dorshitrit/document-reader
v0.1.0
Extract bounded text from PDF, Office and supported text documents. Use file readers for source code.
What this package declares
The file a client reads when it loads this plugin, exactly as this revision carries it.
plugin.json
{
"$schema": "https://agent-plugins.org/schemas/1.0.0/plugin.schema.json",
"name": "document-reader",
"version": "0.1.0",
"description": "Extract bounded text from PDF, Office and supported text documents. Use file readers for source code.",
"extensions": {
"ai.abot.runtime": {
"version": 1,
"entrypoint": "./src/index.cjs",
"catalogGroups": ["read"],
"capabilities": {
"document_reader": {
"description": "Document extraction, not source-code reading. For code (.js, .ts, .html, .css, etc.), select read_one_file or inspect_target when available. Supported documents: PDF, DOCX, XLSX, PPTX, TXT, CSV, Markdown (.md), JSON and RTF. Use source for an attachment id/name or configured-root path; use source_mode=working_path with path beneath the execution working directory. Returns bounded text and logical identities, never physical paths. Changing source_mode does not change supported formats.",
"routingCapability": "filesystem_inspection",
"developmentRoles": ["inspect", "verify"],
"eventPresentation": {
"metadata": {
"source": { "param": "source", "kind": "string" },
"displayTarget": { "param": "path", "kind": "string" },
"sourceMode": { "param": "source_mode", "kind": "string" },
"startChar": { "param": "start_char", "kind": "number" },
"maxChars": { "param": "max_chars", "kind": "number" }
},
"resultMetadata": {
"outputPreview": { "path": "output", "kind": "preview" },
"startChar": { "path": "data.startChar", "kind": "number" },
"endChar": { "path": "data.endChar", "kind": "number" },
"totalCharacters": { "path": "data.totalCharacters", "kind": "number" },
"inputBytes": { "path": "data.inputBytes", "kind": "number" },
"sourceTruncated": { "path": "data.truncated", "kind": "boolean" }
}
},
"runtimePathBindings": [
{
"operationId": "read_document",
"param": "path",
"base": "worker_working_directory",
"default": "."
}
],
"skills": ["document_reader_skill"],
"operations": {
"read_document": {
"summary": "Extract document text, not source code. For .js, .ts, .html, .css and other code files, use read_one_file or inspect_target when available. Accepts only PDF, DOCX, XLSX, PPTX, TXT, CSV, MD, JSON and RTF; returns one bounded character window.",
"outputChannels": {"text": "content", "data": "metadata"},
"attachmentInput": {
"param": "source",
"acceptedMimeTypes": [
"application/pdf",
"application/vnd.openxmlformats-officedocument.wordprocessingml.document",
"application/vnd.openxmlformats-officedocument.spreadsheetml.sheet",
"application/vnd.openxmlformats-officedocument.presentationml.presentation",
"text/plain",
"text/csv",
"text/markdown",
"application/json",
"application/rtf"
],
"mode": { "param": "source_mode", "value": "source" }
},
"input": {
"type": "object",
"additionalProperties": false,
"properties": {
"source_mode": {
"type": "string",
"enum": ["source", "working_path"]
},
"source": {
"type": "string",
"minLength": 1,
"maxLength": 4096
},
"path": {
"type": "string",
"minLength": 1,
"maxLength": 4096
},
"start_char": {
"type": "integer",
"minimum": 0,
"maximum": 10000000
},
"max_chars": {
"type": "integer",
"minimum": 1000,
"maximum": 40000
}
},
"required": []
},
"effect": "read_only",
"approval": "request_policy"
}
}
}
}
}
}
}
Client extensions
Data this package carries for particular clients. The directory lists the clients named and never reads what is addressed to them.
- ai.abot.runtime