The image pipeline — turning one idea into a hundred shipped assets — step 7 of 7

Final image drill. Wire all three lessons together. Write plan_shoot(brief) that takes a brief dict and returns a plan dict:

{"model": str, "count": int, "total_cost": float, "formats": list[str]}

The brief may contain:

• channel: one of "instagram", "web", "email", "tiktok"
• batch_count: int (default 1)
• budget_per_image: float (default 1.0)
• needs_text_in_image: bool
• needs_vector: bool
• photoreal_art_directed: bool
• instruction_heavy: bool
• google_premium: bool
• needs_4k: bool (uses the 4K row for nano banana 2 / Pro)

Use the routing from lesson 01 (pick_image_model), the pricing table from lesson 03 step 06, and the PLATFORM_FORMATS table (provided) to pick output formats by channel.

Four briefs run. Expected output:

B1: model=ideogram-v4              count=  5  total=$  0.30  formats=['WEBP_1920', 'WEBP_400_thumb']
B2: model=gpt-image-2              count=  4  total=$  0.21  formats=['JPEG_1080']
B3: model=gemini-3.1-flash-image   count= 50  total=$  3.35  formats=['JPEG_1080_vertical']
B4: model=gemini-3-pro-image       count= 10  total=$  2.40  formats=['WEBP_1920', 'WEBP_400_thumb']