local-tokenizer does not support gemini-3.1-flash-lite

[jayjk13]

local-tokenizer does not support gemini-3.1-flash-lite

Same class of issue as #1784 (gemini-3-pro-preview) and #1972 (gemini-3-flash-preview).

Environment details

• Programming language: Python
• OS: macOS
• Language runtime version: 3.13.2
• Package version: google-genai==2.8.0 (latest on PyPI at time of report)

Steps to reproduce

from google.genai.local_tokenizer import LocalTokenizer
from google.genai.types import CountTokensResult

tokenizer = LocalTokenizer(model_name="gemini-3.1-flash-lite")
result: CountTokensResult = tokenizer.count_tokens("test")

Actual behavior

ValueError: Model gemini-3.1-flash-lite is not supported. Supported models: gemini-2.5-pro, gemini-2.5-flash, gemini-2.5-flash-lite, gemini-2.0-flash, gemini-2.0-flash-lite, gemini-2.5-pro-preview-06-05, gemini-2.5-pro-preview-05-06, gemini-2.5-pro-exp-03-25, gemini-live-2.5-flash, gemini-2.5-flash-preview-05-20, gemini-2.5-flash-preview-04-17, gemini-2.5-flash-lite-preview-06-17, gemini-2.0-flash-001, gemini-2.0-flash-lite-001, gemini-3-pro-preview.

Expected behavior

LocalTokenizer(model_name="gemini-3.1-flash-lite") should work, since:

1. gemini-3.1-flash-lite is a supported Vertex model (added to SDK model enums in v2.1.0).
2. client.models.count_tokens(model="gemini-3.1-flash-lite", ...) works via the API.
3. Sibling Gemini 3 models like gemini-3-pro-preview already work with LocalTokenizer on 2.8.0.