milieu-cli 0.1.0

package/dist/bridges/reachability/https-check.js

@@ -0,0 +1,38 @@
+import { httpGet } from "../../utils/http-client.js";
+const ABORT_ERRORS = new Set(["dns", "connection_refused", "ssl_error"]);
+/**
+ * Check HTTPS availability via HEAD request to https://<domain>.
+ *
+ * Any response (even 4xx/5xx) means HTTPS works.
+ * Abort-worthy errors: dns, connection_refused, ssl_error.
+ */
+export async function checkHttps(domain, timeout) {
+    const result = await httpGet("https://" + domain, {
+        method: "HEAD",
+        timeout,
+    });
+    if (result.ok) {
+        return {
+            check: {
+                id: "https_available",
+                label: "HTTPS Available",
+                status: "pass",
+                detail: "HTTPS connection successful",
+            },
+            abort: false,
+        };
+    }
+    const { kind, message } = result.error;
+    const abort = ABORT_ERRORS.has(kind);
+    return {
+        check: {
+            id: "https_available",
+            label: "HTTPS Available",
+            status: "fail",
+            detail: message,
+        },
+        abort,
+        abortReason: abort ? kind : undefined,
+    };
+}
+//# sourceMappingURL=https-check.js.map

package/dist/bridges/reachability/https-check.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"https-check.js","sourceRoot":"","sources":["../../../src/bridges/reachability/https-check.ts"],"names":[],"mappings":"AACA,OAAO,EAAE,OAAO,EAAE,MAAM,4BAA4B,CAAC;AAQrD,MAAM,YAAY,GAAG,IAAI,GAAG,CAAC,CAAC,KAAK,EAAE,oBAAoB,EAAE,WAAW,CAAC,CAAC,CAAC;AAEzE;;;;;GAKG;AACH,MAAM,CAAC,KAAK,UAAU,UAAU,CAC9B,MAAc,EACd,OAAgB;IAEhB,MAAM,MAAM,GAAG,MAAM,OAAO,CAAC,UAAU,GAAG,MAAM,EAAE;QAChD,MAAM,EAAE,MAAM;QACd,OAAO;KACR,CAAC,CAAC;IAEH,IAAI,MAAM,CAAC,EAAE,EAAE,CAAC;QACd,OAAO;YACL,KAAK,EAAE;gBACL,EAAE,EAAE,iBAAiB;gBACrB,KAAK,EAAE,iBAAiB;gBACxB,MAAM,EAAE,MAAM;gBACd,MAAM,EAAE,6BAA6B;aACtC;YACD,KAAK,EAAE,KAAK;SACb,CAAC;IACJ,CAAC;IAED,MAAM,EAAE,IAAI,EAAE,OAAO,EAAE,GAAG,MAAM,CAAC,KAAK,CAAC;IACvC,MAAM,KAAK,GAAG,YAAY,CAAC,GAAG,CAAC,IAAI,CAAC,CAAC;IAErC,OAAO;QACL,KAAK,EAAE;YACL,EAAE,EAAE,iBAAiB;YACrB,KAAK,EAAE,iBAAiB;YACxB,MAAM,EAAE,MAAM;YACd,MAAM,EAAE,OAAO;SAChB;QACD,KAAK;QACL,WAAW,EAAE,KAAK,CAAC,CAAC,CAAC,IAAI,CAAC,CAAC,CAAC,SAAS;KACtC,CAAC;AACJ,CAAC"}

package/dist/bridges/reachability/index.d.ts

@@ -0,0 +1,13 @@
+import type { BridgeResult, ScanContext } from "../../core/types.js";
+/**
+ * Run Bridge 1: Reachability.
+ *
+ * Makes 3 HTTP calls:
+ *   1. HEAD https://<domain> (HTTPS availability)
+ *   2. GET  <baseUrl> (page content for meta robots)
+ *   3. GET  https://<domain>/robots.txt (robots.txt fetch)
+ *
+ * Aborts on dns/connection_refused/ssl_error from HTTPS check.
+ */
+export declare function runReachabilityBridge(ctx: ScanContext): Promise<BridgeResult>;
+//# sourceMappingURL=index.d.ts.map

package/dist/bridges/reachability/index.d.ts.map

@@ -0,0 +1 @@
+{"version":3,"file":"index.d.ts","sourceRoot":"","sources":["../../../src/bridges/reachability/index.ts"],"names":[],"mappings":"AAAA,OAAO,KAAK,EAAE,YAAY,EAAS,WAAW,EAAE,MAAM,qBAAqB,CAAC;AAyC5E;;;;;;;;;GASG;AACH,wBAAsB,qBAAqB,CACzC,GAAG,EAAE,WAAW,GACf,OAAO,CAAC,YAAY,CAAC,CAwFvB"}

package/dist/bridges/reachability/index.js

@@ -0,0 +1,115 @@
+import { httpGet } from "../../utils/http-client.js";
+import { checkHttps } from "./https-check.js";
+import { checkHttpStatus } from "./http-status.js";
+import { checkRobotsTxt } from "./robots-txt.js";
+import { evaluateCrawlerPolicies } from "./crawler-policy.js";
+import { checkMetaRobots, checkXRobotsTag } from "./meta-robots.js";
+/**
+ * Calculate bridge score from check results.
+ * - Pass = 1 point, Partial = 0.5 points, Fail/Error = 0 points
+ * - Checks with data.policy === "skip" excluded from both numerator and denominator
+ */
+function calculateScore(checks) {
+    let points = 0;
+    let maxPoints = 0;
+    for (const check of checks) {
+        // Skip checks excluded from scoring (e.g., crawler policy with no robots.txt)
+        if (check.data &&
+            check.data.policy === "skip") {
+            continue;
+        }
+        maxPoints += 1;
+        if (check.status === "pass")
+            points += 1;
+        else if (check.status === "partial")
+            points += 0.5;
+        // fail and error = 0 points
+    }
+    const score = maxPoints === 0 ? 0 : Math.round((points / maxPoints) * 100);
+    const scoreLabel = score >= 80 ? "pass" : score >= 40 ? "partial" : "fail";
+    return { score, scoreLabel };
+}
+/**
+ * Run Bridge 1: Reachability.
+ *
+ * Makes 3 HTTP calls:
+ *   1. HEAD https://<domain> (HTTPS availability)
+ *   2. GET  <baseUrl> (page content for meta robots)
+ *   3. GET  https://<domain>/robots.txt (robots.txt fetch)
+ *
+ * Aborts on dns/connection_refused/ssl_error from HTTPS check.
+ */
+export async function runReachabilityBridge(ctx) {
+    const start = performance.now();
+    // 1. HTTPS check (HEAD request)
+    const httpsResult = await checkHttps(ctx.domain, ctx.options.timeout);
+    // Abort on fatal HTTPS errors
+    if (httpsResult.abort) {
+        return {
+            id: 1,
+            name: "Reachability",
+            status: "evaluated",
+            score: 0,
+            scoreLabel: "fail",
+            checks: [httpsResult.check],
+            durationMs: Math.round(performance.now() - start),
+            abort: true,
+            abortReason: httpsResult.abortReason,
+        };
+    }
+    // 2. Page GET (uses normalized baseUrl)
+    const pageResponse = await httpGet(ctx.baseUrl, {
+        timeout: ctx.options.timeout,
+    });
+    // Store page body for Bridge 2 (JSON-LD, Schema.org extraction)
+    if (pageResponse.ok) {
+        ctx.shared.pageBody = pageResponse.body;
+        ctx.shared.pageHeaders = pageResponse.headers;
+    }
+    // 3. HTTP status check (no HTTP call -- uses pageResponse)
+    const httpStatusCheck = checkHttpStatus(pageResponse);
+    // 4. robots.txt fetch + parse
+    const robotsResult = await checkRobotsTxt(ctx.domain, ctx.options.timeout);
+    // 5. Crawler policies (uses parsed robots.txt data)
+    let targetPath;
+    try {
+        targetPath = new URL(ctx.baseUrl).pathname;
+    }
+    catch {
+        targetPath = "/";
+    }
+    const crawlerChecks = evaluateCrawlerPolicies(robotsResult.parsed, targetPath);
+    // 6. Meta robots (uses page response)
+    let metaRobotsCheck;
+    let xRobotsCheck;
+    if (pageResponse.ok) {
+        metaRobotsCheck = checkMetaRobots(pageResponse.body);
+        xRobotsCheck = checkXRobotsTag(pageResponse.headers);
+    }
+    else {
+        // Page unavailable -- pass empty content (absence of restrictive tags = pass)
+        metaRobotsCheck = checkMetaRobots("");
+        xRobotsCheck = checkXRobotsTag({});
+    }
+    // 7. Collect all checks
+    const checks = [
+        httpsResult.check,
+        httpStatusCheck,
+        robotsResult.check,
+        ...crawlerChecks,
+        metaRobotsCheck,
+        xRobotsCheck,
+    ];
+    // 8. Calculate score
+    const { score, scoreLabel } = calculateScore(checks);
+    return {
+        id: 1,
+        name: "Reachability",
+        status: "evaluated",
+        score,
+        scoreLabel,
+        checks,
+        durationMs: Math.round(performance.now() - start),
+    };
+}
+//# sourceMappingURL=index.js.map

package/dist/bridges/reachability/index.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"index.js","sourceRoot":"","sources":["../../../src/bridges/reachability/index.ts"],"names":[],"mappings":"AACA,OAAO,EAAE,OAAO,EAAE,MAAM,4BAA4B,CAAC;AACrD,OAAO,EAAE,UAAU,EAAE,MAAM,kBAAkB,CAAC;AAC9C,OAAO,EAAE,eAAe,EAAE,MAAM,kBAAkB,CAAC;AACnD,OAAO,EAAE,cAAc,EAAE,MAAM,iBAAiB,CAAC;AACjD,OAAO,EAAE,uBAAuB,EAAE,MAAM,qBAAqB,CAAC;AAC9D,OAAO,EAAE,eAAe,EAAE,eAAe,EAAE,MAAM,kBAAkB,CAAC;AAEpE;;;;GAIG;AACH,SAAS,cAAc,CAAC,MAAe;IAIrC,IAAI,MAAM,GAAG,CAAC,CAAC;IACf,IAAI,SAAS,GAAG,CAAC,CAAC;IAElB,KAAK,MAAM,KAAK,IAAI,MAAM,EAAE,CAAC;QAC3B,8EAA8E;QAC9E,IACE,KAAK,CAAC,IAAI;YACT,KAAK,CAAC,IAAgC,CAAC,MAAM,KAAK,MAAM,EACzD,CAAC;YACD,SAAS;QACX,CAAC;QAED,SAAS,IAAI,CAAC,CAAC;QACf,IAAI,KAAK,CAAC,MAAM,KAAK,MAAM;YAAE,MAAM,IAAI,CAAC,CAAC;aACpC,IAAI,KAAK,CAAC,MAAM,KAAK,SAAS;YAAE,MAAM,IAAI,GAAG,CAAC;QACnD,4BAA4B;IAC9B,CAAC;IAED,MAAM,KAAK,GAAG,SAAS,KAAK,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,CAAC,IAAI,CAAC,KAAK,CAAC,CAAC,MAAM,GAAG,SAAS,CAAC,GAAG,GAAG,CAAC,CAAC;IAC3E,MAAM,UAAU,GACd,KAAK,IAAI,EAAE,CAAC,CAAC,CAAC,MAAM,CAAC,CAAC,CAAC,KAAK,IAAI,EAAE,CAAC,CAAC,CAAC,SAAS,CAAC,CAAC,CAAC,MAAM,CAAC;IAC1D,OAAO,EAAE,KAAK,EAAE,UAAU,EAAE,CAAC;AAC/B,CAAC;AAED;;;;;;;;;GASG;AACH,MAAM,CAAC,KAAK,UAAU,qBAAqB,CACzC,GAAgB;IAEhB,MAAM,KAAK,GAAG,WAAW,CAAC,GAAG,EAAE,CAAC;IAEhC,gCAAgC;IAChC,MAAM,WAAW,GAAG,MAAM,UAAU,CAAC,GAAG,CAAC,MAAM,EAAE,GAAG,CAAC,OAAO,CAAC,OAAO,CAAC,CAAC;IAEtE,8BAA8B;IAC9B,IAAI,WAAW,CAAC,KAAK,EAAE,CAAC;QACtB,OAAO;YACL,EAAE,EAAE,CAAC;YACL,IAAI,EAAE,cAAc;YACpB,MAAM,EAAE,WAAW;YACnB,KAAK,EAAE,CAAC;YACR,UAAU,EAAE,MAAM;YAClB,MAAM,EAAE,CAAC,WAAW,CAAC,KAAK,CAAC;YAC3B,UAAU,EAAE,IAAI,CAAC,KAAK,CAAC,WAAW,CAAC,GAAG,EAAE,GAAG,KAAK,CAAC;YACjD,KAAK,EAAE,IAAI;YACX,WAAW,EAAE,WAAW,CAAC,WAAW;SACrC,CAAC;IACJ,CAAC;IAED,wCAAwC;IACxC,MAAM,YAAY,GAAG,MAAM,OAAO,CAAC,GAAG,CAAC,OAAO,EAAE;QAC9C,OAAO,EAAE,GAAG,CAAC,OAAO,CAAC,OAAO;KAC7B,CAAC,CAAC;IAEH,gEAAgE;IAChE,IAAI,YAAY,CAAC,EAAE,EAAE,CAAC;QACpB,GAAG,CAAC,MAAM,CAAC,QAAQ,GAAG,YAAY,CAAC,IAAI,CAAC;QACxC,GAAG,CAAC,MAAM,CAAC,WAAW,GAAG,YAAY,CAAC,OAAO,CAAC;IAChD,CAAC;IAED,2DAA2D;IAC3D,MAAM,eAAe,GAAG,eAAe,CAAC,YAAY,CAAC,CAAC;IAEtD,8BAA8B;IAC9B,MAAM,YAAY,GAAG,MAAM,cAAc,CACvC,GAAG,CAAC,MAAM,EACV,GAAG,CAAC,OAAO,CAAC,OAAO,CACpB,CAAC;IAEF,oDAAoD;IACpD,IAAI,UAAkB,CAAC;IACvB,IAAI,CAAC;QACH,UAAU,GAAG,IAAI,GAAG,CAAC,GAAG,CAAC,OAAO,CAAC,CAAC,QAAQ,CAAC;IAC7C,CAAC;IAAC,MAAM,CAAC;QACP,UAAU,GAAG,GAAG,CAAC;IACnB,CAAC;IACD,MAAM,aAAa,GAAG,uBAAuB,CAC3C,YAAY,CAAC,MAAM,EACnB,UAAU,CACX,CAAC;IAEF,sCAAsC;IACtC,IAAI,eAAsB,CAAC;IAC3B,IAAI,YAAmB,CAAC;IAExB,IAAI,YAAY,CAAC,EAAE,EAAE,CAAC;QACpB,eAAe,GAAG,eAAe,CAAC,YAAY,CAAC,IAAI,CAAC,CAAC;QACrD,YAAY,GAAG,eAAe,CAAC,YAAY,CAAC,OAAO,CAAC,CAAC;IACvD,CAAC;SAAM,CAAC;QACN,8EAA8E;QAC9E,eAAe,GAAG,eAAe,CAAC,EAAE,CAAC,CAAC;QACtC,YAAY,GAAG,eAAe,CAAC,EAAE,CAAC,CAAC;IACrC,CAAC;IAED,wBAAwB;IACxB,MAAM,MAAM,GAAY;QACtB,WAAW,CAAC,KAAK;QACjB,eAAe;QACf,YAAY,CAAC,KAAK;QAClB,GAAG,aAAa;QAChB,eAAe;QACf,YAAY;KACb,CAAC;IAEF,qBAAqB;IACrB,MAAM,EAAE,KAAK,EAAE,UAAU,EAAE,GAAG,cAAc,CAAC,MAAM,CAAC,CAAC;IAErD,OAAO;QACL,EAAE,EAAE,CAAC;QACL,IAAI,EAAE,cAAc;QACpB,MAAM,EAAE,WAAW;QACnB,KAAK;QACL,UAAU;QACV,MAAM;QACN,UAAU,EAAE,IAAI,CAAC,KAAK,CAAC,WAAW,CAAC,GAAG,EAAE,GAAG,KAAK,CAAC;KAClD,CAAC;AACJ,CAAC"}

package/dist/bridges/reachability/meta-robots.d.ts

@@ -0,0 +1,16 @@
+import type { Check } from "../../core/types.js";
+/**
+ * Check for restrictive meta robots tags in the HTML <head> section.
+ * Uses regex only -- no HTML parser dependency.
+ *
+ * Scans for: robots, googlebot, bingbot name attributes.
+ * Handles both attribute orders, single/double quotes, self-closing tags, case insensitivity.
+ */
+export declare function checkMetaRobots(html: string): Check;
+/**
+ * Check for X-Robots-Tag HTTP header directives.
+ *
+ * Headers object is expected to have lowercase keys (from Phase 2 httpGet).
+ */
+export declare function checkXRobotsTag(headers: Record<string, string>): Check;
+//# sourceMappingURL=meta-robots.d.ts.map

package/dist/bridges/reachability/meta-robots.d.ts.map

@@ -0,0 +1 @@
+{"version":3,"file":"meta-robots.d.ts","sourceRoot":"","sources":["../../../src/bridges/reachability/meta-robots.ts"],"names":[],"mappings":"AAAA,OAAO,KAAK,EAAE,KAAK,EAAE,MAAM,qBAAqB,CAAC;AAEjD;;;;;;GAMG;AACH,wBAAgB,eAAe,CAAC,IAAI,EAAE,MAAM,GAAG,KAAK,CA2EnD;AAED;;;;GAIG;AACH,wBAAgB,eAAe,CAAC,OAAO,EAAE,MAAM,CAAC,MAAM,EAAE,MAAM,CAAC,GAAG,KAAK,CAoDtE"}

package/dist/bridges/reachability/meta-robots.js

@@ -0,0 +1,119 @@
+/**
+ * Check for restrictive meta robots tags in the HTML <head> section.
+ * Uses regex only -- no HTML parser dependency.
+ *
+ * Scans for: robots, googlebot, bingbot name attributes.
+ * Handles both attribute orders, single/double quotes, self-closing tags, case insensitivity.
+ */
+export function checkMetaRobots(html) {
+    const id = "meta_robots";
+    const label = "Meta Robots Tags";
+    // Extract head content (case-insensitive)
+    const headMatch = html.match(/<head[^>]*>([\s\S]*?)<\/head>/i);
+    if (!headMatch) {
+        return {
+            id,
+            label,
+            status: "pass",
+            detail: "No restrictive meta robots tags found",
+            data: { directives: [] },
+        };
+    }
+    const headContent = headMatch[1];
+    const allDirectives = [];
+    // Pattern A: name first, then content
+    const patternA = /<meta\s+[^>]*name\s*=\s*["'](robots|googlebot|bingbot)["'][^>]*content\s*=\s*["']([^"']*)["'][^>]*\/?>/gi;
+    // Pattern B: content first, then name
+    const patternB = /<meta\s+[^>]*content\s*=\s*["']([^"']*)["'][^>]*name\s*=\s*["'](robots|googlebot|bingbot)["'][^>]*\/?>/gi;
+    let match;
+    while ((match = patternA.exec(headContent)) !== null) {
+        const contentValue = match[2];
+        const directives = contentValue
+            .split(",")
+            .map((d) => d.trim().toLowerCase());
+        allDirectives.push(...directives);
+    }
+    while ((match = patternB.exec(headContent)) !== null) {
+        const contentValue = match[1];
+        const directives = contentValue
+            .split(",")
+            .map((d) => d.trim().toLowerCase());
+        allDirectives.push(...directives);
+    }
+    // Filter out empty strings
+    const filtered = allDirectives.filter((d) => d.length > 0);
+    if (filtered.some((d) => d === "noindex")) {
+        return {
+            id,
+            label,
+            status: "fail",
+            detail: `Restrictive meta robots directives found: ${filtered.join(", ")}`,
+            data: { directives: filtered },
+        };
+    }
+    if (filtered.some((d) => d === "nofollow")) {
+        return {
+            id,
+            label,
+            status: "partial",
+            detail: `Restrictive meta robots directives found: ${filtered.join(", ")}`,
+            data: { directives: filtered },
+        };
+    }
+    return {
+        id,
+        label,
+        status: "pass",
+        detail: "No restrictive meta robots tags found",
+        data: { directives: filtered },
+    };
+}
+/**
+ * Check for X-Robots-Tag HTTP header directives.
+ *
+ * Headers object is expected to have lowercase keys (from Phase 2 httpGet).
+ */
+export function checkXRobotsTag(headers) {
+    const id = "x_robots_tag";
+    const label = "X-Robots-Tag Header";
+    const headerValue = headers["x-robots-tag"];
+    if (!headerValue) {
+        return {
+            id,
+            label,
+            status: "pass",
+            detail: "No X-Robots-Tag header",
+            data: { directives: [], raw: "" },
+        };
+    }
+    const directives = headerValue
+        .split(",")
+        .map((d) => d.trim().toLowerCase())
+        .filter((d) => d.length > 0);
+    if (directives.some((d) => d.includes("noindex"))) {
+        return {
+            id,
+            label,
+            status: "fail",
+            detail: `X-Robots-Tag contains restrictive directives: ${directives.join(", ")}`,
+            data: { directives, raw: headerValue },
+        };
+    }
+    if (directives.some((d) => d.includes("nofollow") || d.includes("noarchive") || d === "none")) {
+        return {
+            id,
+            label,
+            status: "partial",
+            detail: `X-Robots-Tag contains directives: ${directives.join(", ")}`,
+            data: { directives, raw: headerValue },
+        };
+    }
+    return {
+        id,
+        label,
+        status: "pass",
+        detail: `X-Robots-Tag header present with no restrictive directives`,
+        data: { directives, raw: headerValue },
+    };
+}
+//# sourceMappingURL=meta-robots.js.map

package/dist/bridges/reachability/meta-robots.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"meta-robots.js","sourceRoot":"","sources":["../../../src/bridges/reachability/meta-robots.ts"],"names":[],"mappings":"AAEA;;;;;;GAMG;AACH,MAAM,UAAU,eAAe,CAAC,IAAY;IAC1C,MAAM,EAAE,GAAG,aAAa,CAAC;IACzB,MAAM,KAAK,GAAG,kBAAkB,CAAC;IAEjC,0CAA0C;IAC1C,MAAM,SAAS,GAAG,IAAI,CAAC,KAAK,CAAC,gCAAgC,CAAC,CAAC;IAC/D,IAAI,CAAC,SAAS,EAAE,CAAC;QACf,OAAO;YACL,EAAE;YACF,KAAK;YACL,MAAM,EAAE,MAAM;YACd,MAAM,EAAE,uCAAuC;YAC/C,IAAI,EAAE,EAAE,UAAU,EAAE,EAAE,EAAE;SACzB,CAAC;IACJ,CAAC;IAED,MAAM,WAAW,GAAG,SAAS,CAAC,CAAC,CAAC,CAAC;IACjC,MAAM,aAAa,GAAa,EAAE,CAAC;IAEnC,sCAAsC;IACtC,MAAM,QAAQ,GACZ,0GAA0G,CAAC;IAE7G,sCAAsC;IACtC,MAAM,QAAQ,GACZ,0GAA0G,CAAC;IAE7G,IAAI,KAA6B,CAAC;IAElC,OAAO,CAAC,KAAK,GAAG,QAAQ,CAAC,IAAI,CAAC,WAAW,CAAC,CAAC,KAAK,IAAI,EAAE,CAAC;QACrD,MAAM,YAAY,GAAG,KAAK,CAAC,CAAC,CAAC,CAAC;QAC9B,MAAM,UAAU,GAAG,YAAY;aAC5B,KAAK,CAAC,GAAG,CAAC;aACV,GAAG,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,IAAI,EAAE,CAAC,WAAW,EAAE,CAAC,CAAC;QACtC,aAAa,CAAC,IAAI,CAAC,GAAG,UAAU,CAAC,CAAC;IACpC,CAAC;IAED,OAAO,CAAC,KAAK,GAAG,QAAQ,CAAC,IAAI,CAAC,WAAW,CAAC,CAAC,KAAK,IAAI,EAAE,CAAC;QACrD,MAAM,YAAY,GAAG,KAAK,CAAC,CAAC,CAAC,CAAC;QAC9B,MAAM,UAAU,GAAG,YAAY;aAC5B,KAAK,CAAC,GAAG,CAAC;aACV,GAAG,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,IAAI,EAAE,CAAC,WAAW,EAAE,CAAC,CAAC;QACtC,aAAa,CAAC,IAAI,CAAC,GAAG,UAAU,CAAC,CAAC;IACpC,CAAC;IAED,2BAA2B;IAC3B,MAAM,QAAQ,GAAG,aAAa,CAAC,MAAM,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,MAAM,GAAG,CAAC,CAAC,CAAC;IAE3D,IAAI,QAAQ,CAAC,IAAI,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,KAAK,SAAS,CAAC,EAAE,CAAC;QAC1C,OAAO;YACL,EAAE;YACF,KAAK;YACL,MAAM,EAAE,MAAM;YACd,MAAM,EAAE,6CAA6C,QAAQ,CAAC,IAAI,CAAC,IAAI,CAAC,EAAE;YAC1E,IAAI,EAAE,EAAE,UAAU,EAAE,QAAQ,EAAE;SAC/B,CAAC;IACJ,CAAC;IAED,IAAI,QAAQ,CAAC,IAAI,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,KAAK,UAAU,CAAC,EAAE,CAAC;QAC3C,OAAO;YACL,EAAE;YACF,KAAK;YACL,MAAM,EAAE,SAAS;YACjB,MAAM,EAAE,6CAA6C,QAAQ,CAAC,IAAI,CAAC,IAAI,CAAC,EAAE;YAC1E,IAAI,EAAE,EAAE,UAAU,EAAE,QAAQ,EAAE;SAC/B,CAAC;IACJ,CAAC;IAED,OAAO;QACL,EAAE;QACF,KAAK;QACL,MAAM,EAAE,MAAM;QACd,MAAM,EAAE,uCAAuC;QAC/C,IAAI,EAAE,EAAE,UAAU,EAAE,QAAQ,EAAE;KAC/B,CAAC;AACJ,CAAC;AAED;;;;GAIG;AACH,MAAM,UAAU,eAAe,CAAC,OAA+B;IAC7D,MAAM,EAAE,GAAG,cAAc,CAAC;IAC1B,MAAM,KAAK,GAAG,qBAAqB,CAAC;IAEpC,MAAM,WAAW,GAAG,OAAO,CAAC,cAAc,CAAC,CAAC;IAC5C,IAAI,CAAC,WAAW,EAAE,CAAC;QACjB,OAAO;YACL,EAAE;YACF,KAAK;YACL,MAAM,EAAE,MAAM;YACd,MAAM,EAAE,wBAAwB;YAChC,IAAI,EAAE,EAAE,UAAU,EAAE,EAAE,EAAE,GAAG,EAAE,EAAE,EAAE;SAClC,CAAC;IACJ,CAAC;IAED,MAAM,UAAU,GAAG,WAAW;SAC3B,KAAK,CAAC,GAAG,CAAC;SACV,GAAG,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,IAAI,EAAE,CAAC,WAAW,EAAE,CAAC;SAClC,MAAM,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,MAAM,GAAG,CAAC,CAAC,CAAC;IAE/B,IAAI,UAAU,CAAC,IAAI,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,QAAQ,CAAC,SAAS,CAAC,CAAC,EAAE,CAAC;QAClD,OAAO;YACL,EAAE;YACF,KAAK;YACL,MAAM,EAAE,MAAM;YACd,MAAM,EAAE,iDAAiD,UAAU,CAAC,IAAI,CAAC,IAAI,CAAC,EAAE;YAChF,IAAI,EAAE,EAAE,UAAU,EAAE,GAAG,EAAE,WAAW,EAAE;SACvC,CAAC;IACJ,CAAC;IAED,IACE,UAAU,CAAC,IAAI,CACb,CAAC,CAAC,EAAE,EAAE,CACJ,CAAC,CAAC,QAAQ,CAAC,UAAU,CAAC,IAAI,CAAC,CAAC,QAAQ,CAAC,WAAW,CAAC,IAAI,CAAC,KAAK,MAAM,CACpE,EACD,CAAC;QACD,OAAO;YACL,EAAE;YACF,KAAK;YACL,MAAM,EAAE,SAAS;YACjB,MAAM,EAAE,qCAAqC,UAAU,CAAC,IAAI,CAAC,IAAI,CAAC,EAAE;YACpE,IAAI,EAAE,EAAE,UAAU,EAAE,GAAG,EAAE,WAAW,EAAE;SACvC,CAAC;IACJ,CAAC;IAED,OAAO;QACL,EAAE;QACF,KAAK;QACL,MAAM,EAAE,MAAM;QACd,MAAM,EAAE,4DAA4D;QACpE,IAAI,EAAE,EAAE,UAAU,EAAE,GAAG,EAAE,WAAW,EAAE;KACvC,CAAC;AACJ,CAAC"}

package/dist/bridges/reachability/robots-parser.d.ts

@@ -0,0 +1,26 @@
+export interface RobotsTxtResult {
+    parseable: boolean;
+    ruleCount: number;
+    groups: RobotsGroup[];
+    sitemaps: string[];
+}
+export interface RobotsGroup {
+    userAgents: string[];
+    rules: RobotsRule[];
+}
+export interface RobotsRule {
+    type: "allow" | "disallow";
+    path: string;
+}
+/**
+ * Parse raw robots.txt content into structured data.
+ * Handles RFC 9309 edge cases: BOM, CRLF/CR/LF, comments,
+ * case-insensitive directives, case-sensitive paths, group boundaries.
+ */
+export declare function parseRobotsTxt(content: string): RobotsTxtResult;
+/**
+ * Check whether a robots.txt path pattern matches a given URL path.
+ * Supports * wildcards and $ end anchor per RFC 9309.
+ */
+export declare function matchesPath(pattern: string, path: string): boolean;
+//# sourceMappingURL=robots-parser.d.ts.map

package/dist/bridges/reachability/robots-parser.d.ts.map

@@ -0,0 +1 @@
+{"version":3,"file":"robots-parser.d.ts","sourceRoot":"","sources":["../../../src/bridges/reachability/robots-parser.ts"],"names":[],"mappings":"AAGA,MAAM,WAAW,eAAe;IAC9B,SAAS,EAAE,OAAO,CAAC;IACnB,SAAS,EAAE,MAAM,CAAC;IAClB,MAAM,EAAE,WAAW,EAAE,CAAC;IACtB,QAAQ,EAAE,MAAM,EAAE,CAAC;CACpB;AAED,MAAM,WAAW,WAAW;IAC1B,UAAU,EAAE,MAAM,EAAE,CAAC;IACrB,KAAK,EAAE,UAAU,EAAE,CAAC;CACrB;AAED,MAAM,WAAW,UAAU;IACzB,IAAI,EAAE,OAAO,GAAG,UAAU,CAAC;IAC3B,IAAI,EAAE,MAAM,CAAC;CACd;AAED;;;;GAIG;AACH,wBAAgB,cAAc,CAAC,OAAO,EAAE,MAAM,GAAG,eAAe,CAmF/D;AAED;;;GAGG;AACH,wBAAgB,WAAW,CAAC,OAAO,EAAE,MAAM,EAAE,IAAI,EAAE,MAAM,GAAG,OAAO,CAyBlE"}

package/dist/bridges/reachability/robots-parser.js

@@ -0,0 +1,105 @@
+// RFC 9309 robots.txt parser and path matcher
+// Pure logic, no I/O
+/**
+ * Parse raw robots.txt content into structured data.
+ * Handles RFC 9309 edge cases: BOM, CRLF/CR/LF, comments,
+ * case-insensitive directives, case-sensitive paths, group boundaries.
+ */
+export function parseRobotsTxt(content) {
+    const groups = [];
+    const sitemaps = [];
+    // 1. Strip UTF-8 BOM
+    let text = content;
+    if (text.charCodeAt(0) === 0xfeff || text.startsWith("\xEF\xBB\xBF")) {
+        text = text.replace(/^\xEF\xBB\xBF/, "").replace(/^\uFEFF/, "");
+    }
+    // 2. Split on CRLF, CR, or LF
+    const lines = text.split(/\r\n|\r|\n/);
+    let currentGroup = null;
+    for (const rawLine of lines) {
+        // 3. Strip comments and trim
+        const commentIdx = rawLine.indexOf("#");
+        const line = (commentIdx >= 0 ? rawLine.substring(0, commentIdx) : rawLine).trim();
+        if (line === "")
+            continue;
+        // 4. Parse directive: split on first ':'
+        const colonIdx = line.indexOf(":");
+        if (colonIdx < 0)
+            continue;
+        const directive = line.substring(0, colonIdx).trim().toLowerCase();
+        const value = line.substring(colonIdx + 1).trim();
+        switch (directive) {
+            case "user-agent": {
+                // 6. If currentGroup has rules, start a new group
+                if (currentGroup && currentGroup.rules.length > 0) {
+                    groups.push(currentGroup);
+                    currentGroup = { userAgents: [value.toLowerCase()], rules: [] };
+                }
+                else if (currentGroup) {
+                    // Consecutive User-agent lines = same group
+                    currentGroup.userAgents.push(value.toLowerCase());
+                }
+                else {
+                    currentGroup = { userAgents: [value.toLowerCase()], rules: [] };
+                }
+                break;
+            }
+            case "allow":
+            case "disallow": {
+                // 7. If no currentGroup, create one with empty userAgents
+                if (!currentGroup) {
+                    currentGroup = { userAgents: [], rules: [] };
+                }
+                currentGroup.rules.push({ type: directive, path: value });
+                break;
+            }
+            case "sitemap": {
+                // 8. Sitemaps are not tied to any group
+                sitemaps.push(value);
+                break;
+            }
+            default:
+                // 9. Unknown directives: ignore
+                break;
+        }
+    }
+    // 10. Push final group
+    if (currentGroup) {
+        groups.push(currentGroup);
+    }
+    // 11. Calculate ruleCount
+    const ruleCount = groups.reduce((sum, g) => sum + g.rules.length, 0);
+    return {
+        parseable: true,
+        ruleCount,
+        groups,
+        sitemaps,
+    };
+}
+/**
+ * Check whether a robots.txt path pattern matches a given URL path.
+ * Supports * wildcards and $ end anchor per RFC 9309.
+ */
+export function matchesPath(pattern, path) {
+    // 1. Empty pattern matches everything
+    if (pattern === "")
+        return true;
+    // 2. Check for $ end anchor
+    let anchorEnd = false;
+    let pat = pattern;
+    if (pat.endsWith("$")) {
+        anchorEnd = true;
+        pat = pat.slice(0, -1);
+    }
+    // 3. Escape regex special chars except * (already removed $ if present)
+    // Escape: \ . + ? [ ] ( ) { } | ^ /
+    const escaped = pat.replace(/([\\.\+\?\[\]\(\)\{\}\|\^\/])/g, "\\$1");
+    // 4. Replace * with .*
+    const regexStr = escaped.replace(/\*/g, ".*");
+    // 5. Build regex: prefix match unless $ anchor
+    const fullRegex = anchorEnd
+        ? new RegExp("^" + regexStr + "$")
+        : new RegExp("^" + regexStr);
+    return fullRegex.test(path);
+}
+//# sourceMappingURL=robots-parser.js.map

package/dist/bridges/reachability/robots-parser.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"robots-parser.js","sourceRoot":"","sources":["../../../src/bridges/reachability/robots-parser.ts"],"names":[],"mappings":"AAAA,8CAA8C;AAC9C,qBAAqB;AAmBrB;;;;GAIG;AACH,MAAM,UAAU,cAAc,CAAC,OAAe;IAC5C,MAAM,MAAM,GAAkB,EAAE,CAAC;IACjC,MAAM,QAAQ,GAAa,EAAE,CAAC;IAE9B,qBAAqB;IACrB,IAAI,IAAI,GAAG,OAAO,CAAC;IACnB,IAAI,IAAI,CAAC,UAAU,CAAC,CAAC,CAAC,KAAK,MAAM,IAAI,IAAI,CAAC,UAAU,CAAC,cAAc,CAAC,EAAE,CAAC;QACrE,IAAI,GAAG,IAAI,CAAC,OAAO,CAAC,eAAe,EAAE,EAAE,CAAC,CAAC,OAAO,CAAC,SAAS,EAAE,EAAE,CAAC,CAAC;IAClE,CAAC;IAED,8BAA8B;IAC9B,MAAM,KAAK,GAAG,IAAI,CAAC,KAAK,CAAC,YAAY,CAAC,CAAC;IAEvC,IAAI,YAAY,GACd,IAAI,CAAC;IAEP,KAAK,MAAM,OAAO,IAAI,KAAK,EAAE,CAAC;QAC5B,6BAA6B;QAC7B,MAAM,UAAU,GAAG,OAAO,CAAC,OAAO,CAAC,GAAG,CAAC,CAAC;QACxC,MAAM,IAAI,GAAG,CACX,UAAU,IAAI,CAAC,CAAC,CAAC,CAAC,OAAO,CAAC,SAAS,CAAC,CAAC,EAAE,UAAU,CAAC,CAAC,CAAC,CAAC,OAAO,CAC7D,CAAC,IAAI,EAAE,CAAC;QAET,IAAI,IAAI,KAAK,EAAE;YAAE,SAAS;QAE1B,yCAAyC;QACzC,MAAM,QAAQ,GAAG,IAAI,CAAC,OAAO,CAAC,GAAG,CAAC,CAAC;QACnC,IAAI,QAAQ,GAAG,CAAC;YAAE,SAAS;QAE3B,MAAM,SAAS,GAAG,IAAI,CAAC,SAAS,CAAC,CAAC,EAAE,QAAQ,CAAC,CAAC,IAAI,EAAE,CAAC,WAAW,EAAE,CAAC;QACnE,MAAM,KAAK,GAAG,IAAI,CAAC,SAAS,CAAC,QAAQ,GAAG,CAAC,CAAC,CAAC,IAAI,EAAE,CAAC;QAElD,QAAQ,SAAS,EAAE,CAAC;YAClB,KAAK,YAAY,CAAC,CAAC,CAAC;gBAClB,kDAAkD;gBAClD,IAAI,YAAY,IAAI,YAAY,CAAC,KAAK,CAAC,MAAM,GAAG,CAAC,EAAE,CAAC;oBAClD,MAAM,CAAC,IAAI,CAAC,YAAY,CAAC,CAAC;oBAC1B,YAAY,GAAG,EAAE,UAAU,EAAE,CAAC,KAAK,CAAC,WAAW,EAAE,CAAC,EAAE,KAAK,EAAE,EAAE,EAAE,CAAC;gBAClE,CAAC;qBAAM,IAAI,YAAY,EAAE,CAAC;oBACxB,4CAA4C;oBAC5C,YAAY,CAAC,UAAU,CAAC,IAAI,CAAC,KAAK,CAAC,WAAW,EAAE,CAAC,CAAC;gBACpD,CAAC;qBAAM,CAAC;oBACN,YAAY,GAAG,EAAE,UAAU,EAAE,CAAC,KAAK,CAAC,WAAW,EAAE,CAAC,EAAE,KAAK,EAAE,EAAE,EAAE,CAAC;gBAClE,CAAC;gBACD,MAAM;YACR,CAAC;YAED,KAAK,OAAO,CAAC;YACb,KAAK,UAAU,CAAC,CAAC,CAAC;gBAChB,0DAA0D;gBAC1D,IAAI,CAAC,YAAY,EAAE,CAAC;oBAClB,YAAY,GAAG,EAAE,UAAU,EAAE,EAAE,EAAE,KAAK,EAAE,EAAE,EAAE,CAAC;gBAC/C,CAAC;gBACD,YAAY,CAAC,KAAK,CAAC,IAAI,CAAC,EAAE,IAAI,EAAE,SAAS,EAAE,IAAI,EAAE,KAAK,EAAE,CAAC,CAAC;gBAC1D,MAAM;YACR,CAAC;YAED,KAAK,SAAS,CAAC,CAAC,CAAC;gBACf,wCAAwC;gBACxC,QAAQ,CAAC,IAAI,CAAC,KAAK,CAAC,CAAC;gBACrB,MAAM;YACR,CAAC;YAED;gBACE,gCAAgC;gBAChC,MAAM;QACV,CAAC;IACH,CAAC;IAED,uBAAuB;IACvB,IAAI,YAAY,EAAE,CAAC;QACjB,MAAM,CAAC,IAAI,CAAC,YAAY,CAAC,CAAC;IAC5B,CAAC;IAED,0BAA0B;IAC1B,MAAM,SAAS,GAAG,MAAM,CAAC,MAAM,CAAC,CAAC,GAAG,EAAE,CAAC,EAAE,EAAE,CAAC,GAAG,GAAG,CAAC,CAAC,KAAK,CAAC,MAAM,EAAE,CAAC,CAAC,CAAC;IAErE,OAAO;QACL,SAAS,EAAE,IAAI;QACf,SAAS;QACT,MAAM;QACN,QAAQ;KACT,CAAC;AACJ,CAAC;AAED;;;GAGG;AACH,MAAM,UAAU,WAAW,CAAC,OAAe,EAAE,IAAY;IACvD,sCAAsC;IACtC,IAAI,OAAO,KAAK,EAAE;QAAE,OAAO,IAAI,CAAC;IAEhC,4BAA4B;IAC5B,IAAI,SAAS,GAAG,KAAK,CAAC;IACtB,IAAI,GAAG,GAAG,OAAO,CAAC;IAClB,IAAI,GAAG,CAAC,QAAQ,CAAC,GAAG,CAAC,EAAE,CAAC;QACtB,SAAS,GAAG,IAAI,CAAC;QACjB,GAAG,GAAG,GAAG,CAAC,KAAK,CAAC,CAAC,EAAE,CAAC,CAAC,CAAC,CAAC;IACzB,CAAC;IAED,wEAAwE;IACxE,oCAAoC;IACpC,MAAM,OAAO,GAAG,GAAG,CAAC,OAAO,CAAC,gCAAgC,EAAE,MAAM,CAAC,CAAC;IAEtE,uBAAuB;IACvB,MAAM,QAAQ,GAAG,OAAO,CAAC,OAAO,CAAC,KAAK,EAAE,IAAI,CAAC,CAAC;IAE9C,+CAA+C;IAC/C,MAAM,SAAS,GAAG,SAAS;QACzB,CAAC,CAAC,IAAI,MAAM,CAAC,GAAG,GAAG,QAAQ,GAAG,GAAG,CAAC;QAClC,CAAC,CAAC,IAAI,MAAM,CAAC,GAAG,GAAG,QAAQ,CAAC,CAAC;IAE/B,OAAO,SAAS,CAAC,IAAI,CAAC,IAAI,CAAC,CAAC;AAC9B,CAAC"}

package/dist/bridges/reachability/robots-txt.d.ts

@@ -0,0 +1,14 @@
+import type { Check } from "../../core/types.js";
+import { type RobotsTxtResult } from "./robots-parser.js";
+export interface RobotsTxtCheckResult {
+    check: Check;
+    parsed: RobotsTxtResult | null;
+}
+/**
+ * Fetch and parse robots.txt for the given domain.
+ *
+ * Returns both the Check result and the parsed data for downstream
+ * use by crawler policy evaluation.
+ */
+export declare function checkRobotsTxt(domain: string, timeout?: number): Promise<RobotsTxtCheckResult>;
+//# sourceMappingURL=robots-txt.d.ts.map

package/dist/bridges/reachability/robots-txt.d.ts.map

@@ -0,0 +1 @@
+{"version":3,"file":"robots-txt.d.ts","sourceRoot":"","sources":["../../../src/bridges/reachability/robots-txt.ts"],"names":[],"mappings":"AAAA,OAAO,KAAK,EAAE,KAAK,EAAE,MAAM,qBAAqB,CAAC;AAEjD,OAAO,EAAkB,KAAK,eAAe,EAAE,MAAM,oBAAoB,CAAC;AAE1E,MAAM,WAAW,oBAAoB;IACnC,KAAK,EAAE,KAAK,CAAC;IACb,MAAM,EAAE,eAAe,GAAG,IAAI,CAAC;CAChC;AAID;;;;;GAKG;AACH,wBAAsB,cAAc,CAClC,MAAM,EAAE,MAAM,EACd,OAAO,CAAC,EAAE,MAAM,GACf,OAAO,CAAC,oBAAoB,CAAC,CA+E/B"}

package/dist/bridges/reachability/robots-txt.js

@@ -0,0 +1,80 @@
+import { httpGet } from "../../utils/http-client.js";
+import { parseRobotsTxt } from "./robots-parser.js";
+const DIRECTIVE_PATTERN = /\b(user-agent|disallow|allow)\s*:/i;
+/**
+ * Fetch and parse robots.txt for the given domain.
+ *
+ * Returns both the Check result and the parsed data for downstream
+ * use by crawler policy evaluation.
+ */
+export async function checkRobotsTxt(domain, timeout) {
+    const id = "robots_txt";
+    const label = "robots.txt";
+    const result = await httpGet("https://" + domain + "/robots.txt", {
+        timeout,
+    });
+    if (!result.ok) {
+        // 404 = no robots.txt
+        if (result.error.kind === "http_error" &&
+            result.error.statusCode === 404) {
+            return {
+                check: {
+                    id,
+                    label,
+                    status: "partial",
+                    detail: "No robots.txt found",
+                },
+                parsed: null,
+            };
+        }
+        // Other errors
+        return {
+            check: {
+                id,
+                label,
+                status: "fail",
+                detail: result.error.message,
+            },
+            parsed: null,
+        };
+    }
+    // Success -- validate content type
+    const contentType = result.headers["content-type"] ?? "";
+    const isTextPlain = contentType.toLowerCase().includes("text/plain");
+    const hasDirectives = DIRECTIVE_PATTERN.test(result.body);
+    if (!isTextPlain && !hasDirectives) {
+        return {
+            check: {
+                id,
+                label,
+                status: "fail",
+                detail: "robots.txt is not a text file",
+            },
+            parsed: null,
+        };
+    }
+    // Parse
+    const parsed = parseRobotsTxt(result.body);
+    if (parsed.ruleCount === 0 && parsed.groups.length === 0) {
+        return {
+            check: {
+                id,
+                label,
+                status: "partial",
+                detail: "robots.txt exists but has no rules",
+            },
+            parsed,
+        };
+    }
+    return {
+        check: {
+            id,
+            label,
+            status: "pass",
+            detail: `robots.txt found with ${parsed.ruleCount} rules`,
+            data: { ruleCount: parsed.ruleCount, sitemaps: parsed.sitemaps },
+        },
+        parsed,
+    };
+}
+//# sourceMappingURL=robots-txt.js.map

package/dist/bridges/reachability/robots-txt.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"robots-txt.js","sourceRoot":"","sources":["../../../src/bridges/reachability/robots-txt.ts"],"names":[],"mappings":"AACA,OAAO,EAAE,OAAO,EAAE,MAAM,4BAA4B,CAAC;AACrD,OAAO,EAAE,cAAc,EAAwB,MAAM,oBAAoB,CAAC;AAO1E,MAAM,iBAAiB,GAAG,oCAAoC,CAAC;AAE/D;;;;;GAKG;AACH,MAAM,CAAC,KAAK,UAAU,cAAc,CAClC,MAAc,EACd,OAAgB;IAEhB,MAAM,EAAE,GAAG,YAAY,CAAC;IACxB,MAAM,KAAK,GAAG,YAAY,CAAC;IAE3B,MAAM,MAAM,GAAG,MAAM,OAAO,CAAC,UAAU,GAAG,MAAM,GAAG,aAAa,EAAE;QAChE,OAAO;KACR,CAAC,CAAC;IAEH,IAAI,CAAC,MAAM,CAAC,EAAE,EAAE,CAAC;QACf,sBAAsB;QACtB,IACE,MAAM,CAAC,KAAK,CAAC,IAAI,KAAK,YAAY;YAClC,MAAM,CAAC,KAAK,CAAC,UAAU,KAAK,GAAG,EAC/B,CAAC;YACD,OAAO;gBACL,KAAK,EAAE;oBACL,EAAE;oBACF,KAAK;oBACL,MAAM,EAAE,SAAS;oBACjB,MAAM,EAAE,qBAAqB;iBAC9B;gBACD,MAAM,EAAE,IAAI;aACb,CAAC;QACJ,CAAC;QAED,eAAe;QACf,OAAO;YACL,KAAK,EAAE;gBACL,EAAE;gBACF,KAAK;gBACL,MAAM,EAAE,MAAM;gBACd,MAAM,EAAE,MAAM,CAAC,KAAK,CAAC,OAAO;aAC7B;YACD,MAAM,EAAE,IAAI;SACb,CAAC;IACJ,CAAC;IAED,mCAAmC;IACnC,MAAM,WAAW,GAAG,MAAM,CAAC,OAAO,CAAC,cAAc,CAAC,IAAI,EAAE,CAAC;IACzD,MAAM,WAAW,GAAG,WAAW,CAAC,WAAW,EAAE,CAAC,QAAQ,CAAC,YAAY,CAAC,CAAC;IACrE,MAAM,aAAa,GAAG,iBAAiB,CAAC,IAAI,CAAC,MAAM,CAAC,IAAI,CAAC,CAAC;IAE1D,IAAI,CAAC,WAAW,IAAI,CAAC,aAAa,EAAE,CAAC;QACnC,OAAO;YACL,KAAK,EAAE;gBACL,EAAE;gBACF,KAAK;gBACL,MAAM,EAAE,MAAM;gBACd,MAAM,EAAE,+BAA+B;aACxC;YACD,MAAM,EAAE,IAAI;SACb,CAAC;IACJ,CAAC;IAED,QAAQ;IACR,MAAM,MAAM,GAAG,cAAc,CAAC,MAAM,CAAC,IAAI,CAAC,CAAC;IAE3C,IAAI,MAAM,CAAC,SAAS,KAAK,CAAC,IAAI,MAAM,CAAC,MAAM,CAAC,MAAM,KAAK,CAAC,EAAE,CAAC;QACzD,OAAO;YACL,KAAK,EAAE;gBACL,EAAE;gBACF,KAAK;gBACL,MAAM,EAAE,SAAS;gBACjB,MAAM,EAAE,oCAAoC;aAC7C;YACD,MAAM;SACP,CAAC;IACJ,CAAC;IAED,OAAO;QACL,KAAK,EAAE;YACL,EAAE;YACF,KAAK;YACL,MAAM,EAAE,MAAM;YACd,MAAM,EAAE,yBAAyB,MAAM,CAAC,SAAS,QAAQ;YACzD,IAAI,EAAE,EAAE,SAAS,EAAE,MAAM,CAAC,SAAS,EAAE,QAAQ,EAAE,MAAM,CAAC,QAAQ,EAAE;SACjE;QACD,MAAM;KACP,CAAC;AACJ,CAAC"}

package/dist/bridges/separation/api-presence.d.ts

@@ -0,0 +1,14 @@
+import type { Check, ContentSource } from "../../core/types.js";
+/**
+ * Detect API presence via multiple signals across content sources.
+ *
+ * Four signal sources:
+ * 1. OpenAPI spec detected by Bridge 2 (boolean from ctx.shared.openApiDetected)
+ * 2. API-related response headers (X-RateLimit-*, X-Request-Id, etc.)
+ * 3. HTML links containing /api/ paths (scanned from all content sources)
+ * 4. Markdown links containing /api/ paths (scanned from all content sources)
+ *
+ * Pure function -- no HTTP calls.
+ */
+export declare function checkApiPresence(openApiDetected: boolean, sources: ContentSource[], headers: Record<string, string>): Check;
+//# sourceMappingURL=api-presence.d.ts.map

package/dist/bridges/separation/api-presence.d.ts.map

@@ -0,0 +1 @@
+{"version":3,"file":"api-presence.d.ts","sourceRoot":"","sources":["../../../src/bridges/separation/api-presence.ts"],"names":[],"mappings":"AAAA,OAAO,KAAK,EAAE,KAAK,EAAE,aAAa,EAAE,MAAM,qBAAqB,CAAC;AA8ChE;;;;;;;;;;GAUG;AACH,wBAAgB,gBAAgB,CAC9B,eAAe,EAAE,OAAO,EACxB,OAAO,EAAE,aAAa,EAAE,EACxB,OAAO,EAAE,MAAM,CAAC,MAAM,EAAE,MAAM,CAAC,GAC9B,KAAK,CA0CP"}