Stop storing raw file bytes in media.text_content

`text_content` is an extracted-text cache, but nothing stopped it from
holding a dump of bytes:

- `fileToText` ended its switch with `default: return buffer.toString("utf-8")`
  and defaulted a missing extension to "txt", so any binary was decoded.
- Both extraction callers gated on `media_type == "document"`, and
  `attachmentFileKind` classes everything non-image/audio/video as a
  document: an SVG, a zip, a spreadsheet, a .bin.
- Nothing capped the length, so a 20 MB attachment could leave 20 MB of
  text in the database.
- `storeChatAttachments` copied the text onto a second `media` row, and
  `SELECT m.*` pulled the column into page props and API responses.

On a real install an SVG held 6852 characters of markup and a
`.designcraft` file held 142 KB of raw bytes.

Changes:

- `file-to-text.ts` lists the text extensions explicitly and returns
  undefined for anything else; no extension is no text.
- `can-extract-text.ts` is the one allowlist (reusing
  `BotTextFileExtensions`), used by both upload routes and by
  `uploadAndRecordMedia`; `extension-of.ts` is shared with the storage
  catalog instead of duplicated.
- `BotAttachmentTextStoreMaxChars` (200k) caps the column via
  `cap-text-content.ts`.
- `store-chat-attachments.ts` no longer copies the text; ingestion
  re-reads the bytes once.
- `media-columns.ts` selects every media column but `text_content`, which
  now has to be asked for (`grab-messages-media`'s reply path and
  ingestion do); the media CRUD routes sanitize rows they write.
- `ingest-bot-file.ts` decides on size alone, since a cached slice made
  an oversized file look already read.
- `bun run media:prune-text` cleans rows that were already stored
  (rerunnable, with a VACUUM hint).

Verified on the dev database: both bad rows cleared (146 KB), rerun
reports nothing to do.

src/pages/api/admin/bots/upload-attachment.ts

@@ -8,6 +8,7 @@ import type { BotMessageAttachment } from "@/src/types";
 import AppError from "@/src/utils/app-error";
 import attachmentFileKind from "@/src/utils/attachment-file-kind";
 import bufferFromBase64 from "@/src/utils/buffer-from-base-64";
+import canExtractText from "@/src/utils/can-extract-text";
 import parseWithSchema from "@/src/utils/parse-with-schema";
 import isReadOnlyUser from "@/src/utils/rbac/is-read-only-user";
 import safeErrorMessage from "@/src/utils/safe-error-message";
@@ -64,7 +65,7 @@ export const handler: BunextAPIRouteHandler<
             media_mime_type: ext,
             media_paradigms: ["bot-attachment"],
             media: { title: name },
-            extract_media_text_content: media_type == "document",
+            extract_media_text_content: canExtractText({ name, mime_type: mime }),
             user: { id: Number(user.id) },
         }).catch(async (error) => {
             await logError({ title: `Attachment ${name} couldn't be saved`, error }).catch(() => {});

src/pages/api/admin/crud/(tables)/media/post.ts

@@ -1,5 +1,6 @@
 import type { BUN_SQLITE_COBBLE_MEDIA } from "@/db/types/db";
 import checkUserAccess from "@/src/functions/backend/auth/check-user-access";
+import sanitizeMediaRowTextContent from "@/src/functions/backend/db/media/sanitize-media-row-text-content";
 import type { AdminCrudAPIParams } from "@/src/types";
 import BunSQLite from "@moduletrace/bun-sqlite";
 import type { APIResponseObject } from "@moduletrace/bunext/types";
@@ -10,9 +11,13 @@ export default async function (
 ): Promise<APIResponseObject> {
     const { table, body, user_types, user } = params;
 
+    /**
+     * A row written straight through the API still may not carry raw
+     * bytes or megabytes in `text_content`.
+     */
     let final_insert_data: BUN_SQLITE_COBBLE_MEDIA[] = [
         ...(body?.insert_data || []),
-    ].map((d) => ({ ...d, user_id: user.id }));
+    ].map((d) => ({ ...sanitizeMediaRowTextContent({ row: d }), user_id: user.id }));
 
     const is_user_allowed_to_post_any = checkUserAccess({
         includes: ["admin"],

src/pages/api/admin/crud/(tables)/media/put.ts

@@ -1,4 +1,6 @@
+import type { BunSQLiteTables, BUN_SQLITE_COBBLE_MEDIA } from "@/db/types/db";
 import checkUserAccess from "@/src/functions/backend/auth/check-user-access";
+import sanitizeMediaRowTextContent from "@/src/functions/backend/db/media/sanitize-media-row-text-content";
 import type { AdminCrudAPIParams } from "@/src/types";
 import BunSQLite from "@moduletrace/bun-sqlite";
 import type { APIResponseObject } from "@moduletrace/bunext/types";
@@ -29,9 +31,21 @@ export default async function (
         targetId = user.id;
     }
 
+    /**
+     * The row it replaces decides whether the new text belongs there, so
+     * an update that only sends `text_content` is judged on the file's
+     * real name and type.
+     */
+    const existing = targetId
+        ? await BunSQLite.select<BUN_SQLITE_COBBLE_MEDIA, (typeof BunSQLiteTables)[number]>({
+              table,
+              query: { query: { id: { value: targetId } } },
+          }).then((res) => res.payload?.[0] || null)
+        : null;
+
     const PUT = await BunSQLite.update({
         table,
-        data: body?.update_data,
+        data: sanitizeMediaRowTextContent({ row: body.update_data, existing }),
         targetId,
         query: final_sql_query,
     });

src/pages/api/admin/tasks/attach-file.ts

@@ -9,6 +9,7 @@ import type { TaskDetail } from "@/src/types";
 import AppError from "@/src/utils/app-error";
 import attachmentFileKind from "@/src/utils/attachment-file-kind";
 import bufferFromBase64 from "@/src/utils/buffer-from-base-64";
+import canExtractText from "@/src/utils/can-extract-text";
 import parseWithSchema from "@/src/utils/parse-with-schema";
 import isReadOnlyUser from "@/src/utils/rbac/is-read-only-user";
 import safeErrorMessage from "@/src/utils/safe-error-message";
@@ -65,7 +66,7 @@ export const handler: BunextAPIRouteHandler<APIResponseObject<TaskDetail>> = asy
                 media_mime_type: ext,
                 media_paradigms: ["task-media"],
                 media: { title: name },
-                extract_media_text_content: media_type == "document",
+                extract_media_text_content: canExtractText({ name, mime_type: mime }),
                 user: { id: Number(user.id) },
             });