@v1nvn/readability-mcp 0.14.1 → 0.16.0

package/dist/assets/{cli-CYsWq1_a.js → cli-CCcnfTRC.js}

@@ -1,37 +1,39 @@
-import { m as readHtmlFile, t as extractArticleFromHtml } from "./extract-CZgSOqXG.js";
+import { m as readHtmlFile, t as extractArticleFromHtml } from "./extract-C55iDWx1.js";
+import "node:fs";
+import { Command, InvalidArgumentError, Option } from "commander";
+//#region ../core/dist/index.js
+function parseQuietly(program, args) {
+	try {
+		program.allowExcessArguments(false).exitOverride().configureOutput({
+			writeOut: () => void 0,
+			writeErr: () => void 0
+		}).parse([...args], { from: "user" });
+		return program;
+	} catch {
+		return;
+	}
+}
+//#endregion
 //#region src/cli.ts
-var USAGE = "Usage: readability-mcp extract [file.html] [--format md|json|html] [--max-chars N]";
 var FORMATS = [
 	"html",
 	"json",
 	"md"
 ];
-function isCliFormat(value) {
-	return value !== void 0 && FORMATS.includes(value);
+function parseMaxChars(value) {
+	const n = Number(value);
+	if (!Number.isInteger(n)) throw new InvalidArgumentError("must be an integer");
+	return n;
+}
+function buildProgram() {
+	return new Command("readability-mcp extract").argument("[file]", "HTML file; stdin when omitted").addOption(new Option("--format <fmt>", "output format").choices(FORMATS).default("md")).option("--max-chars <n>", "truncate the output", parseMaxChars);
 }
 function parseArgs(argv) {
-	let file;
-	let format = "md";
-	let maxChars;
-	const rest = argv.slice(1);
-	for (let i = 0; i < rest.length; i++) {
-		const arg = rest[i];
-		if (arg === "--format") {
-			const value = rest.at(++i);
-			if (!isCliFormat(value)) return;
-			format = value;
-		} else if (arg === "--max-chars") {
-			const value = rest.at(++i);
-			if (value === void 0) return;
-			const n = Number(value);
-			if (!Number.isInteger(n)) return;
-			maxChars = n;
-		} else if (arg.startsWith("--")) return;
-		else if (file === void 0) file = arg;
-		else return;
-	}
+	const program = parseQuietly(buildProgram(), argv.slice(1));
+	if (program === void 0) return;
+	const { format, maxChars } = program.opts();
 	return {
-		file,
+		file: program.args.at(0),
 		format,
 		maxChars
 	};
@@ -49,12 +51,12 @@ function payloadText(result) {
 }
 async function runCli(argv) {
 	if (argv[0] !== "extract") {
-		process.stderr.write(`${USAGE}\n`);
+		process.stderr.write(buildProgram().helpInformation());
 		return 2;
 	}
 	const parsed = parseArgs(argv);
 	if (parsed === void 0) {
-		process.stderr.write(`${USAGE}\n`);
+		process.stderr.write(buildProgram().helpInformation());
 		return 2;
 	}
 	try {
@@ -80,4 +82,4 @@ async function runCli(argv) {
 //#endregion
 export { runCli };
 
-//# sourceMappingURL=cli-CYsWq1_a.js.map
+//# sourceMappingURL=cli-CCcnfTRC.js.map

package/dist/assets/cli-CCcnfTRC.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"cli-CCcnfTRC.js","names":[],"sources":["../../../core/dist/index.js","../../src/cli.ts"],"sourcesContent":["import { existsSync, readFileSync, readdirSync, statSync } from \"node:fs\";\nimport { homedir } from \"node:os\";\nimport { join } from \"node:path\";\n//#region src/hook.ts\n/**\n* Read the Claude Code hook event JSON from stdin; empty or unparseable input\n* yields an empty event, never a thrown error — a hook must always answer.\n*/\nfunction readHookEvent(stream = process.stdin) {\n\treturn new Promise((resolve) => {\n\t\tlet data = \"\";\n\t\tstream.setEncoding(\"utf8\");\n\t\tstream.on(\"data\", (chunk) => {\n\t\t\tdata += chunk;\n\t\t});\n\t\tstream.on(\"end\", () => {\n\t\t\ttry {\n\t\t\t\tresolve(JSON.parse(data));\n\t\t\t} catch {\n\t\t\t\tresolve({});\n\t\t\t}\n\t\t});\n\t\tstream.on(\"error\", () => {\n\t\t\tresolve({});\n\t\t});\n\t});\n}\n/**\n* Which transcript lastReply should read, per the hook event: transcript_path\n* when it names a real file, else session_id, else nothing (lastReply then\n* falls back to the newest session for the current project).\n*/\nfunction replyTarget(event) {\n\tif (event.transcript_path !== void 0 && isFile$1(event.transcript_path)) return event.transcript_path;\n\treturn event.session_id || void 0;\n}\nfunction isFile$1(path) {\n\ttry {\n\t\treturn statSync(path).isFile();\n\t} catch {\n\t\treturn false;\n\t}\n}\n/**\n* Print the UserPromptExpansion decision for a zero-token command: `block`\n* keeps the command from reaching the model, with the output as the `reason`.\n*/\nfunction emitHookBlock(reason) {\n\tprocess.stdout.write(`${JSON.stringify({\n\t\tdecision: \"block\",\n\t\treason\n\t})}\\n`);\n}\n//#endregion\n//#region src/cli.ts\nfunction parseQuietly(program, args) {\n\ttry {\n\t\tprogram.allowExcessArguments(false).exitOverride().configureOutput({\n\t\t\twriteOut: () => void 0,\n\t\t\twriteErr: () => void 0\n\t\t}).parse([...args], { from: \"user\" });\n\t\treturn program;\n\t} catch {\n\t\treturn;\n\t}\n}\nfunction printUsageAndExit(program) {\n\tconsole.error(program.helpInformation());\n\tprocess.exit(1);\n}\nasync function hookOrPrint(hook, failure, run, stdin = process.stdin) {\n\tif (hook) {\n\t\tlet reason;\n\t\ttry {\n\t\t\treason = await run(await readHookEvent(stdin));\n\t\t} catch (e) {\n\t\t\treason = `${failure}: ${e.message}`;\n\t\t}\n\t\temitHookBlock(reason);\n\t\treturn;\n\t}\n\ttry {\n\t\tconsole.log(await run(void 0));\n\t} catch (e) {\n\t\tconsole.error(e.message);\n\t\tprocess.exit(1);\n\t}\n}\n//#endregion\n//#region src/last-reply.ts\nfunction isFile(path) {\n\ttry {\n\t\treturn statSync(path).isFile();\n\t} catch {\n\t\treturn false;\n\t}\n}\nfunction textBlocks(entry) {\n\tconst content = entry.message?.content;\n\tif (entry.type !== \"assistant\" || !Array.isArray(content)) return;\n\tconst blocks = content.filter((b) => typeof b === \"object\" && b !== null && b.type === \"text\");\n\treturn blocks.length > 0 ? blocks : void 0;\n}\n/**\n* The last assistant text reply from a Claude Code session, reproducing Claude\n* Code's `/copy` byte-for-byte: the last assistant entry that contains a\n* `text` block, only its `text` block(s) (tool_use / thinking dropped), blocks\n* joined with a blank line, and no trailing newline.\n*\n* @param arg a transcript file, a session UUID under the project dir, or\n*   nothing to use the newest session for the current project.\n*/\nfunction lastReply(arg) {\n\tconst claudeDir = process.env.CLAUDE_DIR ?? join(homedir(), \".claude\");\n\tconst proj = (process.env.CLAUDE_PROJECT_DIR ?? process.cwd()).replaceAll(\"/\", \"-\");\n\tconst projDir = join(claudeDir, \"projects\", proj);\n\tlet file;\n\tif (arg !== void 0) file = isFile(arg) ? arg : join(projDir, `${arg}.jsonl`);\n\telse if (existsSync(projDir)) {\n\t\tconst newest = readdirSync(projDir).filter((f) => f.endsWith(\".jsonl\")).map((f) => ({\n\t\t\tf,\n\t\t\tmtimeMs: statSync(join(projDir, f)).mtimeMs\n\t\t})).sort((a, b) => b.mtimeMs - a.mtimeMs).at(0);\n\t\tif (newest) file = join(projDir, newest.f);\n\t}\n\tif (file === void 0 || !isFile(file)) throw new Error(`no session transcript found in ${projDir}`);\n\tlet last;\n\tfor (const line of readFileSync(file, \"utf8\").split(\"\\n\")) {\n\t\tif (!line.includes(\"\\\"assistant\\\"\")) continue;\n\t\tlet entry;\n\t\ttry {\n\t\t\tentry = JSON.parse(line);\n\t\t} catch {\n\t\t\tcontinue;\n\t\t}\n\t\tconst blocks = textBlocks(entry);\n\t\tif (blocks) last = blocks;\n\t}\n\treturn (last ?? []).map((b) => b.text ?? \"\").join(\"\\n\\n\");\n}\n//#endregion\n//#region src/text-format.ts\n/**\n* Plain-text rendering primitives shared by the zai and tokens report\n* renderers. Output targets a monospace terminal / hook-block `reason`, so\n* everything here is fixed-width: padding, block-glyph bars, and compact\n* number formatting.\n*/\nvar MONTHS = [\n\t\"Jan\",\n\t\"Feb\",\n\t\"Mar\",\n\t\"Apr\",\n\t\"May\",\n\t\"Jun\",\n\t\"Jul\",\n\t\"Aug\",\n\t\"Sep\",\n\t\"Oct\",\n\t\"Nov\",\n\t\"Dec\"\n];\nvar EIGHTHS = [\n\t\"\",\n\t\"▏\",\n\t\"▎\",\n\t\"▍\",\n\t\"▌\",\n\t\"▋\",\n\t\"▊\",\n\t\"▉\"\n];\nfunction fmtTokens(n) {\n\tif (n == null || Number.isNaN(n)) return \"—\";\n\tif (n >= 1e9) return (n / 1e9).toFixed(1) + \"B\";\n\tif (n >= 1e6) return (n / 1e6).toFixed(1) + \"M\";\n\tif (n >= 1e3) return (n / 1e3).toFixed(1) + \"K\";\n\treturn String(n);\n}\nfunction fmtNum(n) {\n\treturn (n || 0).toLocaleString(\"en-US\");\n}\nfunction padR(s, n) {\n\treturn s.length >= n ? s : s + \" \".repeat(n - s.length);\n}\nfunction padL(s, n) {\n\treturn s.length >= n ? s : \" \".repeat(n - s.length) + s;\n}\n/** Fixed-width bar field (width cols): █ blocks + an eighth-fraction + trailing spaces. */\nfunction barField(v, max, width) {\n\tif (!v || v <= 0 || max <= 0) return \" \".repeat(width);\n\tconst scaled = v / max * width;\n\tlet full = Math.floor(scaled);\n\tlet fi = Math.round((scaled - full) * 8);\n\tif (fi === 8) {\n\t\tfull += 1;\n\t\tfi = 0;\n\t}\n\tif (full === 0 && fi === 0) fi = 1;\n\tlet s = \"█\".repeat(Math.min(full, width));\n\tif (full < width && fi > 0) s += EIGHTHS[fi];\n\tif (s.length < width) s += \" \".repeat(width - s.length);\n\treturn s.slice(0, width);\n}\n/** Filled/empty meter: █ for used, ░ for remaining. */\nfunction meter(pct, width) {\n\tlet filled = Math.round((pct || 0) / 100 * width);\n\tfilled = Math.max(0, Math.min(width, filled));\n\treturn \"█\".repeat(filled) + \"░\".repeat(width - filled);\n}\n//#endregion\nexport { MONTHS, barField, emitHookBlock, fmtNum, fmtTokens, hookOrPrint, lastReply, meter, padL, padR, parseQuietly, printUsageAndExit, readHookEvent, replyTarget };\n\n//# sourceMappingURL=index.js.map","import { parseQuietly } from '@v1nvn/agentic-core';\nimport { Command, InvalidArgumentError, Option } from 'commander';\n\nimport { extractArticleFromHtml } from './tools/extract.js';\nimport { readHtmlFile } from './tools/html-source.js';\n\nimport type { CallToolResult } from '@modelcontextprotocol/sdk/types.js';\nimport type { Readable } from 'node:stream';\n\ntype CliFormat = 'html' | 'json' | 'md';\n\nexport interface ParsedArgs {\n  readonly file: string | undefined;\n  readonly format: CliFormat;\n  readonly maxChars: number | undefined;\n}\n\nconst FORMATS: readonly CliFormat[] = ['html', 'json', 'md'];\n\nfunction parseMaxChars(value: string): number {\n  const n = Number(value);\n  if (!Number.isInteger(n)) {\n    throw new InvalidArgumentError('must be an integer');\n  }\n  return n;\n}\n\nexport function buildProgram(): Command {\n  return new Command('readability-mcp extract')\n    .argument('[file]', 'HTML file; stdin when omitted')\n    .addOption(\n      new Option('--format <fmt>', 'output format')\n        .choices(FORMATS)\n        .default('md'),\n    )\n    .option('--max-chars <n>', 'truncate the output', parseMaxChars);\n}\n\nexport function parseArgs(argv: readonly string[]): ParsedArgs | undefined {\n  const program = parseQuietly(buildProgram(), argv.slice(1));\n  if (program === undefined) {\n    return undefined;\n  }\n  const { format, maxChars } = program.opts<{\n    format: CliFormat;\n    maxChars: number | undefined;\n  }>();\n  return { file: program.args.at(0), format, maxChars };\n}\n\n// The stream is injected rather than reading process.stdin directly so the\n// path is testable. Chunks may be Buffer (process.stdin) or string\n// (Readable.from), so both are handled.\nexport async function readHtml(\n  file: string | undefined,\n  stream: Readable,\n): Promise<string> {\n  if (file !== undefined) {\n    return readHtmlFile(file);\n  }\n  const chunks: string[] = [];\n  for await (const chunk of stream) {\n    if (typeof chunk === 'string') {\n      chunks.push(chunk);\n    } else {\n      chunks.push(Buffer.from(chunk as Uint8Array).toString('utf8'));\n    }\n  }\n  return chunks.join('');\n}\n\nfunction payloadText(result: CallToolResult): string {\n  const first = result.content.at(0);\n  return first !== undefined && 'text' in first ? first.text : '';\n}\n\nexport async function runCli(argv: readonly string[]): Promise<number> {\n  if (argv[0] !== 'extract') {\n    process.stderr.write(buildProgram().helpInformation());\n    return 2;\n  }\n\n  const parsed = parseArgs(argv);\n  if (parsed === undefined) {\n    process.stderr.write(buildProgram().helpInformation());\n    return 2;\n  }\n\n  try {\n    const html = await readHtml(parsed.file, process.stdin);\n    // json reuses the markdown pipeline; the structured object is serialized below.\n    const pipelineFormat = parsed.format === 'html' ? 'html' : 'markdown';\n    const result = extractArticleFromHtml({\n      html,\n      format: pipelineFormat,\n      ...(parsed.maxChars !== undefined ? { maxChars: parsed.maxChars } : {}),\n    });\n\n    if (result.isError) {\n      process.stderr.write(`${payloadText(result)}\\n`);\n      return 1;\n    }\n\n    if (parsed.format === 'json') {\n      process.stdout.write(\n        `${JSON.stringify(result.structuredContent, null, 2)}\\n`,\n      );\n    } else {\n      process.stdout.write(`${payloadText(result)}\\n`);\n    }\n    return 0;\n  } catch (err) {\n    process.stderr.write(\n      `${err instanceof Error ? err.message : String(err)}\\n`,\n    );\n    return 1;\n  }\n}\n"],"mappings":";;;;AAuDA,SAAS,aAAa,SAAS,MAAM;CACpC,IAAI;EACH,QAAQ,qBAAqB,KAAK,CAAC,CAAC,aAAa,CAAC,CAAC,gBAAgB;GAClE,gBAAgB,KAAK;GACrB,gBAAgB,KAAK;EACtB,CAAC,CAAC,CAAC,MAAM,CAAC,GAAG,IAAI,GAAG,EAAE,MAAM,OAAO,CAAC;EACpC,OAAO;CACR,QAAQ;EACP;CACD;AACD;;;AChDA,IAAM,UAAgC;CAAC;CAAQ;CAAQ;AAAI;AAE3D,SAAS,cAAc,OAAuB;CAC5C,MAAM,IAAI,OAAO,KAAK;CACtB,IAAI,CAAC,OAAO,UAAU,CAAC,GACrB,MAAM,IAAI,qBAAqB,oBAAoB;CAErD,OAAO;AACT;AAEA,SAAgB,eAAwB;CACtC,OAAO,IAAI,QAAQ,yBAAyB,CAAC,CAC1C,SAAS,UAAU,+BAA+B,CAAC,CACnD,UACC,IAAI,OAAO,kBAAkB,eAAe,CAAC,CAC1C,QAAQ,OAAO,CAAC,CAChB,QAAQ,IAAI,CACjB,CAAC,CACA,OAAO,mBAAmB,uBAAuB,aAAa;AACnE;AAEA,SAAgB,UAAU,MAAiD;CACzE,MAAM,UAAU,aAAa,aAAa,GAAG,KAAK,MAAM,CAAC,CAAC;CAC1D,IAAI,YAAY,KAAA,GACd;CAEF,MAAM,EAAE,QAAQ,aAAa,QAAQ,KAGlC;CACH,OAAO;EAAE,MAAM,QAAQ,KAAK,GAAG,CAAC;EAAG;EAAQ;CAAS;AACtD;AAKA,eAAsB,SACpB,MACA,QACiB;CACjB,IAAI,SAAS,KAAA,GACX,OAAO,aAAa,IAAI;CAE1B,MAAM,SAAmB,CAAC;CAC1B,WAAW,MAAM,SAAS,QACxB,IAAI,OAAO,UAAU,UACnB,OAAO,KAAK,KAAK;MAEjB,OAAO,KAAK,OAAO,KAAK,KAAmB,CAAC,CAAC,SAAS,MAAM,CAAC;CAGjE,OAAO,OAAO,KAAK,EAAE;AACvB;AAEA,SAAS,YAAY,QAAgC;CACnD,MAAM,QAAQ,OAAO,QAAQ,GAAG,CAAC;CACjC,OAAO,UAAU,KAAA,KAAa,UAAU,QAAQ,MAAM,OAAO;AAC/D;AAEA,eAAsB,OAAO,MAA0C;CACrE,IAAI,KAAK,OAAO,WAAW;EACzB,QAAQ,OAAO,MAAM,aAAa,CAAC,CAAC,gBAAgB,CAAC;EACrD,OAAO;CACT;CAEA,MAAM,SAAS,UAAU,IAAI;CAC7B,IAAI,WAAW,KAAA,GAAW;EACxB,QAAQ,OAAO,MAAM,aAAa,CAAC,CAAC,gBAAgB,CAAC;EACrD,OAAO;CACT;CAEA,IAAI;EACF,MAAM,OAAO,MAAM,SAAS,OAAO,MAAM,QAAQ,KAAK;EAEtD,MAAM,iBAAiB,OAAO,WAAW,SAAS,SAAS;EAC3D,MAAM,SAAS,uBAAuB;GACpC;GACA,QAAQ;GACR,GAAI,OAAO,aAAa,KAAA,IAAY,EAAE,UAAU,OAAO,SAAS,IAAI,CAAC;EACvE,CAAC;EAED,IAAI,OAAO,SAAS;GAClB,QAAQ,OAAO,MAAM,GAAG,YAAY,MAAM,EAAE,GAAG;GAC/C,OAAO;EACT;EAEA,IAAI,OAAO,WAAW,QACpB,QAAQ,OAAO,MACb,GAAG,KAAK,UAAU,OAAO,mBAAmB,MAAM,CAAC,EAAE,GACvD;OAEA,QAAQ,OAAO,MAAM,GAAG,YAAY,MAAM,EAAE,GAAG;EAEjD,OAAO;CACT,SAAS,KAAK;EACZ,QAAQ,OAAO,MACb,GAAG,eAAe,QAAQ,IAAI,UAAU,OAAO,GAAG,EAAE,GACtD;EACA,OAAO;CACT;AACF"}

package/dist/assets/{extract-CZgSOqXG.js → extract-C55iDWx1.js}

@@ -13,7 +13,7 @@ import TurndownService from "turndown";
 import { gfm } from "turndown-plugin-gfm";
 var package_default = {
 	name: "@v1nvn/readability-mcp",
-	version: "0.14.1",
+	version: "0.16.0",
 	description: "MCP server that turns rendered (post-JS) HTML into clean Markdown + metadata via Readability, Turndown, and DOMPurify.",
 	type: "module",
 	main: "dist/index.js",
@@ -44,12 +44,14 @@ var package_default = {
 	},
 	files: ["dist"],
 	publishConfig: { "access": "public" },
-	engines: { "node": ">=22" },
+	engines: { "node": ">=22.22.2" },
 	dependencies: {
 		"@modelcontextprotocol/sdk": "^1.29.0",
 		"@mozilla/readability": "^0.6.0",
+		"@v1nvn/agentic-core": "workspace:^",
+		"commander": "^15.0.0",
 		"dompurify": "^3.4.12",
-		"jsdom": "^29.1.1",
+		"jsdom": "^30.0.1",
 		"remark-gfm": "^4.0.1",
 		"remark-parse": "^11.0.0",
 		"turndown": "^7.2.4",
@@ -2731,4 +2733,4 @@ function registerExtractTool(server) {
 //#endregion
 export { outlineInputShape as $, extractListOutputShape as A, extractLinksInputShape as B, resolveLazyImages as C, chunkTextOutputShape as D, isElement as E, chunkTextInputSchema as F, extractSectionInputSchema as G, extractListInputShape as H, chunkTextInputShape as I, extractTablesInputShape as J, extractSectionInputShape as K, extractGridInputSchema as L, extractTablesOutputShape as M, outlineOutputShape as N, extractGridOutputShape as O, outputSchemaShape as P, outlineInputSchema as Q, extractGridInputShape as R, normalizeDocument as S, buildDocument as T, extractMetadataInputSchema as U, extractListInputSchema as V, extractMetadataInputShape as W, htmlToMarkdownInputShape as X, htmlToMarkdownInputSchema as Y, localPathField as Z, detectGating as _, sanitizeHtml as a, registerResources as at, isReaderable as b, computeTextMetrics as c, renderTable as d, selectorsSchema as et, resolveHeaderKeys as f, absolutize as g, detectPagination as h, toMarkdown as i, toErrorResult as it, extractMetadataOutputShape as j, extractLinksOutputShape as k, nonEmpty as l, readHtmlFile as m, registerExtractTool as n, logger as nt, formatPayload as o, loadConfig as ot, resolveCellText as p, extractTablesInputSchema as q, truncateMarkdown as r, ExtractionError as rt, resolveMetadata as s, extractArticleFromHtml as t, chunkMarkdown as tt, parseTableMatrix as u, TraceCollector as v, resolveReadabilityOptions as w, applySelectors as x, assembleDiagnostics as y, extractLinksInputSchema as z };
 
-//# sourceMappingURL=extract-CZgSOqXG.js.map
+//# sourceMappingURL=extract-C55iDWx1.js.map