feat: revamp DeepSeek v4 model handling

- replace legacy DeepSeek ids with the new deepseek-v4 model family\n- move thinking control to request parameters and preserve assistant reasoning content\n- switch history split to IGNORE transcript injection and map upload auth failures to 401\n- update admin defaults, API docs, samples, and tests for the new model scheme

webui/src/features/settings/useSettingsForm.js

@@ -18,7 +18,7 @@ const DEFAULT_FORM = {
     embeddings: { provider: '' },
     auto_delete: { mode: 'none' },
     history_split: { enabled: true, trigger_after_turns: 1 },
-    claude_mapping_text: '{\n  "fast": "deepseek-chat",\n  "slow": "deepseek-reasoner"\n}',
+    claude_mapping_text: '{\n  "fast": "deepseek-v4-flash",\n  "slow": "deepseek-v4-pro"\n}',
     model_aliases_text: '{}',
 }