Skip to main content

@Waker

Connect IM chats to Wakers and manage routing, requests, and experts.

@Waker turns an existing IM discussion into work that can continue over time. Team members stay in the original chat while QoderWake uses its context, routes each request to a suitable Waker, and returns progress, results, and files. A group needs only one bot even when several specialized Wakers work behind it. Start with a development, customer-support, incident, or content-operations chat that already has useful context. For merges, releases, production changes, or external publishing, require the Waker to present its plan and risk first and wait for human confirmation.
The redesigned @Waker session management page

Prepare Wakers

  • Have at least one enabled Waker that has passed a normal chat test.
  • Give multiple Wakers distinct names and responsibilities, such as project coordination, implementation, and test validation.
  • Verify each Waker's project, workspace, Skills, connectors, and permissions.
  • Define human-confirmation boundaries for high-impact actions.

Configure an IM connection

Path: @Waker → IM Connection Management. The page shows only connection types available to the current region, account, and release.
ConnectionUse@Waker
DingTalk botDingTalk group and bot direct messagesSupported
DingTalk userGroup and direct messages under a signed-in user identitySupported
Feishu botFeishu chatsSupported when shown
Other connectionsBasic messaging or channel-specific featuresFollow the page label
Manage the IM connections available in the current product edition
  1. Add or configure a connection and enter platform credentials only in the protected form.
  2. Complete authorization or QR-code sign-in. For a DingTalk bot, create the bot first, set message receiving to Stream, follow the page's security-setting instructions, and enable direct-message permission when needed.
  3. To read group context or return documents, images, and spreadsheets, install DWS when prompted and authorize the current DingTalk account for chats and files.
  4. Choose the access policy. With Use after pairing, every new chat must request access and be approved; begin with a test account or group.
  5. Choose a reply style. A normal card is sent after generation; an AI card updates while content is generated and may require an allowlist change in the platform console.
  6. Save, confirm that the connection is available, and send a normal test message.
Follow the product guide to configure a DingTalk bot and reply style
Never place credentials in Waker descriptions, knowledge, memory, task requests, or screenshots. The following sections cover connection, authorization, chat access, and testing for each platform. Bot connections reply under a shared bot identity and suit team collaboration. User connections reply under the authorized real user's identity. Before configuring a connection, decide which account will receive messages and whose identity will be used for replies, then choose the appropriate channel.

Choose a connection type

The following table lists how to configure each channel. It does not mean that every region, account, or version offers these connections, or that they have the same @Waker capabilities. Follow the connection types and features shown on your current page.
Configuration guideReply identityBefore you configure
DingTalk BotBotUse the correct entry for standard DingTalk or Ali DingTalk; chat and file capabilities require separate DWS authorization
DingTalk UserAuthorized userCheck the target organization, message reception scope, and polling settings
Feishu BotBotComplete app authorization and the personal authorization required for chat search separately
Feishu UserAuthorized userUse an actual direct chat or a regular conversation group; mention the authorized user in groups
WeCom BotIntelligent botConfigure multi-user mode, allowed members, and group chat authorization
WeCom native channelsBot replying in posts or commentsThe channel creator grants access to all channel content; connect separately from ordinary group chats
WeChatConnected botCurrently supports only basic IM direct chats
QQ BotBotEnter app credentials manually; currently returns only final text results
Lark BotBotUse Lark apps and authorization entries, not Feishu's
SlackBotUse Socket Mode and configure the two token types separately
Microsoft TeamsBotConfigure the bot app, tenant, and gateway before requesting chat access
WhatsAppLinked accountExperimental; link a device from your phone and limit the automatic reply scope first

Before you begin

  • Prepare at least one Waker that can execute tasks normally, along with a chat for testing.
  • Confirm that the device running QoderWake is online. If you use multiple runtime environments, select the same environment throughout connection, authorization, and chat configuration.
  • Start with the smallest message reception scope in a test chat, then expand it based on your test results.
  • Check the Waker's model, working directory, and file and tool permissions. The working directory is on the selected runtime device, which may not be the computer where you opened the console.
App secrets, tokens, and authorization QR codes belong only in protected configuration or authorization interfaces. Do not send them in chats, add them to Waker descriptions, or leave them visible in public screenshots.

Configuration workflow

  1. Select a channel and runtime environment, then complete the platform's app configuration, sign-in, or QR-code authorization.
  2. Save the connection and confirm that it is available and enabled.
  3. Connect the target direct chat, group chat, or channel using a method supported by that channel. Requests also require administrator approval.
  4. Select a Waker, check its model, working directory, and execution permissions, then save and enable the chat.
  5. Configure the response behavior you need within the current channel's capabilities, then return to the original chat to test it.
Connection availability, chat access, and Wake-up Mode are separate states. Adding a bot to a group or completing platform authorization does not mean that the chat has been approved to use a Waker. Platform authorization also does not replace the Waker's execution permissions. Use Use after pairing or pairing mode to connect @Waker; open mode is for ordinary IM, not for bypassing chat access or authorization checks. Enable capabilities such as intelligent routing only when the page provides them and the required checks pass.

DingTalk Bot

Receive and reply to messages as a DingTalk bot. In a group, mention the actual bot rather than typing the literal text "@Waker".

Create and connect the bot

  1. Open the connection management page under @Waker, select a runtime environment, and add a DingTalk bot. Standard DingTalk and Ali DingTalk use their own entries and credentials.
  2. If the page offers a QR-code option, scan it with DingTalk to create the bot and wait for the credentials to be filled in. For an existing bot, enter the corresponding app's AppKey and AppSecret.
  3. In the bot management platform, set message receiving to Stream and check the security settings and IP allowlist against the integration guide. For direct chats, also enable direct-chat capability and set its visibility scope. Complete saving, publication, or approval as required by the platform.
  4. In Read group chat context and send files, install DWS as prompted, then sign in and authorize it. Check the current account, organization, and access scope for the target chats.
  5. For your first connection, you can choose Use after pairing and a normal card. Before using an AI card, check the network allowlist as prompted. Save, then confirm that the connection is available and enabled.

Connect and test chats

For a group chat, add the bot first, then search for the target chat in the chat access wizard. Alternatively, send a message in a direct chat, or select the bot from the group's mention list and send a message. An administrator reviews and approves the request in Pending requests. Select a Waker and check its execution permissions. If you need Wake-up Mode, complete the checks shown on the page. After saving, send a new test task, then separately test another member, a follow-up in the same chat, and file delivery. If you cannot find a group or read its context, check the DWS account, organization, and permissions first. Do not skip authorization checks just because the bot connection works. If group chats work but direct chats do not, check direct-chat capability and visibility scope.

DingTalk User

Reply under the authorized DingTalk user's identity. This connection reads new messages according to its polling settings, so replies may be delayed.

Connect the account and chats

  1. Open the connection management page under @Waker, select a runtime environment, and add a DingTalk user connection. Confirm which account will send automatic replies.
  2. Install DWS as prompted, sign in, authorize it, and check the target organization. Successful sign-in to one organization does not authorize other organizations.
  3. Set the message reception scope to hand over to Waker. To adjust polling speed, set the polling interval under Advanced configuration; you can keep the default initially. The current account configuration page does not offer a Maximum messages per poll setting. Save and enable the connection.
  4. In the chat access wizard, select this user connection and search for the target contact or group chat. For a direct chat, use another contact; the signed-in account itself cannot be the direct-chat recipient.
  5. Select a Waker, check its model, working directory, and permissions, then save and enable the chat. For groups, also check mention-triggered responses or other response rules offered on the page.

Test and troubleshoot

Have a test contact send a task to the authorized account. Allow one polling cycle plus processing time, then confirm that the account replies in the original chat. In a group, have another member trigger a response according to the rules. Test file receipt and opening separately. If there is no reply, check the organization, message reception scope, chat enablement, and polling settings in that order. If directory access or administrative operations are blocked, check the chat's execution permissions rather than repeatedly signing in or resending the same task.

Feishu Bot

Reply as a Feishu bot. Configure app permissions, personal authorization for chat search, and chat access separately.

Create the app and complete authorization

  1. On the connection management page, select a runtime environment and add a Feishu bot. If the page offers a QR-code option, follow the prompts to create an app and wait for the credentials to be filled in. For an existing app, enter its App ID and App Secret manually.
  2. When creating an app manually, enable bot capability in the Feishu open platform and follow the platform guide to configure a persistent connection and message event reception.
  3. In App permissions, review missing permissions, complete them and the visibility scope for test members, then publish the app or obtain administrator approval. Return to QoderWake and run the check again.
  4. For your first connection, choose Use after pairing. To deliver generated files automatically, enable Automatically send artifact files. This option does not automatically package code changes as attachments.
  5. Save and confirm that the connection is available. Do not add the same app more than once; even a disabled old connection may affect duplicate-connection checks.

Connect chats

Add the bot to a group before connecting it. If group search requires personal authorization, scan the page's QR code with Feishu, authorize with an account that can access the target group, and wait for the search permission checks to pass. For direct-chat search, follow its separate personal authorization flow. Add the complete redirect URL to the current app configuration only when the page requires it, then start authorization. Check direct-chat and group-search permissions separately; configuring a callback address is not a mandatory step for group-search QR authorization. A callback for a remote environment must reach that environment; do not rewrite the address yourself. Without search, send a message in a direct chat, or actually mention the bot in a group and send a message, then have an administrator approve the request. Being visible in search does not mean that the bot already has access to the chat. Select a Waker and check its permissions. Enable Wake-up Mode as needed and only within the page's capabilities. Use new messages to test replies, follow-ups in the same chat, and file delivery. If normal replies work but Wake-up Mode or multi-Waker configuration is unavailable, check chat history read permissions and whether the bot has joined the group.

Feishu User

Reply under the authorized user's own identity, for a personal avatar or a Waker. In a group, mention this user, not a separate bot.

Authorize the account and connect chats

  1. On the connection management page, select a runtime environment, open Feishu User, and click Add account. Use your own account to scan the QR code and confirm your identity. Each user can bind only one Feishu user account on the same device.
  2. Complete the full permission authorization, administrator approval, and identity verification required by the page. If app identity permissions are still missing, complete them and verify again, then save and enable the connection. Authorization for personal avatar learning alone does not mean that the IM connection is enabled.
  3. In the chat access wizard, select the user connection. For a direct chat, first confirm that an actual conversation with the contact exists. For a group chat, select a regular conversation group that you have joined and wait for member and history read checks to pass. Topic groups and topic-mode groups are not currently supported.
  4. Select the corresponding personal avatar or Waker, check its model, working directory, and permissions, then save and enable the chat. Configure advanced capabilities according to the page's check results when needed.
  5. For the first group test, use Respond when @mentioned and have another member select the authorized user from the mention list. Configure other response rules separately according to the current page's capabilities.
Permission verification checks the current status; it does not renew authorization. If user authorization is missing or expired, complete Reauthorize before verifying again. Resolve missing app permissions through the permission management entry. Changes to the account's AI label require saving. A chat using a DingTalk user or Feishu user connection can bind both a personal avatar and an ordinary Waker. Test one target first, then add others as offered on the page, define responsibilities and the default response target, and test routing separately. Not every message receives a reply from every target. Platform authorization does not automatically give the other person access to all your files, memory, or management permissions.

Test and maintain

Start with text tests for direct chats, group chats, and follow-ups in the same chat, allowing time for polling. Test image and file sending separately. Successful outbound file delivery does not prove that all images, files, or voice messages can be used as task input. Manual intervention does not guarantee that all automatic replies stop immediately. Use the appropriate switch when you need to pause them. Reauthorizing the same account or turning off the connection does not clear pairings. Switching accounts or deleting the connection clears pairings, so chats must be connected again after you re-add it.

WeCom Bot

Use a WeCom intelligent bot, not a regular group bot Webhook. Creating the bot, setting allowed members, and authorizing group chats are separate steps.

Connect and set the usage scope

  1. On the connection management page, select a runtime environment and add a WeCom bot. Scan the QR code with your phone to create and bind it. For an existing intelligent bot, enter its Bot ID and Bot secret manually. Do not connect the same bot to multiple runtime devices at once.
  2. In the WeCom PC client, open Workbench → Intelligent Bots, open the target bot's details, and click Edit.
  3. Change the usage mode to Multi-user mode. Add the members who need access and at least one test member to Allowed members, then save. QoderWake chat approval does not replace this member scope.
  4. Return to Group chat authorization in the connection configuration. Depending on its status, choose Install and authorize or Authorize. When scanning with your phone, select the current bot and complete authorization for the Messages permission as prompted.
  5. Check the authorization status after returning and click Recheck if needed. Use pairing mode for your first connection, save, and confirm that the connection is available and enabled. Renew expired authorization; you do not need to recreate the bot.

Connect and test chats

For a group chat, add the intelligent bot first, then search for the target group. If you cannot find it, actually mention the bot in the group to send a request, then have an administrator review and approve it. For a direct chat, the other person must send a message first, after which the corresponding request can be approved. Address book search cannot replace this step. Select a Waker and check its execution permissions and the required Wake-up Mode state. Use a new message to test the reply, then have another allowed member repeat the test. Chat history may not include all records shown in the client. If required original text cannot be read, include it in the current message. If only the creator can use the bot, check multi-user mode and allowed members first. If authorization fails, check the selected bot and message permission. Do not treat every error as an expired QR code and keep scanning.

WeCom native channels

Use this flow for posts and comments in the WeCom client's Channels feature. For ordinary direct and group chats, follow WeCom Bot. Check channel access and ordinary group authorization separately.

Connect the bot and authorize channel access

  1. On the connection management page, select a runtime environment and add or open a WeCom intelligent bot. Reuse an available connection instead of creating another bot for the channel.
  2. Scan the QR code to create a new bot, or enter the bot ID and secret for an existing one. Check multi-user mode and allowed members if others need access.
  3. Select Use after pairing, save, and confirm that the connection is enabled and available. Do not connect the same bot to multiple runtime devices at once.
  4. Confirm that the channel allows the current bot. Ask the channel creator to grant it access to all channel content and verify the bot's identity.
CLI authorization for ordinary groups does not prove channel access and is not an additional prerequisite for native channels. If approval reports missing channel access, have the creator grant it, then approve the original request again; do not recreate the connection.

Request access and select the task target

  1. Create a post or add a comment in the target channel. Select the current bot from the mention list and send a test message.
  2. In Pending requests, verify the bot, channel, and request type. Pairing applies to the whole channel, not individual posts. An ordinary group and a channel with the same name are separate access targets.
  3. Start with one available ordinary Waker, check its model, working directory, and file and tool permissions, then approve. For collaboration, select a Group or WakerFlow as offered on the page and define the default target.
  4. Check the channel and task target in the connected-chat list and enable the chat. Personal avatars and Group Chat Q&A Specialists are not supported task targets for channels.
After approval, the system attempts to process the request's first mention and reply to its original post or comment. An old request may lack message location, refer to a recalled message, or be outside the reply window. Mention the bot again in the current post to test; a missing first reply alone does not mean pairing failed.

Configure response behavior

Test manual mentions first, then configure response options, Wake-up Mode, and permission checks as required by the channel details page.
ResponseHow to use itResult location
Manual mentionActually mention the bot in a post or comment and send a taskOriginal post or comment
Conditional responseEnable keyword, sender, or other conditions and send a matching new messageThe matching message's post or comment
Proactive responseEnable it and describe when the bot should interveneThe selected source post or comment
Scheduled responseSet a time and task instructionsA new result post in the current channel
Scheduled responses can use an ordinary Waker or Group. WakerFlow requires an existing post for interaction and cannot use this flow to create scheduled result posts directly. WakerFlow models are configured in its internal nodes. Turning off Wake-up Mode may still allow eligible manual mentions from people to receive replies. To pause channel use, turn off chat enablement and check existing tasks. Conditional and proactive responses require readable channel history, and comment discovery may be delayed. Backfilled history does not automatically rerun old messages.

Verify posts, comments, and attachments

Mention the bot in a post body and in a comment separately, checking that each reply returns to the original location. Continue within one post, then send an independent task in another; context and task continuation are handled separately for different posts. Test image and file input and generated-file output separately with small files, checking that they arrive and open. Have another allowed member repeat the test. For scheduled responses, verify that a new result post appears at the expected time. Do not assume all historical attachments or forwarded chat records can be read; attach required materials to the current message.

WeChat

Currently supports basic IM direct chats with one Waker. WeChat group chat access and Wake-up Mode are not supported.

Connect by QR code and add a direct chat

  1. On the connection management page, select a runtime environment and add a WeChat connection. Wait for the QR code and check the account that will scan it. Scanning again for an existing connection may replace the original account, so confirm the identity first.
  2. Scan with WeChat and confirm on your phone. Return to QoderWake, wait for a successful connection, save as instructed, and check the connection identity and enablement status. Generate a new QR code only after the previous one expires.
  3. Send a request message to the connected bot in the target direct chat. An administrator checks the source in Pending requests and approves it. If the page offers a pairing code, you can send the complete generated pairing message to the target direct chat and use it within the validity period shown on the page.
  4. Select one Waker, check its model, working directory on the runtime device, and permissions, then save and enable the chat.
  5. Return to the same direct chat, send a new text task, and follow up once. Confirm that replies actually arrive in the original chat. Test media features separately within the current page's supported scope.
A successful connection does not mean that the direct chat has been connected. If there is no reply, check pairing, chat enablement, and Waker availability first. No replies in WeChat groups are a current support limitation; do not try to fix this by changing credentials.

QQ Bot

Connect using QQ bot app credentials. The current connection uses the production environment, with no sandbox switch or in-product QR-code authorization. Chats use basic IM capabilities with one Waker.

Configure and connect chats

  1. Create or select an app in the QQ bot open platform, configure its usage scope and go-live requirements, and obtain its App ID and App Secret. Do not substitute a personal QQ account password for app credentials.
  2. On the connection management page, select a runtime environment, add a QQ bot, and enter the app credentials. Save and confirm that the connection is available and enabled.
  3. Send a message to the bot in a direct chat. For a group, add the bot first, then select it from the mention list and send a message. An administrator checks the requester, chat, and bot before approving.
  4. If the page offers a pairing code, send the complete pairing message. In a group, still mention the bot as prompted. Do not connect by manually entering a chat identifier.
  5. Select one Waker, check its model, working directory, and permissions, then save and enable the chat. Return to the original chat and send a text task, then have another authorized member repeat the test.

Reply limitations

Currently, only final text or Markdown results are returned. There is no streaming progress output, and outbound images, videos, and files are not supported. Long replies may be split into chunks and are subject to platform limits. The absence of a card with step-by-step updates does not mean that the task has not run. For tasks that require file delivery, do not make returning a QQ attachment a completion condition.

Lark Bot

Use the apps, credentials, and authorization entries for Lark. Do not enter Lark credentials in a Feishu connection or reuse a Feishu callback address directly.

Configure and connect chats

  1. On the connection management page, select a runtime environment and open the Lark add-connection entry. If the page offers a QR code, follow the prompts to create an app. For manual configuration, create or select a Lark custom app and enter its App ID and App Secret.
  2. For a manually configured app, enable bot capability, configure a persistent connection and message events according to the platform guide, and complete the permissions for sending and receiving messages and accessing required resources.
  3. Set the usage scope for test members, publish the app or obtain approval, then return to QoderWake to save and enable the connection.
  4. Add the bot to a group first. Send a request message in a direct chat, or actually mention the bot in a group and send a message, then have an administrator review and approve it. If the page offers search, follow the corresponding Lark authorization guide to connect by search. Use the complete callback address shown on the page.
  5. Select a Waker, check its model, working directory, and permissions, then save and enable the chat. Enable Wake-up Mode or other advanced capabilities only when the page provides them and the checks pass.
  6. Use new messages to test replies in the original chat, another member, and follow-ups in the same chat. If you need attachments, generate a simple text file and check that it is actually received and can be opened.
After adding permissions, complete the corresponding publication or approval. Finding a chat in search does not mean that the bot has joined its group. If there is no Lark entry, check your current region, account, and version first; do not substitute the Feishu entry.

Slack

Messages are received through Socket Mode. Configure an App-Level Token and a Bot User OAuth Token separately.

Create the app and save the connection

  1. In Slack app management, create or select an app, enable Socket Mode, and create an App-Level Token with the connections:write permission.
  2. Under OAuth & Permissions, complete Bot Token Scopes according to the QoderWake page. The current guide includes chat:write, users:read, channels:read, groups:read, mpim:read, files:write, and reactions:write. Add any other permissions required for message events as prompted by the platform.
  3. Follow Slack's guide to subscribe to the required direct-message, channel-mention, and related message events. Install the app in the target workspace and obtain the Bot User OAuth Token. Run Reinstall App after adding permissions.
  4. On QoderWake's connection management page, select a runtime environment, add Slack, and enter the two tokens in their respective fields. Do not swap them or enter only one.
  5. Check whether Only process messages that @mention the bot in group chats is enabled. Save and confirm that the connection is available and enabled. With this option on, ordinary channel messages are not processed as mention messages.

Connect and test chats

For a direct chat, open the bot conversation. For a channel, add the bot first, then send a message to request access, actually mentioning the bot as required. An administrator checks the source and approves the request. When using a pairing code, send the complete message to the target chat. Do not connect by manually entering a user or channel identifier. Select a Waker and check its execution permissions, then save and enable the chat. First test text replies in the original chat, then have another channel member repeat the test. Test threads, file input, and delivery of small result files separately. If the connection works but messages do not arrive, check permissions, event subscriptions, and whether the bot has joined the channel. If new permissions do not take effect or names are displayed incompletely, check read permissions and reinstall the app.

Microsoft Teams

The connection depends on a bot app, tenant configuration, and gateway relay. Complete deployment according to the platform and product integration guides first. Do not substitute the local console address for the messaging endpoint.

Prepare the app and connect chats

  1. Create or select an Azure Bot app, configure the Microsoft Teams channel, and set the messaging endpoint provided by the integration guide.
  2. Prepare the Azure Bot App ID, App Password, and Microsoft Entra Tenant ID. Install or publish the Teams app according to your organization's requirements so test users can open the bot chat. If required deployment configuration is incomplete, ask your organization's administrator to handle it first.
  3. On QoderWake's connection management page, select a runtime environment and add Microsoft Teams. Enter the app ID, password, and tenant ID, confirming that they belong to the same target configuration. Save and check the connection status and switch.
  4. A test user opens a direct chat with the bot and sends a request message. An administrator checks the requester and bot in Pending requests before approving. This channel does not use a local pairing code; do not bypass requests by manually entering a conversation identifier.
  5. Select a Waker, check its model, working directory, and permissions, then save and enable the chat. Return to the same direct chat where the request was sent, send a new task, and confirm the bot's reply.
For group chats, follow the current page's request instructions. Confirm that the bot has joined first, then test the target group separately. Test threads and attachments separately as well; success in another chat does not replace checks for the current chat. If a request does not appear, check the platform app, organizational access scope, and gateway connection first. Saving credentials does not mean that the gateway and chat binding are ready. Changing the Waker's prompt cannot fix a platform connection problem.

WhatsApp

Connect by linking a device from your phone and reply under the linked account's identity. This feature is experimental. Test it in a limited set of chats before expanding its usage scope.
  1. On the connection management page, select a runtime environment and add WhatsApp. If the page asks for a local account identifier, it is only a display label and does not replace sign-in.
  2. On your phone, open WhatsApp's Linked devices, choose to link a new device, scan the QoderWake QR code, and confirm.
  3. Return to QoderWake and wait for Scanned, connecting to change to a successful connection, then save and enable it. Do not repeatedly generate QR codes while connecting. Generate a new code only after the previous one expires.
  4. Have a test contact send a direct message to the linked account. For a group, confirm that the linked account is a member, then actually mention that account as required by the page. An administrator checks the source and approves the request.
  5. When using a pairing code, generate the complete pairing message first, then send it to the target chat and use it within the validity period shown on the page. Do not connect by manually entering a chat identifier.
  6. Select one Waker, check its model, working directory, and permissions, then save and enable the chat. Test the identity and reply in a direct chat first, then separately test group chats, another member, and the media features you need.
Use the connection switch to pause temporarily. Log out of WhatsApp unlinks the device and clears local authentication, but preserves the connection and pairings. To use it again, scan a new QR code and check chat enablement. Logging out of the linked device from your phone also requires scanning again. If the connection is replaced, check for other clients or duplicate running instances. Do not repeatedly submit the same linking operation.

Checks after connecting

Return to the connected chat and verify the following items in order. The deciding evidence is whether results actually arrive in the original chat. A "Thinking" status, a request disappearing, or a task completing in the console does not prove that messaging succeeded.
CheckHow to verify
Runtime environmentConfirm that the source device is online and the current operation targets the intended environment
Chat and task executorCheck the connection identity, target chat, Waker, model, working directory, and enablement status
Basic replySend a new task in the original chat and confirm that a reply actually arrives under the correct identity
Group triggerTrigger according to the current channel and response rules; when a mention is required, select the correct bot or account from the platform's mention list
ContextAsk a follow-up in the same chat and check that the reply connects to the previous exchange; this does not prove that all history is readable
Member scopeHave another ordinary member repeat the test, rather than testing only the creator or administrator
File deliveryWhen the channel provides file capabilities, check receipt, sending, and whether files can be opened separately; do not test outbound attachments on QQ
Advanced capabilitiesCheck Wake-up Mode, response rules, voice, or scheduling settings separately according to the channel and page capabilities; successful text replies do not prove that every capability is available
When the current channel and page support multiple Wakers, give them distinct names and responsibilities and designate one default Waker. Configure each response type offered on the page separately. When pausing, check the corresponding rules; turning off one response type does not mean that all responses have stopped. When a remote operation shows "Accepted" or "Syncing", wait for the source device to execute it rather than repeatedly creating the same item. Chats that support scheduled responses currently allow up to 15 scheduled rules per chat, including disabled rules, with a minimum interval of 10 minutes. Check the source device's time zone; for older versions, follow the limits shown on the page. For temporary suspension, prefer the connection or chat switch. The effects of deletion, switching accounts, and signing out of authorization vary by channel. Before proceeding, read the page's instructions on pairing retention and recovery. Device shutdown, sleep, or loss of network connectivity affects message reception and task execution.

Understand the four configured objects

  • IM connection: the bot or user identity that receives and sends messages. Removing it immediately stops messaging and invalidates dependent chats.
  • IM chat: the direct or group chat allowed to use @Waker. Authorization is isolated per chat; adding a bot to a group does not automatically authorize every group.
  • Wakers that handle chat tasks: the Wakers selected when the chat is enabled.
  • Wake-up Mode: determines whether this is a plain IM connection or a full @Waker chat with task pickup, intelligent routing, task history, topics, and memory.
Give each Waker a distinct responsibility before enabling the chat. With two or more Wakers, run Check Responsibility Conflicts and either refine their roles or apply a custom routing rule.

Enable and configure @Waker

The full setup path is: make an IM connection available, pair a chat, configure Wakers, then turn on Wake-up Mode and validate the result. After you select Enable @Waker, the wizard moves through IM connection, chat access, and Waker configuration. If the first step reports no available IM connection, return to IM Connection Management and connect a bot or user first. There are two primary ways to pair a chat. Search for the chat when the connection can already discover it. When the chat is not searchable, send a message in IM to create a pending request and approve that request in QoderWake. Both paths finish in the same Waker configuration.

Method 1: Search for a chat and enable it directly

Use this method when the administrator knows the target direct or group chat and the IM connection supports chat search.
  1. On the @Waker page, select Enable @Waker, choose the IM connection that sends and receives messages, and continue.
  2. Choose Direct or Group, then select Search chat as the access method. Add the bot to the target group before pairing a group chat.
  3. Search by chat name, member name, or the ID requested by the page, then select the result. Search prerequisites vary by channel: Feishu can require user authorization, while DingTalk can require DWS to be installed and signed in.
Choose a chat type and connect it by search or message pairing in the current setup guide
  1. Select one or more Wakers and choose exactly one default Waker. The default receives unmatched requests or asks for clarification.
  2. For every Waker, verify the response model, workspace, file-access scope, and other permissions. Do not allow multiple Wakers to write the same file concurrently.
  3. Turn on Wake-up Mode, confirm that the connection, chat, and Wakers are complete in the wizard, then enable the chat.
If the target is not found, do not create duplicate connections. Confirm that the bot is in the group, the connection is available, and required search authorization is complete. If search still cannot find it, use message-based pairing.

Method 2: Send a message and approve the pairing request

Use this method when QoderWake has not discovered the chat or the administrator cannot conveniently search for it. Sending a message creates a pending request; it does not authorize the chat automatically.
  1. Confirm that the IM connection is available. Add the bot to a group, or open its direct chat.
  2. Send any message in a direct chat. In a group, mention the bot and send a message so QoderWake can identify the chat and requester.
  3. Return to the @Waker page and open Pending requests. Filter by source or chat type when necessary.
  4. Verify the chat, requester, and IM connection, then select the request to approve. Do not approve an unrecognized source.
  5. Select Wakers and a default Waker, verify models, workspaces, and permissions, turn on Wake-up Mode, and approve the request.
  6. Return to the original chat and send a validation task. Group messages still mention the same single bot.
Create a request from IM, then return to QoderWake to approve the pairing

Pairing code, when available

Some channels also expose a pairing code as an additional option. After you select a Waker, QoderWake generates a pairing message that is typically valid for 10 minutes. Send the complete message to the target group and mention the bot, or send it directly to the bot. Return to the @Waker list and verify the chat, Wakers, and enabled state. Do not publish or retain pairing codes unnecessarily.

Validate immediately after enabling

The chat appears in the enabled-chat table or card view. Verify its IM connection, Wakers, default Waker, workspace, model, Wake-up Mode, and enabled state. Then send two requests in the same test chat: an obvious request that should route to a specialist and an ambiguous request that should reach the default Waker or trigger a clarification question.

Configure advanced Waker options

Each Waker has independent settings. Review them before saving:
OptionRecommendation
Response modelSelect a stable default model; Auto follows the current recommended configuration
Allow model changes from IMOff by default; enable only when members understand model capability, quota, and data boundaries
Workspace or projectGrant only the scope required for that role; avoid concurrent writes to the same file
File and tool permissionsStart read-only and minimal; keep external sends, deletion, and production writes behind approval
Allow QoderWake management operationsOff by default; enable only for trusted members and explicit administration scenarios
Default WakerSet exactly one to handle unclear requests or ask for clarification
When IM model changes are allowed, a member can explicitly request a model that the page makes available for that task. The selection applies only to that task. If no model is specified, the name is unavailable, or policy disallows it, that Waker's default model is used. Different models consume their corresponding quota, so validate this behavior in a test chat first. QoderWake management access is high risk. It can let a Waker create autonomous tasks or manage Wakers, Skills, and MCP resources. Permission changes, credentials, deletion, and other protected actions still require product authorization and human confirmation. Normal engineering, support, and content groups usually do not need this option.

What is Wake-up Mode

Wake-up Mode turns a basic IM chat into an @Waker workspace for ongoing work. When it is on, @Waker recognizes member intent, routes each task to an appropriate Waker, records follow-up instructions and results, and preserves topics and memory within the chat. Members still interact with one bot and do not need to understand the routing behind it. Leave Wake-up Mode off for simple messaging, fixed Q&A, or chats always handled by one Waker. Turn it on when the chat needs multiple Wakers, continued task execution, and reusable context.
CapabilityWake-up Mode onWake-up Mode off
Behavior@Waker picks up and intelligently dispatches workPlain IM chat connection
WakersMultiple Wakers, a default, and routing rulesOne Waker only; reduce to one before turning the mode off
Task contextTask history and every continuation are recordedNo @Waker task orchestration
Topics and memoryChat, member, and topic memory accumulateNo @Waker topic or memory accumulation
Best forOngoing engineering, incident, and operations workSimple messaging with one fixed Waker
For ordinary IM chats, use standard IM mode when the task target is a Group or Group Chat Q&A Specialist. For Groups and Wake-up Mode in WeCom native channels, follow the channel setup flow rather than applying ordinary group-chat restrictions. Before switching modes, review active tasks, Wakers, and routing rules; turning Wake-up Mode off removes multi-Waker dispatch, task history, and memory behavior from subsequent messages.

Work in IM

  • Group: mention the single bot and state the task. Routing uses names, responsibilities, the default Waker, and routing rules. Task status identifies the Waker doing the work.
  • Direct message: send a task directly. Continue the same task with follow-up messages, or state clearly when a new task or workspace is required.
  • Continue work: reference the previous result and provide new constraints or acceptance criteria.
  • Files: delivery depends on channel capabilities. Use the returned link or the task artifact in QoderWake when native attachments are unavailable.
Do not send passwords, tokens, customer-private data, or other credentials through IM.

Inspect tasks, topics, and memory

Open @Waker → enabled chat → chat details:
ContentScopeAppropriate use
Group shared memoryEveryone in the current groupTeam conventions, stable facts, and confirmed decisions
Member memoryOne member in the current groupRole, preferences, and collaboration habits
Direct-chat memoryThe member's bot chatLong-term context that belongs only to that direct chat
TopicOne discussion in a group or direct chatTask summaries, stage conclusions, and follow-up context
Filter memory by scope, member, time, or source before editing. Do not store a member preference as a group-wide rule or promote a temporary discussion directly into long-term memory. Manage personal and project memory in Memory.

Write a group request

The group always mentions one bot. Members do not need to know how many Wakers sit behind it; responsibilities, the default Waker, and custom routing rules select the executor.
@bot New task: summarize the release blockers discussed today.
Scope: only this group chat and the attachments already shared here.
Deliverable: a table with owner, impact, next step, and due date.
Constraint: do not publish or modify external systems; return a plan and wait for confirmation before any action.
Quote the prior result and say “continue the current task” for the same work. Say “new task” when the goal, project, or main workspace changes. Do not combine a merge, production change, and analysis request in one message.

Configure response rules

Open Response rules in the chat details to control when group messages trigger a Waker:
  • @ response: the default rule. Mentioning the bot triggers a response; when off, only custom rules are evaluated.
  • Message rule: match a sender, keyword, or regular expression without an @ mention; add a cooldown and appended instruction when needed.
  • Schedule rule: initiate work hourly, daily, weekly, monthly, or with a custom five-field Cron expression.
Configure rules within the capabilities offered by the current chat and channel; they do not automatically apply to other chats. In a DingTalk group, turning off @ response without enabling any custom rule stops message responses. Configure conditional, proactive, and scheduled responses for WeCom native channels through the channel setup flow. Test matching conditions, cooldowns, and appended instructions in a test chat before rollout.

Configure chat access rules

Chat access rules determine which members or chats can use the connection. Validate pairing approval or a restricted scope before opening access more widely.
  • Restrict allowed chats, members, or organizations.
  • Keep pairing or administrator approval for new chats.
  • After changing rules, test an allowed source and a source that is not allowed.
  • Channels such as WeCom may differ in group Q&A, files, and identity authorization. Follow the current connection page.
Access rules only determine whether messages can enter. They do not replace the Waker's file, tool, model, or external-operation permissions.

Enable DingTalk voice responses

DingTalk voice responses are off by default. Enable them manually under the target chat's response options when needed.
  • Only relevant new voice messages received afterward are processed; earlier messages are not backfilled.
  • Voice messages unrelated to the current Waker's work receive no response.
  • Validate speech recognition, task routing, and replies in a low-risk test group first.
  • Voice may contain background sounds, other people's conversations, or sensitive information. Agree on its use with group members.

Configure experts

Experts provide human knowledge when a Waker lacks information or needs professional judgment. They do not replace the Waker or formal approval.
  1. Open the Waker used by @Waker and enter its expert configuration.
  2. Add expert identities, specialties, and available channels.
  3. Define when to ask for help, what context to include, and how to continue after a response.
  4. Trigger one test consultation and verify that the answer returns to the original task.
After an expert replies, the Waker should show the advice and conclusions awaiting confirmation in the current task before continuing work that depends on them. Expert confirmation supplements specialist knowledge; it does not approve publishing, deletion, payment, or production changes. Those actions still require separate human confirmation.

Manage and validate

Use the enabled-chat list to filter by chat, connection, model, Wake-up Mode, or status. Chat details contain Overview, Task history, Memory, Experts, and Response rules. You can also edit Wakers, the default, workspaces, and permissions, or pause, resume, and remove the chat.
  • Pause a chat: stop new tasks while retaining configuration and history.
  • Turn Wake-up Mode off: return to standard IM mode after reducing Wakers to one.
  • Remove a chat: unpair @Waker without deleting the IM group itself.
  • Remove an IM connection: immediately stop messaging. Re-adding the same bot restores prior chats as paused, and they must be resumed manually.
Before rollout, validate direct messages, group routing through one bot, unauthorized requests, file delivery, human confirmation, connection-disable behavior, and the expected Wake-up Mode task, topic, and memory records.