feat(api): count the quota by the CDN's client IP and refuse direct calls (#956 )

Two optional settings for deployments behind a CDN such as Cloudflare. CLIENT_IP_HEADER names the header that holds the visitor's real IP (cf-connecting-ip on Cloudflare). The per-IP daily quota used the first X-Forwarded-For entry, which visitors can set to anything, so a made-up IP on every request got a fresh quota. ORIGIN_SECRET makes proxy.ts refuse /api requests whose X-Origin-Secret header does not match. The CDN adds the header, so a call that skips the CDN, and could fake the IP header, gets 403. Pages are not checked, which keeps health checks on / working. Both are unset by default, and nothing changes then.
fix(deps): update vulnerable dependencies with npm audit fix (#804 )
2026-10-06 09:47:49 +08:00 · 2026-10-06 10:32:43 +09:00 · 2026-10-06 09:56:06 +09:00 · 2026-10-06 09:55:26 +09:00 · 2026-10-06 09:49:48 +09:00 · 2026-10-06 09:37:05 +09:00
23 changed files with 1159 additions and 1282 deletions
@@ -427,13 +427,16 @@ export default function ChatPanel({
            let openModelConfig = false
            if (data?.type === "provider") {
                const hints = dict.errors.llm as Record<string, string>
-                text = hints[data.code]
-                    ? `${hints[data.code]}\n\n${data.message}`
-                    : data.message
+                const hint = hints[data.code]
+                text =
+                    hint && data.message
+                        ? `${hint}\n\n${data.message}`
+                        : hint || data.message
                openModelConfig = [
                    "invalid_api_key",
                    "forbidden",
                    "model_not_found",
+                    "server_key_forbidden",
                ].includes(data.code)
            } else if (typeof data?.error === "string") {
                text = data.error
@@ -46,6 +46,8 @@ AI_MODEL=gpt-4o
 OPENAI_BASE_URL=https://your-custom-endpoint/v1
 ```

+LM Studio 等本地 OpenAI 兼容服务也用同样的方式：把 base URL 设为 `http://localhost:1234/v1`（LM Studio 的默认端口），API 密钥填任意非空值即可，例如 `lm-studio`。在上面的环境变量或模型设置里配置都可以。
+
 ### AIHubMix

 AIHubMix 通过单个 API Key 聚合 Claude、GPT、Gemini、DeepSeek 等模型。
@@ -192,7 +194,7 @@ MODELSCOPE_BASE_URL=https://your-custom-endpoint
 可选的自定义 URL：

 ```bash
-OLLAMA_BASE_URL=http://localhost:11434
+OLLAMA_BASE_URL=http://localhost:11434/api
 ```

 ### Vercel AI Gateway
@@ -61,6 +61,8 @@ Optional custom endpoint (for OpenAI-compatible services):
 OPENAI_BASE_URL=https://your-custom-endpoint/v1
 ```

+LM Studio and other local OpenAI-compatible servers work the same way: set the base URL to `http://localhost:1234/v1` (LM Studio's default port) and use any non-empty API key, such as `lm-studio`. This works both in the environment variables above and in the model settings.
+
 ### AIHubMix

 AIHubMix provides access to Claude, GPT, Gemini, DeepSeek, and other models through a single API key.
@@ -194,7 +196,7 @@ AI_MODEL=llama3.2
 Optional custom URL:

 ```bash
-OLLAMA_BASE_URL=http://localhost:11434
+OLLAMA_BASE_URL=http://localhost:11434/api
 ```

 ### ModelScope
@@ -46,6 +46,8 @@ AI_MODEL=gpt-4o
 OPENAI_BASE_URL=https://your-custom-endpoint/v1
 ```

+LM Studio などのローカルな OpenAI 互換サーバーも同じ方法で使えます。ベース URL を `http://localhost:1234/v1`（LM Studio の既定ポート）に設定し、API キーには `lm-studio` など空でない任意の値を入力してください。上の環境変数でも、モデル設定画面でも設定できます。
+
 ### AIHubMix

 AIHubMix は、単一の API キーで Claude、GPT、Gemini、DeepSeek などのモデルへのアクセスを提供します。
@@ -179,7 +181,7 @@ AI_MODEL=llama3.2
 任意のカスタム URL:

 ```bash
-OLLAMA_BASE_URL=http://localhost:11434
+OLLAMA_BASE_URL=http://localhost:11434/api
 ```

 ### ModelScope
@@ -70,7 +70,7 @@ AI_MODEL=global.anthropic.claude-sonnet-4-5-20250929-v1:0
 # AZURE_REASONING_SUMMARY=detailed

 # Ollama Configuration (Local or Cloud)
-# OLLAMA_BASE_URL=https://ollama.com/api  # Optional: Ollama Cloud; defaults to local Ollama (http://127.0.0.1:11434)
+# OLLAMA_BASE_URL=https://ollama.com/api  # Optional: Ollama Cloud; defaults to local Ollama (http://127.0.0.1:11434/api)
 # OLLAMA_API_KEY=your-ollama-cloud-api-key    # Optional: For Ollama Cloud or authenticated remote instances
 # OLLAMA_ENABLE_THINKING=true                 # Optional: Enable thinking for models that support it (e.g., qwen3)

@@ -163,6 +163,16 @@ AI_MODEL=global.anthropic.claude-sonnet-4-5-20250929-v1:0
 # Set to "false" to block private IPs, localhost, and internal hostnames
 # ALLOW_PRIVATE_URLS=false

+# Behind a CDN such as Cloudflare (Optional)
+# The daily quota is counted per IP. By default the IP is the first
+# X-Forwarded-For entry, which visitors can set to anything. Name the header
+# your CDN fills with the visitor's real IP instead:
+# CLIENT_IP_HEADER=cf-connecting-ip
+# Then have the CDN add an X-Origin-Secret header with this value to every
+# request. API calls without it get 403, so nobody can skip the CDN and fake
+# the IP header above.
+# ORIGIN_SECRET=a-long-random-string
+
 # Self-hosted deployment (Optional)
 # Self-hosted users may implement custom quota-management solutions,
 # which triggers the client UI to display messages suggesting self-hosting or sponsorship.
@@ -25,6 +25,7 @@ import { getEnvFallback } from "@/lib/admin/settings"
 import { isPrivateUrl, redirectGuardedFetch } from "@/lib/ssrf-protection"
 import {
    normalizeBaseUrl,
+    ollamaApiUrl,
    PROVIDER_INFO,
    type ProviderName,
 } from "@/lib/types/model-config"
@@ -1025,7 +1026,7 @@ export function getAIModel(clientOverrides?: ClientOverrides): ModelConfig {
                    ? PROVIDER_INFO.ollama.defaultBaseUrl
                    : resolveBaseUrlEnv(overrides, "OLLAMA_BASE_URL"))
            model = createOllama({
-                ...(baseURL && { baseURL }),
+                ...(baseURL && { baseURL: ollamaApiUrl(baseURL) }),
                ...(apiKey && {
                    headers: { Authorization: `Bearer ${apiKey}` },
                }),
@@ -192,6 +192,7 @@
        "llm": {
            "invalid_api_key": "The provider rejected the API key. Check it in model settings.",
            "forbidden": "The provider refused the request. The key may not have access to this model or region.",
+            "server_key_forbidden": "Today's free quota is used up. It resets tomorrow. You can also add your own API key in model settings to keep going.",
            "model_not_found": "The provider does not know this model. Check the model ID in model settings.",
            "insufficient_quota": "The provider account has no credit or quota left.",
            "rate_limited": "The provider is limiting requests. Wait a moment and try again.",
@@ -192,6 +192,7 @@
        "llm": {
            "invalid_api_key": "プロバイダーが API キーを拒否しました。モデル設定で確認してください。",
            "forbidden": "プロバイダーがリクエストを拒否しました。このキーにはこのモデルまたはリージョンの利用権限がない可能性があります。",
+            "server_key_forbidden": "本日の無料枠を使い切りました。明日になると自動的に回復します。モデル設定でご自身の API キーを入力すると、引き続きご利用いただけます。",
            "model_not_found": "プロバイダーがこのモデルを認識できません。モデル設定でモデル ID を確認してください。",
            "insufficient_quota": "プロバイダーのアカウントの残高または利用枠がなくなりました。",
            "rate_limited": "プロバイダーがリクエスト数を制限しています。少し待ってから再試行してください。",
@@ -192,6 +192,7 @@
        "llm": {
            "invalid_api_key": "服務商拒絕了這個 API Key，請在模型設定中檢查。",
            "forbidden": "服務商拒絕了這次請求。這個 Key 可能沒有使用該模型或該地區的權限。",
+            "server_key_forbidden": "今天的免費額度已經用完，明天會自動恢復。您也可以在模型設定中填寫自己的 API Key 繼續使用。",
            "model_not_found": "服務商找不到這個模型，請在模型設定中檢查模型 ID。",
            "insufficient_quota": "服務商帳戶的餘額或額度已經用完。",
            "rate_limited": "服務商正在限制請求頻率，請稍候再試。",
@@ -192,6 +192,7 @@
        "llm": {
            "invalid_api_key": "服务商拒绝了这个 API Key，请在模型设置里检查。",
            "forbidden": "服务商拒绝了这次请求。这个 Key 可能没有使用该模型或该地区的权限。",
+            "server_key_forbidden": "今天的免费额度已经用完，明天会自动恢复。您也可以在模型设置里填写自己的 API Key 继续使用。",
            "model_not_found": "服务商找不到这个模型，请在模型设置里检查模型 ID。",
            "insufficient_quota": "服务商账户的余额或额度已经用完。",
            "rate_limited": "服务商正在限制请求频率，请稍等片刻再试。",
@@ -24,6 +24,8 @@ export type LLMErrorCode =
    | "provider_unavailable"
    | "cannot_connect"
    | "timeout"
+    // A 403 on the server's own key, e.g. a daily spend cap blocked it
+    | "server_key_forbidden"
    | "unknown"

 export interface LLMError {
@@ -130,7 +132,13 @@ export function streamErrorText(error: unknown, hideDetails = false): string {
    const classified = classifyLLMError(error)
    if (hideDetails) {
        console.error("[chat] Provider error:", error)
-        classified.message = "The provider returned an error."
+        if (classified.code === "forbidden") {
+            // The hint says all the user can do; there is no message to add
+            classified.code = "server_key_forbidden"
+            classified.message = ""
+        } else {
+            classified.message = "The provider returned an error."
+        }
    }
    return JSON.stringify(classified)
 }
@@ -3,6 +3,7 @@ import { getModelInfo } from "@/lib/model-catalog"
 import { readLimitedBody } from "@/lib/read-limited-body"
 import {
    normalizeBaseUrl,
+    ollamaApiUrl,
    PROVIDER_INFO,
    type ProviderName,
 } from "@/lib/types/model-config"
@@ -200,8 +201,11 @@ export async function listProviderModels(
            break
        }
        case "ollama": {
-            const api = base.endsWith("/api") ? base : `${base}/api`
-            const data = await getJson(`${api}/tags`, bearer, fetchFn)
+            const data = await getJson(
+                `${ollamaApiUrl(base)}/tags`,
+                bearer,
+                fetchFn,
+            )
            models = (data.models ?? []).map((m: { name: string }) => ({
                id: m.name,
            }))
@@ -622,6 +622,15 @@ export function normalizeBaseUrl(url: string): string {
        .replace(/\/(?:chat\/completions|completions|messages|responses)$/, "")
 }

+/**
+ * Ollama's native API root, which the SDK appends /chat to and the model
+ * list /tags. Users often enter the server address ("http://localhost:11434")
+ * or its OpenAI-compatible one (".../v1"); both get /api.
+ */
+export function ollamaApiUrl(baseUrl: string): string {
+    return `${normalizeBaseUrl(baseUrl).replace(/\/(?:api|v1)$/, "")}/api`
+}
+
 /** Where a chat request goes for a base URL, or null when the SDK decides */
 export function chatRequestUrl(
    provider: ProviderName,
@@ -630,6 +639,7 @@ export function chatRequestUrl(
    const url = normalizeBaseUrl(baseUrl)
    if (!url) return null
    if (provider === "anthropic") return `${url}/messages`
+    if (provider === "ollama") return `${ollamaApiUrl(url)}/chat`
    // These SDKs build their own paths (or, for MiniMax, pick the protocol
    // from the URL)
    const ownPaths: ProviderName[] = [
@@ -637,7 +647,6 @@ export function chatRequestUrl(
        "vertexai",
        "azure",
        "bedrock",
-        "ollama",
        "gateway",
        "minimax",
        "edgeone",
@@ -2,10 +2,19 @@
 * Generate a userId from request for tracking purposes.
 * Uses base64url encoding of IP for URL-safe identifier.
 * Note: base64 is reversible - this is NOT privacy protection.
+ *
+ * The first X-Forwarded-For entry is whatever the visitor sent, so behind a
+ * CDN set CLIENT_IP_HEADER to the header it fills with the real IP (e.g.
+ * cf-connecting-ip), and ORIGIN_SECRET so requests that skip the CDN are
+ * refused (see proxy.ts).
 */
 export function getUserIdFromRequest(req: Request): string {
-    const forwardedFor = req.headers.get("x-forwarded-for")
-    const rawIp = forwardedFor?.split(",")[0]?.trim() || "anonymous"
+    const ipHeader = process.env.CLIENT_IP_HEADER
+    const rawIp =
+        (ipHeader
+            ? req.headers.get(ipHeader)?.trim()
+            : req.headers.get("x-forwarded-for")?.split(",")[0]?.trim()) ||
+        "anonymous"
    return rawIp === "anonymous"
        ? rawIp
        : `user-${Buffer.from(rawIp).toString("base64url")}`
@@ -507,12 +507,12 @@
            }
        },
        "node_modules/@hono/node-server": {
-            "version": "1.19.9",
-            "resolved": "https://registry.npmjs.org/@hono/node-server/-/node-server-1.19.9.tgz",
-            "integrity": "sha512-vHL6w3ecZsky+8P5MD+eFfaGTyCeOHUIFYMGpQGbrBTSmNNoxv0if69rEZ5giu36weC5saFuznL411gRX7bJDw==",
+            "version": "2.1.3",
+            "resolved": "https://registry.npmjs.org/@hono/node-server/-/node-server-2.1.3.tgz",
+            "integrity": "sha512-TA//nWMqPhbfdfneACk6t5a9eqbS9lABEPyKn0/xZTah3H3U2XaVg85rJFl0/Fyit0I552YDHgXGVSf3GwqbUw==",
            "license": "MIT",
            "engines": {
-                "node": ">=18.14.1"
+                "node": ">=20"
            },
            "peerDependencies": {
                "hono": "^4"
@@ -1045,9 +1045,9 @@
            }
        },
        "node_modules/ajv": {
-            "version": "8.17.1",
-            "resolved": "https://registry.npmjs.org/ajv/-/ajv-8.17.1.tgz",
-            "integrity": "sha512-B/gBuNg5SiMTrPkC+A2+cW0RszwxYmn6VYxB/inlBStS5nx6xHIt/ehKRhIMhqusl7a8LjQoZnjCs5vhwxOQ1g==",
+            "version": "8.20.0",
+            "resolved": "https://registry.npmjs.org/ajv/-/ajv-8.20.0.tgz",
+            "integrity": "sha512-Thbli+OlOj+iMPYFBVBfJ3OmCAnaSyNn4M1vz9T6Gka5Jt9ba/HIR56joy65tY6kx/FCF5VXNB819Y7/GUrBGA==",
            "license": "MIT",
            "dependencies": {
                "fast-deep-equal": "^3.1.3",
@@ -1088,20 +1088,20 @@
            }
        },
        "node_modules/body-parser": {
-            "version": "2.2.1",
-            "resolved": "https://registry.npmjs.org/body-parser/-/body-parser-2.2.1.tgz",
-            "integrity": "sha512-nfDwkulwiZYQIGwxdy0RUmowMhKcFVcYXUU7m4QlKYim1rUtg83xm2yjZ40QjDuc291AJjjeSc9b++AWHSgSHw==",
+            "version": "2.3.0",
+            "resolved": "https://registry.npmjs.org/body-parser/-/body-parser-2.3.0.tgz",
+            "integrity": "sha512-2cGmJupaNgg+QUwVLAucDuWuoMZ6EX9iHDRswZ5lsNYEmwPaRknMPCLZz07yTzVq/83p4o/wzbDZbBrTvGGTIw==",
            "license": "MIT",
            "dependencies": {
                "bytes": "^3.1.2",
-                "content-type": "^1.0.5",
+                "content-type": "^2.0.0",
                "debug": "^4.4.3",
-                "http-errors": "^2.0.0",
-                "iconv-lite": "^0.7.0",
+                "http-errors": "^2.0.1",
+                "iconv-lite": "^0.7.2",
                "on-finished": "^2.4.1",
-                "qs": "^6.14.0",
-                "raw-body": "^3.0.1",
-                "type-is": "^2.0.1"
+                "qs": "^6.15.2",
+                "raw-body": "^3.0.2",
+                "type-is": "^2.1.0"
            },
            "engines": {
                "node": ">=18"
@@ -1111,6 +1111,19 @@
                "url": "https://opencollective.com/express"
            }
        },
+        "node_modules/body-parser/node_modules/content-type": {
+            "version": "2.1.0",
+            "resolved": "https://registry.npmjs.org/content-type/-/content-type-2.1.0.tgz",
+            "integrity": "sha512-mj7UPXE0jaqaOsukNZRUEfEi2AcL7C/vwmwcHV0O97eO1E1pxBZuyjlZrx5seTaNBg1U6+o35wpa35Qfcc+7ag==",
+            "license": "MIT",
+            "engines": {
+                "node": ">=18"
+            },
+            "funding": {
+                "type": "opencollective",
+                "url": "https://opencollective.com/express"
+            }
+        },
        "node_modules/boolbase": {
            "version": "2.0.0",
            "resolved": "https://registry.npmjs.org/boolbase/-/boolbase-2.0.0.tgz",
@@ -1577,9 +1590,9 @@
            "license": "MIT"
        },
        "node_modules/es-object-atoms": {
-            "version": "1.1.1",
-            "resolved": "https://registry.npmjs.org/es-object-atoms/-/es-object-atoms-1.1.1.tgz",
-            "integrity": "sha512-FGgH2h8zKNim9ljj7dankFPcICIK9Cp5bm+c2gQSYePhpaG5+esrLODihIorn+Pe6FGJzWhXQotPv73jTaldXA==",
+            "version": "1.1.2",
+            "resolved": "https://registry.npmjs.org/es-object-atoms/-/es-object-atoms-1.1.2.tgz",
+            "integrity": "sha512-HWcBoN6NileqtSydK2FqHbS/LoDd2pqrnQHLyJzBj4kOp/ky2MWMN694xOfkK8/SnUsW2DH7EfyVlydKCsm1Zw==",
            "license": "MIT",
            "dependencies": {
                "es-errors": "^1.3.0"
@@ -1730,12 +1743,13 @@
            }
        },
        "node_modules/express-rate-limit": {
-            "version": "8.2.1",
-            "resolved": "https://registry.npmjs.org/express-rate-limit/-/express-rate-limit-8.2.1.tgz",
-            "integrity": "sha512-PCZEIEIxqwhzw4KF0n7QF4QqruVTcF73O5kFKUnGOyjbCCgizBBiFaYpd/fnBLUMPw/BWw9OsiN7GgrNYr7j6g==",
+            "version": "8.7.0",
+            "resolved": "https://registry.npmjs.org/express-rate-limit/-/express-rate-limit-8.7.0.tgz",
+            "integrity": "sha512-hOwV7WOxXfjRpAM1DSJWZDXx3GhplwD8IfwuwvogD8i1Qnkgosw/H45s4ZnFAUHDAhPjlY9hLBvJhKmGMyY26g==",
            "license": "MIT",
            "dependencies": {
-                "ip-address": "10.0.1"
+                "debug": "^4.4.3",
+                "ip-address": "^10.2.0"
            },
            "engines": {
                "node": ">= 16"
@@ -1754,9 +1768,9 @@
            "license": "MIT"
        },
        "node_modules/fast-uri": {
-            "version": "3.1.0",
-            "resolved": "https://registry.npmjs.org/fast-uri/-/fast-uri-3.1.0.tgz",
-            "integrity": "sha512-iPeeDKJSWf4IEOasVVrknXpaBV0IApz/gp7S2bb7Z4Lljbl2MGJRqInZiUrQwV16cpzw/D3S5j5Julj/gT52AA==",
+            "version": "3.1.8",
+            "resolved": "https://registry.npmjs.org/fast-uri/-/fast-uri-3.1.8.tgz",
+            "integrity": "sha512-GZMtZUTNRpOVIECoXwLNZS5xUGE+mVNbTB8h/7Rwh2TFWcBQiPzTgyZi05BF9UMZKkLJv8XBRJTlU7zg8+ZfMg==",
            "funding": [
                {
                    "type": "github",
@@ -1912,9 +1926,9 @@
            }
        },
        "node_modules/hasown": {
-            "version": "2.0.2",
-            "resolved": "https://registry.npmjs.org/hasown/-/hasown-2.0.2.tgz",
-            "integrity": "sha512-0hJU9SCPvmMzIBdZFqNPXWa6dqh7WdH0cII9y+CyS8rG3nL48Bclra9HmKhVVUHyPWNH5Y7xDwAB7bfgSjkUMQ==",
+            "version": "2.0.4",
+            "resolved": "https://registry.npmjs.org/hasown/-/hasown-2.0.4.tgz",
+            "integrity": "sha512-T2UbfbBEF32wiepXIsMlTW9+dDYC6wMh/t/vYA4tuOMKqWz/n3vr1NFSxQiyP+zk2mXsoMA/i/7qV6LKut1t1A==",
            "license": "MIT",
            "dependencies": {
                "function-bind": "^1.1.2"
@@ -1924,9 +1938,9 @@
            }
        },
        "node_modules/hono": {
-            "version": "4.11.9",
-            "resolved": "https://registry.npmjs.org/hono/-/hono-4.11.9.tgz",
-            "integrity": "sha512-Eaw2YTGM6WOxA6CXbckaEvslr2Ne4NFsKrvc0v97JD5awbmeBLO5w9Ho9L9kmKonrwF9RJlW6BxT1PVv/agBHQ==",
+            "version": "4.13.13",
+            "resolved": "https://registry.npmjs.org/hono/-/hono-4.13.13.tgz",
+            "integrity": "sha512-CQ46U0ZkAGmbT/4UxdzzGJpacP2IeKgY4a5/tOI9AABbpOMfK739wfDXmv1usCk+3RkKj1hQy4/fjhiwa2xlrA==",
            "license": "MIT",
            "engines": {
                "node": ">=16.9.0"
@@ -1990,9 +2004,9 @@
            }
        },
        "node_modules/iconv-lite": {
-            "version": "0.7.1",
-            "resolved": "https://registry.npmjs.org/iconv-lite/-/iconv-lite-0.7.1.tgz",
-            "integrity": "sha512-2Tth85cXwGFHfvRgZWszZSvdo+0Xsqmw8k8ZwxScfcBneNUraK+dxRxRm24nszx80Y0TVio8kKLt5sLE7ZCLlw==",
+            "version": "0.7.3",
+            "resolved": "https://registry.npmjs.org/iconv-lite/-/iconv-lite-0.7.3.tgz",
+            "integrity": "sha512-IKXpvIzjnC9XTAUbVBcMfGS0EPaIXtW6v+zr+RRp+hqULEpo0owZax6wyRwPOJbWbzjYspQwusTsfVr0ifh4uQ==",
            "license": "MIT",
            "dependencies": {
                "safer-buffer": ">= 2.1.2 < 3.0.0"
@@ -2012,9 +2026,9 @@
            "license": "ISC"
        },
        "node_modules/ip-address": {
-            "version": "10.0.1",
-            "resolved": "https://registry.npmjs.org/ip-address/-/ip-address-10.0.1.tgz",
-            "integrity": "sha512-NWv9YLW4PoW2B7xtzaS3NCot75m6nK7Icdv0o3lfMceJVRfSoQwqD4wEH5rLwoKJwUiZ/rfpiVBhnaF0FK4HoA==",
+            "version": "10.7.3",
+            "resolved": "https://registry.npmjs.org/ip-address/-/ip-address-10.7.3.tgz",
+            "integrity": "sha512-A1kdq/tSb5QjvKvAMgIoEvDBIgL7qaqVP/jkvSwYYRZ9iEzvPpopxp2wQfu3SuZRHtpHNxMn8Fs0bS+gf5Xmwg==",
            "license": "MIT",
            "engines": {
                "node": ">= 12"
@@ -2479,9 +2493,9 @@
            "license": "MIT"
        },
        "node_modules/nanoid": {
-            "version": "3.3.12",
-            "resolved": "https://registry.npmjs.org/nanoid/-/nanoid-3.3.12.tgz",
-            "integrity": "sha512-ZB9RH/39qpq5Vu6Y+NmUaFhQR6pp+M2Xt76XBnEwDaGcVAqhlvxrl3B2bKS5D3NH3QR76v3aSrKaF/Kiy7lEtQ==",
+            "version": "3.3.20",
+            "resolved": "https://registry.npmjs.org/nanoid/-/nanoid-3.3.20.tgz",
+            "integrity": "sha512-uKdg2G3GNCKQn9byYOpxbGqrT2fGO5KRt5J/8b3pok8rT6qxGWF6hxMyJiEYtAf+FVyYuD9hRaDqX5uPFYJ4ZQ==",
            "dev": true,
            "funding": [
                {
@@ -2645,9 +2659,9 @@
            }
        },
        "node_modules/path-to-regexp": {
-            "version": "8.3.0",
-            "resolved": "https://registry.npmjs.org/path-to-regexp/-/path-to-regexp-8.3.0.tgz",
-            "integrity": "sha512-7jdwVIRtsP8MYpdXSwOS0YdD0Du+qOoF/AEPIt88PcCFrZCzx41oxku1jD88hZBwbNUIEfpqvuhjFaMAqMTWnA==",
+            "version": "8.4.2",
+            "resolved": "https://registry.npmjs.org/path-to-regexp/-/path-to-regexp-8.4.2.tgz",
+            "integrity": "sha512-qRcuIdP69NPm4qbACK+aDogI5CBDMi1jKe0ry5rSQJz8JVLsC7jV8XpiJjGRLLol3N+R5ihGYcrPLTno6pAdBA==",
            "license": "MIT",
            "funding": {
                "type": "opencollective",
@@ -2691,9 +2705,9 @@
            }
        },
        "node_modules/postcss": {
-            "version": "8.5.15",
-            "resolved": "https://registry.npmjs.org/postcss/-/postcss-8.5.15.tgz",
-            "integrity": "sha512-FfR8sjd4em2T6fb3I2MwAJU7HWVMr9zba+enmQeeWFfCbm+UOC/0X4DS8XtpUTMwWMGbjKYP7xjfNekzyGmB3A==",
+            "version": "8.5.29",
+            "resolved": "https://registry.npmjs.org/postcss/-/postcss-8.5.29.tgz",
+            "integrity": "sha512-49cGhUbXj8Qenv0iTMxA1cFBzxXoctpC9Ujd77t1WcbJIr6nF/eI7g/8MgxrYldFRuAXvja7xQRwavoW7kgrxQ==",
            "dev": true,
            "funding": [
                {
@@ -2711,9 +2725,9 @@
            ],
            "license": "MIT",
            "dependencies": {
-                "nanoid": "^3.3.12",
+                "nanoid": "^3.3.19",
                "picocolors": "^1.1.1",
-                "source-map-js": "^1.2.1"
+                "source-map-js": "^1.2.2"
            },
            "engines": {
                "node": "^10 || ^12 || >=14"
@@ -2745,12 +2759,13 @@
            }
        },
        "node_modules/qs": {
-            "version": "6.14.0",
-            "resolved": "https://registry.npmjs.org/qs/-/qs-6.14.0.tgz",
-            "integrity": "sha512-YWWTjgABSKcvs/nWBi9PycY/JiPJqOD4JA6o9Sej2AtvSGarXxKC3OQSk4pAarbdQlKAh5D4FCQkJNkW+GAn3w==",
+            "version": "6.16.0",
+            "resolved": "https://registry.npmjs.org/qs/-/qs-6.16.0.tgz",
+            "integrity": "sha512-h6fhOIaRrID2CbEY2fqs+7t+UXZo+MLAnU5gRIq85uFtdiUPCdsApMlHhXogKVM4HM2DVbIjGNTTYH2OcmP1vA==",
            "license": "BSD-3-Clause",
            "dependencies": {
-                "side-channel": "^1.1.0"
+                "es-define-property": "^1.0.1",
+                "side-channel": "^1.1.1"
            },
            "engines": {
                "node": ">=0.6"
@@ -2945,14 +2960,14 @@
            }
        },
        "node_modules/side-channel": {
-            "version": "1.1.0",
-            "resolved": "https://registry.npmjs.org/side-channel/-/side-channel-1.1.0.tgz",
-            "integrity": "sha512-ZX99e6tRweoUXqR+VBrslhda51Nh5MTQwou5tnUDgbtyM0dBgmhEDtWGP/xbKn6hqfPRHujUNwz5fy/wbbhnpw==",
+            "version": "1.1.1",
+            "resolved": "https://registry.npmjs.org/side-channel/-/side-channel-1.1.1.tgz",
+            "integrity": "sha512-6x6dK6zJdpTzF4sQeNYxwtvBzf6Eg4GtlesS94HOvTudUeyK2WXAaIfmDgsyslYrRBeFIlsi54AYsFGUuhmvrQ==",
            "license": "MIT",
            "dependencies": {
                "es-errors": "^1.3.0",
-                "object-inspect": "^1.13.3",
-                "side-channel-list": "^1.0.0",
+                "object-inspect": "^1.13.4",
+                "side-channel-list": "^1.0.1",
                "side-channel-map": "^1.0.1",
                "side-channel-weakmap": "^1.0.2"
            },
@@ -2964,13 +2979,13 @@
            }
        },
        "node_modules/side-channel-list": {
-            "version": "1.0.0",
-            "resolved": "https://registry.npmjs.org/side-channel-list/-/side-channel-list-1.0.0.tgz",
-            "integrity": "sha512-FCLHtRD/gnpCiCHEiJLOwdmFP+wzCmDEkc9y7NsYxeF4u7Btsn1ZuwgwJGxImImHicJArLP4R0yX4c2KCrMrTA==",
+            "version": "1.0.1",
+            "resolved": "https://registry.npmjs.org/side-channel-list/-/side-channel-list-1.0.1.tgz",
+            "integrity": "sha512-mjn/0bi/oUURjc5Xl7IaWi/OJJJumuoJFQJfDDyO46+hBWsfaVM65TBHq2eoZBhzl9EchxOijpkbRC8SVBQU0w==",
            "license": "MIT",
            "dependencies": {
                "es-errors": "^1.3.0",
-                "object-inspect": "^1.13.3"
+                "object-inspect": "^1.13.4"
            },
            "engines": {
                "node": ">= 0.4"
@@ -3024,9 +3039,9 @@
            "license": "ISC"
        },
        "node_modules/source-map-js": {
-            "version": "1.2.1",
-            "resolved": "https://registry.npmjs.org/source-map-js/-/source-map-js-1.2.1.tgz",
-            "integrity": "sha512-UXWMKhLOwVKb728IUtQPXxfYU+usdybtUrK/8uGE8CQMvrhOpwvzDBwj0QhSL7MQc7vIsISBG8VQ8+IDQxpfQA==",
+            "version": "1.2.2",
+            "resolved": "https://registry.npmjs.org/source-map-js/-/source-map-js-1.2.2.tgz",
+            "integrity": "sha512-KGj/8Y43x35aZVDtt+J4mK1hoLGHULMYfSkODJNQjNDC3oW1PqPoxMwo0pLUsWM/UEGzON/NxeHywEfNXNP3Vw==",
            "dev": true,
            "license": "BSD-3-Clause",
            "engines": {
@@ -3137,17 +3152,34 @@
            }
        },
        "node_modules/type-is": {
-            "version": "2.0.1",
-            "resolved": "https://registry.npmjs.org/type-is/-/type-is-2.0.1.tgz",
-            "integrity": "sha512-OZs6gsjF4vMp32qrCbiVSkrFmXtG/AZhY3t0iAMrMBiAZyV9oALtXO8hsrHbMXF9x6L3grlFuwW2oAz7cav+Gw==",
+            "version": "2.1.0",
+            "resolved": "https://registry.npmjs.org/type-is/-/type-is-2.1.0.tgz",
+            "integrity": "sha512-faYHw0anBbc/kWF3zFTEnxSFOAGUX9GFbOBthvDdLsIlEoWOFOtS0zgCiQYwIskL9iGXZL3kAXD8OoZ4GmMATA==",
            "license": "MIT",
            "dependencies": {
-                "content-type": "^1.0.5",
+                "content-type": "^2.0.0",
                "media-typer": "^1.1.0",
                "mime-types": "^3.0.0"
            },
            "engines": {
-                "node": ">= 0.6"
+                "node": ">= 18"
+            },
+            "funding": {
+                "type": "opencollective",
+                "url": "https://opencollective.com/express"
+            }
+        },
+        "node_modules/type-is/node_modules/content-type": {
+            "version": "2.1.0",
+            "resolved": "https://registry.npmjs.org/content-type/-/content-type-2.1.0.tgz",
+            "integrity": "sha512-mj7UPXE0jaqaOsukNZRUEfEi2AcL7C/vwmwcHV0O97eO1E1pxBZuyjlZrx5seTaNBg1U6+o35wpa35Qfcc+7ag==",
+            "license": "MIT",
+            "engines": {
+                "node": ">=18"
+            },
+            "funding": {
+                "type": "opencollective",
+                "url": "https://opencollective.com/express"
            }
        },
        "node_modules/typescript": {
@@ -27,9 +27,19 @@ function getLocale(request: NextRequest): string | undefined {
 export function proxy(request: NextRequest) {
    const pathname = request.nextUrl.pathname

-    // Skip API routes, static files, and Next.js internals
+    if (pathname.startsWith("/api/")) {
+        // With ORIGIN_SECRET set, API calls must come through the CDN that
+        // adds this header. A call straight to the origin could fake the
+        // CLIENT_IP_HEADER and get a fresh quota for every made-up IP.
+        const secret = process.env.ORIGIN_SECRET
+        if (secret && request.headers.get("x-origin-secret") !== secret) {
+            return NextResponse.json({ error: "Forbidden" }, { status: 403 })
+        }
+        return
+    }
+
+    // Skip static files and Next.js internals
    if (
-        pathname.startsWith("/api/") ||
        pathname.startsWith("/_next/") ||
        pathname.startsWith("/drawio") ||
        pathname.includes("/favicon") ||
@@ -58,6 +68,9 @@ export function proxy(request: NextRequest) {
 }

 export const config = {
-    // Matcher ignoring `/_next/` and `/api/`
-    matcher: ["/((?!api|_next/static|_next/image|favicon.ico).*)"],
+    // API routes (for ORIGIN_SECRET), and pages without `/_next/` assets
+    matcher: [
+        "/api/:path*",
+        "/((?!api|_next/static|_next/image|favicon.ico).*)",
+    ],
 }
@@ -75,3 +75,30 @@ test("a provider rate limit is not shown as this site's quota", async ({
    // The site's own tokens-per-minute toast
    await expect(page.getByText("Rate limit reached")).toHaveCount(0)
 })
+
+test("a refused server key shows only the quota hint and a settings button", async ({
+    page,
+}) => {
+    // What the chat route streams when the server's key gets a 403, e.g.
+    // after a daily spend cap blocked it
+    const errorText = JSON.stringify({
+        type: "provider",
+        code: "server_key_forbidden",
+        message: "",
+    })
+    await chatWith(page, {
+        status: 200,
+        contentType: "text/event-stream",
+        body: `data: {"type":"start"}\n\ndata: ${JSON.stringify({ type: "error", errorText })}\n\ndata: [DONE]\n\n`,
+    })
+    await expect(
+        page.getByText("Today's free quota is used up", { exact: false }),
+    ).toBeVisible({ timeout: 15000 })
+    await expect(page.getByText("The provider returned an error")).toHaveCount(
+        0,
+    )
+    await page.getByRole("button", { name: "Open model settings" }).click()
+    await expect(
+        page.getByRole("dialog", { name: "AI Model Configuration" }),
+    ).toBeVisible()
+})
@@ -434,7 +434,7 @@ describe("Ollama API key security", () => {

        expect(createOllamaMock).toHaveBeenCalledWith(
            expect.objectContaining({
-                baseURL: "https://my-ollama.com",
+                baseURL: "https://my-ollama.com/api",
                headers: { Authorization: "Bearer client-key" },
            }),
        )
@@ -448,7 +448,7 @@ describe("Ollama API key security", () => {

        expect(createOllamaMock).toHaveBeenCalledWith(
            expect.objectContaining({
-                baseURL: "https://cloud.ollama.com",
+                baseURL: "https://cloud.ollama.com/api",
                headers: { Authorization: "Bearer server-key" },
            }),
        )
@@ -483,7 +483,24 @@ describe("Ollama API key security", () => {

        expect(createOllamaMock).toHaveBeenCalledTimes(1)
        const callArgs = createOllamaMock.mock.calls[0][0]
-        expect(callArgs.baseURL).toBe("https://my-ollama.com")
+        expect(callArgs.baseURL).toBe("https://my-ollama.com/api")
        expect(callArgs).not.toHaveProperty("headers")
    })
+
+    it("sends chat to Ollama's /api for a server address or a /v1 URL", () => {
+        delete process.env.OLLAMA_API_KEY
+
+        for (const baseUrl of [
+            "http://localhost:11434",
+            "http://localhost:11434/",
+            "http://localhost:11434/v1",
+            "http://localhost:11434/api",
+        ]) {
+            createOllamaMock.mockClear()
+            getAIModel({ provider: "ollama", baseUrl, modelId: "llama3.2" })
+            expect(createOllamaMock.mock.calls[0][0].baseURL).toBe(
+                "http://localhost:11434/api",
+            )
+        }
+    })
 })
@@ -1,5 +1,9 @@
 import { describe, expect, it } from "vitest"
-import { chatRequestUrl, normalizeBaseUrl } from "@/lib/types/model-config"
+import {
+    chatRequestUrl,
+    normalizeBaseUrl,
+    ollamaApiUrl,
+} from "@/lib/types/model-config"

 describe("normalizeBaseUrl", () => {
    it("drops spaces, trailing slashes and a pasted endpoint path", () => {
@@ -32,6 +36,9 @@ describe("chatRequestUrl", () => {
        expect(
            chatRequestUrl("anthropic", "https://proxy.example.com/v1"),
        ).toBe("https://proxy.example.com/v1/messages")
+        expect(chatRequestUrl("ollama", "http://localhost:11434")).toBe(
+            "http://localhost:11434/api/chat",
+        )
    })

    it("stays out of the way for SDKs that build their own paths", () => {
@@ -40,3 +47,21 @@ describe("chatRequestUrl", () => {
        expect(chatRequestUrl("glm", "  ")).toBeNull()
    })
 })
+
+describe("ollamaApiUrl", () => {
+    it("points at Ollama's /api whatever form the address takes", () => {
+        for (const url of [
+            "http://localhost:11434",
+            "http://localhost:11434/",
+            "http://localhost:11434/api",
+            "http://localhost:11434/api/",
+            "http://localhost:11434/v1",
+            "http://localhost:11434/v1/chat/completions",
+        ]) {
+            expect(ollamaApiUrl(url)).toBe("http://localhost:11434/api")
+        }
+        expect(ollamaApiUrl("https://ollama.com/api")).toBe(
+            "https://ollama.com/api",
+        )
+    })
+})
@@ -139,7 +139,8 @@ describe("provider error texts in the stream", () => {
        )
        const message = await streamedError({})
        expect(message).not.toMatch(/org-operator/)
-        expect(message).toBe("The provider returned an error.")
+        // A 403 on the server's key gets its own hint and no message
+        expect(message).toBe("")
    })
 })

@@ -0,0 +1,63 @@
+import { NextRequest } from "next/server"
+import { afterEach, describe, expect, it } from "vitest"
+import { getUserIdFromRequest } from "@/lib/user-id"
+import { proxy } from "@/proxy"
+
+const idFor = (ip: string) => `user-${Buffer.from(ip).toString("base64url")}`
+
+afterEach(() => {
+    delete process.env.CLIENT_IP_HEADER
+    delete process.env.ORIGIN_SECRET
+})
+
+describe("getUserIdFromRequest", () => {
+    const req = new Request("http://localhost/api/chat", {
+        headers: {
+            "x-forwarded-for": "203.0.113.9, 198.51.100.7",
+            "cf-connecting-ip": "198.51.100.7",
+        },
+    })
+
+    it("uses the first X-Forwarded-For entry by default", () => {
+        expect(getUserIdFromRequest(req)).toBe(idFor("203.0.113.9"))
+    })
+
+    it("uses CLIENT_IP_HEADER when set", () => {
+        process.env.CLIENT_IP_HEADER = "cf-connecting-ip"
+        expect(getUserIdFromRequest(req)).toBe(idFor("198.51.100.7"))
+    })
+
+    it("is anonymous when the configured header is missing", () => {
+        process.env.CLIENT_IP_HEADER = "cf-connecting-ip"
+        expect(
+            getUserIdFromRequest(new Request("http://localhost/api/chat")),
+        ).toBe("anonymous")
+    })
+})
+
+describe("ORIGIN_SECRET", () => {
+    const call = (path: string, secret?: string) =>
+        proxy(
+            new NextRequest(`http://localhost${path}`, {
+                headers: secret ? { "x-origin-secret": secret } : {},
+            }),
+        )
+
+    it("lets every API call through when unset", () => {
+        expect(call("/api/chat")).toBeUndefined()
+    })
+
+    it("refuses API calls without the right header", async () => {
+        process.env.ORIGIN_SECRET = "s3cret"
+        for (const res of [call("/api/chat"), call("/api/chat", "wrong")]) {
+            expect(res?.status).toBe(403)
+        }
+        expect(call("/api/chat", "s3cret")).toBeUndefined()
+    })
+
+    it("leaves pages alone, such as the health check on /", () => {
+        process.env.ORIGIN_SECRET = "s3cret"
+        expect(call("/")?.status).toBe(307)
+        expect(call("/en")).toBeUndefined()
+    })
+})
@@ -215,11 +215,29 @@ describe("streamErrorText", () => {
            "User: arn:aws:sts::123456789012:assumed-role/app/s is not authorized to perform: bedrock:InvokeModel",
        )
        const hidden = JSON.parse(streamErrorText(error, true))
-        expect(hidden.code).toBe("forbidden")
        expect(hidden.message).not.toMatch(/arn:aws|123456789012/)
        expect(JSON.parse(streamErrorText(error)).message).toMatch(
            /not authorized/,
        )
+        const throttled = JSON.parse(
+            streamErrorText(apiError(429, "Too many tokens"), true),
+        )
+        expect(throttled).toEqual({
+            type: "provider",
+            code: "rate_limited",
+            message: "The provider returned an error.",
+        })
+    })
+
+    it("names a 403 on the server's keys, e.g. a spend cap blocked them", () => {
+        const error = apiError(403, "explicit deny in an identity-based policy")
+        expect(JSON.parse(streamErrorText(error, true))).toEqual({
+            type: "provider",
+            code: "server_key_forbidden",
+            message: "",
+        })
+        // On the user's own key it stays a plain refusal
+        expect(JSON.parse(streamErrorText(error)).code).toBe("forbidden")
    })

    it("classifies a provider error", () => {
Author	SHA1	Message	Date
Dayuan Jiang	18a20aa1ca	feat(api): count the quota by the CDN's client IP and refuse direct calls (#956 ) Two optional settings for deployments behind a CDN such as Cloudflare. CLIENT_IP_HEADER names the header that holds the visitor's real IP (cf-connecting-ip on Cloudflare). The per-IP daily quota used the first X-Forwarded-For entry, which visitors can set to anything, so a made-up IP on every request got a fresh quota. ORIGIN_SECRET makes proxy.ts refuse /api requests whose X-Origin-Secret header does not match. The CDN adds the header, so a call that skips the CDN, and could fake the IP header, gets 403. Pages are not checked, which keeps health checks on / working. Both are unset by default, and nothing changes then.	2026-10-06 10:32:43 +09:00
dependabot[bot]	802f0ada9f	fix(deps): update vulnerable dependencies with npm audit fix (#804 ) Root: 36 vulnerable packages to 9, no critical left (next 16.3.8, electron 39.8.10). MCP server: 11 to 0.	2026-10-06 09:56:06 +09:00
Marvelous Ikponmwosa	257a4bca06	docs: explain how to use LM Studio with the OpenAI provider (#897 ) Set the base URL to http://localhost:1234/v1 and use any non-empty API key.	2026-10-06 09:55:26 +09:00
Dayuan Jiang	83f190e1cd	feat(chat): show a quota hint when the server's key is refused (#953 ) On the server's own credentials a provider 403 now gets its own code, server_key_forbidden, with a hint in all four languages: today's free quota is used up, it resets tomorrow, and users can add their own key in model settings. The generic "The provider returned an error." line is left out for this code. A daily spend cap that blocks a shared key makes every call return 403. The old hint said the key may lack access to the model or region, which points users at a setting they cannot change. A 403 on the user's own key keeps the old hint and the provider's text.	2026-10-06 09:49:48 +09:00
Dayuan Jiang	8639779a23	fix(ollama): send chat requests to the /api path (#954 ) The Ollama SDK appends /chat to the base URL, and Ollama serves chat at /api/chat. The model list already added the missing /api, so with "http://localhost:11434" (the address our docs showed) models were listed but every chat request went to /chat and got a 404. An OpenAI-style ".../v1" address went to /v1/chat. ollamaApiUrl() turns the server address, ".../v1" and ".../api" into ".../api". Chat, the model list and the settings dialog's request URL hint all use it. The docs now show http://localhost:11434/api, which also works on released versions.	2026-10-06 09:37:05 +09:00