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).

open-sse/providers/registry/openrouter.js

@@ -40,8 +40,11 @@ export default {
     { id: "openai/gpt-image-1", name: "GPT Image 1 (via OpenRouter)", params: ["n","size","quality","response_format"], kind: "image" },
     { id: "google/imagen-3.0-generate-002", name: "Imagen 3 (via OpenRouter)", params: ["n","size"], kind: "image" },
     { id: "black-forest-labs/FLUX.1-schnell", name: "FLUX.1 Schnell (via OpenRouter)", params: ["n","size"], kind: "image" },
+    { id: "google/veo-3.1", name: "Veo 3.1 (via OpenRouter)", params: ["duration","aspect_ratio","resolution"], kind: "video" },
+    { id: "openai/sora-2-pro", name: "Sora 2 Pro (via OpenRouter)", params: ["duration","aspect_ratio","resolution"], kind: "video" },
+    { id: "bytedance/seedance-2.0", name: "Seedance 2.0 (via OpenRouter)", params: ["duration","aspect_ratio","resolution"], kind: "video" },
   ],
-  serviceKinds: ["llm","embedding","tts","imageToText"],
+  serviceKinds: ["llm","embedding","tts","imageToText","video"],
   ttsConfig: {
     baseUrl: "https://openrouter.ai/api/v1/chat/completions",
     defaultModel: "openai/gpt-4o-mini-tts",
@@ -57,6 +60,12 @@ export default {
     baseUrl: "https://openrouter.ai/api/v1/images/generations",
     headers: {"HTTP-Referer":"https://endpoint-proxy.local","X-Title":"Endpoint Proxy"},
   },
+  // Async video jobs (POST /videos → { id, status }, GET /videos/{id} polls).
+  // Docs: https://openrouter.ai/docs/api/api-reference/videos
+  videoConfig: {
+    baseUrl: "https://openrouter.ai/api/v1/videos",
+    headers: {"HTTP-Referer":"https://endpoint-proxy.local","X-Title":"Endpoint Proxy"},
+  },
   modelsFetcher: { url: "https://openrouter.ai/api/v1/models", type: "openrouter-free" },
   passthroughModels: true,
 };

open-sse/providers/registry/vertex.js

@@ -27,6 +27,13 @@ export default {
     { id: "gemini-3.1-flash-lite-preview", name: "Gemini 3.1 Flash Lite Preview" },
     { id: "gemini-3-flash-preview", name: "Gemini 3 Flash Preview" },
     { id: "gemini-2.5-flash", name: "Gemini 2.5 Flash" },
+    { id: "veo-3.1-generate-preview", name: "Veo 3.1 (Preview)", params: ["duration","aspect_ratio","resolution","negative_prompt","seed","storage_uri","generate_audio"], kind: "video" },
+    { id: "veo-3.1-fast-generate-preview", name: "Veo 3.1 Fast (Preview)", params: ["duration","aspect_ratio","resolution","negative_prompt","seed","storage_uri","generate_audio"], kind: "video" },
+    { id: "veo-3.0-generate-001", name: "Veo 3", params: ["duration","aspect_ratio","resolution","negative_prompt","seed","storage_uri","generate_audio"], kind: "video" },
+    { id: "veo-2.0-generate-001", name: "Veo 2", params: ["duration","aspect_ratio","negative_prompt","seed","storage_uri"], kind: "video" },
   ],
-  serviceKinds: ["llm","imageToText"],
+  serviceKinds: ["llm","imageToText","video"],
+  // Veo via predictLongRunning + fetchPredictOperation (adapter: handlers/videoProviders/vertex.js).
+  // Docs: https://cloud.google.com/vertex-ai/generative-ai/docs/model-reference/veo-video-generation
+  videoConfig: { baseUrl: "https://aiplatform.googleapis.com" },
 };