Ananke.Platforms.Slack 0.7.2

Ananke.Platforms.Slack

Slack adapter for Ananke - bridges Slack Bot events (Socket Mode and Events API) to Ananke agent workflows via IMessagePlatformAdapter. Supports streaming chat responses using the post-then-edit pattern with automatic debouncing.

Install

dotnet add package Ananke.Platforms.Slack

Prerequisites

1. Create a Slack App at api.slack.com/apps
2. Enable Socket Mode and generate an App-Level Token (xapp-…)
3. Add Bot Token Scopes: chat:write, reactions:write, channels:history, groups:history, im:history, mpim:history
4. Subscribe to bot events: message.channels, message.groups, message.im, message.mpim
5. Install the app to your workspace and copy the Bot User OAuth Token (xoxb-…)

Quick start

using Ananke.Platforms;
using Ananke.Platforms.Slack;

services.AddAnankeSlack(options =>
{
    options.BotToken = config["Slack:BotToken"]!;
    options.AppToken = config["Slack:AppToken"]!;
    options.UseSocketMode = true;
});

services.AddSingleton<IPlatformMessageHandler, MyAgentHandler>();

What it registers

Connection modes

Streaming behavior

Slack does not support server-push streaming into a message. The adapter uses the post-then-edit pattern:

1. On the first text delta, a placeholder message (…) is posted
2. As deltas arrive, the message is edited via chat.update (debounced at 300 ms)
3. On completion, a final edit flushes the complete text

Thread support

Slack threads are handled automatically. Messages with a thread_ts are routed with PlatformMessage.ThreadId set, and responses are posted back into the same thread.

Slash commands — limitations

Unlike Discord, where slash commands can be registered programmatically at runtime, Slack slash commands have significant limitations that prevent automatic ToolKit → /command bridging:

What works today

Slack chat messages (DMs and channel messages) flow through SlackAdapter → IPlatformMessageHandler → StreamingChatWorkflow with full streaming and tool support. The LLM invokes tools naturally during conversation — this covers the primary use case.

Future possibilities

If Slack introduces a richer command model (or if demand justifies the manual-registration workflow), a future version could provide:

• A SlackSlashCommandHandler that maps incoming /command text to ToolKit.Tools[name].ExecuteAsync
• Helper scripts for bulk-configuring Slack commands from a ToolKit manifest
• response_url-based async responses for long-running tools

For now, the recommendation is to use Discord for slash-command-style tool invocation and Slack for conversational agent workflows.

Documentation

Full docs, demos, and architecture: github.com/sevensamurai/Ananke

License

Apache 2.0