Fulfill a pending WeChat visual request through Codex's built-in ImageGen entitlement without an OpenAI API key or separate image API integration. Use when Kimi or another text agent has written a valid visual-request.json into the current WeChat Workdir v1 run and Codex must generate conceptual raster backgrounds, add deterministic Chinese typography, inspect candidates, and return hashed local assets and a visual-result.json; do not use outside Codex, for evidence fabrication, or as a synchronous API/MCP promise.
