Debugging Agents

Agent not responding? Start here - a quick path from symptom to fix using Logs, Activity, and Version History.

Three tools, one flow

When an agent doesn’t behave as expected, SlackHive gives you three places to look. Each one answers a different question:

Tool	Where	Answers
Logs	Agent → Logs tab	What did the agent actually do, step by step?
Activity	Sidebar → Activity	Is the agent currently running? Did it error?
Version History	Agent → History tab	Did a recent change break something?

Start with Activity for a quick status check. Go to Logs for the full trace. Use History to roll back if a change caused the issue.

---

Step 1 — Check Activity

Go to Activity in the sidebar. This is the live kanban of every task your agents are running or have recently completed.

• Active — the agent is mid-run right now
• Completed — finished successfully
• Errors — something went wrong

If the job shows Error, click into it. The error summary tells you:

• Was it a Claude error (model timeout, rate limit)?
• Was it an MCP failure (tool server down, credentials expired)?
• Was it a Slack API failure (bot not in channel, token expired)?

Most errors are in one of these three buckets and the fix is quick.

---

Step 2 — Read the Logs

Activity gives you the error. Logs give you the full story.

Open the agent → Logs tab. Each conversation is an expandable trace with:

• The incoming message
• Every tool call the agent made (MCP, memory read, skill invocation)
• The agent’s reasoning at each step
• The final response

Look for where the trace stops or goes sideways. Common patterns:

Symptom	Likely cause
Agent responds but gives wrong answer	Missing context - check wiki and memory
Agent stops mid-run	MCP server error or timeout
Agent says “I don’t have access to that”	Tool not assigned to the agent
No trace at all	Agent wasn’t running when the message arrived

---

Step 3 — Roll Back with Version History

If the agent was working last week and broke after an edit, use Version History.

Open the agent → History tab. Every save is a snapshot - full diff of what changed: system prompt, skills, memory, tool assignments.

Find the last version that worked, click Restore, and you’re back to the known-good state in one click. You can then compare the two versions side by side to see exactly what the breaking change was.

Before making significant changes to a working agent, note the current version number. If the edit breaks something, you can restore without hunting through history.

---

Common issues and fixes

Agent not responding in Slack

1. Check that the agent’s Slack bot token is valid — Settings → Slack Apps
2. Confirm the agent process is running — Activity should show recent pings
3. Verify the bot has been invited to the channel (/invite @agent-name)

Scheduled job ran but posted nothing

1. Open Activity → find the job run → check status
2. If Success but silent: the agent decided nothing was worth posting (check your prompt - add “post a one-line summary even if nothing changed”)
3. If Error: check the MCP server the agent depends on

Agent gives outdated answers

1. Check Memory - it may be recalling a stale fact. Delete the outdated memory entry.
2. Check the Wiki - if the source was re-ingested, the wiki may need a refresh.
3. If the system prompt was recently edited, check Version History for the change.

MCP tool calls failing

1. Go to Agent → Tools tab - verify the MCP server is listed and active
2. Check the MCP server’s credentials haven’t expired
3. Test the MCP server independently via Test Mode — open the agent → Test tab and send a message that triggers the tool

---

Next steps

Logs

Full reference for the Logs tab and what each field means.

Activity

Live task view with MCP call drill-down.

Version History

Snapshot browsing and one-click restore.

Troubleshooting

Startup errors, port conflicts, and CLI issues.