77cbcd8774
* fix: align DeepSeek provider with V4 API * Fix DeepSeek beta routing for standard chat completions * feat: add DeepSeek V4 model support with thinking mode and reasoning effort * Address DeepSeek review feedback * Set DeepSeek default model to v4 flash * fix: clean-up deprecated models, add migration * fix: move reasoning effort mapping to resolveReasoningEffort * fix: lint empty line * fix: remove duplicate code * fix: add coder model to migration logic --------- Co-authored-by: dclef <drclef233@gmail.com> Co-authored-by: Cohee <18619528+Cohee1207@users.noreply.github.com>