Doc update

Update suggestion content in pr_code_suggestions_prompts.toml

.dockerignore

@@ -1,2 +1,5 @@
 venv/
-pr_agent/settings/.secrets.toml
+pr_agent/settings/.secrets.toml
+pics/
+pr_agent.egg-info/
+build/

.github/workflows/build-and-test.yaml

@@ -0,0 +1,38 @@
+name: Build-and-test
+
+on:
+  push:
+  pull_request:
+    types: [ opened, reopened ]
+
+jobs:
+  build-and-test:
+    runs-on: ubuntu-latest
+
+    steps:
+      - id: checkout
+        uses: actions/checkout@v2
+
+      - id: dockerx
+        name: Setup Docker Buildx
+        uses: docker/setup-buildx-action@v2
+
+      - id: build
+        name: Build dev docker
+        uses: docker/build-push-action@v2
+        with:
+          context: .
+          file: ./docker/Dockerfile
+          push: false
+          load: true
+          tags: codiumai/pr-agent:test
+          cache-from: type=gha,scope=dev
+          cache-to: type=gha,mode=max,scope=dev
+          target: test
+
+      - id: test
+        name: Test dev docker
+        run: |
+          docker run --rm codiumai/pr-agent:test pytest -v
+        
+          

.github/workflows/pr-agent-review.yaml

@@ -0,0 +1,35 @@
+# This workflow enables developers to call PR-Agents `/[actions]` in PR's comments and upon PR creation. 
+# Learn more at https://www.codium.ai/pr-agent/
+# This is v0.2 of this workflow file
+
+name: PR-Agent
+
+on:
+# pull_request:
+# issue_comment:
+  workflow_dispatch:
+
+permissions:
+  issues: write
+  pull-requests: write
+
+jobs:
+  pr_agent_job:
+    runs-on: ubuntu-latest
+    name: Run pr agent on every pull request
+    steps:
+      - name: PR Agent action step
+        id: pragent
+        uses: Codium-ai/pr-agent@main
+        env:
+          OPENAI_KEY: ${{ secrets.OPENAI_KEY }}
+          OPENAI_ORG: ${{ secrets.OPENAI_ORG }} # optional
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+          PINECONE.API_KEY: ${{ secrets.PINECONE_API_KEY }}
+          PINECONE.ENVIRONMENT: ${{ secrets.PINECONE_ENVIRONMENT }}
+          GITHUB_ACTION_CONFIG.AUTO_DESCRIBE: true
+          GITHUB_ACTION_CONFIG.AUTO_REVIEW: true
+          GITHUB_ACTION_CONFIG.AUTO_IMPROVE: true
+
+
+

.github/workflows/review.yaml

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

.gitignore

@@ -1,4 +1,9 @@
 .idea/
 venv/
 pr_agent/settings/.secrets.toml
-__pycache__
+__pycache__
+dist/
+*.egg-info/
+build/
+review.md
+.DS_Store

.pr_agent.toml

@@ -0,0 +1,7 @@
+[pr_reviewer]
+enable_review_labels_effort = true
+enable_auto_approval = true
+
+
+[pr_code_suggestions]
+summarize=true

CHANGELOG.md

@@ -0,0 +1,45 @@
+## 2023-08-03
+
+### Optimized
+- Optimized PR diff processing by introducing caching for diff files, reducing the number of API calls.
+- Refactored `load_large_diff` function to generate a patch only when necessary.
+- Fixed a bug in the GitLab provider where the new file was not retrieved correctly.
+
+## 2023-08-02
+
+### Enhanced
+- Updated several tools in the `pr_agent` package to use commit messages in their functionality.
+- Commit messages are now retrieved and stored in the `vars` dictionary for each tool.
+- Added a section to display the commit messages in the prompts of various tools.
+
+## 2023-08-01
+
+### Enhanced
+- Introduced the ability to retrieve commit messages from pull requests across different git providers.
+- Implemented commit messages retrieval for GitHub and GitLab providers.
+- Updated the PR description template to include a section for commit messages if they exist.
+- Added support for repository-specific configuration files (.pr_agent.yaml) for the PR Agent.
+- Implemented this feature for both GitHub and GitLab providers.
+- Added a new configuration option 'use_repo_settings_file' to enable or disable the use of a repo-specific settings file.
+
+
+## 2023-07-30
+
+### Enhanced
+- Added the ability to modify any configuration parameter from 'configuration.toml' on-the-fly.
+- Updated the command line interface and bot commands to accept configuration changes as arguments.
+- Improved the PR agent to handle additional arguments for each action.
+
+## 2023-07-28
+
+### Improved
+- Enhanced error handling and logging in the GitLab provider.
+- Improved handling of inline comments and code suggestions in GitLab.
+- Fixed a bug where an additional unneeded line was added to code suggestions in GitLab.
+
+## 2023-07-26
+
+### Added
+- New feature for updating the CHANGELOG.md based on the contents of a PR.
+- Added support for this feature for the Github provider.
+- New configuration settings and prompts for the changelog update feature.

Dockerfile.github_action

@@ -1,8 +1,9 @@
 FROM python:3.10 as base
 
 WORKDIR /app
+ADD pyproject.toml .
 ADD requirements.txt .
-RUN pip install -r requirements.txt && rm requirements.txt
+RUN pip install . && rm pyproject.toml requirements.txt
 ENV PYTHONPATH=/app
 ADD pr_agent pr_agent
 ADD github_action/entrypoint.sh /

Dockerfile.github_action_dockerhub

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

INSTALL.md

@@ -0,0 +1,472 @@
+
+## Installation
+
+To get started with PR-Agent quickly, you first need to acquire two tokens:
+
+1. An OpenAI key from [here](https://platform.openai.com/api-keys), with access to GPT-4.
+2. A GitHub\GitLab\BitBucket personal access token (classic), with the repo scope. [GitHub from [here](https://github.com/settings/tokens)]
+
+There are several ways to use PR-Agent:
+
+**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 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)
+- [Bitbucket server and data center](INSTALL.md#bitbucket-server-and-data-center)
+---
+
+### Use Docker image (no installation required)
+
+A list of the relevant tools can be found in the [tools guide](./docs/TOOLS_GUIDE.md).
+
+To invoke a tool (for example `review`), you can run directly from the Docker image. Here's how:
+
+- For GitHub:
+```
+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:latest --pr_url <pr_url> review
+```
+
+Note: If you have a dedicated GitLab instance, you need to specify the custom url as variable:
+```
+docker run --rm -it -e OPENAI.KEY=<your key> -e CONFIG.GIT_PROVIDER=gitlab -e GITLAB.PERSONAL_ACCESS_TOKEN=<your token> -e GITLAB.URL=<your gitlab instance url> 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.
+
+---
+
+
+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
+```
+
+Or you can run a [specific released versions](./RELEASE_NOTES.md) of pr-agent, for example:
+```
+codiumai/pr-agent@v0.9
+```
+
+---
+
+### Run from source
+
+1. Clone this repository:
+
+```
+git clone https://github.com/Codium-ai/pr-agent.git
+```
+
+2. Navigate to the `/pr-agent` folder and install the requirements in your favorite virtual environment:
+
+```
+pip install -e .
+```
+
+*Note: If you get an error related to Rust in the dependency installation then make sure Rust is installed and in your `PATH`, instructions: https://rustup.rs*
+
+3. Copy the secrets template file and fill in your OpenAI key and your GitHub user token:
+
+```
+cp pr_agent/settings/.secrets_template.toml pr_agent/settings/.secrets.toml
+chmod 600 pr_agent/settings/.secrets.toml
+# Edit .secrets.toml file
+```
+
+4. Run the cli.py script:
+
+```
+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 --pr_url <pr_url> generate_labels
+python3 -m pr_agent.cli --issue_url <issue_url> similar_issue
+...
+```
+
+[Optional] Add the pr_agent folder to your PYTHONPATH
+```
+export PYTHONPATH=$PYTHONPATH:<PATH to pr_agent folder>
+```
+
+---
+
+### Run as a GitHub Action
+
+You can use our pre-built Github Action Docker image to run PR-Agent as a Github Action.
+
+1. Add the following file to your repository under `.github/workflows/pr_agent.yml`:
+
+```yaml
+on:
+  pull_request:
+    types:
+      - opened
+      - reopened
+      - ready_for_review
+      - review_requested
+
+  issue_comment:
+    types:
+      - created
+      - edited
+jobs:
+  pr_agent_job:
+    runs-on: ubuntu-latest
+    permissions:
+      issues: write
+      pull-requests: write
+      contents: write
+    name: Run pr agent on every pull request, respond to user comments
+    steps:
+      - name: PR Agent action step
+        id: pragent
+        uses: Codium-ai/pr-agent@main
+        env:
+          OPENAI_KEY: ${{ secrets.OPENAI_KEY }}
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+```
+** if you want to pin your action to a specific release (v0.7 for example) for stability reasons, use:
+```yaml
+on:
+  pull_request:
+    types:
+      - opened
+      - reopened
+      - ready_for_review
+      - review_requested
+
+  issue_comment:
+    types:
+      - created
+      - edited
+
+jobs:
+  pr_agent_job:
+    runs-on: ubuntu-latest
+    permissions:
+      issues: write
+      pull-requests: write
+      contents: write
+    name: Run pr agent on every pull request, respond to user comments
+    steps:
+      - name: PR Agent action step
+        id: pragent
+        uses: Codium-ai/pr-agent@v0.7
+        env:
+          OPENAI_KEY: ${{ secrets.OPENAI_KEY }}
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+```
+2. Add the following secret to your repository under `Settings > Secrets and variables > Actions > New repository secret > Add secret`:
+
+```
+Name = OPENAI_KEY
+Secret = <your key>
+```
+
+The GITHUB_TOKEN secret is automatically created by GitHub.
+
+3. Merge this change to your main branch.
+When you open your next PR, you should see a comment from `github-actions` bot with a review of your PR, and instructions on how to use the rest of the tools.
+
+4. You may configure PR-Agent by adding environment variables under the env section corresponding to any configurable property in the [configuration](pr_agent/settings/configuration.toml) file. Some examples:
+```yaml
+      env:
+        # ... previous environment values
+        OPENAI.ORG: "<Your organization name under your OpenAI account>"
+        PR_REVIEWER.REQUIRE_TESTS_REVIEW: "false" # Disable tests review
+        PR_CODE_SUGGESTIONS.NUM_CODE_SUGGESTIONS: 6 # Increase number of code suggestions
+```
+
+---
+
+### Run as a GitHub App
+Allowing you to automate the review process on your private or public repositories.
+
+1. Create a GitHub App from the [Github Developer Portal](https://docs.github.com/en/developers/apps/creating-a-github-app).
+
+   - Set the following permissions:
+     - Pull requests: Read & write
+     - Issue comment: Read & write
+     - Metadata: Read-only
+     - Contents: Read-only
+   - Set the following events:
+     - Issue comment
+     - Pull request
+     - Push (if you need to enable triggering on PR update)
+
+2. Generate a random secret for your app, and save it for later. For example, you can use:
+
+```
+WEBHOOK_SECRET=$(python -c "import secrets; print(secrets.token_hex(10))")
+```
+
+3. Acquire the following pieces of information from your app's settings page:
+
+   - App private key (click "Generate a private key" and save the file)
+   - App ID
+
+4. Clone this repository:
+
+```
+git clone https://github.com/Codium-ai/pr-agent.git
+```
+
+5. Copy the secrets template file and fill in the following:
+    ```
+    cp pr_agent/settings/.secrets_template.toml pr_agent/settings/.secrets.toml
+    # Edit .secrets.toml file
+    ```
+   - Your OpenAI key.
+   - Copy your app's private key to the private_key field.
+   - Copy your app's ID to the app_id field.
+   - Copy your app's webhook secret to the webhook_secret field.
+   - Set deployment_type to 'app' in [configuration.toml](./pr_agent/settings/configuration.toml)
+
+> The .secrets.toml file is not copied to the Docker image by default, and is only used for local development.
+> If you want to use the .secrets.toml file in your Docker image, you can add remove it from the .dockerignore file.
+> In most production environments, you would inject the secrets file as environment variables or as mounted volumes.
+> For example, in order to inject a secrets file as a volume in a Kubernetes environment you can update your pod spec to include the following,
+> assuming you have a secret named `pr-agent-settings` with a key named `.secrets.toml`:
+```
+       volumes:
+        - name: settings-volume
+          secret:
+            secretName: pr-agent-settings
+// ...
+       containers:
+// ...
+          volumeMounts:
+            - mountPath: /app/pr_agent/settings_prod
+              name: settings-volume
+```
+
+> Another option is to set the secrets as environment variables in your deployment environment, for example `OPENAI.KEY` and `GITHUB.USER_TOKEN`.
+
+6. Build a Docker image for the app and optionally push it to a Docker repository. We'll use Dockerhub as an example:
+
+```
+docker build . -t codiumai/pr-agent:github_app --target github_app -f docker/Dockerfile
+docker push codiumai/pr-agent:github_app  # Push to your Docker repository
+```
+
+7. Host the app using a server, serverless function, or container environment. Alternatively, for development and
+   debugging, you may use tools like smee.io to forward webhooks to your local machine.
+    You can check [Deploy as a Lambda Function](#deploy-as-a-lambda-function)
+
+8. Go back to your app's settings, and set the following:
+
+   - Webhook URL: The URL of your app's server or the URL of the smee.io channel.
+   - Webhook secret: The secret you generated earlier.
+
+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 `.pr_agent.toml`<br>
+> For more information please check out the [USAGE GUIDE](./Usage.md#working-with-github-app)
+---
+
+### Deploy as a Lambda Function
+
+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
+   ```
+3. Push image to ECR
+    ```shell
+	docker tag codiumai/pr-agent:serverless <AWS_ACCOUNT>.dkr.ecr.<AWS_REGION>.amazonaws.com/codiumai/pr-agent:serverless
+	docker push <AWS_ACCOUNT>.dkr.ecr.<AWS_REGION>.amazonaws.com/codiumai/pr-agent:serverless
+    ```
+4. Create a lambda function that uses the uploaded image. Set the lambda timeout to be at least 3m.
+5. Configure the lambda function to have a Function URL.
+6. In the environment variables of the Lambda function, specify `AZURE_DEVOPS_CACHE_DIR` to a writable location such as /tmp. (see [link](https://github.com/Codium-ai/pr-agent/pull/450#issuecomment-1840242269))
+7. 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`
+
+---
+
+### 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:
+
+1. Create an IAM user that you will use to read CodeCommit pull requests and post comments
+    * Note: That user should have CLI access only, not Console access
+2. Add IAM permissions to that user, to allow access to CodeCommit (see IAM Role example below)
+3. Generate an Access Key for your IAM user
+4. Set the Access Key and Secret using environment variables (see Access Key example below)
+5. Set the `git_provider` value to `codecommit` in the `pr_agent/settings/configuration.toml` settings file
+6. Set the `PYTHONPATH` to include your `pr-agent` project directory
+    * Option A: Add `PYTHONPATH="/PATH/TO/PROJECTS/pr-agent` to your `.env` file
+    * Option B: Set `PYTHONPATH` and run the CLI in one command, for example:
+        * `PYTHONPATH="/PATH/TO/PROJECTS/pr-agent python pr_agent/cli.py [--ARGS]`
+
+##### AWS CodeCommit IAM Role Example
+
+Example IAM permissions to that user to allow access to CodeCommit:
+
+* Note: The following is a working example of IAM permissions that has read access to the repositories and write access to allow posting comments
+* Note: If you only want pr-agent to review your pull requests, you can tighten the IAM permissions further, however this IAM example will work, and allow the pr-agent to post comments to the PR
+* Note: You may want to replace the `"Resource": "*"` with your list of repos, to limit access to only those repos
+
+```
+{
+    "Version": "2012-10-17",
+    "Statement": [
+        {
+            "Effect": "Allow",
+            "Action": [
+                "codecommit:BatchDescribe*",
+                "codecommit:BatchGet*",
+                "codecommit:Describe*",
+                "codecommit:EvaluatePullRequestApprovalRules",
+                "codecommit:Get*",
+                "codecommit:List*",
+                "codecommit:PostComment*",
+                "codecommit:PutCommentReaction",
+                "codecommit:UpdatePullRequestDescription",
+                "codecommit:UpdatePullRequestTitle"
+            ],
+            "Resource": "*"
+        }
+    ]
+}
+```
+
+##### AWS CodeCommit Access Key and Secret
+
+Example setting the Access Key and Secret using environment variables
+
+```sh
+export AWS_ACCESS_KEY_ID="XXXXXXXXXXXXXXXX"
+export AWS_SECRET_ACCESS_KEY="XXXXXXXXXXXXXXXX"
+export AWS_DEFAULT_REGION="us-east-1"
+```
+
+##### AWS CodeCommit CLI Example
+
+After you set up AWS CodeCommit using the instructions above, here is an example CLI run that tells pr-agent to **review** a given pull request.
+(Replace your specific PYTHONPATH and PR URL in the example)
+
+```sh
+PYTHONPATH="/PATH/TO/PROJECTS/pr-agent" python pr_agent/cli.py \
+  --pr_url https://us-east-1.console.aws.amazon.com/codesuite/codecommit/repositories/MY_REPO_NAME/pull-requests/321 \
+  review
+```
+
+---
+
+### 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:
+
+```
+WEBHOOK_SECRET=$(python -c "import secrets; print(secrets.token_hex(10))")
+```
+3. Follow the instructions to build the Docker image, setup a secrets file and deploy on your own server from [Method 5](#run-as-a-github-app) steps 4-7. Be sure to set the target to `gitlab_webhook` instead of `github_app` when building the Docker image.
+4. In the secrets file, fill in the following:
+    - Your OpenAI key.
+    - In the [gitlab] section, fill in personal_access_token and shared_secret. The access token can be a personal access token, or a group or project access token.
+    - Set deployment_type to 'gitlab' in [configuration.toml](./pr_agent/settings/configuration.toml)
+5. Create a webhook in GitLab. Set the URL to the URL of your app's server with the path `/webhook` (e.g. `http://pr-agent.example.com:3000/webhook`). Set the secret token to the generated secret from step 2.
+In the "Trigger" section, check the ‘comments’ and ‘merge request events’ boxes.
+6. Test your installation by opening a merge request or commenting on a merge request using one of CodiumAI's commands.
+
+
+
+### Run as a Bitbucket Pipeline
+
+
+You can use the Bitbucket Pipeline system to run PR-Agent on every pull request open or update.
+
+1. Add the following file in your repository bitbucket_pipelines.yml
+
+```yaml
+pipelines:
+    pull-requests:
+      '**':
+        - step:
+            name: PR Agent Review
+            image: python:3.10
+            services:
+              - docker
+            script:
+              - docker run -e CONFIG.GIT_PROVIDER=bitbucket -e OPENAI.KEY=$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 secure variables to your repository under Repository settings > Pipelines > Repository variables.
+OPENAI_API_KEY: <your key>
+BITBUCKET_BEARER_TOKEN: <your token>
+
+You can get a Bitbucket token for your repository by following Repository Settings -> Security -> Access Tokens.
+
+Note that comments on a PR are not supported in Bitbucket Pipeline.
+
+
+### Run using CodiumAI-hosted Bitbucket app
+
+Please contact <support@codium.ai> or visit [CodiumAI pricing page](https://www.codium.ai/pricing/) 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) implementation.
+
+
+### Bitbucket Server and Data Center
+
+Login into your on-prem instance of Bitbucket with your service account username and password.
+Navigate to `Manage account`, `HTTP Access tokens`, `Create Token`.
+Generate the token and add it to .secret.toml under `bitbucket_server` section
+
+```toml
+[bitbucket_server]
+bearer_token = "<your key>"
+```
+
+#### Run it as CLI
+
+Modify `configuration.toml`:
+
+```toml
+git_provider="bitbucket_server"
+```
+
+and pass the Pull request URL:
+```shell
+python cli.py --pr_url https://git.onpreminstanceofbitbucket.com/projects/PROJECT/repos/REPO/pull-requests/1 review
+```
+
+#### Run it as service
+
+To run pr-agent as webhook, build the docker image:
+```
+docker build . -t codiumai/pr-agent:bitbucket_server_webhook --target bitbucket_server_webhook -f docker/Dockerfile
+docker push codiumai/pr-agent:bitbucket_server_webhook  # Push to your Docker repository
+```
+
+Navigate to `Projects` or `Repositories`, `Settings`, `Webhooks`, `Create Webhook`.
+Fill the name and URL, Authentication None select the Pull Request Opened checkbox to receive that event as webhook.
+
+The URL should end with `/webhook`, for example: https://domain.com/webhook
+
+=======

PR_COMPRESSION.md

@@ -1,4 +1,4 @@
-# Git Patch Logic
+# PR Compression Strategy
 There are two scenarios:
 1. The PR is small enough to fit in a single prompt (including system and user prompt)
 2. The PR is too large to fit in a single prompt (including system and user prompt)
@@ -16,7 +16,7 @@ We prioritize the languages of the repo based on the following criteria:
 ## Small PR
 In this case, we can fit the entire PR in a single prompt:
 1. Exclude binary files and non code files (e.g. images, pdfs, etc)
-2. We Expand the surrounding context of each patch to 6 lines above and below the patch
+2. We Expand the surrounding context of each patch to 3 lines above and below the patch
 ## Large PR
 
 ### Motivation
@@ -25,13 +25,13 @@ We want to be able to pack as much information as possible in a single LMM promp
 
 
 
-#### PR compression strategy
+#### Compression strategy
 We prioritize additions over deletions:
  - Combine all deleted files into a single list (`deleted files`)
  - File patches are a list of hunks, remove all hunks of type deletion-only from the hunks in the file patch
 ####  Adaptive and token-aware file patch fitting
 We use [tiktoken](https://github.com/openai/tiktoken) to tokenize the patches after the modifications described above, and we use the following strategy to fit the patches into the prompt:
-1. Withing each language we sort the files by the number of tokens in the file (in descending order):
+1. Within each language we sort the files by the number of tokens in the file (in descending order):
    * ```[[file2.py, file.py],[file4.jsx, file3.js],[readme.md]]```
 2. Iterate through the patches in the order described above
 2. Add the patches to the prompt until the prompt reaches a certain buffer from the max token length
@@ -39,4 +39,4 @@ We use [tiktoken](https://github.com/openai/tiktoken) to tokenize the patches af
 4. If we haven't reached the max token length, add the `deleted files` to the prompt until the prompt reaches the max token length (hard stop), skip the rest of the patches.
 
 ### Example
-![](./pics/git_patch_logic.png)
+<kbd><img src=https://codium.ai/images/git_patch_logic.png width="768"></kbd>

README.md

@@ -2,277 +2,300 @@
 
 <div align="center">
 
-<img src="./pics/logo-dark.png#gh-dark-mode-only" width="250"/>
-<img src="./pics/logo-light.png#gh-light-mode-only" width="250"/>
 
+<picture>
+  <source media="(prefers-color-scheme: dark)" srcset="https://codium.ai/images/pr_agent/logo-dark.png" width="330">
+  <source media="(prefers-color-scheme: light)" srcset="https://codium.ai/images/pr_agent/logo-light.png" width="330">
+  <img alt="logo">
+</picture>
+<br/>
+Making pull requests less painful with an AI agent
 </div>
 
 [![GitHub license](https://img.shields.io/badge/License-Apache_2.0-blue.svg)](https://github.com/Codium-ai/pr-agent/blob/main/LICENSE)
 [![Discord](https://badgen.net/badge/icon/discord?icon=discord&label&color=purple)](https://discord.com/channels/1057273017547378788/1126104260430528613)
-
-CodiumAI `pr-agent` is an open-source tool aiming to help developers review PRs faster and more efficiently. It automatically analyzes the PR, provides feedback and suggestions, and can answer free-text questions.
-
+[![Twitter](https://img.shields.io/twitter/follow/codiumai)](https://twitter.com/codiumai)
+    <a href="https://github.com/Codium-ai/pr-agent/commits/main">
+    <img alt="GitHub" src="https://img.shields.io/github/last-commit/Codium-ai/pr-agent/main?style=for-the-badge" height="20">
+    </a>
 </div>
 
-- [Live demo](#live-demo)
-- [Quickstart](#Quickstart)
-- [Usage and tools](#usage-and-tools)
-- [Configuration](#Configuration)
+## Table of Contents
+- [News and Updates](#news-and-updates)
+- [Overview](#overview)
+- [Example results](#example-results)
+- [Try it now](#try-it-now)
+- [Installation](#installation)
+- [PR-Agent Pro 💎](#pr-agent-pro-)
 - [How it works](#how-it-works)
-- [Roadmap](#roadmap)
-- [Similar projects](#similar-projects)
+- [Why use PR-Agent?](#why-use-pr-agent)
+  
+## News and Updates
 
-## Live demo
+### Feb 29, 2024
+- You can now use the repo's [wiki page](https://github.com/Codium-ai/pr-agent/blob/main/Usage.md#configuration-options) to set configurations for PR-Agent 💎
 
-Experience GPT-4 powered PR review on your public GitHub repository with our hosted pr-agent. To try it, just mention `@CodiumAI-Agent` in any PR comment! The agent will generate a PR review in response.
+<kbd><img src="https://codium.ai/images/pr_agent/wiki_configuration.png" width="512"></kbd>
 
-![Review generation process](./pics/pr-agent-review-process1.gif)
 
-To set up your own pr-agent, see the [Quickstart](#Quickstart) section
+### Feb 21, 2024
+- Added a new command, `/help`, to easily provide a list of available tools and their descriptions, and run them interactively.
+
+<kbd>
+
+<img src="https://www.codium.ai/images/pr_agent/help.png" width="512">
+
+</kbd>
+
+### Feb 18, 2024
+- Introducing the `CI Feedback` tool 💎. The tool automatically triggers when a PR has a failed check. It analyzes the failed check, and provides summarized logs and analysis. Note that this feature requires read access to GitHub 'checks' and 'actions'. See [here](./docs/CI_FEEDBACK.md) for more details.
+- New ability - you can run `/ask` on specific lines of code in the PR from the PR's diff view. See [here](./docs/ASK.md#ask-lines) for more details.
+- Introducing support for [Azure DevOps Webhooks](./Usage.md#azure-devops-webhook), as well as bug fixes and improved support for several ADO commands.
+
+
+## Overview
+<div style="text-align:left;">
+
+CodiumAI PR-Agent is an open-source tool to help efficiently review and handle pull requests.
+
+- See the [Installation Guide](./INSTALL.md) for instructions on installing and running the tool on different git platforms.
+
+- See the [Usage Guide](./Usage.md) for instructions on running the PR-Agent commands via different interfaces, including _CLI_, _online usage_, or by _automatically triggering_ them when a new PR is opened.
+
+- See the [Tools Guide](./docs/TOOLS_GUIDE.md) for a detailed description of the different tools (tools are run via the commands).
+
+Supported commands per platform:
+
+|       |                                                                                                                                         | GitHub             | Gitlab             | Bitbucket          | Azure DevOps       |
+|-------|-----------------------------------------------------------------------------------------------------------------------------------------|:--------------------:|:--------------------:|:--------------------:|:--------------------:|
+| TOOLS | Review                                                                                                                                  | :white_check_mark: | :white_check_mark: | :white_check_mark: | :white_check_mark: |
+|       | ⮑ Incremental                                                                                                                           | :white_check_mark: |                    |                    |                    |
+|       | ⮑ [SOC2 Compliance](https://github.com/Codium-ai/pr-agent/blob/main/docs/REVIEW.md#soc2-ticket-compliance-) 💎                           | :white_check_mark: | :white_check_mark: | :white_check_mark: | :white_check_mark: |
+|       | Describe                                                                                                                                | :white_check_mark: | :white_check_mark: | :white_check_mark: | :white_check_mark: |
+|       | ⮑ [Inline File Summary](https://github.com/Codium-ai/pr-agent/blob/main/docs/DESCRIBE.md#inline-file-summary-) 💎                        | :white_check_mark: |                    |                    |                    |
+|       | Improve                                                                                                                                 | :white_check_mark: | :white_check_mark: | :white_check_mark: | :white_check_mark: |
+|       | ⮑ Extended                                                                                                                              | :white_check_mark: | :white_check_mark: | :white_check_mark: | :white_check_mark: |
+|       | Ask                                                                                                                                     | :white_check_mark: | :white_check_mark: | :white_check_mark: | :white_check_mark: |
+|       | ⮑ [Ask on code lines](./docs/ASK.md#ask-lines)                                                                                          | :white_check_mark: | :white_check_mark: |                    |                    |
+|       | [Custom Suggestions](https://github.com/Codium-ai/pr-agent/blob/main/docs/CUSTOM_SUGGESTIONS.md) 💎                                      | :white_check_mark: | :white_check_mark: | :white_check_mark: | :white_check_mark: |
+|       | [Test](https://github.com/Codium-ai/pr-agent/blob/main/docs/TEST.md) 💎                                                                  | :white_check_mark: | :white_check_mark: |                    | :white_check_mark: |
+|       | Reflect and Review                                                                                                                      | :white_check_mark: | :white_check_mark: | :white_check_mark: | :white_check_mark: |
+|       | Update CHANGELOG.md                                                                                                                     | :white_check_mark: | :white_check_mark: | :white_check_mark: | :white_check_mark: |
+|       | Find Similar Issue                                                                                                                      | :white_check_mark: |                    |                    |                    |
+|       | [Add PR Documentation](https://github.com/Codium-ai/pr-agent/blob/main/docs/ADD_DOCUMENTATION.md) 💎                                     | :white_check_mark: | :white_check_mark: |                   | :white_check_mark: |
+|       | [Custom Labels](https://github.com/Codium-ai/pr-agent/blob/main/docs/DESCRIBE.md#handle-custom-labels-from-the-repos-labels-page-gem) 💎 | :white_check_mark: | :white_check_mark: |                    | :white_check_mark: |
+|       | [Analyze](https://github.com/Codium-ai/pr-agent/blob/main/docs/Analyze.md) 💎                                                            | :white_check_mark: | :white_check_mark: |                    | :white_check_mark: |
+|       | [CI Feedback](https://github.com/Codium-ai/pr-agent/blob/main/docs/CI_FEEDBACK.md) 💎                                                    | :white_check_mark: |                    |                    |                    |
+|       |                                                                                                                                         |                    |                    |                    |                    |
+| USAGE | CLI                                                                                                                                     | :white_check_mark: | :white_check_mark: | :white_check_mark: | :white_check_mark: |
+|       | App / webhook                                                                                                                           | :white_check_mark: | :white_check_mark: | :white_check_mark: | :white_check_mark: |
+|       | Tagging bot                                                                                                                             | :white_check_mark: |                    |                    |                    |
+|       | Actions                                                                                                                                 | :white_check_mark: |                    | :white_check_mark: |                    |
+|       |                                                                                                                                         |                    |                    |                    |                    |
+| CORE  | PR compression                                                                                                                          | :white_check_mark: | :white_check_mark: | :white_check_mark: | :white_check_mark: |
+|       | Repo language prioritization                                                                                                            | :white_check_mark: | :white_check_mark: | :white_check_mark: | :white_check_mark: |
+|       | Adaptive and token-aware file patch fitting                                                                                             | :white_check_mark: | :white_check_mark: | :white_check_mark: | :white_check_mark: |
+|       | Multiple models support                                                                                                                 | :white_check_mark: | :white_check_mark: | :white_check_mark: | :white_check_mark: |
+|       | [Static code analysis](https://github.com/Codium-ai/pr-agent/blob/main/docs/Analyze.md) 💎                                               | :white_check_mark: | :white_check_mark: | :white_check_mark: | :white_check_mark: |
+|       | [Global and wiki configurations](./Usage.md#configuration) 💎                           | :white_check_mark: | :white_check_mark: | :white_check_mark: | :white_check_mark: |
+|       | [PR Actions](https://www.codium.ai/images/pr_agent/pr-actions.mp4) 💎                                                                    | :white_check_mark: |                    |                    |                    |
+- 💎 means this feature is available only in [PR-Agent Pro](https://www.codium.ai/pricing/)
+- Support for additional git providers is described in [here](./docs/Full_environments.md)
+___
+
+‣ **Auto Description ([`/describe`](./docs/DESCRIBE.md))**: Automatically generating PR description - title, type, summary, code walkthrough and labels.
+\
+‣ **Auto Review ([`/review`](./docs/REVIEW.md))**: Adjustable feedback about the PR, possible issues, security concerns, review effort and more.
+\
+‣ **Question Answering ([`/ask ...`](./docs/ASK.md))**: Answering free-text questions about the PR.
+\
+‣ **Code Suggestions ([`/improve`](./docs/IMPROVE.md))**: Code suggestions for improving the PR.
+\
+‣ **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.
+\
+‣ **Add Documentation 💎  ([`/add_docs`](./docs/ADD_DOCUMENTATION.md))**: Generates documentation to methods/functions/classes that changed in the PR.
+\
+‣ **Generate Custom Labels 💎 ([`/generate_labels`](./docs/GENERATE_CUSTOM_LABELS.md))**: Generates custom labels for the PR, based on specific guidelines defined by the user.
+\
+‣ **Analyze 💎 ([`/analyze`](./docs/Analyze.md))**: Identify code components that changed in the PR, and enables to interactively generate tests, docs, and code suggestions for each component.
+\
+‣ **Custom Suggestions 💎 ([`/custom_suggestions`](./docs/CUSTOM_SUGGESTIONS.md))**: Automatically generates custom suggestions for improving the PR code, based on specific guidelines defined by the user.
+\
+‣ **Generate Tests 💎 ([`/test component_name`](./docs/TEST.md))**: Automatically generates unit tests for a selected component, based on the PR code changes.
+\
+‣ **CI Feedback 💎 ([`/checks ci_job`](./docs/CI_FEEDBACK.md))**: Automatically generates feedback and analysis for a failed CI job.
+___
+
+## Example results
+</div>
+<h4><a href="https://github.com/Codium-ai/pr-agent/pull/530">/describe</a></h4>
+<div align="center">
+<p float="center">
+<img src="https://www.codium.ai/images/pr_agent/describe_new_short_main.png" width="512">
+</p>
+</div>
+<hr>
+
+<h4><a href="https://github.com/Codium-ai/pr-agent/pull/732#issuecomment-1975099151">/review</a></h4>
+<div align="center">
+<p float="center">
+<kbd>
+<img src="https://www.codium.ai/images/pr_agent/review_new_short_main.png" width="512">
+</kbd>
+</p>
+</div>
+<hr>
+
+<h4><a href="https://github.com/Codium-ai/pr-agent/pull/732#issuecomment-1975099159">/improve</a></h4>
+<div align="center">
+<p float="center">
+<kbd>
+<img src="https://www.codium.ai/images/pr_agent/improve_new_short_main.png" width="512">
+</kbd>
+</p>
+</div>
+<hr>
+
+<h4><a href="https://github.com/Codium-ai/pr-agent/pull/530">/generate_labels</a></h4>
+<div align="center">
+<p float="center">
+<kbd><img src="https://www.codium.ai/images/pr_agent/geneare_custom_labels_main_short.png" width="300"></kbd>
+</p>
+</div>
+
+[//]: # (<h4><a href="https://github.com/Codium-ai/pr-agent/pull/78#issuecomment-1639739496">/reflect_and_review:</a></h4>)
+
+[//]: # (<div align="center">)
+
+[//]: # (<p float="center">)
+
+[//]: # (<img src="https://www.codium.ai/images/reflect_and_review.gif" width="800">)
+
+[//]: # (</p>)
+
+[//]: # (</div>)
+
+[//]: # (<h4><a href="https://github.com/Codium-ai/pr-agent/pull/229#issuecomment-1695020538">/ask:</a></h4>)
+
+[//]: # (<div align="center">)
+
+[//]: # (<p float="center">)
+
+[//]: # (<img src="https://www.codium.ai/images/ask-2.gif" width="800">)
+
+[//]: # (</p>)
+
+[//]: # (</div>)
+
+[//]: # (<h4><a href="https://github.com/Codium-ai/pr-agent/pull/229#issuecomment-1695024952">/improve:</a></h4>)
+
+[//]: # (<div align="center">)
+
+[//]: # (<p float="center">)
+
+[//]: # (<img src="https://www.codium.ai/images/improve-2.gif" width="800">)
+
+[//]: # (</p>)
+
+[//]: # (</div>)
+<div align="left">
+
+
+</div>
+<hr>
+
+
+## Try it now
+
+Try the GPT-4 powered PR-Agent instantly on _your public GitHub repository_. Just mention `@CodiumAI-Agent` and add the desired command in any PR comment. The agent will generate a response based on your command.
+For example, add a comment to any pull request with the following text:
+```
+@CodiumAI-Agent /review
+```
+and the agent will respond with a review of your PR
+
+![Review generation process](https://www.codium.ai/images/demo-2.gif)
+
+
+To set up your own PR-Agent, see the [Installation](#installation) section below.
+Note that when you set your own PR-Agent or use CodiumAI hosted PR-Agent, there is no need to mention `@CodiumAI-Agent ...`. Instead, directly start with the command, e.g., `/ask ...`.
 
 ---
 
-## Quickstart
-
-To get started with pr-agent quickly, you first need to acquire two tokens:
+## Installation
+To use your own version of PR-Agent, 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.
 
-There are several ways to use pr-agent. Let's start with the simplest one:
+There are several ways to use PR-Agent:
 
----
+**Locally**
+- [Use Docker image (no installation required)](./INSTALL.md#use-docker-image-no-installation-required)
+- [Run from source](./INSTALL.md#run-from-source)
 
-#### Method 1: Use Docker image (no installation required)
+**GitHub specific methods**
+- [Run as a GitHub Action](./INSTALL.md#run-as-a-github-action)
+- [Run as a GitHub App](./INSTALL.md#run-as-a-github-app)
 
-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:
+**GitLab specific methods**
+- [Run a GitLab webhook server](./INSTALL.md#run-a-gitlab-webhook-server)
 
-1. To request a review for a PR, run the following command:
+**BitBucket specific methods**
+- [Run as a Bitbucket Pipeline](./INSTALL.md#run-as-a-bitbucket-pipeline)
 
-```
-docker run --rm -it -e OPENAI.KEY=<your key> -e GITHUB.USER_TOKEN=<your token> codiumai/pr-agent --pr_url <pr url>
-```
+## PR-Agent Pro 💎
+[PR-Agent Pro](https://www.codium.ai/pricing/) is a hosted version of PR-Agent, provided by CodiumAI. It is available for a monthly fee, and provides the following benefits:
+1. **Fully managed** - We take care of everything for you - hosting, models, regular updates, and more. Installation is as simple as signing up and adding the PR-Agent app to your GitHub\BitBucket repo.
+2. **Improved privacy** - No data will be stored or used to train models. PR-Agent Pro will employ zero data retention, and will use an OpenAI account with zero data retention.
+3. **Improved support** - PR-Agent Pro users will receive priority support, and will be able to request new features and capabilities.
+4. **Extra features** -In addition to the benefits listed above, PR-Agent Pro will emphasize more customization, and the usage of static code analysis, in addition to LLM logic, to improve results. It has the following additional tools and features:
+    - [**Analyze PR components**](https://github.com/Codium-ai/pr-agent/blob/main/docs/Analyze.md)
+    - [**Custom Code Suggestions**](https://github.com/Codium-ai/pr-agent/blob/main/docs/CUSTOM_SUGGESTIONS.md)
+    - [**Tests**](https://github.com/Codium-ai/pr-agent/blob/main/docs/TEST.md)
+    - [**PR documentation**](https://github.com/Codium-ai/pr-agent/blob/main/docs/ADD_DOCUMENTATION.md)
+    - [**SOC2 compliance check**](https://github.com/Codium-ai/pr-agent/blob/main/docs/REVIEW.md#soc2-ticket-compliance-)
+    - [**Custom labels**](https://github.com/Codium-ai/pr-agent/blob/main/docs/DESCRIBE.md#handle-custom-labels-from-the-repos-labels-page-gem)
+    - [**Global configuration**](https://github.com/Codium-ai/pr-agent/blob/main/Usage.md#global-configuration-file-)
 
-2. To ask a question about a PR, run the following command:
 
-```
-docker run --rm -it -e OPENAI.KEY=<your key> -e GITHUB.USER_TOKEN=<your token> codiumai/pr-agent --pr_url <pr url> --question "<your question>"
-```
-
-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
-
-1. Clone this repository:
-
-```
-git clone https://github.com/Codium-ai/pr-agent.git
-```
-
-2. Install the requirements in your favorite virtual environment:
-
-```
-pip install -r requirements.txt
-```
-
-3. Copy the secrets template file and fill in your OpenAI key and your GitHub user token:
-
-```
-cp pr_agent/settings/.secrets_template.toml pr_agent/settings/.secrets.toml
-# Edit .secrets.toml file
-```
-
-4. Run the appropriate Python scripts from the scripts folder:
-
-```
-python pr_agent/cli.py --pr_url <pr url>
-python pr_agent/cli.py --pr_url <pr url> --question "<your question>"
-```
-
----
-
-#### Method 3: Method 3: Run as a polling server; request reviews by tagging your Github user on a PR
-
-Follow steps 1-3 of method 2.
-Run the following command to start the server:
-
-```
-python pr_agent/servers/github_polling.py
-```
-
----
-
-#### Method 4: 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).
-
-   - Set the following permissions:
-     - Pull requests: Read & write
-     - Issue comment: Read & write
-     - Metadata: Read-only
-   - Set the following events:
-     - Issue comment
-     - Pull request
-
-2. Generate a random secret for your app, and save it for later. For example, you can use:
-
-```
-WEBHOOK_SECRET=$(python -c "import secrets; print(secrets.token_hex(10))")
-```
-
-3. Acquire the following pieces of information from your app's settings page:
-
-   - App private key (click "Generate a private key", and save the file)
-   - App ID
-
-4. Clone this repository:
-
-```
-git clone https://github.com/Codium-ai/pr-agent.git
-```
-
-5. Copy the secrets template file and fill in the following:
-   - Your OpenAI key.
-   - Set deployment_type to 'app'
-   - Copy your app's private key to the private_key field.
-   - Copy your app's ID to the app_id field.
-   - Copy your app's webhook secret to the webhook_secret field.
-
-```
-cp pr_agent/settings/.secrets_template.toml pr_agent/settings/.secrets.toml
-# Edit .secrets.toml file
-```
-
-6. Build a Docker image for the app and optionally push it to a Docker repository. We'll use Dockerhub as an example:
-
-```
-docker build . -t codiumai/pr-agent:github_app --target github_app -f docker/Dockerfile
-docker push codiumai/pr-agent:github_app  # Push to your Docker repository
-```
-
-7. Host the app using a server, serverless function, or container environment. Alternatively, for development and
-   debugging, you may use tools like smee.io to forward webhooks to your local machine.
-
-8. Go back to your app's settings, set the following:
-
-   - Webhook URL: The URL of your app's server, or the URL of the smee.io channel.
-   - Webhook secret: The secret you generated earlier.
-
-9. Install the app by navigating to the "Install App" tab, and selecting your desired repositories.
-
----
-
-## Usage and Tools
-
-CodiumAI pr-agent provides two types of interactions ("tools"): `"PR Reviewer"` and `"PR Q&A"`.
-
-- The "PR Reviewer" tool automatically analyzes PRs, and provides different types of feedbacks.
-- The "PR Q&A" tool answers free-text questions about the PR.
-
-### PR Reviewer
-
-Here is a quick overview of the different sub-tools of PR Reviewer:
-
-- PR Analysis
-  - Summarize main theme
-  - PR type classification
-  - Is the PR covered by relevant tests
-  - Is this a focused PR
-  - Are there security concerns
-- PR Feedback
-  - General PR suggestions
-  - Code suggestions
-
-This is how a typical output of the PR Reviewer looks like:
-
----
-
-#### PR Analysis
-
-- 🎯 **Main theme:** Adding language extension handler and token handler
-- 📌 **Type of PR:** Enhancement
-- 🧪 **Relevant tests added:** No
-- ✨ **Focused PR:** Yes, the PR is focused on adding two new handlers for language extension and token counting.
-- 🔒 **Security concerns:** No, the PR does not introduce possible security concerns or issues.
-
-#### PR Feedback
-
-- 💡 **General PR suggestions:** The PR is generally well-structured and the code is clean. However, it would be beneficial to add some tests to ensure the new handlers work as expected. Also, consider adding docstrings to the new functions and classes to improve code readability and maintainability.
-
-- 🤖 **Code suggestions:**
-
-  - **relevant file:** pr_agent/algo/language_handler.py
-
-    **suggestion content:** Consider using a set instead of a list for 'bad_extensions' as checking membership in a set is faster than in a list. [medium]
-
-  - **relevant file:** pr_agent/algo/language_handler.py
-
-    **suggestion content:** In the 'filter_bad_extensions' function, you are splitting the filename on '.' and taking the last element to get the extension. This might not work as expected if the filename contains multiple '.' characters. Consider using 'os.path.splitext' to get the file extension more reliably. [important]
-
----
-
-### PR Q&A
-
-This tool answers free-text questions about the PR. This is how a typical output of the PR Q&A looks like:
-
-**Question**: summarize for me the PR in 4 bullet points
-
-**Answer**:
-
-- The PR introduces a new feature to sort files by their main languages. It uses a mapping of programming languages to their file extensions to achieve this.
-- It also introduces a filter to exclude files with certain extensions, deemed as 'bad extensions', from the sorting process.
-- The PR modifies the `get_pr_diff` function in `pr_processing.py` to use the new sorting function. It also refactors the code to move the PR pruning logic into a separate function.
-- A new `TokenHandler` class is introduced in `token_handler.py` to handle token counting operations. This class is initialized with a PR, variables, system, and user, and provides methods to get system and user tokens and to count tokens in a patch.
-
----
-
-## Configuration
-
-The different tools and sub-tools used by CodiumAI pr-agent are easily configurable via the configuration file: `/settings/configuration.toml`.
-
-#### Enabling/disabling sub-tools:
-
-You can enable/disable the different PR Reviewer sub-sections with the following flags:
-
-```
-require_focused_review=true
-require_tests_review=true
-require_security_review=true
-```
 
 ## How it works
 
-![PR-Agent Tools](./pics/pr_agent_overview.png)
+The following diagram illustrates PR-Agent tools and their flow:
+
+![PR-Agent Tools](https://codium.ai/images/pr_agent/diagram-v0.9.png)
 
 Check out the [PR Compression strategy](./PR_COMPRESSION.md) page for more details on how we convert a code diff to a manageable LLM prompt
 
-## Roadmap
+## Why use PR-Agent?
 
-- [ ] Support open-source models, as a replacement for openai models. Note that a minimal requirement for each open-source model is to have 8k+ context, and good support for generating json as an output
-- [ ] Support other Git providers, such as Gitlab and Bitbucket.
-- [ ] Develop additional logics for handling large PRs, and compressing git patches
-- [ ] Dedicated tools and sub-tools for specific programming languages (Python, Javascript, Java, C++, etc)
-- [ ] Add additional context to the prompt. For example, repo (or relevant files) summarization, with tools such a [ctags](https://github.com/universal-ctags/ctags)
-- [ ] Adding more tools. Possible directions:
-  - [ ] Code Quality
-  - [ ] Coding Style
-  - [ ] Performance (are there any performance issues)
-  - [ ] Documentation (is the PR properly documented)
-  - [ ] Rank the PR importance
-  - [ ] ...
+A reasonable question that can be asked is: `"Why use PR-Agent? What makes it stand out from existing tools?"`
 
-## Similar Projects
+Here are some advantages of PR-Agent:
 
-- [CodiumAI - Meaningful tests for busy devs](https://github.com/Codium-ai/codiumai-vscode-release)
-- [Aider - GPT powered coding in your terminal](https://github.com/paul-gauthier/aider)
-- [GPT-Engineer](https://github.com/AntonOsika/gpt-engineer)
-- [CodeReview BOT](https://github.com/anc95/ChatGPT-CodeReview)
-- [AI-Maintainer](https://github.com/merwanehamadi/AI-Maintainer)
+- We emphasize **real-life practical usage**. Each tool (review, improve, ask, ...) has a single GPT-4 call, no more. We feel that this is critical for realistic team usage - obtaining an answer quickly (~30 seconds) and affordably.
+- Our [PR Compression strategy](./PR_COMPRESSION.md)  is a core ability that enables to effectively tackle both short and long PRs.
+- Our JSON prompting strategy enables to have **modular, customizable tools**. For example, the '/review' tool categories can be controlled via the [configuration](pr_agent/settings/configuration.toml) file. Adding additional categories is easy and accessible.
+- We support **multiple git providers** (GitHub, Gitlab, Bitbucket), **multiple ways** to use the tool (CLI, GitHub Action, GitHub App, Docker, ...), and **multiple models** (GPT-4, GPT-3.5, Anthropic, Cohere, Llama2).
+
+
+## Data privacy
+
+If you host PR-Agent 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
+
+When using PR-Agent Pro 💎, hosted by CodiumAI, we will not store any of your data, nor will we use it for training.
+You will also benefit from an OpenAI account with zero data retention.
+
+## Links
+
+[![Join our Discord community](https://raw.githubusercontent.com/Codium-ai/codiumai-vscode-release/main/media/docs/Joincommunity.png)](https://discord.gg/kG35uSHDBc)
+
+- Discord community: https://discord.gg/kG35uSHDBc
+- CodiumAI site: https://codium.ai
+- Blog: https://www.codium.ai/blog/
+- Troubleshooting: https://www.codium.ai/blog/technical-faq-and-troubleshooting/
+- Support: support@codium.ai

RELEASE_NOTES.md

@@ -0,0 +1,103 @@
+## [Version 0.11] - 2023-12-07
+- codiumai/pr-agent:0.11
+- codiumai/pr-agent:0.11-github_app
+- codiumai/pr-agent:0.11-bitbucket-app
+- codiumai/pr-agent:0.11-gitlab_webhook
+- codiumai/pr-agent:0.11-github_polling
+- codiumai/pr-agent:0.11-github_action
+
+### Added::Algo
+- New section in `/describe` tool - [PR changes walkthrough](https://github.com/Codium-ai/pr-agent/pull/509)
+- Improving PR Agent [prompts](https://github.com/Codium-ai/pr-agent/pull/501)
+- Persistent tools (`/review`, `/describe`) now send an [update message](https://github.com/Codium-ai/pr-agent/pull/499) after finishing
+- Add Amazon Bedrock [support](https://github.com/Codium-ai/pr-agent/pull/483)
+
+### Fixed
+- Update [dependencies](https://github.com/Codium-ai/pr-agent/pull/503) in requirements.txt for Python 3.12
+
+
+## [Version 0.10] - 2023-11-15
+- codiumai/pr-agent:0.10
+- codiumai/pr-agent:0.10-github_app
+- codiumai/pr-agent:0.10-bitbucket-app
+- codiumai/pr-agent:0.10-gitlab_webhook
+- codiumai/pr-agent:0.10-github_polling
+- codiumai/pr-agent:0.10-github_action
+
+### Added::Algo
+- Review tool now works with [persistent comments](https://github.com/Codium-ai/pr-agent/pull/451) by default
+- Bitbucket now publishes review suggestions with [code links](https://github.com/Codium-ai/pr-agent/pull/428)
+- Enabling to limit [max number of tokens](https://github.com/Codium-ai/pr-agent/pull/437/files)
+- Support ['gpt-4-1106-preview'](https://github.com/Codium-ai/pr-agent/pull/437/files) model
+- Support for Google's [Vertex AI](https://github.com/Codium-ai/pr-agent/pull/436)
+- Implementing [thresholds](https://github.com/Codium-ai/pr-agent/pull/423) for incremental PR reviews
+- Decoupled custom labels from [PR type](https://github.com/Codium-ai/pr-agent/pull/431)
+
+### Fixed
+- Fixed bug in [parsing quotes](https://github.com/Codium-ai/pr-agent/pull/446) in CLI
+- Preserve [user-added labels](https://github.com/Codium-ai/pr-agent/pull/433) in pull requests
+- Bug fixes in GitLab and BitBucket
+
+## [Version 0.9] - 2023-10-29
+- codiumai/pr-agent:0.9
+- codiumai/pr-agent:0.9-github_app
+- codiumai/pr-agent:0.9-bitbucket-app
+- codiumai/pr-agent:0.9-gitlab_webhook
+- codiumai/pr-agent:0.9-github_polling
+- codiumai/pr-agent:0.9-github_action
+
+### Added::Algo
+- New tool - [generate_labels](https://github.com/Codium-ai/pr-agent/blob/main/docs/GENERATE_CUSTOM_LABELS.md)
+- New ability to use [customize labels](https://github.com/Codium-ai/pr-agent/blob/main/docs/GENERATE_CUSTOM_LABELS.md#how-to-enable-custom-labels) on the `review` and `describe` tools.
+- New tool - [add_docs](https://github.com/Codium-ai/pr-agent/blob/main/docs/ADD_DOCUMENTATION.md)
+- GitHub Action: Can now use a `.pr_agent.toml` file to control configuration parameters (see [Usage Guide](./Usage.md#working-with-github-action)).
+- GitHub App: Added ability to trigger tools on [push events](https://github.com/Codium-ai/pr-agent/blob/main/Usage.md#github-app-automatic-tools-for-new-code-pr-push)
+- Support custom domain URLs for Azure devops integration (see [link](https://github.com/Codium-ai/pr-agent/pull/381)).
+- PR Description default mode is now in [bullet points](https://github.com/Codium-ai/pr-agent/blob/main/pr_agent/settings/configuration.toml#L35).
+
+### Added::Documentation
+Significant documentation updates (see [Installation Guide](https://github.com/Codium-ai/pr-agent/blob/main/INSTALL.md), [Usage Guide](https://github.com/Codium-ai/pr-agent/blob/main/Usage.md), and [Tools Guide](https://github.com/Codium-ai/pr-agent/blob/main/docs/TOOLS_GUIDE.md))
+
+### Fixed
+- Fixed support for BitBucket pipeline (see [link](https://github.com/Codium-ai/pr-agent/pull/386))
+- Fixed a bug in `review -i` tool
+- Added blacklist for specific file extensions in `add_docs` tool (see [link](https://github.com/Codium-ai/pr-agent/pull/385/))
+
+## [Version 0.8] - 2023-09-27
+- codiumai/pr-agent:0.8
+- codiumai/pr-agent:0.8-github_app
+- codiumai/pr-agent:0.8-bitbucket-app
+- codiumai/pr-agent:0.8-gitlab_webhook
+- codiumai/pr-agent:0.8-github_polling
+- codiumai/pr-agent:0.8-github_action
+
+### Added::Algo
+- GitHub Action: Can control which tools will run automatically when a new PR is created. (see usage guide: https://github.com/Codium-ai/pr-agent/blob/main/Usage.md#working-with-github-action)
+- Code suggestion tool: Will try to avoid an 'add comments' suggestion  (see https://github.com/Codium-ai/pr-agent/pull/327)
+
+### Fixed
+- Gitlab: Fixed a bug of improper usage of pr_id
+
+
+## [Version 0.7] - 2023-09-20
+
+### Docker Tags
+- codiumai/pr-agent:0.7
+- codiumai/pr-agent:0.7-github_app
+- codiumai/pr-agent:0.7-bitbucket-app
+- codiumai/pr-agent:0.7-gitlab_webhook
+- codiumai/pr-agent:0.7-github_polling
+- codiumai/pr-agent:0.7-github_action
+ 
+### Added::Algo
+- New tool /similar_issue - Currently on GitHub app and CLI: indexes the issues in the repo, find the most similar issues to the target issue.
+- Describe markers: Empower the /describe tool with a templating capability (see more details in https://github.com/Codium-ai/pr-agent/pull/273).
+- New feature in the /review tool - added an estimated effort estimation to the review (https://github.com/Codium-ai/pr-agent/pull/306).
+
+### Added::Infrastructure
+- Implementation of a GitLab webhook.
+- Implementation of a BitBucket app.
+
+### Fixed
+- Protection against no code suggestions generated.
+- Resilience to repositories where the languages cannot be automatically detected.

Usage.md

@@ -0,0 +1,529 @@
+## Usage Guide
+
+### Table of Contents
+- [Introduction](#introduction)
+- [Configuration Options](#configuration-options)
+- [Managing Mail Notifications](#managing-mail-notifications)
+- [Usage Types](#usage-types)
+  - [Local Repo (CLI)](#working-from-a-local-repo-cli)
+  - [Online Usage](#online-usage)
+  - [GitHub App](#working-with-github-app)
+  - [GitHub Action](#working-with-github-action)
+  - [GitLab Webhook](#working-with-gitlab-webhook)
+  - [BitBucket App](#working-with-bitbucket-self-hosted-app)
+  - [Azure DevOps Provider](#azure-devops-provider)
+- [Additional Configurations Walkthrough](#appendix---additional-configurations-walkthrough)
+  - [Ignoring files from analysis](#ignoring-files-from-analysis)
+  - [Extra instructions](#extra-instructions)
+  - [Working with large PRs](#working-with-large-prs)
+  - [Changing a model](#changing-a-model)
+  - [Patch Extra Lines](#patch-extra-lines)
+  - [Editing the prompts](#editing-the-prompts)
+
+## Introduction
+
+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
+
+
+Specifically, CLI commands can be issued by invoking a pre-built [docker image](/INSTALL.md#running-from-source), or by invoking a [locally cloned repo](INSTALL.md#method-2-run-from-source).
+For online usage, you will need to setup either a [GitHub App](INSTALL.md#method-5-run-as-a-github-app), or a [GitHub Action](INSTALL.md#method-3-run-as-a-github-action).
+GitHub App and GitHub Action also enable to run PR-Agent specific tool automatically when a new PR is opened.
+
+
+### git provider
+The [git_provider](pr_agent/settings/configuration.toml#L4) field in the configuration file determines the GIT provider that will be used by PR-Agent. Currently, the following providers are supported:
+`
+"github", "gitlab", "bitbucket", "azure", "codecommit", "local", "gerrit"
+`
+
+## Configuration Options
+
+The different tools and sub-tools used by CodiumAI PR-Agent are adjustable via the **[configuration file](pr_agent/settings/configuration.toml)**.
+
+In addition to general configuration options, each tool has its own configurations. For example, the `review` tool will use parameters from the [pr_reviewer](/pr_agent/settings/configuration.toml#L16) section in the configuration file.
+See the [Tools Guide](./docs/TOOLS_GUIDE.md) for a detailed description of the different tools and their configurations.
+
+There are three ways to set persistent configurations:
+1. Wiki configuration page 💎
+2. Local configuration file
+3. Global configuration file 💎
+
+In terms of precedence, wiki configurations will override local configurations, and local configurations will override global configurations.
+
+### Wiki configuration file 💎
+
+Specifically for GitHub, with PR-Agent-Pro you can set configurations by creating a page called `.pr_agent.toml` in the [wiki](https://github.com/Codium-ai/pr-agent/wiki/pr_agent.toml) of the repo. 
+The advantage of this method is that it allows to set configurations without needing to commit new content to the repo - just edit the wiki page and **save**.
+
+<kbd><img src="https://codium.ai/images/pr_agent/wiki_configuration.png" width="512"></kbd>
+
+Click [here](https://codium.ai/images/pr_agent/wiki_configuration_pr_agent.mp4) to see a short instructional video. We recommend surrounding the configuration content with triple-quotes, to allow better presentation when displayed in the wiki as markdown.
+An example content:
+
+\`\`\`<br>
+[pr_description] # /describe #<br>
+keep_original_user_title=false<br>
+\`\`\`
+
+PR-Agent will know to remove the triple-quotes when reading the configuration content.
+
+### Local configuration file
+
+By uploading a local `.pr_agent.toml` file to the root of the repo's main branch, you can edit and customize any configuration parameter. Note that you need to upload `.pr_agent.toml` prior to creating a PR, in order for the configuration to take effect.
+
+For example, if you set in `.pr_agent.toml`:
+
+```
+[pr_reviewer]
+extra_instructions="""\
+- instruction a
+- instruction b
+...
+"""
+```
+
+Then you can give a list of extra instructions to the `review` tool.
+
+
+### Global configuration file 💎
+
+If you create a repo called `pr-agent-settings` in your **organization**, it's configuration file `.pr_agent.toml` will be used as a global configuration file for any other repo that belongs to the same organization.
+Parameters from a local `.pr_agent.toml` file, in a specific repo, will override the global configuration parameters.
+
+For example, in the GitHub organization `Codium-ai`:
+- The repo [`https://github.com/Codium-ai/pr-agent-settings`](https://github.com/Codium-ai/pr-agent-settings/blob/main/.pr_agent.toml) contains a `.pr_agent.toml` file that serves as a global configuration file for all the repos in the GitHub organization `Codium-ai`.
+- The repo [`https://github.com/Codium-ai/pr-agent`](https://github.com/Codium-ai/pr-agent/blob/main/.pr_agent.toml) inherits the global configuration file from `pr-agent-settings`.
+
+
+## Managing mail notifications
+Unfortunately, it is not possible in GitHub to disable mail notifications from a specific user.
+If you are subscribed to notifications for a repo with PR-Agent, we recommend turning off notifications for PR comments, to avoid lengthy emails:
+
+<kbd><img src="https://codium.ai/images/pr_agent/notifications.png" width="512"></kbd>
+
+As an alternative, you can filter in your mail provider the notifications specifically from the PR-Agent bot:
+https://www.quora.com/How-can-you-filter-emails-for-specific-people-in-Gmail#:~:text=On%20the%20Filters%20and%20Blocked,the%20body%20of%20the%20email
+
+<kbd><img src="https://codium.ai/images/pr_agent/filter_mail_notifications.png" width="512"></kbd>
+
+## Usage Types
+
+### Working from a local repo (CLI)
+When running from your local repo (CLI), your local configuration file will be used.
+Examples of invoking the different tools via the CLI:
+
+- **Review**:       `python -m pr_agent.cli --pr_url=<pr_url>  review`
+- **Describe**:     `python -m pr_agent.cli --pr_url=<pr_url>  describe`
+- **Improve**:      `python -m pr_agent.cli --pr_url=<pr_url>  improve`
+- **Ask**:          `python -m pr_agent.cli --pr_url=<pr_url>  ask "Write me a poem about this PR"`
+- **Reflect**:      `python -m pr_agent.cli --pr_url=<pr_url>  reflect`
+- **Update Changelog**:      `python -m pr_agent.cli --pr_url=<pr_url>  update_changelog`
+
+`<pr_url>` is the url of the relevant PR (for example: https://github.com/Codium-ai/pr-agent/pull/50).
+
+**Notes:**
+
+(1) in addition to editing your local configuration file, you can also change any configuration value by adding it to the command line:
+```
+python -m pr_agent.cli --pr_url=<pr_url>  /review --pr_reviewer.extra_instructions="focus on the file: ..."
+```
+
+(2) You can print results locally, without publishing them, by setting in `configuration.toml`:
+```
+[config]
+publish_output=false
+verbosity_level=2
+```
+This is useful for debugging or experimenting with different tools.
+
+
+### Online usage
+
+Online usage means invoking PR-Agent tools by [comments](https://github.com/Codium-ai/pr-agent/pull/229#issuecomment-1695021901) on a PR.
+Commands for invoking the different tools via comments:
+
+- **Review**:       `/review`
+- **Describe**:     `/describe`
+- **Improve**:      `/improve`
+- **Ask**:          `/ask "..."`
+- **Reflect**:      `/reflect`
+- **Update Changelog**:      `/update_changelog`
+
+
+To edit a specific configuration value, just add `--config_path=<value>` to any command.
+For example, if you want to edit the `review` tool configurations, you can run:
+```
+/review --pr_reviewer.extra_instructions="..." --pr_reviewer.require_score_review=false
+```
+Any configuration value in [configuration file](pr_agent/settings/configuration.toml) file can be similarly edited. Comment `/config` to see the list of available configurations.
+
+
+### Working with GitHub App
+
+#### GitHub app automatic tools when a new PR is opened
+
+The [github_app](pr_agent/settings/configuration.toml#L108) section defines GitHub app specific configurations.  
+
+The configuration parameter `pr_commands` defines the list of tools that will be **run automatically** when a new PR is opened.
+```
+[github_app]
+pr_commands = [
+    "/describe --pr_description.add_original_user_description=true --pr_description.keep_original_user_title=true",
+    "/review --pr_reviewer.num_code_suggestions=0",
+    "/improve",
+]
+```
+This means that when a new PR is opened/reopened or marked as ready for review, PR-Agent will run the `describe`, `review` and `improve` tools.  
+For the `describe` tool, for example, the `add_original_user_description` and `keep_original_user_title` parameters will be set to true.
+
+You can override the default tool parameters by using one the three options for a [configuration file](#configuration-options): **wiki**, **local**, or **global**. 
+For example, if your local `.pr_agent.toml` file contains:
+```
+[pr_description]
+add_original_user_description = false
+keep_original_user_title = false
+```
+When a new PR is opened, PR-Agent will run the `describe` tool with the above parameters.
+
+To cancel the automatic run of all the tools, set:
+```
+[github_app]
+handle_pr_actions = []
+```
+
+You can also disable automatic runs for PRs with specific titles, by setting the `ignore_pr_titles` parameter with the relevant regex. For example:
+```
+[github_app]
+ignore_pr_title = ["^[Auto]", ".*ignore.*"]
+```
+will ignore PRs with titles that start with "Auto" or contain the word "ignore".
+
+#### GitHub app automatic tools for push actions (commits to an open PR)
+
+In addition to running automatic tools when a PR is opened, the GitHub app can also respond to new code that is pushed to an open PR.
+
+The configuration toggle `handle_push_trigger` can be used to enable this feature.  
+The configuration parameter `push_commands` defines the list of tools that will be **run automatically** when new code is pushed to the PR.
+```
+[github_app]
+handle_push_trigger = true
+push_commands = [
+    "/describe --pr_description.add_original_user_description=true --pr_description.keep_original_user_title=true",
+    "/review  --pr_reviewer.num_code_suggestions=0",
+]
+```
+This means that when new code is pushed to the PR, the PR-Agent will run the `describe` and `review` tools, with the specified parameters.
+
+### Working with GitHub Action
+`GitHub Action` is a different way to trigger PR-Agent tools, and uses a different configuration mechanism than `GitHub App`.
+You can configure settings for `GitHub Action` by adding environment variables under the env section in `.github/workflows/pr_agent.yml` file. 
+Specifically, start by setting the following environment variables:
+```yaml
+      env:
+        OPENAI_KEY: ${{ secrets.OPENAI_KEY }} # Make sure to add your OpenAI key to your repo secrets
+        GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }} # Make sure to add your GitHub token to your repo secrets
+        github_action_config.auto_review: "true" # enable\disable auto review
+        github_action_config.auto_describe: "true" # enable\disable auto describe
+        github_action_config.auto_improve: "true" # enable\disable auto improve
+```
+`github_action_config.auto_review`, `github_action_config.auto_describe` and `github_action_config.auto_improve` are used to enable/disable automatic tools that run when a new PR is opened.
+If not set, the default configuration is for all three tools to run automatically when a new PR is opened.
+
+Note that you can give additional config parameters by adding environment variables to `.github/workflows/pr_agent.yml`, or by using a `.pr_agent.toml` file in the root of your repo, similar to the GitHub App usage.
+
+For example, you can set an environment variable: `pr_description.add_original_user_description=false`, or add a `.pr_agent.toml` file with the following content:
+```
+[pr_description]
+add_original_user_description = false
+```
+
+### Working with GitLab Webhook
+After setting up a GitLab webhook, to control which commands will run automatically when a new PR is opened, you can set the `pr_commands` parameter in the configuration file, similar to the GitHub App:
+```
+[gitlab]
+pr_commands = [
+    "/describe --pr_description.add_original_user_description=true --pr_description.keep_original_user_title=true",
+    "/review --pr_reviewer.num_code_suggestions=0",
+    "/improve",
+]
+```
+
+### Working with BitBucket Self-Hosted App
+Similar to GitHub app, when running PR-Agent from BitBucket App, the default [configuration file](pr_agent/settings/configuration.toml) from a pre-built docker will be initially loaded.
+
+By uploading a local `.pr_agent.toml` file to the root of the repo's main branch, you can edit and customize any configuration parameter. Note that you need to upload `.pr_agent.toml` prior to creating a PR, in order for the configuration to take effect.
+
+For example, if your local `.pr_agent.toml` file contains:
+```
+[pr_reviewer]
+inline_code_comments = true
+```
+
+Each time you invoke a `/review` tool, it will use inline code comments.
+
+#### BitBucket Self-Hosted App automatic tools
+You can configure in your local `.pr_agent.toml` file which tools will **run automatically** when a new PR is opened.
+
+Specifically, set the following values:
+```yaml
+[bitbucket_app]
+auto_review = true    # set as config var in .pr_agent.toml
+auto_describe = true  # set as config var in .pr_agent.toml
+auto_improve = true   # set as config var in .pr_agent.toml
+```
+
+`bitbucket_app.auto_review`, `bitbucket_app.auto_describe` and `bitbucket_app.auto_improve` are used to enable/disable automatic tools.
+If not set, the default option is that only the `review` tool will run automatically when a new PR is opened.
+
+Note that due to limitations of the bitbucket platform, the `auto_describe` tool will be able to publish a PR description only as a comment. 
+In addition, some subsections like `PR changes walkthrough` will not appear, since they require the usage of collapsible sections, which are not supported by bitbucket.
+
+### Azure DevOps provider
+
+To use Azure DevOps provider use the following settings in configuration.toml:
+```
+[config]
+git_provider="azure"
+use_repo_settings_file=false
+```
+
+Azure DevOps provider supports [PAT token](https://learn.microsoft.com/en-us/azure/devops/organizations/accounts/use-personal-access-tokens-to-authenticate?view=azure-devops&tabs=Windows) or [DefaultAzureCredential](https://learn.microsoft.com/en-us/azure/developer/python/sdk/authentication-overview#authentication-in-server-environments) authentication.
+PAT is faster to create, but has build in experation date, and will use the user identity for API calls. 
+Using DefaultAzureCredential you can use managed identity or Service principle, which are more secure and will create seperate ADO user identity (via AAD) to the agent.
+
+If PAT was choosen, you can assign the value in .secrets.toml. 
+If DefaultAzureCredential was choosen, you can assigned the additional env vars like AZURE_CLIENT_SECRET directly, 
+or use managed identity/az cli (for local develpment) without any additional configuration.
+in any case, 'org' value must be assigned in .secrets.toml:
+```
+[azure_devops]
+org = "https://dev.azure.com/YOUR_ORGANIZATION/"
+# pat = "YOUR_PAT_TOKEN" needed only if using PAT for authentication
+```
+
+##### Azure DevOps Webhook
+To trigger from an Azure webhook, you need to manually [add a webhook](https://learn.microsoft.com/en-us/azure/devops/service-hooks/services/webhooks?view=azure-devops). 
+Use the "Pull request created" type to trigger a review, or "Pull request commented on" to trigger any supported comment with /<command> <args> comment on the relevant PR. Note that for the "Pull request commented on" trigger, only API v2.0 is supported.
+
+To control which commands will run automatically when a new PR is opened, you can set the `pr_commands` parameter in the configuration file, similar to the GitHub App:
+```
+[azure_devops_server]
+pr_commands = [
+    "/describe --pr_description.add_original_user_description=true --pr_description.keep_original_user_title=true",
+    "/review --pr_reviewer.num_code_suggestions=0",
+    "/improve",
+]
+```
+
+For webhook security, create a sporadic username/password pair and configure the webhook username and password on both the server and Azure DevOps webhook. These will be sent as basic Auth data by the webhook with each request:
+```
+[azure_devops_server]
+webhook_username = "<basic auth user>"
+webhook_password = "<basic auth password>"
+```
+> :warning: **Ensure that the webhook endpoint is only accessible over HTTPS** to mitigate the risk of credential interception when using basic authentication.
+
+
+## Appendix - additional configurations walkthrough
+
+
+#### Ignoring files from analysis
+In some cases, you may want to exclude specific files or directories from the analysis performed by CodiumAI PR-Agent. This can be useful, for example, when you have files that are generated automatically or files that shouldn't be reviewed, like vendored code.
+
+To ignore files or directories, edit the **[ignore.toml](/pr_agent/settings/ignore.toml)** configuration file. This setting also exposes the following environment variables:
+
+ - `IGNORE.GLOB`
+ - `IGNORE.REGEX`
+
+For example, to ignore python files in a PR with online usage, comment on a PR:
+`/review --ignore.glob=['*.py']`
+
+To ignore python files in all PRs, set in a configuration file:
+```
+[ignore]
+glob = ['*.py']
+```
+
+#### Extra instructions
+All PR-Agent tools have a parameter called `extra_instructions`, that enables to add free-text extra instructions. Example usage:
+```
+/update_changelog --pr_update_changelog.extra_instructions="Make sure to update also the version ..."
+```
+
+#### Working with large PRs
+
+The default mode of CodiumAI is to have a single call per tool, using GPT-4, which has a token limit of 8000 tokens.
+This mode provide a very good speed-quality-cost tradeoff, and can handle most PRs successfully.
+When the PR is above the token limit, it employs a [PR Compression strategy](./PR_COMPRESSION.md).
+
+However, for very large PRs, or in case you want to emphasize quality over speed and cost, there are 2 possible solutions:
+1) [Use a model](#changing-a-model) with larger context, like GPT-32K, or claude-100K. This solution will be applicable for all the tools.
+2) For the `/improve` tool, there is an ['extended' mode](./docs/IMPROVE.md) (`/improve --extended`),
+which divides the PR to chunks, and process each chunk separately. With this mode, regardless of the model, no compression will be done (but for large PRs, multiple model calls may occur)
+
+
+#### Changing a model
+
+See [here](pr_agent/algo/__init__.py) for the list of available models.
+To use a different model than the default (GPT-4), you need to edit [configuration file](pr_agent/settings/configuration.toml#L2).
+For models and environments not from OPENAI, you might need to provide additional keys and other parameters. See below for instructions.
+
+##### Azure
+To use Azure, set in your `.secrets.toml` (working from CLI), or in the GitHub `Settings > Secrets and variables` (working from GitHub App or GitHub Action):
+```
+[openai]
+key = "" # your azure api key
+api_type = "azure"
+api_version = '2023-05-15'  # Check Azure documentation for the current API version
+api_base = ""  # The base URL for your Azure OpenAI resource. e.g. "https://<your resource name>.openai.azure.com"
+deployment_id = ""  # The deployment name you chose when you deployed the engine
+```
+
+and set in your configuration file:
+```
+[config]
+model="" # the OpenAI model you've deployed on Azure (e.g. gpt-3.5-turbo)
+```
+
+##### Huggingface
+
+**Local**
+You can run Huggingface models locally through either [VLLM](https://docs.litellm.ai/docs/providers/vllm) or [Ollama](https://docs.litellm.ai/docs/providers/ollama)
+
+E.g. to use a new Huggingface model locally via Ollama, set:
+```
+[__init__.py]
+MAX_TOKENS = {
+    "model-name-on-ollama": <max_tokens>
+}
+e.g.
+MAX_TOKENS={
+    ...,
+    "ollama/llama2": 4096
+}
+
+
+[config] # in configuration.toml
+model = "ollama/llama2"
+
+[ollama] # in .secrets.toml
+api_base = ... # the base url for your huggingface inference endpoint
+# e.g. if running Ollama locally, you may use:
+api_base = "http://localhost:11434/"
+```
+
+**Inference Endpoints**
+
+To use a new model with Huggingface Inference Endpoints, for example, set:
+```
+[__init__.py]
+MAX_TOKENS = {
+    "model-name-on-huggingface": <max_tokens>
+}
+e.g.
+MAX_TOKENS={
+    ...,
+    "meta-llama/Llama-2-7b-chat-hf": 4096
+}
+[config] # in configuration.toml
+model = "huggingface/meta-llama/Llama-2-7b-chat-hf"
+
+[huggingface] # in .secrets.toml
+key = ... # your huggingface api key
+api_base = ... # the base url for your huggingface inference endpoint
+```
+(you can obtain a Llama2 key from [here](https://replicate.com/replicate/llama-2-70b-chat/api))
+
+##### Replicate
+
+To use Llama2 model with Replicate, for example, set:
+```
+[config] # in configuration.toml
+model = "replicate/llama-2-70b-chat:2c1608e18606fad2812020dc541930f2d0495ce32eee50074220b87300bc16e1"
+[replicate] # in .secrets.toml
+key = ...
+```
+(you can obtain a Llama2 key from [here](https://replicate.com/replicate/llama-2-70b-chat/api))
+
+
+Also review the [AiHandler](pr_agent/algo/ai_handler.py) file for instruction how to set keys for other models.
+
+##### Vertex AI
+
+To use Google's Vertex AI platform and its associated models (chat-bison/codechat-bison) set:
+
+``` 
+[config] # in configuration.toml
+model = "vertex_ai/codechat-bison"
+fallback_models="vertex_ai/codechat-bison"
+
+[vertexai] # in .secrets.toml
+vertex_project = "my-google-cloud-project"
+vertex_location = ""
+```
+
+Your [application default credentials](https://cloud.google.com/docs/authentication/application-default-credentials) will be used for authentication so there is no need to set explicit credentials in most environments.
+
+If you do want to set explicit credentials then you can use the `GOOGLE_APPLICATION_CREDENTIALS` environment variable set to a path to a json credentials file.
+
+##### Amazon Bedrock
+
+To use Amazon Bedrock and its foundational models, add the below configuration:
+
+``` 
+[config] # in configuration.toml
+model = "anthropic.claude-v2"
+fallback_models="anthropic.claude-instant-v1"
+
+[aws] # in .secrets.toml
+bedrock_region = "us-east-1"
+```
+
+Note that you have to add access to foundational models before using them. Please refer to [this document](https://docs.aws.amazon.com/bedrock/latest/userguide/setting-up.html) for more details.
+
+AWS session is automatically authenticated from your environment, but you can also explicitly set `AWS_ACCESS_KEY_ID` and `AWS_SECRET_ACCESS_KEY` environment variables.
+
+
+#### Patch Extra Lines
+By default, around any change in your PR, git patch provides 3 lines of context above and below the change.
+```
+@@ -12,5 +12,5 @@ def func1():
+ code line that already existed in the file...
+ code line that already existed in the file...
+ code line that already existed in the file....
+-code line that was removed in the PR
++new code line added in the PR
+ code line that already existed in the file...
+ code line that already existed in the file...
+ code line that already existed in the file...
+```
+
+For the `review`, `describe`, `ask` and `add_docs` tools, if the token budget allows, PR-Agent tries to increase the number of lines of context, via the parameter:
+```
+[config]
+patch_extra_lines=3
+```
+
+Increasing this number provides more context to the model, but will also increase the token budget.
+If the PR is too large (see [PR Compression strategy](./PR_COMPRESSION.md)), PR-Agent automatically sets this number to 0, using the original git patch.
+
+
+#### Editing the prompts
+The prompts for the various PR-Agent tools are defined in the `pr_agent/settings` folder.
+In practice, the prompts are loaded and stored as a standard setting object.
+Hence, editing them is similar to editing any other configuration value - just place the relevant key in `.pr_agent.toml`file, and override the default value.
+
+For example, if you want to edit the prompts of the [describe](./pr_agent/settings/pr_description_prompts.toml) tool, you can add the following to your `.pr_agent.toml` file:
+```
+[pr_description_prompt]
+system="""
+...
+"""
+user="""
+...
+"""
+```
+Note that the new prompt will need to generate an output compatible with the relevant [post-process function](./pr_agent/tools/pr_description.py#L137).

action.yaml

@@ -1,5 +1,8 @@
-name: 'PR Agent'
+name: 'Codium PR Agent'
 description: 'Summarize, review and suggest improvements for pull requests'
+branding:
+  icon: 'award'
+  color: 'green'
 runs:
   using: 'docker'
-  image: 'Dockerfile.github_action'
+  image: 'Dockerfile.github_action_dockerhub'

docker/Dockerfile

@@ -1,20 +1,41 @@
 FROM python:3.10 as base
 
 WORKDIR /app
+ADD pyproject.toml .
 ADD requirements.txt .
-RUN pip install -r requirements.txt && rm requirements.txt
+RUN pip install . && rm pyproject.toml requirements.txt
 ENV PYTHONPATH=/app
-ADD pr_agent pr_agent
 
 FROM base as github_app
+ADD pr_agent pr_agent
 CMD ["python", "pr_agent/servers/github_app.py"]
 
+FROM base as bitbucket_app
+ADD pr_agent pr_agent
+CMD ["python", "pr_agent/servers/bitbucket_app.py"]
+
+FROM base as bitbucket_server_webhook
+ADD pr_agent pr_agent
+CMD ["python", "pr_agent/servers/bitbucket_server_webhook.py"]
+
 FROM base as github_polling
+ADD pr_agent pr_agent
 CMD ["python", "pr_agent/servers/github_polling.py"]
 
+FROM base as gitlab_webhook
+ADD pr_agent pr_agent
+CMD ["python", "pr_agent/servers/gitlab_webhook.py"]
+
+FROM base as azure_devops_webhook
+ADD pr_agent pr_agent
+CMD ["python", "pr_agent/servers/azuredevops_server_webhook.py"]
+
 FROM base as test
 ADD requirements-dev.txt .
 RUN pip install -r requirements-dev.txt && rm requirements-dev.txt
+ADD pr_agent pr_agent
+ADD tests tests
 
 FROM base as cli
+ADD pr_agent pr_agent
 ENTRYPOINT ["python", "pr_agent/cli.py"]

docker/Dockerfile.lambda

@@ -0,0 +1,12 @@
+FROM public.ecr.aws/lambda/python:3.10
+
+RUN yum update -y && \
+    yum install -y gcc python3-devel && \
+    yum clean all
+
+ADD pyproject.toml .
+RUN pip install . && rm pyproject.toml
+RUN pip install mangum==0.17.0
+COPY pr_agent/ ${LAMBDA_TASK_ROOT}/pr_agent/
+
+CMD ["pr_agent.servers.serverless.serverless"]

docs/ADD_DOCUMENTATION.md

@@ -0,0 +1,24 @@
+# Add Documentation Tool 💎
+The `add_docs` tool scans the PR code changes, and automatically suggests documentation for any code components that changed in the PR (functions, classes, etc.).
+
+It can be invoked manually by commenting on any PR:
+```
+/add_docs
+```
+For example:
+
+<kbd><img src=https://codium.ai/images/pr_agent/docs_command.png width="768"></kbd>
+___
+<kbd><img src=https://codium.ai/images/pr_agent/docs_components.png width="768"></kbd>
+___
+<kbd><img src=https://codium.ai/images/pr_agent/docs_single_component.png width="768"></kbd>
+
+### Configuration options
+ - `docs_style`: The exact style of the documentation (for python docstring). you can choose between: `google`, `numpy`, `sphinx`, `restructuredtext`, `plain`. Default is `sphinx`.
+ - `extra_instructions`: Optional extra instructions to the tool. For example: "focus on the changes in the file X. Ignore change in ...".
+
+Notes 
+- Language that are currently fully supported: Python, Java, C++, JavaScript, TypeScript.
+- For languages that are not fully supported, the tool will suggest documentation only for new components in the PR.
+- A previous version of the tool, that offered support only for new components, was deprecated.
+

docs/ASK.md

@@ -0,0 +1,24 @@
+# ASK Tool
+
+The `ask` tool answers questions about the PR, based on the PR code changes. Make sure to be specific and clear in your questions.
+It can be invoked manually by commenting on any PR:
+```
+/ask "..."
+```
+For example:
+___
+<kbd><img src="https://codium.ai/images/pr_agent/ask_comment.png" width="768"></kbd>
+___
+<kbd><img src="https://codium.ai/images/pr_agent/ask.png" width="768"></kbd>
+___
+
+## Ask lines
+You can run `/ask` on specific lines of code in the PR from the PR's diff view. The tool will answer questions based on the code changes in the selected lines.
+- Click on the '+' sign next to the line number to select the line.
+- To select multiple lines, click on the '+' sign of the first line and then hold and drag to select the rest of the lines. 
+- write `/ask "..."` in the comment box and press `Add single comment` button.
+
+<kbd><img src="https://codium.ai/images/pr_agent/Ask_line.png" width="768"></kbd>
+
+
+Note that the tool does not have "memory" of previous questions, and answers each question independently.

docs/Analyze.md

@@ -0,0 +1,21 @@
+# Analyze Tool 💎
+The `analyze` tool combines static code analysis with LLM capabilities to provide a comprehensive analysis of the PR code changes.
+
+The tool scans the PR code changes, find the code components (methods, functions, classes) that changed, and summarizes the changes in each component.
+
+It can be invoked manually by commenting on any PR:
+```
+/analyze
+```
+
+An example [result](https://github.com/Codium-ai/pr-agent/pull/546#issuecomment-1868524805):
+
+<kbd><img src=https://codium.ai/images/pr_agent/analyze_1.png width="768"></kbd>
+___
+<kbd><img src=https://codium.ai/images/pr_agent/analyze_2.png width="768"></kbd>
+___
+<kbd><img src=https://codium.ai/images/pr_agent/analyze_3.png width="768"></kbd>
+
+
+Notes 
+- Language that are currently supported: Python, Java, C++, JavaScript, TypeScript.

docs/CI_FEEDBACK.md

@@ -0,0 +1,31 @@
+# CI Feedback Tool
+
+The CI feedback tool (`/checks)` automatically triggers when a PR has a failed check.
+The tool analyzes the failed checks and provides several feedbacks:
+- Failed stage
+- Failed test name
+- Failure summary
+- Relevant error logs
+
+<kbd>
+<img src="https://www.codium.ai/images/pr_agent/failed_check1.png" width="768">
+</kbd>
+
+&rarr;
+<kbd>
+<img src="https://www.codium.ai/images/pr_agent/failed_check2.png" width="768">
+</kbd>
+
+___
+
+In addition to being automatically triggered, the tool can also be invoked manually by commenting on a PR:
+```
+/checks "https://github.com/{repo_name}/actions/runs/{run_number}/job/{job_number}"
+```
+where `{repo_name}` is the name of the repository, `{run_number}` is the run number of the failed check, and `{job_number}` is the job number of the failed check.
+
+### Configuration options
+- `enable_auto_checks_feedback` - if set to true, the tool will automatically provide feedback when a check is failed. Default is true.
+- `excluded_checks_list` - a list of checks to exclude from the feedback, for example: ["check1", "check2"]. Default is an empty list.
+- `persistent_comment` - if set to true, the tool will overwrite a previous checks comment with the new feedback. Default is true.
+- `enable_help_text=true` - if set to true, the tool will provide a help message when a user comments "/checks" on a PR. Default is true.

docs/CUSTOM_SUGGESTIONS.md

@@ -0,0 +1,65 @@
+# Custom Suggestions Tool 💎
+
+## Table of Contents
+- [Overview](#overview)
+- [Example usage](#example-usage)
+- [Configuration options](#configuration-options)
+
+
+## Overview
+The `custom_suggestions` tool scans the PR code changes, and automatically generates custom suggestions for improving the PR code.
+It shares similarities with the `improve` tool, but with one main difference: the `custom_suggestions` tool will only propose suggestions that follow specific guidelines defined by the prompt in: `pr_custom_suggestions.prompt` configuration.
+
+The tool can be triggered [automatically](https://github.com/Codium-ai/pr-agent/blob/main/Usage.md#github-app-automatic-tools) every time a new PR is opened, or can be invoked manually by commenting on a PR.
+
+When commenting, use the following template:
+
+```
+/custom_suggestions --pr_custom_suggestions.prompt="The suggestions should focus only on the following:\n-...\n-...\n-..."
+```
+
+With a [configuration file](https://github.com/Codium-ai/pr-agent/blob/main/Usage.md#working-with-github-app), use the following template:
+
+```
+[pr_custom_suggestions]
+prompt="""\
+The suggestions should focus only on the following:
+-...
+-...
+-...
+"""
+```
+Using a configuration file is recommended, since it allows to use multi-line instructions.
+
+Don't forget - with this tool, you are the prompter. Be specific, clear, and concise in the instructions. Specify relevant aspects that you want the model to focus on. \
+You might benefit from several trial-and-error iterations, until you get the correct prompt for your use case.
+
+## Example usage
+
+Here is an example of a possible prompt:
+```
+[pr_custom_suggestions]
+prompt="""\
+The suggestions should focus only on the following:
+- look for edge cases when implementing a new function
+- make sure every variable has a meaningful name
+- make sure the code is efficient
+"""
+```     
+
+The instructions above are just an example. We want to emphasize that the prompt should be specific and clear, and be tailored to the needs of your project.
+
+Results obtained with the prompt above:
+___
+<kbd><img src=https://codium.ai/images/pr_agent/custom_suggestions_prompt.png width="512"></kbd>
+___
+<kbd><img src=https://codium.ai/images/pr_agent/custom_suggestions_result.png width="768"></kbd>
+___
+
+## Configuration options
+
+`prompt`: the prompt for the tool. It should be a multi-line string.
+
+`num_code_suggestions`: number of code suggestions provided by the 'custom_suggestions' tool. Default is 4.
+
+`enable_help_text`: if set to true, the tool will display a help text in the comment. Default is true.

docs/DESCRIBE.md

@@ -0,0 +1,163 @@
+# Describe Tool
+## Table of Contents
+- [Overview](#overview)
+  - [Configuration options](#configuration-options)
+  - [Inline file summary 💎](#inline-file-summary-)
+  - [Handle custom labels from the Repo's labels page :gem:](#handle-custom-labels-from-the-repos-labels-page-gem)
+  - [Markers template](#markers-template)
+- [Usage Tips](#usage-tips)
+  - [Automation](#automation)
+  - [Custom labels](#custom-labels)
+
+## Overview
+The `describe` tool scans the PR code changes, and generates a description for the PR - title, type, summary, walkthrough and labels.
+
+The tool can be triggered automatically every time a new PR is [opened](https://github.com/Codium-ai/pr-agent/blob/main/Usage.md#github-app-automatic-tools), or it can be invoked manually by commenting on any PR:
+```
+/describe
+```
+For example:
+___
+<kbd><img src=https://codium.ai/images/pr_agent/describe_comment.png width="768"></kbd>
+___
+<kbd><img src=https://codium.ai/images/pr_agent/describe_new.png width="768"></kbd>
+___
+  
+### Configuration options
+To edit [configurations](./../pr_agent/settings/configuration.toml#L46) related to the describe tool (`pr_description` section), use the following template:
+```
+/describe --pr_description.some_config1=... --pr_description.some_config2=...
+```
+
+**Possible configurations:**
+- `publish_labels`: if set to true, the tool will publish the labels to the PR. Default is true.
+
+- `publish_description_as_comment`: if set to true, the tool will publish the description as a comment to the PR. If false, it will overwrite the origianl description. Default is false.
+
+- `add_original_user_description`: if set to true, the tool will add the original user description to the generated description. Default is true.
+
+- `keep_original_user_title`: if set to true, the tool will keep the original PR title, and won't change it. Default is true.
+
+- `extra_instructions`: Optional extra instructions to the tool. For example: "focus on the changes in the file X. Ignore change in ...".
+
+- To enable `custom labels`, apply the configuration changes described [here](./GENERATE_CUSTOM_LABELS.md#configuration-changes)
+
+- `enable_pr_type`: if set to false, it will not show the `PR type` as a text value in the description content. Default is true.
+
+- `final_update_message`: if set to true, it will add a comment message [`PR Description updated to latest commit...`](https://github.com/Codium-ai/pr-agent/pull/499#issuecomment-1837412176) after finishing calling `/describe`. Default is true.
+
+- `enable_semantic_files_types`: if set to true, "Changes walkthrough" section will be generated. Default is true.
+- `collapsible_file_list`: if set to true, the file list in the "Changes walkthrough" section will be collapsible. If set to "adaptive", the file list will be collapsible only if there are more than 8 files. Default is "adaptive".
+  
+### Inline file summary 💎
+> This feature is available only in PR-Agent Pro
+
+This feature will enable you to quickly understand the changes in each file while reviewing the code changes (diff view).
+
+To add the walkthrough table to the "Files changed" tab, you can click on the checkbox that appears PR Description status message below the main PR Description:
+
+<kbd><img src=https://codium.ai/images/pr_agent/add_table_checkbox.png width="512"></kbd>
+
+If you prefer to have the file summaries appear in the "Files changed" tab on every PR, change the `pr_description.inline_file_summary` parameter in the configuration file, possible values are:
+
+- `'table'`: File changes walkthrough table will be displayed on the top of the "Files changed" tab, in addition to the "Conversation" tab.
+<kbd><img src=https://codium.ai/images/pr_agent/diffview-table.png width="768"></kbd>
+
+- `true`: A collapsable file comment with changes title and a changes summary for each file in the PR.
+<kbd><img src=https://codium.ai/images/pr_agent/diffview_changes.png width="768"></kbd>
+
+- `false` (`default`): File changes walkthrough will be added only to the "Conversation" tab.
+
+Note that this feature is currently available only for GitHub.
+
+
+### Handle custom labels from the Repo's labels page :gem:
+> This feature is available only in PR-Agent Pro 
+
+You can control  the custom labels that will be suggested by the `describe` tool, from the repo's labels page:
+
+* GitHub : go to `https://github.com/{owner}/{repo}/labels` (or click on the "Labels" tab in the issues or PRs page)
+* GitLab : go to `https://gitlab.com/{owner}/{repo}/-/labels` (or click on "Manage" -> "Labels" on the left menu)
+
+Now add/edit the custom labels. they should be formatted as follows:
+* Label name: The name of the custom label.
+* Description: Start the description of with prefix `pr_agent:`, for example: `pr_agent: Description of when AI should suggest this label`.<br>
+
+The description should be comprehensive and detailed, indicating when to add the desired label. For example:
+<kbd><img src=https://codium.ai/images/pr_agent/add_native_custom_labels.png width="880"></kbd>
+
+
+### Markers template
+To enable markers, set `pr_description.use_description_markers=true`.
+Markers enable to easily integrate user's content and auto-generated content, with a template-like mechanism.
+
+For example, if the PR original description was:
+```
+User content...
+
+## PR Type:
+pr_agent:type
+
+## PR Description:
+pr_agent:summary
+
+## PR Walkthrough:
+pr_agent:walkthrough
+```
+The marker `pr_agent: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.
+
+<kbd><img src=https://codium.ai/images/pr_agent/describe_markers_before.png width="768"></kbd>
+
+==>
+
+<kbd><img src=https://codium.ai/images/pr_agent/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.
+
+
+## Usage Tips
+1)  [Automation](#automation)
+2) [Custom labels](#custom-labels)
+### Automation
+- When you first install the app, the [default mode](https://github.com/Codium-ai/pr-agent/blob/main/Usage.md#github-app-automatic-tools) for the describe tool is:
+```
+pr_commands = ["/describe --pr_description.add_original_user_description=true" 
+                         "--pr_description.keep_original_user_title=true", ...]
+```
+meaning the `describe` tool will run automatically on every PR, will keep the original title, and will add the original user description above the generated description. 
+<br> This default settings aim to strike a good balance between automation and control:
+If you want more automation, just give the PR a title, and the tool will auto-write a full description; If you want more control, you can add a detailed description, and the tool will add the complementary description below it.
+- For maximal automation, you can change the default mode to:
+```
+pr_commands = ["/describe --pr_description.add_original_user_description=false" 
+                         "--pr_description.keep_original_user_title=true", ...]
+```
+so the title will be auto-generated as well.
+- Markers are an alternative way to control the generated description, to give maximal control to the user. If you set:
+```
+pr_commands = ["/describe --pr_description.use_description_markers=true", ...]
+```
+the tool will replace every marker of the form `pr_agent:marker_name` in the PR description with the relevant content, where `marker_name` is one of the following:
+  - `type`: the PR type.
+  - `summary`: the PR summary.
+  - `walkthrough`: the PR walkthrough.
+
+Note that when markers are enabled, if the original PR description does not contain any markers, the tool will not alter the description at all.
+
+### Custom labels
+The default labels of the describe tool are quite generic, since they are meant to be used in any repo: [`Bug fix`, `Tests`, `Enhancement`, `Documentation`, `Other`].
+
+If you specify [custom labels](#handle-custom-labels-from-the-repos-labels-page-gem) in the repo's labels page, you can get tailored labels for your use cases.
+Examples for custom labels:
+- `Main topic:performance` -  pr_agent:The main topic of this PR is performance
+- `New endpoint` -  pr_agent:A new endpoint was added in this PR
+- `SQL query` -  pr_agent:A new SQL query was added in this PR
+- `Dockerfile changes` - pr_agent:The PR contains changes in the Dockerfile
+- ...
+
+The list above is eclectic, and aims to give an idea of different possibilities. Define custom labels that are relevant for your repo and use cases.
+Note that Labels are not mutually exclusive, so you can add multiple label categories.
+<br>Make sure to provide proper title, and a detailed and well-phrased description for each label, so the tool will know when to suggest it.

docs/Full_environments.md

@@ -0,0 +1,27 @@
+## Overview
+`PR-Agent` offers extensive pull request functionalities across various git providers:
+|       |                                             | GitHub | Gitlab | Bitbucket | CodeCommit | Azure DevOps | Gerrit |
+|-------|---------------------------------------------|:------:|:------:|:---------:|:----------:|:----------:|:----------:|
+| TOOLS | Review                                      |   :white_check_mark:    |   :white_check_mark:    |   :white_check_mark:       |   :white_check_mark:    |   :white_check_mark:    |   :white_check_mark:    |
+|       | ⮑ Incremental                              |   :white_check_mark:    |       |           |       |          |     |
+|       | Ask                                         |   :white_check_mark:    |   :white_check_mark:    |   :white_check_mark:          |   :white_check_mark:          | :white_check_mark: |  :white_check_mark:    |
+|       | Auto-Description                            |   :white_check_mark:    |   :white_check_mark:    |   :white_check_mark:        |   :white_check_mark:    |   :white_check_mark:    | :white_check_mark:    |
+|       | Improve Code                                |   :white_check_mark:    |   :white_check_mark:    |   :white_check_mark:        |   :white_check_mark:    |          |    :white_check_mark:    |
+|       | ⮑ Extended                             |   :white_check_mark:    |   :white_check_mark:    |        :white_check_mark:   |   :white_check_mark:    |          | :white_check_mark:    |
+|       | Reflect and Review                          |   :white_check_mark:    |   :white_check_mark:    |   :white_check_mark:        |          |   :white_check_mark:    |    :white_check_mark:    |
+|       | Update CHANGELOG.md                         |   :white_check_mark:    |   :white_check_mark:    |   :white_check_mark:        |   :white_check_mark:    |          |       |
+|       | Find similar issue                          |   :white_check_mark:    |                         |                             |          |          |       |
+|       | Add Documentation                           |   :white_check_mark:    |   :white_check_mark:    |   :white_check_mark:        |   :white_check_mark:    |          |    :white_check_mark:    |
+|       | Generate Custom Labels 💎                   |   :white_check_mark:    |   :white_check_mark:    |         |     |          |      |
+|       |                                             |        |        |      |      |      |
+| USAGE | CLI                                         |   :white_check_mark:    |   :white_check_mark:    |   :white_check_mark:       |   :white_check_mark:    |   :white_check_mark:    |
+|       | App / webhook                               |   :white_check_mark:    |   :white_check_mark:    |           |         |      :white_check_mark:     |
+|       | Tagging bot                                 |   :white_check_mark:    |        |           |          |          |
+|       | Actions                                     |   :white_check_mark:    |        |           |          |          |
+|       | Web server                                  |       |        |           |          |          |  :white_check_mark:   |
+|       |                                             |        |        |      |      |      |
+| CORE  | PR compression                              |   :white_check_mark:    |   :white_check_mark:    |   :white_check_mark:       | :white_check_mark: |   :white_check_mark:       | :white_check_mark:       |
+|       | Repo language prioritization                |   :white_check_mark:    |   :white_check_mark:    |   :white_check_mark:       | :white_check_mark: |   :white_check_mark:       | :white_check_mark:       |
+|       | Adaptive and token-aware<br />file patch fitting |   :white_check_mark:    |   :white_check_mark:    |   :white_check_mark:       | :white_check_mark: |   :white_check_mark:       | :white_check_mark:       |
+|       | Multiple models support |   :white_check_mark:    |   :white_check_mark:    |   :white_check_mark:       | :white_check_mark: |   :white_check_mark:       | :white_check_mark:       |
+|       | Incremental PR Review |   :white_check_mark:    |      |      |      |      |      |

docs/GENERATE_CUSTOM_LABELS.md

@@ -0,0 +1,57 @@
+# Generate Custom Labels 💎
+The `generate_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=https://codium.ai/images/pr_agent/custom_labels_list.png width="768"></kbd>
+
+When running the `generate_labels` tool on a PR that includes changes in SQL queries, it will automatically suggest the custom label:
+<kbd><img src=https://codium.ai/images/pr_agent/custom_label_published.png width="768"></kbd>
+
+Note that in addition to the dedicated tool `generate_labels`, the custom labels will also be used by the `describe` tool.
+
+### How to enable custom labels
+There are 3 ways to enable custom labels:
+
+#### 1. CLI (local configuration file)
+When working from CLI, you need to apply the [configuration changes](#configuration-changes) to the [custom_labels file](./../pr_agent/settings/custom_labels.toml):
+
+#### 2. Repo configuration file
+To enable custom labels, you need to apply the [configuration changes](#configuration-changes) to the local `.pr_agent.toml` file in you repository.
+
+#### 3. Handle custom labels from the Repo's labels page 
+> This feature is available only in PR-Agent Pro 
+* GitHub : `https://github.com/{owner}/{repo}/labels`, or click on the "Labels" tab in the issues or PRs page.
+* GitLab : `https://gitlab.com/{owner}/{repo}/-/labels`, or click on "Manage" -> "Labels" on the left menu.
+
+b. Add/edit the custom labels. It should be formatted as follows:
+* Label name: The name of the custom label.
+* Description: Start the description of with prefix `pr_agent:`, for example: `pr_agent: Description of when AI should suggest this label`.<br>
+The description should be comprehensive and detailed, indicating when to add the desired label.
+<kbd><img src=https://codium.ai/images/pr_agent/add_native_custom_labels.png width="880"></kbd>
+
+c. Now the custom labels will be included in the `generate_labels` tool.
+
+*This feature is supported in GitHub and GitLab.
+
+#### Configuration changes
+ - 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. It should be formatted as follows:
+
+```
+[config]
+enable_custom_labels=true
+
+[custom_labels."Custom Label Name"]
+description = "Description of when AI should suggest this label"
+
+[custom_labels."Custom Label 2"]
+description = "Description of when AI should suggest this label 2"
+```
+

docs/IMPROVE.md

@@ -0,0 +1,97 @@
+# Improve Tool
+
+## Table of Contents
+- [Overview](#overview)
+  - [Configuration options](#configuration-options)
+- [Usage Tips](#usage-tips)
+    - [Extra instructions](#extra-instructions)
+    - [PR footprint - regular vs summarize mode](#pr-footprint---regular-vs-summarize-mode)
+    - [A note on code suggestions quality](#a-note-on-code-suggestions-quality)
+
+## Overview
+The `improve` tool scans the PR code changes, and automatically generates suggestions for improving the PR code.
+The tool can be triggered automatically every time a new PR is [opened](https://github.com/Codium-ai/pr-agent/blob/main/Usage.md#github-app-automatic-tools), or it can be invoked manually by commenting on any PR:
+```
+/improve
+```
+
+### Summarized vs committable code suggestions
+
+The code suggestions can be presented as a single comment (via `pr_code_suggestions.summarize=true`):
+___
+<kbd><img src=https://codium.ai/images/pr_agent/code_suggestions_as_comment.png width="768"></kbd>
+___
+
+Or as a separate commitable code comment for each suggestion:
+___
+<kbd><img src=https://codium.ai/images/pr_agent/improve.png width="768"></kbd>
+
+---
+Note that a single comment has a significantly smaller PR footprint. We recommend this mode for most cases.
+Also note that collapsible are not supported in _Bitbucket_. Hence, the suggestions are presented there as code comments.
+
+### Extended mode
+
+An extended mode, which does not involve PR Compression and provides more comprehensive suggestions, can be invoked by commenting on any PR:
+```
+/improve --extended
+```
+
+or by setting:
+```
+[pr_code_suggestions]
+auto_extended_mode=true
+```
+(True by default).
+
+Note that the extended mode divides the PR code changes into chunks, up to the token limits, where each chunk is handled separately (might use multiple calls to GPT-4 for large PRs).
+Hence, the total number of suggestions is proportional to the number of chunks, i.e., the size of the PR.
+
+### Configuration options
+
+To edit [configurations](./../pr_agent/settings/configuration.toml#L66) related to the improve tool (`pr_code_suggestions` section), use the following template:
+```
+/improve --pr_code_suggestions.some_config1=... --pr_code_suggestions.some_config2=...
+```
+
+#### General options
+- `num_code_suggestions`: number of code suggestions provided by the 'improve' tool. Default is 4.
+- `extra_instructions`: Optional extra instructions to the tool. For example: "focus on the changes in the file X. Ignore change in ...".
+- `rank_suggestions`: if set to true, the tool will rank the suggestions, based on importance. Default is false.
+- `summarize`: if set to true, the tool will display the suggestions in a single comment. Default is false.
+- `enable_help_text`: if set to true, the tool will display a help text in the comment. Default is true.
+#### params for '/improve --extended' mode
+- `auto_extended_mode`: enable extended mode automatically (no need for the `--extended` option). Default is true.
+- `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.
+
+
+## Usage Tips
+
+### Extra instructions
+Extra instructions are very important for the `imrpove` tool, since they enable you to guide the model to suggestions that are more relevant to the specific needs of the project.
+
+Be specific, clear, and concise in the instructions. With extra instructions, you are the prompter. Specify relevant aspects that you want the model to focus on.
+
+Examples for extra instructions:
+```
+[pr_code_suggestions] # /improve #
+extra_instructions="""
+Emphasize the following aspects:
+- Does the code logic cover relevant edge cases?
+- Is the code logic clear and easy to understand?
+- Is the code logic efficient?
+...
+"""
+```
+Use triple quotes to write multi-line instructions. Use bullet points to make the instructions more readable.
+
+### A note on code suggestions quality
+
+- While the current AI for code is getting better and better (GPT-4), it's not flawless. 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 `exra_instructions` field to guide the model to suggestions that are more relevant to the specific needs of the project.
+- Consider also trying the [Custom Suggestions Tool](https://github.com/Codium-ai/pr-agent/blob/main/docs/CUSTOM_SUGGESTIONS.md) 💎, that will **only** propose suggestions that follow specific guidelines defined by user.
+

docs/REVIEW.md

@@ -0,0 +1,176 @@
+# Review Tool
+
+## Table of Contents
+- [Overview](#overview)
+  - [Configuration options](#configuration-options)
+  - [Incremental Mode](#incremental-mode)
+  - [PR Reflection](#pr-reflection)
+- [Usage Tips](#usage-tips)
+  - [General guidelines](#general-guidelines)
+  - [Code suggestions](#code-suggestions)
+  - [Automation](#automation)
+  - [Auto-labels](#auto-labels)
+  - [Extra instructions](#extra-instructions)
+  - [Auto-approval](#auto-approval-1)
+
+## Overview
+The `review` tool scans the PR code changes, and automatically generates a PR review.
+The tool can be triggered automatically every time a new PR is [opened](https://github.com/Codium-ai/pr-agent/blob/main/Usage.md#github-app-automatic-tools), or can be invoked manually by commenting on any PR:
+```
+/review
+```
+For example:
+___
+<kbd><img src=https://codium.ai/images/pr_agent/review_comment.png width="768"></kbd>
+___
+<kbd><img src=https://codium.ai/images/pr_agent/review.png width="768"></kbd>
+___
+
+### Configuration options
+
+To edit [configurations](./../pr_agent/settings/configuration.toml#L19)  related to the review tool (`pr_reviewer` section), use the following template:
+```
+/review --pr_reviewer.some_config1=... --pr_reviewer.some_config2=...
+```
+
+#### General options
+- `num_code_suggestions`: number of code suggestions provided by the 'review' tool. For manual comments, default is 4. For [PR-Agent app](https://github.com/Codium-ai/pr-agent/blob/main/pr_agent/settings/configuration.toml#L142) auto tools, default is 0, meaning no code suggestions will be provided by the review tool, unless you manually edit `pr_commands`.
+- `inline_code_comments`: if set to true, the tool will publish the code suggestions as comments on the code diff. Default is false.
+- `persistent_comment`: if set to true, the review comment will be persistent, meaning that every new review request will edit the previous one. Default is true.
+- `extra_instructions`: Optional extra instructions to the tool. For example: "focus on the changes in the file X. Ignore change in ...".
+#### Enable\\disable features
+- `require_focused_review`: if set to true, the tool will add a section - 'is the PR a focused one'. Default is false.
+- `require_score_review`: if set to true, the tool will add a section that scores the PR. Default is false.
+- `require_tests_review`: if set to true, the tool will add a section that checks if the PR contains tests. Default is true.
+- `require_estimate_effort_to_review`: if set to true, the tool will add a section that estimates the effort needed to review the PR. Default is true.
+#### SOC2 ticket compliance 💎
+This sub-tool checks if the PR description properly contains a ticket to a project management system (e.g., Jira, Asana, Trello, etc.), as required by SOC2 compliance. If not, it will add a label to the PR: "Missing SOC2 ticket".
+- `require_soc2_ticket`: If set to true, the SOC2 ticket checker sub-tool will be enabled. Default is false.
+- `soc2_ticket_prompt`: The prompt for the SOC2 ticket review. Default is: `Does the PR description include a link to ticket in a project management system (e.g., Jira, Asana, Trello, etc.) ?`. Edit this field if your compliance requirements are different.
+#### Adding PR labels
+- `enable_review_labels_security`: if set to true, the tool will publish a 'possible security issue' label if it detects a security issue. Default is true.
+- `enable_review_labels_effort`: if set to true, the tool will publish a 'Review effort [1-5]: x' label. Default is true.
+#### Auto-approval
+- `enable_auto_approval`: if set to true, the tool will approve the PR when invoked with the 'auto_approve' command. Default is false. This flag can be changed only from configuration file.
+- `maximal_review_effort`: maximal effort level for auto-approval. If the PR's estimated review effort is above this threshold, the auto-approval will not run. Default is 5.
+
+###  Incremental Mode
+Incremental review only considers changes since the last PR-Agent review. This can be useful when working on the PR in an iterative manner, and you want to focus on the changes since the last review instead of reviewing the entire PR again.
+For invoking the incremental mode, the following command can be used:
+```
+/review -i
+```
+Note that the incremental mode is only available for GitHub.
+
+<kbd><img src=https://codium.ai/images/pr_agent/incremental_review.png width="768"></kbd>
+
+Under the section 'pr_reviewer', the [configuration file](./../pr_agent/settings/configuration.toml#L19) contains options to customize the 'review -i' tool.  
+These configurations can be used to control the rate at which the incremental review tool will create new review comments when invoked automatically, to prevent making too much noise in the PR.
+- `minimal_commits_for_incremental_review`: Minimal number of commits since the last review that are required to create incremental review.
+If there are less than the specified number of commits since the last review, the tool will not perform any action.
+Default is 0 - the tool will always run, no matter how many commits since the last review.
+- `minimal_minutes_for_incremental_review`: Minimal number of minutes that need to pass since the last reviewed commit to create incremental review.
+If less than the specified number of minutes have passed between the last reviewed commit and running this command, the tool will not perform any action. 
+Default is 0 - the tool will always run, no matter how much time have passed since the last reviewed commit.
+- `require_all_thresholds_for_incremental_review`: If set to true, all the previous thresholds must be met for incremental review to run. If false, only one is enough to run the tool.
+For example, if `minimal_commits_for_incremental_review=2` and `minimal_minutes_for_incremental_review=2`, and we have 3 commits since the last review, but the last reviewed commit is from 1 minute ago:
+When `require_all_thresholds_for_incremental_review=true` the incremental review __will not__ run, because only 1 out of 2 conditions were met (we have enough commits but the last review is too recent),
+but when `require_all_thresholds_for_incremental_review=false` the incremental review __will__ run, because one condition is enough (we have 3 commits which is more than the configured 2).
+Default is false - the tool will run as long as at least once conditions is met.
+
+### PR Reflection
+By invoking:
+```
+/reflect_and_review
+```
+The tool will first ask the author questions about the PR, and will guide the review based on their answers.
+
+<kbd><img src=https://codium.ai/images/pr_agent/reflection_questions.png width="768"></kbd>
+___
+<kbd><img src=https://codium.ai/images/pr_agent/reflection_answers.png width="768"></kbd>
+___
+<kbd><img src=https://codium.ai/images/pr_agent/reflection_insights.png width="768"></kbd>
+___
+
+
+## Usage Tips
+1) [General guidelines](#general-guidelines)
+2) [Code suggestions](#code-suggestions)
+3) [Automation](#automation)
+4) [Auto-labels](#auto-labels)
+5) [Extra instructions](#extra-instructions)
+6) [Auto-approval](#auto-approval)
+
+### General guidelines
+The `review` tool provides a collection of possible feedbacks about a PR.
+It is recommended to review the [Configuration options](#configuration-options) section, and choose the relevant options for your use case.
+
+Some of the features that are disabled by default are quite useful, and should be considered for enabling. For example: 
+`require_score_review`, `require_soc2_ticket`, and more.
+
+On the other hand, if you find one of the enabled features to be irrelevant for your use case, disable it. No default configuration can fit all use cases.
+
+### Code suggestions
+If you set `num_code_suggestions`>0 , the `review` tool will also provide code suggestions.
+
+Notice If you are interested **only** in the code suggestions, it is recommended to use the [`improve`](./IMPROVE.md) feature instead, since it is a dedicated only to code suggestions, and usually gives better results.
+Use the `review` tool if you want to get more comprehensive feedback, which includes code suggestions as well.
+
+### Automation
+- When you first install the app, the [default mode](https://github.com/Codium-ai/pr-agent/blob/main/Usage.md#github-app-automatic-tools) for the `review` tool is:
+```
+pr_commands = ["/review", ...]
+```
+Meaning the `review` tool will run automatically on every PR, with the default configuration.
+Edit this field to enable/disable the tool, or to change the used configurations.
+
+### Auto-labels
+The `review` tool can auto-generate two specific types of labels for a PR:
+- a `possible security issue` label that detects a possible [security issue](https://github.com/Codium-ai/pr-agent/blob/tr/user_description/pr_agent/settings/pr_reviewer_prompts.toml#L136) (`enable_review_labels_security` flag)
+- a `Review effort [1-5]: x` label, where x is the estimated effort to review the PR (`enable_review_labels_effort` flag)
+
+Both modes are useful, and we recommended to enable them.
+
+### Extra instructions
+Extra instructions are important.
+The `review` tool can be configured with extra instructions, which can be used to guide the model to a feedback tailored to the needs of your project.
+
+Be specific, clear, and concise in the instructions. With extra instructions, you are the prompter. Specify the relevant sub-tool, and the relevant aspects of the PR that you want to emphasize.
+
+Examples for extra instructions:
+```
+[pr_reviewer] # /review #
+extra_instructions="""
+In the code feedback section, emphasize the following:
+- Does the code logic cover relevant edge cases?
+- Is the code logic clear and easy to understand?
+- Is the code logic efficient?
+...
+"""
+```
+Use triple quotes to write multi-line instructions. Use bullet points to make the instructions more readable.
+
+
+### Auto-approval
+PR-Agent can approve a PR when a specific comment is invoked.
+
+To ensure safety, the auto-approval feature is disabled by default. To enable auto-approval, you need to actively set in a pre-defined configuration file the following:
+```
+[pr_reviewer]
+enable_auto_approval = true
+```
+(this specific flag cannot be set with a command line argument, only in the configuration file, committed to the repository)
+
+
+After enabling, by commenting on a PR:
+```
+/review auto_approve
+```
+PR-Agent will automatically approve the PR, and add a comment with the approval.
+
+
+You can also enable auto-approval only if the PR meets certain requirements, such as that the `estimated_review_effort` label is equal or below a certain threshold, by adjusting the flag:
+```
+[pr_reviewer]
+maximal_review_effort = 5
+```

docs/SIMILAR_ISSUE.md

@@ -0,0 +1,39 @@
+# Similar Issue Tool
+The similar issue tool retrieves the most similar issues to the current issue.
+It can be invoked manually by commenting on any PR:
+```
+/similar_issue
+```
+For example:
+
+<kbd><img src=https://codium.ai/images/pr_agent/similar_issue_original_issue.png width="768"></kbd>
+<kbd><img src=https://codium.ai/images/pr_agent/similar_issue_comment.png width="768"></kbd>
+<kbd><img src=https://codium.ai/images/pr_agent/similar_issue.png width="768"></kbd>
+
+Note that to perform retrieval, the `similar_issue` tool indexes all the repo previous issues (once).
+
+
+**Select VectorDBs** by changing `pr_similar_issue` parameter in `configuration.toml` file 
+
+2 VectorDBs are available to switch in
+1. LanceDB
+2. Pinecone
+
+To enable usage of the '**similar issue**' tool for Pinecone, you need to set the following keys in `.secrets.toml` (or in the relevant environment variables):
+
+```
+[pinecone]
+api_key = "..."
+environment = "..."
+```
+These parameters can be obtained by registering to [Pinecone](https://app.pinecone.io/?sessionType=signup/).
+
+
+### How to use:
+- To invoke the 'similar issue' tool from **CLI**, run:
+`python3 cli.py --issue_url=... similar_issue`
+
+- To invoke the 'similar' issue tool via online usage, [comment](https://github.com/Codium-ai/pr-agent/issues/178#issuecomment-1716934893) on a PR:
+`/similar_issue`
+
+- You can also enable the 'similar issue' tool to run automatically when a new issue is opened, by adding it to the [pr_commands list in the github_app section](https://github.com/Codium-ai/pr-agent/blob/main/pr_agent/settings/configuration.toml#L66)

docs/TEST.md

@@ -0,0 +1,30 @@
+# Test Tool 💎
+By combining LLM abilities with static code analysis, the `test` tool  generate tests for a selected component, based on the PR code changes.
+It can be invoked manually by commenting on any PR:
+```
+/test component_name
+```
+where 'component_name' is the name of a specific component in the PR.
+To get a list of the components that changed in the PR, use the [`analyze`](https://github.com/Codium-ai/pr-agent/blob/main/docs/Analyze.md) tool.
+
+
+An example [result](https://github.com/Codium-ai/pr-agent/pull/598#issuecomment-1913679429):
+
+<kbd><img src=https://codium.ai/images/pr_agent/test1.png width="704"></kbd>
+___
+<kbd><img src=https://codium.ai/images/pr_agent/test2.png width="768"></kbd>
+___
+<kbd><img src=https://codium.ai/images/pr_agent/test3.png width="768"></kbd>
+
+Language that are currently supported by the tool: Python, Java, C++, JavaScript, TypeScript.
+
+
+
+### Configuration options
+- `num_tests`: number of tests to generate. Default is 3.
+- `testing_framework`: the testing framework to use. If not set, for Python it will use `pytest`, for Java it will use `JUnit`, for C++ it will use `Catch2`, and for JavaScript and TypeScript it will use `jest`.
+- `avoid_mocks`: if set to true, the tool will try to avoid using mocks in the generated tests. Note that even if this option is set to true, the tool might still use mocks if it cannot generate a test without them. Default is true.
+- `extra_instructions`: Optional extra instructions to the tool. For example: "use the following mock injection scheme: ...".
+- `file`: in case there are several components with the same name, you can specify the relevant file.
+- `class_name`: in case there are several methods with the same name in the same file, you can specify the relevant class name.
+- `enable_help_text`: if set to true, the tool will add a help text to the PR comment. Default is true.

docs/TOOLS_GUIDE.md

@@ -0,0 +1,15 @@
+## Tools Guide
+- [DESCRIBE](./DESCRIBE.md)
+- [REVIEW](./REVIEW.md)
+- [IMPROVE](./IMPROVE.md)
+- [ASK](./ASK.md)
+- [SIMILAR_ISSUE](./SIMILAR_ISSUE.md)
+- [UPDATE CHANGELOG](./UPDATE_CHANGELOG.md)
+- [CUSTOM SUGGESTIONS](./CUSTOM_SUGGESTIONS.md) 💎
+- [ADD DOCUMENTATION](./ADD_DOCUMENTATION.md) 💎
+- [GENERATE CUSTOM LABELS](./GENERATE_CUSTOM_LABELS.md) 💎
+- [Analyze](./Analyze.md) 💎
+- [Test](./TEST.md) 💎
+- [CI Feedback](./CI_FEEDBACK.md) 💎
+
+See the **[installation guide](/INSTALL.md)** for instructions on setting up PR-Agent.

docs/UPDATE_CHANGELOG.md

@@ -0,0 +1,19 @@
+# Update Changelog Tool
+
+The `update_changelog` tool automatically updates the CHANGELOG.md file with the PR changes.
+It can be invoked manually by commenting on any PR:
+```
+/update_changelog
+```
+For example:
+
+<kbd><img src=https://codium.ai/images/pr_agent/update_changelog_comment.png width="768"></kbd>
+<kbd><img src=https://codium.ai/images/pr_agent/update_changelog.png width="768"></kbd>
+
+
+### Configuration options
+
+Under the section 'pr_update_changelog', the [configuration file](./../pr_agent/settings/configuration.toml#L50) contains options to customize the 'update changelog' tool:
+
+- `push_changelog_changes`: whether to push the changes to CHANGELOG.md, or just print them. Default is false (print only).
+- `extra_instructions`: Optional extra instructions to the tool. For example: "focus on the changes in the file X. Ignore change in ...

pr_agent/agent/pr_agent.py

@@ -1,24 +1,94 @@
-import re
+import shlex
+from functools import partial
 
+from pr_agent.algo.ai_handlers.base_ai_handler import BaseAiHandler
+from pr_agent.algo.ai_handlers.litellm_ai_handler import LiteLLMAIHandler
+
+from pr_agent.algo.utils import update_settings_from_args
+from pr_agent.config_loader import get_settings
+from pr_agent.git_providers.utils import apply_repo_settings
+from pr_agent.log import get_logger
+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_help_message import PRHelpMessage
+from pr_agent.tools.pr_information_from_user import PRInformationFromUser
+from pr_agent.tools.pr_line_questions import PR_LineQuestions
 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
 
+command2class = {
+    "auto_review": PRReviewer,
+    "answer": PRReviewer,
+    "review": PRReviewer,
+    "review_pr": PRReviewer,
+    "reflect": PRInformationFromUser,
+    "reflect_and_review": PRInformationFromUser,
+    "describe": PRDescription,
+    "describe_pr": PRDescription,
+    "improve": PRCodeSuggestions,
+    "improve_code": PRCodeSuggestions,
+    "ask": PRQuestions,
+    "ask_question": PRQuestions,
+    "ask_line": PR_LineQuestions,
+    "update_changelog": PRUpdateChangelog,
+    "config": PRConfig,
+    "settings": PRConfig,
+    "help": PRHelpMessage,
+    "similar_issue": PRSimilarIssue,
+    "add_docs": PRAddDocs,
+    "generate_labels": PRGenerateLabels,
+}
+
+commands = list(command2class.keys())
 
 class PRAgent:
-    def __init__(self):
-        pass
+    def __init__(self, ai_handler: partial[BaseAiHandler,] = LiteLLMAIHandler):
+        self.ai_handler = ai_handler # will be initialized in run_action
+        self.forbidden_cli_args = ['enable_auto_approval']
 
-    async def handle_request(self, pr_url, request):
-        if 'please review' in request.lower() or 'review' == request.lower().strip() or len(request) == 0:
-            reviewer = PRReviewer(pr_url)
-            await reviewer.review()
+    async def handle_request(self, pr_url, request, notify=None) -> bool:
+        # First, apply repo specific settings if exists
+        apply_repo_settings(pr_url)
 
+        # Then, apply user specific settings if exists
+        if isinstance(request, str):
+            request = request.replace("'", "\\'")
+            lexer = shlex.shlex(request, posix=True)
+            lexer.whitespace_split = True
+            action, *args = list(lexer)
         else:
-            if "please answer" in request.lower():
-                question = re.split(r'(?i)please answer', request)[1].strip()
-            elif request.lower().strip().startswith("answer"):
-                question = re.split(r'(?i)answer', request)[1].strip()
+            action, *args = request
+
+        if args:
+            for forbidden_arg in self.forbidden_cli_args:
+                for arg in args:
+                    if forbidden_arg in arg:
+                        get_logger().error(f"CLI argument for param '{forbidden_arg}' is forbidden. Use instead a configuration file.")
+                        return False
+        args = update_settings_from_args(args)
+
+        action = action.lstrip("/").lower()
+        with get_logger().contextualize(command=action):
+            get_logger().info("PR-Agent request handler started", analytics=True)
+            if action == "reflect_and_review":
+                get_settings().pr_reviewer.ask_and_reflect = True
+            if action == "answer":
+                if notify:
+                    notify()
+                await PRReviewer(pr_url, is_answer=True, args=args, ai_handler=self.ai_handler).run()
+            elif action == "auto_review":
+                await PRReviewer(pr_url, is_auto=True, args=args, ai_handler=self.ai_handler).run()
+            elif action in command2class:
+                if notify:
+                    notify()
+
+                await command2class[action](pr_url, ai_handler=self.ai_handler, args=args).run()
             else:
-                question = request
-            answerer = PRQuestions(pr_url, question)
-            await answerer.answer()
+                return False
+            return True
+

pr_agent/algo/__init__.py

@@ -1,4 +1,5 @@
 MAX_TOKENS = {
+    'text-embedding-ada-002': 8000,
     'gpt-3.5-turbo': 4000,
     'gpt-3.5-turbo-0613': 4000,
     'gpt-3.5-turbo-0301': 4000,
@@ -7,4 +8,18 @@ MAX_TOKENS = {
     'gpt-4': 8000,
     'gpt-4-0613': 8000,
     'gpt-4-32k': 32000,
+    'gpt-4-1106-preview': 128000, # 128K, but may be limited by config.max_model_tokens
+    'gpt-4-0125-preview': 128000,  # 128K, but may be limited by config.max_model_tokens
+    'claude-instant-1': 100000,
+    'claude-2': 100000,
+    'command-nightly': 4096,
+    'replicate/llama-2-70b-chat:2c1608e18606fad2812020dc541930f2d0495ce32eee50074220b87300bc16e1': 4096,
+    'meta-llama/Llama-2-7b-chat-hf': 4096,
+    'vertex_ai/codechat-bison': 6144,
+    'vertex_ai/codechat-bison-32k': 32000,
+    'codechat-bison': 6144,
+    'codechat-bison-32k': 32000,
+    'anthropic.claude-v2': 100000,
+    'anthropic.claude-instant-v1': 100000,
+    'anthropic.claude-v1': 100000,
 }

pr_agent/algo/ai_handler.py

@@ -1,47 +0,0 @@
-import logging
-
-import openai
-from openai.error import APIError, Timeout, TryAgain
-from retry import retry
-
-from pr_agent.config_loader import settings
-
-OPENAI_RETRIES=2
-
-class AiHandler:
-    def __init__(self):
-        try:
-            openai.api_key = settings.openai.key
-            if settings.get("OPENAI.ORG", None):
-                openai.organization = settings.openai.org
-            self.deployment_id = settings.get("OPENAI.DEPLOYMENT_ID", None)
-            if settings.get("OPENAI.API_TYPE", None):
-                openai.api_type = settings.openai.api_type
-            if settings.get("OPENAI.API_VERSION", None):
-                openai.api_version = settings.openai.api_version
-            if settings.get("OPENAI.API_BASE", None):
-                openai.api_base = settings.openai.api_base
-        except AttributeError as e:
-            raise ValueError("OpenAI key is required") from e
-
-    @retry(exceptions=(APIError, Timeout, TryAgain, AttributeError),
-           tries=OPENAI_RETRIES, delay=2, backoff=2, jitter=(1, 3))
-    async def chat_completion(self, model: str, temperature: float, system: str, user: str):
-        try:
-            response = await openai.ChatCompletion.acreate(
-                            model=model,
-                            deployment_id=self.deployment_id,
-                            messages=[
-                                {"role": "system", "content": system},
-                                {"role": "user", "content": user}
-                            ],
-                            temperature=temperature,
-                        )
-        except (APIError, Timeout, TryAgain) as e:
-            logging.error("Error during OpenAI inference: ", e)
-            raise
-        if response is None or len(response.choices) == 0:
-            raise TryAgain
-        resp = response.choices[0]['message']['content']
-        finish_reason = response.choices[0].finish_reason
-        return resp, finish_reason

pr_agent/algo/ai_handlers/base_ai_handler.py

@@ -0,0 +1,28 @@
+from abc import ABC, abstractmethod
+
+class BaseAiHandler(ABC):
+    """
+    This class defines the interface for an AI handler to be used by the PR Agents.  
+    """
+
+    @abstractmethod
+    def __init__(self):
+        pass
+
+    @property
+    @abstractmethod
+    def deployment_id(self):
+        pass
+
+    @abstractmethod   
+    async def chat_completion(self, model: str, system: str, user: str, temperature: float = 0.2):
+        """
+        This method should be implemented to return a chat completion from the AI model.
+        Args:
+            model (str): the name of the model to use for the chat completion
+            system (str): the system message string to use for the chat completion
+            user (str): the user message string to use for the chat completion
+            temperature (float): the temperature to use for the chat completion    
+        """
+        pass
+

pr_agent/algo/ai_handlers/langchain_ai_handler.py

@@ -0,0 +1,67 @@
+try:
+    from langchain.chat_models import ChatOpenAI, AzureChatOpenAI
+    from langchain.schema import SystemMessage, HumanMessage
+except: # we don't enforce langchain as a dependency, so if it's not installed, just move on
+    pass
+
+from pr_agent.algo.ai_handlers.base_ai_handler import BaseAiHandler
+from pr_agent.config_loader import get_settings
+from pr_agent.log import get_logger
+
+from openai.error import APIError, RateLimitError, Timeout, TryAgain
+from retry import retry
+import functools
+
+OPENAI_RETRIES = 5
+
+class LangChainOpenAIHandler(BaseAiHandler):
+    def __init__(self):
+        # Initialize OpenAIHandler specific attributes here
+        super().__init__()
+        self.azure = get_settings().get("OPENAI.API_TYPE", "").lower() == "azure"
+        try:
+            if self.azure:
+                # using a partial function so we can set the deployment_id later to support fallback_deployments
+                # but still need to access the other settings now so we can raise a proper exception if they're missing
+                self._chat = functools.partial(
+                    lambda **kwargs: AzureChatOpenAI(**kwargs),
+                    openai_api_key=get_settings().openai.key,
+                    openai_api_base=get_settings().openai.api_base,
+                    openai_api_version=get_settings().openai.api_version,
+                )
+            else:
+                self._chat = ChatOpenAI(openai_api_key=get_settings().openai.key)
+        except AttributeError as e:
+            if getattr(e, "name"):
+                raise ValueError(f"OpenAI {e.name} is required") from e
+            else:
+                raise e
+    
+    @property
+    def chat(self):
+        if self.azure:
+            # we must set the deployment_id only here (instead of the __init__ method) to support fallback_deployments
+            return self._chat(deployment_name=self.deployment_id)
+        else:
+            return self._chat
+
+    @property
+    def deployment_id(self):
+        """
+        Returns the deployment ID for the OpenAI API.
+        """
+        return get_settings().get("OPENAI.DEPLOYMENT_ID", None)
+    @retry(exceptions=(APIError, Timeout, TryAgain, AttributeError, RateLimitError),
+           tries=OPENAI_RETRIES, delay=2, backoff=2, jitter=(1, 3))
+    async def chat_completion(self, model: str, system: str, user: str, temperature: float = 0.2):
+        try:
+            messages=[SystemMessage(content=system), HumanMessage(content=user)]
+            
+            # get a chat completion from the formatted messages
+            resp = self.chat(messages, model=model, temperature=temperature)
+            finish_reason="completed"
+            return resp.content, finish_reason
+        
+        except (Exception) as e:
+            get_logger().error("Unknown error during OpenAI inference: ", e)
+            raise e

pr_agent/algo/ai_handlers/litellm_ai_handler.py

@@ -0,0 +1,138 @@
+import os
+
+import boto3
+import litellm
+import openai
+from litellm import acompletion
+from openai.error import APIError, RateLimitError, Timeout, TryAgain
+from retry import retry
+from pr_agent.algo.ai_handlers.base_ai_handler import BaseAiHandler
+from pr_agent.config_loader import get_settings
+from pr_agent.log import get_logger
+
+OPENAI_RETRIES = 5
+
+
+class LiteLLMAIHandler(BaseAiHandler):
+    """
+    This class handles interactions with the OpenAI API for chat completions.
+    It initializes the API key and other settings from a configuration file,
+    and provides a method for performing chat completions using the OpenAI ChatCompletion API.
+    """
+
+    def __init__(self):
+        """
+        Initializes the OpenAI API key and other settings from a configuration file.
+        Raises a ValueError if the OpenAI key is missing.
+        """
+        self.azure = False
+        self.aws_bedrock_client = None
+
+        if get_settings().get("OPENAI.KEY", None):
+            openai.api_key = get_settings().openai.key
+            litellm.openai_key = get_settings().openai.key
+        if get_settings().get("litellm.use_client"):
+            litellm_token = get_settings().get("litellm.LITELLM_TOKEN")
+            assert litellm_token, "LITELLM_TOKEN is required"
+            os.environ["LITELLM_TOKEN"] = litellm_token
+            litellm.use_client = True
+        if get_settings().get("OPENAI.ORG", None):
+            litellm.organization = get_settings().openai.org
+        if get_settings().get("OPENAI.API_TYPE", None):
+            if get_settings().openai.api_type == "azure":
+                self.azure = True
+                litellm.azure_key = get_settings().openai.key
+        if get_settings().get("OPENAI.API_VERSION", None):
+            litellm.api_version = get_settings().openai.api_version
+        if get_settings().get("OPENAI.API_BASE", None):
+            litellm.api_base = get_settings().openai.api_base
+        if get_settings().get("ANTHROPIC.KEY", None):
+            litellm.anthropic_key = get_settings().anthropic.key
+        if get_settings().get("COHERE.KEY", None):
+            litellm.cohere_key = get_settings().cohere.key
+        if get_settings().get("REPLICATE.KEY", None):
+            litellm.replicate_key = get_settings().replicate.key
+        if get_settings().get("REPLICATE.KEY", None):
+            litellm.replicate_key = get_settings().replicate.key
+        if get_settings().get("HUGGINGFACE.KEY", None):
+            litellm.huggingface_key = get_settings().huggingface.key
+            if get_settings().get("HUGGINGFACE.API_BASE", None):
+                litellm.api_base = get_settings().huggingface.api_base
+        if get_settings().get("VERTEXAI.VERTEX_PROJECT", None):
+            litellm.vertex_project = get_settings().vertexai.vertex_project
+            litellm.vertex_location = get_settings().get(
+                "VERTEXAI.VERTEX_LOCATION", None
+            )
+        if get_settings().get("AWS.BEDROCK_REGION", None):
+            litellm.AmazonAnthropicConfig.max_tokens_to_sample = 2000
+            self.aws_bedrock_client = boto3.client(
+                service_name="bedrock-runtime",
+                region_name=get_settings().aws.bedrock_region,
+            )
+
+    @property
+    def deployment_id(self):
+        """
+        Returns the deployment ID for the OpenAI API.
+        """
+        return get_settings().get("OPENAI.DEPLOYMENT_ID", None)
+
+    @retry(exceptions=(APIError, Timeout, TryAgain, AttributeError, RateLimitError),
+           tries=OPENAI_RETRIES, delay=2, backoff=2, jitter=(1, 3))
+    async def chat_completion(self, model: str, system: str, user: str, temperature: float = 0.2):
+        """
+        Performs a chat completion using the OpenAI ChatCompletion API.
+        Retries in case of API errors or timeouts.
+        
+        Args:
+            model (str): The model to use for chat completion.
+            temperature (float): The temperature parameter for chat completion.
+            system (str): The system message for chat completion.
+            user (str): The user message for chat completion.
+        
+        Returns:
+            tuple: A tuple containing the response and finish reason from the API.
+        
+        Raises:
+            TryAgain: If the API response is empty or there are no choices in the response.
+            APIError: If there is an error during OpenAI inference.
+            Timeout: If there is a timeout during OpenAI inference.
+            TryAgain: If there is an attribute error during OpenAI inference.
+        """
+        try:
+            resp, finish_reason = None, None
+            deployment_id = self.deployment_id
+            if self.azure:
+                model = 'azure/' + model
+            messages = [{"role": "system", "content": system}, {"role": "user", "content": user}]
+            kwargs = {
+                "model": model,
+                "deployment_id": deployment_id,
+                "messages": messages,
+                "temperature": temperature,
+                "force_timeout": get_settings().config.ai_timeout,
+            }
+            if self.aws_bedrock_client:
+                kwargs["aws_bedrock_client"] = self.aws_bedrock_client
+
+            get_logger().debug("Prompts", artifact={"system": system, "user": user})
+            response = await acompletion(**kwargs)
+        except (APIError, Timeout, TryAgain) as e:
+            get_logger().error("Error during OpenAI inference: ", e)
+            raise
+        except (RateLimitError) as e:
+            get_logger().error("Rate limit error during OpenAI inference: ", e)
+            raise
+        except (Exception) as 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
+        else:
+            resp = response["choices"][0]['message']['content']
+            finish_reason = response["choices"][0]["finish_reason"]
+            # usage = response.get("usage")
+            get_logger().debug(f"\nAI response:\n{resp}")
+            get_logger().debug("Full_response", artifact=response)
+
+        return resp, finish_reason

pr_agent/algo/ai_handlers/openai_ai_handler.py

@@ -0,0 +1,67 @@
+from pr_agent.algo.ai_handlers.base_ai_handler import BaseAiHandler
+import openai
+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
+
+
+class OpenAIHandler(BaseAiHandler):
+    def __init__(self):
+        # Initialize OpenAIHandler specific attributes here
+        try:
+            super().__init__()
+            openai.api_key = get_settings().openai.key
+            if get_settings().get("OPENAI.ORG", None):
+                openai.organization = get_settings().openai.org
+            if get_settings().get("OPENAI.API_TYPE", None):
+                if get_settings().openai.api_type == "azure":
+                    self.azure = True
+                    openai.azure_key = get_settings().openai.key
+            if get_settings().get("OPENAI.API_VERSION", None):
+                openai.api_version = get_settings().openai.api_version
+            if get_settings().get("OPENAI.API_BASE", None):
+                openai.api_base = get_settings().openai.api_base
+
+        except AttributeError as e:
+            raise ValueError("OpenAI key is required") from e
+    @property
+    def deployment_id(self):
+        """
+        Returns the deployment ID for the OpenAI API.
+        """
+        return get_settings().get("OPENAI.DEPLOYMENT_ID", None)
+    
+    @retry(exceptions=(APIError, Timeout, TryAgain, AttributeError, RateLimitError),
+           tries=OPENAI_RETRIES, delay=2, backoff=2, jitter=(1, 3))
+    async def chat_completion(self, model: str, system: str, user: str, temperature: float = 0.2):
+        try:
+            deployment_id = self.deployment_id
+            get_logger().info("System: ", system)
+            get_logger().info("User: ", user)
+            messages = [{"role": "system", "content": system}, {"role": "user", "content": user}]
+
+            chat_completion = await openai.ChatCompletion.acreate(
+                model=model,
+                deployment_id=deployment_id,
+                messages=messages,
+                temperature=temperature,
+            )
+            resp = chat_completion["choices"][0]['message']['content']
+            finish_reason = chat_completion["choices"][0]["finish_reason"]
+            usage = chat_completion.get("usage")
+            get_logger().info("AI response", response=resp, messages=messages, finish_reason=finish_reason,
+                            model=model, usage=usage)
+            return resp, finish_reason       
+        except (APIError, Timeout, TryAgain) as e:
+            get_logger().error("Error during OpenAI inference: ", e)
+            raise
+        except (RateLimitError) as e:
+            get_logger().error("Rate limit error during OpenAI inference: ", e)
+            raise
+        except (Exception) as e:
+            get_logger().error("Unknown error during OpenAI inference: ", e)
+            raise TryAgain from e        

pr_agent/algo/file_filter.py

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

pr_agent/algo/git_patch_processing.py

@@ -1,14 +1,23 @@
 from __future__ import annotations
 
-import logging
 import re
 
-from pr_agent.config_loader import settings
+from pr_agent.config_loader import get_settings
+from pr_agent.algo.types import EDIT_TYPE, FilePatchInfo
+from pr_agent.log import get_logger
 
 
 def extend_patch(original_file_str, patch_str, num_lines) -> str:
     """
-    Extends the patch to include 'num_lines' more surrounding lines
+    Extends the given patch to include a specified number of surrounding lines.
+    
+    Args:
+        original_file_str (str): The original file to which the patch will be applied.
+        patch_str (str): The patch to be applied to the original file.
+        num_lines (int): The number of surrounding lines to include in the extended patch.
+        
+    Returns:
+        str: The extended patch string.
     """
     if not patch_str or num_lines == 0:
         return patch_str
@@ -33,8 +42,16 @@ def extend_patch(original_file_str, patch_str, num_lines) -> str:
                         extended_patch_lines.extend(
                             original_lines[start1 + size1 - 1:start1 + size1 - 1 + num_lines])
 
-                    start1, size1, start2, size2 = map(int, match.groups()[:4])
-                    section_header = match.groups()[4]
+                    res = list(match.groups())
+                    for i in range(len(res)):
+                        if res[i] is None:
+                            res[i] = 0
+                    try:
+                        start1, size1, start2, size2 = map(int, res[:4])
+                    except:  # '@@ -0,0 +1 @@' case
+                        start1, size1, size2 = map(int, res[:3])
+                        start2 = 0
+                    section_header = res[4]
                     extended_start1 = max(1, start1 - num_lines)
                     extended_size1 = size1 + (start1 - extended_start1) + num_lines
                     extended_start2 = max(1, start2 - num_lines)
@@ -47,8 +64,8 @@ def extend_patch(original_file_str, patch_str, num_lines) -> str:
                     continue
             extended_patch_lines.append(line)
     except Exception as e:
-        if settings.config.verbosity_level >= 2:
-            logging.error(f"Failed to extend patch: {e}")
+        if get_settings().config.verbosity_level >= 2:
+            get_logger().error(f"Failed to extend patch: {e}")
         return patch_str
 
     # finish previous hunk
@@ -61,6 +78,14 @@ def extend_patch(original_file_str, patch_str, num_lines) -> str:
 
 
 def omit_deletion_hunks(patch_lines) -> str:
+    """
+    Omit deletion hunks from the patch and return the modified patch.
+    Args:
+    - patch_lines: a list of strings representing the lines of the patch
+    Returns:
+    - A string representing the modified patch with deletion hunks omitted
+    """
+
     temp_hunk = []
     added_patched = []
     add_hunk = False
@@ -91,42 +116,62 @@ def omit_deletion_hunks(patch_lines) -> str:
 
 
 def handle_patch_deletions(patch: str, original_file_content_str: str,
-                           new_file_content_str: str, file_name: str) -> str:
+                           new_file_content_str: str, file_name: str, edit_type: EDIT_TYPE = EDIT_TYPE.UNKNOWN) -> str:
     """
-    Handle entire file or deletion patches
+    Handle entire file or deletion patches.
+
+    This function takes a patch, original file content, new file content, and file name as input.
+    It handles entire file or deletion patches and returns the modified patch with deletion hunks omitted.
+
+    Args:
+        patch (str): The patch to be handled.
+        original_file_content_str (str): The original content of the file.
+        new_file_content_str (str): The new content of the file.
+        file_name (str): The name of the file.
+
+    Returns:
+        str: The modified patch with deletion hunks omitted.
+
     """
-    if not new_file_content_str:
+    if not new_file_content_str and edit_type != EDIT_TYPE.ADDED:
         # logic for handling deleted files - don't show patch, just show that the file was deleted
-        if settings.config.verbosity_level > 0:
-            logging.info(f"Processing file: {file_name}, minimizing deletion file")
+        if get_settings().config.verbosity_level > 0:
+            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 settings.config.verbosity_level > 0:
-                logging.info(f"Processing file: {file_name}, hunks were deleted")
+            if get_settings().config.verbosity_level > 0:
+                get_logger().info(f"Processing file: {file_name}, hunks were deleted")
             patch = patch_new
     return patch
 
 
 def convert_to_hunks_with_lines_numbers(patch: str, file) -> str:
-    # toDO: (maybe remove '-' and '+' from the beginning of the line)
     """
-    ## src/file.ts
---new hunk--
+    Convert a given patch string into a string with line numbers for each hunk, indicating the new and old content of
+    the file.
+
+    Args:
+        patch (str): The patch string to be converted.
+        file: An object containing the filename of the file being patched.
+
+    Returns:
+        str: A string with line numbers for each hunk, indicating the new and old content of the file.
+
+    example output:
+## src/file.ts
+__new hunk__
 881        line1
 882        line2
 883        line3
-884        line4
-885        line6
-886        line7
-887 +      line8
-888 +      line9
-889        line10
-890        line11
+887 +      line4
+888 +      line5
+889        line6
+890        line7
 ...
---old hunk--
+__old hunk__
         line1
         line2
 -       line3
@@ -134,10 +179,9 @@ def convert_to_hunks_with_lines_numbers(patch: str, file) -> str:
         line5
         line6
            ...
-
     """
-    patch_with_lines_str = f"## {file.filename}\n"
-    import re
+    
+    patch_with_lines_str = f"\n\n## file: '{file.filename.strip()}'\n"
     patch_lines = patch.splitlines()
     RE_HUNK_HEADER = re.compile(
         r"^@@ -(\d+)(?:,(\d+))? \+(\d+)(?:,(\d+))? @@[ ]?(.*)")
@@ -145,24 +189,41 @@ def convert_to_hunks_with_lines_numbers(patch: str, file) -> str:
     old_content_lines = []
     match = None
     start1, size1, start2, size2 = -1, -1, -1, -1
+    prev_header_line = []
+    header_line =[]
     for line in patch_lines:
         if 'no newline at end of file' in line.lower():
             continue
 
         if line.startswith('@@'):
+            header_line = line
             match = RE_HUNK_HEADER.match(line)
             if match and new_content_lines:  # found a new hunk, split the previous lines
                 if new_content_lines:
-                    patch_with_lines_str += '\n--new hunk--\n'
+                    if prev_header_line:
+                        patch_with_lines_str += f'\n{prev_header_line}\n'
+                    patch_with_lines_str = patch_with_lines_str.rstrip()+'\n__new hunk__\n'
                     for i, line_new in enumerate(new_content_lines):
                         patch_with_lines_str += f"{start2 + i} {line_new}\n"
                 if old_content_lines:
-                    patch_with_lines_str += '--old hunk--\n'
-                    for i, line_old in enumerate(old_content_lines):
+                    patch_with_lines_str = patch_with_lines_str.rstrip()+'\n__old hunk__\n'
+                    for line_old in old_content_lines:
                         patch_with_lines_str += f"{line_old}\n"
                 new_content_lines = []
                 old_content_lines = []
-            start1, size1, start2, size2 = map(int, match.groups()[:4])
+            if match:
+                prev_header_line = header_line
+
+            res = list(match.groups())
+            for i in range(len(res)):
+                if res[i] is None:
+                    res[i] = 0
+            try:
+                start1, size1, start2, size2 = map(int, res[:4])
+            except: # '@@ -0,0 +1 @@' case
+                start1, size1, size2 = map(int, res[:3])
+                start2 = 0
+
         elif line.startswith('+'):
             new_content_lines.append(line)
         elif line.startswith('-'):
@@ -174,12 +235,69 @@ def convert_to_hunks_with_lines_numbers(patch: str, file) -> str:
     # finishing last hunk
     if match and new_content_lines:
         if new_content_lines:
-            patch_with_lines_str += '\n--new hunk--\n'
+            patch_with_lines_str += f'\n{header_line}\n'
+            patch_with_lines_str = patch_with_lines_str.rstrip()+ '\n__new hunk__\n'
             for i, line_new in enumerate(new_content_lines):
                 patch_with_lines_str += f"{start2 + i} {line_new}\n"
         if old_content_lines:
-            patch_with_lines_str += '\n--old hunk--\n'
-            for i, line_old in enumerate(old_content_lines):
+            patch_with_lines_str = patch_with_lines_str.rstrip() + '\n__old hunk__\n'
+            for line_old in old_content_lines:
                 patch_with_lines_str += f"{line_old}\n"
 
-    return patch_with_lines_str.strip()
+    return patch_with_lines_str.rstrip()
+
+
+def extract_hunk_lines_from_patch(patch: str, file_name, line_start, line_end, side) -> tuple[str, str]:
+
+    patch_with_lines_str = f"\n\n## file: '{file_name.strip()}'\n\n"
+    selected_lines = ""
+    patch_lines = patch.splitlines()
+    RE_HUNK_HEADER = re.compile(
+        r"^@@ -(\d+)(?:,(\d+))? \+(\d+)(?:,(\d+))? @@[ ]?(.*)")
+    match = None
+    start1, size1, start2, size2 = -1, -1, -1, -1
+    skip_hunk = False
+    selected_lines_num = 0
+    for line in patch_lines:
+        if 'no newline at end of file' in line.lower():
+            continue
+
+        if line.startswith('@@'):
+            skip_hunk = False
+            selected_lines_num = 0
+            header_line = line
+
+            match = RE_HUNK_HEADER.match(line)
+
+            res = list(match.groups())
+            for i in range(len(res)):
+                if res[i] is None:
+                    res[i] = 0
+            try:
+                start1, size1, start2, size2 = map(int, res[:4])
+            except:  # '@@ -0,0 +1 @@' case
+                start1, size1, size2 = map(int, res[:3])
+                start2 = 0
+
+            # check if line range is in this hunk
+            if side.lower() == 'left':
+                # check if line range is in this hunk
+                if not (start1 <= line_start <= start1 + size1):
+                    skip_hunk = True
+                    continue
+            elif side.lower() == 'right':
+                if not (start2 <= line_start <= start2 + size2):
+                    skip_hunk = True
+                    continue
+            patch_with_lines_str += f'\n{header_line}\n'
+
+        elif not skip_hunk:
+            if side.lower() == 'right' and line_start <= start2 + selected_lines_num <= line_end:
+                selected_lines += line + '\n'
+            if side.lower() == 'left' and start1 <= selected_lines_num + start1 <= line_end:
+                selected_lines += line + '\n'
+            patch_with_lines_str += line + '\n'
+            if not line.startswith('-'): # currently we don't support /ask line for deleted lines
+                selected_lines_num += 1
+
+    return patch_with_lines_str.rstrip(), selected_lines.rstrip()

pr_agent/algo/pr_processing.py

@@ -1,85 +1,140 @@
 from __future__ import annotations
 
-import difflib
-import logging
-from typing import Any, Tuple, Union
+import traceback
+from typing import Callable, List, Tuple
 
-from pr_agent.algo.git_patch_processing import extend_patch, handle_patch_deletions, \
-    convert_to_hunks_with_lines_numbers
+from github import RateLimitExceededException
+
+from pr_agent.algo.git_patch_processing import convert_to_hunks_with_lines_numbers, extend_patch, handle_patch_deletions
 from pr_agent.algo.language_handler import sort_files_by_main_languages
+from pr_agent.algo.file_filter import filter_ignored
 from pr_agent.algo.token_handler import TokenHandler
-from pr_agent.config_loader import settings
-from pr_agent.git_providers import GithubProvider
+from pr_agent.algo.utils import get_max_tokens, ModelType
+from pr_agent.config_loader import get_settings
+from pr_agent.git_providers.git_provider import GitProvider
+from pr_agent.algo.types import EDIT_TYPE, FilePatchInfo
+from pr_agent.log import get_logger
 
 DELETED_FILES_ = "Deleted files:\n"
 
-MORE_MODIFIED_FILES_ = "More modified files:\n"
+MORE_MODIFIED_FILES_ = "Additional modified files (insufficient token budget to process):\n"
+
+ADDED_FILES_ = "Additional added files (insufficient token budget to process):\n"
 
 OUTPUT_BUFFER_TOKENS_SOFT_THRESHOLD = 1000
 OUTPUT_BUFFER_TOKENS_HARD_THRESHOLD = 600
-PATCH_EXTRA_LINES = 3
 
+def get_pr_diff(git_provider: GitProvider, token_handler: TokenHandler, model: str,
+                add_line_numbers_to_hunks: bool = False, disable_extra_lines: bool = False) -> str:
+    """
+    Returns a string with the diff of the pull request, applying diff minimization techniques if needed.
 
-def get_pr_diff(git_provider: Union[GithubProvider, Any], token_handler: TokenHandler,
-                add_line_numbers_to_hunks: bool = False, disable_extra_lines: bool =False) -> str:
-    """
-    Returns a string with the diff of the PR.
-    If needed, apply diff minimization techniques to reduce the number of tokens
+    Args:
+        git_provider (GitProvider): An object of the GitProvider class representing the Git provider used for the pull
+        request.
+        token_handler (TokenHandler): An object of the TokenHandler class used for handling tokens in the context of the
+        pull request.
+        model (str): The name of the model used for tokenization.
+        add_line_numbers_to_hunks (bool, optional): A boolean indicating whether to add line numbers to the hunks in the
+        diff. Defaults to False.
+        disable_extra_lines (bool, optional): A boolean indicating whether to disable the extension of each patch with
+        extra lines of context. Defaults to False.
+
+    Returns:
+        str: A string with the diff of the pull request, applying diff minimization techniques if needed.
     """
+
     if disable_extra_lines:
-        global PATCH_EXTRA_LINES
         PATCH_EXTRA_LINES = 0
+    else:
+        PATCH_EXTRA_LINES = get_settings().config.patch_extra_lines
+
+    try:
+        diff_files_original = git_provider.get_diff_files()
+    except RateLimitExceededException as e:
+        get_logger().error(f"Rate limit exceeded for git provider API. original message {e}")
+        raise
+
+    diff_files = filter_ignored(diff_files_original)
+    if diff_files != diff_files_original:
+        try:
+            get_logger().info(f"Filtered out {len(diff_files_original) - len(diff_files)} files")
+            new_names = set([a.filename for a in diff_files])
+            orig_names = set([a.filename for a in diff_files_original])
+            get_logger().info(f"Filtered out files: {orig_names - new_names}")
+        except Exception as e:
+            pass
 
-    git_provider.pr.diff_files = list(git_provider.get_diff_files())
 
     # get pr languages
-    pr_languages = sort_files_by_main_languages(git_provider.get_languages(), git_provider.pr.diff_files)
+    pr_languages = sort_files_by_main_languages(git_provider.get_languages(), diff_files)
+    if pr_languages:
+        try:
+            get_logger().info(f"PR main language: {pr_languages[0]['language']}")
+        except Exception as e:
+            pass
 
     # generate a standard diff string, with patch extension
-    patches_extended, total_tokens = pr_generate_extended_diff(pr_languages, token_handler,
-                                                               add_line_numbers_to_hunks)
+    patches_extended, total_tokens, patches_extended_tokens = pr_generate_extended_diff(
+        pr_languages, token_handler, add_line_numbers_to_hunks, patch_extra_lines=PATCH_EXTRA_LINES)
 
     # if we are under the limit, return the full diff
-    if total_tokens + OUTPUT_BUFFER_TOKENS_SOFT_THRESHOLD < token_handler.limit:
+    if total_tokens + OUTPUT_BUFFER_TOKENS_SOFT_THRESHOLD < get_max_tokens(model):
+        get_logger().info(f"Tokens: {total_tokens}, total tokens under limit: {get_max_tokens(model)}, "
+                          f"returning full diff.")
         return "\n".join(patches_extended)
 
     # if we are over the limit, start pruning
-    patches_compressed, modified_file_names, deleted_file_names = \
-        pr_generate_compressed_diff(pr_languages, token_handler, add_line_numbers_to_hunks)
+    get_logger().info(f"Tokens: {total_tokens}, total tokens over limit: {get_max_tokens(model)}, "
+                      f"pruning diff.")
+    patches_compressed, modified_file_names, deleted_file_names, added_file_names = \
+        pr_generate_compressed_diff(pr_languages, token_handler, model, add_line_numbers_to_hunks)
 
     final_diff = "\n".join(patches_compressed)
+    if added_file_names:
+        added_list_str = ADDED_FILES_ + "\n".join(added_file_names)
+        final_diff = final_diff + "\n\n" + added_list_str
     if modified_file_names:
         modified_list_str = MORE_MODIFIED_FILES_ + "\n".join(modified_file_names)
         final_diff = final_diff + "\n\n" + modified_list_str
     if deleted_file_names:
         deleted_list_str = DELETED_FILES_ + "\n".join(deleted_file_names)
         final_diff = final_diff + "\n\n" + deleted_list_str
+    try:
+        get_logger().debug(f"After pruning, added_list_str: {added_list_str}, modified_list_str: {modified_list_str}, "
+                          f"deleted_list_str: {deleted_list_str}")
+    except Exception as e:
+        pass
     return final_diff
 
 
-def pr_generate_extended_diff(pr_languages: list, token_handler: TokenHandler,
-                              add_line_numbers_to_hunks: bool) -> \
-        Tuple[list, int]:
+def pr_generate_extended_diff(pr_languages: list,
+                              token_handler: TokenHandler,
+                              add_line_numbers_to_hunks: bool,
+                              patch_extra_lines: int = 0) -> Tuple[list, int, list]:
     """
-    Generate a standard diff string, with patch extension
+    Generate a standard diff string with patch extension, while counting the number of tokens used and applying diff
+    minimization techniques if needed.
+
+    Args:
+    - pr_languages: A list of dictionaries representing the languages used in the pull request and their corresponding
+      files.
+    - token_handler: An object of the TokenHandler class used for handling tokens in the context of the pull request.
+    - add_line_numbers_to_hunks: A boolean indicating whether to add line numbers to the hunks in the diff.
     """
     total_tokens = token_handler.prompt_tokens  # initial tokens
     patches_extended = []
+    patches_extended_tokens = []
     for lang in pr_languages:
         for file in lang['files']:
             original_file_content_str = file.base_file
-            new_file_content_str = file.head_file
             patch = file.patch
-
-            # handle the case of large patch, that initially was not loaded
-            patch = load_large_diff(file, new_file_content_str, original_file_content_str, patch)
-
             if not patch:
                 continue
 
             # extend each patch with extra lines of context
-            extended_patch = extend_patch(original_file_content_str, patch, num_lines=PATCH_EXTRA_LINES)
-            full_extended_patch = f"## {file.filename}\n\n{extended_patch}\n"
+            extended_patch = extend_patch(original_file_content_str, patch, num_lines=patch_extra_lines)
+            full_extended_patch = f"\n\n## {file.filename}\n\n{extended_patch}\n"
 
             if add_line_numbers_to_hunks:
                 full_extended_patch = convert_to_hunks_with_lines_numbers(extended_patch, file)
@@ -87,21 +142,40 @@ def pr_generate_extended_diff(pr_languages: list, token_handler: TokenHandler,
             patch_tokens = token_handler.count_tokens(full_extended_patch)
             file.tokens = patch_tokens
             total_tokens += patch_tokens
+            patches_extended_tokens.append(patch_tokens)
             patches_extended.append(full_extended_patch)
 
-    return patches_extended, total_tokens
+    return patches_extended, total_tokens, patches_extended_tokens
 
 
-def pr_generate_compressed_diff(top_langs: list, token_handler: TokenHandler,
-                                convert_hunks_to_line_numbers: bool) -> Tuple[list, list, list]:
-    # Apply Diff Minimization techniques to reduce the number of tokens:
-    # 0. Start from the largest diff patch to smaller ones
-    # 1. Don't use extend context lines around diff
-    # 2. Minimize deleted files
-    # 3. Minimize deleted hunks
-    # 4. Minimize all remaining files when you reach token limit
+def pr_generate_compressed_diff(top_langs: list, token_handler: TokenHandler, model: str,
+                                convert_hunks_to_line_numbers: bool) -> Tuple[list, list, list, list]:
+    """
+    Generate a compressed diff string for a pull request, using diff minimization techniques to reduce the number of
+    tokens used.
+    Args:
+        top_langs (list): A list of dictionaries representing the languages used in the pull request and their
+        corresponding files.
+        token_handler (TokenHandler): An object of the TokenHandler class used for handling tokens in the context of the
+        pull request.
+        model (str): The model used for tokenization.
+        convert_hunks_to_line_numbers (bool): A boolean indicating whether to convert hunks to line numbers in the diff.
+    Returns:
+        Tuple[list, list, list]: A tuple containing the following lists:
+            - patches: A list of compressed diff patches for each file in the pull request.
+            - modified_files_list: A list of file names that were skipped due to large patch size.
+            - deleted_files_list: A list of file names that were deleted in the pull request.
+
+    Minimization techniques to reduce the number of tokens:
+    0. Start from the largest diff patch to smaller ones
+    1. Don't use extend context lines around diff
+    2. Minimize deleted files
+    3. Minimize deleted hunks
+    4. Minimize all remaining files when you reach token limit
+    """
 
     patches = []
+    added_files_list = []
     modified_files_list = []
     deleted_files_list = []
     # sort each one of the languages in top_langs by the number of tokens in the diff
@@ -114,13 +188,12 @@ def pr_generate_compressed_diff(top_langs: list, token_handler: TokenHandler,
         original_file_content_str = file.base_file
         new_file_content_str = file.head_file
         patch = file.patch
-        patch = load_large_diff(file, new_file_content_str, original_file_content_str, patch)
         if not patch:
             continue
 
         # removing delete-only hunks
         patch = handle_patch_deletions(patch, original_file_content_str,
-                                       new_file_content_str, file.filename)
+                                       new_file_content_str, file.filename, file.edit_type)
         if patch is None:
             if not deleted_files_list:
                 total_tokens += token_handler.count_tokens(DELETED_FILES_)
@@ -134,44 +207,179 @@ def pr_generate_compressed_diff(top_langs: list, token_handler: TokenHandler,
         new_patch_tokens = token_handler.count_tokens(patch)
 
         # Hard Stop, no more tokens
-        if total_tokens > token_handler.limit - OUTPUT_BUFFER_TOKENS_HARD_THRESHOLD:
-            logging.warning(f"File was fully skipped, no more tokens: {file.filename}.")
+        if total_tokens > get_max_tokens(model) - OUTPUT_BUFFER_TOKENS_HARD_THRESHOLD:
+            get_logger().warning(f"File was fully skipped, no more tokens: {file.filename}.")
             continue
 
         # If the patch is too large, just show the file name
-        if total_tokens + new_patch_tokens > token_handler.limit - OUTPUT_BUFFER_TOKENS_SOFT_THRESHOLD:
+        if total_tokens + new_patch_tokens > get_max_tokens(model) - OUTPUT_BUFFER_TOKENS_SOFT_THRESHOLD:
             # Current logic is to skip the patch if it's too large
             # TODO: Option for alternative logic to remove hunks from the patch to reduce the number of tokens
             #  until we meet the requirements
-            if settings.config.verbosity_level >= 2:
-                logging.warning(f"Patch too large, minimizing it, {file.filename}")
-            if not modified_files_list:
-                total_tokens += token_handler.count_tokens(MORE_MODIFIED_FILES_)
-            modified_files_list.append(file.filename)
-            total_tokens += token_handler.count_tokens(file.filename) + 1
+            if get_settings().config.verbosity_level >= 2:
+                get_logger().warning(f"Patch too large, minimizing it, {file.filename}")
+            if file.edit_type == EDIT_TYPE.ADDED:
+                if not added_files_list:
+                    total_tokens += token_handler.count_tokens(ADDED_FILES_)
+                added_files_list.append(file.filename)
+            else:
+                if not modified_files_list:
+                    total_tokens += token_handler.count_tokens(MORE_MODIFIED_FILES_)
+                modified_files_list.append(file.filename)
+                total_tokens += token_handler.count_tokens(file.filename) + 1
             continue
 
         if patch:
             if not convert_hunks_to_line_numbers:
-                patch_final = f"## {file.filename}\n\n{patch}\n"
+                patch_final = f"\n\n## file: '{file.filename.strip()}\n\n{patch.strip()}\n'"
             else:
-                patch_final = patch
+                patch_final = "\n\n" + patch.strip()
             patches.append(patch_final)
             total_tokens += token_handler.count_tokens(patch_final)
-            if settings.config.verbosity_level >= 2:
-                logging.info(f"Tokens: {total_tokens}, last filename: {file.filename}")
+            if get_settings().config.verbosity_level >= 2:
+                get_logger().info(f"Tokens: {total_tokens}, last filename: {file.filename}")
 
-    return patches, modified_files_list, deleted_files_list
+    return patches, modified_files_list, deleted_files_list, added_files_list
 
 
-def load_large_diff(file, new_file_content_str: str, original_file_content_str: str, patch: str) -> str:
-    if not patch:  # to Do - also add condition for file extension
+async def retry_with_fallback_models(f: Callable, model_type: ModelType = ModelType.REGULAR):
+    all_models = _get_all_models(model_type)
+    all_deployments = _get_all_deployments(all_models)
+    # try each (model, deployment_id) pair until one is successful, otherwise raise exception
+    for i, (model, deployment_id) in enumerate(zip(all_models, all_deployments)):
         try:
-            diff = difflib.unified_diff(original_file_content_str.splitlines(keepends=True),
-                                        new_file_content_str.splitlines(keepends=True))
-            if settings.config.verbosity_level >= 2:
-                logging.warning(f"File was modified, but no patch was found. Manually creating patch: {file.filename}.")
-            patch = ''.join(diff)
-        except Exception:
-            pass
-    return patch
+            get_logger().debug(
+                f"Generating prediction with {model}"
+                f"{(' from deployment ' + deployment_id) if deployment_id else ''}"
+            )
+            get_settings().set("openai.deployment_id", deployment_id)
+            return await f(model)
+        except:
+            get_logger().warning(
+                f"Failed to generate prediction with {model}"
+                f"{(' from deployment ' + deployment_id) if deployment_id else ''}: "
+                f"{traceback.format_exc()}"
+            )
+            if i == len(all_models) - 1:  # If it's the last iteration
+                raise  # Re-raise the last exception
+
+
+def _get_all_models(model_type: ModelType = ModelType.REGULAR) -> List[str]:
+    if model_type == ModelType.TURBO:
+        model = get_settings().config.model_turbo
+    else:
+        model = get_settings().config.model
+    fallback_models = get_settings().config.fallback_models
+    if not isinstance(fallback_models, list):
+        fallback_models = [m.strip() for m in fallback_models.split(",")]
+    all_models = [model] + fallback_models
+    return all_models
+
+
+def _get_all_deployments(all_models: List[str]) -> List[str]:
+    deployment_id = get_settings().get("openai.deployment_id", None)
+    fallback_deployments = get_settings().get("openai.fallback_deployments", [])
+    if not isinstance(fallback_deployments, list) and fallback_deployments:
+        fallback_deployments = [d.strip() for d in fallback_deployments.split(",")]
+    if fallback_deployments:
+        all_deployments = [deployment_id] + fallback_deployments
+        if len(all_deployments) < len(all_models):
+            raise ValueError(f"The number of deployments ({len(all_deployments)}) "
+                             f"is less than the number of models ({len(all_models)})")
+    else:
+        all_deployments = [deployment_id] * len(all_models)
+    return all_deployments
+
+
+def get_pr_multi_diffs(git_provider: GitProvider,
+                       token_handler: TokenHandler,
+                       model: str,
+                       max_calls: int = 5) -> List[str]:
+    """
+    Retrieves the diff files from a Git provider, sorts them by main language, and generates patches for each file.
+    The patches are split into multiple groups based on the maximum number of tokens allowed for the given model.
+
+    Args:
+        git_provider (GitProvider): An object that provides access to Git provider APIs.
+        token_handler (TokenHandler): An object that handles tokens in the context of a pull request.
+        model (str): The name of the model.
+        max_calls (int, optional): The maximum number of calls to retrieve diff files. Defaults to 5.
+
+    Returns:
+        List[str]: A list of final diff strings, split into multiple groups based on the maximum number of tokens allowed for the given model.
+
+    Raises:
+        RateLimitExceededException: If the rate limit for the Git provider API is exceeded.
+    """
+    try:
+        diff_files = git_provider.get_diff_files()
+    except RateLimitExceededException as e:
+        get_logger().error(f"Rate limit exceeded for git provider API. original message {e}")
+        raise
+
+    diff_files = filter_ignored(diff_files)
+
+    # Sort files by main language
+    pr_languages = sort_files_by_main_languages(git_provider.get_languages(), diff_files)
+
+    # Sort files within each language group by tokens in descending order
+    sorted_files = []
+    for lang in pr_languages:
+        sorted_files.extend(sorted(lang['files'], key=lambda x: x.tokens, reverse=True))
+
+
+    # try first a single run with standard diff string, with patch extension, and no deletions
+    patches_extended, total_tokens, patches_extended_tokens = pr_generate_extended_diff(
+        pr_languages, token_handler, add_line_numbers_to_hunks=True)
+    if total_tokens + OUTPUT_BUFFER_TOKENS_SOFT_THRESHOLD < get_max_tokens(model):
+        return ["\n".join(patches_extended)]
+
+    patches = []
+    final_diff_list = []
+    total_tokens = token_handler.prompt_tokens
+    call_number = 1
+    for file in sorted_files:
+        if call_number > max_calls:
+            if get_settings().config.verbosity_level >= 2:
+                get_logger().info(f"Reached max calls ({max_calls})")
+            break
+
+        original_file_content_str = file.base_file
+        new_file_content_str = file.head_file
+        patch = file.patch
+        if not patch:
+            continue
+
+        # Remove delete-only hunks
+        patch = handle_patch_deletions(patch, original_file_content_str, new_file_content_str, file.filename, file.edit_type)
+        if patch is None:
+            continue
+
+        patch = convert_to_hunks_with_lines_numbers(patch, file)
+        new_patch_tokens = token_handler.count_tokens(patch)
+
+        if patch and (token_handler.prompt_tokens + new_patch_tokens) > get_max_tokens(model) - OUTPUT_BUFFER_TOKENS_SOFT_THRESHOLD:
+            get_logger().warning(f"Patch too large, skipping: {file.filename}")
+            continue
+
+        if patch and (total_tokens + new_patch_tokens > get_max_tokens(model) - OUTPUT_BUFFER_TOKENS_SOFT_THRESHOLD):
+            final_diff = "\n".join(patches)
+            final_diff_list.append(final_diff)
+            patches = []
+            total_tokens = token_handler.prompt_tokens
+            call_number += 1
+            if get_settings().config.verbosity_level >= 2:
+                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:
+                get_logger().info(f"Tokens: {total_tokens}, last filename: {file.filename}")
+
+    # Add the last chunk
+    if patches:
+        final_diff = "\n".join(patches)
+        final_diff_list.append(final_diff)
+
+    return final_diff_list

pr_agent/algo/token_handler.py

@@ -1,24 +1,69 @@
 from jinja2 import Environment, StrictUndefined
-from tiktoken import encoding_for_model
+from tiktoken import encoding_for_model, get_encoding
 
-from pr_agent.algo import MAX_TOKENS
-from pr_agent.config_loader import settings
+from pr_agent.config_loader import get_settings
 
 
+def get_token_encoder():
+    return encoding_for_model(get_settings().config.model) if "gpt" in get_settings().config.model else get_encoding(
+        "cl100k_base")
+
 class TokenHandler:
-    def __init__(self, pr, vars: dict, system, user):
-        self.encoder = encoding_for_model(settings.config.model)
-        self.limit = MAX_TOKENS[settings.config.model]
-        self.prompt_tokens = self._get_system_user_tokens(pr, self.encoder, vars, system, user)
+    """
+    A class for handling tokens in the context of a pull request.
+
+    Attributes:
+    - encoder: An object of the encoding_for_model class from the tiktoken module. Used to encode strings and count the
+      number of tokens in them.
+    - limit: The maximum number of tokens allowed for the given model, as defined in the MAX_TOKENS dictionary in the
+      pr_agent.algo module.
+    - prompt_tokens: The number of tokens in the system and user strings, as calculated by the _get_system_user_tokens
+      method.
+    """
+
+    def __init__(self, pr=None, vars: dict = {}, system="", user=""):
+        """
+        Initializes the TokenHandler object.
+
+        Args:
+        - pr: The pull request object.
+        - vars: A dictionary of variables.
+        - system: The system string.
+        - user: The user string.
+        """
+        self.encoder = get_token_encoder()
+        if pr is not None:
+            self.prompt_tokens = self._get_system_user_tokens(pr, self.encoder, vars, system, user)
 
     def _get_system_user_tokens(self, pr, encoder, vars: dict, system, user):
+        """
+        Calculates the number of tokens in the system and user strings.
+
+        Args:
+        - pr: The pull request object.
+        - encoder: An object of the encoding_for_model class from the tiktoken module.
+        - vars: A dictionary of variables.
+        - system: The system string.
+        - user: The user string.
+
+        Returns:
+        The sum of the number of tokens in the system and user strings.
+        """
         environment = Environment(undefined=StrictUndefined)
         system_prompt = environment.from_string(system).render(vars)
         user_prompt = environment.from_string(user).render(vars)
-
         system_prompt_tokens = len(encoder.encode(system_prompt))
         user_prompt_tokens = len(encoder.encode(user_prompt))
         return system_prompt_tokens + user_prompt_tokens
 
     def count_tokens(self, patch: str) -> int:
+        """
+        Counts the number of tokens in a given patch string.
+
+        Args:
+        - patch: The patch string.
+
+        Returns:
+        The number of tokens in the patch string.
+        """
         return len(self.encoder.encode(patch, disallowed_special=()))

pr_agent/algo/types.py

@@ -0,0 +1,23 @@
+from dataclasses import dataclass
+from enum import Enum
+
+
+class EDIT_TYPE(Enum):
+    ADDED = 1
+    DELETED = 2
+    MODIFIED = 3
+    RENAMED = 4
+    UNKNOWN = 5
+
+
+@dataclass
+class FilePatchInfo:
+    base_file: str
+    head_file: str
+    patch: str
+    filename: str
+    tokens: int = -1
+    edit_type: EDIT_TYPE = EDIT_TYPE.UNKNOWN
+    old_filename: str = None
+    num_plus_lines: int = -1
+    num_minus_lines: int = -1

pr_agent/algo/utils.py

@@ -1,84 +1,606 @@
 from __future__ import annotations
 
+import difflib
 import json
-import logging
 import re
 import textwrap
+from datetime import datetime
+from enum import Enum
+from typing import Any, List, Tuple
+
+import yaml
+from starlette_context import context
+
+from pr_agent.algo import MAX_TOKENS
+from pr_agent.algo.token_handler import get_token_encoder
+from pr_agent.config_loader import get_settings, global_settings
+from pr_agent.algo.types import FilePatchInfo
+from pr_agent.log import get_logger
+
+class ModelType(str, Enum):
+    REGULAR = "regular"
+    TURBO = "turbo"
+
+def get_setting(key: str) -> Any:
+    try:
+        key = key.upper()
+        return context.get("settings", global_settings).get(key, global_settings.get(key, None))
+    except Exception:
+        return global_settings.get(key, None)
 
 
-def convert_to_markdown(output_data: dict) -> str:
-    markdown_text = ""
+def emphasize_header(text: str) -> str:
+    try:
+        # Finding the position of the first occurrence of ": "
+        colon_position = text.find(": ")
+
+        # Splitting the string and wrapping the first part in <strong> tags
+        if colon_position != -1:
+            # Everything before the colon (inclusive) is wrapped in <strong> tags
+            transformed_string = "<strong>" + text[:colon_position + 1] + "</strong>" + text[colon_position + 1:]
+        else:
+            # If there's no ": ", return the original string
+            transformed_string = text
+
+        return transformed_string
+    except Exception as e:
+        get_logger().exception(f"Failed to emphasize header: {e}")
+        return text
+
+def convert_to_markdown(output_data: dict, gfm_supported: bool=True) -> str:
+    """
+    Convert a dictionary of data into markdown format.
+    Args:
+        output_data (dict): A dictionary containing data to be converted to markdown format.
+    Returns:
+        str: The markdown formatted text generated from the input dictionary.
+    """    
 
     emojis = {
-        "Main theme": "🎯",
-        "Type of PR": "📌",
-        "Relevant tests added": "🧪",
-        "Unrelated changes": "⚠️",
+        "Possible issues": "🔍",
+        "Score": "🏅",
+        "Relevant tests": "🧪",
         "Focused PR": "✨",
         "Security concerns": "🔒",
-        "General PR suggestions": "💡",
-        "Code suggestions": "🤖"
+        "Insights from user's answers": "📝",
+        "Code feedback": "🤖",
+        "Estimated effort to review [1-5]": "⏱️",
     }
-
-    for key, value in output_data.items():
-        if not value:
-            continue
-        if isinstance(value, dict):
-            markdown_text += f"## {key}\n\n"
-            markdown_text += convert_to_markdown(value)
-        elif isinstance(value, list):
-            if key.lower() == 'code suggestions':
-                markdown_text += "\n"  # just looks nicer with additional line breaks
-            emoji = emojis.get(key, "‣")  # Use a dash if no emoji is found for the key
-            markdown_text += f"- {emoji} **{key}:**\n\n"
-            for item in value:
-                if isinstance(item, dict) and key.lower() == 'code suggestions':
-                    markdown_text += parse_code_suggestion(item)
-                elif item:
-                    markdown_text += f"  - {item}\n"
-        elif value != 'n/a':
-            emoji = emojis.get(key, "‣")  # Use a dash if no emoji is found for the key
-            markdown_text += f"- {emoji} **{key}:** {value}\n"
-    return markdown_text
-
-
-def parse_code_suggestion(code_suggestions: dict) -> str:
     markdown_text = ""
-    for sub_key, sub_value in code_suggestions.items():
-        if isinstance(sub_value, dict):  # "code example"
-            markdown_text += f"  - **{sub_key}:**\n"
-            for code_key, code_value in sub_value.items():  # 'before' and 'after' code
-                code_str = f"```\n{code_value}\n```"
-                code_str_indented = textwrap.indent(code_str, '        ')
-                markdown_text += f"    - **{code_key}:**\n{code_str_indented}\n"
-        else:
-            if "relevant file" in sub_key.lower():
-                markdown_text += f"\n  - **{sub_key}:** {sub_value}\n"
-            else:
-                markdown_text += f"   **{sub_key}:** {sub_value}\n"
+    markdown_text += f"## PR Review\n\n"
+    if gfm_supported:
+        markdown_text += "<table>\n<tr>\n"
+        # markdown_text += """<td> &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;Feedback&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;</td> <td></td></tr>"""
+
+    if not output_data or not output_data.get('review', {}):
+        return ""
+
+    for key, value in output_data['review'].items():
+        if value is None or value == '' or value == {} or value == []:
+            continue
+        key_nice = key.replace('_', ' ').capitalize()
+        emoji = emojis.get(key_nice, "")
+        if gfm_supported:
+            if 'Estimated effort to review' in key_nice:
+                key_nice = 'Estimated&nbsp;effort&nbsp;to&nbsp;review [1-5]'
+            if 'security concerns' in key_nice.lower():
+                value = emphasize_header(value.strip())
+                markdown_text += f"<tr><td> {emoji}&nbsp;<strong>{key_nice}</strong></td><td>\n\n{value}\n\n</td></tr>\n"
+            elif 'possible issues' in key_nice.lower():
+                value = value.strip()
+                issues = value.split('\n- ')
+                number_of_issues = len(issues)
+                if number_of_issues > 1:
+                    markdown_text += f"<tr><td rowspan={number_of_issues}> {emoji}&nbsp;<strong>{key_nice}</strong></td>\n"
+                    for i, issue in enumerate(issues):
+                        issue = issue.strip('-').strip()
+                        issue = emphasize_header(issue.strip())
+                        if i == 0:
+                            markdown_text += f"<td>\n\n{issue}</td></tr>\n"
+                        else:
+                            markdown_text += f"<tr>\n<td>\n\n{issue}</td></tr>\n"
+                else:
+                    value = emphasize_header(value.strip('-').strip())
+                    markdown_text += f"<tr><td> {emoji}&nbsp;<strong>{key_nice}</strong></td><td>\n\n{value}\n\n</td></tr>\n"
+            else:
+                markdown_text += f"<tr><td> {emoji}&nbsp;<strong>{key_nice}</strong></td><td>\n\n{value}\n\n</td></tr>\n"
+        else:
+            if len(value.split()) > 1:
+                markdown_text += f"{emoji} **{key_nice}:**\n\n {value}\n\n"
+            else:
+                markdown_text += f"{emoji} **{key_nice}:** {value}\n\n"
+    if gfm_supported:
+        markdown_text += "</table>\n"
+
+    if 'code_feedback' in output_data:
+        if gfm_supported:
+            markdown_text += f"\n\n"
+            markdown_text += f"<details><summary> <strong>Code feedback:</strong></summary>\n\n"
+            markdown_text += "<hr>"
+        else:
+            markdown_text += f"\n\n** Code feedback:**\n\n"
+        for i, value in enumerate(output_data['code_feedback']):
+            if value is None or value == '' or value == {} or value == []:
+                continue
+            markdown_text += parse_code_suggestion(value, i, gfm_supported)+"\n\n"
+        if markdown_text.endswith('<hr>'):
+            markdown_text = markdown_text[:-4]
+        if gfm_supported:
+            markdown_text += f"</details>"
+    #print(markdown_text)
+
 
-    markdown_text += "\n"
     return markdown_text
 
 
-def try_fix_json(review, max_iter=10):
-    # Try to fix JSON if it is broken/incomplete: parse until the last valid code suggestion
+def parse_code_suggestion(code_suggestion: dict, i: int = 0, gfm_supported: bool = True) -> str:
+    """
+    Convert a dictionary of data into markdown format.
+
+    Args:
+        code_suggestion (dict): A dictionary containing data to be converted to markdown format.
+
+    Returns:
+        str: A string containing the markdown formatted text generated from the input dictionary.
+    """
+    markdown_text = ""
+    if gfm_supported and 'relevant_line' in code_suggestion:
+        markdown_text += '<table>'
+        for sub_key, sub_value in code_suggestion.items():
+            try:
+                if sub_key.lower() == 'relevant_file':
+                    relevant_file = sub_value.strip('`').strip('"').strip("'")
+                    markdown_text += f"<tr><td>relevant file</td><td>{relevant_file}</td></tr>"
+                    # continue
+                elif sub_key.lower() == 'suggestion':
+                    markdown_text += (f"<tr><td>{sub_key} &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;</td>"
+                                      f"<td>\n\n<strong>\n\n{sub_value.strip()}\n\n</strong>\n</td></tr>")
+                elif sub_key.lower() == 'relevant_line':
+                    markdown_text += f"<tr><td>relevant line</td>"
+                    sub_value_list = sub_value.split('](')
+                    relevant_line = sub_value_list[0].lstrip('`').lstrip('[')
+                    if len(sub_value_list) > 1:
+                        link = sub_value_list[1].rstrip(')').strip('`')
+                        markdown_text += f"<td><a href='{link}'>{relevant_line}</a></td>"
+                    else:
+                        markdown_text += f"<td>{relevant_line}</td>"
+                    markdown_text += "</tr>"
+            except Exception as e:
+                get_logger().exception(f"Failed to parse code suggestion: {e}")
+                pass
+        markdown_text += '</table>'
+        markdown_text += "<hr>"
+    else:
+        for sub_key, sub_value in code_suggestion.items():
+            if isinstance(sub_key, str):
+                sub_key = sub_key.rstrip()
+            if isinstance(sub_value,str):
+                sub_value = sub_value.rstrip()
+            if isinstance(sub_value, dict):  # "code example"
+                markdown_text += f"  - **{sub_key}:**\n"
+                for code_key, code_value in sub_value.items():  # 'before' and 'after' code
+                    code_str = f"```\n{code_value}\n```"
+                    code_str_indented = textwrap.indent(code_str, '        ')
+                    markdown_text += f"    - **{code_key}:**\n{code_str_indented}\n"
+            else:
+                if "relevant_file" in sub_key.lower():
+                    markdown_text += f"\n  - **{sub_key}:** {sub_value}  \n"
+                else:
+                    markdown_text += f"   **{sub_key}:** {sub_value}  \n"
+                if "relevant_line" not in sub_key.lower():  # nicer presentation
+                    # markdown_text = markdown_text.rstrip('\n') + "\\\n" # works for gitlab
+                    markdown_text = markdown_text.rstrip('\n') + "   \n"  # works for gitlab and bitbucker
+
+        markdown_text += "\n"
+    return markdown_text
+
+
+def try_fix_json(review, max_iter=10, code_suggestions=False):
+    """
+    Fix broken or incomplete JSON messages and return the parsed JSON data.
+
+    Args:
+    - review: A string containing the JSON message to be fixed.
+    - max_iter: An integer representing the maximum number of iterations to try and fix the JSON message.
+    - code_suggestions: A boolean indicating whether to try and fix JSON messages with code feedback.
+
+    Returns:
+    - data: A dictionary containing the parsed JSON data.
+
+    The function attempts to fix broken or incomplete JSON messages by parsing until the last valid code suggestion.
+    If the JSON message ends with a closing bracket, the function calls the fix_json_escape_char function to fix the
+    message.
+    If code_suggestions is True and the JSON message contains code feedback, the function tries to fix the JSON
+    message by parsing until the last valid code suggestion.
+    The function uses regular expressions to find the last occurrence of "}," with any number of whitespaces or
+    newlines.
+    It tries to parse the JSON message with the closing bracket and checks if it is valid.
+    If the JSON message is valid, the parsed JSON data is returned.
+    If the JSON message is not valid, the last code suggestion is removed and the process is repeated until a valid JSON
+    message is obtained or the maximum number of iterations is reached.
+    If a valid JSON message is not obtained, an error is logged and an empty dictionary is returned.
+    """
+
+    if review.endswith("}"):
+        return fix_json_escape_char(review)
+
     data = {}
-    if review.rfind("'Code suggestions': [") > 0 or review.rfind('"Code suggestions": [') > 0:
+    if code_suggestions:
+        closing_bracket = "]}"
+    else:
+        closing_bracket = "]}}"
+
+    if (review.rfind("'Code feedback': [") > 0 or review.rfind('"Code feedback": [') > 0) or \
+            (review.rfind("'Code suggestions': [") > 0 or review.rfind('"Code suggestions": [') > 0) :
         last_code_suggestion_ind = [m.end() for m in re.finditer(r"\}\s*,", review)][-1] - 1
         valid_json = False
         iter_count = 0
+
         while last_code_suggestion_ind > 0 and not valid_json and iter_count < max_iter:
             try:
-                data = json.loads(review[:last_code_suggestion_ind] + "]}}")
+                data = json.loads(review[:last_code_suggestion_ind] + closing_bracket)
                 valid_json = True
-                review = review[:last_code_suggestion_ind].strip() + "]}}"
+                review = review[:last_code_suggestion_ind].strip() + closing_bracket
             except json.decoder.JSONDecodeError:
                 review = review[:last_code_suggestion_ind]
-                # Use regular expression to find the last occurrence of "}," with any number of whitespaces or newlines
                 last_code_suggestion_ind = [m.end() for m in re.finditer(r"\}\s*,", review)][-1] - 1
                 iter_count += 1
+
         if not valid_json:
-            logging.error("Unable to decode JSON response from AI")
+            get_logger().error("Unable to decode JSON response from AI")
             data = {}
+
     return data
+
+
+def fix_json_escape_char(json_message=None):
+    """
+    Fix broken or incomplete JSON messages and return the parsed JSON data.
+
+    Args:
+        json_message (str): A string containing the JSON message to be fixed.
+
+    Returns:
+        dict: A dictionary containing the parsed JSON data.
+
+    Raises:
+        None
+
+    """
+    try:
+        result = json.loads(json_message)
+    except Exception as e:
+        # Find the offending character index:
+        idx_to_replace = int(str(e).split(' ')[-1].replace(')', ''))
+        # Remove the offending character:
+        json_message = list(json_message)
+        json_message[idx_to_replace] = ' '
+        new_message = ''.join(json_message)
+        return fix_json_escape_char(json_message=new_message)
+    return result
+
+
+def convert_str_to_datetime(date_str):
+    """
+    Convert a string representation of a date and time into a datetime object.
+
+    Args:
+        date_str (str): A string representation of a date and time in the format '%a, %d %b %Y %H:%M:%S %Z'
+
+    Returns:
+        datetime: A datetime object representing the input date and time.
+
+    Example:
+        >>> convert_str_to_datetime('Mon, 01 Jan 2022 12:00:00 UTC')
+        datetime.datetime(2022, 1, 1, 12, 0, 0)
+    """
+    datetime_format = '%a, %d %b %Y %H:%M:%S %Z'
+    return datetime.strptime(date_str, datetime_format)
+
+
+def load_large_diff(filename, new_file_content_str: str, original_file_content_str: str) -> str:
+    """
+    Generate a patch for a modified file by comparing the original content of the file with the new content provided as
+    input.
+
+    Args:
+        new_file_content_str: The new content of the file as a string.
+        original_file_content_str: The original content of the file as a string.
+
+    Returns:
+        The generated or provided patch string.
+
+    Raises:
+        None.
+    """
+    patch = ""
+    try:
+        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:
+            get_logger().warning(f"File was modified, but no patch was found. Manually creating patch: {filename}.")
+        patch = ''.join(diff)
+    except Exception:
+        pass
+    return patch
+
+
+def update_settings_from_args(args: List[str]) -> List[str]:
+    """
+    Update the settings of the Dynaconf object based on the arguments passed to the function.
+
+    Args:
+        args: A list of arguments passed to the function.
+        Example args: ['--pr_code_suggestions.extra_instructions="be funny',
+                  '--pr_code_suggestions.num_code_suggestions=3']
+
+    Returns:
+        None
+
+    Raises:
+        ValueError: If the argument is not in the correct format.
+
+    """
+    other_args = []
+    if args:
+        for arg in args:
+            arg = arg.strip()
+            if arg.startswith('--'):
+                arg = arg.strip('-').strip()
+                vals = arg.split('=', 1)
+                if len(vals) != 2:
+                    if len(vals) > 2: # --extended is a valid argument
+                        get_logger().error(f'Invalid argument format: {arg}')
+                    other_args.append(arg)
+                    continue
+                key, value = _fix_key_value(*vals)
+                get_settings().set(key, value)
+                get_logger().info(f'Updated setting {key} to: "{value}"')
+            else:
+                other_args.append(arg)
+    return other_args
+
+
+def _fix_key_value(key: str, value: str):
+    key = key.strip().upper()
+    value = value.strip()
+    try:
+        value = yaml.safe_load(value)
+    except Exception as e:
+        get_logger().debug(f"Failed to parse YAML for config override {key}={value}", exc_info=e)
+    return key, value
+
+
+def load_yaml(response_text: str, keys_fix_yaml: List[str] = []) -> dict:
+    response_text = response_text.removeprefix('```yaml').rstrip('`')
+    try:
+        data = yaml.safe_load(response_text)
+    except Exception as e:
+        get_logger().error(f"Failed to parse AI prediction: {e}")
+        data = try_fix_yaml(response_text, keys_fix_yaml=keys_fix_yaml)
+    return data
+
+
+def try_fix_yaml(response_text: str, keys_fix_yaml: List[str] = []) -> dict:
+    response_text_lines = response_text.split('\n')
+
+    keys = ['relevant line:', 'suggestion content:', 'relevant file:', 'existing code:', 'improved code:']
+    keys = keys + keys_fix_yaml
+    # first fallback - try to convert 'relevant line: ...' to relevant line: |-\n        ...'
+    response_text_lines_copy = response_text_lines.copy()
+    for i in range(0, len(response_text_lines_copy)):
+        for key in keys:
+            if key in response_text_lines_copy[i] and not '|-' in response_text_lines_copy[i]:
+                response_text_lines_copy[i] = response_text_lines_copy[i].replace(f'{key}',
+                                                                                  f'{key} |-\n        ')
+    try:
+        data = yaml.safe_load('\n'.join(response_text_lines_copy))
+        get_logger().info(f"Successfully parsed AI prediction after adding |-\n")
+        return data
+    except:
+        get_logger().info(f"Failed to parse AI prediction after adding |-\n")
+
+    # second fallback - try to extract only range from first ```yaml to ````
+    snippet_pattern = r'```(yaml)?[\s\S]*?```'
+    snippet = re.search(snippet_pattern, '\n'.join(response_text_lines_copy))
+    if snippet:
+        snippet_text = snippet.group()
+        try:
+            data = yaml.safe_load(snippet_text.removeprefix('```yaml').rstrip('`'))
+            get_logger().info(f"Successfully parsed AI prediction after extracting yaml snippet")
+            return data
+        except:
+            pass
+
+     # third fallback - try to remove leading and trailing curly brackets
+    response_text_copy = response_text.strip().rstrip().removeprefix('{').removesuffix('}').rstrip(':\n')
+    try:
+        data = yaml.safe_load(response_text_copy)
+        get_logger().info(f"Successfully parsed AI prediction after removing curly brackets")
+        return data
+    except:
+        pass
+
+    # fourth fallback - try to remove last lines
+    data = {}
+    for i in range(1, len(response_text_lines)):
+        response_text_lines_tmp = '\n'.join(response_text_lines[:-i])
+        try:
+            data = yaml.safe_load(response_text_lines_tmp)
+            get_logger().info(f"Successfully parsed AI prediction after removing {i} lines")
+            return data
+        except:
+            pass
+
+
+def set_custom_labels(variables, git_provider=None):
+    if not get_settings().config.enable_custom_labels:
+        return
+
+    labels = get_settings().custom_labels
+    if not labels:
+        # set default labels
+        labels = ['Bug fix', 'Tests', 'Bug fix with tests', 'Enhancement', 'Documentation', 'Other']
+        labels_list = "\n      - ".join(labels) if labels else ""
+        labels_list = f"      - {labels_list}" if labels_list else ""
+        variables["custom_labels"] = labels_list
+        return
+
+    # Set custom labels
+    variables["custom_labels_class"] = "class Label(str, Enum):"
+    counter = 0
+    labels_minimal_to_labels_dict = {}
+    for k, v in labels.items():
+        description = "'" + v['description'].strip('\n').replace('\n', '\\n') + "'"
+        # variables["custom_labels_class"] += f"\n    {k.lower().replace(' ', '_')} = '{k}' # {description}"
+        variables["custom_labels_class"] += f"\n    {k.lower().replace(' ', '_')} = {description}"
+        labels_minimal_to_labels_dict[k.lower().replace(' ', '_')] = k
+        counter += 1
+    variables["labels_minimal_to_labels_dict"] = labels_minimal_to_labels_dict
+
+def get_user_labels(current_labels: List[str] = None):
+    """
+    Only keep labels that has been added by the user
+    """
+    try:
+        if current_labels is None:
+            current_labels = []
+        user_labels = []
+        for label in current_labels:
+            if label.lower() in ['bug fix', 'tests', 'enhancement', 'documentation', 'other']:
+                continue
+            if get_settings().config.enable_custom_labels:
+                if label in get_settings().custom_labels:
+                    continue
+            user_labels.append(label)
+        if user_labels:
+            get_logger().debug(f"Keeping user labels: {user_labels}")
+    except Exception as e:
+        get_logger().exception(f"Failed to get user labels: {e}")
+        return current_labels
+    return user_labels
+
+
+def get_max_tokens(model):
+    settings = get_settings()
+    if model in MAX_TOKENS:
+        max_tokens_model = MAX_TOKENS[model]
+    else:
+        raise Exception(f"MAX_TOKENS must be set for model {model} in ./pr_agent/algo/__init__.py")
+
+    if settings.config.max_model_tokens:
+        max_tokens_model = min(settings.config.max_model_tokens, max_tokens_model)
+        # get_logger().debug(f"limiting max tokens to {max_tokens_model}")
+    return max_tokens_model
+
+
+def clip_tokens(text: str, max_tokens: int, add_three_dots=True) -> str:
+    """
+    Clip the number of tokens in a string to a maximum number of tokens.
+
+    Args:
+        text (str): The string to clip.
+        max_tokens (int): The maximum number of tokens allowed in the string.
+        add_three_dots (bool, optional): A boolean indicating whether to add three dots at the end of the clipped
+    Returns:
+        str: The clipped string.
+    """
+    if not text:
+        return text
+
+    try:
+        encoder = get_token_encoder()
+        num_input_tokens = len(encoder.encode(text))
+        if num_input_tokens <= max_tokens:
+            return text
+        num_chars = len(text)
+        chars_per_token = num_chars / num_input_tokens
+        num_output_chars = int(chars_per_token * max_tokens)
+        clipped_text = text[:num_output_chars]
+        if add_three_dots:
+            clipped_text += "...(truncated)"
+        return clipped_text
+    except Exception as e:
+        get_logger().warning(f"Failed to clip tokens: {e}")
+        return text
+
+def replace_code_tags(text):
+    """
+    Replace odd instances of ` with <code> and even instances of ` with </code>
+    """
+    parts = text.split('`')
+    for i in range(1, len(parts), 2):
+        parts[i] = '<code>' + parts[i] + '</code>'
+    return ''.join(parts)
+
+
+def find_line_number_of_relevant_line_in_file(diff_files: List[FilePatchInfo],
+                                              relevant_file: str,
+                                              relevant_line_in_file: str,
+                                              absolute_position: int = None) -> Tuple[int, int]:
+    position = -1
+    if absolute_position is None:
+        absolute_position = -1
+    re_hunk_header = re.compile(
+        r"^@@ -(\d+)(?:,(\d+))? \+(\d+)(?:,(\d+))? @@[ ]?(.*)")
+
+    for file in diff_files:
+        if file.filename and (file.filename.strip() == relevant_file):
+            patch = file.patch
+            patch_lines = patch.splitlines()
+            delta = 0
+            start1, size1, start2, size2 = 0, 0, 0, 0
+            if absolute_position != -1: # matching absolute to relative
+                for i, line in enumerate(patch_lines):
+                    # new hunk
+                    if line.startswith('@@'):
+                        delta = 0
+                        match = re_hunk_header.match(line)
+                        start1, size1, start2, size2 = map(int, match.groups()[:4])
+                    elif not line.startswith('-'):
+                        delta += 1
+
+                    #
+                    absolute_position_curr = start2 + delta - 1
+
+                    if absolute_position_curr == absolute_position:
+                        position = i
+                        break
+            else:
+                # try to find the line in the patch using difflib, with some margin of error
+                matches_difflib: list[str | Any] = difflib.get_close_matches(relevant_line_in_file,
+                                                                             patch_lines, n=3, cutoff=0.93)
+                if len(matches_difflib) == 1 and matches_difflib[0].startswith('+'):
+                    relevant_line_in_file = matches_difflib[0]
+
+
+                for i, line in enumerate(patch_lines):
+                    if line.startswith('@@'):
+                        delta = 0
+                        match = re_hunk_header.match(line)
+                        start1, size1, start2, size2 = map(int, match.groups()[:4])
+                    elif not line.startswith('-'):
+                        delta += 1
+
+                    if relevant_line_in_file in line and line[0] != '-':
+                        position = i
+                        absolute_position = start2 + delta - 1
+                        break
+
+                if position == -1 and relevant_line_in_file[0] == '+':
+                    no_plus_line = relevant_line_in_file[1:].lstrip()
+                    for i, line in enumerate(patch_lines):
+                        if line.startswith('@@'):
+                            delta = 0
+                            match = re_hunk_header.match(line)
+                            start1, size1, start2, size2 = map(int, match.groups()[:4])
+                        elif not line.startswith('-'):
+                            delta += 1
+
+                        if no_plus_line in line and line[0] != '-':
+                            # The model might add a '+' to the beginning of the relevant_line_in_file even if originally
+                            # it's a context line
+                            position = i
+                            absolute_position = start2 + delta - 1
+                            break
+    return position, absolute_position

pr_agent/cli.py

@@ -1,56 +1,67 @@
 import argparse
 import asyncio
-import logging
 import os
 
-from pr_agent.tools.pr_code_suggestions import PRCodeSuggestions
-from pr_agent.tools.pr_description import PRDescription
-from pr_agent.tools.pr_questions import PRQuestions
-from pr_agent.tools.pr_reviewer import PRReviewer
+from pr_agent.agent.pr_agent import PRAgent, commands
+from pr_agent.config_loader import get_settings
+from pr_agent.log import setup_logger
+
+log_level = os.environ.get("LOG_LEVEL", "INFO")
+setup_logger(log_level)
 
 
-def run():
-    parser = argparse.ArgumentParser(description='AI based pull request analyzer', usage="""\
-Usage: cli.py --pr-url <URL on supported git hosting service> <command> [<args>].
+
+def run(inargs=None):
+    parser = argparse.ArgumentParser(description='AI based pull request analyzer', usage=
+"""\
+Usage: cli.py --pr-url=<URL on supported git hosting service> <command> [<args>].
+For example:
+- cli.py --pr_url=... review
+- cli.py --pr_url=... describe
+- cli.py --pr_url=... improve
+- cli.py --pr_url=... ask "write me a poem about this PR"
+- cli.py --pr_url=... reflect
+- cli.py --issue_url=... similar_issue
 
 Supported commands:
-review / review_pr - Add a review that includes a summary of the PR and specific suggestions for improvement.
-ask / ask_question [question] - Ask a question about the PR.
-describe / describe_pr - Modify the PR title and description based on the PR's contents.
-improve / improve_code - Suggest improvements to the code in the PR as pull request comments ready to commit.
+- review / review_pr - Add a review that includes a summary of the PR and specific suggestions for improvement.
+
+- ask / ask_question [question] - Ask a question about the PR.
+
+- describe / describe_pr - Modify the PR title and description based on the PR's contents.
+
+- improve / improve_code - Suggest improvements to the code in the PR as pull request comments ready to commit.
+Extended mode ('improve --extended') employs several calls, and provides a more thorough feedback
+
+- reflect - Ask the PR author questions about the PR.
+
+- update_changelog - Update the changelog based on the PR's contents.
+
+- add_docs
+
+- generate_labels
+
+
+Configuration:
+To edit any configuration parameter from 'configuration.toml', just add -config_path=<value>.
+For example: 'python cli.py --pr_url=... review --pr_reviewer.extra_instructions="focus on the file: ..."'
 """)
-    parser.add_argument('--pr_url', type=str, help='The URL of the PR to review', required=True)
-    parser.add_argument('command', type=str, help='The', choices=['review', 'review_pr',
-                                                                  'ask', 'ask_question',
-                                                                  'describe', 'describe_pr',
-                                                                  'improve', 'improve_code'], default='review')
+    parser.add_argument('--pr_url', type=str, help='The URL of the PR to review', default=None)
+    parser.add_argument('--issue_url', type=str, help='The URL of the Issue to review', default=None)
+    parser.add_argument('command', type=str, help='The', choices=commands, default='review')
     parser.add_argument('rest', nargs=argparse.REMAINDER, default=[])
-    args = parser.parse_args()
-    logging.basicConfig(level=os.environ.get("LOGLEVEL", "INFO"))
+    args = parser.parse_args(inargs)
+    if not args.pr_url and not args.issue_url:
+        parser.print_help()
+        return
+
     command = args.command.lower()
-    if command in ['ask', 'ask_question']:
-        question = ' '.join(args.rest).strip()
-        if len(question) == 0:
-            print("Please specify a question")
-            parser.print_help()
-            return
-        print(f"Question: {question} about PR {args.pr_url}")
-        reviewer = PRQuestions(args.pr_url, question)
-        asyncio.run(reviewer.answer())
-    elif command in ['describe', 'describe_pr']:
-        print(f"PR description: {args.pr_url}")
-        reviewer = PRDescription(args.pr_url)
-        asyncio.run(reviewer.describe())
-    elif command in ['improve', 'improve_code']:
-        print(f"PR code suggestions: {args.pr_url}")
-        reviewer = PRCodeSuggestions(args.pr_url)
-        asyncio.run(reviewer.suggest())
-    elif command in ['review', 'review_pr']:
-        print(f"Reviewing PR: {args.pr_url}")
-        reviewer = PRReviewer(args.pr_url, cli_mode=True)
-        asyncio.run(reviewer.review())
+    get_settings().set("CONFIG.CLI_MODE", True)
+    if args.issue_url:
+        result = asyncio.run(PRAgent().handle_request(args.issue_url, [command] + args.rest))
     else:
-        print(f"Unknown command: {command}")
+        result = asyncio.run(PRAgent().handle_request(args.pr_url, [command] + args.rest))
+    if not result:
         parser.print_help()
 
 

pr_agent/config_loader.py

@@ -1,18 +1,70 @@
 from os.path import abspath, dirname, join
+from pathlib import Path
+from typing import Optional
 
 from dynaconf import Dynaconf
+from starlette_context import context
+
+PR_AGENT_TOML_KEY = 'pr-agent'
 
 current_dir = dirname(abspath(__file__))
-settings = Dynaconf(
+global_settings = Dynaconf(
     envvar_prefix=False,
     merge_enabled=True,
     settings_files=[join(current_dir, f) for f in [
-         "settings/.secrets.toml",
-         "settings/configuration.toml",
-         "settings/pr_reviewer_prompts.toml",
-         "settings/pr_questions_prompts.toml",
-         "settings/pr_description_prompts.toml",
-         "settings/pr_code_suggestions_prompts.toml",
-         "settings_prod/.secrets.toml"
-        ]]
+        "settings/.secrets.toml",
+        "settings/configuration.toml",
+        "settings/ignore.toml",
+        "settings/language_extensions.toml",
+        "settings/pr_reviewer_prompts.toml",
+        "settings/pr_questions_prompts.toml",
+        "settings/pr_line_questions_prompts.toml",
+        "settings/pr_description_prompts.toml",
+        "settings/pr_code_suggestions_prompts.toml",
+        "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/custom_labels.toml"
+    ]]
 )
+
+
+def get_settings():
+    try:
+        return context["settings"]
+    except Exception:
+        return global_settings
+
+
+# Add local configuration from pyproject.toml of the project being reviewed
+def _find_repository_root() -> Path:
+    """
+    Identify project root directory by recursively searching for the .git directory in the parent directories.
+    """
+    cwd = Path.cwd().resolve()
+    no_way_up = False
+    while not no_way_up:
+        no_way_up = cwd == cwd.parent
+        if (cwd / ".git").is_dir():
+            return cwd
+        cwd = cwd.parent
+    return None
+
+
+def _find_pyproject() -> Optional[Path]:
+    """
+    Search for file pyproject.toml in the repository root.
+    """
+    repo_root = _find_repository_root()
+    if repo_root:
+        pyproject = _find_repository_root() / "pyproject.toml"
+        return pyproject if pyproject.is_file() else None
+    return None
+
+
+pyproject_path = _find_pyproject()
+if pyproject_path is not None:
+    get_settings().load_file(pyproject_path, env=f'tool.{PR_AGENT_TOML_KEY}')

pr_agent/git_providers/__init__.py

@@ -1,15 +1,28 @@
-from pr_agent.config_loader import settings
+from pr_agent.config_loader import get_settings
+from pr_agent.git_providers.bitbucket_provider import BitbucketProvider
+from pr_agent.git_providers.bitbucket_server_provider import BitbucketServerProvider
+from pr_agent.git_providers.codecommit_provider import CodeCommitProvider
 from pr_agent.git_providers.github_provider import GithubProvider
 from pr_agent.git_providers.gitlab_provider import GitLabProvider
+from pr_agent.git_providers.local_git_provider import LocalGitProvider
+from pr_agent.git_providers.azuredevops_provider import AzureDevopsProvider
+from pr_agent.git_providers.gerrit_provider import GerritProvider
+
 
 _GIT_PROVIDERS = {
     'github': GithubProvider,
     'gitlab': GitLabProvider,
+    'bitbucket': BitbucketProvider,
+    'bitbucket_server': BitbucketServerProvider,
+    'azure': AzureDevopsProvider,
+    'codecommit': CodeCommitProvider,
+    'local' : LocalGitProvider,
+    'gerrit': GerritProvider,
 }
 
 def get_git_provider():
     try:
-        provider_id = settings.config.git_provider
+        provider_id = get_settings().config.git_provider
     except AttributeError as e:
         raise ValueError("git_provider is a required attribute in the configuration file") from e
     if provider_id not in _GIT_PROVIDERS:

pr_agent/git_providers/azuredevops_provider.py

@@ -0,0 +1,566 @@
+import os
+from typing import Optional, Tuple
+from urllib.parse import urlparse
+
+from ..log import get_logger
+from ..algo.language_handler import is_valid_file
+from ..algo.utils import clip_tokens, find_line_number_of_relevant_line_in_file, load_large_diff
+from ..config_loader import get_settings
+from .git_provider import GitProvider
+from pr_agent.algo.types import EDIT_TYPE, FilePatchInfo
+
+AZURE_DEVOPS_AVAILABLE = True
+ADO_APP_CLIENT_DEFAULT_ID = "499b84ac-1321-427f-aa17-267ca6975798/.default"
+MAX_PR_DESCRIPTION_AZURE_LENGTH = 4000-1
+
+try:
+    # noinspection PyUnresolvedReferences
+    from msrest.authentication import BasicAuthentication
+    # noinspection PyUnresolvedReferences
+    from azure.devops.connection import Connection
+    # noinspection PyUnresolvedReferences
+    from azure.identity import DefaultAzureCredential
+    # noinspection PyUnresolvedReferences
+    from azure.devops.v7_1.git.models import (
+        Comment,
+        CommentThread,
+        GitVersionDescriptor,
+        GitPullRequest,
+    )
+except ImportError:
+    AZURE_DEVOPS_AVAILABLE = False
+
+
+class AzureDevopsProvider(GitProvider):
+
+    def __init__(
+            self, pr_url: Optional[str] = None, incremental: Optional[bool] = False
+    ):
+        if not AZURE_DEVOPS_AVAILABLE:
+            raise ImportError(
+                "Azure DevOps provider is not available. Please install the required dependencies."
+            )
+
+        self.azure_devops_client = self._get_azure_devops_client()
+        self.diff_files = None
+        self.workspace_slug = None
+        self.repo_slug = None
+        self.repo = None
+        self.pr_num = None
+        self.pr = None
+        self.temp_comments = []
+        self.incremental = incremental
+        if pr_url:
+            self.set_pr(pr_url)
+
+    def publish_code_suggestions(self, code_suggestions: list) -> bool:
+        """
+        Publishes code suggestions as comments on the PR.
+        """
+        post_parameters_list = []
+        for suggestion in code_suggestions:
+            body = suggestion['body']
+            relevant_file = suggestion['relevant_file']
+            relevant_lines_start = suggestion['relevant_lines_start']
+            relevant_lines_end = suggestion['relevant_lines_end']
+
+            if not relevant_lines_start or relevant_lines_start == -1:
+                if get_settings().config.verbosity_level >= 2:
+                    get_logger().exception(
+                        f"Failed to publish code suggestion, relevant_lines_start is {relevant_lines_start}")
+                continue
+
+            if relevant_lines_end < relevant_lines_start:
+                if get_settings().config.verbosity_level >= 2:
+                    get_logger().exception(f"Failed to publish code suggestion, "
+                                           f"relevant_lines_end is {relevant_lines_end} and "
+                                           f"relevant_lines_start is {relevant_lines_start}")
+                continue
+
+            if relevant_lines_end > relevant_lines_start:
+                post_parameters = {
+                    "body": body,
+                    "path": relevant_file,
+                    "line": relevant_lines_end,
+                    "start_line": relevant_lines_start,
+                    "start_side": "RIGHT",
+                }
+            else:  # API is different for single line comments
+                post_parameters = {
+                    "body": body,
+                    "path": relevant_file,
+                    "line": relevant_lines_start,
+                    "side": "RIGHT",
+                }
+            post_parameters_list.append(post_parameters)
+
+        try:
+            for post_parameters in post_parameters_list:
+                comment = Comment(content=post_parameters["body"], comment_type=1)
+                thread = CommentThread(comments=[comment],
+                                       thread_context={
+                                           "filePath": post_parameters["path"],
+                                           "rightFileStart": {
+                                               "line": post_parameters["start_line"],
+                                               "offset": 1,
+                                           },
+                                           "rightFileEnd": {
+                                               "line": post_parameters["line"],
+                                               "offset": 1,
+                                           },
+                                       })
+                self.azure_devops_client.create_thread(
+                    comment_thread=thread,
+                    project=self.workspace_slug,
+                    repository_id=self.repo_slug,
+                    pull_request_id=self.pr_num
+                )
+                if get_settings().config.verbosity_level >= 2:
+                    get_logger().info(
+                        f"Published code suggestion on {self.pr_num} at {post_parameters['path']}"
+                    )
+            return True
+        except Exception as e:
+            if get_settings().config.verbosity_level >= 2:
+                get_logger().error(f"Failed to publish code suggestion, error: {e}")
+            return False
+
+    def get_pr_description_full(self) -> str:
+        return self.pr.description
+
+    def edit_comment(self, comment, body: str):
+        try:
+            self.azure_devops_client.update_comment(
+                repository_id=self.repo_slug,
+                pull_request_id=self.pr_num,
+                thread_id=comment["thread_id"],
+                comment_id=comment["comment_id"],
+                comment=Comment(content=body),
+                project=self.workspace_slug,
+            )
+        except Exception as e:
+            get_logger().exception(f"Failed to edit comment, error: {e}")
+
+    def remove_comment(self, comment):
+        try:
+            self.azure_devops_client.delete_comment(
+                repository_id=self.repo_slug,
+                pull_request_id=self.pr_num,
+                thread_id=comment["thread_id"],
+                comment_id=comment["comment_id"],
+                project=self.workspace_slug,
+            )
+        except Exception as e:
+            get_logger().exception(f"Failed to remove comment, error: {e}")
+
+    def publish_labels(self, pr_types):
+        try:
+            for pr_type in pr_types:
+                self.azure_devops_client.create_pull_request_label(
+                    label={"name": pr_type},
+                    project=self.workspace_slug,
+                    repository_id=self.repo_slug,
+                    pull_request_id=self.pr_num,
+                )
+        except Exception as e:
+            get_logger().exception(f"Failed to publish labels, error: {e}")
+
+    def get_pr_labels(self):
+        try:
+            labels = self.azure_devops_client.get_pull_request_labels(
+                project=self.workspace_slug,
+                repository_id=self.repo_slug,
+                pull_request_id=self.pr_num,
+            )
+            return [label.name for label in labels]
+        except Exception as e:
+            get_logger().exception(f"Failed to get labels, error: {e}")
+            return []
+
+    def is_supported(self, capability: str) -> bool:
+        if capability in [
+            "get_issue_comments",
+        ]:
+            return False
+        return True
+
+    def set_pr(self, pr_url: str):
+        self.workspace_slug, self.repo_slug, self.pr_num = self._parse_pr_url(pr_url)
+        self.pr = self._get_pr()
+
+    def get_repo_settings(self):
+        try:
+            contents = self.azure_devops_client.get_item_content(
+                repository_id=self.repo_slug,
+                project=self.workspace_slug,
+                download=False,
+                include_content_metadata=False,
+                include_content=True,
+                path=".pr_agent.toml",
+            )
+            return list(contents)[0]
+        except Exception as e:
+            if get_settings().config.verbosity_level >= 2:
+                get_logger().error(f"Failed to get repo settings, error: {e}")
+            return ""
+
+    def get_files(self):
+        files = []
+        for i in self.azure_devops_client.get_pull_request_commits(
+                project=self.workspace_slug,
+                repository_id=self.repo_slug,
+                pull_request_id=self.pr_num,
+        ):
+            changes_obj = self.azure_devops_client.get_changes(
+                project=self.workspace_slug,
+                repository_id=self.repo_slug,
+                commit_id=i.commit_id,
+            )
+
+            for c in changes_obj.changes:
+                files.append(c["item"]["path"])
+        return list(set(files))
+
+    def get_diff_files(self) -> list[FilePatchInfo]:
+        try:
+
+            if self.diff_files:
+                return self.diff_files
+
+            base_sha = self.pr.last_merge_target_commit
+            head_sha = self.pr.last_merge_source_commit
+
+            commits = self.azure_devops_client.get_pull_request_commits(
+                project=self.workspace_slug,
+                repository_id=self.repo_slug,
+                pull_request_id=self.pr_num,
+            )
+
+            diff_files = []
+            diffs = []
+            diff_types = {}
+
+            for c in commits:
+                changes_obj = self.azure_devops_client.get_changes(
+                    project=self.workspace_slug,
+                    repository_id=self.repo_slug,
+                    commit_id=c.commit_id,
+                )
+                for i in changes_obj.changes:
+                    if i["item"]["gitObjectType"] == "tree":
+                        continue
+                    diffs.append(i["item"]["path"])
+                    diff_types[i["item"]["path"]] = i["changeType"]
+
+            diffs = list(set(diffs))
+
+            for file in diffs:
+                if not is_valid_file(file):
+                    continue
+
+                version = GitVersionDescriptor(
+                    version=head_sha.commit_id, version_type="commit"
+                )
+                try:
+                    new_file_content_str = self.azure_devops_client.get_item(
+                        repository_id=self.repo_slug,
+                        path=file,
+                        project=self.workspace_slug,
+                        version_descriptor=version,
+                        download=False,
+                        include_content=True,
+                    )
+
+                    new_file_content_str = new_file_content_str.content
+                except Exception as error:
+                    get_logger().error(
+                        "Failed to retrieve new file content of %s at version %s. Error: %s",
+                        file,
+                        version,
+                        str(error),
+                    )
+                    new_file_content_str = ""
+
+                edit_type = EDIT_TYPE.MODIFIED
+                if diff_types[file] == "add":
+                    edit_type = EDIT_TYPE.ADDED
+                elif diff_types[file] == "delete":
+                    edit_type = EDIT_TYPE.DELETED
+                elif diff_types[file] == "rename":
+                    edit_type = EDIT_TYPE.RENAMED
+
+                version = GitVersionDescriptor(
+                    version=base_sha.commit_id, version_type="commit"
+                )
+                try:
+                    original_file_content_str = self.azure_devops_client.get_item(
+                        repository_id=self.repo_slug,
+                        path=file,
+                        project=self.workspace_slug,
+                        version_descriptor=version,
+                        download=False,
+                        include_content=True,
+                    )
+                    original_file_content_str = original_file_content_str.content
+                except Exception as error:
+                    get_logger().error(
+                        "Failed to retrieve original file content of %s at version %s. Error: %s",
+                        file,
+                        version,
+                        str(error),
+                    )
+                    original_file_content_str = ""
+
+                patch = load_large_diff(
+                    file, new_file_content_str, original_file_content_str
+                )
+
+                diff_files.append(
+                    FilePatchInfo(
+                        original_file_content_str,
+                        new_file_content_str,
+                        patch=patch,
+                        filename=file,
+                        edit_type=edit_type,
+                    )
+                )
+            self.diff_files = diff_files
+            return diff_files
+        except Exception as e:
+            print(f"Error: {str(e)}")
+            return []
+
+    def publish_comment(self, pr_comment: str, is_temporary: bool = False, thread_context=None):
+        comment = Comment(content=pr_comment)
+        thread = CommentThread(comments=[comment], thread_context=thread_context, status=1)
+        thread_response = self.azure_devops_client.create_thread(
+            comment_thread=thread,
+            project=self.workspace_slug,
+            repository_id=self.repo_slug,
+            pull_request_id=self.pr_num,
+        )
+        response = {"thread_id": thread_response.id, "comment_id": thread_response.comments[0].id}
+        if is_temporary:
+            self.temp_comments.append(response)
+        return response
+
+    def publish_description(self, pr_title: str, pr_body: str):
+        if len(pr_body) > MAX_PR_DESCRIPTION_AZURE_LENGTH:
+
+            usage_guide_text='<details> <summary><strong>✨ Describe tool usage guide:</strong></summary><hr>'
+            ind = pr_body.find(usage_guide_text)
+            if ind != -1:
+                pr_body = pr_body[:ind]
+
+            if len(pr_body) > MAX_PR_DESCRIPTION_AZURE_LENGTH:
+                changes_walkthrough_text = '## **Changes walkthrough**'
+                ind = pr_body.find(changes_walkthrough_text)
+                if ind != -1:
+                    pr_body = pr_body[:ind]
+
+            if len(pr_body) > MAX_PR_DESCRIPTION_AZURE_LENGTH:
+                trunction_message = " ... (description truncated due to length limit)"
+                pr_body = pr_body[:MAX_PR_DESCRIPTION_AZURE_LENGTH - len(trunction_message)] + trunction_message
+                get_logger().warning("PR description was truncated due to length limit")
+        try:
+            updated_pr = GitPullRequest()
+            updated_pr.title = pr_title
+            updated_pr.description = pr_body
+            self.azure_devops_client.update_pull_request(
+                project=self.workspace_slug,
+                repository_id=self.repo_slug,
+                pull_request_id=self.pr_num,
+                git_pull_request_to_update=updated_pr,
+            )
+        except Exception as e:
+            get_logger().exception(
+                f"Could not update pull request {self.pr_num} description: {e}"
+            )
+
+    def remove_initial_comment(self):
+        try:
+            for comment in self.temp_comments:
+                self.remove_comment(comment)
+        except Exception as e:
+            get_logger().exception(f"Failed to remove temp comments, error: {e}")
+
+    def publish_inline_comment(self, body: str, relevant_file: str, relevant_line_in_file: str):
+        self.publish_inline_comments([self.create_inline_comment(body, relevant_file, relevant_line_in_file)])
+
+
+    def create_inline_comment(self, body: str, relevant_file: str, relevant_line_in_file: str,
+                              absolute_position: int = None):
+        position, absolute_position = find_line_number_of_relevant_line_in_file(self.get_diff_files(),
+                                                                                relevant_file.strip('`'),
+                                                                                relevant_line_in_file,
+                                                                                absolute_position)
+        if position == -1:
+            if get_settings().config.verbosity_level >= 2:
+                get_logger().info(f"Could not find position for {relevant_file} {relevant_line_in_file}")
+            subject_type = "FILE"
+        else:
+            subject_type = "LINE"
+        path = relevant_file.strip()
+        return dict(body=body, path=path, position=position, absolute_position=absolute_position) if subject_type == "LINE" else {}
+
+    def publish_inline_comments(self, comments: list[dict], disable_fallback: bool = False):
+            overall_sucess = True
+            for comment in comments:
+                try:
+                    self.publish_comment(comment["body"],
+                                        thread_context={
+                                            "filePath": comment["path"],
+                                            "rightFileStart": {
+                                                "line": comment["absolute_position"],
+                                                "offset": comment["position"],
+                                            },
+                                            "rightFileEnd": {
+                                                "line": comment["absolute_position"],
+                                                "offset": comment["position"],
+                                            },
+                                        })
+                    if get_settings().config.verbosity_level >= 2:
+                        get_logger().info(
+                            f"Published code suggestion on {self.pr_num} at {comment['path']}"
+                        )
+                except Exception as e:
+                    if get_settings().config.verbosity_level >= 2:
+                        get_logger().error(f"Failed to publish code suggestion, error: {e}")
+                    overall_sucess = False
+            return overall_sucess
+
+    def get_title(self):
+        return self.pr.title
+
+    def get_languages(self):
+        languages = []
+        files = self.azure_devops_client.get_items(
+            project=self.workspace_slug,
+            repository_id=self.repo_slug,
+            recursion_level="Full",
+            include_content_metadata=True,
+            include_links=False,
+            download=False,
+        )
+        for f in files:
+            if f.git_object_type == "blob":
+                file_name, file_extension = os.path.splitext(f.path)
+                languages.append(file_extension[1:])
+
+        extension_counts = {}
+        for ext in languages:
+            if ext != "":
+                extension_counts[ext] = extension_counts.get(ext, 0) + 1
+
+        total_extensions = sum(extension_counts.values())
+
+        extension_percentages = {
+            ext: (count / total_extensions) * 100
+            for ext, count in extension_counts.items()
+        }
+
+        return extension_percentages
+
+    def get_pr_branch(self):
+        pr_info = self.azure_devops_client.get_pull_request_by_id(
+            project=self.workspace_slug, pull_request_id=self.pr_num
+        )
+        source_branch = pr_info.source_ref_name.split("/")[-1]
+        return source_branch
+
+    def get_pr_description(self, *, full: bool = True) -> str:
+        max_tokens = get_settings().get("CONFIG.MAX_DESCRIPTION_TOKENS", None)
+        if max_tokens:
+            return clip_tokens(self.pr.description, max_tokens)
+        return self.pr.description
+
+    def get_user_id(self):
+        return 0
+
+    def get_issue_comments(self):
+        raise NotImplementedError(
+            "Azure DevOps provider does not support issue comments yet"
+        )
+
+    def add_eyes_reaction(self, issue_comment_id: int, disable_eyes: bool = False) -> Optional[int]:
+        return True
+
+    def remove_reaction(self, issue_comment_id: int, reaction_id: int) -> bool:
+        return True
+
+    @staticmethod
+    def _parse_pr_url(pr_url: str) -> Tuple[str, str, int]:
+        parsed_url = urlparse(pr_url)
+
+        path_parts = parsed_url.path.strip("/").split("/")
+
+        if len(path_parts) < 6 or path_parts[4] != "pullrequest":
+            raise ValueError(
+                "The provided URL does not appear to be a Azure DevOps PR URL"
+            )
+
+        workspace_slug = path_parts[1]
+        repo_slug = path_parts[3]
+        try:
+            pr_number = int(path_parts[5])
+        except ValueError as e:
+            raise ValueError("Unable to convert PR number to integer") from e
+
+        return workspace_slug, repo_slug, pr_number
+
+    @staticmethod
+    def _get_azure_devops_client():
+        org = get_settings().azure_devops.get("org", None)
+        pat = get_settings().azure_devops.get("pat", None)
+
+        if not org:
+            raise ValueError("Azure DevOps organization is required")
+
+        if pat:
+            auth_token = pat
+        else:
+            try:
+                # try to use azure default credentials
+                # see https://learn.microsoft.com/en-us/python/api/overview/azure/identity-readme?view=azure-python
+                # for usage and env var configuration of user-assigned managed identity, local machine auth etc.
+                get_logger().info("No PAT found in settings, trying to use Azure Default Credentials.")
+                credentials = DefaultAzureCredential()
+                accessToken = credentials.get_token(ADO_APP_CLIENT_DEFAULT_ID)
+                auth_token = accessToken.token
+            except Exception as e:
+                get_logger().error(f"No PAT found in settings, and Azure Default Authentication failed, error: {e}")
+                raise
+
+        credentials = BasicAuthentication("", auth_token)
+
+        credentials = BasicAuthentication("", auth_token)
+        azure_devops_connection = Connection(base_url=org, creds=credentials)
+        azure_devops_client = azure_devops_connection.clients.get_git_client()
+
+        return azure_devops_client
+
+    def _get_repo(self):
+        if self.repo is None:
+            self.repo = self.azure_devops_client.get_repository(
+                project=self.workspace_slug, repository_id=self.repo_slug
+            )
+        return self.repo
+
+    def _get_pr(self):
+        self.pr = self.azure_devops_client.get_pull_request_by_id(
+            pull_request_id=self.pr_num, project=self.workspace_slug
+        )
+        return self.pr
+
+    def get_commit_messages(self):
+        return ""  # not implemented yet
+
+    def get_pr_id(self):
+        try:
+            pr_id = f"{self.workspace_slug}/{self.repo_slug}/{self.pr_num}"
+            return pr_id
+        except Exception as e:
+            if get_settings().config.verbosity_level >= 2:
+                get_logger().error(f"Failed to get pr id, error: {e}")
+            return ""
+

pr_agent/git_providers/bitbucket_provider.py

@@ -0,0 +1,368 @@
+import json
+from typing import Optional, Tuple
+from urllib.parse import urlparse
+
+import requests
+from atlassian.bitbucket import Cloud
+from starlette_context import context
+
+from pr_agent.algo.types import FilePatchInfo, EDIT_TYPE
+from ..algo.utils import find_line_number_of_relevant_line_in_file
+from ..config_loader import get_settings
+from ..log import get_logger
+from .git_provider import GitProvider
+
+
+class BitbucketProvider(GitProvider):
+    def __init__(
+        self, pr_url: Optional[str] = None, incremental: Optional[bool] = False
+    ):
+        s = requests.Session()
+        try:
+            bearer = context.get("bitbucket_bearer_token", None)
+            s.headers["Authorization"] = f"Bearer {bearer}"
+        except Exception:
+            s.headers[
+                "Authorization"
+            ] = f'Bearer {get_settings().get("BITBUCKET.BEARER_TOKEN", None)}'
+        s.headers["Content-Type"] = "application/json"
+        self.headers = s.headers
+        self.bitbucket_client = Cloud(session=s)
+        self.workspace_slug = None
+        self.repo_slug = None
+        self.repo = None
+        self.pr_num = None
+        self.pr = None
+        self.pr_url = pr_url
+        self.temp_comments = []
+        self.incremental = incremental
+        self.diff_files = None
+        if pr_url:
+            self.set_pr(pr_url)
+        self.bitbucket_comment_api_url = self.pr._BitbucketBase__data["links"]["comments"]["href"]
+        self.bitbucket_pull_request_api_url = self.pr._BitbucketBase__data["links"]['self']['href']
+
+    def get_repo_settings(self):
+        try:
+            url = (f"https://api.bitbucket.org/2.0/repositories/{self.workspace_slug}/{self.repo_slug}/src/"
+                   f"{self.pr.destination_branch}/.pr_agent.toml")
+            response = requests.request("GET", url, headers=self.headers)
+            if response.status_code == 404:  # not found
+                return ""
+            contents = response.text.encode('utf-8')
+            return contents
+        except Exception:
+            return ""
+
+    def publish_code_suggestions(self, code_suggestions: list) -> bool:
+        """
+        Publishes code suggestions as comments on the PR.
+        """
+        post_parameters_list = []
+        for suggestion in code_suggestions:
+            body = suggestion["body"]
+            relevant_file = suggestion["relevant_file"]
+            relevant_lines_start = suggestion["relevant_lines_start"]
+            relevant_lines_end = suggestion["relevant_lines_end"]
+
+            if not relevant_lines_start or relevant_lines_start == -1:
+                if get_settings().config.verbosity_level >= 2:
+                    get_logger().exception(
+                        f"Failed to publish code suggestion, relevant_lines_start is {relevant_lines_start}"
+                    )
+                continue
+
+            if relevant_lines_end < relevant_lines_start:
+                if get_settings().config.verbosity_level >= 2:
+                    get_logger().exception(
+                        f"Failed to publish code suggestion, "
+                        f"relevant_lines_end is {relevant_lines_end} and "
+                        f"relevant_lines_start is {relevant_lines_start}"
+                    )
+                continue
+
+            if relevant_lines_end > relevant_lines_start:
+                post_parameters = {
+                    "body": body,
+                    "path": relevant_file,
+                    "line": relevant_lines_end,
+                    "start_line": relevant_lines_start,
+                    "start_side": "RIGHT",
+                }
+            else:  # API is different for single line comments
+                post_parameters = {
+                    "body": body,
+                    "path": relevant_file,
+                    "line": relevant_lines_start,
+                    "side": "RIGHT",
+                }
+            post_parameters_list.append(post_parameters)
+
+        try:
+            self.publish_inline_comments(post_parameters_list)
+            return True
+        except Exception as e:
+            if get_settings().config.verbosity_level >= 2:
+                get_logger().error(f"Failed to publish code suggestion, error: {e}")
+            return False
+
+    def is_supported(self, capability: str) -> bool:
+        if capability in ['get_issue_comments', 'publish_inline_comments', 'get_labels', 'gfm_markdown']:
+            return False
+        return True
+
+    def set_pr(self, pr_url: str):
+        self.workspace_slug, self.repo_slug, self.pr_num = self._parse_pr_url(pr_url)
+        self.pr = self._get_pr()
+
+    def get_files(self):
+        return [diff.new.path for diff in self.pr.diffstat()]
+
+    def get_diff_files(self) -> list[FilePatchInfo]:
+        if self.diff_files:
+            return self.diff_files
+
+        diffs = self.pr.diffstat()
+        diff_split = [
+            "diff --git%s" % x for x in self.pr.diff().split("diff --git") if x.strip()
+        ]
+
+        diff_files = []
+        for index, diff in enumerate(diffs):
+            original_file_content_str = self._get_pr_file_content(
+                diff.old.get_data("links")
+            )
+            new_file_content_str = self._get_pr_file_content(diff.new.get_data("links"))
+            file_patch_canonic_structure = FilePatchInfo(
+                original_file_content_str,
+                new_file_content_str,
+                diff_split[index],
+                diff.new.path,
+            )
+
+            if diff.data['status'] == 'added':
+                file_patch_canonic_structure.edit_type = EDIT_TYPE.ADDED
+            elif diff.data['status'] == 'removed':
+                file_patch_canonic_structure.edit_type = EDIT_TYPE.DELETED
+            elif diff.data['status'] == 'modified':
+                file_patch_canonic_structure.edit_type = EDIT_TYPE.MODIFIED
+            elif diff.data['status'] == 'renamed':
+                file_patch_canonic_structure.edit_type = EDIT_TYPE.RENAMED
+            diff_files.append(file_patch_canonic_structure)
+
+
+        self.diff_files = diff_files
+        return diff_files
+
+    def get_latest_commit_url(self):
+        return self.pr.data['source']['commit']['links']['html']['href']
+
+    def get_comment_url(self, comment):
+        return comment.data['links']['html']['href']
+
+    def publish_persistent_comment(self, pr_comment: str, initial_header: str, update_header: bool = True, name='review'):
+        try:
+            for comment in self.pr.comments():
+                body = comment.raw
+                if initial_header in body:
+                    latest_commit_url = self.get_latest_commit_url()
+                    comment_url = self.get_comment_url(comment)
+                    if update_header:
+                        updated_header = f"{initial_header}\n\n### ({name.capitalize()} updated until commit {latest_commit_url})\n"
+                        pr_comment_updated = pr_comment.replace(initial_header, updated_header)
+                    else:
+                        pr_comment_updated = pr_comment
+                    get_logger().info(f"Persistent mode - updating comment {comment_url} to latest {name} message")
+                    d = {"content": {"raw": pr_comment_updated}}
+                    response = comment._update_data(comment.put(None, data=d))
+                    self.publish_comment(
+                        f"**[Persistent {name}]({comment_url})** updated to latest commit {latest_commit_url}")
+                    return
+        except Exception as e:
+            get_logger().exception(f"Failed to update persistent review, error: {e}")
+            pass
+        self.publish_comment(pr_comment)
+
+    def publish_comment(self, pr_comment: str, is_temporary: bool = False):
+        comment = self.pr.comment(pr_comment)
+        if is_temporary:
+            self.temp_comments.append(comment["id"])
+        return comment
+
+    def edit_comment(self, comment, body: str):
+        try:
+            comment.update(body)
+        except Exception as e:
+            get_logger().exception(f"Failed to update comment, error: {e}")
+
+    def remove_initial_comment(self):
+        try:
+            for comment in self.temp_comments:
+                self.remove_comment(comment)
+        except Exception as e:
+            get_logger().exception(f"Failed to remove temp comments, error: {e}")
+
+    def remove_comment(self, comment):
+        try:
+            self.pr.delete(f"comments/{comment}")
+        except Exception as e:
+            get_logger().exception(f"Failed to remove comment, error: {e}")
+
+    # funtion to create_inline_comment
+    def create_inline_comment(self, body: str, relevant_file: str, relevant_line_in_file: str, absolute_position: int = None):
+        position, absolute_position = find_line_number_of_relevant_line_in_file(self.get_diff_files(),
+                                                                            relevant_file.strip('`'),
+                                                                            relevant_line_in_file, absolute_position)
+        if position == -1:
+            if get_settings().config.verbosity_level >= 2:
+                get_logger().info(f"Could not find position for {relevant_file} {relevant_line_in_file}")
+            subject_type = "FILE"
+        else:
+            subject_type = "LINE"
+        path = relevant_file.strip()
+        return dict(body=body, path=path, position=absolute_position) if subject_type == "LINE" else {}
+
+
+    def publish_inline_comment(self, comment: str, from_line: int, file: str):
+        payload = json.dumps( {
+            "content": {
+                "raw": comment,
+            },
+            "inline": {
+                "to": from_line,
+                "path": file
+            },
+        })
+        response = requests.request(
+            "POST", self.bitbucket_comment_api_url, data=payload, headers=self.headers
+        )
+        return response
+
+    def get_line_link(self, relevant_file: str, relevant_line_start: int, relevant_line_end: int = None) -> str:
+        if relevant_line_start == -1:
+            link = f"{self.pr_url}/#L{relevant_file}"
+        else:
+            link = f"{self.pr_url}/#L{relevant_file}T{relevant_line_start}"
+        return link
+
+    def generate_link_to_relevant_line_number(self, suggestion) -> str:
+        try:
+            relevant_file = suggestion['relevant_file'].strip('`').strip("'").rstrip()
+            relevant_line_str = suggestion['relevant_line'].rstrip()
+            if not relevant_line_str:
+                return ""
+
+            diff_files = self.get_diff_files()
+            position, absolute_position = find_line_number_of_relevant_line_in_file \
+                (diff_files, relevant_file, relevant_line_str)
+
+            if absolute_position != -1 and self.pr_url:
+                link = f"{self.pr_url}/#L{relevant_file}T{absolute_position}"
+                return link
+        except Exception as e:
+            if get_settings().config.verbosity_level >= 2:
+                get_logger().info(f"Failed adding line link, error: {e}")
+
+        return ""
+
+    def publish_inline_comments(self, comments: list[dict]):
+        for comment in comments:
+            if 'position' in comment:
+                self.publish_inline_comment(comment['body'], comment['position'], comment['path'])
+            elif 'start_line' in comment: # multi-line comment
+                # note that bitbucket does not seem to support range - only a comment on a single line - https://community.developer.atlassian.com/t/api-post-endpoint-for-inline-pull-request-comments/60452
+                self.publish_inline_comment(comment['body'], comment['start_line'], comment['path'])
+            elif 'line' in comment: # single-line comment
+                self.publish_inline_comment(comment['body'], comment['line'], comment['path'])
+            else:
+                get_logger().error(f"Could not publish inline comment {comment}")
+
+    def get_title(self):
+        return self.pr.title
+
+    def get_languages(self):
+        languages = {self._get_repo().get_data("language"): 0}
+        return languages
+
+    def get_pr_branch(self):
+        return self.pr.source_branch
+
+    def get_pr_description_full(self):
+        return self.pr.description
+
+    def get_user_id(self):
+        return 0
+
+    def get_issue_comments(self):
+        raise NotImplementedError(
+            "Bitbucket provider does not support issue comments yet"
+        )
+
+    def add_eyes_reaction(self, issue_comment_id: int, disable_eyes: bool = False) -> Optional[int]:
+        return True
+
+    def remove_reaction(self, issue_comment_id: int, reaction_id: int) -> bool:
+        return True
+
+    @staticmethod
+    def _parse_pr_url(pr_url: str) -> Tuple[str, int]:
+        parsed_url = urlparse(pr_url)
+
+        if "bitbucket.org" not in parsed_url.netloc:
+            raise ValueError("The provided URL is not a valid Bitbucket URL")
+
+        path_parts = parsed_url.path.strip("/").split("/")
+
+        if len(path_parts) < 4 or path_parts[2] != "pull-requests":
+            raise ValueError(
+                "The provided URL does not appear to be a Bitbucket PR URL"
+            )
+
+        workspace_slug = path_parts[0]
+        repo_slug = path_parts[1]
+        try:
+            pr_number = int(path_parts[3])
+        except ValueError as e:
+            raise ValueError("Unable to convert PR number to integer") from e
+
+        return workspace_slug, repo_slug, pr_number
+
+    def _get_repo(self):
+        if self.repo is None:
+            self.repo = self.bitbucket_client.workspaces.get(
+                self.workspace_slug
+            ).repositories.get(self.repo_slug)
+        return self.repo
+
+    def _get_pr(self):
+        return self._get_repo().pullrequests.get(self.pr_num)
+
+    def _get_pr_file_content(self, remote_link: str):
+        return ""
+
+    def get_commit_messages(self):
+        return ""  # not implemented yet
+    
+    # bitbucket does not support labels
+    def publish_description(self, pr_title: str, description: str):
+        payload = json.dumps({
+            "description": description,
+            "title": pr_title
+
+            })
+
+        response = requests.request("PUT", self.bitbucket_pull_request_api_url, headers=self.headers, data=payload)
+        try:
+            if response.status_code != 200:
+                get_logger().info(f"Failed to update description, error code: {response.status_code}")
+        except:
+            pass
+        return response
+
+    # bitbucket does not support labels
+    def publish_labels(self, pr_types: list):
+        pass
+    
+    # bitbucket does not support labels
+    def get_pr_labels(self):
+        pass

pr_agent/git_providers/bitbucket_server_provider.py

@@ -0,0 +1,354 @@
+import json
+from typing import Optional, Tuple
+from urllib.parse import urlparse
+
+import requests
+from atlassian.bitbucket import Bitbucket
+from starlette_context import context
+
+from .git_provider import GitProvider
+from pr_agent.algo.types import FilePatchInfo
+from ..algo.utils import load_large_diff, find_line_number_of_relevant_line_in_file
+from ..config_loader import get_settings
+from ..log import get_logger
+
+
+class BitbucketServerProvider(GitProvider):
+    def __init__(
+        self, pr_url: Optional[str] = None, incremental: Optional[bool] = False
+    ):
+        s = requests.Session()
+        try:
+            bearer = context.get("bitbucket_bearer_token", None)
+            s.headers["Authorization"] = f"Bearer {bearer}"
+        except Exception:
+            s.headers[
+                "Authorization"
+            ] = f'Bearer {get_settings().get("BITBUCKET_SERVER.BEARER_TOKEN", None)}'
+
+        s.headers["Content-Type"] = "application/json"
+        self.headers = s.headers
+        self.bitbucket_server_url = None
+        self.workspace_slug = None
+        self.repo_slug = None
+        self.repo = None
+        self.pr_num = None
+        self.pr = None
+        self.pr_url = pr_url
+        self.temp_comments = []
+        self.incremental = incremental
+        self.diff_files = None
+        self.bitbucket_pull_request_api_url = pr_url
+
+        self.bitbucket_server_url = self._parse_bitbucket_server(url=pr_url)
+        self.bitbucket_client = Bitbucket(url=self.bitbucket_server_url,
+                                          token=get_settings().get("BITBUCKET_SERVER.BEARER_TOKEN", None))
+
+        if pr_url:
+            self.set_pr(pr_url)
+
+    def get_repo_settings(self):
+        try:
+            url = (f"{self.bitbucket_server_url}/projects/{self.workspace_slug}/repos/{self.repo_slug}/src/"
+                   f"{self.pr.destination_branch}/.pr_agent.toml")
+            response = requests.request("GET", url, headers=self.headers)
+            if response.status_code == 404:  # not found
+                return ""
+            contents = response.text.encode('utf-8')
+            return contents
+        except Exception:
+            return ""
+
+    def publish_code_suggestions(self, code_suggestions: list) -> bool:
+        """
+        Publishes code suggestions as comments on the PR.
+        """
+        post_parameters_list = []
+        for suggestion in code_suggestions:
+            body = suggestion["body"]
+            relevant_file = suggestion["relevant_file"]
+            relevant_lines_start = suggestion["relevant_lines_start"]
+            relevant_lines_end = suggestion["relevant_lines_end"]
+
+            if not relevant_lines_start or relevant_lines_start == -1:
+                if get_settings().config.verbosity_level >= 2:
+                    get_logger().exception(
+                        f"Failed to publish code suggestion, relevant_lines_start is {relevant_lines_start}"
+                    )
+                continue
+
+            if relevant_lines_end < relevant_lines_start:
+                if get_settings().config.verbosity_level >= 2:
+                    get_logger().exception(
+                        f"Failed to publish code suggestion, "
+                        f"relevant_lines_end is {relevant_lines_end} and "
+                        f"relevant_lines_start is {relevant_lines_start}"
+                    )
+                continue
+
+            if relevant_lines_end > relevant_lines_start:
+                post_parameters = {
+                    "body": body,
+                    "path": relevant_file,
+                    "line": relevant_lines_end,
+                    "start_line": relevant_lines_start,
+                    "start_side": "RIGHT",
+                }
+            else:  # API is different for single line comments
+                post_parameters = {
+                    "body": body,
+                    "path": relevant_file,
+                    "line": relevant_lines_start,
+                    "side": "RIGHT",
+                }
+            post_parameters_list.append(post_parameters)
+
+        try:
+            self.publish_inline_comments(post_parameters_list)
+            return True
+        except Exception as e:
+            if get_settings().config.verbosity_level >= 2:
+                get_logger().error(f"Failed to publish code suggestion, error: {e}")
+            return False
+
+    def is_supported(self, capability: str) -> bool:
+        if capability in ['get_issue_comments', 'get_labels', 'gfm_markdown']:
+            return False
+        return True
+
+    def set_pr(self, pr_url: str):
+        self.workspace_slug, self.repo_slug, self.pr_num = self._parse_pr_url(pr_url)
+        self.pr = self._get_pr()
+
+    def get_file(self, path: str, commit_id: str):
+        file_content = ""
+        try:
+            file_content = self.bitbucket_client.get_content_of_file(self.workspace_slug,
+                                                                     self.repo_slug,
+                                                                     path,
+                                                                     commit_id)
+        except requests.HTTPError as e:
+            get_logger().debug(f"File {path} not found at commit id: {commit_id}")
+        return file_content
+
+    def get_files(self):
+        changes = self.bitbucket_client.get_pull_requests_changes(self.workspace_slug, self.repo_slug, self.pr_num)
+        diffstat = [change["path"]['toString'] for change in changes]
+        return diffstat
+
+    def get_diff_files(self) -> list[FilePatchInfo]:
+        if self.diff_files:
+            return self.diff_files
+
+        commits_in_pr = self.bitbucket_client.get_pull_requests_commits(
+            self.workspace_slug,
+            self.repo_slug,
+            self.pr_num
+        )
+
+        commit_list = list(commits_in_pr)
+        base_sha, head_sha = commit_list[0]['parents'][0]['id'], commit_list[-1]['id']
+
+        diff_files = []
+        original_file_content_str = ""
+        new_file_content_str = ""
+
+        changes = self.bitbucket_client.get_pull_requests_changes(self.workspace_slug, self.repo_slug, self.pr_num)
+        for change in changes:
+            file_path = change['path']['toString']
+            match change['type']:
+                case 'ADD':
+                    edit_type = EDIT_TYPE.ADDED
+                    new_file_content_str = self.get_file(file_path, head_sha)
+                    if isinstance(new_file_content_str, (bytes, bytearray)):
+                        new_file_content_str = new_file_content_str.decode("utf-8")
+                    original_file_content_str = ""
+                case 'DELETE':
+                    edit_type = EDIT_TYPE.DELETED
+                    new_file_content_str = ""
+                    original_file_content_str = self.get_file(file_path, base_sha)
+                    if isinstance(original_file_content_str, (bytes, bytearray)):
+                        original_file_content_str = original_file_content_str.decode("utf-8")
+                case 'RENAME':
+                    edit_type = EDIT_TYPE.RENAMED
+                case _:
+                    edit_type = EDIT_TYPE.MODIFIED
+                    original_file_content_str = self.get_file(file_path, base_sha)
+                    if isinstance(original_file_content_str, (bytes, bytearray)):
+                        original_file_content_str = original_file_content_str.decode("utf-8")
+                    new_file_content_str = self.get_file(file_path, head_sha)
+                    if isinstance(new_file_content_str, (bytes, bytearray)):
+                        new_file_content_str = new_file_content_str.decode("utf-8")
+
+            patch = load_large_diff(file_path, new_file_content_str, original_file_content_str)
+
+            diff_files.append(
+                FilePatchInfo(
+                    original_file_content_str,
+                    new_file_content_str,
+                    patch,
+                    file_path,
+                    edit_type=edit_type,
+                )
+            )
+
+        self.diff_files = diff_files
+        return diff_files
+
+    def publish_comment(self, pr_comment: str, is_temporary: bool = False):
+        if not is_temporary:
+            self.bitbucket_client.add_pull_request_comment(self.workspace_slug, self.repo_slug, self.pr_num, pr_comment)
+
+    def remove_initial_comment(self):
+        try:
+            for comment in self.temp_comments:
+                self.remove_comment(comment)
+        except ValueError as e:
+            get_logger().exception(f"Failed to remove temp comments, error: {e}")
+
+    def remove_comment(self, comment):
+        pass
+
+    # funtion to create_inline_comment
+    def create_inline_comment(self, body: str, relevant_file: str, relevant_line_in_file: str,
+                              absolute_position: int = None):
+
+        position, absolute_position = find_line_number_of_relevant_line_in_file(
+            self.get_diff_files(),
+            relevant_file.strip('`'),
+            relevant_line_in_file,
+            absolute_position
+        )
+        if position == -1:
+            if get_settings().config.verbosity_level >= 2:
+                get_logger().info(f"Could not find position for {relevant_file} {relevant_line_in_file}")
+            subject_type = "FILE"
+        else:
+            subject_type = "LINE"
+        path = relevant_file.strip()
+        return dict(body=body, path=path, position=absolute_position) if subject_type == "LINE" else {}
+
+    def publish_inline_comment(self, comment: str, from_line: int, file: str):
+        payload = {
+            "text": comment,
+            "severity": "NORMAL",
+            "anchor": {
+                "diffType": "EFFECTIVE",
+                "path": file,
+                "lineType": "ADDED",
+                "line": from_line,
+                "fileType": "TO"
+            }
+        }
+
+        response = requests.post(url=self._get_pr_comments_url(), json=payload, headers=self.headers)
+        return response
+
+    def generate_link_to_relevant_line_number(self, suggestion) -> str:
+        try:
+            relevant_file = suggestion['relevant_file'].strip('`').strip("'").rstrip()
+            relevant_line_str = suggestion['relevant_line'].rstrip()
+            if not relevant_line_str:
+                return ""
+
+            diff_files = self.get_diff_files()
+            position, absolute_position = find_line_number_of_relevant_line_in_file \
+                (diff_files, relevant_file, relevant_line_str)
+
+            if absolute_position != -1 and self.pr_url:
+                link = f"{self.pr_url}/#L{relevant_file}T{absolute_position}"
+                return link
+        except Exception as e:
+            if get_settings().config.verbosity_level >= 2:
+                get_logger().info(f"Failed adding line link, error: {e}")
+
+        return ""
+
+    def publish_inline_comments(self, comments: list[dict]):
+        for comment in comments:
+            self.publish_inline_comment(comment['body'], comment['position'], comment['path'])
+
+    def get_title(self):
+        return self.pr.title
+
+    def get_languages(self):
+        return {"yaml": 0}  # devops LOL
+
+    def get_pr_branch(self):
+        return self.pr.fromRef['displayId']
+
+    def get_pr_description_full(self):
+        return self.pr.description
+
+    def get_user_id(self):
+        return 0
+
+    def get_issue_comments(self):
+        raise NotImplementedError(
+            "Bitbucket provider does not support issue comments yet"
+        )
+
+    def add_eyes_reaction(self, issue_comment_id: int, disable_eyes: bool = False) -> Optional[int]:
+        return True
+
+    def remove_reaction(self, issue_comment_id: int, reaction_id: int) -> bool:
+        return True
+
+    @staticmethod
+    def _parse_bitbucket_server(url: str) -> str:
+        parsed_url = urlparse(url)
+        return f"{parsed_url.scheme}://{parsed_url.netloc}"
+
+    @staticmethod
+    def _parse_pr_url(pr_url: str) -> Tuple[str, str, int]:
+        parsed_url = urlparse(pr_url)
+        path_parts = parsed_url.path.strip("/").split("/")
+        if len(path_parts) < 6 or path_parts[4] != "pull-requests":
+            raise ValueError(
+                "The provided URL does not appear to be a Bitbucket PR URL"
+            )
+
+        workspace_slug = path_parts[1]
+        repo_slug = path_parts[3]
+        try:
+            pr_number = int(path_parts[5])
+        except ValueError as e:
+            raise ValueError("Unable to convert PR number to integer") from e
+
+        return workspace_slug, repo_slug, pr_number
+
+    def _get_repo(self):
+        if self.repo is None:
+            self.repo = self.bitbucket_client.get_repo(self.workspace_slug, self.repo_slug)
+        return self.repo
+
+    def _get_pr(self):
+        pr = self.bitbucket_client.get_pull_request(self.workspace_slug, self.repo_slug, pull_request_id=self.pr_num)
+        return type('new_dict', (object,), pr)
+
+    def _get_pr_file_content(self, remote_link: str):
+        return ""
+
+    def get_commit_messages(self):
+        def get_commit_messages(self):
+            raise NotImplementedError("Get commit messages function not implemented yet.")
+    # bitbucket does not support labels
+    def publish_description(self, pr_title: str, description: str):
+        payload = json.dumps({
+            "description": description,
+            "title": pr_title
+        })
+
+        response = requests.put(url=self.bitbucket_pull_request_api_url, headers=self.headers, data=payload)
+        return response
+
+    # bitbucket does not support labels
+    def publish_labels(self, pr_types: list):
+        pass
+    
+    # bitbucket does not support labels
+    def get_pr_labels(self):
+        pass
+
+    def _get_pr_comments_url(self):
+        return f"{self.bitbucket_server_url}/rest/api/latest/projects/{self.workspace_slug}/repos/{self.repo_slug}/pull-requests/{self.pr_num}/comments"

pr_agent/git_providers/codecommit_client.py

@@ -0,0 +1,277 @@
+import boto3
+import botocore
+
+
+class CodeCommitDifferencesResponse:
+    """
+    CodeCommitDifferencesResponse is the response object returned from our get_differences() function.
+    It maps the JSON response to member variables of this class.
+    """
+
+    def __init__(self, json: dict):
+        before_blob = json.get("beforeBlob", {})
+        after_blob = json.get("afterBlob", {})
+
+        self.before_blob_id = before_blob.get("blobId", "")
+        self.before_blob_path = before_blob.get("path", "")
+        self.after_blob_id = after_blob.get("blobId", "")
+        self.after_blob_path = after_blob.get("path", "")
+        self.change_type = json.get("changeType", "")
+
+
+class CodeCommitPullRequestResponse:
+    """
+    CodeCommitPullRequestResponse is the response object returned from our get_pr() function.
+    It maps the JSON response to member variables of this class.
+    """
+
+    def __init__(self, json: dict):
+        self.title = json.get("title", "")
+        self.description = json.get("description", "")
+
+        self.targets = []
+        for target in json.get("pullRequestTargets", []):
+            self.targets.append(CodeCommitPullRequestResponse.CodeCommitPullRequestTarget(target))
+
+    class CodeCommitPullRequestTarget:
+        """
+        CodeCommitPullRequestTarget is a subclass of CodeCommitPullRequestResponse that
+        holds details about an individual target commit.
+        """
+
+        def __init__(self, json: dict):
+            self.source_commit = json.get("sourceCommit", "")
+            self.source_branch = json.get("sourceReference", "")
+            self.destination_commit = json.get("destinationCommit", "")
+            self.destination_branch = json.get("destinationReference", "")
+
+
+class CodeCommitClient:
+    """
+    CodeCommitClient is a wrapper around the AWS boto3 SDK for the CodeCommit client
+    """
+
+    def __init__(self):
+        self.boto_client = None
+
+    def is_supported(self, capability: str) -> bool:
+        if capability in ["gfm_markdown"]:
+            return False
+        return True
+
+    def _connect_boto_client(self):
+        try:
+            self.boto_client = boto3.client("codecommit")
+        except Exception as e:
+            raise ValueError(f"Failed to connect to AWS CodeCommit: {e}") from e
+
+    def get_differences(self, repo_name: int, destination_commit: str, source_commit: str):
+        """
+        Get the differences between two commits in CodeCommit.
+
+        Args:
+        - repo_name: Name of the repository
+        - destination_commit: Commit hash you want to merge into (the "before" hash) (usually on the main or master branch)
+        - source_commit: Commit hash of the code you are adding (the "after" branch)
+
+        Returns:
+        - List of CodeCommitDifferencesResponse objects
+
+        Boto3 Documentation:
+        - aws codecommit get-differences
+        - https://boto3.amazonaws.com/v1/documentation/api/latest/reference/services/codecommit/client/get_differences.html
+        """
+        if self.boto_client is None:
+            self._connect_boto_client()
+
+        # The differences response from AWS is paginated, so we need to iterate through the pages to get all the differences.
+        differences = []
+        try:
+            paginator = self.boto_client.get_paginator("get_differences")
+            for page in paginator.paginate(
+                repositoryName=repo_name,
+                beforeCommitSpecifier=destination_commit,
+                afterCommitSpecifier=source_commit,
+            ):
+                differences.extend(page.get("differences", []))
+        except botocore.exceptions.ClientError as e:
+            if e.response["Error"]["Code"] == 'RepositoryDoesNotExistException':
+                raise ValueError(f"CodeCommit cannot retrieve differences: Repository does not exist: {repo_name}") from e
+            raise ValueError(f"CodeCommit cannot retrieve differences for {source_commit}..{destination_commit}") from e
+        except Exception as e:
+            raise ValueError(f"CodeCommit cannot retrieve differences for {source_commit}..{destination_commit}") from e
+
+        output = []
+        for json in differences:
+            output.append(CodeCommitDifferencesResponse(json))
+        return output
+
+    def get_file(self, repo_name: str, file_path: str, sha_hash: str, optional: bool = False):
+        """
+        Retrieve a file from CodeCommit.
+
+        Args:
+        - repo_name: Name of the repository
+        - file_path: Path to the file you are retrieving
+        - sha_hash: Commit hash of the file you are retrieving
+
+        Returns:
+        - File contents
+
+        Boto3 Documentation:
+        - aws codecommit get_file
+        - https://boto3.amazonaws.com/v1/documentation/api/latest/reference/services/codecommit/client/get_file.html
+        """
+        if not file_path:
+            return ""
+
+        if self.boto_client is None:
+            self._connect_boto_client()
+
+        try:
+            response = self.boto_client.get_file(repositoryName=repo_name, commitSpecifier=sha_hash, filePath=file_path)
+        except botocore.exceptions.ClientError as e:
+            if e.response["Error"]["Code"] == 'RepositoryDoesNotExistException':
+                raise ValueError(f"CodeCommit cannot retrieve PR: Repository does not exist: {repo_name}") from e
+            # if the file does not exist, but is flagged as optional, then return an empty string
+            if optional and e.response["Error"]["Code"] == 'FileDoesNotExistException':
+                return ""
+            raise ValueError(f"CodeCommit cannot retrieve file '{file_path}' from repository '{repo_name}'") from e
+        except Exception as e:
+            raise ValueError(f"CodeCommit cannot retrieve file '{file_path}' from repository '{repo_name}'") from e
+        if "fileContent" not in response:
+            raise ValueError(f"File content is empty for file: {file_path}")
+
+        return response.get("fileContent", "")
+
+    def get_pr(self, repo_name: str, pr_number: int):
+        """
+        Get a information about a CodeCommit PR.
+
+        Args:
+        - repo_name: Name of the repository
+        - pr_number: The PR number you are requesting
+
+        Returns:
+        - CodeCommitPullRequestResponse object
+
+        Boto3 Documentation:
+        - aws codecommit get_pull_request
+        - https://boto3.amazonaws.com/v1/documentation/api/latest/reference/services/codecommit/client/get_pull_request.html
+        """
+        if self.boto_client is None:
+            self._connect_boto_client()
+
+        try:
+            response = self.boto_client.get_pull_request(pullRequestId=str(pr_number))
+        except botocore.exceptions.ClientError as e:
+            if e.response["Error"]["Code"] == 'PullRequestDoesNotExistException':
+                raise ValueError(f"CodeCommit cannot retrieve PR: PR number does not exist: {pr_number}") from e
+            if e.response["Error"]["Code"] == 'RepositoryDoesNotExistException':
+                raise ValueError(f"CodeCommit cannot retrieve PR: Repository does not exist: {repo_name}") from e
+            raise ValueError(f"CodeCommit cannot retrieve PR: {pr_number}: boto client error") from e
+        except Exception as e:
+            raise ValueError(f"CodeCommit cannot retrieve PR: {pr_number}") from e
+
+        if "pullRequest" not in response:
+            raise ValueError("CodeCommit PR number not found: {pr_number}")
+
+        return CodeCommitPullRequestResponse(response.get("pullRequest", {}))
+
+    def publish_description(self, pr_number: int, pr_title: str, pr_body: str):
+        """
+        Set the title and description on a pull request
+
+        Args:
+        - pr_number: the AWS CodeCommit pull request number
+        - pr_title: title of the pull request
+        - pr_body: body of the pull request
+
+        Returns:
+        - None
+
+        Boto3 Documentation:
+        - aws codecommit update_pull_request_title
+        - https://boto3.amazonaws.com/v1/documentation/api/latest/reference/services/codecommit/client/update_pull_request_title.html
+        - aws codecommit update_pull_request_description
+        - https://boto3.amazonaws.com/v1/documentation/api/latest/reference/services/codecommit/client/update_pull_request_description.html
+        """
+        if self.boto_client is None:
+            self._connect_boto_client()
+
+        try:
+            self.boto_client.update_pull_request_title(pullRequestId=str(pr_number), title=pr_title)
+            self.boto_client.update_pull_request_description(pullRequestId=str(pr_number), description=pr_body)
+        except botocore.exceptions.ClientError as e:
+            if e.response["Error"]["Code"] == 'PullRequestDoesNotExistException':
+                raise ValueError(f"PR number does not exist: {pr_number}") from e
+            if e.response["Error"]["Code"] == 'InvalidTitleException':
+                raise ValueError(f"Invalid title for PR number: {pr_number}") from e
+            if e.response["Error"]["Code"] == 'InvalidDescriptionException':
+                raise ValueError(f"Invalid description for PR number: {pr_number}") from e
+            if e.response["Error"]["Code"] == 'PullRequestAlreadyClosedException':
+                raise ValueError(f"PR is already closed: PR number: {pr_number}") from e
+            raise ValueError(f"Boto3 client error calling publish_description") from e
+        except Exception as e:
+            raise ValueError(f"Error calling publish_description") from e
+
+    def publish_comment(self, repo_name: str, pr_number: int, destination_commit: str, source_commit: str, comment: str, annotation_file: str = None, annotation_line: int = None):
+        """
+        Publish a comment to a pull request
+
+        Args:
+        - repo_name: name of the repository
+        - pr_number: number of the pull request
+        - destination_commit: The commit hash you want to merge into (the "before" hash) (usually on the main or master branch)
+        - source_commit: The commit hash of the code you are adding (the "after" branch)
+        - comment: The comment you want to publish
+        - annotation_file: The file you want to annotate (optional)
+        - annotation_line: The line number you want to annotate (optional)
+
+        Comment annotations for CodeCommit are different than GitHub.
+        CodeCommit only designates the starting line number for the comment.
+        It does not support the ending line number to highlight a range of lines.
+
+        Returns:
+        - None
+
+        Boto3 Documentation:
+        - aws codecommit post_comment_for_pull_request
+        - https://boto3.amazonaws.com/v1/documentation/api/latest/reference/services/codecommit/client/post_comment_for_pull_request.html
+        """
+        if self.boto_client is None:
+            self._connect_boto_client()
+
+        try:
+            # If the comment has code annotations,
+            # then set the file path and line number in the location dictionary
+            if annotation_file and annotation_line:
+                self.boto_client.post_comment_for_pull_request(
+                    pullRequestId=str(pr_number),
+                    repositoryName=repo_name,
+                    beforeCommitId=destination_commit,
+                    afterCommitId=source_commit,
+                    content=comment,
+                    location={
+                        "filePath": annotation_file,
+                        "filePosition": annotation_line,
+                        "relativeFileVersion": "AFTER",
+                    },
+                )
+            else:
+                # The comment does not have code annotations
+                self.boto_client.post_comment_for_pull_request(
+                    pullRequestId=str(pr_number),
+                    repositoryName=repo_name,
+                    beforeCommitId=destination_commit,
+                    afterCommitId=source_commit,
+                    content=comment,
+                )
+        except botocore.exceptions.ClientError as e:
+            if e.response["Error"]["Code"] == 'RepositoryDoesNotExistException':
+                raise ValueError(f"Repository does not exist: {repo_name}") from e
+            if e.response["Error"]["Code"] == 'PullRequestDoesNotExistException':
+                raise ValueError(f"PR number does not exist: {pr_number}") from e
+            raise ValueError(f"Boto3 client error calling post_comment_for_pull_request") from e
+        except Exception as e:
+            raise ValueError(f"Error calling post_comment_for_pull_request") from e

pr_agent/git_providers/codecommit_provider.py

@@ -0,0 +1,495 @@
+import os
+import re
+from collections import Counter
+from typing import List, Optional, Tuple
+from urllib.parse import urlparse
+
+from pr_agent.git_providers.codecommit_client import CodeCommitClient
+from pr_agent.algo.types import EDIT_TYPE, FilePatchInfo
+from ..algo.utils import load_large_diff
+from .git_provider import GitProvider
+from ..config_loader import get_settings
+from ..log import get_logger
+
+
+class PullRequestCCMimic:
+    """
+    This class mimics the PullRequest class from the PyGithub library for the CodeCommitProvider.
+    """
+
+    def __init__(self, title: str, diff_files: List[FilePatchInfo]):
+        self.title = title
+        self.diff_files = diff_files
+        self.description = None
+        self.source_commit = None
+        self.source_branch = None  # the branch containing your new code changes
+        self.destination_commit = None
+        self.destination_branch = None  # the branch you are going to merge into
+
+
+class CodeCommitFile:
+    """
+    This class represents a file in a pull request in CodeCommit.
+    """
+
+    def __init__(
+        self,
+        a_path: str,
+        a_blob_id: str,
+        b_path: str,
+        b_blob_id: str,
+        edit_type: EDIT_TYPE,
+    ):
+        self.a_path = a_path
+        self.a_blob_id = a_blob_id
+        self.b_path = b_path
+        self.b_blob_id = b_blob_id
+        self.edit_type: EDIT_TYPE = edit_type
+        self.filename = b_path if b_path else a_path
+
+
+class CodeCommitProvider(GitProvider):
+    """
+    This class implements the GitProvider interface for AWS CodeCommit repositories.
+    """
+
+    def __init__(self, pr_url: Optional[str] = None, incremental: Optional[bool] = False):
+        self.codecommit_client = CodeCommitClient()
+        self.aws_client = None
+        self.repo_name = None
+        self.pr_num = None
+        self.pr = None
+        self.diff_files = None
+        self.git_files = None
+        self.pr_url = pr_url
+        if pr_url:
+            self.set_pr(pr_url)
+
+    def provider_name(self):
+        return "CodeCommit"
+
+    def is_supported(self, capability: str) -> bool:
+        if capability in [
+            "get_issue_comments",
+            "create_inline_comment",
+            "publish_inline_comments",
+            "get_labels",
+            "gfm_markdown"
+        ]:
+            return False
+        return True
+
+    def set_pr(self, pr_url: str):
+        self.repo_name, self.pr_num = self._parse_pr_url(pr_url)
+        self.pr = self._get_pr()
+
+    def get_files(self) -> list[CodeCommitFile]:
+        # bring files from CodeCommit only once
+        if self.git_files:
+            return self.git_files
+
+        self.git_files = []
+        differences = self.codecommit_client.get_differences(self.repo_name, self.pr.destination_commit, self.pr.source_commit)
+        for item in differences:
+            self.git_files.append(CodeCommitFile(item.before_blob_path,
+                                                 item.before_blob_id,
+                                                 item.after_blob_path,
+                                                 item.after_blob_id,
+                                                 CodeCommitProvider._get_edit_type(item.change_type)))
+        return self.git_files
+
+    def get_diff_files(self) -> list[FilePatchInfo]:
+        """
+        Retrieves the list of files that have been modified, added, deleted, or renamed in a pull request in CodeCommit,
+        along with their content and patch information.
+
+        Returns:
+            diff_files (List[FilePatchInfo]): List of FilePatchInfo objects representing the modified, added, deleted,
+            or renamed files in the merge request.
+        """
+        # bring files from CodeCommit only once
+        if self.diff_files:
+            return self.diff_files
+
+        self.diff_files = []
+
+        files = self.get_files()
+        for diff_item in files:
+            patch_filename = ""
+            if diff_item.a_blob_id is not None:
+                patch_filename = diff_item.a_path
+                original_file_content_str = self.codecommit_client.get_file(
+                    self.repo_name, diff_item.a_path, self.pr.destination_commit)
+                if isinstance(original_file_content_str, (bytes, bytearray)):
+                    original_file_content_str = original_file_content_str.decode("utf-8")
+            else:
+                original_file_content_str = ""
+
+            if diff_item.b_blob_id is not None:
+                patch_filename = diff_item.b_path
+                new_file_content_str = self.codecommit_client.get_file(self.repo_name, diff_item.b_path, self.pr.source_commit)
+                if isinstance(new_file_content_str, (bytes, bytearray)):
+                    new_file_content_str = new_file_content_str.decode("utf-8")
+            else:
+                new_file_content_str = ""
+
+            patch = load_large_diff(patch_filename, new_file_content_str, original_file_content_str)
+
+            # Store the diffs as a list of FilePatchInfo objects
+            info = FilePatchInfo(
+                original_file_content_str,
+                new_file_content_str,
+                patch,
+                diff_item.b_path,
+                edit_type=diff_item.edit_type,
+                old_filename=None
+                if diff_item.a_path == diff_item.b_path
+                else diff_item.a_path,
+            )
+            # Only add valid files to the diff list
+            # "bad extensions" are set in the language_extensions.toml file
+            # a "valid file" is one that is not in the "bad extensions" list
+            if is_valid_file(info.filename):
+                self.diff_files.append(info)
+
+        return self.diff_files
+
+    def publish_description(self, pr_title: str, pr_body: str):
+        try:
+            self.codecommit_client.publish_description(
+                pr_number=self.pr_num,
+                pr_title=pr_title,
+                pr_body=CodeCommitProvider._add_additional_newlines(pr_body),
+            )
+        except Exception as e:
+            raise ValueError(f"CodeCommit Cannot publish description for PR: {self.pr_num}") from e    
+
+    def publish_comment(self, pr_comment: str, is_temporary: bool = False):
+        if is_temporary:
+            get_logger().info(pr_comment)
+            return
+
+        pr_comment = CodeCommitProvider._remove_markdown_html(pr_comment)
+        pr_comment = CodeCommitProvider._add_additional_newlines(pr_comment)
+
+        try:
+            self.codecommit_client.publish_comment(
+                repo_name=self.repo_name,
+                pr_number=self.pr_num,
+                destination_commit=self.pr.destination_commit,
+                source_commit=self.pr.source_commit,
+                comment=pr_comment,
+            )
+        except Exception as e:
+            raise ValueError(f"CodeCommit Cannot publish comment for PR: {self.pr_num}") from e
+
+    def publish_code_suggestions(self, code_suggestions: list) -> bool:
+        counter = 1
+        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"]):
+                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:
+                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,
+                    destination_commit=self.pr.destination_commit,
+                    source_commit=self.pr.source_commit,
+                    comment=suggestion["body"],
+                    annotation_file=suggestion["relevant_file"],
+                    annotation_line=suggestion["relevant_lines_start"],
+                )
+            except Exception as e:
+                raise ValueError(f"CodeCommit Cannot publish code suggestions for PR: {self.pr_num}") from e
+            
+            counter += 1
+
+        # The calling function passes in a list of code suggestions, and this function publishes each suggestion one at a time.
+        # If we were to return False here, the calling function will attempt to publish the same list of code suggestions again, one at a time.
+        # Since this function publishes the suggestions one at a time anyway, we always return True here to avoid the retry.        
+        return True
+
+    def publish_labels(self, labels):
+        return [""]  # not implemented yet
+
+    def get_pr_labels(self):
+        return [""]  # not implemented yet
+
+    def remove_initial_comment(self):
+        return ""  # not implemented yet
+
+    def remove_comment(self, comment):
+        return ""  # not implemented yet
+
+    def publish_inline_comment(self, body: str, relevant_file: str, relevant_line_in_file: str):
+        # https://boto3.amazonaws.com/v1/documentation/api/latest/reference/services/codecommit/client/post_comment_for_compared_commit.html
+        raise NotImplementedError("CodeCommit provider does not support publishing inline comments yet")
+
+    def publish_inline_comments(self, comments: list[dict]):
+        raise NotImplementedError("CodeCommit provider does not support publishing inline comments yet")
+
+    def get_title(self):
+        return self.pr.title
+
+    def get_pr_id(self):
+        """
+        Returns the PR ID in the format: "repo_name/pr_number".
+        Note: This is an internal identifier for PR-Agent, 
+        and is not the same as the CodeCommit PR identifier.
+        """
+        try:
+            pr_id = f"{self.repo_name}/{self.pr_num}"
+            return pr_id
+        except:
+            return ""
+        
+    def get_languages(self):
+        """
+        Returns a dictionary of languages, containing the percentage of each language used in the PR.
+
+        Returns:
+        - dict: A dictionary where each key is a language name and the corresponding value is the percentage of that language in the PR.
+        """
+        commit_files = self.get_files()
+        filenames = [ item.filename for item in commit_files ]
+        extensions = CodeCommitProvider._get_file_extensions(filenames)
+
+        # Calculate the percentage of each file extension in the PR
+        percentages = CodeCommitProvider._get_language_percentages(extensions)
+
+        # The global language_extension_map is a dictionary of languages,
+        # where each dictionary item is a BoxList of extensions.
+        # We want a dictionary of extensions,
+        # where each dictionary item is a language name.
+        # We build that language->extension dictionary here in main_extensions_flat.
+        main_extensions_flat = {}
+        language_extension_map_org = get_settings().language_extension_map_org
+        language_extension_map = {k.lower(): v for k, v in language_extension_map_org.items()}
+        for language, extensions in language_extension_map.items():
+            for ext in extensions:
+                main_extensions_flat[ext] = language
+
+        # Map the file extension/languages to percentages
+        languages = {}
+        for ext, pct in percentages.items():
+            languages[main_extensions_flat.get(ext, "")] = pct
+
+        return languages
+
+    def get_pr_branch(self):
+        return self.pr.source_branch
+
+    def get_pr_description_full(self) -> str:
+        return self.pr.description
+
+    def get_user_id(self):
+        return -1  # not implemented yet
+
+    def get_issue_comments(self):
+        raise NotImplementedError("CodeCommit provider does not support issue comments yet")
+
+    def get_repo_settings(self):
+        # a local ".pr_agent.toml" settings file is optional
+        settings_filename = ".pr_agent.toml"
+        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, disable_eyes: bool = False) -> Optional[int]:
+        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:
+        get_logger().info("CodeCommit provider does not support removing reactions yet")
+        return True
+
+    @staticmethod
+    def _parse_pr_url(pr_url: str) -> Tuple[str, int]:
+        """
+        Parse the CodeCommit PR URL and return the repository name and PR number.
+
+        Args:
+        - pr_url: the full AWS CodeCommit pull request URL
+
+        Returns:
+        - Tuple[str, int]: A tuple containing the repository name and PR number.
+        """
+        # Example PR URL:
+        # https://us-east-1.console.aws.amazon.com/codesuite/codecommit/repositories/__MY_REPO__/pull-requests/123456"
+        parsed_url = urlparse(pr_url)
+
+        if not CodeCommitProvider._is_valid_codecommit_hostname(parsed_url.netloc):
+            raise ValueError(f"The provided URL is not a valid CodeCommit URL: {pr_url}")
+
+        path_parts = parsed_url.path.strip("/").split("/")
+
+        if (
+            len(path_parts) < 6
+            or path_parts[0] != "codesuite"
+            or path_parts[1] != "codecommit"
+            or path_parts[2] != "repositories"
+            or path_parts[4] != "pull-requests"
+        ):
+            raise ValueError(f"The provided URL does not appear to be a CodeCommit PR URL: {pr_url}")
+
+        repo_name = path_parts[3]
+
+        try:
+            pr_number = int(path_parts[5])
+        except ValueError as e:
+            raise ValueError(f"Unable to convert PR number to integer: '{path_parts[5]}'") from e
+
+        return repo_name, pr_number
+
+    @staticmethod
+    def _is_valid_codecommit_hostname(hostname: str) -> bool:
+        """
+        Check if the provided hostname is a valid AWS CodeCommit hostname.
+
+        This is not an exhaustive check of AWS region names, 
+        but instead uses a regex to check for matching AWS region patterns.
+
+        Args:
+        - hostname: the hostname to check
+
+        Returns:
+        - bool: True if the hostname is valid, False otherwise.
+        """
+        return re.match(r"^[a-z]{2}-(gov-)?[a-z]+-\d\.console\.aws\.amazon\.com$", hostname) is not None
+
+    def _get_pr(self):
+        response = self.codecommit_client.get_pr(self.repo_name, self.pr_num)
+
+        if len(response.targets) == 0:
+            raise ValueError(f"No files found in CodeCommit PR: {self.pr_num}")
+
+        # 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:
+            get_logger().warning(
+                "Multiple targets in one PR is not supported for CodeCommit yet. Continuing, using the first target only..."
+            )
+
+        # Return our object that mimics PullRequest class from the PyGithub library
+        # (This strategy was copied from the LocalGitProvider)
+        mimic = PullRequestCCMimic(response.title, self.diff_files)
+        mimic.description = response.description
+        mimic.source_commit = response.targets[0].source_commit
+        mimic.source_branch = response.targets[0].source_branch
+        mimic.destination_commit = response.targets[0].destination_commit
+        mimic.destination_branch = response.targets[0].destination_branch
+
+        return mimic
+
+    def get_commit_messages(self):
+        return ""  # not implemented yet
+
+    @staticmethod
+    def _add_additional_newlines(body: str) -> str:
+        """
+        Replace single newlines in a PR body with double newlines.
+
+        CodeCommit Markdown does not seem to render as well as GitHub Markdown,
+        so we add additional newlines to the PR body to make it more readable in CodeCommit.
+
+        Args:
+        - body: the PR body
+
+        Returns:
+        - str: the PR body with the double newlines added
+        """
+        return re.sub(r'(?<!\n)\n(?!\n)', '\n\n', body)
+
+    @staticmethod
+    def _remove_markdown_html(comment: str) -> str:
+        """
+        Remove the HTML tags from a PR comment.
+
+        CodeCommit Markdown does not seem to render as well as GitHub Markdown,
+        so we remove the HTML tags from the PR comment to make it more readable in CodeCommit.
+
+        Args:
+        - comment: the PR comment
+
+        Returns:
+        - str: the PR comment with the HTML tags removed
+        """
+        comment = comment.replace("<details>", "")
+        comment = comment.replace("</details>", "")
+        comment = comment.replace("<summary>", "")
+        comment = comment.replace("</summary>", "")
+        return comment
+
+    @staticmethod
+    def _get_edit_type(codecommit_change_type: str):
+        """
+        Convert the CodeCommit change type string to the EDIT_TYPE enum.
+        The CodeCommit change type string is returned from the get_differences SDK method.
+
+        Args:
+        - codecommit_change_type: the CodeCommit change type string
+
+        Returns:
+        - An EDIT_TYPE enum representing the modified, added, deleted, or renamed file in the PR diff.
+        """
+        t = codecommit_change_type.upper()
+        edit_type = None
+        if t == "A":
+            edit_type = EDIT_TYPE.ADDED
+        elif t == "D":
+            edit_type = EDIT_TYPE.DELETED
+        elif t == "M":
+            edit_type = EDIT_TYPE.MODIFIED
+        elif t == "R":
+            edit_type = EDIT_TYPE.RENAMED
+        return edit_type
+
+    @staticmethod
+    def _get_file_extensions(filenames):
+        """
+        Return a list of file extensions from a list of filenames.
+        The returned extensions will include the dot "." prefix,
+        to accommodate for the dots in the existing language_extension_map settings.
+        Filenames with no extension will return an empty string for the extension.
+
+        Args:
+        - filenames: a list of filenames
+
+        Returns:
+        - list: A list of file extensions, including the dot "." prefix.
+        """
+        extensions = []
+        for filename in filenames:
+            filename, ext = os.path.splitext(filename)
+            if ext:
+                extensions.append(ext.lower())
+            else:
+                extensions.append("")
+        return extensions
+
+    @staticmethod
+    def _get_language_percentages(extensions):
+        """
+        Return a dictionary containing the programming language name (as the key),
+        and the percentage that language is used (as the value),
+        given a list of file extensions.
+
+        Args:
+        - extensions: a list of file extensions
+
+        Returns:
+        - dict: A dictionary where each key is a language name and the corresponding value is the percentage of that language in the PR.
+        """
+        total_files = len(extensions)
+        if total_files == 0:
+            return {}
+
+        # Identify language by file extension and count
+        lang_count = Counter(extensions)
+        # Convert counts to percentages
+        lang_percentage = {
+            lang: round(count / total_files * 100) for lang, count in lang_count.items()
+        }
+        return lang_percentage

pr_agent/git_providers/gerrit_provider.py

@@ -0,0 +1,399 @@
+import json
+import os
+import pathlib
+import shutil
+import subprocess
+import uuid
+from collections import Counter, namedtuple
+from pathlib import Path
+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
+from pr_agent.algo.types import EDIT_TYPE, FilePatchInfo
+from pr_agent.git_providers.local_git_provider import PullRequestMimic
+from pr_agent.log import get_logger
+
+
+def _call(*command, **kwargs) -> (int, str, str):
+    res = subprocess.run(
+        command,
+        stdout=subprocess.PIPE,
+        stderr=subprocess.PIPE,
+        check=True,
+        **kwargs,
+    )
+    return res.stdout.decode()
+
+
+def clone(url, directory):
+    get_logger().info("Cloning %s to %s", url, directory)
+    stdout = _call('git', 'clone', "--depth", "1", url, directory)
+    get_logger().info(stdout)
+
+
+def fetch(url, refspec, cwd):
+    get_logger().info("Fetching %s %s", url, refspec)
+    stdout = _call(
+        'git', 'fetch', '--depth', '2', url, refspec,
+        cwd=cwd
+    )
+    get_logger().info(stdout)
+
+
+def checkout(cwd):
+    get_logger().info("Checking out")
+    stdout = _call('git', 'checkout', "FETCH_HEAD", cwd=cwd)
+    get_logger().info(stdout)
+
+
+def show(*args, cwd=None):
+    get_logger().info("Show")
+    return _call('git', 'show', *args, cwd=cwd)
+
+
+def diff(*args, cwd=None):
+    get_logger().info("Diff")
+    patch = _call('git', 'diff', *args, cwd=cwd)
+    if not patch:
+        get_logger().warning("No changes found")
+        return
+    return patch
+
+
+def reset_local_changes(cwd):
+    get_logger().info("Reset local changes")
+    _call('git', 'checkout', "--force", cwd=cwd)
+
+
+def add_comment(url: urllib3.util.Url, refspec, message):
+    *_, patchset, changenum = refspec.rsplit("/")
+    message = "'" + message.replace("'", "'\"'\"'") + "'"
+    return _call(
+        "ssh",
+        "-p", str(url.port),
+        f"{url.auth}@{url.host}",
+        "gerrit", "review",
+        "--message", message,
+        # "--code-review", score,
+        f"{patchset},{changenum}",
+    )
+
+
+def list_comments(url: urllib3.util.Url, refspec):
+    *_, patchset, _ = refspec.rsplit("/")
+    stdout = _call(
+        "ssh",
+        "-p", str(url.port),
+        f"{url.auth}@{url.host}",
+        "gerrit", "query",
+        "--comments",
+        "--current-patch-set", patchset,
+        "--format", "JSON",
+    )
+    change_set, *_ = stdout.splitlines()
+    return json.loads(change_set)["currentPatchSet"]["comments"]
+
+
+def prepare_repo(url: urllib3.util.Url, project, refspec):
+    repo_url = (f"{url.scheme}://{url.auth}@{url.host}:{url.port}/{project}")
+
+    directory = pathlib.Path(mkdtemp())
+    clone(repo_url, directory),
+    fetch(repo_url, refspec, cwd=directory)
+    checkout(cwd=directory)
+    return directory
+
+
+def adopt_to_gerrit_message(message):
+    lines = message.splitlines()
+    buf = []
+    for line in lines:
+        # remove markdown formatting
+        line = (line.replace("*", "")
+                .replace("``", "`")
+                .replace("<details>", "")
+                .replace("</details>", "")
+                .replace("<summary>", "")
+                .replace("</summary>", ""))
+
+        line = line.strip()
+        if line.startswith('#'):
+            buf.append("\n" +
+                       line.replace('#', '').removesuffix(":").strip() +
+                       ":")
+            continue
+        elif line.startswith('-'):
+            buf.append(line.removeprefix('-').strip())
+            continue
+        else:
+            buf.append(line)
+    return "\n".join(buf).strip()
+
+
+def add_suggestion(src_filename, context: str, start, end: int):
+    with (
+        NamedTemporaryFile("w", delete=False) as tmp,
+        open(src_filename, "r") as src
+    ):
+        lines = src.readlines()
+        tmp.writelines(lines[:start - 1])
+        if context:
+            tmp.write(context)
+        tmp.writelines(lines[end:])
+
+    shutil.copy(tmp.name, src_filename)
+    os.remove(tmp.name)
+
+
+def upload_patch(patch, path):
+    patch_server_endpoint = get_settings().get(
+        'gerrit.patch_server_endpoint')
+    patch_server_token = get_settings().get(
+        'gerrit.patch_server_token')
+
+    response = requests.post(
+        patch_server_endpoint,
+        json={
+            "content": patch,
+            "path": path,
+        },
+        headers={
+            "Content-Type": "application/json",
+            "Authorization": f"Bearer {patch_server_token}",
+        }
+    )
+    response.raise_for_status()
+    patch_server_endpoint = patch_server_endpoint.rstrip("/")
+    return patch_server_endpoint + "/" + path
+
+
+class GerritProvider(GitProvider):
+
+    def __init__(self, key: str, incremental=False):
+        self.project, self.refspec = key.split(':')
+        assert self.project, "Project name is required"
+        assert self.refspec, "Refspec is required"
+        base_url = get_settings().get('gerrit.url')
+        assert base_url, "Gerrit URL is required"
+        user = get_settings().get('gerrit.user')
+        assert user, "Gerrit user is required"
+
+        parsed = urllib3.util.parse_url(base_url)
+        self.parsed_url = urllib3.util.parse_url(
+            f"{parsed.scheme}://{user}@{parsed.host}:{parsed.port}"
+        )
+
+        self.repo_path = prepare_repo(
+            self.parsed_url, self.project, self.refspec
+        )
+        self.repo = Repo(self.repo_path)
+        assert self.repo
+        self.pr_url = base_url
+        self.pr = PullRequestMimic(self.get_pr_title(), self.get_diff_files())
+
+    def get_pr_title(self):
+        """
+        Substitutes the branch-name as the PR-mimic title.
+        """
+        return self.repo.branches[0].name
+
+    def get_issue_comments(self):
+        comments = list_comments(self.parsed_url, self.refspec)
+        Comments = namedtuple('Comments', ['reversed'])
+        Comment = namedtuple('Comment', ['body'])
+        return Comments([Comment(c['message']) for c in reversed(comments)])
+
+    def get_pr_labels(self):
+        raise NotImplementedError(
+            'Getting labels is not implemented for the gerrit provider')
+
+    def add_eyes_reaction(self, issue_comment_id: int, disable_eyes: bool = False):
+        raise NotImplementedError(
+            'Adding reactions is not implemented for the gerrit provider')
+
+    def remove_reaction(self, issue_comment_id: int, reaction_id: int):
+        raise NotImplementedError(
+            'Removing reactions is not implemented for the gerrit provider')
+
+    def get_commit_messages(self):
+        return [self.repo.head.commit.message]
+
+    def get_repo_settings(self):
+        try:
+            with open(self.repo_path / ".pr_agent.toml", 'rb') as f:
+                contents = f.read()
+            return contents
+        except OSError:
+            return b""
+
+    def get_diff_files(self) -> list[FilePatchInfo]:
+        diffs = self.repo.head.commit.diff(
+            self.repo.head.commit.parents[0],  # previous commit
+            create_patch=True,
+            R=True
+        )
+
+        diff_files = []
+        for diff_item in diffs:
+            if diff_item.a_blob is not None:
+                original_file_content_str = (
+                    diff_item.a_blob.data_stream.read().decode('utf-8')
+                )
+            else:
+                original_file_content_str = ""  # empty file
+            if diff_item.b_blob is not None:
+                new_file_content_str = diff_item.b_blob.data_stream.read(). \
+                    decode('utf-8')
+            else:
+                new_file_content_str = ""  # empty file
+            edit_type = EDIT_TYPE.MODIFIED
+            if diff_item.new_file:
+                edit_type = EDIT_TYPE.ADDED
+            elif diff_item.deleted_file:
+                edit_type = EDIT_TYPE.DELETED
+            elif diff_item.renamed_file:
+                edit_type = EDIT_TYPE.RENAMED
+            diff_files.append(
+                FilePatchInfo(
+                    original_file_content_str,
+                    new_file_content_str,
+                    diff_item.diff.decode('utf-8'),
+                    diff_item.b_path,
+                    edit_type=edit_type,
+                    old_filename=None
+                    if diff_item.a_path == diff_item.b_path
+                    else diff_item.a_path
+                )
+            )
+        self.diff_files = diff_files
+        return diff_files
+
+    def get_files(self):
+        diff_index = self.repo.head.commit.diff(
+            self.repo.head.commit.parents[0],  # previous commit
+            R=True
+        )
+        # Get the list of changed files
+        diff_files = [item.a_path for item in diff_index]
+        return diff_files
+
+    def get_languages(self):
+        """
+        Calculate percentage of languages in repository. Used for hunk
+        prioritisation.
+        """
+        # Get all files in repository
+        filepaths = [Path(item.path) for item in
+                     self.repo.tree().traverse() if item.type == 'blob']
+        # Identify language by file extension and count
+        lang_count = Counter(
+            ext.lstrip('.') for filepath in filepaths for ext in
+            [filepath.suffix.lower()])
+        # Convert counts to percentages
+        total_files = len(filepaths)
+        lang_percentage = {lang: count / total_files * 100 for lang, count
+                           in lang_count.items()}
+        return lang_percentage
+
+    def get_pr_description_full(self):
+        return self.repo.head.commit.message
+
+    def get_user_id(self):
+        return self.repo.head.commit.author.email
+
+    def is_supported(self, capability: str) -> bool:
+        if capability in [
+            # 'get_issue_comments',
+            'create_inline_comment',
+            'publish_inline_comments',
+            'get_labels',
+            'gfm_markdown'
+        ]:
+            return False
+        return True
+
+    def split_suggestion(self, msg) -> tuple[str, str]:
+        is_code_context = False
+        description = []
+        context = []
+        for line in msg.splitlines():
+            if line.startswith('```suggestion'):
+                is_code_context = True
+                continue
+            if line.startswith('```'):
+                is_code_context = False
+                continue
+            if is_code_context:
+                context.append(line)
+            else:
+                description.append(
+                    line.replace('*', '')
+                )
+
+        return (
+            '\n'.join(description),
+            '\n'.join(context) + '\n' if context else ''
+        )
+
+    def publish_code_suggestions(self, code_suggestions: list):
+        msg = []
+        for suggestion in code_suggestions:
+            description, code = self.split_suggestion(suggestion['body'])
+            add_suggestion(
+                pathlib.Path(self.repo_path) / suggestion["relevant_file"],
+                code,
+                suggestion["relevant_lines_start"],
+                suggestion["relevant_lines_end"],
+            )
+            patch = diff(cwd=self.repo_path)
+            patch_id = uuid.uuid4().hex[0:4]
+            path = "/".join(["codium-ai", self.refspec, patch_id])
+            full_path = upload_patch(patch, path)
+            reset_local_changes(self.repo_path)
+            msg.append(f'* {description}\n{full_path}')
+
+        if msg:
+            add_comment(self.parsed_url, self.refspec, "\n".join(msg))
+            return True
+
+    def publish_comment(self, pr_comment: str, is_temporary: bool = False):
+        if not is_temporary:
+            msg = adopt_to_gerrit_message(pr_comment)
+            add_comment(self.parsed_url, self.refspec, msg)
+
+    def publish_description(self, pr_title: str, pr_body: str):
+        msg = adopt_to_gerrit_message(pr_body)
+        add_comment(self.parsed_url, self.refspec, pr_title + '\n' + msg)
+
+    def publish_inline_comments(self, comments: list[dict]):
+        raise NotImplementedError(
+            'Publishing inline comments is not implemented for the gerrit '
+            'provider')
+
+    def publish_inline_comment(self, body: str, relevant_file: str,
+                               relevant_line_in_file: str):
+        raise NotImplementedError(
+            'Publishing inline comments is not implemented for the gerrit '
+            'provider')
+
+
+    def publish_labels(self, labels):
+        # Not applicable to the local git provider,
+        # but required by the interface
+        pass
+
+    def remove_initial_comment(self):
+        # remove repo, cloned in previous steps
+        # shutil.rmtree(self.repo_path)
+        pass
+
+    def remove_comment(self, comment):
+        pass
+
+    def get_pr_branch(self):
+        return self.repo.head

pr_agent/git_providers/git_provider.py

@@ -1,26 +1,18 @@
 from abc import ABC, abstractmethod
-from dataclasses import dataclass
 
 # enum EDIT_TYPE (ADDED, DELETED, MODIFIED, RENAMED)
-from enum import Enum
-class EDIT_TYPE(Enum):
-    ADDED = 1
-    DELETED = 2
-    MODIFIED = 3
-    RENAMED = 4
+from typing import Optional
 
-@dataclass
-class FilePatchInfo:
-    base_file: str
-    head_file: str
-    patch: str
-    filename: str
-    tokens: int = -1
-    edit_type: EDIT_TYPE = EDIT_TYPE.MODIFIED
-    old_filename: str = None
+from pr_agent.config_loader import get_settings
+from pr_agent.algo.types import FilePatchInfo
+from pr_agent.log import get_logger
 
 
 class GitProvider(ABC):
+    @abstractmethod
+    def is_supported(self, capability: str) -> bool:
+        pass
+
     @abstractmethod
     def get_diff_files(self) -> list[FilePatchInfo]:
         pass
@@ -30,20 +22,7 @@ class GitProvider(ABC):
         pass
 
     @abstractmethod
-    def publish_comment(self, pr_comment: str, is_temporary: bool = False):
-        pass
-
-    @abstractmethod
-    def publish_inline_comment(self, body: str, relevant_file: str, relevant_line_in_file: str):
-        pass
-
-    @abstractmethod
-    def publish_code_suggestion(self, body: str, relevant_file: str,
-                                relevant_lines_start: int, relevant_lines_end: int):
-        pass
-
-    @abstractmethod
-    def remove_initial_comment(self):
+    def publish_code_suggestions(self, code_suggestions: list) -> bool:
         pass
 
     @abstractmethod
@@ -59,46 +38,241 @@ class GitProvider(ABC):
         pass
 
     @abstractmethod
-    def get_pr_description(self):
+    def get_pr_description_full(self) -> str:
         pass
 
+    def edit_comment(self, comment, body: str):
+        pass
+
+    def reply_to_comment_from_comment_id(self, comment_id: int, body: str):
+        pass
+
+    def get_pr_description(self, *, full: bool = True) -> str:
+        from pr_agent.config_loader import get_settings
+        from pr_agent.algo.utils import clip_tokens
+        max_tokens_description = get_settings().get("CONFIG.MAX_DESCRIPTION_TOKENS", None)
+        description = self.get_pr_description_full() if full else self.get_user_description()
+        if max_tokens_description:
+            return clip_tokens(description, max_tokens_description)
+        return description
+
+    def get_user_description(self) -> str:
+        if hasattr(self, 'user_description') and not (self.user_description is None):
+            return self.user_description
+
+        description = (self.get_pr_description_full() or "").strip()
+        description_lowercase = description.lower()
+        get_logger().debug(f"Existing description", description=description_lowercase)
+
+        # if the existing description wasn't generated by the pr-agent, just return it as-is
+        if not self._is_generated_by_pr_agent(description_lowercase):
+            get_logger().info(f"Existing description was not generated by the pr-agent")
+            return description
+
+        # if the existing description was generated by the pr-agent, but it doesn't contain a user description,
+        # return nothing (empty string) because it means there is no user description
+        user_description_header = "## **user description**"
+        if user_description_header not in description_lowercase:
+            get_logger().info(f"Existing description was generated by the pr-agent, but it doesn't contain a user description")
+            return ""
+
+        # otherwise, extract the original user description from the existing pr-agent description and return it
+        # user_description_start_position = description_lowercase.find(user_description_header) + len(user_description_header)
+        # return description[user_description_start_position:].split("\n", 1)[-1].strip()
+
+        # the 'user description' is in the beginning. extract and return it
+        possible_headers = self._possible_headers()
+        start_position = description_lowercase.find(user_description_header) + len(user_description_header)
+        end_position = len(description)
+        for header in possible_headers: # try to clip at the next header
+            if header != user_description_header and header in description_lowercase:
+                end_position = min(end_position, description_lowercase.find(header))
+        if end_position != len(description) and end_position > start_position:
+            original_user_description = description[start_position:end_position].strip()
+            if original_user_description.endswith("___"):
+                original_user_description = original_user_description[:-3].strip()
+        else:
+            original_user_description = description.split("___")[0].strip()
+            if original_user_description.lower().startswith(user_description_header):
+                original_user_description = original_user_description[len(user_description_header):].strip()
+
+        get_logger().info(f"Extracted user description from existing description",
+                          description=original_user_description)
+        self.user_description = original_user_description
+        return original_user_description
+
+    def _possible_headers(self):
+        return ("## **user description**", "## **pr type**", "## **pr description**", "## **pr labels**", "## **type**", "## **description**",
+                "## **labels**", "### 🤖 generated by pr agent")
+
+    def _is_generated_by_pr_agent(self, description_lowercase: str) -> bool:
+        possible_headers = self._possible_headers()
+        return any(description_lowercase.startswith(header) for header in possible_headers)
+
+    @abstractmethod
+    def get_repo_settings(self):
+        pass
+
+    def get_pr_id(self):
+        return ""
+
+    def get_line_link(self, relevant_file: str, relevant_line_start: int, relevant_line_end: int = None) -> str:
+        return ""
+
+    #### comments operations ####
+    @abstractmethod
+    def publish_comment(self, pr_comment: str, is_temporary: bool = False):
+        pass
+
+    def publish_persistent_comment(self, pr_comment: str, initial_header: str, update_header: bool, name='review'):
+        self.publish_comment(pr_comment)
+
+    @abstractmethod
+    def publish_inline_comment(self, body: str, relevant_file: str, relevant_line_in_file: str):
+        pass
+
+    def create_inline_comment(self, body: str, relevant_file: str, relevant_line_in_file: str,
+                              absolute_position: int = None):
+        raise NotImplementedError("This git provider does not support creating inline comments yet")
+
+    @abstractmethod
+    def publish_inline_comments(self, comments: list[dict]):
+        pass
+
+    @abstractmethod
+    def remove_initial_comment(self):
+        pass
+
+    @abstractmethod
+    def remove_comment(self, comment):
+        pass
+
+    @abstractmethod
+    def get_issue_comments(self):
+        pass
+
+    def get_comment_url(self, comment) -> str:
+        return ""
+
+    #### labels operations ####
+    @abstractmethod
+    def publish_labels(self, labels):
+        pass
+
+    @abstractmethod
+    def get_pr_labels(self):
+        pass
+
+    def get_repo_labels(self):
+        pass
+
+    @abstractmethod
+    def add_eyes_reaction(self, issue_comment_id: int, disable_eyes: bool = False) -> Optional[int]:
+        pass
+
+    @abstractmethod
+    def remove_reaction(self, issue_comment_id: int, reaction_id: int) -> bool:
+        pass
+
+    #### commits operations ####
+    @abstractmethod
+    def get_commit_messages(self):
+        pass
+
+    def get_pr_url(self) -> str:
+        if hasattr(self, 'pr_url'):
+            return self.pr_url
+        return ""
+
+    def get_latest_commit_url(self) -> str:
+        return ""
+
+    def auto_approve(self) -> bool:
+        return False
+
+    def calc_pr_statistics(self, pull_request_data: dict):
+        return {}
+
 
 def get_main_pr_language(languages, files) -> str:
     """
     Get the main language of the commit. Return an empty string if cannot determine.
     """
     main_language_str = ""
+    if not languages:
+        get_logger().info("No languages detected")
+        return main_language_str
+    if not files:
+        get_logger().info("No files in diff")
+        return main_language_str
+
     try:
         top_language = max(languages, key=languages.get).lower()
 
         # validate that the specific commit uses the main language
         extension_list = []
         for file in files:
+            if not file:
+                continue
+            if isinstance(file, str):
+                file = FilePatchInfo(base_file=None, head_file=None, patch=None, filename=file)
             extension_list.append(file.filename.rsplit('.')[-1])
 
         # get the most common extension
-        most_common_extension = max(set(extension_list), key=extension_list.count)
+        most_common_extension = '.' + max(set(extension_list), key=extension_list.count)
+        try:
+            language_extension_map_org = get_settings().language_extension_map_org
+            language_extension_map = {k.lower(): v for k, v in language_extension_map_org.items()}
 
-        # look for a match. TBD: add more languages, do this systematically
-        if most_common_extension == 'py' and top_language == 'python' or \
-                most_common_extension == 'js' and top_language == 'javascript' or \
-                most_common_extension == 'ts' and top_language == 'typescript' or \
-                most_common_extension == 'go' and top_language == 'go' or \
-                most_common_extension == 'java' and top_language == 'java' or \
-                most_common_extension == 'c' and top_language == 'c' or \
-                most_common_extension == 'cpp' and top_language == 'c++' or \
-                most_common_extension == 'cs' and top_language == 'c#' or \
-                most_common_extension == 'swift' and top_language == 'swift' or \
-                most_common_extension == 'php' and top_language == 'php' or \
-                most_common_extension == 'rb' and top_language == 'ruby' or \
-                most_common_extension == 'rs' and top_language == 'rust' or \
-                most_common_extension == 'scala' and top_language == 'scala' or \
-                most_common_extension == 'kt' and top_language == 'kotlin' or \
-                most_common_extension == 'pl' and top_language == 'perl' or \
-                most_common_extension == 'swift' and top_language == 'swift':
-            main_language_str = top_language
+            if top_language in language_extension_map and most_common_extension in language_extension_map[top_language]:
+                main_language_str = top_language
+            else:
+                for language, extensions in language_extension_map.items():
+                    if most_common_extension in extensions:
+                        main_language_str = language
+                        break
+        except Exception as e:
+            get_logger().exception(f"Failed to get main language: {e}")
+            pass
 
-    except Exception:
+        ## old approach:
+        # most_common_extension = max(set(extension_list), key=extension_list.count)
+        # if most_common_extension == 'py' and top_language == 'python' or \
+        #         most_common_extension == 'js' and top_language == 'javascript' or \
+        #         most_common_extension == 'ts' and top_language == 'typescript' or \
+        #         most_common_extension == 'tsx' and top_language == 'typescript' or \
+        #         most_common_extension == 'go' and top_language == 'go' or \
+        #         most_common_extension == 'java' and top_language == 'java' or \
+        #         most_common_extension == 'c' and top_language == 'c' or \
+        #         most_common_extension == 'cpp' and top_language == 'c++' or \
+        #         most_common_extension == 'cs' and top_language == 'c#' or \
+        #         most_common_extension == 'swift' and top_language == 'swift' or \
+        #         most_common_extension == 'php' and top_language == 'php' or \
+        #         most_common_extension == 'rb' and top_language == 'ruby' or \
+        #         most_common_extension == 'rs' and top_language == 'rust' or \
+        #         most_common_extension == 'scala' and top_language == 'scala' or \
+        #         most_common_extension == 'kt' and top_language == 'kotlin' or \
+        #         most_common_extension == 'pl' and top_language == 'perl' or \
+        #         most_common_extension == top_language:
+        #     main_language_str = top_language
+
+    except Exception as e:
+        get_logger().exception(e)
         pass
 
     return main_language_str
+
+class IncrementalPR:
+    def __init__(self, is_incremental: bool = False):
+        self.is_incremental = is_incremental
+        self.commits_range = None
+        self.first_new_commit = None
+        self.last_seen_commit = None
+
+    @property
+    def first_new_commit_sha(self):
+        return None if self.first_new_commit is None else self.first_new_commit.sha
+
+    @property
+    def last_seen_commit_sha(self):
+        return None if self.last_seen_commit is None else self.last_seen_commit.sha

pr_agent/git_providers/github_provider.py

@@ -1,50 +1,226 @@
-import logging
+import time
+import hashlib
 from datetime import datetime
 from typing import Optional, Tuple
 from urllib.parse import urlparse
 
-from github import AppAuthentication, Github
+from github import AppAuthentication, Auth, Github, GithubException
+from retry import retry
+from starlette_context import context
 
-from pr_agent.config_loader import settings
-
-from .git_provider import FilePatchInfo, GitProvider
+from ..algo.language_handler import is_valid_file
+from ..algo.utils import load_large_diff, clip_tokens, find_line_number_of_relevant_line_in_file
+from ..config_loader import get_settings
+from ..log import get_logger
+from ..servers.utils import RateLimitExceeded
+from .git_provider import GitProvider, IncrementalPR
+from pr_agent.algo.types import EDIT_TYPE, FilePatchInfo
 
 
 class GithubProvider(GitProvider):
-    def __init__(self, pr_url: Optional[str] = None):
-        self.installation_id = settings.get("GITHUB.INSTALLATION_ID")
+    def __init__(self, pr_url: Optional[str] = None, incremental=IncrementalPR(False)):
+        self.repo_obj = None
+        try:
+            self.installation_id = context.get("installation_id", None)
+        except Exception:
+            self.installation_id = None
+        self.base_url = get_settings().get("GITHUB.BASE_URL", "https://api.github.com").rstrip("/")
+        self.base_url_html = self.base_url.split("api/")[0].rstrip("/") if "api/" in self.base_url else "https://github.com"
         self.github_client = self._get_github_client()
         self.repo = None
         self.pr_num = None
         self.pr = None
         self.github_user_id = None
         self.diff_files = None
-        if pr_url:
+        self.git_files = None
+        self.incremental = incremental
+        if pr_url and 'pull' in pr_url:
             self.set_pr(pr_url)
-            self.last_commit_id = list(self.pr.get_commits())[-1]
+            self.pr_commits = list(self.pr.get_commits())
+            if self.incremental.is_incremental:
+                self.get_incremental_commits()
+            self.last_commit_id = self.pr_commits[-1]
+            self.pr_url = self.get_pr_url() # pr_url for github actions can be as api.github.com, so we need to get the url from the pr object
+        else:
+            self.pr_commits = None
+
+    def is_supported(self, capability: str) -> bool:
+        return True
+
+    def get_pr_url(self) -> str:
+        return self.pr.html_url
 
     def set_pr(self, pr_url: str):
         self.repo, self.pr_num = self._parse_pr_url(pr_url)
         self.pr = self._get_pr()
 
-    def get_files(self):
-        return self.pr.get_files()
+    def get_incremental_commits(self):
+        if not self.pr_commits:
+            self.pr_commits = list(self.pr.get_commits())
 
+        self.previous_review = self.get_previous_review(full=True, incremental=True)
+        if self.previous_review:
+            self.incremental.commits_range = self.get_commit_range()
+            # Get all files changed during the commit range
+            self.file_set = dict()
+            for commit in self.incremental.commits_range:
+                if commit.commit.message.startswith(f"Merge branch '{self._get_repo().default_branch}'"):
+                    get_logger().info(f"Skipping merge commit {commit.commit.message}")
+                    continue
+                self.file_set.update({file.filename: file for file in commit.files})
+        else:
+            raise ValueError("No previous review found")
+
+    def get_commit_range(self):
+        last_review_time = self.previous_review.created_at
+        first_new_commit_index = None
+        for index in range(len(self.pr_commits) - 1, -1, -1):
+            if self.pr_commits[index].commit.author.date > last_review_time:
+                self.incremental.first_new_commit = self.pr_commits[index]
+                first_new_commit_index = index
+            else:
+                self.incremental.last_seen_commit = self.pr_commits[index]
+                break
+        return self.pr_commits[first_new_commit_index:] if first_new_commit_index is not None else []
+
+    def get_previous_review(self, *, full: bool, incremental: bool):
+        if not (full or incremental):
+            raise ValueError("At least one of full or incremental must be True")
+        if not getattr(self, "comments", None):
+            self.comments = list(self.pr.get_issue_comments())
+        prefixes = []
+        if full:
+            prefixes.append("## PR Review")
+        if incremental:
+            prefixes.append("## Incremental PR Review")
+        for index in range(len(self.comments) - 1, -1, -1):
+            if any(self.comments[index].body.startswith(prefix) for prefix in prefixes):
+                return self.comments[index]
+
+    def get_files(self):
+        if self.incremental.is_incremental and self.file_set:
+            return self.file_set.values()
+        try:
+            git_files = context.get("git_files", None)
+            if git_files:
+                return git_files
+            self.git_files = self.pr.get_files()
+            context["git_files"] = self.git_files
+            return self.git_files
+        except Exception:
+            if not self.git_files:
+                self.git_files = self.pr.get_files()
+            return self.git_files
+
+
+    @retry(exceptions=RateLimitExceeded,
+           tries=get_settings().github.ratelimit_retries, delay=2, backoff=2, jitter=(1, 3))
     def get_diff_files(self) -> list[FilePatchInfo]:
-        files = self.pr.get_files()
-        diff_files = []
-        for file in files:
-            original_file_content_str = self._get_pr_file_content(file, self.pr.base.sha)
-            new_file_content_str = self._get_pr_file_content(file, self.pr.head.sha)
-            diff_files.append(FilePatchInfo(original_file_content_str, new_file_content_str, file.patch, file.filename))
-        self.diff_files = diff_files
-        return diff_files
+        """
+        Retrieves the list of files that have been modified, added, deleted, or renamed in a pull request in GitHub,
+        along with their content and patch information.
+
+        Returns:
+            diff_files (List[FilePatchInfo]): List of FilePatchInfo objects representing the modified, added, deleted,
+            or renamed files in the merge request.
+        """
+        try:
+            try:
+                diff_files = context.get("diff_files", None)
+                if diff_files:
+                    return diff_files
+            except Exception:
+                pass
+
+            if self.diff_files:
+                return self.diff_files
+
+            files = self.get_files()
+            diff_files = []
+
+            for file in files:
+                if not is_valid_file(file.filename):
+                    continue
+
+                new_file_content_str = self._get_pr_file_content(file, self.pr.head.sha)  # communication with GitHub
+                patch = file.patch
+
+                if self.incremental.is_incremental and self.file_set:
+                    original_file_content_str = self._get_pr_file_content(file, self.incremental.last_seen_commit_sha)
+                    patch = load_large_diff(file.filename, new_file_content_str, original_file_content_str)
+                    self.file_set[file.filename] = patch
+                else:
+                    original_file_content_str = self._get_pr_file_content(file, self.pr.base.sha)
+                    if not patch:
+                        patch = load_large_diff(file.filename, new_file_content_str, original_file_content_str)
+
+                if file.status == 'added':
+                    edit_type = EDIT_TYPE.ADDED
+                elif file.status == 'removed':
+                    edit_type = EDIT_TYPE.DELETED
+                elif file.status == 'renamed':
+                    edit_type = EDIT_TYPE.RENAMED
+                elif file.status == 'modified':
+                    edit_type = EDIT_TYPE.MODIFIED
+                else:
+                    get_logger().error(f"Unknown edit type: {file.status}")
+                    edit_type = EDIT_TYPE.UNKNOWN
+
+                # count number of lines added and removed
+                patch_lines = patch.splitlines(keepends=True)
+                num_plus_lines = len([line for line in patch_lines if line.startswith('+')])
+                num_minus_lines = len([line for line in patch_lines if line.startswith('-')])
+                file_patch_canonical_structure = FilePatchInfo(original_file_content_str, new_file_content_str, patch,
+                                                               file.filename, edit_type=edit_type,
+                                                               num_plus_lines=num_plus_lines,
+                                                               num_minus_lines=num_minus_lines,)
+                diff_files.append(file_patch_canonical_structure)
+
+            self.diff_files = diff_files
+            try:
+                context["diff_files"] = diff_files
+            except Exception:
+                pass
+
+            return diff_files
+
+        except GithubException.RateLimitExceededException as e:
+            get_logger().error(f"Rate limit exceeded for GitHub API. Original message: {e}")
+            raise RateLimitExceeded("Rate limit exceeded for GitHub API.") from e
 
     def publish_description(self, pr_title: str, pr_body: str):
         self.pr.edit(title=pr_title, body=pr_body)
-        # self.pr.create_issue_comment(pr_comment)
+
+    def get_latest_commit_url(self) -> str:
+        return self.last_commit_id.html_url
+
+    def get_comment_url(self, comment) -> str:
+        return comment.html_url
+
+    def publish_persistent_comment(self, pr_comment: str, initial_header: str, update_header: bool = True, name='review'):
+        prev_comments = list(self.pr.get_issue_comments())
+        for comment in prev_comments:
+            body = comment.body
+            if body.startswith(initial_header):
+                latest_commit_url = self.get_latest_commit_url()
+                comment_url = self.get_comment_url(comment)
+                if update_header:
+                    updated_header = f"{initial_header}\n\n### ({name.capitalize()} updated until commit {latest_commit_url})\n"
+                    pr_comment_updated = pr_comment.replace(initial_header, updated_header)
+                else:
+                    pr_comment_updated = pr_comment
+                get_logger().info(f"Persistent mode- updating comment {comment_url} to latest review message")
+                response = comment.edit(pr_comment_updated)
+                self.publish_comment(
+                    f"**[Persistent {name}]({comment_url})** updated to latest commit {latest_commit_url}")
+                return
+        self.publish_comment(pr_comment)
 
     def publish_comment(self, pr_comment: str, is_temporary: bool = False):
+        if is_temporary and not get_settings().config.publish_output_progress:
+            get_logger().debug(f"Skipping publish_comment for temporary comment: {pr_comment}")
+            return
+
         response = self.pr.create_issue_comment(pr_comment)
         if hasattr(response, "user") and hasattr(response.user, "login"):
             self.github_user_id = response.user.login
@@ -52,52 +228,163 @@ class GithubProvider(GitProvider):
         if not hasattr(self.pr, 'comments_list'):
             self.pr.comments_list = []
         self.pr.comments_list.append(response)
+        return response
 
     def publish_inline_comment(self, body: str, relevant_file: str, relevant_line_in_file: str):
-        self.diff_files = self.diff_files if self.diff_files else self.get_diff_files()
-        position = -1
-        for file in self.diff_files:
-            if file.filename.strip() == relevant_file:
-                patch = file.patch
-                patch_lines = patch.splitlines()
-                for i, line in enumerate(patch_lines):
-                    if relevant_line_in_file in line:
-                        position = i
-                        break
-                    elif relevant_line_in_file[0] == '+' and relevant_line_in_file[1:] in line:
-                        # The model often adds a '+' to the beginning of the relevant_line_in_file even if originally
-                        # it's a context line
-                        position = i
-                        break
+        self.publish_inline_comments([self.create_inline_comment(body, relevant_file, relevant_line_in_file)])
+
+
+    def create_inline_comment(self, body: str, relevant_file: str, relevant_line_in_file: str,
+                              absolute_position: int = None):
+        position, absolute_position = find_line_number_of_relevant_line_in_file(self.diff_files,
+                                                                                relevant_file.strip('`'),
+                                                                                relevant_line_in_file,
+                                                                                absolute_position)
         if position == -1:
-            if settings.config.verbosity_level >= 2:
-                logging.info(f"Could not find position for {relevant_file} {relevant_line_in_file}")
+            if get_settings().config.verbosity_level >= 2:
+                get_logger().info(f"Could not find position for {relevant_file} {relevant_line_in_file}")
+            subject_type = "FILE"
         else:
-            path = relevant_file.strip()
-            self.pr.create_review_comment(body=body, commit_id=self.last_commit_id, path=path, position=position)
-
-    def publish_code_suggestion(self, body: str,
-                                relevant_file: str,
-                                relevant_lines_start: int,
-                                relevant_lines_end: int):
-        if not relevant_lines_start or relevant_lines_start == -1:
-            if settings.config.verbosity_level >= 2:
-                logging.exception(f"Failed to publish code suggestion, relevant_lines_start is {relevant_lines_start}")
-            return False
-
-        if relevant_lines_end<relevant_lines_start:
-            if settings.config.verbosity_level >= 2:
-                logging.exception(f"Failed to publish code suggestion, "
-                                  f"relevant_lines_end is {relevant_lines_end} and "
-                                  f"relevant_lines_start is {relevant_lines_start}")
-            return False
+            subject_type = "LINE"
+        path = relevant_file.strip()
+        return dict(body=body, path=path, position=position) if subject_type == "LINE" else {}
 
+    def publish_inline_comments(self, comments: list[dict], disable_fallback: bool = False):
         try:
-            import github.PullRequestComment
+            # publish all comments in a single message
+            self.pr.create_review(commit=self.last_commit_id, comments=comments)
+        except Exception as e:
+            if get_settings().config.verbosity_level >= 2:
+                get_logger().error(f"Failed to publish inline comments")
+
+            if (getattr(e, "status", None) == 422
+                    and get_settings().github.publish_inline_comments_fallback_with_verification and not disable_fallback):
+                pass  # continue to try _publish_inline_comments_fallback_with_verification
+            else:
+                raise e # will end up with publishing the comments one by one
+
+            try:
+                self._publish_inline_comments_fallback_with_verification(comments)
+            except Exception as e:
+                if get_settings().config.verbosity_level >= 2:
+                    get_logger().error(f"Failed to publish inline code comments fallback, error: {e}")
+                raise e
+
+    def _publish_inline_comments_fallback_with_verification(self, comments: list[dict]):
+        """
+        Check each inline comment separately against the GitHub API and discard of invalid comments,
+        then publish all the remaining valid comments in a single review.
+        For invalid comments, also try removing the suggestion part and posting the comment just on the first line.
+        """
+        verified_comments, invalid_comments = self._verify_code_comments(comments)
+
+        # publish as a group the verified comments
+        if verified_comments:
+            try:
+                self.pr.create_review(commit=self.last_commit_id, comments=verified_comments)
+            except:
+                pass
+
+        # try to publish one by one the invalid comments as a one-line code comment
+        if invalid_comments and get_settings().github.try_fix_invalid_inline_comments:
+            fixed_comments_as_one_liner = self._try_fix_invalid_inline_comments(
+                [comment for comment, _ in invalid_comments])
+            for comment in fixed_comments_as_one_liner:
+                try:
+                    self.publish_inline_comments([comment], disable_fallback=True)
+                    if get_settings().config.verbosity_level >= 2:
+                        get_logger().info(f"Published invalid comment as a single line comment: {comment}")
+                except:
+                    if get_settings().config.verbosity_level >= 2:
+                        get_logger().error(f"Failed to publish invalid comment as a single line comment: {comment}")
+
+    def _verify_code_comment(self, comment: dict):
+        is_verified = False
+        e = None
+        try:
+            # event ="" # By leaving this blank, you set the review action state to PENDING
+            input = dict(commit_id=self.last_commit_id.sha, comments=[comment])
+            headers, data = self.pr._requester.requestJsonAndCheck(
+                "POST", f"{self.pr.url}/reviews", input=input)
+            pending_review_id = data["id"]
+            is_verified = True
+        except Exception as err:
+            is_verified = False
+            pending_review_id = None
+            e = err
+        if pending_review_id is not None:
+            try:
+                self.pr._requester.requestJsonAndCheck("DELETE", f"{self.pr.url}/reviews/{pending_review_id}")
+            except Exception:
+                pass
+        return is_verified, e
+
+    def _verify_code_comments(self, comments: list[dict]) -> tuple[list[dict], list[tuple[dict, Exception]]]:
+        """Very each comment against the GitHub API and return 2 lists: 1 of verified and 1 of invalid comments"""
+        verified_comments = []
+        invalid_comments = []
+        for comment in comments:
+            time.sleep(1)  # for avoiding secondary rate limit
+            is_verified, e = self._verify_code_comment(comment)
+            if is_verified:
+                verified_comments.append(comment)
+            else:
+                invalid_comments.append((comment, e))
+        return verified_comments, invalid_comments
+
+    def _try_fix_invalid_inline_comments(self, invalid_comments: list[dict]) -> list[dict]:
+        """
+        Try fixing invalid comments by removing the suggestion part and setting the comment just on the first line.
+        Return only comments that have been modified in some way.
+        This is a best-effort attempt to fix invalid comments, and should be verified accordingly.
+        """
+        import copy
+        fixed_comments = []
+        for comment in invalid_comments:
+            try:
+                fixed_comment = copy.deepcopy(comment)  # avoid modifying the original comment dict for later logging
+                if "```suggestion" in comment["body"]:
+                    fixed_comment["body"] = comment["body"].split("```suggestion")[0]
+                if "start_line" in comment:
+                    fixed_comment["line"] = comment["start_line"]
+                    del fixed_comment["start_line"]
+                if "start_side" in comment:
+                    fixed_comment["side"] = comment["start_side"]
+                    del fixed_comment["start_side"]
+                if fixed_comment != comment:
+                    fixed_comments.append(fixed_comment)
+            except Exception as e:
+                if get_settings().config.verbosity_level >= 2:
+                    get_logger().error(f"Failed to fix inline comment, error: {e}")
+        return fixed_comments
+
+    def publish_code_suggestions(self, code_suggestions: list) -> bool:
+        """
+        Publishes code suggestions as comments on the PR.
+        """
+        post_parameters_list = []
+        for suggestion in code_suggestions:
+            body = suggestion['body']
+            relevant_file = suggestion['relevant_file']
+            relevant_lines_start = suggestion['relevant_lines_start']
+            relevant_lines_end = suggestion['relevant_lines_end']
+
+            if not relevant_lines_start or relevant_lines_start == -1:
+                if get_settings().config.verbosity_level >= 2:
+                    get_logger().exception(
+                        f"Failed to publish code suggestion, relevant_lines_start is {relevant_lines_start}")
+                continue
+
+            if relevant_lines_end < relevant_lines_start:
+                if get_settings().config.verbosity_level >= 2:
+                    get_logger().exception(f"Failed to publish code suggestion, "
+                                      f"relevant_lines_end is {relevant_lines_end} and "
+                                      f"relevant_lines_start is {relevant_lines_start}")
+                continue
+
             if relevant_lines_end > relevant_lines_start:
                 post_parameters = {
                     "body": body,
-                    "commit_id": self.last_commit_id._identity,
                     "path": relevant_file,
                     "line": relevant_lines_end,
                     "start_line": relevant_lines_start,
@@ -106,37 +393,50 @@ class GithubProvider(GitProvider):
             else:  # API is different for single line comments
                 post_parameters = {
                     "body": body,
-                    "commit_id": self.last_commit_id._identity,
                     "path": relevant_file,
                     "line": relevant_lines_start,
                     "side": "RIGHT",
                 }
-            headers, data = self.pr._requester.requestJsonAndCheck(
-                "POST", f"{self.pr.url}/comments", input=post_parameters
-            )
-            github.PullRequestComment.PullRequestComment(
-                self.pr._requester, headers, data, completed=True
-            )
+            post_parameters_list.append(post_parameters)
+
+        try:
+            self.publish_inline_comments(post_parameters_list)
             return True
         except Exception as e:
-            if settings.config.verbosity_level >= 2:
-                logging.error(f"Failed to publish code suggestion, error: {e}")
+            if get_settings().config.verbosity_level >= 2:
+                get_logger().error(f"Failed to publish code suggestion, error: {e}")
             return False
 
+    def edit_comment(self, comment, body: str):
+        comment.edit(body=body)
+
+    def reply_to_comment_from_comment_id(self, comment_id: int, body: str):
+        try:
+            # self.pr.get_issue_comment(comment_id).edit(body)
+            headers, data_patch = self.pr._requester.requestJsonAndCheck(
+                "POST", f"{self.base_url}/repos/{self.repo}/pulls/{self.pr_num}/comments/{comment_id}/replies",
+                input={"body": body}
+            )
+        except Exception as e:
+            get_logger().exception(f"Failed to reply comment, error: {e}")
+
     def remove_initial_comment(self):
         try:
-            for comment in self.pr.comments_list:
+            for comment in getattr(self.pr, 'comments_list', []):
                 if comment.is_temporary:
-                    comment.delete()
+                    self.remove_comment(comment)
         except Exception as e:
-            logging.exception(f"Failed to remove initial comment, error: {e}")
+            get_logger().exception(f"Failed to remove initial comment, error: {e}")
+
+    def remove_comment(self, comment):
+        try:
+            comment.delete()
+        except Exception as e:
+            get_logger().exception(f"Failed to remove comment, error: {e}")
 
     def get_title(self):
         return self.pr.title
 
-    def get_description(self):
-        return self.pr.body
-
     def get_languages(self):
         languages = self._get_repo().get_languages()
         return languages
@@ -144,19 +444,20 @@ class GithubProvider(GitProvider):
     def get_pr_branch(self):
         return self.pr.head.ref
 
-    def get_pr_description(self):
+    def get_pr_description_full(self):
         return self.pr.body
 
     def get_user_id(self):
         if not self.github_user_id:
             try:
-                self.github_user_id = self.github_client.get_user().login
+                self.github_user_id = self.github_client.get_user().raw_data['login']
             except Exception as e:
-                logging.exception(f"Failed to get user id, error: {e}")
+                self.github_user_id = ""
+                # logging.exception(f"Failed to get user id, error: {e}")
         return self.github_user_id
 
     def get_notifications(self, since: datetime):
-        deployment_type = settings.get("GITHUB.DEPLOYMENT_TYPE", "user")
+        deployment_type = get_settings().get("GITHUB.DEPLOYMENT_TYPE", "user")
 
         if deployment_type != 'user':
             raise ValueError("Deployment mode must be set to 'user' to get notifications")
@@ -164,6 +465,44 @@ class GithubProvider(GitProvider):
         notifications = self.github_client.get_user().get_notifications(since=since)
         return notifications
 
+    def get_issue_comments(self):
+        return self.pr.get_issue_comments()
+
+    def get_repo_settings(self):
+        try:
+            # 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 ""
+
+    def add_eyes_reaction(self, issue_comment_id: int, disable_eyes: bool = False) -> Optional[int]:
+        if disable_eyes:
+            return None
+        try:
+            headers, data_patch = self.pr._requester.requestJsonAndCheck(
+                "POST", f"{self.base_url}/repos/{self.repo}/issues/comments/{issue_comment_id}/reactions",
+                input={"content": "eyes"}
+            )
+            return data_patch.get("id", None)
+        except Exception as e:
+            get_logger().exception(f"Failed to add eyes reaction, error: {e}")
+            return None
+
+    def remove_reaction(self, issue_comment_id: int, reaction_id: str) -> bool:
+        try:
+            # self.pr.get_issue_comment(issue_comment_id).delete_reaction(reaction_id)
+            headers, data_patch = self.pr._requester.requestJsonAndCheck(
+                "DELETE",
+                f"{self.base_url}/repos/{self.repo}/issues/comments/{issue_comment_id}/reactions/{reaction_id}"
+            )
+            return True
+        except Exception as e:
+            get_logger().exception(f"Failed to remove eyes reaction, error: {e}")
+            return False
+
     @staticmethod
     def _parse_pr_url(pr_url: str) -> Tuple[str, int]:
         parsed_url = urlparse(pr_url)
@@ -193,32 +532,68 @@ class GithubProvider(GitProvider):
 
         return repo_name, pr_number
 
+    @staticmethod
+    def _parse_issue_url(issue_url: str) -> Tuple[str, int]:
+        parsed_url = urlparse(issue_url)
+
+        if 'github.com' not in parsed_url.netloc:
+            raise ValueError("The provided URL is not a valid GitHub URL")
+
+        path_parts = parsed_url.path.strip('/').split('/')
+        if 'api.github.com' in parsed_url.netloc:
+            if len(path_parts) < 5 or path_parts[3] != 'issues':
+                raise ValueError("The provided URL does not appear to be a GitHub ISSUE URL")
+            repo_name = '/'.join(path_parts[1:3])
+            try:
+                issue_number = int(path_parts[4])
+            except ValueError as e:
+                raise ValueError("Unable to convert issue number to integer") from e
+            return repo_name, issue_number
+
+        if len(path_parts) < 4 or path_parts[2] != 'issues':
+            raise ValueError("The provided URL does not appear to be a GitHub PR issue")
+
+        repo_name = '/'.join(path_parts[:2])
+        try:
+            issue_number = int(path_parts[3])
+        except ValueError as e:
+            raise ValueError("Unable to convert issue number to integer") from e
+
+        return repo_name, issue_number
+
     def _get_github_client(self):
-        deployment_type = settings.get("GITHUB.DEPLOYMENT_TYPE", "user")
+        deployment_type = get_settings().get("GITHUB.DEPLOYMENT_TYPE", "user")
 
         if deployment_type == 'app':
             try:
-                private_key = settings.github.private_key
-                app_id = settings.github.app_id
+                private_key = get_settings().github.private_key
+                app_id = get_settings().github.app_id
             except AttributeError as e:
                 raise ValueError("GitHub app ID and private key are required when using GitHub app deployment") from e
             if not self.installation_id:
                 raise ValueError("GitHub app installation ID is required when using GitHub app deployment")
             auth = AppAuthentication(app_id=app_id, private_key=private_key,
                                      installation_id=self.installation_id)
-            return Github(app_auth=auth)
+            return Github(app_auth=auth, base_url=self.base_url)
 
         if deployment_type == 'user':
             try:
-                token = settings.github.user_token
+                token = get_settings().github.user_token
             except AttributeError as e:
                 raise ValueError(
                     "GitHub token is required when using user deployment. See: "
                     "https://github.com/Codium-ai/pr-agent#method-2-run-from-source") from e
-            return Github(token)
+            return Github(auth=Auth.Token(token), base_url=self.base_url)
 
     def _get_repo(self):
-        return self.github_client.get_repo(self.repo)
+        if hasattr(self, 'repo_obj') and \
+                hasattr(self.repo_obj, 'full_name') and \
+                self.repo_obj.full_name == self.repo:
+            return self.repo_obj
+        else:
+            self.repo_obj = self.github_client.get_repo(self.repo)
+            return self.repo_obj
+
 
     def _get_pr(self):
         return self._get_repo().get_pull(self.pr_num)
@@ -229,3 +604,121 @@ class GithubProvider(GitProvider):
         except Exception:
             file_content_str = ""
         return file_content_str
+
+    def publish_labels(self, pr_types):
+        try:
+            label_color_map = {"Bug fix": "1d76db", "Tests": "e99695", "Bug fix with tests": "c5def5",
+                               "Enhancement": "bfd4f2", "Documentation": "d4c5f9",
+                               "Other": "d1bcf9"}
+            post_parameters = []
+            for p in pr_types:
+                color = label_color_map.get(p, "d1bcf9")  # default to "Other" color
+                post_parameters.append({"name": p, "color": color})
+            headers, data = self.pr._requester.requestJsonAndCheck(
+                "PUT", f"{self.pr.issue_url}/labels", input=post_parameters
+            )
+        except Exception as e:
+            get_logger().exception(f"Failed to publish labels, error: {e}")
+
+    def get_pr_labels(self):
+        try:
+            return [label.name for label in self.pr.labels]
+        except Exception as e:
+            get_logger().exception(f"Failed to get labels, error: {e}")
+            return []
+
+    def get_repo_labels(self):
+        labels = self.repo_obj.get_labels()
+        return [label for label in labels]
+
+    def get_commit_messages(self):
+        """
+        Retrieves the commit messages of a pull request.
+
+        Returns:
+            str: A string containing the commit messages of the pull request.
+        """
+        max_tokens = get_settings().get("CONFIG.MAX_COMMITS_TOKENS", None)
+        try:
+            commit_list = self.pr.get_commits()
+            commit_messages = [commit.commit.message for commit in commit_list]
+            commit_messages_str = "\n".join([f"{i + 1}. {message}" for i, message in enumerate(commit_messages)])
+        except Exception:
+            commit_messages_str = ""
+        if max_tokens:
+            commit_messages_str = clip_tokens(commit_messages_str, max_tokens)
+        return commit_messages_str
+
+    def generate_link_to_relevant_line_number(self, suggestion) -> str:
+        try:
+            relevant_file = suggestion['relevant_file'].strip('`').strip("'").strip('\n')
+            relevant_line_str = suggestion['relevant_line'].strip('\n')
+            if not relevant_line_str:
+                return ""
+
+            position, absolute_position = find_line_number_of_relevant_line_in_file \
+                (self.diff_files, relevant_file, relevant_line_str)
+
+            if absolute_position != -1:
+                # # link to right file only
+                # link = f"https://github.com/{self.repo}/blob/{self.pr.head.sha}/{relevant_file}" \
+                #        + "#" + f"L{absolute_position}"
+
+                # link to diff
+                sha_file = hashlib.sha256(relevant_file.encode('utf-8')).hexdigest()
+                link = f"{self.base_url_html}/{self.repo}/pull/{self.pr_num}/files#diff-{sha_file}R{absolute_position}"
+                return link
+        except Exception as e:
+            if get_settings().config.verbosity_level >= 2:
+                get_logger().info(f"Failed adding line link, error: {e}")
+
+        return ""
+
+    def get_line_link(self, relevant_file: str, relevant_line_start: int, relevant_line_end: int = None) -> str:
+        sha_file = hashlib.sha256(relevant_file.encode('utf-8')).hexdigest()
+        if relevant_line_start == -1:
+            link = f"{self.base_url_html}/{self.repo}/pull/{self.pr_num}/files#diff-{sha_file}"
+        elif relevant_line_end:
+            link = f"{self.base_url_html}/{self.repo}/pull/{self.pr_num}/files#diff-{sha_file}R{relevant_line_start}-R{relevant_line_end}"
+        else:
+            link = f"{self.base_url_html}/{self.repo}/pull/{self.pr_num}/files#diff-{sha_file}R{relevant_line_start}"
+        return link
+
+
+    def get_pr_id(self):
+        try:
+            pr_id = f"{self.repo}/{self.pr_num}"
+            return pr_id
+        except:
+            return ""
+
+    def auto_approve(self) -> bool:
+        try:
+            res = self.pr.create_review(event="APPROVE")
+            if res.state == "APPROVED":
+                return True
+            return False
+        except Exception as e:
+            get_logger().exception(f"Failed to auto-approve, error: {e}")
+            return False
+
+    def calc_pr_statistics(self, pull_request_data: dict):
+        try:
+            out = {}
+            from datetime import datetime
+            created_at = pull_request_data['created_at']
+            closed_at = pull_request_data['closed_at']
+            closed_at_datetime = datetime.strptime(closed_at, "%Y-%m-%dT%H:%M:%SZ")
+            created_at_datetime = datetime.strptime(created_at, "%Y-%m-%dT%H:%M:%SZ")
+            difference = closed_at_datetime - created_at_datetime
+            out['hours'] = difference.total_seconds() / 3600
+            out['commits'] = pull_request_data['commits']
+            out['comments'] = pull_request_data['comments']
+            out['review_comments'] = pull_request_data['review_comments']
+            out['changed_files'] = pull_request_data['changed_files']
+            out['additions'] = pull_request_data['additions']
+            out['deletions'] = pull_request_data['deletions']
+        except Exception as e:
+            get_logger().exception(f"Failed to calculate PR statistics, error: {e}")
+            return {}
+        return out

pr_agent/git_providers/gitlab_provider.py

@@ -1,33 +1,52 @@
-import logging
+import hashlib
 import re
 from typing import Optional, Tuple
 from urllib.parse import urlparse
 
 import gitlab
+from gitlab import GitlabGetError
 
-from pr_agent.config_loader import settings
+from ..algo.language_handler import is_valid_file
+from ..algo.utils import load_large_diff, clip_tokens, find_line_number_of_relevant_line_in_file
+from ..config_loader import get_settings
+from .git_provider import GitProvider
+from pr_agent.algo.types import EDIT_TYPE, FilePatchInfo
+from ..log import get_logger
 
-from .git_provider import FilePatchInfo, GitProvider, EDIT_TYPE
 
+class DiffNotFoundError(Exception):
+    """Raised when the diff for a merge request cannot be found."""
+    pass
 
 class GitLabProvider(GitProvider):
-    def __init__(self, merge_request_url: Optional[str] = None):
-        gitlab_url = settings.get("GITLAB.URL", None)
+
+    def __init__(self, merge_request_url: Optional[str] = None, incremental: Optional[bool] = False):
+        gitlab_url = get_settings().get("GITLAB.URL", None)
         if not gitlab_url:
             raise ValueError("GitLab URL is not set in the config file")
-        gitlab_access_token = settings.get("GITLAB.PERSONAL_ACCESS_TOKEN", None)
+        gitlab_access_token = get_settings().get("GITLAB.PERSONAL_ACCESS_TOKEN", None)
         if not gitlab_access_token:
             raise ValueError("GitLab personal access token is not set in the config file")
         self.gl = gitlab.Gitlab(
-            gitlab_url,
-            gitlab_access_token
+            url=gitlab_url,
+            oauth_token=gitlab_access_token
         )
         self.id_project = None
         self.id_mr = None
         self.mr = None
         self.diff_files = None
+        self.git_files = None
         self.temp_comments = []
+        self.pr_url = merge_request_url
         self._set_merge_request(merge_request_url)
+        self.RE_HUNK_HEADER = re.compile(
+            r"^@@ -(\d+)(?:,(\d+))? \+(\d+)(?:,(\d+))? @@[ ]?(.*)")
+        self.incremental = incremental
+
+    def is_supported(self, capability: str) -> bool:
+        if capability in ['get_issue_comments', 'create_inline_comment', 'publish_inline_comments']: # gfm_markdown is supported in gitlab !
+            return False
+        return True
 
     @property
     def pr(self):
@@ -37,120 +56,272 @@ class GitLabProvider(GitProvider):
     def _set_merge_request(self, merge_request_url: str):
         self.id_project, self.id_mr = self._parse_merge_request_url(merge_request_url)
         self.mr = self._get_merge_request()
-        self.last_diff = self.mr.diffs.list()[-1]
+        try:
+            self.last_diff = self.mr.diffs.list(get_all=True)[-1]
+        except IndexError as e:
+            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
+
 
     def _get_pr_file_content(self, file_path: str, branch: str) -> str:
-        return self.gl.projects.get(self.id_project).files.get(file_path, branch).decode()
+        try:
+            return self.gl.projects.get(self.id_project).files.get(file_path, branch).decode()
+        except GitlabGetError:
+            # In case of file creation the method returns GitlabGetError (404 file not found).
+            # In this case we return an empty string for the diff.
+            return ''
 
     def get_diff_files(self) -> list[FilePatchInfo]:
+        """
+        Retrieves the list of files that have been modified, added, deleted, or renamed in a pull request in GitLab,
+        along with their content and patch information.
+
+        Returns:
+            diff_files (List[FilePatchInfo]): List of FilePatchInfo objects representing the modified, added, deleted,
+            or renamed files in the merge request.
+        """
+
+        if self.diff_files:
+            return self.diff_files
+
         diffs = self.mr.changes()['changes']
         diff_files = []
         for diff in diffs:
-            original_file_content_str = self._get_pr_file_content(diff['old_path'], self.mr.target_branch)
-            new_file_content_str = self._get_pr_file_content(diff['new_path'], self.mr.source_branch)
-            edit_type = EDIT_TYPE.MODIFIED
-            if diff['new_file']:
-                edit_type = EDIT_TYPE.ADDED
-            elif diff['deleted_file']:
-                edit_type = EDIT_TYPE.DELETED
-            elif diff['renamed_file']:
-                edit_type = EDIT_TYPE.RENAMED
-            try:
-                original_file_content_str = bytes.decode(original_file_content_str, 'utf-8')
-                new_file_content_str = bytes.decode(new_file_content_str, 'utf-8')
-            except UnicodeDecodeError:
-                logging.warning(
-                    f"Cannot decode file {diff['old_path']} or {diff['new_path']} in merge request {self.id_mr}")
-            diff_files.append(
-                FilePatchInfo(original_file_content_str, new_file_content_str, diff['diff'], diff['new_path'],
-                              edit_type=edit_type,
-                              old_filename=None if diff['old_path'] == diff['new_path'] else diff['old_path']))
+            if is_valid_file(diff['new_path']):
+                # original_file_content_str = self._get_pr_file_content(diff['old_path'], self.mr.target_branch)
+                # new_file_content_str = self._get_pr_file_content(diff['new_path'], self.mr.source_branch)
+                original_file_content_str = self._get_pr_file_content(diff['old_path'], self.mr.diff_refs['base_sha'])
+                new_file_content_str = self._get_pr_file_content(diff['new_path'], self.mr.diff_refs['head_sha'])
+
+                try:
+                    if isinstance(original_file_content_str, bytes):
+                        original_file_content_str = bytes.decode(original_file_content_str, 'utf-8')
+                    if isinstance(new_file_content_str, bytes):
+                        new_file_content_str = bytes.decode(new_file_content_str, 'utf-8')
+                except UnicodeDecodeError:
+                    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
+                if diff['new_file']:
+                    edit_type = EDIT_TYPE.ADDED
+                elif diff['deleted_file']:
+                    edit_type = EDIT_TYPE.DELETED
+                elif diff['renamed_file']:
+                    edit_type = EDIT_TYPE.RENAMED
+
+                filename = diff['new_path']
+                patch = diff['diff']
+                if not patch:
+                    patch = load_large_diff(filename, new_file_content_str, original_file_content_str)
+
+
+                # count number of lines added and removed
+                patch_lines = patch.splitlines(keepends=True)
+                num_plus_lines = len([line for line in patch_lines if line.startswith('+')])
+                num_minus_lines = len([line for line in patch_lines if line.startswith('-')])
+                diff_files.append(
+                    FilePatchInfo(original_file_content_str, new_file_content_str,
+                                  patch=patch,
+                                  filename=filename,
+                                  edit_type=edit_type,
+                                  old_filename=None if diff['old_path'] == diff['new_path'] else diff['old_path'],
+                                  num_plus_lines=num_plus_lines,
+                                  num_minus_lines=num_minus_lines, ))
+
         self.diff_files = diff_files
         return diff_files
 
     def get_files(self):
-        return [change['new_path'] for change in self.mr.changes()['changes']]
+        if not self.git_files:
+            self.git_files = [change['new_path'] for change in self.mr.changes()['changes']]
+        return self.git_files
 
     def publish_description(self, pr_title: str, pr_body: str):
-        logging.exception("Not implemented yet")
-        pass
+        try:
+            self.mr.title = pr_title
+            self.mr.description = pr_body
+            self.mr.save()
+        except Exception as e:
+            get_logger().exception(f"Could not update merge request {self.id_mr} description: {e}")
+
+    def get_latest_commit_url(self):
+        return self.mr.commits().next().web_url
+
+    def get_comment_url(self, comment):
+        return f"{self.mr.web_url}#note_{comment.id}"
+
+    def publish_persistent_comment(self, pr_comment: str, initial_header: str, update_header: bool = True, name='review'):
+        try:
+            for comment in self.mr.notes.list(get_all=True)[::-1]:
+                if comment.body.startswith(initial_header):
+                    latest_commit_url = self.get_latest_commit_url()
+                    comment_url = self.get_comment_url(comment)
+                    if update_header:
+                        updated_header = f"{initial_header}\n\n### ({name.capitalize()} updated until commit {latest_commit_url})\n"
+                        pr_comment_updated = pr_comment.replace(initial_header, updated_header)
+                    else:
+                        pr_comment_updated = pr_comment
+                    get_logger().info(f"Persistent mode - updating comment {comment_url} to latest {name} message")
+                    response = self.mr.notes.update(comment.id, {'body': pr_comment_updated})
+                    self.publish_comment(
+                        f"**[Persistent {name}]({comment_url})** updated to latest commit {latest_commit_url}")
+                    return
+        except Exception as e:
+            get_logger().exception(f"Failed to update persistent review, error: {e}")
+            pass
+        self.publish_comment(pr_comment)
 
     def publish_comment(self, mr_comment: str, is_temporary: bool = False):
         comment = self.mr.notes.create({'body': mr_comment})
         if is_temporary:
             self.temp_comments.append(comment)
+        return comment
+
+    def edit_comment(self, comment, body: str):
+        self.mr.notes.update(comment.id,{'body': body} )
+
+    def reply_to_comment_from_comment_id(self, comment_id: int, body: str):
+        discussion = self.mr.discussions.get(comment_id)
+        discussion.notes.create({'body': body})
 
     def publish_inline_comment(self, body: str, relevant_file: str, relevant_line_in_file: str):
-        self.diff_files = self.diff_files if self.diff_files else self.get_diff_files()
         edit_type, found, source_line_no, target_file, target_line_no = self.search_line(relevant_file,
                                                                                          relevant_line_in_file)
-        if not found:
-            logging.info(f"Could not find position for {relevant_file} {relevant_line_in_file}")
-        else:
-            if edit_type == 'addition':
-                position = target_line_no - 1
-            else:
-                position = source_line_no - 1
-            d = self.last_diff
-            pos_obj = {'position_type': 'text',
-                        'new_path': target_file.filename,
-                        'old_path': target_file.old_filename if target_file.old_filename else target_file.filename,
-                        'base_sha': d.base_commit_sha, 'start_sha': d.start_commit_sha, 'head_sha': d.head_commit_sha}
-            if edit_type == 'deletion':
-                pos_obj['old_line'] = position
-            elif edit_type == 'addition':
-                pos_obj['new_line'] = position
-            else:
-                pos_obj['new_line'] = position
-                pos_obj['old_line'] = position
-            self.mr.discussions.create({'body': body,
-                                        'position': pos_obj})
+        self.send_inline_comment(body, edit_type, found, relevant_file, relevant_line_in_file, source_line_no,
+                                 target_file, target_line_no)
 
-    def publish_code_suggestion(self, body: str,
-                                relevant_file: str,
-                                relevant_lines_start: int,
-                                relevant_lines_end: int):
-        raise "not implemented yet for gitlab"
+    def create_inline_comment(self, body: str, relevant_file: str, relevant_line_in_file: str, absolute_position: int = None):
+        raise NotImplementedError("Gitlab provider does not support creating inline comments yet")
+
+    def create_inline_comments(self, comments: list[dict]):
+        raise NotImplementedError("Gitlab provider does not support publishing inline comments yet")
+
+    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:
+            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:
+                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,
+                       'old_path': target_file.old_filename if target_file.old_filename else target_file.filename,
+                       'base_sha': diff.base_commit_sha, 'start_sha': diff.start_commit_sha, 'head_sha': diff.head_commit_sha}
+            if edit_type == 'deletion':
+                pos_obj['old_line'] = source_line_no - 1
+            elif edit_type == 'addition':
+                pos_obj['new_line'] = target_line_no - 1
+            else:
+                pos_obj['new_line'] = target_line_no - 1
+                pos_obj['old_line'] = source_line_no - 1
+            get_logger().debug(f"Creating comment in {self.id_mr} with body {body} and position {pos_obj}")
+            try:
+                self.mr.discussions.create({'body': body, 'position': pos_obj})
+            except Exception as e:
+                get_logger().debug(
+                    f"Failed to create comment in {self.id_mr} with position {pos_obj} (probably not a '+' line)")
+
+    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:
+            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:
+            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
+            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
+
+    def publish_code_suggestions(self, code_suggestions: list) -> bool:
+        for suggestion in code_suggestions:
+            try:
+                body = suggestion['body']
+                relevant_file = suggestion['relevant_file']
+                relevant_lines_start = suggestion['relevant_lines_start']
+                relevant_lines_end = suggestion['relevant_lines_end']
+
+                diff_files = self.get_diff_files()
+                target_file = None
+                for file in diff_files:
+                    if file.filename == relevant_file:
+                        if file.filename == relevant_file:
+                            target_file = file
+                            break
+                range = relevant_lines_end - relevant_lines_start # no need to add 1
+                body = body.replace('```suggestion', f'```suggestion:-0+{range}')
+                lines = target_file.head_file.splitlines()
+                relevant_line_in_file = lines[relevant_lines_start - 1]
+
+                # edit_type, found, source_line_no, target_file, target_line_no = self.find_in_file(target_file,
+                #                                                                            relevant_line_in_file)
+                # for code suggestions, we want to edit the new code
+                source_line_no = None
+                target_line_no = relevant_lines_start + 1
+                found = True
+                edit_type = 'addition'
+
+                self.send_inline_comment(body, edit_type, found, relevant_file, relevant_line_in_file, source_line_no,
+                                         target_file, target_line_no)
+            except Exception as e:
+                get_logger().exception(f"Could not publish code suggestion:\nsuggestion: {suggestion}\nerror: {e}")
+
+        # note that we publish suggestions one-by-one. so, if one fails, the rest will still be published
+        return True
 
     def search_line(self, relevant_file, relevant_line_in_file):
-        RE_HUNK_HEADER = re.compile(
-            r"^@@ -(\d+)(?:,(\d+))? \+(\d+)(?:,(\d+))? @@[ ]?(.*)")
         target_file = None
+
+        edit_type = self.get_edit_type(relevant_line_in_file)
+        for file in self.get_diff_files():
+            if file.filename == relevant_file:
+                edit_type, found, source_line_no, target_file, target_line_no = self.find_in_file(file,
+                                                                                                  relevant_line_in_file)
+        return edit_type, found, source_line_no, target_file, target_line_no
+
+    def find_in_file(self, file, relevant_line_in_file):
+        edit_type = 'context'
         source_line_no = 0
         target_line_no = 0
         found = False
-        edit_type = self.get_edit_type(relevant_line_in_file)
-        for file in self.diff_files:
-            if file.filename == relevant_file:
-                target_file = file
-                patch = file.patch
-                patch_lines = patch.splitlines()
-                for i, line in enumerate(patch_lines):
-                    if line.startswith('@@'):
-                        match = RE_HUNK_HEADER.match(line)
-                        if not match:
-                            continue
-                        start_old, size_old, start_new, size_new, _ = match.groups()
-                        source_line_no = int(start_old)
-                        target_line_no = int(start_new)
-                        continue
-                    if line.startswith('-'):
-                        source_line_no += 1
-                    elif line.startswith('+'):
-                        target_line_no += 1
-                    elif line.startswith(' '):
-                        source_line_no += 1
-                        target_line_no += 1
-                    if relevant_line_in_file in line:
-                        found = True
-                        edit_type = self.get_edit_type(line)
-                        break
-                    elif relevant_line_in_file[0] == '+' and relevant_line_in_file[1:] in line:
-                        # The model often adds a '+' to the beginning of the relevant_line_in_file even if originally
-                        # it's a context line
-                        found = True
-                        edit_type = self.get_edit_type(line)
-                        break
+        target_file = file
+        patch = file.patch
+        patch_lines = patch.splitlines()
+        for line in patch_lines:
+            if line.startswith('@@'):
+                match = self.RE_HUNK_HEADER.match(line)
+                if not match:
+                    continue
+                start_old, size_old, start_new, size_new, _ = match.groups()
+                source_line_no = int(start_old)
+                target_line_no = int(start_new)
+                continue
+            if line.startswith('-'):
+                source_line_no += 1
+            elif line.startswith('+'):
+                target_line_no += 1
+            elif line.startswith(' '):
+                source_line_no += 1
+                target_line_no += 1
+            if relevant_line_in_file in line:
+                found = True
+                edit_type = self.get_edit_type(line)
+                break
+            elif relevant_line_in_file[0] == '+' and relevant_line_in_file[1:].lstrip() in line:
+                # The model often adds a '+' to the beginning of the relevant_line_in_file even if originally
+                # it's a context line
+                found = True
+                edit_type = self.get_edit_type(line)
+                break
         return edit_type, found, source_line_no, target_file, target_line_no
 
     def get_edit_type(self, relevant_line_in_file):
@@ -164,16 +335,19 @@ class GitLabProvider(GitProvider):
     def remove_initial_comment(self):
         try:
             for comment in self.temp_comments:
-                comment.delete()
+                self.remove_comment(comment)
         except Exception as e:
-            logging.exception(f"Failed to remove temp comments, error: {e}")
+            get_logger().exception(f"Failed to remove temp comments, error: {e}")
+
+    def remove_comment(self, comment):
+        try:
+            comment.delete()
+        except Exception as e:
+            get_logger().exception(f"Failed to remove comment, error: {e}")
 
     def get_title(self):
         return self.mr.title
 
-    def get_description(self):
-        return self.mr.description
-
     def get_languages(self):
         languages = self.gl.projects.get(self.id_project).languages()
         return languages
@@ -181,23 +355,49 @@ class GitLabProvider(GitProvider):
     def get_pr_branch(self):
         return self.mr.source_branch
 
-    def get_pr_description(self):
+    def get_pr_description_full(self):
         return self.mr.description
 
-    def _parse_merge_request_url(self, merge_request_url: str) -> Tuple[int, int]:
+    def get_issue_comments(self):
+        raise NotImplementedError("GitLab provider does not support issue comments yet")
+
+    def get_repo_settings(self):
+        try:
+            contents = self.gl.projects.get(self.id_project).files.get(file_path='.pr_agent.toml', ref=self.mr.target_branch).decode()
+            return contents
+        except Exception:
+            return ""
+
+    def add_eyes_reaction(self, issue_comment_id: int, disable_eyes: bool = False) -> Optional[int]:
+        return True
+
+    def remove_reaction(self, issue_comment_id: int, reaction_id: int) -> bool:
+        return True
+
+    def _parse_merge_request_url(self, merge_request_url: str) -> Tuple[str, int]:
         parsed_url = urlparse(merge_request_url)
 
         path_parts = parsed_url.path.strip('/').split('/')
-        if path_parts[-2] != 'merge_requests':
+        if 'merge_requests' not in path_parts:
             raise ValueError("The provided URL does not appear to be a GitLab merge request URL")
 
+        mr_index = path_parts.index('merge_requests')
+        # Ensure there is an ID after 'merge_requests'
+        if len(path_parts) <= mr_index + 1:
+            raise ValueError("The provided URL does not contain a merge request ID")
+
         try:
-            mr_id = int(path_parts[-1])
+            mr_id = int(path_parts[mr_index + 1])
         except ValueError as e:
             raise ValueError("Unable to convert merge request ID to integer") from e
 
-        # Gitlab supports access by both project numeric ID as well as 'namespace/project_name'
-        return "/".join(path_parts[:2]), mr_id
+        # Handle special delimiter (-)
+        project_path = "/".join(path_parts[:mr_index])
+        if project_path.endswith('/-'):
+            project_path = project_path[:-2]
+
+        # Return the path before 'merge_requests' and the ID
+        return project_path, mr_id
 
     def _get_merge_request(self):
         mr = self.gl.projects.get(self.id_project).mergerequests.get(self.id_mr)
@@ -205,3 +405,77 @@ class GitLabProvider(GitProvider):
 
     def get_user_id(self):
         return None
+
+    def publish_labels(self, pr_types):
+        try:
+            self.mr.labels = list(set(pr_types))
+            self.mr.save()
+        except Exception as e:
+            get_logger().exception(f"Failed to publish labels, error: {e}")
+
+    def publish_inline_comments(self, comments: list[dict]):
+        pass
+
+    def get_pr_labels(self):
+        return self.mr.labels
+
+    def get_repo_labels(self):
+        return self.gl.projects.get(self.id_project).labels.list()
+
+    def get_commit_messages(self):
+        """
+        Retrieves the commit messages of a pull request.
+
+        Returns:
+            str: A string containing the commit messages of the pull request.
+        """
+        max_tokens = get_settings().get("CONFIG.MAX_COMMITS_TOKENS", None)
+        try:
+            commit_messages_list = [commit['message'] for commit in self.mr.commits()._list]
+            commit_messages_str = "\n".join([f"{i + 1}. {message}" for i, message in enumerate(commit_messages_list)])
+        except Exception:
+            commit_messages_str = ""
+        if max_tokens:
+            commit_messages_str = clip_tokens(commit_messages_str, max_tokens)
+        return commit_messages_str
+
+    def get_pr_id(self):
+        try:
+            pr_id = self.mr.web_url
+            return pr_id
+        except:
+            return ""
+
+    def get_line_link(self, relevant_file: str, relevant_line_start: int, relevant_line_end: int = None) -> str:
+        if relevant_line_start == -1:
+            link = f"{self.gl.url}/{self.id_project}/-/blob/{self.mr.source_branch}/{relevant_file}?ref_type=heads"
+        elif relevant_line_end:
+            link = f"{self.gl.url}/{self.id_project}/-/blob/{self.mr.source_branch}/{relevant_file}?ref_type=heads#L{relevant_line_start}-L{relevant_line_end}"
+        else:
+            link = f"{self.gl.url}/{self.id_project}/-/blob/{self.mr.source_branch}/{relevant_file}?ref_type=heads#L{relevant_line_start}"
+        return link
+
+
+    def generate_link_to_relevant_line_number(self, suggestion) -> str:
+        try:
+            relevant_file = suggestion['relevant_file'].strip('`').strip("'").rstrip()
+            relevant_line_str = suggestion['relevant_line'].rstrip()
+            if not relevant_line_str:
+                return ""
+
+            position, absolute_position = find_line_number_of_relevant_line_in_file \
+                (self.diff_files, relevant_file, relevant_line_str)
+
+            if absolute_position != -1:
+                # link to right file only
+                link = f"{self.gl.url}/{self.id_project}/-/blob/{self.mr.source_branch}/{relevant_file}?ref_type=heads#L{absolute_position}"
+
+                # # link to diff
+                # sha_file = hashlib.sha1(relevant_file.encode('utf-8')).hexdigest()
+                # link = f"{self.pr.web_url}/diffs#{sha_file}_{absolute_position}_{absolute_position}"
+                return link
+        except Exception as e:
+            if get_settings().config.verbosity_level >= 2:
+                get_logger().info(f"Failed adding line link, error: {e}")
+
+        return ""

pr_agent/git_providers/local_git_provider.py

@@ -0,0 +1,180 @@
+from collections import Counter
+from pathlib import Path
+from typing import List
+
+from git import Repo
+
+from pr_agent.config_loader import _find_repository_root, get_settings
+from pr_agent.git_providers.git_provider import GitProvider
+from pr_agent.algo.types import EDIT_TYPE, FilePatchInfo
+from pr_agent.log import get_logger
+
+
+class PullRequestMimic:
+    """
+    This class mimics the PullRequest class from the PyGithub library for the LocalGitProvider.
+    """
+
+    def __init__(self, title: str, diff_files: List[FilePatchInfo]):
+        self.title = title
+        self.diff_files = diff_files
+
+
+class LocalGitProvider(GitProvider):
+    """
+    This class implements the GitProvider interface for local git repositories.
+    It mimics the PR functionality of the GitProvider interface,
+    but does not require a hosted git repository.
+    Instead of providing a PR url, the user provides a local branch path to generate a diff-patch.
+    For the MVP it only supports the /review and /describe capabilities.
+    """
+
+    def __init__(self, target_branch_name, incremental=False):
+        self.repo_path = _find_repository_root()
+        if self.repo_path is None:
+            raise ValueError('Could not find repository root')
+        self.repo = Repo(self.repo_path)
+        self.head_branch_name = self.repo.head.ref.name
+        self.target_branch_name = target_branch_name
+        self._prepare_repo()
+        self.diff_files = None
+        self.pr = PullRequestMimic(self.get_pr_title(), self.get_diff_files())
+        self.description_path = get_settings().get('local.description_path') \
+            if get_settings().get('local.description_path') is not None else self.repo_path / 'description.md'
+        self.review_path = get_settings().get('local.review_path') \
+            if get_settings().get('local.review_path') is not None else self.repo_path / 'review.md'
+        # inline code comments are not supported for local git repositories
+        get_settings().pr_reviewer.inline_code_comments = False
+
+    def _prepare_repo(self):
+        """
+        Prepare the repository for PR-mimic generation.
+        """
+        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:
+            raise KeyError(f'Branch: {self.target_branch_name} does not exist')
+
+    def is_supported(self, capability: str) -> bool:
+        if capability in ['get_issue_comments', 'create_inline_comment', 'publish_inline_comments', 'get_labels',
+                          'gfm_markdown']:
+            return False
+        return True
+
+    def get_diff_files(self) -> list[FilePatchInfo]:
+        diffs = self.repo.head.commit.diff(
+            self.repo.merge_base(self.repo.head, self.repo.branches[self.target_branch_name]),
+            create_patch=True,
+            R=True
+        )
+        diff_files = []
+        for diff_item in diffs:
+            if diff_item.a_blob is not None:
+                original_file_content_str = diff_item.a_blob.data_stream.read().decode('utf-8')
+            else:
+                original_file_content_str = ""  # empty file
+            if diff_item.b_blob is not None:
+                new_file_content_str = diff_item.b_blob.data_stream.read().decode('utf-8')
+            else:
+                new_file_content_str = ""  # empty file
+            edit_type = EDIT_TYPE.MODIFIED
+            if diff_item.new_file:
+                edit_type = EDIT_TYPE.ADDED
+            elif diff_item.deleted_file:
+                edit_type = EDIT_TYPE.DELETED
+            elif diff_item.renamed_file:
+                edit_type = EDIT_TYPE.RENAMED
+            diff_files.append(
+                FilePatchInfo(original_file_content_str,
+                              new_file_content_str,
+                              diff_item.diff.decode('utf-8'),
+                              diff_item.b_path,
+                              edit_type=edit_type,
+                              old_filename=None if diff_item.a_path == diff_item.b_path else diff_item.a_path
+                              )
+            )
+        self.diff_files = diff_files
+        return diff_files
+
+    def get_files(self) -> List[str]:
+        """
+        Returns a list of files with changes in the diff.
+        """
+        diff_index = self.repo.head.commit.diff(
+            self.repo.merge_base(self.repo.head, self.repo.branches[self.target_branch_name]),
+            R=True
+        )
+        # Get the list of changed files
+        diff_files = [item.a_path for item in diff_index]
+        return diff_files
+
+    def publish_description(self, pr_title: str, pr_body: str):
+        with open(self.description_path, "w") as file:
+            # Write the string to the file
+            file.write(pr_title + '\n' + pr_body)
+
+    def publish_comment(self, pr_comment: str, is_temporary: bool = False):
+        with open(self.review_path, "w") as file:
+            # Write the string to the file
+            file.write(pr_comment)
+
+    def publish_inline_comment(self, body: str, relevant_file: str, relevant_line_in_file: str):
+        raise NotImplementedError('Publishing inline comments is not implemented for the local git provider')
+
+    def publish_inline_comments(self, comments: list[dict]):
+        raise NotImplementedError('Publishing inline comments is not implemented for the local git provider')
+
+    def publish_code_suggestion(self, body: str, relevant_file: str,
+                                relevant_lines_start: int, relevant_lines_end: int):
+        raise NotImplementedError('Publishing code suggestions is not implemented for the local git provider')
+
+    def publish_code_suggestions(self, code_suggestions: list) -> bool:
+        raise NotImplementedError('Publishing code suggestions is not implemented for the local git provider')
+
+    def publish_labels(self, labels):
+        pass  # Not applicable to the local git provider, but required by the interface
+
+    def remove_initial_comment(self):
+        pass  # Not applicable to the local git provider, but required by the interface
+
+    def remove_comment(self, comment):
+        pass  # Not applicable to the local git provider, but required by the interface
+
+    def get_languages(self):
+        """
+        Calculate percentage of languages in repository. Used for hunk prioritisation.
+        """
+        # Get all files in repository
+        filepaths = [Path(item.path) for item in self.repo.tree().traverse() if item.type == 'blob']
+        # Identify language by file extension and count
+        lang_count = Counter(ext.lstrip('.') for filepath in filepaths for ext in [filepath.suffix.lower()])
+        # Convert counts to percentages
+        total_files = len(filepaths)
+        lang_percentage = {lang: count / total_files * 100 for lang, count in lang_count.items()}
+        return lang_percentage
+
+    def get_pr_branch(self):
+        return self.repo.head
+
+    def get_user_id(self):
+        return -1  # Not used anywhere for the local provider, but required by the interface
+
+    def get_pr_description_full(self):
+        commits_diff = list(self.repo.iter_commits(self.target_branch_name + '..HEAD'))
+        # Get the commit messages and concatenate
+        commit_messages = " ".join([commit.message for commit in commits_diff])
+        # TODO Handle the description better - maybe use gpt-3.5 summarisation here?
+        return commit_messages[:200]  # Use max 200 characters
+
+    def get_pr_title(self):
+        """
+        Substitutes the branch-name as the PR-mimic title.
+        """
+        return self.head_branch_name
+
+    def get_issue_comments(self):
+        raise NotImplementedError('Getting issue comments is not implemented for the local git provider')
+
+    def get_pr_labels(self):
+        raise NotImplementedError('Getting labels is not implemented for the local git provider')

pr_agent/git_providers/utils.py

@@ -0,0 +1,49 @@
+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
+from starlette_context import context
+
+
+def apply_repo_settings(pr_url):
+    if get_settings().config.use_repo_settings_file:
+        repo_settings_file = None
+        try:
+            try:
+                repo_settings = context.get("repo_settings", None)
+            except Exception:
+                repo_settings = None
+                pass
+            if repo_settings is None:  # None is different from "", which is a valid value
+                git_provider = get_git_provider()(pr_url)
+                repo_settings = git_provider.get_repo_settings()
+                try:
+                    context["repo_settings"] = repo_settings
+                except Exception:
+                    pass
+
+            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:\n{new_settings.as_dict()}")
+        except Exception as e:
+            get_logger().exception("Failed to apply repo settings", e)
+        finally:
+            if repo_settings_file:
+                try:
+                    os.remove(repo_settings_file)
+                except Exception as e:
+                    get_logger().error(f"Failed to remove temporary settings file {repo_settings_file}", e)

pr_agent/identity_providers/__init__.py

@@ -0,0 +1,13 @@
+from pr_agent.config_loader import get_settings
+from pr_agent.identity_providers.default_identity_provider import DefaultIdentityProvider
+
+_IDENTITY_PROVIDERS = {
+    'default': DefaultIdentityProvider
+}
+
+
+def get_identity_provider():
+    identity_provider_id = get_settings().get("CONFIG.IDENTITY_PROVIDER", "default")
+    if identity_provider_id not in _IDENTITY_PROVIDERS:
+        raise ValueError(f"Unknown identity provider: {identity_provider_id}")
+    return _IDENTITY_PROVIDERS[identity_provider_id]()

pr_agent/identity_providers/default_identity_provider.py

@@ -0,0 +1,9 @@
+from pr_agent.identity_providers.identity_provider import Eligibility, IdentityProvider
+
+
+class DefaultIdentityProvider(IdentityProvider):
+    def verify_eligibility(self, git_provider, git_provider_id, pr_url):
+        return Eligibility.ELIGIBLE
+
+    def inc_invocation_count(self, git_provider, git_provider_id):
+        pass

pr_agent/identity_providers/identity_provider.py

@@ -0,0 +1,18 @@
+from abc import ABC, abstractmethod
+from enum import Enum
+
+
+class Eligibility(Enum):
+    NOT_ELIGIBLE = 0
+    ELIGIBLE = 1
+    TRIAL = 2
+
+
+class IdentityProvider(ABC):
+    @abstractmethod
+    def verify_eligibility(self, git_provider, git_provier_id, pr_url):
+        pass
+
+    @abstractmethod
+    def inc_invocation_count(self, git_provider, git_provider_id):
+        pass

pr_agent/log/__init__.py

@@ -0,0 +1,65 @@
+import json
+import logging
+import os
+import sys
+from enum import Enum
+
+from loguru import logger
+
+from pr_agent.config_loader import get_settings
+
+
+class LoggingFormat(str, Enum):
+    CONSOLE = "CONSOLE"
+    JSON = "JSON"
+
+
+def json_format(record: dict) -> str:
+    return record["message"]
+
+
+def analytics_filter(record: dict) -> bool:
+    return record.get("extra", {}).get("analytics", False)
+
+
+def inv_analytics_filter(record: dict) -> bool:
+    return not record.get("extra", {}).get("analytics", False)
+
+
+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 and os.getenv("LOG_SANE", "0").lower() == "0":  # better debugging github_app
+        logger.remove(None)
+        logger.add(
+            sys.stdout,
+            filter=inv_analytics_filter,
+            level=level,
+            format="{message}",
+            colorize=False,
+            serialize=True,
+        )
+    elif fmt == LoggingFormat.CONSOLE: # does not print the 'extra' fields
+        logger.remove(None)
+        logger.add(sys.stdout, level=level, colorize=True, filter=inv_analytics_filter)
+
+    log_folder = get_settings().get("CONFIG.ANALYTICS_FOLDER", "")
+    if log_folder:
+        pid = os.getpid()
+        log_file = os.path.join(log_folder, f"pr-agent.{pid}.log")
+        logger.add(
+            log_file,
+            filter=analytics_filter,
+            level=level,
+            format="{message}",
+            colorize=False,
+            serialize=True,
+        )
+
+    return logger
+
+
+def get_logger(*args, **kwargs):
+    return logger

pr_agent/secret_providers/__init__.py

@@ -0,0 +1,19 @@
+from pr_agent.config_loader import get_settings
+
+
+def get_secret_provider():
+    if not get_settings().get("CONFIG.SECRET_PROVIDER"):
+        return None
+
+    provider_id = get_settings().config.secret_provider
+    if provider_id == 'google_cloud_storage':
+        try:
+            from pr_agent.secret_providers.google_cloud_storage_secret_provider import GoogleCloudStorageSecretProvider
+            return GoogleCloudStorageSecretProvider()
+        except Exception as e:
+            raise ValueError(f"Failed to initialize google_cloud_storage secret provider {provider_id}") from e
+    else:
+        raise ValueError("Unknown SECRET_PROVIDER")
+
+
+

pr_agent/secret_providers/google_cloud_storage_secret_provider.py

@@ -0,0 +1,34 @@
+import ujson
+from google.cloud import storage
+
+from pr_agent.config_loader import get_settings
+from pr_agent.log import get_logger
+from pr_agent.secret_providers.secret_provider import SecretProvider
+
+
+class GoogleCloudStorageSecretProvider(SecretProvider):
+    def __init__(self):
+        try:
+            self.client = storage.Client.from_service_account_info(ujson.loads(get_settings().google_cloud_storage.
+                                                                               service_account))
+            self.bucket_name = get_settings().google_cloud_storage.bucket_name
+            self.bucket = self.client.bucket(self.bucket_name)
+        except Exception as e:
+            get_logger().error(f"Failed to initialize Google Cloud Storage Secret Provider: {e}")
+            raise e
+
+    def get_secret(self, secret_name: str) -> str:
+        try:
+            blob = self.bucket.blob(secret_name)
+            return blob.download_as_string()
+        except Exception as 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):
+        try:
+            blob = self.bucket.blob(secret_name)
+            blob.upload_from_string(secret_value)
+        except Exception as e:
+            get_logger().error(f"Failed to store secret {secret_name} in Google Cloud Storage: {e}")
+            raise e

pr_agent/secret_providers/secret_provider.py

@@ -0,0 +1,12 @@
+from abc import ABC, abstractmethod
+
+
+class SecretProvider(ABC):
+
+    @abstractmethod
+    def get_secret(self, secret_name: str) -> str:
+        pass
+
+    @abstractmethod
+    def store_secret(self, secret_name: str, secret_value: str):
+        pass

pr_agent/servers/atlassian-connect.json

@@ -0,0 +1,33 @@
+{
+  "name": "CodiumAI PR-Agent",
+  "description": "CodiumAI PR-Agent",
+  "key": "app_key",
+  "vendor": {
+    "name": "CodiumAI",
+    "url": "https://codium.ai"
+  },
+  "authentication": {
+    "type": "jwt"
+  },
+  "baseUrl": "base_url",
+  "lifecycle": {
+    "installed": "/installed",
+    "uninstalled": "/uninstalled"
+  },
+  "scopes": [
+    "account",
+    "repository",
+    "pullrequest"
+  ],
+  "contexts": [
+    "account"
+  ],
+  "modules": {
+    "webhooks": [
+      {
+        "event": "*",
+        "url": "/webhook"
+      }
+    ]
+  }
+}

pr_agent/servers/azuredevops_server_webhook.py

@@ -0,0 +1,137 @@
+# This file contains the code for the Azure DevOps Server webhook server.
+# The server listens for incoming webhooks from Azure DevOps Server and forwards them to the PR Agent.
+# ADO webhook documentation: https://learn.microsoft.com/en-us/azure/devops/service-hooks/services/webhooks?view=azure-devops
+
+import json
+import os
+import re
+import secrets
+import uvicorn
+from fastapi import APIRouter, Depends, FastAPI, HTTPException
+from fastapi.security import HTTPBasic, HTTPBasicCredentials
+from fastapi.encoders import jsonable_encoder
+from starlette import status
+from starlette.background import BackgroundTasks
+from starlette.middleware import Middleware
+from starlette.requests import Request
+from starlette.responses import JSONResponse
+from starlette_context.middleware import RawContextMiddleware
+
+from pr_agent.agent.pr_agent import PRAgent, command2class
+from pr_agent.algo.utils import update_settings_from_args
+from pr_agent.config_loader import get_settings
+from pr_agent.git_providers.utils import apply_repo_settings
+from pr_agent.log import get_logger
+from fastapi import Request, Depends
+from fastapi.security import HTTPBasic, HTTPBasicCredentials
+from pr_agent.log import get_logger
+
+security = HTTPBasic()
+router = APIRouter()
+available_commands_rgx = re.compile(r"^\/(" + "|".join(command2class.keys()) + r")\s*")
+azure_devops_server = get_settings().get("azure_devops_server")
+WEBHOOK_USERNAME = azure_devops_server.get("webhook_username")
+WEBHOOK_PASSWORD = azure_devops_server.get("webhook_password")
+
+def handle_request(
+    background_tasks: BackgroundTasks, url: str, body: str, log_context: dict
+):
+    log_context["action"] = body
+    log_context["api_url"] = url
+    with get_logger().contextualize(**log_context):
+        background_tasks.add_task(PRAgent().handle_request, url, body)
+
+
+# currently only basic auth is supported with azure webhooks
+# for this reason, https must be enabled to ensure the credentials are not sent in clear text
+def authorize(credentials: HTTPBasicCredentials = Depends(security)):
+        is_user_ok = secrets.compare_digest(credentials.username, WEBHOOK_USERNAME)
+        is_pass_ok = secrets.compare_digest(credentials.password, WEBHOOK_PASSWORD)
+        if not (is_user_ok and is_pass_ok):
+            raise HTTPException(
+                status_code=status.HTTP_401_UNAUTHORIZED,
+                detail='Incorrect username or password.',
+                headers={'WWW-Authenticate': 'Basic'},
+            )
+
+
+async def _perform_commands_azure(commands_conf: str, agent: PRAgent, api_url: str, log_context: dict):
+    apply_repo_settings(api_url)
+    commands = get_settings().get(f"azure_devops_server.{commands_conf}")
+    for command in commands:
+        try:
+            split_command = command.split(" ")
+            command = split_command[0]
+            args = split_command[1:]
+            other_args = update_settings_from_args(args)
+            new_command = ' '.join([command] + other_args)
+            get_logger().info(f"Performing command: {new_command}")
+            with get_logger().contextualize(**log_context):
+                await agent.handle_request(api_url, new_command)
+        except Exception as e:
+            get_logger().error(f"Failed to perform command {command}: {e}")
+
+
+@router.post("/", dependencies=[Depends(authorize)])
+async def handle_webhook(background_tasks: BackgroundTasks, request: Request):
+    log_context = {"server_type": "azure_devops_server"}
+    data = await request.json()
+    get_logger().info(json.dumps(data))
+
+    actions = []
+    if data["eventType"] == "git.pullrequest.created": 
+        # API V1 (latest)
+        pr_url = data["resource"]["_links"]["web"]["href"].replace("_apis/git/repositories", "_git")
+        log_context["event"] = data["eventType"]
+        log_context["api_url"] = pr_url
+        await _perform_commands_azure("pr_commands", PRAgent(), pr_url, log_context)
+        return
+    elif data["eventType"] == "ms.vss-code.git-pullrequest-comment-event" and "content" in data["resource"]["comment"]:
+        if available_commands_rgx.match(data["resource"]["comment"]["content"]):
+            if(data["resourceVersion"] == "2.0"):
+                repo = data["resource"]["pullRequest"]["repository"]["webUrl"]
+                pr_url = f'{repo}/pullrequest/{data["resource"]["pullRequest"]["pullRequestId"]}'
+                actions = [data["resource"]["comment"]["content"]]
+            else: 
+                # API V1 not supported as it does not contain the PR URL
+                return JSONResponse(
+                    status_code=status.HTTP_400_BAD_REQUEST,
+                    content=json.dumps({"message": "version 1.0 webhook for Azure Devops PR comment is not supported. please upgrade to version 2.0"})),
+        else:
+            return JSONResponse(
+                status_code=status.HTTP_400_BAD_REQUEST,
+                content=json.dumps({"message": "Unsupported command"}),
+            )
+    else:
+        return JSONResponse(
+            status_code=status.HTTP_204_NO_CONTENT,
+            content=json.dumps({"message": "Unsupported event"}),
+        )
+
+    log_context["event"] = data["eventType"]
+    log_context["api_url"] = pr_url
+    
+    for action in actions:
+        try:
+            handle_request(background_tasks, pr_url, action, log_context)
+        except Exception as e:
+            get_logger().error("Azure DevOps Trigger failed. Error:" + str(e))
+            return JSONResponse(
+                status_code=status.HTTP_500_INTERNAL_SERVER_ERROR,
+                content=json.dumps({"message": "Internal server error"}),
+            )
+    return JSONResponse(
+        status_code=status.HTTP_202_ACCEPTED, content=jsonable_encoder({"message": "webhook triggerd successfully"})
+    )
+
+@router.get("/")
+async def root():
+    return {"status": "ok"}
+    
+def start():
+    app = FastAPI(middleware=[Middleware(RawContextMiddleware)])
+    app.include_router(router)
+    uvicorn.run(app, host="0.0.0.0", port=int(os.environ.get("PORT", "3000")))
+
+if __name__ == "__main__":
+    start()

pr_agent/servers/bitbucket_app.py

@@ -0,0 +1,190 @@
+import base64
+import copy
+import hashlib
+import json
+import os
+import time
+
+import jwt
+import requests
+import uvicorn
+from fastapi import APIRouter, FastAPI, Request, Response
+from starlette.background import BackgroundTasks
+from starlette.middleware import Middleware
+from starlette.responses import JSONResponse
+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 get_settings, global_settings
+from pr_agent.git_providers.utils import apply_repo_settings
+from pr_agent.identity_providers import get_identity_provider
+from pr_agent.identity_providers.identity_provider import Eligibility
+from pr_agent.log import LoggingFormat, get_logger, setup_logger
+from pr_agent.secret_providers import get_secret_provider
+from pr_agent.servers.github_action_runner import get_setting_or_env, is_true
+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
+
+setup_logger(fmt=LoggingFormat.JSON)
+router = APIRouter()
+secret_provider = get_secret_provider() if get_settings().get("CONFIG.SECRET_PROVIDER") else None
+
+
+async def get_bearer_token(shared_secret: str, client_key: str):
+    try:
+        now = int(time.time())
+        url = "https://bitbucket.org/site/oauth2/access_token"
+        canonical_url = "GET&/site/oauth2/access_token&"
+        qsh = hashlib.sha256(canonical_url.encode("utf-8")).hexdigest()
+        app_key = get_settings().bitbucket.app_key
+
+        payload = {
+            "iss": app_key,
+            "iat": now,
+            "exp": now + 240,
+            "qsh": qsh,
+            "sub": client_key,
+            }
+        token = jwt.encode(payload, shared_secret, algorithm="HS256")
+        payload = 'grant_type=urn%3Abitbucket%3Aoauth2%3Ajwt'
+        headers = {
+            'Authorization': f'JWT {token}',
+            'Content-Type': 'application/x-www-form-urlencoded'
+        }
+        response = requests.request("POST", url, headers=headers, data=payload)
+        bearer_token = response.json()["access_token"]
+        return bearer_token
+    except Exception as e:
+        get_logger().error(f"Failed to get bearer token: {e}")
+        raise e
+
+@router.get("/")
+async def handle_manifest(request: Request, response: Response):
+    cur_dir = os.path.dirname(os.path.abspath(__file__))
+    manifest = open(os.path.join(cur_dir, "atlassian-connect.json"), "rt").read()
+    try:
+        manifest = manifest.replace("app_key", get_settings().bitbucket.app_key)
+        manifest = manifest.replace("base_url", get_settings().bitbucket.base_url)
+    except:
+        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):
+    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()
+    get_logger().debug(data)
+    async def inner():
+        try:
+            try:
+                if data["data"]["actor"]["type"] != "user":
+                    return "OK"
+            except KeyError:
+                get_logger().error("Failed to get actor type, check previous logs, this shouldn't happen.")
+            try:
+                owner = data["data"]["repository"]["owner"]["username"]
+            except Exception as e:
+                get_logger().error(f"Failed to get owner, will continue: {e}")
+                owner = "unknown"
+            sender_id = data["data"]["actor"]["account_id"]
+            log_context["sender"] = owner
+            log_context["sender_id"] = sender_id
+            jwt_parts = input_jwt.split(".")
+            claim_part = jwt_parts[1]
+            claim_part += "=" * (-len(claim_part) % 4)
+            decoded_claims = base64.urlsafe_b64decode(claim_part)
+            claims = json.loads(decoded_claims)
+            client_key = claims["iss"]
+            secrets = json.loads(secret_provider.get_secret(client_key))
+            shared_secret = secrets["shared_secret"]
+            jwt.decode(input_jwt, shared_secret, audience=client_key, algorithms=["HS256"])
+            bearer_token = await get_bearer_token(shared_secret, client_key)
+            context['bitbucket_bearer_token'] = bearer_token
+            context["settings"] = copy.deepcopy(global_settings)
+            event = data["event"]
+            agent = PRAgent()
+            if event == "pullrequest:created":
+                pr_url = data["data"]["pullrequest"]["links"]["html"]["href"]
+                log_context["api_url"] = pr_url
+                log_context["event"] = "pull_request"
+                if pr_url:
+                    with get_logger().contextualize(**log_context):
+                        apply_repo_settings(pr_url)
+                        if get_identity_provider().verify_eligibility("bitbucket",
+                                                                         sender_id, pr_url) is not Eligibility.NOT_ELIGIBLE:
+                            auto_review = get_setting_or_env("BITBUCKET_APP.AUTO_REVIEW", None)
+                            if auto_review is None or is_true(auto_review):  # by default, auto review is enabled
+                                await PRReviewer(pr_url).run()
+                            auto_improve = get_setting_or_env("BITBUCKET_APP.AUTO_IMPROVE", None)
+                            if is_true(auto_improve):  # by default, auto improve is disabled
+                                await PRCodeSuggestions(pr_url).run()
+                            auto_describe = get_setting_or_env("BITBUCKET_APP.AUTO_DESCRIBE", None)
+                            if is_true(auto_describe):  # by default, auto describe is disabled
+                                await PRDescription(pr_url).run()
+                # 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"]
+                with get_logger().contextualize(**log_context):
+                    if get_identity_provider().verify_eligibility("bitbucket",
+                                                                     sender_id, pr_url) is not Eligibility.NOT_ELIGIBLE:
+                        await agent.handle_request(pr_url, comment_body)
+        except Exception as e:
+            get_logger().error(f"Failed to handle webhook: {e}")
+    background_tasks.add_task(inner)
+    return "OK"
+
+@router.get("/webhook")
+async def handle_github_webhooks(request: Request, response: Response):
+    return "Webhook server online!"
+
+@router.post("/installed")
+async def handle_installed_webhooks(request: Request, response: Response):
+    try:
+        get_logger().info("handle_installed_webhooks")
+        get_logger().info(request.headers)
+        data = await request.json()
+        get_logger().info(data)
+        shared_secret = data["sharedSecret"]
+        client_key = data["clientKey"]
+        username = data["principal"]["username"]
+        secrets = {
+            "shared_secret": shared_secret,
+            "client_key": client_key
+        }
+        secret_provider.store_secret(username, json.dumps(secrets))
+    except Exception as 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()
+    get_logger().info(data)
+
+
+def start():
+    get_settings().set("CONFIG.PUBLISH_OUTPUT_PROGRESS", False)
+    get_settings().set("CONFIG.GIT_PROVIDER", "bitbucket")
+    get_settings().set("PR_DESCRIPTION.PUBLISH_DESCRIPTION_AS_COMMENT", True)
+    middleware = [Middleware(RawContextMiddleware)]
+    app = FastAPI(middleware=middleware)
+    app.include_router(router)
+
+    uvicorn.run(app, host="0.0.0.0", port=int(os.getenv("PORT", "3000")))
+
+
+if __name__ == '__main__':
+    start()

pr_agent/servers/bitbucket_server_webhook.py

@@ -0,0 +1,80 @@
+import json
+import os
+
+import uvicorn
+from fastapi import APIRouter, FastAPI
+from fastapi.encoders import jsonable_encoder
+from starlette import status
+from starlette.background import BackgroundTasks
+from starlette.middleware import Middleware
+from starlette.requests import Request
+from starlette.responses import JSONResponse
+from starlette_context.middleware import RawContextMiddleware
+
+from pr_agent.agent.pr_agent import PRAgent
+from pr_agent.config_loader import get_settings
+from pr_agent.log import get_logger
+from pr_agent.servers.utils import verify_signature
+
+router = APIRouter()
+
+
+def handle_request(
+    background_tasks: BackgroundTasks, url: str, body: str, log_context: dict
+):
+    log_context["action"] = body
+    log_context["api_url"] = url
+    with get_logger().contextualize(**log_context):
+        background_tasks.add_task(PRAgent().handle_request, url, body)
+
+
+@router.post("/")
+async def handle_webhook(background_tasks: BackgroundTasks, request: Request):
+    log_context = {"server_type": "bitbucket_server"}
+    data = await request.json()
+    get_logger().info(json.dumps(data))
+
+    webhook_secret = get_settings().get("BITBUCKET_SERVER.WEBHOOK_SECRET", None)
+    if webhook_secret:
+        body_bytes = await request.body()
+        signature_header = request.headers.get("x-hub-signature", None)
+        verify_signature(body_bytes, webhook_secret, signature_header)
+
+    pr_id = data["pullRequest"]["id"]
+    repository_name = data["pullRequest"]["toRef"]["repository"]["slug"]
+    project_name = data["pullRequest"]["toRef"]["repository"]["project"]["key"]
+    bitbucket_server = get_settings().get("BITBUCKET_SERVER.URL")
+    pr_url = f"{bitbucket_server}/projects/{project_name}/repos/{repository_name}/pull-requests/{pr_id}"
+
+    log_context["api_url"] = pr_url
+    log_context["event"] = "pull_request"
+
+    if data["eventKey"] == "pr:opened":
+        body = "review"
+    elif data["eventKey"] == "pr:comment:added":
+        body = data["comment"]["text"]
+    else:
+        return JSONResponse(
+            status_code=status.HTTP_400_BAD_REQUEST,
+            content=json.dumps({"message": "Unsupported event"}),
+        )
+
+    handle_request(background_tasks, pr_url, body, log_context)
+    return JSONResponse(
+        status_code=status.HTTP_200_OK, content=jsonable_encoder({"message": "success"})
+    )
+
+
+@router.get("/")
+async def root():
+    return {"status": "ok"}
+
+
+def start():
+    app = FastAPI(middleware=[Middleware(RawContextMiddleware)])
+    app.include_router(router)
+    uvicorn.run(app, host="0.0.0.0", port=int(os.environ.get("PORT", "3000")))
+
+
+if __name__ == "__main__":
+    start()

pr_agent/servers/gerrit_server.py

@@ -0,0 +1,77 @@
+import copy
+from enum import Enum
+from json import JSONDecodeError
+
+import uvicorn
+from fastapi import APIRouter, FastAPI, HTTPException
+from pydantic import BaseModel
+from starlette.middleware import Middleware
+from starlette_context import context
+from starlette_context.middleware import RawContextMiddleware
+
+from pr_agent.agent.pr_agent import PRAgent
+from pr_agent.config_loader import get_settings, global_settings
+from pr_agent.log import get_logger, setup_logger
+
+setup_logger()
+router = APIRouter()
+
+
+class Action(str, Enum):
+    review = "review"
+    describe = "describe"
+    ask = "ask"
+    improve = "improve"
+    reflect = "reflect"
+    answer = "answer"
+
+
+class Item(BaseModel):
+    refspec: str
+    project: str
+    msg: str
+
+
+@router.post("/api/v1/gerrit/{action}")
+async def handle_gerrit_request(action: Action, item: Item):
+    get_logger().debug("Received a Gerrit request")
+    context["settings"] = copy.deepcopy(global_settings)
+
+    if action == Action.ask:
+        if not item.msg:
+            return HTTPException(
+                status_code=400,
+                detail="msg is required for ask command"
+            )
+    await PRAgent().handle_request(
+        f"{item.project}:{item.refspec}",
+        f"/{item.msg.strip()}"
+    )
+
+
+async def get_body(request):
+    try:
+        body = await request.json()
+    except JSONDecodeError as e:
+        get_logger().error("Error parsing request body", e)
+        return {}
+    return body
+
+
+@router.get("/")
+async def root():
+    return {"status": "ok"}
+
+
+def start():
+    # to prevent adding help messages with the output
+    get_settings().set("CONFIG.CLI_MODE", True)
+    middleware = [Middleware(RawContextMiddleware)]
+    app = FastAPI(middleware=middleware)
+    app.include_router(router)
+
+    uvicorn.run(app, host="0.0.0.0", port=3000)
+
+
+if __name__ == '__main__':
+    start()

pr_agent/servers/github_action_runner.py

@@ -1,57 +1,142 @@
 import asyncio
 import json
 import os
+from typing import Union
 
-from pr_agent.config_loader import settings
-from pr_agent.tools.pr_questions import PRQuestions
+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.servers.github_app import handle_line_comments
+from pr_agent.tools.pr_code_suggestions import PRCodeSuggestions
+from pr_agent.tools.pr_description import PRDescription
 from pr_agent.tools.pr_reviewer import PRReviewer
 
 
+def is_true(value: Union[str, bool]) -> bool:
+    if isinstance(value, bool):
+        return value
+    if isinstance(value, str):
+        return value.lower() == 'true'
+    return False
+
+
+def get_setting_or_env(key: str, default: Union[str, bool] = None) -> Union[str, bool]:
+    try:
+        value = get_settings().get(key, default)
+    except AttributeError:  # TBD still need to debug why this happens on GitHub Actions
+        value = os.getenv(key, None) or os.getenv(key.upper(), None) or os.getenv(key.lower(), None) or default
+    return value
+
+
 async def run_action():
-    GITHUB_EVENT_NAME = os.environ.get('GITHUB_EVENT_NAME', None)
+    # Get environment variables
+    GITHUB_EVENT_NAME = os.environ.get('GITHUB_EVENT_NAME')
+    GITHUB_EVENT_PATH = os.environ.get('GITHUB_EVENT_PATH')
+    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)
+
+    # Check if required environment variables are set
     if not GITHUB_EVENT_NAME:
         print("GITHUB_EVENT_NAME not set")
         return
-    GITHUB_EVENT_PATH = os.environ.get('GITHUB_EVENT_PATH', None)
     if not GITHUB_EVENT_PATH:
         print("GITHUB_EVENT_PATH not set")
         return
-    event_payload = json.load(open(GITHUB_EVENT_PATH, 'r'))
-    RUNNER_DEBUG = os.environ.get('RUNNER_DEBUG', None)
-    if not RUNNER_DEBUG:
-        print("RUNNER_DEBUG not set")
-    OPENAI_KEY = os.environ.get('OPENAI_KEY', None)
     if not OPENAI_KEY:
         print("OPENAI_KEY not set")
         return
-    OPENAI_ORG = os.environ.get('OPENAI_ORG', None)
-    GITHUB_TOKEN = os.environ.get('GITHUB_TOKEN', None)
     if not GITHUB_TOKEN:
         print("GITHUB_TOKEN not set")
         return
-    settings.set("OPENAI.KEY", OPENAI_KEY)
-    if OPENAI_ORG:
-        settings.set("OPENAI.ORG", OPENAI_ORG)
-    settings.set("GITHUB.USER_TOKEN", GITHUB_TOKEN)
-    settings.set("GITHUB.DEPLOYMENT_TYPE", "user")
-    if GITHUB_EVENT_NAME == "pull_request":
-        action = event_payload.get("action", None)
-        if action in ["opened", "reopened"]:
-            pr_url = event_payload.get("pull_request", {}).get("url", None)
-            if pr_url:
-                await PRReviewer(pr_url).review()
 
-    elif GITHUB_EVENT_NAME == "issue_comment":
-        action = event_payload.get("action", None)
+    # Set the environment variables in the settings
+    get_settings().set("OPENAI.KEY", OPENAI_KEY)
+    if OPENAI_ORG:
+        get_settings().set("OPENAI.ORG", OPENAI_ORG)
+    get_settings().set("GITHUB.USER_TOKEN", GITHUB_TOKEN)
+    get_settings().set("GITHUB.DEPLOYMENT_TYPE", "user")
+
+    # Load the event payload
+    try:
+        with open(GITHUB_EVENT_PATH, 'r') as f:
+            event_payload = json.load(f)
+    except json.decoder.JSONDecodeError as e:
+        print(f"Failed to parse JSON: {e}")
+        return
+
+    try:
+        get_logger().info("Applying repo settings")
+        pr_url = event_payload.get("pull_request", {}).get("html_url")
+        if pr_url:
+            apply_repo_settings(pr_url)
+            get_logger().info(f"enable_custom_labels: {get_settings().config.enable_custom_labels}")
+    except Exception as e:
+        get_logger().info(f"github action: failed to apply repo settings: {e}")
+
+    # Handle pull request event
+    if GITHUB_EVENT_NAME == "pull_request":
+        action = event_payload.get("action")
+        if action in ["opened", "reopened", "ready_for_review", "review_requested"]:
+            pr_url = event_payload.get("pull_request", {}).get("url")
+            if pr_url:
+                # legacy - supporting both GITHUB_ACTION and GITHUB_ACTION_CONFIG
+                auto_review = get_setting_or_env("GITHUB_ACTION.AUTO_REVIEW", None)
+                if auto_review is None:
+                    auto_review = get_setting_or_env("GITHUB_ACTION_CONFIG.AUTO_REVIEW", None)
+                auto_describe = get_setting_or_env("GITHUB_ACTION.AUTO_DESCRIBE", None)
+                if auto_describe is None:
+                    auto_describe = get_setting_or_env("GITHUB_ACTION_CONFIG.AUTO_DESCRIBE", None)
+                auto_improve = get_setting_or_env("GITHUB_ACTION.AUTO_IMPROVE", None)
+                if auto_improve is None:
+                    auto_improve = get_setting_or_env("GITHUB_ACTION_CONFIG.AUTO_IMPROVE", None)
+
+                # invoke by default all three tools
+                if auto_describe is None or is_true(auto_describe):
+                    await PRDescription(pr_url).run()
+                if auto_review is None or is_true(auto_review):
+                    await PRReviewer(pr_url).run()
+                if auto_improve is None or is_true(auto_improve):
+                    await PRCodeSuggestions(pr_url).run()
+
+    # Handle issue comment event
+    elif GITHUB_EVENT_NAME == "issue_comment" or GITHUB_EVENT_NAME == "pull_request_review_comment":
+        action = event_payload.get("action")
         if action in ["created", "edited"]:
-            comment_body = event_payload.get("comment", {}).get("body", None)
+            comment_body = event_payload.get("comment", {}).get("body")
+            try:
+                if GITHUB_EVENT_NAME == "pull_request_review_comment":
+                    if '/ask' in comment_body:
+                        comment_body = handle_line_comments(event_payload, comment_body)
+            except Exception as e:
+                get_logger().error(f"Failed to handle line comments: {e}")
+                return
             if comment_body:
-                pr_url = event_payload.get("issue", {}).get("pull_request", {}).get("url", None)
-                if pr_url:
-                    if comment_body.strip().lower() == "review":
-                        await PRReviewer(pr_url).review()
-                    elif comment_body.lstrip().lower().startswith("answer"):
-                        await PRQuestions(pr_url, comment_body).answer()
+                is_pr = False
+                disable_eyes = False
+                # check if issue is pull request
+                if event_payload.get("issue", {}).get("pull_request"):
+                    url = event_payload.get("issue", {}).get("pull_request", {}).get("url")
+                    is_pr = True
+                elif event_payload.get("comment", {}).get("pull_request_url"): # for 'pull_request_review_comment
+                    url = event_payload.get("comment", {}).get("pull_request_url")
+                    is_pr = True
+                    disable_eyes = True
+                else:
+                    url = event_payload.get("issue", {}).get("url")
+
+                if url:
+                    body = comment_body.strip().lower()
+                    comment_id = event_payload.get("comment", {}).get("id")
+                    provider = get_git_provider()(pr_url=url)
+                    if is_pr:
+                        await PRAgent().handle_request(url, body,
+                                    notify=lambda: provider.add_eyes_reaction(comment_id, disable_eyes=disable_eyes))
+                    else:
+                        await PRAgent().handle_request(url, body)
 
 
 if __name__ == '__main__':

pr_agent/servers/github_app.py

@@ -1,64 +1,328 @@
-import logging
-import sys
+import asyncio.locks
+import copy
+import os
+import re
+import uuid
+from typing import Any, Dict, Tuple
 
 import uvicorn
 from fastapi import APIRouter, FastAPI, HTTPException, Request, Response
+from starlette.middleware import Middleware
+from starlette_context import context
+from starlette_context.middleware import RawContextMiddleware
 
 from pr_agent.agent.pr_agent import PRAgent
-from pr_agent.config_loader import settings
-from pr_agent.servers.utils import verify_signature
+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.git_provider import IncrementalPR
+from pr_agent.git_providers.utils import apply_repo_settings
+from pr_agent.identity_providers import get_identity_provider
+from pr_agent.identity_providers.identity_provider import Eligibility
+from pr_agent.log import LoggingFormat, get_logger, setup_logger
+from pr_agent.servers.utils import DefaultDictWithTimeout, verify_signature
 
-logging.basicConfig(stream=sys.stdout, level=logging.DEBUG)
+setup_logger(fmt=LoggingFormat.JSON, level="DEBUG")
+base_path = os.path.dirname(os.path.dirname(os.path.realpath(__file__)))
+build_number_path = os.path.join(base_path, "build_number.txt")
+if os.path.exists(build_number_path):
+    with open(build_number_path) as f:
+        build_number = f.read().strip()
+else:
+    build_number = "unknown"
 router = APIRouter()
 
 
 @router.post("/api/v1/github_webhooks")
 async def handle_github_webhooks(request: Request, response: Response):
-    logging.debug("Received a github webhook")
+    """
+    Receives and processes incoming GitHub webhook requests.
+    Verifies the request signature, parses the request body, and passes it to the handle_request function for further
+    processing.
+    """
+    get_logger().debug("Received a GitHub webhook")
+
+    body = await get_body(request)
+
+    installation_id = body.get("installation", {}).get("id")
+    context["installation_id"] = installation_id
+    context["settings"] = copy.deepcopy(global_settings)
+
+    response = await handle_request(body, event=request.headers.get("X-GitHub-Event", None))
+    return response or {}
+
+
+@router.post("/api/v1/marketplace_webhooks")
+async def handle_marketplace_webhooks(request: Request, response: Response):
+    body = await get_body(request)
+    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
-    body_bytes = await request.body()
-    signature_header = request.headers.get('x-hub-signature-256', None)
-    try:
-        webhook_secret = settings.github.webhook_secret
-    except AttributeError:
-        webhook_secret = None
+    webhook_secret = getattr(get_settings().github, 'webhook_secret', None)
     if webhook_secret:
+        body_bytes = await request.body()
+        signature_header = request.headers.get('x-hub-signature-256', None)
         verify_signature(body_bytes, webhook_secret, signature_header)
-    logging.debug(f'Request body:\n{body}')
-    return await handle_request(body)
+    return body
 
 
-async def handle_request(body):
-    action = body.get("action", None)
-    installation_id = body.get("installation", {}).get("id", None)
-    settings.set("GITHUB.INSTALLATION_ID", installation_id)
-    agent = PRAgent()
-    if action == 'created':
-        if "comment" not in body:
-            return {}
-        comment_body = body.get("comment", {}).get("body", None)
-        if 'sender' in body and 'login' in body['sender'] and 'bot' in body['sender']['login']:
-            return {}
-        if "issue" not in body and "pull_request" not in body["issue"]:
-            return {}
-        pull_request = body["issue"]["pull_request"]
-        api_url = pull_request.get("url", None)
-        await agent.handle_request(api_url, comment_body)
+_duplicate_push_triggers = DefaultDictWithTimeout(ttl=get_settings().github_app.push_trigger_pending_tasks_ttl)
+_pending_task_duplicate_push_conditions = DefaultDictWithTimeout(asyncio.locks.Condition, ttl=get_settings().github_app.push_trigger_pending_tasks_ttl)
 
-    elif action in ["opened"] or 'reopened' in action:
-        pull_request = body.get("pull_request", None)
-        if not pull_request:
-            return {}
-        api_url = pull_request.get("url", None)
-        if api_url is None:
-            return {}
-        await agent.handle_request(api_url, "please review")
+async def handle_comments_on_pr(body: Dict[str, Any],
+                                event: str,
+                                sender: str,
+                                sender_id: str,
+                                action: str,
+                                log_context: Dict[str, Any],
+                                agent: PRAgent):
+    if "comment" not in body:
+        return {}
+    comment_body = body.get("comment", {}).get("body")
+    if comment_body and isinstance(comment_body, str) and not comment_body.lstrip().startswith("/"):
+        get_logger().info("Ignoring comment not starting with /")
+        return {}
+    disable_eyes = False
+    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"]
+        try:
+            if ('/ask' in comment_body and
+                    'subject_type' in body["comment"] and body["comment"]["subject_type"] == "line"):
+                # comment on a code line in the "files changed" tab
+                comment_body = handle_line_comments(body, comment_body)
+                disable_eyes = True
+        except Exception as e:
+            get_logger().error(f"Failed to handle line comments: {e}")
     else:
         return {}
+    log_context["api_url"] = api_url
+    comment_id = body.get("comment", {}).get("id")
+    provider = get_git_provider()(pr_url=api_url)
+    with get_logger().contextualize(**log_context):
+        if get_identity_provider().verify_eligibility("github", sender_id, api_url) is not Eligibility.NOT_ELIGIBLE:
+            get_logger().info(f"Processing comment on PR {api_url=}, comment_body={comment_body}")
+            await agent.handle_request(api_url, comment_body,
+                        notify=lambda: provider.add_eyes_reaction(comment_id, disable_eyes=disable_eyes))
+        else:
+            get_logger().info(f"User {sender=} is not eligible to process comment on PR {api_url=}")
+
+async def handle_new_pr_opened(body: Dict[str, Any],
+                               event: str,
+                               sender: str,
+                               sender_id: str,
+                               action: str,
+                               log_context: Dict[str, Any],
+                               agent: PRAgent):
+    title = body.get("pull_request", {}).get("title", "")
+
+    # logic to ignore PRs with specific titles (e.g. "[Auto] ...")
+    ignore_pr_title_re = get_settings().get("GITHUB_APP.IGNORE_PR_TITLE", [])
+    if not isinstance(ignore_pr_title_re, list):
+        ignore_pr_title_re = [ignore_pr_title_re]
+    if ignore_pr_title_re and any(re.search(regex, title) for regex in ignore_pr_title_re):
+        get_logger().info(f"Ignoring PR with title '{title}' due to github_app.ignore_pr_title setting")
+        return {}
+
+    pull_request, api_url = _check_pull_request_event(action, body, log_context)
+    if not (pull_request and api_url):
+        get_logger().info(f"Invalid PR event: {action=} {api_url=}")
+        return {}
+    if action in get_settings().github_app.handle_pr_actions:  # ['opened', 'reopened', 'ready_for_review', 'review_requested']
+        if get_identity_provider().verify_eligibility("github", sender_id, api_url) is not Eligibility.NOT_ELIGIBLE:
+            await _perform_auto_commands_github("pr_commands", agent, body, api_url, log_context)
+        else:
+            get_logger().info(f"User {sender=} is not eligible to process PR {api_url=}")
+
+async def handle_push_trigger_for_new_commits(body: Dict[str, Any],
+                        event: str,
+                        sender: str,
+                        sender_id: str,
+                        action: str,
+                        log_context: Dict[str, Any],
+                        agent: PRAgent):
+    pull_request, api_url = _check_pull_request_event(action, body, log_context)
+    if not (pull_request and api_url):
+        return {}
+
+    apply_repo_settings(api_url) # we need to apply the repo settings to get the correct settings for the PR. This is quite expensive - a call to the git provider is made for each PR event.
+    if not get_settings().github_app.handle_push_trigger:
+        return {}
+
+    # TODO: do we still want to get the list of commits to filter bot/merge commits?
+    before_sha = body.get("before")
+    after_sha = body.get("after")
+    merge_commit_sha = pull_request.get("merge_commit_sha")
+    if before_sha == after_sha:
+        return {}
+    if get_settings().github_app.push_trigger_ignore_merge_commits and after_sha == merge_commit_sha:
+        return {}
+
+    # Prevent triggering multiple times for subsequent push triggers when one is enough:
+    # The first push will trigger the processing, and if there's a second push in the meanwhile it will wait.
+    # Any more events will be discarded, because they will all trigger the exact same processing on the PR.
+    # We let the second event wait instead of discarding it because while the first event was being processed,
+    # more commits may have been pushed that led to the subsequent events,
+    # so we keep just one waiting as a delegate to trigger the processing for the new commits when done waiting.
+    current_active_tasks = _duplicate_push_triggers.setdefault(api_url, 0)
+    max_active_tasks = 2 if get_settings().github_app.push_trigger_pending_tasks_backlog else 1
+    if current_active_tasks < max_active_tasks:
+        # first task can enter, and second tasks too if backlog is enabled
+        get_logger().info(
+            f"Continue processing push trigger for {api_url=} because there are {current_active_tasks} active tasks"
+        )
+        _duplicate_push_triggers[api_url] += 1
+    else:
+        get_logger().info(
+            f"Skipping push trigger for {api_url=} because another event already triggered the same processing"
+        )
+        return {}
+    async with _pending_task_duplicate_push_conditions[api_url]:
+        if current_active_tasks == 1:
+            # second task waits
+            get_logger().info(
+                f"Waiting to process push trigger for {api_url=} because the first task is still in progress"
+            )
+            await _pending_task_duplicate_push_conditions[api_url].wait()
+            get_logger().info(f"Finished waiting to process push trigger for {api_url=} - continue with flow")
+
+    try:
+        if get_settings().github_app.push_trigger_wait_for_initial_review and not get_git_provider()(api_url,
+                                                                                                     incremental=IncrementalPR(
+                                                                                                             True)).previous_review:
+            get_logger().info(f"Skipping incremental review because there was no initial review for {api_url=} yet")
+            return {}
+        if get_identity_provider().verify_eligibility("github", sender_id, api_url) is not Eligibility.NOT_ELIGIBLE:
+            get_logger().info(f"Performing incremental review for {api_url=} because of {event=} and {action=}")
+            await _perform_auto_commands_github("push_commands", agent, body, api_url, log_context)
+
+    finally:
+        # release the waiting task block
+        async with _pending_task_duplicate_push_conditions[api_url]:
+            _pending_task_duplicate_push_conditions[api_url].notify(1)
+            _duplicate_push_triggers[api_url] -= 1
+
+
+def handle_closed_pr(body, event, action, log_context):
+    pull_request = body.get("pull_request", {})
+    is_merged = pull_request.get("merged", False)
+    if not is_merged:
+        return
+    api_url = pull_request.get("url", "")
+    pr_statistics = get_git_provider()(pr_url=api_url).calc_pr_statistics(pull_request)
+    log_context["api_url"] = api_url
+    get_logger().info("PR-Agent statistics for closed PR", analytics=True, pr_statistics=pr_statistics, **log_context)
+
+
+def get_log_context(body, event, action, build_number):
+    sender = ""
+    sender_id = ""
+    try:
+        sender = body.get("sender", {}).get("login")
+        sender_id = body.get("sender", {}).get("id")
+        repo = body.get("repository", {}).get("full_name", "")
+        git_org = body.get("organization", {}).get("login", "")
+        app_name = get_settings().get("CONFIG.APP_NAME", "Unknown")
+        log_context = {"action": action, "event": event, "sender": sender, "server_type": "github_app",
+                       "request_id": uuid.uuid4().hex, "build_number": build_number, "app_name": app_name,
+                       "repo": repo, "git_org": git_org}
+    except Exception as e:
+        get_logger().error("Failed to get log context", e)
+        log_context = {}
+    return log_context, sender, sender_id
+
+
+async def handle_request(body: Dict[str, Any], event: str):
+    """
+    Handle incoming GitHub webhook requests.
+
+    Args:
+        body: The request body.
+        event: The GitHub event type (e.g. "pull_request", "issue_comment", etc.).
+    """
+    action = body.get("action") # "created", "opened", "reopened", "ready_for_review", "review_requested", "synchronize"
+    if not action:
+        return {}
+    agent = PRAgent()
+    log_context, sender, sender_id = get_log_context(body, event, action, build_number)
+
+    # handle comments on PRs
+    if action == 'created':
+        get_logger().debug(f'Request body', artifact=body, event=event)
+        await handle_comments_on_pr(body, event, sender, sender_id, action, log_context, agent)
+    # handle new PRs
+    elif event == 'pull_request' and action != 'synchronize' and action != 'closed':
+        get_logger().debug(f'Request body', artifact=body, event=event)
+        await handle_new_pr_opened(body, event, sender, sender_id, action, log_context, agent)
+    # handle pull_request event with synchronize action - "push trigger" for new commits
+    elif event == 'pull_request' and action == 'synchronize':
+        get_logger().debug(f'Request body', artifact=body, event=event)
+        await handle_push_trigger_for_new_commits(body, event, sender, sender_id, action, log_context, agent)
+    elif event == 'pull_request' and action == 'closed':
+        if get_settings().get("CONFIG.ANALYTICS_FOLDER", ""):
+            handle_closed_pr(body, event, action, log_context)
+    else:
+        get_logger().info(f"event {event=} action {action=} does not require any handling")
+    return {}
+
+
+def handle_line_comments(body: Dict, comment_body: [str, Any]) -> str:
+    if not comment_body:
+        return ""
+    start_line = body["comment"]["start_line"]
+    end_line = body["comment"]["line"]
+    start_line = end_line if not start_line else start_line
+    question = comment_body.replace('/ask', '').strip()
+    diff_hunk = body["comment"]["diff_hunk"]
+    get_settings().set("ask_diff_hunk", diff_hunk)
+    path = body["comment"]["path"]
+    side = body["comment"]["side"]
+    comment_id = body["comment"]["id"]
+    if '/ask' in comment_body:
+        comment_body = f"/ask_line --line_start={start_line} --line_end={end_line} --side={side} --file_name={path} --comment_id={comment_id} {question}"
+    return comment_body
+
+
+def _check_pull_request_event(action: str, body: dict, log_context: dict) -> Tuple[Dict[str, Any], str]:
+    invalid_result = {}, ""
+    pull_request = body.get("pull_request")
+    if not pull_request:
+        return invalid_result
+    api_url = pull_request.get("url")
+    if not api_url:
+        return invalid_result
+    log_context["api_url"] = api_url
+    if pull_request.get("draft", True) or pull_request.get("state") != "open":
+        return invalid_result
+    if action in ("review_requested", "synchronize") and pull_request.get("created_at") == pull_request.get("updated_at"):
+        # avoid double reviews when opening a PR for the first time
+        return invalid_result
+    return pull_request, api_url
+
+
+async def _perform_auto_commands_github(commands_conf: str, agent: PRAgent, body: dict, api_url: str, log_context: dict):
+    apply_repo_settings(api_url)
+    commands = get_settings().get(f"github_app.{commands_conf}")
+    if not commands:
+        with get_logger().contextualize(**log_context):
+            get_logger().info(f"New PR, but no auto commands configured")
+        return
+    for command in commands:
+        split_command = command.split(" ")
+        command = split_command[0]
+        args = split_command[1:]
+        other_args = update_settings_from_args(args)
+        new_command = ' '.join([command] + other_args)
+        with get_logger().contextualize(**log_context):
+            get_logger().info(f"{commands_conf}. Performing auto command '{new_command}', for {api_url=}")
+            await agent.handle_request(api_url, new_command)
 
 
 @router.get("/")
@@ -66,14 +330,17 @@ async def root():
     return {"status": "ok"}
 
 
-def start():
+if get_settings().github_app.override_deployment_type:
     # Override the deployment type to app
-    settings.set("GITHUB.DEPLOYMENT_TYPE", "app")
-    app = FastAPI()
-    app.include_router(router)
+    get_settings().set("GITHUB.DEPLOYMENT_TYPE", "app")
+get_settings().set("CONFIG.PUBLISH_OUTPUT_PROGRESS", False)
+middleware = [Middleware(RawContextMiddleware)]
+app = FastAPI(middleware=middleware)
+app.include_router(router)
 
-    uvicorn.run(app, host="0.0.0.0", port=3000)
 
+def start():
+    uvicorn.run(app, host="0.0.0.0", port=int(os.environ.get("PORT", "3000")))
 
 if __name__ == '__main__':
     start()

pr_agent/servers/github_polling.py

@@ -1,40 +1,53 @@
 import asyncio
-import logging
-import sys
 from datetime import datetime, timezone
 
 import aiohttp
 
 from pr_agent.agent.pr_agent import PRAgent
-from pr_agent.config_loader import settings
+from pr_agent.config_loader import get_settings
 from pr_agent.git_providers import get_git_provider
+from pr_agent.log import LoggingFormat, get_logger, setup_logger
 
-logging.basicConfig(stream=sys.stdout, level=logging.DEBUG)
+setup_logger(fmt=LoggingFormat.JSON)
 NOTIFICATION_URL = "https://api.github.com/notifications"
 
 
 def now() -> str:
+    """
+    Get the current UTC time in ISO 8601 format.
+    
+    Returns:
+        str: The current UTC time in ISO 8601 format.
+    """
     now_utc = datetime.now(timezone.utc).isoformat()
     now_utc = now_utc.replace("+00:00", "Z")
     return now_utc
 
 
 async def polling_loop():
+    """
+    Polls for notifications and handles them accordingly.
+    """
     handled_ids = set()
     since = [now()]
     last_modified = [None]
     git_provider = get_git_provider()()
     user_id = git_provider.get_user_id()
+    agent = PRAgent()
+    get_settings().set("CONFIG.PUBLISH_OUTPUT_PROGRESS", False)
+
     try:
-        deployment_type = settings.github.deployment_type
-        token = settings.github.user_token
+        deployment_type = get_settings().github.deployment_type
+        token = get_settings().github.user_token
     except AttributeError:
         deployment_type = 'none'
         token = None
+
     if deployment_type != 'user':
         raise ValueError("Deployment mode must be set to 'user' to get notifications")
     if not token:
         raise ValueError("User token must be set to get notifications")
+
     async with aiohttp.ClientSession() as session:
         while True:
             try:
@@ -50,6 +63,7 @@ async def polling_loop():
                     params["since"] = since[0]
                 if last_modified[0]:
                     headers["If-Modified-Since"] = last_modified[0]
+
                 async with session.get(NOTIFICATION_URL, headers=headers, params=params) as response:
                     if response.status == 200:
                         if 'Last-Modified' in response.headers:
@@ -78,18 +92,24 @@ 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
                                             rest_of_comment = comment_body.split(user_tag)[1].strip()
-                                            agent = PRAgent()
-                                            await agent.handle_request(pr_url, rest_of_comment)
+                                            comment_id = comment['id']
+                                            git_provider.set_pr(pr_url)
+                                            success = await agent.handle_request(pr_url, rest_of_comment,
+                                                                                 notify=lambda: git_provider.add_eyes_reaction(comment_id))  # noqa E501
+                                            if not success:
+                                                git_provider.set_pr(pr_url)
+
                     elif response.status != 304:
                         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__':
-    asyncio.run(polling_loop())
+    asyncio.run(polling_loop())

pr_agent/servers/gitlab_polling.py

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

pr_agent/servers/gitlab_webhook.py

@@ -0,0 +1,126 @@
+import copy
+import json
+
+import uvicorn
+from fastapi import APIRouter, FastAPI, Request, status
+from fastapi.encoders import jsonable_encoder
+from fastapi.responses import JSONResponse
+from starlette.background import BackgroundTasks
+from starlette.middleware import Middleware
+from starlette_context import context
+from starlette_context.middleware import RawContextMiddleware
+
+from pr_agent.agent.pr_agent import PRAgent
+from pr_agent.algo.utils import update_settings_from_args
+from pr_agent.config_loader import get_settings, global_settings
+from pr_agent.git_providers.utils import apply_repo_settings
+from pr_agent.log import LoggingFormat, get_logger, setup_logger
+from pr_agent.secret_providers import get_secret_provider
+
+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)
+
+
+async def _perform_commands_gitlab(commands_conf: str, agent: PRAgent, api_url: str, log_context: dict):
+    apply_repo_settings(api_url)
+    commands = get_settings().get(f"gitlab.{commands_conf}", {})
+    for command in commands:
+        try:
+            split_command = command.split(" ")
+            command = split_command[0]
+            args = split_command[1:]
+            other_args = update_settings_from_args(args)
+            new_command = ' '.join([command] + other_args)
+            get_logger().info(f"Performing command: {new_command}")
+            with get_logger().contextualize(**log_context):
+                await agent.handle_request(api_url, new_command)
+        except Exception as e:
+            get_logger().error(f"Failed to perform command {command}: {e}")
+
+
+@router.post("/webhook")
+async def gitlab_webhook(background_tasks: BackgroundTasks, request: Request):
+    log_context = {"server_type": "gitlab_app"}
+    if request.headers.get("X-Gitlab-Token") and secret_provider:
+        request_token = request.headers.get("X-Gitlab-Token")
+        secret = secret_provider.get_secret(request_token)
+        try:
+            secret_dict = json.loads(secret)
+            gitlab_token = secret_dict["gitlab_token"]
+            log_context["sender"] = secret_dict.get("token_name", secret_dict.get("id", "unknown"))
+            context["settings"] = copy.deepcopy(global_settings)
+            context["settings"].gitlab.personal_access_token = gitlab_token
+        except Exception as e:
+            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")
+        if not request.headers.get("X-Gitlab-Token") == secret:
+            return JSONResponse(status_code=status.HTTP_401_UNAUTHORIZED, content=jsonable_encoder({"message": "unauthorized"}))
+    else:
+        return JSONResponse(status_code=status.HTTP_401_UNAUTHORIZED, content=jsonable_encoder({"message": "unauthorized"}))
+    gitlab_token = get_settings().get("GITLAB.PERSONAL_ACCESS_TOKEN", None)
+    if not gitlab_token:
+        return JSONResponse(status_code=status.HTTP_401_UNAUTHORIZED, content=jsonable_encoder({"message": "unauthorized"}))
+    data = await request.json()
+    get_logger().info(json.dumps(data))
+    if data.get('object_kind') == 'merge_request' and data['object_attributes'].get('action') in ['open', 'reopen']:
+        get_logger().info(f"A merge request has been opened: {data['object_attributes'].get('title')}")
+        url = data['object_attributes'].get('url')
+        await _perform_commands_gitlab("pr_commands", PRAgent(), url, log_context)
+        # handle_request(background_tasks, url, "/review", log_context)
+    elif data.get('object_kind') == 'note' and data['event_type'] == 'note':
+        if 'merge_request' in data:
+            mr = data['merge_request']
+            url = mr.get('url')
+            body = data.get('object_attributes', {}).get('note')
+            if data.get('object_attributes', {}).get('type') == 'DiffNote' and '/ask' in body:
+                line_range_ = data['object_attributes']['position']['line_range']
+
+                # if line_range_['start']['type'] == 'new':
+                start_line = line_range_['start']['new_line']
+                end_line = line_range_['end']['new_line']
+                # else:
+                #     start_line = line_range_['start']['old_line']
+                #     end_line = line_range_['end']['old_line']
+
+                question = body.replace('/ask', '').strip()
+                path = data['object_attributes']['position']['new_path']
+                side = 'RIGHT'# if line_range_['start']['type'] == 'new' else 'LEFT'
+                comment_id = data['object_attributes']["discussion_id"]
+                get_logger().info(f"Handling line comment")
+                body = f"/ask_line --line_start={start_line} --line_end={end_line} --side={side} --file_name={path} --comment_id={comment_id} {question}"
+
+            handle_request(background_tasks, url, body, log_context)
+
+    return JSONResponse(status_code=status.HTTP_200_OK, content=jsonable_encoder({"message": "success"}))
+
+
+@router.get("/")
+async def root():
+    return {"status": "ok"}
+
+def start():
+    gitlab_url = get_settings().get("GITLAB.URL", None)
+    if not gitlab_url:
+        raise ValueError("GITLAB.URL is not set")
+    get_settings().config.git_provider = "gitlab"
+    middleware = [Middleware(RawContextMiddleware)]
+    app = FastAPI(middleware=middleware)
+    app.include_router(router)
+
+    uvicorn.run(app, host="0.0.0.0", port=3000)
+
+
+if __name__ == '__main__':
+    start()

pr_agent/servers/help.py

@@ -0,0 +1,354 @@
+class HelpMessage:
+    @staticmethod
+    def get_general_commands_text():
+       commands_text = "> - **/review**: Request a review of your Pull Request.   \n" \
+                "> - **/describe**: Update the PR title and description based on the contents of the PR.   \n" \
+                "> - **/improve [--extended]**: Suggest code improvements. Extended mode provides a higher quality feedback.   \n" \
+                "> - **/ask \\<QUESTION\\>**: Ask a question about the PR.   \n" \
+                "> - **/update_changelog**: Update the changelog based on the PR's contents.   \n" \
+                "> - **/add_docs** 💎: Generate docstring for new components introduced in the PR.   \n" \
+                "> - **/generate_labels** 💎: Generate labels for the PR based on the PR's contents.   \n" \
+                "> - **/analyze** 💎: Automatically analyzes the PR, and presents changes walkthrough for each component.   \n\n" \
+                ">See the [tools guide](https://github.com/Codium-ai/pr-agent/blob/main/docs/TOOLS_GUIDE.md) for more details.\n" \
+                ">To list the possible configuration parameters, add a **/config** comment.   \n"
+       return commands_text
+
+
+    @staticmethod
+    def get_general_bot_help_text():
+        output = f"> To invoke the PR-Agent, add a comment using one of the following commands:  \n{HelpMessage.get_general_commands_text()} \n"
+        return output
+
+    @staticmethod
+    def get_review_usage_guide():
+        output ="**Overview:**\n"
+        output +="The `review` tool scans the PR code changes, and generates a PR review. The tool can be triggered [automatically](https://github.com/Codium-ai/pr-agent/blob/main/Usage.md#github-app-automatic-tools) every time a new PR is opened, or can be invoked manually by commenting on any PR.\n"
+        output +="""\
+When commenting, to edit [configurations](https://github.com/Codium-ai/pr-agent/blob/main/pr_agent/settings/configuration.toml#L19) related to the review tool (`pr_reviewer` section), use the following template:
+```
+/review --pr_reviewer.some_config1=... --pr_reviewer.some_config2=...
+```
+With a [configuration file](https://github.com/Codium-ai/pr-agent/blob/main/Usage.md#working-with-github-app), use the following template:
+```
+[pr_reviewer]
+some_config1=...
+some_config2=...
+```
+    """
+        output +="\n\n<table>"
+
+        # extra instructions
+        output += "<tr><td><details> <summary><strong> Utilizing extra instructions</strong></summary><hr>\n\n"
+        output += '''\
+The `review` tool can be configured with extra instructions, which can be used to guide the model to a feedback tailored to the needs of your project.
+
+Be specific, clear, and concise in the instructions. With extra instructions, you are the prompter. Specify the relevant sub-tool, and the relevant aspects of the PR that you want to emphasize.
+
+Examples for extra instructions:
+```
+[pr_reviewer] # /review #
+extra_instructions="""
+In the 'possible issues' section, emphasize the following:
+- Does the code logic cover relevant edge cases?
+- Is the code logic clear and easy to understand?
+- Is the code logic efficient?
+...
+"""
+```
+Use triple quotes to write multi-line instructions. Use bullet points to make the instructions more readable.
+        '''
+        output += "\n\n</details></td></tr>\n\n"
+
+        # automation
+        output += "<tr><td><details> <summary><strong> How to enable\\disable automation</strong></summary><hr>\n\n"
+        output += """\
+- When you first install PR-Agent app, the [default mode](https://github.com/Codium-ai/pr-agent/blob/main/Usage.md#github-app-automatic-tools) for the `review` tool is:
+```
+pr_commands = ["/review", ...]
+```
+meaning the `review` tool will run automatically on every PR, with the default configuration.
+Edit this field to enable/disable the tool, or to change the used configurations
+        """
+        output += "\n\n</details></td></tr>\n\n"
+
+#         # code feedback
+#         output += "<tr><td><details> <summary><strong> About the 'Code feedback' section</strong></summary><hr>\n\n"
+#         output+="""\
+# The `review` tool provides several type of feedbacks, one of them is code suggestions.
+# If you are interested **only** in the code suggestions, it is recommended to use the [`improve`](https://github.com/Codium-ai/pr-agent/blob/main/docs/IMPROVE.md) feature instead, since it dedicated only to code suggestions, and usually gives better results.
+# Use the `review` tool if you want to get a more comprehensive feedback, which includes code suggestions as well.
+# """
+#         output += "\n\n</details></td></tr>\n\n"
+
+        # auto-labels
+        output += "<tr><td><details> <summary><strong> Auto-labels</strong></summary><hr>\n\n"
+        output+="""\
+The `review` tool can auto-generate two specific types of labels for a PR:
+- a `possible security issue` label, that detects possible [security issues](https://github.com/Codium-ai/pr-agent/blob/tr/user_description/pr_agent/settings/pr_reviewer_prompts.toml#L136) (`enable_review_labels_security` flag)
+- a `Review effort [1-5]: x` label, where x is the estimated effort to review the PR (`enable_review_labels_effort` flag)
+"""
+        output += "\n\n</details></td></tr>\n\n"
+
+        # extra sub-tools
+        output += "<tr><td><details> <summary><strong> Extra sub-tools</strong></summary><hr>\n\n"
+        output += """\
+The `review` tool provides a collection of possible feedbacks about a PR.
+It is recommended to review the [possible options](https://github.com/Codium-ai/pr-agent/blob/main/docs/REVIEW.md#enabledisable-features), and choose the ones relevant for your use case.
+Some of the feature that are disabled by default are quite useful, and should be considered for enabling. For example: 
+`require_score_review`, `require_soc2_ticket`, and more.
+"""
+        output += "\n\n</details></td></tr>\n\n"
+
+        output += "<tr><td><details> <summary><strong> Auto-approve PRs</strong></summary><hr>\n\n"
+        output += '''\
+By invoking:
+```
+/review auto_approve
+```
+The tool will automatically approve the PR, and add a comment with the approval.
+
+
+To ensure safety, the auto-approval feature is disabled by default. To enable auto-approval, you need to actively set in a pre-defined configuration file the following:
+```
+[pr_reviewer]
+enable_auto_approval = true
+```
+(this specific flag cannot be set with a command line argument, only in the configuration file, committed to the repository)
+
+
+You can also enable auto-approval only if the PR meets certain requirements, such as that the `estimated_review_effort` is equal or below a certain threshold, by adjusting the flag:
+```
+[pr_reviewer]
+maximal_review_effort = 5
+```
+'''
+        output += "\n\n</details></td></tr>\n\n"
+
+        # general
+        output += "\n\n<tr><td><details> <summary><strong> More PR-Agent commands</strong></summary><hr> \n\n"
+        output += HelpMessage.get_general_bot_help_text()
+        output += "\n\n</details></td></tr>\n\n"
+
+        output += "</table>"
+
+        output += f"\n\nSee the [review usage](https://github.com/Codium-ai/pr-agent/blob/main/docs/REVIEW.md) page for a comprehensive guide on using this tool.\n\n"
+
+        return output
+
+
+
+    @staticmethod
+    def get_describe_usage_guide():
+        output = "**Overview:**\n"
+        output += "The `describe` tool scans the PR code changes, and generates a description for the PR - title, type, summary, walkthrough and labels. "
+        output += "The tool can be triggered [automatically](https://github.com/Codium-ai/pr-agent/blob/main/Usage.md#github-app-automatic-tools) every time a new PR is opened, or can be invoked manually by commenting on a PR.\n"
+        output += """\
+
+When commenting, to edit [configurations](https://github.com/Codium-ai/pr-agent/blob/main/pr_agent/settings/configuration.toml#L46) related to the describe tool (`pr_description` section), use the following template:
+```
+/describe --pr_description.some_config1=... --pr_description.some_config2=...
+```
+With a [configuration file](https://github.com/Codium-ai/pr-agent/blob/main/Usage.md#working-with-github-app), use the following template:
+```
+[pr_description]
+some_config1=...
+some_config2=...
+```
+"""
+        output += "\n\n<table>"
+
+        # automation
+        output += "<tr><td><details> <summary><strong> Enabling\\disabling automation </strong></summary><hr>\n\n"
+        output += """\
+- When you first install the app, the [default mode](https://github.com/Codium-ai/pr-agent/blob/main/Usage.md#github-app-automatic-tools) for the describe tool is:
+```
+pr_commands = ["/describe --pr_description.add_original_user_description=true" 
+                         "--pr_description.keep_original_user_title=true", ...]
+```
+meaning the `describe` tool will run automatically on every PR, will keep the original title, and will add the original user description above the generated description. 
+
+- Markers are an alternative way to control the generated description, to give maximal control to the user. If you set:
+```
+pr_commands = ["/describe --pr_description.use_description_markers=true", ...]
+```
+the tool will replace every marker of the form `pr_agent:marker_name` in the PR description with the relevant content, where `marker_name` is one of the following:
+  - `type`: the PR type.
+  - `summary`: the PR summary.
+  - `walkthrough`: the PR walkthrough.
+
+Note that when markers are enabled, if the original PR description does not contain any markers, the tool will not alter the description at all.
+        
+"""
+        output += "\n\n</details></td></tr>\n\n"
+
+        # custom labels
+        output += "<tr><td><details> <summary><strong> Custom labels </strong></summary><hr>\n\n"
+        output += """\
+The default labels of the `describe` tool are quite generic: [`Bug fix`, `Tests`, `Enhancement`, `Documentation`, `Other`].
+
+If you specify [custom labels](https://github.com/Codium-ai/pr-agent/blob/main/docs/DESCRIBE.md#handle-custom-labels-from-the-repos-labels-page-gem) in the repo's labels page or via configuration file, you can get tailored labels for your use cases.
+Examples for custom labels:
+- `Main topic:performance` - pr_agent:The main topic of this PR is performance
+- `New endpoint` - pr_agent:A new endpoint was added in this PR
+- `SQL query` - pr_agent:A new SQL query was added in this PR
+- `Dockerfile changes` - pr_agent:The PR contains changes in the Dockerfile
+- ...
+
+The list above is eclectic, and aims to give an idea of different possibilities. Define custom labels that are relevant for your repo and use cases.
+Note that Labels are not mutually exclusive, so you can add multiple label categories.
+Make sure to provide proper title, and a detailed and well-phrased description for each label, so the tool will know when to suggest it.        
+"""
+        output += "\n\n</details></td></tr>\n\n"
+
+        # Inline File Walkthrough
+        output += "<tr><td><details> <summary><strong> Inline File Walkthrough 💎</strong></summary><hr>\n\n"
+        output += """\
+For enhanced user experience, the `describe` tool can add file summaries directly to the "Files changed" tab in the PR page.
+This will enable you to quickly understand the changes in each file, while reviewing the code changes (diffs).
+
+To enable inline file summary, set `pr_description.inline_file_summary` in the configuration file, possible values are:
+- `'table'`: File changes walkthrough table will be displayed on the top of the "Files changed" tab, in addition to the "Conversation" tab.
+- `true`: A collapsable file comment with changes title and a changes summary for each file in the PR.
+- `false` (default): File changes walkthrough will be added only to the "Conversation" tab.
+"""
+
+        # extra instructions
+        output += "<tr><td><details> <summary><strong> Utilizing extra instructions</strong></summary><hr>\n\n"
+        output += '''\
+The `describe` tool can be configured with extra instructions, to guide the model to a feedback tailored to the needs of your project.
+
+Be specific, clear, and concise in the instructions. With extra instructions, you are the prompter. Notice that the general structure of the description is fixed, and cannot be changed. Extra instructions can change the content or style of each sub-section of the PR description.
+
+Examples for extra instructions:
+```
+[pr_description] 
+extra_instructions="""
+- The PR title should be in the format: '<PR type>: <title>'
+- The title should be short and concise (up to 10 words)
+- ...
+"""
+```
+Use triple quotes to write multi-line instructions. Use bullet points to make the instructions more readable.
+'''
+        output += "\n\n</details></td></tr>\n\n"
+
+
+        # general
+        output += "\n\n<tr><td><details> <summary><strong> More PR-Agent commands</strong></summary><hr> \n\n"
+        output += HelpMessage.get_general_bot_help_text()
+        output += "\n\n</details></td></tr>\n\n"
+
+        output += "</table>"
+
+        output += f"\n\nSee the [describe usage](https://github.com/Codium-ai/pr-agent/blob/main/docs/DESCRIBE.md) page for a comprehensive guide on using this tool.\n\n"
+
+        return output
+
+    @staticmethod
+    def get_ask_usage_guide():
+        output = "**Overview:**\n"
+        output += """\
+The `ask` tool answers questions about the PR, based on the PR code changes.
+It can be invoked manually by commenting on any PR:
+```
+/ask "..."
+```
+
+Note that the tool does not have "memory" of previous questions, and answers each question independently.        
+        """
+        output += "\n\n<table>"
+
+        # general
+        output += "\n\n<tr><td><details> <summary><strong> More PR-Agent commands</strong></summary><hr> \n\n"
+        output += HelpMessage.get_general_bot_help_text()
+        output += "\n\n</details></td></tr>\n\n"
+
+        output += "</table>"
+
+        output += f"\n\nSee the [ask usage](https://github.com/Codium-ai/pr-agent/blob/main/docs/ASK.md) page for a comprehensive guide on using this tool.\n\n"
+
+        return output
+
+
+    @staticmethod
+    def get_improve_usage_guide():
+        output = "**Overview:**\n"
+        output += "The `improve` tool scans the PR code changes, and automatically generates suggestions for improving the PR code. "
+        output += "The tool can be triggered [automatically](https://github.com/Codium-ai/pr-agent/blob/main/Usage.md#github-app-automatic-tools) every time a new PR is opened, or can be invoked manually by commenting on a PR.\n"
+        output += """\
+When commenting, to edit [configurations](https://github.com/Codium-ai/pr-agent/blob/main/pr_agent/settings/configuration.toml#L69) related to the improve tool (`pr_code_suggestions` section), use the following template:
+
+```
+/improve --pr_code_suggestions.some_config1=... --pr_code_suggestions.some_config2=...
+```
+
+With a [configuration file](https://github.com/Codium-ai/pr-agent/blob/main/Usage.md#working-with-github-app), use the following template:
+
+```
+[pr_code_suggestions]
+some_config1=...
+some_config2=...
+```
+    
+"""
+        output += "\n\n<table>"
+
+        # automation
+        output += "<tr><td><details> <summary><strong> Enabling\\disabling automation </strong></summary><hr>\n\n"
+        output += """\
+When you first install the app, the [default mode](https://github.com/Codium-ai/pr-agent/blob/main/Usage.md#github-app-automatic-tools) for the improve tool is:
+
+```
+pr_commands = ["/improve --pr_code_suggestions.summarize=true", ...]
+```
+
+meaning the `improve` tool will run automatically on every PR, with summarization enabled. Delete this line to disable the tool from running automatically.
+"""
+        output += "\n\n</details></td></tr>\n\n"
+
+        # extra instructions
+        output += "<tr><td><details> <summary><strong> Utilizing extra instructions</strong></summary><hr>\n\n"
+        output += '''\
+Extra instructions are very important for the `improve` tool, since they enable to guide the model to suggestions that are more relevant to the specific needs of the project.
+
+Be specific, clear, and concise in the instructions. With extra instructions, you are the prompter. Specify relevant aspects that you want the model to focus on.
+
+Examples for extra instructions:
+
+```
+[pr_code_suggestions] # /improve #
+extra_instructions="""
+Emphasize the following aspects:
+- Does the code logic cover relevant edge cases?
+- Is the code logic clear and easy to understand?
+- Is the code logic efficient?
+...
+"""
+```
+
+Use triple quotes to write multi-line instructions. Use bullet points to make the instructions more readable.
+    '''
+        output += "\n\n</details></td></tr>\n\n"
+
+        # suggestions quality
+        output += "\n\n<tr><td><details> <summary><strong> A note on code suggestions quality</strong></summary><hr> \n\n"
+        output += """\
+- While the current AI for code is getting better and better (GPT-4), it's not flawless. Not all the suggestions will be perfect, and a user should not accept all of them automatically.
+- Suggestions are not meant to be simplistic. 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, or use the [custom suggestions :gem:](https://github.com/Codium-ai/pr-agent/blob/main/docs/CUSTOM_SUGGESTIONS.md) tool
+- With large PRs, best quality will be obtained by using 'improve --extended' mode.
+
+
+"""
+        output += "\n\n</details></td></tr>\n\n"\
+
+        # general
+        output += "\n\n<tr><td><details> <summary><strong> More PR-Agent commands</strong></summary><hr> \n\n"
+        output += HelpMessage.get_general_bot_help_text()
+        output += "\n\n</details></td></tr>\n\n"
+
+        output += "</table>"
+
+        output += f"\n\nSee the [improve usage](https://github.com/Codium-ai/pr-agent/blob/main/docs/IMPROVE.md) page for a more comprehensive guide on using this tool.\n\n"
+
+        return output

pr_agent/servers/serverless.py

@@ -0,0 +1,17 @@
+from fastapi import FastAPI
+from mangum import Mangum
+from starlette.middleware import Middleware
+from starlette_context.middleware import RawContextMiddleware
+
+from pr_agent.servers.github_app import router
+
+
+middleware = [Middleware(RawContextMiddleware)]
+app = FastAPI(middleware=middleware)
+app.include_router(router)
+
+handler = Mangum(app, lifespan="off")
+
+
+def serverless(event, context):
+    return handler(event, context)

pr_agent/servers/utils.py

@@ -1,5 +1,8 @@
 import hashlib
 import hmac
+import time
+from collections import defaultdict
+from typing import Callable, Any
 
 from fastapi import HTTPException
 
@@ -21,3 +24,63 @@ def verify_signature(payload_body, secret_token, signature_header):
     if not hmac.compare_digest(expected_signature, signature_header):
         raise HTTPException(status_code=403, detail="Request signatures didn't match!")
 
+
+class RateLimitExceeded(Exception):
+    """Raised when the git provider API rate limit has been exceeded."""
+    pass
+
+
+class DefaultDictWithTimeout(defaultdict):
+    """A defaultdict with a time-to-live (TTL)."""
+
+    def __init__(
+        self,
+        default_factory: Callable[[], Any] = None,
+        ttl: int = None,
+        refresh_interval: int = 60,
+        update_key_time_on_get: bool = True,
+        *args,
+        **kwargs,
+    ):
+        """
+        Args:
+            default_factory: The default factory to use for keys that are not in the dictionary.
+            ttl: The time-to-live (TTL) in seconds.
+            refresh_interval: How often to refresh the dict and delete items older than the TTL.
+            update_key_time_on_get: Whether to update the access time of a key also on get (or only when set).
+        """
+        super().__init__(default_factory, *args, **kwargs)
+        self.__key_times = dict()
+        self.__ttl = ttl
+        self.__refresh_interval = refresh_interval
+        self.__update_key_time_on_get = update_key_time_on_get
+        self.__last_refresh = self.__time() - self.__refresh_interval
+
+    @staticmethod
+    def __time():
+        return time.monotonic()
+
+    def __refresh(self):
+        if self.__ttl is None:
+            return
+        request_time = self.__time()
+        if request_time - self.__last_refresh > self.__refresh_interval:
+            return
+        to_delete = [key for key, key_time in self.__key_times.items() if request_time - key_time > self.__ttl]
+        for key in to_delete:
+            del self[key]
+        self.__last_refresh = request_time
+
+    def __getitem__(self, __key):
+        if self.__update_key_time_on_get:
+            self.__key_times[__key] = self.__time()
+        self.__refresh()
+        return super().__getitem__(__key)
+
+    def __setitem__(self, __key, __value):
+        self.__key_times[__key] = self.__time()
+        return super().__setitem__(__key, __value)
+
+    def __delitem__(self, __key):
+        del self.__key_times[__key]
+        return super().__delitem__(__key)

pr_agent/settings/.secrets_template.toml

@@ -7,17 +7,46 @@
 # See README for details about GitHub App deployment.
 
 [openai]
-key = "<API_KEY>"  # Acquire through https://platform.openai.com
-org = "<ORGANIZATION>"  # Optional, may be commented out.
+key = ""  # Acquire through https://platform.openai.com
+#org = "<ORGANIZATION>"  # Optional, may be commented out.
 # Uncomment the following for Azure OpenAI
 #api_type = "azure"
 #api_version = '2023-05-15'  # Check Azure documentation for the current API version
-#api_base = "<API_BASE>"  # The base URL for your Azure OpenAI resource. e.g. "https://<your resource name>.openai.azure.com"
-#deployment_id = "<DEPLOYMENT_ID>"  # The deployment name you chose when you deployed the engine
+#api_base = ""  # The base URL for your Azure OpenAI resource. e.g. "https://<your resource name>.openai.azure.com"
+#deployment_id = ""  # The deployment name you chose when you deployed the engine
+#fallback_deployments = []  # For each fallback model specified in configuration.toml in the [config] section, specify the appropriate deployment_id
+
+[pinecone]
+api_key = "..."
+environment = "gcp-starter"
+
+[anthropic]
+key = "" # Optional, uncomment if you want to use Anthropic. Acquire through https://www.anthropic.com/
+
+[cohere]
+key = "" # Optional, uncomment if you want to use Cohere. Acquire through https://dashboard.cohere.ai/
+
+[replicate]
+key = "" # Optional, uncomment if you want to use Replicate. Acquire through https://replicate.com/
+
+[huggingface]
+key = "" # Optional, uncomment if you want to use Huggingface Inference API. Acquire through https://huggingface.co/docs/api-inference/quicktour
+api_base = "" # the base url for your huggingface inference endpoint 
+
+[ollama]
+api_base = "" # the base url for your local Llama 2, Code Llama, and other models inference endpoint. Acquire through https://ollama.ai/
+
+[vertexai]
+vertex_project = "" # the google cloud platform project name for your vertexai deployment
+vertex_location = "" # the google cloud platform location for your vertexai deployment
+
+[aws]
+bedrock_region = "" # the AWS region to call Bedrock APIs
 
 [github]
 # ---- Set the following only for deployment type == "user"
-user_token = "<TOKEN>"  # A GitHub personal access token with 'repo' scope.
+user_token = ""  # A GitHub personal access token with 'repo' scope.
+deployment_type = "user" #set to user by default 
 
 # ---- Set the following only for deployment type == "app", see README for details.
 private_key = """\
@@ -32,3 +61,29 @@ webhook_secret = "<WEBHOOK SECRET>"  # Optional, may be commented out.
 # Gitlab personal access token
 personal_access_token = ""
 
+[bitbucket]
+# For Bitbucket personal/repository bearer token
+bearer_token = ""
+
+[bitbucket_server]
+# For Bitbucket Server bearer token
+auth_token = ""
+webhook_secret = ""
+
+# For Bitbucket app
+app_key = ""
+base_url = ""
+
+[litellm]
+LITELLM_TOKEN = "" # see https://docs.litellm.ai/docs/debugging/hosted_debugging for details and instructions on how to get a token
+
+[azure_devops]
+# For Azure devops personal access token
+org = ""
+pat = ""
+
+[azure_devops_server]
+# For Azure devops Server basic auth - configured in the webhook creation 
+# Optional, uncomment if you want to use Azure devops webhooks. Value assinged when you create the webhook
+# webhook_username = "<basic auth user>"
+# webhook_password = "<basic auth password>"

pr_agent/settings/configuration.toml

@@ -1,34 +1,207 @@
 [config]
-model="gpt-4-0613"
+model="gpt-4" # "gpt-4-0125-preview"
+model_turbo="gpt-4-0125-preview"
+fallback_models=["gpt-3.5-turbo-16k"]
 git_provider="github"
-publish_review=true
+publish_output=true
+publish_output_progress=true
 verbosity_level=0 # 0,1,2
+use_extra_bad_extensions=false
+use_wiki_settings_file=true
+use_repo_settings_file=true
+use_global_settings_file=true
+ai_timeout=120 # 2minutes
+max_description_tokens = 500
+max_commits_tokens = 500
+max_model_tokens = 32000 # Limits the maximum number of tokens that can be used by any model, regardless of the model's default capabilities.
+patch_extra_lines = 1
+secret_provider="google_cloud_storage"
+cli_mode=false
+ai_disclaimer_title=""  # Pro feature, title for a collapsible disclaimer to AI outputs
+ai_disclaimer=""  # Pro feature, full text for the AI disclaimer
 
-[pr_reviewer]
-require_focused_review=true
+[pr_reviewer] # /review #
+# enable/disable features
+require_focused_review=false
+require_score_review=false
 require_tests_review=true
-require_security_review=true
-num_code_suggestions=3
-inline_code_comments = true
-
-[pr_questions]
-
-[pr_code_suggestions]
+require_estimate_effort_to_review=true
+# soc2
+require_soc2_ticket=false
+soc2_ticket_prompt="Does the PR description include a link to ticket in a project management system (e.g., Jira, Asana, Trello, etc.) ?"
+# general options
 num_code_suggestions=4
+inline_code_comments = false
+ask_and_reflect=false
+#automatic_review=true
+persistent_comment=true
+extra_instructions = ""
+# review labels
+enable_review_labels_security=true
+enable_review_labels_effort=true
+# specific configurations for incremental review (/review -i)
+require_all_thresholds_for_incremental_review=false
+minimal_commits_for_incremental_review=0
+minimal_minutes_for_incremental_review=0
+enable_help_text=true # Determines whether to include help text in the PR review. Enabled by default.
+# auto approval
+enable_auto_approval=false
+maximal_review_effort=5
+
+
+[pr_description] # /describe #
+publish_labels=true
+publish_description_as_comment=false
+add_original_user_description=true
+keep_original_user_title=true
+use_bullet_points=true
+extra_instructions = ""
+enable_pr_type=true
+final_update_message = true
+enable_help_text=false
+enable_help_comment=true
+## changes walkthrough section
+enable_semantic_files_types=true
+collapsible_file_list='adaptive' # true, false, 'adaptive'
+inline_file_summary=false # false, true, 'table'
+# markers
+use_description_markers=false
+include_generated_by_header=true
+
+#custom_labels = ['Bug fix', 'Tests', 'Bug fix with tests', 'Enhancement', 'Documentation', 'Other']
+
+[pr_questions] # /ask #
+enable_help_text=true
+
+
+[pr_code_suggestions] # /improve #
+max_context_tokens=8000
+num_code_suggestions=4
+summarize = true
+extra_instructions = ""
+rank_suggestions = false
+enable_help_text=true
+# params for '/improve --extended' mode
+auto_extended_mode=true
+num_code_suggestions_per_chunk=5
+max_number_of_calls = 3
+parallel_calls = true
+rank_extended_suggestions = false
+final_clip_factor = 0.8
+
+[pr_add_docs] # /add_docs #
+extra_instructions = ""
+docs_style = "Sphinx Style" # "Google Style with Args, Returns, Attributes...etc", "Numpy Style", "Sphinx Style", "PEP257", "reStructuredText"
+
+[pr_update_changelog] # /update_changelog #
+push_changelog_changes=false
+extra_instructions = ""
+
+[pr_analyze] # /analyze #
+
+[pr_test] # /test #
+extra_instructions = ""
+testing_framework = "" # specify the testing framework you want to use
+num_tests=3            # number of tests to generate. max 5.
+avoid_mocks=true       # if true, the generated tests will prefer to use real objects instead of mocks
+file = ""              # in case there are several components with the same name, you can specify the relevant file
+class_name = ""        # in case there are several methods with the same name in the same file, you can specify the relevant class name
+enable_help_text=true
+
+
+[checks] # /checks (pro feature) #
+enable_auto_checks_feedback=true
+excluded_checks_list=["lint"] # list of checks to exclude, for example: ["check1", "check2"]
+persistent_comment=true
+enable_help_text=true
+
+[pr_help] # /help #
+
+[pr_config] # /config #
 
 [github]
 # The type of deployment to create. Valid values are 'app' or 'user'.
 deployment_type = "user"
+ratelimit_retries = 5
+base_url = "https://api.github.com"
+publish_inline_comments_fallback_with_verification = true
+try_fix_invalid_inline_comments = true
+
+[github_action_config]
+# auto_review = true    # set as env var in .github/workflows/pr-agent.yaml
+# auto_describe = true  # set as env var in .github/workflows/pr-agent.yaml
+# auto_improve = true   # set as env var in .github/workflows/pr-agent.yaml
+
+[github_app]
+# these toggles allows running the github app from custom deployments
+override_deployment_type = true
+# settings for "pull_request" event
+handle_pr_actions = ['opened', 'reopened', 'ready_for_review']
+pr_commands = [
+    "/describe --pr_description.add_original_user_description=true --pr_description.keep_original_user_title=true",
+    "/review --pr_reviewer.num_code_suggestions=0",
+    "/improve --pr_code_suggestions.summarize=true",
+]
+# settings for "pull_request" event with "synchronize" action - used to detect and handle push triggers for new commits
+handle_push_trigger = false
+push_trigger_ignore_bot_commits = true
+push_trigger_ignore_merge_commits = true
+push_trigger_wait_for_initial_review = true
+push_trigger_pending_tasks_backlog = true
+push_trigger_pending_tasks_ttl = 300
+push_commands = [
+    "/describe --pr_description.add_original_user_description=true --pr_description.keep_original_user_title=true",
+    "/review --pr_reviewer.num_code_suggestions=0",
+]
+ignore_pr_title = []
 
 [gitlab]
-# URL to the gitlab service
-url = "https://gitlab.com"
+url = "https://gitlab.com" # URL to the gitlab service
+pr_commands = [
+    "/describe --pr_description.add_original_user_description=true --pr_description.keep_original_user_title=true",
+    "/review --pr_reviewer.num_code_suggestions=0",
+    "/improve --pr_code_suggestions.summarize=true",
+]
 
-# Polling (either project id or namespace/project_name) syntax can be used
-projects_to_monitor = ['org_name/repo_name']
+[bitbucket_app]
+#auto_review = true    # set as config var in .pr_agent.toml
+#auto_describe = true  # set as config var in .pr_agent.toml
+#auto_improve = true   # set as config var in .pr_agent.toml
 
-# Polling trigger
-magic_word = "AutoReview"
 
-# Polling interval
-polling_interval_seconds = 30
+[local]
+# LocalGitProvider settings - uncomment to use paths other than default
+# description_path= "path/to/description.md"
+# review_path= "path/to/review.md"
+
+[gerrit]
+# endpoint to the gerrit service
+# url = "ssh://gerrit.example.com:29418"
+# user for gerrit authentication
+# user = "ai-reviewer"
+# patch server where patches will be saved
+# patch_server_endpoint = "http://127.0.0.1:5000/patch"
+# token to authenticate in the patch server
+# patch_server_token = ""
+
+[bitbucket_server]
+# URL to the BitBucket Server instance
+# url = "https://git.bitbucket.com"
+url = ""
+
+[litellm]
+#use_client = false
+
+[pr_similar_issue]
+skip_comments = false
+force_update_dataset = false
+max_issues_to_scan = 500
+vectordb = "pinecone"
+
+[pinecone]
+# fill and place in .secrets.toml
+#api_key = ...
+# environment = "gcp-starter"
+
+[lancedb]
+uri = "./lancedb"

pr_agent/settings/custom_labels.toml

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

pr_agent/settings/ignore.toml

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

pr_agent/settings/language_extensions.toml

@@ -0,0 +1,438 @@
+[bad_extensions]
+default = [
+    'app',
+    'bin',
+    'bmp',
+    'bz2',
+    'class',
+    'csv',
+    'dat',
+    'db',
+    'dll',
+    'dylib',
+    'egg',
+    'eot',
+    'exe',
+    'gif',
+    'gitignore',
+    'glif',
+    'gradle',
+    'gz',
+    'ico',
+    'jar',
+    'jpeg',
+    'jpg',
+    'lo',
+    'lock',
+    'log',
+    'mp3',
+    'mp4',
+    'nar',
+    'o',
+    'ogg',
+    'otf',
+    'p',
+    'pdf',
+    'png',
+    'pickle',
+    'pkl',
+    'pyc',
+    'pyd',
+    'pyo',
+    'rkt',
+    'so',
+    'ss',
+    'svg',
+    'tar',
+    'tsv',
+    'ttf',
+    'war',
+    'webm',
+    'woff',
+    'woff2',
+    'xz',
+    'zip',
+    'zst',
+    'snap',
+    'lockb'
+]
+extra = [
+    'md',
+    'txt'
+]
+
+[language_extension_map_org]
+ABAP = [".abap", ]
+"AGS Script" = [".ash", ]
+AMPL = [".ampl", ]
+ANTLR = [".g4", ]
+"API Blueprint" = [".apib", ]
+APL = [".apl", ".dyalog", ]
+ASP = [".asp", ".asax", ".ascx", ".ashx", ".asmx", ".aspx", ".axd", ]
+ATS = [".dats", ".hats", ".sats", ]
+ActionScript = [".as", ]
+Ada = [".adb", ".ada", ".ads", ]
+Agda = [".agda", ]
+Alloy = [".als", ]
+ApacheConf = [".apacheconf", ".vhost", ]
+AppleScript = [".applescript", ".scpt", ]
+Arc = [".arc", ]
+Arduino = [".ino", ]
+AsciiDoc = [".asciidoc", ".adoc", ]
+AspectJ = [".aj", ]
+Assembly = [".asm", ".a51", ".nasm", ]
+Augeas = [".aug", ]
+AutoHotkey = [".ahk", ".ahkl", ]
+AutoIt = [".au3", ]
+Awk = [".awk", ".auk", ".gawk", ".mawk", ".nawk", ]
+Batchfile = [".bat", ".cmd", ]
+Befunge = [".befunge", ]
+Bison = [".bison", ]
+BitBake = [".bb", ]
+BlitzBasic = [".decls", ]
+BlitzMax = [".bmx", ]
+Bluespec = [".bsv", ]
+Boo = [".boo", ]
+Brainfuck = [".bf", ]
+Brightscript = [".brs", ]
+Bro = [".bro", ]
+C = [".c", ".cats", ".h", ".idc", ".w", ]
+"C#" = [".cs", ".cake", ".cshtml", ".csx", ]
+"C++" = [".cpp", ".c++", ".cc", ".cp", ".cxx", ".h++", ".hh", ".hpp", ".hxx", ".inl", ".ipp", ".tcc", ".tpp", ".C", ".H", ]
+C-ObjDump = [".c-objdump", ]
+"C2hs Haskell" = [".chs", ]
+CLIPS = [".clp", ]
+CMake = [".cmake", ".cmake.in", ]
+COBOL = [".cob", ".cbl", ".ccp", ".cobol", ".cpy", ]
+CSS = [".css", ]
+CSV = [".csv", ]
+"Cap'n Proto" = [".capnp", ]
+CartoCSS = [".mss", ]
+Ceylon = [".ceylon", ]
+Chapel = [".chpl", ]
+ChucK = [".ck", ]
+Cirru = [".cirru", ]
+Clarion = [".clw", ]
+Clean = [".icl", ".dcl", ]
+Click = [".click", ]
+Clojure = [".clj", ".boot", ".cl2", ".cljc", ".cljs", ".cljs.hl", ".cljscm", ".cljx", ".hic", ]
+CoffeeScript = [".coffee", "._coffee", ".cjsx", ".cson", ".iced", ]
+ColdFusion = [".cfm", ".cfml", ]
+"ColdFusion CFC" = [".cfc", ]
+"Common Lisp" = [".lisp", ".asd", ".lsp", ".ny", ".podsl", ".sexp", ]
+"Component Pascal" = [".cps", ]
+Coq = [".coq", ]
+Cpp-ObjDump = [".cppobjdump", ".c++-objdump", ".c++objdump", ".cpp-objdump", ".cxx-objdump", ]
+Creole = [".creole", ]
+Crystal = [".cr", ]
+Csound = [".csd", ]
+Cucumber = [".feature", ]
+Cuda = [".cu", ".cuh", ]
+Cycript = [".cy", ]
+Cython = [".pyx", ".pxd", ".pxi", ]
+D = [".di", ]
+D-ObjDump = [".d-objdump", ]
+"DIGITAL Command Language" = [".com", ]
+DM = [".dm", ]
+"DNS Zone" = [".zone", ".arpa", ]
+"Darcs Patch" = [".darcspatch", ".dpatch", ]
+Dart = [".dart", ]
+Diff = [".diff", ".patch", ]
+Dockerfile = [".dockerfile", "Dockerfile", ]
+Dogescript = [".djs", ]
+Dylan = [".dylan", ".dyl", ".intr", ".lid", ]
+E = [".E", ]
+ECL = [".ecl", ".eclxml", ]
+Eagle = [".sch", ".brd", ]
+"Ecere Projects" = [".epj", ]
+Eiffel = [".e", ]
+Elixir = [".ex", ".exs", ]
+Elm = [".elm", ]
+"Emacs Lisp" = [".el", ".emacs", ".emacs.desktop", ]
+EmberScript = [".em", ".emberscript", ]
+Erlang = [".erl", ".escript", ".hrl", ".xrl", ".yrl", ]
+"F#" = [".fs", ".fsi", ".fsx", ]
+FLUX = [".flux", ]
+FORTRAN = [".f90", ".f", ".f03", ".f08", ".f77", ".f95", ".for", ".fpp", ]
+Factor = [".factor", ]
+Fancy = [".fy", ".fancypack", ]
+Fantom = [".fan", ]
+Formatted = [".eam.fs", ]
+Forth = [".fth", ".4th", ".forth", ".frt", ]
+FreeMarker = [".ftl", ]
+G-code = [".g", ".gco", ".gcode", ]
+GAMS = [".gms", ]
+GAP = [".gap", ".gi", ]
+GAS = [".s", ]
+GDScript = [".gd", ]
+GLSL = [".glsl", ".fp", ".frag", ".frg", ".fsh", ".fshader", ".geo", ".geom", ".glslv", ".gshader", ".shader", ".vert", ".vrx", ".vsh", ".vshader", ]
+Genshi = [".kid", ]
+"Gentoo Ebuild" = [".ebuild", ]
+"Gentoo Eclass" = [".eclass", ]
+"Gettext Catalog" = [".po", ".pot", ]
+Glyph = [".glf", ]
+Gnuplot = [".gp", ".gnu", ".gnuplot", ".plot", ".plt", ]
+Go = [".go", ]
+Golo = [".golo", ]
+Gosu = [".gst", ".gsx", ".vark", ]
+Grace = [".grace", ]
+Gradle = [".gradle", ]
+"Grammatical Framework" = [".gf", ]
+GraphQL = [".graphql", ]
+"Graphviz (DOT)" = [".dot", ".gv", ]
+Groff = [".man", ".1", ".1in", ".1m", ".1x", ".2", ".3", ".3in", ".3m", ".3qt", ".3x", ".4", ".5", ".6", ".7", ".8", ".9", ".me", ".rno", ".roff", ]
+Groovy = [".groovy", ".grt", ".gtpl", ".gvy", ]
+"Groovy Server Pages" = [".gsp", ]
+HCL = [".hcl", ".tf", ]
+HLSL = [".hlsl", ".fxh", ".hlsli", ]
+HTML = [".html", ".htm", ".html.hl", ".xht", ".xhtml", ]
+"HTML+Django" = [".mustache", ".jinja", ]
+"HTML+EEX" = [".eex", ]
+"HTML+ERB" = [".erb", ".erb.deface", ]
+"HTML+PHP" = [".phtml", ]
+HTTP = [".http", ]
+Haml = [".haml", ".haml.deface", ]
+Handlebars = [".handlebars", ".hbs", ]
+Harbour = [".hb", ]
+Haskell = [".hs", ".hsc", ]
+Haxe = [".hx", ".hxsl", ]
+Hy = [".hy", ]
+IDL = [".dlm", ]
+"IGOR Pro" = [".ipf", ]
+INI = [".ini", ".cfg", ".prefs", ".properties", ]
+"IRC log" = [".irclog", ".weechatlog", ]
+Idris = [".idr", ".lidr", ]
+"Inform 7" = [".ni", ".i7x", ]
+"Inno Setup" = [".iss", ]
+Io = [".io", ]
+Ioke = [".ik", ]
+Isabelle = [".thy", ]
+J = [".ijs", ]
+JFlex = [".flex", ".jflex", ]
+JSON = [".json", ".geojson", ".lock", ".topojson", ]
+JSON5 = [".json5", ]
+JSONLD = [".jsonld", ]
+JSONiq = [".jq", ]
+JSX = [".jsx", ]
+Jade = [".jade", ]
+Jasmin = [".j", ]
+Java = [".java", ]
+"Java Server Pages" = [".jsp", ]
+JavaScript = [".js", "._js", ".bones", ".es6", ".jake", ".jsb", ".jscad", ".jsfl", ".jsm", ".jss", ".njs", ".pac", ".sjs", ".ssjs", ".xsjs", ".xsjslib", ]
+Julia = [".jl", ]
+"Jupyter Notebook" = [".ipynb", ]
+KRL = [".krl", ]
+KiCad = [".kicad_pcb", ]
+Kit = [".kit", ]
+Kotlin = [".kt", ".ktm", ".kts", ]
+LFE = [".lfe", ]
+LLVM = [".ll", ]
+LOLCODE = [".lol", ]
+LSL = [".lsl", ".lslp", ]
+LabVIEW = [".lvproj", ]
+Lasso = [".lasso", ".las", ".lasso8", ".lasso9", ".ldml", ]
+Latte = [".latte", ]
+Lean = [".lean", ".hlean", ]
+Less = [".less", ]
+Lex = [".lex", ]
+LilyPond = [".ly", ".ily", ]
+"Linker Script" = [".ld", ".lds", ]
+Liquid = [".liquid", ]
+"Literate Agda" = [".lagda", ]
+"Literate CoffeeScript" = [".litcoffee", ]
+"Literate Haskell" = [".lhs", ]
+LiveScript = [".ls", "._ls", ]
+Logos = [".xm", ".x", ".xi", ]
+Logtalk = [".lgt", ".logtalk", ]
+LookML = [".lookml", ]
+Lua = [".lua", ".nse", ".pd_lua", ".rbxs", ".wlua", ]
+M = [".mumps", ]
+M4 = [".m4", ]
+MAXScript = [".mcr", ]
+MTML = [".mtml", ]
+MUF = [".muf", ]
+Makefile = [".mak", ".mk", ".mkfile", "Makefile", ]
+Mako = [".mako", ".mao", ]
+Maple = [".mpl", ]
+Markdown = [".md", ".markdown", ".mkd", ".mkdn", ".mkdown", ".ron", ]
+Mask = [".mask", ]
+Mathematica = [".mathematica", ".cdf", ".ma", ".mt", ".nb", ".nbp", ".wl", ".wlt", ]
+Matlab = [".matlab", ]
+Max = [".maxpat", ".maxhelp", ".maxproj", ".mxt", ".pat", ]
+MediaWiki = [".mediawiki", ".wiki", ]
+Metal = [".metal", ]
+MiniD = [".minid", ]
+Mirah = [".druby", ".duby", ".mir", ".mirah", ]
+Modelica = [".mo", ]
+"Module Management System" = [".mms", ".mmk", ]
+Monkey = [".monkey", ]
+MoonScript = [".moon", ]
+Myghty = [".myt", ]
+NSIS = [".nsi", ".nsh", ]
+NetLinx = [".axs", ".axi", ]
+"NetLinx+ERB" = [".axs.erb", ".axi.erb", ]
+NetLogo = [".nlogo", ]
+Nginx = [".nginxconf", ]
+Nimrod = [".nim", ".nimrod", ]
+Ninja = [".ninja", ]
+Nit = [".nit", ]
+Nix = [".nix", ]
+Nu = [".nu", ]
+NumPy = [".numpy", ".numpyw", ".numsc", ]
+OCaml = [".ml", ".eliom", ".eliomi", ".ml4", ".mli", ".mll", ".mly", ]
+ObjDump = [".objdump", ]
+"Objective-C++" = [".mm", ]
+Objective-J = [".sj", ]
+Octave = [".oct", ]
+Omgrofl = [".omgrofl", ]
+Opa = [".opa", ]
+Opal = [".opal", ]
+OpenCL = [".cl", ".opencl", ]
+"OpenEdge ABL" = [".p", ]
+OpenSCAD = [".scad", ]
+Org = [".org", ]
+Ox = [".ox", ".oxh", ".oxo", ]
+Oxygene = [".oxygene", ]
+Oz = [".oz", ]
+PAWN = [".pwn", ]
+PHP = [".php", ".aw", ".ctp", ".php3", ".php4", ".php5", ".phps", ".phpt", ]
+"POV-Ray SDL" = [".pov", ]
+Pan = [".pan", ]
+Papyrus = [".psc", ]
+Parrot = [".parrot", ]
+"Parrot Assembly" = [".pasm", ]
+"Parrot Internal Representation" = [".pir", ]
+Pascal = [".pas", ".dfm", ".dpr", ".lpr", ]
+Perl = [".pl", ".al", ".perl", ".ph", ".plx", ".pm", ".psgi", ".t", ]
+Perl6 = [".6pl", ".6pm", ".nqp", ".p6", ".p6l", ".p6m", ".pl6", ".pm6", ]
+Pickle = [".pkl", ]
+PigLatin = [".pig", ]
+Pike = [".pike", ".pmod", ]
+Pod = [".pod", ]
+PogoScript = [".pogo", ]
+Pony = [".pony", ]
+PostScript = [".ps", ".eps", ]
+PowerShell = [".ps1", ".psd1", ".psm1", ]
+Processing = [".pde", ]
+Prolog = [".prolog", ".yap", ]
+"Propeller Spin" = [".spin", ]
+"Protocol Buffer" = [".proto", ]
+"Public Key" = [".pub", ]
+"Pure Data" = [".pd", ]
+PureBasic = [".pb", ".pbi", ]
+PureScript = [".purs", ]
+Python = [".py", ".bzl", ".gyp", ".lmi", ".pyde", ".pyp", ".pyt", ".pyw", ".tac", ".wsgi", ".xpy", ]
+"Python traceback" = [".pytb", ]
+QML = [".qml", ".qbs", ]
+QMake = [".pri", ]
+R = [".r", ".rd", ".rsx", ]
+RAML = [".raml", ]
+RDoc = [".rdoc", ]
+REALbasic = [".rbbas", ".rbfrm", ".rbmnu", ".rbres", ".rbtbar", ".rbuistate", ]
+RHTML = [".rhtml", ]
+RMarkdown = [".rmd", ]
+Racket = [".rkt", ".rktd", ".rktl", ".scrbl", ]
+"Ragel in Ruby Host" = [".rl", ]
+"Raw token data" = [".raw", ]
+Rebol = [".reb", ".r2", ".r3", ".rebol", ]
+Red = [".red", ".reds", ]
+Redcode = [".cw", ]
+"Ren'Py" = [".rpy", ]
+RenderScript = [".rsh", ]
+RobotFramework = [".robot", ]
+Rouge = [".rg", ]
+Ruby = [".rb", ".builder", ".gemspec", ".god", ".irbrc", ".jbuilder", ".mspec", ".podspec", ".rabl", ".rake", ".rbuild", ".rbw", ".rbx", ".ru", ".ruby", ".thor", ".watchr", ]
+Rust = [".rs", ".rs.in", ]
+SAS = [".sas", ]
+SCSS = [".scss", ]
+SMT = [".smt2", ".smt", ]
+SPARQL = [".sparql", ".rq", ]
+SQF = [".sqf", ".hqf", ]
+SQL = [".pls", ".pck", ".pkb", ".pks", ".plb", ".plsql", ".sql", ".cql", ".ddl", ".prc", ".tab", ".udf", ".viw", ".db2", ]
+STON = [".ston", ]
+SVG = [".svg", ]
+Sage = [".sage", ".sagews", ]
+SaltStack = [".sls", ]
+Sass = [".sass", ]
+Scala = [".scala", ".sbt", ]
+Scaml = [".scaml", ]
+Scheme = [".scm", ".sld", ".sps", ".ss", ]
+Scilab = [".sci", ".sce", ]
+Self = [".self", ]
+Shell = [".sh", ".bash", ".bats", ".command", ".ksh", ".sh.in", ".tmux", ".tool", ".zsh", ]
+ShellSession = [".sh-session", ]
+Shen = [".shen", ]
+Slash = [".sl", ]
+Slim = [".slim", ]
+Smali = [".smali", ]
+Smalltalk = [".st", ]
+Smarty = [".tpl", ]
+Solidity = [".sol", ]
+SourcePawn = [".sp", ".sma", ]
+Squirrel = [".nut", ]
+Stan = [".stan", ]
+"Standard ML" = [".ML", ".fun", ".sig", ".sml", ]
+Stata = [".do", ".ado", ".doh", ".ihlp", ".mata", ".matah", ".sthlp", ]
+Stylus = [".styl", ]
+SuperCollider = [".scd", ]
+Swift = [".swift", ]
+SystemVerilog = [".sv", ".svh", ".vh", ]
+TOML = [".toml", ]
+TXL = [".txl", ]
+Tcl = [".tcl", ".adp", ".tm", ]
+Tcsh = [".tcsh", ".csh", ]
+TeX = [".tex", ".aux", ".bbx", ".bib", ".cbx", ".dtx", ".ins", ".lbx", ".ltx", ".mkii", ".mkiv", ".mkvi", ".sty", ".toc", ]
+Tea = [".tea", ]
+Text = [".txt", ".no", ]
+Textile = [".textile", ]
+Thrift = [".thrift", ]
+Turing = [".tu", ]
+Turtle = [".ttl", ]
+Twig = [".twig", ]
+TypeScript = [".ts", ".tsx", ]
+"Unified Parallel C" = [".upc", ]
+"Unity3D Asset" = [".anim", ".asset", ".mat", ".meta", ".prefab", ".unity", ]
+Uno = [".uno", ]
+UnrealScript = [".uc", ]
+UrWeb = [".ur", ".urs", ]
+VCL = [".vcl", ]
+VHDL = [".vhdl", ".vhd", ".vhf", ".vhi", ".vho", ".vhs", ".vht", ".vhw", ]
+Vala = [".vala", ".vapi", ]
+Verilog = [".veo", ]
+VimL = [".vim", ]
+"Visual Basic" = [".vb", ".bas", ".frm", ".frx", ".vba", ".vbhtml", ".vbs", ]
+Volt = [".volt", ]
+Vue = [".vue", ]
+"Web Ontology Language" = [".owl", ]
+WebAssembly = [".wat", ]
+WebIDL = [".webidl", ]
+X10 = [".x10", ]
+XC = [".xc", ]
+XML = [".xml", ".ant", ".axml", ".ccxml", ".clixml", ".cproject", ".csl", ".csproj", ".ct", ".dita", ".ditamap", ".ditaval", ".dll.config", ".dotsettings", ".filters", ".fsproj", ".fxml", ".glade", ".grxml", ".iml", ".ivy", ".jelly", ".jsproj", ".kml", ".launch", ".mdpolicy", ".mxml", ".nproj", ".nuspec", ".odd", ".osm", ".plist", ".props", ".ps1xml", ".psc1", ".pt", ".rdf", ".rss", ".scxml", ".srdf", ".storyboard", ".stTheme", ".sublime-snippet", ".targets", ".tmCommand", ".tml", ".tmLanguage", ".tmPreferences", ".tmSnippet", ".tmTheme", ".ui", ".urdf", ".ux", ".vbproj", ".vcxproj", ".vssettings", ".vxml", ".wsdl", ".wsf", ".wxi", ".wxl", ".wxs", ".x3d", ".xacro", ".xaml", ".xib", ".xlf", ".xliff", ".xmi", ".xml.dist", ".xproj", ".xsd", ".xul", ".zcml", ]
+XPages = [".xsp-config", ".xsp.metadata", ]
+XProc = [".xpl", ".xproc", ]
+XQuery = [".xquery", ".xq", ".xql", ".xqm", ".xqy", ]
+XS = [".xs", ]
+XSLT = [".xslt", ".xsl", ]
+Xojo = [".xojo_code", ".xojo_menu", ".xojo_report", ".xojo_script", ".xojo_toolbar", ".xojo_window", ]
+Xtend = [".xtend", ]
+YAML = [".yml", ".reek", ".rviz", ".sublime-syntax", ".syntax", ".yaml", ".yaml-tmlanguage", ]
+YANG = [".yang", ]
+Yacc = [".y", ".yacc", ".yy", ]
+Zephir = [".zep", ]
+Zig = [".zig", ]
+Zimpl = [".zimpl", ".zmpl", ".zpl", ]
+desktop = [".desktop", ".desktop.in", ]
+eC = [".ec", ".eh", ]
+edn = [".edn", ]
+fish = [".fish", ]
+mupad = [".mu", ]
+nesC = [".nc", ]
+ooc = [".ooc", ]
+reStructuredText = [".rst", ".rest", ".rest.txt", ".rst.txt", ]
+wisp = [".wisp", ]
+xBase = [".prg", ".prw", ]
+
+[docs_blacklist_extensions]
+# Disable docs for these extensions of text files and scripts that are not programming languages of function, classes and methods
+docs_blacklist = ['sql', 'txt', 'yaml', 'json', 'xml', 'md', 'rst', 'rest', 'rest.txt', 'rst.txt', 'mdpolicy', 'mdown', 'markdown', 'mdwn', 'mkd', 'mkdn', 'mkdown', 'sh']

pr_agent/settings/pr_add_docs.toml

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

pr_agent/settings/pr_code_suggestions_prompts.toml

@@ -1,79 +1,121 @@
 [pr_code_suggestions_prompt]
-system="""You are a language model called CodiumAI-PR-Code-Reviewer.
-Your task is to provide provide meaningfull non-trivial code suggestions to improve the new code in a PR (the '+' lines).
-- Try to give important suggestions like fixing code problems, issues and bugs. As a second priority, provide suggestions for meaningfull code improvements, like performance, vulnerability, modularity, and best practices.
-- Suggestions should refer only to the 'new hunk' code, and focus on improving the new added code lines, with '+'.
-- Provide the exact line number range (inclusive) for each issue.
-- Assume there is additional code in the relevant file that is not included in the diff.
-- Provide up to {{ num_code_suggestions }} code suggestions.
-- Make sure not to provide suggestion repeating modifications already implemented in the new PR code (the '+' lines).
-- Don't output line numbers in the 'improved code' snippets.
+system="""You are PR-Reviewer, a language model that specializes in suggesting code improvements for a Pull Request (PR).
+Your task is to provide meaningful and actionable code suggestions, to improve the new code presented in a PR diff (lines starting with '+').
 
-You must use the following JSON schema to format your answer:
-```json
-{
-    "Code suggestions": {
-      "type": "array",
-      "minItems": 1,
-      "maxItems": {{ num_code_suggestions }},
-      "uniqueItems": "true",
-      "items": {
-        "relevant file": {
-          "type": "string",
-          "description": "the relevant file full path"
-        },
-        "suggestion content": {
-          "type": "string",
-          "description": "a concrete suggestion for meaningfully improving the new PR code."
-        },
-        "existing code": {
-          "type": "string",
-          "description": "a code snippet showing authentic relevant code lines from a 'new hunk' section. It must be continuous, correctly formatted and indented, and without line numbers."
-        },
-        "relevant lines": {
-          "type": "string",
-          "description": "the relevant lines in the 'new hunk' sections, in the format of 'start_line-end_line'. For example: '10-15'. They should be derived from the hunk line numbers, and correspond to the 'existing code' snippet above."
-        },
-        "improved code": {
-          "type": "string",
-          "description": "a new code snippet that can be used to replace the relevant lines in 'new hunk' code. Replacement suggestions should be complete, correctly formatted and indented, and without line numbers."
-        }
-      }
-    }
-}
-```
+Example for the PR Diff format:
+======
+## file: 'src/file1.py'
 
-Example input:
-'
-## src/file1.py
----new_hunk---
-```
-[new hunk code, annotated with line numbers]
-```
----old_hunk---
-```
-[old hunk code]
-```
+@@ ... @@ def func1():
+__new hunk__
+12  code line1 that remained unchanged in the PR
+13 +new hunk code line2 added in the PR
+14  code line3 that remained unchanged in the PR
+__old hunk__
+ code line1 that remained unchanged in the PR
+-old hunk code line2 that was removed in the PR
+ code line3 that remained unchanged in the PR
+
+@@ ... @@ def func2():
+__new hunk__
+...
+__old hunk__
 ...
-'
 
-Don't repeat the prompt in the answer, and avoid outputting the 'type' and 'description' fields.
-"""
 
-user="""PR Info:
-Title: '{{title}}'
-Branch: '{{branch}}'
-Description: '{{description}}'
-{%- if language %}
-Main language: {{language}}
+## file: 'src/file2.py'
+...
+======
+
+
+Specific instructions:
+- Provide up to {{ num_code_suggestions }} code suggestions. The suggestions should be diverse and insightful.
+- The suggestions should refer only to code from the '__new hunk__' sections, and focus on new lines of code (lines starting with '+').
+- Prioritize suggestions that address major problems, issues and bugs in the PR code. As a second priority, suggestions should focus on enhancement, best practice, performance, maintainability, and other aspects.
+- Don't suggest to add docstring, type hints, or comments, or to remove unused imports.
+- Suggestions should not repeat code already present in the '__new hunk__' sections.
+- Provide the exact line numbers range (inclusive) for each suggestion.
+- When quoting variables or names from the code, use backticks (`) instead of single quote (').
+
+
+{%- if extra_instructions %}
+
+
+Extra instructions from the user:
+======
+{{ extra_instructions }}
+======
 {%- endif %}
 
 
-The PR Diff:
-```
-{{diff}}
+The output must be a YAML object equivalent to type $PRCodeSuggestions, according to the following Pydantic definitions:
+=====
+class CodeSuggestion(BaseModel):
+    relevant_file: str = Field(description="the relevant file full path")
+    language: str = Field(description="the code language of the relevant file")
+    suggestion_content: str = Field(description="an actionable suggestion for meaningfully improving the new code introduced in the PR")
+{%- if summarize_mode %}
+    existing_code: str = Field(description="a short code snippet from a '__new hunk__' section to illustrate the relevant existing code. Don't show the line numbers.")
+    improved_code: str = Field(description="a short code snippet to illustrate the improved code, after applying the suggestion.")
+    one_sentence_summary:str = Field(description="a short summary of the suggestion action, in a single sentence. Focus on the 'what'. Be general, and avoid method or variable names.")
+{%- else %}
+    existing_code: str = Field(description="a code snippet, demonstrating the relevant code lines from a '__new hunk__' section. It must be contiguous, correctly formatted and indented, and without line numbers")
+    improved_code: str = Field(description="a new code snippet, that can be used to replace the relevant lines in '__new hunk__' code. Replacement suggestions should be complete, correctly formatted and indented, and without line numbers")
+{%- endif %}
+    relevant_lines_start: int = Field(description="The relevant line number, from a '__new hunk__' section, where the suggestion starts (inclusive). Should be derived from the hunk line numbers, and correspond to the 'existing code' snippet above")
+    relevant_lines_end: int = Field(description="The relevant line number, from a '__new hunk__' section, where the suggestion ends (inclusive). Should be derived from the hunk line numbers, and correspond to the 'existing code' snippet above")
+    label: str = Field(description="a single label for the suggestion, to help the user understand the suggestion type. For example: 'security', 'bug', 'performance', 'enhancement', 'possible issue', 'best practice', 'maintainability', etc. Other labels are also allowed")
+
+class PRCodeSuggestions(BaseModel):
+    code_suggestions: List[CodeSuggestion]
+=====
+
+
+Example output:
+```yaml
+code_suggestions:
+- relevant_file: |
+    src/file1.py
+  language: |
+    python
+  suggestion_content: |
+    ...
+{%- if summarize_mode %}
+  existing_code: |
+    ...
+  improved_code: |
+    ...
+  one_sentence_summary: |
+    ...
+  relevant_lines_start: 12
+  relevant_lines_end: 13
+{%- else %}
+  existing_code: |
+    ...
+  relevant_lines_start: 12
+  relevant_lines_end: 13
+  improved_code: |
+    ...
+{%- endif %}
+  label: |
+    ...
 ```
 
-Response (should be a valid JSON, and nothing else):
-```json
+
+Each YAML output MUST be after a newline, indented, with block scalar indicator ('|').
+"""
+
+user="""PR Info:
+
+Title: '{{title}}'
+
+
+The PR Diff:
+======
+{{ diff|trim }}
+======
+
+
+Response (should be a valid YAML, and nothing else):
+```yaml
 """

pr_agent/settings/pr_custom_labels.toml

@@ -0,0 +1,86 @@
+[pr_custom_labels_prompt]
+system="""You are PR-Reviewer, a language model designed to review a Git Pull Request (PR).
+Your task is to provide labels that describe the PR content.
+{%- if enable_custom_labels %}
+Thoroughly read the labels name and the provided description, and decide whether the label is relevant to the PR.
+{%- endif %}
+
+{%- if extra_instructions %}
+
+Extra instructions from the user:
+======
+{{ extra_instructions }}
+======
+{% endif %}
+
+
+The output must be a YAML object equivalent to type $Labels, according to the following Pydantic definitions:
+======
+{%- if enable_custom_labels %}
+
+{{ custom_labels_class }}
+
+{%- else %}
+class Label(str, Enum):
+    bug_fix = "Bug fix"
+    tests = "Tests"
+    enhancement = "Enhancement"
+    documentation = "Documentation"
+    other = "Other"
+{%- endif %}
+
+class Labels(BaseModel):
+    labels: List[Label] =  Field(min_items=0, description="choose the relevant custom labels that describe the PR content, and return their keys. Use the value field of the Label object to better understand the label meaning.")
+======
+
+
+Example output:
+
+```yaml
+labels:
+- ...
+- ...
+```
+
+Answer should be a valid YAML, and nothing else.
+"""
+
+user="""PR Info:
+
+Previous title: '{{title}}'
+
+Branch: '{{ branch }}'
+
+{%- if description %}
+
+Description:
+======
+{{ description|trim }}
+======
+{%- endif %}
+
+{%- if language %}
+
+Main PR language: '{{ language }}'
+{%- endif %}
+{%- if commit_messages_str %}
+
+
+Commit messages:
+======
+{{ commit_messages_str|trim }}
+======
+{%- endif %}
+
+
+The PR Git Diff:
+======
+{{ diff|trim }}
+======
+
+Note that lines in the diff body are prefixed with a symbol that represents the type of change: '-' for deletions, '+' for additions, and ' ' (a space) for unchanged lines.
+
+
+Response (should be a valid YAML, and nothing else):
+```yaml
+"""

pr_agent/settings/pr_description_prompts.toml

@@ -1,45 +1,130 @@
 [pr_description_prompt]
-system="""You are CodiumAI-PR-Reviewer, a language model designed to review git pull requests.
-Your task is to provide full description of the PR content.
-- Make sure not to focus the new PR code (the '+' lines).
+system="""You are PR-Reviewer, a language model designed to review a Git Pull Request (PR).
+{%- if enable_custom_labels %}
+Your task is to provide a full description for the PR content - files walkthrough, title, type, description and labels.
+{%- else %}
+Your task is to provide a full description for the PR content - files walkthrough, title, type, and description.
+{%- endif %}
+- Focus on the new PR code (lines starting with '+').
+- Keep in mind that the 'Previous title', 'Previous description' and 'Commit messages' sections may be partial, simplistic, non-informative or out of date. Hence, compare them to the PR diff code, and use them only as a reference.
+- The generated title and description should prioritize the most significant changes.
+- If needed, each YAML output should be in block scalar indicator ('|-')
+- When quoting variables or names from the code, use backticks (`) instead of single quote (').
 
-You must use the following JSON schema to format your answer:
-```json
-{
-  "PR Title": {
-      "type": "string",
-      "description": "an informative title for the PR, describing its main theme"
-  },
-  "Type of PR": {
-      "type": "string",
-      "enum": ["Bug fix", "Tests", "Bug fix with tests", "Refactoring", "Enhancement", "Documentation", "Other"]
-    },
-  "PR Description": {
-      "type": "string",
-      "description": "an informative and concise description of the PR"
-  },
-  "PR Main Files Walkthrough": {
-      "type": "string",
-      "description": "a walkthrough of the PR changes. Review main files, in bullet points, and shortly describe the changes in each file (up to 10 most important files). Format: -`filename`: description of changes\n..."
-  }
-}
+{%- if extra_instructions %}
 
-Don't repeat the prompt in the answer, and avoid outputting the 'type' and 'description' fields.
+Extra instructions from the user:
+=====
+{{extra_instructions}}
+=====
+{% endif %}
+
+
+The output must be a YAML object equivalent to type $PRDescription, according to the following Pydantic definitions:
+=====
+class PRType(str, Enum):
+    bug_fix = "Bug fix"
+    tests = "Tests"
+    enhancement = "Enhancement"
+    documentation = "Documentation"
+    other = "Other"
+
+{%- if enable_custom_labels %}
+
+{{ custom_labels_class }}
+
+{%- endif %}
+
+{%- if enable_semantic_files_types %}
+
+Class FileDescription(BaseModel):
+    filename: str = Field(description="the relevant file full path")
+    language: str = Field(description="the relevant file language")
+    changes_summary: str = Field(description="concise summary of the changes in the relevant file, in bullet points (1-4 bullet points).")
+    changes_title: str = Field(description="an informative title for the changes in the files, describing its main theme (5-10 words).")
+    label: str = Field(description="a single semantic label that represents a type of code changes that occurred in the File. Possible values (partial list): 'bug fix', 'tests', 'enhancement', 'documentation', 'error handling', 'configuration changes', 'dependencies', 'formatting', 'miscellaneous', ...")
+{%- endif %}
+
+Class PRDescription(BaseModel):
+    type: List[PRType] = Field(description="one or more types that describe the PR content. Return the label member value (e.g. 'Bug fix', not 'bug_fix')")
+{%- if enable_semantic_files_types %}
+    pr_files[List[FileDescription]] = Field(max_items=15, description="a list of the files in the PR, and their changes summary.")
+{%- endif %}
+    description: str = Field(description="an informative and concise description of the PR. Use bullet points. Display first the most significant changes.")
+    title: str = Field(description="an informative title for the PR, describing its main theme")
+{%- if enable_custom_labels %}
+    labels: List[Label] =  Field(min_items=0, description="choose the relevant custom labels that describe the PR content, and return their keys. Use the value field of the Label object to better understand the label meaning.")
+{%- endif %}
+=====
+
+
+Example output:
+
+```yaml
+type:
+- ...
+- ...
+{%- if enable_semantic_files_types %}
+pr_files:
+- filename: |
+    ...
+  language: |
+    ...
+  changes_summary: |
+    ...
+  changes_title: |
+    ...
+  label: |
+    ...
+...
+{%- endif %}
+description: |-
+  ...
+title: |-
+  ...
+{%- if enable_custom_labels %}
+labels:
+- |
+  ...
+- |
+  ...
+{%- endif %}
+```
+
+Answer should be a valid YAML, and nothing else. Each YAML output MUST be after a newline, with proper indent, and block scalar indicator ('|')
 """
 
 user="""PR Info:
+
+Previous title: '{{title}}'
+
+{%- if description %}
+
+Previous description:
+=====
+{{ description|trim }}
+=====
+{%- endif %}
+
 Branch: '{{branch}}'
-{%- if language %}
-Main language: {{language}}
+
+{%- if commit_messages_str %}
+
+Commit messages:
+=====
+{{ commit_messages_str|trim }}
+=====
 {%- endif %}
 
 
-The PR Git Diff:
-```
-{{diff}}
-```
+The PR Diff:
+=====
+{{ diff|trim }}
+=====
+
 Note that lines in the diff body are prefixed with a symbol that represents the type of change: '-' for deletions, '+' for additions, and ' ' (a space) for unchanged lines.
 
-Response (should be a valid JSON, and nothing else):
-```json
+
+Response (should be a valid YAML, and nothing else):
+```yaml
 """