# NousResearch/hermes-agent · Per-provider request rate and concurrency controls

## Open now

- 1 issue, 2 PRs open on GitHub.
- #108596: Concurrent calls to the same local/self-hosted model backend contend and stall instead of queueing
- PR #108722: fix(agent): serialize concurrent requests to the same local backend
- PR #128816: feat(agent): per-provider max_in_flight and requests_per_minute request admission

These items address adding per-provider configuration for maximum in-flight requests and requests per minute, and handling contention when multiple concurrent requests target the same local or self-hosted model backend.

## TL;DR

- 3 member(s): 1 open issue(s), 0 closed issue(s), 2 open PR(s), 0 merged PR(s), 0 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evidence (`STRUCTURAL_SPANNING`): every member is connected by structural evidence: shared changed files, or a closing/superseded reference.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 `0.67`: 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

- #108596: Concurrent calls to the same local/self-hosted model backend contend and stall instead of queueing

## Prior & competing PRs

- **#108722: fix(agent): serialize concurrent requests to the same local backend**. open
  - maintainer direction: category `uncategorized`; implication `needs_llm`
  - files: `agent/chat_completion_helpers.py`, `agent/model_metadata.py`, `tests/agent/test_local_endpoint_lock.py`
- **#128816: feat(agent): per-provider max_in_flight and requests_per_minute request admission**. open
  - maintainer direction: category `implemented_elsewhere`; implication `superseded`; refs `2a96312c80`, `2a96312c801f7876deac5e62e65fa9b711d9d0bf`, `2a96312c801f7876deac5e62e65fa9b711d9d0bf`, `0466a04bc874983551569fa08810869def4b550b`, `2a96312c801f7876deac5e62e65fa9b711d9d0bf`, `2a96312c801f7876deac5e62e65fa9b711d9d0bf`, `2a96312c801f7876deac5e62e65fa9b711d9d0bf`, `2a96312c801f7876deac5e62e65fa9b711d9d0bf`, `2a96312c801f7876deac5e62e65fa9b711d9d0bf`, `2a96312c801f7876deac5e62e65fa9b711d9d0bf`, `2a96312c801f7876deac5e62e65fa9b711d9d0bf`, `2a96312c801f7876deac5e62e65fa9b711d9d0bf`, `2a96312c801f7876deac5e62e65fa9b711d9d0bf`, `2a96312c801f7876deac5e62e65fa9b711d9d0bf`, `2a96312c801f7876deac5e62e65fa9b711d9d0bf`, `2a96312c801f7876deac5e62e65fa9b711d9d0bf`, `2a96312c801f7876deac5e62e65fa9b711d9d0bf`, `2a96312c801f7876deac5e62e65fa9b711d9d0bf`, `2a96312c801f7876deac5e62e65fa9b711d9d0bf`, `2a96312c801f7876deac5e62e65fa9b711d9d0bf`, `2a96312c801f7876deac5e62e65fa9b711d9d0bf`, `2a96312c801f7876deac5e62e65fa9b711d9d0bf`, `2a96312c801f7876deac5e62e65fa9b711d9d0bf`, `2a96312c801f7876deac5e62e65fa9b711d9d0bf`, `2a96312c801f7876deac5e62e65fa9b711d9d0bf`, `2d2da997d0053d6b4d8611a73dc81bd942be6a1f`, `b682e165f96e9bacdc01c319fb98dacaa58b897d`, `fa129b5e97c050c764675e9712be76c0e7a855ae`, `2a96312c801f7876deac5e62e65fa9b711d9d0bf`, `2a96312c801f7876deac5e62e65fa9b711d9d0bf`, `2a96312c801f7876deac5e62e65fa9b711d9d0bf`, `2a96312c801f7876deac5e62e65fa9b711d9d0bf`, `2a96312c801f7876deac5e62e65fa9b711d9d0bf`, `2a96312c801f7876deac5e62e65fa9b711d9d0bf`, `2a96312c801f7876deac5e62e65fa9b711d9d0bf`, `2a96312c801f7876deac5e62e65fa9b711d9d0bf`, `2a96312c801f7876deac5e62e65fa9b711d9d0bf`, `2a96312c801f7876deac5e62e65fa9b711d9d0bf`, `2a96312c801f7876deac5e62e65fa9b711d9d0bf`, `2a96312c801f7876deac5e62e65fa9b711d9d0bf`, `2a96312c801f7876deac5e62e65fa9b711d9d0bf`, `2a96312c801f7876deac5e62e65fa9b711d9d0bf`, `2a96312c801f7876deac5e62e65fa9b711d9d0bf`, `2a96312c801f7876deac5e62e65fa9b711d9d0bf`, `2a96312c801f7876deac5e62e65fa9b711d9d0bf`, `2a96312c801f7876deac5e62e65fa9b711d9d0bf`, `2a96312c801f7876deac5e62e65fa9b711d9d0bf`, `2a96312c801f7876deac5e62e65fa9b711d9d0bf`, `2a96312c801f7876deac5e62e65fa9b711d9d0bf`, `2a96312c801f7876deac5e62e65fa9b711d9d0bf`, `#128816`, `#172554`, `#128816`, `#110358`, `#110383`
  - files: `agent/auxiliary_client.py`, `agent/chat_completion_helpers.py`, `agent/chat_completion_stream_monitor.py`, `agent/codex_runtime.py`, `agent/llm_concurrency.py`, `agent/rate_limit_credits.py`, `agent/relay_llm.py`, `cli-config.yaml.example`, `hermes_cli/config_providers.py`, `tests/agent/test_llm_concurrency.py`, `website/docs/user-guide/configuration.md`, `website/i18n/zh-Hans/docusaurus-plugin-content-docs/current/user-guide/configuration.md`

## Fix status

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