# NousResearch/hermes-agent · vLLM max_tokens/max_model_len error misparsed as prompt-too-long

## Open now

- 1 issue, 2 PRs open on GitHub.
- #102494: \[Bug\]: vLLM 'max_tokens cannot be greater than max_model_len=max_total_tokens' 400 misparsed as prompt-too-long — sessions die with 'Cannot compress further' on custom-provider switch
- PR #102502: fix(model_metadata): parse vLLM max_model_len=max_total_tokens output-cap rejection
- PR #102527: fix(model_metadata): parse vLLM max_tokens greater than max_model_len error

A bug where vLLM's 400 error about max_tokens exceeding max_model_len is incorrectly parsed as a prompt-too-long rejection, causing sessions to fail with 'Cannot compress further'. Two fixes address the parsing logic for this specific vLLM error format.

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evidence (`STRUCTURAL_SPANNING`): every member is connected by structural evidence: shared changed files, or a closing/superseded reference.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

- #102494: \[Bug\]: vLLM 'max_tokens cannot be greater than max_model_len=max_total_tokens' 400 misparsed as prompt-too-long — sessions die with 'Cannot compress further' on custom-provider switch

## Prior & competing PRs

- **#102502: fix(model_metadata): parse vLLM max_model_len=max_total_tokens output-cap rejection**. open
  - maintainer direction: category `uncategorized`; implication `needs_llm`
  - files: `agent/model_metadata.py`, `tests/agent/test_model_metadata.py`, `tests/test_output_cap_parsing.py`
- **#102527: fix(model_metadata): parse vLLM max_tokens greater than max_model_len error**. open
  - maintainer direction: category `duplicate_of`; implication `duplicate`; refs `#102502`, `#102494`, `#102502`
  - files: `agent/model_metadata.py`, `tests/agent/test_model_metadata.py`, `tests/test_output_cap_parsing.py`
- **#137625: fix(agent): parse vLLM max_model_len=max_total_tokens output-cap rejection**. closed without merge
  - maintainer direction: category `uncategorized`; implication `needs_llm`

## Fix status

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