Access and Consequential Actions

Integration access is the intersection of several decisions. A connected credential alone does not grant every agent every provider tool.

Authorization Checks

Immediately before a run starts, Oblive rechecks:

• organization identity;
• enabled profile;
• explicit profile grant;
• active catalog entry;
• integration status;
• credential readiness;
• selected tools or services; and
• the current authorization epoch.

The resulting capability is scoped to one execution. Disabling an integration, changing credentials, or narrowing access invalidates reusable authorization state.

Read-only Mode

Read-only MCP access requires an explicit provider read-only annotation. CLI reads must be deterministically classified as reads. Unclear operations fail closed.

Full Access

Full access makes selected consequential tools eligible; it does not bypass the action lifecycle. Chat writes remain blocked. Task writes include an idempotency key and plain-language effect summary.

Action Lifecycle

1. The task proposes a typed action.
2. Oblive snapshots policy, authorization, task version, and intent.
3. The action executes immediately or waits for approval according to policy.
4. A fenced execution lease prevents competing executors.
5. The provider is called at most once.
6. A confirmed result stores a receipt.
7. An uncertain transport outcome moves to reconciliation.

Never retry an uncertain effect merely because the client did not receive a response.

Daily Review Threshold

The organization’s daily action limit is a visibility threshold in its configured timezone, not a kill switch. Reaching it opens one non-blocking notification for that local day while actions continue through their normal approval and execution policy. Task-level action budgets remain hard limits. Review recent actions before raising the threshold.