4.2 KiB
title, type, status, created, updated, review_after, verified_on, confidence, tags, sources
| title | type | status | created | updated | review_after | verified_on | confidence | tags | sources | ||
|---|---|---|---|---|---|---|---|---|---|---|---|
| Troubleshoot Tool Loop | runbook | unresolved | 2026-07-22 | 2026-10-20 | 2026-11-19 | 2026-10-20 | medium |
|
Filled in 2026-10-20 from live configuration, live process state and two recorded incidents. The "stub" note below is retained as history.
Troubleshoot Tool Loop
Symptoms
- The agent repeats the same tool call with identical arguments and makes no progress.
- The agent repeats itself in the response stream (no tool involved) — the model loops on its own output and Hermes cuts the stream.
These are two different faults with two different detectors. Do not assume one covers the other.
1. Tool-call loop — detected by tool_loop_guardrails
Symptoms
Agent loops on one tool or endpoint. Hermes emits a warning naming the tool.
Configuration (verified live 2026-10-20, ~/.hermes/config.yaml)
tool_loop_guardrails:
warnings_enabled: true
hard_stop_enabled: false
warn_after:
exact_failure: 2
same_tool_failure: 3
idempotent_no_progress: 2
hard_stop_after:
exact_failure: 5
same_tool_failure: 8
idempotent_no_progress: 5
hard_stop_enabled: falseis the key fact. Hermes will warn about a stuck tool loop but will not force-stop itself. A genuinely stuck loop only gets a warning — a human (or the messaging integration) is the real backstop. See concepts/tool-calling.
Procedure
- Inspect recent Hermes agent logs:
~/.hermes/logs/agent.log*(grep for the tool name). - Identify the looping tool path. Common culprits in this estate: a browser tool against a dead Camofox service, a terminal tool against a stale persistent shell, or a webhook that returns 200 with an empty body.
- Check the dependency, not just the agent. On this estate the most frequent tool-loop cause was an upstream service being down while the tool still returned a response. Verify with the relevant runbook: runbooks/restart-browser, runbooks/restart-hermes, runbooks/provider-health.
- If the loop is a stuck worker, restart it:
systemctl --user restart hermes-gateway.service. - Re-run a limited test scenario and confirm the guard no longer fires.
Verification
Agent handles the same scenario without repeating, and no tool_loop_guardrails warning appears
in agent.log.
2. Model-output (degenerate stream) loop — detected by the stream guard
Symptoms
The run delivers a canned non-answer such as "Your request was not processed. Send it again
if you still want me to carry it out.", and then fails with
RuntimeError: Model output entered a repetition loop and the stream was cut mid-loop; discarding the degenerate response.
This is the 2026-10-18 case — see
incidents/2026-10-18-degenerate-stream-canned-substitute
Procedure
- Read the run's
errorin~/.hermes/cron/executions.db— the phraserepetition loopidentifies this fault. - Check
delivery_outcomeon the same row. In the 2026-10-18 incident the row wasdelivery_outcome: delivered— the canned non-answer reached Telegram before the run failed. A delivered message is not evidence of delivered content. - Confirm the provider is healthy: the 2026-10-18 case rode the same
custom:omni-101alias that produced the 2026-10-14/15 connection-refused storm and the 2026-10-16/17 and 2026-10-19 resource-pressure 503 bursts. See runbooks/provider-health and incidents/2026-10-16-omniroute-503-resource-pressure. - Do not lower
tool_loop_guardrailsthresholds for this fault — they watch tool calls, and the degenerate-stream guard is a separate mechanism.
Verification
The next scheduled run of the job completes with status: completed and error: null, and the
delivered message contains real content.
Last successfully used
2026-07-22 — re-verified against live config and live incidents on 2026-10-20; the procedure has
not itself been executed end-to-end in a live loop, so confidence was raised only to medium.