Per-OS policyHelpers entries can now set retries to control retry attempts after a failed run
A new retries setting on per-OS policyHelpers.<os> entries controls how many additional times a failing policy helper (a script that computes managed settings at startup) is retried before it's counted as a failure. A run counts as failed if the helper couldn't launch, exited with a non-zero code, or timed out. Retries use randomized backoff starting at 250ms and doubling up to 4 seconds between attempts.
This gives administrators a way to tolerate transient failures, like a flaky network call inside the helper script, without immediately treating the whole policy helper as failed.
The entry above is what we published on the day. These lines were added later, as Anthropic's own pages caught up, and they sit beside the original rather than replacing it.
* When the upstream rejects a [thinking signature](https://platform.claude.com/docs/en/build-with-claude/extended-thinking), including with a `400` whose message says the block is `bound to a different conversation`, Claude Code removes ea…llm-gateway-protocol see the edit
The model is currently overloaded. Emitted after automatic retries are exhausted.api/beta/sessions/events/list see the edit
Anthropic's documentation has since written up retries, on List Events.