1 commit

Author	SHA1	Message	Date
teknium1	fa3338c171	test(anthropic): regression guard for DeepSeek /anthropic thinking replay ... Covers the #16748 fix: - unsigned thinking blocks synthesised from reasoning_content survive replay - non-latest assistant turns keep their thinking (DeepSeek validates every turn) - signed Anthropic blocks are stripped (DeepSeek can't validate them) - cache_control is stripped from thinking blocks - OpenAI-compat base (api.deepseek.com without /anthropic) is NOT matched - non-DeepSeek third parties (minimax) keep the generic strip-all behaviour	2026-04-29 08:10:29 -07:00