# NousResearch/hermes-agent · Streaming tool name duplication fix for MiniMax/NVIDIA NIM

## Open now

- Nothing open on GitHub.

These items address a bug where certain models (MiniMax via NVIDIA NIM) resend the tool name in every streaming chunk, causing duplicate tool names in generated tool calls. The work involves identifying the issue and applying a fix to prevent the duplication.

## 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 #12230. Verify it addresses your case.
- **Recommended:** read PR #12230 (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-12230`. 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evidence (`STRUCTURAL_SPANNING`): every member is connected by structural evidence: shared changed files, or a closing/superseded reference.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

- #8259: \[Bug\]: nvidia model: minimaxai/minimax-m2.7, Model generated invalid tool call:

## Prior & competing PRs

- **#12230: fix: prevent streaming tool name duplication (MiniMax/NVIDIA NIM)**. merged to main · fix tier `verified`
  - maintainer direction: category `merged`
  - files: `run_agent.py`, `scripts/release.py`, `tests/run_agent/test_streaming.py`
- **#11984: fix: prevent tool name duplication for models that resend name in every streaming chunk (MiniMax/NVIDIA NIM)**. closed without merge
  - maintainer direction: category `merged_via`; implication `superseded`; refs `#12230`, `#8259`

## Fix status

- Merged to main in PR #12230 (cited above). No release data is tracked. Verify downstream.
- Fix last verified (merged) `2026-04-18`. This confirmation is old and may be out of date (a revert/reopen would not have invalidated it here); re-verify.
