feat(cliproxy): add 'max' thinking level for Claude Opus 4.7

Anthropic exposes `max` as a distinct adaptive-thinking effort above
`xhigh` on Opus 4.7. Previously the validator aliased user input `max`
down to `xhigh`, so users couldn't reach the real top-tier effort
through CCS.

Extend the validator:
- Add `max` to VALID_THINKING_LEVELS and THINKING_LEVEL_RANK (rank 6,
  above xhigh)
- Add `max` to THINKING_LEVEL_BUDGETS (65536, CCS-internal numeric
  mapping for closest-level lookups)
- Widen ThinkingSupport.maxLevel union to include 'max'

The existing `max: 'xhigh'` alias in findClosestLevel is kept as a
graceful fallback for models whose levels list does not include `max`
(e.g. Codex `gpt-5.4`), because exact-match on validLevels takes
priority — so Opus 4.7 returns `max` directly while Codex still maps
`max` -> `xhigh`.

Update the claude.claude-opus-4-7 catalog entry to expose
`['low', 'medium', 'high', 'xhigh', 'max']` with `maxLevel: 'max'`.

Built [OnSteroids](https://onsteroids.ai)

Co-Authored-By: OnSteroids <built@onsteroids.ai>

src/cliproxy/model-catalog.ts

@@ -33,7 +33,7 @@ export interface ThinkingSupport {
   /** Valid level names (for levels type) */
   levels?: string[];
   /** Maximum reasoning effort level (caps effort at this level for levels type) */
-  maxLevel?: 'minimal' | 'low' | 'medium' | 'high' | 'xhigh';
+  maxLevel?: 'minimal' | 'low' | 'medium' | 'high' | 'xhigh' | 'max';
   /** Whether zero/disabled thinking is allowed */
   zeroAllowed?: boolean;
   /** Whether dynamic/auto thinking is allowed */
@@ -298,10 +298,11 @@ export const MODEL_CATALOG: Partial<Record<CLIProxyProvider, ProviderCatalog>> =
         // Opus 4.7 only supports adaptive thinking on the Anthropic API; manual
         // thinking.type: "enabled" with budget_tokens is rejected with 400.
         // Expose effort levels; the proxy translates these into adaptive effort.
+        // `max` is a distinct adaptive effort above `xhigh` exposed by Anthropic.
         thinking: {
           type: 'levels',
-          levels: ['low', 'medium', 'high', 'xhigh'],
-          maxLevel: 'xhigh',
+          levels: ['low', 'medium', 'high', 'xhigh', 'max'],
+          maxLevel: 'max',
           dynamicAllowed: true,
         },
         extendedContext: true,