feat: add Gemini 3.1 stable and 3.5 model identifiers to supported model registry

[Copilot]

Gemini support was lagging behind currently available model IDs, which caused newer Gemini variants to be treated as unknown in token-limit resolution paths. This update adds current Gemini 3.1 stable and 3.5 identifiers for both AI Studio and Vertex AI prefixes.

• Model registry updates (pr_agent/algo/__init__.py)

  • Added Gemini entries to MAX_TOKENS (1,048,576 tokens) for:
    • gemini/gemini-3.1-flash
    • gemini/gemini-3.1-pro
    • gemini/gemini-3.5-flash
    • gemini/gemini-3.5-pro
    • vertex_ai/gemini-3.1-flash
    • vertex_ai/gemini-3.1-pro
    • vertex_ai/gemini-3.5-flash
    • vertex_ai/gemini-3.5-pro

• Coverage extension (tests/unittest/test_get_max_tokens.py)

  • Expanded Gemini parameterized max-token test cases to include the new 3.1 stable and 3.5 IDs.
  • Renamed the Gemini test method to reflect broadened scope.

# New examples now recognized by MAX_TOKENS:
"gemini/gemini-3.5-pro": 1048576
"vertex_ai/gemini-3.1-flash": 1048576

[qodo-free-for-open-source-projects]

Review Summary by Qodo

Add Gemini 3.1 stable and 3.5 model support to registry

✨ Enhancement

Walkthroughs

Description

• Add Gemini 3.1 stable and 3.5 model identifiers to token registry
• Support both AI Studio and Vertex AI prefixes for new models
• Expand test coverage for latest Gemini model variants

Diagram

flowchart LR
  A["New Gemini Models<br/>3.1 stable & 3.5"] -->|"Add to MAX_TOKENS"| B["Model Registry<br/>pr_agent/algo/__init__.py"]
  B -->|"8 new entries"| C["AI Studio & Vertex AI<br/>Prefixes"]
  A -->|"Expand test cases"| D["Test Coverage<br/>test_get_max_tokens.py"]
  D -->|"Rename & parameterize"| E["Updated Test Method"]

Loading

File Changes

1. pr_agent/algo/__init__.py ⚙️ Configuration changes +8/-0

Register Gemini 3.1 stable and 3.5 models

• Added 4 new Gemini 3.1 stable model identifiers with 1,048,576 token limit
• Added 4 new Gemini 3.5 model identifiers with 1,048,576 token limit
• Entries include both gemini/ and vertex_ai/ prefixes
• Models: gemini-3.1-flash, gemini-3.1-pro, gemini-3.5-flash, gemini-3.5-pro

pr_agent/algo/init.py

---

2. tests/unittest/test_get_max_tokens.py 🧪 Tests +9/-1

Expand Gemini model test coverage

• Added 8 new parameterized test cases for Gemini 3.1 stable and 3.5 models
• Covers both AI Studio and Vertex AI model prefixes
• Renamed test method from test_gemini_3_and_3_1_pro_preview to
 test_gemini_3_3_1_and_3_5_models_max_tokens
• Expanded test scope to reflect broader Gemini model coverage

tests/unittest/test_get_max_tokens.py

---

[qodo-free-for-open-source-projects]

Code Review by Qodo

🐞 Bugs (0) 📘 Rule violations (0) 📎 Requirement gaps (0)

Great, no issues found!

Qodo reviewed your code and found no material issues that require review