Cairn
NousResearch/hermes-agent

Fix interrupt attribution for terminal and batch timeouts

Cluster 130207 · agent. Data as of

Nothing open on GitHub. Fix merged in #133271 on 7 Oct 2026. Check it covers your case.

The short answer

0open issues
0open PRs
4items grouped
Known?
Yes. 4 related items grouped here, 1 issue already closed.
Fix event
A fix was merged to main in PR #133271. Check it covers your case. No release data is tracked.
Tracker
The maintainers' tracker marks this resolved, deciding PR #133271. That is separate from the fix event.
Still open
Nothing open on GitHub.

These items address incorrect attribution of soft interrupts and terminal batch timeouts, where system-initiated stops were being misidentified as user interruptions. The work involves routing blame to the correct issuer and adjusting how synthetic interrupt events are surfaced.

Open issues0

No open issues.

Open PRs0

No open pull requests.

Fixes on record

Merged to main. A stamp counts the issues a fix is linked to.

  • #133271 Terminal batch timeouts are no longer reported as the user's stop, a user stop during a wedged batch keeps its message, and interrupted turns stop being answered with "[response interrupted]" (#130207, #132949, salvage #132751)

    merged to main

    files: agent/agent_runtime_helpers.py, agent/agent_runtime_helpers_placeholders.py, agent/conversation_loop.py, agent/interrupt_control.py, agent/message_sanitization.py, agent/terminal_approval_batch.py, agent/tool_executor.py, agent/turn_api_call.py, agent/turn_iteration_prep.py, contributors/emails/[redacted:email], tests/acp_adapter/test_events.py, tests/agent/test_close_interrupted_tool_sequence.py, tests/agent/test_concurrent_interrupt.py, tests/agent/test_interrupt_issuer_attribution.py, tests/agent/test_partial_stream_finish_reason.py, tests/agent/test_replay_echo_retirement.py, tests/agent/test_run_agent.py, tests/agent/test_run_agent_interrupt_hook.py, tests/agent/test_sanitiser_escalation.py, tests/agent/test_steer.py (+3 more)

2 PRs closed without merging

From the close comments: merged via another change 2

  • #130209 fix(agent): attribute terminal batch timeouts to system · merged via another change → 70dcdd6, #133271
  • #132751 fix(agent): attribute soft interrupts to their real issuer, and hide the synthetic interrupt close · merged via another change → 70dcdd6, #133271
Closed issues · 1
  • Closed#130207[Bug]: Terminal batch timeout self-aborts via a soft interrupt(message) — system stop is booked as interrupted_by_user and shown as "Operation interrupted."
How this cluster was grouped
  • Link evidence (structural links throughout): every member is connected by structural evidence: shared changed files, or a closing/superseded reference.
  • Pairwise link density 0.50: the share of item 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.

Pick up a Lab task

Check whether a fix covers the open issues here, with your own agent. Bring back evidence for maintainers.

Open the Lab

At a glance

Subsystem
agent
Merged PRs
#133271
Closed issues
1
Attempts
2 PRs closed without merging
Fix link checked
7 Oct 2026

For your agent

The same facts, typed.

cluster/130207.json
cluster/130207.md