Skip to content

Add MiniMax v2 text-to-video generation - #296

Open
octo-patch wants to merge 1 commit into
Devin-AXIS:mainfrom
octo-patch:octo/20260812-text-to-video-tool-recvrqwr928tZh
Open

Add MiniMax v2 text-to-video generation#296
octo-patch wants to merge 1 commit into
Devin-AXIS:mainfrom
octo-patch:octo/20260812-text-to-video-tool-recvrqwr928tZh

Conversation

@octo-patch

Copy link
Copy Markdown
Contributor

Reason: iPolloWork's Media Center does not support MiniMax v2 text-to-video tasks or task queries.

This change:

  • registers the MiniMax-H3 model and global and China v2 endpoints;
  • creates prompt-only video tasks with validated duration, resolution, ratio, and callback fields;
  • queries regional tasks and normalizes both create and query task identifiers;
  • keeps the API key server-side and adds focused request, parsing, and validation coverage.

Checks:

  • bun test ./apps/server/src/extensions/media-center.test.ts
  • pnpm --filter ipollowork-server typecheck
  • node .codex/skills/ipollowork-maintainable-code/scripts/audit-changes.mjs
  • git diff --check

No runtime recording was captured because this is a server-side integration and no live provider credentials were used; the focused tests exercise the outbound payloads and task responses.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant