ext/new-api
2
0
Fork 0
mirror of https://github.com/QuantumNous/new-api.git synced 2026-09-10 22:20:25 +00:00
Code Activity

feat(plugin): add MiniMax-H3 /v2 video generation to the hailuo task … (#7168)

Browse Source 
* feat(plugin): add MiniMax-H3 /v2 video generation to the hailuo task plugin

MiniMax-H3 speaks a different contract from the other Hailuo models, so the
hailuo task plugin now branches on the upstream model instead of adding a Go
adaptor:

- submit builds /v2/video_generation with a multimodal `content` array
  (text, first/last frame images, reference video/audio, or a full
  `metadata.content` passthrough), an explicit `ratio`, and 768P/2K
  resolutions; `metadata.callback_url` and `metadata.aigc_watermark` pass
  through
- query uses /v2/query/video_generation/{task_id} and parses the
  `{"task": {...}}` envelope, falling back to the /v1 shapes for every other
  model
- the /v2 result is a public CDN URL, so its artifact is proxied
  credentialless instead of through /v1/files/download
- request bounds (duration 4-15, resolution 768P/2K, ratio whitelist, at most
  2 frame images and 9/3/3 reference images/videos/audios) are enforced while
  the request body is built, which the host runs during validation, so an
  out-of-range duration is rejected with a 400 before it can become a billing
  multiplier
- duration and resolution are reported as usage facts only. Like the rest of
  this plugin, extractUsage returns no billing ratios, so per-call pricing is
  flat and 2K/duration pricing is expressed through the model's tiered billing
  expression over those facts.

Query hooks are driver hooks and are documented to receive `ctx.model` and
`ctx.upstreamModel`, but polling has no relay info and never populated them.
The polling and realtime-fetch call sites now carry the persisted task model
properties and the plugin adaptor maps them onto the query context, with
`upstreamModel` falling back to the origin name for tasks submitted without a
channel mapping.

* fix(plugin): validate Hailuo H3 requests and errors
This commit is contained in:
星云猫
2026-09-03 11:04:48 +08:00
committed by GitHub
parent bbd97446c2
commit aece11d2f7
7 changed files with 738 additions and 16 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/plugin-api/v1.md
+1 -1
View File
@@ -139,4 +139,4 @@ Protocol media uses host-injected `ctx.artifacts[key].url`. Provider URLs from `
The persisted field remains `task.data`; there is no `task.raw` alias. Driver hooks (`buildSubmitRequest`, `parseSubmitResponse`, query/result, usage, artifact, and content hooks) stay flat and must not branch on the client path or protocol.
`ctx.model` is the billing and display identity (the origin name the client sent, including a channel-mapping alias). `ctx.upstreamModel` is the machine identity after channel `model_mapping`. Rate tables and model-keyed usage facts must use `ctx.upstreamModel || ctx.model`. Decode and render hooks that echo the client model must keep `ctx.model`. `buildSubmitRequest` must not set descriptor top-level `model` on a mapped pin; the host requires the plugin to echo the alias verbatim.
`ctx.model` is the billing and display identity (the origin name the client sent, including a channel-mapping alias). `ctx.upstreamModel` is the machine identity after channel `model_mapping`. Rate tables and model-keyed usage facts must use `ctx.upstreamModel || ctx.model`. Decode and render hooks that echo the client model must keep `ctx.model`. `buildSubmitRequest` must not set descriptor top-level `model` on a mapped pin; the host requires the plugin to echo the alias verbatim. Background polling has no relay info, so query hooks receive both identities from the persisted task properties, and `ctx.upstreamModel` falls back to `ctx.model` when the task was submitted without a channel mapping.