# NousResearch/hermes-agent · Transcript sanitiser loop detection and escalation

## Open now

- 0 issues, 2 PRs open on GitHub.
- PR #96916: fix(agent): stop empty-transcript sanitizer from warning on every send (#96870)
- PR #97417: fix(agent): add escalation policy for sanitiser healing loops

These items address a problem where the transcript sanitiser repeatedly triggers without surfacing meaningful feedback, adding counters, escalation policy, and a one-time user notice to make repeated healing loops visible rather than silent.

## TL;DR

- 4 member(s): 0 open issue(s), 1 closed issue(s), 2 open PR(s), 1 merged PR(s), 0 PR(s) closed without merging.
- A fix was merged to main in PR #99687. Verify it addresses your case.
- **Recommended:** read PR #99687 (and any competing PRs below) before filing. Confirm the merged change covers your symptom.

## Maintainer resolution verdict

- Internal-tracker verdict over this cluster's issue members: `resolved` · deciding PR(s): `pr-99687`. This is distinct from the fix status above. Weigh it yourself.

## How this cluster was grouped

- Link evidence (`STRUCTURAL_SPANNING`): every member is connected by structural evidence: shared changed files, or a closing/superseded reference.
- Pairwise link density `0.50`: 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.

## Closed / duplicate issues

- #96870: Silent recovery mode: sanitiser + Telegram adapter silently loop while user/agent sees nothing

## Prior & competing PRs

- **#99687: feat(agent): escalate repeated transcript-sanitiser heals — counters, one ERROR, one-time user notice (#96870)**. merged to main · fix tier `verified`
  - maintainer direction: category `merged`
  - files: `agent/agent_runtime_helpers.py`, `agent/conversation_loop.py`, `cli-config.yaml.example`, `hermes_cli/config_defaults.py`, `hermes_cli/debug.py`, `hermes_cli/dump.py`, `tests/run_agent/test_sanitiser_escalation.py`
- **#96916: fix(agent): stop empty-transcript sanitizer from warning on every send (#96870)**. open
  - maintainer direction: category `silent_close`; implication `active`
  - files: `agent/agent_runtime_helpers.py`, `agent/conversation_loop.py`, `tests/run_agent/test_sanitiser_escalation.py`
- **#97417: fix(agent): add escalation policy for sanitiser healing loops**. open
  - maintainer direction: category `silent_close`; implication `active`
  - files: `agent/agent_runtime_helpers.py`

## Fix status

- Merged to main in PR #99687 (cited above). No release data is tracked. Verify downstream.
- Fix last verified (merged) `2026-08-31`.
- Subsystem: `agent`