{"version":"1.0.124","anchor":"server-controlled-extended-thinking-experimental","canonical_anchor":"server-controlled-extended-thinking-experimental","heading":"Server-Controlled Extended Thinking (Experimental)","tier":null,"area":null,"scope":null,"heads_up":null,"url":"https:\/\/changelogs.core-directive.com\/v\/1.0.124\/e\/server-controlled-extended-thinking-experimental","release_url":"https:\/\/changelogs.core-directive.com\/v\/1.0.124","markdown":"### Server-Controlled Extended Thinking (Experimental)\n\n**What:** Server-side feature flag system that enables automatic extended thinking token allocation for specific users without requiring manual triggers.\n\n**Details:**\n\n- New API endpoint `\/api\/oauth\/claude_cli\/client_data` fetches user-specific configuration\n- When `alwaysThinking` is enabled server-side, maximum thinking tokens are automatically allocated\n- Thinking blocks are intelligently hidden when auto-enabled unless user explicitly requested thinking\n- Does not affect manual thinking triggers or `MAX_THINKING_TOKENS` environment variable\n- **Evidence**: Client data API in `TWA()` at line 361888, token allocation in `pT()` at line 362093, hiding logic at line 415872"}