Recover recorded State alongside your workflow
Resume your AgentCore workload and recheck the recorded State it needs.
Guide context
Read recorded State again when an AgentCore application resumes work. Runtime continuation and Kam's durable reconciliation have separate owners.
When an AgentCore application resumes work, read the State it needs again and recheck whether it applies. Kam retains accepted revisions and its own reconciliation progress. Runtime continuation, tool retries and the decision to act stay with the runtime and application.
On this page · 3 sections
Rejoin execution with recorded State
Resume the workload
Your AgentCore runtime and application own continuation and tool attempts.
Read and revalidate State
Kam retains admitted versions and recovers its own reconciliation progress.
Stop on uncertainty
Your application must verify unknown external effects and current permissions before deciding whether to retry.
Two timelines should remain independent#
Your AgentCore application owns how execution resumes. Kam preserves accepted State and advances supported reconciliation as recorded evidence changes. On the next turn, the application must read again and check whether a previous Observation still applies.
Keep workflow continuation in the runtime and application. Kam supplies exact State references and its own recorded processing progress; neither proves that an external tool action completed.
Use exact references for checkpoints#
The planned operational checkpoint is a durable coordinate across exact Snapshot or generation, View, Active State, Observation, source fences and computational versions. Immutable referenced objects can be structurally shared across many checkpoints.
Exact references make retained versions inspectable without copying every payload. Replay does not rerun tools, prove outside actions or remove retention limits.
Durable reconciliation preserves processing progress#
Affected-View discovery persists bounded progress and can redrive lost wakeups. Conditional commits recheck lifecycle, membership and source-State versions so delayed work cannot overwrite newer authority.
The future Turn layer should carry the same discipline into model submission and effects: explicit UNKNOWN outcomes, idempotent stage receipts, and revalidation instead of blind retries.