fix(kits): add Gemini 3.x before 2.5 retirement

[CorieW]

Summary

• Default translate and genai chatbot to gemini-3.6-flash; add 3.x ids to the translate select list (2.5 kept until October 2026).
• Genkit chatbot no longer throws Model not found. for unknown ids — falls through to googleAI.model() / vertexAI.model().
• Resize content filter uses gemini-3.1-flash-lite.
• Vector search Gemini/Vertex embedder uses gemini-embedding-2 (Gemini API retired gemini-embedding-001 on 14 Jul 2026). Flash completion IDs are not embedders.

Why gemini-3.1-flash-lite (not gemini-3.5-flash-lite or higher)

The resize content filter is a high-volume yes/no image check, previously hardcoded to gemini-2.5-flash. We picked gemini-3.1-flash-lite because it is similar in price to that previous default ($0.25/$1.50 vs $0.30/$2.50 per 1M tokens) and performs better (Google: similar or better quality than 2.5 Flash, ~2.5× faster time-to-first-token). gemini-3.5-flash-lite is the same sticker as 2.5 Flash; gemini-3.5-flash and gemini-3.6-flash are about 5× input.

Test plan

• Run firestore-genai-chatbot unit tests (includes current-model Genkit path)
• Confirm translate GEMINI_MODEL select includes 3.x and defaults to 3.6 Flash
• Smoke chatbot + translate with gemini-3.6-flash
• Run storage-resize-images content-filter unit tests
• Smoke vector search Gemini embeddings with gemini-embedding-2

[gemini-code-assist]

Code Review

This pull request updates several Firebase Extensions to use Gemini 3.6 Flash as the default model and gemini-embedding-2 for vector search. It also refactors model reference resolution in the GenAI Chatbot extension to support dynamic fallback instead of throwing errors. The review feedback suggests simplifying shouldUseGenkitClient since model resolution no longer throws, and adding missing Gemini 3.5 models to the translation options for consistency.

[gemini-code-assist]

Since createModelReference has been updated to never throw and always return a ModelReference (falling back to dynamic resolution), the check !!GenkitDiscussionClient.createModelReference(...) in shouldUseGenkitClient will always evaluate to true.

We can simplify shouldUseGenkitClient to only check the candidate count, avoiding redundant model reference creation:

  static shouldUseGenkitClient(config: ResolvedGenaiChatbotConfig): boolean {
    const shouldReturnMultipleCandidates =
      config.candidateCount && config.candidateCount > 1;
    return !shouldReturnMultipleCandidates;
  }

[gemini-code-assist]

The GEMINI_MODEL_OPTIONS list is missing gemini-3.5-flash and gemini-3.5-flash-lite, which are valid Gemini 3.x models and are included in the chatbot's knownIds. Adding them here ensures consistency across extensions and allows users to select these models from the dropdown in the Firebase Console.

Suggested change

	"gemini-3.1-pro-preview",
	"gemini-3.6-flash",
	"gemini-3.1-flash-lite",
	"gemini-3.6-flash",
	"gemini-3.5-flash",
	"gemini-3.5-flash-lite",
	"gemini-3.1-flash-lite",
	"gemini-3.1-pro-preview",