diff --git a/.jules/bolt.md b/.jules/bolt.md
index d3d39015..3866bbbd 100644
--- a/.jules/bolt.md
+++ b/.jules/bolt.md
@@ -24,3 +24,6 @@
 ## 2026-06-29 - Optimize D1 Queries by Batching
 **Learning:** Found N+1 query pattern on the hub stats page (`hub/src/routes/admin/stats.ts`) when iterating over the list of inbound peers to query `events_pulled_24h` for each peer sequentially using `.first()`. This introduces significant roundtrip latency and resource overhead as the number of peers grows. D1 supports batching queries, which can collapse N queries into a single HTTP roundtrip. D1's returned `batch` types can be peculiar, particularly when running against tests using Miniflare or test shims where row result structure might differ across platforms.
 **Action:** Replaced sequential queries in `Promise.all` with `db.batch()` to combine the multiple `db.prepare(...).bind(...)` calls into a single execution, and normalized the output structure parsing. This significantly reduces N+1 overhead and improves performance scaling as the peer count increases.
+## 2026-06-30 - Optimize DO Queries in Agent
+**Learning:** Found N+1 query pattern in `workers/agent/index.ts` where fetching the full thread for agent context was done by iterating over thread metadata using `.map` with `await stub.getEmail(e.id)` inside a `Promise.all`. While `Promise.all` executes concurrently in Node/Workers, executing multiple DO `fetch` calls adds unnecessary roundtrips and DO internal overhead.
+**Action:** Replaced the `Promise.all` sequential fetching with `getFullThread(stub, threadId)` (which proxies to the DO `getThreadEmails` query) to collapse N queries into two batched queries on the DO side, significantly reducing overhead for the context-loading step before agent evaluation.
diff --git a/workers/agent/index.ts b/workers/agent/index.ts
index a651a819..f6af25d1 100644
--- a/workers/agent/index.ts
+++ b/workers/agent/index.ts
@@ -18,12 +18,13 @@ import {
 } from "../../shared/folders";
 import { isPromptInjection, verifyDraft } from "../lib/ai";
 import {
+	getFullThread,
 	getMailboxStub,
 	stripHtmlToText,
 	textToHtml,
 } from "../lib/email-helpers";
 import { resolveMailboxSettings } from "../lib/mailbox-settings";
-import type { EmailFull, EmailMetadata } from "../lib/schemas";
+import type { EmailFull } from "../lib/schemas";
 import {
 	toolDiscardDraft,
 	toolDraftEmail,
@@ -433,28 +434,11 @@ export class EmailAgent extends AIChatAgent<any> {
 			}
 
 			// Load thread for conversation context
-			const threadEmails = (await stub.getEmails({
-				thread_id: emailData.threadId,
-			})) as EmailMetadata[];
-			if (threadEmails.length > 1) {
-				const fullThread = await Promise.all(
-					threadEmails.map(async (e) => {
-						const full = (await stub.getEmail(e.id)) as EmailFull | null;
-						const text = full?.body ? stripHtmlToText(full.body) : "";
-						return {
-							id: e.id,
-							sender: e.sender,
-							recipient: e.recipient,
-							subject: e.subject,
-							date: e.date,
-							folder_id: e.folder_id,
-							body_text: text,
-						};
-					}),
-				);
-				// ⚡ Bolt: Optimize sorting by replacing `new Date(b.date).getTime()` with `Date.parse(b.date)`
-				fullThread.sort((a, b) => Date.parse(a.date) - Date.parse(b.date));
-				threadContext = fullThread
+			// ⚡ Bolt: Replace N+1 query pattern with `getFullThread` which fetches all
+			// thread emails and attachments in two batched queries.
+			const thread = await getFullThread(stub, emailData.threadId);
+			if (thread.message_count > 1) {
+				threadContext = thread.messages
 					.map(
 						(e) =>
 							`[${e.date}] ${e.sender} → ${e.recipient} (${e.folder_id}): ${e.body_text.substring(0, 500)}`,