Skip to content

feat: Scaffold video preprocessing configuration #22

@rdwj

Description

@rdwj

Summary

Include video processing configuration in scaffolded projects. Video-capable agents need a preprocessing sidecar that extracts frames and metadata before passing content to a vision model.

Requirements

  • Add video section to scaffolded agent.yaml with preprocessor_endpoint, frame_extraction_strategy (uniform, keyframe, scene-change), and max_duration_seconds.
  • Include VideoPreprocessor sidecar container definition in the Helm chart when video is enabled.
  • Gate video config behind the fips-agents create interactive prompt (only scaffold when requested).
  • Add a YAML comment noting the vision model dependency (video requires vision to be enabled).

Companion Issues

Companion issues filed on fips-agents/agent-template, fips-agents/gateway-template, fips-agents/ui-template, and fips-agents/examples.

Size

S

Metadata

Metadata

Assignees

No one assigned

    Labels

    enhancementNew feature or request

    Type

    No type

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions