Add Patrol assessment Assistant handoff

docs/release-control/v6/internal/subsystems/api-contracts.md

@@ -431,6 +431,11 @@ the canonical monitored-system blocked payload.
    and the shared dashboard-load bundle inside `frontend-modern/src/stores/aiIntelligence.ts`, so the page orchestration stays on the store-owned bundle instead of enumerating the AI fetches inline
    and the shared `frontend-modern/src/components/Infrastructure/ResourcePolicySummary.tsx` card, so the AI summary page renders the governed policy-posture counts while the resource drawer stays on per-resource policy lines instead of carrying duplicate posture UI loops
    and the dedicated `frontend-modern/src/features/patrol/patrolInvestigationContextModel.ts` owner, so recent-change, learned-correlation, and policy-coverage summary text stays derived from the canonical AI payload in one place instead of as hook-local count and pluralization logic
+   and that same Patrol investigation-context owner, so the current Patrol
+   assessment summary may open Assistant with bounded model-only assessment,
+   verification, latest-run, supporting-context, active-finding, and resource
+   reference context instead of pasting page-local UI text or raw command
+   payloads into chat
    and that same Patrol investigation-context owner, so visible Assistant
    drawer handoffs may include live pending-approval metadata only as safe
    operator context: approval ID, status, risk, requested/expiry timestamps,

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

@@ -809,7 +809,12 @@ frontend primitive boundary.
     investigation-record framing must derive that prompt copy through
     `frontend-modern/src/features/patrol/patrolInvestigationContextModel.ts`
     so shared drawer primitives stay shell-owned rather than becoming a
-    Patrol-specific prompt formatter. The drawer may render a generic
+    Patrol-specific prompt formatter. Patrol assessment-level handoffs must use
+    that same feature helper to attach bounded model-only assessment,
+    verification, latest-run, supporting-context, active-finding, and resource
+    reference context while forcing request-local approval-required mode, so the
+    shared drawer stays a generic shell rather than a Patrol summary prompt
+    builder. The drawer may render a generic
     context-briefing band from `frontend-modern/src/stores/aiChat.ts`, but
     feature-owned helpers must provide the source labels, attention reason,
     evidence summaries, operator-decision copy, action copy, and safety note.

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

@@ -188,6 +188,16 @@ Patrol-specific presentation helpers.
    structured `investigationRecord` as investigation data, even when the legacy
    investigation-detail endpoint has no separate session payload, so it must not
    render empty-state copy above a durable Patrol record.
+   The primary Patrol assessment summary may open Assistant as a whole-surface
+   review handoff, but that handoff must also flow through
+   `frontend-modern/src/features/patrol/patrolInvestigationContextModel.ts`.
+   The summary action may pass the current assessment title, health score,
+   verification recency, latest run, secondary investigation context, bounded
+   active-finding summaries, and structured resource references as model-only
+   context. It must force request-local approval-required mode, keep raw command
+   and approval payloads out of prompt and drawer copy, and frame Assistant as
+   explanation, prioritization, and safe next-step review rather than a generic
+   reactive chat box.
 
 ## Current State
 
@@ -235,6 +245,14 @@ render contract: the header chip, primary summary card, and status bar must
 all route through the shared `frontend-modern/src/utils/patrolRuntimePresentation.ts`
 helper plus the backend `runtime_state` payload instead of inferring operator
 state from the last healthy summary snapshot or run history alone.
+The primary summary card now also has a Patrol-owned Assistant assessment
+handoff. `frontend-modern/src/features/patrol/PatrolIntelligenceSummary.tsx`
+opens Assistant through
+`frontend-modern/src/features/patrol/patrolInvestigationContextModel.ts`, which
+packages the current Patrol assessment, verification posture, latest run,
+secondary investigation context, bounded active-finding summaries, and deduped
+resource references as model-only context while forcing `autonomousMode:false`
+and summarizing proposed-fix command-bearing records by count only.
 That active-runtime label must stay operational rather than verdict-like: the
 header chip should communicate that Patrol is enabled or available, not imply
 that infrastructure health is currently good merely because the runtime is on.