Platform

The policy engine

One function decides whether a tool call proceeds: evaluate(). It is fast, deterministic, explainable, and it defaults to deny.

Decisions

ALLOW

A matching policy permits the call.

DENY

The call is refused. This is the default when nothing matches a risky tool.

AUDIT

The call is permitted but recorded for review.

NO_POLICY

No policy governs this tool at this tier.

What the engine looks at

SignalSourceEffect
Tool known?Tool catalogueUnknown tools are denied outright.
Risk levelTool catalogueHIGH and CRITICAL tools are denied with no policy present.
Data tierRequest contextPUBLIC < INTERNAL < CONFIDENTIAL < RESTRICTED. A tool may be barred from a higher tier.
Matching policyPolicy storeConditions on agent, tool, targets and time windows.
ApprovalTool catalogueSome tools require an approval before the call proceeds.
Rate and frequencyEngine countersWindowed limits on call frequency and volume.
Hot reload Policies reload without a restart through /api/policies/hot, so an operator can tighten a rule in response to something they have just seen.
Extensions cannot change a verdict The extension point hands observers a deep copy of the request and the decision. An extension that throws is recorded, never propagated. This is deliberate: an extension that could flip a decision would be a policy bypass, so the contract test asserts it cannot.