fix(video-render): Veo Vertex AI → Gemini API (T10 follow-up)

박재오 발견: Veo는 Gemini API key 단일로 충분 (ai.google.dev).
Vertex AI의 GCP project + service account JSON + GCS bucket 셋업 불필요.

변경:
- providers/veo.py: generativelanguage.googleapis.com/v1beta endpoint
  + x-goog-api-key 헤더 + response.generateVideoResponse.generatedSamples[0].video.uri
- .env.example: GOOGLE_PROJECT_ID/LOCATION/GCS_BUCKET/SA_JSON 4 변수 → GEMINI_API_KEY 1개
- docker-compose: GCP 4 env + SA JSON volume mount 제거, GEMINI_API_KEY 추가
- requirements.txt: google-cloud-storage 제거 (requests만 사용)

박재오 측 영향: /etc/webai/gcp-sa.json 더미 파일 + GCP_SA_JSON_HOST_PATH env 무관.
GEMINI_API_KEY 1개만 발급하여 .env에 추가하면 됨.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

services/docker-compose.yml

@@ -63,17 +63,13 @@ services:
       - NAS_BASE_URL=${NAS_BASE_URL:-http://192.168.45.54:18801}
       - INTERNAL_API_KEY=${INTERNAL_API_KEY:-}
       - OPENAI_API_KEY=${OPENAI_API_KEY:-}
-      - GOOGLE_PROJECT_ID=${GOOGLE_PROJECT_ID:-}
-      - GOOGLE_LOCATION=${GOOGLE_LOCATION:-us-central1}
-      - GOOGLE_GCS_BUCKET=${GOOGLE_GCS_BUCKET:-}
-      - GOOGLE_APPLICATION_CREDENTIALS=/app/keys/gcp-sa.json
+      - GEMINI_API_KEY=${GEMINI_API_KEY:-}
       - PIAPI_API_KEY=${PIAPI_API_KEY:-}
       - SEEDANCE_API_KEY=${SEEDANCE_API_KEY:-}
       - VIDEO_MEDIA_ROOT=${VIDEO_MEDIA_ROOT:-/mnt/nas/webpage/data/video}
       - VIDEO_MEDIA_URL_PREFIX=${VIDEO_MEDIA_URL_PREFIX:-/media/video}
     volumes:
       - /mnt/nas/webpage/data/video:/mnt/nas/webpage/data/video
-      - ${GCP_SA_JSON_HOST_PATH:-/etc/webai/gcp-sa.json}:/app/keys/gcp-sa.json:ro
     healthcheck:
       test: ["CMD", "python", "-c", "import urllib.request; urllib.request.urlopen('http://localhost:8000/health')"]
       interval: 60s