[BOT ISSUE] fix: add missing Vertex entry for gemini-3.1-flash-lite (stable)

[github-actions]

Missing Vertex provider mapping

The stable model gemini-3.1-flash-lite was recently added to the catalog (commit 2325854, PR #553) with google as the only provider. However, the Vertex AI pricing page confirms this model is also available on Vertex AI. Two entries are needed:

1. Add vertex to the available_providers array of the existing gemini-3.1-flash-lite entry (line 6717)
2. Create a new publishers/google/models/gemini-3.1-flash-lite entry for Vertex

The preview variant publishers/google/models/gemini-3.1-flash-lite-preview already exists in the catalog (line 8445), so this is the natural stable counterpart.

Current catalog state

gemini-3.1-flash-lite (line 6717):

{
  "format": "google",
  "flavor": "chat",
  "multimodal": true,
  "input_cost_per_mil_tokens": 0.25,
  "output_cost_per_mil_tokens": 1.5,
  "input_cache_read_cost_per_mil_tokens": 0.025,
  "displayName": "Gemini 3.1 Flash-Lite",
  "reasoning": true,
  "reasoning_budget": true,
  "max_input_tokens": 1048576,
  "max_output_tokens": 65536,
  "available_providers": ["google"]
}

Proposed changes

1. Update gemini-3.1-flash-lite → add "vertex" to available_providers
2. Add new entry:

"publishers/google/models/gemini-3.1-flash-lite": {
  "format": "google",
  "flavor": "chat",
  "multimodal": true,
  "input_cost_per_mil_tokens": 0.25,
  "output_cost_per_mil_tokens": 1.5,
  "input_cache_read_cost_per_mil_tokens": 0.025,
  "displayName": "Gemini 3.1 Flash-Lite",
  "reasoning": true,
  "reasoning_budget": true,
  "locations": ["global"],
  "max_input_tokens": 1048576,
  "max_output_tokens": 65535
}

Note: Vertex entries for preview models use max_output_tokens: 65535 (vs 65536 in the Google AI entry), following the existing convention seen in publishers/google/models/gemini-3.1-flash-lite-preview.

Verification checklist

• Cross-source confirmation: Model confirmed on (1) Google AI models page with "Stable" badge, (2) Google AI pricing page at $0.25/$1.50, and (3) Vertex AI pricing page listing gemini-3.1-flash-lite with Global pricing at $0.25/$1.50 and Non-global at $0.275/$1.65.
• Recent commits check: Commit 2325854 (PR fix: add Google models gemini-3.1-flash-lite #553) added the Google AI entry but did not add the Vertex entry. No publishers/google/models/gemini-3.1-flash-lite string exists in the current model_list.json.
• ID format validation: Follows existing convention — publishers/google/models/gemini-3.1-flash-lite-preview (preview variant) and publishers/google/models/gemini-2.5-flash-lite (prior generation stable) both exist.

Verification notes

Field	Source
Model available on Vertex	Vertex AI pricing page — listed under Gemini 3.1 section
Vertex Global pricing ($0.25/$1.50)	Vertex AI pricing page
Vertex Non-global pricing ($0.275/$1.65)	Vertex AI pricing page
Model is Stable (not Preview)	Google AI models page
Token limits (1M input, 65K output)	Google AI pricing page and existing catalog entry

Fields NOT verified from official sources:

• supported_regions for Vertex — the Vertex pricing page distinguishes Global vs Non-global pricing but does not enumerate specific regions. The downstream fix job should populate locations based on Vertex region availability docs.

Local files inspected

• packages/proxy/schema/model_list.json — line 6717 (gemini-3.1-flash-lite with google only), line 8445 (publishers/google/models/gemini-3.1-flash-lite-preview exists as precedent)

Relationship to #540

Issue #540 (closed, completed) added gemini-3.1-flash-lite as a Google AI model. That issue explicitly noted "Vertex availability for the stable version is unconfirmed." The Vertex pricing page now confirms availability.

{
  "kind": "missing_model",
  "provider": "vertex",
  "models": ["publishers/google/models/gemini-3.1-flash-lite"],
  "status": "active",
  "model_specs": {
    "publishers/google/models/gemini-3.1-flash-lite": {
      "format": "google",
      "flavor": "chat",
      "multimodal": true,
      "input_cost_per_mil_tokens": 0.25,
      "output_cost_per_mil_tokens": 1.5,
      "input_cache_read_cost_per_mil_tokens": 0.025,
      "displayName": "Gemini 3.1 Flash-Lite",
      "reasoning": true,
      "reasoning_budget": true,
      "locations": ["global"],
      "max_input_tokens": 1048576,
      "max_output_tokens": 65535
    }
  },
  "source_urls": [
    "https://ai.google.dev/gemini-api/docs/models/gemini",
    "https://ai.google.dev/pricing",
    "https://cloud.google.com/vertex-ai/generative-ai/pricing"
  ]
}