feat(api): expose cache metrics in REPL + normalize across providers (#813)

* feat(api): expose cache metrics in REPL + /cache-stats command

* fix(api): normalize Kimi/DeepSeek/Gemini cache fields through shim layer

* test(api): cover /cache-stats rendering + fix CacheMetrics docstring drift

* fix(api): always reset cache turn counter + include date in /cache-stats rows

* refactor(api): unify shim usage builder + add cost-tracker wiring test

* fix(api): classify private-IP/self-hosted OpenAI endpoints as N/A instead of cold

* fix(api): require colon guard on IPv6 ULA prefix to avoid public-host over-match

* perf(api): ring buffer for cache history + hit rate clamp + .localhost TLD

* fix(api): null guards on formatters + document Codex Responses API shape

* fix(api): defensive start-of-turn reset + config gate fallback + env var docs

* fix(api): trust forwarded cache data on self-hosted URLs (data-driven)

* refactor(api): delegate streaming Responses usage to shared makeUsage helper

src/tools/ConfigTool/supportedSettings.ts

@@ -1,5 +1,8 @@
 import { feature } from 'bun:bundle'
-import { getRemoteControlAtStartup } from '../../utils/config.js'
+import {
+  getRemoteControlAtStartup,
+  SHOW_CACHE_STATS_MODES,
+} from '../../utils/config.js'
 import {
   EDITOR_MODES,
   NOTIFICATION_CHANNELS,
@@ -77,6 +80,13 @@ export const SUPPORTED_SETTINGS: Record<string, SettingConfig> = {
     description:
       'Show turn duration message after responses (e.g., "Cooked for 1m 6s")',
   },
+  showCacheStats: {
+    source: 'global',
+    type: 'string',
+    description:
+      'Show per-query cache hit/miss summary at end of turn (off | compact | full)',
+    options: SHOW_CACHE_STATS_MODES,
+  },
   terminalProgressBarEnabled: {
     source: 'global',
     type: 'boolean',