# NousResearch/hermes-agent · Azure/SGLang output-cap rejection handling and retry logic

## Open now

- Nothing open on GitHub.

These items address how the agent handles output-token-cap rejections from Azure and SGLang, improving retry behavior to reduce the cap rather than entering a compression loop. A related bug reports that Hermes sends an oversized max_tokens value regardless of config, also triggering compression loops.

## TL;DR

- 3 member(s): 0 open issue(s), 1 closed issue(s), 0 open PR(s), 1 merged PR(s), 1 PR(s) closed without merging.
- A fix was merged to main in PR #115897. Verify it addresses your case.
- **Recommended:** read PR #115897 (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-115897`. 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evidence (`STRUCTURAL_SPANNING`): every member is connected by structural evidence: shared changed files, or a closing/superseded reference.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.

## Closed / duplicate issues

- #78405: Bug: Hermes sends max_tokens=65536 ignoring config, causes compression loop

## Prior & competing PRs

- **#115897: fix(agent): Azure and SGLang output-cap rejections retry with a smaller cap instead of a compression loop; failure copy stops naming the removed model.max_tokens key (#78405, #83521, salvage #81289, #83558)**. merged to main · fix tier `verified`
  - maintainer direction: category `merged`
  - files: `agent/model_metadata.py`, `agent/turn_overflow.py`, `tests/agent/test_output_cap_parsing.py`
- **#81289: fix(agent): parse Azure output-cap rejection phrasing (#78405)**. closed without merge
  - maintainer direction: category `merged_via`; implication `superseded`; refs `6d8a8bebf70b`, `#115897`, `#78405`, `#83521`, `#81289`, `#83558`

## Fix status

- Merged to main in PR #115897 (cited above). No release data is tracked. Verify downstream.
- Fix last verified (merged) `2026-09-19`.
- Subsystem: `agent`
