feat: support uploaded images in debug voice preview

Allow paste/drag temporary image assets so vision turns work without a live camera frame.

Co-authored-by: Cursor <cursoragent@cursor.com>
This commit is contained in:
Xin Wang
2026-08-05 19:52:37 +08:00
parent 555c8f5fa6
commit e36ca308b8
16 changed files with 686 additions and 94 deletions

View File

@@ -59,3 +59,11 @@ S3_BUCKET = os.getenv("S3_BUCKET", "ai-video")
S3_REGION = os.getenv("S3_REGION", "us-east-1")
KNOWLEDGE_MAX_FILE_BYTES = int(os.getenv("KNOWLEDGE_MAX_FILE_BYTES", "20971520"))
KNOWLEDGE_TOP_K = int(os.getenv("KNOWLEDGE_TOP_K", "5"))
# ---- Realtime user-input image attachments ----
INPUT_IMAGE_MAX_BYTES = int(os.getenv("INPUT_IMAGE_MAX_BYTES", "10485760"))
INPUT_IMAGE_MAX_PIXELS = int(os.getenv("INPUT_IMAGE_MAX_PIXELS", "24000000"))
INPUT_IMAGE_MAX_EDGE = int(os.getenv("INPUT_IMAGE_MAX_EDGE", "2048"))
INPUT_IMAGE_TOKEN_TTL_SECONDS = int(
os.getenv("INPUT_IMAGE_TOKEN_TTL_SECONDS", "600")
)