feat: add support for gemini-3-pro-preview model (qodo-ai#2202)

* feat: add support for gemini-3-pro-preview model

- Add gemini/gemini-3-pro-preview with 1,048,576 max tokens
- Add vertex_ai/gemini-3-pro-preview with 1,048,576 max tokens
- Add test coverage for both model variants
- Update documentation with usage examples for both variants

This enables users to utilize Google's Gemini 3 Pro Preview model
through both Google AI Studio and Vertex AI providers with full
1M+ token context window support.

* refactor: streamline test for gemini-3-pro-preview model

- Consolidate test cases for gemini-3-pro-preview into a parameterized test
- Remove redundant assertions and simplify the test structure
- Ensure both Google AI Studio and Vertex AI variants are covered in a single test

This enhances maintainability and readability of the test suite for the gemini-3-pro-preview model.

Author: claudiunicolaa

docs/docs/usage-guide/qodo_merge_models.md

@@ -10,6 +10,7 @@ The models supported by Qodo Merge are:
 - `anthropic/claude-sonnet-4-5-20250929`
 - `vertex_ai/gemini-2.5-pro`
 - `vertex_ai/gemini-3-pro-preview`
+- `gemini/gemini-3-pro-preview`
 - `gpt-5-2025-08-07`
 - `gpt-5.2-2025-12-11`
 
@@ -41,6 +42,13 @@ To restrict Qodo Merge to using `vertex_ai/gemini-3-pro-preview`:
 model="vertex_ai/gemini-3-pro-preview"
 ```
 
+To restrict Qodo Merge to using `gemini/gemini-3-pro-preview`:
+
+```toml
+[config]
+model="gemini/gemini-3-pro-preview"
+```
+
 To restrict Qodo Merge to using `gpt-5-2025-08-07`:
 
 ```toml

pr_agent/algo/__init__.py

@@ -88,6 +88,7 @@
     'vertex_ai/gemini-2.5-flash-preview-04-17': 1048576,
     'vertex_ai/gemini-2.5-flash-preview-05-20': 1048576,
     'vertex_ai/gemini-2.5-flash': 1048576,
+    'vertex_ai/gemini-3-pro-preview': 1048576,
     'vertex_ai/gemma2': 8200,
     'gemini/gemini-1.5-pro': 1048576,
     'gemini/gemini-1.5-flash': 1048576,
@@ -99,6 +100,7 @@
     'gemini/gemini-2.5-pro-preview-05-06': 1048576,
     'gemini/gemini-2.5-pro-preview-06-05': 1048576,
     'gemini/gemini-2.5-pro': 1048576,
+    'gemini/gemini-3-pro-preview': 1048576,
     'codechat-bison': 6144,
     'codechat-bison-32k': 32000,
     'anthropic.claude-instant-v1': 100000,

tests/unittest/test_get_max_tokens.py

@@ -66,6 +66,20 @@ def test_model_max_tokens_with__limit(self, monkeypatch):
 
         assert get_max_tokens(model) == expected
 
+    @pytest.mark.parametrize("model", [
+        "gemini/gemini-3-pro-preview",
+        "vertex_ai/gemini-3-pro-preview",
+    ])
+    def test_gemini_3_pro_preview(self, monkeypatch, model):
+        fake_settings = type("", (), {
+            "config": type("", (), {
+                "custom_model_max_tokens": 0,
+                "max_model_tokens": 0,
+            })()
+        })()
+        monkeypatch.setattr(utils, "get_settings", lambda: fake_settings)
+        assert get_max_tokens(model) == 1048576
+
     @pytest.mark.parametrize(
         "model",
         [