# NousResearch/hermes-agent · Token counting on truncated or incomplete API responses

## Open now

- 1 issue, 2 PRs open on GitHub.
- #38458: \[Bug\]: The token consumed is not counted if the api call fails for "length" reason.
- PR #38460: fix(conversation): count tokens from length-truncated responses
- PR #38553: fix(agent): track tokens on truncated responses and refund api_call_count on retry exhaustion

These items address token usage not being recorded when API calls encounter errors or responses are truncated due to length limits. Related changes also cover refunding call counts when retries are exhausted.

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evidence (`STRUCTURAL_SPANNING`): every member is connected by structural evidence: shared changed files, or a closing/superseded reference.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

- #38458: \[Bug\]: The token consumed is not counted if the api call fails for "length" reason.

## Prior & competing PRs

- **#38460: fix(conversation): count tokens from length-truncated responses**. open
  - maintainer direction: category `uncategorized`; implication `needs_llm`
  - files: `agent/conversation_loop.py`, `tests/run_agent/test_run_agent.py`
- **#38553: fix(agent): track tokens on truncated responses and refund api_call_count on retry exhaustion**. open
  - maintainer direction: category `uncategorized`; implication `needs_llm`
  - files: `agent/conversation_loop.py`, `tests/run_agent/test_run_agent.py`

## Fix status

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