feat(quota): add Wafer.ai quota provider (#1312)

* feat(quota): add Wafer.ai quota provider

- New provider: wafer.js fetches from https://pass.wafer.ai/v1/inference/quota
- Auth: reads wafer/wafer-ai/wafer_ai keys from auth file
- Timeout: AbortSignal.timeout(15_000) with timeoutSignal.aborted detection
- Response: parses remaining/limit/overage/usedPercent/window_end/plan_tier
- valueLabel: planTier + remaining/limit + overage suffix
- Window: 5h (18000s) via resolveWindowLabel
- Cross-runtime: added to web registry, UI types, VS Code dispatcher

* fix(quota): wafer provider fixes — auth alias, decompression, logo

- Add 'wafer.ai' auth alias to match actual auth key format
- Use 'Accept-Encoding: identity' header to fix Bun fetch
  decompression issue with Cloudflare-backed responses
- Match copilot valueLabel format: 'planTier · X / Y left'
- Add wafer logo alias so Providers and Usage pages resolve
  to the same wafer.ai logo from models.dev

* style(quota): fix indentation of timeoutSignal declaration

* fix(quota): derive window duration from API instead of hardcoding

Compute windowSeconds from window_end - window_start timestamps,
with WAFER_WINDOW_SECONDS (5h) as fallback if timestamps are missing.

---------

Co-authored-by: Bohdan Triapitsyn <artmore@protonmail.com>

packages/ui/src/hooks/useProviderLogo.ts

@@ -23,6 +23,8 @@ const LOGO_ALIAS = new Map<string, string>([
     ['evroc-ai', 'evroc'],
     ['evrocai', 'evroc'],
     ['ollama-cloud', 'ollama'],
+    ['wafer-ai', 'wafer.ai'],
+    ['wafer', 'wafer.ai'],
 ]);
 
 const normalizeProviderId = (providerId: string | null | undefined) => {

packages/ui/src/lib/quota/providers/index.ts

@@ -18,6 +18,7 @@ export const QUOTA_PROVIDERS: QuotaProviderMeta[] = [
   { id: 'minimax-cn-coding-plan', name: 'MiniMax Coding Plan (minimaxi.com)' },
   { id: 'minimax-coding-plan', name: 'MiniMax Coding Plan (minimax.io)' },
   { id: 'ollama-cloud', name: 'Ollama Cloud' },
+  { id: 'wafer', name: 'Wafer.ai' },
 ];
 
 export const QUOTA_PROVIDER_MAP = QUOTA_PROVIDERS.reduce<

packages/ui/src/types/quota.ts

@@ -12,7 +12,8 @@ export type QuotaProviderId =
   | 'zhipuai-coding-plan'
   | 'minimax-coding-plan'
   | 'minimax-cn-coding-plan'
-  | 'ollama-cloud';
+  | 'ollama-cloud'
+  | 'wafer';
 
 export interface UsageWindow {
   usedPercent: number | null;

packages/vscode/src/quotaProviders.ts

@@ -97,10 +97,19 @@ type ZhipuaiMcpTimeLimit = {
 type ZhipuaiPayload = {
   data?: {
     limits?: Array<ZhipuaiTokensLimit | ZhipuaiMcpTimeLimit>;
-    level?: string;
   };
 };
 
+type WaferPayload = {
+  remaining_included_requests?: number | string;
+  included_request_limit?: number | string;
+  overage_request_count?: number | string;
+  current_period_used_percent?: number | string;
+  window_start?: number | string;
+  window_end?: number | string;
+  plan_tier?: string;
+};
+
 export type ProviderResult = {
   providerId: string;
   providerName: string;
@@ -439,6 +448,11 @@ export const listConfiguredQuotaProviders = () => {
     configured.add('ollama-cloud');
   }
 
+  const waferAuth = normalizeAuthEntry(getAuthEntry(auth, ['wafer', 'wafer-ai', 'wafer_ai', 'wafer.ai']));
+  if (waferAuth && ((waferAuth as Record<string, unknown>).key || (waferAuth as Record<string, unknown>).token)) {
+    configured.add('wafer');
+  }
+
   return Array.from(configured);
 };
 
@@ -1738,6 +1752,116 @@ export const fetchNanoGptQuota = async (): Promise<ProviderResult> => {
   }
 };
 
+const WAFER_QUOTA_URL = 'https://pass.wafer.ai/v1/inference/quota';
+const WAFER_WINDOW_SECONDS = 5 * 3600;
+
+export const fetchWaferQuota = async (): Promise<ProviderResult> => {
+  const auth = readAuthFile();
+  const entry = normalizeAuthEntry(getAuthEntry(auth, ['wafer', 'wafer-ai', 'wafer_ai', 'wafer.ai'])) as Record<string, unknown> | null;
+  const apiKey = (entry?.key as string | undefined) ?? (entry?.token as string | undefined);
+
+  if (!apiKey) {
+    return buildResult({
+      providerId: 'wafer',
+      providerName: 'Wafer.ai',
+      ok: false,
+      configured: false,
+      error: 'Not configured',
+    });
+  }
+
+  const timeoutSignal = AbortSignal.timeout(15_000);
+
+  try {
+    const response = await fetch(WAFER_QUOTA_URL, {
+      method: 'GET',
+      headers: {
+        Authorization: `Bearer ${apiKey}`,
+        'Accept-Encoding': 'identity',
+      },
+      signal: timeoutSignal,
+    });
+
+    if (!response.ok) {
+      return buildResult({
+        providerId: 'wafer',
+        providerName: 'Wafer.ai',
+        ok: false,
+        configured: true,
+        error: `API error: ${response.status}`,
+      });
+    }
+
+    const payload = await response.json() as WaferPayload;
+    const remaining = toNumber(payload?.remaining_included_requests);
+    const limit = toNumber(payload?.included_request_limit);
+    const overage = toNumber(payload?.overage_request_count);
+    const usedPercentRaw = toNumber(payload?.current_period_used_percent);
+    const windowStart = toTimestamp(payload?.window_start);
+    const windowEnd = toTimestamp(payload?.window_end);
+    const planTier = asNonEmptyString(payload?.plan_tier);
+
+    if (remaining === null && limit === null && overage === null && usedPercentRaw === null) {
+      return buildResult({
+        providerId: 'wafer',
+        providerName: 'Wafer.ai',
+        ok: false,
+        configured: true,
+        error: 'No quota data in response',
+      });
+    }
+
+    const hasOverage = overage !== null && overage > 0;
+    const usedPercent = hasOverage
+      ? Math.max(0, usedPercentRaw ?? 0)
+      : Math.max(0, Math.min(100, usedPercentRaw ?? 0));
+
+    const windowSeconds = windowStart !== null && windowEnd !== null
+      ? Math.round((windowEnd - windowStart) / 1000)
+      : WAFER_WINDOW_SECONDS;
+    const windowLabel = resolveWindowLabel(windowSeconds);
+
+    let valueLabel: string | null = null;
+    if (remaining !== null && limit !== null) {
+      const parts: string[] = [];
+      if (planTier) parts.push(planTier);
+      parts.push(`${remaining} / ${limit} left`);
+      if (hasOverage) parts.push(`+${overage} overage`);
+      valueLabel = parts.join(' · ');
+    }
+
+    const windows: Record<string, UsageWindow> = {};
+    windows[windowLabel] = toUsageWindow({
+      usedPercent,
+      windowSeconds,
+      resetAt: windowEnd,
+      valueLabel,
+    });
+
+    return buildResult({
+      providerId: 'wafer',
+      providerName: 'Wafer.ai',
+      ok: true,
+      configured: true,
+      usage: { windows },
+    });
+  } catch (error) {
+    const isTimeout = error instanceof DOMException && error.name === 'AbortError' && timeoutSignal.aborted;
+    const isParseError = error instanceof SyntaxError;
+    return buildResult({
+      providerId: 'wafer',
+      providerName: 'Wafer.ai',
+      ok: false,
+      configured: true,
+      error: isTimeout
+        ? 'Request timed out'
+        : isParseError
+          ? 'Invalid response from provider'
+          : (error instanceof Error ? error.message : 'Request failed'),
+    });
+  }
+};
+
 export const fetchQuotaForProvider = async (providerId: string): Promise<ProviderResult> => {
   switch (providerId) {
     case 'claude':
@@ -1766,6 +1890,8 @@ export const fetchQuotaForProvider = async (providerId: string): Promise<Provide
       return fetchZaiQuota();
     case 'zhipuai-coding-plan':
       return fetchZhipuaiCodingPlanQuota();
+    case 'wafer':
+      return fetchWaferQuota();
     default:
       return buildResult({
         providerId,

packages/web/server/lib/quota/DOCUMENTATION.md

@@ -30,6 +30,7 @@ These provider IDs are currently dispatchable via `fetchQuotaForProvider(provide
 | `minimax-coding-plan` | MiniMax Coding Plan (minimax.io) | `providers/minimax-coding-plan.js` | `minimax-coding-plan` |
 | `minimax-cn-coding-plan` | MiniMax Coding Plan (minimaxi.com) | `providers/minimax-cn-coding-plan.js` | `minimax-cn-coding-plan` |
 | `ollama-cloud` | Ollama Cloud | `providers/ollama-cloud.js` | Cookie file at `~/.config/ollama-quota/cookie` (raw session cookie string) |
+| `wafer` | Wafer.ai | `providers/wafer.js` | `wafer`, `wafer-ai`, `wafer_ai`, `wafer.ai` |
 
 ## Internal-only provider module
 - `providers/openai.js` exists for logic parity/reuse but is intentionally not registered for dispatcher ID routing.

packages/web/server/lib/quota/index.js

@@ -21,5 +21,6 @@ export {
   fetchMinimaxCodingPlanQuota,
   fetchMinimaxCnCodingPlanQuota,
   fetchOllamaCloudQuota,
-  fetchZhipuaiQuota
+  fetchZhipuaiQuota,
+  fetchWaferQuota
 } from './providers/index.js';

packages/web/server/lib/quota/providers/index.js

@@ -20,6 +20,7 @@ import * as zhipuaiCodingPlan from './zhipuai-coding-plan.js';
 import * as minimaxCodingPlan from './minimax-coding-plan.js';
 import * as minimaxCnCodingPlan from './minimax-cn-coding-plan.js';
 import * as ollamaCloud from './ollama-cloud.js';
+import * as wafer from './wafer.js';
 
 const registry = {
   claude: {
@@ -99,6 +100,12 @@ const registry = {
     providerName: ollamaCloud.providerName,
     isConfigured: ollamaCloud.isConfigured,
     fetchQuota: ollamaCloud.fetchQuota
+  },
+  wafer: {
+    providerId: wafer.providerId,
+    providerName: wafer.providerName,
+    isConfigured: wafer.isConfigured,
+    fetchQuota: wafer.fetchQuota
   }
 };
 
@@ -158,4 +165,5 @@ export const fetchNanoGptQuota = nanogpt.fetchQuota;
 export const fetchMinimaxCodingPlanQuota = minimaxCodingPlan.fetchQuota;
 export const fetchMinimaxCnCodingPlanQuota = minimaxCnCodingPlan.fetchQuota;
 export const fetchOllamaCloudQuota = ollamaCloud.fetchQuota;
+export const fetchWaferQuota = wafer.fetchQuota;
 export const fetchZhipuaiQuota = zhipuaiCodingPlan.fetchQuota;

packages/web/server/lib/quota/providers/wafer.js

@@ -0,0 +1,131 @@
+import { readAuthFile } from '../../opencode/auth.js';
+import {
+  getAuthEntry,
+  normalizeAuthEntry,
+  buildResult,
+  toUsageWindow,
+  toNumber,
+  toTimestamp,
+  resolveWindowLabel,
+  asNonEmptyString
+} from '../utils/index.js';
+
+export const providerId = 'wafer';
+export const providerName = 'Wafer.ai';
+export const aliases = ['wafer', 'wafer-ai', 'wafer_ai', 'wafer.ai'];
+
+const WAFER_QUOTA_URL = 'https://pass.wafer.ai/v1/inference/quota';
+const WAFER_WINDOW_SECONDS = 5 * 3600;
+
+export const isConfigured = () => {
+  const auth = readAuthFile();
+  const entry = normalizeAuthEntry(getAuthEntry(auth, aliases));
+  return Boolean(entry?.key || entry?.token);
+};
+
+export const fetchQuota = async () => {
+  const auth = readAuthFile();
+  const entry = normalizeAuthEntry(getAuthEntry(auth, aliases));
+  const apiKey = entry?.key ?? entry?.token;
+
+  if (!apiKey) {
+    return buildResult({
+      providerId,
+      providerName,
+      ok: false,
+      configured: false,
+      error: 'Not configured'
+    });
+  }
+
+  const timeoutSignal = AbortSignal.timeout(15_000);
+
+  try {
+    const response = await fetch(WAFER_QUOTA_URL, {
+      method: 'GET',
+      headers: {
+        Authorization: `Bearer ${apiKey}`,
+        'Accept-Encoding': 'identity'
+      },
+      signal: timeoutSignal
+    });
+
+    if (!response.ok) {
+      return buildResult({
+        providerId,
+        providerName,
+        ok: false,
+        configured: true,
+        error: `API error: ${response.status}`
+      });
+    }
+
+    const payload = await response.json();
+    const remaining = toNumber(payload?.remaining_included_requests);
+    const limit = toNumber(payload?.included_request_limit);
+    const overage = toNumber(payload?.overage_request_count);
+    const usedPercentRaw = toNumber(payload?.current_period_used_percent);
+    const windowStart = toTimestamp(payload?.window_start);
+    const windowEnd = toTimestamp(payload?.window_end);
+    const planTier = asNonEmptyString(payload?.plan_tier);
+
+    if (remaining === null && limit === null && overage === null && usedPercentRaw === null) {
+      return buildResult({
+        providerId,
+        providerName,
+        ok: false,
+        configured: true,
+        error: 'No quota data in response'
+      });
+    }
+
+    const hasOverage = overage !== null && overage > 0;
+    const usedPercent = hasOverage
+      ? Math.max(0, usedPercentRaw ?? 0)
+      : Math.max(0, Math.min(100, usedPercentRaw ?? 0));
+
+    const windowSeconds = windowStart !== null && windowEnd !== null
+      ? Math.round((windowEnd - windowStart) / 1000)
+      : WAFER_WINDOW_SECONDS;
+    const windowLabel = resolveWindowLabel(windowSeconds);
+
+    let valueLabel = null;
+    if (remaining !== null && limit !== null) {
+      const parts = [];
+      if (planTier) parts.push(planTier);
+      parts.push(`${remaining} / ${limit} left`);
+      if (hasOverage) parts.push(`+${overage} overage`);
+      valueLabel = parts.join(' · ');
+    }
+
+    const windows = {};
+    windows[windowLabel] = toUsageWindow({
+      usedPercent,
+      windowSeconds,
+      resetAt: windowEnd,
+      valueLabel
+    });
+
+    return buildResult({
+      providerId,
+      providerName,
+      ok: true,
+      configured: true,
+      usage: { windows }
+    });
+  } catch (error) {
+    const isTimeout = error instanceof DOMException && error.name === 'AbortError' && timeoutSignal.aborted;
+    const isParseError = error instanceof SyntaxError;
+    return buildResult({
+      providerId,
+      providerName,
+      ok: false,
+      configured: true,
+      error: isTimeout
+        ? 'Request timed out'
+        : isParseError
+          ? 'Invalid response from provider'
+          : (error instanceof Error ? error.message : 'Request failed')
+    });
+  }
+};