Agent tool calls stall silently with no worker polling, warns deployment thread
krishnan · x · 2026-11-16
In the final posts of a deployment-architecture thread, krishnan highlights two points:
- Silent stall trap: per the docs, if no worker is polling, a session's first tool call simply waits with no error — a job can stall quietly, so someone must actively watch for it.
- Deployment advice: not every team needs the whole stack self-hosted. If only the tools must run inside the network, self-hosted sandboxes can keep Anthropic running the service. Before calling a deployment private, map every place its data travels and name who recovers each failure.
More from coding & agent
- Gemini 4 Hydrogen launched: 2.5x faster than 3.8 Flash, but how much is batching? — krishnan · 2026-11-16
- Running 13 agents in parallel: handhold the critical bits, let the rest rip all day — willcb · 2026-11-16
- Agent sessions stall silently when no worker polls—ops must watch for it — krishnan · 2026-11-16
- Self-hosted Managed Agents migrates nothing—not even session history—and drops webhooks and cron — krishnan · 2026-11-16
- Self-hosting agents buys control but you own the server, database, sandboxes and every release — krishnan · 2026-11-16
- Researchers formally specify ops interfaces for CockroachDB, Kafka and RabbitMQ to make AI operators verifiable — tianyin_xu · 2026-11-16