safety security
A Retry Is a New Authority Decision
A recovery study separates permission to dispatch, evidence of an external effect and permission to reconcile instead of treating checkpoints as consent.
Summary
A recovery study separates permission to dispatch, evidence of an external effect and permission to reconcile instead of treating checkpoints as consent.
Durable workflows can resume after permissions change while an earlier external action remains uncertain. This conformance study models checkpoint state, authority to dispatch, provider-side effect evidence and authority to reconcile as separate obligations. It runs 336 histories across LangGraph and Temporal hosts, three provider contracts and four application policies; paired host cells produced identical checked outcomes. Retained-ledger reconciliation passed all 42 histories per host, including unresolved outcomes whose reservations remained open. The result concerns the declared finite histories, fake providers and policy profiles. It does not prove that every production retry system is safe, but it makes a consequential design rule explicit: saved state is not renewed permission.
Why it matters
A recovery study separates permission to dispatch, evidence of an external effect and permission to reconcile instead of treating checkpoints as consent.
Limits and context
- It does not prove that every production retry system is safe, but it makes a consequential design rule explicit: saved state is not renewed permission.
Key claims
A recovery study separates permission to dispatch, evidence of an external effect and permission to reconcile instead of treating checkpoints as consent.
Qualification: It does not prove that every production retry system is safe, but it makes a consequential design rule explicit: saved state is not renewed permission.
Evidence: source-2026-10-26-005
Sources
- arXiv preprint 2610.31916, original v1arXiv · primary research
Corrections
No corrections have been recorded for this story.