Merge pull request qodo-ai#509 from Codium-ai/trlabeling_files_extended

Enhancement of PR Description and Labeling Features

pr_agent/algo/utils.py

@@ -343,7 +343,7 @@ def set_custom_labels(variables):
     labels = get_settings().custom_labels
     if not labels:
         # set default labels
-        labels = ['Bug fix', 'Tests', 'Bug fix with tests', 'Refactoring', 'Enhancement', 'Documentation', 'Other']
+        labels = ['Bug fix', 'Tests', 'Bug fix with tests', 'Enhancement', 'Documentation', 'Other']
         labels_list = "\n      - ".join(labels) if labels else ""
         labels_list = f"      - {labels_list}" if labels_list else ""
         variables["custom_labels"] = labels_list
@@ -367,7 +367,7 @@ def get_user_labels(current_labels: List[str] = None):
             current_labels = []
         user_labels = []
         for label in current_labels:
-            if label.lower() in ['bug fix', 'tests', 'refactoring', 'enhancement', 'documentation', 'other']:
+            if label.lower() in ['bug fix', 'tests', 'enhancement', 'documentation', 'other']:
                 continue
             if get_settings().config.enable_custom_labels:
                 if label in get_settings().custom_labels:

pr_agent/git_providers/bitbucket_provider.py

@@ -229,7 +229,10 @@ def publish_inline_comment(self, comment: str, from_line: int, file: str):
         return response
 
     def get_line_link(self, relevant_file: str, relevant_line_start: int, relevant_line_end: int = None) -> str:
-        link = f"{self.pr_url}/#L{relevant_file}T{relevant_line_start}"
+        if relevant_line_start == -1:
+            link = f"{self.pr_url}/#L{relevant_file}"
+        else:
+            link = f"{self.pr_url}/#L{relevant_file}T{relevant_line_start}"
         return link
 
     def generate_link_to_relevant_line_number(self, suggestion) -> str:

pr_agent/git_providers/git_provider.py

@@ -26,6 +26,8 @@ class FilePatchInfo:
     tokens: int = -1
     edit_type: EDIT_TYPE = EDIT_TYPE.UNKNOWN
     old_filename: str = None
+    num_plus_lines: int = -1
+    num_minus_lines: int = -1
 
 
 class GitProvider(ABC):

pr_agent/git_providers/github_provider.py

@@ -143,8 +143,15 @@ def get_diff_files(self) -> list[FilePatchInfo]:
                 else:
                     get_logger().error(f"Unknown edit type: {file.status}")
                     edit_type = EDIT_TYPE.UNKNOWN
+
+                # count number of lines added and removed
+                patch_lines = patch.splitlines(keepends=True)
+                num_plus_lines = len([line for line in patch_lines if line.startswith('+')])
+                num_minus_lines = len([line for line in patch_lines if line.startswith('-')])
                 file_patch_canonical_structure = FilePatchInfo(original_file_content_str, new_file_content_str, patch,
-                                                               file.filename, edit_type=edit_type)
+                                                               file.filename, edit_type=edit_type,
+                                                               num_plus_lines=num_plus_lines,
+                                                               num_minus_lines=num_minus_lines,)
                 diff_files.append(file_patch_canonical_structure)
 
             self.diff_files = diff_files
@@ -442,7 +449,7 @@ def _get_pr_file_content(self, file: FilePatchInfo, sha: str) -> str:
     def publish_labels(self, pr_types):
         try:
             label_color_map = {"Bug fix": "1d76db", "Tests": "e99695", "Bug fix with tests": "c5def5",
-                               "Refactoring": "bfdadc", "Enhancement": "bfd4f2", "Documentation": "d4c5f9",
+                               "Enhancement": "bfd4f2", "Documentation": "d4c5f9",
                                "Other": "d1bcf9"}
             post_parameters = []
             for p in pr_types:
@@ -506,7 +513,9 @@ def generate_link_to_relevant_line_number(self, suggestion) -> str:
 
     def get_line_link(self, relevant_file: str, relevant_line_start: int, relevant_line_end: int = None) -> str:
         sha_file = hashlib.sha256(relevant_file.encode('utf-8')).hexdigest()
-        if relevant_line_end:
+        if relevant_line_start == -1:
+            link = f"https://github.com/{self.repo}/pull/{self.pr_num}/files#diff-{sha_file}"
+        elif relevant_line_end:
             link = f"https://github.com/{self.repo}/pull/{self.pr_num}/files#diff-{sha_file}R{relevant_line_start}-R{relevant_line_end}"
         else:
             link = f"https://github.com/{self.repo}/pull/{self.pr_num}/files#diff-{sha_file}R{relevant_line_start}"

pr_agent/git_providers/gitlab_provider.py

@@ -115,12 +115,20 @@ def get_diff_files(self) -> list[FilePatchInfo]:
                 if not patch:
                     patch = load_large_diff(filename, new_file_content_str, original_file_content_str)
 
+
+                # count number of lines added and removed
+                patch_lines = patch.splitlines(keepends=True)
+                num_plus_lines = len([line for line in patch_lines if line.startswith('+')])
+                num_minus_lines = len([line for line in patch_lines if line.startswith('-')])
                 diff_files.append(
                     FilePatchInfo(original_file_content_str, new_file_content_str,
                                   patch=patch,
                                   filename=filename,
                                   edit_type=edit_type,
-                                  old_filename=None if diff['old_path'] == diff['new_path'] else diff['old_path']))
+                                  old_filename=None if diff['old_path'] == diff['new_path'] else diff['old_path'],
+                                  num_plus_lines=num_plus_lines,
+                                  num_minus_lines=num_minus_lines, ))
+
         self.diff_files = diff_files
         return diff_files
 
@@ -424,7 +432,9 @@ def get_pr_id(self):
             return ""
 
     def get_line_link(self, relevant_file: str, relevant_line_start: int, relevant_line_end: int = None) -> str:
-        if relevant_line_end:
+        if relevant_line_start == -1:
+            link = f"https://gitlab.com/codiumai/pr-agent/-/blob/{self.mr.source_branch}/{relevant_file}?ref_type=heads"
+        elif relevant_line_end:
             link = f"https://gitlab.com/codiumai/pr-agent/-/blob/{self.mr.source_branch}/{relevant_file}?ref_type=heads#L{relevant_line_start}-L{relevant_line_end}"
         else:
             link = f"https://gitlab.com/codiumai/pr-agent/-/blob/{self.mr.source_branch}/{relevant_file}?ref_type=heads#L{relevant_line_start}"

pr_agent/servers/help.py

@@ -1,19 +1,19 @@
-commands_text = "> **/review**: Request a review of your Pull Request.\n" \
-                "> **/describe**: Update the PR title and description based on the contents of the PR.\n" \
-                "> **/improve [--extended]**: Suggest code improvements. Extended mode provides a higher quality feedback.\n" \
-                "> **/ask \\<QUESTION\\>**: Ask a question about the PR.\n" \
-                "> **/update_changelog**: Update the changelog based on the PR's contents.\n" \
-                "> **/add_docs**: Generate docstring for new components introduced in the PR.\n" \
-                "> **/generate_labels**: Generate labels for the PR based on the PR's contents.\n" \
+commands_text = "> **/review**: Request a review of your Pull Request.   \n" \
+                "> **/describe**: Update the PR title and description based on the contents of the PR.   \n" \
+                "> **/improve [--extended]**: Suggest code improvements. Extended mode provides a higher quality feedback.   \n" \
+                "> **/ask \\<QUESTION\\>**: Ask a question about the PR.   \n" \
+                "> **/update_changelog**: Update the changelog based on the PR's contents.   \n" \
+                "> **/add_docs**: Generate docstring for new components introduced in the PR.   \n" \
+                "> **/generate_labels**: Generate labels for the PR based on the PR's contents.   \n" \
                 "> see the [tools guide](https://github.com/Codium-ai/pr-agent/blob/main/docs/TOOLS_GUIDE.md) for more details.\n\n" \
-                ">To edit any configuration parameter from the [configuration.toml](https://github.com/Codium-ai/pr-agent/blob/main/pr_agent/settings/configuration.toml), add --config_path=new_value.\n" \
-                ">For example: /review --pr_reviewer.extra_instructions=\"focus on the file: ...\" \n" \
-                ">To list the possible configuration parameters, add a **/config** comment.\n" \
+                ">To edit any configuration parameter from the [configuration.toml](https://github.com/Codium-ai/pr-agent/blob/main/pr_agent/settings/configuration.toml), add --config_path=new_value.  \n" \
+                ">For example: /review --pr_reviewer.extra_instructions=\"focus on the file: ...\"    \n" \
+                ">To list the possible configuration parameters, add a **/config** comment.   \n" \
 
 
 def bot_help_text(user: str):
-    return f"> Tag me in a comment '@{user}' and add one of the following commands:\n" + commands_text
+    return f"> Tag me in a comment '@{user}' and add one of the following commands:  \n" + commands_text
 
 
-actions_help_text = "> To invoke the PR-Agent, add a comment using one of the following commands:\n" + \
+actions_help_text = "> To invoke the PR-Agent, add a comment using one of the following commands:  \n" + \
                     commands_text

pr_agent/settings/configuration.toml

@@ -46,13 +46,16 @@ keep_original_user_title=false
 use_bullet_points=true
 extra_instructions = ""
 enable_pr_type=true
+enable_file_walkthrough=false
+enable_semantic_files_types=true
 final_update_message = true
 
+
 # markers
 use_description_markers=false
 include_generated_by_header=true
 
-#custom_labels = ['Bug fix', 'Tests', 'Bug fix with tests', 'Refactoring', 'Enhancement', 'Documentation', 'Other']
+#custom_labels = ['Bug fix', 'Tests', 'Bug fix with tests', 'Enhancement', 'Documentation', 'Other']
 
 [pr_questions] # /ask #
 

pr_agent/settings/custom_labels.toml

@@ -8,10 +8,8 @@ enable_custom_labels=false
 #description = """Adds or modifies tests"""
 #[custom_labels."Bug fix with tests"]
 #description = """Fixes a bug in the code and adds or modifies tests"""
-#[custom_labels."Refactoring"]
-#description = """Code refactoring without changing functionality"""
 #[custom_labels."Enhancement"]
-#description = """Adds new features or functionality"""
+#description = """Adds new features or modifies existing ones"""
 #[custom_labels."Documentation"]
 #description = """Adds or modifies documentation"""
 #[custom_labels."Other"]

pr_agent/settings/pr_custom_labels.toml

@@ -24,7 +24,6 @@ The output must be a YAML object equivalent to type $Labels, according to the fo
 class Label(str, Enum):
     bug_fix = "Bug fix"
     tests = "Tests"
-    refactoring = "Refactoring"
     enhancement = "Enhancement"
     documentation = "Documentation"
     other = "Other"

pr_agent/settings/pr_description_prompts.toml

@@ -20,7 +20,6 @@ The output must be a YAML object equivalent to type $PRDescription, according to
 class PRType(str, Enum):
     bug_fix = "Bug fix"
     tests = "Tests"
-    refactoring = "Refactoring"
     enhancement = "Enhancement"
     documentation = "Documentation"
     other = "Other"
@@ -31,18 +30,32 @@ class PRType(str, Enum):
 
 {%- endif %}
 
+{%- if enable_file_walkthrough %}
 class FileWalkthrough(BaseModel):
     filename: str = Field(description="the relevant file full path")
-    changes_in_file: str = Field(description="minimal and concise description of the changes in the relevant file")
+    changes_in_file: str = Field(description="minimal and concise summary of the changes in the relevant file")
+{%- endif %}
+
+{%- if enable_semantic_files_types %}
+Class FileDescription(BaseModel):
+    filename: str = Field(description="the relevant file full path")
+    changes_summary: str = Field(description="minimal and concise summary of the changes in the relevant file")
+    label: str = Field(description="a single semantic label that represents a type of code changes that occurred in the File. Possible values (partial list): 'bug fix', 'tests', 'enhancement', 'documentation', 'error handling', 'configuration changes', 'dependencies', 'formatting', 'miscellaneous', ...")
+{%- endif %}
 
 Class PRDescription(BaseModel):
     title: str = Field(description="an informative title for the PR, describing its main theme")
-    type: List[PRType] = Field(description="one or more types that describe the PR type. . Return the label value, not the name.")
+    type: List[PRType] = Field(description="one or more types that describe the PR type. Return the label value, not the name.")
     description: str = Field(description="an informative and concise description of the PR. {%- if use_bullet_points %} Use bullet points.{% endif %}")
 {%- if enable_custom_labels %}
     labels: List[Label] = Field(min_items=0, description="custom labels that describe the PR. Return the label value, not the name.")
 {%- endif %}
+{%- if enable_file_walkthrough %}
     main_files_walkthrough: List[FileWalkthrough] = Field(max_items=10)
+{%- endif %}
+{%- if enable_semantic_files_types %}
+    pr_files[List[FileDescription]] = Field(max_items=15")
+{%- endif %}
 =====
 
 
@@ -61,9 +74,21 @@ labels:
 {%- endif %}
 description: |-
   ...
+{%- if enable_file_walkthrough %}
 main_files_walkthrough:
 - ...
 - ...
+{%- endif %}
+{%- if enable_semantic_files_types %}
+pr_files:
+- filename: |
+    ...
+  changes_summary: |
+    ...
+  label: |
+    ...
+...
+{%- endif %}
 ```
 
 Answer should be a valid YAML, and nothing else. Each YAML output MUST be after a newline, with proper indent, and block scalar indicator ('|-')

pr_agent/settings/pr_reviewer_prompts.toml

@@ -57,7 +57,6 @@ PR Analysis:
     enum:
       - Bug fix
       - Tests
-      - Refactoring
       - Enhancement
       - Documentation
       - Other