# NousResearch/hermes-agent · Agent fallback chain behavior: api_mode, reset, cooldown

## Open now

- 1 issue, 2 PRs open on GitHub.
- #57582: Fallback chain (_fallback_index) doesn't reset on primary recovery — mid-session exhaustion silently disables failover for rest of session
- PR #16346: fix(agent): respect fallback api_mode overrides
- PR #57700: fix(agent): gate exhaustion cooldown to bounded window, preserve #24996 replay throttle

These members all concern the agent's fallback handling. Topics include respecting explicit api_mode overrides, a fallback index not resetting after primary recovery, and bounding an exhaustion cooldown while keeping a replay throttle. The titles show related themes but do not establish one single shared problem.

## TL;DR

- 4 member(s): 1 open issue(s), 0 closed issue(s), 2 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evidence (`STRUCTURAL_SPANNING`): every member is connected by structural evidence: shared changed files, or a closing/superseded reference.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.

## Open related issues

- #57582: Fallback chain (_fallback_index) doesn't reset on primary recovery — mid-session exhaustion silently disables failover for rest of session

## Prior & competing PRs

- **#16346: fix(agent): respect fallback api_mode overrides**. open
  - maintainer direction: category `uncategorized`; implication `needs_llm`
  - files: `agent/agent_init.py`, `agent/chat_completion_helpers.py`, `gateway/run.py`, `hermes_cli/runtime_provider.py`, `tests/gateway/test_auth_fallback.py`, `tests/gateway/test_session_model_override_routing.py`, `tests/run_agent/test_init_fallback_on_exhausted_pool.py`, `tests/run_agent/test_provider_fallback.py`
- **#57700: fix(agent): gate exhaustion cooldown to bounded window, preserve #24996 replay throttle**. open
  - maintainer direction: category `duplicate_of`; implication `duplicate`; refs `#57700`, `#57535`, `#57691`
  - files: `agent/chat_completion_fallback.py`, `agent/chat_completion_helpers.py`, `tests/agent/test_fallback_exhaustion_cooldown.py`, `tests/agent/test_primary_runtime_restore.py`
- **#57957: \[codex\] fix(fallback): honor explicit api_mode**. closed without merge
  - maintainer direction: category `duplicate_of`; implication `duplicate`; refs `#16346`, `#29749`, `#57582`, `#57700`

## Fix status

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