Activity

A live board of active, completed, and errored agent work.

The Activity page is the fastest way to see what your agents are doing right now. Every Slack thread, test run, and scheduled job becomes a task card. The board groups them into active work, recent completions, and errors so you can scan the workspace without opening every channel.

Open it from the sidebar under Activity. The board polls every 4 seconds, so fresh work shows up without a reload.

Columns

Column	What’s in it
Active	Work still in progress.
Recent	Completed work with no current error.
Errors	Work that needs attention.

Each card shows the request, the agent, the person who started it, turn count, sensitive-data markers when relevant, and the latest update time. Cards are intentionally compact so the board stays useful when the workspace is busy.

Filters

Narrow the board with the controls above the columns:

• Agent - show only tasks that involved a specific agent.
• Window - default is the last 7 days; switch to a shorter or longer window when investigating.

Filters are saved in the URL, so you can share a filtered view with a teammate.

Stats strip

Above the board, four cards summarize the current filtered view:

• Active - tasks with in-flight work.
• Completed - finished without any errors.
• Errors - tasks with at least one errored activity.
• Total - sum of the above.

Use the strip as a quick health check. If Errors spikes, jump straight to the error column or open Observability for a deeper trace.

Task detail

Click any card to open the task detail page:

• The original request and initiator
• The assigned agent and status
• Turns, tool calls, tokens, and latency
• A trace of each response or tool call
• A link back to the original Slack thread when available

Long requests are shortened on the board, then shown with more context on the detail page.

Replay failed work

If a task failed, Activity shows a replay control. Replay reruns the failed turn in place, which is useful for transient backend interruptions, tool timeouts, or temporary Slack delivery issues.

Replay only appears where it is safe and allowed for your role.

Enabling

Current installs enable Activity capture in .env by default. If you are running an older manual install and the board is empty, confirm the flag is present:

# in .env
ACTIVITY_DASHBOARD=1

Restart SlackHive after changing .env:

slackhive stop && slackhive start

Access control

Who sees what on the dashboard depends on role:

Role	What they see
superadmin / admin	Every task across every agent.
editor	Only tasks that touched an agent they created or were granted access to via agent access.
viewer	Blocked entirely - the sidebar link is hidden and all three activity API routes return 403.

Enforcement happens server-side on every request, so URL tampering (e.g. passing ?agent=<someone-elses>) can’t bypass it. Agent access is managed on each agent’s detail page → Access (admin/superadmin only).

Retention

Tasks, activities, and tool calls live in the same SQLite database as everything else (~/.slackhive/data.db). There is no automatic pruning today - back up the DB if you want a long-term record, or truncate the tasks, activities, and tool_calls tables directly when you need to reclaim space.

Related

Observability

Session traces, tokens, sensitive access, tools, latency, and replay.

Live Logs

Real-time runner logs when you need raw operational detail.