+  const localized =
+    debug?.localizedMessage?.message ||
+    detail0?.localizedMessage?.message ||
+    parsed?.message ||
+    "";
+
+  if (status === 401) {
+    return "Kimi authentication expired. Please re-authorize.";
+  }
+
+  // Live OAuth token without Kimi Code usage entitlement returns 403
+  // REASON_FEATURE_NO_PERMISSION — not an expired session.
+  if (
+    status === 403 &&
+    (reason === "REASON_FEATURE_NO_PERMISSION" ||
+      /permission_denied|do not have permission|subscribe/i.test(
+        `${parsed?.code || ""} ${localized} ${responseText || ""}`,
+      ))
+  ) {
+    return (
+      localized ||
+      "Kimi connected, but this account has no permission to view usage. Subscribe to Kimi Code to access quota."
+    );
+  }
+
+  const snippet = (localized || responseText || "").slice(0, 100);
+  return snippet
+    ? `Kimi Coding connected. API Error ${status}: ${snippet}`
+    : `Kimi Coding connected. API Error ${status}`;
+}
+
+function makeQuota({ used, total, remaining, resetAt }) {
+  const safeTotal = Math.max(0, toFiniteNumber(total, 0));
+  const safeUsed = Math.max(0, toFiniteNumber(used, 0));
+  // Prefer provider remaining when present; never set absolute `remaining`
+  // on the quota object — QuotaTable treats it as a 0–100 percentage.
+  let remainingPct;
+  if (safeTotal > 0 && remaining != null && Number.isFinite(Number(remaining))) {
+    remainingPct = (Math.max(0, Number(remaining)) / safeTotal) * 100;
+  } else if (safeTotal > 0) {
+    remainingPct = (Math.max(0, safeTotal - safeUsed) / safeTotal) * 100;
+  } else {
+    remainingPct = 0;
+  }
+  return {
+    used: safeUsed,
+    total: safeTotal,
+    remainingPercentage: remainingPct,
+    resetAt: resetAt || null,
+    unlimited: false,
+  };
+}
+
+/**
+ * @param {string|null|undefined} accessToken
+ * @param {string|null|undefined} apiKey
+ * @param {object|null} proxyOptions
+ * @param {object|null} providerSpecificData
+ */
+export async function getKimiUsage(
+  accessToken = null,
+  apiKey = null,
+  proxyOptions = null,
+  providerSpecificData = null,
+) {
+  const useApiKey = typeof apiKey === "string" && apiKey.length > 0;
+  const useOAuth = !useApiKey && typeof accessToken === "string" && accessToken.length > 0;
+
+  if (!useApiKey && !useOAuth) {
+    return { message: "Kimi access token or API key not available." };
+  }
+
+  const authHeaders = useApiKey
+    ? { "x-api-key": apiKey }
+    : {
+        Authorization: `Bearer ${accessToken}`,
+        ...buildKimiHeaders(providerSpecificData?.deviceId),
+      };
+
+  try {
+    const response = await proxyAwareFetch(
+      USAGE_URL,
+      {
+        method: "GET",
+        headers: {
+          ...authHeaders,
+          "Content-Type": "application/json",
+          Accept: "application/json",
+        },
+      },
+      proxyOptions,
+    );
+
+    const responseText = await response.text().catch(() => "");
+
+    if (!response.ok) {
+      return {
+        plan: "Kimi Coding",
+        message: formatKimiUsageError(response.status, responseText),
+      };
+    }
+
+    let data;
+    try {
+      data = JSON.parse(responseText || "{}");
+    } catch {
+      return {
+        plan: "Kimi Coding",
+        message: "Kimi Coding connected. Invalid JSON response from API.",
+      };
+    }
+
+    const quotas = {};
+    const usageObj = data?.usage && typeof data.usage === "object" ? data.usage : {};
+    const usageLimit = toFiniteNumber(usageObj.limit ?? usageObj.Limit, 0);
+    const usageUsed = toFiniteNumber(usageObj.used ?? usageObj.Used, 0);
+    const usageRemainingRaw = usageObj.remaining ?? usageObj.Remaining;
+    const usageRemaining =
+      usageRemainingRaw != null && usageRemainingRaw !== ""
+        ? toFiniteNumber(usageRemainingRaw, NaN)
+        : NaN;
+    const usageResetTime =
+      usageObj.resetTime || usageObj.ResetTime || usageObj.reset_at || usageObj.resetAt;
+
+    if (usageLimit > 0) {
+      quotas.Weekly = makeQuota({
+        used: usageUsed,
+        total: usageLimit,
+        remaining: Number.isFinite(usageRemaining) ? usageRemaining : null,
+        resetAt: parseResetTime(usageResetTime),
+      });
+    }
+
+    const limitsArray = Array.isArray(data?.limits) ? data.limits : [];
+    for (const item of limitsArray) {
+      if (!item || typeof item !== "object") continue;
+      const detail = item.detail && typeof item.detail === "object" ? item.detail : {};
+      const limit = toFiniteNumber(detail.limit ?? detail.Limit, 0);
+      const remaining = toFiniteNumber(detail.remaining ?? detail.Remaining, NaN);
+      const resetTime = detail.resetTime || detail.reset_at || detail.resetAt;
+      if (limit > 0) {
+        const rem = Number.isFinite(remaining) ? remaining : Math.max(0, limit);
+        quotas.Ratelimit = makeQuota({
+          used: Math.max(0, limit - rem),
+          total: limit,
+          remaining: rem,
+          resetAt: parseResetTime(resetTime),
+        });
+      }
+    }
+
+    const membershipLevel = data?.user?.membership?.level;
+    const planName = getKimiPlanName(membershipLevel) || "Kimi Coding";
+
+    if (Object.keys(quotas).length > 0) {
+      return { plan: planName, quotas };
+    }
+
+    return {
+      plan: planName,
+      message: "Kimi Coding connected. Usage tracked per request.",
+    };
+  } catch (error) {
+    return {
+      message: `Kimi Coding connected. Unable to fetch usage: ${error.message}`,
+    };
+  }
+}
--- a/open-sse/services/usage/misc.js
+++ b/open-sse/services/usage/misc.js
@@ -1,5 +1,5 @@
 /**
- * Misc usage handlers (Qwen, iFlow, Ollama, GLM, Vercel AI Gateway, Qoder)
+ * Misc usage handlers (iFlow, Ollama, GLM, Vercel AI Gateway, Qoder)
 */

 import { proxyAwareFetch } from "../../utils/proxyFetch.js";
@@ -15,23 +15,6 @@ const GLM_QUOTA_URLS = {
 // Returns { balance: "95.50", total_used: "4.50" } (USD as decimal strings).
 const VERCEL_AI_GATEWAY_CREDITS_URL = U("vercel-ai-gateway").url;

-/**
- * Qwen Usage
- */
-export async function getQwenUsage(accessToken, providerSpecificData) {
-  try {
-    const resourceUrl = providerSpecificData?.resourceUrl;
-    if (!resourceUrl) {
-      return { message: "Qwen connected. No resource URL available." };
-    }
-
-    // Qwen may have usage endpoint at resource URL
-    return { message: "Qwen connected. Usage tracked per request." };
-  } catch (error) {
-    return { message: "Unable to fetch Qwen usage." };
-  }
-}
-
 /**
 * iFlow Usage
 */
@@ -46,23 +29,86 @@ export async function getIflowUsage(accessToken) {

 /**
 * Ollama Cloud Usage
- * Ollama Cloud uses an API key from ollama.com/settings/keys
- * and has no public usage API — free tier has light usage limits (resets every 5h & 7d).
- * This returns an informational message with the plan details.
+ * GET https://ollama.com/api/usage — session (5h) + weekly (7d) `usage` is a 0..1
+ *   ratio (1.0 = limit reached, e.g. weekly 100% used). No reset timestamp exposed.
+ * POST https://ollama.com/api/me — plan label (fail-open).
+ * Auth: Authorization: Bearer <apiKey>
 */
-export async function getOllamaUsage(accessToken, providerSpecificData) {
+export async function getOllamaUsage(apiKey, providerSpecificData, proxyOptions = null) {
+  if (!apiKey) {
+    return { message: "Ollama Cloud API key not available." };
+  }
+
  try {
-    // Ollama Cloud does not expose a public quota/usage API.
-    // The provider is configured as noAuth with a notice explaining limits.
-    // We return a graceful message so the UI shows a friendly state instead of an error.
-    const plan = providerSpecificData?.plan || "Free";
-    return {
-      plan,
-      message: "Ollama Cloud uses a free tier with light usage limits (resets every 5h & 7d). For detailed usage tracking, visit ollama.com/settings/keys.",
-      quotas: [],
-    };
+    const response = await proxyAwareFetch("https://ollama.com/api/usage", {
+      headers: {
+        Authorization: `Bearer ${apiKey}`,
+        Accept: "application/json",
+      },
+    }, proxyOptions);
+
+    if (response.status === 401 || response.status === 403) {
+      return { message: "Ollama Cloud API key invalid or expired." };
+    }
+
+    if (!response.ok) {
+      return { message: `Ollama Cloud usage API error (${response.status}).` };
+    }
+
+    let data;
+    try {
+      data = await response.json();
+    } catch {
+      return { message: "Ollama Cloud usage response was not JSON." };
+    }
+
+    // Best-effort plan label from /api/me
+    const me = await proxyAwareFetch("https://ollama.com/api/me", {
+      method: "POST",
+      headers: {
+        Authorization: `Bearer ${apiKey}`,
+        Accept: "application/json",
+        "Content-Length": "0",
+      },
+    }, proxyOptions).then((r) => (r.ok ? r.json() : null)).catch(() => null);
+
+    const planRaw = typeof me?.Plan === "string" ? me.Plan : "";
+    const plan = planRaw
+      ? planRaw.charAt(0).toUpperCase() + planRaw.slice(1).toLowerCase()
+      : "Ollama Cloud";
+
+    const limits = data?.limits && typeof data.limits === "object" ? data.limits : {};
+
+    // Ollama `usage` is a 0..1 ratio (1.0 = limit reached). Convert to a 0..100
+    // bar. Do NOT set absolute `remaining` — QuotaTable reads remainingPercentage.
+    function ratioQuota(usageRatio, resetAt = null) {
+      const ratio = Math.max(0, Math.min(1, Number(usageRatio) || 0));
+      const usedPct = Math.round(ratio * 100);
+      return { used: usedPct, total: 100, remainingPercentage: 100 - usedPct, resetAt, unlimited: false };
+    }
+
+    const sessionRaw = limits.session?.usage;
+    const weeklyRaw = limits.weekly?.usage;
+    const sessionNum = Number(sessionRaw);
+    const weeklyNum = Number(weeklyRaw);
+    const hasSession = sessionRaw !== undefined && sessionRaw !== null && !Number.isNaN(sessionNum);
+    const hasWeekly = weeklyRaw !== undefined && weeklyRaw !== null && !Number.isNaN(weeklyNum);
+
+    if (!hasSession && !hasWeekly) {
+      return {
+        plan,
+        message: "Ollama Cloud connected. No usage limits reported.",
+        quotas: {},
+      };
+    }
+
+    const quotas = {};
+    if (hasSession) quotas["Session (5h)"] = ratioQuota(sessionNum);
+    if (hasWeekly) quotas["Weekly (7d)"] = ratioQuota(weeklyNum);
+
+    return { plan, quotas };
  } catch (error) {
-    return { message: "Unable to fetch Ollama Cloud usage." };
+    return { message: `Ollama Cloud error: ${error.message}` };
  }
 }