feat(google-gemini): add new models [bot]

[models-bot]

Auto-generated by model-addition-agent for provider google-gemini.

---

Note

Low Risk
Adds a new model metadata YAML for Google Gemini; no executable code changes, so impact is limited to model availability/selection and pricing/limits data.

Overview
Introduces a new providers/google-gemini/gemini-3.1-flash-lite.yaml model definition, including token pricing, limits (up to 1M context / 65k output), supported modalities, and enabled features (tools/function calling, structured/JSON output, prompt caching, code execution).

Marks the model as active for chat mode with serverless provisioning, configurable sampling params, and a declared deprecation date.

^{Reviewed by Cursor Bugbot for commit ce80316. Bugbot is set up for automated code reviews on this repo. Configure here.}

[cursor]

Cursor Bugbot has reviewed your changes and found 2 potential issues.

^{❌ Bugbot Autofix is OFF. To automatically fix reported issues with cloud agents, enable autofix in the Cursor dashboard.}

^{Reviewed by Cursor Bugbot for commit 52b4f63. Configure here.}

[github-actions]

/test-models

[harshiv-26]

Gateway test results

• Total: 24
• Passed: 24
• Failed: 0
• Validation failed: 0
• Errored: 0
• Skipped: 0
• Success rate: 100.0%

Provider	Model	Scenarios
google-gemini	gemini-3.1-flash-lite	success: tool-call, parallel-tool-call, json-output, params, parallel-tool-call:stream, tool-call:stream, structured-output, params:stream, json-output:stream, structured-output:stream, parallel-tool-call:stream:google-genai, params:stream:google-genai, params:google-genai, structured-output:google-genai, tool-call:google-genai, json-output:stream:google-genai, parallel-tool-call:google-genai, tool-call:stream:google-genai, json-output:google-genai, structured-output:stream:google-genai, reasoning:stream, reasoning:stream:google-genai, reasoning, reasoning:google-genai