Merge pull request #404 from Codium-ai/tr/final_fixes

final fixes
2025-07-08 06:40:39 +08:00 · 2023-10-29 12:31:40 +02:00 · 2023-10-29 12:29:14 +02:00 · 2023-10-29 11:40:36 +02:00 · 2023-10-29 02:34:18 -07:00 · 2023-10-29 10:58:42 +02:00
57 changed files with 966 additions and 524 deletions
--- a/Dockerfile.bitbucket_pipeline
+++ b/Dockerfile.bitbucket_pipeline
@ -1,18 +0,0 @@
-FROM python:3.10 as base
-
-ENV OPENAI_API_KEY=${OPENAI_API_KEY} \
-    BITBUCKET_BEARER_TOKEN=${BITBUCKET_BEARER_TOKEN} \
-    BITBUCKET_PR_ID=${BITBUCKET_PR_ID} \
-    BITBUCKET_REPO_SLUG=${BITBUCKET_REPO_SLUG} \
-    BITBUCKET_WORKSPACE=${BITBUCKET_WORKSPACE}
-
-
-WORKDIR /app
-ADD pyproject.toml .
-ADD requirements.txt .
-RUN pip install . && rm pyproject.toml requirements.txt
-ENV PYTHONPATH=/app
-ADD pr_agent pr_agent
-ADD bitbucket_pipeline/entrypoint.sh /
-RUN chmod +x /entrypoint.sh
-ENTRYPOINT ["/entrypoint.sh"]
--- a/INSTALL.md
+++ b/INSTALL.md
@ -4,66 +4,69 @@
 To get started with PR-Agent quickly, you first need to acquire two tokens:

 1. An OpenAI key from [here](https://platform.openai.com/), with access to GPT-4.
-2. A GitHub personal access token (classic) with the repo scope.
+2. A GitHub\GitLab\BitBucket personal access token (classic) with the repo scope.

 There are several ways to use PR-Agent:

- [Method 1: Use Docker image (no installation required)](INSTALL.md#method-1-use-docker-image-no-installation-required)
- [Method 2: Run from source](INSTALL.md#method-2-run-from-source)
- [Method 3: Run as a GitHub Action](INSTALL.md#method-3-run-as-a-github-action)
- [Method 4: Run as a polling server](INSTALL.md#method-4-run-as-a-polling-server)
- [Method 5: Run as a GitHub App](INSTALL.md#method-5-run-as-a-github-app)
- [Method 6: Deploy as a Lambda Function](INSTALL.md#method-6---deploy-as-a-lambda-function)
- [Method 7: AWS CodeCommit](INSTALL.md#method-7---aws-codecommit-setup)
- [Method 8: Run a GitLab webhook server](INSTALL.md#method-8---run-a-gitlab-webhook-server)
- [Method 9: Run as a Bitbucket Pipeline](INSTALL.md#method-9-run-as-a-bitbucket-pipeline)
+**Locally**
+- [Using Docker image (no installation required)](INSTALL.md#use-docker-image-no-installation-required)
+- [Run from source](INSTALL.md#run-from-source)
+
+**GitHub specific methods**
+- [Run as a GitHub Action](INSTALL.md#run-as-a-github-action)
+- [Run as a polling server](INSTALL.md#run-as-a-polling-server)
+- [Run as a GitHub App](INSTALL.md#run-as-a-github-app)
+- [Deploy as a Lambda Function](INSTALL.md#deploy-as-a-lambda-function)
+- [AWS CodeCommit](INSTALL.md#aws-codecommit-setup)
+
+**GitLab specific methods**
+- [Run a GitLab webhook server](INSTALL.md#run-a-gitlab-webhook-server)
+
+**BitBucket specific methods**
+- [Run as a Bitbucket Pipeline](INSTALL.md#run-as-a-bitbucket-pipeline)
+- [Run on a hosted app](INSTALL.md#run-on-a-hosted-bitbucket-app)
 ---

-### Method 1: Use Docker image (no installation required)
+### Use Docker image (no installation required)

 To request a review for a PR, or ask a question about a PR, you can run directly from the Docker image. Here's how:

-1. To request a review for a PR, run the following command:
-
 For GitHub:
 ```
-docker run --rm -it -e OPENAI.KEY=<your key> -e GITHUB.USER_TOKEN=<your token> codiumai/pr-agent --pr_url <pr_url> review
+docker run --rm -it -e OPENAI.KEY=<your key> -e GITHUB.USER_TOKEN=<your token> codiumai/pr-agent:latest --pr_url <pr_url> review
 ```
 For GitLab:
 ```
-docker run --rm -it -e OPENAI.KEY=<your key> -e CONFIG.GIT_PROVIDER=gitlab -e GITLAB.PERSONAL_ACCESS_TOKEN=<your token> codiumai/pr-agent --pr_url <pr_url> review
+docker run --rm -it -e OPENAI.KEY=<your key> -e CONFIG.GIT_PROVIDER=gitlab -e GITLAB.PERSONAL_ACCESS_TOKEN=<your token> codiumai/pr-agent:latest --pr_url <pr_url> review
 ```
+For BitBucket:
+```
+docker run --rm -it -e CONFIG.GIT_PROVIDER=bitbucket -e OPENAI.KEY=$OPENAI_API_KEY -e BITBUCKET.BEARER_TOKEN=$BITBUCKET_BEARER_TOKEN codiumai/pr-agent:latest --pr_url=<pr_url> review
+```
+
 For other git providers, update CONFIG.GIT_PROVIDER accordingly, and check the `pr_agent/settings/.secrets_template.toml` file for the environment variables expected names and values.

-2. To ask a question about a PR, run the following command:

+Similarly, 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> ask "<your question>"
 ```
-Note: If you want to ensure you're running a specific version of the Docker image, consider using the image's digest.
-The digest is a unique identifier for a specific version of an image. You can pull and run an image using its digest by referencing it like so: repository@sha256:digest. Always ensure you're using the correct and trusted digest for your operations.

-1. To request a review for a PR using a specific digest, run the following command:
+A list of the relevant tools can be found in the [tools guide](./docs/TOOLS_GUIDE.md).
+
+
+Note: If you want to ensure you're running a specific version of the Docker image, consider using the image's digest:
 ```bash
 docker run --rm -it -e OPENAI.KEY=<your key> -e GITHUB.USER_TOKEN=<your token> codiumai/pr-agent@sha256:71b5ee15df59c745d352d84752d01561ba64b6d51327f97d46152f0c58a5f678 --pr_url <pr_url> review
 ```
-
-2. To ask a question about a PR using the same digest, run the following command:
-```bash
-docker run --rm -it -e OPENAI.KEY=<your key> -e GITHUB.USER_TOKEN=<your token> codiumai/pr-agent@sha256:71b5ee15df59c745d352d84752d01561ba64b6d51327f97d46152f0c58a5f678 --pr_url <pr_url> ask "<your question>"
+in addition, you can run a [specific released versions](./RELEASE_NOTES.md) of pr-agent, for example:
+```
+codiumai/pr-agent@v0.8
 ```
-
-Possible questions you can ask include:
-
- What is the main theme of this PR?
- Is the PR ready for merge?
- What are the main changes in this PR?
- Should this PR be split into smaller parts?
- Can you compose a rhymed song about this PR?

 ---

-### Method 2: Run from source
+### Run from source

 1. Clone this repository:

@ -93,11 +96,14 @@ python3 -m pr_agent.cli --pr_url <pr_url> review
 python3 -m pr_agent.cli --pr_url <pr_url> ask <your question>
 python3 -m pr_agent.cli --pr_url <pr_url> describe
 python3 -m pr_agent.cli --pr_url <pr_url> improve
+python3 -m pr_agent.cli --pr_url <pr_url> add_docs
+python3 -m pr_agent.cli --issue_url <issue_url> similar_issue
+...
 ```

 ---

-### Method 3: Run as a GitHub Action
+### Run as a GitHub Action

 You can use our pre-built Github Action Docker image to run PR-Agent as a Github Action.

@ -167,10 +173,11 @@ When you open your next PR, you should see a comment from `github-actions` bot w

 ---

-### Method 4: Run as a polling server
-Request reviews by tagging your Github user on a PR
+### Run as a polling server
+Request reviews by tagging your GitHub user on a PR
+
+Follow [steps 1-3](#run-as-a-github-action) of the GitHub Action setup.

-Follow steps 1-3 of method 2.
 Run the following command to start the server:

 ```
@ -179,7 +186,7 @@ python pr_agent/servers/github_polling.py

 ---

-### Method 5: Run as a GitHub App
+### Run as a GitHub App
 Allowing you to automate the review process on your private or public repositories.

 1. Create a GitHub App from the [Github Developer Portal](https://docs.github.com/en/developers/apps/creating-a-github-app).
@ -260,13 +267,13 @@ 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.

 > **Note:** When running PR-Agent from GitHub App, the default configuration file (configuration.toml) will be loaded.<br>
-> However, you can override the default tool parameters by uploading a local configuration file<br>
-> For more information please check out [CONFIGURATION.md](Usage.md#working-from-github-app-pre-built-repo)
+> However, you can override the default tool parameters by uploading a local configuration file `.pr_agent.toml`<br>
+> For more information please check out the [USAGE GUIDE](./Usage.md#working-with-github-app)
 ---

-### Method 6 - Deploy as a Lambda Function
+### Deploy as a Lambda Function

-1. Follow steps 1-5 of [Method 5](#method-5-run-as-a-github-app).
+1. Follow steps 1-5 of [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
@ -278,12 +285,12 @@ docker push codiumai/pr-agent:github_app  # Push to your Docker repository
    ```
 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.
+6. Go back to steps 8-9 of [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`

 ---

-### Method 7 - AWS CodeCommit Setup
+### AWS CodeCommit Setup

 Not all features have been added to CodeCommit yet.  As of right now, CodeCommit has been implemented to run the pr-agent CLI on the command line, using AWS credentials stored in environment variables.  (More features will be added in the future.)  The following is a set of instructions to have pr-agent do a review of your CodeCommit pull request from the command line:

@ -353,7 +360,7 @@ PYTHONPATH="/PATH/TO/PROJECTS/pr-agent" python pr_agent/cli.py \

 ---

-### Method 8 - Run a GitLab webhook server
+### Run a GitLab webhook server

 1. From the GitLab workspace or group, create an access token. Enable the "api" scope only.
 2. Generate a random secret for your app, and save it for later. For example, you can use:
@ -372,62 +379,36 @@ In the "Trigger" section, check the ‘comments’ and ‘merge request events



-### Method 9: Run as a Bitbucket Pipeline
+### Run as a Bitbucket Pipeline


-You can use our pre-build Bitbucket-Pipeline docker image to run as Bitbucket-Pipeline.
+You can use the Bitbucket Pipeline system to run PR-Agent on every pull request open or update.

 1. Add the following file in your repository bitbucket_pipelines.yml

 ```yaml
-  pipelines:
+pipelines:
    pull-requests:
      '**':
        - step:
-            name: PR Agent Pipeline
-            caches:
-              - pip
-            image: python:3.8
+            name: PR Agent Review
+            image: python:3.10
            services:
              - docker
            script:
-              - git clone https://github.com/Codium-ai/pr-agent.git
-              - cd pr-agent
-              - docker build -t bitbucket_runner:latest -f Dockerfile.bitbucket_pipeline .
-              - docker run -e OPENAI_API_KEY=$OPENAI_API_KEY -e BITBUCKET_BEARER_TOKEN=$BITBUCKET_BEARER_TOKEN -e BITBUCKET_PR_ID=$BITBUCKET_PR_ID -e BITBUCKET_REPO_SLUG=$BITBUCKET_REPO_SLUG -e BITBUCKET_WORKSPACE=$BITBUCKET_WORKSPACE bitbucket_runner:latest
+              - docker run -e CONFIG.GIT_PROVIDER=bitbucket -e OPENAI.KEY=$OPENAI_API_KEY -e BITBUCKET.BEARER_TOKEN=$BITBUCKET_BEARER_TOKEN codiumai/pr-agent:latest --pr_url=https://bitbucket.org/$BITBUCKET_WORKSPACE/$BITBUCKET_REPO_SLUG/pull-requests/$BITBUCKET_PR_ID review
 ```

-2. Add the following secret to your repository under Repository settings > Pipelines > Repository variables.
+2. Add the following secure variables to your repository under Repository settings > Pipelines > Repository variables.
 OPENAI_API_KEY: <your key>
 BITBUCKET_BEARER_TOKEN: <your token>

-3. To get BITBUCKET_BEARER_TOKEN follow these steps
-  So here is my step by step tutorial
-  i) Insert your workspace name instead of {workspace_name} and go to the following link in order to create an OAuth consumer.
-
-      https://bitbucket.org/{workspace_name}/workspace/settings/api
-
-      set callback URL to http://localhost:8976 (doesn't need to be a real server there)
-      select permissions: repository -> read
-
-  ii) use consumer's Key as a {client_id} and open the following URL in the browser
-
-      https://bitbucket.org/site/oauth2/authorize?client_id={client_id}&response_type=code
-
-  iii)
-      after you press "Grant access" in the browser it will redirect you to
-
-      http://localhost:8976?code=<CODE>
-
-  iv) use the code from the previous step and consumer's Key as a {client_id}, and consumer's Secret as {client_secret}
-
-      curl -X POST -u "{client_id}:{client_secret}" \
-          https://bitbucket.org/site/oauth2/access_token \
-          -d grant_type=authorization_code \
-          -d code={code} \
+You can get a Bitbucket token for your repository by following Repository Settings -> Security -> Access Tokens.


-After completing this steps, you just to place this access token in the repository varibles.
+### Run on a hosted Bitbucket app
+
+Please contact <support@codium.ai> if you're interested in a hosted BitBucket app solution that provides full functionality including PR reviews and comment handling. It's based on the [bitbucket_app.py](https://github.com/Codium-ai/pr-agent/blob/main/pr_agent/git_providers/bitbucket_provider.py) implmentation.


 =======
--- a/README.md
+++ b/README.md
@ -28,16 +28,16 @@ CodiumAI `PR-Agent` is an open-source tool aiming to help developers review pull
 \
 ‣ **Update Changelog ([`/update_changelog`](./docs/UPDATE_CHANGELOG.md))**: Automatically updating the CHANGELOG.md file with the PR changes.
 \
-‣ **Find similar issue ([`/similar_issue`](./docs/SIMILAR_ISSUE.md))**: Automatically retrieves and presents similar issues
+‣ **Find Similar Issue ([`/similar_issue`](./docs/SIMILAR_ISSUE.md))**: Automatically retrieves and presents similar issues
 \
 ‣ **Add Documentation ([`/add_docs`](./docs/ADD_DOCUMENTATION.md))**: Automatically adds documentation to un-documented functions/classes in the PR.

-See the [Usage Guide](./Usage.md) for instructions how to run the different tools from _CLI_, _online usage_, Or by _automatically triggering_ them when a new PR is opened.
+See the [Installation Guide](./INSTALL.md) for instructions how to install and run the tool on different platforms.
+
+See the [Usage Guide](./Usage.md) for instructions how to run the different tools from _CLI_, _online usage_, or by _automatically triggering_ them when a new PR is opened.

 See the [Tools Guide](./docs/TOOLS_GUIDE.md) for detailed description of the different tools.

-See the [Release notes](./RELEASE_NOTES.md) for updates on the latest changes.
-
 <h3>Example results:</h3>
 </div>
 <h4><a href="https://github.com/Codium-ai/pr-agent/pull/229#issuecomment-1687561986">/describe:</a></h4>
@ -204,6 +204,9 @@ Here are some advantages of PR-Agent:
  - [x] Documentation (is the PR properly documented)
  - [ ] ...

+See the [Release notes](./RELEASE_NOTES.md) for updates on the latest changes.
+
+
 ## Similar Projects

 - [CodiumAI - Meaningful tests for busy devs](https://github.com/Codium-ai/codiumai-vscode-release) (although various capabilities are much more advanced in the CodiumAI IDE plugins)
@ -211,7 +214,12 @@ Here are some advantages of PR-Agent:
 - [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)
-  
+
+## Data Privacy
+
+If you use self-host PR-Agent, e.g. via CLI running on your computer, with your OpenAI API key, it is between you and OpenAI. You can read their API data privacy policy here:
+https://openai.com/enterprise-privacy
+
 ## Links

 [![Join our Discord community](https://raw.githubusercontent.com/Codium-ai/codiumai-vscode-release/main/media/docs/Joincommunity.png)](https://discord.gg/kG35uSHDBc)
--- a/Usage.md
+++ b/Usage.md
@ -12,7 +12,7 @@

 ### Introduction

-See the **[installation guide](/INSTALL.md)** for instructions on how to setup PR-Agent. After installation, there are three basic ways to invoke CodiumAI PR-Agent:
+After [installation](/INSTALL.md), there are three basic ways to invoke CodiumAI PR-Agent:
 1. Locally running a CLI command
 2. Online usage - by [commenting](https://github.com/Codium-ai/pr-agent/pull/229#issuecomment-1695021901) on a PR
 3. Enabling PR-Agent tools to run automatically when a new PR is opened
--- a/bitbucket_pipeline/entrypoint.sh
+++ b/bitbucket_pipeline/entrypoint.sh
@ -1,2 +0,0 @@
-#!/bin/bash
-python /app/pr_agent/servers/bitbucket_pipeline_runner.py
--- a/docs/DESCRIBE.md
+++ b/docs/DESCRIBE.md
@ -27,18 +27,14 @@ Under the section 'pr_description', the [configuration file](./../pr_agent/setti

 - `extra_instructions`: Optional extra instructions to the tool. For example: "focus on the changes in the file X. Ignore change in ...".

-#### Markers template
+### Markers template

 markers enable to easily integrate user's content and auto-generated content, with a template-like mechanism.

- `use_description_markers`: if set to true, the tool will use markers template. It replaces every marker of the form `pr_agent:marker_name` with the relevant content. Default is false.
-
 For example, if the PR original description was:
 ```
 User content...

-## PR Type:
-pr_agent:pr_type

 ## PR Description:
 pr_agent:summary
@ -46,6 +42,21 @@ pr_agent:summary
 ## PR Walkthrough:
 pr_agent:walkthrough
 ```
-The marker `pr_agent:pr_type` will be replaced with the PR type, `pr_agent:summary` will be replaced with the PR summary, and `pr_agent:walkthrough` will be replaced with the PR walkthrough.
+The marker `pr_agent:summary` will be replaced with the PR summary, and `pr_agent:walkthrough` will be replaced with the PR walkthrough.

+##### Example:
+```
+        env:
+          pr_description.use_description_markers: 'true'
+```          
+
+<kbd><img src=./../pics/describe_markers_before.png width="768"></kbd>
+
+==>
+
+<kbd><img src=./../pics/describe_markers_after.png width="768"></kbd>
+
+##### Configuration params:
+
+- `use_description_markers`: if set to true, the tool will use markers template. It replaces every marker of the form `pr_agent:marker_name` with the relevant content. Default is false.
 - `include_generated_by_header`: if set to true, the tool will add a dedicated header: 'Generated by PR Agent at ...' to any automatic content. Default is true.
--- a/docs/GENERATE_CUSTOM_LABELS.md
+++ b/docs/GENERATE_CUSTOM_LABELS.md
@ -0,0 +1,35 @@
+# Generate Custom Labels
+The `generte_labels` tool scans the PR code changes, and given a list of labels and their descriptions, it automatically suggests labels that match the PR code changes.
+
+It can be invoked manually by commenting on any PR:
+```
+/generate_labels
+```
+For example:
+
+If we wish to add detect changes to SQL queries in a given PR, we can add the following custom label along with its description:
+
+<kbd><img src=./../pics/custom_labels_list.png width="768"></kbd>
+When running the `generte_labels` tool on a PR that includes changes in SQL queries, it will automatically suggest the custom label:
+<kbd><img src=./../pics/custom_label_published.png width="768"></kbd>
+
+### Configuration options
+To enable custom labels, you need to add the following configuration to the [custom_labels file](./../pr_agent/settings/custom_labels.toml):
+ - Change `enable_custom_labels` to True: This will turn off the default labels and enable the custom labels provided in the custom_labels.toml file.
+ - Add the custom labels to the custom_labels.toml file. It should be formatted as follows:
+ ```
+[custom_labels."Custom Label Name"]
+description = "Description of when AI should suggest this label"
+```
+ - You can add modify the list to include all the custom labels you wish to use in your repository.
+
+#### Github Action
+To use the `generte_labels` tool with Github Action:
+
+- Add the following file to your repository under `env` section in `.github/workflows/pr_agent.yml`
+- Comma separated list of custom labels and their descriptions
+- The number of labels and descriptions should be the same and in the same order (empty descriptions are allowed):
+```
+CUSTOM_LABELS: "label1, label2, ..."
+CUSTOM_LABELS_DESCRIPTION: "label1 description, label2 description, ..."
+```
--- a/docs/IMPROVE.md
+++ b/docs/IMPROVE.md
@ -31,4 +31,15 @@ Under the section 'pr_code_suggestions', the [configuration file](./../pr_agent/
 - `num_code_suggestions_per_chunk`: number of code suggestions provided by the 'improve' tool, per chunk. Default is 8.
 - `rank_extended_suggestions`: if set to true, the tool will rank the suggestions, based on importance. Default is true.
 - `max_number_of_calls`: maximum number of chunks. Default is 5.
- `final_clip_factor`: factor to remove suggestions with low confidence. Default is 0.9.
+- `final_clip_factor`: factor to remove suggestions with low confidence. Default is 0.9.
+
+
+#### A note on code suggestions quality
+
+- With current level of AI for code (GPT-4), mistakes can happen. Not all the suggestions will be perfect, and a user should not accept all of them automatically.
+
+- Suggestions are not meant to be [simplistic](./../pr_agent/settings/pr_code_suggestions_prompts.toml#L34). Instead, they aim to give deep feedback and raise questions, ideas and thoughts to the user, who can then use his judgment, experience, and understanding of the code base.
+
+- Recommended to use the 'extra_instructions' field to guide the model to suggestions that are more relevant to the specific needs of the project.
+
+- Best quality will be obtained by using 'improve --extended' mode.
--- a/docs/REVIEW.md
+++ b/docs/REVIEW.md
@ -43,4 +43,15 @@ The tool will first ask the author questions about the PR, and will guide the re

 <kbd><img src=./../pics/reflection_questions.png width="768"></kbd>
 <kbd><img src=./../pics/reflection_answers.png width="768"></kbd>
-<kbd><img src=./../pics/reflection_insights.png width="768"></kbd>
+<kbd><img src=./../pics/reflection_insights.png width="768"></kbd>
+
+
+#### A note on code suggestions quality
+
+- With current level of AI for code (GPT-4), mistakes can happen. Not all the suggestions will be perfect, and a user should not accept all of them automatically.
+
+- Suggestions are not meant to be [simplistic](./../pr_agent/settings/pr_reviewer_prompts.toml#L29). Instead, they aim to give deep feedback and raise questions, ideas and thoughts to the user, who can then use his judgment, experience, and understanding of the code base.
+
+- Recommended to use the 'extra_instructions' field to guide the model to suggestions that are more relevant to the specific needs of the project.
+
+- Unlike the 'review' feature, which does a lot of things, the ['improve --extended'](./IMPROVE.md) feature is dedicated only to suggestions, and usually gives better results.
--- a/pics/custom_label_published.png
+++ b/pics/custom_label_published.png
--- a/pics/custom_labels_list.png
+++ b/pics/custom_labels_list.png
--- a/pics/describe_markers_after.png
+++ b/pics/describe_markers_after.png
--- a/pics/describe_markers_before.png
+++ b/pics/describe_markers_before.png
--- a/pr_agent/agent/pr_agent.py
+++ b/pr_agent/agent/pr_agent.py
@ -1,20 +1,18 @@
-import logging
-import os
 import shlex
-import tempfile

 from pr_agent.algo.utils import update_settings_from_args
 from pr_agent.config_loader import get_settings
-from pr_agent.git_providers import get_git_provider
+from pr_agent.git_providers.utils import apply_repo_settings
 from pr_agent.tools.pr_add_docs import PRAddDocs
 from pr_agent.tools.pr_code_suggestions import PRCodeSuggestions
+from pr_agent.tools.pr_config import PRConfig
 from pr_agent.tools.pr_description import PRDescription
+from pr_agent.tools.pr_generate_labels import PRGenerateLabels
 from pr_agent.tools.pr_information_from_user import PRInformationFromUser
-from pr_agent.tools.pr_similar_issue import PRSimilarIssue
 from pr_agent.tools.pr_questions import PRQuestions
 from pr_agent.tools.pr_reviewer import PRReviewer
+from pr_agent.tools.pr_similar_issue import PRSimilarIssue
 from pr_agent.tools.pr_update_changelog import PRUpdateChangelog
-from pr_agent.tools.pr_config import PRConfig

 command2class = {
    "auto_review": PRReviewer,
@ -34,6 +32,7 @@ command2class = {
    "settings": PRConfig,
    "similar_issue": PRSimilarIssue,
    "add_docs": PRAddDocs,
+    "generate_labels": PRGenerateLabels,
 }

 commands = list(command2class.keys())
@ -44,22 +43,7 @@ class PRAgent:

    async def handle_request(self, pr_url, request, notify=None) -> bool:
        # First, apply repo specific settings if exists
-        if get_settings().config.use_repo_settings_file:
-            repo_settings_file = None
-            try:
-                git_provider = get_git_provider()(pr_url)
-                repo_settings = git_provider.get_repo_settings()
-                if repo_settings:
-                    repo_settings_file = None
-                    fd, repo_settings_file = tempfile.mkstemp(suffix='.toml')
-                    os.write(fd, repo_settings)
-                    get_settings().load_file(repo_settings_file)
-            finally:
-                if repo_settings_file:
-                    try:
-                        os.remove(repo_settings_file)
-                    except Exception as e:
-                        logging.error(f"Failed to remove temporary settings file {repo_settings_file}", e)
+        apply_repo_settings(pr_url)

        # Then, apply user specific settings if exists
        request = request.replace("'", "\\'")
@ -84,3 +68,4 @@ class PRAgent:
        else:
            return False
        return True
+
--- a/pr_agent/algo/ai_handler.py
+++ b/pr_agent/algo/ai_handler.py
@ -1,4 +1,3 @@
-import logging
 import os

 import litellm
@ -7,6 +6,8 @@ from litellm import acompletion
 from openai.error import APIError, RateLimitError, Timeout, TryAgain
 from retry import retry
 from pr_agent.config_loader import get_settings
+from pr_agent.log import get_logger
+
 OPENAI_RETRIES = 5


@ -88,34 +89,34 @@ class AiHandler:
        try:
            deployment_id = self.deployment_id
            if get_settings().config.verbosity_level >= 2:
-                logging.debug(
+                get_logger().debug(
                    f"Generating completion with {model}"
                    f"{(' from deployment ' + deployment_id) if deployment_id else ''}"
                )
            if self.azure:
                model = 'azure/' + model
+            messages = [{"role": "system", "content": system}, {"role": "user", "content": user}]
            response = await acompletion(
                model=model,
                deployment_id=deployment_id,
-                messages=[
-                    {"role": "system", "content": system},
-                    {"role": "user", "content": user}
-                ],
+                messages=messages,
                temperature=temperature,
                force_timeout=get_settings().config.ai_timeout
            )
        except (APIError, Timeout, TryAgain) as e:
-            logging.error("Error during OpenAI inference: ", e)
+            get_logger().error("Error during OpenAI inference: ", e)
            raise
        except (RateLimitError) as e:
-            logging.error("Rate limit error during OpenAI inference: ", e)
+            get_logger().error("Rate limit error during OpenAI inference: ", e)
            raise
        except (Exception) as e:
-            logging.error("Unknown error during OpenAI inference: ", e)
+            get_logger().error("Unknown error during OpenAI inference: ", e)
            raise TryAgain from e
        if response is None or len(response["choices"]) == 0:
            raise TryAgain
        resp = response["choices"][0]['message']['content']
        finish_reason = response["choices"][0]["finish_reason"]
-        print(resp, finish_reason)
+        usage = response.get("usage")
+        get_logger().info("AI response", response=resp, messages=messages, finish_reason=finish_reason,
+                          model=model, usage=usage)
        return resp, finish_reason
--- a/pr_agent/algo/git_patch_processing.py
+++ b/pr_agent/algo/git_patch_processing.py
@ -1,8 +1,9 @@
 from __future__ import annotations
-import logging
+
 import re

 from pr_agent.config_loader import get_settings
+from pr_agent.log import get_logger


 def extend_patch(original_file_str, patch_str, num_lines) -> str:
@ -63,7 +64,7 @@ def extend_patch(original_file_str, patch_str, num_lines) -> str:
            extended_patch_lines.append(line)
    except Exception as e:
        if get_settings().config.verbosity_level >= 2:
-            logging.error(f"Failed to extend patch: {e}")
+            get_logger().error(f"Failed to extend patch: {e}")
        return patch_str

    # finish previous hunk
@ -134,14 +135,14 @@ def handle_patch_deletions(patch: str, original_file_content_str: str,
    if not new_file_content_str:
        # logic for handling deleted files - don't show patch, just show that the file was deleted
        if get_settings().config.verbosity_level > 0:
-            logging.info(f"Processing file: {file_name}, minimizing deletion file")
+            get_logger().info(f"Processing file: {file_name}, minimizing deletion file")
        patch = None # file was deleted
    else:
        patch_lines = patch.splitlines()
        patch_new = omit_deletion_hunks(patch_lines)
        if patch != patch_new:
            if get_settings().config.verbosity_level > 0:
-                logging.info(f"Processing file: {file_name}, hunks were deleted")
+                get_logger().info(f"Processing file: {file_name}, hunks were deleted")
            patch = patch_new
    return patch

--- a/pr_agent/algo/pr_processing.py
+++ b/pr_agent/algo/pr_processing.py
@ -1,7 +1,6 @@
 from __future__ import annotations

 import difflib
-import logging
 import re
 import traceback
 from typing import Any, Callable, List, Tuple
@ -15,6 +14,7 @@ from pr_agent.algo.file_filter import filter_ignored
 from pr_agent.algo.token_handler import TokenHandler, get_token_encoder
 from pr_agent.config_loader import get_settings
 from pr_agent.git_providers.git_provider import FilePatchInfo, GitProvider
+from pr_agent.log import get_logger

 DELETED_FILES_ = "Deleted files:\n"

@ -51,7 +51,7 @@ def get_pr_diff(git_provider: GitProvider, token_handler: TokenHandler, model: s
    try:
        diff_files = git_provider.get_diff_files()
    except RateLimitExceededException as e:
-        logging.error(f"Rate limit exceeded for git provider API. original message {e}")
+        get_logger().error(f"Rate limit exceeded for git provider API. original message {e}")
        raise

    diff_files = filter_ignored(diff_files)
@ -180,7 +180,7 @@ def pr_generate_compressed_diff(top_langs: list, token_handler: TokenHandler, mo

        # Hard Stop, no more tokens
        if total_tokens > MAX_TOKENS[model] - OUTPUT_BUFFER_TOKENS_HARD_THRESHOLD:
-            logging.warning(f"File was fully skipped, no more tokens: {file.filename}.")
+            get_logger().warning(f"File was fully skipped, no more tokens: {file.filename}.")
            continue

        # If the patch is too large, just show the file name
@ -189,7 +189,7 @@ def pr_generate_compressed_diff(top_langs: list, token_handler: TokenHandler, mo
            # TODO: Option for alternative logic to remove hunks from the patch to reduce the number of tokens
            #  until we meet the requirements
            if get_settings().config.verbosity_level >= 2:
-                logging.warning(f"Patch too large, minimizing it, {file.filename}")
+                get_logger().warning(f"Patch too large, minimizing it, {file.filename}")
            if not modified_files_list:
                total_tokens += token_handler.count_tokens(MORE_MODIFIED_FILES_)
            modified_files_list.append(file.filename)
@ -204,7 +204,7 @@ def pr_generate_compressed_diff(top_langs: list, token_handler: TokenHandler, mo
            patches.append(patch_final)
            total_tokens += token_handler.count_tokens(patch_final)
            if get_settings().config.verbosity_level >= 2:
-                logging.info(f"Tokens: {total_tokens}, last filename: {file.filename}")
+                get_logger().info(f"Tokens: {total_tokens}, last filename: {file.filename}")

    return patches, modified_files_list, deleted_files_list

@ -218,7 +218,7 @@ async def retry_with_fallback_models(f: Callable):
            get_settings().set("openai.deployment_id", deployment_id)
            return await f(model)
        except Exception as e:
-            logging.warning(
+            get_logger().warning(
                f"Failed to generate prediction with {model}"
                f"{(' from deployment ' + deployment_id) if deployment_id else ''}: "
                f"{traceback.format_exc()}"
@ -340,7 +340,7 @@ def clip_tokens(text: str, max_tokens: int) -> str:
        clipped_text = text[:num_output_chars]
        return clipped_text
    except Exception as e:
-        logging.warning(f"Failed to clip tokens: {e}")
+        get_logger().warning(f"Failed to clip tokens: {e}")
        return text


@ -367,7 +367,7 @@ def get_pr_multi_diffs(git_provider: GitProvider,
    try:
        diff_files = git_provider.get_diff_files()
    except RateLimitExceededException as e:
-        logging.error(f"Rate limit exceeded for git provider API. original message {e}")
+        get_logger().error(f"Rate limit exceeded for git provider API. original message {e}")
        raise

    diff_files = filter_ignored(diff_files)
@ -387,7 +387,7 @@ def get_pr_multi_diffs(git_provider: GitProvider,
    for file in sorted_files:
        if call_number > max_calls:
            if get_settings().config.verbosity_level >= 2:
-                logging.info(f"Reached max calls ({max_calls})")
+                get_logger().info(f"Reached max calls ({max_calls})")
            break

        original_file_content_str = file.base_file
@ -410,13 +410,13 @@ def get_pr_multi_diffs(git_provider: GitProvider,
            total_tokens = token_handler.prompt_tokens
            call_number += 1
            if get_settings().config.verbosity_level >= 2:
-                logging.info(f"Call number: {call_number}")
+                get_logger().info(f"Call number: {call_number}")

        if patch:
            patches.append(patch)
            total_tokens += new_patch_tokens
            if get_settings().config.verbosity_level >= 2:
-                logging.info(f"Tokens: {total_tokens}, last filename: {file.filename}")
+                get_logger().info(f"Tokens: {total_tokens}, last filename: {file.filename}")

    # Add the last chunk
    if patches:
--- a/pr_agent/algo/utils.py
+++ b/pr_agent/algo/utils.py
@ -2,7 +2,6 @@ from __future__ import annotations

 import difflib
 import json
-import logging
 import re
 import textwrap
 from datetime import datetime
@ -11,6 +10,7 @@ from typing import Any, List
 import yaml
 from starlette_context import context
 from pr_agent.config_loader import get_settings, global_settings
+from pr_agent.log import get_logger


 def get_setting(key: str) -> Any:
@ -159,7 +159,7 @@ def try_fix_json(review, max_iter=10, code_suggestions=False):
                iter_count += 1

        if not valid_json:
-            logging.error("Unable to decode JSON response from AI")
+            get_logger().error("Unable to decode JSON response from AI")
            data = {}

    return data
@ -230,7 +230,7 @@ def load_large_diff(filename, new_file_content_str: str, original_file_content_s
        diff = difflib.unified_diff(original_file_content_str.splitlines(keepends=True),
                                    new_file_content_str.splitlines(keepends=True))
        if get_settings().config.verbosity_level >= 2:
-            logging.warning(f"File was modified, but no patch was found. Manually creating patch: {filename}.")
+            get_logger().warning(f"File was modified, but no patch was found. Manually creating patch: {filename}.")
        patch = ''.join(diff)
    except Exception:
        pass
@ -262,12 +262,12 @@ def update_settings_from_args(args: List[str]) -> List[str]:
                vals = arg.split('=', 1)
                if len(vals) != 2:
                    if len(vals) > 2: # --extended is a valid argument
-                        logging.error(f'Invalid argument format: {arg}')
+                        get_logger().error(f'Invalid argument format: {arg}')
                    other_args.append(arg)
                    continue
                key, value = _fix_key_value(*vals)
                get_settings().set(key, value)
-                logging.info(f'Updated setting {key} to: "{value}"')
+                get_logger().info(f'Updated setting {key} to: "{value}"')
            else:
                other_args.append(arg)
    return other_args
@ -279,7 +279,7 @@ def _fix_key_value(key: str, value: str):
    try:
        value = yaml.safe_load(value)
    except Exception as e:
-        logging.error(f"Failed to parse YAML for config override {key}={value}", exc_info=e)
+        get_logger().error(f"Failed to parse YAML for config override {key}={value}", exc_info=e)
    return key, value


@ -288,7 +288,7 @@ def load_yaml(review_text: str) -> dict:
    try:
        data = yaml.safe_load(review_text)
    except Exception as e:
-        logging.error(f"Failed to parse AI prediction: {e}")
+        get_logger().error(f"Failed to parse AI prediction: {e}")
        data = try_fix_yaml(review_text)
    return data

@ -299,8 +299,24 @@ def try_fix_yaml(review_text: str) -> dict:
        review_text_lines_tmp = '\n'.join(review_text_lines[:-i])
        try:
            data = yaml.load(review_text_lines_tmp, Loader=yaml.SafeLoader)
-            logging.info(f"Successfully parsed AI prediction after removing {i} lines")
+            get_logger().info(f"Successfully parsed AI prediction after removing {i} lines")
            break
        except:
            pass
    return data
+
+
+def set_custom_labels(variables):
+    labels = get_settings().custom_labels
+    if not labels:
+        # set default labels
+        labels = ['Bug fix', 'Tests', 'Bug fix with tests', 'Refactoring', 'Enhancement', 'Documentation', 'Other']
+        labels_list = "\n      - ".join(labels) if labels else ""
+        labels_list = f"      - {labels_list}" if labels_list else ""
+        variables["custom_labels"] = labels_list
+        return
+    final_labels = ""
+    for k, v in labels.items():
+        final_labels += f"      - {k} ({v['description']})\n"
+    variables["custom_labels"] = final_labels
+    variables["custom_labels_examples"] = f"      - {list(labels.keys())[0]}"
--- a/pr_agent/cli.py
+++ b/pr_agent/cli.py
@ -1,11 +1,12 @@
 import argparse
 import asyncio
-import logging
 import os

 from pr_agent.agent.pr_agent import PRAgent, commands
 from pr_agent.config_loader import get_settings
+from pr_agent.log import setup_logger

+setup_logger()

 def run(inargs=None):
    parser = argparse.ArgumentParser(description='AI based pull request analyzer', usage=
@ -47,7 +48,6 @@ For example: 'python cli.py --pr_url=... review --pr_reviewer.extra_instructions
        parser.print_help()
        return

-    logging.basicConfig(level=os.environ.get("LOGLEVEL", "INFO"))
    command = args.command.lower()
    get_settings().set("CONFIG.CLI_MODE", True)
    if args.issue_url:
--- a/pr_agent/config_loader.py
+++ b/pr_agent/config_loader.py
@ -23,8 +23,10 @@ global_settings = Dynaconf(
        "settings/pr_sort_code_suggestions_prompts.toml",
        "settings/pr_information_from_user_prompts.toml",
        "settings/pr_update_changelog_prompts.toml",
+        "settings/pr_custom_labels.toml",
        "settings/pr_add_docs.toml",
-        "settings_prod/.secrets.toml"
+        "settings_prod/.secrets.toml",
+        "settings/custom_labels.toml"
    ]]
 )

--- a/pr_agent/git_providers/azuredevops_provider.py
+++ b/pr_agent/git_providers/azuredevops_provider.py
@ -1,10 +1,11 @@
 import json
-import logging
 from typing import Optional, Tuple
 from urllib.parse import urlparse

 import os

+from ..log import get_logger
+
 AZURE_DEVOPS_AVAILABLE = True
 try:
    from msrest.authentication import BasicAuthentication
@ -55,7 +56,7 @@ class AzureDevopsProvider:
                                                                 path=".pr_agent.toml")
            return contents
        except Exception as e:
-            logging.exception("get repo settings error")
+            get_logger().exception("get repo settings error")
            return ""

    def get_files(self):
@ -110,7 +111,7 @@ class AzureDevopsProvider:

                    new_file_content_str = new_file_content_str.content
                except Exception as error:
-                    logging.error("Failed to retrieve new file content of %s at version %s. Error: %s", file, version, str(error))
+                    get_logger().error("Failed to retrieve new file content of %s at version %s. Error: %s", file, version, str(error))
                    new_file_content_str = ""

                edit_type = EDIT_TYPE.MODIFIED
@ -131,7 +132,7 @@ class AzureDevopsProvider:
                                                                              include_content=True)
                    original_file_content_str = original_file_content_str.content
                except Exception as error:
-                    logging.error("Failed to retrieve original file content of %s at version %s. Error: %s", file, version, str(error))
+                    get_logger().error("Failed to retrieve original file content of %s at version %s. Error: %s", file, version, str(error))
                    original_file_content_str = ""

                patch = load_large_diff(file, new_file_content_str, original_file_content_str)
@ -166,7 +167,7 @@ class AzureDevopsProvider:
                                                         pull_request_id=self.pr_num,
                                                         git_pull_request_to_update=updated_pr)
        except Exception as e:
-            logging.exception(f"Could not update pull request {self.pr_num} description: {e}")
+            get_logger().exception(f"Could not update pull request {self.pr_num} description: {e}")

    def remove_initial_comment(self):
        return ""  # not implemented yet
@ -235,9 +236,6 @@ class AzureDevopsProvider:
    def _parse_pr_url(pr_url: str) -> Tuple[str, int]:
        parsed_url = urlparse(pr_url)

-        if 'azure.com' not in parsed_url.netloc:
-            raise ValueError("The provided URL is not a valid Azure DevOps URL")
-
        path_parts = parsed_url.path.strip('/').split('/')

        if len(path_parts) < 6 or path_parts[4] != 'pullrequest':
--- a/pr_agent/git_providers/bitbucket_provider.py
+++ b/pr_agent/git_providers/bitbucket_provider.py
@ -1,5 +1,4 @@
 import json
-import logging
 from typing import Optional, Tuple
 from urllib.parse import urlparse

@ -7,8 +6,9 @@ import requests
 from atlassian.bitbucket import Cloud
 from starlette_context import context

-from ..algo.pr_processing import clip_tokens, find_line_number_of_relevant_line_in_file
+from ..algo.pr_processing import find_line_number_of_relevant_line_in_file
 from ..config_loader import get_settings
+from ..log import get_logger
 from .git_provider import FilePatchInfo, GitProvider


@ -61,14 +61,14 @@ class BitbucketProvider(GitProvider):

            if not relevant_lines_start or relevant_lines_start == -1:
                if get_settings().config.verbosity_level >= 2:
-                    logging.exception(
+                    get_logger().exception(
                        f"Failed to publish code suggestion, relevant_lines_start is {relevant_lines_start}"
                    )
                continue

            if relevant_lines_end < relevant_lines_start:
                if get_settings().config.verbosity_level >= 2:
-                    logging.exception(
+                    get_logger().exception(
                        f"Failed to publish code suggestion, "
                        f"relevant_lines_end is {relevant_lines_end} and "
                        f"relevant_lines_start is {relevant_lines_start}"
@ -97,7 +97,7 @@ class BitbucketProvider(GitProvider):
            return True
        except Exception as e:
            if get_settings().config.verbosity_level >= 2:
-                logging.error(f"Failed to publish code suggestion, error: {e}")
+                get_logger().error(f"Failed to publish code suggestion, error: {e}")
            return False

    def is_supported(self, capability: str) -> bool:
@ -144,7 +144,7 @@ class BitbucketProvider(GitProvider):
            for comment in self.temp_comments:
                self.pr.delete(f"comments/{comment}")
        except Exception as e:
-            logging.exception(f"Failed to remove temp comments, error: {e}")
+            get_logger().exception(f"Failed to remove temp comments, error: {e}")


    # funtion to create_inline_comment
@ -152,7 +152,7 @@ class BitbucketProvider(GitProvider):
        position, absolute_position = find_line_number_of_relevant_line_in_file(self.get_diff_files(), relevant_file.strip('`'), relevant_line_in_file)
        if position == -1:
            if get_settings().config.verbosity_level >= 2:
-                logging.info(f"Could not find position for {relevant_file} {relevant_line_in_file}")
+                get_logger().info(f"Could not find position for {relevant_file} {relevant_line_in_file}")
            subject_type = "FILE"
        else:
            subject_type = "LINE"
--- a/pr_agent/git_providers/codecommit_provider.py
+++ b/pr_agent/git_providers/codecommit_provider.py
@ -1,17 +1,16 @@
-import logging
 import os
 import re
 from collections import Counter
 from typing import List, Optional, Tuple
 from urllib.parse import urlparse

-from ..algo.language_handler import is_valid_file, language_extension_map
-from ..algo.pr_processing import clip_tokens
-from ..algo.utils import load_large_diff
-from ..config_loader import get_settings
-from .git_provider import EDIT_TYPE, FilePatchInfo, GitProvider, IncrementalPR
 from pr_agent.git_providers.codecommit_client import CodeCommitClient

+from ..algo.language_handler import is_valid_file, language_extension_map
+from ..algo.utils import load_large_diff
+from .git_provider import EDIT_TYPE, FilePatchInfo, GitProvider
+from ..log import get_logger
+

 class PullRequestCCMimic:
    """
@ -166,7 +165,7 @@ class CodeCommitProvider(GitProvider):

    def publish_comment(self, pr_comment: str, is_temporary: bool = False):
        if is_temporary:
-            logging.info(pr_comment)
+            get_logger().info(pr_comment)
            return

        pr_comment = CodeCommitProvider._remove_markdown_html(pr_comment)
@ -188,12 +187,12 @@ class CodeCommitProvider(GitProvider):
        for suggestion in code_suggestions:
            # Verify that each suggestion has the required keys
            if not all(key in suggestion for key in ["body", "relevant_file", "relevant_lines_start"]):
-                logging.warning(f"Skipping code suggestion #{counter}: Each suggestion must have 'body', 'relevant_file', 'relevant_lines_start' keys")
+                get_logger().warning(f"Skipping code suggestion #{counter}: Each suggestion must have 'body', 'relevant_file', 'relevant_lines_start' keys")
                continue
       
            # Publish the code suggestion to CodeCommit
            try:
-                logging.debug(f"Code Suggestion #{counter} in file: {suggestion['relevant_file']}: {suggestion['relevant_lines_start']}")
+                get_logger().debug(f"Code Suggestion #{counter} in file: {suggestion['relevant_file']}: {suggestion['relevant_lines_start']}")
                self.codecommit_client.publish_comment(
                    repo_name=self.repo_name,
                    pr_number=self.pr_num,
@ -296,11 +295,11 @@ class CodeCommitProvider(GitProvider):
        return self.codecommit_client.get_file(self.repo_name, settings_filename, self.pr.source_commit, optional=True)

    def add_eyes_reaction(self, issue_comment_id: int) -> Optional[int]:
-        logging.info("CodeCommit provider does not support eyes reaction yet")
+        get_logger().info("CodeCommit provider does not support eyes reaction yet")
        return True

    def remove_reaction(self, issue_comment_id: int, reaction_id: int) -> bool:
-        logging.info("CodeCommit provider does not support removing reactions yet")
+        get_logger().info("CodeCommit provider does not support removing reactions yet")
        return True

    @staticmethod
@ -366,7 +365,7 @@ class CodeCommitProvider(GitProvider):
        # TODO: implement support for multiple targets in one CodeCommit PR
        #       for now, we are only using the first target in the PR
        if len(response.targets) > 1:
-            logging.warning(
+            get_logger().warning(
                "Multiple targets in one PR is not supported for CodeCommit yet. Continuing, using the first target only..."
            )

--- a/pr_agent/git_providers/gerrit_provider.py
+++ b/pr_agent/git_providers/gerrit_provider.py
@ -1,5 +1,4 @@
 import json
-import logging
 import os
 import pathlib
 import shutil
@ -7,18 +6,16 @@ import subprocess
 import uuid
 from collections import Counter, namedtuple
 from pathlib import Path
-from tempfile import mkdtemp, NamedTemporaryFile
+from tempfile import NamedTemporaryFile, mkdtemp

 import requests
 import urllib3.util
 from git import Repo

 from pr_agent.config_loader import get_settings
-from pr_agent.git_providers.git_provider import GitProvider, FilePatchInfo, \
-    EDIT_TYPE
+from pr_agent.git_providers.git_provider import EDIT_TYPE, FilePatchInfo, GitProvider
 from pr_agent.git_providers.local_git_provider import PullRequestMimic
-
-logger = logging.getLogger(__name__)
+from pr_agent.log import get_logger


 def _call(*command, **kwargs) -> (int, str, str):
@ -33,42 +30,42 @@ def _call(*command, **kwargs) -> (int, str, str):


 def clone(url, directory):
-    logger.info("Cloning %s to %s", url, directory)
+    get_logger().info("Cloning %s to %s", url, directory)
    stdout = _call('git', 'clone', "--depth", "1", url, directory)
-    logger.info(stdout)
+    get_logger().info(stdout)


 def fetch(url, refspec, cwd):
-    logger.info("Fetching %s %s", url, refspec)
+    get_logger().info("Fetching %s %s", url, refspec)
    stdout = _call(
        'git', 'fetch', '--depth', '2', url, refspec,
        cwd=cwd
    )
-    logger.info(stdout)
+    get_logger().info(stdout)


 def checkout(cwd):
-    logger.info("Checking out")
+    get_logger().info("Checking out")
    stdout = _call('git', 'checkout', "FETCH_HEAD", cwd=cwd)
-    logger.info(stdout)
+    get_logger().info(stdout)


 def show(*args, cwd=None):
-    logger.info("Show")
+    get_logger().info("Show")
    return _call('git', 'show', *args, cwd=cwd)


 def diff(*args, cwd=None):
-    logger.info("Diff")
+    get_logger().info("Diff")
    patch = _call('git', 'diff', *args, cwd=cwd)
    if not patch:
-        logger.warning("No changes found")
+        get_logger().warning("No changes found")
        return
    return patch


 def reset_local_changes(cwd):
-    logger.info("Reset local changes")
+    get_logger().info("Reset local changes")
    _call('git', 'checkout', "--force", cwd=cwd)


--- a/pr_agent/git_providers/git_provider.py
+++ b/pr_agent/git_providers/git_provider.py
@ -1,4 +1,3 @@
-import logging
 from abc import ABC, abstractmethod
 from dataclasses import dataclass

@ -6,6 +5,8 @@ from dataclasses import dataclass
 from enum import Enum
 from typing import Optional

+from pr_agent.log import get_logger
+

 class EDIT_TYPE(Enum):
    ADDED = 1
@ -136,7 +137,7 @@ def get_main_pr_language(languages, files) -> str:
    """
    main_language_str = ""
    if not languages:
-        logging.info("No languages detected")
+        get_logger().info("No languages detected")
        return main_language_str

    try:
@ -172,7 +173,7 @@ def get_main_pr_language(languages, files) -> str:
            main_language_str = top_language

    except Exception as e:
-        logging.exception(e)
+        get_logger().exception(e)
        pass

    return main_language_str
--- a/pr_agent/git_providers/github_provider.py
+++ b/pr_agent/git_providers/github_provider.py
@ -1,20 +1,19 @@
-import logging
 import hashlib
-
 from datetime import datetime
-from typing import Optional, Tuple, Any
+from typing import Optional, Tuple
 from urllib.parse import urlparse

-from github import AppAuthentication, Auth, Github, GithubException, Reaction
+from github import AppAuthentication, Auth, Github, GithubException
 from retry import retry
 from starlette_context import context

-from .git_provider import FilePatchInfo, GitProvider, IncrementalPR
 from ..algo.language_handler import is_valid_file
+from ..algo.pr_processing import clip_tokens, find_line_number_of_relevant_line_in_file
 from ..algo.utils import load_large_diff
-from ..algo.pr_processing import find_line_number_of_relevant_line_in_file, clip_tokens
 from ..config_loader import get_settings
+from ..log import get_logger
 from ..servers.utils import RateLimitExceeded
+from .git_provider import FilePatchInfo, GitProvider, IncrementalPR


 class GithubProvider(GitProvider):
@ -58,7 +57,7 @@ class GithubProvider(GitProvider):
            self.file_set = dict()
            for commit in self.incremental.commits_range:
                if commit.commit.message.startswith(f"Merge branch '{self._get_repo().default_branch}'"):
-                    logging.info(f"Skipping merge commit {commit.commit.message}")
+                    get_logger().info(f"Skipping merge commit {commit.commit.message}")
                    continue
                self.file_set.update({file.filename: file for file in commit.files})

@ -78,7 +77,7 @@ class GithubProvider(GitProvider):
        self.previous_review = None
        self.comments = list(self.pr.get_issue_comments())
        for index in range(len(self.comments) - 1, -1, -1):
-            if self.comments[index].body.startswith("## PR Analysis"):
+            if self.comments[index].body.startswith("## PR Analysis") or self.comments[index].body.startswith("## Incremental PR Review"):
                self.previous_review = self.comments[index]
                break

@ -130,7 +129,7 @@ class GithubProvider(GitProvider):
            return diff_files

        except GithubException.RateLimitExceededException as e:
-            logging.error(f"Rate limit exceeded for GitHub API. Original message: {e}")
+            get_logger().error(f"Rate limit exceeded for GitHub API. Original message: {e}")
            raise RateLimitExceeded("Rate limit exceeded for GitHub API.") from e

    def publish_description(self, pr_title: str, pr_body: str):
@ -138,7 +137,7 @@ class GithubProvider(GitProvider):

    def publish_comment(self, pr_comment: str, is_temporary: bool = False):
        if is_temporary and not get_settings().config.publish_output_progress:
-            logging.debug(f"Skipping publish_comment for temporary comment: {pr_comment}")
+            get_logger().debug(f"Skipping publish_comment for temporary comment: {pr_comment}")
            return
        response = self.pr.create_issue_comment(pr_comment)
        if hasattr(response, "user") and hasattr(response.user, "login"):
@ -156,7 +155,7 @@ class GithubProvider(GitProvider):
        position, absolute_position = find_line_number_of_relevant_line_in_file(self.diff_files, relevant_file.strip('`'), relevant_line_in_file)
        if position == -1:
            if get_settings().config.verbosity_level >= 2:
-                logging.info(f"Could not find position for {relevant_file} {relevant_line_in_file}")
+                get_logger().info(f"Could not find position for {relevant_file} {relevant_line_in_file}")
            subject_type = "FILE"
        else:
            subject_type = "LINE"
@ -179,13 +178,13 @@ class GithubProvider(GitProvider):

            if not relevant_lines_start or relevant_lines_start == -1:
                if get_settings().config.verbosity_level >= 2:
-                    logging.exception(
+                    get_logger().exception(
                        f"Failed to publish code suggestion, relevant_lines_start is {relevant_lines_start}")
                continue

            if relevant_lines_end < relevant_lines_start:
                if get_settings().config.verbosity_level >= 2:
-                    logging.exception(f"Failed to publish code suggestion, "
+                    get_logger().exception(f"Failed to publish code suggestion, "
                                      f"relevant_lines_end is {relevant_lines_end} and "
                                      f"relevant_lines_start is {relevant_lines_start}")
                continue
@ -212,7 +211,7 @@ class GithubProvider(GitProvider):
            return True
        except Exception as e:
            if get_settings().config.verbosity_level >= 2:
-                logging.error(f"Failed to publish code suggestion, error: {e}")
+                get_logger().error(f"Failed to publish code suggestion, error: {e}")
            return False

    def remove_initial_comment(self):
@ -221,7 +220,7 @@ class GithubProvider(GitProvider):
                if comment.is_temporary:
                    comment.delete()
        except Exception as e:
-            logging.exception(f"Failed to remove initial comment, error: {e}")
+            get_logger().exception(f"Failed to remove initial comment, error: {e}")

    def get_title(self):
        return self.pr.title
@ -259,7 +258,10 @@ class GithubProvider(GitProvider):

    def get_repo_settings(self):
        try:
-            contents = self.repo_obj.get_contents(".pr_agent.toml", ref=self.pr.head.sha).decoded_content
+            # contents = self.repo_obj.get_contents(".pr_agent.toml", ref=self.pr.head.sha).decoded_content
+
+            # more logical to take 'pr_agent.toml' from the default branch
+            contents = self.repo_obj.get_contents(".pr_agent.toml").decoded_content
            return contents
        except Exception:
            return ""
@ -269,7 +271,7 @@ class GithubProvider(GitProvider):
            reaction = self.pr.get_issue_comment(issue_comment_id).create_reaction("eyes")
            return reaction.id
        except Exception as e:
-            logging.exception(f"Failed to add eyes reaction, error: {e}")
+            get_logger().exception(f"Failed to add eyes reaction, error: {e}")
            return None

    def remove_reaction(self, issue_comment_id: int, reaction_id: int) -> bool:
@ -277,7 +279,7 @@ class GithubProvider(GitProvider):
            self.pr.get_issue_comment(issue_comment_id).delete_reaction(reaction_id)
            return True
        except Exception as e:
-            logging.exception(f"Failed to remove eyes reaction, error: {e}")
+            get_logger().exception(f"Failed to remove eyes reaction, error: {e}")
            return False


@ -396,13 +398,13 @@ class GithubProvider(GitProvider):
                "PUT", f"{self.pr.issue_url}/labels", input=post_parameters
            )
        except Exception as e:
-            logging.exception(f"Failed to publish labels, error: {e}")
+            get_logger().exception(f"Failed to publish labels, error: {e}")

    def get_labels(self):
        try:
            return [label.name for label in self.pr.labels]
        except Exception as e:
-            logging.exception(f"Failed to get labels, error: {e}")
+            get_logger().exception(f"Failed to get labels, error: {e}")
            return []

    def get_commit_messages(self):
@ -444,7 +446,7 @@ class GithubProvider(GitProvider):
                return link
        except Exception as e:
            if get_settings().config.verbosity_level >= 2:
-                logging.info(f"Failed adding line link, error: {e}")
+                get_logger().info(f"Failed adding line link, error: {e}")

        return ""

--- a/pr_agent/git_providers/gitlab_provider.py
+++ b/pr_agent/git_providers/gitlab_provider.py
@ -1,5 +1,4 @@
 import hashlib
-import logging
 import re
 from typing import Optional, Tuple
 from urllib.parse import urlparse
@ -12,8 +11,8 @@ from ..algo.pr_processing import clip_tokens, find_line_number_of_relevant_line_
 from ..algo.utils import load_large_diff
 from ..config_loader import get_settings
 from .git_provider import EDIT_TYPE, FilePatchInfo, GitProvider
+from ..log import get_logger

-logger = logging.getLogger()

 class DiffNotFoundError(Exception):
    """Raised when the diff for a merge request cannot be found."""
@ -59,7 +58,7 @@ class GitLabProvider(GitProvider):
        try:
            self.last_diff = self.mr.diffs.list(get_all=True)[-1]
        except IndexError as e:
-            logger.error(f"Could not get diff for merge request {self.id_mr}")
+            get_logger().error(f"Could not get diff for merge request {self.id_mr}")
            raise DiffNotFoundError(f"Could not get diff for merge request {self.id_mr}") from e


@ -99,7 +98,7 @@ class GitLabProvider(GitProvider):
                    if isinstance(new_file_content_str, bytes):
                        new_file_content_str = bytes.decode(new_file_content_str, 'utf-8')
                except UnicodeDecodeError:
-                    logging.warning(
+                    get_logger().warning(
                        f"Cannot decode file {diff['old_path']} or {diff['new_path']} in merge request {self.id_mr}")

                edit_type = EDIT_TYPE.MODIFIED
@ -135,7 +134,7 @@ class GitLabProvider(GitProvider):
            self.mr.description = pr_body
            self.mr.save()
        except Exception as e:
-            logging.exception(f"Could not update merge request {self.id_mr} description: {e}")
+            get_logger().exception(f"Could not update merge request {self.id_mr} description: {e}")

    def publish_comment(self, mr_comment: str, is_temporary: bool = False):
        comment = self.mr.notes.create({'body': mr_comment})
@ -157,12 +156,12 @@ class GitLabProvider(GitProvider):
    def send_inline_comment(self,body: str,edit_type: str,found: bool,relevant_file: str,relevant_line_in_file: int,
                            source_line_no: int, target_file: str,target_line_no: int) -> None:
        if not found:
-            logging.info(f"Could not find position for {relevant_file} {relevant_line_in_file}")
+            get_logger().info(f"Could not find position for {relevant_file} {relevant_line_in_file}")
        else:
            # in order to have exact sha's we have to find correct diff for this change
            diff = self.get_relevant_diff(relevant_file, relevant_line_in_file)
            if diff is None:
-                logger.error(f"Could not get diff for merge request {self.id_mr}")
+                get_logger().error(f"Could not get diff for merge request {self.id_mr}")
                raise DiffNotFoundError(f"Could not get diff for merge request {self.id_mr}")
            pos_obj = {'position_type': 'text',
                       'new_path': target_file.filename,
@ -175,23 +174,23 @@ class GitLabProvider(GitProvider):
            else:
                pos_obj['new_line'] = target_line_no - 1
                pos_obj['old_line'] = source_line_no - 1
-            logging.debug(f"Creating comment in {self.id_mr} with body {body} and position {pos_obj}")
+            get_logger().debug(f"Creating comment in {self.id_mr} with body {body} and position {pos_obj}")
            self.mr.discussions.create({'body': body, 'position': pos_obj})

    def get_relevant_diff(self, relevant_file: str, relevant_line_in_file: int) -> Optional[dict]:
        changes = self.mr.changes()  # Retrieve the changes for the merge request once
        if not changes:
-            logging.error('No changes found for the merge request.')
+            get_logger().error('No changes found for the merge request.')
            return None
        all_diffs = self.mr.diffs.list(get_all=True)
        if not all_diffs:
-            logging.error('No diffs found for the merge request.')
+            get_logger().error('No diffs found for the merge request.')
            return None
        for diff in all_diffs:
            for change in changes['changes']:
                if change['new_path'] == relevant_file and relevant_line_in_file in change['diff']:
                    return diff
-            logging.debug(
+            get_logger().debug(
                f'No relevant diff found for {relevant_file} {relevant_line_in_file}. Falling back to last diff.')
        return self.last_diff  # fallback to last_diff if no relevant diff is found

@ -226,7 +225,7 @@ class GitLabProvider(GitProvider):
                self.send_inline_comment(body, edit_type, found, relevant_file, relevant_line_in_file, source_line_no,
                                         target_file, target_line_no)
            except Exception as e:
-                logging.exception(f"Could not publish code suggestion:\nsuggestion: {suggestion}\nerror: {e}")
+                get_logger().exception(f"Could not publish code suggestion:\nsuggestion: {suggestion}\nerror: {e}")

        # note that we publish suggestions one-by-one. so, if one fails, the rest will still be published
        return True
@ -290,7 +289,7 @@ class GitLabProvider(GitProvider):
            for comment in self.temp_comments:
                comment.delete()
        except Exception as e:
-            logging.exception(f"Failed to remove temp comments, error: {e}")
+            get_logger().exception(f"Failed to remove temp comments, error: {e}")

    def get_title(self):
        return self.mr.title
@ -358,7 +357,7 @@ class GitLabProvider(GitProvider):
            self.mr.labels = list(set(pr_types))
            self.mr.save()
        except Exception as e:
-            logging.exception(f"Failed to publish labels, error: {e}")
+            get_logger().exception(f"Failed to publish labels, error: {e}")

    def publish_inline_comments(self, comments: list[dict]):
        pass
@ -410,6 +409,6 @@ class GitLabProvider(GitProvider):
                return link
        except Exception as e:
            if get_settings().config.verbosity_level >= 2:
-                logging.info(f"Failed adding line link, error: {e}")
+                get_logger().info(f"Failed adding line link, error: {e}")

        return ""
--- a/pr_agent/git_providers/local_git_provider.py
+++ b/pr_agent/git_providers/local_git_provider.py
@ -1,4 +1,3 @@
-import logging
 from collections import Counter
 from pathlib import Path
 from typing import List
@ -7,6 +6,7 @@ from git import Repo

 from pr_agent.config_loader import _find_repository_root, get_settings
 from pr_agent.git_providers.git_provider import EDIT_TYPE, FilePatchInfo, GitProvider
+from pr_agent.log import get_logger


 class PullRequestMimic:
@ -49,7 +49,7 @@ class LocalGitProvider(GitProvider):
        """
        Prepare the repository for PR-mimic generation.
        """
-        logging.debug('Preparing repository for PR-mimic generation...')
+        get_logger().debug('Preparing repository for PR-mimic generation...')
        if self.repo.is_dirty():
            raise ValueError('The repository is not in a clean state. Please commit or stash pending changes.')
        if self.target_branch_name not in self.repo.heads:
--- a/pr_agent/git_providers/utils.py
+++ b/pr_agent/git_providers/utils.py
@ -0,0 +1,36 @@
+import copy
+import os
+import tempfile
+
+from dynaconf import Dynaconf
+
+from pr_agent.config_loader import get_settings
+from pr_agent.git_providers import get_git_provider
+from pr_agent.log import get_logger
+
+
+def apply_repo_settings(pr_url):
+    if get_settings().config.use_repo_settings_file:
+        repo_settings_file = None
+        try:
+            git_provider = get_git_provider()(pr_url)
+            repo_settings = git_provider.get_repo_settings()
+            if repo_settings:
+                repo_settings_file = None
+                fd, repo_settings_file = tempfile.mkstemp(suffix='.toml')
+                os.write(fd, repo_settings)
+                new_settings = Dynaconf(settings_files=[repo_settings_file])
+                for section, contents in new_settings.as_dict().items():
+                    section_dict = copy.deepcopy(get_settings().as_dict().get(section, {}))
+                    for key, value in contents.items():
+                        section_dict[key] = value
+                    get_settings().unset(section)
+                    get_settings().set(section, section_dict, merge=False)
+                    get_logger().info(f"Applying repo settings for section {section}, contents: {contents}")
+
+        finally:
+            if repo_settings_file:
+                try:
+                    os.remove(repo_settings_file)
+                except Exception as e:
+                    get_logger().error(f"Failed to remove temporary settings file {repo_settings_file}", e)
--- a/pr_agent/log/init.py
+++ b/pr_agent/log/init.py
@ -0,0 +1,40 @@
+import json
+import logging
+import sys
+from enum import Enum
+
+from loguru import logger
+
+
+class LoggingFormat(str, Enum):
+    CONSOLE = "CONSOLE"
+    JSON = "JSON"
+
+
+def json_format(record: dict) -> str:
+    return record["message"]
+
+
+def setup_logger(level: str = "INFO", fmt: LoggingFormat = LoggingFormat.CONSOLE):
+    level: int = logging.getLevelName(level.upper())
+    if type(level) is not int:
+        level = logging.INFO
+
+    if fmt == LoggingFormat.JSON:
+        logger.remove(None)
+        logger.add(
+            sys.stdout,
+            level=level,
+            format="{message}",
+            colorize=False,
+            serialize=True,
+        )
+    elif fmt == LoggingFormat.CONSOLE:
+        logger.remove(None)
+        logger.add(sys.stdout, level=level, colorize=True)
+
+    return logger
+
+
+def get_logger(*args, **kwargs):
+    return logger
--- a/pr_agent/secret_providers/google_cloud_storage_secret_provider.py
+++ b/pr_agent/secret_providers/google_cloud_storage_secret_provider.py
@ -1,9 +1,8 @@
 import ujson
-
 from google.cloud import storage

 from pr_agent.config_loader import get_settings
-from pr_agent.git_providers.gitlab_provider import logger
+from pr_agent.log import get_logger
 from pr_agent.secret_providers.secret_provider import SecretProvider


@ -15,7 +14,7 @@ class GoogleCloudStorageSecretProvider(SecretProvider):
            self.bucket_name = get_settings().google_cloud_storage.bucket_name
            self.bucket = self.client.bucket(self.bucket_name)
        except Exception as e:
-            logger.error(f"Failed to initialize Google Cloud Storage Secret Provider: {e}")
+            get_logger().error(f"Failed to initialize Google Cloud Storage Secret Provider: {e}")
            raise e

    def get_secret(self, secret_name: str) -> str:
@ -23,7 +22,7 @@ class GoogleCloudStorageSecretProvider(SecretProvider):
            blob = self.bucket.blob(secret_name)
            return blob.download_as_string()
        except Exception as e:
-            logger.error(f"Failed to get secret {secret_name} from Google Cloud Storage: {e}")
+            get_logger().error(f"Failed to get secret {secret_name} from Google Cloud Storage: {e}")
            return ""

    def store_secret(self, secret_name: str, secret_value: str):
@ -31,5 +30,5 @@ class GoogleCloudStorageSecretProvider(SecretProvider):
            blob = self.bucket.blob(secret_name)
            blob.upload_from_string(secret_value)
        except Exception as e:
-            logger.error(f"Failed to store secret {secret_name} in Google Cloud Storage: {e}")
+            get_logger().error(f"Failed to store secret {secret_name} in Google Cloud Storage: {e}")
            raise e
--- a/pr_agent/servers/bitbucket_app.py
+++ b/pr_agent/servers/bitbucket_app.py
@ -1,9 +1,7 @@
 import copy
 import hashlib
 import json
-import logging
 import os
-import sys
 import time

 import jwt
@ -18,9 +16,10 @@ from starlette_context.middleware import RawContextMiddleware

 from pr_agent.agent.pr_agent import PRAgent
 from pr_agent.config_loader import get_settings, global_settings
+from pr_agent.log import LoggingFormat, get_logger, setup_logger
 from pr_agent.secret_providers import get_secret_provider

-logging.basicConfig(stream=sys.stdout, level=logging.INFO)
+setup_logger(fmt=LoggingFormat.JSON)
 router = APIRouter()
 secret_provider = get_secret_provider()

@ -49,7 +48,7 @@ async def get_bearer_token(shared_secret: str, client_key: str):
        bearer_token = response.json()["access_token"]
        return bearer_token
    except Exception as e:
-        logging.error(f"Failed to get bearer token: {e}")
+        get_logger().error(f"Failed to get bearer token: {e}")
        raise e

@router.get("/")
@ -60,21 +59,23 @@ async def handle_manifest(request: Request, response: Response):
        manifest = manifest.replace("app_key", get_settings().bitbucket.app_key)
        manifest = manifest.replace("base_url", get_settings().bitbucket.base_url)
    except:
-        logging.error("Failed to replace api_key in Bitbucket manifest, trying to continue")
+        get_logger().error("Failed to replace api_key in Bitbucket manifest, trying to continue")
    manifest_obj = json.loads(manifest)
    return JSONResponse(manifest_obj)

@router.post("/webhook")
 async def handle_github_webhooks(background_tasks: BackgroundTasks, request: Request):
-    print(request.headers)
+    log_context = {"server_type": "bitbucket_app"}
+    get_logger().debug(request.headers)
    jwt_header = request.headers.get("authorization", None)
    if jwt_header:
        input_jwt = jwt_header.split(" ")[1]
    data = await request.json()
-    print(data)
+    get_logger().debug(data)
    async def inner():
        try:
            owner = data["data"]["repository"]["owner"]["username"]
+            log_context["sender"] = owner
            secrets = json.loads(secret_provider.get_secret(owner))
            shared_secret = secrets["shared_secret"]
            client_key = secrets["client_key"]
@ -86,13 +87,19 @@ async def handle_github_webhooks(background_tasks: BackgroundTasks, request: Req
            agent = PRAgent()
            if event == "pullrequest:created":
                pr_url = data["data"]["pullrequest"]["links"]["html"]["href"]
-                await agent.handle_request(pr_url, "review")
+                log_context["api_url"] = pr_url
+                log_context["event"] = "pull_request"
+                with get_logger().contextualize(**log_context):
+                    await agent.handle_request(pr_url, "review")
            elif event == "pullrequest:comment_created":
                pr_url = data["data"]["pullrequest"]["links"]["html"]["href"]
+                log_context["api_url"] = pr_url
+                log_context["event"] = "comment"
                comment_body = data["data"]["comment"]["content"]["raw"]
-                await agent.handle_request(pr_url, comment_body)
+                with get_logger().contextualize(**log_context):
+                    await agent.handle_request(pr_url, comment_body)
        except Exception as e:
-            logging.error(f"Failed to handle webhook: {e}")
+            get_logger().error(f"Failed to handle webhook: {e}")
    background_tasks.add_task(inner)
    return "OK"

@ -103,9 +110,10 @@ async def handle_github_webhooks(request: Request, response: Response):
@router.post("/installed")
 async def handle_installed_webhooks(request: Request, response: Response):
    try:
-        print(request.headers)
+        get_logger().info("handle_installed_webhooks")
+        get_logger().info(request.headers)
        data = await request.json()
-        print(data)
+        get_logger().info(data)
        shared_secret = data["sharedSecret"]
        client_key = data["clientKey"]
        username = data["principal"]["username"]
@ -115,13 +123,15 @@ async def handle_installed_webhooks(request: Request, response: Response):
        }
        secret_provider.store_secret(username, json.dumps(secrets))
    except Exception as e:
-        logging.error(f"Failed to register user: {e}")
+        get_logger().error(f"Failed to register user: {e}")
        return JSONResponse({"error": "Unable to register user"}, status_code=500)

@router.post("/uninstalled")
 async def handle_uninstalled_webhooks(request: Request, response: Response):
+    get_logger().info("handle_uninstalled_webhooks")
+
    data = await request.json()
-    print(data)
+    get_logger().info(data)


 def start():
--- a/pr_agent/servers/bitbucket_pipeline_runner.py
+++ b/pr_agent/servers/bitbucket_pipeline_runner.py
@ -1,34 +0,0 @@
-import os
-from pr_agent.agent.pr_agent import PRAgent
-from pr_agent.config_loader import get_settings
-from pr_agent.tools.pr_reviewer import PRReviewer
-import asyncio
-
-async def run_action():
-    try:
-        pull_request_id = os.environ.get("BITBUCKET_PR_ID", '')
-        slug = os.environ.get("BITBUCKET_REPO_SLUG", '')
-        workspace = os.environ.get("BITBUCKET_WORKSPACE", '')
-        bearer_token = os.environ.get('BITBUCKET_BEARER_TOKEN', None)
-        OPENAI_KEY = os.environ.get('OPENAI_API_KEY') or os.environ.get('OPENAI.KEY')
-        OPENAI_ORG = os.environ.get('OPENAI_ORG') or os.environ.get('OPENAI.ORG')
-        # Check if required environment variables are set
-        if not bearer_token:
-            print("BITBUCKET_BEARER_TOKEN not set")
-            return
-        
-        if not OPENAI_KEY:
-            print("OPENAI_KEY not set")
-            return
-        # Set the environment variables in the settings
-        get_settings().set("BITBUCKET.BEARER_TOKEN", bearer_token)
-        get_settings().set("OPENAI.KEY", OPENAI_KEY)
-        if OPENAI_ORG:
-            get_settings().set("OPENAI.ORG", OPENAI_ORG)
-        if pull_request_id and slug and workspace:
-            pr_url = f"https://bitbucket.org/{workspace}/{slug}/pull-requests/{pull_request_id}"
-            await PRReviewer(pr_url).run()
-    except Exception as e:
-        print(f"An error occurred: {e}")
-if __name__ == "__main__":
-    asyncio.run(run_action())
--- a/pr_agent/servers/gerrit_server.py
+++ b/pr_agent/servers/gerrit_server.py
@ -1,6 +1,4 @@
 import copy
-import logging
-import sys
 from enum import Enum
 from json import JSONDecodeError

@ -12,9 +10,10 @@ from starlette_context import context
 from starlette_context.middleware import RawContextMiddleware

 from pr_agent.agent.pr_agent import PRAgent
-from pr_agent.config_loader import global_settings, get_settings
+from pr_agent.config_loader import get_settings, global_settings
+from pr_agent.log import get_logger, setup_logger

-logging.basicConfig(stream=sys.stdout, level=logging.DEBUG)
+setup_logger()
 router = APIRouter()


@ -35,7 +34,7 @@ class Item(BaseModel):

@router.post("/api/v1/gerrit/{action}")
 async def handle_gerrit_request(action: Action, item: Item):
-    logging.debug("Received a Gerrit request")
+    get_logger().debug("Received a Gerrit request")
    context["settings"] = copy.deepcopy(global_settings)

    if action == Action.ask:
@ -54,7 +53,7 @@ async def get_body(request):
    try:
        body = await request.json()
    except JSONDecodeError as e:
-        logging.error("Error parsing request body", e)
+        get_logger().error("Error parsing request body", e)
        return {}
    return body

--- a/pr_agent/servers/github_action_runner.py
+++ b/pr_agent/servers/github_action_runner.py
@ -5,6 +5,8 @@ import os
 from pr_agent.agent.pr_agent import PRAgent
 from pr_agent.config_loader import get_settings
 from pr_agent.git_providers import get_git_provider
+from pr_agent.git_providers.utils import apply_repo_settings
+from pr_agent.log import get_logger
 from pr_agent.tools.pr_code_suggestions import PRCodeSuggestions
 from pr_agent.tools.pr_description import PRDescription
 from pr_agent.tools.pr_reviewer import PRReviewer
@ -17,8 +19,11 @@ async def run_action():
    OPENAI_KEY = os.environ.get('OPENAI_KEY') or os.environ.get('OPENAI.KEY')
    OPENAI_ORG = os.environ.get('OPENAI_ORG') or os.environ.get('OPENAI.ORG')
    GITHUB_TOKEN = os.environ.get('GITHUB_TOKEN')
-    get_settings().set("CONFIG.PUBLISH_OUTPUT_PROGRESS", False)
+    CUSTOM_LABELS = os.environ.get('CUSTOM_LABELS')
+    CUSTOM_LABELS_DESCRIPTIONS = os.environ.get('CUSTOM_LABELS_DESCRIPTIONS')
+    # CUSTOM_LABELS is a comma separated list of labels (string), convert to list and strip spaces

+    get_settings().set("CONFIG.PUBLISH_OUTPUT_PROGRESS", False)

    # Check if required environment variables are set
    if not GITHUB_EVENT_NAME:
@ -33,6 +38,7 @@ async def run_action():
    if not GITHUB_TOKEN:
        print("GITHUB_TOKEN not set")
        return
+    # CUSTOM_LABELS_DICT = handle_custom_labels(CUSTOM_LABELS, CUSTOM_LABELS_DESCRIPTIONS)

    # Set the environment variables in the settings
    get_settings().set("OPENAI.KEY", OPENAI_KEY)
@ -40,6 +46,7 @@ async def run_action():
        get_settings().set("OPENAI.ORG", OPENAI_ORG)
    get_settings().set("GITHUB.USER_TOKEN", GITHUB_TOKEN)
    get_settings().set("GITHUB.DEPLOYMENT_TYPE", "user")
+    # get_settings().set("CUSTOM_LABELS", CUSTOM_LABELS_DICT)

    # Load the event payload
    try:
@ -49,6 +56,15 @@ async def run_action():
        print(f"Failed to parse JSON: {e}")
        return

+    try:
+        get_logger().info("Applying repo settings")
+        pr_url = event_payload.get("pull_request", {}).get("html_url")
+        if pr_url:
+            apply_repo_settings(pr_url)
+            get_logger().info(f"enable_custom_labels: {get_settings().config.enable_custom_labels}")
+    except Exception as e:
+        get_logger().info(f"github action: failed to apply repo settings: {e}")
+
    # Handle pull request event
    if GITHUB_EVENT_NAME == "pull_request":
        action = event_payload.get("action")
@ -88,5 +104,31 @@ async def run_action():
                        await PRAgent().handle_request(url, body)


+def handle_custom_labels(CUSTOM_LABELS, CUSTOM_LABELS_DESCRIPTIONS):
+    if CUSTOM_LABELS:
+        CUSTOM_LABELS = [x.strip() for x in CUSTOM_LABELS.split(',')]
+    else:
+        # Set default labels
+        CUSTOM_LABELS = ['Bug fix', 'Tests', 'Bug fix with tests', 'Refactoring', 'Enhancement', 'Documentation',
+                         'Other']
+        print(f"Using default labels: {CUSTOM_LABELS}")
+    if CUSTOM_LABELS_DESCRIPTIONS:
+        CUSTOM_LABELS_DESCRIPTIONS = [x.strip() for x in CUSTOM_LABELS_DESCRIPTIONS.split(',')]
+    else:
+        # Set default labels
+        CUSTOM_LABELS_DESCRIPTIONS = ['Fixes a bug in the code', 'Adds or modifies tests',
+                                     'Fixes a bug in the code and adds or modifies tests',
+                                     'Refactors the code without changing its functionality',
+                                     'Adds new features or functionality',
+                                     'Adds or modifies documentation',
+                                     'Other changes that do not fit in any of the above categories']
+        print(f"Using default labels: {CUSTOM_LABELS_DESCRIPTIONS}")
+    # create a dictionary of labels and descriptions
+    CUSTOM_LABELS_DICT = dict()
+    for i in range(len(CUSTOM_LABELS)):
+        CUSTOM_LABELS_DICT[CUSTOM_LABELS[i]] = {'description': CUSTOM_LABELS_DESCRIPTIONS[i]}
+    return CUSTOM_LABELS_DICT
+
+
 if __name__ == '__main__':
    asyncio.run(run_action())
--- a/pr_agent/servers/github_app.py
+++ b/pr_agent/servers/github_app.py
@ -1,6 +1,4 @@
 import copy
-import logging
-import sys
 import os
 import time
 from typing import Any, Dict
@ -15,9 +13,12 @@ from pr_agent.agent.pr_agent import PRAgent
 from pr_agent.algo.utils import update_settings_from_args
 from pr_agent.config_loader import get_settings, global_settings
 from pr_agent.git_providers import get_git_provider
+from pr_agent.git_providers.utils import apply_repo_settings
+from pr_agent.log import LoggingFormat, get_logger, setup_logger
 from pr_agent.servers.utils import verify_signature

-logging.basicConfig(stream=sys.stdout, level=logging.INFO)
+setup_logger(fmt=LoggingFormat.JSON)
+
 router = APIRouter()


@ -28,11 +29,11 @@ async def handle_github_webhooks(request: Request, response: Response):
    Verifies the request signature, parses the request body, and passes it to the handle_request function for further
    processing.
    """
-    logging.debug("Received a GitHub webhook")
+    get_logger().debug("Received a GitHub webhook")

    body = await get_body(request)

-    logging.debug(f'Request body:\n{body}')
+    get_logger().debug(f'Request body:\n{body}')
    installation_id = body.get("installation", {}).get("id")
    context["installation_id"] = installation_id
    context["settings"] = copy.deepcopy(global_settings)
@ -44,13 +45,13 @@ async def handle_github_webhooks(request: Request, response: Response):
@router.post("/api/v1/marketplace_webhooks")
 async def handle_marketplace_webhooks(request: Request, response: Response):
    body = await get_body(request)
-    logging.info(f'Request body:\n{body}')
+    get_logger().info(f'Request body:\n{body}')

 async def get_body(request):
    try:
        body = await request.json()
    except Exception as e:
-        logging.error("Error parsing request body", e)
+        get_logger().error("Error parsing request body", e)
        raise HTTPException(status_code=400, detail="Error parsing request body") from e
    webhook_secret = getattr(get_settings().github, 'webhook_secret', None)
    if webhook_secret:
@ -76,8 +77,8 @@ async def handle_request(body: Dict[str, Any], event: str):
        return {}
    agent = PRAgent()
    bot_user = get_settings().github_app.bot_user
-    logging.info(f"action: '{action}'")
-    logging.info(f"event: '{event}'")
+    sender = body.get("sender", {}).get("login")
+    log_context = {"action": action, "event": event, "sender": sender, "server_type": "github_app"}

    if get_settings().github_app.duplicate_requests_cache and _is_duplicate_request(body):
        return {}
@ -87,22 +88,23 @@ async def handle_request(body: Dict[str, Any], event: str):
        if "comment" not in body:
            return {}
        comment_body = body.get("comment", {}).get("body")
-        sender = body.get("sender", {}).get("login")
        if sender and bot_user in sender:
-            logging.info(f"Ignoring comment from {bot_user} user")
+            get_logger().info(f"Ignoring comment from {bot_user} user")
            return {}
-        logging.info(f"Processing comment from {sender} user")
+        get_logger().info(f"Processing comment from {sender} user")
        if "issue" in body and "pull_request" in body["issue"] and "url" in body["issue"]["pull_request"]:
            api_url = body["issue"]["pull_request"]["url"]
        elif "comment" in body and "pull_request_url" in body["comment"]:
            api_url = body["comment"]["pull_request_url"]
        else:
            return {}
-        logging.info(body)
-        logging.info(f"Handling comment because of event={event} and action={action}")
+        log_context["api_url"] = api_url
+        get_logger().info(body)
+        get_logger().info(f"Handling comment because of event={event} and action={action}")
        comment_id = body.get("comment", {}).get("id")
        provider = get_git_provider()(pr_url=api_url)
-        await agent.handle_request(api_url, comment_body, notify=lambda: provider.add_eyes_reaction(comment_id))
+        with get_logger().contextualize(**log_context):
+            await agent.handle_request(api_url, comment_body, notify=lambda: provider.add_eyes_reaction(comment_id))

    # handle pull_request event:
    #   automatically review opened/reopened/ready_for_review PRs as long as they're not in draft,
@ -114,6 +116,7 @@ async def handle_request(body: Dict[str, Any], event: str):
        api_url = pull_request.get("url")
        if not api_url:
            return {}
+        log_context["api_url"] = api_url
        if pull_request.get("draft", True) or pull_request.get("state") != "open" or pull_request.get("user", {}).get("login", "") == bot_user:
            return {}
        if action in get_settings().github_app.handle_pr_actions:
@ -123,18 +126,20 @@ async def handle_request(body: Dict[str, Any], event: str):
                if pull_request.get("created_at") == pull_request.get("updated_at"):
                    # avoid double reviews when opening a PR for the first time
                    return {}
-            logging.info(f"Performing review because of event={event} and action={action}")
+            get_logger().info(f"Performing review because of event={event} and action={action}")
+            apply_repo_settings(api_url)
            for command in get_settings().github_app.pr_commands:
                split_command = command.split(" ")
                command = split_command[0]
                args = split_command[1:]
                other_args = update_settings_from_args(args)
                new_command = ' '.join([command] + other_args)
-                logging.info(body)
-                logging.info(f"Performing command: {new_command}")
-                await agent.handle_request(api_url, new_command)
+                get_logger().info(body)
+                get_logger().info(f"Performing command: {new_command}")
+                with get_logger().contextualize(**log_context):
+                    await agent.handle_request(api_url, new_command)

-    logging.info("event or action does not require handling")
+    get_logger().info("event or action does not require handling")
    return {}


@ -144,7 +149,7 @@ def _is_duplicate_request(body: Dict[str, Any]) -> bool:
    This function checks if the request is duplicate and if so - ignores it.
    """
    request_hash = hash(str(body))
-    logging.info(f"request_hash: {request_hash}")
+    get_logger().info(f"request_hash: {request_hash}")
    request_time = time.monotonic()
    ttl = get_settings().github_app.duplicate_requests_cache_ttl  # in seconds
    to_delete = [key for key, key_time in _duplicate_requests_cache.items() if request_time - key_time > ttl]
@ -153,7 +158,7 @@ def _is_duplicate_request(body: Dict[str, Any]) -> bool:
    is_duplicate = request_hash in _duplicate_requests_cache
    _duplicate_requests_cache[request_hash] = request_time
    if is_duplicate:
-        logging.info(f"Ignoring duplicate request {request_hash}")
+        get_logger().info(f"Ignoring duplicate request {request_hash}")
    return is_duplicate


--- a/pr_agent/servers/github_polling.py
+++ b/pr_agent/servers/github_polling.py
@ -1,6 +1,4 @@
 import asyncio
-import logging
-import sys
 from datetime import datetime, timezone

 import aiohttp
@ -8,9 +6,10 @@ import aiohttp
 from pr_agent.agent.pr_agent import PRAgent
 from pr_agent.config_loader import get_settings
 from pr_agent.git_providers import get_git_provider
+from pr_agent.log import LoggingFormat, get_logger, setup_logger
 from pr_agent.servers.help import bot_help_text

-logging.basicConfig(stream=sys.stdout, level=logging.DEBUG)
+setup_logger(fmt=LoggingFormat.JSON)
 NOTIFICATION_URL = "https://api.github.com/notifications"


@ -94,7 +93,7 @@ async def polling_loop():
                                            comment_body = comment['body'] if 'body' in comment else ''
                                            commenter_github_user = comment['user']['login'] \
                                                if 'user' in comment else ''
-                                            logging.info(f"Commenter: {commenter_github_user}\nComment: {comment_body}")
+                                            get_logger().info(f"Commenter: {commenter_github_user}\nComment: {comment_body}")
                                            user_tag = "@" + user_id
                                            if user_tag not in comment_body:
                                                continue
@ -112,7 +111,7 @@ async def polling_loop():
                        print(f"Failed to fetch notifications. Status code: {response.status}")

            except Exception as e:
-                logging.error(f"Exception during processing of a notification: {e}")
+                get_logger().error(f"Exception during processing of a notification: {e}")


 if __name__ == '__main__':
--- a/pr_agent/servers/gitlab_webhook.py
+++ b/pr_agent/servers/gitlab_webhook.py
@ -1,7 +1,5 @@
 import copy
 import json
-import logging
-import sys

 import uvicorn
 from fastapi import APIRouter, FastAPI, Request, status
@ -14,26 +12,37 @@ from starlette_context.middleware import RawContextMiddleware

 from pr_agent.agent.pr_agent import PRAgent
 from pr_agent.config_loader import get_settings, global_settings
+from pr_agent.log import LoggingFormat, get_logger, setup_logger
 from pr_agent.secret_providers import get_secret_provider

-logging.basicConfig(stream=sys.stdout, level=logging.INFO)
+setup_logger(fmt=LoggingFormat.JSON)
 router = APIRouter()

 secret_provider = get_secret_provider() if get_settings().get("CONFIG.SECRET_PROVIDER") else None


+def handle_request(background_tasks: BackgroundTasks, url: str, body: str, log_context: dict):
+    log_context["action"] = body
+    log_context["event"] = "pull_request" if body == "/review" else "comment"
+    log_context["api_url"] = url
+    with get_logger().contextualize(**log_context):
+        background_tasks.add_task(PRAgent().handle_request, url, body)
+
+
@router.post("/webhook")
 async def gitlab_webhook(background_tasks: BackgroundTasks, request: Request):
+    log_context = {"server_type": "gitlab_app"}
    if request.headers.get("X-Gitlab-Token") and secret_provider:
        request_token = request.headers.get("X-Gitlab-Token")
        secret = secret_provider.get_secret(request_token)
        try:
            secret_dict = json.loads(secret)
            gitlab_token = secret_dict["gitlab_token"]
+            log_context["sender"] = secret_dict["id"]
            context["settings"] = copy.deepcopy(global_settings)
            context["settings"].gitlab.personal_access_token = gitlab_token
        except Exception as e:
-            logging.error(f"Failed to validate secret {request_token}: {e}")
+            get_logger().error(f"Failed to validate secret {request_token}: {e}")
            return JSONResponse(status_code=status.HTTP_401_UNAUTHORIZED, content=jsonable_encoder({"message": "unauthorized"}))
    elif get_settings().get("GITLAB.SHARED_SECRET"):
        secret = get_settings().get("GITLAB.SHARED_SECRET")
@ -45,17 +54,17 @@ async def gitlab_webhook(background_tasks: BackgroundTasks, request: Request):
    if not gitlab_token:
        return JSONResponse(status_code=status.HTTP_401_UNAUTHORIZED, content=jsonable_encoder({"message": "unauthorized"}))
    data = await request.json()
-    logging.info(json.dumps(data))
+    get_logger().info(json.dumps(data))
    if data.get('object_kind') == 'merge_request' and data['object_attributes'].get('action') in ['open', 'reopen']:
-        logging.info(f"A merge request has been opened: {data['object_attributes'].get('title')}")
+        get_logger().info(f"A merge request has been opened: {data['object_attributes'].get('title')}")
        url = data['object_attributes'].get('url')
-        background_tasks.add_task(PRAgent().handle_request, url, "/review")
+        handle_request(background_tasks, url, "/review")
    elif data.get('object_kind') == 'note' and data['event_type'] == 'note':
        if 'merge_request' in data:
            mr = data['merge_request']
            url = mr.get('url')
            body = data.get('object_attributes', {}).get('note')
-            background_tasks.add_task(PRAgent().handle_request, url, body)
+            handle_request(background_tasks, url, body)
    return JSONResponse(status_code=status.HTTP_200_OK, content=jsonable_encoder({"message": "success"}))


--- a/pr_agent/servers/serverless.py
+++ b/pr_agent/servers/serverless.py
@ -1,12 +1,10 @@
-import logging
-
 from fastapi import FastAPI
 from mangum import Mangum

+from pr_agent.log import setup_logger
 from pr_agent.servers.github_app import router

-logger = logging.getLogger()
-logger.setLevel(logging.DEBUG)
+setup_logger()

 app = FastAPI()
 app.include_router(router)
--- a/pr_agent/settings/configuration.toml
+++ b/pr_agent/settings/configuration.toml
@ -31,11 +31,15 @@ publish_labels=true
 publish_description_as_comment=false
 add_original_user_description=false
 keep_original_user_title=false
+use_bullet_points=true
 extra_instructions = ""
+
 # markers
 use_description_markers=false
 include_generated_by_header=true

+#custom_labels = ['Bug fix', 'Tests', 'Bug fix with tests', 'Refactoring', 'Enhancement', 'Documentation', 'Other']
+
 [pr_questions] # /ask #

 [pr_code_suggestions] # /improve #
@ -122,4 +126,4 @@ max_issues_to_scan = 500
 [pinecone]
 # fill and place in .secrets.toml
 #api_key = ...
-# environment = "gcp-starter"
+# environment = "gcp-starter"
--- a/pr_agent/settings/custom_labels.toml
+++ b/pr_agent/settings/custom_labels.toml
@ -0,0 +1,18 @@
+[config]
+enable_custom_labels=false
+
+## template for custom labels
+#[custom_labels."Bug fix"]
+#description = "Fixes a bug in the code"
+#[custom_labels."Tests"]
+#description = "Adds or modifies tests"
+#[custom_labels."Bug fix with tests"]
+#description = "Fixes a bug in the code and adds or modifies tests"
+#[custom_labels."Refactoring"]
+#description = "Code refactoring without changing functionality"
+#[custom_labels."Enhancement"]
+#description = "Adds new features or functionality"
+#[custom_labels."Documentation"]
+#description = "Adds or modifies documentation"
+#[custom_labels."Other"]
+#description = "Other changes that do not fit in any of the above categories"
--- a/pr_agent/settings/language_extensions.toml
+++ b/pr_agent/settings/language_extensions.toml
@ -433,3 +433,6 @@ reStructuredText = [".rst", ".rest", ".rest.txt", ".rst.txt", ]
 wisp = [".wisp", ]
 xBase = [".prg", ".prw", ]

+[docs_blacklist_extensions]
+# Disable docs for these extensions of text files and scripts that are not programming languages of function, classes and methods
+docs_blacklist = ['sql', 'txt', 'yaml', 'json', 'xml', 'md', 'rst', 'rest', 'rest.txt', 'rst.txt', 'mdpolicy', 'mdown', 'markdown', 'mdwn', 'mkd', 'mkdn', 'mkdown', 'sh']
--- a/pr_agent/settings/pr_custom_labels.toml
+++ b/pr_agent/settings/pr_custom_labels.toml
@ -0,0 +1,72 @@
+[pr_custom_labels_prompt]
+system="""You are CodiumAI-PR-Reviewer, a language model designed to review git pull requests.
+Your task is to label the type of the PR content.
+- Make sure not to focus the new PR code (the '+' lines).
+- If needed, each YAML output should be in block scalar format ('|-')
+{%- if extra_instructions %}
+
+Extra instructions from the user:
+'
+{{ extra_instructions }}
+'
+{% endif %}
+
+You must use the following YAML schema to format your answer:
+```yaml
+PR Type:
+  type: array
+{%- if enable_custom_labels %}
+  description: One or more labels that describe the PR type. Don't output the description in the parentheses.
+{%- endif %}
+  items:
+    type: string
+    enum:
+{%- if enable_custom_labels %}
+{{ custom_labels }}
+{%- else %}
+      - Bug fix
+      - Tests
+      - Refactoring
+      - Enhancement
+      - Documentation
+      - Other
+{%- endif %}
+
+Example output:
+```yaml
+PR Type:
+{%- if enable_custom_labels %}
+{{ custom_labels_examples }}
+{%- else %}
+  - Bug fix
+  - Tests
+{%- endif %}
+```
+
+Make sure to output a valid YAML. Don't repeat the prompt in the answer, and avoid outputting the 'type' and 'description' fields.
+"""
+
+user="""PR Info:
+Previous title: '{{title}}'
+Previous description: '{{description}}'
+Branch: '{{branch}}'
+{%- if language %}
+
+Main language: {{language}}
+{%- endif %}
+{%- if commit_messages_str %}
+
+Commit messages:
+{{commit_messages_str}}
+{%- 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 YAML, and nothing else):
+```yaml
+"""
--- a/pr_agent/settings/pr_description_prompts.toml
+++ b/pr_agent/settings/pr_description_prompts.toml
@ -19,19 +19,26 @@ PR Title:
  description: an informative title for the PR, describing its main theme
 PR Type:
  type: array
+{%- if enable_custom_labels %}
+  description: One or more labels that describe the PR type. Don't output the description in the parentheses.
+{%- endif %}
  items:
    type: string
    enum:
+{%- if enable_custom_labels %}
+{{ custom_labels }}
+{%- else %}
      - Bug fix
      - Tests
-      - Bug fix with tests
      - Refactoring
      - Enhancement
      - Documentation
      - Other
+{%- endif %}
 PR Description:
  type: string
-  description: an informative and concise description of the PR
+  description: an informative and concise description of the PR.
+  {%- if use_bullet_points %} Use bullet points. {% endif %}
 PR Main Files Walkthrough:
  type: array
  maxItems: 10
@ -51,7 +58,11 @@ Example output:
 PR Title: |-
  ...
 PR Type:
+{%- if enable_custom_labels %}
+{{ custom_labels_examples }}
+{%- else %}
  - Bug fix
+{%- endif %}
 PR Description: |-
  ...
 PR Main Files Walkthrough:
--- a/pr_agent/settings/pr_reviewer_prompts.toml
+++ b/pr_agent/settings/pr_reviewer_prompts.toml
@ -25,7 +25,7 @@ code line that already existed in the file....
 The review should focus on new code added in the PR (lines starting with '+'), and not on code that already existed in the file (lines starting with '-', or without prefix).

 {%- if num_code_suggestions > 0 %}
- Provide up to {{ num_code_suggestions }} code suggestions.
+- Provide up to {{ num_code_suggestions }} code suggestions. Try to provide diverse and insightful suggestions.
 - Focus on important suggestions like fixing code problems, issues and bugs. As a second priority, provide suggestions for meaningful code improvements, like performance, vulnerability, modularity, and best practices.
 - Avoid making suggestions that have already been implemented in the PR code. For example, if you want to add logs, or change a variable to const, or anything else, make sure it isn't already in the PR code.
 - Don't suggest to add docstring, type hints, or comments.
@ -51,13 +51,22 @@ PR Analysis:
    description: summary of the PR in 2-3 sentences.
  Type of PR:
    type: string
+{%- if enable_custom_labels %}
+  description: One or more labels that describe the PR type. Don't output the description in the parentheses.
+{%- endif %}
+  items:
+    type: string
    enum:
+{%- if enable_custom_labels %}
+{{ custom_labels }}
+{%- else %}
      - Bug fix
      - Tests
      - Refactoring
      - Enhancement
      - Documentation
      - Other
+{%- endif %}
 {%- if require_score %}
  Score:
    type: int
@ -99,10 +108,10 @@ PR Feedback:
  General suggestions:
    type: string
    description: |-
-      General suggestions and feedback for the contributors and maintainers of
-      this PR. May include important suggestions for the overall structure,
-      primary purpose, best practices, critical bugs, and other aspects of the
-      PR. Don't address PR title and description, or lack of tests. Explain your suggestions.
+      General suggestions and feedback for the contributors and maintainers of this PR.
+      May include important suggestions for the overall structure,
+      primary purpose, best practices, critical bugs, and other aspects of the PR.
+      Don't address PR title and description, or lack of tests. Explain your suggestions.
 {%- if num_code_suggestions > 0 %}
  Code feedback:
    type: array
@ -115,11 +124,10 @@ PR Feedback:
      suggestion:
        type: string
        description: |-
-          a concrete suggestion for meaningfully improving the new PR code. Also
-          describe how, specifically, the suggestion can be applied to new PR
-          code. Add tags with importance measure that matches each suggestion
-          ('important' or 'medium'). Do not make suggestions for updating or
-          adding docstrings, renaming PR title and description, or linter like.
+          a concrete suggestion for meaningfully improving the new PR code.
+          Also describe how, specifically, the suggestion can be applied to new PR code.
+          Add tags with importance measure that matches each suggestion ('important' or 'medium').
+          Do not make suggestions for updating or adding docstrings, renaming PR title and description, or linter like.
      relevant line:
        type: string
        description: |-
--- a/pr_agent/tools/pr_add_docs.py
+++ b/pr_agent/tools/pr_add_docs.py
@ -1,16 +1,17 @@
 import copy
-import logging
 import textwrap
-from typing import List, Dict
+from typing import Dict
+
 from jinja2 import Environment, StrictUndefined

 from pr_agent.algo.ai_handler import AiHandler
-from pr_agent.algo.pr_processing import get_pr_diff, retry_with_fallback_models, get_pr_multi_diffs
+from pr_agent.algo.pr_processing import get_pr_diff, retry_with_fallback_models
 from pr_agent.algo.token_handler import TokenHandler
 from pr_agent.algo.utils import load_yaml
 from pr_agent.config_loader import get_settings
-from pr_agent.git_providers import BitbucketProvider, get_git_provider
+from pr_agent.git_providers import get_git_provider
 from pr_agent.git_providers.git_provider import get_main_pr_language
+from pr_agent.log import get_logger


 class PRAddDocs:
@ -43,34 +44,39 @@ class PRAddDocs:

    async def run(self):
        try:
-            logging.info('Generating code Docs for PR...')
+            get_logger().info('Generating code Docs for PR...')
            if get_settings().config.publish_output:
                self.git_provider.publish_comment("Generating Documentation...", is_temporary=True)

-            logging.info('Preparing PR documentation...')
+            get_logger().info('Preparing PR documentation...')
            await retry_with_fallback_models(self._prepare_prediction)
            data = self._prepare_pr_code_docs()
            if (not data) or (not 'Code Documentation' in data):
-                logging.info('No code documentation found for PR.')
+                get_logger().info('No code documentation found for PR.')
                return

            if get_settings().config.publish_output:
-                logging.info('Pushing PR documentation...')
+                get_logger().info('Pushing PR documentation...')
                self.git_provider.remove_initial_comment()
-                logging.info('Pushing inline code documentation...')
+                get_logger().info('Pushing inline code documentation...')
                self.push_inline_docs(data)
        except Exception as e:
-            logging.error(f"Failed to generate code documentation for PR, error: {e}")
+            get_logger().error(f"Failed to generate code documentation for PR, error: {e}")

    async def _prepare_prediction(self, model: str):
-        logging.info('Getting PR diff...')
+        get_logger().info('Getting PR diff...')
+
+        # Disable adding docs to scripts and other non-relevant text files
+        from pr_agent.algo.language_handler import bad_extensions
+        bad_extensions += get_settings().docs_blacklist_extensions.docs_blacklist
+
        self.patches_diff = get_pr_diff(self.git_provider,
                                        self.token_handler,
                                        model,
                                        add_line_numbers_to_hunks=True,
                                        disable_extra_lines=False)

-        logging.info('Getting AI prediction...')
+        get_logger().info('Getting AI prediction...')
        self.prediction = await self._get_prediction(model)

    async def _get_prediction(self, model: str):
@ -80,8 +86,8 @@ class PRAddDocs:
        system_prompt = environment.from_string(get_settings().pr_add_docs_prompt.system).render(variables)
        user_prompt = environment.from_string(get_settings().pr_add_docs_prompt.user).render(variables)
        if get_settings().config.verbosity_level >= 2:
-            logging.info(f"\nSystem prompt:\n{system_prompt}")
-            logging.info(f"\nUser prompt:\n{user_prompt}")
+            get_logger().info(f"\nSystem prompt:\n{system_prompt}")
+            get_logger().info(f"\nUser prompt:\n{user_prompt}")
        response, finish_reason = await self.ai_handler.chat_completion(model=model, temperature=0.2,
                                                                        system=system_prompt, user=user_prompt)

@ -103,7 +109,7 @@ class PRAddDocs:
        for d in data['Code Documentation']:
            try:
                if get_settings().config.verbosity_level >= 2:
-                    logging.info(f"add_docs: {d}")
+                    get_logger().info(f"add_docs: {d}")
                relevant_file = d['relevant file'].strip()
                relevant_line = int(d['relevant line'])  # absolute position
                documentation = d['documentation']
@ -118,11 +124,11 @@ class PRAddDocs:
                                             'relevant_lines_end': relevant_line})
            except Exception:
                if get_settings().config.verbosity_level >= 2:
-                    logging.info(f"Could not parse code docs: {d}")
+                    get_logger().info(f"Could not parse code docs: {d}")

        is_successful = self.git_provider.publish_code_suggestions(docs)
        if not is_successful:
-            logging.info("Failed to publish code docs, trying to publish each docs separately")
+            get_logger().info("Failed to publish code docs, trying to publish each docs separately")
            for doc_suggestion in docs:
                self.git_provider.publish_code_suggestions([doc_suggestion])

@ -154,7 +160,7 @@ class PRAddDocs:
                        new_code_snippet = new_code_snippet.rstrip() + "\n" + original_initial_line
        except Exception as e:
            if get_settings().config.verbosity_level >= 2:
-                logging.info(f"Could not dedent code snippet for file {relevant_file}, error: {e}")
+                get_logger().info(f"Could not dedent code snippet for file {relevant_file}, error: {e}")

        return new_code_snippet

--- a/pr_agent/tools/pr_code_suggestions.py
+++ b/pr_agent/tools/pr_code_suggestions.py
@ -1,16 +1,17 @@
 import copy
-import logging
 import textwrap
-from typing import List, Dict
+from typing import Dict, List
+
 from jinja2 import Environment, StrictUndefined

 from pr_agent.algo.ai_handler import AiHandler
-from pr_agent.algo.pr_processing import get_pr_diff, retry_with_fallback_models, get_pr_multi_diffs
+from pr_agent.algo.pr_processing import get_pr_diff, get_pr_multi_diffs, retry_with_fallback_models
 from pr_agent.algo.token_handler import TokenHandler
 from pr_agent.algo.utils import load_yaml
 from pr_agent.config_loader import get_settings
-from pr_agent.git_providers import BitbucketProvider, get_git_provider
+from pr_agent.git_providers import get_git_provider
 from pr_agent.git_providers.git_provider import get_main_pr_language
+from pr_agent.log import get_logger


 class PRCodeSuggestions:
@ -52,42 +53,42 @@ class PRCodeSuggestions:

    async def run(self):
        try:
-            logging.info('Generating code suggestions for PR...')
+            get_logger().info('Generating code suggestions for PR...')
            if get_settings().config.publish_output:
                self.git_provider.publish_comment("Preparing review...", is_temporary=True)

-            logging.info('Preparing PR review...')
+            get_logger().info('Preparing PR review...')
            if not self.is_extended:
                await retry_with_fallback_models(self._prepare_prediction)
                data = self._prepare_pr_code_suggestions()
            else:
                data = await retry_with_fallback_models(self._prepare_prediction_extended)
            if (not data) or (not 'Code suggestions' in data):
-                logging.info('No code suggestions found for PR.')
+                get_logger().info('No code suggestions found for PR.')
                return

            if (not self.is_extended and get_settings().pr_code_suggestions.rank_suggestions) or \
                    (self.is_extended and get_settings().pr_code_suggestions.rank_extended_suggestions):
-                logging.info('Ranking Suggestions...')
+                get_logger().info('Ranking Suggestions...')
                data['Code suggestions'] = await self.rank_suggestions(data['Code suggestions'])

            if get_settings().config.publish_output:
-                logging.info('Pushing PR review...')
+                get_logger().info('Pushing PR review...')
                self.git_provider.remove_initial_comment()
-                logging.info('Pushing inline code suggestions...')
+                get_logger().info('Pushing inline code suggestions...')
                self.push_inline_code_suggestions(data)
        except Exception as e:
-            logging.error(f"Failed to generate code suggestions for PR, error: {e}")
+            get_logger().error(f"Failed to generate code suggestions for PR, error: {e}")

    async def _prepare_prediction(self, model: str):
-        logging.info('Getting PR diff...')
+        get_logger().info('Getting PR diff...')
        self.patches_diff = get_pr_diff(self.git_provider,
                                        self.token_handler,
                                        model,
                                        add_line_numbers_to_hunks=True,
                                        disable_extra_lines=True)

-        logging.info('Getting AI prediction...')
+        get_logger().info('Getting AI prediction...')
        self.prediction = await self._get_prediction(model)

    async def _get_prediction(self, model: str):
@ -97,8 +98,8 @@ class PRCodeSuggestions:
        system_prompt = environment.from_string(get_settings().pr_code_suggestions_prompt.system).render(variables)
        user_prompt = environment.from_string(get_settings().pr_code_suggestions_prompt.user).render(variables)
        if get_settings().config.verbosity_level >= 2:
-            logging.info(f"\nSystem prompt:\n{system_prompt}")
-            logging.info(f"\nUser prompt:\n{user_prompt}")
+            get_logger().info(f"\nSystem prompt:\n{system_prompt}")
+            get_logger().info(f"\nUser prompt:\n{user_prompt}")
        response, finish_reason = await self.ai_handler.chat_completion(model=model, temperature=0.2,
                                                                        system=system_prompt, user=user_prompt)

@ -120,7 +121,7 @@ class PRCodeSuggestions:
        for d in data['Code suggestions']:
            try:
                if get_settings().config.verbosity_level >= 2:
-                    logging.info(f"suggestion: {d}")
+                    get_logger().info(f"suggestion: {d}")
                relevant_file = d['relevant file'].strip()
                relevant_lines_start = int(d['relevant lines start'])  # absolute position
                relevant_lines_end = int(d['relevant lines end'])
@ -136,11 +137,11 @@ class PRCodeSuggestions:
                                         'relevant_lines_end': relevant_lines_end})
            except Exception:
                if get_settings().config.verbosity_level >= 2:
-                    logging.info(f"Could not parse suggestion: {d}")
+                    get_logger().info(f"Could not parse suggestion: {d}")

        is_successful = self.git_provider.publish_code_suggestions(code_suggestions)
        if not is_successful:
-            logging.info("Failed to publish code suggestions, trying to publish each suggestion separately")
+            get_logger().info("Failed to publish code suggestions, trying to publish each suggestion separately")
            for code_suggestion in code_suggestions:
                self.git_provider.publish_code_suggestions([code_suggestion])

@ -162,19 +163,19 @@ class PRCodeSuggestions:
                    new_code_snippet = textwrap.indent(new_code_snippet, delta_spaces * " ").rstrip('\n')
        except Exception as e:
            if get_settings().config.verbosity_level >= 2:
-                logging.info(f"Could not dedent code snippet for file {relevant_file}, error: {e}")
+                get_logger().info(f"Could not dedent code snippet for file {relevant_file}, error: {e}")

        return new_code_snippet

    async def _prepare_prediction_extended(self, model: str) -> dict:
-        logging.info('Getting PR diff...')
+        get_logger().info('Getting PR diff...')
        patches_diff_list = get_pr_multi_diffs(self.git_provider, self.token_handler, model,
                                               max_calls=get_settings().pr_code_suggestions.max_number_of_calls)

-        logging.info('Getting multi AI predictions...')
+        get_logger().info('Getting multi AI predictions...')
        prediction_list = []
        for i, patches_diff in enumerate(patches_diff_list):
-            logging.info(f"Processing chunk {i + 1} of {len(patches_diff_list)}")
+            get_logger().info(f"Processing chunk {i + 1} of {len(patches_diff_list)}")
            self.patches_diff = patches_diff
            prediction = await self._get_prediction(model)
            prediction_list.append(prediction)
@ -222,8 +223,8 @@ class PRCodeSuggestions:
                variables)
            user_prompt = environment.from_string(get_settings().pr_sort_code_suggestions_prompt.user).render(variables)
            if get_settings().config.verbosity_level >= 2:
-                logging.info(f"\nSystem prompt:\n{system_prompt}")
-                logging.info(f"\nUser prompt:\n{user_prompt}")
+                get_logger().info(f"\nSystem prompt:\n{system_prompt}")
+                get_logger().info(f"\nUser prompt:\n{user_prompt}")
            response, finish_reason = await self.ai_handler.chat_completion(model=model, system=system_prompt,
                                                                            user=user_prompt)

@ -238,7 +239,7 @@ class PRCodeSuggestions:
                data_sorted = data_sorted[:new_len]
        except Exception as e:
            if get_settings().config.verbosity_level >= 1:
-                logging.info(f"Could not sort suggestions, error: {e}")
+                get_logger().info(f"Could not sort suggestions, error: {e}")
            data_sorted = suggestion_list

        return data_sorted
--- a/pr_agent/tools/pr_config.py
+++ b/pr_agent/tools/pr_config.py
@ -1,7 +1,6 @@
-import logging
-
 from pr_agent.config_loader import get_settings
 from pr_agent.git_providers import get_git_provider
+from pr_agent.log import get_logger


 class PRConfig:
@ -19,11 +18,11 @@ class PRConfig:
        self.git_provider = get_git_provider()(pr_url)

    async def run(self):
-        logging.info('Getting configuration settings...')
-        logging.info('Preparing configs...')
+        get_logger().info('Getting configuration settings...')
+        get_logger().info('Preparing configs...')
        pr_comment = self._prepare_pr_configs()
        if get_settings().config.publish_output:
-            logging.info('Pushing configs...')
+            get_logger().info('Pushing configs...')
            self.git_provider.publish_comment(pr_comment)
            self.git_provider.remove_initial_comment()
        return ""
@ -44,5 +43,5 @@ class PRConfig:
                comment_str += f"\n{header.lower()}.{key.lower()} = {repr(value) if isinstance(value, str) else value}"
                comment_str += "  "
        if get_settings().config.verbosity_level >= 2:
-            logging.info(f"comment_str:\n{comment_str}")
+            get_logger().info(f"comment_str:\n{comment_str}")
        return comment_str
--- a/pr_agent/tools/pr_description.py
+++ b/pr_agent/tools/pr_description.py
@ -1,7 +1,5 @@
 import copy
-import json
 import re
-import logging
 from typing import List, Tuple

 from jinja2 import Environment, StrictUndefined
@ -9,10 +7,11 @@ from jinja2 import Environment, StrictUndefined
 from pr_agent.algo.ai_handler import AiHandler
 from pr_agent.algo.pr_processing import get_pr_diff, retry_with_fallback_models
 from pr_agent.algo.token_handler import TokenHandler
-from pr_agent.algo.utils import load_yaml
+from pr_agent.algo.utils import load_yaml, set_custom_labels
 from pr_agent.config_loader import get_settings
 from pr_agent.git_providers import get_git_provider
 from pr_agent.git_providers.git_provider import get_main_pr_language
+from pr_agent.log import get_logger


 class PRDescription:
@ -41,8 +40,12 @@ class PRDescription:
            "description": self.git_provider.get_pr_description(full=False),
            "language": self.main_pr_language,
            "diff": "",  # empty diff for initial calculation
+            "use_bullet_points": get_settings().pr_description.use_bullet_points,
            "extra_instructions": get_settings().pr_description.extra_instructions,
-            "commit_messages_str": self.git_provider.get_commit_messages()
+            "commit_messages_str": self.git_provider.get_commit_messages(),
+            "enable_custom_labels": get_settings().config.enable_custom_labels,
+            "custom_labels": "",
+            "custom_labels_examples": "",
        }

        self.user_description = self.git_provider.get_user_description()
@ -65,13 +68,13 @@ class PRDescription:
        """

        try:
-            logging.info(f"Generating a PR description {self.pr_id}")
+            get_logger().info(f"Generating a PR description {self.pr_id}")
            if get_settings().config.publish_output:
                self.git_provider.publish_comment("Preparing PR description...", is_temporary=True)

            await retry_with_fallback_models(self._prepare_prediction)

-            logging.info(f"Preparing answer {self.pr_id}")
+            get_logger().info(f"Preparing answer {self.pr_id}")
            if self.prediction:
                self._prepare_data()
            else:
@ -88,7 +91,7 @@ class PRDescription:
            full_markdown_description = f"## Title\n\n{pr_title}\n\n___\n{pr_body}"

            if get_settings().config.publish_output:
-                logging.info(f"Pushing answer {self.pr_id}")
+                get_logger().info(f"Pushing answer {self.pr_id}")
                if get_settings().pr_description.publish_description_as_comment:
                    self.git_provider.publish_comment(full_markdown_description)
                else:
@ -100,7 +103,7 @@ class PRDescription:
                        self.git_provider.publish_labels(pr_labels + current_labels)
                self.git_provider.remove_initial_comment()
        except Exception as e:
-            logging.error(f"Error generating PR description {self.pr_id}: {e}")
+            get_logger().error(f"Error generating PR description {self.pr_id}: {e}")
        
        return ""

@ -121,9 +124,9 @@ class PRDescription:
        if get_settings().pr_description.use_description_markers and 'pr_agent:' not in self.user_description:
            return None

-        logging.info(f"Getting PR diff {self.pr_id}")
+        get_logger().info(f"Getting PR diff {self.pr_id}")
        self.patches_diff = get_pr_diff(self.git_provider, self.token_handler, model)
-        logging.info(f"Getting AI prediction {self.pr_id}")
+        get_logger().info(f"Getting AI prediction {self.pr_id}")
        self.prediction = await self._get_prediction(model)

    async def _get_prediction(self, model: str) -> str:
@ -140,12 +143,13 @@ class PRDescription:
        variables["diff"] = self.patches_diff  # update diff

        environment = Environment(undefined=StrictUndefined)
+        set_custom_labels(variables)
        system_prompt = environment.from_string(get_settings().pr_description_prompt.system).render(variables)
        user_prompt = environment.from_string(get_settings().pr_description_prompt.user).render(variables)

        if get_settings().config.verbosity_level >= 2:
-            logging.info(f"\nSystem prompt:\n{system_prompt}")
-            logging.info(f"\nUser prompt:\n{user_prompt}")
+            get_logger().info(f"\nSystem prompt:\n{system_prompt}")
+            get_logger().info(f"\nUser prompt:\n{user_prompt}")

        response, finish_reason = await self.ai_handler.chat_completion(
            model=model,
@ -156,7 +160,6 @@ class PRDescription:

        return response

-
    def _prepare_data(self):
        # Load the AI prediction data into a dictionary
        self.data = load_yaml(self.prediction.strip())
@ -178,7 +181,7 @@ class PRDescription:
        return pr_types

    def _prepare_pr_answer_with_markers(self) -> Tuple[str, str]:
-        logging.info(f"Using description marker replacements {self.pr_id}")
+        get_logger().info(f"Using description marker replacements {self.pr_id}")
        title = self.vars["title"]
        body = self.user_description
        if get_settings().pr_description.include_generated_by_header:
@ -186,6 +189,11 @@ class PRDescription:
        else:
            ai_header = ""

+        ai_type = self.data.get('PR Type')
+        if ai_type and not re.search(r'<!--\s*pr_agent:type\s*-->', body):
+            pr_type = f"{ai_header}{ai_type}"
+            body = body.replace('pr_agent:type', pr_type)
+
        ai_summary = self.data.get('PR Description')
        if ai_summary and not re.search(r'<!--\s*pr_agent:summary\s*-->', body):
            summary = f"{ai_header}{ai_summary}"
@ -252,6 +260,6 @@ class PRDescription:
                pr_body += "\n___\n"

        if get_settings().config.verbosity_level >= 2:
-            logging.info(f"title:\n{title}\n{pr_body}")
+            get_logger().info(f"title:\n{title}\n{pr_body}")

        return title, pr_body
--- a/pr_agent/tools/pr_generate_labels.py
+++ b/pr_agent/tools/pr_generate_labels.py
@ -0,0 +1,163 @@
+import copy
+import re
+from typing import List, Tuple
+
+from jinja2 import Environment, StrictUndefined
+
+from pr_agent.algo.ai_handler import AiHandler
+from pr_agent.algo.pr_processing import get_pr_diff, retry_with_fallback_models
+from pr_agent.algo.token_handler import TokenHandler
+from pr_agent.algo.utils import load_yaml, set_custom_labels
+from pr_agent.config_loader import get_settings
+from pr_agent.git_providers import get_git_provider
+from pr_agent.git_providers.git_provider import get_main_pr_language
+from pr_agent.log import get_logger
+
+
+class PRGenerateLabels:
+    def __init__(self, pr_url: str, args: list = None):
+        """
+        Initialize the PRGenerateLabels object with the necessary attributes and objects for generating labels
+        corresponding to the PR using an AI model.
+        Args:
+            pr_url (str): The URL of the pull request.
+            args (list, optional): List of arguments passed to the PRGenerateLabels class. Defaults to None.
+        """
+        # Initialize the git provider and main PR language
+        self.git_provider = get_git_provider()(pr_url)
+        self.main_pr_language = get_main_pr_language(
+            self.git_provider.get_languages(), self.git_provider.get_files()
+        )
+        self.pr_id = self.git_provider.get_pr_id()
+
+        # Initialize the AI handler
+        self.ai_handler = AiHandler()
+    
+        # Initialize the variables dictionary
+        self.vars = {
+            "title": self.git_provider.pr.title,
+            "branch": self.git_provider.get_pr_branch(),
+            "description": self.git_provider.get_pr_description(full=False),
+            "language": self.main_pr_language,
+            "diff": "",  # empty diff for initial calculation
+            "use_bullet_points": get_settings().pr_description.use_bullet_points,
+            "extra_instructions": get_settings().pr_description.extra_instructions,
+            "commit_messages_str": self.git_provider.get_commit_messages(),
+            "custom_labels": "",
+            "custom_labels_examples": "",
+            "enable_custom_labels": get_settings().config.enable_custom_labels,
+        }
+
+        # Initialize the token handler
+        self.token_handler = TokenHandler(
+            self.git_provider.pr,
+            self.vars,
+            get_settings().pr_custom_labels_prompt.system,
+            get_settings().pr_custom_labels_prompt.user,
+        )
+    
+        # Initialize patches_diff and prediction attributes
+        self.patches_diff = None
+        self.prediction = None
+
+    async def run(self):
+        """
+        Generates a PR labels using an AI model and publishes it to the PR.
+        """
+
+        try:
+            get_logger().info(f"Generating a PR labels {self.pr_id}")
+            if get_settings().config.publish_output:
+                self.git_provider.publish_comment("Preparing PR labels...", is_temporary=True)
+
+            await retry_with_fallback_models(self._prepare_prediction)
+
+            get_logger().info(f"Preparing answer {self.pr_id}")
+            if self.prediction:
+                self._prepare_data()
+            else:
+                return None
+
+            pr_labels = self._prepare_labels()
+
+            if get_settings().config.publish_output:
+                get_logger().info(f"Pushing labels {self.pr_id}")
+                if self.git_provider.is_supported("get_labels"):
+                    current_labels = self.git_provider.get_labels()
+                    if current_labels is None:
+                        current_labels = []
+                    self.git_provider.publish_labels(pr_labels + current_labels)
+                self.git_provider.remove_initial_comment()
+        except Exception as e:
+            get_logger().error(f"Error generating PR labels {self.pr_id}: {e}")
+        
+        return ""
+
+    async def _prepare_prediction(self, model: str) -> None:
+        """
+        Prepare the AI prediction for the PR labels based on the provided model.
+
+        Args:
+            model (str): The name of the model to be used for generating the prediction.
+
+        Returns:
+            None
+
+        Raises:
+            Any exceptions raised by the 'get_pr_diff' and '_get_prediction' functions.
+
+        """
+
+        get_logger().info(f"Getting PR diff {self.pr_id}")
+        self.patches_diff = get_pr_diff(self.git_provider, self.token_handler, model)
+        get_logger().info(f"Getting AI prediction {self.pr_id}")
+        self.prediction = await self._get_prediction(model)
+
+    async def _get_prediction(self, model: str) -> str:
+        """
+        Generate an AI prediction for the PR labels based on the provided model.
+
+        Args:
+            model (str): The name of the model to be used for generating the prediction.
+
+        Returns:
+            str: The generated AI prediction.
+        """
+        variables = copy.deepcopy(self.vars)
+        variables["diff"] = self.patches_diff  # update diff
+
+        environment = Environment(undefined=StrictUndefined)
+        set_custom_labels(variables)
+        system_prompt = environment.from_string(get_settings().pr_custom_labels_prompt.system).render(variables)
+        user_prompt = environment.from_string(get_settings().pr_custom_labels_prompt.user).render(variables)
+
+        if get_settings().config.verbosity_level >= 2:
+            get_logger().info(f"\nSystem prompt:\n{system_prompt}")
+            get_logger().info(f"\nUser prompt:\n{user_prompt}")
+
+        response, finish_reason = await self.ai_handler.chat_completion(
+            model=model,
+            temperature=0.2,
+            system=system_prompt,
+            user=user_prompt
+        )
+
+        return response
+
+    def _prepare_data(self):
+        # Load the AI prediction data into a dictionary
+        self.data = load_yaml(self.prediction.strip())
+
+
+
+    def _prepare_labels(self) -> List[str]:
+        pr_types = []
+
+        # If the 'PR Type' key is present in the dictionary, split its value by comma and assign it to 'pr_types'
+        if 'PR Type' in self.data:
+            if type(self.data['PR Type']) == list:
+                pr_types = self.data['PR Type']
+            elif type(self.data['PR Type']) == str:
+                pr_types = self.data['PR Type'].split(',')
+
+        return pr_types
--- a/pr_agent/tools/pr_information_from_user.py
+++ b/pr_agent/tools/pr_information_from_user.py
@ -1,5 +1,4 @@
 import copy
-import logging

 from jinja2 import Environment, StrictUndefined

@ -9,6 +8,7 @@ from pr_agent.algo.token_handler import TokenHandler
 from pr_agent.config_loader import get_settings
 from pr_agent.git_providers import get_git_provider
 from pr_agent.git_providers.git_provider import get_main_pr_language
+from pr_agent.log import get_logger


 class PRInformationFromUser:
@ -34,22 +34,22 @@ class PRInformationFromUser:
        self.prediction = None

    async def run(self):
-        logging.info('Generating question to the user...')
+        get_logger().info('Generating question to the user...')
        if get_settings().config.publish_output:
            self.git_provider.publish_comment("Preparing questions...", is_temporary=True)
        await retry_with_fallback_models(self._prepare_prediction)
-        logging.info('Preparing questions...')
+        get_logger().info('Preparing questions...')
        pr_comment = self._prepare_pr_answer()
        if get_settings().config.publish_output:
-            logging.info('Pushing questions...')
+            get_logger().info('Pushing questions...')
            self.git_provider.publish_comment(pr_comment)
            self.git_provider.remove_initial_comment()
        return ""

    async def _prepare_prediction(self, model):
-        logging.info('Getting PR diff...')
+        get_logger().info('Getting PR diff...')
        self.patches_diff = get_pr_diff(self.git_provider, self.token_handler, model)
-        logging.info('Getting AI prediction...')
+        get_logger().info('Getting AI prediction...')
        self.prediction = await self._get_prediction(model)

    async def _get_prediction(self, model: str):
@ -59,8 +59,8 @@ class PRInformationFromUser:
        system_prompt = environment.from_string(get_settings().pr_information_from_user_prompt.system).render(variables)
        user_prompt = environment.from_string(get_settings().pr_information_from_user_prompt.user).render(variables)
        if get_settings().config.verbosity_level >= 2:
-            logging.info(f"\nSystem prompt:\n{system_prompt}")
-            logging.info(f"\nUser prompt:\n{user_prompt}")
+            get_logger().info(f"\nSystem prompt:\n{system_prompt}")
+            get_logger().info(f"\nUser prompt:\n{user_prompt}")
        response, finish_reason = await self.ai_handler.chat_completion(model=model, temperature=0.2,
                                                                        system=system_prompt, user=user_prompt)
        return response
@ -68,7 +68,7 @@ class PRInformationFromUser:
    def _prepare_pr_answer(self) -> str:
        model_output = self.prediction.strip()
        if get_settings().config.verbosity_level >= 2:
-            logging.info(f"answer_str:\n{model_output}")
+            get_logger().info(f"answer_str:\n{model_output}")
        answer_str = f"{model_output}\n\n Please respond to the questions above in the following format:\n\n" +\
                     "\n>/answer\n>1) ...\n>2) ...\n>...\n"
        return answer_str
--- a/pr_agent/tools/pr_questions.py
+++ b/pr_agent/tools/pr_questions.py
@ -1,5 +1,4 @@
 import copy
-import logging

 from jinja2 import Environment, StrictUndefined

@ -9,6 +8,7 @@ from pr_agent.algo.token_handler import TokenHandler
 from pr_agent.config_loader import get_settings
 from pr_agent.git_providers import get_git_provider
 from pr_agent.git_providers.git_provider import get_main_pr_language
+from pr_agent.log import get_logger


 class PRQuestions:
@ -44,22 +44,22 @@ class PRQuestions:
        return question_str

    async def run(self):
-        logging.info('Answering a PR question...')
+        get_logger().info('Answering a PR question...')
        if get_settings().config.publish_output:
            self.git_provider.publish_comment("Preparing answer...", is_temporary=True)
        await retry_with_fallback_models(self._prepare_prediction)
-        logging.info('Preparing answer...')
+        get_logger().info('Preparing answer...')
        pr_comment = self._prepare_pr_answer()
        if get_settings().config.publish_output:
-            logging.info('Pushing answer...')
+            get_logger().info('Pushing answer...')
            self.git_provider.publish_comment(pr_comment)
            self.git_provider.remove_initial_comment()
        return ""

    async def _prepare_prediction(self, model: str):
-        logging.info('Getting PR diff...')
+        get_logger().info('Getting PR diff...')
        self.patches_diff = get_pr_diff(self.git_provider, self.token_handler, model)
-        logging.info('Getting AI prediction...')
+        get_logger().info('Getting AI prediction...')
        self.prediction = await self._get_prediction(model)

    async def _get_prediction(self, model: str):
@ -69,8 +69,8 @@ class PRQuestions:
        system_prompt = environment.from_string(get_settings().pr_questions_prompt.system).render(variables)
        user_prompt = environment.from_string(get_settings().pr_questions_prompt.user).render(variables)
        if get_settings().config.verbosity_level >= 2:
-            logging.info(f"\nSystem prompt:\n{system_prompt}")
-            logging.info(f"\nUser prompt:\n{user_prompt}")
+            get_logger().info(f"\nSystem prompt:\n{system_prompt}")
+            get_logger().info(f"\nUser prompt:\n{user_prompt}")
        response, finish_reason = await self.ai_handler.chat_completion(model=model, temperature=0.2,
                                                                        system=system_prompt, user=user_prompt)
        return response
@ -79,5 +79,5 @@ class PRQuestions:
        answer_str = f"Question: {self.question_str}\n\n"
        answer_str += f"Answer:\n{self.prediction.strip()}\n\n"
        if get_settings().config.verbosity_level >= 2:
-            logging.info(f"answer_str:\n{answer_str}")
+            get_logger().info(f"answer_str:\n{answer_str}")
        return answer_str
--- a/pr_agent/tools/pr_reviewer.py
+++ b/pr_agent/tools/pr_reviewer.py
@ -1,6 +1,4 @@
 import copy
-import json
-import logging
 from collections import OrderedDict
 from typing import List, Tuple

@ -9,13 +7,13 @@ from jinja2 import Environment, StrictUndefined
 from yaml import SafeLoader

 from pr_agent.algo.ai_handler import AiHandler
-from pr_agent.algo.pr_processing import get_pr_diff, retry_with_fallback_models, \
-    find_line_number_of_relevant_line_in_file, clip_tokens
+from pr_agent.algo.pr_processing import get_pr_diff, retry_with_fallback_models
 from pr_agent.algo.token_handler import TokenHandler
-from pr_agent.algo.utils import convert_to_markdown, try_fix_json, try_fix_yaml, load_yaml
+from pr_agent.algo.utils import convert_to_markdown, load_yaml, try_fix_yaml, set_custom_labels
 from pr_agent.config_loader import get_settings
 from pr_agent.git_providers import get_git_provider
 from pr_agent.git_providers.git_provider import IncrementalPR, get_main_pr_language
+from pr_agent.log import get_logger
 from pr_agent.servers.help import actions_help_text, bot_help_text


@ -65,6 +63,8 @@ class PRReviewer:
            'answer_str': answer_str,
            "extra_instructions": get_settings().pr_reviewer.extra_instructions,
            "commit_messages_str": self.git_provider.get_commit_messages(),
+            "custom_labels": "",
+            "enable_custom_labels": get_settings().config.enable_custom_labels,
        }

        self.token_handler = TokenHandler(
@ -98,29 +98,29 @@ class PRReviewer:

        try:
            if self.is_auto and not get_settings().pr_reviewer.automatic_review:
-                logging.info(f'Automatic review is disabled {self.pr_url}')
+                get_logger().info(f'Automatic review is disabled {self.pr_url}')
                return None

-            logging.info(f'Reviewing PR: {self.pr_url} ...')
+            get_logger().info(f'Reviewing PR: {self.pr_url} ...')

            if get_settings().config.publish_output:
                self.git_provider.publish_comment("Preparing review...", is_temporary=True)

            await retry_with_fallback_models(self._prepare_prediction)

-            logging.info('Preparing PR review...')
+            get_logger().info('Preparing PR review...')
            pr_comment = self._prepare_pr_review()

            if get_settings().config.publish_output:
-                logging.info('Pushing PR review...')
+                get_logger().info('Pushing PR review...')
                self.git_provider.publish_comment(pr_comment)
                self.git_provider.remove_initial_comment()

                if get_settings().pr_reviewer.inline_code_comments:
-                    logging.info('Pushing inline code comments...')
+                    get_logger().info('Pushing inline code comments...')
                    self._publish_inline_code_comments()
        except Exception as e:
-            logging.error(f"Failed to review PR: {e}")
+            get_logger().error(f"Failed to review PR: {e}")

    async def _prepare_prediction(self, model: str) -> None:
        """
@ -132,9 +132,9 @@ class PRReviewer:
        Returns:
            None
        """
-        logging.info('Getting PR diff...')
+        get_logger().info('Getting PR diff...')
        self.patches_diff = get_pr_diff(self.git_provider, self.token_handler, model)
-        logging.info('Getting AI prediction...')
+        get_logger().info('Getting AI prediction...')
        self.prediction = await self._get_prediction(model)

    async def _get_prediction(self, model: str) -> str:
@ -151,12 +151,13 @@ class PRReviewer:
        variables["diff"] = self.patches_diff  # update diff

        environment = Environment(undefined=StrictUndefined)
+        set_custom_labels(variables)
        system_prompt = environment.from_string(get_settings().pr_review_prompt.system).render(variables)
        user_prompt = environment.from_string(get_settings().pr_review_prompt.user).render(variables)

        if get_settings().config.verbosity_level >= 2:
-            logging.info(f"\nSystem prompt:\n{system_prompt}")
-            logging.info(f"\nUser prompt:\n{user_prompt}")
+            get_logger().info(f"\nSystem prompt:\n{system_prompt}")
+            get_logger().info(f"\nUser prompt:\n{user_prompt}")

        response, finish_reason = await self.ai_handler.chat_completion(
            model=model,
@ -249,7 +250,7 @@ class PRReviewer:

        # Log markdown response if verbosity level is high
        if get_settings().config.verbosity_level >= 2:
-            logging.info(f"Markdown response:\n{markdown_text}")
+            get_logger().info(f"Markdown response:\n{markdown_text}")

        if markdown_text == None or len(markdown_text) == 0:
            markdown_text = ""
@ -268,7 +269,7 @@ class PRReviewer:
        try:
            data = yaml.load(review_text, Loader=SafeLoader)
        except Exception as e:
-            logging.error(f"Failed to parse AI prediction: {e}")
+            get_logger().error(f"Failed to parse AI prediction: {e}")
            data = try_fix_yaml(review_text)

        comments: List[str] = []
@ -277,7 +278,7 @@ class PRReviewer:
            relevant_line_in_file = suggestion.get('relevant line', '').strip()
            content = suggestion.get('suggestion', '')
            if not relevant_file or not relevant_line_in_file or not content:
-                logging.info("Skipping inline comment with missing file/line/content")
+                get_logger().info("Skipping inline comment with missing file/line/content")
                continue

            if self.git_provider.is_supported("create_inline_comment"):
--- a/pr_agent/tools/pr_similar_issue.py
+++ b/pr_agent/tools/pr_similar_issue.py
@ -1,18 +1,18 @@
-import copy
-import json
-import logging
+import time
 from enum import Enum
-from typing import List, Tuple
-import pinecone
+from typing import List
+
 import openai
 import pandas as pd
+import pinecone
+from pinecone_datasets import Dataset, DatasetMetadata
 from pydantic import BaseModel, Field

 from pr_agent.algo import MAX_TOKENS
 from pr_agent.algo.token_handler import TokenHandler
 from pr_agent.config_loader import get_settings
 from pr_agent.git_providers import get_git_provider
-from pinecone_datasets import Dataset, DatasetMetadata
+from pr_agent.log import get_logger

 MODEL = "text-embedding-ada-002"

@ -47,6 +47,13 @@ class PRSimilarIssue:

        # check if index exists, and if repo is already indexed
        run_from_scratch = False
+        if run_from_scratch:  # for debugging
+            pinecone.init(api_key=api_key, environment=environment)
+            if index_name in pinecone.list_indexes():
+                get_logger().info('Removing index...')
+                pinecone.delete_index(index_name)
+                get_logger().info('Done')
+
        upsert = True
        pinecone.init(api_key=api_key, environment=environment)
        if not index_name in pinecone.list_indexes():
@ -62,11 +69,11 @@ class PRSimilarIssue:
                    upsert = False

        if run_from_scratch or upsert:  # index the entire repo
-            logging.info('Indexing the entire repo...')
+            get_logger().info('Indexing the entire repo...')

-            logging.info('Getting issues...')
+            get_logger().info('Getting issues...')
            issues = list(repo_obj.get_issues(state='all'))
-            logging.info('Done')
+            get_logger().info('Done')
            self._update_index_with_issues(issues, repo_name_for_index, upsert=upsert)
        else:  # update index if needed
            pinecone_index = pinecone.Index(index_name=index_name)
@ -92,20 +99,20 @@ class PRSimilarIssue:
                    break

            if issues_to_update:
-                logging.info(f'Updating index with {counter} new issues...')
+                get_logger().info(f'Updating index with {counter} new issues...')
                self._update_index_with_issues(issues_to_update, repo_name_for_index, upsert=True)
            else:
-                logging.info('No new issues to update')
+                get_logger().info('No new issues to update')

    async def run(self):
-        logging.info('Getting issue...')
+        get_logger().info('Getting issue...')
        repo_name, original_issue_number = self.git_provider._parse_issue_url(self.issue_url.split('=')[-1])
        issue_main = self.git_provider.repo_obj.get_issue(original_issue_number)
        issue_str, comments, number = self._process_issue(issue_main)
        openai.api_key = get_settings().openai.key
-        logging.info('Done')
+        get_logger().info('Done')

-        logging.info('Querying...')
+        get_logger().info('Querying...')
        res = openai.Embedding.create(input=[issue_str], engine=MODEL)
        embeds = [record['embedding'] for record in res['data']]
        pinecone_index = pinecone.Index(index_name=self.index_name)
@ -117,7 +124,16 @@ class PRSimilarIssue:
        relevant_comment_number_list = []
        score_list = []
        for r in res['matches']:
-            issue_number = int(r["id"].split('.')[0].split('_')[-1])
+            # skip example issue
+            if 'example_issue_' in r["id"]:
+                continue
+
+            try:
+                issue_number = int(r["id"].split('.')[0].split('_')[-1])
+            except:
+                get_logger().debug(f"Failed to parse issue number from {r['id']}")
+                continue
+
            if original_issue_number == issue_number:
                continue
            if issue_number not in relevant_issues_number_list:
@ -127,9 +143,9 @@ class PRSimilarIssue:
            else:
                relevant_comment_number_list.append(-1)
            score_list.append(str("{:.2f}".format(r['score'])))
-        logging.info('Done')
+        get_logger().info('Done')

-        logging.info('Publishing response...')
+        get_logger().info('Publishing response...')
        similar_issues_str = "### Similar Issues\n___\n\n"
        for i, issue_number_similar in enumerate(relevant_issues_number_list):
            issue = self.git_provider.repo_obj.get_issue(issue_number_similar)
@ -140,8 +156,8 @@ class PRSimilarIssue:
            similar_issues_str += f"{i + 1}. **[{title}]({url})** (score={score_list[i]})\n\n"
        if get_settings().config.publish_output:
            response = issue_main.create_comment(similar_issues_str)
-        logging.info(similar_issues_str)
-        logging.info('Done')
+        get_logger().info(similar_issues_str)
+        get_logger().info('Done')

    def _process_issue(self, issue):
        header = issue.title
@ -155,7 +171,7 @@ class PRSimilarIssue:
        return issue_str, comments, number

    def _update_index_with_issues(self, issues_list, repo_name_for_index, upsert=False):
-        logging.info('Processing issues...')
+        get_logger().info('Processing issues...')
        corpus = Corpus()
        example_issue_record = Record(
            id=f"example_issue_{repo_name_for_index}",
@ -171,9 +187,9 @@ class PRSimilarIssue:

            counter += 1
            if counter % 100 == 0:
-                logging.info(f"Scanned {counter} issues")
+                get_logger().info(f"Scanned {counter} issues")
            if counter >= self.max_issues_to_scan:
-                logging.info(f"Scanned {self.max_issues_to_scan} issues, stopping")
+                get_logger().info(f"Scanned {self.max_issues_to_scan} issues, stopping")
                break

            issue_str, comments, number = self._process_issue(issue)
@ -210,9 +226,9 @@ class PRSimilarIssue:
                            )
                            corpus.append(comment_record)
        df = pd.DataFrame(corpus.dict()["documents"])
-        logging.info('Done')
+        get_logger().info('Done')

-        logging.info('Embedding...')
+        get_logger().info('Embedding...')
        openai.api_key = get_settings().openai.key
        list_to_encode = list(df["text"].values)
        try:
@ -220,7 +236,7 @@ class PRSimilarIssue:
            embeds = [record['embedding'] for record in res['data']]
        except:
            embeds = []
-            logging.error('Failed to embed entire list, embedding one by one...')
+            get_logger().error('Failed to embed entire list, embedding one by one...')
            for i, text in enumerate(list_to_encode):
                try:
                    res = openai.Embedding.create(input=[text], engine=MODEL)
@ -231,21 +247,23 @@ class PRSimilarIssue:
        meta = DatasetMetadata.empty()
        meta.dense_model.dimension = len(embeds[0])
        ds = Dataset.from_pandas(df, meta)
-        logging.info('Done')
+        get_logger().info('Done')

        api_key = get_settings().pinecone.api_key
        environment = get_settings().pinecone.environment
        if not upsert:
-            logging.info('Creating index from scratch...')
+            get_logger().info('Creating index from scratch...')
            ds.to_pinecone_index(self.index_name, api_key=api_key, environment=environment)
+            time.sleep(15)  # wait for pinecone to finalize indexing before querying
        else:
-            logging.info('Upserting index...')
+            get_logger().info('Upserting index...')
            namespace = ""
            batch_size: int = 100
            concurrency: int = 10
            pinecone.init(api_key=api_key, environment=environment)
            ds._upsert_to_index(self.index_name, namespace, batch_size, concurrency)
-        logging.info('Done')
+            time.sleep(5)  # wait for pinecone to finalize upserting before querying
+        get_logger().info('Done')


 class IssueLevel(str, Enum):
--- a/pr_agent/tools/pr_update_changelog.py
+++ b/pr_agent/tools/pr_update_changelog.py
@ -1,5 +1,4 @@
 import copy
-import logging
 from datetime import date
 from time import sleep
 from typing import Tuple
@ -10,8 +9,9 @@ from pr_agent.algo.ai_handler import AiHandler
 from pr_agent.algo.pr_processing import get_pr_diff, retry_with_fallback_models
 from pr_agent.algo.token_handler import TokenHandler
 from pr_agent.config_loader import get_settings
-from pr_agent.git_providers import GithubProvider, get_git_provider
+from pr_agent.git_providers import get_git_provider
 from pr_agent.git_providers.git_provider import get_main_pr_language
+from pr_agent.log import get_logger

 CHANGELOG_LINES = 50

@ -48,26 +48,26 @@ class PRUpdateChangelog:
    async def run(self):
        # assert type(self.git_provider) == GithubProvider, "Currently only Github is supported"

-        logging.info('Updating the changelog...')
+        get_logger().info('Updating the changelog...')
        if get_settings().config.publish_output:
            self.git_provider.publish_comment("Preparing changelog updates...", is_temporary=True)
        await retry_with_fallback_models(self._prepare_prediction)
-        logging.info('Preparing PR changelog updates...')
+        get_logger().info('Preparing PR changelog updates...')
        new_file_content, answer = self._prepare_changelog_update()
        if get_settings().config.publish_output:
            self.git_provider.remove_initial_comment()
-            logging.info('Publishing changelog updates...')
+            get_logger().info('Publishing changelog updates...')
            if self.commit_changelog:
-                logging.info('Pushing PR changelog updates to repo...')
+                get_logger().info('Pushing PR changelog updates to repo...')
                self._push_changelog_update(new_file_content, answer)
            else:
-                logging.info('Publishing PR changelog as comment...')
+                get_logger().info('Publishing PR changelog as comment...')
                self.git_provider.publish_comment(f"**Changelog updates:**\n\n{answer}")

    async def _prepare_prediction(self, model: str):
-        logging.info('Getting PR diff...')
+        get_logger().info('Getting PR diff...')
        self.patches_diff = get_pr_diff(self.git_provider, self.token_handler, model)
-        logging.info('Getting AI prediction...')
+        get_logger().info('Getting AI prediction...')
        self.prediction = await self._get_prediction(model)

    async def _get_prediction(self, model: str):
@ -77,8 +77,8 @@ class PRUpdateChangelog:
        system_prompt = environment.from_string(get_settings().pr_update_changelog_prompt.system).render(variables)
        user_prompt = environment.from_string(get_settings().pr_update_changelog_prompt.user).render(variables)
        if get_settings().config.verbosity_level >= 2:
-            logging.info(f"\nSystem prompt:\n{system_prompt}")
-            logging.info(f"\nUser prompt:\n{user_prompt}")
+            get_logger().info(f"\nSystem prompt:\n{system_prompt}")
+            get_logger().info(f"\nUser prompt:\n{user_prompt}")
        response, finish_reason = await self.ai_handler.chat_completion(model=model, temperature=0.2,
                                                                        system=system_prompt, user=user_prompt)

@ -100,7 +100,7 @@ class PRUpdateChangelog:
                      "\n>'/update_changelog --pr_update_changelog.push_changelog_changes=true'\n"

        if get_settings().config.verbosity_level >= 2:
-            logging.info(f"answer:\n{answer}")
+            get_logger().info(f"answer:\n{answer}")

        return new_file_content, answer

@ -149,7 +149,7 @@ Example:
        except Exception:
            self.changelog_file_str = ""
            if self.commit_changelog:
-                logging.info("No CHANGELOG.md file found in the repository. Creating one...")
+                get_logger().info("No CHANGELOG.md file found in the repository. Creating one...")
                changelog_file = self.git_provider.repo_obj.create_file(path="CHANGELOG.md",
                                                                             message='add CHANGELOG.md',
                                                                             content="",
--- a/requirements.txt
+++ b/requirements.txt
@ -20,4 +20,5 @@ ujson==5.8.0
 azure-devops==7.1.0b3
 msrest==0.7.1
 pinecone-client
-pinecone-datasets @ git+https://github.com/mrT23/pinecone-datasets.git@main
+pinecone-datasets @ git+https://github.com/mrT23/pinecone-datasets.git@main
+loguru==0.7.2
--- a/tests/unittest/test_handle_patch_deletions.py
+++ b/tests/unittest/test_handle_patch_deletions.py
@ -43,18 +43,6 @@ class TestHandlePatchDeletions:
        assert handle_patch_deletions(patch, original_file_content_str, new_file_content_str,
                                      file_name) == patch.rstrip()

-    # Tests that handle_patch_deletions logs a message when verbosity_level is greater than 0
-    def test_handle_patch_deletions_happy_path_verbosity_level_greater_than_0(self, caplog):
-        patch = '--- a/file.py\n+++ b/file.py\n@@ -1,2 +1,2 @@\n-foo\n-bar\n+baz\n'
-        original_file_content_str = 'foo\nbar\n'
-        new_file_content_str = ''
-        file_name = 'file.py'
-        get_settings().config.verbosity_level = 1
-
-        with caplog.at_level(logging.INFO):
-            handle_patch_deletions(patch, original_file_content_str, new_file_content_str, file_name)
-            assert any("Processing file" in message for message in caplog.messages)
-
    # Tests that handle_patch_deletions returns 'File was deleted' when new_file_content_str is empty
    def test_handle_patch_deletions_edge_case_new_file_content_empty(self):
        patch = '--- a/file.py\n+++ b/file.py\n@@ -1,2 +1,2 @@\n-foo\n-bar\n'
Author	SHA1	Message	Date
Hussam Lawen	9a585de364	Merge pull request #404 from Codium-ai/tr/final_fixes final fixes	2023-10-29 12:31:40 +02:00
mrT23	c27dc436c4	final fixes	2023-10-29 12:29:14 +02:00
mrT23	7374243d0b	enable_custom_labels	2023-10-29 11:40:36 +02:00
mrT23	5c568bc0c5	Merge pull request #403 from Codium-ai/tr/fix_custom_labels Refactoring Custom Labels Handling and Documentation Update	2023-10-29 02:34:18 -07:00
mrT23	22c196cb3b	Merge remote-tracking branch 'origin/main' into tr/fix_custom_labels # Conflicts: # pr_agent/git_providers/github_provider.py	2023-10-29 10:58:42 +02:00
mrT23	d2cc856cfc	Merge pull request #402 from Codium-ai/tr/github_action_uses_toml Update GitHub Action to Use .pr_agent.toml	2023-10-29 01:55:33 -07:00
mrT23	d772213cfc	fix labels	2023-10-29 08:58:12 +02:00
mrT23	638db96311	github action now also uses .pr_agent.toml	2023-10-28 13:34:32 +03:00
Hussam Lawen	4dffabf397	Merge pull request #396 from Codium-ai/hl/custom_labels Implement Custom Labels for PRs	2023-10-28 01:37:54 +03:00
Hussam.lawen	6f2bbd3baa	Add documentation	2023-10-28 00:45:59 +03:00
Hussam.lawen	9e41f3780c	disable custom labels by default	2023-10-27 21:22:56 +03:00
Hussam.lawen	f53ec1d0cc	move enable custom labels to custom labels function	2023-10-27 21:12:58 +03:00
mrT23	f7666cb59a	Update INSTALL.md	2023-10-27 11:49:39 +03:00
Hussam.lawen	a7cb59ca8b	small fix	2023-10-27 08:10:29 +03:00
Hussam.lawen	ca0ea77415	refactor	2023-10-27 07:58:42 +03:00
Hussam.lawen	0cf27e5fee	custom labels disabled by default	2023-10-27 07:54:59 +03:00
Hussam.lawen	f3bdbfc103	Add /generate_labels function + fix issues	2023-10-26 23:28:33 +03:00
mrT23	20e3acdd86	Merge pull request #393 from Kryslynn93/patch-1 Update configuration.toml	2023-10-26 07:43:00 -07:00
mrT23	f965b09571	Merge pull request #398 from Codium-ai/tr/readme_updates Update Documentation and Installation Instructions	2023-10-26 07:37:05 -07:00
mrT23	b8583c998d	readme	2023-10-26 12:16:58 +03:00
mrT23	726594600b	readme	2023-10-26 12:10:14 +03:00
mrT23	c77cc1d6ed	readme	2023-10-26 11:56:03 +03:00
mrT23	b6c9e01a59	readme	2023-10-26 11:51:32 +03:00
Ori Kotek	ec673214c8	Update INSTALL.md	2023-10-26 11:18:07 +03:00
Hussam.lawen	16777a5334	Add custom label description	2023-10-25 13:48:27 +03:00
Hussam.lawen	1a89c7eadf	refactor + add description options	2023-10-24 22:28:57 +03:00
Hussam.lawen	07617eab5a	add custom labels	2023-10-24 22:06:27 +03:00
Krystal Boozel	f9e4c2b098	Update configuration.toml	2023-10-23 21:34:12 -04:00
Hussam.lawen	fa24413201	Custom Labels	2023-10-23 16:29:33 +03:00
mrT23	b6cabda586	quick fix	2023-10-19 17:24:37 +03:00
mrT23	abbce60f18	Merge remote-tracking branch 'origin/main'	2023-10-19 17:10:30 +03:00
mrT23	5daaaf2c1d	quick fix	2023-10-19 17:10:21 +03:00
mrT23	e8f207691e	Merge pull request #391 from Codium-ai/tr/readme Update and Enhance DESCRIBE.md Documentation	2023-10-19 02:03:50 -07:00
mrT23	b0dce4ceae	describe	2023-10-19 12:02:12 +03:00
Ori Kotek	fc494296d7	Merge pull request #387 from Codium-ai/ok/json_logging_in_bitbucket Enhancing Logging in Bitbucket, GitLab, and Google Cloud Storage Secret Provider	2023-10-19 11:59:26 +03:00
mrT23	67b4069540	describe	2023-10-19 11:45:41 +03:00
mrT23	e6defcc846	describe	2023-10-19 11:43:18 +03:00
mrT23	096fcbbc17	describe	2023-10-19 11:40:01 +03:00
mrT23	eb7add1c77	describe	2023-10-19 11:38:21 +03:00
Hussam Lawen	1b6fb3ea53	Merge pull request #385 from Codium-ai/hl/fix_add_docs_in_scripts Add Blacklist for Non-Editable File Extensions in Documentation	2023-10-19 11:21:36 +03:00
mrT23	c57b70f1d4	Merge pull request #390 from Codium-ai/tr/readme Enhancing Documentation and Updating Configuration for PR Descriptions	2023-10-19 01:04:24 -07:00
mrT23	a2c3db463a	use_bullet_points	2023-10-19 10:45:42 +03:00
mrT23	193da1c356	update readme	2023-10-19 09:22:26 +03:00
mrT23	5bc26880b3	update readme	2023-10-19 09:20:36 +03:00
mrT23	21a1cc970e	- update readme - minor prompts change	2023-10-19 09:16:20 +03:00
Ori Kotek	954727ad67	Merge pull request #386 from Codium-ai/ok/fix_bitbucket_pipeline Refactor Bitbucket Pipeline Integration and Update Documentation	2023-10-18 16:45:26 +03:00
Ori Kotek	1314898cbf	Enhance logging in bitbucket_app, gitlab_webhook, and google_cloud_storage_secret_provider with JSON format and additional context	2023-10-18 16:44:03 +03:00
Ori Kotek	ff04d459d7	Update Bitbucket Pipeline instructions in INSTALL.md, remove redundant functionality	2023-10-18 15:46:43 +03:00
Hussam Lawen	88ca501c0c	Merge pull request #377 from zmeir/zmeir-review_incremental_detect_header Get previous incremental review	2023-10-18 00:30:42 +03:00
mrT23	fe284a8f91	Merge pull request #382 from Codium-ai/tr/similar_issue_fix Enhancements and Error Handling in Similar Issue Tool	2023-10-17 09:49:35 -07:00
mrT23	d41fe0cf79	comment	2023-10-17 19:45:04 +03:00
Hussam.lawen	3673924fe9	Add docs editable blacklist of file extensions like sql, yaml...	2023-10-17 18:50:39 +03:00
mrT23	d5c098de73	another protection	2023-10-17 10:21:05 +03:00
mrT23	9f5c0daa8e	protection	2023-10-17 09:43:48 +03:00
mrT23	bce2262d4e	Merge pull request #381 from moccajoghurt/feature-allow-custom-urls Support Custom Domain URLs for Azure DevOps Integration	2023-10-16 22:38:27 -07:00
Marius Anderie	e6f1e0520a	remove azure.com url restriction	2023-10-16 20:38:14 +02:00
Zohar Meir	d8de89ae33	Get previous incremental review When getting the last commit in `/review -i` consider also the last __incremental__ review, not just the last __full__ review Full disclosure I'm not really sure the `/review -i` feature work very well - I might be wrong but it seemed like the actual review in fact addressed all the changes in the PR, and not just the ones from the last review (even though it adds a link to the commit of the last review). I think the commit list gathered in `/review -i` doesn't propagate the actual list the reviewer uses. Again, I might be wrong, just took a brief glance at it.	2023-10-16 16:37:10 +03:00
Ori Kotek	428c38e3d9	Merge pull request #376 from Codium-ai/feature/better_logger Refactor logging system to use custom logger across the codebase	2023-10-16 16:32:27 +03:00
Ori Kotek	7ffdf8de37	Remove verbosity level check in handle_patch_deletions test	2023-10-16 16:25:57 +03:00
Ori Kotek	83e670c5df	Enhance logging context in github_app server with server type	2023-10-16 16:13:09 +03:00
Ori Kotek	c324d88be3	Refactor logging system to use custom logger across the codebase	2023-10-16 14:56:00 +03:00