# NousResearch/hermes-agent · Tool-call loop guardrail halt and recovery behavior

## Open now

- 2 issues, 1 PR open on GitHub.
- #53959: \[Feature Request\] same_tool_failure_halt guardrail should support fallback strategies instead of hard stop
- #64322: \[Bug\]: Tool loop guardrail hard-stop silently halts task and requires manual prompt instead of allowing model recovery
- PR #92433: fix(agent): rebound once after blocked tool batch

These issues and PRs concern how the agent handles tool-call loop guardrail triggers, specifically whether a hard stop should silently halt the task or first give the model an opportunity to recover or use fallback strategies before ending the turn.

## TL;DR

- 4 member(s): 2 open issue(s), 0 closed issue(s), 1 open PR(s), 0 merged PR(s), 1 PR(s) closed without merging.
- No fix has been merged to main; one or more PRs were attempted (see below).
- **Recommended:** review the prior/competing PR(s) below. A fix was attempted but not merged; your case may extend or revive that work.

## Maintainer resolution verdict

- Internal-tracker verdict over this cluster's issue members: `unresolved`. This is distinct from the fix status above. Weigh it yourself.

## How this cluster was grouped

- Link evidence (`STRUCTURAL_PARTIAL`): some members are connected by structural evidence (shared changed files, or a closing/superseded reference); the rest are joined by an automated relevance judgement over their text.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 `0.39`: the share of member 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.

## Open related issues

- #53959: \[Feature Request\] same_tool_failure_halt guardrail should support fallback strategies instead of hard stop
- #64322: \[Bug\]: Tool loop guardrail hard-stop silently halts task and requires manual prompt instead of allowing model recovery

## Prior & competing PRs

- **#64363: fix(agent): let guardrail hard-stop give the model one rebound before halting**. closed without merge
  - maintainer direction: category `stale_abandoned`; implication `active`
- **#92433: fix(agent): rebound once after blocked tool batch**. open
  - maintainer direction: category `partial_fix`; implication `needs_llm`; refs `#64322`, `#94442`, `#64804`, `#64322`
  - files: `agent/agent_init.py`, `agent/conversation_loop.py`, `agent/tool_guardrails.py`, `agent/turn_context.py`, `tests/run_agent/test_tool_call_guardrail_runtime.py`

## Fix status

- No merged fix on record.
- Subsystem: `agent`