Commit Graph

4 Commits

Author SHA1 Message Date
28e26f4295 Merge origin/master (v0.5.75) into gitea/new_feature
Resolve conflicts:
- package.json / cli/package.json: take 0.5.75
- .gitignore: union both sides (upstream 9router-*/temp files + local state dirs)
- CHANGELOG.md: keep both blocks, v0.5.75 above v0.5.70
- nonStreamingHandler.js: merge imports (unwrapClineEnvelope +
  tokensForDetail/shouldPersistRequestDetail); drop dead appendRequestLog
- providers/[id]/page.js: union useState blocks (compatible-model states
  + importingClineModels)

Co-authored-by: CommandCodeBot <noreply@commandcode.ai>
2026-09-17 14:14:43 +07:00
coozgan
3288bbc47e feat(video): add OpenRouter and Vertex AI (Veo) video generation
Video generation was xAI-only. Adds an adapter layer under
open-sse/handlers/videoProviders/ so /v1/videos/* can target OpenRouter or
Google Cloud credentials. A provider with no adapter keeps the exact previous
behaviour (raw body to {baseUrl}/{action}, poll {baseUrl}/{id}, verbatim
passthrough), so the xAI path is unchanged.

- openrouter: async job shape identical to xAI; creation POSTs to the /videos
  collection root (no /generations suffix) and the registry HTTP-Referer /
  X-Title headers are applied. Bodies pass through verbatim.
- vertex: two-way translation, since Veo does not speak the OpenAI-ish videos
  shape. create -> :predictLongRunning { instances[], parameters{} }, poll ->
  :fetchPredictOperation (Veo has no REST GET poll). The operation resource
  name is base64url-encoded into the job id so GET /v1/videos/{id} stays a
  flat path. Access tokens are minted from Service Account JSON via the
  existing refreshVertexToken; raw API keys are rejected up front. The
  operation response maps back onto the { id, status, video, videos } shape
  clients already poll.
- videoCore: the request plan is rebuilt per attempt, so the 401 -> refresh
  once -> retry once path picks up the refreshed token. Adapter validation
  errors return 400 before any upstream call, so a malformed request can never
  create a billable job.
- videoGeneration: GET /v1/videos/{id} resolves the provider from the pinned
  x-connection-id connection, then ?provider=, then falls back to the xAI
  default.
- registry: openrouter and vertex gain videoConfig, the video serviceKind and
  video-kind models (Veo 3.1 / 3 / 2, Sora 2 Pro, Seedance 2.0).
2026-09-10 22:05:22 +07:00
144dda2ac2 fix(routing): fall through to compatible node when built-in alias has no credentials 2026-08-22 14:33:53 +07:00
ann
d6761c6fb0 feat(xai): add Grok Imagine video generation (/v1/videos) + CLI
Async video job proxy mirroring the existing image-generation layer split:
Next routes → src/sse/handlers/videoGeneration.js (auth gate, account
fallback loop, refresh persistence) → open-sse/handlers/videoCore.js
(transparent upstream proxy, 401 refresh-once/retry-once, secret sanitization).

- POST /v1/videos/{generations,edits,extensions}: byte-exact body forward
  (JSON + multipart), request_id passthrough, Idempotency-Key forwarded
- GET /v1/videos/{request_id}: status/progress/video.url passthrough
- Register grok-imagine-video (kind: "video"); add "video" to MODEL_TYPE_TO_KIND
  so video models stay out of chat lists (also fixes runwayml leak)
- 9router xai video CLI: submit → poll → atomic MP4 download
- No auto-retry of creation POSTs (billable jobs); rotate accounts only on
  401/403/429; sanitize Bearer tokens + credential values from errors/logs

Closes #1285
2026-07-16 15:29:52 +07:00