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]>
66 lines
2.4 KiB
TypeScript
66 lines
2.4 KiB
TypeScript
import { AppData } from "@/src/data/app-data";
|
|
import type { BotFileScopesPayload } from "@/src/types";
|
|
import grabMediaURL from "../../media/grab-media-url";
|
|
import grabBotFileQuotaBytes, { grabBotFileQuotaMb } from "./grab-bot-file-quota-bytes";
|
|
import grabStorageUsage from "./grab-storage-usage";
|
|
import listBotFiles from "./list-bot-files";
|
|
|
|
type Params = {
|
|
bot_id: number;
|
|
/**
|
|
* The workspace the conversation is in: its shared folder, else the
|
|
* bot's own.
|
|
*/
|
|
workspace_id?: number | string | null;
|
|
};
|
|
|
|
/**
|
|
* A conversation's files, for its page props: the folder it works in
|
|
* (a workspace's shared one, else the bot's own), its latest
|
|
* `AppData.BotFilesPageSize` of them, and the usage against the quota.
|
|
* The full list (folders, search, older files) loads in the files modal.
|
|
*
|
|
* It takes the whole folder tree, not just its top level: a bot saves into
|
|
* paths like `reports/` or `seo/coderank/`, and a file chip in a message
|
|
* can only find the file it names among these, so a top-level-only list
|
|
* left every nested `[file:ID]` unclickable plain text in the chat.
|
|
*/
|
|
export default async function grabConversationFiles({
|
|
bot_id,
|
|
workspace_id,
|
|
}: Params): Promise<BotFileScopesPayload> {
|
|
const scope = workspace_id
|
|
? ({ scope: "workspace", owner_id: Number(workspace_id) } as const)
|
|
: ({ scope: "bot", owner_id: Number(bot_id) } as const);
|
|
|
|
const [files, usage, quota_bytes, quota_mb] = await Promise.all([
|
|
listBotFiles({ scopes: [scope], recursive: true, limit: AppData.BotFilesPageSize }),
|
|
grabStorageUsage(scope),
|
|
grabBotFileQuotaBytes(),
|
|
grabBotFileQuotaMb(),
|
|
]);
|
|
|
|
return {
|
|
files: files.map((file) => {
|
|
const { media_url } = grabMediaURL({ media: { id: file.media_id } as any });
|
|
|
|
return {
|
|
id: Number(file.id),
|
|
name: file.name || "",
|
|
path: file.path || "",
|
|
size: Number(file.size) || 0,
|
|
media_type: String(file.media_type || "document"),
|
|
purpose: String(file.purpose || "writing"),
|
|
scope: String(file.scope || "bot"),
|
|
owner_id: Number(file.owner_id) || 0,
|
|
created_at: Number(file.created_at) || 0,
|
|
url: media_url || "",
|
|
};
|
|
}),
|
|
folders: [],
|
|
usage,
|
|
quota_bytes,
|
|
quota_mb,
|
|
};
|
|
}
|