Merge pull request #408 from Codium-ai/tr/final_fixes

fixed review
better link
2025-07-04 21:00:40 +08:00 · 2023-10-29 09:02:48 -07:00 · 2023-10-29 18:01:50 +02:00 · 2023-10-29 17:59:46 +02:00 · 2023-10-29 16:54:59 +02:00 · 2023-10-29 16:33:38 +02:00
41 changed files with 893 additions and 164 deletions
--- a/INSTALL.md
+++ b/INSTALL.md
@ -4,66 +4,69 @@
 To get started with PR-Agent quickly, you first need to acquire two tokens:

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

 There are several ways to use PR-Agent:

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

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

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

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

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

+Similarly, to ask a question about a PR, run the following command:
 ```
 docker run --rm -it -e OPENAI.KEY=<your key> -e GITHUB.USER_TOKEN=<your token> codiumai/pr-agent --pr_url <pr_url> ask "<your question>"
 ```
-Note: If you want to ensure you're running a specific version of the Docker image, consider using the image's digest.
-The digest is a unique identifier for a specific version of an image. You can pull and run an image using its digest by referencing it like so: repository@sha256:digest. Always ensure you're using the correct and trusted digest for your operations.

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

 ---

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

 1. Clone this repository:

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

 ---

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

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

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

 ---

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

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

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

 ---

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

 1. Create a GitHub App from the [Github Developer Portal](https://docs.github.com/en/developers/apps/creating-a-github-app).
@ -260,13 +267,13 @@ docker push codiumai/pr-agent:github_app  # Push to your Docker repository
 9. Install the app by navigating to the "Install App" tab and selecting your desired repositories.

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

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

-1. Follow steps 1-5 of [Method 5](#method-5-run-as-a-github-app).
+1. Follow steps 1-5 of [Method 5](#run-as-a-github-app).
 2. Build a docker image that can be used as a lambda function
    ```shell
    docker buildx build --platform=linux/amd64 . -t codiumai/pr-agent:serverless -f docker/Dockerfile.lambda
@ -278,12 +285,12 @@ docker push codiumai/pr-agent:github_app  # Push to your Docker repository
    ```
 4. Create a lambda function that uses the uploaded image. Set the lambda timeout to be at least 3m.
 5. Configure the lambda function to have a Function URL.
-6. Go back to steps 8-9 of [Method 5](#method-5-run-as-a-github-app) with the function url as your Webhook URL.
+6. Go back to steps 8-9 of [Method 5](#run-as-a-github-app) with the function url as your Webhook URL.
    The Webhook URL would look like `https://<LAMBDA_FUNCTION_URL>/api/v1/github_webhooks`

 ---

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

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

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

 ---

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

 1. From the GitLab workspace or group, create an access token. Enable the "api" scope only.
 2. Generate a random secret for your app, and save it for later. For example, you can use:
@ -372,7 +379,7 @@ In the "Trigger" section, check the ‘comments’ and ‘merge request events



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


 You can use the Bitbucket Pipeline system to run PR-Agent on every pull request open or update.
@ -396,7 +403,12 @@ pipelines:
 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
+You can get a Bitbucket token for your repository by following Repository Settings -> Security -> Access Tokens.
+
+
+### Run on a hosted Bitbucket app
+
+Please contact <support@codium.ai> if you're interested in a hosted BitBucket app solution that provides full functionality including PR reviews and comment handling. It's based on the [bitbucket_app.py](https://github.com/Codium-ai/pr-agent/blob/main/pr_agent/git_providers/bitbucket_provider.py) implmentation.


 =======
--- a/README.md
+++ b/README.md
@ -28,16 +28,18 @@ CodiumAI `PR-Agent` is an open-source tool aiming to help developers review pull
 \
 ‣ **Update Changelog ([`/update_changelog`](./docs/UPDATE_CHANGELOG.md))**: Automatically updating the CHANGELOG.md file with the PR changes.
 \
-‣ **Find similar issue ([`/similar_issue`](./docs/SIMILAR_ISSUE.md))**: Automatically retrieves and presents similar issues
+‣ **Find Similar Issue ([`/similar_issue`](./docs/SIMILAR_ISSUE.md))**: Automatically retrieves and presents similar issues
 \
 ‣ **Add Documentation ([`/add_docs`](./docs/ADD_DOCUMENTATION.md))**: Automatically adds documentation to un-documented functions/classes in the PR.
+\
+‣ **Generate Custom Labels ([`/generate_labels`](./docs/GENERATE_CUSTOM_LABELS.md))**: Automatically suggests custom labels based on the PR code changes.

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

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

-See the [Release notes](./RELEASE_NOTES.md) for updates on the latest changes.
-
 <h3>Example results:</h3>
 </div>
 <h4><a href="https://github.com/Codium-ai/pr-agent/pull/229#issuecomment-1687561986">/describe:</a></h4>
@ -115,6 +117,7 @@ See the [Release notes](./RELEASE_NOTES.md) for updates on the latest changes.
 |       | 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 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:    |           |          |          |
@ -204,6 +207,9 @@ Here are some advantages of PR-Agent:
  - [x] Documentation (is the PR properly documented)
  - [ ] ...

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

 - [CodiumAI - Meaningful tests for busy devs](https://github.com/Codium-ai/codiumai-vscode-release) (although various capabilities are much more advanced in the CodiumAI IDE plugins)
@ -212,6 +218,11 @@ Here are some advantages of PR-Agent:
 - [CodeReview BOT](https://github.com/anc95/ChatGPT-CodeReview)
 - [AI-Maintainer](https://github.com/merwanehamadi/AI-Maintainer)

+## Data Privacy
+
+If you use self-host PR-Agent, e.g. via CLI running on your computer, with your OpenAI API key, it is between you and OpenAI. You can read their API data privacy policy here:
+https://openai.com/enterprise-privacy
+
 ## Links

 [![Join our Discord community](https://raw.githubusercontent.com/Codium-ai/codiumai-vscode-release/main/media/docs/Joincommunity.png)](https://discord.gg/kG35uSHDBc)
--- a/RELEASE_NOTES.md
+++ b/RELEASE_NOTES.md
@ -1,3 +1,27 @@
+## [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.
+- 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
--- a/Usage.md
+++ b/Usage.md
@ -12,7 +12,7 @@

 ### Introduction

-See the **[installation guide](/INSTALL.md)** for instructions on how to setup PR-Agent. After installation, there are three basic ways to invoke CodiumAI PR-Agent:
+After [installation](/INSTALL.md), there are three basic ways to invoke CodiumAI PR-Agent:
 1. Locally running a CLI command
 2. Online usage - by [commenting](https://github.com/Codium-ai/pr-agent/pull/229#issuecomment-1695021901) on a PR
 3. Enabling PR-Agent tools to run automatically when a new PR is opened
@ -112,15 +112,27 @@ When running PR-Agent from [GitHub App](INSTALL.md#method-5-run-as-a-github-app)

 #### GitHub app automatic tools
 The [github_app](pr_agent/settings/configuration.toml#L56) section defines GitHub app specific configurations.  
-An important parameter is `pr_commands`, which is a list of tools that will be **run automatically** when a new PR is opened:
+In this section you can define configurations to control the conditions for which tools will **run automatically**.  
+Note that a local `.pr_agent.toml` file enables you to edit and customize the default parameters of any tool, not just the ones that are run automatically.
+
+##### GitHub app automatic tools for PR actions
+The GitHub app can respond to the following actions on a PR:
+1. `opened` - Opening a new PR
+2. `reopened` - Reopening a closed PR
+3. `ready_for_review` - Moving a PR from Draft to Open
+4. `review_requested` - Specifically requesting review (in the PR reviewers list) from the `github-actions[bot]` user
+
+The configuration parameter `handle_pr_actions` defines the list of actions for which the GitHub app will trigger the PR-Agent.  
+The configuration parameter `pr_commands` defines the list of tools that will be **run automatically** when one of the above action happens (e.g. a new PR is opened):
 ```
 [github_app]
+handle_pr_actions = ['opened', 'reopened', 'ready_for_review', 'review_requested']
 pr_commands = [
    "/describe --pr_description.add_original_user_description=true --pr_description.keep_original_user_title=true",
    "/auto_review",
 ]
 ```
-This means that when a new PR is opened, PR-Agent will run the `describe` and `auto_review` tools.
+This means that when a new PR is opened/reopened or marked as ready for review, PR-Agent will run the `describe` and `auto_review` tools.  
 For the describe tool, the `add_original_user_description` and `keep_original_user_title` parameters will be set to true.

 You can override the default tool parameters by uploading a local configuration file called `.pr_agent.toml` to the root of your repo.
@ -135,11 +147,27 @@ When a new PR is opened, PR-Agent will run the `describe` tool with the above pa
 To cancel the automatic run of all the tools, set:
 ```
 [github_app]
-pr_commands = ""
+handle_pr_actions = []
 ```

+##### GitHub app automatic tools for new code (PR push)
+In addition the running automatic tools when a PR is opened, the GitHub app can also respond to new code that is pushed to an open PR.

-Note that a local `.pr_agent.toml` file enables you to edit and customize the default parameters of any tool, not just the ones that are run automatically.
+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",
+    "/auto_review -i --pr_reviewer.remove_previous_review_comment=true",
+]
+```
+The means that when new code is pused to the PR, the PR-Agent will run the `describe` and incremental `auto_review` tools.  
+For the describe tool, the `add_original_user_description` and `keep_original_user_title` parameters will be set to true.  
+For the `auto_review` tool, it will run in incremental mode, and the `remove_previous_review_comment` parameter will be set to true.
+
+Much like the configurations for `pr_commands`, you can override the default tool paramteres by uploading a local configuration file to the root of your repo.

 #### Editing the prompts
 The prompts for the various PR-Agent tools are defined in the `pr_agent/settings` folder.
@ -159,21 +187,28 @@ 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).

 ### Working with GitHub Action
-You can configure settings in GitHub action by adding environment variables under the env section in `.github/workflows/pr_agent.yml` file. Some examples:
+You can configure settings in 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:
-        # ... 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
-        github_action.auto_review: "true" # Enable auto review
-        github_action.auto_describe: "true" # Enable auto describe
-        github_action.auto_improve: "false" # Disable auto improve
+        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.auto_review: "true" # enable\disable auto review
+        github_action.auto_describe: "true" # enable\disable auto describe
+        github_action.auto_improve: "false" # enable\disable auto improve
 ```
-specifically, `github_action.auto_review`, `github_action.auto_describe` and `github_action.auto_improve` are used to enable/disable automatic tools that run when a new PR is opened.
-
+`github_action.auto_review`, `github_action.auto_describe` and `github_action.auto_improve` are used to enable/disable automatic tools that run when a new PR is opened.
 If not set, the default option is that only the `review` tool will 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
+```
+
+
 ### Changing a model

 See [here](pr_agent/algo/__init__.py) for the list of available models.
--- a/docs/DESCRIBE.md
+++ b/docs/DESCRIBE.md
@ -26,19 +26,15 @@ Under the section 'pr_description', the [configuration file](./../pr_agent/setti
 - `keep_original_user_title`: if set to true, the tool will keep the original PR title, and won't change it. Default is false.

 - `extra_instructions`: Optional extra instructions to the tool. For example: "focus on the changes in the file X. Ignore change in ...".
-
-#### Markers template
+- To enable `custom labels`, apply the configuration changes described [here](./GENERATE_CUSTOM_LABELS.md#configuration-changes)
+### Markers template

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

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

-## PR Type:
-pr_agent:pr_type

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

+##### Example:
+```
+        env:
+          pr_description.use_description_markers: 'true'
+```          
+
+<kbd><img src=./../pics/describe_markers_before.png width="768"></kbd>
+
+==>
+
+<kbd><img src=./../pics/describe_markers_after.png width="768"></kbd>
+
+##### Configuration params:
+
+- `use_description_markers`: if set to true, the tool will use markers template. It replaces every marker of the form `pr_agent:marker_name` with the relevant content. Default is false.
 - `include_generated_by_header`: if set to true, the tool will add a dedicated header: 'Generated by PR Agent at ...' to any automatic content. Default is true.
--- a/docs/GENERATE_CUSTOM_LABELS.md
+++ b/docs/GENERATE_CUSTOM_LABELS.md
@ -0,0 +1,40 @@
+# 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=./../pics/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=./../pics/custom_label_published.png width="768"></kbd>
+
+### How to enable custom labels
+
+Note that in addition to the dedicated tool `generate_labels`, the custom labels will also be used by the `review` and `describe` tools.
+
+#### CLI
+To enable custom labels, you need to apply the [configuration changes](#configuration-changes) to the [custom_labels file](./../pr_agent/settings/custom_labels.toml):
+
+#### GitHub Action and GitHub App
+To enable custom labels, you need to apply the [configuration changes](#configuration-changes) to the local `.pr_agent.toml` file in you repository.
+
+#### 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"
+```
+
--- a/docs/IMPROVE.md
+++ b/docs/IMPROVE.md
@ -32,3 +32,14 @@ Under the section 'pr_code_suggestions', the [configuration file](./../pr_agent/
 - `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.
+
+
+#### A note on code suggestions quality
+
+- With current level of AI for code (GPT-4), mistakes can happen. Not all the suggestions will be perfect, and a user should not accept all of them automatically.
+
+- Suggestions are not meant to be [simplistic](./../pr_agent/settings/pr_code_suggestions_prompts.toml#L34). Instead, they aim to give deep feedback and raise questions, ideas and thoughts to the user, who can then use his judgment, experience, and understanding of the code base.
+
+- Recommended to use the 'extra_instructions' field to guide the model to suggestions that are more relevant to the specific needs of the project.
+
+- Best quality will be obtained by using 'improve --extended' mode.
--- a/docs/REVIEW.md
+++ b/docs/REVIEW.md
@ -25,6 +25,7 @@ Under the section 'pr_reviewer', the [configuration file](./../pr_agent/settings
 - `inline_code_comments`: if set to true, the tool will publish the code suggestions as comments on the code diff. Default is false.
 - `automatic_review`: if set to false, no automatic reviews will be done. 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) 
 ####  Incremental Mode
 For an incremental review, which 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, the following command can be used:
 ```
@ -44,3 +45,14 @@ The tool will first ask the author questions about the PR, and will guide the re
 <kbd><img src=./../pics/reflection_questions.png width="768"></kbd>
 <kbd><img src=./../pics/reflection_answers.png width="768"></kbd>
 <kbd><img src=./../pics/reflection_insights.png width="768"></kbd>
+
+
+#### A note on code suggestions quality
+
+- With current level of AI for code (GPT-4), mistakes can happen. Not all the suggestions will be perfect, and a user should not accept all of them automatically.
+
+- Suggestions are not meant to be [simplistic](./../pr_agent/settings/pr_reviewer_prompts.toml#L29). Instead, they aim to give deep feedback and raise questions, ideas and thoughts to the user, who can then use his judgment, experience, and understanding of the code base.
+
+- Recommended to use the 'extra_instructions' field to guide the model to suggestions that are more relevant to the specific needs of the project.
+
+- Unlike the 'review' feature, which does a lot of things, the ['improve --extended'](./IMPROVE.md) feature is dedicated only to suggestions, and usually gives better results.
--- a/docs/TOOLS_GUIDE.md
+++ b/docs/TOOLS_GUIDE.md
@ -6,5 +6,6 @@
 - [SIMILAR_ISSUE](./SIMILAR_ISSUE.md)
 - [UPDATE CHANGELOG](./UPDATE_CHANGELOG.md)
 - [ADD DOCUMENTATION](./ADD_DOCUMENTATION.md)
+- [GENERATE CUSTOM LABELS](./GENERATE_CUSTOM_LABELS.md)

 See the **[installation guide](/INSTALL.md)** for instructions on how to setup PR-Agent.
--- a/pics/custom_label_published.png
+++ b/pics/custom_label_published.png
--- a/pics/custom_labels_list.png
+++ b/pics/custom_labels_list.png
--- a/pics/describe_markers_after.png
+++ b/pics/describe_markers_after.png
--- a/pics/describe_markers_before.png
+++ b/pics/describe_markers_before.png
--- a/pr_agent/agent/pr_agent.py
+++ b/pr_agent/agent/pr_agent.py
@ -7,6 +7,7 @@ from pr_agent.tools.pr_add_docs import PRAddDocs
 from pr_agent.tools.pr_code_suggestions import PRCodeSuggestions
 from pr_agent.tools.pr_config import PRConfig
 from pr_agent.tools.pr_description import PRDescription
+from pr_agent.tools.pr_generate_labels import PRGenerateLabels
 from pr_agent.tools.pr_information_from_user import PRInformationFromUser
 from pr_agent.tools.pr_questions import PRQuestions
 from pr_agent.tools.pr_reviewer import PRReviewer
@ -31,6 +32,7 @@ command2class = {
    "settings": PRConfig,
    "similar_issue": PRSimilarIssue,
    "add_docs": PRAddDocs,
+    "generate_labels": PRGenerateLabels,
 }

 commands = list(command2class.keys())
--- a/pr_agent/algo/utils.py
+++ b/pr_agent/algo/utils.py
@ -101,7 +101,8 @@ def parse_code_suggestion(code_suggestions: dict, gfm_supported: bool=True) -> s
                markdown_text += f"   **{sub_key}:** {sub_value}\n"
            if not gfm_supported:
                if "relevant line" not in sub_key.lower(): # nicer presentation
-                        markdown_text = markdown_text.rstrip('\n') + "\\\n"
+                        # 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
@ -304,3 +305,22 @@ def try_fix_yaml(review_text: str) -> dict:
        except:
            pass
    return data
+
+
+def set_custom_labels(variables):
+    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', 'Refactoring', 'Enhancement', 'Documentation', 'Other']
+        labels_list = "\n      - ".join(labels) if labels else ""
+        labels_list = f"      - {labels_list}" if labels_list else ""
+        variables["custom_labels"] = labels_list
+        return
+    final_labels = ""
+    for k, v in labels.items():
+        final_labels += f"      - {k} ({v['description']})\n"
+    variables["custom_labels"] = final_labels
+    variables["custom_labels_examples"] = f"      - {list(labels.keys())[0]}"
--- a/pr_agent/config_loader.py
+++ b/pr_agent/config_loader.py
@ -23,8 +23,10 @@ global_settings = Dynaconf(
        "settings/pr_sort_code_suggestions_prompts.toml",
        "settings/pr_information_from_user_prompts.toml",
        "settings/pr_update_changelog_prompts.toml",
+        "settings/pr_custom_labels.toml",
        "settings/pr_add_docs.toml",
-        "settings_prod/.secrets.toml"
+        "settings_prod/.secrets.toml",
+        "settings/custom_labels.toml"
    ]]
 )

--- a/pr_agent/git_providers/bitbucket_provider.py
+++ b/pr_agent/git_providers/bitbucket_provider.py
@ -142,10 +142,15 @@ class BitbucketProvider(GitProvider):
    def remove_initial_comment(self):
        try:
            for comment in self.temp_comments:
-                self.pr.delete(f"comments/{comment}")
+                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):
--- a/pr_agent/git_providers/codecommit_provider.py
+++ b/pr_agent/git_providers/codecommit_provider.py
@ -221,6 +221,9 @@ class CodeCommitProvider(GitProvider):
    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")
--- a/pr_agent/git_providers/gerrit_provider.py
+++ b/pr_agent/git_providers/gerrit_provider.py
@ -396,5 +396,8 @@ class GerritProvider(GitProvider):
        # shutil.rmtree(self.repo_path)
        pass

+    def remove_comment(self, comment):
+        pass
+
    def get_pr_branch(self):
        return self.repo.head
--- a/pr_agent/git_providers/git_provider.py
+++ b/pr_agent/git_providers/git_provider.py
@ -71,6 +71,10 @@ class GitProvider(ABC):
    def remove_initial_comment(self):
        pass

+    @abstractmethod
+    def remove_comment(self, comment):
+        pass
+
    @abstractmethod
    def get_languages(self):
        pass
--- a/pr_agent/git_providers/github_provider.py
+++ b/pr_agent/git_providers/github_provider.py
@ -50,7 +50,7 @@ class GithubProvider(GitProvider):
    def get_incremental_commits(self):
        self.commits = list(self.pr.get_commits())

-        self.get_previous_review()
+        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
@ -63,7 +63,7 @@ class GithubProvider(GitProvider):

    def get_commit_range(self):
        last_review_time = self.previous_review.created_at
-        first_new_commit_index = 0
+        first_new_commit_index = None
        for index in range(len(self.commits) - 1, -1, -1):
            if self.commits[index].commit.author.date > last_review_time:
                self.incremental.first_new_commit_sha = self.commits[index].sha
@ -71,15 +71,21 @@ class GithubProvider(GitProvider):
            else:
                self.incremental.last_seen_commit_sha = self.commits[index].sha
                break
-        return self.commits[first_new_commit_index:]
+        return self.commits[first_new_commit_index:] if first_new_commit_index is not None else []

-    def get_previous_review(self):
-        self.previous_review = None
-        self.comments = list(self.pr.get_issue_comments())
+    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 Analysis")
+        if incremental:
+            prefixes.append("## Incremental PR Review")
        for index in range(len(self.comments) - 1, -1, -1):
-            if self.comments[index].body.startswith("## PR Analysis") or self.comments[index].body.startswith("## Incremental PR Review"):
-                self.previous_review = self.comments[index]
-                break
+            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:
@ -218,10 +224,16 @@ class GithubProvider(GitProvider):
        try:
            for comment in getattr(self.pr, 'comments_list', []):
                if comment.is_temporary:
-                    comment.delete()
+                    self.remove_comment(comment)
        except Exception as 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

@ -258,7 +270,10 @@ class GithubProvider(GitProvider):

    def get_repo_settings(self):
        try:
-            contents = self.repo_obj.get_contents(".pr_agent.toml", ref=self.pr.head.sha).decoded_content
+            # contents = self.repo_obj.get_contents(".pr_agent.toml", ref=self.pr.head.sha).decoded_content
+
+            # more logical to take 'pr_agent.toml' from the default branch
+            contents = self.repo_obj.get_contents(".pr_agent.toml").decoded_content
            return contents
        except Exception:
            return ""
--- a/pr_agent/git_providers/gitlab_provider.py
+++ b/pr_agent/git_providers/gitlab_provider.py
@ -287,10 +287,16 @@ 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:
            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

--- a/pr_agent/git_providers/local_git_provider.py
+++ b/pr_agent/git_providers/local_git_provider.py
@ -140,6 +140,9 @@ class LocalGitProvider(GitProvider):
    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.
--- a/pr_agent/git_providers/utils.py
+++ b/pr_agent/git_providers/utils.py
@ -26,6 +26,7 @@ def apply_repo_settings(pr_url):
                        section_dict[key] = value
                    get_settings().unset(section)
                    get_settings().set(section, section_dict, merge=False)
+                    get_logger().info(f"Applying repo settings for section {section}, contents: {contents}")

        finally:
            if repo_settings_file:
--- a/pr_agent/secret_providers/google_cloud_storage_secret_provider.py
+++ b/pr_agent/secret_providers/google_cloud_storage_secret_provider.py
@ -1,9 +1,8 @@
 import ujson
-
 from google.cloud import storage

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


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

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

    def store_secret(self, secret_name: str, secret_value: str):
@ -31,5 +30,5 @@ class GoogleCloudStorageSecretProvider(SecretProvider):
            blob = self.bucket.blob(secret_name)
            blob.upload_from_string(secret_value)
        except Exception as e:
-            logger.error(f"Failed to store secret {secret_name} in Google Cloud Storage: {e}")
+            get_logger().error(f"Failed to store secret {secret_name} in Google Cloud Storage: {e}")
            raise e
--- a/pr_agent/servers/bitbucket_app.py
+++ b/pr_agent/servers/bitbucket_app.py
@ -65,15 +65,17 @@ async def handle_manifest(request: Request, response: Response):

@router.post("/webhook")
 async def handle_github_webhooks(background_tasks: BackgroundTasks, request: Request):
-    print(request.headers)
+    log_context = {"server_type": "bitbucket_app"}
+    get_logger().debug(request.headers)
    jwt_header = request.headers.get("authorization", None)
    if jwt_header:
        input_jwt = jwt_header.split(" ")[1]
    data = await request.json()
-    print(data)
+    get_logger().debug(data)
    async def inner():
        try:
            owner = data["data"]["repository"]["owner"]["username"]
+            log_context["sender"] = owner
            secrets = json.loads(secret_provider.get_secret(owner))
            shared_secret = secrets["shared_secret"]
            client_key = secrets["client_key"]
@ -85,11 +87,17 @@ async def handle_github_webhooks(background_tasks: BackgroundTasks, request: Req
            agent = PRAgent()
            if event == "pullrequest:created":
                pr_url = data["data"]["pullrequest"]["links"]["html"]["href"]
-                await agent.handle_request(pr_url, "review")
+                log_context["api_url"] = pr_url
+                log_context["event"] = "pull_request"
+                with get_logger().contextualize(**log_context):
+                    await agent.handle_request(pr_url, "review")
            elif event == "pullrequest:comment_created":
                pr_url = data["data"]["pullrequest"]["links"]["html"]["href"]
+                log_context["api_url"] = pr_url
+                log_context["event"] = "comment"
                comment_body = data["data"]["comment"]["content"]["raw"]
-                await agent.handle_request(pr_url, comment_body)
+                with get_logger().contextualize(**log_context):
+                    await agent.handle_request(pr_url, comment_body)
        except Exception as e:
            get_logger().error(f"Failed to handle webhook: {e}")
    background_tasks.add_task(inner)
@ -102,9 +110,10 @@ async def handle_github_webhooks(request: Request, response: Response):
@router.post("/installed")
 async def handle_installed_webhooks(request: Request, response: Response):
    try:
-        print(request.headers)
+        get_logger().info("handle_installed_webhooks")
+        get_logger().info(request.headers)
        data = await request.json()
-        print(data)
+        get_logger().info(data)
        shared_secret = data["sharedSecret"]
        client_key = data["clientKey"]
        username = data["principal"]["username"]
@ -119,8 +128,10 @@ async def handle_installed_webhooks(request: Request, response: Response):

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


 def start():
--- a/pr_agent/servers/github_action_runner.py
+++ b/pr_agent/servers/github_action_runner.py
@ -5,6 +5,8 @@ import os
 from pr_agent.agent.pr_agent import PRAgent
 from pr_agent.config_loader import get_settings
 from pr_agent.git_providers import get_git_provider
+from pr_agent.git_providers.utils import apply_repo_settings
+from pr_agent.log import get_logger
 from pr_agent.tools.pr_code_suggestions import PRCodeSuggestions
 from pr_agent.tools.pr_description import PRDescription
 from pr_agent.tools.pr_reviewer import PRReviewer
@ -19,7 +21,6 @@ async def run_action():
    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")
@ -49,6 +50,15 @@ async def run_action():
        print(f"Failed to parse JSON: {e}")
        return

+    try:
+        get_logger().info("Applying repo settings")
+        pr_url = event_payload.get("pull_request", {}).get("html_url")
+        if pr_url:
+            apply_repo_settings(pr_url)
+            get_logger().info(f"enable_custom_labels: {get_settings().config.enable_custom_labels}")
+    except Exception as e:
+        get_logger().info(f"github action: failed to apply repo settings: {e}")
+
    # Handle pull request event
    if GITHUB_EVENT_NAME == "pull_request":
        action = event_payload.get("action")
--- a/pr_agent/servers/github_app.py
+++ b/pr_agent/servers/github_app.py
@ -1,7 +1,7 @@
 import copy
 import os
-import time
-from typing import Any, Dict
+import asyncio.locks
+from typing import Any, Dict, List, Tuple

 import uvicorn
 from fastapi import APIRouter, FastAPI, HTTPException, Request, Response
@ -14,8 +14,9 @@ from pr_agent.algo.utils import update_settings_from_args
 from pr_agent.config_loader import get_settings, global_settings
 from pr_agent.git_providers import get_git_provider
 from pr_agent.git_providers.utils import apply_repo_settings
+from pr_agent.git_providers.git_provider import IncrementalPR
 from pr_agent.log import LoggingFormat, get_logger, setup_logger
-from pr_agent.servers.utils import verify_signature
+from pr_agent.servers.utils import verify_signature, DefaultDictWithTimeout

 setup_logger(fmt=LoggingFormat.JSON)

@ -47,6 +48,7 @@ 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()
@ -61,7 +63,9 @@ async def get_body(request):
    return body


-_duplicate_requests_cache = {}
+_duplicate_requests_cache = DefaultDictWithTimeout(ttl=get_settings().github_app.duplicate_requests_cache_ttl)
+_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)


 async def handle_request(body: Dict[str, Any], event: str):
@ -109,40 +113,110 @@ async def handle_request(body: Dict[str, Any], event: str):
    # handle pull_request event:
    #   automatically review opened/reopened/ready_for_review PRs as long as they're not in draft,
    #   as well as direct review requests from the bot
-    elif event == 'pull_request':
-        pull_request = body.get("pull_request")
-        if not pull_request:
-            return {}
-        api_url = pull_request.get("url")
-        if not api_url:
-            return {}
-        log_context["api_url"] = api_url
-        if pull_request.get("draft", True) or pull_request.get("state") != "open" or pull_request.get("user", {}).get("login", "") == bot_user:
+    elif event == 'pull_request' and action != 'synchronize':
+        pull_request, api_url = _check_pull_request_event(action, body, log_context, bot_user)
+        if not (pull_request and api_url):
            return {}
        if action in get_settings().github_app.handle_pr_actions:
            if action == "review_requested":
                if body.get("requested_reviewer", {}).get("login", "") != bot_user:
                    return {}
-                if pull_request.get("created_at") == pull_request.get("updated_at"):
-                    # avoid double reviews when opening a PR for the first time
-                    return {}
-            get_logger().info(f"Performing review because of event={event} and action={action}")
-            apply_repo_settings(api_url)
-            for command in get_settings().github_app.pr_commands:
-                split_command = command.split(" ")
-                command = split_command[0]
-                args = split_command[1:]
-                other_args = update_settings_from_args(args)
-                new_command = ' '.join([command] + other_args)
-                get_logger().info(body)
-                get_logger().info(f"Performing command: {new_command}")
-                with get_logger().contextualize(**log_context):
-                    await agent.handle_request(api_url, new_command)
+            get_logger().info(f"Performing review for {api_url=} because of {event=} and {action=}")
+            await _perform_commands(get_settings().github_app.pr_commands, agent, body, api_url, log_context)
+
+    # handle pull_request event with synchronize action - "push trigger" for new commits
+    elif event == 'pull_request' and action == 'synchronize' and get_settings().github_app.handle_push_trigger:
+        pull_request, api_url = _check_pull_request_event(action, body, log_context, bot_user)
+        if not (pull_request and api_url):
+            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 {}
+        if get_settings().github_app.push_trigger_ignore_bot_commits and body.get("sender", {}).get("login", "") == bot_user:
+            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 {}
+            get_logger().info(f"Performing incremental review for {api_url=} because of {event=} and {action=}")
+            await _perform_commands(get_settings().github_app.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

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


+def _check_pull_request_event(action: str, body: dict, log_context: dict, bot_user: str) -> 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" or pull_request.get("user", {}).get("login", "") == bot_user:
+        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_commands(commands: List[str], agent: PRAgent, body: dict, api_url: str, log_context: dict):
+    apply_repo_settings(api_url)
+    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)
+        get_logger().info(body)
+        get_logger().info(f"Performing command: {new_command}")
+        with get_logger().contextualize(**log_context):
+            await agent.handle_request(api_url, new_command)
+
+
 def _is_duplicate_request(body: Dict[str, Any]) -> bool:
    """
    In some deployments its possible to get duplicate requests if the handling is long,
@ -150,13 +224,8 @@ def _is_duplicate_request(body: Dict[str, Any]) -> bool:
    """
    request_hash = hash(str(body))
    get_logger().info(f"request_hash: {request_hash}")
-    request_time = time.monotonic()
-    ttl = get_settings().github_app.duplicate_requests_cache_ttl  # in seconds
-    to_delete = [key for key, key_time in _duplicate_requests_cache.items() if request_time - key_time > ttl]
-    for key in to_delete:
-        del _duplicate_requests_cache[key]
-    is_duplicate = request_hash in _duplicate_requests_cache
-    _duplicate_requests_cache[request_hash] = request_time
+    is_duplicate = _duplicate_requests_cache.get(request_hash, False)
+    _duplicate_requests_cache[request_hash] = True
    if is_duplicate:
        get_logger().info(f"Ignoring duplicate request {request_hash}")
    return is_duplicate
--- a/pr_agent/servers/gitlab_webhook.py
+++ b/pr_agent/servers/gitlab_webhook.py
@ -12,23 +12,33 @@ 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
+from pr_agent.log import LoggingFormat, get_logger, setup_logger
 from pr_agent.secret_providers import get_secret_provider

-setup_logger()
+setup_logger(fmt=LoggingFormat.JSON)
 router = APIRouter()

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


+def handle_request(background_tasks: BackgroundTasks, url: str, body: str, log_context: dict):
+    log_context["action"] = body
+    log_context["event"] = "pull_request" if body == "/review" else "comment"
+    log_context["api_url"] = url
+    with get_logger().contextualize(**log_context):
+        background_tasks.add_task(PRAgent().handle_request, url, body)
+
+
@router.post("/webhook")
 async def gitlab_webhook(background_tasks: BackgroundTasks, request: Request):
+    log_context = {"server_type": "gitlab_app"}
    if request.headers.get("X-Gitlab-Token") and secret_provider:
        request_token = request.headers.get("X-Gitlab-Token")
        secret = secret_provider.get_secret(request_token)
        try:
            secret_dict = json.loads(secret)
            gitlab_token = secret_dict["gitlab_token"]
+            log_context["sender"] = secret_dict["id"]
            context["settings"] = copy.deepcopy(global_settings)
            context["settings"].gitlab.personal_access_token = gitlab_token
        except Exception as e:
@ -48,13 +58,13 @@ async def gitlab_webhook(background_tasks: BackgroundTasks, request: Request):
    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')
-        background_tasks.add_task(PRAgent().handle_request, url, "/review")
+        handle_request(background_tasks, url, "/review")
    elif data.get('object_kind') == 'note' and data['event_type'] == 'note':
        if 'merge_request' in data:
            mr = data['merge_request']
            url = mr.get('url')
            body = data.get('object_attributes', {}).get('note')
-            background_tasks.add_task(PRAgent().handle_request, url, body)
+            handle_request(background_tasks, url, body)
    return JSONResponse(status_code=status.HTTP_200_OK, content=jsonable_encoder({"message": "success"}))


--- a/pr_agent/servers/utils.py
+++ b/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

@ -25,3 +28,59 @@ def verify_signature(payload_body, secret_token, signature_header):
 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)
--- a/pr_agent/settings/configuration.toml
+++ b/pr_agent/settings/configuration.toml
@ -24,6 +24,7 @@ num_code_suggestions=4
 inline_code_comments = false
 ask_and_reflect=false
 automatic_review=true
+remove_previous_review_comment=false
 extra_instructions = ""

 [pr_description] # /describe #
@ -31,11 +32,15 @@ publish_labels=true
 publish_description_as_comment=false
 add_original_user_description=false
 keep_original_user_title=false
+use_bullet_points=true
 extra_instructions = ""
+
 # markers
 use_description_markers=false
 include_generated_by_header=true

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

 [pr_code_suggestions] # /improve #
@ -82,6 +87,27 @@ pr_commands = [
    "/describe --pr_description.add_original_user_description=true --pr_description.keep_original_user_title=true",
    "/auto_review",
 ]
+# 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",
+    """/auto_review -i \
+       --pr_reviewer.require_focused_review=false \
+       --pr_reviewer.require_score_review=false \
+       --pr_reviewer.require_tests_review=false \
+       --pr_reviewer.require_security_review=false \
+       --pr_reviewer.require_estimate_effort_to_review=false \
+       --pr_reviewer.num_code_suggestions=0 \
+       --pr_reviewer.inline_code_comments=false \
+       --pr_reviewer.remove_previous_review_comment=true \
+       --pr_reviewer.extra_instructions='' \
+    """
+]

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

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

 {%- if num_code_suggestions > 0 %}
- Provide up to {{ num_code_suggestions }} code suggestions.
+- Provide up to {{ num_code_suggestions }} code suggestions. Try to provide diverse and insightful suggestions.
 - Focus on important suggestions like fixing code problems, issues and bugs. As a second priority, provide suggestions for meaningful code improvements, like performance, vulnerability, modularity, and best practices.
 - Avoid making suggestions that have already been implemented in the PR code. For example, if you want to add logs, or change a variable to const, or anything else, make sure it isn't already in the PR code.
 - Don't suggest to add docstring, type hints, or comments.
@ -51,13 +51,22 @@ PR Analysis:
    description: summary of the PR in 2-3 sentences.
  Type of PR:
    type: string
+{%- if enable_custom_labels %}
+  description: One or more labels that describe the PR type. Don't output the description in the parentheses.
+{%- endif %}
+  items:
+    type: string
    enum:
+{%- if enable_custom_labels %}
+{{ custom_labels }}
+{%- else %}
      - Bug fix
      - Tests
      - Refactoring
      - Enhancement
      - Documentation
      - Other
+{%- endif %}
 {%- if require_score %}
  Score:
    type: int
@ -99,10 +108,10 @@ PR Feedback:
  General suggestions:
    type: string
    description: |-
-      General suggestions and feedback for the contributors and maintainers of
-      this PR. May include important suggestions for the overall structure,
-      primary purpose, best practices, critical bugs, and other aspects of the
-      PR. Don't address PR title and description, or lack of tests. Explain your suggestions.
+      General suggestions and feedback for the contributors and maintainers of this PR.
+      May include important suggestions for the overall structure,
+      primary purpose, best practices, critical bugs, and other aspects of the PR.
+      Don't address PR title and description, or lack of tests. Explain your suggestions.
 {%- if num_code_suggestions > 0 %}
  Code feedback:
    type: array
@ -115,11 +124,10 @@ PR Feedback:
      suggestion:
        type: string
        description: |-
-          a concrete suggestion for meaningfully improving the new PR code. Also
-          describe how, specifically, the suggestion can be applied to new PR
-          code. Add tags with importance measure that matches each suggestion
-          ('important' or 'medium'). Do not make suggestions for updating or
-          adding docstrings, renaming PR title and description, or linter like.
+          a concrete suggestion for meaningfully improving the new PR code.
+          Also describe how, specifically, the suggestion can be applied to new PR code.
+          Add tags with importance measure that matches each suggestion ('important' or 'medium').
+          Do not make suggestions for updating or adding docstrings, renaming PR title and description, or linter like.
      relevant line:
        type: string
        description: |-
--- a/pr_agent/tools/pr_add_docs.py
+++ b/pr_agent/tools/pr_add_docs.py
@ -65,6 +65,11 @@ class PRAddDocs:

    async def _prepare_prediction(self, model: str):
        get_logger().info('Getting PR diff...')
+
+        # Disable adding docs to scripts and other non-relevant text files
+        from pr_agent.algo.language_handler import bad_extensions
+        bad_extensions += get_settings().docs_blacklist_extensions.docs_blacklist
+
        self.patches_diff = get_pr_diff(self.git_provider,
                                        self.token_handler,
                                        model,
--- a/pr_agent/tools/pr_description.py
+++ b/pr_agent/tools/pr_description.py
@ -7,7 +7,7 @@ from jinja2 import Environment, StrictUndefined
 from pr_agent.algo.ai_handler import AiHandler
 from pr_agent.algo.pr_processing import get_pr_diff, retry_with_fallback_models
 from pr_agent.algo.token_handler import TokenHandler
-from pr_agent.algo.utils import load_yaml
+from pr_agent.algo.utils import load_yaml, set_custom_labels
 from pr_agent.config_loader import get_settings
 from pr_agent.git_providers import get_git_provider
 from pr_agent.git_providers.git_provider import get_main_pr_language
@ -40,8 +40,12 @@ class PRDescription:
            "description": self.git_provider.get_pr_description(full=False),
            "language": self.main_pr_language,
            "diff": "",  # empty diff for initial calculation
+            "use_bullet_points": get_settings().pr_description.use_bullet_points,
            "extra_instructions": get_settings().pr_description.extra_instructions,
-            "commit_messages_str": self.git_provider.get_commit_messages()
+            "commit_messages_str": self.git_provider.get_commit_messages(),
+            "enable_custom_labels": get_settings().config.enable_custom_labels,
+            "custom_labels": "",
+            "custom_labels_examples": "",
        }

        self.user_description = self.git_provider.get_user_description()
@ -139,6 +143,7 @@ class PRDescription:
        variables["diff"] = self.patches_diff  # update diff

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

@ -155,7 +160,6 @@ class PRDescription:

        return response

-
    def _prepare_data(self):
        # Load the AI prediction data into a dictionary
        self.data = load_yaml(self.prediction.strip())
@ -185,6 +189,11 @@ class PRDescription:
        else:
            ai_header = ""

+        ai_type = self.data.get('PR Type')
+        if ai_type and not re.search(r'<!--\s*pr_agent:type\s*-->', body):
+            pr_type = f"{ai_header}{ai_type}"
+            body = body.replace('pr_agent:type', pr_type)
+
        ai_summary = self.data.get('PR Description')
        if ai_summary and not re.search(r'<!--\s*pr_agent:summary\s*-->', body):
            summary = f"{ai_header}{ai_summary}"
--- a/pr_agent/tools/pr_generate_labels.py
+++ b/pr_agent/tools/pr_generate_labels.py
@ -0,0 +1,163 @@
+import copy
+import re
+from typing import List, Tuple
+
+from jinja2 import Environment, StrictUndefined
+
+from pr_agent.algo.ai_handler import AiHandler
+from pr_agent.algo.pr_processing import get_pr_diff, retry_with_fallback_models
+from pr_agent.algo.token_handler import TokenHandler
+from pr_agent.algo.utils import load_yaml, set_custom_labels
+from pr_agent.config_loader import get_settings
+from pr_agent.git_providers import get_git_provider
+from pr_agent.git_providers.git_provider import get_main_pr_language
+from pr_agent.log import get_logger
+
+
+class PRGenerateLabels:
+    def __init__(self, pr_url: str, args: list = None):
+        """
+        Initialize the PRGenerateLabels object with the necessary attributes and objects for generating labels
+        corresponding to the PR using an AI model.
+        Args:
+            pr_url (str): The URL of the pull request.
+            args (list, optional): List of arguments passed to the PRGenerateLabels class. Defaults to None.
+        """
+        # Initialize the git provider and main PR language
+        self.git_provider = get_git_provider()(pr_url)
+        self.main_pr_language = get_main_pr_language(
+            self.git_provider.get_languages(), self.git_provider.get_files()
+        )
+        self.pr_id = self.git_provider.get_pr_id()
+
+        # Initialize the AI handler
+        self.ai_handler = AiHandler()
+    
+        # Initialize the variables dictionary
+        self.vars = {
+            "title": self.git_provider.pr.title,
+            "branch": self.git_provider.get_pr_branch(),
+            "description": self.git_provider.get_pr_description(full=False),
+            "language": self.main_pr_language,
+            "diff": "",  # empty diff for initial calculation
+            "use_bullet_points": get_settings().pr_description.use_bullet_points,
+            "extra_instructions": get_settings().pr_description.extra_instructions,
+            "commit_messages_str": self.git_provider.get_commit_messages(),
+            "custom_labels": "",
+            "custom_labels_examples": "",
+            "enable_custom_labels": get_settings().config.enable_custom_labels,
+        }
+
+        # Initialize the token handler
+        self.token_handler = TokenHandler(
+            self.git_provider.pr,
+            self.vars,
+            get_settings().pr_custom_labels_prompt.system,
+            get_settings().pr_custom_labels_prompt.user,
+        )
+    
+        # Initialize patches_diff and prediction attributes
+        self.patches_diff = None
+        self.prediction = None
+
+    async def run(self):
+        """
+        Generates a PR labels using an AI model and publishes it to the PR.
+        """
+
+        try:
+            get_logger().info(f"Generating a PR labels {self.pr_id}")
+            if get_settings().config.publish_output:
+                self.git_provider.publish_comment("Preparing PR labels...", is_temporary=True)
+
+            await retry_with_fallback_models(self._prepare_prediction)
+
+            get_logger().info(f"Preparing answer {self.pr_id}")
+            if self.prediction:
+                self._prepare_data()
+            else:
+                return None
+
+            pr_labels = self._prepare_labels()
+
+            if get_settings().config.publish_output:
+                get_logger().info(f"Pushing labels {self.pr_id}")
+                if self.git_provider.is_supported("get_labels"):
+                    current_labels = self.git_provider.get_labels()
+                    if current_labels is None:
+                        current_labels = []
+                    self.git_provider.publish_labels(pr_labels + current_labels)
+                self.git_provider.remove_initial_comment()
+        except Exception as e:
+            get_logger().error(f"Error generating PR labels {self.pr_id}: {e}")
+        
+        return ""
+
+    async def _prepare_prediction(self, model: str) -> None:
+        """
+        Prepare the AI prediction for the PR labels based on the provided model.
+
+        Args:
+            model (str): The name of the model to be used for generating the prediction.
+
+        Returns:
+            None
+
+        Raises:
+            Any exceptions raised by the 'get_pr_diff' and '_get_prediction' functions.
+
+        """
+
+        get_logger().info(f"Getting PR diff {self.pr_id}")
+        self.patches_diff = get_pr_diff(self.git_provider, self.token_handler, model)
+        get_logger().info(f"Getting AI prediction {self.pr_id}")
+        self.prediction = await self._get_prediction(model)
+
+    async def _get_prediction(self, model: str) -> str:
+        """
+        Generate an AI prediction for the PR labels based on the provided model.
+
+        Args:
+            model (str): The name of the model to be used for generating the prediction.
+
+        Returns:
+            str: The generated AI prediction.
+        """
+        variables = copy.deepcopy(self.vars)
+        variables["diff"] = self.patches_diff  # update diff
+
+        environment = Environment(undefined=StrictUndefined)
+        set_custom_labels(variables)
+        system_prompt = environment.from_string(get_settings().pr_custom_labels_prompt.system).render(variables)
+        user_prompt = environment.from_string(get_settings().pr_custom_labels_prompt.user).render(variables)
+
+        if get_settings().config.verbosity_level >= 2:
+            get_logger().info(f"\nSystem prompt:\n{system_prompt}")
+            get_logger().info(f"\nUser prompt:\n{user_prompt}")
+
+        response, finish_reason = await self.ai_handler.chat_completion(
+            model=model,
+            temperature=0.2,
+            system=system_prompt,
+            user=user_prompt
+        )
+
+        return response
+
+    def _prepare_data(self):
+        # Load the AI prediction data into a dictionary
+        self.data = load_yaml(self.prediction.strip())
+
+
+
+    def _prepare_labels(self) -> List[str]:
+        pr_types = []
+
+        # If the 'PR Type' key is present in the dictionary, split its value by comma and assign it to 'pr_types'
+        if 'PR Type' in self.data:
+            if type(self.data['PR Type']) == list:
+                pr_types = self.data['PR Type']
+            elif type(self.data['PR Type']) == str:
+                pr_types = self.data['PR Type'].split(',')
+
+        return pr_types
--- a/pr_agent/tools/pr_reviewer.py
+++ b/pr_agent/tools/pr_reviewer.py
@ -9,7 +9,7 @@ from yaml import SafeLoader
 from pr_agent.algo.ai_handler import AiHandler
 from pr_agent.algo.pr_processing import get_pr_diff, retry_with_fallback_models
 from pr_agent.algo.token_handler import TokenHandler
-from pr_agent.algo.utils import convert_to_markdown, load_yaml, try_fix_yaml
+from pr_agent.algo.utils import convert_to_markdown, load_yaml, try_fix_yaml, set_custom_labels
 from pr_agent.config_loader import get_settings
 from pr_agent.git_providers import get_git_provider
 from pr_agent.git_providers.git_provider import IncrementalPR, get_main_pr_language
@ -63,6 +63,8 @@ class PRReviewer:
            'answer_str': answer_str,
            "extra_instructions": get_settings().pr_reviewer.extra_instructions,
            "commit_messages_str": self.git_provider.get_commit_messages(),
+            "custom_labels": "",
+            "enable_custom_labels": get_settings().config.enable_custom_labels,
        }

        self.token_handler = TokenHandler(
@ -98,6 +100,9 @@ class PRReviewer:
            if self.is_auto and not get_settings().pr_reviewer.automatic_review:
                get_logger().info(f'Automatic review is disabled {self.pr_url}')
                return None
+            if self.is_auto and self.incremental.is_incremental and not self.incremental.first_new_commit_sha:
+                get_logger().info(f"Incremental review is enabled for {self.pr_url} but there are no new commits")
+                return None

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

@ -113,7 +118,9 @@ class PRReviewer:
                get_logger().info('Pushing PR review...')
                self.git_provider.publish_comment(pr_comment)
                self.git_provider.remove_initial_comment()
-
+                previous_review_comment = self._get_previous_review_comment()
+                if previous_review_comment:
+                    self._remove_previous_review_comment(previous_review_comment)
                if get_settings().pr_reviewer.inline_code_comments:
                    get_logger().info('Pushing inline code comments...')
                    self._publish_inline_code_comments()
@ -149,6 +156,7 @@ class PRReviewer:
        variables["diff"] = self.patches_diff  # update diff

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

@ -228,9 +236,13 @@ class PRReviewer:
        if self.incremental.is_incremental:
            last_commit_url = f"{self.git_provider.get_pr_url()}/commits/" \
                              f"{self.git_provider.incremental.first_new_commit_sha}"
+            last_commit_msg = self.incremental.commits_range[0].commit.message if self.incremental.commits_range else ""
+            incremental_review_markdown_text = f"Starting from commit {last_commit_url}"
+            if last_commit_msg:
+                incremental_review_markdown_text += f"  \n_({last_commit_msg.splitlines(keepends=False)[0]})_"
            data = OrderedDict(data)
            data.update({'Incremental PR Review': {
-                "⏮️ Review for commits since previous PR-Agent review": f"Starting from commit {last_commit_url}"}})
+                "⏮️ Review for commits since previous PR-Agent review": incremental_review_markdown_text}})
            data.move_to_end('Incremental PR Review', last=False)

        markdown_text = convert_to_markdown(data, self.git_provider.is_supported("gfm_markdown"))
@ -311,3 +323,26 @@ class PRReviewer:
                    break

        return question_str, answer_str
+
+    def _get_previous_review_comment(self):
+        """
+        Get the previous review comment if it exists.
+        """
+        try:
+            if get_settings().pr_reviewer.remove_previous_review_comment and hasattr(self.git_provider, "get_previous_review"):
+                return self.git_provider.get_previous_review(
+                    full=not self.incremental.is_incremental,
+                    incremental=self.incremental.is_incremental,
+                )
+        except Exception as e:
+            get_logger().exception(f"Failed to get previous review comment, error: {e}")
+
+    def _remove_previous_review_comment(self, comment):
+        """
+        Remove the previous review comment if it exists.
+        """
+        try:
+            if get_settings().pr_reviewer.remove_previous_review_comment and comment:
+                self.git_provider.remove_comment(comment)
+        except Exception as e:
+            get_logger().exception(f"Failed to remove previous review comment, error: {e}")
--- a/pr_agent/tools/pr_similar_issue.py
+++ b/pr_agent/tools/pr_similar_issue.py
@ -48,9 +48,9 @@ class PRSimilarIssue:
        # check if index exists, and if repo is already indexed
        run_from_scratch = False
        if run_from_scratch:  # for debugging
-            if not index_name in pinecone.list_indexes():
+            pinecone.init(api_key=api_key, environment=environment)
+            if index_name in pinecone.list_indexes():
                get_logger().info('Removing index...')
-                pinecone.init(api_key=api_key, environment=environment)
                pinecone.delete_index(index_name)
                get_logger().info('Done')
Author	SHA1	Message	Date
mrT23	b57ec301e8	Merge pull request #408 from Codium-ai/tr/final_fixes fixed review	2023-10-29 09:02:48 -07:00
mrT23	71da20ea7e	better link	2023-10-29 18:01:50 +02:00
mrT23	c895657310	fixed review	2023-10-29 17:59:46 +02:00
Ori Kotek	eda20ccca9	Merge pull request #407 from zmeir/patch-1 Update Usage.md with new GitHub App features	2023-10-29 16:54:59 +02:00
Zohar Meir	aed113cd79	Update Usage.md with new GitHub App features	2023-10-29 16:33:38 +02:00
mrT23	0ab07a46c6	Merge pull request #405 from Codium-ai/tr/final_fixes Final Fixes and Updates to PR Agent	2023-10-29 06:02:34 -07:00
mrT23	5f32e28933	generate_labels	2023-10-29 15:02:16 +02:00
mrT23	7538c4dd2f	generate_labels	2023-10-29 14:59:50 +02:00
mrT23	e3845283f8	release notes	2023-10-29 14:58:36 +02:00
mrT23	a85921d3c5	release notes	2023-10-29 14:49:35 +02:00
mrT23	27b64fbcaf	release notes	2023-10-29 14:47:46 +02:00
mrT23	8d50f2ae82	release notes	2023-10-29 14:43:45 +02:00
mrT23	e97a03f522	Merge remote-tracking branch 'origin/main' into tr/final_fixes	2023-10-29 14:38:33 +02:00
mrT23	2e3344b5b0	Merge pull request #406 from Codium-ai/hl/custom_labels Add documentation to custom labels	2023-10-29 05:38:11 -07:00
mrT23	e1b51eace7	release notes	2023-10-29 14:37:04 +02:00
Hussam.lawen	49e3d5ec5f	Add documentation	2023-10-29 13:58:01 +02:00
mrT23	afa78ed3fb	final fixes	2023-10-29 13:07:22 +02:00
mrT23	72d5e4748e	final fixes	2023-10-29 13:05:15 +02:00
Ori Kotek	61d3e1ebf4	Merge pull request #394 from zmeir/zmeir-external-push_trigger Added support for automatic review on push event	2023-10-29 13:04:33 +02:00
mrT23	055b5ea700	final fixes	2023-10-29 13:03:12 +02:00
Hussam.lawen	3434296792	Documentation	2023-10-29 13:02:07 +02:00
mrT23	ae375c2ff0	final fixes	2023-10-29 13:01:55 +02:00
Hussam.lawen	3d5efdf4f3	Merge commit '9a585de36461a6941cb77009e5ab5f4b568a1ff7' into hl/custom_labels	2023-10-29 13:01:53 +02:00
Hussam Lawen	9a585de364	Merge pull request #404 from Codium-ai/tr/final_fixes final fixes	2023-10-29 12:31:40 +02:00
mrT23	c27dc436c4	final fixes	2023-10-29 12:29:14 +02:00
Hussam.lawen	e83747300d	Merge branch 'main' of github.com:Codium-ai/pr-agent into hl/custom_labels	2023-10-29 12:09:43 +02:00
mrT23	7374243d0b	enable_custom_labels	2023-10-29 11:40:36 +02:00
mrT23	5c568bc0c5	Merge pull request #403 from Codium-ai/tr/fix_custom_labels Refactoring Custom Labels Handling and Documentation Update	2023-10-29 02:34:18 -07:00
mrT23	22c196cb3b	Merge remote-tracking branch 'origin/main' into tr/fix_custom_labels # Conflicts: # pr_agent/git_providers/github_provider.py	2023-10-29 10:58:42 +02:00
mrT23	d2cc856cfc	Merge pull request #402 from Codium-ai/tr/github_action_uses_toml Update GitHub Action to Use .pr_agent.toml	2023-10-29 01:55:33 -07:00
Hussam.lawen	013a689b33	generate_labels fix	2023-10-29 10:43:04 +02:00
mrT23	d772213cfc	fix labels	2023-10-29 08:58:12 +02:00
mrT23	638db96311	github action now also uses .pr_agent.toml	2023-10-28 13:34:32 +03:00
Hussam Lawen	4dffabf397	Merge pull request #396 from Codium-ai/hl/custom_labels Implement Custom Labels for PRs	2023-10-28 01:37:54 +03:00
Hussam.lawen	6f2bbd3baa	Add documentation	2023-10-28 00:45:59 +03:00
Hussam.lawen	9e41f3780c	disable custom labels by default	2023-10-27 21:22:56 +03:00
Hussam.lawen	f53ec1d0cc	move enable custom labels to custom labels function	2023-10-27 21:12:58 +03:00
mrT23	f7666cb59a	Update INSTALL.md	2023-10-27 11:49:39 +03:00
Hussam.lawen	a7cb59ca8b	small fix	2023-10-27 08:10:29 +03:00
Hussam.lawen	ca0ea77415	refactor	2023-10-27 07:58:42 +03:00
Hussam.lawen	0cf27e5fee	custom labels disabled by default	2023-10-27 07:54:59 +03:00
Hussam.lawen	f3bdbfc103	Add /generate_labels function + fix issues	2023-10-26 23:28:33 +03:00
mrT23	20e3acdd86	Merge pull request #393 from Kryslynn93/patch-1 Update configuration.toml	2023-10-26 07:43:00 -07:00
mrT23	f965b09571	Merge pull request #398 from Codium-ai/tr/readme_updates Update Documentation and Installation Instructions	2023-10-26 07:37:05 -07:00
Zohar Meir	e6bea76eee	Typo	2023-10-26 17:07:16 +03:00
zmeir	414f2b6767	Fix incremental review if there are no new commits (would have performed a full review instead)	2023-10-26 16:49:55 +03:00
zmeir	6541575a0e	Refactor to use pull_request synchronize event	2023-10-26 16:49:54 +03:00
zmeir	02570ea797	Remove previous review comment on push event	2023-10-26 16:46:54 +03:00
mrT23	b8583c998d	readme	2023-10-26 12:16:58 +03:00
mrT23	726594600b	readme	2023-10-26 12:10:14 +03:00
mrT23	c77cc1d6ed	readme	2023-10-26 11:56:03 +03:00
mrT23	b6c9e01a59	readme	2023-10-26 11:51:32 +03:00
Ori Kotek	ec673214c8	Update INSTALL.md	2023-10-26 11:18:07 +03:00
Hussam.lawen	16777a5334	Add custom label description	2023-10-25 13:48:27 +03:00
zmeir	65bb70a1dd	Added support for automatic review on push event The new feature can be enabled via the new configuration `github_app.handle_push_event`. To avoid any unwanted side-effects, the current default of this configuration is set to `false`. The high level flow (assuming the configuration is enabled): 1. receive push event from GitHub 2. extract branch and commits from event 3. find PR url for branch (currently does not support PRs from forks) 4. perform configured commands (e.g. `/describe`, `/review -i`) The push event flow is guarded by a backlog queue so that multiple push events on the same branch won't trigger multiple duplicate runs of the PR-Agent commands. Example timeline: 1. push 1 - start handling event 2. push 2 - waiting to be handled while push 1 event is still running 3. push 3 - event is dropped since handling it and handling push 2 is the same, so it is redundant 4. push 1 finished being handled 5. push 2 awakens from wait and continues handling (potentially reviewing the commits of both push 2 and push 3) All of these options are configurable and can be enabled/disabled as per the user's desire. Additional minor changes in this PR: 1. Created `DefaultDictWithTimeout` utility class to avoid too much boilerplate code in managing caches for outdated triggers. 2. Guard against running increment review when there are no new commits. 3. Minor styling changes for incremented review text.	2023-10-25 11:15:23 +03:00
Hussam.lawen	1a89c7eadf	refactor + add description options	2023-10-24 22:28:57 +03:00
Hussam.lawen	07617eab5a	add custom labels	2023-10-24 22:06:27 +03:00
Krystal Boozel	f9e4c2b098	Update configuration.toml	2023-10-23 21:34:12 -04:00
Hussam.lawen	fa24413201	Custom Labels	2023-10-23 16:29:33 +03:00
mrT23	b6cabda586	quick fix	2023-10-19 17:24:37 +03:00
mrT23	abbce60f18	Merge remote-tracking branch 'origin/main'	2023-10-19 17:10:30 +03:00
mrT23	5daaaf2c1d	quick fix	2023-10-19 17:10:21 +03:00
mrT23	e8f207691e	Merge pull request #391 from Codium-ai/tr/readme Update and Enhance DESCRIBE.md Documentation	2023-10-19 02:03:50 -07:00
mrT23	b0dce4ceae	describe	2023-10-19 12:02:12 +03:00
Ori Kotek	fc494296d7	Merge pull request #387 from Codium-ai/ok/json_logging_in_bitbucket Enhancing Logging in Bitbucket, GitLab, and Google Cloud Storage Secret Provider	2023-10-19 11:59:26 +03:00
mrT23	67b4069540	describe	2023-10-19 11:45:41 +03:00
mrT23	e6defcc846	describe	2023-10-19 11:43:18 +03:00
mrT23	096fcbbc17	describe	2023-10-19 11:40:01 +03:00
mrT23	eb7add1c77	describe	2023-10-19 11:38:21 +03:00
Hussam Lawen	1b6fb3ea53	Merge pull request #385 from Codium-ai/hl/fix_add_docs_in_scripts Add Blacklist for Non-Editable File Extensions in Documentation	2023-10-19 11:21:36 +03:00
mrT23	c57b70f1d4	Merge pull request #390 from Codium-ai/tr/readme Enhancing Documentation and Updating Configuration for PR Descriptions	2023-10-19 01:04:24 -07:00
mrT23	a2c3db463a	use_bullet_points	2023-10-19 10:45:42 +03:00
mrT23	193da1c356	update readme	2023-10-19 09:22:26 +03:00
mrT23	5bc26880b3	update readme	2023-10-19 09:20:36 +03:00
mrT23	21a1cc970e	- update readme - minor prompts change	2023-10-19 09:16:20 +03:00
Ori Kotek	954727ad67	Merge pull request #386 from Codium-ai/ok/fix_bitbucket_pipeline Refactor Bitbucket Pipeline Integration and Update Documentation	2023-10-18 16:45:26 +03:00
Ori Kotek	1314898cbf	Enhance logging in bitbucket_app, gitlab_webhook, and google_cloud_storage_secret_provider with JSON format and additional context	2023-10-18 16:44:03 +03:00
Hussam.lawen	3673924fe9	Add docs editable blacklist of file extensions like sql, yaml...	2023-10-17 18:50:39 +03:00