メニュー
Simulating a crash on an agent for testing crash recovery. Use when testing durable execution, verifying state recovery after failures, or validating that an agent correctly resumes from its operation log.
デフォルトでは、最初にソースを確認する Prompt が選択されています。直接コマンドに切り替えるか、ローカルコピーをダウンロードすることもできます。
インストールを決める前に、SKILL.md と SkillsMP に表示されている付属ファイルをお読みください。
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
直接コマンドでは確認用 Prompt が省略されます。実行前にソースを確認してください。
npx skills add https://github.com/golemcloud/golem --skill golem-test-crash-recoveryコマンドは1行のまま表示されます。コピー前に横へスクロールして全体を確認してください。
ローカルで確認しますか？SkillsMP が現在取得できるファイルをダウンロードできます。
Investigating benchmark performance by running Golem benchmarks with OTLP tracing enabled and analyzing trace data from Jaeger. Use when diagnosing slow benchmarks, understanding benchmark call flows, or profiling span durations during benchmark runs.
Investigating worker-executor performance by running executor tests with OTLP tracing enabled and analyzing trace data from Jaeger. Use when diagnosing slow tests, understanding executor call flows, or profiling span durations.
Setting up a Golem Cloud account from scratch. Use when creating a Golem Cloud account, authenticating with Golem Cloud via the CLI, setting up a cloud profile, or deploying to Golem Cloud for the first time.
SOC 職業分類に基づく
SKILL.md を表示中
| name | golem-test-crash-recovery |
| description | Simulating a crash on an agent for testing crash recovery. Use when testing durable execution, verifying state recovery after failures, or validating that an agent correctly resumes from its operation log. |
Both golem and golem-cli can be used — all commands below work with either binary.
The <AGENT_ID> format depends on the agent's language — refer to the language-specific invocation skills for the exact syntax.
agent simulate-crash — Simulate a CrashSimulates a crash on an agent for testing purposes. The agent starts recovering and resuming immediately by replaying its operation log.
This is useful for verifying that an agent's durable state is correctly persisted and that it can recover from unexpected failures without data loss.
golem agent simulate-crash <AGENT_ID>
Replay is slow? Don't try to skip oplog writes. Durable agents always write to the oplog by design — there is no way to opt out of persistence for a durable agent. If recovery is slow because the oplog has grown large (long-running agents, frequent state changes, heartbeats, polling loops, recurring tasks), the correct fix is snapshot-based recovery: enable periodic snapshotting so recovery starts from the latest snapshot instead of replaying the full history. See the language-specific
golem-custom-snapshot-*skill.
Simulate a crash on an agent:
golem agent simulate-crash <AGENT_ID>
Typical test workflow — invoke a method, simulate a crash, then verify state is preserved:
golem agent invoke <AGENT_ID> <METHOD> [ARGS]
golem agent simulate-crash <AGENT_ID>
golem agent invoke <AGENT_ID> <GETTER_METHOD>