Add bots files handling logic

2026-10-21 17:56:09 +01:00
parent b0af4db1bf
commit d17a4a7bdd
97 changed files with 5843 additions and 41 deletions
@@ -0,0 +1,93 @@
+import BunSQLite from "@moduletrace/bun-sqlite";
+import type { BUN_SQLITE_COBBLE_MEDIA } from "@/db/types/db";
+import { BotUploadFolder } from "@/src/dict/bot-file-dict";
+import enqueueFileIngest from "@/src/file-ingest/enqueue-file-ingest";
+import { logError } from "@/src/functions/backend/logger";
+import grabDirNames from "@/src/utils/grab-dir-names";
+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 searchable 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 { DATA_DIR } = grabDirNames();
+    const folder = `${BotUploadFolder}/${new Date().toISOString().slice(0, 7)}`;
+
+    for (const file of media) {
+        try {
+            if (!file.media_write_path) continue;
+
+            const source = Bun.file(`${DATA_DIR}/${file.media_write_path}`);
+
+            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-${file.id}` });
+
+            const saved = await recordBotFile({
+                bot_id,
+                scope: workspace_id ? "workspace" : "bot",
+                owner_id: workspace_id || bot_id,
+                path: `${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,
+            });
+
+            /**
+             * The same text the upload already extracted, so a PDF isn't
+             * unpacked a second time.
+             */
+            if (file.text_content && saved.media_id) {
+                await BunSQLite.sql({
+                    sql: `UPDATE media SET text_content = ? WHERE id = ?`,
+                    values: [file.text_content, saved.media_id],
+                }).catch(() => {});
+            }
+
+            await enqueueFileIngest({ file_id: saved.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";
+}