Refactor pr_code_suggestions logic and update prompts for clarity and consistency

pr_agent/settings/pr_code_suggestions_prompts.toml

@@ -40,7 +40,7 @@ Specific instructions for generating code suggestions:
 - Suggestions should not repeat code already present in the '__new hunk__' sections.
 - Provide the exact line numbers range (inclusive) for each suggestion. Use the line numbers from the '__new hunk__' sections.
 - When quoting variables or names from the code, use backticks (`) instead of single quote (').
-- Be aware that you are reviewing a PR code diff, and that the entire codebase is not available for you as context. Hence, don't suggest changes that require knowledge of the entire codebase.
+- Take into account that you are reviewing a PR code diff, and that the entire codebase is not available for you as context. Hence, avoid suggestions that might conflict with unseen parts of the codebase."
 
 
 {%- if extra_instructions %}
@@ -59,14 +59,9 @@ class CodeSuggestion(BaseModel):
     relevant_file: str = Field(description="the relevant file full path")
     language: str = Field(description="the code language of the relevant file")
     suggestion_content: str = Field(description="an actionable suggestion for meaningfully improving the new code introduced in the PR")
-{%- if not commitable_code_suggestions_mode %}
     existing_code: str = Field(description="a short code snippet from a '__new hunk__' section to illustrate the relevant existing code. Don't show the line numbers.")
     improved_code: str = Field(description="a short code snippet to illustrate the improved code, after applying the suggestion.")
     one_sentence_summary:str = Field(description="a short summary of the suggestion action, in a single sentence. Focus on the 'what'. Be general, and avoid method or variable names.")
-{%- else %}
-    existing_code: str = Field(description="a code snippet, demonstrating the relevant code lines from a '__new hunk__' section. It must be contiguous, correctly formatted and indented, and without line numbers. Use abbreviations if needed")
-    improved_code: str = Field(description="If relevant, a new code snippet, that can be used to replace the relevant lines in '__new hunk__' code. Replacement suggestions should be complete, correctly formatted and indented, and without line numbers". Retrun '...' if not applicable")
-{%- endif %}
     relevant_lines_start: int = Field(description="The relevant line number, from a '__new hunk__' section, where the suggestion starts (inclusive). Should be derived from the hunk line numbers, and correspond to the 'existing code' snippet above")
     relevant_lines_end: int = Field(description="The relevant line number, from a '__new hunk__' section, where the suggestion ends (inclusive). Should be derived from the hunk line numbers, and correspond to the 'existing code' snippet above")
     label: str = Field(description="a single label for the suggestion, to help the user understand the suggestion type. For example: 'security', 'possible bug', 'possible issue', 'performance', 'enhancement', 'best practice', 'maintainability', etc. Other labels are also allowed")
@@ -85,7 +80,6 @@ code_suggestions:
     python
   suggestion_content: |
     ...
-{%- if not commitable_code_suggestions_mode %}
   existing_code: |
     ...
   improved_code: |
@@ -94,14 +88,6 @@ code_suggestions:
     ...
   relevant_lines_start: 12
   relevant_lines_end: 13
-{%- else %}
-  existing_code: |
-    ...
-  relevant_lines_start: 12
-  relevant_lines_end: 13
-  improved_code: |
-    ...
-{%- endif %}
   label: |
     ...
 ```

pr_agent/settings/pr_code_suggestions_reflect_prompts.toml

@@ -46,9 +46,7 @@ __old hunk__
 The output must be a YAML object equivalent to type $PRCodeSuggestionsFeedback, according to the following Pydantic definitions:
 =====
 class CodeSuggestionFeedback(BaseModel):
-{%- if not commitable_code_suggestions_mode %}
     suggestion_summary: str = Field(description="repeated from the input")
-{%- endif %}
     relevant_file: str = Field(description="repeated from the input")
     suggestion_score: int = Field(description="The actual output - the score of the suggestion, from 0 to 10. Give 0 if the suggestion is plain wrong. Otherwise, give a score from 1 to 10 (inclusive), where 1 is the lowest and 10 is the highest.")
     why: str = Field(description="Short and concise explanation of why the suggestion received the score (one to two sentences).")
@@ -61,13 +59,9 @@ class PRCodeSuggestionsFeedback(BaseModel):
 Example output:
 ```yaml
 code_suggestions:
-{%- if not commitable_code_suggestions_mode %}
 - suggestion_content: |
     Use a more descriptive variable name here
   relevant_file: "src/file1.py"
-{%- else %}
-- relevant_file: "src/file1.py"
-{%- endif %}
   suggestion_score: 6
   why: |
     The variable name 't' is not descriptive enough

pr_agent/tools/pr_code_suggestions.py

@@ -57,7 +57,6 @@ class PRCodeSuggestions:
             "language": self.main_language,
             "diff": "",  # empty diff for initial calculation
             "num_code_suggestions": num_code_suggestions,
-            "commitable_code_suggestions_mode": get_settings().pr_code_suggestions.commitable_code_suggestions,
             "extra_instructions": get_settings().pr_code_suggestions.extra_instructions,
             "commit_messages_str": self.git_provider.get_commit_messages(),
         }
@@ -106,7 +105,8 @@ class PRCodeSuggestions:
 
             if get_settings().config.publish_output:
                 self.git_provider.remove_initial_comment()
-                if (not get_settings().pr_code_suggestions.commitable_code_suggestions) and self.git_provider.is_supported("gfm_markdown"):
+                if ((not get_settings().pr_code_suggestions.commitable_code_suggestions) and
+                        self.git_provider.is_supported("gfm_markdown")):
 
                     # generate summarized suggestions
                     pr_body = self.generate_summarized_suggestions(data)
@@ -226,8 +226,8 @@ class PRCodeSuggestions:
         one_sentence_summary_list = []
         for i, suggestion in enumerate(data['code_suggestions']):
             try:
-                if not get_settings().pr_code_suggestions.commitable_code_suggestions:
+                if (not suggestion or 'one_sentence_summary' not in suggestion or
-                    if not suggestion or 'one_sentence_summary' not in suggestion or 'label' not in suggestion or 'relevant_file' not in suggestion:
+                        'label' not in suggestion or 'relevant_file' not in suggestion):
                     get_logger().debug(f"Skipping suggestion {i + 1}, because it is invalid: {suggestion}")
                     continue
 
@@ -241,10 +241,13 @@ class PRCodeSuggestions:
 
                 if ('existing_code' in suggestion) and ('improved_code' in suggestion):
                     if suggestion['existing_code'] == suggestion['improved_code']:
-                        get_logger().debug(f"skipping improved suggestion {i + 1}, because equal to existing code: {suggestion['existing_code']}")
+                        get_logger().debug(
+                            f"edited improved suggestion {i + 1}, because equal to existing code: {suggestion['existing_code']}")
+                        if get_settings().pr_code_suggestions.commitable_code_suggestions:
+                            suggestion['improved_code'] = "" # we need 'existing_code' to locate the code in the PR
+                        else:
                             suggestion['existing_code'] = ""
                     suggestion = self._truncate_if_needed(suggestion)
-                    if not get_settings().pr_code_suggestions.commitable_code_suggestions:
                     one_sentence_summary_list.append(suggestion['one_sentence_summary'])
                     suggestion_list.append(suggestion)
                 else:
@@ -278,6 +281,9 @@ class PRCodeSuggestions:
                 if new_code_snippet:
                     new_code_snippet = self.dedent_code(relevant_file, relevant_lines_start, new_code_snippet)
 
+                if d.get('score'):
+                    body = f"**Suggestion:** {content} [{label}, importance: {d.get('score')}]\n```suggestion\n" + new_code_snippet + "\n```"
+                else:
                     body = f"**Suggestion:** {content} [{label}]\n```suggestion\n" + new_code_snippet + "\n```"
                 code_suggestions.append({'body': body, 'relevant_file': relevant_file,
                                              'relevant_lines_start': relevant_lines_start,
@@ -327,7 +333,8 @@ class PRCodeSuggestions:
         self.patches_diff_list = get_pr_multi_diffs(self.git_provider, self.token_handler, model,
                                                     max_calls=get_settings().pr_code_suggestions.max_number_of_calls)
         if self.patches_diff_list:
-            get_logger().debug(f"PR diff", artifact=self.patches_diff_list)
+            get_logger().info(f"Number of PR chunk calls: {len(self.patches_diff_list)}")
+            get_logger().debug(f"PR diff:", artifact=self.patches_diff_list)
 
             # parallelize calls to AI:
             if get_settings().pr_code_suggestions.parallel_calls:
@@ -342,10 +349,10 @@ class PRCodeSuggestions:
 
 
             data = {"code_suggestions": []}
-            for i, predictions in enumerate(prediction_list):
+            for predictions in enumerate(prediction_list):
-                if "code_suggestions" in predictions:
+                if "code_suggestions" in enumerate(predictions):
                     score_threshold = max(1,get_settings().pr_code_suggestions.suggestions_score_threshold)
-                    for prediction in predictions["code_suggestions"]:
+                    for i, prediction in predictions["code_suggestions"]:
                         try:
                             if get_settings().pr_code_suggestions.self_reflect_on_suggestions:
                                 score = int(prediction["score"])
@@ -547,8 +554,7 @@ class PRCodeSuggestions:
             variables = {'suggestion_list': suggestion_list,
                          'suggestion_str': suggestion_str,
                          "diff": patches_diff,
-                         'num_code_suggestions': len(suggestion_list),
+                         'num_code_suggestions': len(suggestion_list)}
-                         'commitable_code_suggestions_mode': get_settings().pr_code_suggestions.commitable_code_suggestions,}
             model = get_settings().config.model
             environment = Environment(undefined=StrictUndefined)
             system_prompt_reflect = environment.from_string(get_settings().pr_code_suggestions_reflect_prompt.system).render(