feat(mm): add gpt-image-2 as a starter model (#9096)

* feat(mm): add gpt-image-2 as a starter model

Adds OpenAI GPT-Image-2 to the external API model list.

- Registers "gpt-image-2" in OpenAIProvider._GPT_IMAGE_MODELS so it
  uses the correct GPT Image request/response path (output_format,
  edits endpoint, etc.)
- Adds openai_gpt_image_2 StarterModel entry with the same aspect
  ratios and panel schema as gpt-image-1

Notable gpt-image-2 constraints (handled by not exposing them in the
panel schema): no transparent background support, input_fidelity is
not configurable (always high fidelity).

* fix(external): extend request timeout to 300s for gpt-image-2

gpt-image-2 is significantly slower than other GPT Image models,
especially through a proxy. The default 120s timeout causes failures.
Adds a per-model timeout map so other models are unaffected.

---------

Co-authored-by: Alexander Eichhorn <alex@eichhorn.dev>
Co-authored-by: Jonathan <34005131+JPPhoto@users.noreply.github.com>