feat(policy): enforce truthfulness and autonomy guardrails

Add runtime truthfulness modes and autonomy-level tool gating with audit metadata for overrides/denials.

Wire policy through prompt assembly, tool execution context, and daemon/gateway agent paths; update tests and planning state for Phase 3 PR #2 completion.

src/tools/policy.ts

@@ -1,4 +1,4 @@
-import type { ToolsConfig, ToolProfile } from '../config/schema.js';
+import type { AutonomyLevel, ToolsConfig, ToolProfile } from '../config/schema.js';
 import type { Tool } from './types.js';
 
 // ── Profile definitions ─────────────────────────────────────────────
@@ -140,6 +140,8 @@ export interface ToolPolicyContext {
   sender?: string;
   /** Model tier for audit logging. */
   tier?: string;
+  /** Autonomy level for tool execution (affects confirmation requirements). */
+  autonomyLevel?: AutonomyLevel;
 }
 
 // ── ToolPolicy engine ───────────────────────────────────────────────