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]>
87 lines
2.8 KiB
TypeScript
87 lines
2.8 KiB
TypeScript
import mediaFilePath from "@/src/utils/media-file-path";
|
|
import type { BUN_SQLITE_COBBLE_MEDIA } from "@/db/types/db";
|
|
import { BotUploadFolder } from "@/src/dict/bot-file-dict";
|
|
import { logError } from "@/src/functions/backend/logger";
|
|
import recordBotFile from "./record-bot-file";
|
|
|
|
type Params = {
|
|
bot_id: number | string;
|
|
workspace_id?: number | string | null;
|
|
user_id: number | string;
|
|
media: BUN_SQLITE_COBBLE_MEDIA[];
|
|
};
|
|
|
|
/**
|
|
* Copies the files the user attached to a message into the conversation's
|
|
* folder (`uploads/<yyyy-mm>/<name>`), so they stay findable after the
|
|
* message scrolls away and a later run can find them. Best effort: a
|
|
* failure is logged, never shown, and the message still goes out.
|
|
*/
|
|
export default async function storeChatAttachments({
|
|
bot_id,
|
|
workspace_id,
|
|
user_id,
|
|
media,
|
|
}: Params) {
|
|
if (!media.length) return;
|
|
|
|
const folder = `${BotUploadFolder}/${new Date().toISOString().slice(0, 7)}`;
|
|
|
|
for (const file of media) {
|
|
try {
|
|
const absolute = mediaFilePath({ write_path: file.media_write_path });
|
|
|
|
if (!absolute) continue;
|
|
|
|
const source = Bun.file(absolute);
|
|
|
|
if (!(await source.exists())) continue;
|
|
|
|
/**
|
|
* Its name, made safe and unique enough that a second upload
|
|
* of "invoice.pdf" doesn't overwrite the first.
|
|
*/
|
|
const name = safeName({ name: file.title || `file-${file.id}` });
|
|
|
|
/**
|
|
* The text stays on the message's own `bot-attachment` row,
|
|
* where a reply reads it. Copying it onto the file's row kept
|
|
* the same text twice and left the copy behind when the
|
|
* upload was pruned; a bot reads the bytes with `read_file`
|
|
* instead.
|
|
*/
|
|
const saved = await recordBotFile({
|
|
bot_id,
|
|
scope: workspace_id ? "workspace" : "bot",
|
|
owner_id: workspace_id || bot_id,
|
|
path: `${folder}/${name}`,
|
|
data: new Uint8Array(await source.arrayBuffer()),
|
|
purpose: "upload",
|
|
source: "chat-upload",
|
|
media_type: (file.media_type as any) || undefined,
|
|
mime_type: file.mime_type || undefined,
|
|
user_id,
|
|
});
|
|
} catch (error) {
|
|
await logError({
|
|
title: `A chat attachment couldn't be saved to the bot's files`,
|
|
error,
|
|
metadata: { media_id: file.id, bot_id },
|
|
}).catch(() => {});
|
|
}
|
|
}
|
|
}
|
|
|
|
/**
|
|
* A file name that is safe on disk.
|
|
*/
|
|
function safeName({ name }: { name: string }) {
|
|
const cleaned = name
|
|
.replace(/[<>:"|?*/\\]/g, "-")
|
|
.replace(/\s+/g, " ")
|
|
.trim()
|
|
.slice(0, 100);
|
|
|
|
return cleaned || "file";
|
|
}
|