Account for image inputs in LLM gateway token estimates

[barrygreengus]

Problem

The LLM API gateway does not estimate image input tokens from image dimensions
and the target model's visual processor. Multimodal requests can therefore
reserve input-token capacity based on serialized payload size rather than the
visual tokens consumed by inference.

Desired behavior

• Read dimensions from base64-encoded image headers without decoding pixels.
• Bound header inspection so malformed images cannot cause unbounded scans.
• Apply model-specific patch, tile, and fixed-token estimators where known.
• Use a conservative fallback for unknown models or unavailable dimensions.
• Keep model-name matching explicit so unrelated names cannot select a cheaper
  estimator.

Acceptance criteria

• Chat Completions and Responses admission accounting includes every image.
• Common NIM vision models use documented processor equations.
• Unknown models receive a size-based bounded estimate.
• PNG, JPEG, GIF, and WebP base64 inputs are covered by tests.