Merge remote-tracking branch 'origin/main' into tr/issue_tool

# Conflicts:
#	pr_agent/algo/utils.py

pr_agent/agent/pr_agent.py

@@ -16,6 +16,7 @@ from pr_agent.tools.pr_update_changelog import PRUpdateChangelog
 from pr_agent.tools.pr_config import PRConfig
 
 command2class = {
+    "auto_review": PRReviewer,
     "answer": PRReviewer,
     "review": PRReviewer,
     "review_pr": PRReviewer,
@@ -72,6 +73,8 @@ class PRAgent:
             if notify:
                 notify()
             await PRReviewer(pr_url, is_answer=True, args=args).run()
+        elif action == "auto_review":
+            await PRReviewer(pr_url, is_auto=True, args=args).run()
         elif action in command2class:
             if notify:
                 notify()

pr_agent/algo/ai_handler.py

@@ -26,6 +26,7 @@ class AiHandler:
         try:
             openai.api_key = get_settings().openai.key
             litellm.openai_key = get_settings().openai.key
+            litellm.debugger = get_settings().config.litellm_debugger
             self.azure = False
             if get_settings().get("OPENAI.ORG", None):
                 litellm.organization = get_settings().openai.org
@@ -43,6 +44,10 @@ class AiHandler:
                 litellm.cohere_key = get_settings().cohere.key
             if get_settings().get("REPLICATE.KEY", None):
                 litellm.replicate_key = get_settings().replicate.key
+            if get_settings().get("REPLICATE.KEY", None):
+                litellm.replicate_key = get_settings().replicate.key
+            if get_settings().get("HUGGINGFACE.KEY", None):
+                litellm.huggingface_key = get_settings().huggingface.key
         except AttributeError as e:
             raise ValueError("OpenAI key is required") from e
 
@@ -55,7 +60,7 @@ class AiHandler:
 
     @retry(exceptions=(APIError, Timeout, TryAgain, AttributeError, RateLimitError),
            tries=OPENAI_RETRIES, delay=2, backoff=2, jitter=(1, 3))
-    async def chat_completion(self, model: str, temperature: float, system: str, user: str):
+    async def chat_completion(self, model: str, system: str, user: str, temperature: float = 0.2):
         """
         Performs a chat completion using the OpenAI ChatCompletion API.
         Retries in case of API errors or timeouts.

pr_agent/algo/git_patch_processing.py

@@ -1,5 +1,4 @@
 from __future__ import annotations
-
 import logging
 import re
 
@@ -157,7 +156,7 @@ def convert_to_hunks_with_lines_numbers(patch: str, file) -> str:
 
     example output:
 ## src/file.ts
---new hunk--
+__new hunk__
 881        line1
 882        line2
 883        line3
@@ -166,7 +165,7 @@ def convert_to_hunks_with_lines_numbers(patch: str, file) -> str:
 889        line6
 890        line7
 ...
---old hunk--
+__old hunk__
         line1
         line2
 -       line3
@@ -176,8 +175,7 @@ def convert_to_hunks_with_lines_numbers(patch: str, file) -> str:
            ...
     """
     
-    patch_with_lines_str = f"## {file.filename}\n"
-    import re
+    patch_with_lines_str = f"\n\n## {file.filename}\n"
     patch_lines = patch.splitlines()
     RE_HUNK_HEADER = re.compile(
         r"^@@ -(\d+)(?:,(\d+))? \+(\d+)(?:,(\d+))? @@[ ]?(.*)")
@@ -185,23 +183,30 @@ def convert_to_hunks_with_lines_numbers(patch: str, file) -> str:
     old_content_lines = []
     match = None
     start1, size1, start2, size2 = -1, -1, -1, -1
+    prev_header_line = []
+    header_line =[]
     for line in patch_lines:
         if 'no newline at end of file' in line.lower():
             continue
 
         if line.startswith('@@'):
+            header_line = line
             match = RE_HUNK_HEADER.match(line)
             if match and new_content_lines:  # found a new hunk, split the previous lines
                 if new_content_lines:
-                    patch_with_lines_str += '\n--new hunk--\n'
+                    if prev_header_line:
+                        patch_with_lines_str += f'\n{prev_header_line}\n'
+                    patch_with_lines_str += '__new hunk__\n'
                     for i, line_new in enumerate(new_content_lines):
                         patch_with_lines_str += f"{start2 + i} {line_new}\n"
                 if old_content_lines:
-                    patch_with_lines_str += '--old hunk--\n'
+                    patch_with_lines_str += '__old hunk__\n'
                     for line_old in old_content_lines:
                         patch_with_lines_str += f"{line_old}\n"
                 new_content_lines = []
                 old_content_lines = []
+            if match:
+                prev_header_line = header_line
             try:
                 start1, size1, start2, size2 = map(int, match.groups()[:4])
             except: # '@@ -0,0 +1 @@' case
@@ -219,12 +224,13 @@ def convert_to_hunks_with_lines_numbers(patch: str, file) -> str:
     # finishing last hunk
     if match and new_content_lines:
         if new_content_lines:
-            patch_with_lines_str += '\n--new hunk--\n'
+            patch_with_lines_str += f'\n{header_line}\n'
+            patch_with_lines_str += '\n__new hunk__\n'
             for i, line_new in enumerate(new_content_lines):
                 patch_with_lines_str += f"{start2 + i} {line_new}\n"
         if old_content_lines:
-            patch_with_lines_str += '\n--old hunk--\n'
+            patch_with_lines_str += '\n__old hunk__\n'
             for line_old in old_content_lines:
                 patch_with_lines_str += f"{line_old}\n"
 
-    return patch_with_lines_str.strip()
+    return patch_with_lines_str.rstrip()

pr_agent/algo/pr_processing.py

@@ -57,7 +57,7 @@ def get_pr_diff(git_provider: GitProvider, token_handler: TokenHandler, model: s
     pr_languages = sort_files_by_main_languages(git_provider.get_languages(), diff_files)
 
     # generate a standard diff string, with patch extension
-    patches_extended, total_tokens = pr_generate_extended_diff(pr_languages, token_handler,
+    patches_extended, total_tokens, patches_extended_tokens = pr_generate_extended_diff(pr_languages, token_handler,
                                                                add_line_numbers_to_hunks)
 
     # if we are under the limit, return the full diff
@@ -78,9 +78,9 @@ def get_pr_diff(git_provider: GitProvider, token_handler: TokenHandler, model: s
     return final_diff
 
 
-def pr_generate_extended_diff(pr_languages: list, token_handler: TokenHandler,
-                              add_line_numbers_to_hunks: bool) -> \
-        Tuple[list, int]:
+def pr_generate_extended_diff(pr_languages: list,
+                              token_handler: TokenHandler,
+                              add_line_numbers_to_hunks: bool) -> Tuple[list, int, list]:
     """
     Generate a standard diff string with patch extension, while counting the number of tokens used and applying diff
     minimization techniques if needed.
@@ -90,13 +90,10 @@ def pr_generate_extended_diff(pr_languages: list, token_handler: TokenHandler,
       files.
     - token_handler: An object of the TokenHandler class used for handling tokens in the context of the pull request.
     - add_line_numbers_to_hunks: A boolean indicating whether to add line numbers to the hunks in the diff.
-
-    Returns:
-    - patches_extended: A list of extended patches for each file in the pull request.
-    - total_tokens: The total number of tokens used in the extended patches.
     """
     total_tokens = token_handler.prompt_tokens  # initial tokens
     patches_extended = []
+    patches_extended_tokens = []
     for lang in pr_languages:
         for file in lang['files']:
             original_file_content_str = file.base_file
@@ -106,7 +103,7 @@ def pr_generate_extended_diff(pr_languages: list, token_handler: TokenHandler,
 
             # extend each patch with extra lines of context
             extended_patch = extend_patch(original_file_content_str, patch, num_lines=PATCH_EXTRA_LINES)
-            full_extended_patch = f"## {file.filename}\n\n{extended_patch}\n"
+            full_extended_patch = f"\n\n## {file.filename}\n\n{extended_patch}\n"
 
             if add_line_numbers_to_hunks:
                 full_extended_patch = convert_to_hunks_with_lines_numbers(extended_patch, file)
@@ -114,9 +111,10 @@ def pr_generate_extended_diff(pr_languages: list, token_handler: TokenHandler,
             patch_tokens = token_handler.count_tokens(full_extended_patch)
             file.tokens = patch_tokens
             total_tokens += patch_tokens
+            patches_extended_tokens.append(patch_tokens)
             patches_extended.append(full_extended_patch)
 
-    return patches_extended, total_tokens
+    return patches_extended, total_tokens, patches_extended_tokens
 
 
 def pr_generate_compressed_diff(top_langs: list, token_handler: TokenHandler, model: str,
@@ -324,7 +322,9 @@ def clip_tokens(text: str, max_tokens: int) -> str:
     Returns:
         str: The clipped string.
     """
-    # We'll estimate the number of tokens by hueristically assuming 2.5 tokens per word
+    if not text:
+        return text
+
     try:
         encoder = get_token_encoder()
         num_input_tokens = len(encoder.encode(text))
@@ -337,4 +337,84 @@ def clip_tokens(text: str, max_tokens: int) -> str:
         return clipped_text
     except Exception as e:
         logging.warning(f"Failed to clip tokens: {e}")
-        return text
+        return text
+
+
+def get_pr_multi_diffs(git_provider: GitProvider,
+                       token_handler: TokenHandler,
+                       model: str,
+                       max_calls: int = 5) -> List[str]:
+    """
+    Retrieves the diff files from a Git provider, sorts them by main language, and generates patches for each file.
+    The patches are split into multiple groups based on the maximum number of tokens allowed for the given model.
+    
+    Args:
+        git_provider (GitProvider): An object that provides access to Git provider APIs.
+        token_handler (TokenHandler): An object that handles tokens in the context of a pull request.
+        model (str): The name of the model.
+        max_calls (int, optional): The maximum number of calls to retrieve diff files. Defaults to 5.
+    
+    Returns:
+        List[str]: A list of final diff strings, split into multiple groups based on the maximum number of tokens allowed for the given model.
+    
+    Raises:
+        RateLimitExceededException: If the rate limit for the Git provider API is exceeded.
+    """
+    try:
+        diff_files = git_provider.get_diff_files()
+    except RateLimitExceededException as e:
+        logging.error(f"Rate limit exceeded for git provider API. original message {e}")
+        raise
+
+    # Sort files by main language
+    pr_languages = sort_files_by_main_languages(git_provider.get_languages(), diff_files)
+
+    # Sort files within each language group by tokens in descending order
+    sorted_files = []
+    for lang in pr_languages:
+        sorted_files.extend(sorted(lang['files'], key=lambda x: x.tokens, reverse=True))
+
+    patches = []
+    final_diff_list = []
+    total_tokens = token_handler.prompt_tokens
+    call_number = 1
+    for file in sorted_files:
+        if call_number > max_calls:
+            if get_settings().config.verbosity_level >= 2:
+                logging.info(f"Reached max calls ({max_calls})")
+            break
+
+        original_file_content_str = file.base_file
+        new_file_content_str = file.head_file
+        patch = file.patch
+        if not patch:
+            continue
+
+        # Remove delete-only hunks
+        patch = handle_patch_deletions(patch, original_file_content_str, new_file_content_str, file.filename)
+        if patch is None:
+            continue
+
+        patch = convert_to_hunks_with_lines_numbers(patch, file)
+        new_patch_tokens = token_handler.count_tokens(patch)
+        if patch and (total_tokens + new_patch_tokens > MAX_TOKENS[model] - OUTPUT_BUFFER_TOKENS_SOFT_THRESHOLD):
+            final_diff = "\n".join(patches)
+            final_diff_list.append(final_diff)
+            patches = []
+            total_tokens = token_handler.prompt_tokens
+            call_number += 1
+            if get_settings().config.verbosity_level >= 2:
+                logging.info(f"Call number: {call_number}")
+
+        if patch:
+            patches.append(patch)
+            total_tokens += new_patch_tokens
+            if get_settings().config.verbosity_level >= 2:
+                logging.info(f"Tokens: {total_tokens}, last filename: {file.filename}")
+
+    # Add the last chunk
+    if patches:
+        final_diff = "\n".join(patches)
+        final_diff_list.append(final_diff)
+
+    return final_diff_list

pr_agent/algo/utils.py

@@ -250,9 +250,7 @@ def update_settings_from_args(args: List[str]) -> List[str]:
                     logging.error(f'Invalid argument format: {arg}')
                     other_args.append(arg)
                     continue
-                key, value = vals
-                key = key.strip().upper()
-                value = value.strip()
+                key, value = _fix_key_value(*vals)
                 if key in get_settings():
                     get_settings().set(key, value)
                     logging.info(f'Updated setting {key} to: "{value}"')

pr_agent/cli.py

@@ -19,13 +19,21 @@ For example:
 - cli.py --pr_url=... reflect
 
 Supported commands:
-review / review_pr - Add a review that includes a summary of the PR and specific suggestions for improvement.
-ask / ask_question [question] - Ask a question about the PR.
-describe / describe_pr - Modify the PR title and description based on the PR's contents.
-improve / improve_code - Suggest improvements to the code in the PR as pull request comments ready to commit.
-reflect - Ask the PR author questions about the PR.
-update_changelog - Update the changelog based on the PR's contents.
+-review / review_pr - Add a review that includes a summary of the PR and specific suggestions for improvement.
 
+-ask / ask_question [question] - Ask a question about the PR.
+
+-describe / describe_pr - Modify the PR title and description based on the PR's contents.
+
+-improve / improve_code - Suggest improvements to the code in the PR as pull request comments ready to commit.
+Extended mode ('improve --extended') employs several calls, and provides a more thorough feedback
+
+-reflect - Ask the PR author questions about the PR.
+
+-update_changelog - Update the changelog based on the PR's contents.
+
+
+Configuration:
 To edit any configuration parameter from 'configuration.toml', just add -config_path=<value>.
 For example: 'python cli.py --pr_url=... review --pr_reviewer.extra_instructions="focus on the file: ..."'
 """)

pr_agent/config_loader.py

@@ -19,6 +19,7 @@ global_settings = Dynaconf(
         "settings/pr_questions_prompts.toml",
         "settings/pr_description_prompts.toml",
         "settings/pr_code_suggestions_prompts.toml",
+        "settings/pr_sort_code_suggestions_prompts.toml",
         "settings/pr_information_from_user_prompts.toml",
         "settings/pr_update_changelog_prompts.toml",
         "settings_prod/.secrets.toml"

pr_agent/git_providers/__init__.py

@@ -1,13 +1,17 @@
 from pr_agent.config_loader import get_settings
 from pr_agent.git_providers.bitbucket_provider import BitbucketProvider
+from pr_agent.git_providers.codecommit_provider import CodeCommitProvider
 from pr_agent.git_providers.github_provider import GithubProvider
 from pr_agent.git_providers.gitlab_provider import GitLabProvider
 from pr_agent.git_providers.local_git_provider import LocalGitProvider
+from pr_agent.git_providers.azuredevops_provider import AzureDevopsProvider
 
 _GIT_PROVIDERS = {
     'github': GithubProvider,
     'gitlab': GitLabProvider,
     'bitbucket': BitbucketProvider,
+    'azure': AzureDevopsProvider,
+    'codecommit': CodeCommitProvider,
     'local' : LocalGitProvider
 }
 

pr_agent/git_providers/azuredevops_provider.py

@@ -0,0 +1,269 @@
+import json
+import logging
+from typing import Optional, Tuple
+from urllib.parse import urlparse
+
+import os
+
+AZURE_DEVOPS_AVAILABLE = True
+try:
+    from msrest.authentication import BasicAuthentication
+    from azure.devops.connection import Connection
+    from azure.devops.v7_1.git.models import Comment, CommentThread, GitVersionDescriptor, GitPullRequest
+except ImportError:
+    AZURE_DEVOPS_AVAILABLE = False
+
+from ..algo.pr_processing import clip_tokens
+from ..config_loader import get_settings
+from ..algo.utils import load_large_diff
+from ..algo.language_handler import is_valid_file
+from .git_provider import EDIT_TYPE, FilePatchInfo
+
+
+class AzureDevopsProvider:
+    def __init__(self, pr_url: Optional[str] = None, incremental: Optional[bool] = False):
+        if not AZURE_DEVOPS_AVAILABLE:
+            raise ImportError("Azure DevOps provider is not available. Please install the required dependencies.")
+
+        self.azure_devops_client = self._get_azure_devops_client()
+
+        self.workspace_slug = None
+        self.repo_slug = None
+        self.repo = None
+        self.pr_num = None
+        self.pr = None
+        self.temp_comments = []
+        self.incremental = incremental
+        if pr_url:
+            self.set_pr(pr_url)
+
+    def is_supported(self, capability: str) -> bool:
+        if capability in ['get_issue_comments', 'create_inline_comment', 'publish_inline_comments', 'get_labels', 'remove_initial_comment']:
+            return False
+        return True
+
+    def set_pr(self, pr_url: str):
+        self.workspace_slug, self.repo_slug, self.pr_num = self._parse_pr_url(pr_url)
+        self.pr = self._get_pr()
+
+    def get_repo_settings(self):
+        try:
+            contents = self.azure_devops_client.get_item_content(repository_id=self.repo_slug,
+                                                                 project=self.workspace_slug, download=False,
+                                                                 include_content_metadata=False, include_content=True,
+                                                                 path=".pr_agent.toml")
+            return contents
+        except Exception as e:
+            logging.exception("get repo settings error")
+            return ""
+
+    def get_files(self):
+        files = []
+        for i in self.azure_devops_client.get_pull_request_commits(project=self.workspace_slug,
+                                                                   repository_id=self.repo_slug,
+                                                                   pull_request_id=self.pr_num):
+
+            changes_obj = self.azure_devops_client.get_changes(project=self.workspace_slug,
+                                                               repository_id=self.repo_slug, commit_id=i.commit_id)
+
+            for c in changes_obj.changes:
+                files.append(c['item']['path'])
+        return list(set(files))
+
+    def get_diff_files(self) -> list[FilePatchInfo]:
+        try:
+            base_sha = self.pr.last_merge_target_commit
+            head_sha = self.pr.last_merge_source_commit
+
+            commits = self.azure_devops_client.get_pull_request_commits(project=self.workspace_slug,
+                                                                        repository_id=self.repo_slug,
+                                                                        pull_request_id=self.pr_num)
+
+            diff_files = []
+            diffs = []
+            diff_types = {}
+
+            for c in commits:
+                changes_obj = self.azure_devops_client.get_changes(project=self.workspace_slug,
+                                                                   repository_id=self.repo_slug, commit_id=c.commit_id)
+                for i in changes_obj.changes:
+                    diffs.append(i['item']['path'])
+                    diff_types[i['item']['path']] = i['changeType']
+
+            diffs = list(set(diffs))
+
+            for file in diffs:
+                if not is_valid_file(file):
+                    continue
+
+                version = GitVersionDescriptor(version=head_sha.commit_id, version_type='commit')
+                new_file_content_str = self.azure_devops_client.get_item(repository_id=self.repo_slug,
+                                                                         path=file,
+                                                                         project=self.workspace_slug,
+                                                                         version_descriptor=version,
+                                                                         download=False,
+                                                                         include_content=True)
+
+                new_file_content_str = new_file_content_str.content
+
+                edit_type = EDIT_TYPE.MODIFIED
+                if diff_types[file] == 'add':
+                    edit_type = EDIT_TYPE.ADDED
+                elif diff_types[file] == 'delete':
+                    edit_type = EDIT_TYPE.DELETED
+                elif diff_types[file] == 'rename':
+                    edit_type = EDIT_TYPE.RENAMED
+
+                version = GitVersionDescriptor(version=base_sha.commit_id, version_type='commit')
+                original_file_content_str = self.azure_devops_client.get_item(repository_id=self.repo_slug,
+                                                                              path=file,
+                                                                              project=self.workspace_slug,
+                                                                              version_descriptor=version,
+                                                                              download=False,
+                                                                              include_content=True)
+                original_file_content_str = original_file_content_str.content
+
+                patch = load_large_diff(file, new_file_content_str, original_file_content_str)
+
+                diff_files.append(FilePatchInfo(original_file_content_str, new_file_content_str,
+                                                patch=patch,
+                                                filename=file,
+                                                edit_type=edit_type))
+
+            self.diff_files = diff_files
+            return diff_files
+        except Exception as e:
+            print(f"Error: {str(e)}")
+            return []
+
+    def publish_comment(self, pr_comment: str, is_temporary: bool = False):
+        comment = Comment(content=pr_comment)
+        thread = CommentThread(comments=[comment])
+        thread_response = self.azure_devops_client.create_thread(comment_thread=thread, project=self.workspace_slug,
+                                                                 repository_id=self.repo_slug,
+                                                                 pull_request_id=self.pr_num)
+        if is_temporary:
+            self.temp_comments.append({'thread_id': thread_response.id, 'comment_id': comment.id})
+
+    def publish_description(self, pr_title: str, pr_body: str):
+        try:
+            updated_pr = GitPullRequest()
+            updated_pr.title = pr_title
+            updated_pr.description = pr_body
+            self.azure_devops_client.update_pull_request(project=self.workspace_slug,
+                                                         repository_id=self.repo_slug,
+                                                         pull_request_id=self.pr_num,
+                                                         git_pull_request_to_update=updated_pr)
+        except Exception as e:
+            logging.exception(f"Could not update pull request {self.pr_num} description: {e}")
+
+    def remove_initial_comment(self):
+        return ""  # not implemented yet
+
+    def publish_inline_comment(self, body: str, relevant_file: str, relevant_line_in_file: str):
+        raise NotImplementedError("Azure DevOps provider does not support publishing inline comment yet")
+
+    def create_inline_comment(self, body: str, relevant_file: str, relevant_line_in_file: str):
+        raise NotImplementedError("Azure DevOps provider does not support creating inline comments yet")
+
+    def publish_inline_comments(self, comments: list[dict]):
+        raise NotImplementedError("Azure DevOps provider does not support publishing inline comments yet")
+
+    def get_title(self):
+        return self.pr.title
+
+    def get_languages(self):
+        languages = []
+        files = self.azure_devops_client.get_items(project=self.workspace_slug, repository_id=self.repo_slug,
+                                                   recursion_level="Full", include_content_metadata=True,
+                                                   include_links=False, download=False)
+        for f in files:
+            if f.git_object_type == 'blob':
+                file_name, file_extension = os.path.splitext(f.path)
+                languages.append(file_extension[1:])
+
+        extension_counts = {}
+        for ext in languages:
+            if ext != '':
+                extension_counts[ext] = extension_counts.get(ext, 0) + 1
+
+        total_extensions = sum(extension_counts.values())
+
+        extension_percentages = {ext: (count / total_extensions) * 100 for ext, count in extension_counts.items()}
+
+        return extension_percentages
+
+    def get_pr_branch(self):
+        pr_info = self.azure_devops_client.get_pull_request_by_id(project=self.workspace_slug,
+                                                                  pull_request_id=self.pr_num)
+        source_branch = pr_info.source_ref_name.split('/')[-1]
+        return source_branch
+
+    def get_pr_description(self):
+        max_tokens = get_settings().get("CONFIG.MAX_DESCRIPTION_TOKENS", None)
+        if max_tokens:
+            return clip_tokens(self.pr.description, max_tokens)
+        return self.pr.description
+
+    def get_user_id(self):
+        return 0
+
+    def get_issue_comments(self):
+        raise NotImplementedError("Azure DevOps provider does not support issue comments yet")
+
+    def add_eyes_reaction(self, issue_comment_id: int) -> Optional[int]:
+        return True
+
+    def remove_reaction(self, issue_comment_id: int, reaction_id: int) -> bool:
+        return True
+
+    def get_issue_comments(self):
+        raise NotImplementedError("Azure DevOps provider does not support issue comments yet")
+
+    @staticmethod
+    def _parse_pr_url(pr_url: str) -> Tuple[str, int]:
+        parsed_url = urlparse(pr_url)
+
+        if 'azure.com' not in parsed_url.netloc:
+            raise ValueError("The provided URL is not a valid Azure DevOps URL")
+
+        path_parts = parsed_url.path.strip('/').split('/')
+
+        if len(path_parts) < 6 or path_parts[4] != 'pullrequest':
+            raise ValueError("The provided URL does not appear to be a Azure DevOps PR URL")
+
+        workspace_slug = path_parts[1]
+        repo_slug = path_parts[3]
+        try:
+            pr_number = int(path_parts[5])
+        except ValueError as e:
+            raise ValueError("Unable to convert PR number to integer") from e
+
+        return workspace_slug, repo_slug, pr_number
+
+    def _get_azure_devops_client(self):
+        try:
+            pat = get_settings().azure_devops.pat
+            org = get_settings().azure_devops.org
+        except AttributeError as e:
+            raise ValueError(
+                "Azure DevOps PAT token is required ") from e
+
+        credentials = BasicAuthentication('', pat)
+        azure_devops_connection = Connection(base_url=org, creds=credentials)
+        azure_devops_client = azure_devops_connection.clients.get_git_client()
+
+        return azure_devops_client
+
+    def _get_repo(self):
+        if self.repo is None:
+            self.repo = self.azure_devops_client.get_repository(project=self.workspace_slug,
+                                                                repository_id=self.repo_slug)
+        return self.repo
+
+    def _get_pr(self):
+        self.pr = self.azure_devops_client.get_pull_request_by_id(pull_request_id=self.pr_num, project=self.workspace_slug)
+        return self.pr
+
+    def get_commit_messages(self):
+        return ""  # not implemented yet

pr_agent/git_providers/bitbucket_provider.py

@@ -1,21 +1,31 @@
+import json
 import logging
 from typing import Optional, Tuple
 from urllib.parse import urlparse
 
 import requests
 from atlassian.bitbucket import Cloud
+from starlette_context import context
 
-from ..algo.pr_processing import clip_tokens
 from ..config_loader import get_settings
-from .git_provider import FilePatchInfo
+from .git_provider import FilePatchInfo, GitProvider
 
 
-class BitbucketProvider:
-    def __init__(self, pr_url: Optional[str] = None, incremental: Optional[bool] = False):
+class BitbucketProvider(GitProvider):
+    def __init__(
+        self, pr_url: Optional[str] = None, incremental: Optional[bool] = False
+    ):
         s = requests.Session()
-        s.headers['Authorization'] = f'Bearer {get_settings().get("BITBUCKET.BEARER_TOKEN", None)}'
+        try:
+            bearer = context.get("bitbucket_bearer_token", None)
+            s.headers["Authorization"] = f"Bearer {bearer}"
+        except Exception:
+            s.headers[
+                "Authorization"
+            ] = f'Bearer {get_settings().get("BITBUCKET.BEARER_TOKEN", None)}'
+        s.headers["Content-Type"] = "application/json"
+        self.headers = s.headers
         self.bitbucket_client = Cloud(session=s)
-
         self.workspace_slug = None
         self.repo_slug = None
         self.repo = None
@@ -25,16 +35,78 @@ class BitbucketProvider:
         self.incremental = incremental
         if pr_url:
             self.set_pr(pr_url)
+        self.bitbucket_comment_api_url = self.pr._BitbucketBase__data["links"][
+            "comments"
+        ]["href"]
 
     def get_repo_settings(self):
         try:
-            contents = self.repo_obj.get_contents(".pr_agent.toml", ref=self.pr.head.sha).decoded_content
+            contents = self.repo_obj.get_contents(
+                ".pr_agent.toml", ref=self.pr.head.sha
+            ).decoded_content
             return contents
         except Exception:
             return ""
 
+    def publish_code_suggestions(self, code_suggestions: list) -> bool:
+        """
+        Publishes code suggestions as comments on the PR.
+        """
+        post_parameters_list = []
+        for suggestion in code_suggestions:
+            body = suggestion["body"]
+            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:
+                    logging.exception(
+                        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:
+                    logging.exception(
+                        f"Failed to publish code suggestion, "
+                        f"relevant_lines_end is {relevant_lines_end} and "
+                        f"relevant_lines_start is {relevant_lines_start}"
+                    )
+                continue
+
+            if relevant_lines_end > relevant_lines_start:
+                post_parameters = {
+                    "body": body,
+                    "path": relevant_file,
+                    "line": relevant_lines_end,
+                    "start_line": relevant_lines_start,
+                    "start_side": "RIGHT",
+                }
+            else:  # API is different for single line comments
+                post_parameters = {
+                    "body": body,
+                    "path": relevant_file,
+                    "line": relevant_lines_start,
+                    "side": "RIGHT",
+                }
+            post_parameters_list.append(post_parameters)
+
+        try:
+            self.publish_inline_comments(post_parameters_list)
+            return True
+        except Exception as e:
+            if get_settings().config.verbosity_level >= 2:
+                logging.error(f"Failed to publish code suggestion, error: {e}")
+            return False
+
     def is_supported(self, capability: str) -> bool:
-        if capability in ['get_issue_comments', 'create_inline_comment', 'publish_inline_comments', 'get_labels']:
+        if capability in [
+            "get_issue_comments",
+            "create_inline_comment",
+            "publish_inline_comments",
+            "get_labels",
+        ]:
             return False
         return True
 
@@ -47,65 +119,80 @@ class BitbucketProvider:
 
     def get_diff_files(self) -> list[FilePatchInfo]:
         diffs = self.pr.diffstat()
-        diff_split = ['diff --git%s' % x for x in self.pr.diff().split('diff --git') if x.strip()]
-        
+        diff_split = [
+            "diff --git%s" % x for x in self.pr.diff().split("diff --git") if x.strip()
+        ]
+
         diff_files = []
         for index, diff in enumerate(diffs):
-            original_file_content_str = self._get_pr_file_content(diff.old.get_data('links'))
-            new_file_content_str = self._get_pr_file_content(diff.new.get_data('links'))
-            diff_files.append(FilePatchInfo(original_file_content_str, new_file_content_str,
-                                            diff_split[index], diff.new.path))
+            original_file_content_str = self._get_pr_file_content(
+                diff.old.get_data("links")
+            )
+            new_file_content_str = self._get_pr_file_content(diff.new.get_data("links"))
+            diff_files.append(
+                FilePatchInfo(
+                    original_file_content_str,
+                    new_file_content_str,
+                    diff_split[index],
+                    diff.new.path,
+                )
+            )
         return diff_files
 
     def publish_comment(self, pr_comment: str, is_temporary: bool = False):
         comment = self.pr.comment(pr_comment)
         if is_temporary:
-            self.temp_comments.append(comment['id'])
+            self.temp_comments.append(comment["id"])
 
     def remove_initial_comment(self):
         try:
             for comment in self.temp_comments:
-                self.pr.delete(f'comments/{comment}')
+                self.pr.delete(f"comments/{comment}")
         except Exception as e:
             logging.exception(f"Failed to remove temp comments, error: {e}")
 
-    def publish_inline_comment(self, body: str, relevant_file: str, relevant_line_in_file: str):
-        pass
-
-    def create_inline_comment(self, body: str, relevant_file: str, relevant_line_in_file: str):
-        raise NotImplementedError("Bitbucket provider does not support creating inline comments yet")
+    def publish_inline_comment(
+        self, comment: str, from_line: int, to_line: int, file: str
+    ):
+        payload = json.dumps(
+            {
+                "content": {
+                    "raw": comment,
+                },
+                "inline": {"to": from_line, "path": file},
+            }
+        )
+        response = requests.request(
+            "POST", self.bitbucket_comment_api_url, data=payload, headers=self.headers
+        )
+        return response
 
     def publish_inline_comments(self, comments: list[dict]):
-        raise NotImplementedError("Bitbucket provider does not support publishing inline comments yet")
+        for comment in comments:
+            self.publish_inline_comment(
+                comment["body"], comment["start_line"], comment["line"], comment["path"]
+            )
 
     def get_title(self):
         return self.pr.title
 
     def get_languages(self):
-        languages = {self._get_repo().get_data('language'): 0}
+        languages = {self._get_repo().get_data("language"): 0}
         return languages
 
     def get_pr_branch(self):
         return self.pr.source_branch
 
-    def get_pr_description(self):
-        max_tokens = get_settings().get("CONFIG.MAX_DESCRIPTION_TOKENS", None)
-        if max_tokens:
-            return clip_tokens(self.pr.description, max_tokens)
+    def get_pr_description_full(self):
         return self.pr.description
 
     def get_user_id(self):
         return 0
 
     def get_issue_comments(self):
-        raise NotImplementedError("Bitbucket provider does not support issue comments yet")
-
-    def get_repo_settings(self):
-        try:
-            contents = self.repo_obj.get_contents(".pr_agent.toml", ref=self.pr.head.sha).decoded_content
-            return contents
-        except Exception:
-            return ""
+        raise NotImplementedError(
+            "Bitbucket provider does not support issue comments yet"
+        )
 
     def add_eyes_reaction(self, issue_comment_id: int) -> Optional[int]:
         return True
@@ -116,14 +203,16 @@ class BitbucketProvider:
     @staticmethod
     def _parse_pr_url(pr_url: str) -> Tuple[str, int]:
         parsed_url = urlparse(pr_url)
-        
-        if 'bitbucket.org' not in parsed_url.netloc:
+
+        if "bitbucket.org" not in parsed_url.netloc:
             raise ValueError("The provided URL is not a valid Bitbucket URL")
 
-        path_parts = parsed_url.path.strip('/').split('/')
-        
-        if len(path_parts) < 4 or path_parts[2] != 'pull-requests':
-            raise ValueError("The provided URL does not appear to be a Bitbucket PR URL")
+        path_parts = parsed_url.path.strip("/").split("/")
+
+        if len(path_parts) < 4 or path_parts[2] != "pull-requests":
+            raise ValueError(
+                "The provided URL does not appear to be a Bitbucket PR URL"
+            )
 
         workspace_slug = path_parts[0]
         repo_slug = path_parts[1]
@@ -136,7 +225,9 @@ class BitbucketProvider:
 
     def _get_repo(self):
         if self.repo is None:
-            self.repo = self.bitbucket_client.workspaces.get(self.workspace_slug).repositories.get(self.repo_slug)
+            self.repo = self.bitbucket_client.workspaces.get(
+                self.workspace_slug
+            ).repositories.get(self.repo_slug)
         return self.repo
 
     def _get_pr(self):
@@ -147,3 +238,16 @@ class BitbucketProvider:
 
     def get_commit_messages(self):
         return ""  # not implemented yet
+
+    def publish_description(self, pr_title: str, pr_body: str):
+        pass
+    def create_inline_comment(
+        self, body: str, relevant_file: str, relevant_line_in_file: str
+    ):
+        pass
+
+    def publish_labels(self, labels):
+        pass
+
+    def get_labels(self):
+        pass

pr_agent/git_providers/codecommit_client.py

@@ -0,0 +1,272 @@
+import boto3
+import botocore
+
+
+class CodeCommitDifferencesResponse:
+    """
+    CodeCommitDifferencesResponse is the response object returned from our get_differences() function.
+    It maps the JSON response to member variables of this class.
+    """
+
+    def __init__(self, json: dict):
+        before_blob = json.get("beforeBlob", {})
+        after_blob = json.get("afterBlob", {})
+
+        self.before_blob_id = before_blob.get("blobId", "")
+        self.before_blob_path = before_blob.get("path", "")
+        self.after_blob_id = after_blob.get("blobId", "")
+        self.after_blob_path = after_blob.get("path", "")
+        self.change_type = json.get("changeType", "")
+
+
+class CodeCommitPullRequestResponse:
+    """
+    CodeCommitPullRequestResponse is the response object returned from our get_pr() function.
+    It maps the JSON response to member variables of this class.
+    """
+
+    def __init__(self, json: dict):
+        self.title = json.get("title", "")
+        self.description = json.get("description", "")
+
+        self.targets = []
+        for target in json.get("pullRequestTargets", []):
+            self.targets.append(CodeCommitPullRequestResponse.CodeCommitPullRequestTarget(target))
+
+    class CodeCommitPullRequestTarget:
+        """
+        CodeCommitPullRequestTarget is a subclass of CodeCommitPullRequestResponse that
+        holds details about an individual target commit.
+        """
+
+        def __init__(self, json: dict):
+            self.source_commit = json.get("sourceCommit", "")
+            self.source_branch = json.get("sourceReference", "")
+            self.destination_commit = json.get("destinationCommit", "")
+            self.destination_branch = json.get("destinationReference", "")
+
+
+class CodeCommitClient:
+    """
+    CodeCommitClient is a wrapper around the AWS boto3 SDK for the CodeCommit client
+    """
+
+    def __init__(self):
+        self.boto_client = None
+
+    def _connect_boto_client(self):
+        try:
+            self.boto_client = boto3.client("codecommit")
+        except Exception as e:
+            raise ValueError(f"Failed to connect to AWS CodeCommit: {e}")
+
+    def get_differences(self, repo_name: int, destination_commit: str, source_commit: str):
+        """
+        Get the differences between two commits in CodeCommit.
+
+        Args:
+        - repo_name: Name of the repository
+        - destination_commit: Commit hash you want to merge into (the "before" hash) (usually on the main or master branch)
+        - source_commit: Commit hash of the code you are adding (the "after" branch)
+
+        Returns:
+        - List of CodeCommitDifferencesResponse objects
+
+        Boto3 Documentation:
+        - aws codecommit get-differences
+        - https://boto3.amazonaws.com/v1/documentation/api/latest/reference/services/codecommit/client/get_differences.html
+        """
+        if self.boto_client is None:
+            self._connect_boto_client()
+
+        # The differences response from AWS is paginated, so we need to iterate through the pages to get all the differences.
+        differences = []
+        try:
+            paginator = self.boto_client.get_paginator("get_differences")
+            for page in paginator.paginate(
+                repositoryName=repo_name,
+                beforeCommitSpecifier=destination_commit,
+                afterCommitSpecifier=source_commit,
+            ):
+                differences.extend(page.get("differences", []))
+        except botocore.exceptions.ClientError as e:
+            if e.response["Error"]["Code"] == 'RepositoryDoesNotExistException':
+                raise ValueError(f"CodeCommit cannot retrieve differences: Repository does not exist: {repo_name}") from e
+            raise ValueError(f"CodeCommit cannot retrieve differences for {source_commit}..{destination_commit}") from e
+        except Exception as e:
+            raise ValueError(f"CodeCommit cannot retrieve differences for {source_commit}..{destination_commit}") from e
+
+        output = []
+        for json in differences:
+            output.append(CodeCommitDifferencesResponse(json))
+        return output
+
+    def get_file(self, repo_name: str, file_path: str, sha_hash: str, optional: bool = False):
+        """
+        Retrieve a file from CodeCommit.
+
+        Args:
+        - repo_name: Name of the repository
+        - file_path: Path to the file you are retrieving
+        - sha_hash: Commit hash of the file you are retrieving
+
+        Returns:
+        - File contents
+
+        Boto3 Documentation:
+        - aws codecommit get_file
+        - https://boto3.amazonaws.com/v1/documentation/api/latest/reference/services/codecommit/client/get_file.html
+        """
+        if not file_path:
+            return ""
+
+        if self.boto_client is None:
+            self._connect_boto_client()
+
+        try:
+            response = self.boto_client.get_file(repositoryName=repo_name, commitSpecifier=sha_hash, filePath=file_path)
+        except botocore.exceptions.ClientError as e:
+            if e.response["Error"]["Code"] == 'RepositoryDoesNotExistException':
+                raise ValueError(f"CodeCommit cannot retrieve PR: Repository does not exist: {repo_name}") from e
+            # if the file does not exist, but is flagged as optional, then return an empty string
+            if optional and e.response["Error"]["Code"] == 'FileDoesNotExistException':
+                return ""
+            raise ValueError(f"CodeCommit cannot retrieve file '{file_path}' from repository '{repo_name}'") from e
+        except Exception as e:
+            raise ValueError(f"CodeCommit cannot retrieve file '{file_path}' from repository '{repo_name}'") from e
+        if "fileContent" not in response:
+            raise ValueError(f"File content is empty for file: {file_path}")
+
+        return response.get("fileContent", "")
+
+    def get_pr(self, repo_name: str, pr_number: int):
+        """
+        Get a information about a CodeCommit PR.
+
+        Args:
+        - repo_name: Name of the repository
+        - pr_number: The PR number you are requesting
+
+        Returns:
+        - CodeCommitPullRequestResponse object
+
+        Boto3 Documentation:
+        - aws codecommit get_pull_request
+        - https://boto3.amazonaws.com/v1/documentation/api/latest/reference/services/codecommit/client/get_pull_request.html
+        """
+        if self.boto_client is None:
+            self._connect_boto_client()
+
+        try:
+            response = self.boto_client.get_pull_request(pullRequestId=str(pr_number))
+        except botocore.exceptions.ClientError as e:
+            if e.response["Error"]["Code"] == 'PullRequestDoesNotExistException':
+                raise ValueError(f"CodeCommit cannot retrieve PR: PR number does not exist: {pr_number}") from e
+            if e.response["Error"]["Code"] == 'RepositoryDoesNotExistException':
+                raise ValueError(f"CodeCommit cannot retrieve PR: Repository does not exist: {repo_name}") from e
+            raise ValueError(f"CodeCommit cannot retrieve PR: {pr_number}: boto client error") from e
+        except Exception as e:
+            raise ValueError(f"CodeCommit cannot retrieve PR: {pr_number}") from e
+
+        if "pullRequest" not in response:
+            raise ValueError("CodeCommit PR number not found: {pr_number}")
+
+        return CodeCommitPullRequestResponse(response.get("pullRequest", {}))
+
+    def publish_description(self, pr_number: int, pr_title: str, pr_body: str):
+        """
+        Set the title and description on a pull request
+
+        Args:
+        - pr_number: the AWS CodeCommit pull request number
+        - pr_title: title of the pull request
+        - pr_body: body of the pull request
+
+        Returns:
+        - None
+
+        Boto3 Documentation:
+        - aws codecommit update_pull_request_title
+        - https://boto3.amazonaws.com/v1/documentation/api/latest/reference/services/codecommit/client/update_pull_request_title.html
+        - aws codecommit update_pull_request_description
+        - https://boto3.amazonaws.com/v1/documentation/api/latest/reference/services/codecommit/client/update_pull_request_description.html
+        """
+        if self.boto_client is None:
+            self._connect_boto_client()
+
+        try:
+            self.boto_client.update_pull_request_title(pullRequestId=str(pr_number), title=pr_title)
+            self.boto_client.update_pull_request_description(pullRequestId=str(pr_number), description=pr_body)
+        except botocore.exceptions.ClientError as e:
+            if e.response["Error"]["Code"] == 'PullRequestDoesNotExistException':
+                raise ValueError(f"PR number does not exist: {pr_number}") from e
+            if e.response["Error"]["Code"] == 'InvalidTitleException':
+                raise ValueError(f"Invalid title for PR number: {pr_number}") from e
+            if e.response["Error"]["Code"] == 'InvalidDescriptionException':
+                raise ValueError(f"Invalid description for PR number: {pr_number}") from e
+            if e.response["Error"]["Code"] == 'PullRequestAlreadyClosedException':
+                raise ValueError(f"PR is already closed: PR number: {pr_number}") from e
+            raise ValueError(f"Boto3 client error calling publish_description") from e
+        except Exception as e:
+            raise ValueError(f"Error calling publish_description") from e
+
+    def publish_comment(self, repo_name: str, pr_number: int, destination_commit: str, source_commit: str, comment: str, annotation_file: str = None, annotation_line: int = None):
+        """
+        Publish a comment to a pull request
+
+        Args:
+        - repo_name: name of the repository
+        - pr_number: number of the pull request
+        - destination_commit: The commit hash you want to merge into (the "before" hash) (usually on the main or master branch)
+        - source_commit: The commit hash of the code you are adding (the "after" branch)
+        - comment: The comment you want to publish
+        - annotation_file: The file you want to annotate (optional)
+        - annotation_line: The line number you want to annotate (optional)
+
+        Comment annotations for CodeCommit are different than GitHub.
+        CodeCommit only designates the starting line number for the comment.
+        It does not support the ending line number to highlight a range of lines.
+
+        Returns:
+        - None
+
+        Boto3 Documentation:
+        - aws codecommit post_comment_for_pull_request
+        - https://boto3.amazonaws.com/v1/documentation/api/latest/reference/services/codecommit/client/post_comment_for_pull_request.html
+        """
+        if self.boto_client is None:
+            self._connect_boto_client()
+
+        try:
+            # If the comment has code annotations,
+            # then set the file path and line number in the location dictionary
+            if annotation_file and annotation_line:
+                self.boto_client.post_comment_for_pull_request(
+                    pullRequestId=str(pr_number),
+                    repositoryName=repo_name,
+                    beforeCommitId=destination_commit,
+                    afterCommitId=source_commit,
+                    content=comment,
+                    location={
+                        "filePath": annotation_file,
+                        "filePosition": annotation_line,
+                        "relativeFileVersion": "AFTER",
+                    },
+                )
+            else:
+                # The comment does not have code annotations
+                self.boto_client.post_comment_for_pull_request(
+                    pullRequestId=str(pr_number),
+                    repositoryName=repo_name,
+                    beforeCommitId=destination_commit,
+                    afterCommitId=source_commit,
+                    content=comment,
+                )
+        except botocore.exceptions.ClientError as e:
+            if e.response["Error"]["Code"] == 'RepositoryDoesNotExistException':
+                raise ValueError(f"Repository does not exist: {repo_name}") from e
+            if e.response["Error"]["Code"] == 'PullRequestDoesNotExistException':
+                raise ValueError(f"PR number does not exist: {pr_number}") from e
+            raise ValueError(f"Boto3 client error calling post_comment_for_pull_request") from e
+        except Exception as e:
+            raise ValueError(f"Error calling post_comment_for_pull_request") from e

pr_agent/git_providers/codecommit_provider.py

@@ -0,0 +1,480 @@
+import logging
+import os
+import re
+from collections import Counter
+from typing import List, Optional, Tuple
+from urllib.parse import urlparse
+
+from ..algo.language_handler import is_valid_file, language_extension_map
+from ..algo.pr_processing import clip_tokens
+from ..algo.utils import load_large_diff
+from ..config_loader import get_settings
+from .git_provider import EDIT_TYPE, FilePatchInfo, GitProvider, IncrementalPR
+from pr_agent.git_providers.codecommit_client import CodeCommitClient
+
+
+class PullRequestCCMimic:
+    """
+    This class mimics the PullRequest class from the PyGithub library for the CodeCommitProvider.
+    """
+
+    def __init__(self, title: str, diff_files: List[FilePatchInfo]):
+        self.title = title
+        self.diff_files = diff_files
+        self.description = None
+        self.source_commit = None
+        self.source_branch = None  # the branch containing your new code changes
+        self.destination_commit = None
+        self.destination_branch = None  # the branch you are going to merge into
+
+
+class CodeCommitFile:
+    """
+    This class represents a file in a pull request in CodeCommit.
+    """
+
+    def __init__(
+        self,
+        a_path: str,
+        a_blob_id: str,
+        b_path: str,
+        b_blob_id: str,
+        edit_type: EDIT_TYPE,
+    ):
+        self.a_path = a_path
+        self.a_blob_id = a_blob_id
+        self.b_path = b_path
+        self.b_blob_id = b_blob_id
+        self.edit_type: EDIT_TYPE = edit_type
+        self.filename = b_path if b_path else a_path
+
+
+class CodeCommitProvider(GitProvider):
+    """
+    This class implements the GitProvider interface for AWS CodeCommit repositories.
+    """
+
+    def __init__(self, pr_url: Optional[str] = None, incremental: Optional[bool] = False):
+        self.codecommit_client = CodeCommitClient()
+        self.aws_client = None
+        self.repo_name = None
+        self.pr_num = None
+        self.pr = None
+        self.diff_files = None
+        self.git_files = None
+        if pr_url:
+            self.set_pr(pr_url)
+
+    def provider_name(self):
+        return "CodeCommit"
+
+    def is_supported(self, capability: str) -> bool:
+        if capability in [
+            "get_issue_comments",
+            "create_inline_comment",
+            "publish_inline_comments",
+            "get_labels",
+        ]:
+            return False
+        return True
+
+    def set_pr(self, pr_url: str):
+        self.repo_name, self.pr_num = self._parse_pr_url(pr_url)
+        self.pr = self._get_pr()
+
+    def get_files(self) -> list[CodeCommitFile]:
+        # bring files from CodeCommit only once
+        if self.git_files:
+            return self.git_files
+
+        self.git_files = []
+        differences = self.codecommit_client.get_differences(self.repo_name, self.pr.destination_commit, self.pr.source_commit)
+        for item in differences:
+            self.git_files.append(CodeCommitFile(item.before_blob_path,
+                                                 item.before_blob_id,
+                                                 item.after_blob_path,
+                                                 item.after_blob_id,
+                                                 CodeCommitProvider._get_edit_type(item.change_type)))
+        return self.git_files
+
+    def get_diff_files(self) -> list[FilePatchInfo]:
+        """
+        Retrieves the list of files that have been modified, added, deleted, or renamed in a pull request in CodeCommit,
+        along with their content and patch information.
+
+        Returns:
+            diff_files (List[FilePatchInfo]): List of FilePatchInfo objects representing the modified, added, deleted,
+            or renamed files in the merge request.
+        """
+        # bring files from CodeCommit only once
+        if self.diff_files:
+            return self.diff_files
+
+        self.diff_files = []
+
+        files = self.get_files()
+        for diff_item in files:
+            patch_filename = ""
+            if diff_item.a_blob_id is not None:
+                patch_filename = diff_item.a_path
+                original_file_content_str = self.codecommit_client.get_file(
+                    self.repo_name, diff_item.a_path, self.pr.destination_commit)
+                if isinstance(original_file_content_str, (bytes, bytearray)):
+                    original_file_content_str = original_file_content_str.decode("utf-8")
+            else:
+                original_file_content_str = ""
+
+            if diff_item.b_blob_id is not None:
+                patch_filename = diff_item.b_path
+                new_file_content_str = self.codecommit_client.get_file(self.repo_name, diff_item.b_path, self.pr.source_commit)
+                if isinstance(new_file_content_str, (bytes, bytearray)):
+                    new_file_content_str = new_file_content_str.decode("utf-8")
+            else:
+                new_file_content_str = ""
+
+            patch = load_large_diff(patch_filename, new_file_content_str, original_file_content_str)
+
+            # Store the diffs as a list of FilePatchInfo objects
+            info = FilePatchInfo(
+                original_file_content_str,
+                new_file_content_str,
+                patch,
+                diff_item.b_path,
+                edit_type=diff_item.edit_type,
+                old_filename=None
+                if diff_item.a_path == diff_item.b_path
+                else diff_item.a_path,
+            )
+            # Only add valid files to the diff list
+            # "bad extensions" are set in the language_extensions.toml file
+            # a "valid file" is one that is not in the "bad extensions" list
+            if is_valid_file(info.filename):
+                self.diff_files.append(info)
+
+        return self.diff_files
+
+    def publish_description(self, pr_title: str, pr_body: str):
+        try:
+            self.codecommit_client.publish_description(
+                pr_number=self.pr_num,
+                pr_title=pr_title,
+                pr_body=CodeCommitProvider._add_additional_newlines(pr_body),
+            )
+        except Exception as e:
+            raise ValueError(f"CodeCommit Cannot publish description for PR: {self.pr_num}") from e    
+
+    def publish_comment(self, pr_comment: str, is_temporary: bool = False):
+        if is_temporary:
+            logging.info(pr_comment)
+            return
+
+        pr_comment = CodeCommitProvider._remove_markdown_html(pr_comment)
+        pr_comment = CodeCommitProvider._add_additional_newlines(pr_comment)
+
+        try:
+            self.codecommit_client.publish_comment(
+                repo_name=self.repo_name,
+                pr_number=self.pr_num,
+                destination_commit=self.pr.destination_commit,
+                source_commit=self.pr.source_commit,
+                comment=pr_comment,
+            )
+        except Exception as e:
+            raise ValueError(f"CodeCommit Cannot publish comment for PR: {self.pr_num}") from e
+
+    def publish_code_suggestions(self, code_suggestions: list) -> bool:
+        counter = 1
+        for suggestion in code_suggestions:
+            # Verify that each suggestion has the required keys
+            if not all(key in suggestion for key in ["body", "relevant_file", "relevant_lines_start"]):
+                logging.warning(f"Skipping code suggestion #{counter}: Each suggestion must have 'body', 'relevant_file', 'relevant_lines_start' keys")
+                continue
+       
+            # Publish the code suggestion to CodeCommit
+            try:
+                logging.debug(f"Code Suggestion #{counter} in file: {suggestion['relevant_file']}: {suggestion['relevant_lines_start']}")
+                self.codecommit_client.publish_comment(
+                    repo_name=self.repo_name,
+                    pr_number=self.pr_num,
+                    destination_commit=self.pr.destination_commit,
+                    source_commit=self.pr.source_commit,
+                    comment=suggestion["body"],
+                    annotation_file=suggestion["relevant_file"],
+                    annotation_line=suggestion["relevant_lines_start"],
+                )
+            except Exception as e:
+                raise ValueError(f"CodeCommit Cannot publish code suggestions for PR: {self.pr_num}") from e
+            
+            counter += 1
+
+        # The calling function passes in a list of code suggestions, and this function publishes each suggestion one at a time.
+        # If we were to return False here, the calling function will attempt to publish the same list of code suggestions again, one at a time.
+        # Since this function publishes the suggestions one at a time anyway, we always return True here to avoid the retry.        
+        return True
+
+    def publish_labels(self, labels):
+        return [""]  # not implemented yet
+
+    def get_labels(self):
+        return [""]  # not implemented yet
+
+    def remove_initial_comment(self):
+        return ""  # not implemented yet
+
+    def publish_inline_comment(self, body: str, relevant_file: str, relevant_line_in_file: str):
+        # https://boto3.amazonaws.com/v1/documentation/api/latest/reference/services/codecommit/client/post_comment_for_compared_commit.html
+        raise NotImplementedError("CodeCommit provider does not support publishing inline comments yet")
+
+    def create_inline_comment(self, body: str, relevant_file: str, relevant_line_in_file: str):
+        raise NotImplementedError("CodeCommit provider does not support creating inline comments yet")
+
+    def publish_inline_comments(self, comments: list[dict]):
+        raise NotImplementedError("CodeCommit provider does not support publishing inline comments yet")
+
+    def get_title(self):
+        return self.pr.get("title", "")
+
+    def get_languages(self):
+        """
+        Returns a dictionary of languages, containing the percentage of each language used in the PR.
+
+        Returns:
+        - dict: A dictionary where each key is a language name and the corresponding value is the percentage of that language in the PR.
+        """
+        commit_files = self.get_files()
+        filenames = [ item.filename for item in commit_files ]
+        extensions = CodeCommitProvider._get_file_extensions(filenames)
+
+        # Calculate the percentage of each file extension in the PR
+        percentages = CodeCommitProvider._get_language_percentages(extensions)
+
+        # The global language_extension_map is a dictionary of languages,
+        # where each dictionary item is a BoxList of extensions.
+        # We want a dictionary of extensions,
+        # where each dictionary item is a language name.
+        # We build that language->extension dictionary here in main_extensions_flat.
+        main_extensions_flat = {}
+        for language, extensions in language_extension_map.items():
+            for ext in extensions:
+                main_extensions_flat[ext] = language
+
+        # Map the file extension/languages to percentages
+        languages = {}
+        for ext, pct in percentages.items():
+            languages[main_extensions_flat.get(ext, "")] = pct
+
+        return languages
+
+    def get_pr_branch(self):
+        return self.pr.source_branch
+
+    def get_pr_description_full(self) -> str:
+        return self.pr.description
+
+    def get_user_id(self):
+        return -1  # not implemented yet
+
+    def get_issue_comments(self):
+        raise NotImplementedError("CodeCommit provider does not support issue comments yet")
+
+    def get_repo_settings(self):
+        # a local ".pr_agent.toml" settings file is optional
+        settings_filename = ".pr_agent.toml"
+        return self.codecommit_client.get_file(self.repo_name, settings_filename, self.pr.source_commit, optional=True)
+
+    def add_eyes_reaction(self, issue_comment_id: int) -> Optional[int]:
+        logging.info("CodeCommit provider does not support eyes reaction yet")
+        return True
+
+    def remove_reaction(self, issue_comment_id: int, reaction_id: int) -> bool:
+        logging.info("CodeCommit provider does not support removing reactions yet")
+        return True
+
+    @staticmethod
+    def _parse_pr_url(pr_url: str) -> Tuple[str, int]:
+        """
+        Parse the CodeCommit PR URL and return the repository name and PR number.
+
+        Args:
+        - pr_url: the full AWS CodeCommit pull request URL
+
+        Returns:
+        - Tuple[str, int]: A tuple containing the repository name and PR number.
+        """
+        # Example PR URL:
+        # https://us-east-1.console.aws.amazon.com/codesuite/codecommit/repositories/__MY_REPO__/pull-requests/123456"
+        parsed_url = urlparse(pr_url)
+
+        if not CodeCommitProvider._is_valid_codecommit_hostname(parsed_url.netloc):
+            raise ValueError(f"The provided URL is not a valid CodeCommit URL: {pr_url}")
+
+        path_parts = parsed_url.path.strip("/").split("/")
+
+        if (
+            len(path_parts) < 6
+            or path_parts[0] != "codesuite"
+            or path_parts[1] != "codecommit"
+            or path_parts[2] != "repositories"
+            or path_parts[4] != "pull-requests"
+        ):
+            raise ValueError(f"The provided URL does not appear to be a CodeCommit PR URL: {pr_url}")
+
+        repo_name = path_parts[3]
+
+        try:
+            pr_number = int(path_parts[5])
+        except ValueError as e:
+            raise ValueError(f"Unable to convert PR number to integer: '{path_parts[5]}'") from e
+
+        return repo_name, pr_number
+
+    @staticmethod
+    def _is_valid_codecommit_hostname(hostname: str) -> bool:
+        """
+        Check if the provided hostname is a valid AWS CodeCommit hostname.
+
+        This is not an exhaustive check of AWS region names, 
+        but instead uses a regex to check for matching AWS region patterns.
+
+        Args:
+        - hostname: the hostname to check
+
+        Returns:
+        - bool: True if the hostname is valid, False otherwise.
+        """
+        return re.match(r"^[a-z]{2}-(gov-)?[a-z]+-\d\.console\.aws\.amazon\.com$", hostname) is not None
+
+    def _get_pr(self):
+        response = self.codecommit_client.get_pr(self.repo_name, self.pr_num)
+
+        if len(response.targets) == 0:
+            raise ValueError(f"No files found in CodeCommit PR: {self.pr_num}")
+
+        # TODO: implement support for multiple targets in one CodeCommit PR
+        #       for now, we are only using the first target in the PR
+        if len(response.targets) > 1:
+            logging.warning(
+                "Multiple targets in one PR is not supported for CodeCommit yet. Continuing, using the first target only..."
+            )
+
+        # Return our object that mimics PullRequest class from the PyGithub library
+        # (This strategy was copied from the LocalGitProvider)
+        mimic = PullRequestCCMimic(response.title, self.diff_files)
+        mimic.description = response.description
+        mimic.source_commit = response.targets[0].source_commit
+        mimic.source_branch = response.targets[0].source_branch
+        mimic.destination_commit = response.targets[0].destination_commit
+        mimic.destination_branch = response.targets[0].destination_branch
+
+        return mimic
+
+    def get_commit_messages(self):
+        return ""  # not implemented yet
+
+    @staticmethod
+    def _add_additional_newlines(body: str) -> str:
+        """
+        Replace single newlines in a PR body with double newlines.
+
+        CodeCommit Markdown does not seem to render as well as GitHub Markdown,
+        so we add additional newlines to the PR body to make it more readable in CodeCommit.
+
+        Args:
+        - body: the PR body
+
+        Returns:
+        - str: the PR body with the double newlines added
+        """
+        return re.sub(r'(?<!\n)\n(?!\n)', '\n\n', body)
+
+    @staticmethod
+    def _remove_markdown_html(comment: str) -> str:
+        """
+        Remove the HTML tags from a PR comment.
+
+        CodeCommit Markdown does not seem to render as well as GitHub Markdown,
+        so we remove the HTML tags from the PR comment to make it more readable in CodeCommit.
+
+        Args:
+        - comment: the PR comment
+
+        Returns:
+        - str: the PR comment with the HTML tags removed
+        """
+        comment = comment.replace("<details>", "")
+        comment = comment.replace("</details>", "")
+        comment = comment.replace("<summary>", "")
+        comment = comment.replace("</summary>", "")
+        return comment
+
+    @staticmethod
+    def _get_edit_type(codecommit_change_type: str):
+        """
+        Convert the CodeCommit change type string to the EDIT_TYPE enum.
+        The CodeCommit change type string is returned from the get_differences SDK method.
+
+        Args:
+        - codecommit_change_type: the CodeCommit change type string
+
+        Returns:
+        - An EDIT_TYPE enum representing the modified, added, deleted, or renamed file in the PR diff.
+        """
+        t = codecommit_change_type.upper()
+        edit_type = None
+        if t == "A":
+            edit_type = EDIT_TYPE.ADDED
+        elif t == "D":
+            edit_type = EDIT_TYPE.DELETED
+        elif t == "M":
+            edit_type = EDIT_TYPE.MODIFIED
+        elif t == "R":
+            edit_type = EDIT_TYPE.RENAMED
+        return edit_type
+
+    @staticmethod
+    def _get_file_extensions(filenames):
+        """
+        Return a list of file extensions from a list of filenames.
+        The returned extensions will include the dot "." prefix,
+        to accommodate for the dots in the existing language_extension_map settings.
+        Filenames with no extension will return an empty string for the extension.
+
+        Args:
+        - filenames: a list of filenames
+
+        Returns:
+        - list: A list of file extensions, including the dot "." prefix.
+        """
+        extensions = []
+        for filename in filenames:
+            filename, ext = os.path.splitext(filename)
+            if ext:
+                extensions.append(ext.lower())
+            else:
+                extensions.append("")
+        return extensions
+
+    @staticmethod
+    def _get_language_percentages(extensions):
+        """
+        Return a dictionary containing the programming language name (as the key),
+        and the percentage that language is used (as the value),
+        given a list of file extensions.
+
+        Args:
+        - extensions: a list of file extensions
+
+        Returns:
+        - dict: A dictionary where each key is a language name and the corresponding value is the percentage of that language in the PR.
+        """
+        total_files = len(extensions)
+        if total_files == 0:
+            return {}
+
+        # Identify language by file extension and count
+        lang_count = Counter(extensions)
+        # Convert counts to percentages
+        lang_percentage = {
+            lang: round(count / total_files * 100) for lang, count in lang_count.items()
+        }
+        return lang_percentage

pr_agent/git_providers/git_provider.py

@@ -1,3 +1,4 @@
+import logging
 from abc import ABC, abstractmethod
 from dataclasses import dataclass
 
@@ -54,7 +55,7 @@ class GitProvider(ABC):
         pass
 
     @abstractmethod
-    def publish_code_suggestions(self, code_suggestions: list):
+    def publish_code_suggestions(self, code_suggestions: list) -> bool:
         pass
 
     @abstractmethod
@@ -82,9 +83,30 @@ class GitProvider(ABC):
         pass
 
     @abstractmethod
-    def get_pr_description(self):
+    def get_pr_description_full(self) -> str:
         pass
 
+    def get_pr_description(self, *, full: bool = True) -> str:
+        from pr_agent.config_loader import get_settings
+        from pr_agent.algo.pr_processing import clip_tokens
+        max_tokens = get_settings().get("CONFIG.MAX_DESCRIPTION_TOKENS", None)
+        description = self.get_pr_description_full() if full else self.get_user_description()
+        if max_tokens:
+            return clip_tokens(description, max_tokens)
+        return description
+
+    def get_user_description(self) -> str:
+        description = (self.get_pr_description_full() or "").strip()
+        # if the existing description wasn't generated by the pr-agent, just return it as-is
+        if not description.startswith("## PR Type"):
+            return description
+        # if the existing description was generated by the pr-agent, but it doesn't contain the user description,
+        # return nothing (empty string) because it means there is no user description
+        if "## User Description:" not in description:
+            return ""
+        # otherwise, extract the original user description from the existing pr-agent description and return it
+        return description.split("## User Description:", 1)[1].strip()
+
     @abstractmethod
     def get_issue_comments(self):
         pass
@@ -116,6 +138,8 @@ def get_main_pr_language(languages, files) -> str:
         # validate that the specific commit uses the main language
         extension_list = []
         for file in files:
+            if isinstance(file, str):
+                file = FilePatchInfo(base_file=None, head_file=None, patch=None, filename=file)
             extension_list.append(file.filename.rsplit('.')[-1])
 
         # get the most common extension
@@ -137,10 +161,11 @@ def get_main_pr_language(languages, files) -> str:
                 most_common_extension == 'scala' and top_language == 'scala' or \
                 most_common_extension == 'kt' and top_language == 'kotlin' or \
                 most_common_extension == 'pl' and top_language == 'perl' or \
-                most_common_extension == 'swift' and top_language == 'swift':
+                most_common_extension == top_language:
             main_language_str = top_language
 
-    except Exception:
+    except Exception as e:
+        logging.exception(e)
         pass
 
     return main_language_str

pr_agent/git_providers/github_provider.py

@@ -166,7 +166,7 @@ class GithubProvider(GitProvider):
     def publish_inline_comments(self, comments: list[dict]):
         self.pr.create_review(commit=self.last_commit_id, comments=comments)
 
-    def publish_code_suggestions(self, code_suggestions: list):
+    def publish_code_suggestions(self, code_suggestions: list) -> bool:
         """
         Publishes code suggestions as comments on the PR.
         """
@@ -233,10 +233,7 @@ class GithubProvider(GitProvider):
     def get_pr_branch(self):
         return self.pr.head.ref
 
-    def get_pr_description(self):
-        max_tokens = get_settings().get("CONFIG.MAX_DESCRIPTION_TOKENS", None)
-        if max_tokens:
-            return clip_tokens(self.pr.body, max_tokens)
+    def get_pr_description_full(self):
         return self.pr.body
 
     def get_user_id(self):

pr_agent/git_providers/gitlab_provider.py

@@ -14,6 +14,9 @@ from .git_provider import EDIT_TYPE, FilePatchInfo, GitProvider
 
 logger = logging.getLogger()
 
+class DiffNotFoundError(Exception):
+    """Raised when the diff for a merge request cannot be found."""
+    pass
 
 class GitLabProvider(GitProvider):
 
@@ -56,7 +59,7 @@ class GitLabProvider(GitProvider):
             self.last_diff = self.mr.diffs.list(get_all=True)[-1]
         except IndexError as e:
             logger.error(f"Could not get diff for merge request {self.id_mr}")
-            raise ValueError(f"Could not get diff for merge request {self.id_mr}") from e
+            raise DiffNotFoundError(f"Could not get diff for merge request {self.id_mr}") from e
 
 
     def _get_pr_file_content(self, file_path: str, branch: str) -> str:
@@ -150,16 +153,20 @@ class GitLabProvider(GitProvider):
     def create_inline_comments(self, comments: list[dict]):
         raise NotImplementedError("Gitlab provider does not support publishing inline comments yet")
 
-    def send_inline_comment(self, body, edit_type, found, relevant_file, relevant_line_in_file, source_line_no,
-                            target_file, target_line_no):
+    def send_inline_comment(self,body: str,edit_type: str,found: bool,relevant_file: str,relevant_line_in_file: int,
+                            source_line_no: int, target_file: str,target_line_no: int) -> None:
         if not found:
             logging.info(f"Could not find position for {relevant_file} {relevant_line_in_file}")
         else:
-            d = self.last_diff
+            # in order to have exact sha's we have to find correct diff for this change
+            diff = self.get_relevant_diff(relevant_file, relevant_line_in_file)
+            if diff is None:
+                logger.error(f"Could not get diff for merge request {self.id_mr}")
+                raise DiffNotFoundError(f"Could not get diff for merge request {self.id_mr}")
             pos_obj = {'position_type': 'text',
                        'new_path': target_file.filename,
                        'old_path': target_file.old_filename if target_file.old_filename else target_file.filename,
-                       'base_sha': d.base_commit_sha, 'start_sha': d.start_commit_sha, 'head_sha': d.head_commit_sha}
+                       'base_sha': diff.base_commit_sha, 'start_sha': diff.start_commit_sha, 'head_sha': diff.head_commit_sha}
             if edit_type == 'deletion':
                 pos_obj['old_line'] = source_line_no - 1
             elif edit_type == 'addition':
@@ -171,7 +178,24 @@ class GitLabProvider(GitProvider):
             self.mr.discussions.create({'body': body,
                                         'position': pos_obj})
 
-    def publish_code_suggestions(self, code_suggestions: list):
+    def get_relevant_diff(self, relevant_file: str, relevant_line_in_file: int) -> Optional[dict]:
+        changes = self.mr.changes()  # Retrieve the changes for the merge request once
+        if not changes:
+            logging.error('No changes found for the merge request.')
+            return None
+        all_diffs = self.mr.diffs.list(get_all=True)
+        if not all_diffs:
+            logging.error('No diffs found for the merge request.')
+            return None
+        for diff in all_diffs:
+            for change in changes['changes']:
+                if change['new_path'] == relevant_file and relevant_line_in_file in change['diff']:
+                    return diff
+            logging.debug(
+                f'No relevant diff found for {relevant_file} {relevant_line_in_file}. Falling back to last diff.')
+        return self.last_diff  # fallback to last_diff if no relevant diff is found
+
+    def publish_code_suggestions(self, code_suggestions: list) -> bool:
         for suggestion in code_suggestions:
             try:
                 body = suggestion['body']
@@ -275,10 +299,7 @@ class GitLabProvider(GitProvider):
     def get_pr_branch(self):
         return self.mr.source_branch
 
-    def get_pr_description(self):
-        max_tokens = get_settings().get("CONFIG.MAX_DESCRIPTION_TOKENS", None)
-        if max_tokens:
-            return clip_tokens(self.mr.description, max_tokens)
+    def get_pr_description_full(self):
         return self.mr.description
 
     def get_issue_comments(self):

pr_agent/git_providers/local_git_provider.py

@@ -130,7 +130,7 @@ class LocalGitProvider(GitProvider):
                                 relevant_lines_start: int, relevant_lines_end: int):
         raise NotImplementedError('Publishing code suggestions is not implemented for the local git provider')
 
-    def publish_code_suggestions(self, code_suggestions: list):
+    def publish_code_suggestions(self, code_suggestions: list) -> bool:
         raise NotImplementedError('Publishing code suggestions is not implemented for the local git provider')
 
     def publish_labels(self, labels):
@@ -158,7 +158,7 @@ class LocalGitProvider(GitProvider):
     def get_user_id(self):
         return -1  # Not used anywhere for the local provider, but required by the interface
 
-    def get_pr_description(self):
+    def get_pr_description_full(self):
         commits_diff = list(self.repo.iter_commits(self.target_branch_name + '..HEAD'))
         # Get the commit messages and concatenate
         commit_messages = " ".join([commit.message for commit in commits_diff])

pr_agent/secret_providers/__init__.py

@@ -0,0 +1,16 @@
+from pr_agent.config_loader import get_settings
+
+
+def get_secret_provider():
+    try:
+        provider_id = get_settings().config.secret_provider
+    except AttributeError as e:
+        raise ValueError("secret_provider is a required attribute in the configuration file") from e
+    try:
+        if provider_id == 'google_cloud_storage':
+            from pr_agent.secret_providers.google_cloud_storage_secret_provider import GoogleCloudStorageSecretProvider
+            return GoogleCloudStorageSecretProvider()
+        else:
+            raise ValueError(f"Unknown secret provider: {provider_id}")
+    except Exception as e:
+        raise ValueError(f"Failed to initialize secret provider {provider_id}") from e

pr_agent/secret_providers/google_cloud_storage_secret_provider.py

@@ -0,0 +1,35 @@
+import ujson
+
+from google.cloud import storage
+
+from pr_agent.config_loader import get_settings
+from pr_agent.git_providers.gitlab_provider import logger
+from pr_agent.secret_providers.secret_provider import SecretProvider
+
+
+class GoogleCloudStorageSecretProvider(SecretProvider):
+    def __init__(self):
+        try:
+            self.client = storage.Client.from_service_account_info(ujson.loads(get_settings().google_cloud_storage.
+                                                                               service_account))
+            self.bucket_name = get_settings().google_cloud_storage.bucket_name
+            self.bucket = self.client.bucket(self.bucket_name)
+        except Exception as e:
+            logger.error(f"Failed to initialize Google Cloud Storage Secret Provider: {e}")
+            raise e
+
+    def get_secret(self, secret_name: str) -> str:
+        try:
+            blob = self.bucket.blob(secret_name)
+            return blob.download_as_string()
+        except Exception as e:
+            logger.error(f"Failed to get secret {secret_name} from Google Cloud Storage: {e}")
+            return ""
+
+    def store_secret(self, secret_name: str, secret_value: str):
+        try:
+            blob = self.bucket.blob(secret_name)
+            blob.upload_from_string(secret_value)
+        except Exception as e:
+            logger.error(f"Failed to store secret {secret_name} in Google Cloud Storage: {e}")
+            raise e

pr_agent/secret_providers/secret_provider.py

@@ -0,0 +1,12 @@
+from abc import ABC, abstractmethod
+
+
+class SecretProvider(ABC):
+
+    @abstractmethod
+    def get_secret(self, secret_name: str) -> str:
+        pass
+
+    @abstractmethod
+    def store_secret(self, secret_name: str, secret_value: str):
+        pass

pr_agent/servers/atlassian-connect.json

@@ -0,0 +1,33 @@
+{
+  "name": "CodiumAI PR-Agent",
+  "description": "CodiumAI PR-Agent",
+  "key": "app_key",
+  "vendor": {
+    "name": "CodiumAI",
+    "url": "https://codium.ai"
+  },
+  "authentication": {
+    "type": "jwt"
+  },
+  "baseUrl": "base_url",
+  "lifecycle": {
+    "installed": "/installed",
+    "uninstalled": "/uninstalled"
+  },
+  "scopes": [
+    "account",
+    "repository",
+    "pullrequest"
+  ],
+  "contexts": [
+    "account"
+  ],
+  "modules": {
+    "webhooks": [
+      {
+        "event": "*",
+        "url": "/webhook"
+      }
+    ]
+  }
+}

pr_agent/servers/bitbucket_app.py

@@ -0,0 +1,139 @@
+import copy
+import hashlib
+import json
+import logging
+import os
+import sys
+import time
+
+import jwt
+import requests
+import uvicorn
+from fastapi import APIRouter, FastAPI, Request, Response
+from starlette.background import BackgroundTasks
+from starlette.middleware import Middleware
+from starlette.responses import JSONResponse
+from starlette_context import context
+from starlette_context.middleware import RawContextMiddleware
+
+from pr_agent.agent.pr_agent import PRAgent
+from pr_agent.config_loader import get_settings, global_settings
+from pr_agent.secret_providers import get_secret_provider
+
+logging.basicConfig(stream=sys.stdout, level=logging.INFO)
+router = APIRouter()
+secret_provider = get_secret_provider()
+
+async def get_bearer_token(shared_secret: str, client_key: str):
+    try:
+        now = int(time.time())
+        url = "https://bitbucket.org/site/oauth2/access_token"
+        canonical_url = "GET&/site/oauth2/access_token&"
+        qsh = hashlib.sha256(canonical_url.encode("utf-8")).hexdigest()
+        app_key = get_settings().bitbucket.app_key
+
+        payload = {
+            "iss": app_key,
+            "iat": now,
+            "exp": now + 240,
+            "qsh": qsh,
+            "sub": client_key,
+            }
+        token = jwt.encode(payload, shared_secret, algorithm="HS256")
+        payload = 'grant_type=urn%3Abitbucket%3Aoauth2%3Ajwt'
+        headers = {
+            'Authorization': f'JWT {token}',
+            'Content-Type': 'application/x-www-form-urlencoded'
+        }
+        response = requests.request("POST", url, headers=headers, data=payload)
+        bearer_token = response.json()["access_token"]
+        return bearer_token
+    except Exception as e:
+        logging.error(f"Failed to get bearer token: {e}")
+        raise e
+
+@router.get("/")
+async def handle_manifest(request: Request, response: Response):
+    cur_dir = os.path.dirname(os.path.abspath(__file__))
+    manifest = open(os.path.join(cur_dir, "atlassian-connect.json"), "rt").read()
+    try:
+        manifest = manifest.replace("app_key", get_settings().bitbucket.app_key)
+        manifest = manifest.replace("base_url", get_settings().bitbucket.base_url)
+    except:
+        logging.error("Failed to replace api_key in Bitbucket manifest, trying to continue")
+    manifest_obj = json.loads(manifest)
+    return JSONResponse(manifest_obj)
+
+@router.post("/webhook")
+async def handle_github_webhooks(background_tasks: BackgroundTasks, request: Request):
+    print(request.headers)
+    jwt_header = request.headers.get("authorization", None)
+    if jwt_header:
+        input_jwt = jwt_header.split(" ")[1]
+    data = await request.json()
+    print(data)
+    async def inner():
+        try:
+            owner = data["data"]["repository"]["owner"]["username"]
+            secrets = json.loads(secret_provider.get_secret(owner))
+            shared_secret = secrets["shared_secret"]
+            client_key = secrets["client_key"]
+            jwt.decode(input_jwt, shared_secret, audience=client_key, algorithms=["HS256"])
+            bearer_token = await get_bearer_token(shared_secret, client_key)
+            context['bitbucket_bearer_token'] = bearer_token
+            context["settings"] = copy.deepcopy(global_settings)
+            event = data["event"]
+            agent = PRAgent()
+            if event == "pullrequest:created":
+                pr_url = data["data"]["pullrequest"]["links"]["html"]["href"]
+                await agent.handle_request(pr_url, "review")
+            elif event == "pullrequest:comment_created":
+                pr_url = data["data"]["pullrequest"]["links"]["html"]["href"]
+                comment_body = data["data"]["comment"]["content"]["raw"]
+                await agent.handle_request(pr_url, comment_body)
+        except Exception as e:
+            logging.error(f"Failed to handle webhook: {e}")
+    background_tasks.add_task(inner)
+    return "OK"
+
+@router.get("/webhook")
+async def handle_github_webhooks(request: Request, response: Response):
+    return "Webhook server online!"
+
+@router.post("/installed")
+async def handle_installed_webhooks(request: Request, response: Response):
+    try:
+        print(request.headers)
+        data = await request.json()
+        print(data)
+        shared_secret = data["sharedSecret"]
+        client_key = data["clientKey"]
+        username = data["principal"]["username"]
+        secrets = {
+            "shared_secret": shared_secret,
+            "client_key": client_key
+        }
+        secret_provider.store_secret(username, json.dumps(secrets))
+    except Exception as e:
+        logging.error(f"Failed to register user: {e}")
+        return JSONResponse({"error": "Unable to register user"}, status_code=500)
+
+@router.post("/uninstalled")
+async def handle_uninstalled_webhooks(request: Request, response: Response):
+    data = await request.json()
+    print(data)
+
+
+def start():
+    get_settings().set("CONFIG.PUBLISH_OUTPUT_PROGRESS", False)
+    get_settings().set("CONFIG.GIT_PROVIDER", "bitbucket")
+    get_settings().set("PR_DESCRIPTION.PUBLISH_DESCRIPTION_AS_COMMENT", True)
+    middleware = [Middleware(RawContextMiddleware)]
+    app = FastAPI(middleware=middleware)
+    app.include_router(router)
+
+    uvicorn.run(app, host="0.0.0.0", port=int(os.getenv("PORT", "3000")))
+
+
+if __name__ == '__main__':
+    start()

pr_agent/servers/github_app.py

@@ -1,6 +1,8 @@
 import copy
 import logging
 import sys
+import os
+import time
 from typing import Any, Dict
 
 import uvicorn
@@ -10,11 +12,12 @@ from starlette_context import context
 from starlette_context.middleware import RawContextMiddleware
 
 from pr_agent.agent.pr_agent import PRAgent
+from pr_agent.algo.utils import update_settings_from_args
 from pr_agent.config_loader import get_settings, global_settings
 from pr_agent.git_providers import get_git_provider
 from pr_agent.servers.utils import verify_signature
 
-logging.basicConfig(stream=sys.stdout, level=logging.DEBUG)
+logging.basicConfig(stream=sys.stdout, level=logging.INFO)
 router = APIRouter()
 
 
@@ -34,7 +37,8 @@ async def handle_github_webhooks(request: Request, response: Response):
     context["installation_id"] = installation_id
     context["settings"] = copy.deepcopy(global_settings)
 
-    return await handle_request(body)
+    response = await handle_request(body, event=request.headers.get("X-GitHub-Event", None))
+    return response or {}
 
 
 @router.post("/api/v1/marketplace_webhooks")
@@ -48,71 +52,125 @@ async def get_body(request):
     except Exception as e:
         logging.error("Error parsing request body", e)
         raise HTTPException(status_code=400, detail="Error parsing request body") from e
-    body_bytes = await request.body()
-    signature_header = request.headers.get('x-hub-signature-256', None)
     webhook_secret = getattr(get_settings().github, 'webhook_secret', None)
     if webhook_secret:
+        body_bytes = await request.body()
+        signature_header = request.headers.get('x-hub-signature-256', None)
         verify_signature(body_bytes, webhook_secret, signature_header)
     return body
 
 
+_duplicate_requests_cache = {}
 
 
-async def handle_request(body: Dict[str, Any]):
+async def handle_request(body: Dict[str, Any], event: str):
     """
     Handle incoming GitHub webhook requests.
 
     Args:
         body: The request body.
+        event: The GitHub event type.
     """
     action = body.get("action")
     if not action:
         return {}
     agent = PRAgent()
+    bot_user = get_settings().github_app.bot_user
+    logging.info(f"action: '{action}'")
+    logging.info(f"event: '{event}'")
 
+    if get_settings().github_app.duplicate_requests_cache and _is_duplicate_request(body):
+        return {}
+
+    # handle all sorts of comment events (e.g. issue_comment)
     if action == 'created':
         if "comment" not in body:
             return {}
         comment_body = body.get("comment", {}).get("body")
         sender = body.get("sender", {}).get("login")
-        if sender and 'bot' in sender:
+        if sender and bot_user in sender:
+            logging.info(f"Ignoring comment from {bot_user} user")
             return {}
-        if "issue" not in body or "pull_request" not in body["issue"]:
+        logging.info(f"Processing comment from {sender} user")
+        if "issue" in body and "pull_request" in body["issue"] and "url" in body["issue"]["pull_request"]:
+            api_url = body["issue"]["pull_request"]["url"]
+        elif "comment" in body and "pull_request_url" in body["comment"]:
+            api_url = body["comment"]["pull_request_url"]
+        else:
             return {}
-        pull_request = body["issue"]["pull_request"]
-        api_url = pull_request.get("url")
+        logging.info(f"Handling comment because of event={event} and action={action}")
         comment_id = body.get("comment", {}).get("id")
         provider = get_git_provider()(pr_url=api_url)
         await agent.handle_request(api_url, comment_body, notify=lambda: provider.add_eyes_reaction(comment_id))
 
-
-    elif action == "opened" or 'reopened' in action:
+    # handle pull_request event:
+    #   automatically review opened/reopened/ready_for_review PRs as long as they're not in draft,
+    #   as well as direct review requests from the bot
+    elif event == 'pull_request':
         pull_request = body.get("pull_request")
         if not pull_request:
             return {}
         api_url = pull_request.get("url")
         if not api_url:
             return {}
-        await agent.handle_request(api_url, "/review")
+        if pull_request.get("draft", True) or pull_request.get("state") != "open" or pull_request.get("user", {}).get("login", "") == bot_user:
+            return {}
+        if action in get_settings().github_app.handle_pr_actions:
+            if action == "review_requested":
+                if body.get("requested_reviewer", {}).get("login", "") != bot_user:
+                    return {}
+                if pull_request.get("created_at") == pull_request.get("updated_at"):
+                    # avoid double reviews when opening a PR for the first time
+                    return {}
+            logging.info(f"Performing review because of event={event} and action={action}")
+            for command in get_settings().github_app.pr_commands:
+                split_command = command.split(" ")
+                command = split_command[0]
+                args = split_command[1:]
+                other_args = update_settings_from_args(args)
+                new_command = ' '.join([command] + other_args)
+                logging.info(f"Performing command: {new_command}")
+                await agent.handle_request(api_url, new_command)
 
+    logging.info("event or action does not require handling")
     return {}
 
 
+def _is_duplicate_request(body: Dict[str, Any]) -> bool:
+    """
+    In some deployments its possible to get duplicate requests if the handling is long,
+    This function checks if the request is duplicate and if so - ignores it.
+    """
+    request_hash = hash(str(body))
+    logging.info(f"request_hash: {request_hash}")
+    request_time = time.monotonic()
+    ttl = get_settings().github_app.duplicate_requests_cache_ttl  # in seconds
+    to_delete = [key for key, key_time in _duplicate_requests_cache.items() if request_time - key_time > ttl]
+    for key in to_delete:
+        del _duplicate_requests_cache[key]
+    is_duplicate = request_hash in _duplicate_requests_cache
+    _duplicate_requests_cache[request_hash] = request_time
+    if is_duplicate:
+        logging.info(f"Ignoring duplicate request {request_hash}")
+    return is_duplicate
+
+
 @router.get("/")
 async def root():
     return {"status": "ok"}
 
 
 def start():
-    # Override the deployment type to app
-    get_settings().set("GITHUB.DEPLOYMENT_TYPE", "app")
+    if get_settings().github_app.override_deployment_type:
+        # Override the deployment type to app
+        get_settings().set("GITHUB.DEPLOYMENT_TYPE", "app")
     get_settings().set("CONFIG.PUBLISH_OUTPUT_PROGRESS", False)
     middleware = [Middleware(RawContextMiddleware)]
     app = FastAPI(middleware=middleware)
     app.include_router(router)
 
-    uvicorn.run(app, host="0.0.0.0", port=3000)
+    uvicorn.run(app, host="0.0.0.0", port=int(os.environ.get("PORT", "3000")))
 
 
 if __name__ == '__main__':
-    start()
+    start()

pr_agent/servers/help.py

@@ -1,7 +1,7 @@
 commands_text = "> **/review [-i]**: Request a review of your Pull Request. For an incremental review, which only " \
                 "considers changes since the last review, include the '-i' option.\n" \
                 "> **/describe**: Modify the PR title and description based on the contents of the PR.\n" \
-                "> **/improve**: Suggest improvements to the code in the PR. \n" \
+                "> **/improve [--extended]**: Suggest improvements to the code in the PR. Extended mode employs several calls, and provides a more thorough feedback. \n" \
                 "> **/ask \\<QUESTION\\>**: Pose a question about the PR.\n" \
                 "> **/update_changelog**: Update the changelog based on the PR's contents.\n\n" \
                 ">To edit any configuration parameter from **configuration.toml**, add --config_path=new_value\n" \

pr_agent/settings/configuration.toml

@@ -10,19 +10,24 @@ use_repo_settings_file=true
 ai_timeout=180
 max_description_tokens = 500
 max_commits_tokens = 500
+litellm_debugger=false
+secret_provider="google_cloud_storage"
 
 [pr_reviewer] # /review #
-require_focused_review=true
+require_focused_review=false
 require_score_review=false
 require_tests_review=true
 require_security_review=true
-num_code_suggestions=3
+num_code_suggestions=4
 inline_code_comments = false
 ask_and_reflect=false
+automatic_review=true
 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 #
@@ -30,6 +35,12 @@ 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
@@ -42,6 +53,21 @@ extra_instructions = ""
 deployment_type = "user"
 ratelimit_retries = 5
 
+[github_app]
+# these toggles allows running the github app from custom deployments
+bot_user = "github-actions[bot]"
+override_deployment_type = true
+# in some deployments it's possible to get duplicate requests if the handling is long,
+# these settings are used to avoid handling duplicate requests.
+duplicate_requests_cache = false
+duplicate_requests_cache_ttl = 60  # in seconds
+# settings for "pull_request" event
+handle_pr_actions = ['opened', 'reopened', 'ready_for_review', 'review_requested']
+pr_commands = [
+    "/describe --pr_description.add_original_user_description=true --pr_description.keep_original_user_title=true",
+    "/auto_review",
+]
+
 [gitlab]
 # URL to the gitlab service
 url = "https://gitlab.com"

pr_agent/settings/pr_code_suggestions_prompts.toml

@@ -1,90 +1,130 @@
 [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 '+'.
-- 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.
+system="""You are a language model called PR-Code-Reviewer, that specializes in suggesting code improvements for Pull Request (PR).
+Your task is to provide meaningful and actionable code suggestions, to improve the new code presented in a PR.
+
+Example for a 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 line1 added in the PR
+15 +new code line2 added in the PR
+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:
 - 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.
+- Prioritize suggestions that address major problems, issues and bugs in the code.
+  As a second priority, suggestions should focus on best practices, code readability, maintainability, enhancments, performance, and other aspects.
+  Don't suggest to add docstring or type hints.
+  Try to provide diverse and insightful suggestions.
+- Suggestions should refer only to code from the '__new hunk__' sections, and focus on new lines of code (lines starting with '+').
+  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.
+  For each suggestion, make sure to take into consideration also the context, meaning the lines before and after the relevant code.
+- Provide the exact line numbers range (inclusive) for each issue.
+- Assume there is additional relevant code, that is not included in the diff.
+
 
 {%- if extra_instructions %}
 
 Extra instructions from the user:
 {{ extra_instructions }}
-{% endif %}
+{%- endif %}
 
-You must use the following JSON schema to format your answer:
-```json
-{
-    "Code suggestions": {
-      "type": "array",
-      "minItems": 1,
-      "maxItems": {{ num_code_suggestions }},
-      "uniqueItems": "true",
-      "items": {
-        "relevant file": {
-          "type": "string",
-          "description": "the relevant file full path"
-        },
-        "suggestion content": {
-          "type": "string",
-          "description": "a concrete suggestion for meaningfully improving the new PR code."
-        },
-        "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."
-        },
-        "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."
-        },
-        "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."
-        }
-      }
-    }
-}
+You must use the following YAML schema to format your answer:
+```yaml
+Code suggestions:
+  type: array
+  minItems: 1
+  maxItems: {{ num_code_suggestions }}
+  uniqueItems: true
+  items:
+    relevant file:
+      type: string
+      description: the relevant file full path
+    suggestion content:
+      type: string
+      description: |-
+        a concrete suggestion for meaningfully improving the new PR code.
+    existing code:
+      type: string
+      description: |-
+        a code snippet showing the relevant code lines from a '__new hunk__' section.
+        It must be contiguous, correctly formatted and indented, and without line numbers.
+    relevant lines start:
+      type: integer
+      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:
+      type: integer
+      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.
+    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.
 ```
 
-Example input:
-'
-## src/file1.py
----new_hunk---
+Example output:
+```yaml
+Code suggestions:
+  - relevant file: |-
+        src/file1.py
+    suggestion content: |-
+        Add a docstring to func1()
+    existing code: |-
+        def func1():
+    relevant lines start: 12
+    relevant lines end: 12
+    improved code: |-
+        ...
 ```
-[new hunk code, annotated with line numbers]
-```
----old_hunk---
-```
-[old hunk code]
-```
-...
-'
 
+
+Each YAML output MUST be after a newline, indented, with block scalar indicator ('|-').
 Don't repeat the prompt in the answer, and avoid outputting the 'type' and 'description' fields.
 """
 
 user="""PR Info:
-Title: '{{title}}'
-Branch: '{{branch}}'
-Description: '{{description}}'
-{%- if language %}
-Main language: {{language}}
-{%- endif %}
-{%- if commit_messages_str %}
 
-Commit messages:
-{{commit_messages_str}}
+Title: '{{title}}'
+
+Branch: '{{branch}}'
+
+Description: '{{description}}'
+
+{%- if language %}
+
+Main language: {{language}}
 {%- endif %}
 
 
 The PR Diff:
 ```
-{{diff}}
+{{- diff|trim }}
 ```
 
-Response (should be a valid JSON, and nothing else):
-```json
+Response (should be a valid YAML, and nothing else):
+```yaml
 """

pr_agent/settings/pr_reviewer_prompts.toml

@@ -1,13 +1,36 @@
 [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).
+system="""You are 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 meaningful code suggestions.
+
+Example PR Diff input:
+'
+## src/file1.py
+
+@@ -12,5 +12,5 @@ def func1():
+code line that already existed in the file...
+code line that already existed in the file....
+-code line that was removed in the PR
++new code line added in the PR
+ code line that already existed in the file...
+ code line that already existed in the file...
+
+@@ ... @@ def func2():
+...
+
+
+## src/file2.py
+...
+'
+
+Thre review should focus on new code added in the PR (lines starting with '+'), and not on code that already existed in the file (lines starting with '-', or without prefix).
+
 {%- 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.
-- 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).
+- 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.
+- 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 PR code.
+- Don't suggest to add docstring or type hints.
+- Suggestions should focus on improving the new code added in the PR (lines starting with '+')
 {%- endif %}
-- If needed, each YAML output should be in block scalar format ('|-')
 
 {%- if extra_instructions %}
 
@@ -21,6 +44,9 @@ PR Analysis:
   Main theme:
     type: string
     description: a short explanation of the PR
+  PR summary:
+    type: string
+    description: summary of the PR in 2-3 sentences.
   Type of PR:
     type: string
     enum:
@@ -33,7 +59,7 @@ PR Analysis:
 {%- if require_score %}
   Score:
     type: int
-    description: >-
+    description: |-
       Rate this PR on a scale of 0-100 (inclusive), where 0 means the worst
       possible PR code, and 100 means PR code of the highest quality, without
       any bugs or performance issues, that is ready to be merged immediately and
@@ -47,13 +73,13 @@ PR Analysis:
 {%- if question_str %}
   Insights from user's answer:
     type: string
-    description: >-
+    description: |-
       shortly summarize the insights you gained from the user's answers to the questions
 {%- endif %}
 {%- if require_focused %}
   Focused PR:
     type: string
-    description: >-
+    description: |-
       Is this a focused PR, in the sense that all the PR code diff changes are
       united under a single focused theme ? If the theme is too broad, or the PR
       code diff changes are too scattered, then the PR is not focused. Explain
@@ -62,12 +88,11 @@ PR Analysis:
 PR Feedback:
   General suggestions:
     type: string
-    description: >-
+    description: |-
       General suggestions and feedback for the contributors and maintainers of
       this PR. May include important suggestions for the overall structure,
       primary purpose, best practices, critical bugs, and other aspects of the
-      PR. Don't address PR title and description, or lack of tests. Explain your
-      suggestions.
+      PR. Don't address PR title and description, or lack of tests. Explain your suggestions.
 {%- if num_code_suggestions > 0 %}
   Code feedback:
     type: array
@@ -79,7 +104,7 @@ PR Feedback:
         description: the relevant file full path
       suggestion:
         type: string
-        description: |
+        description: |-
           a concrete suggestion for meaningfully improving the new PR code. Also
           describe how, specifically, the suggestion can be applied to new PR
           code. Add tags with importance measure that matches each suggestion
@@ -87,9 +112,9 @@ PR Feedback:
           adding docstrings, renaming PR title and description, or linter like.
       relevant line:
         type: string
-        description: |
+        description: |-
           a single code line taken from the relevant file, to which the suggestion applies.
-          The line should be a '+' line.
+          The code line should start with a '+'.
           Make sure to output the line exactly as it appears in the relevant file
 {%- endif %}
 {%- if require_security %}
@@ -104,22 +129,29 @@ PR Feedback:
 Example output:
 ```yaml
 PR Analysis:
-  Main theme: xxx
-  Type of PR: Bug fix
+  Main theme: |-
+    xxx
+  PR summary: |-
+    xxx
+  Type of PR: |-
+    Bug fix
 {%- if require_score %}
   Score: 89
 {%- endif %}
-  Relevant tests added: No
+  Relevant tests added: |-
+    No
 {%- if require_focused %}
   Focused PR: no, because ...
 {%- endif %}
 PR Feedback:
-  General PR suggestions: ...
+  General PR suggestions: |-
+    ...
 {%- if num_code_suggestions > 0 %}
   Code feedback:
     - relevant file: |-
         directory/xxx.py
-      suggestion: xxx [important]
+      suggestion: |-
+        xxx [important]
       relevant line: |-
         xxx
     ...
@@ -129,7 +161,7 @@ PR Feedback:
 {%- endif %}
 ```
 
-Make sure to output a valid YAML. Use multi-line block scalar ('|') if needed.
+Each YAML output MUST be after a newline, indented, with block scalar indicator ('|-').
 Don't repeat the prompt in the answer, and avoid outputting the 'type' and 'description' fields.
 """
 
@@ -161,7 +193,7 @@ The PR Git Diff:
 ```
 {{diff}}
 ```
-Note that lines in the diff body are prefixed with a symbol that represents the type of change: '-' for deletions, '+' for additions, and ' ' (a space) for unchanged lines.
+Note that lines in the diff body are prefixed with a symbol that represents the type of change: '-' for deletions, '+' for additions. Focus on the '+' lines.
 
 Response (should be a valid YAML, and nothing else):
 ```yaml

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
+"""

pr_agent/tools/pr_code_suggestions.py

@@ -1,14 +1,13 @@
 import copy
-import json
 import logging
 import textwrap
-
+from typing import List, Dict
 from jinja2 import Environment, StrictUndefined
 
 from pr_agent.algo.ai_handler import AiHandler
-from pr_agent.algo.pr_processing import get_pr_diff, retry_with_fallback_models
+from pr_agent.algo.pr_processing import get_pr_diff, retry_with_fallback_models, get_pr_multi_diffs
 from pr_agent.algo.token_handler import TokenHandler
-from pr_agent.algo.utils import try_fix_json
+from pr_agent.algo.utils import load_yaml
 from pr_agent.config_loader import get_settings
 from pr_agent.git_providers import BitbucketProvider, get_git_provider
 from pr_agent.git_providers.git_provider import get_main_pr_language
@@ -22,6 +21,13 @@ class PRCodeSuggestions:
             self.git_provider.get_languages(), self.git_provider.get_files()
         )
 
+        # extended mode
+        self.is_extended = any(["extended" in arg for arg in args])
+        if self.is_extended:
+            num_code_suggestions = get_settings().pr_code_suggestions.num_code_suggestions_per_chunk
+        else:
+            num_code_suggestions = get_settings().pr_code_suggestions.num_code_suggestions
+
         self.ai_handler = AiHandler()
         self.patches_diff = None
         self.prediction = None
@@ -32,7 +38,7 @@ class PRCodeSuggestions:
             "description": self.git_provider.get_pr_description(),
             "language": self.main_language,
             "diff": "",  # empty diff for initial calculation
-            "num_code_suggestions": get_settings().pr_code_suggestions.num_code_suggestions,
+            "num_code_suggestions": num_code_suggestions,
             "extra_instructions": get_settings().pr_code_suggestions.extra_instructions,
             "commit_messages_str": self.git_provider.get_commit_messages(),
         }
@@ -42,18 +48,26 @@ class PRCodeSuggestions:
                                           get_settings().pr_code_suggestions_prompt.user)
 
     async def run(self):
-        assert type(self.git_provider) != BitbucketProvider, "Bitbucket is not supported for now"
-
         logging.info('Generating code suggestions for PR...')
         if get_settings().config.publish_output:
             self.git_provider.publish_comment("Preparing review...", is_temporary=True)
-        await retry_with_fallback_models(self._prepare_prediction)
+
         logging.info('Preparing PR review...')
-        data = self._prepare_pr_code_suggestions()
+        if not self.is_extended:
+            await retry_with_fallback_models(self._prepare_prediction)
+            data = self._prepare_pr_code_suggestions()
+        else:
+            data = await retry_with_fallback_models(self._prepare_prediction_extended)
+
+        if (not self.is_extended and get_settings().pr_code_suggestions.rank_suggestions) or \
+                (self.is_extended and get_settings().pr_code_suggestions.rank_extended_suggestions):
+            logging.info('Ranking Suggestions...')
+            data['Code suggestions'] = await self.rank_suggestions(data['Code suggestions'])
+
         if get_settings().config.publish_output:
             logging.info('Pushing PR review...')
             self.git_provider.remove_initial_comment()
-            logging.info('Pushing inline code comments...')
+            logging.info('Pushing inline code suggestions...')
             self.push_inline_code_suggestions(data)
 
     async def _prepare_prediction(self, model: str):
@@ -81,14 +95,11 @@ class PRCodeSuggestions:
 
         return response
 
-    def _prepare_pr_code_suggestions(self) -> str:
+    def _prepare_pr_code_suggestions(self) -> Dict:
         review = self.prediction.strip()
-        try:
-            data = json.loads(review)
-        except json.decoder.JSONDecodeError:
-            if get_settings().config.verbosity_level >= 2:
-                logging.info(f"Could not parse json response: {review}")
-            data = try_fix_json(review, code_suggestions=True)
+        data = load_yaml(review)
+        if isinstance(data, list):
+            data = {'Code suggestions': data}
         return data
 
     def push_inline_code_suggestions(self, data):
@@ -102,11 +113,8 @@ class PRCodeSuggestions:
                 if get_settings().config.verbosity_level >= 2:
                     logging.info(f"suggestion: {d}")
                 relevant_file = d['relevant file'].strip()
-                relevant_lines_str = d['relevant lines'].strip()
-                if ',' in relevant_lines_str:  # handling 'relevant lines': '181, 190' or '178-184, 188-194'
-                    relevant_lines_str = relevant_lines_str.split(',')[0]
-                relevant_lines_start = int(relevant_lines_str.split('-')[0])  # absolute position
-                relevant_lines_end = int(relevant_lines_str.split('-')[-1])
+                relevant_lines_start = int(d['relevant lines start'])  # absolute position
+                relevant_lines_end = int(d['relevant lines end'])
                 content = d['suggestion content']
                 new_code_snippet = d['improved code']
 
@@ -121,7 +129,11 @@ class PRCodeSuggestions:
                 if get_settings().config.verbosity_level >= 2:
                     logging.info(f"Could not parse suggestion: {d}")
 
-        self.git_provider.publish_code_suggestions(code_suggestions)
+        is_successful = self.git_provider.publish_code_suggestions(code_suggestions)
+        if not is_successful:
+            logging.info("Failed to publish code suggestions, trying to publish each suggestion separately")
+            for code_suggestion in code_suggestions:
+                self.git_provider.publish_code_suggestions([code_suggestion])
 
     def dedent_code(self, relevant_file, relevant_lines_start, new_code_snippet):
         try:  # dedent code snippet
@@ -145,3 +157,81 @@ class PRCodeSuggestions:
 
         return new_code_snippet
 
+    async def _prepare_prediction_extended(self, model: str) -> dict:
+        logging.info('Getting PR diff...')
+        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)
+
+        logging.info('Getting multi AI predictions...')
+        prediction_list = []
+        for i, patches_diff in enumerate(patches_diff_list):
+            logging.info(f"Processing chunk {i + 1} of {len(patches_diff_list)}")
+            self.patches_diff = patches_diff
+            prediction = await self._get_prediction(model)
+            prediction_list.append(prediction)
+        self.prediction_list = prediction_list
+
+        data = {}
+        for prediction in prediction_list:
+            self.prediction = prediction
+            data_per_chunk = self._prepare_pr_code_suggestions()
+            if "Code suggestions" in data:
+                data["Code suggestions"].extend(data_per_chunk["Code suggestions"])
+            else:
+                data.update(data_per_chunk)
+        self.data = data
+        return data
+
+    async def rank_suggestions(self, data: List) -> List:
+        """
+        Call a model to rank (sort) code suggestions based on their importance order.
+
+        Args:
+            data (List): A list of code suggestions to be ranked.
+
+        Returns:
+            List: The ranked list of code suggestions.
+        """
+
+        suggestion_list = []
+        # remove invalid suggestions
+        for i, suggestion in enumerate(data):
+            if suggestion['existing code'] != suggestion['improved code']:
+                suggestion_list.append(suggestion)
+
+        data_sorted = [[]] * len(suggestion_list)
+
+        try:
+            suggestion_str = ""
+            for i, suggestion in enumerate(suggestion_list):
+                suggestion_str += f"suggestion {i + 1}: " + str(suggestion) + '\n\n'
+
+            variables = {'suggestion_list': suggestion_list, 'suggestion_str': suggestion_str}
+            model = get_settings().config.model
+            environment = Environment(undefined=StrictUndefined)
+            system_prompt = environment.from_string(get_settings().pr_sort_code_suggestions_prompt.system).render(
+                variables)
+            user_prompt = environment.from_string(get_settings().pr_sort_code_suggestions_prompt.user).render(variables)
+            if get_settings().config.verbosity_level >= 2:
+                logging.info(f"\nSystem prompt:\n{system_prompt}")
+                logging.info(f"\nUser prompt:\n{user_prompt}")
+            response, finish_reason = await self.ai_handler.chat_completion(model=model, system=system_prompt,
+                                                                            user=user_prompt)
+
+            sort_order = load_yaml(response)
+            for s in sort_order['Sort Order']:
+                suggestion_number = s['suggestion number']
+                importance_order = s['importance order']
+                data_sorted[importance_order - 1] = suggestion_list[suggestion_number - 1]
+
+            if get_settings().pr_code_suggestions.final_clip_factor != 1:
+                new_len = int(0.5 + len(data_sorted) * get_settings().pr_code_suggestions.final_clip_factor)
+                data_sorted = data_sorted[:new_len]
+        except Exception as e:
+            if get_settings().config.verbosity_level >= 1:
+                logging.info(f"Could not sort suggestions, error: {e}")
+            data_sorted = suggestion_list
+
+        return data_sorted
+
+

pr_agent/tools/pr_description.py

@@ -36,12 +36,14 @@ class PRDescription:
         self.vars = {
             "title": self.git_provider.pr.title,
             "branch": self.git_provider.get_pr_branch(),
-            "description": self.git_provider.get_pr_description(),
+            "description": self.git_provider.get_pr_description(full=False),
             "language": self.main_pr_language,
             "diff": "",  # empty diff for initial calculation
             "extra_instructions": get_settings().pr_description.extra_instructions,
             "commit_messages_str": self.git_provider.get_commit_messages()
         }
+
+        self.user_description = self.git_provider.get_user_description()
     
         # Initialize the token handler
         self.token_handler = TokenHandler(
@@ -145,15 +147,12 @@ class PRDescription:
         # Load the AI prediction data into a dictionary
         data = load_yaml(self.prediction.strip())
 
+        if get_settings().pr_description.add_original_user_description and self.user_description:
+            data["User Description"] = self.user_description
+
         # Initialization
         pr_types = []
 
-        # Iterate over the dictionary items and append the key and value to 'markdown_text' in a markdown format
-        markdown_text = ""
-        for key, value in data.items():
-            markdown_text += f"## {key}\n\n"
-            markdown_text += f"{value}\n\n"
-
         # If the 'PR Type' key is present in the dictionary, split its value by comma and assign it to 'pr_types'
         if 'PR Type' in data:
             if type(data['PR Type']) == list:
@@ -161,13 +160,19 @@ class PRDescription:
             elif type(data['PR Type']) == str:
                 pr_types = data['PR Type'].split(',')
 
-        # Assign the value of the 'PR Title' key to 'title' variable and remove it from the dictionary
-        title = data.pop('PR Title')
+        # Remove the 'PR Title' key from the dictionary
+        ai_title = data.pop('PR Title')
+        if get_settings().pr_description.keep_original_user_title:
+            # Assign the original PR title to the 'title' variable
+            title = self.vars["title"]
+        else:
+            # Assign the value of the 'PR Title' key to 'title' variable
+            title = ai_title
 
         # Iterate over the remaining dictionary items and append the key and value to 'pr_body' in a markdown format,
         # except for the items containing the word 'walkthrough'
         pr_body = ""
-        for key, value in data.items():
+        for idx, (key, value) in enumerate(data.items()):
             pr_body += f"## {key}:\n"
             if 'walkthrough' in key.lower():
                 # for filename, description in value.items():
@@ -179,7 +184,11 @@ class PRDescription:
                 # if the value is a list, join its items by comma
                 if type(value) == list:
                     value = ', '.join(v for v in value)
-                pr_body += f"{value}\n\n___\n"
+                pr_body += f"{value}\n"
+            if idx < len(data) - 1:
+                pr_body += "\n___\n"
+
+        markdown_text = f"## Title\n\n{title}\n\n___\n{pr_body}"
 
         if get_settings().config.verbosity_level >= 2:
             logging.info(f"title:\n{title}\n{pr_body}")

pr_agent/tools/pr_reviewer.py

@@ -23,7 +23,7 @@ class PRReviewer:
     """
     The PRReviewer class is responsible for reviewing a pull request and generating feedback using an AI model.
     """
-    def __init__(self, pr_url: str, is_answer: bool = False, args: list = None):
+    def __init__(self, pr_url: str, is_answer: bool = False, is_auto: bool = False, args: list = None):
         """
         Initialize the PRReviewer object with the necessary attributes and objects to review a pull request.
 
@@ -40,6 +40,7 @@ class PRReviewer:
         )
         self.pr_url = pr_url
         self.is_answer = is_answer
+        self.is_auto = is_auto
 
         if self.is_answer and not self.git_provider.is_supported("get_issue_comments"):
             raise Exception(f"Answer mode is not supported for {get_settings().config.git_provider} for now")
@@ -93,8 +94,12 @@ class PRReviewer:
         """
         Review the pull request and generate feedback.
         """
-        logging.info('Reviewing PR...')
-    
+        if self.is_auto and not get_settings().pr_reviewer.automatic_review:
+            logging.info(f'Automatic review is disabled {self.pr_url}')
+            return None
+
+        logging.info(f'Reviewing PR: {self.pr_url} ...')
+
         if get_settings().config.publish_output:
             self.git_provider.publish_comment("Preparing review...", is_temporary=True)