chore: address lint errors

biome.json

@@ -1,7 +1,8 @@
 {
-	"$schema": "https://biomejs.dev/schemas/2.0.6/schema.json",
+	"$schema": "https://biomejs.dev/schemas/2.2.4/schema.json",
 	"files": {
-		"ignoreUnknown": true
+		"ignoreUnknown": true,
+		"includes": ["**", "!**/src/tests/__fixtures__"]
 	},
 	"vcs": {
 		"enabled": true,

src/commands/sessions.ts

@@ -3,6 +3,8 @@ import type {
 	ProcessingSummaryResult,
 } from "@/core/ProcessingPipeline";
 import type { CrawlMetadata, FieldExtractionStats } from "@/core/types";
+import type { ContentFieldName } from "@/crawlers/extractors/ContentPageExtractor";
+import type { ListingFieldName } from "@/crawlers/extractors/ListingPageExtractor";
 import type {
 	ContentMetadata,
 	CrawlSession,
@@ -206,7 +208,7 @@ function calculateFieldStats(
 ): FieldExtractionStats[] {
 	if (contents.length === 0) return [];
 
-	const fields = [
+	const fields: Array<{ name: ListingFieldName; isOptional: boolean }> = [
 		{ name: "title", isOptional: false },
 		{ name: "url", isOptional: false },
 		{ name: "author", isOptional: true },
@@ -251,7 +253,7 @@ function calculateContentFieldStats(
 
 	return [
 		{
-			fieldName: "content",
+			fieldName: "content" as ContentFieldName,
 			successCount,
 			totalAttempts: contents.length,
 			isOptional: false,

src/core/ProcessingPipeline.ts

@@ -1,4 +1,5 @@
 import type {
+	ContentSessionLinker,
 	CrawledData,
 	CrawlerRegistry,
 	CrawlOptions,
@@ -38,7 +39,7 @@ export interface ProcessingPipeline {
 async function handleItemStorage(
 	data: CrawledData,
 	contentStore: ContentStore,
-	metadataTracker?: any,
+	metadataTracker?: ContentSessionLinker,
 ): Promise<ProcessedData> {
 	try {
 		const storageResult = await contentStore.store(data);
@@ -79,7 +80,7 @@ async function handleItemStorage(
 async function processPageItems(
 	items: CrawledData[],
 	contentStore: ContentStore,
-	metadataTracker?: any,
+	metadataTracker?: ContentSessionLinker,
 ): Promise<ProcessedData[]> {
 	const processedData: ProcessedData[] = [];
 

src/core/types.ts

@@ -164,11 +164,7 @@ export interface CrawlMetadata {
 	contentFieldStats: FieldExtractionStats[];
 	listingErrors: string[];
 	contentErrors: string[];
-	stoppedReason?:
-		| "max_pages"
-		| "no_next_button"
-		| "all_duplicates"
-		| "process_interrupted";
+	stoppedReason?: StoppedReason;
 }
 
 // Interface for junction table linking

src/tests/commands/crawl.test.ts

@@ -1,6 +1,7 @@
 import { describe, expect, it, vi } from "vitest";
 import { crawlWithOptions } from "@/commands/crawl";
 import { sources } from "@/config/sources/index.js";
+import type { ProcessingPipeline } from "@/core/ProcessingPipeline";
 import { ERROR_MESSAGES } from "@/ui/constants";
 import { displaySources } from "@/ui/formatter";
 import { validatePositiveIntegerOrEmpty } from "@/ui/utils";
@@ -96,8 +97,11 @@ describe("Crawl Command Validation", () => {
 describe("crawlWithOptions", () => {
 	it("should display available sources when source not found", async () => {
 		// Mock pipeline
-		const mockPipeline = {
+		const mockPipeline: ProcessingPipeline = {
 			processSummary: vi.fn(),
+			process: vi.fn(),
+			getMetadataStore: vi.fn(),
+			getContentStore: vi.fn(),
 		};
 
 		// Mock console.log
@@ -106,7 +110,7 @@ describe("crawlWithOptions", () => {
 		// Call crawlWithOptions with non-existent source
 		const result = await crawlWithOptions(
 			{ source: "non-existent-source" },
-			mockPipeline as any,
+			mockPipeline,
 		);
 
 		// Verify the error message and available sources are displayed

src/tests/commands/sessions.test.ts

@@ -1,7 +1,7 @@
 import { beforeEach, describe, expect, it, vi } from "vitest";
 import { handleSessions } from "@/commands/sessions";
 import type { ProcessingPipeline } from "@/core/ProcessingPipeline";
-import type { CrawlSession, MetadataStore } from "@/storage/index";
+import type { CrawlSession, MetadataStore } from "@/storage/MetadataStore";
 
 // Mock inquirer
 const mockPrompt = vi.fn();

src/tests/crawlers/extractors/BrowserFieldExtractor.test.ts

@@ -26,7 +26,7 @@ describe("BrowserFieldExtractor", () => {
 					}
 					return null;
 				}),
-			} as any;
+			} as unknown as Document;
 
 			const result = extractionFunction({
 				container_selector: ".container",
@@ -71,13 +71,13 @@ describe("BrowserFieldExtractor", () => {
 					}
 					return null;
 				}),
-			} as any;
+			} as unknown as Document;
 
 			global.window = {
 				location: {
 					href: "https://example.com/page",
 				},
-			} as any;
+			} as unknown as typeof window;
 
 			const result = extractionFunction({
 				container_selector: ".container",
@@ -98,10 +98,10 @@ describe("BrowserFieldExtractor", () => {
 
 			// Mock browser context - container not found
 			global.document = {
-				querySelector: vi.fn().mockImplementation((selector: string) => {
+				querySelector: vi.fn().mockImplementation((_selector: string) => {
 					return null; // Always return null to simulate missing container
 				}),
-			} as any;
+			} as unknown as Document;
 
 			const result = extractionFunction({
 				container_selector: ".nonexistent",
@@ -124,7 +124,7 @@ describe("BrowserFieldExtractor", () => {
 
 			// Mock browser context - container exists but field element doesn't
 			const mockContainer = {
-				querySelector: vi.fn().mockImplementation((selector: string) => {
+				querySelector: vi.fn().mockImplementation((_selector: string) => {
 					return null; // Always return null for field elements
 				}),
 			};
@@ -136,7 +136,7 @@ describe("BrowserFieldExtractor", () => {
 					}
 					return null;
 				}),
-			} as any;
+			} as unknown as Document;
 
 			const result = extractionFunction({
 				container_selector: ".container",
@@ -170,7 +170,7 @@ describe("BrowserFieldExtractor", () => {
 					}
 					return null;
 				}),
-			} as any;
+			} as unknown as Document;
 
 			const result = extractionFunction({
 				container_selector: ".container",
@@ -203,7 +203,7 @@ describe("BrowserFieldExtractor", () => {
 					}
 					return null;
 				}),
-			} as any;
+			} as unknown as Document;
 
 			const result = extractionFunction({
 				container_selector: ".container",
@@ -249,13 +249,13 @@ describe("BrowserFieldExtractor", () => {
 					}
 					return null;
 				}),
-			} as any;
+			} as unknown as Document;
 
 			global.window = {
 				location: {
 					href: "https://example.com/page",
 				},
-			} as any;
+			} as unknown as typeof window;
 
 			const result = extractionFunction({
 				container_selector: ".container",
@@ -296,7 +296,7 @@ describe("BrowserFieldExtractor", () => {
 					}
 					return null;
 				}),
-			} as any;
+			} as unknown as Document;
 
 			const result = extractionFunction({
 				container_selector: ".container",
@@ -342,7 +342,7 @@ describe("BrowserFieldExtractor", () => {
 					}
 					return null;
 				}),
-			} as any;
+			} as unknown as Document;
 
 			const result = extractionFunction({
 				container_selector: ".container",
@@ -392,7 +392,7 @@ describe("BrowserFieldExtractor", () => {
 					}
 					return null;
 				}),
-			} as any;
+			} as unknown as Document;
 
 			const result = extractionFunction({
 				container_selector: ".container",

src/tests/crawlers/extractors/BrowserFieldExtractor.whitespace.test.ts

@@ -23,7 +23,7 @@ describe("BrowserFieldExtractor - Whitespace handling", () => {
 					}
 					return null;
 				}),
-			} as any;
+			} as unknown as Document;
 
 			const result = extractionFunction({
 				container_selector: ".container",
@@ -74,7 +74,7 @@ describe("BrowserFieldExtractor - Whitespace handling", () => {
 					}
 					return null;
 				}),
-			} as any;
+			} as unknown as Document;
 
 			const result = extractionFunction({
 				container_selector: ".container",

src/tests/crawlers/extractors/ConcurrentContentExtractor.test.ts

@@ -1,4 +1,3 @@
-import type { Page } from "puppeteer";
 import { beforeEach, describe, expect, it, vi } from "vitest";
 import type {
 	CrawledData,
@@ -14,7 +13,6 @@ describe("ConcurrentContentExtractor", () => {
 	let mockBrowserHandler: BrowserHandler;
 	let mockExtractContentForSingleItem: ReturnType<typeof vi.fn>;
 	let concurrentExtractor: ReturnType<typeof createConcurrentContentExtractor>;
-	let mockPage: Page;
 	let mockMetadataStore: MetadataStore;
 
 	const mockConfig: SourceConfig = {
@@ -68,19 +66,19 @@ describe("ConcurrentContentExtractor", () => {
 			setupNewPage: mockNewPage,
 		} as unknown as BrowserHandler;
 
-		mockPage = {
-			browser: () => mockBrowserHandler,
-		} as unknown as Page;
-
 		// Create mock metadata store
 		mockMetadataStore = {
 			getExistingUrls: vi.fn().mockReturnValue(new Set()),
 		} as unknown as MetadataStore;
 
 		// Create concurrent extractor with proper dependencies
-		concurrentExtractor = createConcurrentContentExtractor(mockBrowserHandler, {
+		const extractorDependencies = {
 			extractContentForSingleItem: mockExtractContentForSingleItem,
-		});
+		};
+		concurrentExtractor = createConcurrentContentExtractor(
+			mockBrowserHandler,
+			extractorDependencies,
+		);
 	});
 
 	describe("extractConcurrently", () => {

src/tests/crawlers/extractors/ContentPageExtractor.test.ts

@@ -457,7 +457,7 @@ describe("ContentPageExtractor", () => {
 
 		it("should handle missing URL gracefully", async () => {
 			const mockItem: CrawledData = {
-				url: undefined as any, // Intentionally missing URL
+				url: undefined as unknown as string, // Intentionally missing URL
 				title: "Article 1",
 				content: "Content 1",
 				crawledAt: new Date(),

src/tests/crawlers/extractors/ListingPageExtractor.test.ts

@@ -386,7 +386,7 @@ describe("ListingPageExtractor", () => {
 			...mockConfig,
 			listing: {
 				...mockConfig.listing,
-				shouldExcludeItem: vi.fn().mockImplementation((html, values) => {
+				shouldExcludeItem: vi.fn().mockImplementation((_html, values) => {
 					return values?.title === "Excluded Article";
 				}),
 			},