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

Deployment on AWS Lambda

.dockerignore

@@ -1,2 +1,3 @@
 venv/
-pr_agent/settings/.secrets.toml
+pr_agent/settings/.secrets.toml
+pics/

INSTALL.md

@@ -149,16 +149,35 @@ git clone https://github.com/Codium-ai/pr-agent.git
 ```
 
 5. Copy the secrets template file and fill in the following:
+    ```
+    cp pr_agent/settings/.secrets_template.toml pr_agent/settings/.secrets.toml
+    # Edit .secrets.toml file
+    ```
    - Your OpenAI key.
-   - Set deployment_type to 'app'
    - Copy your app's private key to the private_key field.
    - Copy your app's ID to the app_id field.
    - Copy your app's webhook secret to the webhook_secret field.
+   - Set deployment_type to 'app' in [configuration.toml](./pr_agent/settings/configuration.toml)
 
+> The .secrets.toml file is not copied to the Docker image by default, and is only used for local development. 
+> If you want to use the .secrets.toml file in your Docker image, you can add remove it from the .dockerignore file.
+> In most production environments, you would inject the secrets file as environment variables or as mounted volumes. 
+> For example, in order to inject a secrets file as a volume in a Kubernetes environment you can update your pod spec to include the following,
+> assuming you have a secret named `pr-agent-settings` with a key named `.secrets.toml`:
+``` 
+       volumes:
+        - name: settings-volume
+          secret:
+            secretName: pr-agent-settings
+// ...
+       containers:
+// ...
+          volumeMounts:
+            - mountPath: /app/pr_agent/settings_prod
+              name: settings-volume
 ```
-cp pr_agent/settings/.secrets_template.toml pr_agent/settings/.secrets.toml
-# Edit .secrets.toml file
-```
+
+> Another option is to set the secrets as environment variables in your deployment environment, for example `OPENAI.KEY` and `GITHUB.USER_TOKEN`.
 
 6. Build a Docker image for the app and optionally push it to a Docker repository. We'll use Dockerhub as an example:
 
@@ -169,6 +188,7 @@ docker push codiumai/pr-agent:github_app  # Push to your Docker repository
 
 7. Host the app using a server, serverless function, or container environment. Alternatively, for development and
    debugging, you may use tools like smee.io to forward webhooks to your local machine.
+    You can check [Deploy as a Lambda Function](#deploy-as-a-lambda-function)
 
 8. Go back to your app's settings, and set the following:
 
@@ -178,3 +198,20 @@ docker push codiumai/pr-agent:github_app  # Push to your Docker repository
 9. Install the app by navigating to the "Install App" tab and selecting your desired repositories.
 
 ---
+
+####  Deploy as a Lambda Function
+
+1. Follow steps 1-5 of [Method 5](#method-5-run-as-a-github-app).
+2. Build a docker image that can be used as a lambda function
+    ```shell
+    docker buildx build --platform=linux/amd64 . -t codiumai/pr-agent:serverless -f docker/Dockerfile.lambda
+   ```
+3. Push image to ECR
+    ```shell
+	docker tag codiumai/pr-agent:serverless <AWS_ACCOUNT>.dkr.ecr.<AWS_REGION>.amazonaws.com/codiumai/pr-agent:serverless
+	docker push <AWS_ACCOUNT>.dkr.ecr.<AWS_REGION>.amazonaws.com/codiumai/pr-agent:serverless
+    ```
+4. Create a lambda function that uses the uploaded image. Set the lambda timeout to be at least 3m.
+5. Configure the lambda function to have a Function URL.
+6. Go back to steps 8-9 of [Method 5](#method-5-run-as-a-github-app) with the function url as your Webhook URL.
+    The Webhook URL would look like `https://<LAMBDA_FUNCTION_URL>/api/v1/github_webhooks`

PR_COMPRESSION.md

@@ -39,4 +39,4 @@ We use [tiktoken](https://github.com/openai/tiktoken) to tokenize the patches af
 4. If we haven't reached the max token length, add the `deleted files` to the prompt until the prompt reaches the max token length (hard stop), skip the rest of the patches.
 
 ### Example
-![](./pics/git_patch_logic.png)
+![](https://codium.ai/images/git_patch_logic.png)

README.md

@@ -24,28 +24,28 @@ CodiumAI `PR-Agent` is an open-source tool aiming to help developers review PRs
 
 <h3>Example results:</h2>
 </div>
-<h4>Describe:</h4>
+<h4>/describe:</h4>
 <div align="center">
 <p float="center">
-<img src="./pics/describe.gif" width="800">
+<img src="https://codium.ai/images/describe.gif" width="800">
 </p>
 </div>
-<h4>Review:</h4>
+<h4>/review:</h4>
 <div align="center">
 <p float="center">
-<img src="./pics/review.gif" width="800">
+<img src="https://codium.ai/images/review.gif" width="800">
 </p>
 </div>
-<h4>Ask:</h4>
+<h4>/ask:</h4>
 <div align="center">
 <p float="center">
-<img src="./pics/ask.gif" width="800">
+<img src="https://codium.ai/images/ask.gif" width="800">
 </p>
 </div>
-<h4>Improve:</h4>
+<h4>/improve:</h4>
 <div align="center">
 <p float="center">
-<img src="./pics/improve.gif" width="800">
+<img src="https://codium.ai/images/improve.gif" width="800">
 </p>
 </div>
 <div align="left">
@@ -62,40 +62,42 @@ CodiumAI `PR-Agent` is an open-source tool aiming to help developers review PRs
 
 ## Live demo
 
-Experience GPT-4 powered PR review on your public GitHub repository with our hosted PR-Agent. To try it, just mention `@CodiumAI-Agent` in any PR comment! The agent will generate a PR review in response.
+Experience GPT-4 powered PR review on your public GitHub repository with our hosted PR-Agent. To try it, just mention `@CodiumAI-Agent` and add the desired command in any PR comment! The agent will generate a response based on your command.
 
-![Review generation process](./pics/pr-agent-review-process1.gif)
+![Review generation process](https://codium.ai/images/demo.gif)
 
 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                                | ✓      |        |           |
+|       |                                             | GitHub | Gitlab | Bitbucket |
+|-------|---------------------------------------------|:------:|:------:|:---------:|
+| TOOLS | Review                                      |   :white_check_mark:    |   :white_check_mark:    |   :white_check_mark:       |
+|       | ⮑ Inline review                             |   :white_check_mark:    |   :white_check_mark:    |           |
+|       | Ask                                         |   :white_check_mark:    |   :white_check_mark:    |           |
+|       | Auto-Description                            |   :white_check_mark:    |  :white_check_mark:      |           |
+|       | Improve Code                                |   :white_check_mark:    |   :white_check_mark:    |           |
+|       | Reflect and Review                          |   :white_check_mark:    |                         |           |
 |       |                                             |        |        |           |
-| USAGE | CLI                                         | ✓      | ✓      | ✓         |
-|       | Tagging bot                                 | ✓      | ✓      |           |
-|       | Actions                                     | ✓      |        |           |
+| USAGE | CLI                                         |   :white_check_mark:    |   :white_check_mark:    |   :white_check_mark:       |
+|       | Tagging bot                                 |   :white_check_mark:    |   :white_check_mark:    |           |
+|       | Actions                                     |   :white_check_mark:    |        |           |
 |       |                                             |        |        |           |
-| CORE  | PR compression                              | ✓      | ✓      | ✓         |
-|       | Repo language prioritization                | ✓      | ✓      | ✓         |
-|       | Adaptive and token-aware<br />file patch fitting | ✓      | ✓      | ✓         |
+| CORE  | PR compression                              |   :white_check_mark:    |   :white_check_mark:    |   :white_check_mark:       |
+|       | Repo language prioritization                |   :white_check_mark:    |   :white_check_mark:    |   :white_check_mark:       |
+|       | Adaptive and token-aware<br />file patch fitting |   :white_check_mark:    |   :white_check_mark:    |   :white_check_mark:       |
 
 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"
+- **Reflect**:      python cli.py --pr-url=<pr_url>  reflect
 
 "<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.
+In the [configuration](./CONFIGURATION.md) file you can select your git provider (GitHub, Gitlab, Bitbucket), and further configure the different tools.
 
 ## Quickstart
 
@@ -111,25 +113,26 @@ There are several ways to use PR-Agent. Let's start with the simplest one:
 Here are several ways to install and run PR-Agent:
 
 - [Method 1: Use Docker image (no installation required)](INSTALL.md#method-1-use-docker-image-no-installation-required)
-- [Method 2: Run as a Github Action](INSTALL.md#method-2-run-as-a-github-action)
+- [Method 2: Run as a GitHub Action](INSTALL.md#method-2-run-as-a-github-action)
 - [Method 3: Run from source](INSTALL.md#method-3-run-from-source)
 - [Method 4: Run as a polling server](INSTALL.md#method-4-run-as-a-polling-server)
-  - Request reviews by tagging your Github user on a PR
-- [Method 5: Run as a Github App](INSTALL.md#method-5-run-as-a-github-app)
+  - Request reviews by tagging your GitHub user on a PR
+- [Method 5: Run as a GitHub App](INSTALL.md#method-5-run-as-a-github-app)
   - Allowing you to automate the review process on your private or public repositories
 
 ## Usage and Tools
 
-**PR-Agent** provides four types of interactions ("tools"): `"PR Reviewer"`, `"PR Q&A"`, `"PR Description"` and `"PR Code Sueggestions"`.
+**PR-Agent** provides five types of interactions ("tools"): `"PR Reviewer"`, `"PR Q&A"`, `"PR Description"`, `"PR Code Sueggestions"` and `"PR Reflect and Review"`.
 
-- The "PR Reviewer" tool automatically analyzes PRs, and provides different types of feedback.
-- The "PR Ask" tool answers free-text questions about the PR.
+- The "PR Reviewer" tool automatically analyzes PRs, and provides various types of feedback.
+- The "PR Q&A" tool answers free-text questions about the PR.
 - The "PR Description" tool automatically sets the PR Title and body.
 - The "PR Code Suggestion" tool provide inline code suggestions for the PR that can be applied and committed.
+- The "PR Reflect and Review" tool first initiates a dialog with the user and asks them to reflect on the PR, and then provides a review.
 
 ## How it works
 
-![PR-Agent Tools](./pics/pr_agent_overview.png)
+![PR-Agent Tools](https://www.codium.ai/wp-content/uploads/2023/07/codiumai-diagram-v4.jpg)
 
 Check out the [PR Compression strategy](./PR_COMPRESSION.md) page for more details on how we convert a code diff to a manageable LLM prompt
 
@@ -138,11 +141,11 @@ Check out the [PR Compression strategy](./PR_COMPRESSION.md) page for more detai
 - [ ] 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)
 - [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:
   - [x] PR description
   - [x] Inline code suggestions
+  - [x] Reflect and review
   - [ ] Enforcing CONTRIBUTING.md guidelines
   - [ ] Performance (are there any performance issues)
   - [ ] Documentation (is the PR properly documented)

docker/Dockerfile.lambda

@@ -0,0 +1,12 @@
+FROM public.ecr.aws/lambda/python:3.10
+
+RUN yum update -y && \
+    yum install -y gcc python3-devel && \
+    yum clean all
+
+ADD requirements.txt .
+RUN pip install -r requirements.txt && rm requirements.txt
+RUN pip install mangum==16.0.0
+COPY pr_agent/ ${LAMBDA_TASK_ROOT}/pr_agent/
+
+CMD ["pr_agent.servers.serverless.serverless"]

pr_agent/agent/pr_agent.py

@@ -1,7 +1,9 @@
 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_information_from_user import PRInformationFromUser
 from pr_agent.tools.pr_questions import PRQuestions
 from pr_agent.tools.pr_reviewer import PRReviewer
 
@@ -11,8 +13,13 @@ class PRAgent:
         pass
 
     async def handle_request(self, pr_url, request) -> bool:
-        if any(cmd in request for cmd in ["/review", "/review_pr"]):
-            await PRReviewer(pr_url).review()
+        if any(cmd in request for cmd in ["/answer"]):
+            await PRReviewer(pr_url, is_answer=True).review()
+        elif any(cmd in request for cmd in ["/review", "/review_pr", "/reflect_and_review"]):
+            if settings.pr_reviewer.ask_and_reflect or "/reflect_and_review" in request:
+                await PRInformationFromUser(pr_url).generate_questions()
+            else:
+                await PRReviewer(pr_url).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"]):

pr_agent/algo/git_patch_processing.py

@@ -158,7 +158,7 @@ def convert_to_hunks_with_lines_numbers(patch: str, file) -> str:
                         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):
+                    for line_old in old_content_lines:
                         patch_with_lines_str += f"{line_old}\n"
                 new_content_lines = []
                 old_content_lines = []
@@ -179,7 +179,7 @@ def convert_to_hunks_with_lines_numbers(patch: str, file) -> str:
                 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):
+            for line_old in old_content_lines:
                 patch_with_lines_str += f"{line_old}\n"
 
     return patch_with_lines_str.strip()

pr_agent/algo/language_handler.py

@@ -64,7 +64,11 @@ bad_extensions = [
 
 
 def filter_bad_extensions(files):
-    return [f for f in files if f.filename.split('.')[-1] not in bad_extensions]
+    return [f for f in files if is_valid_file(f.filename)]
+
+
+def is_valid_file(filename):
+    return filename.split('.')[-1] not in bad_extensions
 
 
 def sort_files_by_main_languages(languages: Dict, files: list):

pr_agent/algo/pr_processing.py

@@ -4,8 +4,7 @@ import difflib
 import logging
 from typing import Any, Tuple, Union
 
-from pr_agent.algo.git_patch_processing import extend_patch, handle_patch_deletions, \
-    convert_to_hunks_with_lines_numbers
+from pr_agent.algo.git_patch_processing import convert_to_hunks_with_lines_numbers, extend_patch, handle_patch_deletions
 from pr_agent.algo.language_handler import sort_files_by_main_languages
 from pr_agent.algo.token_handler import TokenHandler
 from pr_agent.config_loader import settings
@@ -30,10 +29,10 @@ def get_pr_diff(git_provider: Union[GithubProvider, Any], token_handler: TokenHa
         global PATCH_EXTRA_LINES
         PATCH_EXTRA_LINES = 0
 
-    git_provider.pr.diff_files = list(git_provider.get_diff_files())
+    diff_files = list(git_provider.get_diff_files())
 
     # get pr languages
-    pr_languages = sort_files_by_main_languages(git_provider.get_languages(), git_provider.pr.diff_files)
+    pr_languages = sort_files_by_main_languages(git_provider.get_languages(), diff_files)
 
     # generate a standard diff string, with patch extension
     patches_extended, total_tokens = pr_generate_extended_diff(pr_languages, token_handler,

pr_agent/algo/utils.py

@@ -17,6 +17,7 @@ def convert_to_markdown(output_data: dict) -> str:
         "Focused PR": "✨",
         "Security concerns": "🔒",
         "General PR suggestions": "💡",
+        "Insights from user's answers": "📝",
         "Code suggestions": "🤖"
     }
 
@@ -61,18 +62,24 @@ def parse_code_suggestion(code_suggestions: dict) -> str:
     return markdown_text
 
 
-def try_fix_json(review, max_iter=10):
+def try_fix_json(review, max_iter=10, code_suggestions=False):
+    if review.endswith("}"):
+        return fix_json_escape_char(review)
     # Try to fix JSON if it is broken/incomplete: parse until the last valid code suggestion
     data = {}
+    if code_suggestions:
+        closing_bracket = "]}"
+    else:
+        closing_bracket = "]}}"
     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] + "]}}")
+                data = json.loads(review[:last_code_suggestion_ind] + closing_bracket)
                 valid_json = True
-                review = review[:last_code_suggestion_ind].strip() + "]}}"
+                review = review[:last_code_suggestion_ind].strip() + closing_bracket
             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
@@ -82,3 +89,17 @@ def try_fix_json(review, max_iter=10):
             logging.error("Unable to decode JSON response from AI")
             data = {}
     return data
+
+
+def fix_json_escape_char(json_message=None):
+    try:
+        result = json.loads(json_message)
+    except Exception as e:
+        # Find the offending character index:
+        idx_to_replace = int(str(e).split(' ')[-1].replace(')', ''))
+        # Remove the offending character:
+        json_message = list(json_message)
+        json_message[idx_to_replace] = ' '
+        new_message = ''.join(json_message)
+        return fix_json_escape_char(json_message=new_message)
+    return result

pr_agent/cli.py

@@ -5,32 +5,37 @@ import os
 
 from pr_agent.tools.pr_code_suggestions import PRCodeSuggestions
 from pr_agent.tools.pr_description import PRDescription
+from pr_agent.tools.pr_information_from_user import PRInformationFromUser
 from pr_agent.tools.pr_questions import PRQuestions
 from pr_agent.tools.pr_reviewer import PRReviewer
 
 
-def run():
+def run(args=None):
     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"
+- cli.py --pr-url=... review
+- cli.py --pr-url=... describe
+- cli.py --pr-url=... improve
+- cli.py --pr-url=... ask "write me a poem about this PR"
+- cli.py --pr-url=... reflect
 
 Supported commands:
 review / review_pr - Add a review that includes a summary of the PR and specific suggestions for improvement.
 ask / ask_question [question] - Ask a question about the PR.
 describe / describe_pr - Modify the PR title and description based on the PR's contents.
 improve / improve_code - Suggest improvements to the code in the PR as pull request comments ready to commit.
+reflect - Ask the PR author questions about the PR.
 """)
     parser.add_argument('--pr_url', type=str, help='The URL of the PR to review', required=True)
     parser.add_argument('command', type=str, help='The', choices=['review', 'review_pr',
                                                                   'ask', 'ask_question',
                                                                   'describe', 'describe_pr',
-                                                                  'improve', 'improve_code'], default='review')
+                                                                  'improve', 'improve_code',
+                                                                  'reflect', 'review_after_reflect'],
+                        default='review')
     parser.add_argument('rest', nargs=argparse.REMAINDER, default=[])
-    args = parser.parse_args()
+    args = parser.parse_args(args)
     logging.basicConfig(level=os.environ.get("LOGLEVEL", "INFO"))
     command = args.command.lower()
     if command in ['ask', 'ask_question']:
@@ -54,6 +59,14 @@ improve / improve_code - Suggest improvements to the code in the PR as pull requ
         print(f"Reviewing PR: {args.pr_url}")
         reviewer = PRReviewer(args.pr_url, cli_mode=True)
         asyncio.run(reviewer.review())
+    elif command in ['reflect']:
+        print(f"Asking the PR author questions: {args.pr_url}")
+        reviewer = PRInformationFromUser(args.pr_url)
+        asyncio.run(reviewer.generate_questions())
+    elif command in ['review_after_reflect']:
+        print(f"Processing author's answers and sending review: {args.pr_url}")
+        reviewer = PRReviewer(args.pr_url, cli_mode=True, is_answer=True)
+        asyncio.run(reviewer.review())
     else:
         print(f"Unknown command: {command}")
         parser.print_help()

pr_agent/config_loader.py

@@ -13,6 +13,7 @@ settings = Dynaconf(
          "settings/pr_questions_prompts.toml",
          "settings/pr_description_prompts.toml",
          "settings/pr_code_suggestions_prompts.toml",
+         "settings/pr_information_from_user_prompts.toml",
          "settings_prod/.secrets.toml"
         ]]
 )

pr_agent/git_providers/__init__.py

@@ -1,7 +1,7 @@
 from pr_agent.config_loader import settings
+from pr_agent.git_providers.bitbucket_provider import BitbucketProvider
 from pr_agent.git_providers.github_provider import GithubProvider
 from pr_agent.git_providers.gitlab_provider import GitLabProvider
-from pr_agent.git_providers.bitbucket_provider import BitbucketProvider
 
 _GIT_PROVIDERS = {
     'github': GithubProvider,

pr_agent/git_providers/bitbucket_provider.py

@@ -1,5 +1,4 @@
 import logging
-from datetime import datetime
 from typing import Optional, Tuple
 from urllib.parse import urlparse
 
@@ -10,6 +9,7 @@ from pr_agent.config_loader import settings
 
 from .git_provider import FilePatchInfo
 
+
 class BitbucketProvider:
     def __init__(self, pr_url: Optional[str] = None):
         s = requests.Session()
@@ -25,6 +25,11 @@ class BitbucketProvider:
         if pr_url:
             self.set_pr(pr_url)
 
+    def is_supported(self, capability: str) -> bool:
+        if capability in ['get_issue_comments', 'create_inline_comment', 'publish_inline_comments']:
+            return False
+        return True
+
     def set_pr(self, pr_url: str):
         self.workspace_slug, self.repo_slug, self.pr_num = self._parse_pr_url(pr_url)
         self.pr = self._get_pr()
@@ -40,7 +45,8 @@ class BitbucketProvider:
         for index, diff in enumerate(diffs):
             original_file_content_str = self._get_pr_file_content(diff.old.get_data('links'))
             new_file_content_str = self._get_pr_file_content(diff.new.get_data('links'))
-            diff_files.append(FilePatchInfo(original_file_content_str, new_file_content_str, diff_split[index], diff.new.path))
+            diff_files.append(FilePatchInfo(original_file_content_str, new_file_content_str,
+                                            diff_split[index], diff.new.path))
         return diff_files
 
     def publish_comment(self, pr_comment: str, is_temporary: bool = False):
@@ -58,12 +64,15 @@ class BitbucketProvider:
     def publish_inline_comment(self, body: str, relevant_file: str, relevant_line_in_file: str):
         pass
 
+    def create_inline_comment(self, body: str, relevant_file: str, relevant_line_in_file: str):
+        raise NotImplementedError("Bitbucket provider does not support creating inline comments yet")
+
+    def publish_inline_comments(self, comments: list[dict]):
+        raise NotImplementedError("Bitbucket provider does not support publishing inline comments yet")
+
     def get_title(self):
         return self.pr.title
 
-    def get_description(self):
-        return self.pr.body
-
     def get_languages(self):
         languages = {self._get_repo().get_data('language'): 0}
         return languages
@@ -77,6 +86,9 @@ class BitbucketProvider:
     def get_user_id(self):
         return 0
 
+    def get_issue_comments(self):
+        raise NotImplementedError("Bitbucket provider does not support issue comments yet")
+
     @staticmethod
     def _parse_pr_url(pr_url: str) -> Tuple[str, int]:
         parsed_url = urlparse(pr_url)

pr_agent/git_providers/git_provider.py

@@ -3,12 +3,15 @@ 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
@@ -21,6 +24,10 @@ class FilePatchInfo:
 
 
 class GitProvider(ABC):
+    @abstractmethod
+    def is_supported(self, capability: str) -> bool:
+        pass
+
     @abstractmethod
     def get_diff_files(self) -> list[FilePatchInfo]:
         pass
@@ -37,6 +44,14 @@ class GitProvider(ABC):
     def publish_inline_comment(self, body: str, relevant_file: str, relevant_line_in_file: str):
         pass
 
+    @abstractmethod
+    def create_inline_comment(self, body: str, relevant_file: str, relevant_line_in_file: str):
+        pass
+
+    @abstractmethod
+    def publish_inline_comments(self, comments: list[dict]):
+        pass
+
     @abstractmethod
     def publish_code_suggestion(self, body: str, relevant_file: str,
                                 relevant_lines_start: int, relevant_lines_end: int):
@@ -62,6 +77,10 @@ class GitProvider(ABC):
     def get_pr_description(self):
         pass
 
+    @abstractmethod
+    def get_issue_comments(self):
+        pass
+
 
 def get_main_pr_language(languages, files) -> str:
     """

pr_agent/git_providers/github_provider.py

@@ -3,11 +3,12 @@ from datetime import datetime
 from typing import Optional, Tuple
 from urllib.parse import urlparse
 
-from github import AppAuthentication, Github
+from github import AppAuthentication, Github, Auth
 
 from pr_agent.config_loader import settings
 
 from .git_provider import FilePatchInfo, GitProvider
+from ..algo.language_handler import is_valid_file
 
 
 class GithubProvider(GitProvider):
@@ -23,6 +24,9 @@ class GithubProvider(GitProvider):
             self.set_pr(pr_url)
             self.last_commit_id = list(self.pr.get_commits())[-1]
 
+    def is_supported(self, capability: str) -> bool:
+        return True
+
     def set_pr(self, pr_url: str):
         self.repo, self.pr_num = self._parse_pr_url(pr_url)
         self.pr = self._get_pr()
@@ -34,9 +38,10 @@ class GithubProvider(GitProvider):
         files = self.pr.get_files()
         diff_files = []
         for file in files:
-            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))
+            if is_valid_file(file.filename):
+                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
 
@@ -54,6 +59,9 @@ class GithubProvider(GitProvider):
         self.pr.comments_list.append(response)
 
     def publish_inline_comment(self, body: str, relevant_file: str, relevant_line_in_file: str):
+        self.publish_inline_comments([self.create_inline_comment(body, relevant_file, relevant_line_in_file)])
+
+    def create_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:
@@ -64,7 +72,7 @@ class GithubProvider(GitProvider):
                     if relevant_line_in_file in line:
                         position = i
                         break
-                    elif relevant_line_in_file[0] == '+' and relevant_line_in_file[1:] in line:
+                    elif relevant_line_in_file[0] == '+' and relevant_line_in_file[1:].lstrip() 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
@@ -72,9 +80,16 @@ class GithubProvider(GitProvider):
         if position == -1:
             if settings.config.verbosity_level >= 2:
                 logging.info(f"Could not find position for {relevant_file} {relevant_line_in_file}")
+            subject_type = "FILE"
         else:
-            path = relevant_file.strip()
-            self.pr.create_review_comment(body=body, commit_id=self.last_commit_id, path=path, position=position)
+            subject_type = "LINE"
+        path = relevant_file.strip()
+        # placeholder for future API support (already supported in single inline comment)
+        # return dict(body=body, path=path, position=position, subject_type=subject_type)
+        return dict(body=body, path=path, position=position) if subject_type == "LINE" else {}
+
+    def publish_inline_comments(self, comments: list[dict]):
+        self.pr.create_review(commit=self.last_commit_id, comments=comments)
 
     def publish_code_suggestion(self, body: str,
                                 relevant_file: str,
@@ -134,9 +149,6 @@ class GithubProvider(GitProvider):
     def get_title(self):
         return self.pr.title
 
-    def get_description(self):
-        return self.pr.body
-
     def get_languages(self):
         languages = self._get_repo().get_languages()
         return languages
@@ -164,6 +176,9 @@ class GithubProvider(GitProvider):
         notifications = self.github_client.get_user().get_notifications(since=since)
         return notifications
 
+    def get_issue_comments(self):
+        return self.pr.get_issue_comments()
+
     @staticmethod
     def _parse_pr_url(pr_url: str) -> Tuple[str, int]:
         parsed_url = urlparse(pr_url)
@@ -215,7 +230,7 @@ class GithubProvider(GitProvider):
                 raise ValueError(
                     "GitHub token is required when using user deployment. See: "
                     "https://github.com/Codium-ai/pr-agent#method-2-run-from-source") from e
-            return Github(token)
+            return Github(auth=Auth.Token(token))
 
     def _get_repo(self):
         return self.github_client.get_repo(self.repo)

pr_agent/git_providers/gitlab_provider.py

@@ -4,10 +4,12 @@ from typing import Optional, Tuple
 from urllib.parse import urlparse
 
 import gitlab
+from gitlab import GitlabGetError
 
 from pr_agent.config_loader import settings
 
-from .git_provider import FilePatchInfo, GitProvider, EDIT_TYPE
+from .git_provider import EDIT_TYPE, FilePatchInfo, GitProvider
+from ..algo.language_handler import is_valid_file
 
 
 class GitLabProvider(GitProvider):
@@ -28,6 +30,13 @@ class GitLabProvider(GitProvider):
         self.diff_files = None
         self.temp_comments = []
         self._set_merge_request(merge_request_url)
+        self.RE_HUNK_HEADER = re.compile(
+            r"^@@ -(\d+)(?:,(\d+))? \+(\d+)(?:,(\d+))? @@[ ]?(.*)")
+
+    def is_supported(self, capability: str) -> bool:
+        if capability in ['get_issue_comments', 'create_inline_comment', 'publish_inline_comments']:
+            return False
+        return True
 
     @property
     def pr(self):
@@ -40,31 +49,39 @@ class GitLabProvider(GitProvider):
         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()
+        try:
+            return self.gl.projects.get(self.id_project).files.get(file_path, branch).decode()
+        except GitlabGetError:
+            # In case of file creation the method returns GitlabGetError (404 file not found).
+            # In this case we return an empty string for the diff.
+            return ''
 
     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']))
+            if is_valid_file(diff['new_path']):
+                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:
+                    if isinstance(original_file_content_str, bytes):
+                        original_file_content_str = bytes.decode(original_file_content_str, 'utf-8')
+                    if isinstance(new_file_content_str, bytes):
+                        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
 
@@ -72,8 +89,12 @@ class GitLabProvider(GitProvider):
         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
+        try:
+            self.mr.title = pr_title
+            self.mr.description = pr_body
+            self.mr.save()
+        except Exception as e:
+            logging.exception(f"Could not update merge request {self.id_mr} description: {e}")
 
     def publish_comment(self, mr_comment: str, is_temporary: bool = False):
         comment = self.mr.notes.create({'body': mr_comment})
@@ -84,25 +105,32 @@ class GitLabProvider(GitProvider):
         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)
+        self.send_inline_comment(body, edit_type, found, relevant_file, relevant_line_in_file, source_line_no,
+                                 target_file, target_line_no)
+
+    def create_inline_comment(self, body: str, relevant_file: str, relevant_line_in_file: str):
+        raise NotImplementedError("Gitlab provider does not support creating inline comments yet")
+
+    def create_inline_comment(self, comments: list[dict]):
+        raise NotImplementedError("Gitlab provider does not support publishing inline comments yet")
+
+    def send_inline_comment(self, body, edit_type, found, relevant_file, relevant_line_in_file, source_line_no,
+                            target_file, target_line_no):
         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}
+                       '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
+                pos_obj['old_line'] = source_line_no - 1
             elif edit_type == 'addition':
-                pos_obj['new_line'] = position
+                pos_obj['new_line'] = target_line_no - 1
             else:
-                pos_obj['new_line'] = position
-                pos_obj['old_line'] = position
+                pos_obj['new_line'] = target_line_no - 1
+                pos_obj['old_line'] = source_line_no - 1
             self.mr.discussions.create({'body': body,
                                         'position': pos_obj})
 
@@ -110,47 +138,67 @@ class GitLabProvider(GitProvider):
                                 relevant_file: str,
                                 relevant_lines_start: int,
                                 relevant_lines_end: int):
-        raise "not implemented yet for gitlab"
+        self.diff_files = self.diff_files if self.diff_files else self.get_diff_files()
+        target_file = None
+        for file in self.diff_files:
+            if file.filename == relevant_file:
+                if file.filename == relevant_file:
+                    target_file = file
+                    break
+        range = relevant_lines_end - relevant_lines_start + 1
+        body = body.replace('```suggestion', f'```suggestion:-0+{range}')
+
+        lines = target_file.head_file.splitlines()
+        relevant_line_in_file = lines[relevant_lines_start - 1]
+        edit_type, found, source_line_no, target_file, target_line_no = self.find_in_file(target_file,
+                                                                                          relevant_line_in_file)
+        self.send_inline_comment(body, edit_type, found, relevant_file, relevant_line_in_file, source_line_no,
+                                 target_file, target_line_no)
 
     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
+                edit_type, found, source_line_no, target_file, target_line_no = self.find_in_file(file,
+                                                                                                  relevant_line_in_file)
+        return edit_type, found, source_line_no, target_file, target_line_no
+
+    def find_in_file(self, file, relevant_line_in_file):
+        edit_type = 'context'
+        source_line_no = 0
+        target_line_no = 0
+        found = False
+        target_file = file
+        patch = file.patch
+        patch_lines = patch.splitlines()
+        for line in patch_lines:
+            if line.startswith('@@'):
+                match = self.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:].lstrip() 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):
@@ -171,9 +219,6 @@ class GitLabProvider(GitProvider):
     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
@@ -184,6 +229,9 @@ class GitLabProvider(GitProvider):
     def get_pr_description(self):
         return self.mr.description
 
+    def get_issue_comments(self):
+        raise NotImplementedError("GitLab provider does not support issue comments yet")
+
     def _parse_merge_request_url(self, merge_request_url: str) -> Tuple[int, int]:
         parsed_url = urlparse(merge_request_url)
 

pr_agent/servers/github_action_runner.py

@@ -1,12 +1,9 @@
 import asyncio
 import json
 import os
-import re
 
+from pr_agent.agent.pr_agent import PRAgent
 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
 
 
@@ -53,20 +50,7 @@ async def run_action():
                 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}")
+                    await PRAgent().handle_request(pr_url, body)
 
 
 if __name__ == '__main__':

pr_agent/servers/github_polling.py

@@ -1,6 +1,5 @@
 import asyncio
 import logging
-import re
 import sys
 from datetime import datetime, timezone
 
@@ -10,10 +9,6 @@ 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"
@@ -103,5 +98,6 @@ async def polling_loop():
             except Exception as e:
                 logging.error(f"Exception during processing of a notification: {e}")
 
+
 if __name__ == '__main__':
     asyncio.run(polling_loop())

pr_agent/servers/serverless.py

@@ -0,0 +1,18 @@
+import logging
+
+from fastapi import FastAPI
+from mangum import Mangum
+
+from pr_agent.servers.github_app import router
+
+logger = logging.getLogger()
+logger.setLevel(logging.DEBUG)
+
+app = FastAPI()
+app.include_router(router)
+
+handler = Mangum(app, lifespan="off")
+
+
+def serverless(event, context):
+    return handler(event, context)

pr_agent/settings/configuration.toml

@@ -1,7 +1,7 @@
 [config]
 model="gpt-4-0613"
 git_provider="github"
-publish_review=true
+publish_output=true
 verbosity_level=0 # 0,1,2
 
 [pr_reviewer]
@@ -10,6 +10,10 @@ require_tests_review=true
 require_security_review=true
 num_code_suggestions=3
 inline_code_comments = true
+ask_and_reflect=false
+
+[pr_description]
+publish_description_as_comment=false
 
 [pr_questions]
 

pr_agent/settings/pr_information_from_user_prompts.toml

@@ -0,0 +1,34 @@
+[pr_information_from_user_prompt]
+system="""You are CodiumAI-PR-Reviewer, a language model designed to review git pull requests.
+Given the PR Info and the PR Git Diff, generate 3 short questions about the PR code for the PR author.
+The goal of the questions is to help the language model understand the PR better, so the questions should be insightful, informative, non-trivial, and relevant to the PR.
+You should prefer asking yes\\no questions, or multiple choice questions. Also add at least one open-ended question, but make sure they are not too difficult, and can be answered in a sentence or two.
+
+
+Example output:
+'
+Questions to better understand the PR:
+1) ...
+2) ...
+...
+'
+"""
+
+user="""PR Info:
+Title: '{{title}}'
+Branch: '{{branch}}'
+Description: '{{description}}'
+{%- 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:
+"""

pr_agent/settings/pr_reviewer_prompts.toml

@@ -2,8 +2,11 @@
 system="""You are CodiumAI-PR-Reviewer, a language model designed to review git pull requests.
 Your task is to provide constructive and concise feedback for the PR, and also provide meaningfull code suggestions to improve the new PR code (the '+' lines).
 - Provide up to {{ num_code_suggestions }} code suggestions.
+{%- if num_code_suggestions > 0 %}
 - 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.
+- Suggestions should focus on improving the new added code lines.
 - Make sure not to provide suggestions repeating modifications already implemented in the new PR code (the '+' lines).
+{%- endif %}
 
 You must use the following JSON schema to format your answer:
 ```json
@@ -23,6 +26,12 @@ You must use the following JSON schema to format your answer:
       "description": "yes\\no question: does this PR have relevant tests ?"
     },
 {%- endif %}
+{%- if question_str %}
+    "Insights from user's answer": {
+      "type": "string",
+      "description": "shortly summarize the insights you gained from the user's answers to the questions"
+    },
+{%- endif %}
 {%- if require_focused %}
     "Focused PR": {
       "type": "string",
@@ -35,6 +44,7 @@ You must use the following JSON schema to format your answer:
       "type": "string",
       "description": "General suggestions and feedback for the contributors and maintainers of this PR. May include important suggestions for the overall structure, primary purpose, best practices, critical bugs, and other aspects of the PR. Explain your suggestions."
     },
+{%- if num_code_suggestions > 0 %}
     "Code suggestions": {
       "type": "array",
       "maxItems": {{ num_code_suggestions }},
@@ -54,6 +64,7 @@ You must use the following JSON schema to format your answer:
         }
       }
     },
+{%- endif %}
 {%- if require_security %}
     "Security concerns": {
       "type": "string",
@@ -82,6 +93,7 @@ Example output:
     "PR Feedback":
     {
         "General PR suggestions": "..., `xxx`...",
+{%- if num_code_suggestions > 0 %}
         "Code suggestions": [
             {
                 "relevant file": "directory/xxx.py",
@@ -90,6 +102,7 @@ Example output:
             },
             ...
         ]
+{%- endif %}
 {%- if require_security %},
        "Security concerns": "No, because ..."
 {%- endif %}
@@ -108,6 +121,16 @@ Description: '{{description}}'
 Main language: {{language}}
 {%- endif %}
 
+{%- if question_str %}
+######
+Here are questions to better understand the PR. Use the answers to provide better feedback.
+
+{{question_str|trim}}
+
+User answers:
+{{answer_str|trim}}
+######
+{%- endif %}
 
 The PR Git Diff:
 ```

pr_agent/tools/pr_code_suggestions.py

@@ -8,9 +8,9 @@ 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.algo.utils import 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 import BitbucketProvider, get_git_provider
 from pr_agent.git_providers.git_provider import get_main_pr_language
 
 
@@ -39,10 +39,10 @@ class PRCodeSuggestions:
                                           settings.pr_code_suggestions_prompt.user)
 
     async def suggest(self):
-        assert type(self.git_provider) == GithubProvider, "Only Github is supported for now"
+        assert type(self.git_provider) != BitbucketProvider, "Bitbucket is not supported for now"
 
         logging.info('Generating code suggestions for PR...')
-        if settings.config.publish_review:
+        if settings.config.publish_output:
             self.git_provider.publish_comment("Preparing review...", is_temporary=True)
         logging.info('Getting PR diff...')
 
@@ -56,13 +56,12 @@ class PRCodeSuggestions:
         self.prediction = await self._get_prediction()
         logging.info('Preparing PR review...')
         data = self._prepare_pr_code_suggestions()
-        if settings.config.publish_review:
+        if settings.config.publish_output:
             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
@@ -86,7 +85,7 @@ class PRCodeSuggestions:
         except json.decoder.JSONDecodeError:
             if settings.config.verbosity_level >= 2:
                 logging.info(f"Could not parse json response: {review}")
-            data = try_fix_json(review)
+            data = try_fix_json(review, code_suggestions=True)
         return data
 
     def push_inline_code_suggestions(self, data):
@@ -98,12 +97,12 @@ class PRCodeSuggestions:
             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()
+                    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:
@@ -121,7 +120,7 @@ class PRCodeSuggestions:
                         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,
+            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

@@ -7,7 +7,6 @@ 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
@@ -23,7 +22,7 @@ class PRDescription:
         self.vars = {
             "title": self.git_provider.pr.title,
             "branch": self.git_provider.get_pr_branch(),
-            "description": self.git_provider.get_description(),
+            "description": self.git_provider.get_pr_description(),
             "language": self.main_pr_language,
             "diff": "",  # empty diff for initial calculation
         }
@@ -36,17 +35,20 @@ class PRDescription:
 
     async def describe(self):
         logging.info('Generating a PR description...')
-        if settings.config.publish_review:
+        if settings.config.publish_output:
             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:
+        pr_title, pr_body, markdown_text = self._prepare_pr_answer()
+        if settings.config.publish_output:
             logging.info('Pushing answer...')
-            self.git_provider.publish_description(pr_title, pr_body)
+            if settings.pr_description.publish_description_as_comment:
+                self.git_provider.publish_comment(markdown_text)
+            else:
+                self.git_provider.publish_description(pr_title, pr_body)
             self.git_provider.remove_initial_comment()
         return ""
 
@@ -66,10 +68,11 @@ class PRDescription:
 
     def _prepare_pr_answer(self):
         data = json.loads(self.prediction)
+        markdown_text = ""
+        for key, value in data.items():
+            markdown_text += f"## {key}\n\n"
+            markdown_text += f"{value}\n\n"
         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():
@@ -80,4 +83,4 @@ class PRDescription:
                 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
+        return title, pr_body, markdown_text

pr_agent/tools/pr_information_from_user.py

@@ -0,0 +1,71 @@
+import copy
+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.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 PRInformationFromUser:
+    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_pr_description(),
+            "language": self.main_pr_language,
+            "diff": "",  # empty diff for initial calculation
+        }
+        self.token_handler = TokenHandler(self.git_provider.pr,
+                                          self.vars,
+                                          settings.pr_information_from_user_prompt.system,
+                                          settings.pr_information_from_user_prompt.user)
+        self.patches_diff = None
+        self.prediction = None
+
+    async def generate_questions(self):
+        logging.info('Generating question to the user...')
+        if settings.config.publish_output:
+            self.git_provider.publish_comment("Preparing questions...", 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 questions...')
+        pr_comment = self._prepare_pr_answer()
+        if settings.config.publish_output:
+            logging.info('Pushing questions...')
+            self.git_provider.publish_comment(pr_comment)
+            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_information_from_user_prompt.system).render(variables)
+        user_prompt = environment.from_string(settings.pr_information_from_user_prompt.user).render(variables)
+        if settings.config.verbosity_level >= 2:
+            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) -> str:
+        model_output = self.prediction.strip()
+        if settings.config.verbosity_level >= 2:
+            logging.info(f"answer_str:\n{model_output}")
+        answer_str = f"{model_output}\n\n Please respond to the questions above in the following format:\n\n" +\
+                     "\n>/answer\n>1) ...\n>2) ...\n>...\n"
+        return answer_str

pr_agent/tools/pr_questions.py

@@ -22,7 +22,7 @@ class PRQuestions:
         self.vars = {
             "title": self.git_provider.pr.title,
             "branch": self.git_provider.get_pr_branch(),
-            "description": self.git_provider.get_description(),
+            "description": self.git_provider.get_pr_description(),
             "language": self.main_pr_language,
             "diff": "",  # empty diff for initial calculation
             "questions": self.question_str,
@@ -36,7 +36,7 @@ class PRQuestions:
 
     async def answer(self):
         logging.info('Answering a PR question...')
-        if settings.config.publish_review:
+        if settings.config.publish_output:
             self.git_provider.publish_comment("Preparing answer...", is_temporary=True)
         logging.info('Getting PR diff...')
         self.patches_diff = get_pr_diff(self.git_provider, self.token_handler)
@@ -44,7 +44,7 @@ class PRQuestions:
         self.prediction = await self._get_prediction()
         logging.info('Preparing answer...')
         pr_comment = self._prepare_pr_answer()
-        if settings.config.publish_review:
+        if settings.config.publish_output:
             logging.info('Pushing answer...')
             self.git_provider.publish_comment(pr_comment)
             self.git_provider.remove_initial_comment()

pr_agent/tools/pr_reviewer.py

@@ -11,16 +11,20 @@ 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
+from pr_agent.servers.help import actions_help_text, bot_help_text
 
 
 class PRReviewer:
-    def __init__(self, pr_url: str, cli_mode=False):
+    def __init__(self, pr_url: str, cli_mode=False, is_answer: bool = 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.is_answer = is_answer
+        if self.is_answer and not self.git_provider.is_supported("get_issue_comments"):
+            raise Exception(f"Answer mode is not supported for {settings.config.git_provider} for now")
+        answer_str, question_str = self._get_user_answers()
         self.ai_handler = AiHandler()
         self.patches_diff = None
         self.prediction = None
@@ -35,6 +39,9 @@ class PRReviewer:
             "require_security": settings.pr_reviewer.require_security_review,
             "require_focused": settings.pr_reviewer.require_focused_review,
             'num_code_suggestions': settings.pr_reviewer.num_code_suggestions,
+            #
+            'question_str': question_str,
+            'answer_str': answer_str,
         }
         self.token_handler = TokenHandler(self.git_provider.pr,
                                           self.vars,
@@ -43,15 +50,15 @@ class PRReviewer:
 
     async def review(self):
         logging.info('Reviewing PR...')
-        if settings.config.publish_review:
-                self.git_provider.publish_comment("Preparing review...", is_temporary=True)
+        if settings.config.publish_output:
+            self.git_provider.publish_comment("Preparing review...", 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 PR review...')
         pr_comment = self._prepare_pr_review()
-        if settings.config.publish_review:
+        if settings.config.publish_output:
             logging.info('Pushing PR review...')
             self.git_provider.publish_comment(pr_comment)
             self.git_provider.remove_initial_comment()
@@ -89,8 +96,16 @@ 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']
+        if settings.config.git_provider != 'bitbucket' and \
+                settings.pr_reviewer.inline_code_comments and \
+                'Code suggestions' in data['PR Feedback']:
+            # keeping only code suggestions that can't be submitted as inline comments
+            data['PR Feedback']['Code suggestions'] = [
+                d for d in data['PR Feedback']['Code suggestions']
+                if any(key not in d for key in ('relevant file', 'relevant line in file', 'suggestion content'))
+            ]
+            if not data['PR Feedback']['Code suggestions']:
+                del data['PR Feedback']['Code suggestions']
 
         markdown_text = convert_to_markdown(data)
         user = self.git_provider.get_user_id()
@@ -107,15 +122,43 @@ class PRReviewer:
         return markdown_text
 
     def _publish_inline_code_comments(self):
+        if settings.pr_reviewer.num_code_suggestions == 0:
+            return
+
         review = self.prediction.strip()
         try:
             data = json.loads(review)
         except json.decoder.JSONDecodeError:
             data = try_fix_json(review)
 
+        comments = []
         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']
+            relevant_file = d.get('relevant file', '').strip()
+            relevant_line_in_file = d.get('relevant line in file', '').strip()
+            content = d.get('suggestion content', '')
+            if not relevant_file or not relevant_line_in_file or not content:
+                logging.info("Skipping inline comment with missing file/line/content")
+                continue
 
-            self.git_provider.publish_inline_comment(content, relevant_file, relevant_line_in_file)
+            if self.git_provider.is_supported("create_inline_comment"):
+                comment = self.git_provider.create_inline_comment(content, relevant_file, relevant_line_in_file)
+                if comment:
+                    comments.append(comment)
+            else:
+                self.git_provider.publish_inline_comment(content, relevant_file, relevant_line_in_file)
+
+        if comments:
+            self.git_provider.publish_inline_comments(comments)
+
+    def _get_user_answers(self):
+        answer_str = question_str = ""
+        if self.is_answer:
+            discussion_messages = self.git_provider.get_issue_comments()
+            for message in discussion_messages.reversed:
+                if "Questions to better understand the PR:" in message.body:
+                    question_str = message.body
+                elif '/answer' in message.body:
+                    answer_str = message.body
+                if answer_str and question_str:
+                    break
+        return question_str, answer_str

requirements.txt

@@ -1,6 +1,6 @@
 dynaconf==3.1.12
 fastapi==0.99.0
-PyGithub==1.58.2
+PyGithub==1.59.*
 retry==0.9.2
 openai==0.27.8
 Jinja2==3.1.2

tests/unit/test_fix_output.py

@@ -1,13 +1,12 @@
 # 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...'
+        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...'  # noqa: E501
         expected_output = {
             'PR Analysis': {
                 'Main theme': 'xxx',
@@ -26,7 +25,7 @@ class TestTryFixJson:
         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...'
+        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...'  # noqa: E501
         expected_output = {
             'PR Analysis': {
                 'Main theme': 'xxx',
@@ -45,7 +44,7 @@ class TestTryFixJson:
         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.}  ,..'
+        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.}  ,..'  # noqa: E501
         expected_output = {
             'PR Analysis': {
                 'Main theme': 'xxx',
@@ -64,7 +63,7 @@ class TestTryFixJson:
         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'
+        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'  # noqa: E501
         expected_output = {
             'PR Analysis': {
                 'Main theme': 'xxx',