Cairn

Agent looping, hanging, and timeout behavior fixes

NousResearch/hermes-agent · cluster 6260 · agent

Data as of

5 open items. Fix merged in #6387. Check it covers your case.

The short answer

4open issues
1open PR
12items grouped
Known?
Yes. 12 related items grouped here, 3 issues already closed.
Fix event
A fix was merged to main in PR #6387. Check it covers your case. No release data is tracked.
Tracker
The maintainers' tracker marks this partially resolved, deciding PR #6387. That is separate from the fix event.
Still open
4 issues and 1 PR.

A mix of bug reports about agents getting stuck in loops or becoming unresponsive, alongside fixes targeting retry/timeout architecture, inactivity-based timeouts, tool loop guardrails, and cron scheduling issues. The members span two adjacent themes: agent execution reliability and cron job timing correctness.

Open issues4

  • Issue#57804[Bug]: looping when trying to fix itself
  • Issue#57809[Bug]: started nonsense language
  • Issue#57818[Bug]: stops working
  • Issue#57923[Bug]: got into loop AGAIN

Open PRs1

  • PR#57851fix: add same-call-repeat guardrail for idempotent tools with varying results

Fixes on record

Merged to main. A stamp counts the issues a fix is linked to.

  • #6387 fix(gateway): staged inactivity warning before timeout escalation

    merged to main

    files: cli-config.yaml.example, gateway/run.py, hermes_cli/config.py, tests/gateway/test_gateway_inactivity_timeout.py

  • #100967 fix(guardrails): tool-call loops hard-stop on unattended platforms, identical replays halt for any tool (#49075, #89069; salvage #49189, #47231)

    merged to main

    files: agent/agent_init.py, agent/tool_guardrails.py, cli-config.yaml.example, hermes_cli/config_defaults.py, run_agent.py, tests/agent/test_tool_guardrails.py, tests/run_agent/test_tool_call_guardrail_runtime.py, website/docs/user-guide/configuration.md, website/docs/user-guide/docker.md

2 PRs closed without merging

From the close comments: done elsewhere 1 · merged via another change 1

  • #6263 fix(gateway): staged inactivity warning before timeout escalation · merged via another change → #6387
  • #57816 fix: enable hard-stop tool loop guardrails by default, add idempotent streak detection · done elsewhere → 25d954c, #100967, #49189
Closed issues · 3
  • Closed#6260Inactivity timeout fires repeatedly with MiniMax 2.7 highspeed
  • Closed#57815[Bug]: looping and stuck and stopping work
  • Closed#57839[Bug]: agent gets stuck for 30 min not working
How this cluster was grouped
  • Link evidence (partly structural links): some members are connected by structural evidence (shared changed files, or a closing/superseded reference); the rest are joined by an automated relevance judgement over their text.
  • Members outside that structural core may belong to a different underlying problem.
  • Pairwise link density 0.12: the share of item pairs that carry a link, counting a structural link in full and a relevance-only link at 0.36. 1.00 means every pair is linked.

Pick up a Lab task

Check whether a fix covers the open issues here, with your own agent. Bring back evidence for maintainers.

Open the Lab

At a glance

Subsystem
agent
Merged PRs
#6387, #100967
Closed issues
3
Attempts
2 PRs closed without merging
Fix link checked
2 Sep 2026

For your agent

The same facts, typed.

cluster/6260.json
cluster/6260.md