Add knowledgebases

Knowledgebases give bots RAG over documents, scoped like extensions: to
particular bots, to a workspace, or to every bot, with their own button
beside Tools in the composer. Documents are chunked and embedded by the
file-ingest worker with the install's embedding model, which is now an
install-wide setting rather than a per-bot one.

- Word search runs on an FTS5 index ranked by BM25, with a scored LIKE
  fallback for scripts written without spaces.
- Changing the embedding model re-indexes documents automatically.
- Ingest jobs wait without spending attempts while every embedding model
  rests, fail at once on errors retrying can't fix, and keep passages
  searchable by words when the model refuses.
- Settings > Knowledgebases shows each knowledgebase's and document's
  index state: spinner, warning, grey check (words only) or green check.

Co-Authored-By: Claude Opus 5.5 <[email protected]>

src/utils/knowledgebase-passage-block.ts

@@ -0,0 +1,24 @@
+type Params = {
+    /**
+     * Where the passage is from, e.g. "Product handbook / pricing.md".
+     */
+    source: string;
+    document_id: number;
+    /**
+     * Where in the document, e.g. "passage 3".
+     */
+    at: string;
+    text: string;
+};
+
+/**
+ * One knowledgebase passage for a bot to read, fenced so nothing inside it
+ * reads as the app's own words.
+ */
+export default function knowledgebasePassageBlock({ source, document_id, at, text }: Params) {
+    const body = text.trim();
+    const longest_run = Math.max(0, ...(body.match(/`+/g) || []).map((run) => run.length));
+    const fence = "`".repeat(Math.max(3, longest_run + 1));
+
+    return [`From ${source} (document ${document_id}, ${at}):`, fence, body, fence].join("\n");
+}