feat(ai): Phase 1 step 3-6 — LLM adapter + per-field AI suggest endpoint + UI

Approach C upgrade на templates foundation (!233). Admin может попросить AI
предложить новое поле — system prompt force'ит structural JSON Schema
fragment, admin review через accept/edit/reject. Bitemporal draft workflow
unchanged downstream.

## Backend
- `LlmAdapter` — OpenAI-compatible /v1/chat/completions client (Ollama,
  vLLM, OpenAI). Bean conditional на ordinis.ai.enabled=true.
- `AiSchemaService` — system prompt + 3 few-shot examples, JSON output
  parsing (с markdown fence stripping), validation (fieldName snake_case).
  In-memory circuit breaker: 10 fails в 60s → open 5 min.
- `AiSchemaController`:
  - GET /api/v1/ai/info → 200 (enabled) / 404 (disabled). Frontend probe.
  - POST /api/v1/ai/suggest-field → suggestion. Per-IP rate limit 30/min.
- All bean-conditional: ordinis.ai.enabled=false → controllers нет →
  endpoints 404 → frontend hides AI buttons automatically.

## Frontend
- `useAiFeatureAvailable` query — probes /ai/info, cache 5 min
- `useAiSuggestField` mutation — 30s timeout (LLM может быть slow)
- `AiFieldSuggestPanel` component — inline expandable: prompt → preview →
  accept/retry/reject. Error handling per HTTP status (503/429/422/502/404).
- DictionaryEditorDialog: AI toggle visible на schema tab когда
  aiAvailable=true. Accept wraps suggestion в mini-schema → parseSchemaJson
  (reuse existing kind-inference) → push в properties (overwrite если
  duplicate fieldName).
- i18n RU + EN

## Config
- application.yml: ordinis.ai.{enabled,endpoint,model,bearer-token,
  timeout-seconds}
- Helm writer.yaml: ORDINIS_AI_* env vars, optional secretRef для bearer
- values.yaml: ai.{enabled,endpoint,model,timeoutSeconds,bearerTokenSecretRef}
  defaults disabled

Pair с infra MR — values-staging enables AI с vortex.nstart.cloud Ollama
serving qwen2.5:7b.

ordinis-admin-ui/src/api/mutations.ts

@@ -2,6 +2,7 @@ import { useCallback, useRef } from 'react'
 import { useMutation, useQueryClient } from '@tanstack/react-query'
 import {
   apiClient,
+  type AiFieldSuggestion,
   type BulkCloseRequest,
   type BulkCloseResponse,
   type CascadeCloseResult,
@@ -741,3 +742,28 @@ export const useUpdateNotificationPreferences = () => {
     },
   })
 }
+
+/**
+ * AI Schema Assist — per-field suggest. Returns parsed {fieldName, schema}.
+ * Каллер показывает diff preview, user accept/edit/reject.
+ *
+ * 404 → AI disabled на бэкенде — frontend hides button (handled в caller).
+ * 503/circuit_open → temporary unavailable, show banner.
+ * 422 → bad output from LLM — show error message, suggest retry.
+ * 429 → rate limit, show "try again in a minute".
+ */
+export const useAiSuggestField = () => {
+  return useMutation({
+    mutationFn: async (req: {
+      existingSchema: unknown
+      prompt: string
+    }): Promise<AiFieldSuggestion> => {
+      const { data } = await apiClient.post<AiFieldSuggestion>(
+        '/ai/suggest-field',
+        req,
+        { timeout: 30_000 }, // override default 10s — LLM может быть slow
+      )
+      return data
+    },
+  })
+}