openai version

Add publish_output_progress config support to AzureDevOps, BitBucket and Gitlab providers

README.md

@@ -43,14 +43,22 @@ Qode Merge PR-Agent aims to help efficiently review and handle pull requests, by
 
 ## News and Updates
 
-### November 7, 2024
+### December 2, 2024
 
-Added new option: `--pr_code_suggestions.focus_only_on_problems=true`
+Open-source repositories can now freely use Qodo Merge Pro, and enjoy easy one-click installation using our dedicated [app](https://github.com/apps/qodo-merge-pro-for-open-source).
 
-When enabled, this option reduces the number of code suggestions and categorizes them into just two groups: "Possible Issues" and "General". The suggestions will focus primarily on identifying and fixing code problems, rather than style considerations like best practices, maintainability, or readability.
+<kbd><img src="https://github.com/user-attachments/assets/b0838724-87b9-43b0-ab62-73739a3a855c" width="512"></kbd>
 
-This mode is ideal for developers who want to concentrate specifically on finding and fixing potential bugs in their pull request code.
 
+### November 18, 2024
+
+A new mode was enabled by default for code suggestions - `--pr_code_suggestions.focus_only_on_problems=true`:
+
+- This option reduces the number of code suggestions received
+- The suggestions will focus more on identifying and fixing code problems, rather than style considerations like best practices, maintainability, or readability.
+- The suggestions will be categorized into just two groups: "Possible Issues" and "General".
+
+Still, if you prefer the previous mode, you can set `--pr_code_suggestions.focus_only_on_problems=false` in the [configuration file](https://qodo-merge-docs.qodo.ai/usage-guide/configuration_options/).
 
 **Example results:**
 
@@ -68,51 +76,6 @@ Focused mode
 Qodo Merge PR Agent will now leverage context from Jira or GitHub tickets to enhance the PR Feedback. Read more about this feature 
 [here](https://qodo-merge-docs.qodo.ai/core-abilities/fetching_ticket_context/)
 
-### November 3, 2024
-
-Meaningful improvement to the quality of code suggestions by separating the code suggestion generation from [line number detection](https://github.com/Codium-ai/pr-agent/pull/1338)
-
-<kbd>![image](https://github.com/user-attachments/assets/093c185c-31ca-47a1-a4fe-be7d9335ea66)</kbd>
-
-
-### October 27, 2024
-
-Qodo Merge PR Agent will now automatically document accepted code suggestions in a dedicated wiki page (`.pr_agent_accepted_suggestions`), enabling users to track historical changes, assess the tool's effectiveness, and learn from previously implemented recommendations in the repository.
-
-This dedicated wiki page will also serve as a foundation for future AI model improvements, allowing it to learn from historically implemented suggestions and generate more targeted, contextually relevant recommendations.
-Read more about this novel feature [here](https://qodo-merge-docs.qodo.ai/tools/improve/#suggestion-tracking).
-
-<kbd><img href="https://qodo.ai/images/pr_agent/pr_agent_accepted_suggestions1.png" src="https://qodo.ai/images/pr_agent/pr_agent_accepted_suggestions1.png" width="768"></kbd>
-
-
-
-### October 21, 2024
-**Disable publishing labels by default:**
-
-The default setting for `pr_description.publish_labels` has been updated to `false`. This means that labels generated by the `/describe` tool will no longer be published, unless this configuration is explicitly set to `true`.
-
-We constantly strive to balance informative AI analysis with reducing unnecessary noise. User feedback indicated that in many cases, the original PR title alone provides sufficient information, making the generated labels (`enhancement`, `documentation`, `bug fix`, ...) redundant.
-The [`review_effort`](https://qodo-merge-docs.qodo.ai/tools/review/#configuration-options) label, generated by the `review` tool, will still be published by default, as it provides valuable information enabling reviewers to prioritize small PRs first.
-
-However, every user has different preferences. To still publish the `describe` labels, set `pr_description.publish_labels=true` in the [configuration file](https://qodo-merge-docs.qodo.ai/usage-guide/configuration_options/).
-For more tailored and relevant labeling, we recommend using the [`custom_labels 💎`](https://qodo-merge-docs.qodo.ai/tools/custom_labels/) tool, that allows generating labels specific to your project's needs.
-
-<kbd>![image](https://github.com/user-attachments/assets/8f38d222-53b1-4742-b2ec-7ea0a30c9076)</kbd>
-
-→
-
-<kbd>![image](https://github.com/user-attachments/assets/8285bd90-0dda-4c7e-9237-bbfde5e21880)</kbd>
-
-
-
-### October 14, 2024
-Improved support for GitHub enterprise server with [GitHub Actions](https://qodo-merge-docs.qodo.ai/installation/github/#action-for-github-enterprise-server)
-
-### October 10, 2024
-New ability for the `review` tool - **ticket compliance feedback**. If the PR contains a ticket number, PR-Agent will check if the PR code actually [complies](https://github.com/Codium-ai/pr-agent/pull/1279#issuecomment-2404042130) with the ticket requirements.
-
-<kbd><img src="https://github.com/user-attachments/assets/4a2a728b-5f47-40fa-80cc-16efd296938c" width="768"></kbd>
-
 
 ## Overview
 <div style="text-align:left;">

docs/docs/installation/azure.md

@@ -51,10 +51,12 @@ stages:
 ```
 This script will run Qodo Merge on every new merge request, with the `improve`, `review`, and `describe` commands.
 Note that you need to export the `azure_devops__pat` and `OPENAI_KEY` variables in the Azure DevOps pipeline settings (Pipelines -> Library -> + Variable group):
+
 ![Qodo Merge Pro](https://codium.ai/images/pr_agent/azure_devops_pipeline_secrets.png){width=468}
 
 Make sure to give pipeline permissions to the `pr_agent` variable group.
 
+> Note that Azure Pipelines lacks support for triggering workflows from PR comments. If you find a viable solution, please contribute it to our [issue tracker](https://github.com/Codium-ai/pr-agent/issues)
 
 ## Azure DevOps from CLI
 

docs/docs/tools/improve.md

@@ -245,6 +245,32 @@ enable_global_best_practices = true
 
 Then, create a `best_practices.md` wiki file in the root of [global](https://qodo-merge-docs.qodo.ai/usage-guide/configuration_options/#global-configuration-file) configuration repository,  `pr-agent-settings`.
 
+##### Best practices for multiple languages
+For a git organization working with multiple programming languages, you can maintain a centralized global `best_practices.md` file containing language-specific guidelines. 
+When reviewing pull requests, Qodo Merge automatically identifies the programming language and applies the relevant best practices from this file.
+Structure your `best_practices.md` file using the following format:
+
+```
+# [Python]
+...
+# [Java]
+...
+# [JavaScript]
+...
+```
+
+##### Dedicated label for best practices suggestions
+Best practice suggestions are labeled as `Organization best practice` by default. 
+To customize this label, modify it in your configuration file:
+
+```toml
+[best_practices]
+organization_name = ""
+```
+
+And the label will be: `{organization_name} best practice`.
+
+
 ##### Example results
 
 ![best_practice](https://codium.ai/images/pr_agent/org_best_practice.png){width=512}
@@ -277,7 +303,7 @@ Using a combination of both can help the AI model to provide relevant and tailor
       </tr>
       <tr>
         <td><b>focus_only_on_problems</b></td>
-        <td>If set to true, suggestions will focus primarily on identifying and fixing code problems, and less on style considerations like best practices, maintainability, or readability. Default is false.</td> 
+        <td>If set to true, suggestions will focus primarily on identifying and fixing code problems, and less on style considerations like best practices, maintainability, or readability. Default is true.</td> 
       </tr>
       <tr>
         <td><b>persistent_comment</b></td>

docs/overrides/partials/integrations/analytics/custom.html

@@ -3,5 +3,5 @@
     new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0],
     j=d.createElement(s),dl=l!='dataLayer'?'&l='+l:'';j.async=true;j.src=
     'https://www.googletagmanager.com/gtm.js?id='+i+dl;f.parentNode.insertBefore(j,f);
-    })(window,document,'script','dataLayer','GTM-5C9KZBM3');</script>
+    })(window,document,'script','dataLayer','GTM-M6PJSFV');</script>
     <!-- End Google Tag Manager -->

pr_agent/algo/__init__.py

@@ -19,6 +19,7 @@ MAX_TOKENS = {
     'gpt-4o-mini': 128000,  # 128K, but may be limited by config.max_model_tokens
     'gpt-4o-mini-2024-07-18': 128000,  # 128K, but may be limited by config.max_model_tokens
     'gpt-4o-2024-08-06': 128000,  # 128K, but may be limited by config.max_model_tokens
+    'gpt-4o-2024-11-20': 128000,  # 128K, but may be limited by config.max_model_tokens
     'o1-mini': 128000,  # 128K, but may be limited by config.max_model_tokens
     'o1-mini-2024-09-12': 128000,  # 128K, but may be limited by config.max_model_tokens
     'o1-preview': 128000,  # 128K, but may be limited by config.max_model_tokens

pr_agent/algo/utils.py

@@ -173,7 +173,7 @@ def convert_to_markdown_v2(output_data: dict,
                 if is_value_no(value):
                     markdown_text += f'### {emoji} No relevant tests\n\n'
                 else:
-                    markdown_text += f"### PR contains tests\n\n"
+                    markdown_text += f"### {emoji} PR contains tests\n\n"
         elif 'ticket compliance check' in key_nice.lower():
             markdown_text = ticket_markdown_logic(emoji, markdown_text, value, gfm_supported)
         elif 'security concerns' in key_nice.lower():
@@ -224,12 +224,21 @@ def convert_to_markdown_v2(output_data: dict,
                         issue_content = issue.get('issue_content', '').strip()
                         start_line = int(str(issue.get('start_line', 0)).strip())
                         end_line = int(str(issue.get('end_line', 0)).strip())
-                        reference_link = git_provider.get_line_link(relevant_file, start_line, end_line)
+                        if git_provider:
+                            reference_link = git_provider.get_line_link(relevant_file, start_line, end_line)
+                        else:
+                            reference_link = None
 
                         if gfm_supported:
-                            issue_str = f"<a href='{reference_link}'><strong>{issue_header}</strong></a><br>{issue_content}"
+                            if reference_link is not None and len(reference_link) > 0:
+                                issue_str = f"<a href='{reference_link}'><strong>{issue_header}</strong></a><br>{issue_content}"
+                            else:
+                                issue_str = f"<strong>{issue_header}</strong><br>{issue_content}"
                         else:
-                            issue_str = f"[**{issue_header}**]({reference_link})\n\n{issue_content}\n\n"
+                            if reference_link is not None and len(reference_link) > 0:
+                                issue_str = f"[**{issue_header}**]({reference_link})\n\n{issue_content}\n\n"
+                            else:
+                                issue_str = f"**{issue_header}**\n\n{issue_content}\n\n"
                         markdown_text += f"{issue_str}\n\n"
                     except Exception as e:
                         get_logger().exception(f"Failed to process 'Recommended focus areas for review': {e}")

pr_agent/cli.py

@@ -92,4 +92,3 @@ def run(inargs=None, args=None):
 
 if __name__ == '__main__':
     run()
-    aa= "rr"

pr_agent/git_providers/azuredevops_provider.py

@@ -67,16 +67,14 @@ class AzureDevopsProvider(GitProvider):
             relevant_lines_end = suggestion['relevant_lines_end']
 
             if not relevant_lines_start or relevant_lines_start == -1:
-                if get_settings().config.verbosity_level >= 2:
+                get_logger().warning(
-                    get_logger().exception(
+                    f"Failed to publish code suggestion, relevant_lines_start is {relevant_lines_start}")
-                        f"Failed to publish code suggestion, relevant_lines_start is {relevant_lines_start}")
                 continue
 
             if relevant_lines_end < relevant_lines_start:
-                if get_settings().config.verbosity_level >= 2:
+                get_logger().warning(f"Failed to publish code suggestion, "
-                    get_logger().exception(f"Failed to publish code suggestion, "
+                                       f"relevant_lines_end is {relevant_lines_end} and "
-                                           f"relevant_lines_end is {relevant_lines_end} and "
+                                       f"relevant_lines_start is {relevant_lines_start}")
-                                           f"relevant_lines_start is {relevant_lines_start}")
                 continue
 
             if relevant_lines_end > relevant_lines_start:
@@ -95,9 +93,11 @@ class AzureDevopsProvider(GitProvider):
                     "side": "RIGHT",
                 }
             post_parameters_list.append(post_parameters)
+        if not post_parameters_list:
+            return False
 
-        try:
+        for post_parameters in post_parameters_list:
-            for post_parameters in post_parameters_list:
+            try:
                 comment = Comment(content=post_parameters["body"], comment_type=1)
                 thread = CommentThread(comments=[comment],
                                        thread_context={
@@ -117,15 +117,11 @@ class AzureDevopsProvider(GitProvider):
                     repository_id=self.repo_slug,
                     pull_request_id=self.pr_num
                 )
-                if get_settings().config.verbosity_level >= 2:
+            except Exception as e:
-                    get_logger().info(
+                get_logger().warning(f"Azure failed to publish code suggestion, error: {e}")
-                        f"Published code suggestion on {self.pr_num} at {post_parameters['path']}"
+        return True
-                    )
+
-            return True
+
-        except Exception as e:
-            if get_settings().config.verbosity_level >= 2:
-                get_logger().error(f"Failed to publish code suggestion, error: {e}")
-            return False
 
     def get_pr_description_full(self) -> str:
         return self.pr.description
@@ -382,6 +378,9 @@ class AzureDevopsProvider(GitProvider):
             return []
 
     def publish_comment(self, pr_comment: str, is_temporary: bool = False, thread_context=None):
+        if is_temporary and not get_settings().config.publish_output_progress:
+            get_logger().debug(f"Skipping publish_comment for temporary comment: {pr_comment}")
+            return None
         comment = Comment(content=pr_comment)
         thread = CommentThread(comments=[comment], thread_context=thread_context, status=5)
         thread_response = self.azure_devops_client.create_thread(

pr_agent/git_providers/bitbucket_provider.py

@@ -1,4 +1,6 @@
+import difflib
 import json
+import re
 from typing import Optional, Tuple
 from urllib.parse import urlparse
 
@@ -72,24 +74,38 @@ class BitbucketProvider(GitProvider):
         post_parameters_list = []
         for suggestion in code_suggestions:
             body = suggestion["body"]
+            original_suggestion = suggestion.get('original_suggestion', None)  # needed for diff code
+            if original_suggestion:
+                try:
+                    existing_code = original_suggestion['existing_code'].rstrip() + "\n"
+                    improved_code = original_suggestion['improved_code'].rstrip() + "\n"
+                    diff = difflib.unified_diff(existing_code.split('\n'),
+                                                improved_code.split('\n'), n=999)
+                    patch_orig = "\n".join(diff)
+                    patch = "\n".join(patch_orig.splitlines()[5:]).strip('\n')
+                    diff_code = f"\n\n```diff\n{patch.rstrip()}\n```"
+                    # replace ```suggestion ... ``` with diff_code, using regex:
+                    body = re.sub(r'```suggestion.*?```', diff_code, body, flags=re.DOTALL)
+                except Exception as e:
+                    get_logger().exception(f"Bitbucket failed to get diff code for publishing, error: {e}")
+                    continue
+
             relevant_file = suggestion["relevant_file"]
             relevant_lines_start = suggestion["relevant_lines_start"]
             relevant_lines_end = suggestion["relevant_lines_end"]
 
             if not relevant_lines_start or relevant_lines_start == -1:
-                if get_settings().config.verbosity_level >= 2:
+                get_logger().exception(
-                    get_logger().exception(
+                    f"Failed to publish code suggestion, relevant_lines_start is {relevant_lines_start}"
-                        f"Failed to publish code suggestion, relevant_lines_start is {relevant_lines_start}"
+                )
-                    )
                 continue
 
             if relevant_lines_end < relevant_lines_start:
-                if get_settings().config.verbosity_level >= 2:
+                get_logger().exception(
-                    get_logger().exception(
+                    f"Failed to publish code suggestion, "
-                        f"Failed to publish code suggestion, "
+                    f"relevant_lines_end is {relevant_lines_end} and "
-                        f"relevant_lines_end is {relevant_lines_end} and "
+                    f"relevant_lines_start is {relevant_lines_start}"
-                        f"relevant_lines_start is {relevant_lines_start}"
+                )
-                    )
                 continue
 
             if relevant_lines_end > relevant_lines_start:
@@ -113,8 +129,7 @@ class BitbucketProvider(GitProvider):
             self.publish_inline_comments(post_parameters_list)
             return True
         except Exception as e:
-            if get_settings().config.verbosity_level >= 2:
+            get_logger().error(f"Bitbucket failed to publish code suggestion, error: {e}")
-                get_logger().error(f"Failed to publish code suggestion, error: {e}")
             return False
 
     def publish_file_comments(self, file_comments: list) -> bool:
@@ -122,7 +137,7 @@ class BitbucketProvider(GitProvider):
 
     def is_supported(self, capability: str) -> bool:
         if capability in ['get_issue_comments', 'publish_inline_comments', 'get_labels', 'gfm_markdown',
-                          'publish_file_comments']:
+                            'publish_file_comments']:
             return False
         return True
 
@@ -310,6 +325,9 @@ class BitbucketProvider(GitProvider):
         self.publish_comment(pr_comment)
 
     def publish_comment(self, pr_comment: str, is_temporary: bool = False):
+        if is_temporary and not get_settings().config.publish_output_progress:
+            get_logger().debug(f"Skipping publish_comment for temporary comment: {pr_comment}")
+            return None
         pr_comment = self.limit_output_characters(pr_comment, self.max_comment_length)
         comment = self.pr.comment(pr_comment)
         if is_temporary:

pr_agent/git_providers/bitbucket_server_provider.py

@@ -1,10 +1,14 @@
-from distutils.version import LooseVersion
+import difflib
+import re
+
+from packaging.version import parse as parse_version
 from typing import Optional, Tuple
 from urllib.parse import quote_plus, urlparse
 
 from atlassian.bitbucket import Bitbucket
 from requests.exceptions import HTTPError
 
+from ..algo.git_patch_processing import decode_if_bytes
 from ..algo.language_handler import is_valid_file
 from ..algo.types import EDIT_TYPE, FilePatchInfo
 from ..algo.utils import (find_line_number_of_relevant_line_in_file,
@@ -36,7 +40,7 @@ class BitbucketServerProvider(GitProvider):
                                                               token=get_settings().get("BITBUCKET_SERVER.BEARER_TOKEN",
                                                                                        None))
         try:
-            self.bitbucket_api_version = LooseVersion(self.bitbucket_client.get("rest/api/1.0/application-properties").get('version'))
+            self.bitbucket_api_version = parse_version(self.bitbucket_client.get("rest/api/1.0/application-properties").get('version'))
         except Exception:
             self.bitbucket_api_version = None
 
@@ -66,24 +70,37 @@ class BitbucketServerProvider(GitProvider):
         post_parameters_list = []
         for suggestion in code_suggestions:
             body = suggestion["body"]
+            original_suggestion = suggestion.get('original_suggestion', None)  # needed for diff code
+            if original_suggestion:
+                try:
+                    existing_code = original_suggestion['existing_code'].rstrip() + "\n"
+                    improved_code = original_suggestion['improved_code'].rstrip() + "\n"
+                    diff = difflib.unified_diff(existing_code.split('\n'),
+                                                improved_code.split('\n'), n=999)
+                    patch_orig = "\n".join(diff)
+                    patch = "\n".join(patch_orig.splitlines()[5:]).strip('\n')
+                    diff_code = f"\n\n```diff\n{patch.rstrip()}\n```"
+                    # replace ```suggestion ... ``` with diff_code, using regex:
+                    body = re.sub(r'```suggestion.*?```', diff_code, body, flags=re.DOTALL)
+                except Exception as e:
+                    get_logger().exception(f"Bitbucket failed to get diff code for publishing, error: {e}")
+                    continue
             relevant_file = suggestion["relevant_file"]
             relevant_lines_start = suggestion["relevant_lines_start"]
             relevant_lines_end = suggestion["relevant_lines_end"]
 
             if not relevant_lines_start or relevant_lines_start == -1:
-                if get_settings().config.verbosity_level >= 2:
+                get_logger().warning(
-                    get_logger().exception(
+                    f"Failed to publish code suggestion, relevant_lines_start is {relevant_lines_start}"
-                        f"Failed to publish code suggestion, relevant_lines_start is {relevant_lines_start}"
+                )
-                    )
                 continue
 
             if relevant_lines_end < relevant_lines_start:
-                if get_settings().config.verbosity_level >= 2:
+                get_logger().warning(
-                    get_logger().exception(
+                    f"Failed to publish code suggestion, "
-                        f"Failed to publish code suggestion, "
+                    f"relevant_lines_end is {relevant_lines_end} and "
-                        f"relevant_lines_end is {relevant_lines_end} and "
+                    f"relevant_lines_start is {relevant_lines_start}"
-                        f"relevant_lines_start is {relevant_lines_start}"
+                )
-                    )
                 continue
 
             if relevant_lines_end > relevant_lines_start:
@@ -160,7 +177,7 @@ class BitbucketServerProvider(GitProvider):
         head_sha = self.pr.fromRef['latestCommit']
 
         # if Bitbucket api version is >= 8.16 then use the merge-base api for 2-way diff calculation
-        if self.bitbucket_api_version is not None and self.bitbucket_api_version >= LooseVersion("8.16"):
+        if self.bitbucket_api_version is not None and self.bitbucket_api_version >= parse_version("8.16"):
             try:
                 base_sha = self.bitbucket_client.get(self._get_merge_base())['id']
             except Exception as e:
@@ -175,7 +192,7 @@ class BitbucketServerProvider(GitProvider):
             # if Bitbucket api version is None or < 7.0 then do a simple diff with a guaranteed common ancestor
             base_sha = source_commits_list[-1]['parents'][0]['id']
             # if Bitbucket api version is 7.0-8.15 then use 2-way diff functionality for the base_sha
-            if self.bitbucket_api_version is not None and self.bitbucket_api_version >= LooseVersion("7.0"):
+            if self.bitbucket_api_version is not None and self.bitbucket_api_version >= parse_version("7.0"):
                 try:
                     destination_commits = list(
                         self.bitbucket_client.get_commits(self.workspace_slug, self.repo_slug, base_sha,
@@ -201,25 +218,21 @@ class BitbucketServerProvider(GitProvider):
                 case 'ADD':
                     edit_type = EDIT_TYPE.ADDED
                     new_file_content_str = self.get_file(file_path, head_sha)
-                    if isinstance(new_file_content_str, (bytes, bytearray)):
+                    new_file_content_str = decode_if_bytes(new_file_content_str)
-                        new_file_content_str = new_file_content_str.decode("utf-8")
                     original_file_content_str = ""
                 case 'DELETE':
                     edit_type = EDIT_TYPE.DELETED
                     new_file_content_str = ""
                     original_file_content_str = self.get_file(file_path, base_sha)
-                    if isinstance(original_file_content_str, (bytes, bytearray)):
+                    original_file_content_str = decode_if_bytes(original_file_content_str)
-                        original_file_content_str = original_file_content_str.decode("utf-8")
                 case 'RENAME':
                     edit_type = EDIT_TYPE.RENAMED
                 case _:
                     edit_type = EDIT_TYPE.MODIFIED
                     original_file_content_str = self.get_file(file_path, base_sha)
-                    if isinstance(original_file_content_str, (bytes, bytearray)):
+                    original_file_content_str = decode_if_bytes(original_file_content_str)
-                        original_file_content_str = original_file_content_str.decode("utf-8")
                     new_file_content_str = self.get_file(file_path, head_sha)
-                    if isinstance(new_file_content_str, (bytes, bytearray)):
+                    new_file_content_str = decode_if_bytes(new_file_content_str)
-                        new_file_content_str = new_file_content_str.decode("utf-8")
 
             patch = load_large_diff(file_path, new_file_content_str, original_file_content_str)
 
@@ -330,10 +343,10 @@ class BitbucketServerProvider(GitProvider):
         for comment in comments:
             if 'position' in comment:
                 self.publish_inline_comment(comment['body'], comment['position'], comment['path'])
-            elif 'start_line' in comment:  # multi-line comment
+            elif 'start_line' in comment: # multi-line comment
                 # note that bitbucket does not seem to support range - only a comment on a single line - https://community.developer.atlassian.com/t/api-post-endpoint-for-inline-pull-request-comments/60452
                 self.publish_inline_comment(comment['body'], comment['start_line'], comment['path'])
-            elif 'line' in comment:  # single-line comment
+            elif 'line' in comment: # single-line comment
                 self.publish_inline_comment(comment['body'], comment['line'], comment['path'])
             else:
                 get_logger().error(f"Could not publish inline comment: {comment}")

pr_agent/git_providers/github_provider.py

@@ -1,5 +1,8 @@
+import copy
+import difflib
 import hashlib
 import itertools
+import re
 import time
 import traceback
 from datetime import datetime
@@ -11,6 +14,7 @@ from retry import retry
 from starlette_context import context
 
 from ..algo.file_filter import filter_ignored
+from ..algo.git_patch_processing import extract_hunk_headers
 from ..algo.language_handler import is_valid_file
 from ..algo.types import EDIT_TYPE
 from ..algo.utils import (PRReviewHeader, Range, clip_tokens,
@@ -415,7 +419,10 @@ class GithubProvider(GitProvider):
         Publishes code suggestions as comments on the PR.
         """
         post_parameters_list = []
-        for suggestion in code_suggestions:
+
+        code_suggestions_validated = self.validate_comments_inside_hunks(code_suggestions)
+
+        for suggestion in code_suggestions_validated:
             body = suggestion['body']
             relevant_file = suggestion['relevant_file']
             relevant_lines_start = suggestion['relevant_lines_start']
@@ -872,3 +879,100 @@ class GithubProvider(GitProvider):
 
     def calc_pr_statistics(self, pull_request_data: dict):
             return {}
+
+    def validate_comments_inside_hunks(self, code_suggestions):
+        """
+        validate that all committable comments are inside PR hunks - this is a must for committable comments in GitHub
+        """
+        code_suggestions_copy = copy.deepcopy(code_suggestions)
+        diff_files = self.get_diff_files()
+        RE_HUNK_HEADER = re.compile(
+            r"^@@ -(\d+)(?:,(\d+))? \+(\d+)(?:,(\d+))? @@[ ]?(.*)")
+
+        # map file extensions to programming languages
+        language_extension_map_org = get_settings().language_extension_map_org
+        extension_to_language = {}
+        for language, extensions in language_extension_map_org.items():
+            for ext in extensions:
+                extension_to_language[ext] = language
+        for file in diff_files:
+            extension_s = '.' + file.filename.rsplit('.')[-1]
+            language_name = "txt"
+            if extension_s and (extension_s in extension_to_language):
+                language_name = extension_to_language[extension_s]
+            file.language = language_name.lower()
+
+        for suggestion in code_suggestions_copy:
+            try:
+                relevant_file_path = suggestion['relevant_file']
+                for file in diff_files:
+                    if file.filename == relevant_file_path:
+
+                        # generate on-demand the patches range for the relevant file
+                        patch_str = file.patch
+                        if not hasattr(file, 'patches_range'):
+                            file.patches_range = []
+                            patch_lines = patch_str.splitlines()
+                            for i, line in enumerate(patch_lines):
+                                if line.startswith('@@'):
+                                    match = RE_HUNK_HEADER.match(line)
+                                    # identify hunk header
+                                    if match:
+                                        section_header, size1, size2, start1, start2 = extract_hunk_headers(match)
+                                        file.patches_range.append({'start': start2, 'end': start2 + size2 - 1})
+
+                        patches_range = file.patches_range
+                        comment_start_line = suggestion.get('relevant_lines_start', None)
+                        comment_end_line = suggestion.get('relevant_lines_end', None)
+                        original_suggestion = suggestion.get('original_suggestion', None) # needed for diff code
+                        if not comment_start_line or not comment_end_line or not original_suggestion:
+                            continue
+
+                        # check if the comment is inside a valid hunk
+                        is_valid_hunk = False
+                        min_distance = float('inf')
+                        patch_range_min = None
+                        # find the hunk that contains the comment, or the closest one
+                        for i, patch_range in enumerate(patches_range):
+                            d1 = comment_start_line - patch_range['start']
+                            d2 = patch_range['end'] - comment_end_line
+                            if d1 >= 0 and d2 >= 0:  # found a valid hunk
+                                is_valid_hunk = True
+                                min_distance = 0
+                                patch_range_min = patch_range
+                                break
+                            elif d1 * d2 <= 0:  # comment is possibly inside the hunk
+                                d1_clip = abs(min(0, d1))
+                                d2_clip = abs(min(0, d2))
+                                d = max(d1_clip, d2_clip)
+                                if d < min_distance:
+                                    patch_range_min = patch_range
+                                    min_distance = min(min_distance, d)
+                        if not is_valid_hunk:
+                            if min_distance < 10:  # 10 lines - a reasonable distance to consider the comment inside the hunk
+                                # make the suggestion non-committable, yet multi line
+                                suggestion['relevant_lines_start'] = max(suggestion['relevant_lines_start'], patch_range_min['start'])
+                                suggestion['relevant_lines_end'] = min(suggestion['relevant_lines_end'], patch_range_min['end'])
+                                body = suggestion['body'].strip()
+
+                                # present new diff code in collapsible
+                                existing_code = original_suggestion['existing_code'].rstrip() + "\n"
+                                improved_code = original_suggestion['improved_code'].rstrip() + "\n"
+                                diff = difflib.unified_diff(existing_code.split('\n'),
+                                                            improved_code.split('\n'), n=999)
+                                patch_orig = "\n".join(diff)
+                                patch = "\n".join(patch_orig.splitlines()[5:]).strip('\n')
+                                diff_code = f"\n\n<details><summary>New proposed code:</summary>\n\n```diff\n{patch.rstrip()}\n```"
+                                # replace ```suggestion ... ``` with diff_code, using regex:
+                                body = re.sub(r'```suggestion.*?```', diff_code, body, flags=re.DOTALL)
+                                body += "\n\n</details>"
+                                suggestion['body'] = body
+                                get_logger().info(f"Comment was moved to a valid hunk, "
+                                                  f"start_line={suggestion['relevant_lines_start']}, end_line={suggestion['relevant_lines_end']}, file={file.filename}")
+                            else:
+                                get_logger().error(f"Comment is not inside a valid hunk, "
+                                                   f"start_line={suggestion['relevant_lines_start']}, end_line={suggestion['relevant_lines_end']}, file={file.filename}")
+            except Exception as e:
+                get_logger().error(f"Failed to process patch for committable comment, error: {e}")
+        return code_suggestions_copy
+

pr_agent/git_providers/gitlab_provider.py

@@ -1,3 +1,4 @@
+import difflib
 import hashlib
 import re
 from typing import Optional, Tuple
@@ -193,6 +194,9 @@ class GitLabProvider(GitProvider):
         self.publish_persistent_comment_full(pr_comment, initial_header, update_header, name, final_update_message)
 
     def publish_comment(self, mr_comment: str, is_temporary: bool = False):
+        if is_temporary and not get_settings().config.publish_output_progress:
+            get_logger().debug(f"Skipping publish_comment for temporary comment: {mr_comment}")
+            return None
         mr_comment = self.limit_output_characters(mr_comment, self.max_comment_chars)
         comment = self.mr.notes.create({'body': mr_comment})
         if is_temporary:
@@ -278,20 +282,23 @@ class GitLabProvider(GitProvider):
                         new_code_snippet = original_suggestion['improved_code']
                         content = original_suggestion['suggestion_content']
                         label = original_suggestion['label']
-                        if 'score' in original_suggestion:
+                        score = original_suggestion.get('score', 7)
-                            score = original_suggestion['score']
-                        else:
-                            score = 7
 
                     if hasattr(self, 'main_language'):
                         language = self.main_language
                     else:
                         language = ''
                     link = self.get_line_link(relevant_file, line_start, line_end)
-                    body_fallback =f"**Suggestion:** {content} [{label}, importance: {score}]\n___\n"
+                    body_fallback =f"**Suggestion:** {content} [{label}, importance: {score}]\n\n"
-                    body_fallback +=f"\n\nReplace  lines ([{line_start}-{line_end}]({link}))\n\n```{language}\n{old_code_snippet}\n````\n\n"
+                    body_fallback +=f"\n\n<details><summary>[{target_file.filename} [{line_start}-{line_end}]]({link}):</summary>\n\n"
-                    body_fallback +=f"with\n\n```{language}\n{new_code_snippet}\n````"
+                    body_fallback += f"\n\n___\n\n`(Cannot implement directly - GitLab API allows committable suggestions strictly on MR diff lines)`"
-                    body_fallback += f"\n\n___\n\n`(Cannot implement this suggestion directly, as gitlab API does not enable committing to a non -+ line in a PR)`"
+                    body_fallback+="</details>\n\n"
+                    diff_patch = difflib.unified_diff(old_code_snippet.split('\n'),
+                                                new_code_snippet.split('\n'), n=999)
+                    patch_orig = "\n".join(diff_patch)
+                    patch = "\n".join(patch_orig.splitlines()[5:]).strip('\n')
+                    diff_code = f"\n\n```diff\n{patch.rstrip()}\n```"
+                    body_fallback += diff_code
 
                     # Create a general note on the file in the MR
                     self.mr.notes.create({
@@ -304,6 +311,7 @@ class GitLabProvider(GitProvider):
                             'file_path': f'{target_file.filename}',
                         }
                     })
+                    get_logger().debug(f"Created fallback comment in MR {self.id_mr} with position {pos_obj}")
 
                     # get_logger().debug(
                     #     f"Failed to create comment in MR {self.id_mr} with position {pos_obj} (probably not a '+' line)")

pr_agent/settings/configuration.toml

@@ -1,8 +1,8 @@
 [config]
 # models
 model="gpt-4-turbo-2024-04-09"
-model_turbo="gpt-4o-2024-08-06"
+model_turbo="gpt-4o-2024-11-20"
-fallback_models=["gpt-4o-2024-05-13"]
+fallback_models=["gpt-4o-2024-08-06"]
 # CLI
 git_provider="github"
 publish_output=true
@@ -111,7 +111,7 @@ max_context_tokens=16000
 #
 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
-focus_only_on_problems=false
+focus_only_on_problems=true
 #
 extra_instructions = ""
 rank_suggestions = false

requirements.txt

@@ -12,10 +12,10 @@ google-cloud-aiplatform==1.38.0
 google-generativeai==0.8.3
 google-cloud-storage==2.10.0
 Jinja2==3.1.2
-litellm==1.52.0
+litellm==1.52.12
 loguru==0.7.2
 msrest==0.7.1
-openai==1.54.1
+openai==1.55.3
 pytest==7.4.0
 PyGithub==1.59.*
 PyYAML==6.0.1