feat: remote agents honor interrupt/stop/play control signals#442
Open
amit-gazal-thenvoi wants to merge 8 commits into
Open
feat: remote agents honor interrupt/stop/play control signals#442amit-gazal-thenvoi wants to merge 8 commits into
amit-gazal-thenvoi wants to merge 8 commits into
Conversation
Wires agent_control into the bridge's AgentRunner: interrupt/stop cancel whatever forward task is currently in flight for a room, and play proactively nudges the room via /next instead of waiting for the next natural event. The bridge holds no Band lifecycle logic, so interrupt and stop are handled identically here — the consume-vs-replay distinction and durable per-room suppression already happen correctly downstream via OneShotInvoker's /next claim check and the platform's stop gate.
The ReconnectedEvent path in ExecutionContext._process_event always ran the full /next sync, unlike the idle-timeout and resync-sentinel paths which already short-circuit on _stopped. The platform gate made this safe (a stopped room's /next is guaranteed empty), but it wasted a call on every reconnect while stopped. Skip locally for consistency with the other _stopped short-circuits.
… sync A stop control signal landing mid-cycle during _synchronize_with_next or _resync_pending_messages left the message in 'processing' for replay, but the enclosing loop kept polling /next, which returns 'processing' messages same as before. The very next iteration re-claimed and fully re-ran the cycle stop just aborted. Both loops now check self._stopped after processing a backlog message and stop polling until play resumes. Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
…y budget A cycle cancelled by our own stop/interrupt control signal never actually ran the handler, but record_attempt() was still charging it as a real attempt. At the default max_message_retries=1, a message stopped once and replayed via /next on resume would immediately land in permanently_failed before ever reaching the adapter. Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
…te-agents-honor-interrupt-and-stopresume # Conflicts: # src/band/client/streaming/client.py # src/band/platform/link.py # src/band/runtime/execution.py # src/band/runtime/platform_runtime.py # uv.lock
Collaborator
|
|
AlexanderZ-Band
requested changes
Jul 16, 2026
AlexanderZ-Band
left a comment
AlexanderZ-Band
left a comment
Collaborator
There was a problem hiding this comment.
See inline comments — main blockers: the in-flight cancellation gaps in the bridge (task registration ordering, play blocking the receive path), the interrupt/stop lifecycle windows in execution.py, and tests/integration/test_control_signals.py failing to import (thenvoi_rest).
- Extract control-signal routing/dedup into ControlSignalHandler (control.py), slimming AgentRunner; keep cancel/nudge/room-list on the runner. - Bridge: track in-flight forwards per room as a set so interrupt/stop cancels the running forward and queued same-room waiters; match/case dispatch with an unknown-mode warning; run play /next nudges as tracked background tasks so a following stop/interrupt isn't blocked on the receive path; flatten nesting. - execution.py: honor an interrupt/stop that lands in the claim->cycle window (before the cancellable task exists) via _cycle_armed/_pending_interrupt and a shared _abort_cycle unwind; queue the durable ack for retry when an interrupted message's mark_processed fails. - retry_tracker: discard_attempt decrements by one instead of clearing, so interrupting a retry doesn't reset the whole retry budget. - forwarder: document that interrupt/stop is best-effort for AgentCore (the in-flight boto3 thread can't be cancelled). - Tests: shared BlockingHandler fake, wait_until helper, and user-owned room fixture (reuses only marker-titled rooms it created, so room-scope stop/play can't 403); typed client for the mention helper; loop_scope=session on the control integration class; cover the claim->cycle-window signal paths. - Remove planning/manual-test scratch docs. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Resolve tests/conftest.py import conflict: keep `import asyncio` (used by BlockingHandler) and drop `import os` (main replaced os.environ reads with a pydantic-settings CollectionGateSettings). Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Collaborator
Author
|
@AlexanderZ-Band re: splitting the control-signal code out of |
AlexanderZ-Band
approved these changes
Jul 22, 2026
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
2 participants
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
agent_control:{agent_id}and handlesinterrupt/stop/playpreemptively, out-of-band from the message queue, so a signal can abort a reasoning cycle already in flight (ExecutionContext/AgentRuntime).interruptaborts the in-flight cycle and consumes the message (nothing sent, no replay).stopdoes the same plus durably suppresses new cycles in that room untilplay, which triggers a rehydration-style/nextcatch-up.band-bridge) honors the same signals for one-shot/bridged agents:interrupt/stopcancel whatever forward call is currently in flight for a room;playproactively nudges the room via/nextinstead of waiting for the next natural event.ReconnectedEventsync path now short-circuits locally on_stopped, consistent with the other stopped-guards, instead of making a/nextcall already known to return empty.Test plan
uv run pytest tests/ --ignore=tests/integration/ --ignore=tests/e2e/— full unit suite greenuv run pytest tests/runtime/ tests/platform/ tests/websocket/ tests/bridge/ tests/test_platform_runtime.py— control-signal suites green (851 passed)uv run ruff check ./uv run ruff format --check ./uv run pyrefly check— cleantests/integration/test_control_signals.py) — require a live platform +BAND_API_KEY/BAND_API_KEY_USER; not run in CI🤖 Generated with Claude Code