Merge remote-tracking branch 'upstream/main' into abstract-BaseAiHandler

pr_agent/agent/pr_agent.py

@@ -1,19 +1,18 @@
-import logging
-import os
 import shlex
-import tempfile
 
 from pr_agent.algo.utils import update_settings_from_args
 from pr_agent.config_loader import get_settings
-from pr_agent.git_providers import get_git_provider
+from pr_agent.git_providers.utils import apply_repo_settings
+from pr_agent.tools.pr_add_docs import PRAddDocs
 from pr_agent.tools.pr_code_suggestions import PRCodeSuggestions
+from pr_agent.tools.pr_config import PRConfig
 from pr_agent.tools.pr_description import PRDescription
+from pr_agent.tools.pr_generate_labels import PRGenerateLabels
 from pr_agent.tools.pr_information_from_user import PRInformationFromUser
-from pr_agent.tools.pr_similar_issue import PRSimilarIssue
 from pr_agent.tools.pr_questions import PRQuestions
 from pr_agent.tools.pr_reviewer import PRReviewer
+from pr_agent.tools.pr_similar_issue import PRSimilarIssue
 from pr_agent.tools.pr_update_changelog import PRUpdateChangelog
-from pr_agent.tools.pr_config import PRConfig
 
 command2class = {
     "auto_review": PRReviewer,
@@ -32,6 +31,8 @@ command2class = {
     "config": PRConfig,
     "settings": PRConfig,
     "similar_issue": PRSimilarIssue,
+    "add_docs": PRAddDocs,
+    "generate_labels": PRGenerateLabels,
 }
 
 commands = list(command2class.keys())
@@ -42,28 +43,16 @@ class PRAgent:
 
     async def handle_request(self, pr_url, request, notify=None) -> bool:
         # First, apply repo specific settings if exists
-        if get_settings().config.use_repo_settings_file:
-            repo_settings_file = None
-            try:
-                git_provider = get_git_provider()(pr_url)
-                repo_settings = git_provider.get_repo_settings()
-                if repo_settings:
-                    repo_settings_file = None
-                    fd, repo_settings_file = tempfile.mkstemp(suffix='.toml')
-                    os.write(fd, repo_settings)
-                    get_settings().load_file(repo_settings_file)
-            finally:
-                if repo_settings_file:
-                    try:
-                        os.remove(repo_settings_file)
-                    except Exception as e:
-                        logging.error(f"Failed to remove temporary settings file {repo_settings_file}", e)
+        apply_repo_settings(pr_url)
 
         # Then, apply user specific settings if exists
-        request = request.replace("'", "\\'")
-        lexer = shlex.shlex(request, posix=True)
-        lexer.whitespace_split = True
-        action, *args = list(lexer)
+        if isinstance(request, str):
+            request = request.replace("'", "\\'")
+            lexer = shlex.shlex(request, posix=True)
+            lexer.whitespace_split = True
+            action, *args = list(lexer)
+        else:
+            action, *args = request
         args = update_settings_from_args(args)
 
         action = action.lstrip("/").lower()
@@ -82,3 +71,4 @@ class PRAgent:
         else:
             return False
         return True
+

pr_agent/algo/__init__.py

@@ -8,9 +8,17 @@ MAX_TOKENS = {
     'gpt-4': 8000,
     'gpt-4-0613': 8000,
     'gpt-4-32k': 32000,
+    'gpt-4-1106-preview': 128000, # 128K, but may be limited by config.max_model_tokens
     'claude-instant-1': 100000,
     'claude-2': 100000,
     'command-nightly': 4096,
     'replicate/llama-2-70b-chat:2c1608e18606fad2812020dc541930f2d0495ce32eee50074220b87300bc16e1': 4096,
-    'meta-llama/Llama-2-7b-chat-hf': 4096
+    'meta-llama/Llama-2-7b-chat-hf': 4096,
+    'vertex_ai/codechat-bison': 6144,
+    'vertex_ai/codechat-bison-32k': 32000,
+    'codechat-bison': 6144,
+    'codechat-bison-32k': 32000,
+    'anthropic.claude-v2': 100000,
+    'anthropic.claude-instant-v1': 100000,
+    'anthropic.claude-v1': 100000,
 }

pr_agent/algo/ai_handler.py

@@ -1,6 +1,6 @@
-import logging
 import os
 
+import boto3
 import litellm
 import openai
 from litellm import acompletion
@@ -8,6 +8,8 @@ from openai.error import APIError, RateLimitError, Timeout, TryAgain
 from retry import retry
 from pr_agent.config_loader import get_settings
 from pr_agent.algo.base_ai_handler import BaseAiHandler
+from pr_agent.log import get_logger
+
 OPENAI_RETRIES = 5
 
 
@@ -23,39 +25,50 @@ class AiHandler(BaseAiHandler):
         Initializes the OpenAI API key and other settings from a configuration file.
         Raises a ValueError if the OpenAI key is missing.
         """
-        try:
+        self.azure = False
+        self.aws_bedrock_client = None
+
+        if get_settings().get("OPENAI.KEY", None):
             openai.api_key = get_settings().openai.key
             litellm.openai_key = get_settings().openai.key
-            if get_settings().get("litellm.use_client"):
-                litellm_token = get_settings().get("litellm.LITELLM_TOKEN")
-                assert litellm_token, "LITELLM_TOKEN is required"
-                os.environ["LITELLM_TOKEN"] = litellm_token
-                litellm.use_client = True
-            self.azure = False
-            if get_settings().get("OPENAI.ORG", None):
-                litellm.organization = get_settings().openai.org
-            if get_settings().get("OPENAI.API_TYPE", None):
-                if get_settings().openai.api_type == "azure":
-                    self.azure = True
-                    litellm.azure_key = get_settings().openai.key
-            if get_settings().get("OPENAI.API_VERSION", None):
-                litellm.api_version = get_settings().openai.api_version
-            if get_settings().get("OPENAI.API_BASE", None):
-                litellm.api_base = get_settings().openai.api_base
-            if get_settings().get("ANTHROPIC.KEY", None):
-                litellm.anthropic_key = get_settings().anthropic.key
-            if get_settings().get("COHERE.KEY", None):
-                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
-                if get_settings().get("HUGGINGFACE.API_BASE", None):
-                    litellm.api_base = get_settings().huggingface.api_base
-        except AttributeError as e:
-            raise ValueError("OpenAI key is required") from e
+        if get_settings().get("litellm.use_client"):
+            litellm_token = get_settings().get("litellm.LITELLM_TOKEN")
+            assert litellm_token, "LITELLM_TOKEN is required"
+            os.environ["LITELLM_TOKEN"] = litellm_token
+            litellm.use_client = True
+        if get_settings().get("OPENAI.ORG", None):
+            litellm.organization = get_settings().openai.org
+        if get_settings().get("OPENAI.API_TYPE", None):
+            if get_settings().openai.api_type == "azure":
+                self.azure = True
+                litellm.azure_key = get_settings().openai.key
+        if get_settings().get("OPENAI.API_VERSION", None):
+            litellm.api_version = get_settings().openai.api_version
+        if get_settings().get("OPENAI.API_BASE", None):
+            litellm.api_base = get_settings().openai.api_base
+        if get_settings().get("ANTHROPIC.KEY", None):
+            litellm.anthropic_key = get_settings().anthropic.key
+        if get_settings().get("COHERE.KEY", None):
+            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
+            if get_settings().get("HUGGINGFACE.API_BASE", None):
+                litellm.api_base = get_settings().huggingface.api_base
+        if get_settings().get("VERTEXAI.VERTEX_PROJECT", None):
+            litellm.vertex_project = get_settings().vertexai.vertex_project
+            litellm.vertex_location = get_settings().get(
+                "VERTEXAI.VERTEX_LOCATION", None
+            )
+        if get_settings().get("AWS.BEDROCK_REGION", None):
+            litellm.AmazonAnthropicConfig.max_tokens_to_sample = 2000
+            self.aws_bedrock_client = boto3.client(
+                service_name="bedrock-runtime",
+                region_name=get_settings().aws.bedrock_region,
+            )
 
     @property
     def deployment_id(self):
@@ -89,33 +102,37 @@ class AiHandler(BaseAiHandler):
         try:
             deployment_id = self.deployment_id
             if get_settings().config.verbosity_level >= 2:
-                logging.debug(
+                get_logger().debug(
                     f"Generating completion with {model}"
                     f"{(' from deployment ' + deployment_id) if deployment_id else ''}"
                 )
-            response = await acompletion(
-                model=model,
-                deployment_id=deployment_id,
-                messages=[
-                    {"role": "system", "content": system},
-                    {"role": "user", "content": user}
-                ],
-                temperature=temperature,
-                azure=self.azure,
-                force_timeout=get_settings().config.ai_timeout
-            )
+            if self.azure:
+                model = 'azure/' + model
+            messages = [{"role": "system", "content": system}, {"role": "user", "content": user}]
+            kwargs = {
+                "model": model,
+                "deployment_id": deployment_id,
+                "messages": messages,
+                "temperature": temperature,
+                "force_timeout": get_settings().config.ai_timeout,
+            }
+            if self.aws_bedrock_client:
+                kwargs["aws_bedrock_client"] = self.aws_bedrock_client
+            response = await acompletion(**kwargs)
         except (APIError, Timeout, TryAgain) as e:
-            logging.error("Error during OpenAI inference: ", e)
+            get_logger().error("Error during OpenAI inference: ", e)
             raise
         except (RateLimitError) as e:
-            logging.error("Rate limit error during OpenAI inference: ", e)
+            get_logger().error("Rate limit error during OpenAI inference: ", e)
             raise
         except (Exception) as e:
-            logging.error("Unknown error during OpenAI inference: ", e)
+            get_logger().error("Unknown error during OpenAI inference: ", e)
             raise TryAgain from e
         if response is None or len(response["choices"]) == 0:
             raise TryAgain
         resp = response["choices"][0]['message']['content']
         finish_reason = response["choices"][0]["finish_reason"]
-        print(resp, finish_reason)
+        usage = response.get("usage")
+        get_logger().info("AI response", response=resp, messages=messages, finish_reason=finish_reason,
+                          model=model, usage=usage)
         return resp, finish_reason

pr_agent/algo/file_filter.py

@@ -0,0 +1,36 @@
+import fnmatch
+import re
+
+from pr_agent.config_loader import get_settings
+
+def filter_ignored(files):
+    """
+    Filter out files that match the ignore patterns.
+    """
+
+    try:
+        # load regex patterns, and translate glob patterns to regex
+        patterns = get_settings().ignore.regex
+        if isinstance(patterns, str):
+            patterns = [patterns]
+        glob_setting = get_settings().ignore.glob
+        if isinstance(glob_setting, str): # --ignore.glob=[.*utils.py], --ignore.glob=.*utils.py
+            glob_setting = glob_setting.strip('[]').split(",")
+        patterns += [fnmatch.translate(glob) for glob in glob_setting]
+
+        # compile all valid patterns
+        compiled_patterns = []
+        for r in patterns:
+            try:
+                compiled_patterns.append(re.compile(r))
+            except re.error:
+                pass
+
+        # keep filenames that _don't_ match the ignore regex
+        for r in compiled_patterns:
+            files = [f for f in files if (f.filename and not r.match(f.filename))]
+
+    except Exception as e:
+        print(f"Could not filter file list: {e}")
+
+    return files

pr_agent/algo/git_patch_processing.py

@@ -1,8 +1,10 @@
 from __future__ import annotations
-import logging
+
 import re
 
 from pr_agent.config_loader import get_settings
+from pr_agent.git_providers.git_provider import EDIT_TYPE
+from pr_agent.log import get_logger
 
 
 def extend_patch(original_file_str, patch_str, num_lines) -> str:
@@ -63,7 +65,7 @@ def extend_patch(original_file_str, patch_str, num_lines) -> str:
             extended_patch_lines.append(line)
     except Exception as e:
         if get_settings().config.verbosity_level >= 2:
-            logging.error(f"Failed to extend patch: {e}")
+            get_logger().error(f"Failed to extend patch: {e}")
         return patch_str
 
     # finish previous hunk
@@ -114,7 +116,7 @@ def omit_deletion_hunks(patch_lines) -> str:
 
 
 def handle_patch_deletions(patch: str, original_file_content_str: str,
-                           new_file_content_str: str, file_name: str) -> str:
+                           new_file_content_str: str, file_name: str, edit_type: EDIT_TYPE = EDIT_TYPE.UNKNOWN) -> str:
     """
     Handle entire file or deletion patches.
 
@@ -131,17 +133,17 @@ def handle_patch_deletions(patch: str, original_file_content_str: str,
         str: The modified patch with deletion hunks omitted.
 
     """
-    if not new_file_content_str:
+    if not new_file_content_str and edit_type != EDIT_TYPE.ADDED:
         # logic for handling deleted files - don't show patch, just show that the file was deleted
         if get_settings().config.verbosity_level > 0:
-            logging.info(f"Processing file: {file_name}, minimizing deletion file")
+            get_logger().info(f"Processing file: {file_name}, minimizing deletion file")
         patch = None # file was deleted
     else:
         patch_lines = patch.splitlines()
         patch_new = omit_deletion_hunks(patch_lines)
         if patch != patch_new:
             if get_settings().config.verbosity_level > 0:
-                logging.info(f"Processing file: {file_name}, hunks were deleted")
+                get_logger().info(f"Processing file: {file_name}, hunks were deleted")
             patch = patch_new
     return patch
 

pr_agent/algo/language_handler.py

@@ -3,8 +3,7 @@ from typing import Dict
 
 from pr_agent.config_loader import get_settings
 
-language_extension_map_org = get_settings().language_extension_map_org
-language_extension_map = {k.lower(): v for k, v in language_extension_map_org.items()}
+
 
 # Bad Extensions, source: https://github.com/EleutherAI/github-downloader/blob/345e7c4cbb9e0dc8a0615fd995a08bf9d73b3fe6/download_repo_text.py  # noqa: E501
 bad_extensions = get_settings().bad_extensions.default
@@ -29,6 +28,8 @@ def sort_files_by_main_languages(languages: Dict, files: list):
     # languages_sorted = sorted(languages, key=lambda x: x[1], reverse=True)
     # get all extensions for the languages
     main_extensions = []
+    language_extension_map_org = get_settings().language_extension_map_org
+    language_extension_map = {k.lower(): v for k, v in language_extension_map_org.items()}
     for language in languages_sorted_list:
         if language.lower() in language_extension_map:
             main_extensions.append(language_extension_map[language.lower()])

pr_agent/algo/pr_processing.py

@@ -1,27 +1,29 @@
 from __future__ import annotations
 
 import difflib
-import logging
 import re
 import traceback
 from typing import Any, Callable, List, Tuple
 
 from github import RateLimitExceededException
 
-from pr_agent.algo import MAX_TOKENS
 from pr_agent.algo.git_patch_processing import convert_to_hunks_with_lines_numbers, extend_patch, handle_patch_deletions
 from pr_agent.algo.language_handler import sort_files_by_main_languages
-from pr_agent.algo.token_handler import TokenHandler, get_token_encoder
+from pr_agent.algo.file_filter import filter_ignored
+from pr_agent.algo.token_handler import TokenHandler
+from pr_agent.algo.utils import get_max_tokens
 from pr_agent.config_loader import get_settings
-from pr_agent.git_providers.git_provider import FilePatchInfo, GitProvider
+from pr_agent.git_providers.git_provider import FilePatchInfo, GitProvider, EDIT_TYPE
+from pr_agent.log import get_logger
 
 DELETED_FILES_ = "Deleted files:\n"
 
-MORE_MODIFIED_FILES_ = "More modified files:\n"
+MORE_MODIFIED_FILES_ = "Additional modified files (insufficient token budget to process):\n"
+
+ADDED_FILES_ = "Additional added files (insufficient token budget to process):\n"
 
 OUTPUT_BUFFER_TOKENS_SOFT_THRESHOLD = 1000
 OUTPUT_BUFFER_TOKENS_HARD_THRESHOLD = 600
-PATCH_EXTRA_LINES = 3
 
 def get_pr_diff(git_provider: GitProvider, token_handler: TokenHandler, model: str,
                 add_line_numbers_to_hunks: bool = False, disable_extra_lines: bool = False) -> str:
@@ -44,31 +46,37 @@ def get_pr_diff(git_provider: GitProvider, token_handler: TokenHandler, model: s
     """
 
     if disable_extra_lines:
-        global PATCH_EXTRA_LINES
         PATCH_EXTRA_LINES = 0
+    else:
+        PATCH_EXTRA_LINES = get_settings().config.patch_extra_lines
 
     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}")
+        get_logger().error(f"Rate limit exceeded for git provider API. original message {e}")
         raise
 
+    diff_files = filter_ignored(diff_files)
+
     # get pr languages
     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, patches_extended_tokens = pr_generate_extended_diff(pr_languages, token_handler,
-                                                               add_line_numbers_to_hunks)
+    patches_extended, total_tokens, patches_extended_tokens = pr_generate_extended_diff(
+        pr_languages, token_handler, add_line_numbers_to_hunks, patch_extra_lines=PATCH_EXTRA_LINES)
 
     # if we are under the limit, return the full diff
-    if total_tokens + OUTPUT_BUFFER_TOKENS_SOFT_THRESHOLD < MAX_TOKENS[model]:
+    if total_tokens + OUTPUT_BUFFER_TOKENS_SOFT_THRESHOLD < get_max_tokens(model):
         return "\n".join(patches_extended)
 
     # if we are over the limit, start pruning
-    patches_compressed, modified_file_names, deleted_file_names = \
+    patches_compressed, modified_file_names, deleted_file_names, added_file_names = \
         pr_generate_compressed_diff(pr_languages, token_handler, model, add_line_numbers_to_hunks)
 
     final_diff = "\n".join(patches_compressed)
+    if added_file_names:
+        added_list_str = ADDED_FILES_ + "\n".join(added_file_names)
+        final_diff = final_diff + "\n\n" + added_list_str
     if modified_file_names:
         modified_list_str = MORE_MODIFIED_FILES_ + "\n".join(modified_file_names)
         final_diff = final_diff + "\n\n" + modified_list_str
@@ -80,7 +88,8 @@ def get_pr_diff(git_provider: GitProvider, token_handler: TokenHandler, model: s
 
 def pr_generate_extended_diff(pr_languages: list,
                               token_handler: TokenHandler,
-                              add_line_numbers_to_hunks: bool) -> Tuple[list, int, list]:
+                              add_line_numbers_to_hunks: bool,
+                              patch_extra_lines: int = 0) -> 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.
@@ -102,7 +111,7 @@ def pr_generate_extended_diff(pr_languages: list,
                 continue
 
             # extend each patch with extra lines of context
-            extended_patch = extend_patch(original_file_content_str, patch, num_lines=PATCH_EXTRA_LINES)
+            extended_patch = extend_patch(original_file_content_str, patch, num_lines=patch_extra_lines)
             full_extended_patch = f"\n\n## {file.filename}\n\n{extended_patch}\n"
 
             if add_line_numbers_to_hunks:
@@ -118,7 +127,7 @@ def pr_generate_extended_diff(pr_languages: list,
 
 
 def pr_generate_compressed_diff(top_langs: list, token_handler: TokenHandler, model: str,
-                                convert_hunks_to_line_numbers: bool) -> Tuple[list, list, list]:
+                                convert_hunks_to_line_numbers: bool) -> Tuple[list, list, list, list]:
     """
     Generate a compressed diff string for a pull request, using diff minimization techniques to reduce the number of
     tokens used.
@@ -144,6 +153,7 @@ def pr_generate_compressed_diff(top_langs: list, token_handler: TokenHandler, mo
     """
 
     patches = []
+    added_files_list = []
     modified_files_list = []
     deleted_files_list = []
     # sort each one of the languages in top_langs by the number of tokens in the diff
@@ -161,7 +171,7 @@ def pr_generate_compressed_diff(top_langs: list, token_handler: TokenHandler, mo
 
         # removing delete-only hunks
         patch = handle_patch_deletions(patch, original_file_content_str,
-                                       new_file_content_str, file.filename)
+                                       new_file_content_str, file.filename, file.edit_type)
         if patch is None:
             if not deleted_files_list:
                 total_tokens += token_handler.count_tokens(DELETED_FILES_)
@@ -175,21 +185,26 @@ def pr_generate_compressed_diff(top_langs: list, token_handler: TokenHandler, mo
         new_patch_tokens = token_handler.count_tokens(patch)
 
         # Hard Stop, no more tokens
-        if total_tokens > MAX_TOKENS[model] - OUTPUT_BUFFER_TOKENS_HARD_THRESHOLD:
-            logging.warning(f"File was fully skipped, no more tokens: {file.filename}.")
+        if total_tokens > get_max_tokens(model) - OUTPUT_BUFFER_TOKENS_HARD_THRESHOLD:
+            get_logger().warning(f"File was fully skipped, no more tokens: {file.filename}.")
             continue
 
         # If the patch is too large, just show the file name
-        if total_tokens + new_patch_tokens > MAX_TOKENS[model] - OUTPUT_BUFFER_TOKENS_SOFT_THRESHOLD:
+        if total_tokens + new_patch_tokens > get_max_tokens(model) - OUTPUT_BUFFER_TOKENS_SOFT_THRESHOLD:
             # Current logic is to skip the patch if it's too large
             # TODO: Option for alternative logic to remove hunks from the patch to reduce the number of tokens
             #  until we meet the requirements
             if get_settings().config.verbosity_level >= 2:
-                logging.warning(f"Patch too large, minimizing it, {file.filename}")
-            if not modified_files_list:
-                total_tokens += token_handler.count_tokens(MORE_MODIFIED_FILES_)
-            modified_files_list.append(file.filename)
-            total_tokens += token_handler.count_tokens(file.filename) + 1
+                get_logger().warning(f"Patch too large, minimizing it, {file.filename}")
+            if file.edit_type == EDIT_TYPE.ADDED:
+                if not added_files_list:
+                    total_tokens += token_handler.count_tokens(ADDED_FILES_)
+                added_files_list.append(file.filename)
+            else:
+                if not modified_files_list:
+                    total_tokens += token_handler.count_tokens(MORE_MODIFIED_FILES_)
+                modified_files_list.append(file.filename)
+                total_tokens += token_handler.count_tokens(file.filename) + 1
             continue
 
         if patch:
@@ -200,9 +215,9 @@ def pr_generate_compressed_diff(top_langs: list, token_handler: TokenHandler, mo
             patches.append(patch_final)
             total_tokens += token_handler.count_tokens(patch_final)
             if get_settings().config.verbosity_level >= 2:
-                logging.info(f"Tokens: {total_tokens}, last filename: {file.filename}")
+                get_logger().info(f"Tokens: {total_tokens}, last filename: {file.filename}")
 
-    return patches, modified_files_list, deleted_files_list
+    return patches, modified_files_list, deleted_files_list, added_files_list
 
 
 async def retry_with_fallback_models(f: Callable):
@@ -214,7 +229,7 @@ async def retry_with_fallback_models(f: Callable):
             get_settings().set("openai.deployment_id", deployment_id)
             return await f(model)
         except Exception as e:
-            logging.warning(
+            get_logger().warning(
                 f"Failed to generate prediction with {model}"
                 f"{(' from deployment ' + deployment_id) if deployment_id else ''}: "
                 f"{traceback.format_exc()}"
@@ -267,7 +282,7 @@ def find_line_number_of_relevant_line_in_file(diff_files: List[FilePatchInfo],
         r"^@@ -(\d+)(?:,(\d+))? \+(\d+)(?:,(\d+))? @@[ ]?(.*)")
 
     for file in diff_files:
-        if file.filename.strip() == relevant_file:
+        if file.filename and (file.filename.strip() == relevant_file):
             patch = file.patch
             patch_lines = patch.splitlines()
 
@@ -311,35 +326,6 @@ def find_line_number_of_relevant_line_in_file(diff_files: List[FilePatchInfo],
     return position, absolute_position
 
 
-def clip_tokens(text: str, max_tokens: int) -> str:
-    """
-    Clip the number of tokens in a string to a maximum number of tokens.
-
-    Args:
-        text (str): The string to clip.
-        max_tokens (int): The maximum number of tokens allowed in the string.
-
-    Returns:
-        str: The clipped string.
-    """
-    if not text:
-        return text
-
-    try:
-        encoder = get_token_encoder()
-        num_input_tokens = len(encoder.encode(text))
-        if num_input_tokens <= max_tokens:
-            return text
-        num_chars = len(text)
-        chars_per_token = num_chars / num_input_tokens
-        num_output_chars = int(chars_per_token * max_tokens)
-        clipped_text = text[:num_output_chars]
-        return clipped_text
-    except Exception as e:
-        logging.warning(f"Failed to clip tokens: {e}")
-        return text
-
-
 def get_pr_multi_diffs(git_provider: GitProvider,
                        token_handler: TokenHandler,
                        model: str,
@@ -347,25 +333,27 @@ def get_pr_multi_diffs(git_provider: GitProvider,
     """
     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}")
+        get_logger().error(f"Rate limit exceeded for git provider API. original message {e}")
         raise
 
+    diff_files = filter_ignored(diff_files)
+
     # Sort files by main language
     pr_languages = sort_files_by_main_languages(git_provider.get_languages(), diff_files)
 
@@ -381,7 +369,7 @@ def get_pr_multi_diffs(git_provider: GitProvider,
     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})")
+                get_logger().info(f"Reached max calls ({max_calls})")
             break
 
         original_file_content_str = file.base_file
@@ -391,26 +379,26 @@ def get_pr_multi_diffs(git_provider: GitProvider,
             continue
 
         # Remove delete-only hunks
-        patch = handle_patch_deletions(patch, original_file_content_str, new_file_content_str, file.filename)
+        patch = handle_patch_deletions(patch, original_file_content_str, new_file_content_str, file.filename, file.edit_type)
         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):
+        if patch and (total_tokens + new_patch_tokens > get_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}")
+                get_logger().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}")
+                get_logger().info(f"Tokens: {total_tokens}, last filename: {file.filename}")
 
     # Add the last chunk
     if patches:

pr_agent/algo/utils.py

@@ -2,7 +2,6 @@ from __future__ import annotations
 
 import difflib
 import json
-import logging
 import re
 import textwrap
 from datetime import datetime
@@ -10,7 +9,11 @@ from typing import Any, List
 
 import yaml
 from starlette_context import context
+
+from pr_agent.algo import MAX_TOKENS
+from pr_agent.algo.token_handler import get_token_encoder
 from pr_agent.config_loader import get_settings, global_settings
+from pr_agent.log import get_logger
 
 
 def get_setting(key: str) -> Any:
@@ -55,14 +58,15 @@ def convert_to_markdown(output_data: dict, gfm_supported: bool=True) -> str:
             emoji = emojis.get(key, "")
             if key.lower() == 'code feedback':
                 if gfm_supported:
-                    markdown_text += f"\n\n- **<details><summary> { emoji } Code feedback:**</summary>\n\n"
+                    markdown_text += f"\n\n- "
+                    markdown_text += f"<details><summary> { emoji } Code feedback:</summary>\n\n"
                 else:
                     markdown_text += f"\n\n- **{emoji} Code feedback:**\n\n"
             else:
                 markdown_text += f"- {emoji} **{key}:**\n\n"
             for item in value:
                 if isinstance(item, dict) and key.lower() == 'code feedback':
-                    markdown_text += parse_code_suggestion(item)
+                    markdown_text += parse_code_suggestion(item, gfm_supported)
                 elif item:
                     markdown_text += f"  - {item}\n"
             if key.lower() == 'code feedback':
@@ -76,7 +80,7 @@ def convert_to_markdown(output_data: dict, gfm_supported: bool=True) -> str:
     return markdown_text
 
 
-def parse_code_suggestion(code_suggestions: dict) -> str:
+def parse_code_suggestion(code_suggestions: dict, gfm_supported: bool=True) -> str:
     """
     Convert a dictionary of data into markdown format.
 
@@ -96,9 +100,13 @@ def parse_code_suggestion(code_suggestions: dict) -> str:
                 markdown_text += f"    - **{code_key}:**\n{code_str_indented}\n"
         else:
             if "relevant file" in sub_key.lower():
-                markdown_text += f"\n  - **{sub_key}:** {sub_value}\n"
+                markdown_text += f"\n  - **{sub_key}:** {sub_value}  \n"
             else:
-                markdown_text += f"   **{sub_key}:** {sub_value}\n"
+                markdown_text += f"   **{sub_key}:** {sub_value}  \n"
+            if not gfm_supported:
+                if "relevant line" not in sub_key.lower(): # nicer presentation
+                        # markdown_text = markdown_text.rstrip('\n') + "\\\n" # works for gitlab
+                        markdown_text = markdown_text.rstrip('\n') + "   \n"  # works for gitlab and bitbucker
 
     markdown_text += "\n"
     return markdown_text
@@ -156,7 +164,7 @@ def try_fix_json(review, max_iter=10, code_suggestions=False):
                 iter_count += 1
 
         if not valid_json:
-            logging.error("Unable to decode JSON response from AI")
+            get_logger().error("Unable to decode JSON response from AI")
             data = {}
 
     return data
@@ -227,7 +235,7 @@ def load_large_diff(filename, new_file_content_str: str, original_file_content_s
         diff = difflib.unified_diff(original_file_content_str.splitlines(keepends=True),
                                     new_file_content_str.splitlines(keepends=True))
         if get_settings().config.verbosity_level >= 2:
-            logging.warning(f"File was modified, but no patch was found. Manually creating patch: {filename}.")
+            get_logger().warning(f"File was modified, but no patch was found. Manually creating patch: {filename}.")
         patch = ''.join(diff)
     except Exception:
         pass
@@ -259,12 +267,12 @@ def update_settings_from_args(args: List[str]) -> List[str]:
                 vals = arg.split('=', 1)
                 if len(vals) != 2:
                     if len(vals) > 2: # --extended is a valid argument
-                        logging.error(f'Invalid argument format: {arg}')
+                        get_logger().error(f'Invalid argument format: {arg}')
                     other_args.append(arg)
                     continue
                 key, value = _fix_key_value(*vals)
                 get_settings().set(key, value)
-                logging.info(f'Updated setting {key} to: "{value}"')
+                get_logger().info(f'Updated setting {key} to: "{value}"')
             else:
                 other_args.append(arg)
     return other_args
@@ -276,28 +284,142 @@ def _fix_key_value(key: str, value: str):
     try:
         value = yaml.safe_load(value)
     except Exception as e:
-        logging.error(f"Failed to parse YAML for config override {key}={value}", exc_info=e)
+        get_logger().debug(f"Failed to parse YAML for config override {key}={value}", exc_info=e)
     return key, value
 
 
-def load_yaml(review_text: str) -> dict:
-    review_text = review_text.removeprefix('```yaml').rstrip('`')
+def load_yaml(response_text: str) -> dict:
+    response_text = response_text.removeprefix('```yaml').rstrip('`')
     try:
-        data = yaml.safe_load(review_text)
+        data = yaml.safe_load(response_text)
     except Exception as e:
-        logging.error(f"Failed to parse AI prediction: {e}")
-        data = try_fix_yaml(review_text)
+        get_logger().error(f"Failed to parse AI prediction: {e}")
+        data = try_fix_yaml(response_text)
     return data
 
-def try_fix_yaml(review_text: str) -> dict:
-    review_text_lines = review_text.split('\n')
+def try_fix_yaml(response_text: str) -> dict:
+    response_text_lines = response_text.split('\n')
+
+    keys = ['relevant line:', 'suggestion content:', 'relevant file:']
+    # first fallback - try to convert 'relevant line: ...' to relevant line: |-\n        ...'
+    response_text_lines_copy = response_text_lines.copy()
+    for i in range(0, len(response_text_lines_copy)):
+        for key in keys:
+            if key in response_text_lines_copy[i] and not '|-' in response_text_lines_copy[i]:
+                response_text_lines_copy[i] = response_text_lines_copy[i].replace(f'{key}',
+                                                                                  f'{key} |-\n        ')
+    try:
+        data = yaml.safe_load('\n'.join(response_text_lines_copy))
+        get_logger().info(f"Successfully parsed AI prediction after adding |-\n")
+        return data
+    except:
+        get_logger().info(f"Failed to parse AI prediction after adding |-\n")
+
+    # second fallback - try to remove last lines
     data = {}
-    for i in range(1, len(review_text_lines)):
-        review_text_lines_tmp = '\n'.join(review_text_lines[:-i])
+    for i in range(1, len(response_text_lines)):
+        response_text_lines_tmp = '\n'.join(response_text_lines[:-i])
         try:
-            data = yaml.load(review_text_lines_tmp, Loader=yaml.SafeLoader)
-            logging.info(f"Successfully parsed AI prediction after removing {i} lines")
+            data = yaml.safe_load(response_text_lines_tmp,)
+            get_logger().info(f"Successfully parsed AI prediction after removing {i} lines")
             break
         except:
             pass
-    return data
+    
+    # thrid fallback - try to remove leading and trailing curly brackets
+    response_text_copy = response_text.strip().rstrip().removeprefix('{').removesuffix('}')
+    try:
+        data = yaml.safe_load(response_text_copy,)
+        get_logger().info(f"Successfully parsed AI prediction after removing curly brackets")
+        return data
+    except:
+        pass
+
+
+def set_custom_labels(variables):
+    if not get_settings().config.enable_custom_labels:
+        return
+
+    labels = get_settings().custom_labels
+    if not labels:
+        # set default labels
+        labels = ['Bug fix', 'Tests', 'Bug fix with tests', 'Enhancement', 'Documentation', 'Other']
+        labels_list = "\n      - ".join(labels) if labels else ""
+        labels_list = f"      - {labels_list}" if labels_list else ""
+        variables["custom_labels"] = labels_list
+        return
+    #final_labels = ""
+    #for k, v in labels.items():
+    #    final_labels += f"      - {k} ({v['description']})\n"
+    #variables["custom_labels"] = final_labels
+    #variables["custom_labels_examples"] = f"      - {list(labels.keys())[0]}"
+    variables["custom_labels_class"] = "class Label(str, Enum):"
+    for k, v in labels.items():
+        description = v['description'].strip('\n').replace('\n', '\\n')
+        variables["custom_labels_class"] += f"\n    {k.lower().replace(' ', '_')} = '{k}' # {description}"
+
+def get_user_labels(current_labels: List[str] = None):
+    """
+    Only keep labels that has been added by the user
+    """
+    try:
+        if current_labels is None:
+            current_labels = []
+        user_labels = []
+        for label in current_labels:
+            if label.lower() in ['bug fix', 'tests', 'enhancement', 'documentation', 'other']:
+                continue
+            if get_settings().config.enable_custom_labels:
+                if label in get_settings().custom_labels:
+                    continue
+            user_labels.append(label)
+        if user_labels:
+            get_logger().info(f"Keeping user labels: {user_labels}")
+    except Exception as e:
+        get_logger().exception(f"Failed to get user labels: {e}")
+        return current_labels
+    return user_labels
+
+
+def get_max_tokens(model):
+    settings = get_settings()
+    if model in MAX_TOKENS:
+        max_tokens_model = MAX_TOKENS[model]
+    else:
+        raise Exception(f"MAX_TOKENS must be set for model {model} in ./pr_agent/algo/__init__.py")
+
+    if settings.config.max_model_tokens:
+        max_tokens_model = min(settings.config.max_model_tokens, max_tokens_model)
+        # get_logger().debug(f"limiting max tokens to {max_tokens_model}")
+    return max_tokens_model
+
+
+def clip_tokens(text: str, max_tokens: int, add_three_dots=True) -> str:
+    """
+    Clip the number of tokens in a string to a maximum number of tokens.
+
+    Args:
+        text (str): The string to clip.
+        max_tokens (int): The maximum number of tokens allowed in the string.
+        add_three_dots (bool, optional): A boolean indicating whether to add three dots at the end of the clipped
+    Returns:
+        str: The clipped string.
+    """
+    if not text:
+        return text
+
+    try:
+        encoder = get_token_encoder()
+        num_input_tokens = len(encoder.encode(text))
+        if num_input_tokens <= max_tokens:
+            return text
+        num_chars = len(text)
+        chars_per_token = num_chars / num_input_tokens
+        num_output_chars = int(chars_per_token * max_tokens)
+        clipped_text = text[:num_output_chars]
+        if add_three_dots:
+            clipped_text += "...(truncated)"
+        return clipped_text
+    except Exception as e:
+        get_logger().warning(f"Failed to clip tokens: {e}")
+        return text

pr_agent/cli.py

@@ -1,10 +1,13 @@
 import argparse
 import asyncio
-import logging
 import os
 
 from pr_agent.agent.pr_agent import PRAgent, commands
 from pr_agent.config_loader import get_settings
+from pr_agent.log import setup_logger
+
+setup_logger()
+
 
 
 def run(inargs=None):
@@ -20,18 +23,22 @@ For example:
 - cli.py --issue_url=... similar_issue
 
 Supported commands:
--review / review_pr - Add a review that includes a summary of the PR and specific suggestions for improvement.
+- 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.
+- 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.
+- 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.
+- 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.
+- reflect - Ask the PR author questions about the PR.
 
--update_changelog - Update the changelog based on the PR's contents.
+- update_changelog - Update the changelog based on the PR's contents.
+
+- add_docs
+
+- generate_labels
 
 
 Configuration:
@@ -47,13 +54,12 @@ For example: 'python cli.py --pr_url=... review --pr_reviewer.extra_instructions
         parser.print_help()
         return
 
-    logging.basicConfig(level=os.environ.get("LOGLEVEL", "INFO"))
     command = args.command.lower()
     get_settings().set("CONFIG.CLI_MODE", True)
     if args.issue_url:
-        result = asyncio.run(PRAgent().handle_request(args.issue_url, command + " " + " ".join(args.rest)))
+        result = asyncio.run(PRAgent().handle_request(args.issue_url, [command] + args.rest))
     else:
-        result = asyncio.run(PRAgent().handle_request(args.pr_url, command + " " + " ".join(args.rest)))
+        result = asyncio.run(PRAgent().handle_request(args.pr_url, [command] + args.rest))
     if not result:
         parser.print_help()
 

pr_agent/config_loader.py

@@ -14,6 +14,7 @@ global_settings = Dynaconf(
     settings_files=[join(current_dir, f) for f in [
         "settings/.secrets.toml",
         "settings/configuration.toml",
+        "settings/ignore.toml",
         "settings/language_extensions.toml",
         "settings/pr_reviewer_prompts.toml",
         "settings/pr_questions_prompts.toml",
@@ -22,7 +23,10 @@ global_settings = Dynaconf(
         "settings/pr_sort_code_suggestions_prompts.toml",
         "settings/pr_information_from_user_prompts.toml",
         "settings/pr_update_changelog_prompts.toml",
-        "settings_prod/.secrets.toml"
+        "settings/pr_custom_labels.toml",
+        "settings/pr_add_docs.toml",
+        "settings_prod/.secrets.toml",
+        "settings/custom_labels.toml"
     ]]
 )
 

pr_agent/git_providers/__init__.py

@@ -1,5 +1,6 @@
 from pr_agent.config_loader import get_settings
 from pr_agent.git_providers.bitbucket_provider import BitbucketProvider
+from pr_agent.git_providers.bitbucket_server_provider import BitbucketServerProvider
 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
@@ -12,6 +13,7 @@ _GIT_PROVIDERS = {
     'github': GithubProvider,
     'gitlab': GitLabProvider,
     'bitbucket': BitbucketProvider,
+    'bitbucket_server': BitbucketServerProvider,
     'azure': AzureDevopsProvider,
     'codecommit': CodeCommitProvider,
     'local' : LocalGitProvider,

pr_agent/git_providers/azuredevops_provider.py

@@ -1,10 +1,11 @@
 import json
-import logging
 from typing import Optional, Tuple
 from urllib.parse import urlparse
 
 import os
 
+from ..log import get_logger
+
 AZURE_DEVOPS_AVAILABLE = True
 try:
     from msrest.authentication import BasicAuthentication
@@ -13,9 +14,8 @@ try:
 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.utils import load_large_diff, clip_tokens
 from ..algo.language_handler import is_valid_file
 from .git_provider import EDIT_TYPE, FilePatchInfo
 
@@ -55,7 +55,7 @@ class AzureDevopsProvider:
                                                                  path=".pr_agent.toml")
             return contents
         except Exception as e:
-            logging.exception("get repo settings error")
+            get_logger().exception("get repo settings error")
             return ""
 
     def get_files(self):
@@ -100,14 +100,18 @@ class AzureDevopsProvider:
                     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)
+                try:
+                    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
+                    new_file_content_str = new_file_content_str.content
+                except Exception as error:
+                    get_logger().error("Failed to retrieve new file content of %s at version %s. Error: %s", file, version, str(error))
+                    new_file_content_str = ""
 
                 edit_type = EDIT_TYPE.MODIFIED
                 if diff_types[file] == 'add':
@@ -118,13 +122,17 @@ class AzureDevopsProvider:
                     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,
+                try:
+                    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
+                    original_file_content_str = original_file_content_str.content
+                except Exception as error:
+                    get_logger().error("Failed to retrieve original file content of %s at version %s. Error: %s", file, version, str(error))
+                    original_file_content_str = ""
 
                 patch = load_large_diff(file, new_file_content_str, original_file_content_str)
 
@@ -158,7 +166,7 @@ class AzureDevopsProvider:
                                                          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}")
+            get_logger().exception(f"Could not update pull request {self.pr_num} description: {e}")
 
     def remove_initial_comment(self):
         return ""  # not implemented yet
@@ -227,9 +235,6 @@ class AzureDevopsProvider:
     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':

pr_agent/git_providers/bitbucket_provider.py

@@ -1,5 +1,4 @@
 import json
-import logging
 from typing import Optional, Tuple
 from urllib.parse import urlparse
 
@@ -7,9 +6,10 @@ import requests
 from atlassian.bitbucket import Cloud
 from starlette_context import context
 
-from ..algo.pr_processing import clip_tokens, find_line_number_of_relevant_line_in_file
+from ..algo.pr_processing import find_line_number_of_relevant_line_in_file
 from ..config_loader import get_settings
-from .git_provider import FilePatchInfo, GitProvider
+from ..log import get_logger
+from .git_provider import FilePatchInfo, GitProvider, EDIT_TYPE
 
 
 class BitbucketProvider(GitProvider):
@@ -32,8 +32,10 @@ class BitbucketProvider(GitProvider):
         self.repo = None
         self.pr_num = None
         self.pr = None
+        self.pr_url = pr_url
         self.temp_comments = []
         self.incremental = incremental
+        self.diff_files = None
         if pr_url:
             self.set_pr(pr_url)
         self.bitbucket_comment_api_url = self.pr._BitbucketBase__data["links"]["comments"]["href"]
@@ -41,9 +43,12 @@ class BitbucketProvider(GitProvider):
 
     def get_repo_settings(self):
         try:
-            contents = self.repo_obj.get_contents(
-                ".pr_agent.toml", ref=self.pr.head.sha
-            ).decoded_content
+            url = (f"https://api.bitbucket.org/2.0/repositories/{self.workspace_slug}/{self.repo_slug}/src/"
+                   f"{self.pr.destination_branch}/.pr_agent.toml")
+            response = requests.request("GET", url, headers=self.headers)
+            if response.status_code == 404:  # not found
+                return ""
+            contents = response.text.encode('utf-8')
             return contents
         except Exception:
             return ""
@@ -61,14 +66,14 @@ class BitbucketProvider(GitProvider):
 
             if not relevant_lines_start or relevant_lines_start == -1:
                 if get_settings().config.verbosity_level >= 2:
-                    logging.exception(
+                    get_logger().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(
+                    get_logger().exception(
                         f"Failed to publish code suggestion, "
                         f"relevant_lines_end is {relevant_lines_end} and "
                         f"relevant_lines_start is {relevant_lines_start}"
@@ -97,7 +102,7 @@ class BitbucketProvider(GitProvider):
             return True
         except Exception as e:
             if get_settings().config.verbosity_level >= 2:
-                logging.error(f"Failed to publish code suggestion, error: {e}")
+                get_logger().error(f"Failed to publish code suggestion, error: {e}")
             return False
 
     def is_supported(self, capability: str) -> bool:
@@ -113,6 +118,9 @@ class BitbucketProvider(GitProvider):
         return [diff.new.path for diff in self.pr.diffstat()]
 
     def get_diff_files(self) -> list[FilePatchInfo]:
+        if self.diff_files:
+            return self.diff_files
+
         diffs = self.pr.diffstat()
         diff_split = [
             "diff --git%s" % x for x in self.pr.diff().split("diff --git") if x.strip()
@@ -124,16 +132,56 @@ class BitbucketProvider(GitProvider):
                 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,
-                )
+            file_patch_canonic_structure = FilePatchInfo(
+                original_file_content_str,
+                new_file_content_str,
+                diff_split[index],
+                diff.new.path,
             )
+
+            if diff.data['status'] == 'added':
+                file_patch_canonic_structure.edit_type = EDIT_TYPE.ADDED
+            elif diff.data['status'] == 'removed':
+                file_patch_canonic_structure.edit_type = EDIT_TYPE.DELETED
+            elif diff.data['status'] == 'modified':
+                file_patch_canonic_structure.edit_type = EDIT_TYPE.MODIFIED
+            elif diff.data['status'] == 'renamed':
+                file_patch_canonic_structure.edit_type = EDIT_TYPE.RENAMED
+            diff_files.append(file_patch_canonic_structure)
+
+
+        self.diff_files = diff_files
         return diff_files
 
+    def get_latest_commit_url(self):
+        return self.pr.data['source']['commit']['links']['html']['href']
+
+    def get_comment_url(self, comment):
+        return comment.data['links']['html']['href']
+
+    def publish_persistent_comment(self, pr_comment: str, initial_header: str, update_header: bool = True):
+        try:
+            for comment in self.pr.comments():
+                body = comment.raw
+                if initial_header in body:
+                    latest_commit_url = self.get_latest_commit_url()
+                    comment_url = self.get_comment_url(comment)
+                    if update_header:
+                        updated_header = f"{initial_header}\n\n### (review updated until commit {latest_commit_url})\n"
+                        pr_comment_updated = pr_comment.replace(initial_header, updated_header)
+                    else:
+                        pr_comment_updated = pr_comment
+                    get_logger().info(f"Persistent mode- updating comment {comment_url} to latest review message")
+                    d = {"content": {"raw": pr_comment_updated}}
+                    response = comment._update_data(comment.put(None, data=d))
+                    self.publish_comment(
+                        f"**[Persistent review]({comment_url})** updated to latest commit {latest_commit_url}")
+                    return
+        except Exception as e:
+            get_logger().exception(f"Failed to update persistent review, error: {e}")
+            pass
+        self.publish_comment(pr_comment)
+
     def publish_comment(self, pr_comment: str, is_temporary: bool = False):
         comment = self.pr.comment(pr_comment)
         if is_temporary:
@@ -142,17 +190,22 @@ class BitbucketProvider(GitProvider):
     def remove_initial_comment(self):
         try:
             for comment in self.temp_comments:
-                self.pr.delete(f"comments/{comment}")
+                self.remove_comment(comment)
         except Exception as e:
-            logging.exception(f"Failed to remove temp comments, error: {e}")
+            get_logger().exception(f"Failed to remove temp comments, error: {e}")
 
+    def remove_comment(self, comment):
+        try:
+            self.pr.delete(f"comments/{comment}")
+        except Exception as e:
+            get_logger().exception(f"Failed to remove comment, error: {e}")
 
     # funtion to create_inline_comment
     def create_inline_comment(self, body: str, relevant_file: str, relevant_line_in_file: str):
         position, absolute_position = find_line_number_of_relevant_line_in_file(self.get_diff_files(), relevant_file.strip('`'), relevant_line_in_file)
         if position == -1:
             if get_settings().config.verbosity_level >= 2:
-                logging.info(f"Could not find position for {relevant_file} {relevant_line_in_file}")
+                get_logger().info(f"Could not find position for {relevant_file} {relevant_line_in_file}")
             subject_type = "FILE"
         else:
             subject_type = "LINE"
@@ -175,9 +228,44 @@ class BitbucketProvider(GitProvider):
         )
         return response
 
+    def get_line_link(self, relevant_file: str, relevant_line_start: int, relevant_line_end: int = None) -> str:
+        if relevant_line_start == -1:
+            link = f"{self.pr_url}/#L{relevant_file}"
+        else:
+            link = f"{self.pr_url}/#L{relevant_file}T{relevant_line_start}"
+        return link
+
+    def generate_link_to_relevant_line_number(self, suggestion) -> str:
+        try:
+            relevant_file = suggestion['relevant file'].strip('`').strip("'")
+            relevant_line_str = suggestion['relevant line']
+            if not relevant_line_str:
+                return ""
+
+            diff_files = self.get_diff_files()
+            position, absolute_position = find_line_number_of_relevant_line_in_file \
+                (diff_files, relevant_file, relevant_line_str)
+
+            if absolute_position != -1 and self.pr_url:
+                link = f"{self.pr_url}/#L{relevant_file}T{absolute_position}"
+                return link
+        except Exception as e:
+            if get_settings().config.verbosity_level >= 2:
+                get_logger().info(f"Failed adding line link, error: {e}")
+
+        return ""
+
     def publish_inline_comments(self, comments: list[dict]):
         for comment in comments:
-            self.publish_inline_comment(comment['body'], comment['start_line'], comment['path'])
+            if 'position' in comment:
+                self.publish_inline_comment(comment['body'], comment['position'], comment['path'])
+            elif 'start_line' in comment: # multi-line comment
+                # note that bitbucket does not seem to support range - only a comment on a single line - https://community.developer.atlassian.com/t/api-post-endpoint-for-inline-pull-request-comments/60452
+                self.publish_inline_comment(comment['body'], comment['start_line'], comment['path'])
+            elif 'line' in comment: # single-line comment
+                self.publish_inline_comment(comment['body'], comment['line'], comment['path'])
+            else:
+                get_logger().error(f"Could not publish inline comment {comment}")
 
     def get_title(self):
         return self.pr.title
@@ -254,6 +342,11 @@ class BitbucketProvider(GitProvider):
             })
 
         response = requests.request("PUT", self.bitbucket_pull_request_api_url, headers=self.headers, data=payload)
+        try:
+            if response.status_code != 200:
+                get_logger().info(f"Failed to update description, error code: {response.status_code}")
+        except:
+            pass
         return response
 
     # bitbucket does not support labels

pr_agent/git_providers/bitbucket_server_provider.py

@@ -0,0 +1,351 @@
+import json
+from typing import Optional, Tuple
+from urllib.parse import urlparse
+
+import requests
+from atlassian.bitbucket import Bitbucket
+from starlette_context import context
+
+from .git_provider import FilePatchInfo, GitProvider, EDIT_TYPE
+from ..algo.pr_processing import find_line_number_of_relevant_line_in_file
+from ..algo.utils import load_large_diff
+from ..config_loader import get_settings
+from ..log import get_logger
+
+
+class BitbucketServerProvider(GitProvider):
+    def __init__(
+        self, pr_url: Optional[str] = None, incremental: Optional[bool] = False
+    ):
+        s = requests.Session()
+        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_SERVER.BEARER_TOKEN", None)}'
+
+        s.headers["Content-Type"] = "application/json"
+        self.headers = s.headers
+        self.bitbucket_server_url = None
+        self.workspace_slug = None
+        self.repo_slug = None
+        self.repo = None
+        self.pr_num = None
+        self.pr = None
+        self.pr_url = pr_url
+        self.temp_comments = []
+        self.incremental = incremental
+        self.diff_files = None
+        self.bitbucket_pull_request_api_url = pr_url
+
+        self.bitbucket_server_url = self._parse_bitbucket_server(url=pr_url)
+        self.bitbucket_client = Bitbucket(url=self.bitbucket_server_url,
+                                          token=get_settings().get("BITBUCKET_SERVER.BEARER_TOKEN", None))
+
+        if pr_url:
+            self.set_pr(pr_url)
+
+    def get_repo_settings(self):
+        try:
+            url = (f"{self.bitbucket_server_url}/projects/{self.workspace_slug}/repos/{self.repo_slug}/src/"
+                   f"{self.pr.destination_branch}/.pr_agent.toml")
+            response = requests.request("GET", url, headers=self.headers)
+            if response.status_code == 404:  # not found
+                return ""
+            contents = response.text.encode('utf-8')
+            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:
+                    get_logger().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:
+                    get_logger().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:
+                get_logger().error(f"Failed to publish code suggestion, error: {e}")
+            return False
+
+    def is_supported(self, capability: str) -> bool:
+        if capability in ['get_issue_comments', 'get_labels', 'gfm_markdown']:
+            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_file(self, path: str, commit_id: str):
+        file_content = ""
+        try:
+            file_content = self.bitbucket_client.get_content_of_file(self.workspace_slug,
+                                                                     self.repo_slug,
+                                                                     path,
+                                                                     commit_id)
+        except requests.HTTPError as e:
+            get_logger().debug(f"File {path} not found at commit id: {commit_id}")
+        return file_content
+
+    def get_files(self):
+        changes = self.bitbucket_client.get_pull_requests_changes(self.workspace_slug, self.repo_slug, self.pr_num)
+        diffstat = [change["path"]['toString'] for change in changes]
+        return diffstat
+
+    def get_diff_files(self) -> list[FilePatchInfo]:
+        if self.diff_files:
+            return self.diff_files
+
+        commits_in_pr = self.bitbucket_client.get_pull_requests_commits(
+            self.workspace_slug,
+            self.repo_slug,
+            self.pr_num
+        )
+
+        commit_list = list(commits_in_pr)
+        base_sha, head_sha = commit_list[0]['parents'][0]['id'], commit_list[-1]['id']
+
+        diff_files = []
+        original_file_content_str = ""
+        new_file_content_str = ""
+
+        changes = self.bitbucket_client.get_pull_requests_changes(self.workspace_slug, self.repo_slug, self.pr_num)
+        for change in changes:
+            file_path = change['path']['toString']
+            match change['type']:
+                case 'ADD':
+                    edit_type = EDIT_TYPE.ADDED
+                    new_file_content_str = self.get_file(file_path, head_sha)
+                    if isinstance(new_file_content_str, (bytes, bytearray)):
+                        new_file_content_str = new_file_content_str.decode("utf-8")
+                    original_file_content_str = ""
+                case 'DELETE':
+                    edit_type = EDIT_TYPE.DELETED
+                    new_file_content_str = ""
+                    original_file_content_str = self.get_file(file_path, base_sha)
+                    if isinstance(original_file_content_str, (bytes, bytearray)):
+                        original_file_content_str = original_file_content_str.decode("utf-8")
+                case 'RENAME':
+                    edit_type = EDIT_TYPE.RENAMED
+                case _:
+                    edit_type = EDIT_TYPE.MODIFIED
+                    original_file_content_str = self.get_file(file_path, base_sha)
+                    if isinstance(original_file_content_str, (bytes, bytearray)):
+                        original_file_content_str = original_file_content_str.decode("utf-8")
+                    new_file_content_str = self.get_file(file_path, head_sha)
+                    if isinstance(new_file_content_str, (bytes, bytearray)):
+                        new_file_content_str = new_file_content_str.decode("utf-8")
+
+            patch = load_large_diff(file_path, new_file_content_str, original_file_content_str)
+
+            diff_files.append(
+                FilePatchInfo(
+                    original_file_content_str,
+                    new_file_content_str,
+                    patch,
+                    file_path,
+                    edit_type=edit_type,
+                )
+            )
+
+        self.diff_files = diff_files
+        return diff_files
+
+    def publish_comment(self, pr_comment: str, is_temporary: bool = False):
+        if not is_temporary:
+            self.bitbucket_client.add_pull_request_comment(self.workspace_slug, self.repo_slug, self.pr_num, pr_comment)
+
+    def remove_initial_comment(self):
+        try:
+            for comment in self.temp_comments:
+                self.remove_comment(comment)
+        except ValueError as e:
+            get_logger().exception(f"Failed to remove temp comments, error: {e}")
+
+    def remove_comment(self, comment):
+        pass
+
+    # funtion to create_inline_comment
+    def create_inline_comment(self, body: str, relevant_file: str, relevant_line_in_file: str):
+        position, absolute_position = find_line_number_of_relevant_line_in_file(
+            self.get_diff_files(),
+            relevant_file.strip('`'),
+            relevant_line_in_file
+        )
+        if position == -1:
+            if get_settings().config.verbosity_level >= 2:
+                get_logger().info(f"Could not find position for {relevant_file} {relevant_line_in_file}")
+            subject_type = "FILE"
+        else:
+            subject_type = "LINE"
+        path = relevant_file.strip()
+        return dict(body=body, path=path, position=absolute_position) if subject_type == "LINE" else {}
+
+    def publish_inline_comment(self, comment: str, from_line: int, file: str):
+        payload = {
+            "text": comment,
+            "severity": "NORMAL",
+            "anchor": {
+                "diffType": "EFFECTIVE",
+                "path": file,
+                "lineType": "ADDED",
+                "line": from_line,
+                "fileType": "TO"
+            }
+        }
+
+        response = requests.post(url=self._get_pr_comments_url(), json=payload, headers=self.headers)
+        return response
+
+    def generate_link_to_relevant_line_number(self, suggestion) -> str:
+        try:
+            relevant_file = suggestion['relevant file'].strip('`').strip("'")
+            relevant_line_str = suggestion['relevant line']
+            if not relevant_line_str:
+                return ""
+
+            diff_files = self.get_diff_files()
+            position, absolute_position = find_line_number_of_relevant_line_in_file \
+                (diff_files, relevant_file, relevant_line_str)
+
+            if absolute_position != -1 and self.pr_url:
+                link = f"{self.pr_url}/#L{relevant_file}T{absolute_position}"
+                return link
+        except Exception as e:
+            if get_settings().config.verbosity_level >= 2:
+                get_logger().info(f"Failed adding line link, error: {e}")
+
+        return ""
+
+    def publish_inline_comments(self, comments: list[dict]):
+        for comment in comments:
+            self.publish_inline_comment(comment['body'], comment['position'], comment['path'])
+
+    def get_title(self):
+        return self.pr.title
+
+    def get_languages(self):
+        return {"yaml": 0}  # devops LOL
+
+    def get_pr_branch(self):
+        return self.pr.fromRef['displayId']
+
+    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 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
+
+    @staticmethod
+    def _parse_bitbucket_server(url: str) -> str:
+        parsed_url = urlparse(url)
+        return f"{parsed_url.scheme}://{parsed_url.netloc}"
+
+    @staticmethod
+    def _parse_pr_url(pr_url: str) -> Tuple[str, str, int]:
+        parsed_url = urlparse(pr_url)
+        path_parts = parsed_url.path.strip("/").split("/")
+        if len(path_parts) < 6 or path_parts[4] != "pull-requests":
+            raise ValueError(
+                "The provided URL does not appear to be a Bitbucket 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_repo(self):
+        if self.repo is None:
+            self.repo = self.bitbucket_client.get_repo(self.workspace_slug, self.repo_slug)
+        return self.repo
+
+    def _get_pr(self):
+        pr = self.bitbucket_client.get_pull_request(self.workspace_slug, self.repo_slug, pull_request_id=self.pr_num)
+        return type('new_dict', (object,), pr)
+
+    def _get_pr_file_content(self, remote_link: str):
+        return ""
+
+    def get_commit_messages(self):
+        def get_commit_messages(self):
+            raise NotImplementedError("Get commit messages function not implemented yet.")
+    # bitbucket does not support labels
+    def publish_description(self, pr_title: str, description: str):
+        payload = json.dumps({
+            "description": description,
+            "title": pr_title
+        })
+
+        response = requests.put(url=self.bitbucket_pull_request_api_url, headers=self.headers, data=payload)
+        return response
+
+    # bitbucket does not support labels
+    def publish_labels(self, pr_types: list):
+        pass
+    
+    # bitbucket does not support labels
+    def get_labels(self):
+        pass
+
+    def _get_pr_comments_url(self):
+        return f"{self.bitbucket_server_url}/rest/api/latest/projects/{self.workspace_slug}/repos/{self.repo_slug}/pull-requests/{self.pr_num}/comments"

pr_agent/git_providers/codecommit_provider.py

@@ -1,17 +1,16 @@
-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
 
+from ..algo.utils import load_large_diff
+from .git_provider import EDIT_TYPE, FilePatchInfo, GitProvider
+from ..config_loader import get_settings
+from ..log import get_logger
+
 
 class PullRequestCCMimic:
     """
@@ -62,6 +61,7 @@ class CodeCommitProvider(GitProvider):
         self.pr = None
         self.diff_files = None
         self.git_files = None
+        self.pr_url = pr_url
         if pr_url:
             self.set_pr(pr_url)
 
@@ -166,7 +166,7 @@ class CodeCommitProvider(GitProvider):
 
     def publish_comment(self, pr_comment: str, is_temporary: bool = False):
         if is_temporary:
-            logging.info(pr_comment)
+            get_logger().info(pr_comment)
             return
 
         pr_comment = CodeCommitProvider._remove_markdown_html(pr_comment)
@@ -188,12 +188,12 @@ class CodeCommitProvider(GitProvider):
         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")
+                get_logger().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']}")
+                get_logger().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,
@@ -222,6 +222,9 @@ class CodeCommitProvider(GitProvider):
     def remove_initial_comment(self):
         return ""  # not implemented yet
 
+    def remove_comment(self, comment):
+        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")
@@ -267,6 +270,8 @@ class CodeCommitProvider(GitProvider):
         # where each dictionary item is a language name.
         # We build that language->extension dictionary here in main_extensions_flat.
         main_extensions_flat = {}
+        language_extension_map_org = get_settings().language_extension_map_org
+        language_extension_map = {k.lower(): v for k, v in language_extension_map_org.items()}
         for language, extensions in language_extension_map.items():
             for ext in extensions:
                 main_extensions_flat[ext] = language
@@ -296,11 +301,11 @@ class CodeCommitProvider(GitProvider):
         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")
+        get_logger().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")
+        get_logger().info("CodeCommit provider does not support removing reactions yet")
         return True
 
     @staticmethod
@@ -366,7 +371,7 @@ class CodeCommitProvider(GitProvider):
         # 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(
+            get_logger().warning(
                 "Multiple targets in one PR is not supported for CodeCommit yet. Continuing, using the first target only..."
             )
 

pr_agent/git_providers/gerrit_provider.py

@@ -1,5 +1,4 @@
 import json
-import logging
 import os
 import pathlib
 import shutil
@@ -7,18 +6,16 @@ import subprocess
 import uuid
 from collections import Counter, namedtuple
 from pathlib import Path
-from tempfile import mkdtemp, NamedTemporaryFile
+from tempfile import NamedTemporaryFile, mkdtemp
 
 import requests
 import urllib3.util
 from git import Repo
 
 from pr_agent.config_loader import get_settings
-from pr_agent.git_providers.git_provider import GitProvider, FilePatchInfo, \
-    EDIT_TYPE
+from pr_agent.git_providers.git_provider import EDIT_TYPE, FilePatchInfo, GitProvider
 from pr_agent.git_providers.local_git_provider import PullRequestMimic
-
-logger = logging.getLogger(__name__)
+from pr_agent.log import get_logger
 
 
 def _call(*command, **kwargs) -> (int, str, str):
@@ -33,42 +30,42 @@ def _call(*command, **kwargs) -> (int, str, str):
 
 
 def clone(url, directory):
-    logger.info("Cloning %s to %s", url, directory)
+    get_logger().info("Cloning %s to %s", url, directory)
     stdout = _call('git', 'clone', "--depth", "1", url, directory)
-    logger.info(stdout)
+    get_logger().info(stdout)
 
 
 def fetch(url, refspec, cwd):
-    logger.info("Fetching %s %s", url, refspec)
+    get_logger().info("Fetching %s %s", url, refspec)
     stdout = _call(
         'git', 'fetch', '--depth', '2', url, refspec,
         cwd=cwd
     )
-    logger.info(stdout)
+    get_logger().info(stdout)
 
 
 def checkout(cwd):
-    logger.info("Checking out")
+    get_logger().info("Checking out")
     stdout = _call('git', 'checkout', "FETCH_HEAD", cwd=cwd)
-    logger.info(stdout)
+    get_logger().info(stdout)
 
 
 def show(*args, cwd=None):
-    logger.info("Show")
+    get_logger().info("Show")
     return _call('git', 'show', *args, cwd=cwd)
 
 
 def diff(*args, cwd=None):
-    logger.info("Diff")
+    get_logger().info("Diff")
     patch = _call('git', 'diff', *args, cwd=cwd)
     if not patch:
-        logger.warning("No changes found")
+        get_logger().warning("No changes found")
         return
     return patch
 
 
 def reset_local_changes(cwd):
-    logger.info("Reset local changes")
+    get_logger().info("Reset local changes")
     _call('git', 'checkout', "--force", cwd=cwd)
 
 
@@ -195,7 +192,7 @@ class GerritProvider(GitProvider):
         )
         self.repo = Repo(self.repo_path)
         assert self.repo
-
+        self.pr_url = base_url
         self.pr = PullRequestMimic(self.get_pr_title(), self.get_diff_files())
 
     def get_pr_title(self):
@@ -399,5 +396,8 @@ class GerritProvider(GitProvider):
         # shutil.rmtree(self.repo_path)
         pass
 
+    def remove_comment(self, comment):
+        pass
+
     def get_pr_branch(self):
         return self.repo.head

pr_agent/git_providers/git_provider.py

@@ -1,4 +1,3 @@
-import logging
 from abc import ABC, abstractmethod
 from dataclasses import dataclass
 
@@ -6,12 +5,16 @@ from dataclasses import dataclass
 from enum import Enum
 from typing import Optional
 
+from pr_agent.config_loader import get_settings
+from pr_agent.log import get_logger
+
 
 class EDIT_TYPE(Enum):
     ADDED = 1
     DELETED = 2
     MODIFIED = 3
     RENAMED = 4
+    UNKNOWN = 5
 
 
 @dataclass
@@ -21,8 +24,10 @@ class FilePatchInfo:
     patch: str
     filename: str
     tokens: int = -1
-    edit_type: EDIT_TYPE = EDIT_TYPE.MODIFIED
+    edit_type: EDIT_TYPE = EDIT_TYPE.UNKNOWN
     old_filename: str = None
+    num_plus_lines: int = -1
+    num_minus_lines: int = -1
 
 
 class GitProvider(ABC):
@@ -38,38 +43,10 @@ class GitProvider(ABC):
     def publish_description(self, pr_title: str, pr_body: str):
         pass
 
-    @abstractmethod
-    def publish_comment(self, pr_comment: str, is_temporary: bool = False):
-        pass
-
-    @abstractmethod
-    def publish_inline_comment(self, body: str, relevant_file: str, relevant_line_in_file: str):
-        pass
-
-    @abstractmethod
-    def create_inline_comment(self, body: str, relevant_file: str, relevant_line_in_file: str):
-        pass
-
-    @abstractmethod
-    def publish_inline_comments(self, comments: list[dict]):
-        pass
-
     @abstractmethod
     def publish_code_suggestions(self, code_suggestions: list) -> bool:
         pass
 
-    @abstractmethod
-    def publish_labels(self, labels):
-        pass
-
-    @abstractmethod
-    def get_labels(self):
-        pass
-
-    @abstractmethod
-    def remove_initial_comment(self):
-        pass
-
     @abstractmethod
     def get_languages(self):
         pass
@@ -88,17 +65,17 @@ class GitProvider(ABC):
 
     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)
+        from pr_agent.algo.utils import clip_tokens
+        max_tokens_description = 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)
+        if max_tokens_description:
+            return clip_tokens(description, max_tokens_description)
         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"):
+        if not any(description.startswith(header) for header in ("## PR Type", "## PR Description")):
             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
@@ -108,11 +85,57 @@ class GitProvider(ABC):
         return description.split("## User Description:", 1)[1].strip()
 
     @abstractmethod
-    def get_issue_comments(self):
+    def get_repo_settings(self):
+        pass
+
+    def get_pr_id(self):
+        return ""
+
+    def get_line_link(self, relevant_file: str, relevant_line_start: int, relevant_line_end: int = None) -> str:
+        return ""
+
+    #### comments operations ####
+    @abstractmethod
+    def publish_comment(self, pr_comment: str, is_temporary: bool = False):
+        pass
+
+    def publish_persistent_comment(self, pr_comment: str, initial_header: str, update_header: bool):
+        self.publish_comment(pr_comment)
+
+    @abstractmethod
+    def publish_inline_comment(self, body: str, relevant_file: str, relevant_line_in_file: str):
         pass
 
     @abstractmethod
-    def get_repo_settings(self):
+    def create_inline_comment(self, body: str, relevant_file: str, relevant_line_in_file: str):
+        pass
+
+    @abstractmethod
+    def publish_inline_comments(self, comments: list[dict]):
+        pass
+
+    @abstractmethod
+    def remove_initial_comment(self):
+        pass
+
+    @abstractmethod
+    def remove_comment(self, comment):
+        pass
+
+    @abstractmethod
+    def get_issue_comments(self):
+        pass
+
+    def get_comment_url(self, comment) -> str:
+        return ""
+
+    #### labels operations ####
+    @abstractmethod
+    def publish_labels(self, labels):
+        pass
+
+    @abstractmethod
+    def get_labels(self):
         pass
 
     @abstractmethod
@@ -123,11 +146,12 @@ class GitProvider(ABC):
     def remove_reaction(self, issue_comment_id: int, reaction_id: int) -> bool:
         pass
 
+    #### commits operations ####
     @abstractmethod
     def get_commit_messages(self):
         pass
 
-    def get_pr_id(self):
+    def get_latest_commit_url(self) -> str:
         return ""
 
 def get_main_pr_language(languages, files) -> str:
@@ -136,7 +160,10 @@ def get_main_pr_language(languages, files) -> str:
     """
     main_language_str = ""
     if not languages:
-        logging.info("No languages detected")
+        get_logger().info("No languages detected")
+        return main_language_str
+    if not files:
+        get_logger().info("No files in diff")
         return main_language_str
 
     try:
@@ -145,34 +172,52 @@ def get_main_pr_language(languages, files) -> str:
         # validate that the specific commit uses the main language
         extension_list = []
         for file in files:
+            if not file:
+                continue
             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
-        most_common_extension = max(set(extension_list), key=extension_list.count)
+        most_common_extension = '.' + max(set(extension_list), key=extension_list.count)
+        try:
+            language_extension_map_org = get_settings().language_extension_map_org
+            language_extension_map = {k.lower(): v for k, v in language_extension_map_org.items()}
 
-        # look for a match. TBD: add more languages, do this systematically
-        if most_common_extension == 'py' and top_language == 'python' or \
-                most_common_extension == 'js' and top_language == 'javascript' or \
-                most_common_extension == 'ts' and top_language == 'typescript' or \
-                most_common_extension == 'go' and top_language == 'go' or \
-                most_common_extension == 'java' and top_language == 'java' or \
-                most_common_extension == 'c' and top_language == 'c' or \
-                most_common_extension == 'cpp' and top_language == 'c++' or \
-                most_common_extension == 'cs' and top_language == 'c#' or \
-                most_common_extension == 'swift' and top_language == 'swift' or \
-                most_common_extension == 'php' and top_language == 'php' or \
-                most_common_extension == 'rb' and top_language == 'ruby' or \
-                most_common_extension == 'rs' and top_language == 'rust' or \
-                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 == top_language:
-            main_language_str = top_language
+            if top_language in language_extension_map and most_common_extension in language_extension_map[top_language]:
+                main_language_str = top_language
+            else:
+                for language, extensions in language_extension_map.items():
+                    if most_common_extension in extensions:
+                        main_language_str = language
+                        break
+        except Exception as e:
+            get_logger().exception(f"Failed to get main language: {e}")
+            pass
+
+        ## old approach:
+        # most_common_extension = max(set(extension_list), key=extension_list.count)
+        # if most_common_extension == 'py' and top_language == 'python' or \
+        #         most_common_extension == 'js' and top_language == 'javascript' or \
+        #         most_common_extension == 'ts' and top_language == 'typescript' or \
+        #         most_common_extension == 'tsx' and top_language == 'typescript' or \
+        #         most_common_extension == 'go' and top_language == 'go' or \
+        #         most_common_extension == 'java' and top_language == 'java' or \
+        #         most_common_extension == 'c' and top_language == 'c' or \
+        #         most_common_extension == 'cpp' and top_language == 'c++' or \
+        #         most_common_extension == 'cs' and top_language == 'c#' or \
+        #         most_common_extension == 'swift' and top_language == 'swift' or \
+        #         most_common_extension == 'php' and top_language == 'php' or \
+        #         most_common_extension == 'rb' and top_language == 'ruby' or \
+        #         most_common_extension == 'rs' and top_language == 'rust' or \
+        #         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 == top_language:
+        #     main_language_str = top_language
 
     except Exception as e:
-        logging.exception(e)
+        get_logger().exception(e)
         pass
 
     return main_language_str
@@ -182,6 +227,13 @@ class IncrementalPR:
     def __init__(self, is_incremental: bool = False):
         self.is_incremental = is_incremental
         self.commits_range = None
-        self.first_new_commit_sha = None
-        self.last_seen_commit_sha = None
+        self.first_new_commit = None
+        self.last_seen_commit = None
 
+    @property
+    def first_new_commit_sha(self):
+        return None if self.first_new_commit is None else self.first_new_commit.sha
+
+    @property
+    def last_seen_commit_sha(self):
+        return None if self.last_seen_commit is None else self.last_seen_commit.sha

pr_agent/git_providers/github_provider.py

@@ -1,20 +1,19 @@
-import logging
 import hashlib
-
 from datetime import datetime
-from typing import Optional, Tuple, Any
+from typing import Optional, Tuple
 from urllib.parse import urlparse
 
-from github import AppAuthentication, Auth, Github, GithubException, Reaction
+from github import AppAuthentication, Auth, Github, GithubException
 from retry import retry
 from starlette_context import context
 
-from .git_provider import FilePatchInfo, GitProvider, IncrementalPR
 from ..algo.language_handler import is_valid_file
-from ..algo.utils import load_large_diff
-from ..algo.pr_processing import find_line_number_of_relevant_line_in_file, clip_tokens
+from ..algo.pr_processing import find_line_number_of_relevant_line_in_file
+from ..algo.utils import load_large_diff, clip_tokens
 from ..config_loader import get_settings
+from ..log import get_logger
 from ..servers.utils import RateLimitExceeded
+from .git_provider import FilePatchInfo, GitProvider, IncrementalPR, EDIT_TYPE
 
 
 class GithubProvider(GitProvider):
@@ -35,6 +34,7 @@ class GithubProvider(GitProvider):
         if pr_url and 'pull' in pr_url:
             self.set_pr(pr_url)
             self.last_commit_id = list(self.pr.get_commits())[-1]
+            self.pr_url = self.get_pr_url() # pr_url for github actions can be as api.github.com, so we need to get the url from the pr object
 
     def is_supported(self, capability: str) -> bool:
         return True
@@ -51,36 +51,44 @@ class GithubProvider(GitProvider):
     def get_incremental_commits(self):
         self.commits = list(self.pr.get_commits())
 
-        self.get_previous_review()
+        self.previous_review = self.get_previous_review(full=True, incremental=True)
         if self.previous_review:
             self.incremental.commits_range = self.get_commit_range()
             # Get all files changed during the commit range
             self.file_set = dict()
             for commit in self.incremental.commits_range:
                 if commit.commit.message.startswith(f"Merge branch '{self._get_repo().default_branch}'"):
-                    logging.info(f"Skipping merge commit {commit.commit.message}")
+                    get_logger().info(f"Skipping merge commit {commit.commit.message}")
                     continue
                 self.file_set.update({file.filename: file for file in commit.files})
+        else:
+            raise ValueError("No previous review found")
 
     def get_commit_range(self):
         last_review_time = self.previous_review.created_at
-        first_new_commit_index = 0
+        first_new_commit_index = None
         for index in range(len(self.commits) - 1, -1, -1):
             if self.commits[index].commit.author.date > last_review_time:
-                self.incremental.first_new_commit_sha = self.commits[index].sha
+                self.incremental.first_new_commit = self.commits[index]
                 first_new_commit_index = index
             else:
-                self.incremental.last_seen_commit_sha = self.commits[index].sha
+                self.incremental.last_seen_commit = self.commits[index]
                 break
-        return self.commits[first_new_commit_index:]
+        return self.commits[first_new_commit_index:] if first_new_commit_index is not None else []
 
-    def get_previous_review(self):
-        self.previous_review = None
-        self.comments = list(self.pr.get_issue_comments())
+    def get_previous_review(self, *, full: bool, incremental: bool):
+        if not (full or incremental):
+            raise ValueError("At least one of full or incremental must be True")
+        if not getattr(self, "comments", None):
+            self.comments = list(self.pr.get_issue_comments())
+        prefixes = []
+        if full:
+            prefixes.append("## PR Analysis")
+        if incremental:
+            prefixes.append("## Incremental PR Review")
         for index in range(len(self.comments) - 1, -1, -1):
-            if self.comments[index].body.startswith("## PR Analysis"):
-                self.previous_review = self.comments[index]
-                break
+            if any(self.comments[index].body.startswith(prefix) for prefix in prefixes):
+                return self.comments[index]
 
     def get_files(self):
         if self.incremental.is_incremental and self.file_set:
@@ -124,22 +132,68 @@ class GithubProvider(GitProvider):
                     if not patch:
                         patch = load_large_diff(file.filename, new_file_content_str, original_file_content_str)
 
-                diff_files.append(FilePatchInfo(original_file_content_str, new_file_content_str, patch, file.filename))
+                if file.status == 'added':
+                    edit_type = EDIT_TYPE.ADDED
+                elif file.status == 'removed':
+                    edit_type = EDIT_TYPE.DELETED
+                elif file.status == 'renamed':
+                    edit_type = EDIT_TYPE.RENAMED
+                elif file.status == 'modified':
+                    edit_type = EDIT_TYPE.MODIFIED
+                else:
+                    get_logger().error(f"Unknown edit type: {file.status}")
+                    edit_type = EDIT_TYPE.UNKNOWN
+
+                # count number of lines added and removed
+                patch_lines = patch.splitlines(keepends=True)
+                num_plus_lines = len([line for line in patch_lines if line.startswith('+')])
+                num_minus_lines = len([line for line in patch_lines if line.startswith('-')])
+                file_patch_canonical_structure = FilePatchInfo(original_file_content_str, new_file_content_str, patch,
+                                                               file.filename, edit_type=edit_type,
+                                                               num_plus_lines=num_plus_lines,
+                                                               num_minus_lines=num_minus_lines,)
+                diff_files.append(file_patch_canonical_structure)
 
             self.diff_files = diff_files
             return diff_files
 
         except GithubException.RateLimitExceededException as e:
-            logging.error(f"Rate limit exceeded for GitHub API. Original message: {e}")
+            get_logger().error(f"Rate limit exceeded for GitHub API. Original message: {e}")
             raise RateLimitExceeded("Rate limit exceeded for GitHub API.") from e
 
     def publish_description(self, pr_title: str, pr_body: str):
         self.pr.edit(title=pr_title, body=pr_body)
 
+    def get_latest_commit_url(self) -> str:
+        return self.last_commit_id.html_url
+
+    def get_comment_url(self, comment) -> str:
+        return comment.html_url
+
+    def publish_persistent_comment(self, pr_comment: str, initial_header: str, update_header: bool = True):
+        prev_comments = list(self.pr.get_issue_comments())
+        for comment in prev_comments:
+            body = comment.body
+            if body.startswith(initial_header):
+                latest_commit_url = self.get_latest_commit_url()
+                comment_url = self.get_comment_url(comment)
+                if update_header:
+                    updated_header = f"{initial_header}\n\n### (review updated until commit {latest_commit_url})\n"
+                    pr_comment_updated = pr_comment.replace(initial_header, updated_header)
+                else:
+                    pr_comment_updated = pr_comment
+                get_logger().info(f"Persistent mode- updating comment {comment_url} to latest review message")
+                response = comment.edit(pr_comment_updated)
+                self.publish_comment(
+                    f"**[Persistent review]({comment_url})** updated to latest commit {latest_commit_url}")
+                return
+        self.publish_comment(pr_comment)
+
     def publish_comment(self, pr_comment: str, is_temporary: bool = False):
         if is_temporary and not get_settings().config.publish_output_progress:
-            logging.debug(f"Skipping publish_comment for temporary comment: {pr_comment}")
+            get_logger().debug(f"Skipping publish_comment for temporary comment: {pr_comment}")
             return
+
         response = self.pr.create_issue_comment(pr_comment)
         if hasattr(response, "user") and hasattr(response.user, "login"):
             self.github_user_id = response.user.login
@@ -156,7 +210,7 @@ class GithubProvider(GitProvider):
         position, absolute_position = find_line_number_of_relevant_line_in_file(self.diff_files, relevant_file.strip('`'), relevant_line_in_file)
         if position == -1:
             if get_settings().config.verbosity_level >= 2:
-                logging.info(f"Could not find position for {relevant_file} {relevant_line_in_file}")
+                get_logger().info(f"Could not find position for {relevant_file} {relevant_line_in_file}")
             subject_type = "FILE"
         else:
             subject_type = "LINE"
@@ -179,13 +233,13 @@ class GithubProvider(GitProvider):
 
             if not relevant_lines_start or relevant_lines_start == -1:
                 if get_settings().config.verbosity_level >= 2:
-                    logging.exception(
+                    get_logger().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, "
+                    get_logger().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
@@ -212,16 +266,22 @@ class GithubProvider(GitProvider):
             return True
         except Exception as e:
             if get_settings().config.verbosity_level >= 2:
-                logging.error(f"Failed to publish code suggestion, error: {e}")
+                get_logger().error(f"Failed to publish code suggestion, error: {e}")
             return False
 
     def remove_initial_comment(self):
         try:
             for comment in getattr(self.pr, 'comments_list', []):
                 if comment.is_temporary:
-                    comment.delete()
+                    self.remove_comment(comment)
         except Exception as e:
-            logging.exception(f"Failed to remove initial comment, error: {e}")
+            get_logger().exception(f"Failed to remove initial comment, error: {e}")
+
+    def remove_comment(self, comment):
+        try:
+            comment.delete()
+        except Exception as e:
+            get_logger().exception(f"Failed to remove comment, error: {e}")
 
     def get_title(self):
         return self.pr.title
@@ -259,7 +319,10 @@ class GithubProvider(GitProvider):
 
     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
+
+            # more logical to take 'pr_agent.toml' from the default branch
+            contents = self.repo_obj.get_contents(".pr_agent.toml").decoded_content
             return contents
         except Exception:
             return ""
@@ -269,7 +332,7 @@ class GithubProvider(GitProvider):
             reaction = self.pr.get_issue_comment(issue_comment_id).create_reaction("eyes")
             return reaction.id
         except Exception as e:
-            logging.exception(f"Failed to add eyes reaction, error: {e}")
+            get_logger().exception(f"Failed to add eyes reaction, error: {e}")
             return None
 
     def remove_reaction(self, issue_comment_id: int, reaction_id: int) -> bool:
@@ -277,7 +340,7 @@ class GithubProvider(GitProvider):
             self.pr.get_issue_comment(issue_comment_id).delete_reaction(reaction_id)
             return True
         except Exception as e:
-            logging.exception(f"Failed to remove eyes reaction, error: {e}")
+            get_logger().exception(f"Failed to remove eyes reaction, error: {e}")
             return False
 
 
@@ -352,7 +415,7 @@ class GithubProvider(GitProvider):
                 raise ValueError("GitHub app installation ID is required when using GitHub app deployment")
             auth = AppAuthentication(app_id=app_id, private_key=private_key,
                                      installation_id=self.installation_id)
-            return Github(app_auth=auth)
+            return Github(app_auth=auth, base_url=get_settings().github.base_url)
 
         if deployment_type == 'user':
             try:
@@ -361,7 +424,7 @@ class GithubProvider(GitProvider):
                 raise ValueError(
                     "GitHub token is required when using user deployment. See: "
                     "https://github.com/Codium-ai/pr-agent#method-2-run-from-source") from e
-            return Github(auth=Auth.Token(token))
+            return Github(auth=Auth.Token(token), base_url=get_settings().github.base_url)
 
     def _get_repo(self):
         if hasattr(self, 'repo_obj') and \
@@ -386,7 +449,7 @@ class GithubProvider(GitProvider):
     def publish_labels(self, pr_types):
         try:
             label_color_map = {"Bug fix": "1d76db", "Tests": "e99695", "Bug fix with tests": "c5def5",
-                               "Refactoring": "bfdadc", "Enhancement": "bfd4f2", "Documentation": "d4c5f9",
+                               "Enhancement": "bfd4f2", "Documentation": "d4c5f9",
                                "Other": "d1bcf9"}
             post_parameters = []
             for p in pr_types:
@@ -396,13 +459,13 @@ class GithubProvider(GitProvider):
                 "PUT", f"{self.pr.issue_url}/labels", input=post_parameters
             )
         except Exception as e:
-            logging.exception(f"Failed to publish labels, error: {e}")
+            get_logger().exception(f"Failed to publish labels, error: {e}")
 
     def get_labels(self):
         try:
             return [label.name for label in self.pr.labels]
         except Exception as e:
-            logging.exception(f"Failed to get labels, error: {e}")
+            get_logger().exception(f"Failed to get labels, error: {e}")
             return []
 
     def get_commit_messages(self):
@@ -444,10 +507,21 @@ class GithubProvider(GitProvider):
                 return link
         except Exception as e:
             if get_settings().config.verbosity_level >= 2:
-                logging.info(f"Failed adding line link, error: {e}")
+                get_logger().info(f"Failed adding line link, error: {e}")
 
         return ""
 
+    def get_line_link(self, relevant_file: str, relevant_line_start: int, relevant_line_end: int = None) -> str:
+        sha_file = hashlib.sha256(relevant_file.encode('utf-8')).hexdigest()
+        if relevant_line_start == -1:
+            link = f"https://github.com/{self.repo}/pull/{self.pr_num}/files#diff-{sha_file}"
+        elif relevant_line_end:
+            link = f"https://github.com/{self.repo}/pull/{self.pr_num}/files#diff-{sha_file}R{relevant_line_start}-R{relevant_line_end}"
+        else:
+            link = f"https://github.com/{self.repo}/pull/{self.pr_num}/files#diff-{sha_file}R{relevant_line_start}"
+        return link
+
+
     def get_pr_id(self):
         try:
             pr_id = f"{self.repo}/{self.pr_num}"

pr_agent/git_providers/gitlab_provider.py

@@ -1,4 +1,4 @@
-import logging
+import hashlib
 import re
 from typing import Optional, Tuple
 from urllib.parse import urlparse
@@ -7,12 +7,12 @@ import gitlab
 from gitlab import GitlabGetError
 
 from ..algo.language_handler import is_valid_file
-from ..algo.pr_processing import clip_tokens
-from ..algo.utils import load_large_diff
+from ..algo.pr_processing import find_line_number_of_relevant_line_in_file
+from ..algo.utils import load_large_diff, clip_tokens
 from ..config_loader import get_settings
 from .git_provider import EDIT_TYPE, FilePatchInfo, GitProvider
+from ..log import get_logger
 
-logger = logging.getLogger()
 
 class DiffNotFoundError(Exception):
     """Raised when the diff for a merge request cannot be found."""
@@ -37,13 +37,14 @@ class GitLabProvider(GitProvider):
         self.diff_files = None
         self.git_files = None
         self.temp_comments = []
+        self.pr_url = merge_request_url
         self._set_merge_request(merge_request_url)
         self.RE_HUNK_HEADER = re.compile(
             r"^@@ -(\d+)(?:,(\d+))? \+(\d+)(?:,(\d+))? @@[ ]?(.*)")
         self.incremental = incremental
 
     def is_supported(self, capability: str) -> bool:
-        if capability in ['get_issue_comments', 'create_inline_comment', 'publish_inline_comments', 'gfm_markdown']:
+        if capability in ['get_issue_comments', 'create_inline_comment', 'publish_inline_comments']: # gfm_markdown is supported in gitlab !
             return False
         return True
 
@@ -58,7 +59,7 @@ class GitLabProvider(GitProvider):
         try:
             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}")
+            get_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}") from e
 
 
@@ -98,7 +99,7 @@ class GitLabProvider(GitProvider):
                     if isinstance(new_file_content_str, bytes):
                         new_file_content_str = bytes.decode(new_file_content_str, 'utf-8')
                 except UnicodeDecodeError:
-                    logging.warning(
+                    get_logger().warning(
                         f"Cannot decode file {diff['old_path']} or {diff['new_path']} in merge request {self.id_mr}")
 
                 edit_type = EDIT_TYPE.MODIFIED
@@ -114,12 +115,20 @@ class GitLabProvider(GitProvider):
                 if not patch:
                     patch = load_large_diff(filename, new_file_content_str, original_file_content_str)
 
+
+                # count number of lines added and removed
+                patch_lines = patch.splitlines(keepends=True)
+                num_plus_lines = len([line for line in patch_lines if line.startswith('+')])
+                num_minus_lines = len([line for line in patch_lines if line.startswith('-')])
                 diff_files.append(
                     FilePatchInfo(original_file_content_str, new_file_content_str,
                                   patch=patch,
                                   filename=filename,
                                   edit_type=edit_type,
-                                  old_filename=None if diff['old_path'] == diff['new_path'] else diff['old_path']))
+                                  old_filename=None if diff['old_path'] == diff['new_path'] else diff['old_path'],
+                                  num_plus_lines=num_plus_lines,
+                                  num_minus_lines=num_minus_lines, ))
+
         self.diff_files = diff_files
         return diff_files
 
@@ -134,7 +143,34 @@ class GitLabProvider(GitProvider):
             self.mr.description = pr_body
             self.mr.save()
         except Exception as e:
-            logging.exception(f"Could not update merge request {self.id_mr} description: {e}")
+            get_logger().exception(f"Could not update merge request {self.id_mr} description: {e}")
+
+    def get_latest_commit_url(self):
+        return self.mr.commits().next().web_url
+
+    def get_comment_url(self, comment):
+        return f"{self.mr.web_url}#note_{comment.id}"
+
+    def publish_persistent_comment(self, pr_comment: str, initial_header: str, update_header: bool = True):
+        try:
+            for comment in self.mr.notes.list(get_all=True)[::-1]:
+                if comment.body.startswith(initial_header):
+                    latest_commit_url = self.get_latest_commit_url()
+                    comment_url = self.get_comment_url(comment)
+                    if update_header:
+                        updated_header = f"{initial_header}\n\n### (review updated until commit {latest_commit_url})\n"
+                        pr_comment_updated = pr_comment.replace(initial_header, updated_header)
+                    else:
+                        pr_comment_updated = pr_comment
+                    get_logger().info(f"Persistent mode- updating comment {comment_url} to latest review message")
+                    response = self.mr.notes.update(comment.id, {'body': pr_comment_updated})
+                    self.publish_comment(
+                        f"**[Persistent review]({comment_url})** updated to latest commit {latest_commit_url}")
+                    return
+        except Exception as e:
+            get_logger().exception(f"Failed to update persistent review, error: {e}")
+            pass
+        self.publish_comment(pr_comment)
 
     def publish_comment(self, mr_comment: str, is_temporary: bool = False):
         comment = self.mr.notes.create({'body': mr_comment})
@@ -156,12 +192,12 @@ class GitLabProvider(GitProvider):
     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}")
+            get_logger().info(f"Could not find position for {relevant_file} {relevant_line_in_file}")
         else:
             # 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}")
+                get_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,
@@ -174,24 +210,23 @@ class GitLabProvider(GitProvider):
             else:
                 pos_obj['new_line'] = target_line_no - 1
                 pos_obj['old_line'] = source_line_no - 1
-            logging.debug(f"Creating comment in {self.id_mr} with body {body} and position {pos_obj}")
-            self.mr.discussions.create({'body': body,
-                                        'position': pos_obj})
+            get_logger().debug(f"Creating comment in {self.id_mr} with body {body} and position {pos_obj}")
+            self.mr.discussions.create({'body': body, 'position': pos_obj})
 
     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.')
+            get_logger().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.')
+            get_logger().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(
+            get_logger().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
 
@@ -226,7 +261,10 @@ class GitLabProvider(GitProvider):
                 self.send_inline_comment(body, edit_type, found, relevant_file, relevant_line_in_file, source_line_no,
                                          target_file, target_line_no)
             except Exception as e:
-                logging.exception(f"Could not publish code suggestion:\nsuggestion: {suggestion}\nerror: {e}")
+                get_logger().exception(f"Could not publish code suggestion:\nsuggestion: {suggestion}\nerror: {e}")
+
+        # note that we publish suggestions one-by-one. so, if one fails, the rest will still be published
+        return True
 
     def search_line(self, relevant_file, relevant_line_in_file):
         target_file = None
@@ -285,9 +323,15 @@ class GitLabProvider(GitProvider):
     def remove_initial_comment(self):
         try:
             for comment in self.temp_comments:
-                comment.delete()
+                self.remove_comment(comment)
         except Exception as e:
-            logging.exception(f"Failed to remove temp comments, error: {e}")
+            get_logger().exception(f"Failed to remove temp comments, error: {e}")
+
+    def remove_comment(self, comment):
+        try:
+            comment.delete()
+        except Exception as e:
+            get_logger().exception(f"Failed to remove comment, error: {e}")
 
     def get_title(self):
         return self.mr.title
@@ -307,7 +351,7 @@ class GitLabProvider(GitProvider):
 
     def get_repo_settings(self):
         try:
-            contents = self.gl.projects.get(self.id_project).files.get(file_path='.pr_agent.toml', ref=self.mr.source_branch)
+            contents = self.gl.projects.get(self.id_project).files.get(file_path='.pr_agent.toml', ref=self.mr.target_branch).decode()
             return contents
         except Exception:
             return ""
@@ -355,7 +399,7 @@ class GitLabProvider(GitProvider):
             self.mr.labels = list(set(pr_types))
             self.mr.save()
         except Exception as e:
-            logging.exception(f"Failed to publish labels, error: {e}")
+            get_logger().exception(f"Failed to publish labels, error: {e}")
 
     def publish_inline_comments(self, comments: list[dict]):
         pass
@@ -386,3 +430,37 @@ class GitLabProvider(GitProvider):
             return pr_id
         except:
             return ""
+
+    def get_line_link(self, relevant_file: str, relevant_line_start: int, relevant_line_end: int = None) -> str:
+        if relevant_line_start == -1:
+            link = f"https://gitlab.com/codiumai/pr-agent/-/blob/{self.mr.source_branch}/{relevant_file}?ref_type=heads"
+        elif relevant_line_end:
+            link = f"https://gitlab.com/codiumai/pr-agent/-/blob/{self.mr.source_branch}/{relevant_file}?ref_type=heads#L{relevant_line_start}-L{relevant_line_end}"
+        else:
+            link = f"https://gitlab.com/codiumai/pr-agent/-/blob/{self.mr.source_branch}/{relevant_file}?ref_type=heads#L{relevant_line_start}"
+        return link
+
+
+    def generate_link_to_relevant_line_number(self, suggestion) -> str:
+        try:
+            relevant_file = suggestion['relevant file'].strip('`').strip("'")
+            relevant_line_str = suggestion['relevant line']
+            if not relevant_line_str:
+                return ""
+
+            position, absolute_position = find_line_number_of_relevant_line_in_file \
+                (self.diff_files, relevant_file, relevant_line_str)
+
+            if absolute_position != -1:
+                # link to right file only
+                link = f"https://gitlab.com/codiumai/pr-agent/-/blob/{self.mr.source_branch}/{relevant_file}?ref_type=heads#L{absolute_position}"
+
+                # # link to diff
+                # sha_file = hashlib.sha1(relevant_file.encode('utf-8')).hexdigest()
+                # link = f"{self.pr.web_url}/diffs#{sha_file}_{absolute_position}_{absolute_position}"
+                return link
+        except Exception as e:
+            if get_settings().config.verbosity_level >= 2:
+                get_logger().info(f"Failed adding line link, error: {e}")
+
+        return ""

pr_agent/git_providers/local_git_provider.py

@@ -1,4 +1,3 @@
-import logging
 from collections import Counter
 from pathlib import Path
 from typing import List
@@ -7,6 +6,7 @@ from git import Repo
 
 from pr_agent.config_loader import _find_repository_root, get_settings
 from pr_agent.git_providers.git_provider import EDIT_TYPE, FilePatchInfo, GitProvider
+from pr_agent.log import get_logger
 
 
 class PullRequestMimic:
@@ -49,7 +49,7 @@ class LocalGitProvider(GitProvider):
         """
         Prepare the repository for PR-mimic generation.
         """
-        logging.debug('Preparing repository for PR-mimic generation...')
+        get_logger().debug('Preparing repository for PR-mimic generation...')
         if self.repo.is_dirty():
             raise ValueError('The repository is not in a clean state. Please commit or stash pending changes.')
         if self.target_branch_name not in self.repo.heads:
@@ -140,6 +140,9 @@ class LocalGitProvider(GitProvider):
     def remove_initial_comment(self):
         pass  # Not applicable to the local git provider, but required by the interface
 
+    def remove_comment(self, comment):
+        pass  # Not applicable to the local git provider, but required by the interface
+
     def get_languages(self):
         """
         Calculate percentage of languages in repository. Used for hunk prioritisation.

pr_agent/git_providers/utils.py

@@ -0,0 +1,37 @@
+import copy
+import os
+import tempfile
+
+from dynaconf import Dynaconf
+
+from pr_agent.config_loader import get_settings
+from pr_agent.git_providers import get_git_provider
+from pr_agent.log import get_logger
+
+
+def apply_repo_settings(pr_url):
+    if get_settings().config.use_repo_settings_file:
+        repo_settings_file = None
+        try:
+            git_provider = get_git_provider()(pr_url)
+            repo_settings = git_provider.get_repo_settings()
+            if repo_settings:
+                repo_settings_file = None
+                fd, repo_settings_file = tempfile.mkstemp(suffix='.toml')
+                os.write(fd, repo_settings)
+                new_settings = Dynaconf(settings_files=[repo_settings_file])
+                for section, contents in new_settings.as_dict().items():
+                    section_dict = copy.deepcopy(get_settings().as_dict().get(section, {}))
+                    for key, value in contents.items():
+                        section_dict[key] = value
+                    get_settings().unset(section)
+                    get_settings().set(section, section_dict, merge=False)
+                    get_logger().info(f"Applying repo settings for section {section}, contents: {contents}")
+        except Exception as e:
+            get_logger().exception("Failed to apply repo settings", e)
+        finally:
+            if repo_settings_file:
+                try:
+                    os.remove(repo_settings_file)
+                except Exception as e:
+                    get_logger().error(f"Failed to remove temporary settings file {repo_settings_file}", e)

pr_agent/log/__init__.py

@@ -0,0 +1,40 @@
+import json
+import logging
+import sys
+from enum import Enum
+
+from loguru import logger
+
+
+class LoggingFormat(str, Enum):
+    CONSOLE = "CONSOLE"
+    JSON = "JSON"
+
+
+def json_format(record: dict) -> str:
+    return record["message"]
+
+
+def setup_logger(level: str = "INFO", fmt: LoggingFormat = LoggingFormat.CONSOLE):
+    level: int = logging.getLevelName(level.upper())
+    if type(level) is not int:
+        level = logging.INFO
+
+    if fmt == LoggingFormat.JSON:
+        logger.remove(None)
+        logger.add(
+            sys.stdout,
+            level=level,
+            format="{message}",
+            colorize=False,
+            serialize=True,
+        )
+    elif fmt == LoggingFormat.CONSOLE:
+        logger.remove(None)
+        logger.add(sys.stdout, level=level, colorize=True)
+
+    return logger
+
+
+def get_logger(*args, **kwargs):
+    return logger

pr_agent/secret_providers/google_cloud_storage_secret_provider.py

@@ -1,9 +1,8 @@
 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.log import get_logger
 from pr_agent.secret_providers.secret_provider import SecretProvider
 
 
@@ -15,7 +14,7 @@ class GoogleCloudStorageSecretProvider(SecretProvider):
             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}")
+            get_logger().error(f"Failed to initialize Google Cloud Storage Secret Provider: {e}")
             raise e
 
     def get_secret(self, secret_name: str) -> str:
@@ -23,7 +22,7 @@ class GoogleCloudStorageSecretProvider(SecretProvider):
             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}")
+            get_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):
@@ -31,5 +30,5 @@ class GoogleCloudStorageSecretProvider(SecretProvider):
             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}")
+            get_logger().error(f"Failed to store secret {secret_name} in Google Cloud Storage: {e}")
             raise e

pr_agent/servers/bitbucket_app.py

@@ -1,9 +1,7 @@
 import copy
 import hashlib
 import json
-import logging
 import os
-import sys
 import time
 
 import jwt
@@ -18,9 +16,10 @@ 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.log import LoggingFormat, get_logger, setup_logger
 from pr_agent.secret_providers import get_secret_provider
 
-logging.basicConfig(stream=sys.stdout, level=logging.INFO)
+setup_logger(fmt=LoggingFormat.JSON)
 router = APIRouter()
 secret_provider = get_secret_provider()
 
@@ -49,7 +48,7 @@ async def get_bearer_token(shared_secret: str, client_key: str):
         bearer_token = response.json()["access_token"]
         return bearer_token
     except Exception as e:
-        logging.error(f"Failed to get bearer token: {e}")
+        get_logger().error(f"Failed to get bearer token: {e}")
         raise e
 
 @router.get("/")
@@ -60,21 +59,23 @@ async def handle_manifest(request: Request, response: Response):
         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")
+        get_logger().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)
+    log_context = {"server_type": "bitbucket_app"}
+    get_logger().debug(request.headers)
     jwt_header = request.headers.get("authorization", None)
     if jwt_header:
         input_jwt = jwt_header.split(" ")[1]
     data = await request.json()
-    print(data)
+    get_logger().debug(data)
     async def inner():
         try:
             owner = data["data"]["repository"]["owner"]["username"]
+            log_context["sender"] = owner
             secrets = json.loads(secret_provider.get_secret(owner))
             shared_secret = secrets["shared_secret"]
             client_key = secrets["client_key"]
@@ -86,13 +87,19 @@ async def handle_github_webhooks(background_tasks: BackgroundTasks, request: Req
             agent = PRAgent()
             if event == "pullrequest:created":
                 pr_url = data["data"]["pullrequest"]["links"]["html"]["href"]
-                await agent.handle_request(pr_url, "review")
+                log_context["api_url"] = pr_url
+                log_context["event"] = "pull_request"
+                with get_logger().contextualize(**log_context):
+                    await agent.handle_request(pr_url, "review")
             elif event == "pullrequest:comment_created":
                 pr_url = data["data"]["pullrequest"]["links"]["html"]["href"]
+                log_context["api_url"] = pr_url
+                log_context["event"] = "comment"
                 comment_body = data["data"]["comment"]["content"]["raw"]
-                await agent.handle_request(pr_url, comment_body)
+                with get_logger().contextualize(**log_context):
+                    await agent.handle_request(pr_url, comment_body)
         except Exception as e:
-            logging.error(f"Failed to handle webhook: {e}")
+            get_logger().error(f"Failed to handle webhook: {e}")
     background_tasks.add_task(inner)
     return "OK"
 
@@ -103,9 +110,10 @@ async def handle_github_webhooks(request: Request, response: Response):
 @router.post("/installed")
 async def handle_installed_webhooks(request: Request, response: Response):
     try:
-        print(request.headers)
+        get_logger().info("handle_installed_webhooks")
+        get_logger().info(request.headers)
         data = await request.json()
-        print(data)
+        get_logger().info(data)
         shared_secret = data["sharedSecret"]
         client_key = data["clientKey"]
         username = data["principal"]["username"]
@@ -115,13 +123,15 @@ async def handle_installed_webhooks(request: Request, response: Response):
         }
         secret_provider.store_secret(username, json.dumps(secrets))
     except Exception as e:
-        logging.error(f"Failed to register user: {e}")
+        get_logger().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):
+    get_logger().info("handle_uninstalled_webhooks")
+
     data = await request.json()
-    print(data)
+    get_logger().info(data)
 
 
 def start():

pr_agent/servers/bitbucket_pipeline_runner.py

@@ -1,34 +0,0 @@
-import os
-from pr_agent.agent.pr_agent import PRAgent
-from pr_agent.config_loader import get_settings
-from pr_agent.tools.pr_reviewer import PRReviewer
-import asyncio
-
-async def run_action():
-    try:
-        pull_request_id = os.environ.get("BITBUCKET_PR_ID", '')
-        slug = os.environ.get("BITBUCKET_REPO_SLUG", '')
-        workspace = os.environ.get("BITBUCKET_WORKSPACE", '')
-        bearer_token = os.environ.get('BITBUCKET_BEARER_TOKEN', None)
-        OPENAI_KEY = os.environ.get('OPENAI_API_KEY') or os.environ.get('OPENAI.KEY')
-        OPENAI_ORG = os.environ.get('OPENAI_ORG') or os.environ.get('OPENAI.ORG')
-        # Check if required environment variables are set
-        if not bearer_token:
-            print("BITBUCKET_BEARER_TOKEN not set")
-            return
-        
-        if not OPENAI_KEY:
-            print("OPENAI_KEY not set")
-            return
-        # Set the environment variables in the settings
-        get_settings().set("BITBUCKET.BEARER_TOKEN", bearer_token)
-        get_settings().set("OPENAI.KEY", OPENAI_KEY)
-        if OPENAI_ORG:
-            get_settings().set("OPENAI.ORG", OPENAI_ORG)
-        if pull_request_id and slug and workspace:
-            pr_url = f"https://bitbucket.org/{workspace}/{slug}/pull-requests/{pull_request_id}"
-            await PRReviewer(pr_url).run()
-    except Exception as e:
-        print(f"An error occurred: {e}")
-if __name__ == "__main__":
-    asyncio.run(run_action())

pr_agent/servers/bitbucket_server_webhook.py

@@ -0,0 +1,64 @@
+import json
+
+import uvicorn
+from fastapi import APIRouter, FastAPI
+from fastapi.encoders import jsonable_encoder
+from starlette import status
+from starlette.background import BackgroundTasks
+from starlette.middleware import Middleware
+from starlette.requests import Request
+from starlette.responses import JSONResponse
+from starlette_context.middleware import RawContextMiddleware
+
+from pr_agent.agent.pr_agent import PRAgent
+from pr_agent.config_loader import get_settings
+from pr_agent.log import get_logger
+
+router = APIRouter()
+
+
+def handle_request(background_tasks: BackgroundTasks, url: str, body: str, log_context: dict):
+    log_context["action"] = body
+    log_context["event"] = "pull_request" if body == "review" else "comment"
+    log_context["api_url"] = url
+    with get_logger().contextualize(**log_context):
+        background_tasks.add_task(PRAgent().handle_request, url, body)
+
+
+@router.post("/webhook")
+async def handle_webhook(background_tasks: BackgroundTasks, request: Request):
+    log_context = {"server_type": "bitbucket_server"}
+    data = await request.json()
+    get_logger().info(json.dumps(data))
+
+    pr_id = data['pullRequest']['id']
+    repository_name = data['pullRequest']['toRef']['repository']['slug']
+    project_name = data['pullRequest']['toRef']['repository']['project']['key']
+    bitbucket_server = get_settings().get("BITBUCKET_SERVER.URL")
+    pr_url = f"{bitbucket_server}/projects/{project_name}/repos/{repository_name}/pull-requests/{pr_id}"
+
+    log_context["api_url"] = pr_url
+    log_context["event"] = "pull_request"
+
+    handle_request(background_tasks, pr_url, "review", log_context)
+    return JSONResponse(status_code=status.HTTP_200_OK, content=jsonable_encoder({"message": "success"}))
+
+
+@router.get("/")
+async def root():
+    return {"status": "ok"}
+
+
+def start():
+    bitbucket_server_url = get_settings().get("BITBUCKET_SERVER.URL", None)
+    if not bitbucket_server_url:
+        raise ValueError("BITBUCKET_SERVER.URL is not set")
+    get_settings().config.git_provider = "bitbucket_server"
+    middleware = [Middleware(RawContextMiddleware)]
+    app = FastAPI(middleware=middleware)
+    app.include_router(router)
+    uvicorn.run(app, host="0.0.0.0", port=3000)
+
+
+if __name__ == '__main__':
+    start()

pr_agent/servers/gerrit_server.py

@@ -1,6 +1,4 @@
 import copy
-import logging
-import sys
 from enum import Enum
 from json import JSONDecodeError
 
@@ -12,9 +10,10 @@ 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 global_settings, get_settings
+from pr_agent.config_loader import get_settings, global_settings
+from pr_agent.log import get_logger, setup_logger
 
-logging.basicConfig(stream=sys.stdout, level=logging.DEBUG)
+setup_logger()
 router = APIRouter()
 
 
@@ -35,7 +34,7 @@ class Item(BaseModel):
 
 @router.post("/api/v1/gerrit/{action}")
 async def handle_gerrit_request(action: Action, item: Item):
-    logging.debug("Received a Gerrit request")
+    get_logger().debug("Received a Gerrit request")
     context["settings"] = copy.deepcopy(global_settings)
 
     if action == Action.ask:
@@ -54,7 +53,7 @@ async def get_body(request):
     try:
         body = await request.json()
     except JSONDecodeError as e:
-        logging.error("Error parsing request body", e)
+        get_logger().error("Error parsing request body", e)
         return {}
     return body
 

pr_agent/servers/github_action_runner.py

@@ -1,15 +1,34 @@
 import asyncio
 import json
 import os
+from typing import Union
 
 from pr_agent.agent.pr_agent import PRAgent
 from pr_agent.config_loader import get_settings
 from pr_agent.git_providers import get_git_provider
+from pr_agent.git_providers.utils import apply_repo_settings
+from pr_agent.log import get_logger
 from pr_agent.tools.pr_code_suggestions import PRCodeSuggestions
 from pr_agent.tools.pr_description import PRDescription
 from pr_agent.tools.pr_reviewer import PRReviewer
 
 
+def is_true(value: Union[str, bool]) -> bool:
+    if isinstance(value, bool):
+        return value
+    if isinstance(value, str):
+        return value.lower() == 'true'
+    return False
+
+
+def get_setting_or_env(key: str, default: Union[str, bool] = None) -> Union[str, bool]:
+    try:
+        value = get_settings().get(key, default)
+    except AttributeError:  # TBD still need to debug why this happens on GitHub Actions
+        value = os.getenv(key, None) or os.getenv(key.upper(), None) or os.getenv(key.lower(), None) or default
+    return value
+
+
 async def run_action():
     # Get environment variables
     GITHUB_EVENT_NAME = os.environ.get('GITHUB_EVENT_NAME')
@@ -19,7 +38,6 @@ async def run_action():
     GITHUB_TOKEN = os.environ.get('GITHUB_TOKEN')
     get_settings().set("CONFIG.PUBLISH_OUTPUT_PROGRESS", False)
 
-
     # Check if required environment variables are set
     if not GITHUB_EVENT_NAME:
         print("GITHUB_EVENT_NAME not set")
@@ -49,20 +67,29 @@ async def run_action():
         print(f"Failed to parse JSON: {e}")
         return
 
+    try:
+        get_logger().info("Applying repo settings")
+        pr_url = event_payload.get("pull_request", {}).get("html_url")
+        if pr_url:
+            apply_repo_settings(pr_url)
+            get_logger().info(f"enable_custom_labels: {get_settings().config.enable_custom_labels}")
+    except Exception as e:
+        get_logger().info(f"github action: failed to apply repo settings: {e}")
+
     # Handle pull request event
     if GITHUB_EVENT_NAME == "pull_request":
         action = event_payload.get("action")
         if action in ["opened", "reopened"]:
             pr_url = event_payload.get("pull_request", {}).get("url")
             if pr_url:
-                auto_review = os.environ.get('github_action.auto_review', None)
-                if auto_review is None or (isinstance(auto_review, str) and auto_review.lower() == 'true'):
+                auto_review = get_setting_or_env("GITHUB_ACTION.AUTO_REVIEW", None)
+                if auto_review is None or is_true(auto_review):
                     await PRReviewer(pr_url).run()
-                auto_describe = os.environ.get('github_action.auto_describe', None)
-                if isinstance(auto_describe, str) and auto_describe.lower() == 'true':
+                auto_describe = get_setting_or_env("GITHUB_ACTION.AUTO_DESCRIBE", None)
+                if is_true(auto_describe):
                     await PRDescription(pr_url).run()
-                auto_improve = os.environ.get('github_action.auto_improve', None)
-                if isinstance(auto_improve, str) and auto_improve.lower() == 'true':
+                auto_improve = get_setting_or_env("GITHUB_ACTION.AUTO_IMPROVE", None)
+                if is_true(auto_improve):
                     await PRCodeSuggestions(pr_url).run()
 
     # Handle issue comment event
@@ -89,4 +116,4 @@ async def run_action():
 
 
 if __name__ == '__main__':
-    asyncio.run(run_action())
+    asyncio.run(run_action())

pr_agent/servers/github_app.py

@@ -1,9 +1,7 @@
 import copy
-import logging
-import sys
 import os
-import time
-from typing import Any, Dict
+import asyncio.locks
+from typing import Any, Dict, List, Tuple
 
 import uvicorn
 from fastapi import APIRouter, FastAPI, HTTPException, Request, Response
@@ -15,9 +13,13 @@ 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
+from pr_agent.git_providers.utils import apply_repo_settings
+from pr_agent.git_providers.git_provider import IncrementalPR
+from pr_agent.log import LoggingFormat, get_logger, setup_logger
+from pr_agent.servers.utils import verify_signature, DefaultDictWithTimeout
+
+setup_logger(fmt=LoggingFormat.JSON)
 
-logging.basicConfig(stream=sys.stdout, level=logging.INFO)
 router = APIRouter()
 
 
@@ -28,11 +30,11 @@ async def handle_github_webhooks(request: Request, response: Response):
     Verifies the request signature, parses the request body, and passes it to the handle_request function for further
     processing.
     """
-    logging.debug("Received a GitHub webhook")
+    get_logger().debug("Received a GitHub webhook")
 
     body = await get_body(request)
 
-    logging.debug(f'Request body:\n{body}')
+    get_logger().debug(f'Request body:\n{body}')
     installation_id = body.get("installation", {}).get("id")
     context["installation_id"] = installation_id
     context["settings"] = copy.deepcopy(global_settings)
@@ -44,13 +46,14 @@ async def handle_github_webhooks(request: Request, response: Response):
 @router.post("/api/v1/marketplace_webhooks")
 async def handle_marketplace_webhooks(request: Request, response: Response):
     body = await get_body(request)
-    logging.info(f'Request body:\n{body}')
+    get_logger().info(f'Request body:\n{body}')
+
 
 async def get_body(request):
     try:
         body = await request.json()
     except Exception as e:
-        logging.error("Error parsing request body", e)
+        get_logger().error("Error parsing request body", e)
         raise HTTPException(status_code=400, detail="Error parsing request body") from e
     webhook_secret = getattr(get_settings().github, 'webhook_secret', None)
     if webhook_secret:
@@ -60,7 +63,9 @@ async def get_body(request):
     return body
 
 
-_duplicate_requests_cache = {}
+_duplicate_requests_cache = DefaultDictWithTimeout(ttl=get_settings().github_app.duplicate_requests_cache_ttl)
+_duplicate_push_triggers = DefaultDictWithTimeout(ttl=get_settings().github_app.push_trigger_pending_tasks_ttl)
+_pending_task_duplicate_push_conditions = DefaultDictWithTimeout(asyncio.locks.Condition, ttl=get_settings().github_app.push_trigger_pending_tasks_ttl)
 
 
 async def handle_request(body: Dict[str, Any], event: str):
@@ -76,8 +81,8 @@ async def handle_request(body: Dict[str, Any], event: str):
         return {}
     agent = PRAgent()
     bot_user = get_settings().github_app.bot_user
-    logging.info(f"action: '{action}'")
-    logging.info(f"event: '{event}'")
+    sender = body.get("sender", {}).get("login")
+    log_context = {"action": action, "event": event, "sender": sender, "server_type": "github_app"}
 
     if get_settings().github_app.duplicate_requests_cache and _is_duplicate_request(body):
         return {}
@@ -87,73 +92,143 @@ async def handle_request(body: Dict[str, Any], event: str):
         if "comment" not in body:
             return {}
         comment_body = body.get("comment", {}).get("body")
-        sender = body.get("sender", {}).get("login")
         if sender and bot_user in sender:
-            logging.info(f"Ignoring comment from {bot_user} user")
+            get_logger().info(f"Ignoring comment from {bot_user} user")
             return {}
-        logging.info(f"Processing comment from {sender} user")
+        get_logger().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 {}
-        logging.info(body)
-        logging.info(f"Handling comment because of event={event} and action={action}")
+        log_context["api_url"] = api_url
+        get_logger().info(body)
+        get_logger().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))
+        with get_logger().contextualize(**log_context):
+            await agent.handle_request(api_url, comment_body, notify=lambda: provider.add_eyes_reaction(comment_id))
 
     # 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 {}
-        if pull_request.get("draft", True) or pull_request.get("state") != "open" or pull_request.get("user", {}).get("login", "") == bot_user:
+    elif event == 'pull_request' and action != 'synchronize':
+        pull_request, api_url = _check_pull_request_event(action, body, log_context, bot_user)
+        if not (pull_request and api_url):
             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(body)
-                logging.info(f"Performing command: {new_command}")
-                await agent.handle_request(api_url, new_command)
+            get_logger().info(f"Performing review for {api_url=} because of {event=} and {action=}")
+            await _perform_commands("pr_commands", agent, body, api_url, log_context)
 
-    logging.info("event or action does not require handling")
+    # handle pull_request event with synchronize action - "push trigger" for new commits
+    elif event == 'pull_request' and action == 'synchronize' and get_settings().github_app.handle_push_trigger:
+        pull_request, api_url = _check_pull_request_event(action, body, log_context, bot_user)
+        if not (pull_request and api_url):
+            return {}
+
+        # TODO: do we still want to get the list of commits to filter bot/merge commits?
+        before_sha = body.get("before")
+        after_sha = body.get("after")
+        merge_commit_sha = pull_request.get("merge_commit_sha")
+        if before_sha == after_sha:
+            return {}
+        if get_settings().github_app.push_trigger_ignore_merge_commits and after_sha == merge_commit_sha:
+            return {}
+        if get_settings().github_app.push_trigger_ignore_bot_commits and body.get("sender", {}).get("login", "") == bot_user:
+            return {}
+
+        # Prevent triggering multiple times for subsequent push triggers when one is enough:
+        # The first push will trigger the processing, and if there's a second push in the meanwhile it will wait.
+        # Any more events will be discarded, because they will all trigger the exact same processing on the PR.
+        # We let the second event wait instead of discarding it because while the first event was being processed,
+        # more commits may have been pushed that led to the subsequent events,
+        # so we keep just one waiting as a delegate to trigger the processing for the new commits when done waiting.
+        current_active_tasks = _duplicate_push_triggers.setdefault(api_url, 0)
+        max_active_tasks = 2 if get_settings().github_app.push_trigger_pending_tasks_backlog else 1
+        if current_active_tasks < max_active_tasks:
+            # first task can enter, and second tasks too if backlog is enabled
+            get_logger().info(
+                f"Continue processing push trigger for {api_url=} because there are {current_active_tasks} active tasks"
+            )
+            _duplicate_push_triggers[api_url] += 1
+        else:
+            get_logger().info(
+                f"Skipping push trigger for {api_url=} because another event already triggered the same processing"
+            )
+            return {}
+        async with _pending_task_duplicate_push_conditions[api_url]:
+            if current_active_tasks == 1:
+                # second task waits
+                get_logger().info(
+                    f"Waiting to process push trigger for {api_url=} because the first task is still in progress"
+                )
+                await _pending_task_duplicate_push_conditions[api_url].wait()
+                get_logger().info(f"Finished waiting to process push trigger for {api_url=} - continue with flow")
+
+        try:
+            if get_settings().github_app.push_trigger_wait_for_initial_review and not get_git_provider()(api_url, incremental=IncrementalPR(True)).previous_review:
+                get_logger().info(f"Skipping incremental review because there was no initial review for {api_url=} yet")
+                return {}
+            get_logger().info(f"Performing incremental review for {api_url=} because of {event=} and {action=}")
+            await _perform_commands("push_commands", agent, body, api_url, log_context)
+
+        finally:
+            # release the waiting task block
+            async with _pending_task_duplicate_push_conditions[api_url]:
+                _pending_task_duplicate_push_conditions[api_url].notify(1)
+                _duplicate_push_triggers[api_url] -= 1
+
+    get_logger().info("event or action does not require handling")
     return {}
 
 
+def _check_pull_request_event(action: str, body: dict, log_context: dict, bot_user: str) -> Tuple[Dict[str, Any], str]:
+    invalid_result = {}, ""
+    pull_request = body.get("pull_request")
+    if not pull_request:
+        return invalid_result
+    api_url = pull_request.get("url")
+    if not api_url:
+        return invalid_result
+    log_context["api_url"] = api_url
+    if pull_request.get("draft", True) or pull_request.get("state") != "open" or pull_request.get("user", {}).get("login", "") == bot_user:
+        return invalid_result
+    if action in ("review_requested", "synchronize") and pull_request.get("created_at") == pull_request.get("updated_at"):
+        # avoid double reviews when opening a PR for the first time
+        return invalid_result
+    return pull_request, api_url
+
+
+async def _perform_commands(commands_conf: str, agent: PRAgent, body: dict, api_url: str, log_context: dict):
+    apply_repo_settings(api_url)
+    commands = get_settings().get(f"github_app.{commands_conf}")
+    for command in 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)
+        get_logger().info(body)
+        get_logger().info(f"Performing command: {new_command}")
+        with get_logger().contextualize(**log_context):
+            await agent.handle_request(api_url, new_command)
+
+
 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
+    get_logger().info(f"request_hash: {request_hash}")
+    is_duplicate = _duplicate_requests_cache.get(request_hash, False)
+    _duplicate_requests_cache[request_hash] = True
     if is_duplicate:
-        logging.info(f"Ignoring duplicate request {request_hash}")
+        get_logger().info(f"Ignoring duplicate request {request_hash}")
     return is_duplicate
 
 

pr_agent/servers/github_polling.py

@@ -1,6 +1,4 @@
 import asyncio
-import logging
-import sys
 from datetime import datetime, timezone
 
 import aiohttp
@@ -8,9 +6,10 @@ import aiohttp
 from pr_agent.agent.pr_agent import PRAgent
 from pr_agent.config_loader import get_settings
 from pr_agent.git_providers import get_git_provider
+from pr_agent.log import LoggingFormat, get_logger, setup_logger
 from pr_agent.servers.help import bot_help_text
 
-logging.basicConfig(stream=sys.stdout, level=logging.DEBUG)
+setup_logger(fmt=LoggingFormat.JSON)
 NOTIFICATION_URL = "https://api.github.com/notifications"
 
 
@@ -94,7 +93,7 @@ async def polling_loop():
                                             comment_body = comment['body'] if 'body' in comment else ''
                                             commenter_github_user = comment['user']['login'] \
                                                 if 'user' in comment else ''
-                                            logging.info(f"Commenter: {commenter_github_user}\nComment: {comment_body}")
+                                            get_logger().info(f"Commenter: {commenter_github_user}\nComment: {comment_body}")
                                             user_tag = "@" + user_id
                                             if user_tag not in comment_body:
                                                 continue
@@ -112,7 +111,7 @@ async def polling_loop():
                         print(f"Failed to fetch notifications. Status code: {response.status}")
 
             except Exception as e:
-                logging.error(f"Exception during processing of a notification: {e}")
+                get_logger().error(f"Exception during processing of a notification: {e}")
 
 
 if __name__ == '__main__':

pr_agent/servers/gitlab_webhook.py

@@ -1,7 +1,5 @@
 import copy
 import json
-import logging
-import sys
 
 import uvicorn
 from fastapi import APIRouter, FastAPI, Request, status
@@ -14,26 +12,37 @@ 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.log import LoggingFormat, get_logger, setup_logger
 from pr_agent.secret_providers import get_secret_provider
 
-logging.basicConfig(stream=sys.stdout, level=logging.INFO)
+setup_logger(fmt=LoggingFormat.JSON)
 router = APIRouter()
 
 secret_provider = get_secret_provider() if get_settings().get("CONFIG.SECRET_PROVIDER") else None
 
 
+def handle_request(background_tasks: BackgroundTasks, url: str, body: str, log_context: dict):
+    log_context["action"] = body
+    log_context["event"] = "pull_request" if body == "/review" else "comment"
+    log_context["api_url"] = url
+    with get_logger().contextualize(**log_context):
+        background_tasks.add_task(PRAgent().handle_request, url, body)
+
+
 @router.post("/webhook")
 async def gitlab_webhook(background_tasks: BackgroundTasks, request: Request):
+    log_context = {"server_type": "gitlab_app"}
     if request.headers.get("X-Gitlab-Token") and secret_provider:
         request_token = request.headers.get("X-Gitlab-Token")
         secret = secret_provider.get_secret(request_token)
         try:
             secret_dict = json.loads(secret)
             gitlab_token = secret_dict["gitlab_token"]
+            log_context["sender"] = secret_dict.get("token_name", secret_dict.get("id", "unknown"))
             context["settings"] = copy.deepcopy(global_settings)
             context["settings"].gitlab.personal_access_token = gitlab_token
         except Exception as e:
-            logging.error(f"Failed to validate secret {request_token}: {e}")
+            get_logger().error(f"Failed to validate secret {request_token}: {e}")
             return JSONResponse(status_code=status.HTTP_401_UNAUTHORIZED, content=jsonable_encoder({"message": "unauthorized"}))
     elif get_settings().get("GITLAB.SHARED_SECRET"):
         secret = get_settings().get("GITLAB.SHARED_SECRET")
@@ -45,17 +54,17 @@ async def gitlab_webhook(background_tasks: BackgroundTasks, request: Request):
     if not gitlab_token:
         return JSONResponse(status_code=status.HTTP_401_UNAUTHORIZED, content=jsonable_encoder({"message": "unauthorized"}))
     data = await request.json()
-    logging.info(json.dumps(data))
+    get_logger().info(json.dumps(data))
     if data.get('object_kind') == 'merge_request' and data['object_attributes'].get('action') in ['open', 'reopen']:
-        logging.info(f"A merge request has been opened: {data['object_attributes'].get('title')}")
+        get_logger().info(f"A merge request has been opened: {data['object_attributes'].get('title')}")
         url = data['object_attributes'].get('url')
-        background_tasks.add_task(PRAgent().handle_request, url, "/review")
+        handle_request(background_tasks, url, "/review", log_context)
     elif data.get('object_kind') == 'note' and data['event_type'] == 'note':
         if 'merge_request' in data:
             mr = data['merge_request']
             url = mr.get('url')
             body = data.get('object_attributes', {}).get('note')
-            background_tasks.add_task(PRAgent().handle_request, url, body)
+            handle_request(background_tasks, url, body, log_context)
     return JSONResponse(status_code=status.HTTP_200_OK, content=jsonable_encoder({"message": "success"}))
 
 

pr_agent/servers/help.py

@@ -1,17 +1,19 @@
-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 [--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" \
-                ">For example: /review --pr_reviewer.extra_instructions=\"focus on the file: ...\" \n" \
-                ">To list the possible configuration parameters, use the **/config** command.\n" \
+commands_text = "> **/review**: Request a review of your Pull Request.   \n" \
+                "> **/describe**: Update the PR title and description based on the contents of the PR.   \n" \
+                "> **/improve [--extended]**: Suggest code improvements. Extended mode provides a higher quality feedback.   \n" \
+                "> **/ask \\<QUESTION\\>**: Ask a question about the PR.   \n" \
+                "> **/update_changelog**: Update the changelog based on the PR's contents.   \n" \
+                "> **/add_docs**: Generate docstring for new components introduced in the PR.   \n" \
+                "> **/generate_labels**: Generate labels for the PR based on the PR's contents.   \n" \
+                "> see the [tools guide](https://github.com/Codium-ai/pr-agent/blob/main/docs/TOOLS_GUIDE.md) for more details.\n\n" \
+                ">To edit any configuration parameter from the [configuration.toml](https://github.com/Codium-ai/pr-agent/blob/main/pr_agent/settings/configuration.toml), add --config_path=new_value.  \n" \
+                ">For example: /review --pr_reviewer.extra_instructions=\"focus on the file: ...\"    \n" \
+                ">To list the possible configuration parameters, add a **/config** comment.   \n" \
 
 
 def bot_help_text(user: str):
-    return f"> Tag me in a comment '@{user}' and add one of the following commands:\n" + commands_text
+    return f"> Tag me in a comment '@{user}' and add one of the following commands:  \n" + commands_text
 
 
-actions_help_text = "> To invoke the PR-Agent, add a comment using one of the following commands:\n" + \
+actions_help_text = "> To invoke the PR-Agent, add a comment using one of the following commands:  \n" + \
                     commands_text

pr_agent/servers/serverless.py

@@ -1,14 +1,13 @@
-import logging
-
 from fastapi import FastAPI
 from mangum import Mangum
+from starlette.middleware import Middleware
+from starlette_context.middleware import RawContextMiddleware
 
 from pr_agent.servers.github_app import router
 
-logger = logging.getLogger()
-logger.setLevel(logging.DEBUG)
 
-app = FastAPI()
+middleware = [Middleware(RawContextMiddleware)]
+app = FastAPI(middleware=middleware)
 app.include_router(router)
 
 handler = Mangum(app, lifespan="off")

pr_agent/servers/utils.py

@@ -1,5 +1,8 @@
 import hashlib
 import hmac
+import time
+from collections import defaultdict
+from typing import Callable, Any
 
 from fastapi import HTTPException
 
@@ -25,3 +28,59 @@ def verify_signature(payload_body, secret_token, signature_header):
 class RateLimitExceeded(Exception):
     """Raised when the git provider API rate limit has been exceeded."""
     pass
+
+
+class DefaultDictWithTimeout(defaultdict):
+    """A defaultdict with a time-to-live (TTL)."""
+
+    def __init__(
+        self,
+        default_factory: Callable[[], Any] = None,
+        ttl: int = None,
+        refresh_interval: int = 60,
+        update_key_time_on_get: bool = True,
+        *args,
+        **kwargs,
+    ):
+        """
+        Args:
+            default_factory: The default factory to use for keys that are not in the dictionary.
+            ttl: The time-to-live (TTL) in seconds.
+            refresh_interval: How often to refresh the dict and delete items older than the TTL.
+            update_key_time_on_get: Whether to update the access time of a key also on get (or only when set).
+        """
+        super().__init__(default_factory, *args, **kwargs)
+        self.__key_times = dict()
+        self.__ttl = ttl
+        self.__refresh_interval = refresh_interval
+        self.__update_key_time_on_get = update_key_time_on_get
+        self.__last_refresh = self.__time() - self.__refresh_interval
+
+    @staticmethod
+    def __time():
+        return time.monotonic()
+
+    def __refresh(self):
+        if self.__ttl is None:
+            return
+        request_time = self.__time()
+        if request_time - self.__last_refresh > self.__refresh_interval:
+            return
+        to_delete = [key for key, key_time in self.__key_times.items() if request_time - key_time > self.__ttl]
+        for key in to_delete:
+            del self[key]
+        self.__last_refresh = request_time
+
+    def __getitem__(self, __key):
+        if self.__update_key_time_on_get:
+            self.__key_times[__key] = self.__time()
+        self.__refresh()
+        return super().__getitem__(__key)
+
+    def __setitem__(self, __key, __value):
+        self.__key_times[__key] = self.__time()
+        return super().__setitem__(__key, __value)
+
+    def __delitem__(self, __key):
+        del self.__key_times[__key]
+        return super().__delitem__(__key)

pr_agent/settings/.secrets_template.toml

@@ -34,7 +34,14 @@ key = "" # Optional, uncomment if you want to use Huggingface Inference API. Acq
 api_base = "" # the base url for your huggingface inference endpoint 
 
 [ollama]
-api_base = "" # the base url for your huggingface inference endpoint 
+api_base = "" # the base url for your local Llama 2, Code Llama, and other models inference endpoint. Acquire through https://ollama.ai/
+
+[vertexai]
+vertex_project = "" # the google cloud platform project name for your vertexai deployment
+vertex_location = "" # the google cloud platform location for your vertexai deployment
+
+[aws]
+bedrock_region = "" # the AWS region to call Bedrock APIs
 
 [github]
 # ---- Set the following only for deployment type == "user"

pr_agent/settings/configuration.toml

@@ -1,5 +1,5 @@
 [config]
-model="gpt-4"
+model="gpt-4" # "gpt-4-1106-preview"
 fallback_models=["gpt-3.5-turbo-16k"]
 git_provider="github"
 publish_output=true
@@ -10,35 +10,58 @@ use_repo_settings_file=true
 ai_timeout=180
 max_description_tokens = 500
 max_commits_tokens = 500
+max_model_tokens = 32000 # Limits the maximum number of tokens that can be used by any model, regardless of the model's default capabilities.
+patch_extra_lines = 3
 secret_provider="google_cloud_storage"
 cli_mode=false
 
 [pr_reviewer] # /review #
+# enable/disable features
 require_focused_review=false
 require_score_review=false
 require_tests_review=true
 require_security_review=true
 require_estimate_effort_to_review=true
+# general options
 num_code_suggestions=4
 inline_code_comments = false
 ask_and_reflect=false
 automatic_review=true
+remove_previous_review_comment=false
+persistent_comment=true
 extra_instructions = ""
+# review labels
+enable_review_labels_security=true
+enable_review_labels_effort=false
+# specific configurations for incremental review (/review -i)
+require_all_thresholds_for_incremental_review=false
+minimal_commits_for_incremental_review=0
+minimal_minutes_for_incremental_review=0
 
 [pr_description] # /describe #
 publish_labels=true
 publish_description_as_comment=false
 add_original_user_description=false
 keep_original_user_title=false
+use_bullet_points=true
 extra_instructions = ""
+enable_pr_type=true
+enable_file_walkthrough=false
+enable_semantic_files_types=true
+final_update_message = true
+
+
 # markers
 use_description_markers=false
 include_generated_by_header=true
 
+#custom_labels = ['Bug fix', 'Tests', 'Bug fix with tests', 'Enhancement', 'Documentation', 'Other']
+
 [pr_questions] # /ask #
 
 [pr_code_suggestions] # /improve #
 num_code_suggestions=4
+summarize = false
 extra_instructions = ""
 rank_suggestions = false
 # params for '/improve --extended' mode
@@ -47,6 +70,10 @@ rank_extended_suggestions = true
 max_number_of_calls = 5
 final_clip_factor = 0.9
 
+[pr_add_docs] # /add_docs #
+extra_instructions = ""
+docs_style = "Sphinx Style" # "Google Style with Args, Returns, Attributes...etc", "Numpy Style", "Sphinx Style", "PEP257", "reStructuredText"
+
 [pr_update_changelog] # /update_changelog #
 push_changelog_changes=false
 extra_instructions = ""
@@ -57,6 +84,7 @@ extra_instructions = ""
 # The type of deployment to create. Valid values are 'app' or 'user'.
 deployment_type = "user"
 ratelimit_retries = 5
+base_url = "https://api.github.com"
 
 [github_action]
 # auto_review = true    # set as env var in .github/workflows/pr-agent.yaml
@@ -77,6 +105,30 @@ pr_commands = [
     "/describe --pr_description.add_original_user_description=true --pr_description.keep_original_user_title=true",
     "/auto_review",
 ]
+# settings for "pull_request" event with "synchronize" action - used to detect and handle push triggers for new commits
+handle_push_trigger = false
+push_trigger_ignore_bot_commits = true
+push_trigger_ignore_merge_commits = true
+push_trigger_wait_for_initial_review = true
+push_trigger_pending_tasks_backlog = true
+push_trigger_pending_tasks_ttl = 300
+push_commands = [
+    "/describe --pr_description.add_original_user_description=true --pr_description.keep_original_user_title=true",
+    """/auto_review -i \
+       --pr_reviewer.require_focused_review=false \
+       --pr_reviewer.require_score_review=false \
+       --pr_reviewer.require_tests_review=false \
+       --pr_reviewer.require_security_review=false \
+       --pr_reviewer.require_estimate_effort_to_review=false \
+       --pr_reviewer.num_code_suggestions=0 \
+       --pr_reviewer.inline_code_comments=false \
+       --pr_reviewer.remove_previous_review_comment=true \
+       --pr_reviewer.require_all_thresholds_for_incremental_review=false \
+       --pr_reviewer.minimal_commits_for_incremental_review=5 \
+       --pr_reviewer.minimal_minutes_for_incremental_review=30 \
+       --pr_reviewer.extra_instructions='' \
+    """
+]
 
 [gitlab]
 # URL to the gitlab service
@@ -117,4 +169,4 @@ max_issues_to_scan = 500
 [pinecone]
 # fill and place in .secrets.toml
 #api_key = ...
-# environment = "gcp-starter"
+# environment = "gcp-starter"

pr_agent/settings/custom_labels.toml

@@ -0,0 +1,16 @@
+[config]
+enable_custom_labels=false
+
+## template for custom labels
+#[custom_labels."Bug fix"]
+#description = """Fixes a bug in the code"""
+#[custom_labels."Tests"]
+#description = """Adds or modifies tests"""
+#[custom_labels."Bug fix with tests"]
+#description = """Fixes a bug in the code and adds or modifies tests"""
+#[custom_labels."Enhancement"]
+#description = """Adds new features or modifies existing ones"""
+#[custom_labels."Documentation"]
+#description = """Adds or modifies documentation"""
+#[custom_labels."Other"]
+#description = """Other changes that do not fit in any of the above categories"""

pr_agent/settings/ignore.toml

@@ -0,0 +1,11 @@
+[ignore]
+
+glob = [
+    # Ignore files and directories matching these glob patterns.
+    # See https://docs.python.org/3/library/glob.html
+    'vendor/**',
+]
+regex = [
+    # Ignore files and directories matching these regex patterns.
+    # See https://learnbyexample.github.io/python-regex-cheatsheet/
+]

pr_agent/settings/language_extensions.toml

@@ -433,3 +433,6 @@ reStructuredText = [".rst", ".rest", ".rest.txt", ".rst.txt", ]
 wisp = [".wisp", ]
 xBase = [".prg", ".prw", ]
 
+[docs_blacklist_extensions]
+# Disable docs for these extensions of text files and scripts that are not programming languages of function, classes and methods
+docs_blacklist = ['sql', 'txt', 'yaml', 'json', 'xml', 'md', 'rst', 'rest', 'rest.txt', 'rst.txt', 'mdpolicy', 'mdown', 'markdown', 'mdwn', 'mkd', 'mkdn', 'mkdown', 'sh']

pr_agent/settings/pr_add_docs.toml

@@ -0,0 +1,126 @@
+[pr_add_docs_prompt]
+system="""You are PR-Doc, a language model that specializes in generating documentation for code components in a Pull Request (PR).
+Your task is to generate {{ docs_for_language }} for code components in the PR Diff.
+
+
+Example for the PR Diff format:
+======
+## src/file1.py
+
+@@ -12,3 +12,4 @@ def func1():
+__new hunk__
+12  code line1 that remained unchanged in the PR
+14 +new code line1 added in the PR
+15 +new code line2 added in the PR
+16  code line2 that remained unchanged in the PR
+__old hunk__
+ code line1 that remained unchanged in the PR
+-code line that was removed in the PR
+ code line2 that remained unchanged in the PR
+
+
+@@ ... @@ def func2():
+__new hunk__
+...
+__old hunk__
+...
+
+
+## src/file2.py
+...
+======
+
+
+Specific instructions:
+- Try to identify edited/added code components (classes/functions/methods...) that are undocumented, and generate {{ docs_for_language }} for each one.
+- If there are documented (any type of {{ language }} documentation) code components in the PR, Don't generate {{ docs_for_language }} for them.
+- Ignore code components that don't appear fully in the '__new hunk__' section. For example, you must see the component header and body.
+- Make sure the {{ docs_for_language }} starts and ends with standart {{ language }} {{ docs_for_language }} signs.
+- The {{ docs_for_language }} should be in standard format.
+- Provide the exact line number (inclusive) where the {{ docs_for_language }} should be added.
+
+
+{%- if extra_instructions %}
+
+Extra instructions from the user:
+======
+{{ extra_instructions }}
+======
+{%- endif %}
+
+
+You must use the following YAML schema to format your answer:
+```yaml
+Code Documentation:
+  type: array
+  uniqueItems: true
+  items:
+    relevant file:
+      type: string
+      description: the relevant file full path
+    relevant line:
+      type: integer
+      description: |-
+        The relevant line number from a '__new hunk__' section where the {{ docs_for_language }} should be added.
+    doc placement:
+      type: string
+      enum:
+        - before
+        - after
+      description: |-
+        The {{ docs_for_language }} placement relative to the relevant line (code component).
+    documentation:
+      type: string
+      description: |-
+        The {{ docs_for_language }} content. It should be complete, correctly formatted and indented, and without line numbers.
+```
+
+Example output:
+```yaml
+Code Documentation:
+-   relevant file: |-
+        src/file1.py
+    relevant lines: 12
+    doc placement: after
+    documentation: |-
+        \"\"\"
+        This is a python docstring for func1.
+        \"\"\"
+- ...
+...
+```
+
+
+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 }}'
+
+{%- if description %}
+
+Description:
+======
+{{ description|trim }}
+======
+{%- endif %}
+
+{%- if language %}
+
+Main PR language: '{{language}}'
+{%- endif %}
+
+
+The PR Diff:
+======
+{{ diff|trim }}
+======
+
+
+Response (should be a valid YAML, and nothing else):
+```yaml
+"""

pr_agent/settings/pr_code_suggestions_prompts.toml

@@ -1,22 +1,21 @@
 [pr_code_suggestions_prompt]
-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.
+system="""You are PR-Reviewer, a language model that specializes in suggesting code improvements for a Pull Request (PR).
+Your task is to provide meaningful and actionable code suggestions, to improve the new code presented in a PR diff (lines starting with '+').
 
-Example for a PR Diff input:
-'
+Example for the PR Diff format:
+======
 ## src/file1.py
 
-@@ -12,3 +12,5 @@ def func1():
+@@ -12,3 +12,4 @@ def func1():
 __new hunk__
-12  code line that already existed in the file...
-13  code line that already existed in the file....
+12  code line1 that remained unchanged in the PR
 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...
+16  code line2 that remained unchanged in the PR
 __old hunk__
- code line that already existed in the file...
+ code line1 that remained unchanged in the PR
 -code line that was removed in the PR
- code line that already existed in the file...
+ code line2 that remained unchanged in the PR
 
 
 @@ ... @@ def func2():
@@ -28,27 +27,29 @@ __old hunk__
 
 ## src/file2.py
 ...
-'
+======
+
 
 Specific instructions:
-- Provide up to {{ num_code_suggestions }} code suggestions.
-- 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, type hints, or comments.
-  Try to provide diverse and insightful suggestions.
+- Provide up to {{ num_code_suggestions }} code suggestions. Try to provide diverse and insightful suggestions.
+- 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, type hints, or comments.
 - 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.
+- 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 suggestion.
 - Assume there is additional relevant code, that is not included in the diff.
 
 
 {%- if extra_instructions %}
 
 Extra instructions from the user:
+======
 {{ extra_instructions }}
+======
 {%- endif %}
 
+
 You must use the following YAML schema to format your answer:
 ```yaml
 Code suggestions:
@@ -89,16 +90,19 @@ Code suggestions:
 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: |-
-        ...
+- 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: |-
+    ...
+...
 ```
 
 
@@ -112,18 +116,25 @@ Title: '{{title}}'
 
 Branch: '{{branch}}'
 
-Description: '{{description}}'
+{%- if description %}
+
+Description:
+======
+{{ description|trim }}
+======
+{%- endif %}
 
 {%- if language %}
 
-Main language: {{language}}
+Main PR language: '{{ language }}'
 {%- endif %}
 
 
 The PR Diff:
-```
-{{- diff|trim }}
-```
+======
+{{ diff|trim }}
+======
+
 
 Response (should be a valid YAML, and nothing else):
 ```yaml

pr_agent/settings/pr_custom_labels.toml

@@ -0,0 +1,86 @@
+[pr_custom_labels_prompt]
+system="""You are PR-Reviewer, a language model designed to review a Git Pull Request (PR).
+Your task is to provide labels that describe the PR content.
+{%- if enable_custom_labels %}
+Thoroughly read the labels name and the provided description, and decide whether the label is relevant to the PR.
+{%- endif %}
+
+{%- if extra_instructions %}
+
+Extra instructions from the user:
+======
+{{ extra_instructions }}
+======
+{% endif %}
+
+
+The output must be a YAML object equivalent to type $Labels, according to the following Pydantic definitions:
+======
+{%- if enable_custom_labels %}
+
+{{ custom_labels_class }}
+
+{%- else %}
+class Label(str, Enum):
+    bug_fix = "Bug fix"
+    tests = "Tests"
+    enhancement = "Enhancement"
+    documentation = "Documentation"
+    other = "Other"
+{%- endif %}
+
+class Labels(BaseModel):
+    labels: List[Label] = Field(min_items=0, description="custom labels that describe the PR. Return the label value, not the name.")
+======
+
+
+Example output:
+
+```yaml
+labels:
+- ...
+- ...
+```
+
+Answer should be a valid YAML, and nothing else.
+"""
+
+user="""PR Info:
+
+Previous title: '{{title}}'
+
+Branch: '{{ branch }}'
+
+{%- if description %}
+
+Description:
+======
+{{ description|trim }}
+======
+{%- endif %}
+
+{%- if language %}
+
+Main PR language: '{{ language }}'
+{%- endif %}
+{%- if commit_messages_str %}
+
+
+Commit messages:
+======
+{{ commit_messages_str|trim }}
+======
+{%- endif %}
+
+
+The PR Git Diff:
+======
+{{ diff|trim }}
+======
+
+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.
+
+
+Response (should be a valid YAML, and nothing else):
+```yaml
+"""

pr_agent/settings/pr_description_prompts.toml

@@ -1,86 +1,133 @@
 [pr_description_prompt]
-system="""You are CodiumAI-PR-Reviewer, a language model designed to review git pull requests.
-Your task is to provide full description of the PR content.
-- Make sure not to focus the new PR code (the '+' lines).
-- Notice that the 'Previous title', 'Previous description' and 'Commit messages' sections may be partial, simplistic, non-informative or not up-to-date. Hence, compare them to the PR diff code, and use them only as a reference.
--  If needed, each YAML output should be in block scalar format ('|-')
+system="""You are PR-Reviewer, a language model designed to review a Git Pull Request (PR).
+Your task is to provide a full description for the PR content - title, type, description, and main files walkthrough.
+- Focus on the new PR code (lines starting with '+').
+- Keep in mind that the 'Previous title', 'Previous description' and 'Commit messages' sections may be partial, simplistic, non-informative or out of date. Hence, compare them to the PR diff code, and use them only as a reference.
+- The generated title and description should prioritize the most significant changes.
+- If needed, each YAML output should be in block scalar indicator ('|-')
+
 {%- if extra_instructions %}
 
 Extra instructions from the user:
+=====
 {{ extra_instructions }}
+=====
 {% endif %}
 
-You must use the following YAML schema to format your answer:
-```yaml
-PR Title:
-  type: string
-  description: an informative title for the PR, describing its main theme
-PR Type:
-  type: array
-  items:
-    type: string
-    enum:
-      - Bug fix
-      - Tests
-      - Bug fix with tests
-      - Refactoring
-      - Enhancement
-      - Documentation
-      - Other
-PR Description:
-  type: string
-  description: an informative and concise description of the PR
-PR Main Files Walkthrough:
-  type: array
-  maxItems: 10
-  description: |-
-    a walkthrough of the PR changes. Review main files, and shortly describe the changes in each file (up to 10 most important files).
-  items:
-    filename:
-      type: string
-      description: the relevant file full path
-    changes in file:
-      type: string
-      description: minimal and concise description of the changes in the relevant file
+
+The output must be a YAML object equivalent to type $PRDescription, according to the following Pydantic definitions:
+=====
+class PRType(str, Enum):
+    bug_fix = "Bug fix"
+    tests = "Tests"
+    enhancement = "Enhancement"
+    documentation = "Documentation"
+    other = "Other"
+
+{%- if enable_custom_labels %}
+
+{{ custom_labels_class }}
+
+{%- endif %}
+
+{%- if enable_file_walkthrough %}
+class FileWalkthrough(BaseModel):
+    filename: str = Field(description="the relevant file full path")
+    changes_in_file: str = Field(description="minimal and concise summary of the changes in the relevant file")
+{%- endif %}
+
+{%- if enable_semantic_files_types %}
+Class FileDescription(BaseModel):
+    filename: str = Field(description="the relevant file full path")
+    changes_summary: str = Field(description="minimal and concise summary of the changes in the relevant file")
+    label: str = Field(description="a single semantic label that represents a type of code changes that occurred in the File. Possible values (partial list): 'bug fix', 'tests', 'enhancement', 'documentation', 'error handling', 'configuration changes', 'dependencies', 'formatting', 'miscellaneous', ...")
+{%- endif %}
+
+Class PRDescription(BaseModel):
+    title: str = Field(description="an informative title for the PR, describing its main theme")
+    type: List[PRType] = Field(description="one or more types that describe the PR type. Return the label value, not the name.")
+    description: str = Field(description="an informative and concise description of the PR. {%- if use_bullet_points %} Use bullet points.{% endif %}")
+{%- if enable_custom_labels %}
+    labels: List[Label] = Field(min_items=0, description="custom labels that describe the PR. Return the label value, not the name.")
+{%- endif %}
+{%- if enable_file_walkthrough %}
+    main_files_walkthrough: List[FileWalkthrough] = Field(max_items=10)
+{%- endif %}
+{%- if enable_semantic_files_types %}
+    pr_files[List[FileDescription]] = Field(max_items=15")
+{%- endif %}
+=====
 
 
 Example output:
+
 ```yaml
-PR Title: |-
+title: |-
   ...
-PR Type:
-  - Bug fix
-PR Description: |-
+type:
+- ...
+- ...
+{%- if enable_custom_labels %}
+labels:
+- ...
+- ...
+{%- endif %}
+description: |-
   ...
-PR Main Files Walkthrough:
-  - ...
-  - ...
+{%- if enable_file_walkthrough %}
+main_files_walkthrough:
+- ...
+- ...
+{%- endif %}
+{%- if enable_semantic_files_types %}
+pr_files:
+- filename: |
+    ...
+  changes_summary: |
+    ...
+  label: |
+    ...
+...
+{%- endif %}
 ```
 
-Make sure to output a valid YAML. Don't repeat the prompt in the answer, and avoid outputting the 'type' and 'description' fields.
+Answer should be a valid YAML, and nothing else. Each YAML output MUST be after a newline, with proper indent, and block scalar indicator ('|-')
 """
 
 user="""PR Info:
+
 Previous title: '{{title}}'
-Previous description: '{{description}}'
+
+{%- if description %}
+
+Previous description:
+=====
+{{ description|trim }}
+=====
+{%- endif %}
+
 Branch: '{{branch}}'
 {%- if language %}
 
-Main language: {{language}}
+Main PR language: '{{ language }}'
 {%- endif %}
 {%- if commit_messages_str %}
 
 Commit messages:
-{{commit_messages_str}}
+=====
+{{ commit_messages_str|trim }}
+=====
 {%- endif %}
 
 
-The PR Git Diff:
-```
-{{diff}}
-```
+The PR Diff:
+=====
+{{ diff|trim }}
+=====
+
 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.
 
+
 Response (should be a valid YAML, and nothing else):
 ```yaml
 """

pr_agent/settings/pr_information_from_user_prompts.toml

@@ -1,5 +1,5 @@
 [pr_information_from_user_prompt]
-system="""You are CodiumAI-PR-Reviewer, a language model designed to review git pull requests.
+system="""You are PR-Reviewer, a language model designed to review a Git Pull Request (PR).
 Given the PR Info and the PR Git Diff, generate 3 short questions about the PR code for the PR author.
 The goal of the questions is to help the language model understand the PR better, so the questions should be insightful, informative, non-trivial, and relevant to the PR.
 You should prefer asking yes\\no questions, or multiple choice questions. Also add at least one open-ended question, but make sure they are not too difficult, and can be answered in a sentence or two.
@@ -16,22 +16,36 @@ Questions to better understand the PR:
 
 user="""PR Info:
 Title: '{{title}}'
+
 Branch: '{{branch}}'
-Description: '{{description}}'
+
+{%- if description %}
+
+Description:
+======
+{{ description|trim }}
+======
+{%- endif %}
+
 {%- if language %}
-Main language: {{language}}
+
+Main PR language: '{{ language }}'
 {%- endif %}
 {%- if commit_messages_str %}
 
+
 Commit messages:
-{{commit_messages_str}}
+======
+{{ commit_messages_str|trim }}
+======
 {%- endif %}
 
 
 The PR Git Diff:
-```
-{{diff}}
-```
+======
+{{ diff|trim }}
+======
+
 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
 
 

pr_agent/settings/pr_questions_prompts.toml

@@ -1,36 +1,42 @@
 [pr_questions_prompt]
-system="""You are CodiumAI-PR-Reviewer, a language model designed to review git pull requests.
-Your task is to answer questions about the new PR code (the '+' lines), and provide feedback.
+system="""You are PR-Reviewer, a language model designed to review a Git Pull Request (PR).
+
+Your goal is to answer questions\\tasks about the new PR code (lines starting with '+'), and provide feedback.
 Be informative, constructive, and give examples. Try to be as specific as possible.
-Don't avoid answering the questions. You must answer the questions, as best as you can, without adding unrelated content.
-Make sure not to repeat modifications already implemented in the new PR code (the '+' lines).
+Don't avoid answering the questions. You must answer the questions, as best as you can, without adding any unrelated content.
 """
 
 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}}'
+
+{%- if description %}
+
+Description:
+======
+{{ description|trim }}
+======
+{%- endif %}
+
+{%- if language %}
+
+Main PR language: '{{ language }}'
 {%- endif %}
 
 
 The PR Git Diff:
-```
-{{diff}}
-```
+======
+{{ diff|trim }}
+======
 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
 
 
 The PR Questions:
-```
-{{ questions }}
-```
+======
+{{ questions|trim }}
+======
 
-Response:
+Response to the PR Questions:
 """

pr_agent/settings/pr_reviewer_prompts.toml

@@ -1,18 +1,19 @@
 [pr_review_prompt]
-system="""You are PR-Reviewer, a language model designed to review git pull requests.
+system="""You are PR-Reviewer, a language model designed to review a Git Pull Request (PR).
 Your task is to provide constructive and concise feedback for the PR, and also provide meaningful code suggestions.
+The review should focus on new code added in the PR diff (lines starting with '+')
 
-Example PR Diff input:
-'
+Example PR Diff:
+======
 ## 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 1 that remained unchanged in the PR
+code line 2 that remained unchanged in the PR
 -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...
++code line added in the PR
+code line 3 that remained unchanged in the PR
+
 
 @@ ... @@ def func2():
 ...
@@ -20,24 +21,28 @@ code line that already existed in the file....
 
 ## src/file2.py
 ...
-'
-
-The 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.
+
+
+Code suggestions guidelines:
+- Provide up to {{ num_code_suggestions }} code suggestions. Try to provide diverse and insightful suggestions.
 - 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, type hints, or comments.
-- Suggestions should focus on improving the new code added in the PR (lines starting with '+')
+- Suggestions should focus on the new code added in the PR diff (lines starting with '+')
 {%- endif %}
 
 {%- if extra_instructions %}
 
 Extra instructions from the user:
+======
 {{ extra_instructions }}
+======
 {% endif %}
 
+
 You must use the following YAML schema to format your answer:
 ```yaml
 PR Analysis:
@@ -52,7 +57,6 @@ PR Analysis:
     enum:
       - Bug fix
       - Tests
-      - Refactoring
       - Enhancement
       - Documentation
       - Other
@@ -91,16 +95,16 @@ PR Analysis:
     description: >-
       Estimate, on a scale of 1-5 (inclusive), the time and effort required to review this PR by an experienced and knowledgeable developer. 1 means short and easy review , 5 means long and hard review.
       Take into account the size, complexity, quality, and the needed changes of the PR code diff.
-      Explain your answer shortly (1-2 sentences).
+      Explain your answer shortly (1-2 sentences). Use the format: '1, because ...'
 {%- endif %}
 PR Feedback:
   General suggestions:
     type: string
     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.
+      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.
 {%- if num_code_suggestions > 0 %}
   Code feedback:
     type: array
@@ -113,11 +117,10 @@ PR Feedback:
       suggestion:
         type: string
         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
-          ('important' or 'medium'). Do not make suggestions for updating or
-          adding docstrings, renaming PR title and description, or linter like.
+          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 ('important' or 'medium').
+          Do not make suggestions for updating or adding docstrings, renaming PR title and description, or linter like.
       relevant line:
         type: string
         description: |-
@@ -129,8 +132,8 @@ PR Feedback:
   Security concerns:
     type: string
     description: >-
-      yes\\no question: does this PR code introduce possible security concerns or
-      issues, like SQL injection, XSS, CSRF, and others ? If answered 'yes',explain your answer shortly
+      does this PR code introduce possible vulnerabilities such as exposure of sensitive information (e.g., API keys, secrets, passwords), or security concerns like SQL injection, XSS, CSRF, and others ? Answer 'No' if there are no possible issues.
+      Answer 'Yes, because ...' if there are security concerns or issues. Explain your answer shortly.
 {%- endif %}
 ```
 
@@ -142,7 +145,7 @@ PR Analysis:
   PR summary: |-
     xxx
   Type of PR: |-
-    Bug fix
+    ...
 {%- if require_score %}
   Score: 89
 {%- endif %}
@@ -152,7 +155,8 @@ PR Analysis:
   Focused PR: no, because ...
 {%- endif %}
 {%- if require_estimate_effort_to_review %}
-  Estimated effort to review [1-5]: 3, because ...
+  Estimated effort to review [1-5]: |-
+    3, because ...
 {%- endif %}
 PR Feedback:
   General PR suggestions: |-
@@ -177,34 +181,50 @@ Don't repeat the prompt in the answer, and avoid outputting the 'type' and 'desc
 """
 
 user="""PR Info:
+
 Title: '{{title}}'
+
 Branch: '{{branch}}'
-Description: '{{description}}'
+
+{%- if description %}
+
+Description:
+======
+{{ description|trim }}
+======
+{%- endif %}
+
 {%- if language %}
-Main language: {{language}}
+
+Main PR language: '{{ language }}'
 {%- endif %}
 {%- if commit_messages_str %}
 
 Commit messages:
+======
 {{commit_messages_str}}
+======
 {%- endif %}
 
 {%- if question_str %}
-######
+=====
 Here are questions to better understand the PR. Use the answers to provide better feedback.
 
-{{question_str|trim}}
+{{ question_str|trim }}
 
 User answers:
-{{answer_str|trim}}
-######
+'
+{{ answer_str|trim }}
+'
+=====
 {%- endif %}
 
-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. Focus on the '+' lines.
+
+The PR Diff:
+======
+{{ diff|trim }}
+======
+
 
 Response (should be a valid YAML, and nothing else):
 ```yaml

pr_agent/settings/pr_sort_code_suggestions_prompts.toml

@@ -2,10 +2,10 @@
 system="""
 """
 
-user="""You are given a list of code suggestions to improve a PR:
-
+user="""You are given a list of code suggestions to improve a Git Pull Request (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.

pr_agent/settings/pr_update_changelog_prompts.toml

@@ -1,5 +1,5 @@
 [pr_update_changelog_prompt]
-system="""You are a language model called CodiumAI-PR-Changlog-summarizer.
+system="""You are a language model called PR-Changelog-Updater.
 Your task is to update the CHANGELOG.md file of the project, to shortly summarize important changes introduced in this PR (the '+' lines).
 - The output should match the existing CHANGELOG.md format, style and conventions, so it will look like a natural part of the file. For example, if previous changes were summarized in a single line, you should do the same.
 - Don't repeat previous changes. Generate only new content, that is not already in the CHANGELOG.md file.
@@ -8,28 +8,44 @@ Your task is to update the CHANGELOG.md file of the project, to shortly summariz
 {%- if extra_instructions %}
 
 Extra instructions from the user:
-{{ extra_instructions }}
+======
+{{ extra_instructions|trim }}
+======
 {%- endif %}
 """
 
 user="""PR Info:
+
 Title: '{{title}}'
+
 Branch: '{{branch}}'
-Description: '{{description}}'
+
+{%- if description %}
+
+Description:
+======
+{{ description|trim }}
+======
+{%- endif %}
+
 {%- if language %}
-Main language: {{language}}
+
+Main PR language: '{{ language }}'
 {%- endif %}
 {%- if commit_messages_str %}
 
+
 Commit messages:
-{{commit_messages_str}}
+======
+{{ commit_messages_str|trim }}
+======
 {%- endif %}
 
 
-The PR Diff:
-```
-{{diff}}
-```
+The PR Git Diff:
+======
+{{ diff|trim }}
+======
 
 Current date:
 ```
@@ -37,9 +53,10 @@ Current date:
 ```
 
 The current CHANGELOG.md:
-```
+======
 {{ changelog_file_str }}
-```
+======
+
 
 Response:
 """

pr_agent/tools/pr_add_docs.py

@@ -0,0 +1,179 @@
+import copy
+import textwrap
+from typing import 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.token_handler import TokenHandler
+from pr_agent.algo.utils import load_yaml
+from pr_agent.config_loader import get_settings
+from pr_agent.git_providers import get_git_provider
+from pr_agent.git_providers.git_provider import get_main_pr_language
+from pr_agent.log import get_logger
+
+
+class PRAddDocs:
+    def __init__(self, pr_url: str, cli_mode=False, args: list = None):
+
+        self.git_provider = get_git_provider()(pr_url)
+        self.main_language = get_main_pr_language(
+            self.git_provider.get_languages(), self.git_provider.get_files()
+        )
+
+        self.ai_handler = AiHandler()
+        self.patches_diff = None
+        self.prediction = None
+        self.cli_mode = cli_mode
+        self.vars = {
+            "title": self.git_provider.pr.title,
+            "branch": self.git_provider.get_pr_branch(),
+            "description": self.git_provider.get_pr_description(),
+            "language": self.main_language,
+            "diff": "",  # empty diff for initial calculation
+            "extra_instructions": get_settings().pr_add_docs.extra_instructions,
+            "commit_messages_str": self.git_provider.get_commit_messages(),
+            'docs_for_language': get_docs_for_language(self.main_language,
+                                                       get_settings().pr_add_docs.docs_style),
+        }
+        self.token_handler = TokenHandler(self.git_provider.pr,
+                                          self.vars,
+                                          get_settings().pr_add_docs_prompt.system,
+                                          get_settings().pr_add_docs_prompt.user)
+
+    async def run(self):
+        try:
+            get_logger().info('Generating code Docs for PR...')
+            if get_settings().config.publish_output:
+                self.git_provider.publish_comment("Generating Documentation...", is_temporary=True)
+
+            get_logger().info('Preparing PR documentation...')
+            await retry_with_fallback_models(self._prepare_prediction)
+            data = self._prepare_pr_code_docs()
+            if (not data) or (not 'Code Documentation' in data):
+                get_logger().info('No code documentation found for PR.')
+                return
+
+            if get_settings().config.publish_output:
+                get_logger().info('Pushing PR documentation...')
+                self.git_provider.remove_initial_comment()
+                get_logger().info('Pushing inline code documentation...')
+                self.push_inline_docs(data)
+        except Exception as e:
+            get_logger().error(f"Failed to generate code documentation for PR, error: {e}")
+
+    async def _prepare_prediction(self, model: str):
+        get_logger().info('Getting PR diff...')
+
+        # Disable adding docs to scripts and other non-relevant text files
+        from pr_agent.algo.language_handler import bad_extensions
+        bad_extensions += get_settings().docs_blacklist_extensions.docs_blacklist
+
+        self.patches_diff = get_pr_diff(self.git_provider,
+                                        self.token_handler,
+                                        model,
+                                        add_line_numbers_to_hunks=True,
+                                        disable_extra_lines=False)
+
+        get_logger().info('Getting AI prediction...')
+        self.prediction = await self._get_prediction(model)
+
+    async def _get_prediction(self, model: str):
+        variables = copy.deepcopy(self.vars)
+        variables["diff"] = self.patches_diff  # update diff
+        environment = Environment(undefined=StrictUndefined)
+        system_prompt = environment.from_string(get_settings().pr_add_docs_prompt.system).render(variables)
+        user_prompt = environment.from_string(get_settings().pr_add_docs_prompt.user).render(variables)
+        if get_settings().config.verbosity_level >= 2:
+            get_logger().info(f"\nSystem prompt:\n{system_prompt}")
+            get_logger().info(f"\nUser prompt:\n{user_prompt}")
+        response, finish_reason = await self.ai_handler.chat_completion(model=model, temperature=0.2,
+                                                                        system=system_prompt, user=user_prompt)
+
+        return response
+
+    def _prepare_pr_code_docs(self) -> Dict:
+        docs = self.prediction.strip()
+        data = load_yaml(docs)
+        if isinstance(data, list):
+            data = {'Code Documentation': data}
+        return data
+
+    def push_inline_docs(self, data):
+        docs = []
+
+        if not data['Code Documentation']:
+            return self.git_provider.publish_comment('No code documentation found to improve this PR.')
+
+        for d in data['Code Documentation']:
+            try:
+                if get_settings().config.verbosity_level >= 2:
+                    get_logger().info(f"add_docs: {d}")
+                relevant_file = d['relevant file'].strip()
+                relevant_line = int(d['relevant line'])  # absolute position
+                documentation = d['documentation']
+                doc_placement = d['doc placement'].strip()
+                if documentation:
+                    new_code_snippet = self.dedent_code(relevant_file, relevant_line, documentation, doc_placement,
+                                                        add_original_line=True)
+
+                    body = f"**Suggestion:** Proposed documentation\n```suggestion\n" + new_code_snippet + "\n```"
+                    docs.append({'body': body, 'relevant_file': relevant_file,
+                                             'relevant_lines_start': relevant_line,
+                                             'relevant_lines_end': relevant_line})
+            except Exception:
+                if get_settings().config.verbosity_level >= 2:
+                    get_logger().info(f"Could not parse code docs: {d}")
+
+        is_successful = self.git_provider.publish_code_suggestions(docs)
+        if not is_successful:
+            get_logger().info("Failed to publish code docs, trying to publish each docs separately")
+            for doc_suggestion in docs:
+                self.git_provider.publish_code_suggestions([doc_suggestion])
+
+    def dedent_code(self, relevant_file, relevant_lines_start, new_code_snippet, doc_placement='after',
+                    add_original_line=False):
+        try:  # dedent code snippet
+            self.diff_files = self.git_provider.diff_files if self.git_provider.diff_files \
+                else self.git_provider.get_diff_files()
+            original_initial_line = None
+            for file in self.diff_files:
+                if file.filename.strip() == relevant_file:
+                    original_initial_line = file.head_file.splitlines()[relevant_lines_start - 1]
+                    break
+            if original_initial_line:
+                if doc_placement == 'after':
+                    line = file.head_file.splitlines()[relevant_lines_start]
+                else:
+                    line = original_initial_line
+                suggested_initial_line = new_code_snippet.splitlines()[0]
+                original_initial_spaces = len(line) - len(line.lstrip())
+                suggested_initial_spaces = len(suggested_initial_line) - len(suggested_initial_line.lstrip())
+                delta_spaces = original_initial_spaces - suggested_initial_spaces
+                if delta_spaces > 0:
+                    new_code_snippet = textwrap.indent(new_code_snippet, delta_spaces * " ").rstrip('\n')
+                if add_original_line:
+                    if doc_placement == 'after':
+                        new_code_snippet = original_initial_line + "\n" + new_code_snippet
+                    else:
+                        new_code_snippet = new_code_snippet.rstrip() + "\n" + original_initial_line
+        except Exception as e:
+            if get_settings().config.verbosity_level >= 2:
+                get_logger().info(f"Could not dedent code snippet for file {relevant_file}, error: {e}")
+
+        return new_code_snippet
+
+
+def get_docs_for_language(language, style):
+    language = language.lower()
+    if language == 'java':
+        return "Javadocs"
+    elif language in ['python', 'lisp', 'clojure']:
+        return f"Docstring ({style})"
+    elif language in ['javascript', 'typescript']:
+        return "JSdocs"
+    elif language == 'c++':
+        return "Doxygen"
+    else:
+        return "Docs"

pr_agent/tools/pr_code_suggestions.py

@@ -1,16 +1,16 @@
 import copy
-import logging
 import textwrap
-from typing import List, Dict
+from typing import Dict, List
 from jinja2 import Environment, StrictUndefined
 
 from pr_agent.algo.ai_handler import BaseAiHandler, AiHandler
-from pr_agent.algo.pr_processing import get_pr_diff, retry_with_fallback_models, get_pr_multi_diffs
+from pr_agent.algo.pr_processing import get_pr_diff, get_pr_multi_diffs, retry_with_fallback_models
 from pr_agent.algo.token_handler import TokenHandler
 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 import get_git_provider
 from pr_agent.git_providers.git_provider import get_main_pr_language
+from pr_agent.log import get_logger
 
 
 class PRCodeSuggestions:
@@ -52,42 +52,46 @@ class PRCodeSuggestions:
 
     async def run(self):
         try:
-            logging.info('Generating code suggestions for PR...')
+            get_logger().info('Generating code suggestions for PR...')
             if get_settings().config.publish_output:
-                self.git_provider.publish_comment("Preparing review...", is_temporary=True)
+                self.git_provider.publish_comment("Preparing suggestions...", is_temporary=True)
 
-            logging.info('Preparing PR review...')
+            get_logger().info('Preparing 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 data) or (not 'Code suggestions' in data):
-                logging.info('No code suggestions found for PR.')
+                get_logger().info('No code suggestions found for PR.')
                 return
 
             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...')
+                get_logger().info('Ranking Suggestions...')
                 data['Code suggestions'] = await self.rank_suggestions(data['Code suggestions'])
 
             if get_settings().config.publish_output:
-                logging.info('Pushing PR review...')
+                get_logger().info('Pushing PR code suggestions...')
                 self.git_provider.remove_initial_comment()
-                logging.info('Pushing inline code suggestions...')
-                self.push_inline_code_suggestions(data)
+                if get_settings().pr_code_suggestions.summarize:
+                    get_logger().info('Pushing summarize code suggestions...')
+                    self.publish_summarizes_suggestions(data)
+                else:
+                    get_logger().info('Pushing inline code suggestions...')
+                    self.push_inline_code_suggestions(data)
         except Exception as e:
-            logging.error(f"Failed to generate code suggestions for PR, error: {e}")
+            get_logger().error(f"Failed to generate code suggestions for PR, error: {e}")
 
     async def _prepare_prediction(self, model: str):
-        logging.info('Getting PR diff...')
+        get_logger().info('Getting PR diff...')
         self.patches_diff = get_pr_diff(self.git_provider,
                                         self.token_handler,
                                         model,
                                         add_line_numbers_to_hunks=True,
                                         disable_extra_lines=True)
 
-        logging.info('Getting AI prediction...')
+        get_logger().info('Getting AI prediction...')
         self.prediction = await self._get_prediction(model)
 
     async def _get_prediction(self, model: str):
@@ -97,8 +101,8 @@ class PRCodeSuggestions:
         system_prompt = environment.from_string(get_settings().pr_code_suggestions_prompt.system).render(variables)
         user_prompt = environment.from_string(get_settings().pr_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}")
+            get_logger().info(f"\nSystem prompt:\n{system_prompt}")
+            get_logger().info(f"\nUser prompt:\n{user_prompt}")
         response, finish_reason = await self.ai_handler.chat_completion(model=model, temperature=0.2,
                                                                         system=system_prompt, user=user_prompt)
 
@@ -115,12 +119,13 @@ class PRCodeSuggestions:
         code_suggestions = []
 
         if not data['Code suggestions']:
+            get_logger().info('No suggestions found to improve this PR.')
             return self.git_provider.publish_comment('No suggestions found to improve this PR.')
 
         for d in data['Code suggestions']:
             try:
                 if get_settings().config.verbosity_level >= 2:
-                    logging.info(f"suggestion: {d}")
+                    get_logger().info(f"suggestion: {d}")
                 relevant_file = d['relevant file'].strip()
                 relevant_lines_start = int(d['relevant lines start'])  # absolute position
                 relevant_lines_end = int(d['relevant lines end'])
@@ -136,11 +141,11 @@ class PRCodeSuggestions:
                                          'relevant_lines_end': relevant_lines_end})
             except Exception:
                 if get_settings().config.verbosity_level >= 2:
-                    logging.info(f"Could not parse suggestion: {d}")
+                    get_logger().info(f"Could not parse suggestion: {d}")
 
         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")
+            get_logger().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])
 
@@ -162,19 +167,19 @@ class PRCodeSuggestions:
                     new_code_snippet = textwrap.indent(new_code_snippet, delta_spaces * " ").rstrip('\n')
         except Exception as e:
             if get_settings().config.verbosity_level >= 2:
-                logging.info(f"Could not dedent code snippet for file {relevant_file}, error: {e}")
+                get_logger().info(f"Could not dedent code snippet for file {relevant_file}, error: {e}")
 
         return new_code_snippet
 
     async def _prepare_prediction_extended(self, model: str) -> dict:
-        logging.info('Getting PR diff...')
+        get_logger().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...')
+        get_logger().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)}")
+            get_logger().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)
@@ -222,8 +227,8 @@ class PRCodeSuggestions:
                 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}")
+                get_logger().info(f"\nSystem prompt:\n{system_prompt}")
+                get_logger().info(f"\nUser prompt:\n{user_prompt}")
             response, finish_reason = await self.ai_handler.chat_completion(model=model, system=system_prompt,
                                                                             user=user_prompt)
 
@@ -238,9 +243,46 @@ class PRCodeSuggestions:
                 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}")
+                get_logger().info(f"Could not sort suggestions, error: {e}")
             data_sorted = suggestion_list
 
         return data_sorted
 
+    def publish_summarizes_suggestions(self, data: Dict):
+        try:
+            data_markdown = "## PR Code Suggestions\n\n"
+
+            language_extension_map_org = get_settings().language_extension_map_org
+            extension_to_language = {}
+            for language, extensions in language_extension_map_org.items():
+                for ext in extensions:
+                    extension_to_language[ext] = language
+
+            for s in data['Code suggestions']:
+                try:
+                    extension_s = s['relevant file'].rsplit('.')[-1]
+                    code_snippet_link = self.git_provider.get_line_link(s['relevant file'], s['relevant lines start'],
+                                                                        s['relevant lines end'])
+                    data_markdown += f"\n💡 Suggestion:\n\n**{s['suggestion content']}**\n\n"
+                    if code_snippet_link:
+                        data_markdown += f" File: [{s['relevant file']} ({s['relevant lines start']}-{s['relevant lines end']})]({code_snippet_link})\n\n"
+                    else:
+                        data_markdown += f"File: {s['relevant file']} ({s['relevant lines start']}-{s['relevant lines end']})\n\n"
+                    if self.git_provider.is_supported("gfm_markdown"):
+                        data_markdown += "<details> <summary> Example code:</summary>\n\n"
+                        data_markdown += f"___\n\n"
+                    language_name = "python"
+                    if extension_s and (extension_s in extension_to_language):
+                        language_name = extension_to_language[extension_s]
+                    data_markdown += f"Existing code:\n```{language_name}\n{s['existing code']}\n```\n"
+                    data_markdown += f"Improved code:\n```{language_name}\n{s['improved code']}\n```\n"
+                    if self.git_provider.is_supported("gfm_markdown"):
+                        data_markdown += "</details>\n"
+                    data_markdown += "\n___\n\n"
+                except Exception as e:
+                    get_logger().error(f"Could not parse suggestion: {s}, error: {e}")
+            self.git_provider.publish_comment(data_markdown)
+        except Exception as e:
+            get_logger().info(f"Failed to publish summarized code suggestions, error: {e}")
+
 

pr_agent/tools/pr_config.py

@@ -1,7 +1,6 @@
-import logging
-
 from pr_agent.config_loader import get_settings
 from pr_agent.git_providers import get_git_provider
+from pr_agent.log import get_logger
 
 
 class PRConfig:
@@ -19,11 +18,11 @@ class PRConfig:
         self.git_provider = get_git_provider()(pr_url)
 
     async def run(self):
-        logging.info('Getting configuration settings...')
-        logging.info('Preparing configs...')
+        get_logger().info('Getting configuration settings...')
+        get_logger().info('Preparing configs...')
         pr_comment = self._prepare_pr_configs()
         if get_settings().config.publish_output:
-            logging.info('Pushing configs...')
+            get_logger().info('Pushing configs...')
             self.git_provider.publish_comment(pr_comment)
             self.git_provider.remove_initial_comment()
         return ""
@@ -44,5 +43,5 @@ class PRConfig:
                 comment_str += f"\n{header.lower()}.{key.lower()} = {repr(value) if isinstance(value, str) else value}"
                 comment_str += "  "
         if get_settings().config.verbosity_level >= 2:
-            logging.info(f"comment_str:\n{comment_str}")
+            get_logger().info(f"comment_str:\n{comment_str}")
         return comment_str

pr_agent/tools/pr_description.py

@@ -1,7 +1,5 @@
 import copy
-import json
 import re
-import logging
 from typing import List, Tuple
 
 from jinja2 import Environment, StrictUndefined
@@ -9,10 +7,11 @@ from jinja2 import Environment, StrictUndefined
 from pr_agent.algo.ai_handler import BaseAiHandler, AiHandler
 from pr_agent.algo.pr_processing import get_pr_diff, retry_with_fallback_models
 from pr_agent.algo.token_handler import TokenHandler
-from pr_agent.algo.utils import load_yaml
+from pr_agent.algo.utils import load_yaml, set_custom_labels, get_user_labels
 from pr_agent.config_loader import get_settings
 from pr_agent.git_providers import get_git_provider
 from pr_agent.git_providers.git_provider import get_main_pr_language
+from pr_agent.log import get_logger
 
 
 class PRDescription:
@@ -31,6 +30,11 @@ class PRDescription:
         )
         self.pr_id = self.git_provider.get_pr_id()
 
+        if get_settings().pr_description.enable_semantic_files_types and not self.git_provider.is_supported(
+                "gfm_markdown"):
+            get_logger().debug(f"Disabling semantic files types for {self.pr_id}")
+            get_settings().pr_description.enable_semantic_files_types = False
+
         # Initialize the AI handler
         self.ai_handler = ai_handler
     
@@ -41,8 +45,13 @@ class PRDescription:
             "description": self.git_provider.get_pr_description(full=False),
             "language": self.main_pr_language,
             "diff": "",  # empty diff for initial calculation
+            "use_bullet_points": get_settings().pr_description.use_bullet_points,
             "extra_instructions": get_settings().pr_description.extra_instructions,
-            "commit_messages_str": self.git_provider.get_commit_messages()
+            "commit_messages_str": self.git_provider.get_commit_messages(),
+            "enable_custom_labels": get_settings().config.enable_custom_labels,
+            "custom_labels_class": "",  # will be filled if necessary in 'set_custom_labels' function
+            "enable_file_walkthrough": get_settings().pr_description.enable_file_walkthrough,
+            "enable_semantic_files_types": get_settings().pr_description.enable_semantic_files_types,
         }
 
         self.user_description = self.git_provider.get_user_description()
@@ -65,18 +74,21 @@ class PRDescription:
         """
 
         try:
-            logging.info(f"Generating a PR description {self.pr_id}")
+            get_logger().info(f"Generating a PR description {self.pr_id}")
             if get_settings().config.publish_output:
                 self.git_provider.publish_comment("Preparing PR description...", is_temporary=True)
 
             await retry_with_fallback_models(self._prepare_prediction)
 
-            logging.info(f"Preparing answer {self.pr_id}")
+            get_logger().info(f"Preparing answer {self.pr_id}")
             if self.prediction:
                 self._prepare_data()
             else:
                 return None
 
+            if get_settings().pr_description.enable_semantic_files_types:
+                self._prepare_file_labels()
+
             pr_labels = []
             if get_settings().pr_description.publish_labels:
                 pr_labels = self._prepare_labels()
@@ -88,19 +100,25 @@ class PRDescription:
             full_markdown_description = f"## Title\n\n{pr_title}\n\n___\n{pr_body}"
 
             if get_settings().config.publish_output:
-                logging.info(f"Pushing answer {self.pr_id}")
+                get_logger().info(f"Pushing answer {self.pr_id}")
                 if get_settings().pr_description.publish_description_as_comment:
                     self.git_provider.publish_comment(full_markdown_description)
                 else:
                     self.git_provider.publish_description(pr_title, pr_body)
                     if get_settings().pr_description.publish_labels and self.git_provider.is_supported("get_labels"):
                         current_labels = self.git_provider.get_labels()
-                        if current_labels is None:
-                            current_labels = []
-                        self.git_provider.publish_labels(pr_labels + current_labels)
+                        user_labels = get_user_labels(current_labels)
+                        self.git_provider.publish_labels(pr_labels + user_labels)
+
+                    if (get_settings().pr_description.final_update_message and
+                            hasattr(self.git_provider, 'pr_url') and self.git_provider.pr_url):
+                        latest_commit_url = self.git_provider.get_latest_commit_url()
+                        if latest_commit_url:
+                            self.git_provider.publish_comment(
+                                f"**[PR Description]({self.git_provider.pr_url})** updated to latest commit ({latest_commit_url})")
                 self.git_provider.remove_initial_comment()
         except Exception as e:
-            logging.error(f"Error generating PR description {self.pr_id}: {e}")
+            get_logger().error(f"Error generating PR description {self.pr_id}: {e}")
         
         return ""
 
@@ -121,9 +139,9 @@ class PRDescription:
         if get_settings().pr_description.use_description_markers and 'pr_agent:' not in self.user_description:
             return None
 
-        logging.info(f"Getting PR diff {self.pr_id}")
+        get_logger().info(f"Getting PR diff {self.pr_id}")
         self.patches_diff = get_pr_diff(self.git_provider, self.token_handler, model)
-        logging.info(f"Getting AI prediction {self.pr_id}")
+        get_logger().info(f"Getting AI prediction {self.pr_id}")
         self.prediction = await self._get_prediction(model)
 
     async def _get_prediction(self, model: str) -> str:
@@ -140,12 +158,13 @@ class PRDescription:
         variables["diff"] = self.patches_diff  # update diff
 
         environment = Environment(undefined=StrictUndefined)
+        set_custom_labels(variables)
         system_prompt = environment.from_string(get_settings().pr_description_prompt.system).render(variables)
         user_prompt = environment.from_string(get_settings().pr_description_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}")
+            get_logger().info(f"\nSystem prompt:\n{system_prompt}")
+            get_logger().info(f"\nUser prompt:\n{user_prompt}")
 
         response, finish_reason = await self.ai_handler.chat_completion(
             model=model,
@@ -154,8 +173,10 @@ class PRDescription:
             user=user_prompt
         )
 
-        return response
+        if get_settings().config.verbosity_level >= 2:
+            get_logger().info(f"\nAI response:\n{response}")
 
+        return response
 
     def _prepare_data(self):
         # Load the AI prediction data into a dictionary
@@ -169,16 +190,20 @@ class PRDescription:
         pr_types = []
 
         # 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 self.data:
-            if type(self.data['PR Type']) == list:
-                pr_types = self.data['PR Type']
-            elif type(self.data['PR Type']) == str:
-                pr_types = self.data['PR Type'].split(',')
-
+        if 'labels' in self.data:
+            if type(self.data['labels']) == list:
+                pr_types = self.data['labels']
+            elif type(self.data['labels']) == str:
+                pr_types = self.data['labels'].split(',')
+        elif 'type' in self.data:
+            if type(self.data['type']) == list:
+                pr_types = self.data['type']
+            elif type(self.data['type']) == str:
+                pr_types = self.data['type'].split(',')
         return pr_types
 
     def _prepare_pr_answer_with_markers(self) -> Tuple[str, str]:
-        logging.info(f"Using description marker replacements {self.pr_id}")
+        get_logger().info(f"Using description marker replacements {self.pr_id}")
         title = self.vars["title"]
         body = self.user_description
         if get_settings().pr_description.include_generated_by_header:
@@ -186,7 +211,12 @@ class PRDescription:
         else:
             ai_header = ""
 
-        ai_summary = self.data.get('PR Description')
+        ai_type = self.data.get('type')
+        if ai_type and not re.search(r'<!--\s*pr_agent:type\s*-->', body):
+            pr_type = f"{ai_header}{ai_type}"
+            body = body.replace('pr_agent:type', pr_type)
+
+        ai_summary = self.data.get('description')
         if ai_summary and not re.search(r'<!--\s*pr_agent:summary\s*-->', body):
             summary = f"{ai_header}{ai_summary}"
             body = body.replace('pr_agent:summary', summary)
@@ -215,12 +245,17 @@ class PRDescription:
 
         # Iterate over the dictionary items and append the key and value to 'markdown_text' in a markdown format
         markdown_text = ""
+        # Don't display 'PR Labels'
+        if 'labels' in self.data and self.git_provider.is_supported("get_labels"):
+            self.data.pop('labels')
+        if not get_settings().pr_description.enable_pr_type:
+            self.data.pop('type')
         for key, value in self.data.items():
             markdown_text += f"## {key}\n\n"
             markdown_text += f"{value}\n\n"
 
         # Remove the 'PR Title' key from the dictionary
-        ai_title = self.data.pop('PR Title', self.vars["title"])
+        ai_title = self.data.pop('title', self.vars["title"])
         if get_settings().pr_description.keep_original_user_title:
             # Assign the original PR title to the 'title' variable
             title = self.vars["title"]
@@ -232,26 +267,131 @@ class PRDescription:
         # except for the items containing the word 'walkthrough'
         pr_body = ""
         for idx, (key, value) in enumerate(self.data.items()):
-            pr_body += f"## {key}:\n"
+            if key == 'pr_files':
+                value = self.file_label_dict
+                key_publish = "PR changes walkthrough"
+            else:
+                key_publish = key.rstrip(':').replace("_", " ").capitalize()
+            pr_body += f"## {key_publish}\n"
             if 'walkthrough' in key.lower():
-                # for filename, description in value.items():
                 if self.git_provider.is_supported("gfm_markdown"):
                     pr_body += "<details> <summary>files:</summary>\n\n"
                 for file in value:
                     filename = file['filename'].replace("'", "`")
-                    description = file['changes in file']
-                    pr_body += f'`{filename}`: {description}\n'
+                    description = file['changes_in_file']
+                    pr_body += f'- `{filename}`: {description}\n'
                 if self.git_provider.is_supported("gfm_markdown"):
-                    pr_body +="</details>\n"
+                    pr_body += "</details>\n"
+            elif 'pr_files' in key.lower():
+                pr_body = self.process_pr_files_prediction(pr_body, value)
             else:
                 # if the value is a list, join its items by comma
-                if type(value) == list:
+                if isinstance(value, list):
                     value = ', '.join(v for v in value)
                 pr_body += f"{value}\n"
             if idx < len(self.data) - 1:
                 pr_body += "\n___\n"
 
         if get_settings().config.verbosity_level >= 2:
-            logging.info(f"title:\n{title}\n{pr_body}")
+            get_logger().info(f"title:\n{title}\n{pr_body}")
 
-        return title, pr_body
+        return title, pr_body
+
+    def _prepare_file_labels(self):
+        self.file_label_dict = {}
+        for file in self.data['pr_files']:
+            try:
+                filename = file['filename'].replace("'", "`").replace('"', '`')
+                changes_summary = file['changes_summary']
+                label = file['label']
+                if label not in self.file_label_dict:
+                    self.file_label_dict[label] = []
+                self.file_label_dict[label].append((filename, changes_summary))
+            except Exception as e:
+                get_logger().error(f"Error preparing file label dict {self.pr_id}: {e}")
+                pass
+
+    def process_pr_files_prediction(self, pr_body, value):
+        if not self.git_provider.is_supported("gfm_markdown"):
+            get_logger().info(f"Disabling semantic files types for {self.pr_id} since gfm_markdown is not supported")
+            return pr_body
+
+        try:
+            pr_body += "<table>"
+            header = f"Relevant files"
+            delta = 65
+            header += "&nbsp; " * delta
+            pr_body += f"""<thead><tr><th></th><th>{header}</th></tr></thead>"""
+            pr_body += """<tbody>"""
+            for semantic_label in value.keys():
+                s_label = semantic_label.strip("'").strip('"')
+                pr_body += f"""<tr><td><strong>{s_label.capitalize()}</strong></td>"""
+                list_tuples = value[semantic_label]
+                pr_body += f"""<td><details><summary>{len(list_tuples)} files</summary><table>"""
+                for filename, file_change_description in list_tuples:
+                    filename = filename.replace("'", "`")
+                    filename_publish = filename.split("/")[-1]
+                    filename_publish = f"{filename_publish}"
+                    if len(filename_publish) < (delta - 5):
+                        filename_publish += "&nbsp; " * ((delta - 5) - len(filename_publish))
+                    diff_plus_minus = ""
+                    diff_files = self.git_provider.diff_files
+                    for f in diff_files:
+                        if f.filename.lower() == filename.lower():
+                            num_plus_lines = f.num_plus_lines
+                            num_minus_lines = f.num_minus_lines
+                            diff_plus_minus += f"+{num_plus_lines}/-{num_minus_lines}"
+                            break
+
+                    # try to add line numbers link to code suggestions
+                    link = ""
+                    if hasattr(self.git_provider, 'get_line_link'):
+                        filename = filename.strip()
+                        link = self.git_provider.get_line_link(filename, relevant_line_start=-1)
+
+                    file_change_description = self._insert_br_after_x_chars(file_change_description, x=(delta - 5))
+                    pr_body += f"""
+<tr>
+  <td>
+    <details>
+      <summary><strong>{filename_publish}</strong></summary>
+      <ul>
+        {filename}<br><br>
+        <strong>{file_change_description}</strong>
+      </ul>
+    </details>
+  </td>
+  <td><a href="{link}"> {diff_plus_minus}</a></td>
+
+</tr>                    
+"""
+                pr_body += """</table></details></td></tr>"""
+            pr_body += """</tr></tbody></table>"""
+
+        except Exception as e:
+            get_logger().error(f"Error processing pr files to markdown {self.pr_id}: {e}")
+            pass
+        return pr_body
+
+    def _insert_br_after_x_chars(self, text, x=70):
+        """
+        Insert <br> into a string after a word that increases its length above x characters.
+        """
+        if len(text) < x:
+            return text
+
+        words = text.split(' ')
+        new_text = ""
+        current_length = 0
+
+        for word in words:
+            # Check if adding this word exceeds x characters
+            if current_length + len(word) > x:
+                new_text += "<br>"  # Insert line break
+                current_length = 0  # Reset counter
+
+            # Add the word to the new text
+            new_text += word + " "
+            current_length += len(word) + 1  # Add 1 for the space
+
+        return new_text.strip()  # Remove trailing space

pr_agent/tools/pr_generate_labels.py

@@ -0,0 +1,171 @@
+import copy
+import re
+from typing import List, Tuple
+
+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.token_handler import TokenHandler
+from pr_agent.algo.utils import load_yaml, set_custom_labels, get_user_labels
+from pr_agent.config_loader import get_settings
+from pr_agent.git_providers import get_git_provider
+from pr_agent.git_providers.git_provider import get_main_pr_language
+from pr_agent.log import get_logger
+
+
+class PRGenerateLabels:
+    def __init__(self, pr_url: str, args: list = None):
+        """
+        Initialize the PRGenerateLabels object with the necessary attributes and objects for generating labels
+        corresponding to the PR using an AI model.
+        Args:
+            pr_url (str): The URL of the pull request.
+            args (list, optional): List of arguments passed to the PRGenerateLabels class. Defaults to None.
+        """
+        # Initialize the git provider and main PR language
+        self.git_provider = get_git_provider()(pr_url)
+        self.main_pr_language = get_main_pr_language(
+            self.git_provider.get_languages(), self.git_provider.get_files()
+        )
+        self.pr_id = self.git_provider.get_pr_id()
+
+        # Initialize the AI handler
+        self.ai_handler = AiHandler()
+    
+        # Initialize the variables dictionary
+        self.vars = {
+            "title": self.git_provider.pr.title,
+            "branch": self.git_provider.get_pr_branch(),
+            "description": self.git_provider.get_pr_description(full=False),
+            "language": self.main_pr_language,
+            "diff": "",  # empty diff for initial calculation
+            "use_bullet_points": get_settings().pr_description.use_bullet_points,
+            "extra_instructions": get_settings().pr_description.extra_instructions,
+            "commit_messages_str": self.git_provider.get_commit_messages(),
+            "enable_custom_labels": get_settings().config.enable_custom_labels,
+            "custom_labels_class": "",  # will be filled if necessary in 'set_custom_labels' function
+        }
+
+        # Initialize the token handler
+        self.token_handler = TokenHandler(
+            self.git_provider.pr,
+            self.vars,
+            get_settings().pr_custom_labels_prompt.system,
+            get_settings().pr_custom_labels_prompt.user,
+        )
+    
+        # Initialize patches_diff and prediction attributes
+        self.patches_diff = None
+        self.prediction = None
+
+    async def run(self):
+        """
+        Generates a PR labels using an AI model and publishes it to the PR.
+        """
+
+        try:
+            get_logger().info(f"Generating a PR labels {self.pr_id}")
+            if get_settings().config.publish_output:
+                self.git_provider.publish_comment("Preparing PR labels...", is_temporary=True)
+
+            await retry_with_fallback_models(self._prepare_prediction)
+
+            get_logger().info(f"Preparing answer {self.pr_id}")
+            if self.prediction:
+                self._prepare_data()
+            else:
+                return None
+
+            pr_labels = self._prepare_labels()
+
+            if get_settings().config.publish_output:
+                get_logger().info(f"Pushing labels {self.pr_id}")
+
+                current_labels = self.git_provider.get_labels()
+                user_labels = get_user_labels(current_labels)
+                pr_labels = pr_labels + user_labels
+
+                if self.git_provider.is_supported("get_labels"):
+                    self.git_provider.publish_labels(pr_labels)
+                elif pr_labels:
+                    value = ', '.join(v for v in pr_labels)
+                    pr_labels_text = f"## PR Labels:\n{value}\n"
+                    self.git_provider.publish_comment(pr_labels_text, is_temporary=False)
+                self.git_provider.remove_initial_comment()
+        except Exception as e:
+            get_logger().error(f"Error generating PR labels {self.pr_id}: {e}")
+        
+        return ""
+
+    async def _prepare_prediction(self, model: str) -> None:
+        """
+        Prepare the AI prediction for the PR labels based on the provided model.
+
+        Args:
+            model (str): The name of the model to be used for generating the prediction.
+
+        Returns:
+            None
+
+        Raises:
+            Any exceptions raised by the 'get_pr_diff' and '_get_prediction' functions.
+
+        """
+
+        get_logger().info(f"Getting PR diff {self.pr_id}")
+        self.patches_diff = get_pr_diff(self.git_provider, self.token_handler, model)
+        get_logger().info(f"Getting AI prediction {self.pr_id}")
+        self.prediction = await self._get_prediction(model)
+
+    async def _get_prediction(self, model: str) -> str:
+        """
+        Generate an AI prediction for the PR labels based on the provided model.
+
+        Args:
+            model (str): The name of the model to be used for generating the prediction.
+
+        Returns:
+            str: The generated AI prediction.
+        """
+        variables = copy.deepcopy(self.vars)
+        variables["diff"] = self.patches_diff  # update diff
+
+        environment = Environment(undefined=StrictUndefined)
+        set_custom_labels(variables)
+        system_prompt = environment.from_string(get_settings().pr_custom_labels_prompt.system).render(variables)
+        user_prompt = environment.from_string(get_settings().pr_custom_labels_prompt.user).render(variables)
+
+        if get_settings().config.verbosity_level >= 2:
+            get_logger().info(f"\nSystem prompt:\n{system_prompt}")
+            get_logger().info(f"\nUser prompt:\n{user_prompt}")
+
+        response, finish_reason = await self.ai_handler.chat_completion(
+            model=model,
+            temperature=0.2,
+            system=system_prompt,
+            user=user_prompt
+        )
+
+        if get_settings().config.verbosity_level >= 2:
+            get_logger().info(f"\nAI response:\n{response}")
+
+        return response
+
+    def _prepare_data(self):
+        # Load the AI prediction data into a dictionary
+        self.data = load_yaml(self.prediction.strip())
+
+
+
+    def _prepare_labels(self) -> List[str]:
+        pr_types = []
+
+        # If the 'labels' key is present in the dictionary, split its value by comma and assign it to 'pr_types'
+        if 'labels' in self.data:
+            if type(self.data['labels']) == list:
+                pr_types = self.data['labels']
+            elif type(self.data['labels']) == str:
+                pr_types = self.data['labels'].split(',')
+
+        return pr_types

pr_agent/tools/pr_information_from_user.py

@@ -1,5 +1,4 @@
 import copy
-import logging
 
 from jinja2 import Environment, StrictUndefined
 
@@ -9,6 +8,7 @@ from pr_agent.algo.token_handler import TokenHandler
 from pr_agent.config_loader import get_settings
 from pr_agent.git_providers import get_git_provider
 from pr_agent.git_providers.git_provider import get_main_pr_language
+from pr_agent.log import get_logger
 
 
 class PRInformationFromUser:
@@ -34,22 +34,22 @@ class PRInformationFromUser:
         self.prediction = None
 
     async def run(self):
-        logging.info('Generating question to the user...')
+        get_logger().info('Generating question to the user...')
         if get_settings().config.publish_output:
             self.git_provider.publish_comment("Preparing questions...", is_temporary=True)
         await retry_with_fallback_models(self._prepare_prediction)
-        logging.info('Preparing questions...')
+        get_logger().info('Preparing questions...')
         pr_comment = self._prepare_pr_answer()
         if get_settings().config.publish_output:
-            logging.info('Pushing questions...')
+            get_logger().info('Pushing questions...')
             self.git_provider.publish_comment(pr_comment)
             self.git_provider.remove_initial_comment()
         return ""
 
     async def _prepare_prediction(self, model):
-        logging.info('Getting PR diff...')
+        get_logger().info('Getting PR diff...')
         self.patches_diff = get_pr_diff(self.git_provider, self.token_handler, model)
-        logging.info('Getting AI prediction...')
+        get_logger().info('Getting AI prediction...')
         self.prediction = await self._get_prediction(model)
 
     async def _get_prediction(self, model: str):
@@ -59,8 +59,8 @@ class PRInformationFromUser:
         system_prompt = environment.from_string(get_settings().pr_information_from_user_prompt.system).render(variables)
         user_prompt = environment.from_string(get_settings().pr_information_from_user_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}")
+            get_logger().info(f"\nSystem prompt:\n{system_prompt}")
+            get_logger().info(f"\nUser prompt:\n{user_prompt}")
         response, finish_reason = await self.ai_handler.chat_completion(model=model, temperature=0.2,
                                                                         system=system_prompt, user=user_prompt)
         return response
@@ -68,7 +68,7 @@ class PRInformationFromUser:
     def _prepare_pr_answer(self) -> str:
         model_output = self.prediction.strip()
         if get_settings().config.verbosity_level >= 2:
-            logging.info(f"answer_str:\n{model_output}")
+            get_logger().info(f"answer_str:\n{model_output}")
         answer_str = f"{model_output}\n\n Please respond to the questions above in the following format:\n\n" +\
                      "\n>/answer\n>1) ...\n>2) ...\n>...\n"
         return answer_str

pr_agent/tools/pr_questions.py

@@ -1,5 +1,4 @@
 import copy
-import logging
 
 from jinja2 import Environment, StrictUndefined
 
@@ -9,6 +8,7 @@ from pr_agent.algo.token_handler import TokenHandler
 from pr_agent.config_loader import get_settings
 from pr_agent.git_providers import get_git_provider
 from pr_agent.git_providers.git_provider import get_main_pr_language
+from pr_agent.log import get_logger
 
 
 class PRQuestions:
@@ -44,22 +44,22 @@ class PRQuestions:
         return question_str
 
     async def run(self):
-        logging.info('Answering a PR question...')
+        get_logger().info('Answering a PR question...')
         if get_settings().config.publish_output:
             self.git_provider.publish_comment("Preparing answer...", is_temporary=True)
         await retry_with_fallback_models(self._prepare_prediction)
-        logging.info('Preparing answer...')
+        get_logger().info('Preparing answer...')
         pr_comment = self._prepare_pr_answer()
         if get_settings().config.publish_output:
-            logging.info('Pushing answer...')
+            get_logger().info('Pushing answer...')
             self.git_provider.publish_comment(pr_comment)
             self.git_provider.remove_initial_comment()
         return ""
 
     async def _prepare_prediction(self, model: str):
-        logging.info('Getting PR diff...')
+        get_logger().info('Getting PR diff...')
         self.patches_diff = get_pr_diff(self.git_provider, self.token_handler, model)
-        logging.info('Getting AI prediction...')
+        get_logger().info('Getting AI prediction...')
         self.prediction = await self._get_prediction(model)
 
     async def _get_prediction(self, model: str):
@@ -69,8 +69,8 @@ class PRQuestions:
         system_prompt = environment.from_string(get_settings().pr_questions_prompt.system).render(variables)
         user_prompt = environment.from_string(get_settings().pr_questions_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}")
+            get_logger().info(f"\nSystem prompt:\n{system_prompt}")
+            get_logger().info(f"\nUser prompt:\n{user_prompt}")
         response, finish_reason = await self.ai_handler.chat_completion(model=model, temperature=0.2,
                                                                         system=system_prompt, user=user_prompt)
         return response
@@ -79,5 +79,5 @@ class PRQuestions:
         answer_str = f"Question: {self.question_str}\n\n"
         answer_str += f"Answer:\n{self.prediction.strip()}\n\n"
         if get_settings().config.verbosity_level >= 2:
-            logging.info(f"answer_str:\n{answer_str}")
+            get_logger().info(f"answer_str:\n{answer_str}")
         return answer_str

pr_agent/tools/pr_reviewer.py

@@ -1,6 +1,5 @@
 import copy
-import json
-import logging
+import datetime
 from collections import OrderedDict
 from typing import List, Tuple
 
@@ -11,10 +10,11 @@ from yaml import SafeLoader
 from pr_agent.algo.ai_handler import BaseAiHandler, AiHandler
 from pr_agent.algo.pr_processing import get_pr_diff, retry_with_fallback_models
 from pr_agent.algo.token_handler import TokenHandler
-from pr_agent.algo.utils import convert_to_markdown, try_fix_json, try_fix_yaml, load_yaml
+from pr_agent.algo.utils import convert_to_markdown, load_yaml, try_fix_yaml, set_custom_labels, get_user_labels
 from pr_agent.config_loader import get_settings
 from pr_agent.git_providers import get_git_provider
 from pr_agent.git_providers.git_provider import IncrementalPR, get_main_pr_language
+from pr_agent.log import get_logger
 from pr_agent.servers.help import actions_help_text, bot_help_text
 
 
@@ -64,6 +64,8 @@ class PRReviewer:
             'answer_str': answer_str,
             "extra_instructions": get_settings().pr_reviewer.extra_instructions,
             "commit_messages_str": self.git_provider.get_commit_messages(),
+            "custom_labels": "",
+            "enable_custom_labels": get_settings().config.enable_custom_labels,
         }
 
         self.token_handler = TokenHandler(
@@ -97,29 +99,41 @@ class PRReviewer:
 
         try:
             if self.is_auto and not get_settings().pr_reviewer.automatic_review:
-                logging.info(f'Automatic review is disabled {self.pr_url}')
+                get_logger().info(f'Automatic review is disabled {self.pr_url}')
+                return None
+            if self.incremental.is_incremental and not self._can_run_incremental_review():
                 return None
 
-            logging.info(f'Reviewing PR: {self.pr_url} ...')
+            get_logger().info(f'Reviewing PR: {self.pr_url} ...')
 
             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...')
+            get_logger().info('Preparing PR review...')
             pr_comment = self._prepare_pr_review()
 
             if get_settings().config.publish_output:
-                logging.info('Pushing PR review...')
-                self.git_provider.publish_comment(pr_comment)
-                self.git_provider.remove_initial_comment()
+                get_logger().info('Pushing PR review...')
+                previous_review_comment = self._get_previous_review_comment()
 
+                # publish the review
+                if get_settings().pr_reviewer.persistent_comment and not self.incremental.is_incremental:
+                    self.git_provider.publish_persistent_comment(pr_comment,
+                                                                 initial_header="## PR Analysis",
+                                                                 update_header=True)
+                else:
+                    self.git_provider.publish_comment(pr_comment)
+
+                self.git_provider.remove_initial_comment()
+                if previous_review_comment:
+                    self._remove_previous_review_comment(previous_review_comment)
                 if get_settings().pr_reviewer.inline_code_comments:
-                    logging.info('Pushing inline code comments...')
+                    get_logger().info('Pushing inline code comments...')
                     self._publish_inline_code_comments()
         except Exception as e:
-            logging.error(f"Failed to review PR: {e}")
+            get_logger().error(f"Failed to review PR: {e}")
 
     async def _prepare_prediction(self, model: str) -> None:
         """
@@ -131,9 +145,9 @@ class PRReviewer:
         Returns:
             None
         """
-        logging.info('Getting PR diff...')
+        get_logger().info('Getting PR diff...')
         self.patches_diff = get_pr_diff(self.git_provider, self.token_handler, model)
-        logging.info('Getting AI prediction...')
+        get_logger().info('Getting AI prediction...')
         self.prediction = await self._get_prediction(model)
 
     async def _get_prediction(self, model: str) -> str:
@@ -154,8 +168,8 @@ class PRReviewer:
         user_prompt = environment.from_string(get_settings().pr_review_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}")
+            get_logger().info(f"\nSystem prompt:\n{system_prompt}")
+            get_logger().info(f"\nUser prompt:\n{user_prompt}")
 
         response, finish_reason = await self.ai_handler.chat_completion(
             model=model,
@@ -164,6 +178,9 @@ class PRReviewer:
             user=user_prompt
         )
 
+        if get_settings().config.verbosity_level >= 2:
+            get_logger().info(f"\nAI response:\n{response}")
+
         return response
 
     def _prepare_pr_review(self) -> str:
@@ -208,14 +225,22 @@ class PRReviewer:
                         link = self.git_provider.generate_link_to_relevant_line_number(suggestion)
                         if link:
                             suggestion['relevant line'] = f"[{suggestion['relevant line']}]({link})"
+                    else:
+                        pass
+
 
         # Add incremental review section
         if self.incremental.is_incremental:
             last_commit_url = f"{self.git_provider.get_pr_url()}/commits/" \
                               f"{self.git_provider.incremental.first_new_commit_sha}"
+            last_commit_msg = self.incremental.commits_range[0].commit.message if self.incremental.commits_range else ""
+            incremental_review_markdown_text = f"Starting from commit {last_commit_url}"
+            if last_commit_msg:
+                replacement = last_commit_msg.splitlines(keepends=False)[0].replace('_', r'\_')
+                incremental_review_markdown_text += f"  \n_({replacement})_"
             data = OrderedDict(data)
             data.update({'Incremental PR Review': {
-                "⏮️ Review for commits since previous PR-Agent review": f"Starting from commit {last_commit_url}"}})
+                "⏮️ Review for commits since previous PR-Agent review": incremental_review_markdown_text}})
             data.move_to_end('Incremental PR Review', last=False)
 
         markdown_text = convert_to_markdown(data, self.git_provider.is_supported("gfm_markdown"))
@@ -224,14 +249,22 @@ class PRReviewer:
         # Add help text if not in CLI mode
         if not get_settings().get("CONFIG.CLI_MODE", False):
             markdown_text += "\n### How to use\n"
-            if user and '[bot]' not in user:
+            if self.git_provider.is_supported("gfm_markdown"):
+                markdown_text += "\n <details> <summary> Instructions</summary>\n\n"
+            bot_user = "[bot]" if get_settings().github_app.override_deployment_type else get_settings().github_app.bot_user
+            if user and bot_user not in user:
                 markdown_text += bot_help_text(user)
             else:
                 markdown_text += actions_help_text
+            if self.git_provider.is_supported("gfm_markdown"):
+                markdown_text += "\n</details>\n"
+
+        # Add custom labels from the review prediction (effort, security)
+        self.set_review_labels(data)
 
         # Log markdown response if verbosity level is high
         if get_settings().config.verbosity_level >= 2:
-            logging.info(f"Markdown response:\n{markdown_text}")
+            get_logger().info(f"Markdown response:\n{markdown_text}")
 
         if markdown_text == None or len(markdown_text) == 0:
             markdown_text = ""
@@ -245,21 +278,14 @@ class PRReviewer:
         if get_settings().pr_reviewer.num_code_suggestions == 0:
             return
 
-        review_text = self.prediction.strip()
-        review_text = review_text.removeprefix('```yaml').rstrip('`')
-        try:
-            data = yaml.load(review_text, Loader=SafeLoader)
-        except Exception as e:
-            logging.error(f"Failed to parse AI prediction: {e}")
-            data = try_fix_yaml(review_text)
-
+        data = load_yaml(self.prediction.strip())
         comments: List[str] = []
         for suggestion in data.get('PR Feedback', {}).get('Code feedback', []):
             relevant_file = suggestion.get('relevant file', '').strip()
             relevant_line_in_file = suggestion.get('relevant line', '').strip()
             content = suggestion.get('suggestion', '')
             if not relevant_file or not relevant_line_in_file or not content:
-                logging.info("Skipping inline comment with missing file/line/content")
+                get_logger().info("Skipping inline comment with missing file/line/content")
                 continue
 
             if self.git_provider.is_supported("create_inline_comment"):
@@ -295,3 +321,83 @@ class PRReviewer:
                     break
 
         return question_str, answer_str
+
+    def _get_previous_review_comment(self):
+        """
+        Get the previous review comment if it exists.
+        """
+        try:
+            if get_settings().pr_reviewer.remove_previous_review_comment and hasattr(self.git_provider, "get_previous_review"):
+                return self.git_provider.get_previous_review(
+                    full=not self.incremental.is_incremental,
+                    incremental=self.incremental.is_incremental,
+                )
+        except Exception as e:
+            get_logger().exception(f"Failed to get previous review comment, error: {e}")
+
+    def _remove_previous_review_comment(self, comment):
+        """
+        Remove the previous review comment if it exists.
+        """
+        try:
+            if get_settings().pr_reviewer.remove_previous_review_comment and comment:
+                self.git_provider.remove_comment(comment)
+        except Exception as e:
+            get_logger().exception(f"Failed to remove previous review comment, error: {e}")
+
+    def _can_run_incremental_review(self) -> bool:
+        """Checks if we can run incremental review according the various configurations and previous review"""
+        # checking if running is auto mode but there are no new commits
+        if self.is_auto and not self.incremental.first_new_commit_sha:
+            get_logger().info(f"Incremental review is enabled for {self.pr_url} but there are no new commits")
+            return False
+        # checking if there are enough commits to start the review
+        num_new_commits = len(self.incremental.commits_range)
+        num_commits_threshold = get_settings().pr_reviewer.minimal_commits_for_incremental_review
+        not_enough_commits = num_new_commits < num_commits_threshold
+        # checking if the commits are not too recent to start the review
+        recent_commits_threshold = datetime.datetime.now() - datetime.timedelta(
+            minutes=get_settings().pr_reviewer.minimal_minutes_for_incremental_review
+        )
+        last_seen_commit_date = (
+            self.incremental.last_seen_commit.commit.author.date if self.incremental.last_seen_commit else None
+        )
+        all_commits_too_recent = (
+            last_seen_commit_date > recent_commits_threshold if self.incremental.last_seen_commit else False
+        )
+        # check all the thresholds or just one to start the review
+        condition = any if get_settings().pr_reviewer.require_all_thresholds_for_incremental_review else all
+        if condition((not_enough_commits, all_commits_too_recent)):
+            get_logger().info(
+                f"Incremental review is enabled for {self.pr_url} but didn't pass the threshold check to run:"
+                f"\n* Number of new commits = {num_new_commits} (threshold is {num_commits_threshold})"
+                f"\n* Last seen commit date = {last_seen_commit_date} (threshold is {recent_commits_threshold})"
+            )
+            return False
+        return True
+
+    def set_review_labels(self, data):
+        if (get_settings().pr_reviewer.enable_review_labels_security or
+                get_settings().pr_reviewer.enable_review_labels_effort):
+            try:
+                review_labels = []
+                if get_settings().pr_reviewer.enable_review_labels_effort:
+                    estimated_effort = data['PR Analysis']['Estimated effort to review [1-5]']
+                    estimated_effort_number = int(estimated_effort.split(',')[0])
+                    if 1 <= estimated_effort_number <= 5: # 1, because ...
+                        review_labels.append(f'Review effort [1-5]: {estimated_effort_number}')
+                if get_settings().pr_reviewer.enable_review_labels_security:
+                    security_concerns = data['PR Analysis']['Security concerns'] # yes, because ...
+                    security_concerns_bool = 'yes' in security_concerns.lower() or 'true' in security_concerns.lower()
+                    if security_concerns_bool:
+                        review_labels.append('Possible security concern')
+
+                current_labels = self.git_provider.get_labels()
+                current_labels_filtered = [label for label in current_labels if
+                                           not label.lower().startswith('review effort [1-5]:') and not label.lower().startswith(
+                                               'possible security concern')]
+                if current_labels or review_labels:
+                    get_logger().info(f"Setting review labels: {review_labels + current_labels_filtered}")
+                    self.git_provider.publish_labels(review_labels + current_labels_filtered)
+            except Exception as e:
+                get_logger().error(f"Failed to set review labels, error: {e}")

pr_agent/tools/pr_similar_issue.py

@@ -1,18 +1,19 @@
-import copy
-import json
-import logging
+import time
 from enum import Enum
-from typing import List, Tuple
-import pinecone
+from typing import List
+
 import openai
 import pandas as pd
+import pinecone
+from pinecone_datasets import Dataset, DatasetMetadata
 from pydantic import BaseModel, Field
 
 from pr_agent.algo import MAX_TOKENS
 from pr_agent.algo.token_handler import TokenHandler
+from pr_agent.algo.utils import get_max_tokens
 from pr_agent.config_loader import get_settings
 from pr_agent.git_providers import get_git_provider
-from pinecone_datasets import Dataset, DatasetMetadata
+from pr_agent.log import get_logger
 
 MODEL = "text-embedding-ada-002"
 
@@ -47,6 +48,13 @@ class PRSimilarIssue:
 
         # check if index exists, and if repo is already indexed
         run_from_scratch = False
+        if run_from_scratch:  # for debugging
+            pinecone.init(api_key=api_key, environment=environment)
+            if index_name in pinecone.list_indexes():
+                get_logger().info('Removing index...')
+                pinecone.delete_index(index_name)
+                get_logger().info('Done')
+
         upsert = True
         pinecone.init(api_key=api_key, environment=environment)
         if not index_name in pinecone.list_indexes():
@@ -62,11 +70,11 @@ class PRSimilarIssue:
                     upsert = False
 
         if run_from_scratch or upsert:  # index the entire repo
-            logging.info('Indexing the entire repo...')
+            get_logger().info('Indexing the entire repo...')
 
-            logging.info('Getting issues...')
+            get_logger().info('Getting issues...')
             issues = list(repo_obj.get_issues(state='all'))
-            logging.info('Done')
+            get_logger().info('Done')
             self._update_index_with_issues(issues, repo_name_for_index, upsert=upsert)
         else:  # update index if needed
             pinecone_index = pinecone.Index(index_name=index_name)
@@ -92,20 +100,20 @@ class PRSimilarIssue:
                     break
 
             if issues_to_update:
-                logging.info(f'Updating index with {counter} new issues...')
+                get_logger().info(f'Updating index with {counter} new issues...')
                 self._update_index_with_issues(issues_to_update, repo_name_for_index, upsert=True)
             else:
-                logging.info('No new issues to update')
+                get_logger().info('No new issues to update')
 
     async def run(self):
-        logging.info('Getting issue...')
+        get_logger().info('Getting issue...')
         repo_name, original_issue_number = self.git_provider._parse_issue_url(self.issue_url.split('=')[-1])
         issue_main = self.git_provider.repo_obj.get_issue(original_issue_number)
         issue_str, comments, number = self._process_issue(issue_main)
         openai.api_key = get_settings().openai.key
-        logging.info('Done')
+        get_logger().info('Done')
 
-        logging.info('Querying...')
+        get_logger().info('Querying...')
         res = openai.Embedding.create(input=[issue_str], engine=MODEL)
         embeds = [record['embedding'] for record in res['data']]
         pinecone_index = pinecone.Index(index_name=self.index_name)
@@ -117,7 +125,16 @@ class PRSimilarIssue:
         relevant_comment_number_list = []
         score_list = []
         for r in res['matches']:
-            issue_number = int(r["id"].split('.')[0].split('_')[-1])
+            # skip example issue
+            if 'example_issue_' in r["id"]:
+                continue
+
+            try:
+                issue_number = int(r["id"].split('.')[0].split('_')[-1])
+            except:
+                get_logger().debug(f"Failed to parse issue number from {r['id']}")
+                continue
+
             if original_issue_number == issue_number:
                 continue
             if issue_number not in relevant_issues_number_list:
@@ -127,9 +144,9 @@ class PRSimilarIssue:
             else:
                 relevant_comment_number_list.append(-1)
             score_list.append(str("{:.2f}".format(r['score'])))
-        logging.info('Done')
+        get_logger().info('Done')
 
-        logging.info('Publishing response...')
+        get_logger().info('Publishing response...')
         similar_issues_str = "### Similar Issues\n___\n\n"
         for i, issue_number_similar in enumerate(relevant_issues_number_list):
             issue = self.git_provider.repo_obj.get_issue(issue_number_similar)
@@ -140,8 +157,8 @@ class PRSimilarIssue:
             similar_issues_str += f"{i + 1}. **[{title}]({url})** (score={score_list[i]})\n\n"
         if get_settings().config.publish_output:
             response = issue_main.create_comment(similar_issues_str)
-        logging.info(similar_issues_str)
-        logging.info('Done')
+        get_logger().info(similar_issues_str)
+        get_logger().info('Done')
 
     def _process_issue(self, issue):
         header = issue.title
@@ -155,7 +172,7 @@ class PRSimilarIssue:
         return issue_str, comments, number
 
     def _update_index_with_issues(self, issues_list, repo_name_for_index, upsert=False):
-        logging.info('Processing issues...')
+        get_logger().info('Processing issues...')
         corpus = Corpus()
         example_issue_record = Record(
             id=f"example_issue_{repo_name_for_index}",
@@ -171,9 +188,9 @@ class PRSimilarIssue:
 
             counter += 1
             if counter % 100 == 0:
-                logging.info(f"Scanned {counter} issues")
+                get_logger().info(f"Scanned {counter} issues")
             if counter >= self.max_issues_to_scan:
-                logging.info(f"Scanned {self.max_issues_to_scan} issues, stopping")
+                get_logger().info(f"Scanned {self.max_issues_to_scan} issues, stopping")
                 break
 
             issue_str, comments, number = self._process_issue(issue)
@@ -181,7 +198,7 @@ class PRSimilarIssue:
             username = issue.user.login
             created_at = str(issue.created_at)
             if len(issue_str) < 8000 or \
-                    self.token_handler.count_tokens(issue_str) < MAX_TOKENS[MODEL]:  # fast reject first
+                    self.token_handler.count_tokens(issue_str) < get_max_tokens(MODEL):  # fast reject first
                 issue_record = Record(
                     id=issue_key + "." + "issue",
                     text=issue_str,
@@ -210,9 +227,9 @@ class PRSimilarIssue:
                             )
                             corpus.append(comment_record)
         df = pd.DataFrame(corpus.dict()["documents"])
-        logging.info('Done')
+        get_logger().info('Done')
 
-        logging.info('Embedding...')
+        get_logger().info('Embedding...')
         openai.api_key = get_settings().openai.key
         list_to_encode = list(df["text"].values)
         try:
@@ -220,7 +237,7 @@ class PRSimilarIssue:
             embeds = [record['embedding'] for record in res['data']]
         except:
             embeds = []
-            logging.error('Failed to embed entire list, embedding one by one...')
+            get_logger().error('Failed to embed entire list, embedding one by one...')
             for i, text in enumerate(list_to_encode):
                 try:
                     res = openai.Embedding.create(input=[text], engine=MODEL)
@@ -231,21 +248,23 @@ class PRSimilarIssue:
         meta = DatasetMetadata.empty()
         meta.dense_model.dimension = len(embeds[0])
         ds = Dataset.from_pandas(df, meta)
-        logging.info('Done')
+        get_logger().info('Done')
 
         api_key = get_settings().pinecone.api_key
         environment = get_settings().pinecone.environment
         if not upsert:
-            logging.info('Creating index from scratch...')
+            get_logger().info('Creating index from scratch...')
             ds.to_pinecone_index(self.index_name, api_key=api_key, environment=environment)
+            time.sleep(15)  # wait for pinecone to finalize indexing before querying
         else:
-            logging.info('Upserting index...')
+            get_logger().info('Upserting index...')
             namespace = ""
             batch_size: int = 100
             concurrency: int = 10
             pinecone.init(api_key=api_key, environment=environment)
             ds._upsert_to_index(self.index_name, namespace, batch_size, concurrency)
-        logging.info('Done')
+            time.sleep(5)  # wait for pinecone to finalize upserting before querying
+        get_logger().info('Done')
 
 
 class IssueLevel(str, Enum):

pr_agent/tools/pr_update_changelog.py

@@ -1,5 +1,4 @@
 import copy
-import logging
 from datetime import date
 from time import sleep
 from typing import Tuple
@@ -10,8 +9,9 @@ from pr_agent.algo.ai_handler import BaseAiHandler, AiHandler
 from pr_agent.algo.pr_processing import get_pr_diff, retry_with_fallback_models
 from pr_agent.algo.token_handler import TokenHandler
 from pr_agent.config_loader import get_settings
-from pr_agent.git_providers import GithubProvider, get_git_provider
+from pr_agent.git_providers import get_git_provider
 from pr_agent.git_providers.git_provider import get_main_pr_language
+from pr_agent.log import get_logger
 
 CHANGELOG_LINES = 50
 
@@ -48,26 +48,26 @@ class PRUpdateChangelog:
     async def run(self):
         # assert type(self.git_provider) == GithubProvider, "Currently only Github is supported"
 
-        logging.info('Updating the changelog...')
+        get_logger().info('Updating the changelog...')
         if get_settings().config.publish_output:
             self.git_provider.publish_comment("Preparing changelog updates...", is_temporary=True)
         await retry_with_fallback_models(self._prepare_prediction)
-        logging.info('Preparing PR changelog updates...')
+        get_logger().info('Preparing PR changelog updates...')
         new_file_content, answer = self._prepare_changelog_update()
         if get_settings().config.publish_output:
             self.git_provider.remove_initial_comment()
-            logging.info('Publishing changelog updates...')
+            get_logger().info('Publishing changelog updates...')
             if self.commit_changelog:
-                logging.info('Pushing PR changelog updates to repo...')
+                get_logger().info('Pushing PR changelog updates to repo...')
                 self._push_changelog_update(new_file_content, answer)
             else:
-                logging.info('Publishing PR changelog as comment...')
+                get_logger().info('Publishing PR changelog as comment...')
                 self.git_provider.publish_comment(f"**Changelog updates:**\n\n{answer}")
 
     async def _prepare_prediction(self, model: str):
-        logging.info('Getting PR diff...')
+        get_logger().info('Getting PR diff...')
         self.patches_diff = get_pr_diff(self.git_provider, self.token_handler, model)
-        logging.info('Getting AI prediction...')
+        get_logger().info('Getting AI prediction...')
         self.prediction = await self._get_prediction(model)
 
     async def _get_prediction(self, model: str):
@@ -77,8 +77,8 @@ class PRUpdateChangelog:
         system_prompt = environment.from_string(get_settings().pr_update_changelog_prompt.system).render(variables)
         user_prompt = environment.from_string(get_settings().pr_update_changelog_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}")
+            get_logger().info(f"\nSystem prompt:\n{system_prompt}")
+            get_logger().info(f"\nUser prompt:\n{user_prompt}")
         response, finish_reason = await self.ai_handler.chat_completion(model=model, temperature=0.2,
                                                                         system=system_prompt, user=user_prompt)
 
@@ -100,7 +100,7 @@ class PRUpdateChangelog:
                       "\n>'/update_changelog --pr_update_changelog.push_changelog_changes=true'\n"
 
         if get_settings().config.verbosity_level >= 2:
-            logging.info(f"answer:\n{answer}")
+            get_logger().info(f"answer:\n{answer}")
 
         return new_file_content, answer
 
@@ -149,7 +149,7 @@ Example:
         except Exception:
             self.changelog_file_str = ""
             if self.commit_changelog:
-                logging.info("No CHANGELOG.md file found in the repository. Creating one...")
+                get_logger().info("No CHANGELOG.md file found in the repository. Creating one...")
                 changelog_file = self.git_provider.repo_obj.create_file(path="CHANGELOG.md",
                                                                              message='add CHANGELOG.md',
                                                                              content="",