# NousResearch/hermes-agent · Max output token limits ignored in some modes

## Open now

- 1 issue, 2 PRs open on GitHub.
- #104485: max_output_tokens override and HERMES_MAX_TOKENS are both ignored; only model.max_tokens caps the request
- PR #104495: fix(oneshot): resolve the output cap like the interactive CLI
- PR #104853: fix(agent): honor max_output_tokens overrides and HERMES_MAX_TOKENS

These items concern a bug where max_output_tokens overrides and the HERMES_MAX_TOKENS environment variable are not respected, with only the model's default cap being applied. Fixes are proposed for both the agent and oneshot execution paths.

## 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evidence (`STRUCTURAL_SPANNING`): every member is connected by structural evidence: shared changed files, or a closing/superseded reference.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

- #104485: max_output_tokens override and HERMES_MAX_TOKENS are both ignored; only model.max_tokens caps the request

## Prior & competing PRs

- **#104495: fix(oneshot): resolve the output cap like the interactive CLI**. open
  - maintainer direction: category `uncategorized`; implication `needs_llm`
  - files: `hermes_cli/oneshot.py`, `tests/hermes_cli/test_oneshot_max_tokens.py`
- **#104853: fix(agent): honor max_output_tokens overrides and HERMES_MAX_TOKENS**. open
  - maintainer direction: category `uncategorized`; implication `needs_llm`
  - files: `agent/agent_init.py`, `agent/chat_completion_helpers.py`, `agent/models_dev.py`, `agent/output_limits.py`, `tests/agent/test_models_dev.py`, `tests/agent/test_output_token_config.py`

## Fix status

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