fix: improve interrupt responsiveness during concurrent tool execution#10935
Merged
Conversation
…n and follow-up turns Three targeted fixes for the 'agent stuck on terminal command' report: 1. **Concurrent tool wait loop now checks interrupts** (run_agent.py) The sequential path checked _interrupt_requested before each tool call, but the concurrent path's wait loop just blocked with 30s timeouts. Now polls every 5s and cancels pending futures on interrupt, giving already-running tools 3s to notice the per-thread interrupt signal. 2. **Cancelled concurrent tools get proper interrupt messages** (run_agent.py) When a concurrent tool is cancelled or didn't return a result due to interrupt, the tool result message says 'skipped due to user interrupt' instead of a generic error. 3. **Typing indicator fires before follow-up turn** (gateway/run.py) After an interrupt is acknowledged and the pending message dequeued, the gateway now sends a typing indicator before starting the recursive _run_agent call. This gives the user immediate visual feedback that the system is processing their new message (closing the perceived 'dead air' gap between the interrupt ack and the response). Reported by @_SushantSays.
shuv1337
added a commit
to shuv1337/hermes-agent
that referenced
this pull request
Apr 16, 2026
Upstream's QQ platform hint (added in the salvaged PR NousResearch#10935/NousResearch#10940 block that landed during this merge) re-introduced the 'MEDIA:/absolute/path/to/file' literal that our prior commit 03f8a5e fixed for WeCom. The ANTHROPIC_OAUTH_BLOCKED_LITERALS guard test flagged it. Same fix pattern: 'absolute' -> 'full' to break tokenization.
ulasbilgen
pushed a commit
to ulasbilgen/hermes-adhd-agent
that referenced
this pull request
May 1, 2026
…n and follow-up turns (NousResearch#10935) Three targeted fixes for the 'agent stuck on terminal command' report: 1. **Concurrent tool wait loop now checks interrupts** (run_agent.py) The sequential path checked _interrupt_requested before each tool call, but the concurrent path's wait loop just blocked with 30s timeouts. Now polls every 5s and cancels pending futures on interrupt, giving already-running tools 3s to notice the per-thread interrupt signal. 2. **Cancelled concurrent tools get proper interrupt messages** (run_agent.py) When a concurrent tool is cancelled or didn't return a result due to interrupt, the tool result message says 'skipped due to user interrupt' instead of a generic error. 3. **Typing indicator fires before follow-up turn** (gateway/run.py) After an interrupt is acknowledged and the pending message dequeued, the gateway now sends a typing indicator before starting the recursive _run_agent call. This gives the user immediate visual feedback that the system is processing their new message (closing the perceived 'dead air' gap between the interrupt ack and the response). Reported by @_SushantSays.
aj-nt
pushed a commit
to aj-nt/hermes-agent
that referenced
this pull request
May 1, 2026
…n and follow-up turns (NousResearch#10935) Three targeted fixes for the 'agent stuck on terminal command' report: 1. **Concurrent tool wait loop now checks interrupts** (run_agent.py) The sequential path checked _interrupt_requested before each tool call, but the concurrent path's wait loop just blocked with 30s timeouts. Now polls every 5s and cancels pending futures on interrupt, giving already-running tools 3s to notice the per-thread interrupt signal. 2. **Cancelled concurrent tools get proper interrupt messages** (run_agent.py) When a concurrent tool is cancelled or didn't return a result due to interrupt, the tool result message says 'skipped due to user interrupt' instead of a generic error. 3. **Typing indicator fires before follow-up turn** (gateway/run.py) After an interrupt is acknowledged and the pending message dequeued, the gateway now sends a typing indicator before starting the recursive _run_agent call. This gives the user immediate visual feedback that the system is processing their new message (closing the perceived 'dead air' gap between the interrupt ack and the response). Reported by @_SushantSays.
02356abc
pushed a commit
to 02356abc/hermes-agent
that referenced
this pull request
May 14, 2026
…n and follow-up turns (NousResearch#10935) Three targeted fixes for the 'agent stuck on terminal command' report: 1. **Concurrent tool wait loop now checks interrupts** (run_agent.py) The sequential path checked _interrupt_requested before each tool call, but the concurrent path's wait loop just blocked with 30s timeouts. Now polls every 5s and cancels pending futures on interrupt, giving already-running tools 3s to notice the per-thread interrupt signal. 2. **Cancelled concurrent tools get proper interrupt messages** (run_agent.py) When a concurrent tool is cancelled or didn't return a result due to interrupt, the tool result message says 'skipped due to user interrupt' instead of a generic error. 3. **Typing indicator fires before follow-up turn** (gateway/run.py) After an interrupt is acknowledged and the pending message dequeued, the gateway now sends a typing indicator before starting the recursive _run_agent call. This gives the user immediate visual feedback that the system is processing their new message (closing the perceived 'dead air' gap between the interrupt ack and the response). Reported by @_SushantSays.
gweeteve
pushed a commit
to gweeteve/hermes-agent
that referenced
this pull request
Jun 2, 2026
…n and follow-up turns (NousResearch#10935) Three targeted fixes for the 'agent stuck on terminal command' report: 1. **Concurrent tool wait loop now checks interrupts** (run_agent.py) The sequential path checked _interrupt_requested before each tool call, but the concurrent path's wait loop just blocked with 30s timeouts. Now polls every 5s and cancels pending futures on interrupt, giving already-running tools 3s to notice the per-thread interrupt signal. 2. **Cancelled concurrent tools get proper interrupt messages** (run_agent.py) When a concurrent tool is cancelled or didn't return a result due to interrupt, the tool result message says 'skipped due to user interrupt' instead of a generic error. 3. **Typing indicator fires before follow-up turn** (gateway/run.py) After an interrupt is acknowledged and the pending message dequeued, the gateway now sends a typing indicator before starting the recursive _run_agent call. This gives the user immediate visual feedback that the system is processing their new message (closing the perceived 'dead air' gap between the interrupt ack and the response). Reported by @_SushantSays.
Egavasyug
pushed a commit
to Egavasyug/hermes-agent
that referenced
this pull request
Jun 10, 2026
…n and follow-up turns (NousResearch#10935) Three targeted fixes for the 'agent stuck on terminal command' report: 1. **Concurrent tool wait loop now checks interrupts** (run_agent.py) The sequential path checked _interrupt_requested before each tool call, but the concurrent path's wait loop just blocked with 30s timeouts. Now polls every 5s and cancels pending futures on interrupt, giving already-running tools 3s to notice the per-thread interrupt signal. 2. **Cancelled concurrent tools get proper interrupt messages** (run_agent.py) When a concurrent tool is cancelled or didn't return a result due to interrupt, the tool result message says 'skipped due to user interrupt' instead of a generic error. 3. **Typing indicator fires before follow-up turn** (gateway/run.py) After an interrupt is acknowledged and the pending message dequeued, the gateway now sends a typing indicator before starting the recursive _run_agent call. This gives the user immediate visual feedback that the system is processing their new message (closing the perceived 'dead air' gap between the interrupt ack and the response). Reported by @_SushantSays.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Fixes the 'agent stuck on long terminal command' issue reported by @_SushantSays on Twitter. When a user sends a message while the agent is running a long-running terminal command, the interrupt is acknowledged but the follow-up can feel unresponsive.
Changes
1. Concurrent tool wait loop now checks interrupts (
run_agent.py)The sequential tool execution path already checked
_interrupt_requestedbefore each tool call (line 7538), but the concurrent path's wait loop was a blind 30-second poll. Now:_interrupt_requestedeach poll2. Cancelled concurrent tools get proper interrupt messages (
run_agent.py)When a concurrent tool is cancelled or didn't return a result due to interrupt, the tool result message says 'skipped due to user interrupt' instead of a generic error.
3. Typing indicator fires before follow-up turn (
gateway/run.py)After an interrupt is acknowledged and the pending message dequeued, the gateway sends a typing indicator before starting the recursive
_run_agentcall. This closes the perceived 'dead air' gap between the interrupt ack and the response — the user sees the typing bubble immediately instead of silence while the system bootstraps the new turn.Test plan
tests/run_agent/test_concurrent_interrupt.py— verifies both the mid-execution interrupt path and the pre-flight skip pathtest_busy_session_ack,test_interrupt_key_match,test_telegram_photo_interruptsContext
The core interrupt mechanism works correctly (per-thread interrupt flags, terminal process group kill, sequential tool skip). The remaining user-perceived 'stuck' state comes from:
Reported by
@_SushantSaysvia Twitter thread.