Byte length detected by the file adapter.
Number of UTF-16 code units detected in the decoded text body.
This lets chunk readers validate character ranges without reopening the raw file.
Number of text lines detected during file intake.
Raw text bodies must live in sidecar/durable artifacts, not in user message metadata.
Compact handoff memo for later agents.
Explain what the content item appears to contribute, which downstream phase should care, and what must not be inferred yet. For example, an ERD can be structural, a meeting transcript can be requirement-oriented, and one item can be both when annotations contain business rules beside structure.
Metadata branch discriminator.
Downstream semantic roles for this content item.
Empty means the content item should not feed a phase directly. Supporting evidence, metadata-only value, policy limitations, intake gaps, or unsupported content should be explained in memo instead of adding a separate enum here.
Text-like metadata for a file upload.
This branch is for plain text, markdown, logs, SQL, JSON, or similar text-readable files after deterministic file intake. It is not used for direct chat text content.