01d6002d41
Photos now use [IMAGE:/path] format instead of [Photo] /path, so the existing multimodal pipeline validates vision capability and rejects unsupported providers (Groq, OpenAI-compatible) with a user-facing error before calling the LLM. Tests added (all offline, no API keys required): - attachment_photo_content_uses_image_marker - attachment_document_content_uses_document_label - photo_image_marker_detected_by_multimodal - photo_image_marker_with_caption - e2e_attachment_saves_file_and_formats_content - groq_provider_rejects_photo_with_vision_error - e2e_photo_attachment_rejected_by_non_vision_provider Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> |
||
|---|---|---|
| .. | ||
| fixtures | ||
| agent_e2e.rs | ||
| agent_loop_robustness.rs | ||
| channel_routing.rs | ||
| config_persistence.rs | ||
| dockerignore_test.rs | ||
| memory_comparison.rs | ||
| memory_restart.rs | ||
| otel_dependency_feature_regression.rs | ||
| provider_resolution.rs | ||
| provider_schema.rs | ||
| reply_target_field_regression.rs | ||
| telegram_attachment_fallback.rs | ||
| whatsapp_webhook_security.rs | ||