fix(weixin): chunk long replies for iLink limits

README.en.md

@@ -46,7 +46,7 @@ Connect IM bots to DeepSeek Harness by scanning a QR code, using an App Manifest
 | Channel | Setup | Messaging and replies |
 | --- | --- | --- |
 | Feishu | Create a bot by QR code, or bind one with App ID + App Secret | Persistent connection for incoming messages; streaming cards show thinking, tool progress, and replies |
-| WeChat | Scan a QR code to bind a WeChat bot | Tencent iLink long polling for sending and receiving messages |
+| WeChat | Scan a QR code to bind a WeChat bot | Tencent iLink long polling for sending and receiving messages; long replies are sent in 1,800-character chunks |
 | DingTalk | Create a bot by QR code, or bind one with Client ID + Client Secret | DingTalk Stream connection; streaming replies through AI Cards |
 | WeCom | Create an intelligent bot by QR code, or bind one with Bot ID + Secret | Official WebSocket connection; native thinking state, tool progress, and streaming replies |
 | QQ | Create a bot with mobile QQ QR scanning, or bind one with AppID + AppSecret | WebSocket connection; private chats show typing and receive one Markdown reply, while mentioned group chats receive only the final answer |

README.md

@@ -49,7 +49,7 @@ Connect IM bots to DeepSeek Harness by scanning a QR code, using an App Manifest
 | 渠道 | 接入方式 | 消息与回复 |
 | --- | --- | --- |
 | 飞书 | 扫码创建机器人，或使用 App ID + App Secret 手动绑定 | 长连接接收消息；通过飞书流式卡片显示思考、工具进度和回答 |
-| 微信 | 使用微信扫码绑定机器人 | 腾讯 iLink 长轮询收发消息 |
+| 微信 | 使用微信扫码绑定机器人 | 腾讯 iLink 长轮询收发消息；长回复会按 1,800 字符分段发送 |
 | 钉钉 | 扫码创建机器人，或使用 Client ID + Client Secret 手动绑定 | 钉钉 Stream 长连接；通过 AI Card 流式显示回答 |
 | 企业微信 | 使用企业微信 App 扫码创建智能机器人，或使用 Bot ID + Secret 手动绑定 | 官方 WebSocket 长连接；原生显示“正在思考中”、工具执行进度和流式回答 |
 | QQ | 使用手机 QQ 扫码创建机器人，或使用 AppID + AppSecret 手动绑定 | WebSocket 长连接；私聊显示“正在输入”并以单条 Markdown 回复，群聊被 @ 后只发送最终答案 |

src/channels/weixin/weixin-bridge.mjs

@@ -184,7 +184,7 @@ export class WeixinHarnessBridge {
     status = createWeixinBridgeStatus(),
     logger = console,
     replyTimeoutMs = 600_000,
-    maxMessageChars = 4_000,
+    maxMessageChars = 1_800,
     signal,
   }) {
     if (!api || typeof api.sendText !== 'function') throw new TypeError('Weixin API is required');

test/channels/weixin/weixin-bridge.test.mjs

@@ -150,6 +150,38 @@ test('Weixin bridge hands a native file source to the current Harness turn', asy
   assert.deepEqual(sent, ['文件已收到']);
 });
 
+test('Weixin splits long replies below the iLink text limit', async () => {
+  const fixture = stateFixture();
+  fixture.sessions.set('p2p:owner-user', 'session-long-reply');
+  const chunks = [];
+  const answer = '答案'.repeat(1_000);
+  const bridge = new WeixinHarnessBridge({
+    api: {
+      sendText: async ({ text }) => {
+        chunks.push(text);
+        return { messageId: `weixin-long-${chunks.length}` };
+      },
+    },
+    baseUrl: 'https://ilinkai.weixin.qq.com',
+    token: 'token',
+    ownerUserId: 'owner-user',
+    harness: {
+      sessionExists: async () => true,
+      ask: async () => answer,
+    },
+    state: fixture.state,
+  });
+
+  const receipt = await bridge.accept(message('weixin-long-reply', '生成一段长回答'));
+
+  assert.ok(chunks.length > 1);
+  assert.ok(chunks.every((chunk) => chunk.length <= 1_800));
+  assert.equal(chunks.join(''), answer);
+  assert.equal(receipt.providerMessageIds.length, chunks.length);
+  assert.equal(bridge.status.messagesReplied, 1);
+  assert.equal(bridge.status.lastMessageError, null);
+});
+
 test('Weixin starts a native-file download before an earlier queued turn finishes', async () => {
   const fixture = stateFixture();
   fixture.sessions.set('p2p:owner-user', 'session-prefetch-file');