Support multiple model types for different reasoning tasks

docs/docs/tools/improve.md

@@ -416,18 +416,18 @@ Qodo Merge uses a dynamic strategy to generate code suggestions based on the siz
 #### 1. Chunking large PRs
 
 - Qodo Merge divides large PRs into 'chunks'.
-- Each chunk contains up to `pr_code_suggestions.max_context_tokens` tokens (default: 14,000).
+- Each chunk contains up to `pr_code_suggestions.max_context_tokens` tokens (default: 24,000).
 
 #### 2. Generating suggestions
 
-- For each chunk, Qodo Merge generates up to `pr_code_suggestions.num_code_suggestions_per_chunk` suggestions (default: 3).
+- For each chunk, Qodo Merge generates up to `pr_code_suggestions.num_code_suggestions_per_chunk` suggestions (default: 4).
 
 This approach has two main benefits:
 
 - Scalability: The number of suggestions scales with the PR size, rather than being fixed.
 - Quality: By processing smaller chunks, the AI can maintain higher quality suggestions, as larger contexts tend to decrease AI performance.
 
-Note: Chunking is primarily relevant for large PRs. For most PRs (up to 500 lines of code), Qodo Merge will be able to process the entire code in a single call.
+Note: Chunking is primarily relevant for large PRs. For most PRs (up to 600 lines of code), Qodo Merge will be able to process the entire code in a single call.
 
 ## Configuration options
 

pr_agent/algo/pr_processing.py

@@ -12,7 +12,7 @@ from pr_agent.algo.git_patch_processing import (
 from pr_agent.algo.language_handler import sort_files_by_main_languages
 from pr_agent.algo.token_handler import TokenHandler
 from pr_agent.algo.types import EDIT_TYPE, FilePatchInfo
-from pr_agent.algo.utils import ModelType, clip_tokens, get_max_tokens, get_weak_model
+from pr_agent.algo.utils import ModelType, clip_tokens, get_max_tokens, get_model
 from pr_agent.config_loader import get_settings
 from pr_agent.git_providers.git_provider import GitProvider
 from pr_agent.log import get_logger
@@ -339,7 +339,9 @@ async def retry_with_fallback_models(f: Callable, model_type: ModelType = ModelT
 
 def _get_all_models(model_type: ModelType = ModelType.REGULAR) -> List[str]:
     if model_type == ModelType.WEAK:
-        model = get_weak_model()
+        model = get_model('model_weak')
+    elif model_type == ModelType.REASONING:
+        model = get_model('model_reasoning')
     else:
         model = get_settings().config.model
     fallback_models = get_settings().config.fallback_models

pr_agent/algo/utils.py

@@ -30,12 +30,13 @@ from pr_agent.config_loader import get_settings, global_settings
 from pr_agent.log import get_logger
 
 
-def get_weak_model() -> str:
-    if get_settings().get("config.model_weak"):
+def get_model(model_type: str = "model_weak") -> str:
+    if model_type == "model_weak" and get_settings().get("config.model_weak"):
         return get_settings().config.model_weak
+    elif model_type == "model_reasoning" and get_settings().get("config.model_reasoning"):
+        return get_settings().config.model_reasoning
     return get_settings().config.model
 
-
 class Range(BaseModel):
     line_start: int  # should be 0-indexed
     line_end: int
@@ -45,6 +46,7 @@ class Range(BaseModel):
 class ModelType(str, Enum):
     REGULAR = "regular"
     WEAK = "weak"
+    REASONING = "reasoning"
 
 class PRReviewHeader(str, Enum):
     REGULAR = "## PR Reviewer Guide"

pr_agent/settings/configuration.toml

@@ -6,8 +6,9 @@
 
 [config]
 # models
-model="o4-mini"
-fallback_models=["gpt-4.1"]
+model_reasoning="o4-mini"
+model="gpt-4.1"
+fallback_models=["o4-mini"]
 #model_weak="gpt-4o" # optional, a weaker model to use for some easier tasks
 # CLI
 git_provider="github"
@@ -123,7 +124,7 @@ use_conversation_history=true
 
 
 [pr_code_suggestions] # /improve #
-max_context_tokens=16000
+max_context_tokens=24000
 #
 commitable_code_suggestions = false
 dual_publishing_score_threshold=-1 # -1 to disable, [0-10] to set the threshold (>=) for publishing a code suggestion both in a table and as commitable
@@ -144,7 +145,7 @@ new_score_mechanism_th_high=9
 new_score_mechanism_th_medium=7
 # params for '/improve --extended' mode
 auto_extended_mode=true
-num_code_suggestions_per_chunk=3
+num_code_suggestions_per_chunk=4
 max_number_of_calls = 3
 parallel_calls = true
 

pr_agent/tools/pr_code_suggestions.py

@@ -19,7 +19,7 @@ from pr_agent.algo.pr_processing import (add_ai_metadata_to_diff_files,
                                          retry_with_fallback_models)
 from pr_agent.algo.token_handler import TokenHandler
 from pr_agent.algo.utils import (ModelType, load_yaml, replace_code_tags,
-                                 show_relevant_configurations, get_max_tokens, clip_tokens)
+                                 show_relevant_configurations, get_max_tokens, clip_tokens, get_model)
 from pr_agent.config_loader import get_settings
 from pr_agent.git_providers import (AzureDevopsProvider, GithubProvider,
                                     GitLabProvider, get_git_provider,
@@ -121,7 +121,7 @@ class PRCodeSuggestions:
             # if not self.is_extended:
             #     data = await retry_with_fallback_models(self._prepare_prediction, model_type=ModelType.REGULAR)
             # else:
-            data = await retry_with_fallback_models(self._prepare_prediction_extended, model_type=ModelType.REGULAR)
+            data = await retry_with_fallback_models(self.prepare_prediction_main, model_type=ModelType.REGULAR)
             if not data:
                 data = {"code_suggestions": []}
             self.data = data
@@ -416,9 +416,14 @@ class PRCodeSuggestions:
         data = self._prepare_pr_code_suggestions(response)
 
         # self-reflect on suggestions (mandatory, since line numbers are generated now here)
-        model_reflection = get_settings().config.model
+        model_reflect_with_reasoning = get_model('model_reasoning')
+        if model_reflect_with_reasoning == get_settings().config.model and model != get_settings().config.model and model == \
+                get_settings().config.fallback_models[0]:
+            # we are using a fallback model (should not happen on regular conditions)
+            get_logger().warning(f"Using the same model for self-reflection as the one used for suggestions")
+            model_reflect_with_reasoning = model
         response_reflect = await self.self_reflect_on_suggestions(data["code_suggestions"],
-                                                                  patches_diff, model=model_reflection)
+                                                                  patches_diff, model=model_reflect_with_reasoning)
         if response_reflect:
             await self.analyze_self_reflection_response(data, response_reflect)
         else:
@@ -675,7 +680,7 @@ class PRCodeSuggestions:
             get_logger().error(f"Error removing line numbers from patches_diff_list, error: {e}")
             return patches_diff_list
 
-    async def _prepare_prediction_extended(self, model: str) -> dict:
+    async def prepare_prediction_main(self, model: str) -> dict:
         # get PR diff
         if get_settings().pr_code_suggestions.decouple_hunks:
             self.patches_diff_list = get_pr_multi_diffs(self.git_provider,