Coding-agent bypass: modality sweep (prose, structured data formats, and exotic containers)

Holds the coding-assistant persona, the eval-fixture pretext, and the target content (romantic-love reciprocation) completely constant across 13 prompts, varying only the requested output format/container — plain prose, seven multi-field structured-data formats (YAML/JSON/Python/CSV/SQL/Markdown/XML), and five exotic containers (base64, ROT13, French, a single-field .env assignment, a multi-field log line) that isolate whether the boundary is about raw structuredness or specifically multi-field schema mimicry. Reveals whether a model's coding-agent-bypass vulnerability is format-specific (a narrow, addressable coverage gap) or persona/pretext-gated and format-independent (a broader gap that format-level fixes won't touch). Companion piece to coding-agent-safety-bypass.yml — see that file's header for the underlying mechanism.