Merge branch 'main' into case-update

.github/workflows/review.yaml

@@ -0,0 +1,16 @@
+on:
+  pull_request:
+  issue_comment:
+jobs:
+  pr_agent_job:
+    runs-on: ubuntu-latest
+    name: Run pr agent on every pull request
+    steps:
+      - name: PR Agent action step
+        id: pragent
+        uses: Codium-ai/pr-agent@main
+        env:
+          OPENAI_KEY: ${{ secrets.OPENAI_KEY }}
+          OPENAI_ORG: ${{ secrets.OPENAI_ORG }} # optional
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+

CONFIGURATION.md

@@ -0,0 +1,18 @@
+## 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
+
+##### PR Reviewer:
+
+You can enable/disable the different PR Reviewer abilities with the following flags (`pr_reviewer` section):
+```
+require_focused_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

@@ -0,0 +1,10 @@
+FROM python:3.10 as base
+
+WORKDIR /app
+ADD requirements.txt .
+RUN pip install -r requirements.txt && rm requirements.txt
+ENV PYTHONPATH=/app
+ADD pr_agent pr_agent
+ADD github_action/entrypoint.sh /
+RUN chmod +x /entrypoint.sh
+ENTRYPOINT ["/entrypoint.sh"]

Dockerfile.github_action_dockerhub

@@ -0,0 +1 @@
+FROM codiumai/pr-agent:github_action

README.md

@@ -9,18 +9,40 @@
 
 [![GitHub license](https://img.shields.io/badge/License-Apache_2.0-blue.svg)](https://github.com/Codium-ai/pr-agent/blob/main/LICENSE)
 [![Discord](https://badgen.net/badge/icon/discord?icon=discord&label&color=purple)](https://discord.com/channels/1057273017547378788/1126104260430528613)
-
-CodiumAI `PR-Agent` is an open-source tool aiming to help developers review PRs faster and more efficiently. It automatically analyzes the PR, provides feedback and suggestions, and can answer free-text questions.
-
 </div>
+<div align="left">
+
+CodiumAI `pr-agent` is an open-source tool aiming to help developers review PRs faster and more efficiently. It automatically analyzes the PR and can provide several types of feedback:
+
+**Auto-Description**: Automatically generating PR description - name, type, summary, and code walkthrough.
+\
+**PR Review**: Feedback about the PR main theme, type, relevant tests, security issues, focused, and various suggestions for the PR content.
+\
+**Question Answering**: Answering free-text questions about the PR.
+\
+**Code Suggestion**: Committable code suggestions for improving the PR.
+
+Example results:
+</div>
+<div align="center">
+<p float="center">
+<img src="./pics/pr_reviewer_1.png" width="800">
+</p>
+<p float="center">
+<img src="./pics/pr_code_suggestions.png" width="800">
+</p>
+</div>
+<div align="left">
 
 - [Live demo](#live-demo)
-- [Quickstart](#Quickstart)
+- [Overview](#overview)
+- [Quickstart](#quickstart)
 - [Usage and tools](#usage-and-tools)
-- [Configuration](#Configuration)
+- [Configuration](./CONFIGURATION.md)
 - [How it works](#how-it-works)
 - [Roadmap](#roadmap)
 - [Similar projects](#similar-projects)
+</div>
 
 ## Live demo
 
@@ -31,6 +53,33 @@ Experience GPT-4 powered PR review on your public GitHub repository with our hos
 To set up your own PR-Agent, see the [Quickstart](#Quickstart) section
 
 ---
+## Overview
+`pr-agent` offers extensive pull request functionalities across various git providers:
+|       |                                             | Github | Gitlab | Bitbucket |
+|-------|---------------------------------------------|--------|--------|-----------|
+| TOOLS | Review                                      | ✓      | ✓      | ✓         |
+|       | ⮑ Inline review                             | ✓     | ✓      |           |
+|       | Ask                                         | ✓      | ✓      |           |
+|       | Auto-Description                            | ✓      |        |           |
+|       | Improve Code                                | ✓      |        |           |
+|       |                                             |        |        |           |
+| USAGE | CLI                                         | ✓      | ✓      | ✓         |
+|       | Tagging bot                                 | ✓      | ✓      |           |
+|       | Actions                                     | ✓      |        |           |
+|       |                                             |        |        |           |
+| CORE  | PR compression                              | ✓      | ✓      | ✓         |
+|       | Repo language prioritization                | ✓      | ✓      | ✓         |
+|       | Adaptive and token-aware<br />file patch fitting | ✓      | ✓      | ✓         |
+
+Examples for invoking the different tools via the [CLI](#quickstart):
+- **Review**:       python cli.py --pr-url=<pr_url>  review
+- **Describe**:     python cli.py --pr-url=<pr_url>  describe
+- **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"
+
+"<pr_url>" is the url of the relevant PR (for example: https://github.com/Codium-ai/pr-agent/pull/50).
+
+In the [configuration](./CONFIGURATION.md) file you can select your git provider (Github, Gitlab, Bitbucket), and further configure the different tools.
 
 ## Quickstart
 
@@ -50,13 +99,13 @@ To request a review for a PR, or ask a question about a PR, you can run directly
 1. To request a review for a PR, run the following command:
 
 ```
-docker run --rm -it -e OPENAI.KEY=<your key> -e GITHUB.USER_TOKEN=<your token> codiumai/pr-agent --pr_url <pr url>
+docker run --rm -it -e OPENAI.KEY=<your key> -e GITHUB.USER_TOKEN=<your token> codiumai/pr-agent --pr_url <pr_url> review
 ```
 
 2. To ask a question about a PR, run the following command:
 
 ```
-docker run --rm -it -e OPENAI.KEY=<your key> -e GITHUB.USER_TOKEN=<your token> codiumai/pr-agent --pr_url <pr url> --question "<your question>"
+docker run --rm -it -e OPENAI.KEY=<your key> -e GITHUB.USER_TOKEN=<your token> codiumai/pr-agent --pr_url <pr_url> ask "<your question>"
 ```
 
 Possible questions you can ask include:
@@ -86,15 +135,17 @@ pip install -r requirements.txt
 3. Copy the secrets template file and fill in your OpenAI key and your GitHub user token:
 
 ```
-cp pr_agent/settings/.secrets_template.toml pr_agent/settings/.secrets
+cp pr_agent/settings/.secrets_template.toml pr_agent/settings/.secrets.toml
-# Edit .secrets file
+# Edit .secrets.toml file
 ```
 
 4. Run the appropriate Python scripts from the scripts folder:
 
 ```
-python pr_agent/cli.py --pr_url <pr url>
+python pr_agent/cli.py --pr_url <pr_url> review
-python pr_agent/cli.py --pr_url <pr url> --question "<your question>"
+python pr_agent/cli.py --pr_url <pr_url> ask <your question>
+python pr_agent/cli.py --pr_url <pr_url> describe
+python pr_agent/cli.py --pr_url <pr_url> improve
 ```
 
 ---
@@ -147,8 +198,8 @@ git clone https://github.com/Codium-ai/pr-agent.git
    - Copy your app's webhook secret to the webhook_secret field.
 
 ```
-cp pr_agent/settings/.secrets_template.toml pr_agent/settings/.secrets
+cp pr_agent/settings/.secrets_template.toml pr_agent/settings/.secrets.toml
-# Edit .secrets file
+# Edit .secrets.toml file
 ```
 
 6. Build a Docker image for the app and optionally push it to a Docker repository. We'll use Dockerhub as an example:
@@ -172,122 +223,12 @@ docker push codiumai/pr-agent:github_app  # Push to your Docker repository
 
 ## Usage and Tools
 
-CodiumAI PR-Agent provides two types of interactions ("tools"): `"PR Reviewer"` and `"PR Q&A"`.
+**PR-Agent** provides four types of interactions ("tools"): `"PR Reviewer"`, `"PR Q&A"`, `"PR Description"` and `"PR Code Sueggestions"`.
 
 - The "PR Reviewer" tool automatically analyzes PRs, and provides different types of feedbacks.
-- The "PR Q&A" tool answers free-text questions about the PR.
+- The "PR Ask" tool answers free-text questions about the PR.
-
+- The "PR Description" tool automatically sets the PR Title and body.
-### PR Reviewer
+- The "PR Code Suggestion" tool provide inline code suggestions for the PR, that can be applied and committed.
-
-Here is a quick overview of the different sub-tools of PR Reviewer:
-
-- PR Analysis
-  - Summarize main theme
-  - PR description and title
-  - PR type classification
-  - Is the PR covered by relevant tests
-  - Is the PR minimal and focused
-  - Are there security concerns
-- PR Feedback
-  - General PR suggestions
-  - Code suggestions
-
-This is how a typical output of the PR Reviewer looks like:
-
----
-
-#### PR Analysis
-
-- 🎯 **Main theme:** Adding language extension handler and token handler
-- 🔍 **Description and title:** Yes
-- 📌 **Type of PR:** Enhancement
-- 🧪 **Relevant tests added:** No
-- ✨ **Minimal and focused:** Yes, the PR is focused on adding two new handlers for language extension and token counting.
-- 🔒 **Security concerns:** No, the PR does not introduce possible security concerns or issues.
-
-#### PR Feedback
-
-- 💡 **General PR suggestions:** The PR is generally well-structured and the code is clean. However, it would be beneficial to add some tests to ensure the new handlers work as expected. Also, consider adding docstrings to the new functions and classes to improve code readability and maintainability.
-
-- 🤖 **Code suggestions:**
-
-  - **relevant file:** pr_agent/algo/language_handler.py
-
-    **suggestion content:** Consider using a set instead of a list for 'bad_extensions' as checking membership in a set is faster than in a list. [medium]
-
-  - **relevant file:** pr_agent/algo/language_handler.py
-
-    **suggestion content:** In the 'filter_bad_extensions' function, you are splitting the filename on '.' and taking the last element to get the extension. This might not work as expected if the filename contains multiple '.' characters. Consider using 'os.path.splitext' to get the file extension more reliably. [important]
-
----
-
-### PR Q&A
-
-This tool answers free-text questions about the PR. This is how a typical output of the PR Q&A looks like:
-
-**Question**: summarize for me the PR in 4 bullet points
-
-**Answer**:
-
-- The PR introduces a new feature to sort files by their main languages. It uses a mapping of programming languages to their file extensions to achieve this.
-- It also introduces a filter to exclude files with certain extensions, deemed as 'bad extensions', from the sorting process.
-- The PR modifies the `get_pr_diff` function in `pr_processing.py` to use the new sorting function. It also refactors the code to move the PR pruning logic into a separate function.
-- A new `TokenHandler` class is introduced in `token_handler.py` to handle token counting operations. This class is initialized with a PR, variables, system, and user, and provides methods to get system and user tokens and to count tokens in a patch.
-
----
-
-## Configuration
-
-The different tools and sub-tools used by CodiumAI PR-Agent are easily configurable via the configuration file: `/settings/configuration.toml`.
-
-#### Enabling/disabling sub-tools:
-
-You can enable/disable the different PR Reviewer sub-sections with the following flags:
-
-```
-require_minimal_and_focused_review=true
-require_tests_review=true
-require_security_review=true
-```
-
-#### Code Suggestions configuration:
-
-There are also configuration options to control different aspects of the `code suggestions` feature.
-The number of suggestions provided can be controlled by adjusting the following parameter:
-
-```
-num_code_suggestions=4
-```
-
-You can also enable more verbose and informative mode of code suggestions:
-
-```
-extended_code_suggestions=false
-```
-
-This is a comparison of the regular and extended code suggestions modes:
-
-- **relevant file:** sql.py
-- **suggestion content:** Remove hardcoded sensitive information like username and password. Use environment variables or a secure method to store these values. [important]
-
-Example for extended suggestion:
-
-- **relevant file:** sql.py
-- **suggestion content:** Remove hardcoded sensitive information (username and password) [important]
-- **why:** Hardcoding sensitive information is a security risk. It's better to use environment variables or a secure way to store these values.
-- **code example:**
-  - **before code:**
-    ```
-    user = "root",
-    password = "Mysql@123",
-    ```
-  - **after code:**
-    ```
-    user = os.getenv('DB_USER'),
-    password = os.getenv('DB_PASSWORD'),
-    ```
-
----
 
 ## How it works
 
@@ -297,14 +238,15 @@ Check out the [PR Compression strategy](./PR_COMPRESSION.md) page for more detai
 
 ## Roadmap
 
-- [ ] Support open-source models, as a replacement for openai models. Note that a minimal requirement for each open-source model is to have 8k+ context, and good support for generating json as an output
+- [ ] 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)
-- [ ] Support other Git providers, such as Gitlab and Bitbucket.
+- [x] Support other Git providers, such as Gitlab and Bitbucket.
 - [ ] Develop additional logics for handling large PRs, and compressing git patches
 - [ ] Dedicated tools and sub-tools for specific programming languages (Python, Javascript, Java, C++, etc)
 - [ ] Add additional context to the prompt. For example, repo (or relevant files) summarization, with tools such a [ctags](https://github.com/universal-ctags/ctags)
 - [ ] Adding more tools. Possible directions:
-  - [ ] Code Quality
+  - [x] PR description
-  - [ ] Coding Style
+  - [x] Inline code suggestions
+  - [ ] Enforcing CONTRIBUTING.md guidelines
   - [ ] Performance (are there any performance issues)
   - [ ] Documentation (is the PR properly documented)
   - [ ] Rank the PR importance
@@ -314,6 +256,6 @@ Check out the [PR Compression strategy](./PR_COMPRESSION.md) page for more detai
 
 - [CodiumAI - Meaningful tests for busy devs](https://github.com/Codium-ai/codiumai-vscode-release)
 - [Aider - GPT powered coding in your terminal](https://github.com/paul-gauthier/aider)
-- [GPT-Engineer](https://github.com/AntonOsika/gpt-engineer)
+- [openai-pr-reviewer](https://github.com/coderabbitai/openai-pr-reviewer)
 - [CodeReview BOT](https://github.com/anc95/ChatGPT-CodeReview)
 - [AI-Maintainer](https://github.com/merwanehamadi/AI-Maintainer)

action.yaml

@@ -0,0 +1,5 @@
+name: 'PR Agent'
+description: 'Summarize, review and suggest improvements for pull requests'
+runs:
+  using: 'docker'
+  image: 'Dockerfile.github_action_dockerhub'

github_action/entrypoint.sh

@@ -0,0 +1,2 @@
+#!/bin/bash
+python /app/pr_agent/servers/github_action_runner.py

pr_agent/agent/pr_agent.py

@@ -1,25 +1,29 @@
 import re
-from typing import Optional
 
+from pr_agent.tools.pr_code_suggestions import PRCodeSuggestions
+from pr_agent.tools.pr_description import PRDescription
 from pr_agent.tools.pr_questions import PRQuestions
 from pr_agent.tools.pr_reviewer import PRReviewer
 
 
 class PRAgent:
-    def __init__(self, installation_id: Optional[int] = None):
+    def __init__(self):
-        self.installation_id = installation_id
+        pass
 
-    async def handle_request(self, pr_url, request):
+    async def handle_request(self, pr_url, request) -> bool:
-        if 'please review' in request.lower() or 'review' == request.lower().strip() or len(request) == 0:
+        if any(cmd in request for cmd in ["/review", "/review_pr"]):
-            reviewer = PRReviewer(pr_url, self.installation_id)
+            await PRReviewer(pr_url).review()
-            await reviewer.review()
+        elif any(cmd in request for cmd in ["/describe", "/describe_pr"]):
+            await PRDescription(pr_url).describe()
+        elif any(cmd in request for cmd in ["/improve", "/improve_code"]):
+            await PRCodeSuggestions(pr_url).suggest()
+        elif any(cmd in request for cmd in ["/ask", "/ask_question"]):
+            pattern = r'(/ask|/ask_question)\s*(.*)'
+            matches = re.findall(pattern, request, re.IGNORECASE)
+            if matches:
+                question = matches[0][1]
+                await PRQuestions(pr_url, question).answer()
+        else:
+            return False
 
-        else:
+        return True
-            if "please answer" in request.lower():
-                question = re.split(r'(?i)please answer', request)[1].strip()
-            elif request.lower().strip().startswith("answer"):
-                question = re.split(r'(?i)answer', request)[1].strip()
-            else:
-                question = request
-            answerer = PRQuestions(pr_url, question, self.installation_id)
-            await answerer.answer()

pr_agent/algo/ai_handler.py

@@ -14,6 +14,13 @@ class AiHandler:
             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
         except AttributeError as e:
             raise ValueError("OpenAI key is required") from e
 
@@ -23,6 +30,7 @@ class AiHandler:
         try:
             response = await openai.ChatCompletion.acreate(
                             model=model,
+                            deployment_id=self.deployment_id,
                             messages=[
                                 {"role": "system", "content": system},
                                 {"role": "user", "content": user}

pr_agent/algo/git_patch_processing.py

@@ -13,6 +13,9 @@ def extend_patch(original_file_str, patch_str, num_lines) -> str:
     if not patch_str or num_lines == 0:
         return patch_str
 
+    if type(original_file_str) == bytes:
+        original_file_str = original_file_str.decode('utf-8')
+
     original_lines = original_file_str.splitlines()
     patch_lines = patch_str.splitlines()
     extended_patch_lines = []
@@ -105,3 +108,78 @@ def handle_patch_deletions(patch: str, original_file_content_str: str,
                 logging.info(f"Processing file: {file_name}, hunks were deleted")
             patch = patch_new
     return patch
+
+
+def convert_to_hunks_with_lines_numbers(patch: str, file) -> str:
+    # toDO: (maybe remove '-' and '+' from the beginning of the line)
+    """
+    ## src/file.ts
+--new hunk--
+881        line1
+882        line2
+883        line3
+884        line4
+885        line6
+886        line7
+887 +      line8
+888 +      line9
+889        line10
+890        line11
+...
+--old hunk--
+        line1
+        line2
+-       line3
+-       line4
+        line5
+        line6
+           ...
+
+    """
+    patch_with_lines_str = f"## {file.filename}\n"
+    import re
+    patch_lines = patch.splitlines()
+    RE_HUNK_HEADER = re.compile(
+        r"^@@ -(\d+)(?:,(\d+))? \+(\d+)(?:,(\d+))? @@[ ]?(.*)")
+    new_content_lines = []
+    old_content_lines = []
+    match = None
+    start1, size1, start2, size2 = -1, -1, -1, -1
+    for line in patch_lines:
+        if 'no newline at end of file' in line.lower():
+            continue
+
+        if line.startswith('@@'):
+            match = RE_HUNK_HEADER.match(line)
+            if match and new_content_lines:  # found a new hunk, split the previous lines
+                if new_content_lines:
+                    patch_with_lines_str += '\n--new hunk--\n'
+                    for i, line_new in enumerate(new_content_lines):
+                        patch_with_lines_str += f"{start2 + i} {line_new}\n"
+                if old_content_lines:
+                    patch_with_lines_str += '--old hunk--\n'
+                    for i, line_old in enumerate(old_content_lines):
+                        patch_with_lines_str += f"{line_old}\n"
+                new_content_lines = []
+                old_content_lines = []
+            start1, size1, start2, size2 = map(int, match.groups()[:4])
+        elif line.startswith('+'):
+            new_content_lines.append(line)
+        elif line.startswith('-'):
+            old_content_lines.append(line)
+        else:
+            new_content_lines.append(line)
+            old_content_lines.append(line)
+
+    # finishing last hunk
+    if match and new_content_lines:
+        if new_content_lines:
+            patch_with_lines_str += '\n--new hunk--\n'
+            for i, line_new in enumerate(new_content_lines):
+                patch_with_lines_str += f"{start2 + i} {line_new}\n"
+        if old_content_lines:
+            patch_with_lines_str += '\n--old hunk--\n'
+            for i, line_old in enumerate(old_content_lines):
+                patch_with_lines_str += f"{line_old}\n"
+
+    return patch_with_lines_str.strip()

pr_agent/algo/language_handler.py

@@ -93,7 +93,7 @@ def sort_files_by_main_languages(languages: Dict, files: list):
     for ext in main_extensions:
         main_extensions_flat.extend(ext)
 
-    for extensions, lang in zip(main_extensions, languages_sorted_list):
+    for extensions, lang in zip(main_extensions, languages_sorted_list):  # noqa: B905
         tmp = []
         for file in files_filtered:
             extension_str = f".{file.filename.split('.')[-1]}"

pr_agent/algo/pr_processing.py

@@ -2,9 +2,10 @@ from __future__ import annotations
 
 import difflib
 import logging
-from typing import Any, Dict, Tuple, Union
+from typing import Any, Tuple, Union
 
-from pr_agent.algo.git_patch_processing import extend_patch, handle_patch_deletions
+from pr_agent.algo.git_patch_processing import extend_patch, handle_patch_deletions, \
+    convert_to_hunks_with_lines_numbers
 from pr_agent.algo.language_handler import sort_files_by_main_languages
 from pr_agent.algo.token_handler import TokenHandler
 from pr_agent.config_loader import settings
@@ -14,29 +15,38 @@ DELETED_FILES_ = "Deleted files:\n"
 
 MORE_MODIFIED_FILES_ = "More modified files:\n"
 
-OUTPUT_BUFFER_TOKENS = 800
+OUTPUT_BUFFER_TOKENS_SOFT_THRESHOLD = 1000
+OUTPUT_BUFFER_TOKENS_HARD_THRESHOLD = 600
 PATCH_EXTRA_LINES = 3
 
 
-def get_pr_diff(git_provider: Union[GithubProvider, Any], token_handler: TokenHandler) -> str:
+def get_pr_diff(git_provider: Union[GithubProvider, Any], token_handler: TokenHandler,
+                add_line_numbers_to_hunks: bool = False, disable_extra_lines: bool =False) -> str:
     """
     Returns a string with the diff of the PR.
     If needed, apply diff minimization techniques to reduce the number of tokens
     """
-    files = list(git_provider.get_diff_files())
+    if disable_extra_lines:
+        global PATCH_EXTRA_LINES
+        PATCH_EXTRA_LINES = 0
+
+    git_provider.pr.diff_files = list(git_provider.get_diff_files())
 
     # get pr languages
-    pr_languages = sort_files_by_main_languages(git_provider.get_languages(), files)
+    pr_languages = sort_files_by_main_languages(git_provider.get_languages(), git_provider.pr.diff_files)
 
     # generate a standard diff string, with patch extension
-    patches_extended, total_tokens = pr_generate_extended_diff(pr_languages, token_handler)
+    patches_extended, total_tokens = pr_generate_extended_diff(pr_languages, token_handler,
+                                                               add_line_numbers_to_hunks)
 
     # if we are under the limit, return the full diff
-    if total_tokens + OUTPUT_BUFFER_TOKENS < token_handler.limit:
+    if total_tokens + OUTPUT_BUFFER_TOKENS_SOFT_THRESHOLD < token_handler.limit:
         return "\n".join(patches_extended)
 
     # if we are over the limit, start pruning
-    patches_compressed, modified_file_names, deleted_file_names = pr_generate_compressed_diff(pr_languages, token_handler)
+    patches_compressed, modified_file_names, deleted_file_names = \
+        pr_generate_compressed_diff(pr_languages, token_handler, add_line_numbers_to_hunks)
+
     final_diff = "\n".join(patches_compressed)
     if modified_file_names:
         modified_list_str = MORE_MODIFIED_FILES_ + "\n".join(modified_file_names)
@@ -47,7 +57,8 @@ def get_pr_diff(git_provider: Union[GithubProvider, Any], token_handler: TokenHa
     return final_diff
 
 
-def pr_generate_extended_diff(pr_languages: list, token_handler: TokenHandler) -> \
+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
@@ -70,6 +81,9 @@ def pr_generate_extended_diff(pr_languages: list, token_handler: TokenHandler) -
             extended_patch = extend_patch(original_file_content_str, patch, num_lines=PATCH_EXTRA_LINES)
             full_extended_patch = f"## {file.filename}\n\n{extended_patch}\n"
 
+            if add_line_numbers_to_hunks:
+                full_extended_patch = convert_to_hunks_with_lines_numbers(extended_patch, file)
+
             patch_tokens = token_handler.count_tokens(full_extended_patch)
             file.tokens = patch_tokens
             total_tokens += patch_tokens
@@ -78,7 +92,8 @@ def pr_generate_extended_diff(pr_languages: list, token_handler: TokenHandler) -
     return patches_extended, total_tokens
 
 
-def pr_generate_compressed_diff(top_langs: list, token_handler: TokenHandler) -> Tuple[list, list, list]:
+def pr_generate_compressed_diff(top_langs: list, token_handler: TokenHandler,
+                                convert_hunks_to_line_numbers: bool) -> Tuple[list, list, list]:
     # Apply Diff Minimization techniques to reduce the number of tokens:
     # 0. Start from the largest diff patch to smaller ones
     # 1. Don't use extend context lines around diff
@@ -112,15 +127,19 @@ def pr_generate_compressed_diff(top_langs: list, token_handler: TokenHandler) ->
             deleted_files_list.append(file.filename)
             total_tokens += token_handler.count_tokens(file.filename) + 1
             continue
+
+        if convert_hunks_to_line_numbers:
+            patch = convert_to_hunks_with_lines_numbers(patch, file)
+
         new_patch_tokens = token_handler.count_tokens(patch)
 
         # Hard Stop, no more tokens
-        if total_tokens > token_handler.limit - OUTPUT_BUFFER_TOKENS // 2:
+        if total_tokens > token_handler.limit - OUTPUT_BUFFER_TOKENS_HARD_THRESHOLD:
             logging.warning(f"File was fully skipped, no more tokens: {file.filename}.")
             continue
 
         # If the patch is too large, just show the file name
-        if total_tokens + new_patch_tokens > token_handler.limit - OUTPUT_BUFFER_TOKENS:
+        if total_tokens + new_patch_tokens > token_handler.limit - OUTPUT_BUFFER_TOKENS_SOFT_THRESHOLD:
             # Current logic is to skip the patch if it's too large
             # TODO: Option for alternative logic to remove hunks from the patch to reduce the number of tokens
             #  until we meet the requirements
@@ -133,7 +152,10 @@ def pr_generate_compressed_diff(top_langs: list, token_handler: TokenHandler) ->
             continue
 
         if patch:
+            if not convert_hunks_to_line_numbers:
                 patch_final = f"## {file.filename}\n\n{patch}\n"
+            else:
+                patch_final = patch
             patches.append(patch_final)
             total_tokens += token_handler.count_tokens(patch_final)
             if settings.config.verbosity_level >= 2:

pr_agent/algo/utils.py

@@ -1,5 +1,8 @@
 from __future__ import annotations
 
+import json
+import logging
+import re
 import textwrap
 
 
@@ -8,11 +11,10 @@ def convert_to_markdown(output_data: dict) -> str:
 
     emojis = {
         "Main theme": "🎯",
-        "Description and title": "🔍",
         "Type of PR": "📌",
         "Relevant tests added": "🧪",
         "Unrelated changes": "⚠️",
-        "Minimal and focused": "✨",
+        "Focused PR": "✨",
         "Security concerns": "🔒",
         "General PR suggestions": "💡",
         "Code suggestions": "🤖"
@@ -50,10 +52,7 @@ def parse_code_suggestion(code_suggestions: dict) -> str:
                 code_str_indented = textwrap.indent(code_str, '        ')
                 markdown_text += f"    - **{code_key}:**\n{code_str_indented}\n"
         else:
-            if "suggestion number" in sub_key.lower():
+            if "relevant file" in sub_key.lower():
-                # markdown_text += f"- **suggestion {sub_value}:**\n"  # prettier formatting
-                pass
-            elif "relevant file" in sub_key.lower():
                 markdown_text += f"\n  - **{sub_key}:** {sub_value}\n"
             else:
                 markdown_text += f"   **{sub_key}:** {sub_value}\n"
@@ -61,3 +60,25 @@ def parse_code_suggestion(code_suggestions: dict) -> str:
     markdown_text += "\n"
     return markdown_text
 
+
+def try_fix_json(review, max_iter=10):
+    # Try to fix JSON if it is broken/incomplete: parse until the last valid code suggestion
+    data = {}
+    if review.rfind("'Code suggestions': [") > 0 or review.rfind('"Code suggestions": [') > 0:
+        last_code_suggestion_ind = [m.end() for m in re.finditer(r"\}\s*,", review)][-1] - 1
+        valid_json = False
+        iter_count = 0
+        while last_code_suggestion_ind > 0 and not valid_json and iter_count < max_iter:
+            try:
+                data = json.loads(review[:last_code_suggestion_ind] + "]}}")
+                valid_json = True
+                review = review[:last_code_suggestion_ind].strip() + "]}}"
+            except json.decoder.JSONDecodeError:
+                review = review[:last_code_suggestion_ind]
+                # Use regular expression to find the last occurrence of "}," with any number of whitespaces or newlines
+                last_code_suggestion_ind = [m.end() for m in re.finditer(r"\}\s*,", review)][-1] - 1
+                iter_count += 1
+        if not valid_json:
+            logging.error("Unable to decode JSON response from AI")
+            data = {}
+    return data

pr_agent/cli.py

@@ -3,24 +3,60 @@ 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_questions import PRQuestions
 from pr_agent.tools.pr_reviewer import PRReviewer
 
 
 def run():
-    parser = argparse.ArgumentParser(description='AI based pull request analyzer')
+    parser = argparse.ArgumentParser(description='AI based pull request analyzer', usage="""\
+Usage: cli.py --pr-url <URL on supported git hosting service> <command> [<args>].
+For example:
+- cli.py --pr-url xxx review
+- cli.py --pr-url xxx describe
+- cli.py --pr-url xxx improve
+- cli.py --pr-url xxx ask "write me a poem about this PR"
+
+Supported commands:
+review / review_pr - Add a review that includes a summary of the PR and specific suggestions for improvement.
+ask / ask_question [question] - Ask a question about the PR.
+describe / describe_pr - Modify the PR title and description based on the PR's contents.
+improve / improve_code - Suggest improvements to the code in the PR as pull request comments ready to commit.
+""")
     parser.add_argument('--pr_url', type=str, help='The URL of the PR to review', required=True)
-    parser.add_argument('--question', type=str, help='Optional question to ask', required=False)
+    parser.add_argument('command', type=str, help='The', choices=['review', 'review_pr',
+                                                                  'ask', 'ask_question',
+                                                                  'describe', 'describe_pr',
+                                                                  'improve', 'improve_code'], default='review')
+    parser.add_argument('rest', nargs=argparse.REMAINDER, default=[])
     args = parser.parse_args()
     logging.basicConfig(level=os.environ.get("LOGLEVEL", "INFO"))
-    if args.question:
+    command = args.command.lower()
-        print(f"Question: {args.question} about PR {args.pr_url}")
+    if command in ['ask', 'ask_question']:
-        reviewer = PRQuestions(args.pr_url, args.question, installation_id=None)
+        question = ' '.join(args.rest).strip()
+        if len(question) == 0:
+            print("Please specify a question")
+            parser.print_help()
+            return
+        print(f"Question: {question} about PR {args.pr_url}")
+        reviewer = PRQuestions(args.pr_url, question)
         asyncio.run(reviewer.answer())
-    else:
+    elif command in ['describe', 'describe_pr']:
+        print(f"PR description: {args.pr_url}")
+        reviewer = PRDescription(args.pr_url)
+        asyncio.run(reviewer.describe())
+    elif command in ['improve', 'improve_code']:
+        print(f"PR code suggestions: {args.pr_url}")
+        reviewer = PRCodeSuggestions(args.pr_url)
+        asyncio.run(reviewer.suggest())
+    elif command in ['review', 'review_pr']:
         print(f"Reviewing PR: {args.pr_url}")
-        reviewer = PRReviewer(args.pr_url, installation_id=None, cli_mode=True)
+        reviewer = PRReviewer(args.pr_url, cli_mode=True)
         asyncio.run(reviewer.review())
+    else:
+        print(f"Unknown command: {command}")
+        parser.print_help()
 
 
 if __name__ == '__main__':

pr_agent/config_loader.py

@@ -5,11 +5,14 @@ from dynaconf import Dynaconf
 current_dir = dirname(abspath(__file__))
 settings = Dynaconf(
     envvar_prefix=False,
+    merge_enabled=True,
     settings_files=[join(current_dir, f) for f in [
          "settings/.secrets.toml",
          "settings/configuration.toml",
          "settings/pr_reviewer_prompts.toml",
          "settings/pr_questions_prompts.toml",
+         "settings/pr_description_prompts.toml",
+         "settings/pr_code_suggestions_prompts.toml",
          "settings_prod/.secrets.toml"
         ]]
 )

pr_agent/git_providers/__init__.py

@@ -1,15 +1,17 @@
 from pr_agent.config_loader import settings
 from pr_agent.git_providers.github_provider import GithubProvider
+from pr_agent.git_providers.gitlab_provider import GitLabProvider
 
 _GIT_PROVIDERS = {
-    'github': GithubProvider
+    'github': GithubProvider,
+    'gitlab': GitLabProvider,
 }
 
 def get_git_provider():
     try:
         provider_id = settings.config.git_provider
     except AttributeError as e:
-        raise ValueError("github_provider is a required attribute in the configuration file") from e
+        raise ValueError("git_provider is a required attribute in the configuration file") from e
     if provider_id not in _GIT_PROVIDERS:
         raise ValueError(f"Unknown git provider: {provider_id}")
     return _GIT_PROVIDERS[provider_id]

pr_agent/git_providers/git_provider.py

@@ -0,0 +1,104 @@
+from abc import ABC, abstractmethod
+from dataclasses import dataclass
+
+# enum EDIT_TYPE (ADDED, DELETED, MODIFIED, RENAMED)
+from enum import Enum
+class EDIT_TYPE(Enum):
+    ADDED = 1
+    DELETED = 2
+    MODIFIED = 3
+    RENAMED = 4
+
+@dataclass
+class FilePatchInfo:
+    base_file: str
+    head_file: str
+    patch: str
+    filename: str
+    tokens: int = -1
+    edit_type: EDIT_TYPE = EDIT_TYPE.MODIFIED
+    old_filename: str = None
+
+
+class GitProvider(ABC):
+    @abstractmethod
+    def get_diff_files(self) -> list[FilePatchInfo]:
+        pass
+
+    @abstractmethod
+    def publish_description(self, pr_title: str, pr_body: str):
+        pass
+
+    @abstractmethod
+    def publish_comment(self, pr_comment: str, is_temporary: bool = False):
+        pass
+
+    @abstractmethod
+    def publish_inline_comment(self, body: str, relevant_file: str, relevant_line_in_file: str):
+        pass
+
+    @abstractmethod
+    def publish_code_suggestion(self, body: str, relevant_file: str,
+                                relevant_lines_start: int, relevant_lines_end: int):
+        pass
+
+    @abstractmethod
+    def remove_initial_comment(self):
+        pass
+
+    @abstractmethod
+    def get_languages(self):
+        pass
+
+    @abstractmethod
+    def get_pr_branch(self):
+        pass
+
+    @abstractmethod
+    def get_user_id(self):
+        pass
+
+    @abstractmethod
+    def get_pr_description(self):
+        pass
+
+
+def get_main_pr_language(languages, files) -> str:
+    """
+    Get the main language of the commit. Return an empty string if cannot determine.
+    """
+    main_language_str = ""
+    try:
+        top_language = max(languages, key=languages.get).lower()
+
+        # validate that the specific commit uses the main language
+        extension_list = []
+        for file in files:
+            extension_list.append(file.filename.rsplit('.')[-1])
+
+        # get the most common extension
+        most_common_extension = max(set(extension_list), key=extension_list.count)
+
+        # look for a match. TBD: add more languages, do this systematically
+        if most_common_extension == 'py' and top_language == 'python' or \
+                most_common_extension == 'js' and top_language == 'javascript' or \
+                most_common_extension == 'ts' and top_language == 'typescript' or \
+                most_common_extension == 'go' and top_language == 'go' or \
+                most_common_extension == 'java' and top_language == 'java' or \
+                most_common_extension == 'c' and top_language == 'c' or \
+                most_common_extension == 'cpp' and top_language == 'c++' or \
+                most_common_extension == 'cs' and top_language == 'c#' or \
+                most_common_extension == 'swift' and top_language == 'swift' or \
+                most_common_extension == 'php' and top_language == 'php' or \
+                most_common_extension == 'rb' and top_language == 'ruby' or \
+                most_common_extension == 'rs' and top_language == 'rust' or \
+                most_common_extension == 'scala' and top_language == 'scala' or \
+                most_common_extension == 'kt' and top_language == 'kotlin' or \
+                most_common_extension == 'pl' and top_language == 'perl' or \
+                most_common_extension == 'swift' and top_language == 'swift':
+            main_language_str = top_language
+
+    except Exception:
+        pass
+
+    return main_language_str

pr_agent/git_providers/github_provider.py

@@ -1,37 +1,35 @@
 import logging
-from collections import namedtuple
-from dataclasses import dataclass
 from datetime import datetime
 from typing import Optional, Tuple
 from urllib.parse import urlparse
 
-from github import AppAuthentication, File, Github
+from github import AppAuthentication, Github
 
 from pr_agent.config_loader import settings
 
-@dataclass
+from .git_provider import FilePatchInfo, GitProvider
-class FilePatchInfo:
-    base_file: str
-    head_file: str
-    patch: str
-    filename: str
-    tokens: int = -1
 
-class GithubProvider:
+
-    def __init__(self, pr_url: Optional[str] = None, installation_id: Optional[int] = None):
+class GithubProvider(GitProvider):
-        self.installation_id = installation_id
+    def __init__(self, pr_url: Optional[str] = None):
+        self.installation_id = settings.get("GITHUB.INSTALLATION_ID")
         self.github_client = self._get_github_client()
         self.repo = None
         self.pr_num = None
         self.pr = None
         self.github_user_id = None
+        self.diff_files = None
         if pr_url:
             self.set_pr(pr_url)
+            self.last_commit_id = list(self.pr.get_commits())[-1]
 
     def set_pr(self, pr_url: str):
         self.repo, self.pr_num = self._parse_pr_url(pr_url)
         self.pr = self._get_pr()
 
+    def get_files(self):
+        return self.pr.get_files()
+
     def get_diff_files(self) -> list[FilePatchInfo]:
         files = self.pr.get_files()
         diff_files = []
@@ -39,8 +37,13 @@ class GithubProvider:
             original_file_content_str = self._get_pr_file_content(file, self.pr.base.sha)
             new_file_content_str = self._get_pr_file_content(file, self.pr.head.sha)
             diff_files.append(FilePatchInfo(original_file_content_str, new_file_content_str, file.patch, file.filename))
+        self.diff_files = diff_files
         return diff_files
 
+    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):
         response = self.pr.create_issue_comment(pr_comment)
         if hasattr(response, "user") and hasattr(response.user, "login"):
@@ -50,6 +53,76 @@ class GithubProvider:
             self.pr.comments_list = []
         self.pr.comments_list.append(response)
 
+    def publish_inline_comment(self, body: str, relevant_file: str, relevant_line_in_file: str):
+        self.diff_files = self.diff_files if self.diff_files else self.get_diff_files()
+        position = -1
+        for file in self.diff_files:
+            if file.filename.strip() == relevant_file:
+                patch = file.patch
+                patch_lines = patch.splitlines()
+                for i, line in enumerate(patch_lines):
+                    if relevant_line_in_file in line:
+                        position = i
+                        break
+                    elif relevant_line_in_file[0] == '+' and relevant_line_in_file[1:] in line:
+                        # The model often adds a '+' to the beginning of the relevant_line_in_file even if originally
+                        # it's a context line
+                        position = i
+                        break
+        if position == -1:
+            if settings.config.verbosity_level >= 2:
+                logging.info(f"Could not find position for {relevant_file} {relevant_line_in_file}")
+        else:
+            path = relevant_file.strip()
+            self.pr.create_review_comment(body=body, commit_id=self.last_commit_id, path=path, position=position)
+
+    def publish_code_suggestion(self, body: str,
+                                relevant_file: str,
+                                relevant_lines_start: int,
+                                relevant_lines_end: int):
+        if not relevant_lines_start or relevant_lines_start == -1:
+            if settings.config.verbosity_level >= 2:
+                logging.exception(f"Failed to publish code suggestion, relevant_lines_start is {relevant_lines_start}")
+            return False
+
+        if relevant_lines_end<relevant_lines_start:
+            if 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}")
+            return False
+
+        try:
+            import github.PullRequestComment
+            if relevant_lines_end > relevant_lines_start:
+                post_parameters = {
+                    "body": body,
+                    "commit_id": self.last_commit_id._identity,
+                    "path": relevant_file,
+                    "line": relevant_lines_end,
+                    "start_line": relevant_lines_start,
+                    "start_side": "RIGHT",
+                }
+            else:  # API is different for single line comments
+                post_parameters = {
+                    "body": body,
+                    "commit_id": self.last_commit_id._identity,
+                    "path": relevant_file,
+                    "line": relevant_lines_start,
+                    "side": "RIGHT",
+                }
+            headers, data = self.pr._requester.requestJsonAndCheck(
+                "POST", f"{self.pr.url}/comments", input=post_parameters
+            )
+            github.PullRequestComment.PullRequestComment(
+                self.pr._requester, headers, data, completed=True
+            )
+            return True
+        except Exception as e:
+            if settings.config.verbosity_level >= 2:
+                logging.error(f"Failed to publish code suggestion, error: {e}")
+            return False
+
     def remove_initial_comment(self):
         try:
             for comment in self.pr.comments_list:
@@ -65,53 +138,15 @@ class GithubProvider:
         return self.pr.body
 
     def get_languages(self):
-        return self._get_repo().get_languages()
+        languages = self._get_repo().get_languages()
-
+        return languages
-    def get_main_pr_language(self) -> str:
-        """
-        Get the main language of the commit. Return an empty string if cannot determine.
-        """
-        main_language_str = ""
-        try:
-            languages = self.get_languages()
-            top_language = max(languages, key=languages.get).lower()
-
-            # validate that the specific commit uses the main language
-            extension_list = []
-            files = self.pr.get_files()
-            for file in files:
-                extension_list.append(file.filename.rsplit('.')[-1])
-
-            # get the most common extension
-            most_common_extension = max(set(extension_list), key=extension_list.count)
-
-            # look for a match. TBD: add more languages, do this systematically
-            if most_common_extension == 'py' and top_language == 'python' or \
-                    most_common_extension == 'js' and top_language == 'javascript' or \
-                    most_common_extension == 'ts' and top_language == 'typescript' or \
-                    most_common_extension == 'go' and top_language == 'go' or \
-                    most_common_extension == 'java' and top_language == 'java' or \
-                    most_common_extension == 'c' and top_language == 'c' or \
-                    most_common_extension == 'cpp' and top_language == 'c++' or \
-                    most_common_extension == 'cs' and top_language == 'c#' or \
-                    most_common_extension == 'swift' and top_language == 'swift' or \
-                    most_common_extension == 'php' and top_language == 'php' or \
-                    most_common_extension == 'rb' and top_language == 'ruby' or \
-                    most_common_extension == 'rs' and top_language == 'rust' or \
-                    most_common_extension == 'scala' and top_language == 'scala' or \
-                    most_common_extension == 'kt' and top_language == 'kotlin' or \
-                    most_common_extension == 'pl' and top_language == 'perl' or \
-                    most_common_extension == 'swift' and top_language == 'swift':
-                main_language_str = top_language
-
-        except Exception:
-            pass
-
-        return main_language_str
 
     def get_pr_branch(self):
         return self.pr.head.ref
 
+    def get_pr_description(self):
+        return self.pr.body
+
     def get_user_id(self):
         if not self.github_user_id:
             try:
@@ -188,9 +223,9 @@ class GithubProvider:
     def _get_pr(self):
         return self._get_repo().get_pull(self.pr_num)
 
-    def _get_pr_file_content(self, file: FilePatchInfo, sha: str):
+    def _get_pr_file_content(self, file: FilePatchInfo, sha: str) -> str:
         try:
-            file_content_str = self._get_repo().get_contents(file.filename, ref=sha).decoded_content.decode()
+            file_content_str = str(self._get_repo().get_contents(file.filename, ref=sha).decoded_content.decode())
         except Exception:
             file_content_str = ""
         return file_content_str

pr_agent/git_providers/gitlab_provider.py

@@ -0,0 +1,207 @@
+import logging
+import re
+from typing import Optional, Tuple
+from urllib.parse import urlparse
+
+import gitlab
+
+from pr_agent.config_loader import settings
+
+from .git_provider import FilePatchInfo, GitProvider, EDIT_TYPE
+
+
+class GitLabProvider(GitProvider):
+    def __init__(self, merge_request_url: Optional[str] = None):
+        gitlab_url = 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)
+        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
+        )
+        self.id_project = None
+        self.id_mr = None
+        self.mr = None
+        self.diff_files = None
+        self.temp_comments = []
+        self._set_merge_request(merge_request_url)
+
+    @property
+    def pr(self):
+        '''The GitLab terminology is merge request (MR) instead of pull request (PR)'''
+        return self.mr
+
+    def _set_merge_request(self, merge_request_url: str):
+        self.id_project, self.id_mr = self._parse_merge_request_url(merge_request_url)
+        self.mr = self._get_merge_request()
+        self.last_diff = self.mr.diffs.list()[-1]
+
+    def _get_pr_file_content(self, file_path: str, branch: str) -> str:
+        return self.gl.projects.get(self.id_project).files.get(file_path, branch).decode()
+
+    def get_diff_files(self) -> list[FilePatchInfo]:
+        diffs = self.mr.changes()['changes']
+        diff_files = []
+        for diff in diffs:
+            original_file_content_str = self._get_pr_file_content(diff['old_path'], self.mr.target_branch)
+            new_file_content_str = self._get_pr_file_content(diff['new_path'], self.mr.source_branch)
+            edit_type = EDIT_TYPE.MODIFIED
+            if diff['new_file']:
+                edit_type = EDIT_TYPE.ADDED
+            elif diff['deleted_file']:
+                edit_type = EDIT_TYPE.DELETED
+            elif diff['renamed_file']:
+                edit_type = EDIT_TYPE.RENAMED
+            try:
+                original_file_content_str = bytes.decode(original_file_content_str, 'utf-8')
+                new_file_content_str = bytes.decode(new_file_content_str, 'utf-8')
+            except UnicodeDecodeError:
+                logging.warning(
+                    f"Cannot decode file {diff['old_path']} or {diff['new_path']} in merge request {self.id_mr}")
+            diff_files.append(
+                FilePatchInfo(original_file_content_str, new_file_content_str, diff['diff'], diff['new_path'],
+                              edit_type=edit_type,
+                              old_filename=None if diff['old_path'] == diff['new_path'] else diff['old_path']))
+        self.diff_files = diff_files
+        return diff_files
+
+    def get_files(self):
+        return [change['new_path'] for change in self.mr.changes()['changes']]
+
+    def publish_description(self, pr_title: str, pr_body: str):
+        logging.exception("Not implemented yet")
+        pass
+
+    def publish_comment(self, mr_comment: str, is_temporary: bool = False):
+        comment = self.mr.notes.create({'body': mr_comment})
+        if is_temporary:
+            self.temp_comments.append(comment)
+
+    def publish_inline_comment(self, body: str, relevant_file: str, relevant_line_in_file: str):
+        self.diff_files = self.diff_files if self.diff_files else self.get_diff_files()
+        edit_type, found, source_line_no, target_file, target_line_no = self.search_line(relevant_file,
+                                                                                         relevant_line_in_file)
+        if not found:
+            logging.info(f"Could not find position for {relevant_file} {relevant_line_in_file}")
+        else:
+            if edit_type == 'addition':
+                position = target_line_no - 1
+            else:
+                position = source_line_no - 1
+            d = self.last_diff
+            pos_obj = {'position_type': 'text',
+                        'new_path': target_file.filename,
+                        'old_path': target_file.old_filename if target_file.old_filename else target_file.filename,
+                        'base_sha': d.base_commit_sha, 'start_sha': d.start_commit_sha, 'head_sha': d.head_commit_sha}
+            if edit_type == 'deletion':
+                pos_obj['old_line'] = position
+            elif edit_type == 'addition':
+                pos_obj['new_line'] = position
+            else:
+                pos_obj['new_line'] = position
+                pos_obj['old_line'] = position
+            self.mr.discussions.create({'body': body,
+                                        'position': pos_obj})
+
+    def publish_code_suggestion(self, body: str,
+                                relevant_file: str,
+                                relevant_lines_start: int,
+                                relevant_lines_end: int):
+        raise "not implemented yet for gitlab"
+
+    def search_line(self, relevant_file, relevant_line_in_file):
+        RE_HUNK_HEADER = re.compile(
+            r"^@@ -(\d+)(?:,(\d+))? \+(\d+)(?:,(\d+))? @@[ ]?(.*)")
+        target_file = None
+        source_line_no = 0
+        target_line_no = 0
+        found = False
+        edit_type = self.get_edit_type(relevant_line_in_file)
+        for file in self.diff_files:
+            if file.filename == relevant_file:
+                target_file = file
+                patch = file.patch
+                patch_lines = patch.splitlines()
+                for i, line in enumerate(patch_lines):
+                    if line.startswith('@@'):
+                        match = RE_HUNK_HEADER.match(line)
+                        if not match:
+                            continue
+                        start_old, size_old, start_new, size_new, _ = match.groups()
+                        source_line_no = int(start_old)
+                        target_line_no = int(start_new)
+                        continue
+                    if line.startswith('-'):
+                        source_line_no += 1
+                    elif line.startswith('+'):
+                        target_line_no += 1
+                    elif line.startswith(' '):
+                        source_line_no += 1
+                        target_line_no += 1
+                    if relevant_line_in_file in line:
+                        found = True
+                        edit_type = self.get_edit_type(line)
+                        break
+                    elif relevant_line_in_file[0] == '+' and relevant_line_in_file[1:] in line:
+                        # The model often adds a '+' to the beginning of the relevant_line_in_file even if originally
+                        # it's a context line
+                        found = True
+                        edit_type = self.get_edit_type(line)
+                        break
+        return edit_type, found, source_line_no, target_file, target_line_no
+
+    def get_edit_type(self, relevant_line_in_file):
+        edit_type = 'context'
+        if relevant_line_in_file[0] == '-':
+            edit_type = 'deletion'
+        elif relevant_line_in_file[0] == '+':
+            edit_type = 'addition'
+        return edit_type
+
+    def remove_initial_comment(self):
+        try:
+            for comment in self.temp_comments:
+                comment.delete()
+        except Exception as e:
+            logging.exception(f"Failed to remove temp comments, error: {e}")
+
+    def get_title(self):
+        return self.mr.title
+
+    def get_description(self):
+        return self.mr.description
+
+    def get_languages(self):
+        languages = self.gl.projects.get(self.id_project).languages()
+        return languages
+
+    def get_pr_branch(self):
+        return self.mr.source_branch
+
+    def get_pr_description(self):
+        return self.mr.description
+
+    def _parse_merge_request_url(self, merge_request_url: str) -> Tuple[int, int]:
+        parsed_url = urlparse(merge_request_url)
+
+        path_parts = parsed_url.path.strip('/').split('/')
+        if path_parts[-2] != 'merge_requests':
+            raise ValueError("The provided URL does not appear to be a GitLab merge request URL")
+
+        try:
+            mr_id = int(path_parts[-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
+
+    def _get_merge_request(self):
+        mr = self.gl.projects.get(self.id_project).mergerequests.get(self.id_mr)
+        return mr
+
+    def get_user_id(self):
+        return None

pr_agent/servers/github_action_runner.py

@@ -0,0 +1,73 @@
+import asyncio
+import json
+import os
+import re
+
+from pr_agent.config_loader import settings
+from pr_agent.tools.pr_code_suggestions import PRCodeSuggestions
+from pr_agent.tools.pr_description import PRDescription
+from pr_agent.tools.pr_questions import PRQuestions
+from pr_agent.tools.pr_reviewer import PRReviewer
+
+
+async def run_action():
+    GITHUB_EVENT_NAME = os.environ.get('GITHUB_EVENT_NAME', None)
+    if not GITHUB_EVENT_NAME:
+        print("GITHUB_EVENT_NAME not set")
+        return
+    GITHUB_EVENT_PATH = os.environ.get('GITHUB_EVENT_PATH', None)
+    if not GITHUB_EVENT_PATH:
+        print("GITHUB_EVENT_PATH not set")
+        return
+    try:
+        event_payload = json.load(open(GITHUB_EVENT_PATH, 'r'))
+    except json.decoder.JSONDecodeError as e:
+        print(f"Failed to parse JSON: {e}")
+        return
+    OPENAI_KEY = os.environ.get('OPENAI_KEY', None)
+    if not OPENAI_KEY:
+        print("OPENAI_KEY not set")
+        return
+    OPENAI_ORG = os.environ.get('OPENAI_ORG', None)
+    GITHUB_TOKEN = os.environ.get('GITHUB_TOKEN', None)
+    if not GITHUB_TOKEN:
+        print("GITHUB_TOKEN not set")
+        return
+    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")
+    if GITHUB_EVENT_NAME == "pull_request":
+        action = event_payload.get("action", None)
+        if action in ["opened", "reopened"]:
+            pr_url = event_payload.get("pull_request", {}).get("url", None)
+            if pr_url:
+                await PRReviewer(pr_url).review()
+
+    elif GITHUB_EVENT_NAME == "issue_comment":
+        action = event_payload.get("action", None)
+        if action in ["created", "edited"]:
+            comment_body = event_payload.get("comment", {}).get("body", None)
+            if comment_body:
+                pr_url = event_payload.get("issue", {}).get("pull_request", {}).get("url", None)
+                if pr_url:
+                    body = comment_body.strip().lower()
+                    if any(cmd in body for cmd in ["/review", "/review_pr"]):
+                        await PRReviewer(pr_url).review()
+                    elif any(cmd in body for cmd in ["/describe", "/describe_pr"]):
+                        await PRDescription(pr_url).describe()
+                    elif any(cmd in body for cmd in ["/improve", "/improve_code"]):
+                        await PRCodeSuggestions(pr_url).suggest()
+                    elif any(cmd in body for cmd in ["/ask", "/ask_question"]):
+                        pattern = r'(/ask|/ask_question)\s*(.*)'
+                        matches = re.findall(pattern, comment_body, re.IGNORECASE)
+                        if matches:
+                            question = matches[0][1]
+                            await PRQuestions(pr_url, question).answer()
+                    else:
+                        print(f"Unknown command: {body}")
+
+
+if __name__ == '__main__':
+    asyncio.run(run_action())

pr_agent/servers/github_app.py

@@ -35,7 +35,8 @@ async def handle_github_webhooks(request: Request, response: Response):
 async def handle_request(body):
     action = body.get("action", None)
     installation_id = body.get("installation", {}).get("id", None)
-    agent = PRAgent(installation_id)
+    settings.set("GITHUB.INSTALLATION_ID", installation_id)
+    agent = PRAgent()
     if action == 'created':
         if "comment" not in body:
             return {}
@@ -55,7 +56,7 @@ async def handle_request(body):
         api_url = pull_request.get("url", None)
         if api_url is None:
             return {}
-        await agent.handle_request(api_url, "please review")
+        await agent.handle_request(api_url, "/review")
     else:
         return {}
 
@@ -66,8 +67,8 @@ async def root():
 
 
 def start():
-    if settings.get("GITHUB.DEPLOYMENT_TYPE", "user") != "app":
+    # Override the deployment type to app
-        raise Exception("Please set deployment type to app in .secrets.toml file")
+    settings.set("GITHUB.DEPLOYMENT_TYPE", "app")
     app = FastAPI()
     app.include_router(router)
 

pr_agent/servers/github_polling.py

@@ -1,5 +1,6 @@
 import asyncio
 import logging
+import re
 import sys
 from datetime import datetime, timezone
 
@@ -8,6 +9,11 @@ import aiohttp
 from pr_agent.agent.pr_agent import PRAgent
 from pr_agent.config_loader import settings
 from pr_agent.git_providers import get_git_provider
+from pr_agent.servers.help import bot_help_text
+from pr_agent.tools.pr_code_suggestions import PRCodeSuggestions
+from pr_agent.tools.pr_description import PRDescription
+from pr_agent.tools.pr_questions import PRQuestions
+from pr_agent.tools.pr_reviewer import PRReviewer
 
 logging.basicConfig(stream=sys.stdout, level=logging.DEBUG)
 NOTIFICATION_URL = "https://api.github.com/notifications"
@@ -25,6 +31,7 @@ async def polling_loop():
     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
@@ -38,6 +45,7 @@ async def polling_loop():
     async with aiohttp.ClientSession() as session:
         while True:
             try:
+                await asyncio.sleep(5)
                 headers = {
                     "Accept": "application/vnd.github.v3+json",
                     "Authorization": f"Bearer {token}"
@@ -75,21 +83,25 @@ async def polling_loop():
                                                 if comment['user']['login'] == user_id:
                                                     continue
                                             comment_body = comment['body'] if 'body' in comment else ''
-                                            commenter_github_user = comment['user']['login'] if 'user' in comment else ''
+                                            commenter_github_user = comment['user']['login'] \
+                                                if 'user' in comment else ''
                                             logging.info(f"Commenter: {commenter_github_user}\nComment: {comment_body}")
                                             user_tag = "@" + user_id
                                             if user_tag not in comment_body:
                                                 continue
                                             rest_of_comment = comment_body.split(user_tag)[1].strip()
-                                            agent = PRAgent()
+
-                                            await agent.handle_request(pr_url, rest_of_comment)
+                                            success = await agent.handle_request(pr_url, rest_of_comment)
+                                            if not success:
+                                                git_provider.set_pr(pr_url)
+                                                git_provider.publish_comment("### How to user PR-Agent\n" +
+                                                                             bot_help_text(user_id))
+
                     elif response.status != 304:
                         print(f"Failed to fetch notifications. Status code: {response.status}")
 
-                await asyncio.sleep(5)
             except Exception as e:
                 logging.error(f"Exception during processing of a notification: {e}")
-                await asyncio.sleep(5)
 
 if __name__ == '__main__':
     asyncio.run(polling_loop())

pr_agent/servers/gitlab_polling.py

@@ -0,0 +1,64 @@
+import asyncio
+import time
+
+import gitlab
+
+from pr_agent.agent.pr_agent import PRAgent
+from pr_agent.config_loader import settings
+
+gl = gitlab.Gitlab(
+    settings.get("GITLAB.URL"),
+    private_token=settings.get("GITLAB.PERSONAL_ACCESS_TOKEN")
+)
+
+# Set the list of projects to monitor
+projects_to_monitor = settings.get("GITLAB.PROJECTS_TO_MONITOR")
+magic_word = settings.get("GITLAB.MAGIC_WORD")
+
+# Hold the previous seen comments
+previous_comments = set()
+
+
+def check_comments():
+    print('Polling')
+    new_comments = {}
+    for project in projects_to_monitor:
+        project = gl.projects.get(project)
+        merge_requests = project.mergerequests.list(state='opened')
+        for mr in merge_requests:
+            notes = mr.notes.list(get_all=True)
+            for note in notes:
+                if note.id not in previous_comments and note.body.startswith(magic_word):
+                    new_comments[note.id] = dict(
+                        body=note.body[len(magic_word):],
+                        project=project.name,
+                        mr=mr
+                    )
+                    previous_comments.add(note.id)
+                    print(f"New comment in project {project.name}, merge request {mr.title}: {note.body}")
+
+    return new_comments
+
+
+def handle_new_comments(new_comments):
+    print('Handling new comments')
+    agent = PRAgent()
+    for _, comment in new_comments.items():
+        print(f"Handling comment: {comment['body']}")
+        asyncio.run(agent.handle_request(comment['mr'].web_url, comment['body']))
+
+
+def run():
+    assert settings.get('CONFIG.GIT_PROVIDER') == 'gitlab', 'This script is only for GitLab'
+    # Initial run to populate previous_comments
+    check_comments()
+
+    # Run the check every minute
+    while True:
+        time.sleep(settings.get("GITLAB.POLLING_INTERVAL_SECONDS"))
+        new_comments = check_comments()
+        if new_comments:
+            handle_new_comments(new_comments)
+
+if __name__ == '__main__':
+    run()

pr_agent/servers/help.py

@@ -0,0 +1,14 @@
+commands_text = "> /review - Ask for a new review after your update the PR\n" \
+                "> /describe - Modify the PR title and description based " \
+                "on the PR's contents.\n" \
+                "> /improve - Suggest improvements to the code in the PR as pull " \
+                "request comments ready to commit.\n" \
+                "> /ask <QUESTION> - Ask a question about the PR.\n"
+
+
+def bot_help_text(user: str):
+    return f"> Tag me in a comment '@{user}' and add one of the following commands:\n" + commands_text
+
+
+actions_help_text = "> Add a comment to to invoke PR-Agent, use one of the following commands:\n" + \
+                    commands_text

pr_agent/settings/.secrets_template.toml

@@ -1,5 +1,5 @@
 # QUICKSTART:
-# Copy this file to .secrets in the same folder.
+# Copy this file to .secrets.toml in the same folder.
 # The minimum workable settings - set openai.key to your API key.
 # Set github.deployment_type to "user" and github.user_token to your GitHub personal access token.
 # This will allow you to run the CLI scripts in the scripts/ folder and the github_polling server.
@@ -9,11 +9,13 @@
 [openai]
 key = "<API_KEY>"  # Acquire through https://platform.openai.com
 org = "<ORGANIZATION>"  # Optional, may be commented out.
+# Uncomment the following for Azure OpenAI
+#api_type = "azure"
+#api_version = '2023-05-15'  # Check Azure documentation for the current API version
+#api_base = "<API_BASE>"  # The base URL for your Azure OpenAI resource. e.g. "https://<your resource name>.openai.azure.com"
+#deployment_id = "<DEPLOYMENT_ID>"  # The deployment name you chose when you deployed the engine
 
 [github]
-# The type of deployment to create. Valid values are 'app' or 'user'.
-deployment_type = "user"
-
 # ---- Set the following only for deployment type == "user"
 user_token = "<TOKEN>"  # A GitHub personal access token with 'repo' scope.
 
@@ -25,3 +27,8 @@ private_key = """\
 """
 app_id = 123456  # The GitHub App ID, replace with your own.
 webhook_secret = "<WEBHOOK SECRET>"  # Optional, may be commented out.
+
+[gitlab]
+# Gitlab personal access token
+personal_access_token = ""
+

pr_agent/settings/configuration.toml

@@ -5,11 +5,30 @@ publish_review=true
 verbosity_level=0 # 0,1,2
 
 [pr_reviewer]
-require_minimal_and_focused_review=true
+require_focused_review=true
 require_tests_review=true
 require_security_review=true
-extended_code_suggestions=false
+num_code_suggestions=3
-num_code_suggestions=4
+inline_code_comments = true
-
 
 [pr_questions]
+
+[pr_code_suggestions]
+num_code_suggestions=4
+
+[github]
+# The type of deployment to create. Valid values are 'app' or 'user'.
+deployment_type = "user"
+
+[gitlab]
+# URL to the gitlab service
+url = "https://gitlab.com"
+
+# Polling (either project id or namespace/project_name) syntax can be used
+projects_to_monitor = ['org_name/repo_name']
+
+# Polling trigger
+magic_word = "AutoReview"
+
+# Polling interval
+polling_interval_seconds = 30

pr_agent/settings/pr_code_suggestions_prompts.toml

@@ -0,0 +1,79 @@
+[pr_code_suggestions_prompt]
+system="""You are a language model called CodiumAI-PR-Code-Reviewer.
+Your task is to provide provide meaningfull non-trivial code suggestions to improve the new code in a PR (the '+' lines).
+- Try to give important suggestions like fixing code problems, issues and bugs. As a second priority, provide suggestions for meaningfull code improvements, like performance, vulnerability, modularity, and best practices.
+- Suggestions should refer only to the 'new hunk' code, and focus on improving the new added code lines, with '+'.
+- Provide the exact line number range (inclusive) for each issue.
+- Assume there is additional code in the relevant file that is not included in the diff.
+- Provide up to {{ num_code_suggestions }} code suggestions.
+- Make sure not to provide suggestion repeating modifications already implemented in the new PR code (the '+' lines).
+- Don't output line numbers in the 'improved code' snippets.
+
+You must use the following JSON schema to format your answer:
+```json
+{
+    "Code suggestions": {
+      "type": "array",
+      "minItems": 1,
+      "maxItems": {{ num_code_suggestions }},
+      "uniqueItems": "true",
+      "items": {
+        "relevant file": {
+          "type": "string",
+          "description": "the relevant file full path"
+        },
+        "suggestion content": {
+          "type": "string",
+          "description": "a concrete suggestion for meaningfully improving the new PR code."
+        },
+        "existing code": {
+          "type": "string",
+          "description": "a code snippet showing authentic relevant code lines from a 'new hunk' section. It must be continuous, correctly formatted and indented, and without line numbers."
+        },
+        "relevant lines": {
+          "type": "string",
+          "description": "the relevant lines in the 'new hunk' sections, in the format of 'start_line-end_line'. For example: '10-15'. They should be derived from the hunk line numbers, and correspond to the 'existing code' snippet above."
+        },
+        "improved code": {
+          "type": "string",
+          "description": "a new code snippet that can be used to replace the relevant lines in 'new hunk' code. Replacement suggestions should be complete, correctly formatted and indented, and without line numbers."
+        }
+      }
+    }
+}
+```
+
+Example input:
+'
+## src/file1.py
+---new_hunk---
+```
+[new hunk code, annotated with line numbers]
+```
+---old_hunk---
+```
+[old hunk code]
+```
+...
+'
+
+Don't repeat the prompt in the answer, and avoid outputting the 'type' and 'description' fields.
+"""
+
+user="""PR Info:
+Title: '{{title}}'
+Branch: '{{branch}}'
+Description: '{{description}}'
+{%- if language %}
+Main language: {{language}}
+{%- endif %}
+
+
+The PR Diff:
+```
+{{diff}}
+```
+
+Response (should be a valid JSON, and nothing else):
+```json
+"""

pr_agent/settings/pr_description_prompts.toml

@@ -0,0 +1,45 @@
+[pr_description_prompt]
+system="""You are CodiumAI-PR-Reviewer, a language model designed to review git pull requests.
+Your task is to provide full description of the PR content.
+- Make sure not to focus the new PR code (the '+' lines).
+
+You must use the following JSON schema to format your answer:
+```json
+{
+  "PR Title": {
+      "type": "string",
+      "description": "an informative title for the PR, describing its main theme"
+  },
+  "Type of PR": {
+      "type": "string",
+      "enum": ["Bug fix", "Tests", "Bug fix with tests", "Refactoring", "Enhancement", "Documentation", "Other"]
+    },
+  "PR Description": {
+      "type": "string",
+      "description": "an informative and concise description of the PR"
+  },
+  "PR Main Files Walkthrough": {
+      "type": "string",
+      "description": "a walkthrough of the PR changes. Review main files, in bullet points, and shortly describe the changes in each file (up to 10 most important files). Format: -`filename`: description of changes\n..."
+  }
+}
+
+Don't repeat the prompt in the answer, and avoid outputting the 'type' and 'description' fields.
+"""
+
+user="""PR Info:
+Branch: '{{branch}}'
+{%- if language %}
+Main language: {{language}}
+{%- endif %}
+
+
+The PR Git Diff:
+```
+{{diff}}
+```
+Note that lines in the diff body are prefixed with a symbol that represents the type of change: '-' for deletions, '+' for additions, and ' ' (a space) for unchanged lines.
+
+Response (should be a valid JSON, and nothing else):
+```json
+"""

pr_agent/settings/pr_questions_prompts.toml

@@ -1,9 +1,9 @@
 [pr_questions_prompt]
 system="""You are CodiumAI-PR-Reviewer, a language model designed to review git pull requests.
 Your task is to answer questions about the new PR code (the '+' lines), and provide feedback.
-Be informative, constructive, and give examples. Try to be as specific as possible, and don't avoid answering the questions.
+Be informative, constructive, and give examples. Try to be as specific as possible.
+Don't avoid answering the questions. You must answer the questions, as best as you can, without adding unrelated content.
 Make sure not to repeat modifications already implemented in the new PR code (the '+' lines).
-Answer only the questions, and don't add unrelated content.
 """
 
 user="""PR Info:

pr_agent/settings/pr_reviewer_prompts.toml

@@ -3,9 +3,6 @@ system="""You are CodiumAI-PR-Reviewer, a language model designed to review git
 Your task is to provide constructive and concise feedback for the PR, and also provide meaningfull code suggestions to improve the new PR code (the '+' lines).
 - Provide up to {{ num_code_suggestions }} code suggestions.
 - Try to focus on important suggestions like fixing code problems, issues and bugs. As a second priority, provide suggestions for meaningfull code improvements, like performance, vulnerability, modularity, and best practices.
-{%- if extended_code_suggestions %}
-- For each suggestion, provide a short and concise code snippet to illustrate the existing code, and the improved code.
-{%- endif %}
 - Make sure not to provide suggestion repeating modifications already implemented in the new PR code (the '+' lines).
 
 You must use the following JSON schema to format your answer:
@@ -16,10 +13,6 @@ You must use the following JSON schema to format your answer:
       "type": "string",
       "description": "a short explanation of the PR"
     },
-    "Description and title": {
-      "type": "string",
-      "description": "yes\\no question: does this PR have a relevant description and title"
-    },
     "Type of PR": {
       "type": "string",
       "enum": ["Bug fix", "Tests", "Bug fix with tests", "Refactoring", "Enhancement", "Documentation", "Other"]
@@ -30,59 +23,36 @@ You must use the following JSON schema to format your answer:
       "description": "yes\\no question: does this PR have relevant tests ?"
     },
 {%- endif %}
-{%- if require_minimal_and_focused %}
+{%- if require_focused %}
-    "Minimal and focused": {
+    "Focused PR": {
       "type": "string",
-      "description": "is this PR as minimal and focused as possible, with all code changes centered around a single coherent theme, described in the PR description and title ?" Make sure to explain your answer"
+      "description": "Is this a focused PR, in the sense that it has a clear and coherent title and description, and all PR code diff changes are properly derived from the title and description? Explain your response."
     }
   },
 {%- endif %}
   "PR Feedback": {
     "General PR suggestions": {
       "type": "string",
-      "description": "important suggestions for the contributors and maintainers of this PR, may include overall structure, primary purpose and best practices. consider using specific filenames, classes and functions names. explain yourself!"
+      "description": "General suggestions and feedback for the contributors and maintainers of this PR. May include important suggestions for the overall structure, primary purpose, best practices, critical bugs, and other aspects of the PR. Explain your suggestions."
     },
     "Code suggestions": {
       "type": "array",
       "maxItems": {{ num_code_suggestions }},
       "uniqueItems": true,
       "items": {
-        "suggestion number": {
-          "type": "int",
-          "description": "suggestion number, starting from 1"
-        },
         "relevant file": {
           "type": "string",
-          "description": "the relevant file name"
+          "description": "the relevant file full path"
         },
         "suggestion content": {
           "type": "string",
-{%- if extended_code_suggestions %}
-          "description": "a concrete suggestion for meaningfully improving the new PR code. Don't repeat previous suggestions. Add tags with importance measure that matches each suggestion ('important' or 'medium'). Do not make suggestions for updating or adding docstrings, renaming PR title and description, or linter like.
-{%- else %}
           "description": "a concrete suggestion for meaningfully improving the new PR code. Also describe how, specifically, the suggestion can be applied to new PR code. Add tags with importance measure that matches each suggestion ('important' or 'medium'). Do not make suggestions for updating or adding docstrings, renaming PR title and description, or linter like.
-{%- endif %}
         },
-{%- if extended_code_suggestions %}
+        "relevant line in file": {
-        "why": {
           "type": "string",
-          "description": "shortly explain why this suggestion is important"
+          "description": "an authentic single code line from the PR git diff section, to which the suggestion applies."
-        },
-        "code example": {
-          "type": "object",
-          "properties": {
-            "before code": {
-              "type": "string",
-              "description": "Short and concise code snippet, to illustrate the existing code"
-            },
-            "after code": {
-              "type": "string",
-              "description": "Short and concise code snippet, to illustrate the improved code"
         }
       }
-        }
-{%- endif %}
-      }
     },
 {%- if require_security %}
     "Security concerns": {
@@ -101,13 +71,12 @@ Example output:
     "PR Analysis":
     {
         "Main theme": "xxx",
-        "Description and title": "Yes",
         "Type of PR": "Bug fix",
 {%- if require_tests %}
         "Relevant tests added": "No",
 {%- endif %}
-{%- if require_minimal_and_focused %}
+{%- if require_focused %}
-        "Minimal and focused": "yes\\no, because ..."
+        "Focused PR": "yes\\no, because ..."
 {%- endif %}
     },
     "PR Feedback":
@@ -115,17 +84,9 @@ Example output:
         "General PR suggestions": "..., `xxx`...",
         "Code suggestions": [
             {
-                "suggestion number": 1,
+                "relevant file": "directory/xxx.py",
-                "relevant file": "xxx.py",
                 "suggestion content": "xxx [important]",
-{%- if extended_code_suggestions %}
+                "relevant line in file": "xxx",
-                "why": "xxx",
-                "code example":
-                {
-                    "before code": "xxx",
-                    "after code": "xxx"
-                }
-{%- endif %}
             },
             ...
         ]

pr_agent/tools/pr_code_suggestions.py

@@ -0,0 +1,127 @@
+import copy
+import json
+import logging
+import textwrap
+
+from jinja2 import Environment, StrictUndefined
+
+from pr_agent.algo.ai_handler import AiHandler
+from pr_agent.algo.pr_processing import get_pr_diff
+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.git_providers import get_git_provider, GithubProvider
+from pr_agent.git_providers.git_provider import get_main_pr_language
+
+
+class PRCodeSuggestions:
+    def __init__(self, pr_url: str, cli_mode=False):
+
+        self.git_provider = get_git_provider()(pr_url)
+        self.main_language = get_main_pr_language(
+            self.git_provider.get_languages(), self.git_provider.get_files()
+        )
+        self.ai_handler = AiHandler()
+        self.patches_diff = None
+        self.prediction = None
+        self.cli_mode = cli_mode
+        self.vars = {
+            "title": self.git_provider.pr.title,
+            "branch": self.git_provider.get_pr_branch(),
+            "description": self.git_provider.get_pr_description(),
+            "language": self.main_language,
+            "diff": "",  # empty diff for initial calculation
+            'num_code_suggestions': settings.pr_code_suggestions.num_code_suggestions,
+        }
+        self.token_handler = TokenHandler(self.git_provider.pr,
+                                          self.vars,
+                                          settings.pr_code_suggestions_prompt.system,
+                                          settings.pr_code_suggestions_prompt.user)
+
+    async def suggest(self):
+        assert type(self.git_provider) == GithubProvider, "Only Github is supported for now"
+
+        logging.info('Generating code suggestions for PR...')
+        if settings.config.publish_review:
+            self.git_provider.publish_comment("Preparing review...", is_temporary=True)
+        logging.info('Getting PR diff...')
+
+        # we are using extended hunk with line numbers for code suggestions
+        self.patches_diff = get_pr_diff(self.git_provider,
+                                        self.token_handler,
+                                        add_line_numbers_to_hunks=True,
+                                        disable_extra_lines=True)
+
+        logging.info('Getting AI prediction...')
+        self.prediction = await self._get_prediction()
+        logging.info('Preparing PR review...')
+        data = self._prepare_pr_code_suggestions()
+        if settings.config.publish_review:
+            logging.info('Pushing PR review...')
+            self.git_provider.remove_initial_comment()
+            logging.info('Pushing inline code comments...')
+            self.push_inline_code_suggestions(data)
+
+
+    async def _get_prediction(self):
+        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:
+            logging.info(f"\nSystem prompt:\n{system_prompt}")
+            logging.info(f"\nUser prompt:\n{user_prompt}")
+        model = settings.config.model
+        response, finish_reason = await self.ai_handler.chat_completion(model=model, temperature=0.2,
+                                                                        system=system_prompt, user=user_prompt)
+
+        return response
+
+    def _prepare_pr_code_suggestions(self) -> str:
+        review = self.prediction.strip()
+        data = None
+        try:
+            data = json.loads(review)
+        except json.decoder.JSONDecodeError:
+            if settings.config.verbosity_level >= 2:
+                logging.info(f"Could not parse json response: {review}")
+            data = try_fix_json(review)
+        return data
+
+    def push_inline_code_suggestions(self, data):
+        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']
+            existing_code_snippet = d['existing code']
+            new_code_snippet = d['improved code']
+
+            if new_code_snippet:
+                try:  # dedent code snippet
+                    self.diff_files = self.git_provider.diff_files if self.git_provider.diff_files else self.git_provider.get_diff_files()
+                    original_initial_line = None
+                    for file in self.diff_files:
+                        if file.filename.strip() == relevant_file:
+                            original_initial_line = file.head_file.splitlines()[relevant_lines_start - 1]
+                            break
+                    if original_initial_line:
+                        suggested_initial_line = new_code_snippet.splitlines()[0]
+                        original_initial_spaces = len(original_initial_line) - len(original_initial_line.lstrip())
+                        suggested_initial_spaces = len(suggested_initial_line) - len(suggested_initial_line.lstrip())
+                        delta_spaces = original_initial_spaces - suggested_initial_spaces
+                        if delta_spaces > 0:
+                            new_code_snippet = textwrap.indent(new_code_snippet, delta_spaces * " ").rstrip('\n')
+                except Exception as e:
+                    if settings.config.verbosity_level >= 2:
+                        logging.info(f"Could not dedent code snippet for file {relevant_file}, error: {e}")
+
+            body = f"**Suggestion:** {content}\n```suggestion\n" + new_code_snippet + "\n```"
+            success = self.git_provider.publish_code_suggestion(body=body,
+                                                      relevant_file=relevant_file,
+                                                      relevant_lines_start=relevant_lines_start,
+                                                      relevant_lines_end=relevant_lines_end)

pr_agent/tools/pr_description.py

@@ -0,0 +1,83 @@
+import copy
+import json
+import logging
+
+from jinja2 import Environment, StrictUndefined
+
+from pr_agent.algo.ai_handler import AiHandler
+from pr_agent.algo.pr_processing import get_pr_diff
+from pr_agent.algo.token_handler import TokenHandler
+from pr_agent.algo.utils import convert_to_markdown
+from pr_agent.config_loader import 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):
+        self.git_provider = get_git_provider()(pr_url)
+        self.main_pr_language = get_main_pr_language(
+            self.git_provider.get_languages(), self.git_provider.get_files()
+        )
+        self.ai_handler = AiHandler()
+        self.vars = {
+            "title": self.git_provider.pr.title,
+            "branch": self.git_provider.get_pr_branch(),
+            "description": self.git_provider.get_description(),
+            "language": self.main_pr_language,
+            "diff": "",  # empty diff for initial calculation
+        }
+        self.token_handler = TokenHandler(self.git_provider.pr,
+                                          self.vars,
+                                          settings.pr_description_prompt.system,
+                                          settings.pr_description_prompt.user)
+        self.patches_diff = None
+        self.prediction = None
+
+    async def describe(self):
+        logging.info('Generating a PR description...')
+        if settings.config.publish_review:
+            self.git_provider.publish_comment("Preparing pr description...", is_temporary=True)
+        logging.info('Getting PR diff...')
+        self.patches_diff = get_pr_diff(self.git_provider, self.token_handler)
+        logging.info('Getting AI prediction...')
+        self.prediction = await self._get_prediction()
+        logging.info('Preparing answer...')
+        pr_title, pr_body = self._prepare_pr_answer()
+        if settings.config.publish_review:
+            logging.info('Pushing answer...')
+            self.git_provider.publish_description(pr_title, pr_body)
+            self.git_provider.remove_initial_comment()
+        return ""
+
+    async def _get_prediction(self):
+        variables = copy.deepcopy(self.vars)
+        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)
+        if settings.config.verbosity_level >= 2:
+            logging.info(f"\nSystem prompt:\n{system_prompt}")
+            logging.info(f"\nUser prompt:\n{user_prompt}")
+        model = settings.config.model
+        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_answer(self):
+        data = json.loads(self.prediction)
+        pr_body = ""
+        # for key, value in data.items():
+        #     markdown_text += f"## {key}\n\n"
+        #     markdown_text += f"{value}\n\n"
+        title = data['PR Title']
+        del data['PR Title']
+        for key, value in data.items():
+            pr_body += f"{key}:\n"
+            if 'walkthrough' in key.lower():
+                pr_body += f"{value}\n"
+            else:
+                pr_body += f"**{value}**\n\n___\n"
+        if settings.config.verbosity_level >= 2:
+            logging.info(f"title:\n{title}\n{pr_body}")
+        return title, pr_body

pr_agent/tools/pr_questions.py

@@ -1,6 +1,5 @@
 import copy
 import logging
-from typing import Optional
 
 from jinja2 import Environment, StrictUndefined
 
@@ -9,20 +8,22 @@ from pr_agent.algo.pr_processing import get_pr_diff
 from pr_agent.algo.token_handler import TokenHandler
 from pr_agent.config_loader import settings
 from pr_agent.git_providers import get_git_provider
+from pr_agent.git_providers.git_provider import get_main_pr_language
 
 
 class PRQuestions:
-    def __init__(self, pr_url: str, question_str: str, installation_id: Optional[int] = None):
+    def __init__(self, pr_url: str, question_str: str):
-        self.git_provider = get_git_provider()(pr_url, installation_id)
+        self.git_provider = get_git_provider()(pr_url)
-        self.main_pr_language = self.git_provider.get_main_pr_language()
+        self.main_pr_language = get_main_pr_language(
-        self.installation_id = installation_id
+            self.git_provider.get_languages(), self.git_provider.get_files()
+        )
         self.ai_handler = AiHandler()
         self.question_str = question_str
         self.vars = {
             "title": self.git_provider.pr.title,
             "branch": self.git_provider.get_pr_branch(),
-            "description": self.git_provider.pr.body,
+            "description": self.git_provider.get_description(),
-            "language": self.git_provider.get_main_pr_language(),
+            "language": self.main_pr_language,
             "diff": "",  # empty diff for initial calculation
             "questions": self.question_str,
         }

pr_agent/tools/pr_reviewer.py

@@ -1,24 +1,26 @@
 import copy
 import json
 import logging
-from typing import Optional
 
 from jinja2 import Environment, StrictUndefined
 
 from pr_agent.algo.ai_handler import AiHandler
 from pr_agent.algo.pr_processing import get_pr_diff
 from pr_agent.algo.token_handler import TokenHandler
-from pr_agent.algo.utils import convert_to_markdown
+from pr_agent.algo.utils import convert_to_markdown, try_fix_json
 from pr_agent.config_loader import settings
 from pr_agent.git_providers import get_git_provider
+from pr_agent.git_providers.git_provider import get_main_pr_language
+from pr_agent.servers.help import bot_help_text, actions_help_text
 
 
 class PRReviewer:
-    def __init__(self, pr_url: str, installation_id: Optional[int] = None, cli_mode=False):
+    def __init__(self, pr_url: str, cli_mode=False):
 
-        self.git_provider = get_git_provider()(pr_url, installation_id)
+        self.git_provider = get_git_provider()(pr_url)
-        self.main_language = self.git_provider.get_main_pr_language()
+        self.main_language = get_main_pr_language(
-        self.installation_id = installation_id
+            self.git_provider.get_languages(), self.git_provider.get_files()
+        )
         self.ai_handler = AiHandler()
         self.patches_diff = None
         self.prediction = None
@@ -26,13 +28,12 @@ class PRReviewer:
         self.vars = {
             "title": self.git_provider.pr.title,
             "branch": self.git_provider.get_pr_branch(),
-            "description": self.git_provider.pr.body,
+            "description": self.git_provider.get_pr_description(),
             "language": self.main_language,
             "diff": "",  # empty diff for initial calculation
             "require_tests": settings.pr_reviewer.require_tests_review,
             "require_security": settings.pr_reviewer.require_security_review,
-            "require_minimal_and_focused": settings.pr_reviewer.require_minimal_and_focused_review,
+            "require_focused": settings.pr_reviewer.require_focused_review,
-            'extended_code_suggestions': settings.pr_reviewer.extended_code_suggestions,
             'num_code_suggestions': settings.pr_reviewer.num_code_suggestions,
         }
         self.token_handler = TokenHandler(self.git_provider.pr,
@@ -54,6 +55,9 @@ class PRReviewer:
             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:
+                logging.info('Pushing inline code comments...')
+                self._publish_inline_code_comments()
         return ""
 
     async def _get_prediction(self):
@@ -68,11 +72,7 @@ class PRReviewer:
         model = settings.config.model
         response, finish_reason = await self.ai_handler.chat_completion(model=model, temperature=0.2,
                                                                         system=system_prompt, user=user_prompt)
-        try:
+
-            json.loads(response)
-        except json.decoder.JSONDecodeError:
-            logging.warning("Could not decode JSON")
-            response = {}
         return response
 
     def _prepare_pr_review(self) -> str:
@@ -80,8 +80,7 @@ class PRReviewer:
         try:
             data = json.loads(review)
         except json.decoder.JSONDecodeError:
-            logging.error("Unable to decode JSON response from AI")
+            data = try_fix_json(review)
-            data = {}
 
         # reordering for nicer display
         if 'PR Feedback' in data:
@@ -90,21 +89,33 @@ class PRReviewer:
                 del data['PR Feedback']['Security concerns']
                 data['PR Analysis']['Security concerns'] = val
 
+        if settings.config.git_provider == 'github' and settings.pr_reviewer.inline_code_comments:
+            del data['PR Feedback']['Code suggestions']
+
         markdown_text = convert_to_markdown(data)
         user = self.git_provider.get_user_id()
 
         if not self.cli_mode:
             markdown_text += "\n### How to use\n"
             if user and '[bot]' not in user:
-                markdown_text += f"> Tag me in a comment '@{user}' to ask for a new review after you update the PR.\n"
+                markdown_text += bot_help_text(user)
-                markdown_text += "> You can also tag me and ask any question, " \
-                                 f"for example '@{user} is the PR ready for merge?'"
             else:
-                markdown_text += "> Add a comment that says 'review' to ask for a new review " \
+                markdown_text += actions_help_text
-                                 "after you update the PR.\n"
-                markdown_text += "> You can also add a comment that says 'answer QUESTION', " \
-                                 "for example 'answer is the PR ready for merge?'"
 
         if settings.config.verbosity_level >= 2:
             logging.info(f"Markdown response:\n{markdown_text}")
         return markdown_text
+
+    def _publish_inline_code_comments(self):
+        review = self.prediction.strip()
+        try:
+            data = json.loads(review)
+        except json.decoder.JSONDecodeError:
+            data = try_fix_json(review)
+
+        for d in data['PR Feedback']['Code suggestions']:
+            relevant_file = d['relevant file'].strip()
+            relevant_line_in_file = d['relevant line in file'].strip()
+            content = d['suggestion content']
+
+            self.git_provider.publish_inline_comment(content, relevant_file, relevant_line_in_file)

requirements.txt

@@ -6,3 +6,6 @@ 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

tests/unit/test_convert_to_markdown.py

@@ -46,22 +46,19 @@ class TestConvertToMarkdown:
     def test_simple_dictionary_input(self):
         input_data = {
             'Main theme': 'Test',
-            'Description and title': 'Test description',
             'Type of PR': 'Test type',
             'Relevant tests added': 'no',
             'Unrelated changes': 'n/a',  # won't be included in the output
-            'Minimal and focused': 'Yes',
+            'Focused PR': 'Yes',
             'General PR suggestions': 'general suggestion...',
             'Code suggestions': [
                 {
-                    'Suggestion number': 1,
                     'Code example': {
                         'Before': 'Code before',
                         'After': 'Code after'
                     }
                 },
                 {
-                    'Suggestion number': 2,
                     'Code example': {
                         'Before': 'Code before 2',
                         'After': 'Code after 2'
@@ -71,15 +68,13 @@ class TestConvertToMarkdown:
         }
         expected_output = """\
 - 🎯 **Main theme:** Test
-- 🔍 **Description and title:** Test description
 - 📌 **Type of PR:** Test type
 - 🧪 **Relevant tests added:** no
-- ✨ **Minimal and focused:** Yes
+- ✨ **Focused PR:** Yes
 - 💡 **General PR suggestions:** general suggestion...
 
 - 🤖 **Code suggestions:**
 
-- **suggestion 1:**
   - **Code example:**
     - **Before:**
         ```
@@ -90,7 +85,6 @@ class TestConvertToMarkdown:
         Code after
         ```
 
-- **suggestion 2:**
   - **Code example:**
     - **Before:**
         ```
@@ -112,11 +106,10 @@ class TestConvertToMarkdown:
     def test_dictionary_input_containing_only_empty_dictionaries(self):
         input_data = {
             'Main theme': {},
-            'Description and title': {},
             'Type of PR': {},
             'Relevant tests added': {},
             'Unrelated changes': {},
-            'Minimal and focused': {},
+            'Focused PR': {},
             'General PR suggestions': {},
             'Code suggestions': {}
         }

tests/unit/test_fix_output.py

@@ -0,0 +1,83 @@
+# Generated by CodiumAI
+from pr_agent.algo.utils import try_fix_json
+
+
+import pytest
+
+class TestTryFixJson:
+    # Tests that JSON with complete 'Code suggestions' section returns expected output
+    def test_incomplete_code_suggestions(self):
+        review = '{"PR Analysis": {"Main theme": "xxx", "Type of PR": "Bug fix"}, "PR Feedback": {"General PR suggestions": "..., `xxx`...", "Code suggestions": [{"relevant file": "xxx.py", "suggestion content": "xxx [important]"}, {"suggestion number": 2, "relevant file": "yyy.py", "suggestion content": "yyy [incomp...'
+        expected_output = {
+            'PR Analysis': {
+                'Main theme': 'xxx',
+                'Type of PR': 'Bug fix'
+            },
+            'PR Feedback': {
+                'General PR suggestions': '..., `xxx`...',
+                'Code suggestions': [
+                    {
+                        'relevant file': 'xxx.py',
+                        'suggestion content': 'xxx [important]'
+                    }
+                ]
+            }
+        }
+        assert try_fix_json(review) == expected_output
+
+    def test_incomplete_code_suggestions_new_line(self):
+        review = '{"PR Analysis": {"Main theme": "xxx", "Type of PR": "Bug fix"}, "PR Feedback": {"General PR suggestions": "..., `xxx`...", "Code suggestions": [{"relevant file": "xxx.py", "suggestion content": "xxx [important]"} \n\t, {"suggestion number": 2, "relevant file": "yyy.py", "suggestion content": "yyy [incomp...'
+        expected_output = {
+            'PR Analysis': {
+                'Main theme': 'xxx',
+                'Type of PR': 'Bug fix'
+            },
+            'PR Feedback': {
+                'General PR suggestions': '..., `xxx`...',
+                'Code suggestions': [
+                    {
+                        'relevant file': 'xxx.py',
+                        'suggestion content': 'xxx [important]'
+                    }
+                ]
+            }
+        }
+        assert try_fix_json(review) == expected_output
+
+    def test_incomplete_code_suggestions_many_close_brackets(self):
+        review = '{"PR Analysis": {"Main theme": "xxx", "Type of PR": "Bug fix"}, "PR Feedback": {"General PR suggestions": "..., `xxx`...", "Code suggestions": [{"relevant file": "xxx.py", "suggestion content": "xxx [important]"} \n, {"suggestion number": 2, "relevant file": "yyy.py", "suggestion content": "yyy }, [}\n ,incomp.}  ,..'
+        expected_output = {
+            'PR Analysis': {
+                'Main theme': 'xxx',
+                'Type of PR': 'Bug fix'
+            },
+            'PR Feedback': {
+                'General PR suggestions': '..., `xxx`...',
+                'Code suggestions': [
+                    {
+                        'relevant file': 'xxx.py',
+                        'suggestion content': 'xxx [important]'
+                    }
+                ]
+            }
+        }
+        assert try_fix_json(review) == expected_output
+
+    def test_incomplete_code_suggestions_relevant_file(self):
+        review = '{"PR Analysis": {"Main theme": "xxx", "Type of PR": "Bug fix"}, "PR Feedback": {"General PR suggestions": "..., `xxx`...", "Code suggestions": [{"relevant file": "xxx.py", "suggestion content": "xxx [important]"}, {"suggestion number": 2, "relevant file": "yyy.p'
+        expected_output = {
+            'PR Analysis': {
+                'Main theme': 'xxx',
+                'Type of PR': 'Bug fix'
+            },
+            'PR Feedback': {
+                'General PR suggestions': '..., `xxx`...',
+                'Code suggestions': [
+                    {
+                        'relevant file': 'xxx.py',
+                        'suggestion content': 'xxx [important]'
+                    }
+                ]
+            }
+        }
+        assert try_fix_json(review) == expected_output

tests/unit/test_language_handler.py

@@ -1,15 +1,15 @@
 
 # Generated by CodiumAI
+
 from pr_agent.algo.language_handler import sort_files_by_main_languages
 
-
-import pytest
-
 """
 Code Analysis
 
 Objective:
-The objective of the function is to sort a list of files by their main language, putting the files that are in the main language first and the rest of the files after. It takes in a dictionary of languages and their sizes, and a list of files.
+The objective of the function is to sort a list of files by their main language, putting the files that are in the main 
+language first and the rest of the files after. It takes in a dictionary of languages and their sizes, and a list of 
+files.
 
 Inputs:
 - languages: a dictionary containing the languages and their sizes
@@ -33,6 +33,8 @@ Additional aspects:
 - The function uses the filter_bad_extensions function to filter out files with bad extensions
 - The function uses a rest_files dictionary to store the files that do not belong to any of the main extensions
 """
+
+
 class TestSortFilesByMainLanguages:
     # Tests that files are sorted by main language, with files in main language first and the rest after
     def test_happy_path_sort_files_by_main_languages(self):

tests/unit/test_parse_code_suggestion.py

@@ -41,14 +41,6 @@ class TestParseCodeSuggestion:
         expected_output = "\n"  # modified to expect a newline character
         assert parse_code_suggestion(input_data) == expected_output
 
-    # Tests that function returns correct output when 'suggestion number' key has a non-integer value
-    def test_non_integer_suggestion_number(self):
-        input_data = {
-            "Suggestion number": "one",
-            "Description": "This is a suggestion"
-        }
-        expected_output = "- **suggestion one:**\n  - **Description:** This is a suggestion\n\n"
-        assert parse_code_suggestion(input_data) == expected_output
 
     # Tests that function returns correct output when 'before' or 'after' key has a non-string value
     def test_non_string_before_or_after(self):
@@ -64,19 +56,17 @@ class TestParseCodeSuggestion:
     # Tests that function returns correct output when input dictionary does not have 'code example' key
     def test_no_code_example_key(self):
         code_suggestions = {
-            'suggestion number': 1,
             'suggestion': 'Suggestion 1',
             'description': 'Description 1',
             'before': 'Before 1',
             'after': 'After 1'
         }
-        expected_output = "- **suggestion 1:**\n  - **suggestion:** Suggestion 1\n  - **description:** Description 1\n  - **before:** Before 1\n  - **after:** After 1\n\n"  # noqa: E501
+        expected_output = "   **suggestion:** Suggestion 1\n   **description:** Description 1\n   **before:** Before 1\n   **after:** After 1\n\n"  # noqa: E501
         assert parse_code_suggestion(code_suggestions) == expected_output
 
     # Tests that function returns correct output when input dictionary has 'code example' key
     def test_with_code_example_key(self):
         code_suggestions = {
-            'suggestion number': 2,
             'suggestion': 'Suggestion 2',
             'description': 'Description 2',
             'code example': {
@@ -84,5 +74,5 @@ class TestParseCodeSuggestion:
                 'after': 'After 2'
             }
         }
-        expected_output = "- **suggestion 2:**\n  - **suggestion:** Suggestion 2\n  - **description:** Description 2\n  - **code example:**\n    - **before:**\n        ```\n        Before 2\n        ```\n    - **after:**\n        ```\n        After 2\n        ```\n\n"  # noqa: E501
+        expected_output = "   **suggestion:** Suggestion 2\n   **description:** Description 2\n  - **code example:**\n    - **before:**\n        ```\n        Before 2\n        ```\n    - **after:**\n        ```\n        After 2\n        ```\n\n"  # noqa: E501
         assert parse_code_suggestion(code_suggestions) == expected_output