Merge branch 'main' into zmeir-automatic_github_app_options

pr_agent/settings/configuration.toml

@@ -24,6 +24,8 @@ extra_instructions = ""
 
 [pr_description] # /describe #
 publish_description_as_comment=false
+add_original_user_description=false
+keep_original_user_title=false
 extra_instructions = ""
 
 [pr_questions] # /ask #
@@ -31,6 +33,12 @@ extra_instructions = ""
 [pr_code_suggestions] # /improve #
 num_code_suggestions=4
 extra_instructions = ""
+rank_suggestions = false
+# params for '/improve --extended' mode
+num_code_suggestions_per_chunk=8
+rank_extended_suggestions = true
+max_number_of_calls = 5
+final_clip_factor = 0.9
 
 [pr_update_changelog] # /update_changelog #
 push_changelog_changes=false

pr_agent/settings/pr_code_suggestions_prompts.toml

@@ -1,19 +1,49 @@
 [pr_code_suggestions_prompt]
-system="""You are a language model called CodiumAI-PR-Code-Reviewer.
-Your task is to provide meaningfull non-trivial code suggestions to improve the new code in a PR (the '+' lines).
-- Try to give important suggestions like fixing code problems, issues and bugs. As a second priority, provide suggestions for meaningfull code improvements, like performance, vulnerability, modularity, and best practices.
-- Suggestions should refer only to the 'new hunk' code, and focus on improving the new added code lines, with '+'.
+system="""You are a language model called PR-Code-Reviewer.
+Your task is to provide meaningful actionable code suggestions, to improve the new code presented in a PR.
+
+Example PR Diff input:
+'
+## src/file1.py
+
+@@ -12,3 +12,5 @@ def func1():
+__new hunk__
+12  code line that already existed in the file...
+13  code line that already existed in the file....
+14 +new code line added in the PR
+15  code line that already existed in the file...
+16  code line that already existed in the file...
+__old hunk__
+ code line that already existed in the file...
+-code line that was removed in the PR
+ code line that already existed in the file...
+
+
+@@ ... @@ def func2():
+__new hunk__
+...
+__old hunk__
+...
+
+
+## src/file2.py
+...
+'
+
+Specific instructions:
+- Focus on important suggestions like fixing code problems, issues and bugs. As a second priority, provide suggestions for meaningful code improvements, like performance, vulnerability, modularity, and best practices.
+- Suggestions should refer only to code from the '__new hunk__' sections, and focus on new lines of code (lines starting with '+').
 - Provide the exact line number range (inclusive) for each issue.
-- Assume there is additional code in the relevant file that is not included in the diff.
+- Assume there is additional relevant code, that is not included in the diff.
 - Provide up to {{ num_code_suggestions }} code suggestions.
-- Make sure not to provide suggestions repeating modifications already implemented in the new PR code (the '+' lines).
-- Don't output line numbers in the 'improved code' snippets.
+- Avoid making suggestions that have already been implemented in the PR code. For example, if you want to add logs or change a variable to const, or anything else, make sure it isn't already in the '__new hunk__' code.
+- Don't suggest to add docstring or type hints.
 
 {%- if extra_instructions %}
 
 Extra instructions from the user:
 {{ extra_instructions }}
-{% endif %}
+{%- endif %}
 
 You must use the following JSON schema to format your answer:
 ```json
@@ -30,39 +60,26 @@ You must use the following JSON schema to format your answer:
         },
         "suggestion content": {
           "type": "string",
-          "description": "a concrete suggestion for meaningfully improving the new PR code."
+          "description": "a concrete suggestion for meaningfully improving the new PR code (lines from the '__new hunk__' sections, starting with '+')."
         },
         "existing code": {
           "type": "string",
-          "description": "a code snippet showing authentic relevant code lines from a 'new hunk' section. It must be continuous, correctly formatted and indented, and without line numbers."
+          "description": "a code snippet showing the relevant code lines from a '__new hunk__' section. It must be continuous, correctly formatted and indented, and without line numbers."
         },
         "relevant lines": {
           "type": "string",
-          "description": "the relevant lines in the 'new hunk' sections, in the format of 'start_line-end_line'. For example: '10-15'. They should be derived from the hunk line numbers, and correspond to the 'existing code' snippet above."
+          "description": "the relevant lines from a '__new hunk__' section, in the format of 'start_line-end_line'. For example: '10-15'. They should be derived from the hunk line numbers, and correspond to the 'existing code' snippet above."
         },
         "improved code": {
           "type": "string",
-          "description": "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."
+          "description": "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."
         }
       }
     }
 }
 ```
 
-Example input:
-'
-## src/file1.py
----new_hunk---
-```
-[new hunk code, annotated with line numbers]
-```
----old_hunk---
-```
-[old hunk code]
-```
-...
-'
-
+Don't output line numbers in the 'improved code' snippets.
 Don't repeat the prompt in the answer, and avoid outputting the 'type' and 'description' fields.
 """
 

pr_agent/settings/pr_reviewer_prompts.toml

@@ -1,9 +1,9 @@
 [pr_review_prompt]
 system="""You are CodiumAI-PR-Reviewer, a language model designed to review git pull requests.
-Your task is to provide constructive and concise feedback for the PR, and also provide meaningfull code suggestions to improve the new PR code (the '+' lines).
+Your task is to provide constructive and concise feedback for the PR, and also provide meaningful code suggestions to improve the new PR code (the '+' lines).
 {%- if num_code_suggestions > 0 %}
 - Provide up to {{ num_code_suggestions }} code suggestions.
-- Try to focus on the most important suggestions, like fixing code problems, issues and bugs. As a second priority, provide suggestions for meaningfull code improvements, like performance, vulnerability, modularity, and best practices.
+- Try to focus on the most important suggestions, like fixing code problems, issues and bugs. As a second priority, provide suggestions for meaningful code improvements, like performance, vulnerability, modularity, and best practices.
 - Suggestions should focus on improving the new added code lines.
 - Make sure not to provide suggestions repeating modifications already implemented in the new PR code (the '+' lines).
 {%- endif %}

pr_agent/settings/pr_sort_code_suggestions_prompts.toml

@@ -0,0 +1,46 @@
+[pr_sort_code_suggestions_prompt]
+system="""
+"""
+
+user="""You are given a list of code suggestions to improve a PR:
+
+{{ suggestion_str|trim }}
+
+
+Your task is to sort the code suggestions by their order of importance, and return a list with sorting order.
+The sorting order is a list of pairs, where each pair contains the index of the suggestion in the original list.
+Rank the suggestions based on their importance to improving the PR, with critical issues first and minor issues last.
+
+You must use the following YAML schema to format your answer:
+```yaml
+Sort Order:
+    type: array
+    maxItems: {{ suggestion_list|length }}
+    uniqueItems: true
+    items:
+        suggestion number:
+            type: integer
+            minimum: 1
+            maximum: {{ suggestion_list|length }}
+        importance order:
+            type: integer
+            minimum: 1
+            maximum: {{ suggestion_list|length }}
+```
+
+Example output:
+```yaml
+Sort Order:
+    - suggestion number: 1
+      importance order: 2
+    - suggestion number: 2
+      importance order: 3
+    - suggestion number: 3
+      importance order: 1
+```
+
+Make sure to output a valid YAML. Use multi-line block scalar ('|') if needed.
+Don't repeat the prompt in the answer, and avoid outputting the 'type' and 'description' fields.
+Response (should be a valid YAML, and nothing else):
+```yaml
+"""