feat(deepseek): use responses api for v4 flash - #3926

Action items

• [medium] [possible mistake] providers/opencode/models/deepseek-v4-flash.toml:16 - Check: provider.shape must describe the inference surface of that catalog provider, not only the upstream model. Why: These OpenCode Zen/Go entries set shape = "responses" and cite only DeepSeek’s native Responses guide. That does not establish Zen/Go routing. providers/opencode/provider.toml documents /zen/v1/responses for OpenAI and /zen/v1/chat/completions for compatible models; these DeepSeek rows still use the provider default @ai-sdk/openai-compatible (no npm override), unlike OpenCode GPT rows that select the OpenAI surface with npm = "@ai-sdk/openai". Applying Responses here can mis-route clients once shape is consumed. Action: Verify OpenCode Zen, Zen Free, and Go actually expose deepseek-v4-flash on a Responses endpoint; cite that OpenCode surface (and align npm/endpoint notes if needed). If they still use chat-completions, drop shape = "responses" from the three OpenCode catalog files and keep it only on direct DeepSeek if that native claim holds.

Closing this pull request as stale because it has not been updated in 30 days. Feel free to reopen it or submit a new pull request if the work is resumed.