github-actions[bot]
deploy from github actions 2026-06-18
c8ae75d
Raw
History Blame Contribute Delete
8.77 kB
/**
* Misc usage handlers (Qwen, iFlow, Ollama, GLM, Vercel AI Gateway, Qoder)
*/
import { proxyAwareFetch } from "../../utils/proxyFetch.js";
import { U } from "./shared.js";
// GLM quota endpoints (region-aware) — url from registry transport.usage
const GLM_QUOTA_URLS = {
international: U("glm").url,
china: U("glm-cn").url,
};
// Vercel AI Gateway credits endpoint
// 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
*/
export async function getIflowUsage(accessToken) {
try {
// iFlow may have usage endpoint
return { message: "iFlow connected. Usage tracked per request." };
} catch (error) {
return { message: "Unable to fetch iFlow usage." };
}
}
/**
* 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.
*/
export async function getOllamaUsage(accessToken, providerSpecificData) {
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: [],
};
} catch (error) {
return { message: "Unable to fetch Ollama Cloud usage." };
}
}
/**
* GLM Coding Plan usage (international + China regions)
*/
export async function getGlmUsage(apiKey, provider, proxyOptions = null) {
if (!apiKey) {
return { message: "GLM API key not available." };
}
const region = provider === "glm-cn" ? "china" : "international";
const quotaUrl = GLM_QUOTA_URLS[region];
try {
const response = await proxyAwareFetch(quotaUrl, {
headers: {
Authorization: `Bearer ${apiKey}`,
Accept: "application/json",
},
}, proxyOptions);
if (!response.ok) {
if (response.status === 401) {
return { message: "GLM API key invalid or expired." };
}
return { message: `GLM quota API error (${response.status}).` };
}
const json = await response.json();
const data = json?.data && typeof json.data === "object" ? json.data : {};
const limits = Array.isArray(data.limits) ? data.limits : [];
const quotas = {};
for (const limit of limits) {
if (!limit || limit.type !== "TOKENS_LIMIT") continue;
const usedPercent = Number(limit.percentage) || 0;
const resetMs = Number(limit.nextResetTime) || 0;
const remaining = Math.max(0, 100 - usedPercent);
quotas["session"] = {
used: usedPercent,
total: 100,
remaining,
remainingPercentage: remaining,
resetAt: resetMs > 0 ? new Date(resetMs).toISOString() : null,
unlimited: false,
};
}
const levelRaw = typeof data.level === "string" ? data.level : "";
const plan = levelRaw
? levelRaw.charAt(0).toUpperCase() + levelRaw.slice(1).toLowerCase()
: "Unknown";
return { plan, quotas };
} catch (error) {
return { message: `GLM error: ${error.message}` };
}
}
/**
* Vercel AI Gateway usage — credit balance for the API key
*
* Calls GET /v1/credits which returns:
* { "balance": "95.50", "total_used": "4.50" } (USD as decimal strings)
*
* We surface this as a single "Balance ($)" quota row so the existing
* QuotaTable / progress-bar UI can render it. used = total_used,
* total = balance + total_used (the original credit allotment), so the
* remaining percentage equals balance / total.
*
* Docs: https://vercel.com/docs/ai-gateway/usage
*/
export async function getVercelAiGatewayUsage(apiKey, proxyOptions = null) {
if (!apiKey) {
return { message: "Vercel AI Gateway API key not available." };
}
try {
const response = await proxyAwareFetch(VERCEL_AI_GATEWAY_CREDITS_URL, {
method: "GET",
headers: {
Authorization: `Bearer ${apiKey}`,
Accept: "application/json",
},
}, proxyOptions);
if (response.status === 401 || response.status === 403) {
return { message: "Vercel AI Gateway API key invalid or expired." };
}
if (!response.ok) {
const errorText = await response.text().catch(() => "");
const trimmed = errorText ? `: ${errorText.slice(0, 200)}` : "";
return { message: `Vercel AI Gateway credits API error (${response.status})${trimmed}` };
}
const data = await response.json();
// Vercel returns numeric strings; coerce safely.
const balance = Number(data?.balance) || 0;
const totalUsed = Number(data?.total_used) || 0;
// Vercel gives $5/month free credit. The API doesn't return the
// monthly allocation so we use the known constant as the denominator.
const MONTHLY_CREDIT = 5;
const remainingPercentage = (balance / MONTHLY_CREDIT) * 100;
if (balance <= 0 && totalUsed <= 0) {
return {
plan: "Pay-as-you-go",
message: "Vercel AI Gateway connected. No credit allocation found (BYOK or unfunded account).",
quotas: {},
};
}
// "Used (USD)": how much has been spent this month (no fixed cap → unlimited).
// "Remaining (USD)": balance remaining out of the $5 monthly allocation.
return {
plan: "Pay-as-you-go",
quotas: {
"Used (USD)": {
used: totalUsed,
total: 0,
remaining: 0,
remainingPercentage: 100,
unlimited: true,
},
"Remaining (USD)": {
used: balance,
total: MONTHLY_CREDIT,
remaining: balance,
remainingPercentage,
unlimited: false,
},
},
};
} catch (error) {
return { message: `Vercel AI Gateway error: ${error.message}` };
}
}
export async function getQoderUsage(accessToken, proxyOptions = null) {
if (!accessToken) {
return { message: "Qoder usage unavailable: no access token" };
}
try {
const response = await proxyAwareFetch(
U("qoder").url,
{
method: "GET",
headers: {
Authorization: `Bearer ${accessToken}`,
Accept: "application/json",
},
},
proxyOptions,
);
if (!response.ok) {
return { message: `Qoder connected. Usage fetch returned ${response.status}.` };
}
const body = await response.json().catch(() => null);
if (!body) {
return { message: "Qoder connected. Usage response was not JSON." };
}
// Quota records live under `quotas`; scalar metadata
// (totalUsagePercentage, isQuotaExceeded, expiresAt) are surfaced as
// siblings so the dashboard parser doesn't try to render them as rows.
const userQuota = body.userQuota || {};
const orgQuota = body.orgResourcePackage || {};
// Qoder publishes a single absolute reset timestamp (`expiresAt` in ms);
// surface it on every quota record as ISO so the table can render
// "resets at" alongside used/total.
const expiresAtMs = Number.isFinite(Number(body.expiresAt)) && Number(body.expiresAt) > 0
? Number(body.expiresAt)
: null;
const resetAt = expiresAtMs ? new Date(expiresAtMs).toISOString() : null;
const quotas = {
user: {
total: Number(userQuota.total) || 0,
used: Number(userQuota.used) || 0,
remaining: Number(userQuota.remaining) || 0,
unit: userQuota.unit || "credits",
resetAt,
},
organization: {
total: Number(orgQuota.total) || 0,
used: Number(orgQuota.used) || 0,
remaining: Number(orgQuota.remaining) || 0,
unit: orgQuota.unit || "credits",
resetAt,
},
};
return {
quotas,
totalUsagePercentage: Number(body.totalUsagePercentage) || 0,
isQuotaExceeded: !!body.isQuotaExceeded,
expiresAt: expiresAtMs,
};
} catch (error) {
return { message: `Qoder connected. Unable to fetch usage: ${error.message}` };
}
}