YouTube URLs are one supported source-ingestion path. Harmonia resolves source metadata and media only after the operator attests that the material is authorized for processing.
How Harmonia uses it
The ingest stage validates the URL, records source rights, resolves public metadata through YouTube/oEmbed, and obtains media for the worker’s transcription and analysis pipeline. Timed transcript segments and authorized video evidence become the closed-world source package supplied to Nimi.
Google OAuth configuration is available where an authorized source requires it. Public URLs do not grant reuse rights by themselves; the job retains the operator’s rights declaration and source provenance.
Security and authority
Source ingestion cannot authorize publication. Models receive only the bounded source package and may not claim facts outside its transcript/frame evidence. Credentials and download details remain server-side.
Failure behavior
Invalid URLs, unavailable or private media, unsupported formats, rights failures, metadata mismatch, and download/transcription errors remain visible. Harmonia does not substitute fake transcripts.
Evidence status
URL validation, rights records, local fixtures, and stage contracts have automated coverage. A real end-to-end source claim requires the captured authorized URL, resolved metadata, transcript, and source digest.
Relevant files
agent/harmonia_agent/youtube.pyagent/harmonia_agent/content.pyagent/harmonia_agent/stages.pysrc/lib/sourceRights.tsdocs/evidence-runbook.mdx
Last modified on August 28, 2026
