Follow-up implementation issue for the design plan tracked in #668 and added in PR #669.\n\nScope:\n- Add first-class audio and video context config models following the existing image-context pattern.\n- Keep context values limited to URL or base64 source data.\n- Preserve existing image-context behavior and backward compatibility.\n- Add provider adapter translation for supported media blocks.\n- Raise canonical unsupported-capability errors for providers or routes that cannot consume audio/video context.\n- Add focused config, engine, adapter, and regression tests described in the plan.\n\nOut of scope:\n- Audio or video generation columns.\n- Local path handling for new audio/video contexts.\n- Provider file upload lifecycle, file IDs, or config-layer filenames.\n- Automatic video frame extraction.\n\nReferences:\n- Planning issue: #668\n- Planning PR: #669
Follow-up implementation issue for the design plan tracked in #668 and added in PR #669.\n\nScope:\n- Add first-class audio and video context config models following the existing image-context pattern.\n- Keep context values limited to URL or base64 source data.\n- Preserve existing image-context behavior and backward compatibility.\n- Add provider adapter translation for supported media blocks.\n- Raise canonical unsupported-capability errors for providers or routes that cannot consume audio/video context.\n- Add focused config, engine, adapter, and regression tests described in the plan.\n\nOut of scope:\n- Audio or video generation columns.\n- Local path handling for new audio/video contexts.\n- Provider file upload lifecycle, file IDs, or config-layer filenames.\n- Automatic video frame extraction.\n\nReferences:\n- Planning issue: #668\n- Planning PR: #669