Add generate-image agent skill

[shatfield4]

Pull Request Type

• ✨ feat (New feature)
• 🐛 fix (Bug fix)
• ♻️ refactor (Code refactoring without changing behavior)
• 💄 style (UI style changes)
• 🔨 chore (Build, CI, maintenance)
• 📝 docs (Documentation updates)

Relevant Issues

resolves #6139

Description

• add a generate-image agent skill so images can be generated via a tool call
• skill accepts a prompt, optional dimensions, and an edit flag for transforming an image already in the conversation
• edits use the images attached to the last user message, falling back to the image generated earlier in the session
• show a placeholder card while the image is generating that swaps for the result, or clears if generation fails or is cancelled
• send the generated image inline over the socket so it renders immediately, and persist it to the chat so it rerenders on reload
• when no image generation provider is configured the skill tells the agent to point the user at Settings > Image Generation
• hide the skill in the in-chat tools menu until a provider is configured, while always listing it on the agent skills settings page

Visuals (if applicable)

Additional Information

• Will create translations PR after review is approved

Developer Validations

• I ran yarn lint from the root of the repo & committed changes
• Relevant documentation has been updated (if applicable)
• I have tested my code functionality
• Docker build succeeds locally

[timothycarambat]

Just some questions, nit, and potentially a refactor opp for frontend for detecting if imgen is supported.