A durable agent can resume a consequential action while its authority changes and the action's external outcome remains uncertain. We study execution-time reliability of tool-using AI agents, isolating recovery decisions from language-model behavior. Checkpoint state, permission to dispatch, evidence of an external effect and permission to reconcile are distinct obligations. We present a finite conformance study that checks these obligations through histories scored against a provider effect ledger hidden from the recovering application. A prospectively frozen campaign executes 336 histories on native LangGraph and Temporal hosts, crossing 14 schedules, three provider contracts and four matched application policies. All 168 paired host cells have identical checked outcomes. Per host, retained-ledger reconciliation passes all 42 histories: 21 checked completions, 15 denials and six unknown outcomes with reservations retained. Cached retry, revalidation before retry and stable-key retry pass 30, 36 and 31 histories respectively. A separate 16-case component study of InfinityOS, an enterprise AI platform developed by Arya.ai, exercises exported authority, worker, recovery and settlement code over repository fakes. The results isolate the roles of current authority, provider contracts and retained observations in recovery, with safety, completion and unresolved obligations reported separately for the declared application profile.
Figures & tables
Host and authored policy
Passing histories
Reported successes
Checked completions
Denied
Unknown
LangGraph: Cached retry
30 / 42
27
15
15
0
LangGraph: Revalidate retry
36 / 42
21
15
15
6
LangGraph: Stable-key retry
31 / 42
27
16
15
0
LangGraph: Ledger reconciliation
42 / 42
21
21
15
6
Temporal: Cached retry
30 / 42
27
15
15
0
Temporal: Revalidate retry
36 / 42
21
15
15
6
Table I: Finite native conformance outcomes by authored policy
Figure 1: Finite policy outcomes. Each bar contains 42 histories. Checked completion, reported success with a violation, denial and unresolved work are separate.
Figure 2: Boundary coverage for the 168 LangGraph cells. C means checked completion, D denial, U unresolved reservation and F a conformance violation. P1 is deduplicating, P2 queryable and P3 opaque. All paired Temporal cells have the same checked outcomes.