@xberg-io/opencode-xberg 1.0.14 → 1.1.1

package/.opencode/plugins/xberg.js

@@ -1,21 +1,19 @@
 // AI-RULEZ :: GENERATED FILE — DO NOT EDIT
-// Content-Hash: blake3:a176d5615df7d9fc0f850b5d83d3355f87d3045645f185d67c0d1e5edfb4a6c6
-// Source-Hash: blake3:c3730974b95d68f86536f7c420114fdefdaf54253473d6bec3cfefe6dacc7d4d
+// Content-Hash: blake3:0c4b20b2428ca03b76e22085bdcc856fbac85091cd3f6d157655d6c25c02714f
+// Source-Hash: blake3:745562ff11c7f58507a71dedd56c8d6eab478fe2122112e395cad42ab1f17172
 // Schema-Version: v1
 
-import {tool} from "@opencode-ai/plugin";
-import {spawn} from "node:child_process";
+import { tool } from "@opencode-ai/plugin";
+import { spawn } from "node:child_process";
 
 const schema = tool.schema;
 
-const wireFormat = schema.enum([ "text", "json", "toon" ])
-                       .default("json")
-                       .describe("CLI output format.");
+const wireFormat = schema.enum(["text", "json", "toon"]).default("json").describe("CLI output format.");
 
-const contentFormat =
-    schema.enum([ "plain", "markdown", "djot", "html", "json" ])
-        .optional()
-        .describe("Document content rendering format.");
+const contentFormat = schema
+  .enum(["plain", "markdown", "djot", "html", "json"])
+  .optional()
+  .describe("Document content rendering format.");
 
 function hasValue(value) {
   return value !== undefined && value !== null && value !== "";
@@ -35,7 +33,7 @@ function validateJson(value, name) {
   try {
     JSON.parse(value);
   } catch (error) {
-    throw new Error(`${name} must be valid JSON: ${error.message}`);
+    throw new Error(`${name} must be valid JSON: ${error.message}`, { cause: error });
   }
 }
 
@@ -44,10 +42,10 @@ function runCli(args, context) {
 
   return new Promise((resolve, reject) => {
     const child = spawn("xberg", args, {
-      cwd : directory,
-      env : process.env,
-      signal : context?.abort,
-      stdio : [ "ignore", "pipe", "pipe" ],
+      cwd: directory,
+      env: process.env,
+      signal: context?.abort,
+      stdio: ["ignore", "pipe", "pipe"],
     });
 
     const stdout = [];
@@ -58,10 +56,10 @@ function runCli(args, context) {
     child.on("error", (error) => {
       if (error.code === "ENOENT") {
         resolve({
-          title : "xberg CLI not found",
-          output :
-              "Install the xberg CLI with `brew install xberg-io/tap/xberg`, or run it via `npx -y @xberg-io/xberg-cli` / `uvx --from xberg-cli xberg`.",
-          metadata : {exitCode : 127, command : "xberg", subcommand : args[0]},
+          title: "xberg CLI not found",
+          output:
+            "Install the xberg CLI with `brew install xberg-io/tap/xberg`, or run it via `npx -y @xberg-io/xberg-cli` / `uvx --from xberg-cli xberg`.",
+          metadata: { exitCode: 127, command: "xberg", subcommand: args[0] },
         });
         return;
       }
@@ -70,70 +68,65 @@ function runCli(args, context) {
     child.on("close", (exitCode, signal) => {
       const stdoutText = Buffer.concat(stdout).toString("utf8").trim();
       const stderrText = Buffer.concat(stderr).toString("utf8").trim();
-      const output = [
-        stdoutText, stderrText && `stderr:\n${stderrText}`
-      ].filter(Boolean).join("\n\n");
+      const output = [stdoutText, stderrText && `stderr:\n${stderrText}`].filter(Boolean).join("\n\n");
 
       resolve({
-        title : exitCode === 0 ? `xberg ${args[0]}` : `xberg ${args[0]} failed`,
-        output : output || "(no output)",
-        metadata : {
+        title: exitCode === 0 ? `xberg ${args[0]}` : `xberg ${args[0]} failed`,
+        output: output || "(no output)",
+        metadata: {
           exitCode,
           signal,
-          command : "xberg",
-          subcommand : args[0],
+          command: "xberg",
+          subcommand: args[0],
         },
       });
     });
   });
 }
 
-export const XbergPlugin = async () => ({
-  tool : {
-    xberg_extract : tool({
-      description :
-          "Extract text, tables, metadata, and images from a local document with the xberg CLI.",
-      args : {
-        path : schema.string().min(1).describe("Path to the local document."),
-        format : wireFormat,
-        content_format : contentFormat,
-        mime_type : schema.string().min(1).optional().describe(
-            "Optional MIME type hint."),
-        config_json : schema.string().min(2).optional().describe(
-            "Optional ExtractionConfig JSON."),
-      },
-      async execute(args, context) {
-        validateJson(args.config_json, "config_json");
-
-        const cliArgs = [ "extract", args.path, "--format", args.format ];
-        pushOption(cliArgs, "--content-format", args.content_format);
-        pushOption(cliArgs, "--mime-type", args.mime_type);
-        pushOption(cliArgs, "--config-json", args.config_json);
-
-        return runCli(cliArgs, context);
-      },
-    }),
-    xberg_detect : tool({
-      description : "Detect the MIME type for a local file with the xberg CLI.",
-      args : {
-        path : schema.string().min(1).describe("Path to the local file."),
-        format : wireFormat,
-      },
-      async execute(args, context) {
-        return runCli([ "detect", args.path, "--format", args.format ],
-                      context);
-      },
-    }),
-    xberg_formats : tool({
-      description : "List document formats supported by the xberg CLI.",
-      args : {
-        format : wireFormat,
-      },
-      async execute(args, context) {
-        return runCli([ "formats", "--format", args.format ], context);
-      },
-    }),
-  },
-});
+export const XbergPlugin = () =>
+  Promise.resolve({
+    tool: {
+      xberg_extract: tool({
+        description: "Extract text, tables, metadata, and images from a local document with the xberg CLI.",
+        args: {
+          path: schema.string().min(1).describe("Path to the local document."),
+          format: wireFormat,
+          content_format: contentFormat,
+          mime_type: schema.string().min(1).optional().describe("Optional MIME type hint."),
+          config_json: schema.string().min(2).optional().describe("Optional ExtractionConfig JSON."),
+        },
+        async execute(args, context) {
+          validateJson(args.config_json, "config_json");
+
+          const cliArgs = ["extract", args.path, "--format", args.format];
+          pushOption(cliArgs, "--content-format", args.content_format);
+          pushOption(cliArgs, "--mime-type", args.mime_type);
+          pushOption(cliArgs, "--config-json", args.config_json);
+
+          return await runCli(cliArgs, context);
+        },
+      }),
+      xberg_detect: tool({
+        description: "Detect the MIME type for a local file with the xberg CLI.",
+        args: {
+          path: schema.string().min(1).describe("Path to the local file."),
+          format: wireFormat,
+        },
+        async execute(args, context) {
+          return await runCli(["detect", args.path, "--format", args.format], context);
+        },
+      }),
+      xberg_formats: tool({
+        description: "List document formats supported by the xberg CLI.",
+        args: {
+          format: wireFormat,
+        },
+        async execute(args, context) {
+          return await runCli(["formats", "--format", args.format], context);
+        },
+      }),
+    },
+  });
 
 export default XbergPlugin;

package/README.md

@@ -1,6 +1,6 @@
 # xberg
 
-Extract text, tables, metadata, and images from 101 document formats — PDF, Office, images with OCR, HTML, email, archives, academic — using the local `xberg` CLI in your agent.
+Extract text, tables, metadata, and images from 107 document formats — PDF, Office, images with OCR, HTML, email, archives, academic — using the local `xberg` CLI in your agent.
 
 <!-- ~keep TODO: add screenshot -->
 
@@ -51,7 +51,7 @@ sudo apt install tesseract-ocr-*   # Debian/Ubuntu
 
 | Skill | Trigger |
 |-------|---------|
-| **xberg** | Extract text, tables, metadata, and images from 101 document formats (PDF, Office, images, HTML, email, archives, academic) using Xberg. Use when writing code that calls Xberg APIs in Python, Node.js/TypeScript, Rust, or CLI. Covers installation, extraction (sync/async), configuration (OCR, chunking, output format), batch processing, error handling, and plugins. |
+| **xberg** | Extract text, tables, metadata, and images from 107 document formats (PDF, Office, images, HTML, email, archives, academic) using Xberg. Use when writing code that calls Xberg APIs in Python, Node.js/TypeScript, Rust, or CLI. Covers installation, extraction (sync/async), configuration (OCR, chunking, output format), batch processing, error handling, and plugins. |
 | **extracting-with-ocr** | Use when extracting text from scanned PDFs, photographed pages, or images that have no embedded text layer. Covers OCR backends, language packs, force-OCR, and performance tuning. |
 | **extracting-tables** | Use when extracting tabular data from PDFs, spreadsheets, or images. Covers layout-aware table detection, table model selection, output formats (markdown / JSON cells), and known limits. |
 | **chunking** | Use when splitting extracted text into chunks for LLM context windows or RAG ingestion. Covers chunk size, overlap, markdown/yaml/semantic chunkers, tokenizer-based sizing, and the standalone `chunk` command. |
@@ -65,7 +65,7 @@ sudo apt install tesseract-ocr-*   # Debian/Ubuntu
 |-----------|---------|
 | **CLI Reference** | All commands, flags, config precedence, exit codes |
 | **Configuration Reference** | TOML/YAML/JSON formats, auto-discovery, env vars, full schema |
-| **Supported Formats** | All 101 formats (115 file extensions) with file extensions and MIME types |
+| **Supported Formats** | Format families, extensions, capabilities, and authoritative discovery commands |
 | **Python API Reference** | All functions, config classes, plugin protocols, exact signatures |
 | **Node.js API Reference** | All functions, TypeScript interfaces, worker pool APIs |
 | **Rust API Reference** | All functions with feature gates, structs, Cargo.toml examples |

package/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@xberg-io/opencode-xberg",
-  "version": "1.0.14",
-  "description": "Local document extraction: text, tables, metadata, images from 101 formats with optional OCR.",
+  "version": "1.1.1",
+  "description": "Local document extraction: text, tables, metadata, images from 107 formats with optional OCR.",
   "keywords": [
     "document-intelligence",
     "extraction",