@astrasyncai/verification-gateway 5.21.1 → 5.22.0

package/dist/edge-core/index.mjs

@@ -1,5 +1,5 @@
 // src/version.ts
-var SDK_VERSION = "5.21.1";
+var SDK_VERSION = "5.22.0";
 
 // src/http.ts
 var SDK_USER_AGENT = `astrasync-sdk/${SDK_VERSION}`;
@@ -98,7 +98,11 @@ var PLATFORM_HEADER_NAMES = /* @__PURE__ */ new Set([
   "x-goog-api-client",
   "user-agent",
   "x-agent-card-url",
-  "x-agent-provider"
+  "x-agent-provider",
+  // Round 31 — Web Bot Auth's Signature-Agent names the signing agent's
+  // directory host (a public URL, never a secret). It attributes a signed
+  // agent even when its UA is stock Chrome.
+  "signature-agent"
 ]);
 var PLATFORM_HEADER_PREFIXES = [
   "x-goog-",
@@ -229,7 +233,8 @@ var PLATFORM_AGENT_SIGNATURES = [
     uaPatterns: [/claude/i, /anthropic/i],
     agentCardPatterns: [/anthropic\.com/i, /claude\.ai/i],
     apiKeyFormatPatterns: [/^sk-ant/i],
-    headerPatterns: [/^anthropic-version/i, /^anthropic-beta/i, /^x-anthropic-/i]
+    headerPatterns: [/^anthropic-version/i, /^anthropic-beta/i, /^x-anthropic-/i],
+    wafLabelPatterns: [/\bclaude/i, /\banthropic/i]
   },
   {
     vendor: "chatgpt",
@@ -240,7 +245,14 @@ var PLATFORM_AGENT_SIGNATURES = [
     uaPatterns: [/chatgpt/i, /openai/i, /gpt-?\d/i, /\bGPTBot\b/i, /\bOAI-SearchBot\b/i],
     agentCardPatterns: [/openai\.com/i, /chatgpt\.com/i],
     apiKeyFormatPatterns: [/^sk-proj/i, /^sk-svcacct/i],
-    headerPatterns: [/^openai-organization/i, /^openai-project/i, /^openai-version/i]
+    headerPatterns: [
+      /^openai-organization/i,
+      /^openai-project/i,
+      /^openai-version/i,
+      // ChatGPT agent signs with Web Bot Auth under this directory host.
+      /^signature-agent: "?https:\/\/chatgpt\.com/i
+    ],
+    wafLabelPatterns: [/\bgptbot\b/i, /\bchatgpt/i, /\boai-searchbot\b/i, /\bopenai/i]
   },
   {
     vendor: "gemini",
@@ -261,7 +273,8 @@ var PLATFORM_AGENT_SIGNATURES = [
     ],
     agentCardPatterns: [/gemini\.google\.com/i, /ai\.google\.dev/i],
     apiKeyFormatPatterns: [/^aiza/i],
-    headerPatterns: [/^x-goog-user-project/i, /^x-goog-api-client/i]
+    headerPatterns: [/^x-goog-user-project/i, /^x-goog-api-client/i],
+    wafLabelPatterns: [/\bgoogle-extended\b/i, /\bgoogleother\b/i, /\bgemini/i]
   },
   {
     vendor: "cursor",
@@ -280,7 +293,31 @@ var PLATFORM_AGENT_SIGNATURES = [
     displayName: "Perplexity",
     uaPatterns: [/perplexity/i],
     agentCardPatterns: [/perplexity\.ai/i],
-    apiKeyFormatPatterns: [/^pplx-/i]
+    apiKeyFormatPatterns: [/^pplx-/i],
+    wafLabelPatterns: [/\bperplexity/i]
+  },
+  // Round 30.1: xAI's documented crawlers (GrokBot/1.0, xAI-Grok/1.0,
+  // Grok-DeepSearch/1.0). Anchored, versioned tokens — never in a stock UA.
+  {
+    vendor: "grok",
+    displayName: "xAI Grok",
+    uaPatterns: [/\bGrokBot\//i, /\bxAI-Grok\//i, /\bGrok-DeepSearch\//i],
+    agentCardPatterns: [/\bx\.ai\b/i, /grok\.com/i],
+    apiKeyFormatPatterns: [/^xai-/i],
+    wafLabelPatterns: [/\bgrok/i, /\bxai\b/i]
+  },
+  // Round 30.1: Meta AI's index and fetch crawlers. facebookexternalhit
+  // (link previews) is deliberately NOT here — it stays a generic crawler.
+  {
+    vendor: "meta-ai",
+    displayName: "Meta AI",
+    uaPatterns: [/\bMeta-WebIndexer\b/i, /\bMeta-ExternalFetcher\b/i],
+    agentCardPatterns: [/meta\.ai/i],
+    wafLabelPatterns: [
+      /\bmeta-webindexer\b/i,
+      /\bmeta-externalfetcher\b/i,
+      /\bmeta-externalagent\b/i
+    ]
   },
   // Agentic browsers — versioned-token patterns ONLY (a stock Chrome UA must
   // never match). Distinct vendor keys (not 'chatgpt'/'perplexity'): the
@@ -328,6 +365,7 @@ function matchPlatformSignature(signatures, input) {
   const apiKeyFormat = input.apiKeyFormat ?? "";
   const ja4 = input.ja4 ?? "";
   const asn = input.asn ?? "";
+  const wafLabels = input.wafLabels ?? [];
   const headerLines = [];
   if (input.platformHeaders) {
     for (const [name, value] of Object.entries(input.platformHeaders)) {
@@ -341,7 +379,8 @@ function matchPlatformSignature(signatures, input) {
     const headerMatch = headerLines.length > 0 && sig.headerPatterns?.some((p) => headerLines.some((line) => p.test(line)));
     const ja4Match = ja4.length > 0 && sig.ja4Patterns?.some((p) => p.test(ja4));
     const asnMatch = asn.length > 0 && sig.asnList?.includes(asn);
-    if (uaMatch || cardMatch || keyMatch || headerMatch || ja4Match || asnMatch) {
+    const wafMatch = wafLabels.length > 0 && sig.wafLabelPatterns?.some((p) => wafLabels.some((label) => p.test(label)));
+    if (uaMatch || cardMatch || keyMatch || headerMatch || ja4Match || asnMatch || wafMatch) {
       const uaBase = ua.split(/[\s/]/)[0]?.toLowerCase() ?? "";
       const cardHost = (() => {
         try {
@@ -350,7 +389,7 @@ function matchPlatformSignature(signatures, input) {
           return "";
         }
       })();
-      const keyBasis = uaBase || cardHost || apiKeyFormat || ja4 || asn && `asn${asn}` || "unknown";
+      const keyBasis = uaBase || cardHost || apiKeyFormat || ja4 || asn && `asn${asn}` || wafMatch && `waf:${wafLabels[0]?.toLowerCase()}` || "unknown";
       return {
         vendor: sig.vendor,
         fingerprintKey: `${sig.vendor}:${keyBasis}`,
@@ -1863,7 +1902,7 @@ function resetBeaconBuffer(options) {
   beaconBuffer = new BeaconBuffer(options);
   return beaconBuffer;
 }
-async function emitBeacon(options, req, classification, budgetMs, queryValueAllowlist, apiKey) {
+async function emitBeacon(options, req, classification, budgetMs, queryValueAllowlist, apiKey, edgeOutcome) {
   const attemptId = extractAttemptId(req);
   const declaredSource = normalizeDeclaredSource(headerValue(req, "x-astra-source"));
   const userAgent = headerValue(req, "user-agent");
@@ -1890,7 +1929,10 @@ async function emitBeacon(options, req, classification, budgetMs, queryValueAllo
     // caller.
     observedMetadata: buildObservedMetadata(req, queryValueAllowlist),
     // Capture time — batched delivery skews createdAt by the flush delay.
-    observedAt: (/* @__PURE__ */ new Date()).toISOString()
+    observedAt: (/* @__PURE__ */ new Date()).toISOString(),
+    // Round 31 — the edge's own verdict, so enforce-mode denies are
+    // recorded as denies rather than passes.
+    ...edgeOutcome && { edgeDecision: edgeOutcome.decision, edgeMode: edgeOutcome.mode }
   };
   for (const k of Object.keys(item)) if (item[k] === void 0) delete item[k];
   const buffer = getBeaconBuffer();
@@ -1910,7 +1952,8 @@ async function emitBeacon(options, req, classification, budgetMs, queryValueAllo
       userAgent ?? "",
       req.method,
       req.uri,
-      attemptId ?? ""
+      attemptId ?? "",
+      edgeOutcome?.decision ?? ""
     ].join("\0") : void 0
   );
   const flushing = buffer.flush();
@@ -2084,12 +2127,15 @@ async function runTier(options, req, classification, policy, apiKey, capture) {
           }
           return outcomeFromVerifyResult(classification, result);
         }
-        await emitBeacon(options, req, classification, beaconMs, queryValueAllowlist, apiKey);
         const outcome = baseOutcome(classification);
         if (policy.mode === "enforce" && policy.depth !== "classify") {
           outcome.decision = "deny";
           outcome.reasons = ["agent is not registered with AstraSync"];
         }
+        await emitBeacon(options, req, classification, beaconMs, queryValueAllowlist, apiKey, {
+          decision: outcome.decision === "deny" ? "deny" : "allow",
+          mode: policy.mode
+        });
         return outcome;
       }
       case "anonymous-bot": {
@@ -2100,7 +2146,8 @@ async function runTier(options, req, classification, policy, apiKey, capture) {
             { ...classification, protocol: classification.protocol ?? "ua-heuristic" },
             beaconMs,
             queryValueAllowlist,
-            apiKey
+            apiKey,
+            { decision: "allow", mode: policy.mode }
           );
         }
         return baseOutcome(classification);