Route Patrol approval handoffs through structured context

docs/release-control/v6/internal/subsystems/ai-runtime.md

@@ -309,7 +309,13 @@ runtime cost control, and shared AI transport surfaces.
     while preserving the safe visible briefing and request-local
     approval-required posture; later turns must rely on backend-owned session
     model-context hydration and current canonical stores instead of resending
-    stale browser handoff payloads.
+    stale browser handoff payloads. Patrol approval-row Assistant entries are
+    still Patrol finding handoffs, not local prompt-only shortcuts: live
+    approval rows, expired proposed-fix rows, and missing-detail queued-fix
+    recovery rows must route through the shared Patrol finding handoff builder
+    so the backend receives the same bounded model-only finding context,
+    resource reference, and safe action reference posture that the main finding
+    handoff uses.
     Proposed-fix command text must stay out of both the persisted chat message
     and the model-only handoff context, and command payloads remain
     approval-context data, not conversational copy.

docs/release-control/v6/internal/subsystems/frontend-primitives.md

@@ -877,18 +877,20 @@ frontend primitive boundary.
     structured finding context, so
     Patrol handoffs render as Patrol handoffs or Patrol findings, and alert
     handoffs render as alert investigations, rather than generic dashboard
-    briefs. Patrol approval-row Assistant prompts must
-    follow that same drawer primitive contract: safe approval metadata may enter
-    the prompt and context, but raw command text stays out and the scoped
-    request must pass `autonomousMode:false` instead of changing the user's
-    persistent Assistant control level. Patrol remediation-plan drawer handoffs
-    must use the same primitive boundary: plan title/status/risk, step labels,
-    and command counts may enter Assistant context; raw command and rollback
-    command payloads must stay in the governed remediation/action panel. Finding
-    discussion handoffs that reference a live approval, proposed fix, fix
-    outcome, or remediation plan must also pass `autonomousMode:false` as a
-    request-local override so the drawer shows approval-required posture without
-    mutating the persistent Assistant control setting.
+    briefs. Patrol approval-row Assistant prompts must route through the same
+    feature-owned finding handoff helper rather than hand-written prompt-only
+    drawer opens: safe approval metadata, proposed-fix summaries, resource
+    references, and bounded `handoff_actions` may enter the prompt and context,
+    but raw command text stays out and the scoped request must pass
+    `autonomousMode:false` instead of changing the user's persistent Assistant
+    control level. Patrol remediation-plan drawer handoffs must use the same
+    primitive boundary: plan title/status/risk, step labels, and command counts
+    may enter Assistant context; raw command and rollback command payloads must
+    stay in the governed remediation/action panel. Finding discussion handoffs
+    that reference a live approval, proposed fix, fix outcome, or remediation
+    plan must also pass `autonomousMode:false` as a request-local override so
+    the drawer shows approval-required posture without mutating the persistent
+    Assistant control setting.
 11. Keep shared filter primitives coherent with route-owned option hydration.
     Feature shells such as `frontend-modern/src/features/infrastructure/`
     must keep a route-owned canonical option visible in shared selects like

docs/release-control/v6/internal/subsystems/patrol-intelligence.md

@@ -171,13 +171,16 @@ Patrol-specific presentation helpers.
    sync. The model-only context may include current finding status, recurrence,
    investigation record facts, evidence, verification, approval posture,
    dry-run posture, proposed-fix summary, and target resource references without
-   raw command payloads. Inline
-   Patrol approval actions that open Assistant must follow the
-   same rule: pass approval ID/status/risk/target plus safe summary/count
-   metadata as review context, force the request-local approval-required mode,
-   attach the Patrol-owned visible drawer briefing for the pending approval, and
-   never paste the approval command or proposed-fix command text into the chat
-   prompt. Remediation-plan Assistant
+   raw command payloads. Inline Patrol approval actions in
+   `frontend-modern/src/components/patrol/ApprovalSection.tsx` that open
+   Assistant must follow that same Patrol-owned handoff model rather than a
+   prompt-only local shortcut: pass approval ID/status/risk/target plus safe
+   summary/count metadata as review context, attach the target resource
+   reference, include bounded `handoff_actions` for live approvals or structured
+   proposed fixes when present, force the request-local approval-required mode,
+   attach the Patrol-owned visible drawer briefing for the pending approval or
+   queued-fix recovery state, and never paste the approval command or
+   proposed-fix command text into the chat prompt. Remediation-plan Assistant
    handoffs follow the same boundary: step labels, plan status, risk, and command
    counts are allowed, safe suggested prompts may ask about plan risk,
    prerequisites, rollback, and verification, while command and rollback command