{"repo":"NousResearch/hermes-agent","public_id":"53959","display_label":"Tool-call loop guardrail halt and recovery behavior","summary":"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.","subsystem":"agent","counts":{"members":4,"open_issues":2,"open_issues_distinct":2,"open_prs":1,"closed_issues":0,"merged_prs":0,"attempt_prs":2},"landed_fix":null,"resolution":{"state":"unresolved","by":null},"freshness":{"state":"never_verified","last_verified_at":null,"is_stale":false},"grouping":{"backbone":"STRUCTURAL_PARTIAL","link_density":0.3933333333333333},"fix_edges":[],"members":[{"kind":"issue","number":53959,"title":"[Feature Request] same_tool_failure_halt guardrail should support fallback strategies instead of hard stop","url":null,"state":"open"},{"kind":"issue","number":64322,"title":"[Bug]: Tool loop guardrail hard-stop silently halts task and requires manual prompt instead of allowing model recovery","url":null,"state":"open"},{"kind":"pr","number":64363,"title":"fix(agent): let guardrail hard-stop give the model one rebound before halting","url":null,"state":"closed","close_reason":{"category":"stale_abandoned","implication":"active"},"merged":false},{"kind":"pr","number":92433,"title":"fix(agent): rebound once after blocked tool batch","url":null,"state":"open","close_reason":{"refs":[{"kind":"pr","value":"#64322","number":64322},{"kind":"pr","value":"#94442","number":94442},{"kind":"pr","value":"#64804","number":64804},{"kind":"pr","value":"#64322","number":64322}],"category":"partial_fix","implication":"needs_llm"},"merged":false}],"trust":{"default_tier":"verified","includes_suggested":false}}