# NousResearch/hermes-agent · CUA session restart after MCP timeout

## Open now

- Nothing open on GitHub.

These items address a bug where the CUA driver backend fails to restart or recreate a session following an MCP timeout, causing all subsequent tool calls to fail. The work includes surfacing the outcome-unknown state when a timeout occurs.

## 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 #94186. Verify it addresses your case.
- **Recommended:** read PR #94186 (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-94186`. 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evidence (`STRUCTURAL_SPANNING`): every member is connected by structural evidence: shared changed files, or a closing/superseded reference.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

- #74799: \`CuaDriverBackend.call_tool\` does not restart the session after an MCP timeout, so every later call fails

## Prior & competing PRs

- **#94186: fix(computer-use): recreate CUA session after timeout with outcome-unknown surfacing (#85125 3b)**. merged to main · fix tier `verified`
  - maintainer direction: category `merged`
  - files: `tests/tools/test_computer_use.py`, `tools/computer_use/cua_backend.py`
- **#74877: fix(computer-use): restart CUA session after timeout**. closed without merge
  - maintainer direction: category `superseded_by_pr`; implication `superseded`; refs `#94186`

## Fix status

- Merged to main in PR #94186 (cited above). No release data is tracked. Verify downstream.
- Fix last verified (merged) `2026-08-24`.
- Subsystem: `agent`