tbenandClaude Opus 5.5
ac3ebc43d4
Every bot file was chunked into bot_file_chunks and embedded into bot_file_vectors, and uploads kept their extracted text in media.text_content, which together took most of the database. Bot files are no longer indexed: bots find them by name or path with list_files and read them with read_file, and search_files, ingest_file and the files modal's re-read button are gone. Attachments keep no text; a reply reads a document from the file. Only knowledgebase documents keep text. The schema drops both tables and the ingest columns. At boot, dropStoredFileText removes what older versions stored (file jobs, upload text) and vacuums once much of the database is free. The media:prune-text script it replaces is removed. Co-Authored-By: Claude Opus 5.5 <[email protected]>
90 lines
3.6 KiB
TypeScript
90 lines
3.6 KiB
TypeScript
import { z } from "zod";
|
|
import { AppData } from "@/src/data/app-data";
|
|
import listBotFiles from "@/src/functions/backend/db/bot-files/list-bot-files";
|
|
import folderRef from "@/src/utils/folder-ref";
|
|
import type { HarnessTool } from "../../types";
|
|
import { fileRef, formatBytes, type StorageToolContext } from "./storage-tool-context";
|
|
|
|
type Args = {
|
|
folder?: string;
|
|
search?: string;
|
|
recursive?: boolean;
|
|
scope?: string;
|
|
};
|
|
|
|
/**
|
|
* Lists a bot's files: one folder's, or everything under it, or whatever
|
|
* matches a name. Each file comes with its `[file:ID]` ref so the bot can
|
|
* read it, and the answer names the folder it is in with a folder ref, so a
|
|
* bot that points at "everything in reports/" writes something the user can
|
|
* actually open.
|
|
*/
|
|
export default function listFilesTool(context: StorageToolContext): HarnessTool<Args> {
|
|
return {
|
|
name: "list_files",
|
|
description: `List the files you have saved, newest first: one folder's with "folder", everything with "recursive", or the ones whose name or path has "search". Each line has its path, size and [file:ID] ref (e.g. [file:12]) to read it. The answer also names the folder as a folder ref, which opens it in Files without downloading anything: a file is a [file:ID] ref, a folder is a [folder:...] ref.`,
|
|
schema: z.object({
|
|
folder: z.string().max(AppData.BotFilePathMaxChars).optional(),
|
|
search: z.string().max(120).optional(),
|
|
recursive: z.boolean().optional(),
|
|
scope: z
|
|
.string()
|
|
.optional()
|
|
.describe(`"bot:<id>" or "workspace:<id>", to look in one of your directories only`),
|
|
}),
|
|
run: async ({ args }) => {
|
|
const folder = args.folder?.trim() || "";
|
|
|
|
const files = await listBotFiles({
|
|
scopes: context.scopes,
|
|
folder,
|
|
recursive: args.recursive,
|
|
search: args.search,
|
|
});
|
|
|
|
if (!files.length) {
|
|
return folder
|
|
? `Nothing in ${folder}.`
|
|
: `You have no files yet. Write one with write_file.`;
|
|
}
|
|
|
|
const lines = files.map((file) => {
|
|
const where = file.scope == "workspace" ? ` (workspace ${file.owner_id})` : "";
|
|
|
|
return `- ${file.path} - ${formatBytes({ bytes: Number(file.size) || 0 })}${where} ${fileRef({ file_id: file.id! })}`;
|
|
});
|
|
|
|
const more =
|
|
files.length >= AppData.BotFileListMaxItems
|
|
? `\n(Showing the first ${AppData.BotFileListMaxItems}. Narrow it with "folder" or "search".)`
|
|
: "";
|
|
|
|
return `${files.length} file(s):\n${lines.join("\n")}${more}\n\nThe folder: ${folderRefFor({ files, folder, scopes: context.scopes })}`;
|
|
},
|
|
};
|
|
}
|
|
|
|
/**
|
|
* The folder the listing is about, as a folder ref the bot can put in a
|
|
* message: the one it asked for, else the one the first file is in. Its
|
|
* volume is the scope the file lives in.
|
|
*/
|
|
function folderRefFor({
|
|
files,
|
|
folder,
|
|
scopes,
|
|
}: {
|
|
files: { scope?: string | null; owner_id?: number | string | null; folder?: string | null }[];
|
|
folder: string;
|
|
scopes: StorageToolContext["scopes"];
|
|
}) {
|
|
const first = files[0];
|
|
const scope = first
|
|
? scopes.find((it) => it.scope == first.scope && Number(it.owner_id) == Number(first.owner_id))
|
|
: scopes[0];
|
|
const path = folder || first?.folder || "";
|
|
const volume = scope?.scope == "workspace" ? "workspace" : "bot";
|
|
|
|
return folderRef({ volume, owner_id: scope?.owner_id || 0, path });
|
|
}
|