Merge remote-tracking branch 'origin/main' into ok/settings_refactor

Adding Commit Messages Retrieval Functionality

.dockerignore

@@ -1,3 +1,5 @@
 venv/
 pr_agent/settings/.secrets.toml
-pics/
+pics/
+pr_agent.egg-info/
+build/

.gitignore

@@ -1,4 +1,8 @@
 .idea/
 venv/
 pr_agent/settings/.secrets.toml
-__pycache__
+__pycache__
+dist/
+*.egg-info/
+build/
+review.md

CHANGELOG.md

@@ -0,0 +1,27 @@
+## 2023-08-01
+
+### Enhanced
+- Introduced the ability to retrieve commit messages from pull requests across different git providers.
+- Implemented commit messages retrieval for GitHub and GitLab providers.
+- Updated the PR description template to include a section for commit messages if they exist.
+
+## 2023-07-30
+
+### Enhanced
+- Added the ability to modify any configuration parameter from 'configuration.toml' on-the-fly.
+- Updated the command line interface and bot commands to accept configuration changes as arguments.
+- Improved the PR agent to handle additional arguments for each action.
+
+## 2023-07-28
+
+### Improved
+- Enhanced error handling and logging in the GitLab provider.
+- Improved handling of inline comments and code suggestions in GitLab.
+- Fixed a bug where an additional unneeded line was added to code suggestions in GitLab.
+
+## 2023-07-26
+
+### Added
+- New feature for updating the CHANGELOG.md based on the contents of a PR.
+- Added support for this feature for the Github provider.
+- New configuration settings and prompts for the changelog update feature.

CONFIGURATION.md

@@ -1,19 +1,12 @@
 ## Configuration
 
-The different tools and sub-tools used by CodiumAI pr-agent are easily configurable via the configuration file: `/pr-agent/settings/configuration.toml`.
-##### Git Provider:
-You can select your git_provider with the flag `git_provider` in the `config` section
+The different tools and sub-tools used by CodiumAI pr-agent are adjustable via the configuration file: `/pr-agent/settings/configuration.toml`.
 
-##### PR Reviewer:
+To edit the configuration of any tool, just add `--config_path=<value>` to you command.
+For example if you want to edit online the `pr_reviewer` configurations, you can run:
+```
+/review --pr_reviewer.extra_instructions="focus on the file xyz" --pr_reviewer.require_score_review=false ...
+```
+
+Any configuration value in `configuration.toml` file can be similarly edited.
 
-You can enable/disable the different PR Reviewer abilities with the following flags (`pr_reviewer` section):
-```
-require_focused_review=true
-require_score_review=true
-require_tests_review=true
-require_security_review=true
-```
-You can contol the number of suggestions returned by the PR Reviewer with the following flag:
-```inline_code_comments=3```
-And enable/disable the inline code suggestions with the following flag:
-```inline_code_comments=true```

Dockerfile.github_action

@@ -1,8 +1,8 @@
 FROM python:3.10 as base
 
 WORKDIR /app
-ADD requirements.txt .
-RUN pip install -r requirements.txt && rm requirements.txt
+ADD pyproject.toml .
+RUN pip install . && rm pyproject.toml
 ENV PYTHONPATH=/app
 ADD pr_agent pr_agent
 ADD github_action/entrypoint.sh /

PR_COMPRESSION.md

@@ -31,7 +31,7 @@ We prioritize additions over deletions:
  - File patches are a list of hunks, remove all hunks of type deletion-only from the hunks in the file patch
 ####  Adaptive and token-aware file patch fitting
 We use [tiktoken](https://github.com/openai/tiktoken) to tokenize the patches after the modifications described above, and we use the following strategy to fit the patches into the prompt:
-1. Withing each language we sort the files by the number of tokens in the file (in descending order):
+1. Within each language we sort the files by the number of tokens in the file (in descending order):
    * ```[[file2.py, file.py],[file4.jsx, file3.js],[readme.md]]```
 2. Iterate through the patches in the order described above
 2. Add the patches to the prompt until the prompt reaches a certain buffer from the max token length
@@ -39,4 +39,4 @@ We use [tiktoken](https://github.com/openai/tiktoken) to tokenize the patches af
 4. If we haven't reached the max token length, add the `deleted files` to the prompt until the prompt reaches the max token length (hard stop), skip the rest of the patches.
 
 ### Example
-![](https://codium.ai/images/git_patch_logic.png)
+![](https://codium.ai/images/git_patch_logic.png)

README.md

@@ -23,7 +23,9 @@ CodiumAI `PR-Agent` is an open-source tool aiming to help developers review pull
 \
 **Question Answering**: Answering free-text questions about the PR.
 \
-**Code Suggestion**: Committable code suggestions for improving the PR.
+**Code Suggestions**: Committable code suggestions for improving the PR.
+\
+**Update Changelog**: Automatically updating the CHANGELOG.md file with the PR changes.
 
 <h3>Example results:</h2>
 </div>
@@ -66,6 +68,7 @@ CodiumAI `PR-Agent` is an open-source tool aiming to help developers review pull
 - [Usage and tools](#usage-and-tools)
 - [Configuration](./CONFIGURATION.md)
 - [How it works](#how-it-works)
+- [Why use PR-Agent](#why-use-pr-agent)
 - [Roadmap](#roadmap)
 - [Similar projects](#similar-projects)
 </div>
@@ -81,6 +84,7 @@ CodiumAI `PR-Agent` is an open-source tool aiming to help developers review pull
 |       | Auto-Description                            |   :white_check_mark:    |  :white_check_mark:      |           |
 |       | Improve Code                                |   :white_check_mark:    |   :white_check_mark:    |           |
 |       | Reflect and Review                          |   :white_check_mark:    |                         |           |
+|       | Update CHANGELOG.md                         |   :white_check_mark:    |                         |           |
 |       |                                             |        |        |           |
 | USAGE | CLI                                         |   :white_check_mark:    |   :white_check_mark:    |   :white_check_mark:       |
 |       | App / webhook                               |   :white_check_mark:    |   :white_check_mark:    |           |
@@ -98,6 +102,7 @@ Examples for invoking the different tools via the CLI:
 - **Improve**:      python cli.py --pr-url=<pr_url>  improve
 - **Ask**:          python cli.py --pr-url=<pr_url>  ask "Write me a poem about this PR"
 - **Reflect**:      python cli.py --pr-url=<pr_url>  reflect
+- **Update Changelog**:      python cli.py --pr-url=<pr_url>  update_changelog
 
 "<pr_url>" is the url of the relevant PR (for example: https://github.com/Codium-ai/pr-agent/pull/50).
 
@@ -132,13 +137,14 @@ There are several ways to use PR-Agent:
 
 ## Usage and Tools
 
-**PR-Agent** provides five types of interactions ("tools"): `"PR Reviewer"`, `"PR Q&A"`, `"PR Description"`, `"PR Code Sueggestions"` and `"PR Reflect and Review"`.
+**PR-Agent** provides six types of interactions ("tools"): `"PR Reviewer"`, `"PR Q&A"`, `"PR Description"`, `"PR Code Sueggestions"`, `"PR Reflect and Review"` and `"PR Update Changlog"`.
 
 - The "PR Reviewer" tool automatically analyzes PRs, and provides various types of feedback.
 - The "PR Q&A" tool answers free-text questions about the PR.
 - The "PR Description" tool automatically sets the PR Title and body.
 - The "PR Code Suggestion" tool provide inline code suggestions for the PR that can be applied and committed.
 - The "PR Reflect and Review" tool initiates a dialog with the user, asks them to reflect on the PR, and then provides a more focused review.
+- The "PR Update Changelog" tool automatically updates the CHANGELOG.md file with the PR changes.
 
 ## How it works
 
@@ -146,6 +152,19 @@ There are several ways to use PR-Agent:
 
 Check out the [PR Compression strategy](./PR_COMPRESSION.md) page for more details on how we convert a code diff to a manageable LLM prompt
 
+## Why use PR-Agent?
+
+A reasonable question that can be asked is: `"Why use PR-Agent? What make it stand out from existing tools?"`
+
+Here are some of the reasons why:
+
+- We emphasize **real-life practical usage**. Each tool (review, improve, ask, ...) has a single GPT-4 call, no more. We feel that this is critical for realistic team usage - obtaining an answer quickly (~30 seconds) and affordably.
+- Our [PR Compression strategy](./PR_COMPRESSION.md)  is a core ability that enables to effectively tackle both short and long PRs.
+- Our JSON prompting strategy enables to have **modular, customizable tools**. For example, the '/review' tool categories can be controlled via the configuration file. Adding additional categories is easy and accessible.
+- We support **multiple git providers** (GitHub, Gitlab, Bitbucket), and multiple ways to use the tool (CLI, GitHub Action, GitHub App, Docker, ...).
+- We are open-source, and welcome contributions from the community.
+
+
 ## Roadmap
 
 - [ ] Support open-source models, as a replacement for OpenAI models. (Note - a minimal requirement for each open-source model is to have 8k+ context, and good support for generating JSON as an output)

docker/Dockerfile

@@ -1,8 +1,8 @@
 FROM python:3.10 as base
 
 WORKDIR /app
-ADD requirements.txt .
-RUN pip install -r requirements.txt && rm requirements.txt
+ADD pyproject.toml .
+RUN pip install . && rm pyproject.toml
 ENV PYTHONPATH=/app
 ADD pr_agent pr_agent
 

docker/Dockerfile.lambda

@@ -4,9 +4,9 @@ RUN yum update -y && \
     yum install -y gcc python3-devel && \
     yum clean all
 
-ADD requirements.txt .
-RUN pip install -r requirements.txt && rm requirements.txt
-RUN pip install mangum==16.0.0
+ADD pyproject.toml .
+RUN pip install . && rm pyproject.toml
+RUN pip install mangum==0.17.0
 COPY pr_agent/ ${LAMBDA_TASK_ROOT}/pr_agent/
 
 CMD ["pr_agent.servers.serverless.serverless"]

pr_agent/agent/pr_agent.py

@@ -1,33 +1,48 @@
-import re
+import shlex
 
-from pr_agent.config_loader import settings
+from pr_agent.algo.utils import update_settings_from_args
+from pr_agent.config_loader import get_settings
 from pr_agent.tools.pr_code_suggestions import PRCodeSuggestions
 from pr_agent.tools.pr_description import PRDescription
 from pr_agent.tools.pr_information_from_user import PRInformationFromUser
 from pr_agent.tools.pr_questions import PRQuestions
 from pr_agent.tools.pr_reviewer import PRReviewer
+from pr_agent.tools.pr_update_changelog import PRUpdateChangelog
 
+command2class = {
+    "answer": PRReviewer,
+    "review": PRReviewer,
+    "review_pr": PRReviewer,
+    "reflect": PRInformationFromUser,
+    "reflect_and_review": PRInformationFromUser,
+    "describe": PRDescription,
+    "describe_pr": PRDescription,
+    "improve": PRCodeSuggestions,
+    "improve_code": PRCodeSuggestions,
+    "ask": PRQuestions,
+    "ask_question": PRQuestions,
+    "update_changelog": PRUpdateChangelog,
+}
+
+commands = list(command2class.keys())
 
 class PRAgent:
     def __init__(self):
         pass
 
     async def handle_request(self, pr_url, request) -> bool:
-        action, *args = request.strip().split()
-        if any(cmd == action for cmd in ["/answer"]):
-            await PRReviewer(pr_url, is_answer=True).review()
-        elif any(cmd == action for cmd in ["/review", "/review_pr", "/reflect_and_review"]):
-            if settings.pr_reviewer.ask_and_reflect or "/reflect_and_review" in request:
-                await PRInformationFromUser(pr_url).generate_questions()
-            else:
-                await PRReviewer(pr_url, args=args).review()
-        elif any(cmd == action for cmd in ["/describe", "/describe_pr"]):
-            await PRDescription(pr_url).describe()
-        elif any(cmd == action for cmd in ["/improve", "/improve_code"]):
-            await PRCodeSuggestions(pr_url).suggest()
-        elif any(cmd == action for cmd in ["/ask", "/ask_question"]):
-            await PRQuestions(pr_url, args).answer()
+        request = request.replace("'", "\\'")
+        lexer = shlex.shlex(request, posix=True)
+        lexer.whitespace_split = True
+        action, *args = list(lexer)
+        args = update_settings_from_args(args)
+        action = action.lstrip("/").lower()
+        if action == "reflect_and_review" and not get_settings().pr_reviewer.ask_and_reflect:
+            action = "review"
+        if action == "answer":
+            await PRReviewer(pr_url, is_answer=True, args=args).run()
+        elif action in command2class:
+            await command2class[action](pr_url, args=args).run()
         else:
             return False
-
         return True

pr_agent/algo/ai_handler.py

@@ -1,10 +1,10 @@
 import logging
 
 import openai
-from openai.error import APIError, Timeout, TryAgain, RateLimitError
+from openai.error import APIError, RateLimitError, Timeout, TryAgain
 from retry import retry
 
-from pr_agent.config_loader import settings
+from pr_agent.config_loader import get_settings
 
 OPENAI_RETRIES=5
 
@@ -21,16 +21,16 @@ class AiHandler:
         Raises a ValueError if the OpenAI key is missing.
         """
         try:
-            openai.api_key = settings.openai.key
-            if settings.get("OPENAI.ORG", None):
-                openai.organization = settings.openai.org
-            self.deployment_id = settings.get("OPENAI.DEPLOYMENT_ID", None)
-            if settings.get("OPENAI.API_TYPE", None):
-                openai.api_type = settings.openai.api_type
-            if settings.get("OPENAI.API_VERSION", None):
-                openai.api_version = settings.openai.api_version
-            if settings.get("OPENAI.API_BASE", None):
-                openai.api_base = settings.openai.api_base
+            openai.api_key = get_settings().openai.key
+            if get_settings().get("OPENAI.ORG", None):
+                openai.organization = get_settings().openai.org
+            self.deployment_id = get_settings().get("OPENAI.DEPLOYMENT_ID", None)
+            if get_settings().get("OPENAI.API_TYPE", None):
+                openai.api_type = get_settings().openai.api_type
+            if get_settings().get("OPENAI.API_VERSION", None):
+                openai.api_version = get_settings().openai.api_version
+            if get_settings().get("OPENAI.API_BASE", None):
+                openai.api_base = get_settings().openai.api_base
         except AttributeError as e:
             raise ValueError("OpenAI key is required") from e
 

pr_agent/algo/git_patch_processing.py

@@ -3,7 +3,7 @@ from __future__ import annotations
 import logging
 import re
 
-from pr_agent.config_loader import settings
+from pr_agent.config_loader import get_settings
 
 
 def extend_patch(original_file_str, patch_str, num_lines) -> str:
@@ -55,7 +55,7 @@ def extend_patch(original_file_str, patch_str, num_lines) -> str:
                     continue
             extended_patch_lines.append(line)
     except Exception as e:
-        if settings.config.verbosity_level >= 2:
+        if get_settings().config.verbosity_level >= 2:
             logging.error(f"Failed to extend patch: {e}")
         return patch_str
 
@@ -126,14 +126,14 @@ def handle_patch_deletions(patch: str, original_file_content_str: str,
     """
     if not new_file_content_str:
         # logic for handling deleted files - don't show patch, just show that the file was deleted
-        if settings.config.verbosity_level > 0:
+        if get_settings().config.verbosity_level > 0:
             logging.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 settings.config.verbosity_level > 0:
+            if get_settings().config.verbosity_level > 0:
                 logging.info(f"Processing file: {file_name}, hunks were deleted")
             patch = patch_new
     return patch
@@ -141,7 +141,8 @@ def handle_patch_deletions(patch: str, original_file_content_str: str,
 
 def convert_to_hunks_with_lines_numbers(patch: str, file) -> str:
     """
-    Convert a given patch string into a string with line numbers for each hunk, indicating the new and old content of the file.
+    Convert a given patch string into a string with line numbers for each hunk, indicating the new and old content of
+    the file.
 
     Args:
         patch (str): The patch string to be converted.

pr_agent/algo/language_handler.py

@@ -1,19 +1,19 @@
 # Language Selection, source: https://github.com/bigcode-project/bigcode-dataset/blob/main/language_selection/programming-languages-to-file-extensions.json  # noqa E501
 from typing import Dict
 
-from pr_agent.config_loader import settings
+from pr_agent.config_loader import get_settings
 
-language_extension_map_org = settings.language_extension_map_org
+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 = settings.bad_extensions.default
-if settings.config.use_extra_bad_extensions:
-    bad_extensions += settings.bad_extensions.extra
+bad_extensions = get_settings().bad_extensions.default
+if get_settings().config.use_extra_bad_extensions:
+    bad_extensions += get_settings().bad_extensions.extra
 
 
 def filter_bad_extensions(files):
-    return [f for f in files if is_valid_file(f.filename)]
+    return [f for f in files if f.filename is not None and is_valid_file(f.filename)]
 
 
 def is_valid_file(filename):

pr_agent/algo/pr_processing.py

@@ -1,14 +1,16 @@
 from __future__ import annotations
 
 import logging
-from typing import Tuple, Union, Callable, List
+from typing import Callable, 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
 from pr_agent.algo.utils import load_large_diff
-from pr_agent.config_loader import settings
+from pr_agent.config_loader import get_settings
 from pr_agent.git_providers.git_provider import GitProvider
 
 DELETED_FILES_ = "Deleted files:\n"
@@ -19,18 +21,21 @@ 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:
     """
     Returns a string with the diff of the pull request, applying diff minimization techniques if needed.
 
     Args:
-        git_provider (GitProvider): An object of the GitProvider class representing the Git provider used for the pull request.
-        token_handler (TokenHandler): An object of the TokenHandler class used for handling tokens in the context of the pull request.
+        git_provider (GitProvider): An object of the GitProvider class representing the Git provider used for the pull
+        request.
+        token_handler (TokenHandler): An object of the TokenHandler class used for handling tokens in the context of the
+        pull request.
         model (str): The name of the model used for tokenization.
-        add_line_numbers_to_hunks (bool, optional): A boolean indicating whether to add line numbers to the hunks in the diff. Defaults to False.
-        disable_extra_lines (bool, optional): A boolean indicating whether to disable the extension of each patch with extra lines of context. Defaults to False.
+        add_line_numbers_to_hunks (bool, optional): A boolean indicating whether to add line numbers to the hunks in the
+        diff. Defaults to False.
+        disable_extra_lines (bool, optional): A boolean indicating whether to disable the extension of each patch with
+        extra lines of context. Defaults to False.
 
     Returns:
         str: A string with the diff of the pull request, applying diff minimization techniques if needed.
@@ -40,7 +45,11 @@ def get_pr_diff(git_provider: GitProvider, token_handler: TokenHandler, model: s
         global PATCH_EXTRA_LINES
         PATCH_EXTRA_LINES = 0
 
-    diff_files = list(git_provider.get_diff_files())
+    try:
+        diff_files = list(git_provider.get_diff_files())
+    except RateLimitExceededException as e:
+        logging.error(f"Rate limit exceeded for git provider API. original message {e}")
+        raise
 
     # get pr languages
     pr_languages = sort_files_by_main_languages(git_provider.get_languages(), diff_files)
@@ -71,10 +80,12 @@ def pr_generate_extended_diff(pr_languages: list, token_handler: TokenHandler,
                               add_line_numbers_to_hunks: bool) -> \
         Tuple[list, int]:
     """
-    Generate a standard diff string with patch extension, while counting the number of tokens used and applying diff minimization techniques if needed.
+    Generate a standard diff string with patch extension, while counting the number of tokens used and applying diff
+    minimization techniques if needed.
 
     Args:
-    - pr_languages: A list of dictionaries representing the languages used in the pull request and their corresponding files.
+    - pr_languages: A list of dictionaries representing the languages used in the pull request and their corresponding
+      files.
     - token_handler: An object of the TokenHandler class used for handling tokens in the context of the pull request.
     - add_line_numbers_to_hunks: A boolean indicating whether to add line numbers to the hunks in the diff.
 
@@ -114,10 +125,13 @@ def pr_generate_extended_diff(pr_languages: list, token_handler: TokenHandler,
 def pr_generate_compressed_diff(top_langs: list, token_handler: TokenHandler, model: str,
                                 convert_hunks_to_line_numbers: bool) -> Tuple[list, list, list]:
     """
-    Generate a compressed diff string for a pull request, using diff minimization techniques to reduce the number of tokens used.
+    Generate a compressed diff string for a pull request, using diff minimization techniques to reduce the number of
+    tokens used.
     Args:
-        top_langs (list): A list of dictionaries representing the languages used in the pull request and their corresponding files.
-        token_handler (TokenHandler): An object of the TokenHandler class used for handling tokens in the context of the pull request.
+        top_langs (list): A list of dictionaries representing the languages used in the pull request and their
+        corresponding files.
+        token_handler (TokenHandler): An object of the TokenHandler class used for handling tokens in the context of the
+        pull request.
         model (str): The model used for tokenization.
         convert_hunks_to_line_numbers (bool): A boolean indicating whether to convert hunks to line numbers in the diff.
     Returns:
@@ -176,7 +190,7 @@ def pr_generate_compressed_diff(top_langs: list, token_handler: TokenHandler, mo
             # 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 settings.config.verbosity_level >= 2:
+            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_)
@@ -191,15 +205,15 @@ def pr_generate_compressed_diff(top_langs: list, token_handler: TokenHandler, mo
                 patch_final = patch
             patches.append(patch_final)
             total_tokens += token_handler.count_tokens(patch_final)
-            if settings.config.verbosity_level >= 2:
+            if get_settings().config.verbosity_level >= 2:
                 logging.info(f"Tokens: {total_tokens}, last filename: {file.filename}")
 
     return patches, modified_files_list, deleted_files_list
 
 
 async def retry_with_fallback_models(f: Callable):
-    model = settings.config.model
-    fallback_models = settings.config.fallback_models
+    model = get_settings().config.model
+    fallback_models = get_settings().config.fallback_models
     if not isinstance(fallback_models, list):
         fallback_models = [fallback_models]
     all_models = [model] + fallback_models

pr_agent/algo/token_handler.py

@@ -1,8 +1,7 @@
 from jinja2 import Environment, StrictUndefined
 from tiktoken import encoding_for_model
 
-from pr_agent.algo import MAX_TOKENS
-from pr_agent.config_loader import settings
+from pr_agent.config_loader import get_settings
 
 
 class TokenHandler:
@@ -10,9 +9,12 @@ class TokenHandler:
     A class for handling tokens in the context of a pull request.
 
     Attributes:
-    - encoder: An object of the encoding_for_model class from the tiktoken module. Used to encode strings and count the number of tokens in them.
-    - limit: The maximum number of tokens allowed for the given model, as defined in the MAX_TOKENS dictionary in the pr_agent.algo module.
-    - prompt_tokens: The number of tokens in the system and user strings, as calculated by the _get_system_user_tokens method.
+    - encoder: An object of the encoding_for_model class from the tiktoken module. Used to encode strings and count the
+      number of tokens in them.
+    - limit: The maximum number of tokens allowed for the given model, as defined in the MAX_TOKENS dictionary in the
+      pr_agent.algo module.
+    - prompt_tokens: The number of tokens in the system and user strings, as calculated by the _get_system_user_tokens
+      method.
     """
 
     def __init__(self, pr, vars: dict, system, user):
@@ -25,7 +27,7 @@ class TokenHandler:
         - system: The system string.
         - user: The user string.
         """
-        self.encoder = encoding_for_model(settings.config.model)
+        self.encoder = encoding_for_model(get_settings().config.model)
         self.prompt_tokens = self._get_system_user_tokens(pr, self.encoder, vars, system, user)
 
     def _get_system_user_tokens(self, pr, encoder, vars: dict, system, user):

pr_agent/algo/utils.py

@@ -1,14 +1,24 @@
 from __future__ import annotations
 
 import difflib
-from datetime import datetime
 import json
 import logging
 import re
 import textwrap
+from datetime import datetime
+from typing import Any, List
 
-from pr_agent.config_loader import settings
+from starlette_context import context
 
+from pr_agent.config_loader import get_settings, global_settings
+
+
+def get_setting(key: str) -> Any:
+    try:
+        key = key.upper()
+        return context.get("settings", global_settings).get(key, global_settings.get(key, None))
+    except Exception:
+        return global_settings.get(key, None)
 
 def convert_to_markdown(output_data: dict) -> str:
     """
@@ -96,12 +106,16 @@ def try_fix_json(review, max_iter=10, code_suggestions=False):
     - data: A dictionary containing the parsed JSON data.
 
     The function attempts to fix broken or incomplete JSON messages by parsing until the last valid code suggestion.
-    If the JSON message ends with a closing bracket, the function calls the fix_json_escape_char function to fix the message.
-    If code_suggestions is True and the JSON message contains code suggestions, the function tries to fix the JSON message by parsing until the last valid code suggestion.
-    The function uses regular expressions to find the last occurrence of "}," with any number of whitespaces or newlines.
+    If the JSON message ends with a closing bracket, the function calls the fix_json_escape_char function to fix the
+    message.
+    If code_suggestions is True and the JSON message contains code suggestions, the function tries to fix the JSON
+    message by parsing until the last valid code suggestion.
+    The function uses regular expressions to find the last occurrence of "}," with any number of whitespaces or
+    newlines.
     It tries to parse the JSON message with the closing bracket and checks if it is valid.
     If the JSON message is valid, the parsed JSON data is returned.
-    If the JSON message is not valid, the last code suggestion is removed and the process is repeated until a valid JSON message is obtained or the maximum number of iterations is reached.
+    If the JSON message is not valid, the last code suggestion is removed and the process is repeated until a valid JSON
+    message is obtained or the maximum number of iterations is reached.
     If a valid JSON message is not obtained, an error is logged and an empty dictionary is returned.
     """
 
@@ -183,7 +197,8 @@ def convert_str_to_datetime(date_str):
 
 def load_large_diff(file, new_file_content_str: str, original_file_content_str: str, patch: str) -> str:
     """
-    Generate a patch for a modified file by comparing the original content of the file with the new content provided as input.
+    Generate a patch for a modified file by comparing the original content of the file with the new content provided as
+    input.
 
     Args:
         file: The file object for which the patch needs to be generated.
@@ -198,16 +213,55 @@ def load_large_diff(file, new_file_content_str: str, original_file_content_str:
         None.
 
     Additional Information:
-        - If 'patch' is not provided as input, the function generates a patch using the 'difflib' library and returns it as output.
-        - If the 'settings.config.verbosity_level' is greater than or equal to 2, a warning message is logged indicating that the file was modified but no patch was found, and a patch is manually created.
+        - If 'patch' is not provided as input, the function generates a patch using the 'difflib' library and returns it
+          as output.
+        - If the 'settings.config.verbosity_level' is greater than or equal to 2, a warning message is logged indicating
+          that the file was modified but no patch was found, and a patch is manually created.
     """
     if not patch:  # to Do - also add condition for file extension
         try:
             diff = difflib.unified_diff(original_file_content_str.splitlines(keepends=True),
                                         new_file_content_str.splitlines(keepends=True))
-            if settings.config.verbosity_level >= 2:
+            if get_settings().config.verbosity_level >= 2:
                 logging.warning(f"File was modified, but no patch was found. Manually creating patch: {file.filename}.")
             patch = ''.join(diff)
         except Exception:
             pass
     return patch
+
+
+def update_settings_from_args(args: List[str]) -> List[str]:
+    """
+    Update the settings of the Dynaconf object based on the arguments passed to the function.
+
+    Args:
+        args: A list of arguments passed to the function.
+        Example args: ['--pr_code_suggestions.extra_instructions="be funny',
+                  '--pr_code_suggestions.num_code_suggestions=3']
+
+    Returns:
+        None
+
+    Raises:
+        ValueError: If the argument is not in the correct format.
+
+    """
+    other_args = []
+    if args:
+        for arg in args:
+            arg = arg.strip()
+            if arg.startswith('--'):
+                arg = arg.strip('-').strip()
+                vals = arg.split('=')
+                if len(vals) != 2:
+                    logging.error(f'Invalid argument format: {arg}')
+                    other_args.append(arg)
+                    continue
+                key, value = vals
+                key = key.strip().upper()
+                value = value.strip()
+                get_settings().set(key, value)
+                logging.info(f'Updated setting {key} to: "{value}"')
+            else:
+                other_args.append(arg)
+    return other_args

pr_agent/cli.py

@@ -3,14 +3,11 @@ import asyncio
 import logging
 import os
 
-from pr_agent.tools.pr_code_suggestions import PRCodeSuggestions
-from pr_agent.tools.pr_description import PRDescription
-from pr_agent.tools.pr_information_from_user import PRInformationFromUser
-from pr_agent.tools.pr_questions import PRQuestions
-from pr_agent.tools.pr_reviewer import PRReviewer
+from pr_agent.agent.pr_agent import PRAgent, commands
+from pr_agent.config_loader import get_settings
 
 
-def run(args=None):
+def run(inargs=None):
     parser = argparse.ArgumentParser(description='AI based pull request analyzer', usage=
 """\
 Usage: cli.py --pr-url <URL on supported git hosting service> <command> [<args>].
@@ -27,75 +24,22 @@ ask / ask_question [question] - Ask a question about the PR.
 describe / describe_pr - Modify the PR title and description based on the PR's contents.
 improve / improve_code - Suggest improvements to the code in the PR as pull request comments ready to commit.
 reflect - Ask the PR author questions about the PR.
+update_changelog - Update the changelog based on the PR's contents.
+
+To edit any configuration parameter from 'configuration.toml', just add -config_path=<value>.
+For example: '- cli.py --pr-url=... review --pr_reviewer.extra_instructions="focus on the file: ..."'
 """)
     parser.add_argument('--pr_url', type=str, help='The URL of the PR to review', required=True)
-    parser.add_argument('command', type=str, help='The', choices=['review', 'review_pr',
-                                                                  'ask', 'ask_question',
-                                                                  'describe', 'describe_pr',
-                                                                  'improve', 'improve_code',
-                                                                  'reflect', 'review_after_reflect'],
-                                                                   default='review')
+    parser.add_argument('command', type=str, help='The', choices=commands, default='review')
     parser.add_argument('rest', nargs=argparse.REMAINDER, default=[])
-    args = parser.parse_args(args)
+    args = parser.parse_args(inargs)
     logging.basicConfig(level=os.environ.get("LOGLEVEL", "INFO"))
     command = args.command.lower()
-    commands = {
-        'ask': _handle_ask_command,
-        'ask_question': _handle_ask_command,
-        'describe': _handle_describe_command,
-        'describe_pr': _handle_describe_command,
-        'improve': _handle_improve_command,
-        'improve_code': _handle_improve_command,
-        'review': _handle_review_command,
-        'review_pr': _handle_review_command,
-        'reflect': _handle_reflect_command,
-        'review_after_reflect': _handle_review_after_reflect_command
-    }
-    if command in commands:
-        commands[command](args.pr_url, args.rest)
-    else:
-        print(f"Unknown command: {command}")
+    get_settings().set("CONFIG.CLI_MODE", True)
+    result = asyncio.run(PRAgent().handle_request(args.pr_url, command + " " + " ".join(args.rest)))
+    if not result:
         parser.print_help()
 
 
-def _handle_ask_command(pr_url: str, rest: list):
-    if len(rest) == 0:
-        print("Please specify a question")
-        return
-    print(f"Question: {' '.join(rest)} about PR {pr_url}")
-    reviewer = PRQuestions(pr_url, rest)
-    asyncio.run(reviewer.answer())
-
-
-def _handle_describe_command(pr_url: str, rest: list):
-    print(f"PR description: {pr_url}")
-    reviewer = PRDescription(pr_url)
-    asyncio.run(reviewer.describe())
-
-
-def _handle_improve_command(pr_url: str, rest: list):
-    print(f"PR code suggestions: {pr_url}")
-    reviewer = PRCodeSuggestions(pr_url)
-    asyncio.run(reviewer.suggest())
-
-
-def _handle_review_command(pr_url: str, rest: list):
-    print(f"Reviewing PR: {pr_url}")
-    reviewer = PRReviewer(pr_url, cli_mode=True, args=rest)
-    asyncio.run(reviewer.review())
-
-
-def _handle_reflect_command(pr_url: str, rest: list):
-    print(f"Asking the PR author questions: {pr_url}")
-    reviewer = PRInformationFromUser(pr_url)
-    asyncio.run(reviewer.generate_questions())
-
-
-def _handle_review_after_reflect_command(pr_url: str, rest: list):
-    print(f"Processing author's answers and sending review: {pr_url}")
-    reviewer = PRReviewer(pr_url, cli_mode=True, is_answer=True)
-    asyncio.run(reviewer.review())
-
-
 if __name__ == '__main__':
     run()

pr_agent/config_loader.py

@@ -1,20 +1,64 @@
 from os.path import abspath, dirname, join
+from pathlib import Path
+from typing import Optional
 
 from dynaconf import Dynaconf
+from starlette_context import context
+
+PR_AGENT_TOML_KEY = 'pr-agent'
 
 current_dir = dirname(abspath(__file__))
-settings = Dynaconf(
+global_settings = Dynaconf(
     envvar_prefix=False,
     merge_enabled=True,
     settings_files=[join(current_dir, f) for f in [
-         "settings/.secrets.toml",
-         "settings/configuration.toml",
-         "settings/language_extensions.toml",
-         "settings/pr_reviewer_prompts.toml",
-         "settings/pr_questions_prompts.toml",
-         "settings/pr_description_prompts.toml",
-         "settings/pr_code_suggestions_prompts.toml",
-         "settings/pr_information_from_user_prompts.toml",
-         "settings_prod/.secrets.toml"
-        ]]
+        "settings/.secrets.toml",
+        "settings/configuration.toml",
+        "settings/language_extensions.toml",
+        "settings/pr_reviewer_prompts.toml",
+        "settings/pr_questions_prompts.toml",
+        "settings/pr_description_prompts.toml",
+        "settings/pr_code_suggestions_prompts.toml",
+        "settings/pr_information_from_user_prompts.toml",
+        "settings/pr_update_changelog_prompts.toml",
+        "settings_prod/.secrets.toml"
+    ]]
 )
+
+
+def get_settings():
+    try:
+        return context["settings"]
+    except Exception:
+        return global_settings
+
+
+# Add local configuration from pyproject.toml of the project being reviewed
+def _find_repository_root() -> Path:
+    """
+    Identify project root directory by recursively searching for the .git directory in the parent directories.
+    """
+    cwd = Path.cwd().resolve()
+    no_way_up = False
+    while not no_way_up:
+        no_way_up = cwd == cwd.parent
+        if (cwd / ".git").is_dir():
+            return cwd
+        cwd = cwd.parent
+    return None
+
+
+def _find_pyproject() -> Optional[Path]:
+    """
+    Search for file pyproject.toml in the repository root.
+    """
+    repo_root = _find_repository_root()
+    if repo_root:
+        pyproject = _find_repository_root() / "pyproject.toml"
+        return pyproject if pyproject.is_file() else None
+    return None
+
+
+pyproject_path = _find_pyproject()
+if pyproject_path is not None:
+    get_settings().load_file(pyproject_path, env=f'tool.{PR_AGENT_TOML_KEY}')

pr_agent/git_providers/__init__.py

@@ -1,17 +1,19 @@
-from pr_agent.config_loader import settings
+from pr_agent.config_loader import get_settings
 from pr_agent.git_providers.bitbucket_provider import BitbucketProvider
 from pr_agent.git_providers.github_provider import GithubProvider
 from pr_agent.git_providers.gitlab_provider import GitLabProvider
+from pr_agent.git_providers.local_git_provider import LocalGitProvider
 
 _GIT_PROVIDERS = {
     'github': GithubProvider,
     'gitlab': GitLabProvider,
     'bitbucket': BitbucketProvider,
+    'local' : LocalGitProvider
 }
 
 def get_git_provider():
     try:
-        provider_id = settings.config.git_provider
+        provider_id = get_settings().config.git_provider
     except AttributeError as e:
         raise ValueError("git_provider is a required attribute in the configuration file") from e
     if provider_id not in _GIT_PROVIDERS:

pr_agent/git_providers/bitbucket_provider.py

@@ -5,15 +5,14 @@ from urllib.parse import urlparse
 import requests
 from atlassian.bitbucket import Cloud
 
-from pr_agent.config_loader import settings
-
+from ..config_loader import get_settings
 from .git_provider import FilePatchInfo
 
 
 class BitbucketProvider:
     def __init__(self, pr_url: Optional[str] = None, incremental: Optional[bool] = False):
         s = requests.Session()
-        s.headers['Authorization'] = f'Bearer {settings.get("BITBUCKET.BEARER_TOKEN", None)}'
+        s.headers['Authorization'] = f'Bearer {get_settings().get("BITBUCKET.BEARER_TOKEN", None)}'
         self.bitbucket_client = Cloud(session=s)
 
         self.workspace_slug = None
@@ -121,3 +120,6 @@ class BitbucketProvider:
 
     def _get_pr_file_content(self, remote_link: str):
         return ""
+
+    def get_commit_messages(self):
+        return ""  # not implemented yet

pr_agent/git_providers/git_provider.py

@@ -136,3 +136,4 @@ class IncrementalPR:
         self.commits_range = None
         self.first_new_commit_sha = None
         self.last_seen_commit_sha = None
+

pr_agent/git_providers/github_provider.py

@@ -3,19 +3,24 @@ from datetime import datetime
 from typing import Optional, Tuple
 from urllib.parse import urlparse
 
-from github import AppAuthentication, Github, Auth
+from github import AppAuthentication, Auth, Github, GithubException
+from retry import retry
+from starlette_context import context
 
-from pr_agent.config_loader import settings
-
-from .git_provider import FilePatchInfo, GitProvider, IncrementalPR
 from ..algo.language_handler import is_valid_file
 from ..algo.utils import load_large_diff
+from ..config_loader import get_settings
+from ..servers.utils import RateLimitExceeded
+from .git_provider import FilePatchInfo, GitProvider, IncrementalPR
 
 
 class GithubProvider(GitProvider):
     def __init__(self, pr_url: Optional[str] = None, incremental=IncrementalPR(False)):
         self.repo_obj = None
-        self.installation_id = settings.get("GITHUB.INSTALLATION_ID")
+        try:
+            self.installation_id = context.get("installation_id", None)
+        except Exception:
+            self.installation_id = None
         self.github_client = self._get_github_client()
         self.repo = None
         self.pr_num = None
@@ -78,34 +83,41 @@ class GithubProvider(GitProvider):
             return self.file_set.values()
         return self.pr.get_files()
 
+    @retry(exceptions=RateLimitExceeded,
+           tries=get_settings().github.ratelimit_retries, delay=2, backoff=2, jitter=(1, 3))
     def get_diff_files(self) -> list[FilePatchInfo]:
-        files = self.get_files()
-        diff_files = []
-        for file in files:
-            if is_valid_file(file.filename):
-                new_file_content_str = self._get_pr_file_content(file, self.pr.head.sha)
-                patch = file.patch
-                if self.incremental.is_incremental and self.file_set:
-                    original_file_content_str = self._get_pr_file_content(file, self.incremental.last_seen_commit_sha)
-                    patch = load_large_diff(file,
-                                            new_file_content_str,
-                                            original_file_content_str,
-                                             None)
-                    self.file_set[file.filename] = patch
-                else:
-                    original_file_content_str = self._get_pr_file_content(file, self.pr.base.sha)
+        try:
+            files = self.get_files()
+            diff_files = []
+            for file in files:
+                if is_valid_file(file.filename):
+                    new_file_content_str = self._get_pr_file_content(file, self.pr.head.sha)
+                    patch = file.patch
+                    if self.incremental.is_incremental and self.file_set:
+                        original_file_content_str = self._get_pr_file_content(file,
+                                                                              self.incremental.last_seen_commit_sha)
+                        patch = load_large_diff(file,
+                                                new_file_content_str,
+                                                original_file_content_str,
+                                                None)
+                        self.file_set[file.filename] = patch
+                    else:
+                        original_file_content_str = self._get_pr_file_content(file, self.pr.base.sha)
 
-                diff_files.append(
-                    FilePatchInfo(original_file_content_str, new_file_content_str, patch, file.filename))
-        self.diff_files = diff_files
-        return diff_files
+                    diff_files.append(
+                        FilePatchInfo(original_file_content_str, new_file_content_str, patch, file.filename))
+            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}")
+            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)
         # self.pr.create_issue_comment(pr_comment)
 
     def publish_comment(self, pr_comment: str, is_temporary: bool = False):
-        if is_temporary and not settings.config.publish_output_progress:
+        if is_temporary and not get_settings().config.publish_output_progress:
             logging.debug(f"Skipping publish_comment for temporary comment: {pr_comment}")
             return
         response = self.pr.create_issue_comment(pr_comment)
@@ -136,7 +148,7 @@ class GithubProvider(GitProvider):
                         position = i
                         break
         if position == -1:
-            if settings.config.verbosity_level >= 2:
+            if get_settings().config.verbosity_level >= 2:
                 logging.info(f"Could not find position for {relevant_file} {relevant_line_in_file}")
             subject_type = "FILE"
         else:
@@ -161,13 +173,13 @@ class GithubProvider(GitProvider):
             relevant_lines_end = suggestion['relevant_lines_end']
 
             if not relevant_lines_start or relevant_lines_start == -1:
-                if settings.config.verbosity_level >= 2:
+                if get_settings().config.verbosity_level >= 2:
                     logging.exception(
                         f"Failed to publish code suggestion, relevant_lines_start is {relevant_lines_start}")
                 continue
 
             if relevant_lines_end < relevant_lines_start:
-                if settings.config.verbosity_level >= 2:
+                if get_settings().config.verbosity_level >= 2:
                     logging.exception(f"Failed to publish code suggestion, "
                                       f"relevant_lines_end is {relevant_lines_end} and "
                                       f"relevant_lines_start is {relevant_lines_start}")
@@ -194,7 +206,7 @@ class GithubProvider(GitProvider):
             self.pr.create_review(commit=self.last_commit_id, comments=post_parameters_list)
             return True
         except Exception as e:
-            if settings.config.verbosity_level >= 2:
+            if get_settings().config.verbosity_level >= 2:
                 logging.error(f"Failed to publish code suggestion, error: {e}")
             return False
 
@@ -228,7 +240,7 @@ class GithubProvider(GitProvider):
         return self.github_user_id
 
     def get_notifications(self, since: datetime):
-        deployment_type = settings.get("GITHUB.DEPLOYMENT_TYPE", "user")
+        deployment_type = get_settings().get("GITHUB.DEPLOYMENT_TYPE", "user")
 
         if deployment_type != 'user':
             raise ValueError("Deployment mode must be set to 'user' to get notifications")
@@ -269,12 +281,12 @@ class GithubProvider(GitProvider):
         return repo_name, pr_number
 
     def _get_github_client(self):
-        deployment_type = settings.get("GITHUB.DEPLOYMENT_TYPE", "user")
+        deployment_type = get_settings().get("GITHUB.DEPLOYMENT_TYPE", "user")
 
         if deployment_type == 'app':
             try:
-                private_key = settings.github.private_key
-                app_id = settings.github.app_id
+                private_key = get_settings().github.private_key
+                app_id = get_settings().github.app_id
             except AttributeError as e:
                 raise ValueError("GitHub app ID and private key are required when using GitHub app deployment") from e
             if not self.installation_id:
@@ -285,7 +297,7 @@ class GithubProvider(GitProvider):
 
         if deployment_type == 'user':
             try:
-                token = settings.github.user_token
+                token = get_settings().github.user_token
             except AttributeError as e:
                 raise ValueError(
                     "GitHub token is required when using user deployment. See: "
@@ -314,7 +326,9 @@ 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", "Other": "d1bcf9"}
+            label_color_map = {"Bug fix": "1d76db", "Tests": "e99695", "Bug fix with tests": "c5def5",
+                               "Refactoring": "bfdadc", "Enhancement": "bfd4f2", "Documentation": "d4c5f9",
+                               "Other": "d1bcf9"}
             post_parameters = []
             for p in pr_types:
                 color = label_color_map.get(p, "d1bcf9")  # default to "Other" color
@@ -330,4 +344,19 @@ class GithubProvider(GitProvider):
             return [label.name for label in self.pr.labels]
         except Exception as e:
             logging.exception(f"Failed to get labels, error: {e}")
-            return []
+            return []
+
+    def get_commit_messages(self) -> str:
+        """
+        Retrieves the commit messages of a pull request.
+
+        Returns:
+            str: A string containing the commit messages of the pull request.
+        """
+        try:
+            commit_list = self.pr.get_commits()
+            commit_messages = [commit.commit.message for commit in commit_list]
+            commit_messages_str = "\n".join([f"{i + 1}. {message}" for i, message in enumerate(commit_messages)])
+        except:
+            commit_messages_str = ""
+        return commit_messages_str

pr_agent/git_providers/gitlab_provider.py

@@ -6,9 +6,8 @@ from urllib.parse import urlparse
 import gitlab
 from gitlab import GitlabGetError
 
-from pr_agent.config_loader import settings
-
 from ..algo.language_handler import is_valid_file
+from ..config_loader import get_settings
 from .git_provider import EDIT_TYPE, FilePatchInfo, GitProvider
 
 logger = logging.getLogger()
@@ -16,17 +15,16 @@ logger = logging.getLogger()
 
 class GitLabProvider(GitProvider):
 
-
     def __init__(self, merge_request_url: Optional[str] = None, incremental: Optional[bool] = False):
-        gitlab_url = settings.get("GITLAB.URL", None)
+        gitlab_url = get_settings().get("GITLAB.URL", None)
         if not gitlab_url:
             raise ValueError("GitLab URL is not set in the config file")
-        gitlab_access_token = settings.get("GITLAB.PERSONAL_ACCESS_TOKEN", None)
+        gitlab_access_token = get_settings().get("GITLAB.PERSONAL_ACCESS_TOKEN", None)
         if not gitlab_access_token:
             raise ValueError("GitLab personal access token is not set in the config file")
         self.gl = gitlab.Gitlab(
-            gitlab_url,
-            gitlab_access_token
+            url=gitlab_url,
+            oauth_token=gitlab_access_token
         )
         self.id_project = None
         self.id_mr = None
@@ -141,32 +139,42 @@ 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})
 
     def publish_code_suggestions(self, code_suggestions: 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']
+            try:
+                body = suggestion['body']
+                relevant_file = suggestion['relevant_file']
+                relevant_lines_start = suggestion['relevant_lines_start']
+                relevant_lines_end = suggestion['relevant_lines_end']
 
-            self.diff_files = self.diff_files if self.diff_files else self.get_diff_files()
-            target_file = None
-            for file in self.diff_files:
-                if file.filename == relevant_file:
+                self.diff_files = self.diff_files if self.diff_files else self.get_diff_files()
+                target_file = None
+                for file in self.diff_files:
                     if file.filename == relevant_file:
-                        target_file = file
-                        break
-            range = relevant_lines_end - relevant_lines_start + 1
-            body = body.replace('```suggestion', f'```suggestion:-0+{range}')
+                        if file.filename == relevant_file:
+                            target_file = file
+                            break
+                range = relevant_lines_end - relevant_lines_start # no need to add 1
+                body = body.replace('```suggestion', f'```suggestion:-0+{range}')
+                lines = target_file.head_file.splitlines()
+                relevant_line_in_file = lines[relevant_lines_start - 1]
 
-            lines = target_file.head_file.splitlines()
-            relevant_line_in_file = lines[relevant_lines_start - 1]
-            edit_type, found, source_line_no, target_file, target_line_no = self.find_in_file(target_file,
-                                                                                              relevant_line_in_file)
-            self.send_inline_comment(body, edit_type, found, relevant_file, relevant_line_in_file, source_line_no,
-                                     target_file, target_line_no)
+                # edit_type, found, source_line_no, target_file, target_line_no = self.find_in_file(target_file,
+                #                                                                            relevant_line_in_file)
+                # for code suggestions, we want to edit the new code
+                source_line_no = None
+                target_line_no = relevant_lines_start + 1
+                found = True
+                edit_type = 'addition'
+
+                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}")
 
     def search_line(self, relevant_file, relevant_line_in_file):
         target_file = None
@@ -245,20 +253,30 @@ class GitLabProvider(GitProvider):
     def get_issue_comments(self):
         raise NotImplementedError("GitLab provider does not support issue comments yet")
 
-    def _parse_merge_request_url(self, merge_request_url: str) -> Tuple[int, int]:
+    def _parse_merge_request_url(self, merge_request_url: str) -> Tuple[str, int]:
         parsed_url = urlparse(merge_request_url)
 
         path_parts = parsed_url.path.strip('/').split('/')
-        if path_parts[-2] != 'merge_requests':
+        if 'merge_requests' not in path_parts:
             raise ValueError("The provided URL does not appear to be a GitLab merge request URL")
 
+        mr_index = path_parts.index('merge_requests')
+        # Ensure there is an ID after 'merge_requests'
+        if len(path_parts) <= mr_index + 1:
+            raise ValueError("The provided URL does not contain a merge request ID")
+
         try:
-            mr_id = int(path_parts[-1])
+            mr_id = int(path_parts[mr_index + 1])
         except ValueError as e:
             raise ValueError("Unable to convert merge request ID to integer") from e
 
-        # Gitlab supports access by both project numeric ID as well as 'namespace/project_name'
-        return "/".join(path_parts[:2]), mr_id
+        # Handle special delimiter (-)
+        project_path = "/".join(path_parts[:mr_index])
+        if project_path.endswith('/-'):
+            project_path = project_path[:-2]
+
+        # Return the path before 'merge_requests' and the ID
+        return project_path, mr_id
 
     def _get_merge_request(self):
         mr = self.gl.projects.get(self.id_project).mergerequests.get(self.id_mr)
@@ -279,3 +297,17 @@ class GitLabProvider(GitProvider):
 
     def get_labels(self):
         return self.mr.labels
+
+    def get_commit_messages(self) -> str:
+        """
+        Retrieves the commit messages of a pull request.
+
+        Returns:
+            str: A string containing the commit messages of the pull request.
+        """
+        try:
+            commit_messages_list = [commit['message'] for commit in self.mr.commits()._list]
+            commit_messages_str = "\n".join([f"{i + 1}. {message}" for i, message in enumerate(commit_messages_list)])
+        except:
+            commit_messages_str = ""
+        return commit_messages_str

pr_agent/git_providers/local_git_provider.py

@@ -0,0 +1,178 @@
+import logging
+from collections import Counter
+from pathlib import Path
+from typing import List
+
+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
+
+
+class PullRequestMimic:
+    """
+    This class mimics the PullRequest class from the PyGithub library for the LocalGitProvider.
+    """
+
+    def __init__(self, title: str, diff_files: List[FilePatchInfo]):
+        self.title = title
+        self.diff_files = diff_files
+
+
+class LocalGitProvider(GitProvider):
+    """
+    This class implements the GitProvider interface for local git repositories.
+    It mimics the PR functionality of the GitProvider interface,
+    but does not require a hosted git repository.
+    Instead of providing a PR url, the user provides a local branch path to generate a diff-patch.
+    For the MVP it only supports the /review and /describe capabilities.
+    """
+
+    def __init__(self, target_branch_name, incremental=False):
+        self.repo_path = _find_repository_root()
+        if self.repo_path is None:
+            raise ValueError('Could not find repository root')
+        self.repo = Repo(self.repo_path)
+        self.head_branch_name = self.repo.head.ref.name
+        self.target_branch_name = target_branch_name
+        self._prepare_repo()
+        self.diff_files = None
+        self.pr = PullRequestMimic(self.get_pr_title(), self.get_diff_files())
+        self.description_path = get_settings().get('local.description_path') \
+            if get_settings().get('local.description_path') is not None else self.repo_path / 'description.md'
+        self.review_path = get_settings().get('local.review_path') \
+            if get_settings().get('local.review_path') is not None else self.repo_path / 'review.md'
+        # inline code comments are not supported for local git repositories
+        get_settings().pr_reviewer.inline_code_comments = False
+
+    def _prepare_repo(self):
+        """
+        Prepare the repository for PR-mimic generation.
+        """
+        logging.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:
+            raise KeyError(f'Branch: {self.target_branch_name} does not exist')
+
+    def is_supported(self, capability: str) -> bool:
+        if capability in ['get_issue_comments', 'create_inline_comment', 'publish_inline_comments', 'get_labels']:
+            return False
+        return True
+
+    def get_diff_files(self) -> list[FilePatchInfo]:
+        diffs = self.repo.head.commit.diff(
+            self.repo.merge_base(self.repo.head, self.repo.branches[self.target_branch_name]),
+            create_patch=True,
+            R=True
+        )
+        diff_files = []
+        for diff_item in diffs:
+            if diff_item.a_blob is not None:
+                original_file_content_str = diff_item.a_blob.data_stream.read().decode('utf-8')
+            else:
+                original_file_content_str = ""  # empty file
+            if diff_item.b_blob is not None:
+                new_file_content_str = diff_item.b_blob.data_stream.read().decode('utf-8')
+            else:
+                new_file_content_str = ""  # empty file
+            edit_type = EDIT_TYPE.MODIFIED
+            if diff_item.new_file:
+                edit_type = EDIT_TYPE.ADDED
+            elif diff_item.deleted_file:
+                edit_type = EDIT_TYPE.DELETED
+            elif diff_item.renamed_file:
+                edit_type = EDIT_TYPE.RENAMED
+            diff_files.append(
+                FilePatchInfo(original_file_content_str,
+                              new_file_content_str,
+                              diff_item.diff.decode('utf-8'),
+                              diff_item.b_path,
+                              edit_type=edit_type,
+                              old_filename=None if diff_item.a_path == diff_item.b_path else diff_item.a_path
+                              )
+            )
+        self.diff_files = diff_files
+        return diff_files
+
+    def get_files(self) -> List[str]:
+        """
+        Returns a list of files with changes in the diff.
+        """
+        diff_index = self.repo.head.commit.diff(
+            self.repo.merge_base(self.repo.head, self.repo.branches[self.target_branch_name]),
+            R=True
+        )
+        # Get the list of changed files
+        diff_files = [item.a_path for item in diff_index]
+        return diff_files
+
+    def publish_description(self, pr_title: str, pr_body: str):
+        with open(self.description_path, "w") as file:
+            # Write the string to the file
+            file.write(pr_title + '\n' + pr_body)
+
+    def publish_comment(self, pr_comment: str, is_temporary: bool = False):
+        with open(self.review_path, "w") as file:
+            # Write the string to the file
+            file.write(pr_comment)
+
+    def publish_inline_comment(self, body: str, relevant_file: str, relevant_line_in_file: str):
+        raise NotImplementedError('Publishing inline comments is not implemented for the local git provider')
+
+    def create_inline_comment(self, body: str, relevant_file: str, relevant_line_in_file: str):
+        raise NotImplementedError('Creating inline comments is not implemented for the local git provider')
+
+    def publish_inline_comments(self, comments: list[dict]):
+        raise NotImplementedError('Publishing inline comments is not implemented for the local git provider')
+
+    def publish_code_suggestion(self, body: str, relevant_file: str,
+                                relevant_lines_start: int, relevant_lines_end: int):
+        raise NotImplementedError('Publishing code suggestions is not implemented for the local git provider')
+
+    def publish_code_suggestions(self, code_suggestions: list):
+        raise NotImplementedError('Publishing code suggestions is not implemented for the local git provider')
+
+    def publish_labels(self, labels):
+        pass  # Not applicable to the local git provider, but required by the interface
+
+    def remove_initial_comment(self):
+        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.
+        """
+        # Get all files in repository
+        filepaths = [Path(item.path) for item in self.repo.tree().traverse() if item.type == 'blob']
+        # Identify language by file extension and count
+        lang_count = Counter(ext.lstrip('.') for filepath in filepaths for ext in [filepath.suffix.lower()])
+        # Convert counts to percentages
+        total_files = len(filepaths)
+        lang_percentage = {lang: count / total_files * 100 for lang, count in lang_count.items()}
+        return lang_percentage
+
+    def get_pr_branch(self):
+        return self.repo.head
+
+    def get_user_id(self):
+        return -1  # Not used anywhere for the local provider, but required by the interface
+
+    def get_pr_description(self):
+        commits_diff = list(self.repo.iter_commits(self.target_branch_name + '..HEAD'))
+        # Get the commit messages and concatenate
+        commit_messages = " ".join([commit.message for commit in commits_diff])
+        # TODO Handle the description better - maybe use gpt-3.5 summarisation here?
+        return commit_messages[:200]  # Use max 200 characters
+
+    def get_pr_title(self):
+        """
+        Substitutes the branch-name as the PR-mimic title.
+        """
+        return self.head_branch_name
+
+    def get_issue_comments(self):
+        raise NotImplementedError('Getting issue comments is not implemented for the local git provider')
+
+    def get_labels(self):
+        raise NotImplementedError('Getting labels is not implemented for the local git provider')

pr_agent/servers/github_action_runner.py

@@ -3,7 +3,7 @@ import json
 import os
 
 from pr_agent.agent.pr_agent import PRAgent
-from pr_agent.config_loader import settings
+from pr_agent.config_loader import get_settings
 from pr_agent.tools.pr_reviewer import PRReviewer
 
 
@@ -30,11 +30,11 @@ async def run_action():
         return
 
     # Set the environment variables in the settings
-    settings.set("OPENAI.KEY", OPENAI_KEY)
+    get_settings().set("OPENAI.KEY", OPENAI_KEY)
     if OPENAI_ORG:
-        settings.set("OPENAI.ORG", OPENAI_ORG)
-    settings.set("GITHUB.USER_TOKEN", GITHUB_TOKEN)
-    settings.set("GITHUB.DEPLOYMENT_TYPE", "user")
+        get_settings().set("OPENAI.ORG", OPENAI_ORG)
+    get_settings().set("GITHUB.USER_TOKEN", GITHUB_TOKEN)
+    get_settings().set("GITHUB.DEPLOYMENT_TYPE", "user")
 
     # Load the event payload
     try:
@@ -50,7 +50,7 @@ async def run_action():
         if action in ["opened", "reopened"]:
             pr_url = event_payload.get("pull_request", {}).get("url")
             if pr_url:
-                await PRReviewer(pr_url).review()
+                await PRReviewer(pr_url).run()
 
     # Handle issue comment event
     elif GITHUB_EVENT_NAME == "issue_comment":

pr_agent/servers/github_app.py

@@ -1,11 +1,16 @@
+import copy
 import logging
 import sys
+from typing import Any, Dict
 
 import uvicorn
 from fastapi import APIRouter, FastAPI, HTTPException, Request, Response
+from starlette.middleware import Middleware
+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 settings
+from pr_agent.config_loader import get_settings, global_settings
 from pr_agent.servers.utils import verify_signature
 
 logging.basicConfig(stream=sys.stdout, level=logging.DEBUG)
@@ -14,7 +19,29 @@ router = APIRouter()
 
 @router.post("/api/v1/github_webhooks")
 async def handle_github_webhooks(request: Request, response: Response):
-    logging.debug("Received a github webhook")
+    """
+    Receives and processes incoming GitHub webhook requests.
+    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")
+
+    body = await get_body(request)
+
+    logging.debug(f'Request body:\n{body}')
+    installation_id = body.get("installation", {}).get("id")
+    context["installation_id"] = installation_id
+    context["settings"] = copy.deepcopy(global_settings)
+
+    return await handle_request(body)
+
+
+@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}')
+
+async def get_body(request):
     try:
         body = await request.json()
     except Exception as e:
@@ -22,43 +49,49 @@ async def handle_github_webhooks(request: Request, response: Response):
         raise HTTPException(status_code=400, detail="Error parsing request body") from e
     body_bytes = await request.body()
     signature_header = request.headers.get('x-hub-signature-256', None)
-    try:
-        webhook_secret = settings.github.webhook_secret
-    except AttributeError:
-        webhook_secret = None
+    webhook_secret = getattr(get_settings().github, 'webhook_secret', None)
     if webhook_secret:
         verify_signature(body_bytes, webhook_secret, signature_header)
-    logging.debug(f'Request body:\n{body}')
-    return await handle_request(body)
+    return body
 
 
-async def handle_request(body):
-    action = body.get("action", None)
-    installation_id = body.get("installation", {}).get("id", None)
-    settings.set("GITHUB.INSTALLATION_ID", installation_id)
+
+
+async def handle_request(body: Dict[str, Any]):
+    """
+    Handle incoming GitHub webhook requests.
+
+    Args:
+        body: The request body.
+    """
+    action = body.get("action")
+    if not action:
+        return {}
     agent = PRAgent()
+
     if action == 'created':
         if "comment" not in body:
             return {}
-        comment_body = body.get("comment", {}).get("body", None)
-        if 'sender' in body and 'login' in body['sender'] and 'bot' in body['sender']['login']:
+        comment_body = body.get("comment", {}).get("body")
+        sender = body.get("sender", {}).get("login")
+        if sender and 'bot' in sender:
             return {}
-        if "issue" not in body and "pull_request" not in body["issue"]:
+        if "issue" not in body or "pull_request" not in body["issue"]:
             return {}
         pull_request = body["issue"]["pull_request"]
-        api_url = pull_request.get("url", None)
+        api_url = pull_request.get("url")
         await agent.handle_request(api_url, comment_body)
 
-    elif action in ["opened"] or 'reopened' in action:
-        pull_request = body.get("pull_request", None)
+    elif action == "opened" or 'reopened' in action:
+        pull_request = body.get("pull_request")
         if not pull_request:
             return {}
-        api_url = pull_request.get("url", None)
-        if api_url is None:
+        api_url = pull_request.get("url")
+        if not api_url:
             return {}
         await agent.handle_request(api_url, "/review")
-    else:
-        return {}
+
+    return {}
 
 
 @router.get("/")
@@ -68,12 +101,13 @@ async def root():
 
 def start():
     # Override the deployment type to app
-    settings.set("GITHUB.DEPLOYMENT_TYPE", "app")
-    app = FastAPI()
+    get_settings().set("GITHUB.DEPLOYMENT_TYPE", "app")
+    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()
+    start()

pr_agent/servers/github_polling.py

@@ -6,7 +6,7 @@ from datetime import datetime, timezone
 import aiohttp
 
 from pr_agent.agent.pr_agent import PRAgent
-from pr_agent.config_loader import settings
+from pr_agent.config_loader import get_settings
 from pr_agent.git_providers import get_git_provider
 from pr_agent.servers.help import bot_help_text
 
@@ -15,28 +15,40 @@ NOTIFICATION_URL = "https://api.github.com/notifications"
 
 
 def now() -> str:
+    """
+    Get the current UTC time in ISO 8601 format.
+    
+    Returns:
+        str: The current UTC time in ISO 8601 format.
+    """
     now_utc = datetime.now(timezone.utc).isoformat()
     now_utc = now_utc.replace("+00:00", "Z")
     return now_utc
 
 
 async def polling_loop():
+    """
+    Polls for notifications and handles them accordingly.
+    """
     handled_ids = set()
     since = [now()]
     last_modified = [None]
     git_provider = get_git_provider()()
     user_id = git_provider.get_user_id()
     agent = PRAgent()
+
     try:
-        deployment_type = settings.github.deployment_type
-        token = settings.github.user_token
+        deployment_type = get_settings().github.deployment_type
+        token = get_settings().github.user_token
     except AttributeError:
         deployment_type = 'none'
         token = None
+
     if deployment_type != 'user':
         raise ValueError("Deployment mode must be set to 'user' to get notifications")
     if not token:
         raise ValueError("User token must be set to get notifications")
+
     async with aiohttp.ClientSession() as session:
         while True:
             try:
@@ -52,6 +64,7 @@ async def polling_loop():
                     params["since"] = since[0]
                 if last_modified[0]:
                     headers["If-Modified-Since"] = last_modified[0]
+
                 async with session.get(NOTIFICATION_URL, headers=headers, params=params) as response:
                     if response.status == 200:
                         if 'Last-Modified' in response.headers:
@@ -100,4 +113,4 @@ async def polling_loop():
 
 
 if __name__ == '__main__':
-    asyncio.run(polling_loop())
+    asyncio.run(polling_loop())

pr_agent/servers/gitlab_webhook.py

@@ -7,7 +7,7 @@ from fastapi.responses import JSONResponse
 from starlette.background import BackgroundTasks
 
 from pr_agent.agent.pr_agent import PRAgent
-from pr_agent.config_loader import settings
+from pr_agent.config_loader import get_settings
 
 app = FastAPI()
 router = APIRouter()
@@ -29,13 +29,13 @@ async def gitlab_webhook(background_tasks: BackgroundTasks, request: Request):
     return JSONResponse(status_code=status.HTTP_200_OK, content=jsonable_encoder({"message": "success"}))
 
 def start():
-    gitlab_url = settings.get("GITLAB.URL", None)
+    gitlab_url = get_settings().get("GITLAB.URL", None)
     if not gitlab_url:
         raise ValueError("GITLAB.URL is not set")
-    gitlab_token = settings.get("GITLAB.PERSONAL_ACCESS_TOKEN", None)
+    gitlab_token = get_settings().get("GITLAB.PERSONAL_ACCESS_TOKEN", None)
     if not gitlab_token:
         raise ValueError("GITLAB.PERSONAL_ACCESS_TOKEN is not set")
-    settings.config.git_provider = "gitlab"
+    get_settings().config.git_provider = "gitlab"
 
     app = FastAPI()
     app.include_router(router)

pr_agent/servers/help.py

@@ -1,9 +1,10 @@
 commands_text = "> **/review [-i]**: Request a review of your Pull Request. For an incremental review, which only " \
                 "considers changes since the last review, include the '-i' option.\n" \
                 "> **/describe**: Modify the PR title and description based on the contents of the PR.\n" \
-                "> **/improve**: Suggest improvements to the code in the PR. " \
-                "These will be provided as pull request comments, ready to commit.\n" \
-                "> **/ask \\<QUESTION\\>**: Pose a question about the PR.\n"
+                "> **/improve**: Suggest improvements to the code in the PR. \n" \
+                "> **/ask \\<QUESTION\\>**: Pose a question about the PR.\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: ...\" " \
 
 
 def bot_help_text(user: str):

pr_agent/servers/utils.py

@@ -21,3 +21,7 @@ def verify_signature(payload_body, secret_token, signature_header):
     if not hmac.compare_digest(expected_signature, signature_header):
         raise HTTPException(status_code=403, detail="Request signatures didn't match!")
 
+
+class RateLimitExceeded(Exception):
+    """Raised when the git provider API rate limit has been exceeded."""
+    pass

pr_agent/settings/configuration.toml

@@ -1,13 +1,13 @@
 [config]
 model="gpt-4"
-fallback-models=["gpt-3.5-turbo-16k", "gpt-3.5-turbo"]
+fallback_models=["gpt-3.5-turbo-16k"]
 git_provider="github"
 publish_output=true
 publish_output_progress=true
 verbosity_level=0 # 0,1,2
 use_extra_bad_extensions=false
 
-[pr_reviewer]
+[pr_reviewer] # /review #
 require_focused_review=true
 require_score_review=false
 require_tests_review=true
@@ -15,18 +15,26 @@ require_security_review=true
 num_code_suggestions=0
 inline_code_comments = true
 ask_and_reflect=false
+extra_instructions = ""
 
-[pr_description]
+[pr_description] # /describe #
 publish_description_as_comment=false
+extra_instructions = ""
 
-[pr_questions]
+[pr_questions] # /ask #
 
-[pr_code_suggestions]
+[pr_code_suggestions] # /improve #
 num_code_suggestions=4
+extra_instructions = ""
+
+[pr_update_changelog] # /update_changelog #
+push_changelog_changes=false
+extra_instructions = ""
 
 [github]
 # The type of deployment to create. Valid values are 'app' or 'user'.
 deployment_type = "user"
+ratelimit_retries = 5
 
 [gitlab]
 # URL to the gitlab service
@@ -40,3 +48,8 @@ magic_word = "AutoReview"
 
 # Polling interval
 polling_interval_seconds = 30
+
+[local]
+# LocalGitProvider settings - uncomment to use paths other than default
+# description_path= "path/to/description.md"
+# review_path= "path/to/review.md"

pr_agent/settings/pr_code_suggestions_prompts.toml

@@ -9,6 +9,12 @@ Your task is to provide meaningfull non-trivial code suggestions to improve the
 - Make sure not to provide suggestions repeating modifications already implemented in the new PR code (the '+' lines).
 - Don't output line numbers in the 'improved code' snippets.
 
+{%- if extra_instructions %}
+
+Extra instructions from the user:
+{{ extra_instructions }}
+{% endif %}
+
 You must use the following JSON schema to format your answer:
 ```json
 {

pr_agent/settings/pr_description_prompts.toml

@@ -3,6 +3,12 @@ system="""You are CodiumAI-PR-Reviewer, a language model designed to review git
 Your task is to provide full description of the PR content.
 - Make sure not to focus the new PR code (the '+' lines).
 
+{%- if extra_instructions %}
+
+Extra instructions from the user:
+{{ extra_instructions }}
+{% endif %}
+
 You must use the following JSON schema to format your answer:
 ```json
 {
@@ -30,8 +36,14 @@ Don't repeat the prompt in the answer, and avoid outputting the 'type' and 'desc
 user="""PR Info:
 Branch: '{{branch}}'
 {%- if language %}
+
 Main language: {{language}}
 {%- endif %}
+{%- if commit_messages_str %}
+
+Commit messages:
+{{commit_messages_str}}
+{%- endif %}
 
 
 The PR Git Diff:

pr_agent/settings/pr_reviewer_prompts.toml

@@ -8,6 +8,12 @@ Your task is to provide constructive and concise feedback for the PR, and also p
 - Make sure not to provide suggestions repeating modifications already implemented in the new PR code (the '+' lines).
 {%- endif %}
 
+{%- if extra_instructions %}
+
+Extra instructions from the user:
+{{ extra_instructions }}
+{% endif %}
+
 You must use the following JSON schema to format your answer:
 ```json
 {

pr_agent/settings/pr_update_changelog_prompts.toml

@@ -0,0 +1,40 @@
+[pr_update_changelog_prompt]
+system="""You are a language model called CodiumAI-PR-Changlog-summarizer.
+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.
+- Be general, and avoid specific details, files, etc. The output should be minimal, no more than 3-4 short lines. Ignore non-relevant subsections.
+
+{%- if extra_instructions %}
+
+Extra instructions from the user:
+{{ extra_instructions }}
+{%- endif %}
+"""
+
+user="""PR Info:
+Title: '{{title}}'
+Branch: '{{branch}}'
+Description: '{{description}}'
+{%- if language %}
+Main language: {{language}}
+{%- endif %}
+
+
+The PR Diff:
+```
+{{diff}}
+```
+
+Current date:
+```
+{{today}}
+```
+
+The current CHANGELOG.md:
+```
+{{ changelog_file_str }}
+```
+
+Response:
+"""

pr_agent/tools/pr_code_suggestions.py

@@ -9,18 +9,19 @@ 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 try_fix_json
-from pr_agent.config_loader import settings
+from pr_agent.config_loader import get_settings
 from pr_agent.git_providers import BitbucketProvider, get_git_provider
 from pr_agent.git_providers.git_provider import get_main_pr_language
 
 
 class PRCodeSuggestions:
-    def __init__(self, pr_url: str, cli_mode=False):
+    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
@@ -31,23 +32,24 @@ class PRCodeSuggestions:
             "description": self.git_provider.get_pr_description(),
             "language": self.main_language,
             "diff": "",  # empty diff for initial calculation
-            'num_code_suggestions': settings.pr_code_suggestions.num_code_suggestions,
+            "num_code_suggestions": get_settings().pr_code_suggestions.num_code_suggestions,
+            "extra_instructions": get_settings().pr_code_suggestions.extra_instructions,
         }
         self.token_handler = TokenHandler(self.git_provider.pr,
                                           self.vars,
-                                          settings.pr_code_suggestions_prompt.system,
-                                          settings.pr_code_suggestions_prompt.user)
+                                          get_settings().pr_code_suggestions_prompt.system,
+                                          get_settings().pr_code_suggestions_prompt.user)
 
-    async def suggest(self):
+    async def run(self):
         assert type(self.git_provider) != BitbucketProvider, "Bitbucket is not supported for now"
 
         logging.info('Generating code suggestions for PR...')
-        if settings.config.publish_output:
+        if get_settings().config.publish_output:
             self.git_provider.publish_comment("Preparing review...", is_temporary=True)
         await retry_with_fallback_models(self._prepare_prediction)
         logging.info('Preparing PR review...')
         data = self._prepare_pr_code_suggestions()
-        if settings.config.publish_output:
+        if get_settings().config.publish_output:
             logging.info('Pushing PR review...')
             self.git_provider.remove_initial_comment()
             logging.info('Pushing inline code comments...')
@@ -68,9 +70,9 @@ class PRCodeSuggestions:
         variables = copy.deepcopy(self.vars)
         variables["diff"] = self.patches_diff  # update diff
         environment = Environment(undefined=StrictUndefined)
-        system_prompt = environment.from_string(settings.pr_code_suggestions_prompt.system).render(variables)
-        user_prompt = environment.from_string(settings.pr_code_suggestions_prompt.user).render(variables)
-        if settings.config.verbosity_level >= 2:
+        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}")
         response, finish_reason = await self.ai_handler.chat_completion(model=model, temperature=0.2,
@@ -83,7 +85,7 @@ class PRCodeSuggestions:
         try:
             data = json.loads(review)
         except json.decoder.JSONDecodeError:
-            if settings.config.verbosity_level >= 2:
+            if get_settings().config.verbosity_level >= 2:
                 logging.info(f"Could not parse json response: {review}")
             data = try_fix_json(review, code_suggestions=True)
         return data
@@ -91,22 +93,28 @@ class PRCodeSuggestions:
     def push_inline_code_suggestions(self, data):
         code_suggestions = []
         for d in data['Code suggestions']:
-            if settings.config.verbosity_level >= 2:
-                logging.info(f"suggestion: {d}")
-            relevant_file = d['relevant file'].strip()
-            relevant_lines_str = d['relevant lines'].strip()
-            relevant_lines_start = int(relevant_lines_str.split('-')[0])  # absolute position
-            relevant_lines_end = int(relevant_lines_str.split('-')[-1])
-            content = d['suggestion content']
-            new_code_snippet = d['improved code']
+            try:
+                if get_settings().config.verbosity_level >= 2:
+                    logging.info(f"suggestion: {d}")
+                relevant_file = d['relevant file'].strip()
+                relevant_lines_str = d['relevant lines'].strip()
+                if ',' in relevant_lines_str:  # handling 'relevant lines': '181, 190' or '178-184, 188-194'
+                    relevant_lines_str = relevant_lines_str.split(',')[0]
+                relevant_lines_start = int(relevant_lines_str.split('-')[0])  # absolute position
+                relevant_lines_end = int(relevant_lines_str.split('-')[-1])
+                content = d['suggestion content']
+                new_code_snippet = d['improved code']
 
-            if new_code_snippet:
-                new_code_snippet = self.dedent_code(relevant_file, relevant_lines_start, new_code_snippet)
+                if new_code_snippet:
+                    new_code_snippet = self.dedent_code(relevant_file, relevant_lines_start, new_code_snippet)
 
-            body = f"**Suggestion:** {content}\n```suggestion\n" + new_code_snippet + "\n```"
-            code_suggestions.append({'body': body,'relevant_file': relevant_file,
-                                     'relevant_lines_start': relevant_lines_start,
-                                     'relevant_lines_end': relevant_lines_end})
+                body = f"**Suggestion:** {content}\n```suggestion\n" + new_code_snippet + "\n```"
+                code_suggestions.append({'body': body, 'relevant_file': relevant_file,
+                                         'relevant_lines_start': relevant_lines_start,
+                                         'relevant_lines_end': relevant_lines_end})
+            except Exception:
+                if get_settings().config.verbosity_level >= 2:
+                    logging.info(f"Could not parse suggestion: {d}")
 
         self.git_provider.publish_code_suggestions(code_suggestions)
 
@@ -127,7 +135,8 @@ class PRCodeSuggestions:
                 if delta_spaces > 0:
                     new_code_snippet = textwrap.indent(new_code_snippet, delta_spaces * " ").rstrip('\n')
         except Exception as e:
-            if settings.config.verbosity_level >= 2:
+            if get_settings().config.verbosity_level >= 2:
                 logging.info(f"Could not dedent code snippet for file {relevant_file}, error: {e}")
 
         return new_code_snippet
+

pr_agent/tools/pr_description.py

@@ -1,32 +1,34 @@
 import copy
 import json
 import logging
-from typing import Tuple, List
+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.config_loader import settings
+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
 
 
 class PRDescription:
-    def __init__(self, pr_url: str):
+    def __init__(self, pr_url: str, args: list = None):
         """
-        Initialize the PRDescription object with the necessary attributes and objects for generating a PR description using an AI model.
+        Initialize the PRDescription object with the necessary attributes and objects for generating a PR description
+        using an AI model.
         Args:
             pr_url (str): The URL of the pull request.
+            args (list, optional): List of arguments passed to the PRDescription 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()
         )
-    
+        commit_messages_str = self.git_provider.get_commit_messages()
+
         # Initialize the AI handler
         self.ai_handler = AiHandler()
     
@@ -37,26 +39,28 @@ class PRDescription:
             "description": self.git_provider.get_pr_description(),
             "language": self.main_pr_language,
             "diff": "",  # empty diff for initial calculation
+            "extra_instructions": get_settings().pr_description.extra_instructions,
+            "commit_messages_str": commit_messages_str
         }
     
         # Initialize the token handler
         self.token_handler = TokenHandler(
             self.git_provider.pr,
             self.vars,
-            settings.pr_description_prompt.system,
-            settings.pr_description_prompt.user,
+            get_settings().pr_description_prompt.system,
+            get_settings().pr_description_prompt.user,
         )
     
         # Initialize patches_diff and prediction attributes
         self.patches_diff = None
         self.prediction = None
 
-    async def describe(self):
+    async def run(self):
         """
         Generates a PR description using an AI model and publishes it to the PR.
         """
         logging.info('Generating a PR description...')
-        if settings.config.publish_output:
+        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)
@@ -64,9 +68,9 @@ class PRDescription:
         logging.info('Preparing answer...')
         pr_title, pr_body, pr_types, markdown_text = self._prepare_pr_answer()
         
-        if settings.config.publish_output:
+        if get_settings().config.publish_output:
             logging.info('Pushing answer...')
-            if settings.pr_description.publish_description_as_comment:
+            if get_settings().pr_description.publish_description_as_comment:
                 self.git_provider.publish_comment(markdown_text)
             else:
                 self.git_provider.publish_description(pr_title, pr_body)
@@ -112,10 +116,10 @@ class PRDescription:
         variables["diff"] = self.patches_diff  # update diff
 
         environment = Environment(undefined=StrictUndefined)
-        system_prompt = environment.from_string(settings.pr_description_prompt.system).render(variables)
-        user_prompt = environment.from_string(settings.pr_description_prompt.user).render(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 settings.config.verbosity_level >= 2:
+        if get_settings().config.verbosity_level >= 2:
             logging.info(f"\nSystem prompt:\n{system_prompt}")
             logging.info(f"\nUser prompt:\n{user_prompt}")
 
@@ -160,13 +164,13 @@ class PRDescription:
         # Iterate over the remaining dictionary items and append the key and value to 'pr_body' in a markdown format,
         # except for the items containing the word 'walkthrough'
         for key, value in data.items():
-            pr_body += f"{key}:\n"
+            pr_body += f"## {key}:\n"
             if 'walkthrough' in key.lower():
                 pr_body += f"{value}\n"
             else:
-                pr_body += f"**{value}**\n\n___\n"
+                pr_body += f"{value}\n\n___\n"
 
-        if settings.config.verbosity_level >= 2:
+        if get_settings().config.verbosity_level >= 2:
             logging.info(f"title:\n{title}\n{pr_body}")
 
         return title, pr_body, pr_types, markdown_text

pr_agent/tools/pr_information_from_user.py

@@ -6,15 +6,13 @@ 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.config_loader import settings
+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
 
 
-
-
 class PRInformationFromUser:
-    def __init__(self, pr_url: str):
+    def __init__(self, pr_url: str, args: list = None):
         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()
@@ -29,19 +27,19 @@ class PRInformationFromUser:
         }
         self.token_handler = TokenHandler(self.git_provider.pr,
                                           self.vars,
-                                          settings.pr_information_from_user_prompt.system,
-                                          settings.pr_information_from_user_prompt.user)
+                                          get_settings().pr_information_from_user_prompt.system,
+                                          get_settings().pr_information_from_user_prompt.user)
         self.patches_diff = None
         self.prediction = None
 
-    async def generate_questions(self):
+    async def run(self):
         logging.info('Generating question to the user...')
-        if settings.config.publish_output:
+        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...')
         pr_comment = self._prepare_pr_answer()
-        if settings.config.publish_output:
+        if get_settings().config.publish_output:
             logging.info('Pushing questions...')
             self.git_provider.publish_comment(pr_comment)
             self.git_provider.remove_initial_comment()
@@ -57,9 +55,9 @@ class PRInformationFromUser:
         variables = copy.deepcopy(self.vars)
         variables["diff"] = self.patches_diff  # update diff
         environment = Environment(undefined=StrictUndefined)
-        system_prompt = environment.from_string(settings.pr_information_from_user_prompt.system).render(variables)
-        user_prompt = environment.from_string(settings.pr_information_from_user_prompt.user).render(variables)
-        if settings.config.verbosity_level >= 2:
+        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}")
         response, finish_reason = await self.ai_handler.chat_completion(model=model, temperature=0.2,
@@ -68,7 +66,7 @@ class PRInformationFromUser:
 
     def _prepare_pr_answer(self) -> str:
         model_output = self.prediction.strip()
-        if settings.config.verbosity_level >= 2:
+        if get_settings().config.verbosity_level >= 2:
             logging.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"

pr_agent/tools/pr_questions.py

@@ -6,7 +6,7 @@ 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.config_loader import settings
+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
 
@@ -30,8 +30,8 @@ class PRQuestions:
         }
         self.token_handler = TokenHandler(self.git_provider.pr,
                                           self.vars,
-                                          settings.pr_questions_prompt.system,
-                                          settings.pr_questions_prompt.user)
+                                          get_settings().pr_questions_prompt.system,
+                                          get_settings().pr_questions_prompt.user)
         self.patches_diff = None
         self.prediction = None
 
@@ -42,14 +42,14 @@ class PRQuestions:
             question_str = ""
         return question_str
 
-    async def answer(self):
+    async def run(self):
         logging.info('Answering a PR question...')
-        if settings.config.publish_output:
+        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...')
         pr_comment = self._prepare_pr_answer()
-        if settings.config.publish_output:
+        if get_settings().config.publish_output:
             logging.info('Pushing answer...')
             self.git_provider.publish_comment(pr_comment)
             self.git_provider.remove_initial_comment()
@@ -65,9 +65,9 @@ class PRQuestions:
         variables = copy.deepcopy(self.vars)
         variables["diff"] = self.patches_diff  # update diff
         environment = Environment(undefined=StrictUndefined)
-        system_prompt = environment.from_string(settings.pr_questions_prompt.system).render(variables)
-        user_prompt = environment.from_string(settings.pr_questions_prompt.user).render(variables)
-        if settings.config.verbosity_level >= 2:
+        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}")
         response, finish_reason = await self.ai_handler.chat_completion(model=model, temperature=0.2,
@@ -77,6 +77,6 @@ class PRQuestions:
     def _prepare_pr_answer(self) -> str:
         answer_str = f"Question: {self.question_str}\n\n"
         answer_str += f"Answer:\n{self.prediction.strip()}\n\n"
-        if settings.config.verbosity_level >= 2:
+        if get_settings().config.verbosity_level >= 2:
             logging.info(f"answer_str:\n{answer_str}")
         return answer_str

pr_agent/tools/pr_reviewer.py

@@ -2,6 +2,7 @@ import copy
 import json
 import logging
 from collections import OrderedDict
+from typing import List, Tuple
 
 from jinja2 import Environment, StrictUndefined
 
@@ -9,15 +10,26 @@ 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 convert_to_markdown, try_fix_json
-from pr_agent.config_loader import settings
+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, IncrementalPR
+from pr_agent.git_providers.git_provider import IncrementalPR, get_main_pr_language
 from pr_agent.servers.help import actions_help_text, bot_help_text
 
 
 class PRReviewer:
-    def __init__(self, pr_url: str, cli_mode=False, is_answer: bool = False, args=None):
-        self.parse_args(args)
+    """
+    The PRReviewer class is responsible for reviewing a pull request and generating feedback using an AI model.
+    """
+    def __init__(self, pr_url: str, is_answer: bool = False, args: list = None):
+        """
+        Initialize the PRReviewer object with the necessary attributes and objects to review a pull request.
+
+        Args:
+            pr_url (str): The URL of the pull request to be reviewed.
+            is_answer (bool, optional): Indicates whether the review is being done in answer mode. Defaults to False.
+            args (list, optional): List of arguments passed to the PRReviewer class. Defaults to None.
+        """
+        self.parse_args(args) # -i command
 
         self.git_provider = get_git_provider()(pr_url, incremental=self.incremental)
         self.main_language = get_main_pr_language(
@@ -25,34 +37,47 @@ class PRReviewer:
         )
         self.pr_url = pr_url
         self.is_answer = is_answer
+
         if self.is_answer and not self.git_provider.is_supported("get_issue_comments"):
-            raise Exception(f"Answer mode is not supported for {settings.config.git_provider} for now")
-        answer_str, question_str = self._get_user_answers()
+            raise Exception(f"Answer mode is not supported for {get_settings().config.git_provider} for now")
         self.ai_handler = AiHandler()
         self.patches_diff = None
         self.prediction = None
-        self.cli_mode = cli_mode
+
+        answer_str, question_str = self._get_user_answers()
         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
-            "require_score": settings.pr_reviewer.require_score_review,
-            "require_tests": settings.pr_reviewer.require_tests_review,
-            "require_security": settings.pr_reviewer.require_security_review,
-            "require_focused": settings.pr_reviewer.require_focused_review,
-            'num_code_suggestions': settings.pr_reviewer.num_code_suggestions,
-            #
+            "require_score": get_settings().pr_reviewer.require_score_review,
+            "require_tests": get_settings().pr_reviewer.require_tests_review,
+            "require_security": get_settings().pr_reviewer.require_security_review,
+            "require_focused": get_settings().pr_reviewer.require_focused_review,
+            'num_code_suggestions': get_settings().pr_reviewer.num_code_suggestions,
             'question_str': question_str,
             'answer_str': answer_str,
+            "extra_instructions": get_settings().pr_reviewer.extra_instructions,
         }
-        self.token_handler = TokenHandler(self.git_provider.pr,
-                                          self.vars,
-                                          settings.pr_review_prompt.system,
-                                          settings.pr_review_prompt.user)
 
-    def parse_args(self, args):
+        self.token_handler = TokenHandler(
+            self.git_provider.pr,
+            self.vars,
+            get_settings().pr_review_prompt.system,
+            get_settings().pr_review_prompt.user
+        )
+
+    def parse_args(self, args: List[str]) -> None:
+        """
+        Parse the arguments passed to the PRReviewer class and set the 'incremental' attribute accordingly.
+
+        Args:
+            args: A list of arguments passed to the PRReviewer class.
+
+        Returns:
+            None
+        """
         is_incremental = False
         if args and len(args) >= 1:
             arg = args[0]
@@ -60,60 +85,95 @@ class PRReviewer:
                 is_incremental = True
         self.incremental = IncrementalPR(is_incremental)
 
-    async def review(self):
+    async def run(self) -> None:
+        """
+        Review the pull request and generate feedback.
+        """
         logging.info('Reviewing PR...')
-        if settings.config.publish_output:
+    
+        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...')
         pr_comment = self._prepare_pr_review()
-        if settings.config.publish_output:
+    
+        if get_settings().config.publish_output:
             logging.info('Pushing PR review...')
             self.git_provider.publish_comment(pr_comment)
             self.git_provider.remove_initial_comment()
-            if settings.pr_reviewer.inline_code_comments:
+        
+            if get_settings().pr_reviewer.inline_code_comments:
                 logging.info('Pushing inline code comments...')
                 self._publish_inline_code_comments()
-        return ""
 
-    async def _prepare_prediction(self, model: str):
+    async def _prepare_prediction(self, model: str) -> None:
+        """
+        Prepare the AI prediction for the pull request review.
+
+        Args:
+            model: A string representing the AI model to be used for the prediction.
+
+        Returns:
+            None
+        """
         logging.info('Getting PR diff...')
         self.patches_diff = get_pr_diff(self.git_provider, self.token_handler, model)
         logging.info('Getting AI prediction...')
         self.prediction = await self._get_prediction(model)
 
-    async def _get_prediction(self, model: str):
+    async def _get_prediction(self, model: str) -> str:
+        """
+        Generate an AI prediction for the pull request review.
+
+        Args:
+            model: A string representing the AI model to be used for the prediction.
+
+        Returns:
+            A string representing the AI prediction for the pull request review.
+        """
         variables = copy.deepcopy(self.vars)
         variables["diff"] = self.patches_diff  # update diff
+
         environment = Environment(undefined=StrictUndefined)
-        system_prompt = environment.from_string(settings.pr_review_prompt.system).render(variables)
-        user_prompt = environment.from_string(settings.pr_review_prompt.user).render(variables)
-        if settings.config.verbosity_level >= 2:
+        system_prompt = environment.from_string(get_settings().pr_review_prompt.system).render(variables)
+        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}")
-        response, finish_reason = await self.ai_handler.chat_completion(model=model, temperature=0.2,
-                                                                        system=system_prompt, user=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_review(self) -> str:
+        """
+        Prepare the PR review by processing the AI prediction and generating a markdown-formatted text that summarizes
+        the feedback.
+        """
         review = self.prediction.strip()
+    
         try:
             data = json.loads(review)
         except json.decoder.JSONDecodeError:
             data = try_fix_json(review)
 
-        # reordering for nicer display
-        if 'PR Feedback' in data:
-            if 'Security concerns' in data['PR Feedback']:
-                val = data['PR Feedback']['Security concerns']
-                del data['PR Feedback']['Security concerns']
-                data['PR Analysis']['Security concerns'] = val
+        # Move 'Security concerns' key to 'PR Analysis' section for better display
+        if 'PR Feedback' in data and 'Security concerns' in data['PR Feedback']:
+            val = data['PR Feedback']['Security concerns']
+            del data['PR Feedback']['Security concerns']
+            data['PR Analysis']['Security concerns'] = val
 
-        if settings.config.git_provider != 'bitbucket' and \
-                settings.pr_reviewer.inline_code_comments and \
-                'Code suggestions' in data['PR Feedback']:
-            # keeping only code suggestions that can't be submitted as inline comments
+        # Filter out code suggestions that can be submitted as inline comments
+        if get_settings().config.git_provider != 'bitbucket' and get_settings().pr_reviewer.inline_code_comments \
+                and 'Code suggestions' in data['PR Feedback']:
             data['PR Feedback']['Code suggestions'] = [
                 d for d in data['PR Feedback']['Code suggestions']
                 if any(key not in d for key in ('relevant file', 'relevant line in file', 'suggestion content'))
@@ -121,9 +181,10 @@ class PRReviewer:
             if not data['PR Feedback']['Code suggestions']:
                 del data['PR Feedback']['Code suggestions']
 
+        # Add incremental review section
         if self.incremental.is_incremental:
-            # Rename title when incremental review - Add to the beginning of the dict
-            last_commit_url = f"{self.git_provider.get_pr_url()}/commits/{self.git_provider.incremental.first_new_commit_sha}"
+            last_commit_url = f"{self.git_provider.get_pr_url()}/commits/" \
+                              f"{self.git_provider.incremental.first_new_commit_sha}"
             data = OrderedDict(data)
             data.update({'Incremental PR Review': {
                 "⏮️ Review for commits since previous PR-Agent review": f"Starting from commit {last_commit_url}"}})
@@ -132,19 +193,25 @@ class PRReviewer:
         markdown_text = convert_to_markdown(data)
         user = self.git_provider.get_user_id()
 
-        if not self.cli_mode:
+        # 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:
                 markdown_text += bot_help_text(user)
             else:
                 markdown_text += actions_help_text
 
-        if settings.config.verbosity_level >= 2:
+        # Log markdown response if verbosity level is high
+        if get_settings().config.verbosity_level >= 2:
             logging.info(f"Markdown response:\n{markdown_text}")
+    
         return markdown_text
 
-    def _publish_inline_code_comments(self):
-        if settings.pr_reviewer.num_code_suggestions == 0:
+    def _publish_inline_code_comments(self) -> None:
+        """
+        Publishes inline comments on a pull request with code suggestions generated by the AI model.
+        """
+        if get_settings().pr_reviewer.num_code_suggestions == 0:
             return
 
         review = self.prediction.strip()
@@ -153,11 +220,11 @@ class PRReviewer:
         except json.decoder.JSONDecodeError:
             data = try_fix_json(review)
 
-        comments = []
-        for d in data['PR Feedback']['Code suggestions']:
-            relevant_file = d.get('relevant file', '').strip()
-            relevant_line_in_file = d.get('relevant line in file', '').strip()
-            content = d.get('suggestion content', '')
+        comments: List[str] = []
+        for suggestion in data.get('PR Feedback', {}).get('Code suggestions', []):
+            relevant_file = suggestion.get('relevant file', '').strip()
+            relevant_line_in_file = suggestion.get('relevant line in file', '').strip()
+            content = suggestion.get('suggestion content', '')
             if not relevant_file or not relevant_line_in_file or not content:
                 logging.info("Skipping inline comment with missing file/line/content")
                 continue
@@ -172,15 +239,26 @@ class PRReviewer:
         if comments:
             self.git_provider.publish_inline_comments(comments)
 
-    def _get_user_answers(self):
-        answer_str = question_str = ""
+    def _get_user_answers(self) -> Tuple[str, str]:
+        """
+        Retrieves the question and answer strings from the discussion messages related to a pull request.
+
+        Returns:
+            A tuple containing the question and answer strings.
+        """
+        question_str = ""
+        answer_str = ""
+
         if self.is_answer:
             discussion_messages = self.git_provider.get_issue_comments()
+
             for message in discussion_messages.reversed:
                 if "Questions to better understand the PR:" in message.body:
                     question_str = message.body
                 elif '/answer' in message.body:
                     answer_str = message.body
+
                 if answer_str and question_str:
                     break
+
         return question_str, answer_str

pr_agent/tools/pr_update_changelog.py

@@ -0,0 +1,159 @@
+import copy
+import logging
+from datetime import date
+from time import sleep
+from typing import 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.config_loader import get_settings
+from pr_agent.git_providers import GithubProvider, get_git_provider
+from pr_agent.git_providers.git_provider import get_main_pr_language
+
+CHANGELOG_LINES = 50
+
+
+class PRUpdateChangelog:
+    def __init__(self, pr_url: str, cli_mode=False, args=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.commit_changelog = get_settings().pr_update_changelog.push_changelog_changes
+        self._get_changlog_file()  # self.changelog_file_str
+        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
+            "changelog_file_str": self.changelog_file_str,
+            "today": date.today(),
+            "extra_instructions": get_settings().pr_update_changelog.extra_instructions,
+        }
+        self.token_handler = TokenHandler(self.git_provider.pr,
+                                          self.vars,
+                                          get_settings().pr_update_changelog_prompt.system,
+                                          get_settings().pr_update_changelog_prompt.user)
+
+    async def run(self):
+        assert type(self.git_provider) == GithubProvider, "Currently only Github is supported"
+
+        logging.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...')
+        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...')
+            if self.commit_changelog:
+                logging.info('Pushing PR changelog updates to repo...')
+                self._push_changelog_update(new_file_content, answer)
+            else:
+                logging.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...')
+        self.patches_diff = get_pr_diff(self.git_provider, self.token_handler, model)
+        logging.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_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}")
+        response, finish_reason = await self.ai_handler.chat_completion(model=model, temperature=0.2,
+                                                                        system=system_prompt, user=user_prompt)
+
+        return response
+
+    def _prepare_changelog_update(self) -> Tuple[str, str]:
+        answer = self.prediction.strip().strip("```").strip()  # noqa B005
+        if hasattr(self, "changelog_file"):
+            existing_content = self.changelog_file.decoded_content.decode()
+        else:
+            existing_content = ""
+        if existing_content:
+            new_file_content = answer + "\n\n" + self.changelog_file.decoded_content.decode()
+        else:
+            new_file_content = answer
+
+        if not self.commit_changelog:
+            answer += "\n\n\n>to commit the new content to the CHANGELOG.md file, please type:" \
+                      "\n>'/update_changelog --pr_update_changelog.push_changelog_changes=true'\n"
+
+        if get_settings().config.verbosity_level >= 2:
+            logging.info(f"answer:\n{answer}")
+
+        return new_file_content, answer
+
+    def _push_changelog_update(self, new_file_content, answer):
+        self.git_provider.repo_obj.update_file(path=self.changelog_file.path,
+                                               message="Update CHANGELOG.md",
+                                               content=new_file_content,
+                                               sha=self.changelog_file.sha,
+                                               branch=self.git_provider.get_pr_branch())
+        d = dict(body="CHANGELOG.md update",
+                 path=self.changelog_file.path,
+                 line=max(2, len(answer.splitlines())),
+                 start_line=1)
+
+        sleep(5)  # wait for the file to be updated
+        last_commit_id = list(self.git_provider.pr.get_commits())[-1]
+        try:
+            self.git_provider.pr.create_review(commit=last_commit_id, comments=[d])
+        except Exception:
+            # we can't create a review for some reason, let's just publish a comment
+            self.git_provider.publish_comment(f"**Changelog updates:**\n\n{answer}")
+
+
+    def _get_default_changelog(self):
+        example_changelog = \
+"""
+Example:
+## <current_date>
+
+### Added
+...
+### Changed
+...
+### Fixed
+...
+"""
+        return example_changelog
+
+    def _get_changlog_file(self):
+        try:
+            self.changelog_file = self.git_provider.repo_obj.get_contents("CHANGELOG.md",
+                                                                          ref=self.git_provider.get_pr_branch())
+            changelog_file_lines = self.changelog_file.decoded_content.decode().splitlines()
+            changelog_file_lines = changelog_file_lines[:CHANGELOG_LINES]
+            self.changelog_file_str = "\n".join(changelog_file_lines)
+        except Exception:
+            self.changelog_file_str = ""
+            if self.commit_changelog:
+                logging.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="",
+                                                                             branch=self.git_provider.get_pr_branch())
+                self.changelog_file = changelog_file['content']
+
+        if not self.changelog_file_str:
+            self.changelog_file_str = self._get_default_changelog()

pyproject.toml

@@ -1,3 +1,64 @@
+[build-system]
+requires = ["setuptools>=61.0"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "pr_agent"
+version = "0.0.1"
+
+authors = [
+  {name = "Itamar Friedman", email = "itamar.f@codium.ai"},
+]
+maintainers = [
+  {name = "Ori Kotek", email = "ori.k@codium.ai"},
+  {name = "Tal Ridnik", email = "tal.r@codium.ai"},
+  {name = "Hussam Lawen", email = "hussam.l@codium.ai"},
+  {name = "Sagi Medina", email = "sagi.m@codium.ai"}
+]
+description = "CodiumAI PR-Agent is an open-source tool to automatically analyze a pull request and provide several types of feedback"
+readme = "README.md"
+requires-python = ">=3.9"
+keywords = ["ai", "tool", "developer", "review", "agent"]
+license = {file = "LICENSE", name = "Apache 2.0 License"}
+classifiers = [
+  "Development Status :: 3 - Alpha",
+  "Intended Audience :: Developers",
+  "Operating System :: Independent",
+  "Programming Language :: Python :: 3",
+]
+
+dependencies = [
+  "dynaconf==3.1.12",
+  "fastapi==0.99.0",
+  "PyGithub==1.59.*",
+  "retry==0.9.2",
+  "openai==0.27.8",
+  "Jinja2==3.1.2",
+  "tiktoken==0.4.0",
+  "uvicorn==0.22.0",
+  "python-gitlab==3.15.0",
+  "pytest~=7.4.0",
+  "aiohttp~=3.8.4",
+  "atlassian-python-api==3.39.0",
+  "GitPython~=3.1.32",
+  "starlette-context==0.3.6"
+]
+
+[project.urls]
+"Homepage" = "https://github.com/Codium-ai/pr-agent"
+
+[tool.setuptools]
+include-package-data = false
+license-files = ["LICENSE"]
+
+[tool.setuptools.packages.find]
+where = ["."]
+include = ["pr_agent"]
+
+[project.scripts]
+pr-agent = "pr_agent.cli:run"
+
+
 [tool.ruff]
 
 line-length = 120

requirements.txt

@@ -1,12 +1 @@
-dynaconf==3.1.12
-fastapi==0.99.0
-PyGithub==1.59.*
-retry==0.9.2
-openai==0.27.8
-Jinja2==3.1.2
-tiktoken==0.4.0
-uvicorn==0.22.0
-python-gitlab==3.15.0
-pytest~=7.4.0
-aiohttp~=3.8.4
-atlassian-python-api==3.39.0
+-e .

setup.py

@@ -0,0 +1,5 @@
+# for compatibility with legacy tools
+# see: https://setuptools.pypa.io/en/latest/userguide/pyproject_config.html
+from setuptools import setup
+
+setup()

tests/unittest/test_handle_patch_deletions.py

@@ -2,7 +2,7 @@
 import logging
 
 from pr_agent.algo.git_patch_processing import handle_patch_deletions
-from pr_agent.config_loader import settings
+from pr_agent.config_loader import get_settings
 
 """
 Code Analysis
@@ -49,7 +49,7 @@ class TestHandlePatchDeletions:
         original_file_content_str = 'foo\nbar\n'
         new_file_content_str = ''
         file_name = 'file.py'
-        settings.config.verbosity_level = 1
+        get_settings().config.verbosity_level = 1
 
         with caplog.at_level(logging.INFO):
             handle_patch_deletions(patch, original_file_content_str, new_file_content_str, file_name)