Merge pull request #1172 from MaxHoecker/bugfix/bb-2-way-diff-fix

Bugfix/bb 2 way diff fix
docs: restructure Chrome extension documentation and add features and data privacy sections
2025-07-08 23:00:43 +08:00 · 2024-09-03 16:24:42 +03:00 · 2024-09-02 21:25:54 +03:00 · 2024-09-02 21:16:10 +03:00 · 2024-09-02 08:28:10 +03:00 · 2024-09-02 08:27:58 +03:00
114 changed files with 6058 additions and 1796 deletions
--- a/.github/workflows/build-and-test.yaml
+++ b/.github/workflows/build-and-test.yaml
@ -36,6 +36,6 @@ jobs:
      - id: test
        name: Test dev docker
        run: |
-          docker run --rm codiumai/pr-agent:test pytest -v
+          docker run --rm codiumai/pr-agent:test pytest -v tests/unittest
        
          
--- a/.github/workflows/code_coverage.yaml
+++ b/.github/workflows/code_coverage.yaml
@ -0,0 +1,54 @@
+name: Code-coverage
+
+on:
+  workflow_dispatch:
+  # push:
+  #   branches:
+  #     - main
+  pull_request:
+    branches:
+      - main
+
+jobs:
+  build-and-test:
+    runs-on: ubuntu-latest
+
+    steps:
+      - id: checkout
+        uses: actions/checkout@v2
+
+      - id: dockerx
+        name: Setup Docker Buildx
+        uses: docker/setup-buildx-action@v2
+
+      - id: build
+        name: Build dev docker
+        uses: docker/build-push-action@v2
+        with:
+          context: .
+          file: ./docker/Dockerfile
+          push: false
+          load: true
+          tags: codiumai/pr-agent:test
+          cache-from: type=gha,scope=dev
+          cache-to: type=gha,mode=max,scope=dev
+          target: test
+
+      - id: code_cov
+        name: Test dev docker
+        run: |
+          docker run --name test_container codiumai/pr-agent:test  pytest  tests/unittest --cov=pr_agent --cov-report term --cov-report xml:coverage.xml 
+          docker cp test_container:/app/coverage.xml coverage.xml
+          docker rm test_container
+
+
+      - name: Validate coverage report
+        run: |
+          if [ ! -f coverage.xml ]; then
+            echo "Coverage report not found"
+            exit 1
+          fi
+      - name: Upload coverage to Codecov
+        uses: codecov/codecov-action@v4.0.1
+        with:
+          token: ${{ secrets.CODECOV_TOKEN }}
--- a/.github/workflows/e2e_tests.yaml
+++ b/.github/workflows/e2e_tests.yaml
@ -0,0 +1,46 @@
+name: PR-Agent E2E tests
+
+on:
+  workflow_dispatch:
+#  schedule:
+#    - cron: '0 0 * * *' # This cron expression runs the workflow every night at midnight UTC
+
+jobs:
+  pr_agent_job:
+    runs-on: ubuntu-latest
+    name: PR-Agent E2E GitHub App Test
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v2
+
+      - name: Setup Docker Buildx
+        uses: docker/setup-buildx-action@v2
+
+      - id: build
+        name: Build dev docker
+        uses: docker/build-push-action@v2
+        with:
+          context: .
+          file: ./docker/Dockerfile
+          push: false
+          load: true
+          tags: codiumai/pr-agent:test
+          cache-from: type=gha,scope=dev
+          cache-to: type=gha,mode=max,scope=dev
+          target: test
+
+      - id: test1
+        name: E2E test github app
+        run: |
+           docker run -e GITHUB.USER_TOKEN=${{ secrets.TOKEN_GITHUB }} --rm codiumai/pr-agent:test pytest -v tests/e2e_tests/test_github_app.py
+
+      - id: test2
+        name: E2E gitlab webhook
+        run: |
+          docker run -e gitlab.PERSONAL_ACCESS_TOKEN=${{ secrets.TOKEN_GITLAB }} --rm codiumai/pr-agent:test pytest -v tests/e2e_tests/test_gitlab_webhook.py
+
+
+      - id: test3
+        name: E2E bitbucket app
+        run: |
+          docker run -e BITBUCKET.USERNAME=${{ secrets.BITBUCKET_USERNAME }}  -e BITBUCKET.PASSWORD=${{ secrets.BITBUCKET_PASSWORD }} --rm codiumai/pr-agent:test pytest -v tests/e2e_tests/test_bitbucket_app.py
--- a/.gitignore
+++ b/.gitignore
@ -1,4 +1,6 @@
 .idea/
+.lsp/
+.vscode/
 venv/
 pr_agent/settings/.secrets.toml
 __pycache__
--- a/.pr_agent.toml
+++ b/.pr_agent.toml
@ -2,6 +2,5 @@
 enable_review_labels_effort = true
 enable_auto_approval = true

-
-[pr_code_suggestions]
-summarize=true
+[config]
+model="claude-3-5-sonnet"
--- a/README.md
+++ b/README.md
@ -10,12 +10,15 @@

 </picture>
 <br/>
-CodiumAI PR-Agent aims to help efficiently review and handle pull requests, by providing AI feedbacks and suggestions
+CodiumAI PR-Agent aims to help efficiently review and handle pull requests, by providing AI feedback and suggestions
 </div>

 [![GitHub license](https://img.shields.io/badge/License-Apache_2.0-blue.svg)](https://github.com/Codium-ai/pr-agent/blob/main/LICENSE)
+[![Static Badge](https://img.shields.io/badge/Chrome-Extension-violet)](https://chromewebstore.google.com/detail/pr-agent-chrome-extension/ephlnjeghhogofkifjloamocljapahnl)
+[![Static Badge](https://img.shields.io/badge/Code-Benchmark-blue)](https://pr-agent-docs.codium.ai/finetuning_benchmark/)
 [![Discord](https://badgen.net/badge/icon/discord?icon=discord&label&color=purple)](https://discord.com/channels/1057273017547378788/1126104260430528613)
 [![Twitter](https://img.shields.io/twitter/follow/codiumai)](https://twitter.com/codiumai)
+[![Cheat Sheet](https://img.shields.io/badge/Cheat-Sheet-red)](https://www.codium.ai/images/pr_agent/cheat_sheet.pdf)
    <a href="https://github.com/Codium-ai/pr-agent/commits/main">
    <img alt="GitHub" src="https://img.shields.io/github/last-commit/Codium-ai/pr-agent/main?style=for-the-badge" height="20">
    </a>
@ -34,43 +37,37 @@ CodiumAI PR-Agent aims to help efficiently review and handle pull requests, by p
 - [Overview](#overview)
 - [Example results](#example-results)
 - [Try it now](#try-it-now)
- [PR-Agent Pro 💎](#pr-agent-pro-)
+- [PR-Agent Pro 💎](https://pr-agent-docs.codium.ai/overview/pr_agent_pro/)
 - [How it works](#how-it-works)
 - [Why use PR-Agent?](#why-use-pr-agent)
  
 ## News and Updates

-### April 14, 2024
-You can now ask questions about images that appear in the comment, where the entire PR is considered as the context.
-see [here](https://pr-agent-docs.codium.ai/tools/ask/#ask-on-images) for more details.
+### August 26, 2024

-<kbd><img src="https://codium.ai/images/pr_agent/ask_images5.png" width="512"></kbd>
+New version of [PR Agent Chrom Extension](https://chromewebstore.google.com/detail/pr-agent-chrome-extension/ephlnjeghhogofkifjloamocljapahnl) was released, with full support of context-aware **PR Chat**. This novel feature is free to use for any open-source repository. See more details in [here](https://pr-agent-docs.codium.ai/chrome-extension/#pr-chat).

-### March 24, 2024
-PR-Agent is now available for easy installation via [pip](https://pr-agent-docs.codium.ai/installation/locally/#using-pip-package).
+<kbd><img src="https://www.codium.ai/images/pr_agent/pr_chat_1.png" width="768"></kbd>

-### March 17, 2024
- A new feature is now available for the review tool: [`require_can_be_split_review`](https://pr-agent-docs.codium.ai/tools/review/#enabledisable-features). 
-If set to true, the tool will add a section that checks if the PR contains several themes, and can be split into smaller PRs.
+<kbd><img src="https://www.codium.ai/images/pr_agent/pr_chat_2.png" width="768"></kbd>

-<kbd><img src="https://codium.ai/images/pr_agent/multiple_pr_themes.png" width="512"></kbd>

-### March 10, 2024
- A new [knowledge-base website](https://pr-agent-docs.codium.ai/) for PR-Agent is now available. It includes detailed information about the different tools, usage guides and more, in an accessible and organized format.
+### August 11, 2024
+Increased PR context size for improved results, and enabled [asymmetric context](https://github.com/Codium-ai/pr-agent/pull/1114/files#diff-9290a3ad9a86690b31f0450b77acd37ef1914b41fabc8a08682d4da433a77f90R69-R70)

-### March 8, 2024
+### August 10, 2024
+Added support for [Azure devops pipeline](https://pr-agent-docs.codium.ai/installation/azure/) - you can now easily run PR-Agent as an Azure devops pipeline, without needing to set up your own server.

- A new tool, [Find Similar Code](https://pr-agent-docs.codium.ai/tools/similar_code/) 💎 is now available. 
-<br>This tool retrieves the most similar code components from inside the organization's codebase, or from open-source code:

-<kbd><a href="https://codium.ai/images/pr_agent/similar_code.mp4"><img src="https://codium.ai/images/pr_agent/similar_code_global2.png" width="512"></a></kbd>
+### August 5, 2024
+Added support for [GitLab pipeline](https://pr-agent-docs.codium.ai/installation/gitlab/#run-as-a-gitlab-pipeline) - you can now run easily PR-Agent as a GitLab pipeline, without needing to set up your own server.

-(click on the image to see an instructional video)
+### July 28, 2024

-### Feb 29, 2024
- You can now use the repo's [wiki page](https://pr-agent-docs.codium.ai/usage-guide/configuration_options/) to set configurations for PR-Agent 💎
+(1) improved support for bitbucket server - [auto commands](https://github.com/Codium-ai/pr-agent/pull/1059) and [direct links](https://github.com/Codium-ai/pr-agent/pull/1061)
+
+(2) custom models are now [supported](https://pr-agent-docs.codium.ai/usage-guide/changing_a_model/#custom-models)

-<kbd><img src="https://codium.ai/images/pr_agent/wiki_configuration.png" width="512"></kbd>


 ## Overview
@ -79,39 +76,39 @@ If set to true, the tool will add a section that checks if the PR contains sever
 Supported commands per platform:

 |       |                                                                                                         | GitHub             | Gitlab             | Bitbucket          | Azure DevOps |
-|-------|-------------------------------------------------------------------------------------------------------------------|:--------------------:|:--------------------:|:--------------------:|:--------------------:|
+|-------|---------------------------------------------------------------------------------------------------------|:--------------------:|:--------------------:|:--------------------:|:------------:|
 | TOOLS | Review                                                                                                  | ✅ | ✅ | ✅ |      ✅       |
 |       | ⮑ Incremental                                                                                           | ✅ |                    |                    |              |
-|       | ⮑ [SOC2 Compliance](https://pr-agent-docs.codium.ai/tools/review/#soc2-ticket-compliance) 💎            | ✅ | ✅ | ✅ | ✅ |
+|       | ⮑ [SOC2 Compliance](https://pr-agent-docs.codium.ai/tools/review/#soc2-ticket-compliance) 💎            | ✅ | ✅ | ✅ |              |
 |       | Describe                                                                                                | ✅ | ✅ | ✅ |      ✅       |
 |       | ⮑ [Inline File Summary](https://pr-agent-docs.codium.ai/tools/describe#inline-file-summary) 💎          | ✅ |                    |                    |              |
 |       | Improve                                                                                                 | ✅ | ✅ | ✅ |      ✅       |
 |       | ⮑ Extended                                                                                              | ✅ | ✅ | ✅ |      ✅       |
 |       | Ask                                                                                                     | ✅ | ✅ | ✅ |      ✅       |
 |       | ⮑ [Ask on code lines](https://pr-agent-docs.codium.ai/tools/ask#ask-lines)                              | ✅ | ✅ |                    |              |
-|       | [Custom Suggestions](https://pr-agent-docs.codium.ai/tools/custom_suggestions/) 💎                      | ✅ | ✅ | ✅ | ✅ |
-|       | [Test](https://pr-agent-docs.codium.ai/tools/test/) 💎                                                  | ✅ | ✅ |                    | ✅ |
+|       | [Custom Prompt](https://pr-agent-docs.codium.ai/tools/custom_prompt/) 💎                                | ✅ | ✅ | ✅ |              |
+|       | [Test](https://pr-agent-docs.codium.ai/tools/test/) 💎                                                  | ✅ | ✅ |                    |              |
 |       | Reflect and Review                                                                                      | ✅ | ✅ | ✅ |      ✅       |
 |       | Update CHANGELOG.md                                                                                     | ✅ | ✅ | ✅ |      ✅       |
 |       | Find Similar Issue                                                                                      | ✅ |                    |                    |              |
-|       | [Add PR Documentation](https://pr-agent-docs.codium.ai/tools/documentation/) 💎                         | ✅ | ✅ |                   | ✅ |
-|       | [Custom Labels](https://pr-agent-docs.codium.ai/tools/custom_labels/) 💎                                | ✅ | ✅ |                    | ✅ |
-|       | [Analyze](https://pr-agent-docs.codium.ai/tools/analyze/) 💎                                            | ✅ | ✅ |                    | ✅ |
+|       | [Add PR Documentation](https://pr-agent-docs.codium.ai/tools/documentation/) 💎                         | ✅ | ✅ |                   |              |
+|       | [Custom Labels](https://pr-agent-docs.codium.ai/tools/custom_labels/) 💎                                | ✅ | ✅ |                    |              |
+|       | [Analyze](https://pr-agent-docs.codium.ai/tools/analyze/) 💎                                            | ✅ | ✅ |                    |              |
 |       | [CI Feedback](https://pr-agent-docs.codium.ai/tools/ci_feedback/) 💎                                    | ✅ |                    |                    |              |
 |       | [Similar Code](https://pr-agent-docs.codium.ai/tools/similar_code/) 💎                                  | ✅ |                    |                    |              |
 |       |                                                                                                         |                    |                    |                    |              |
 | USAGE | CLI                                                                                                     | ✅ | ✅ | ✅ |      ✅       |
 |       | App / webhook                                                                                           | ✅ | ✅ | ✅ |      ✅       |
 |       | Tagging bot                                                                                             | ✅ |                    |                    |              |
-|       | Actions                                                                                                           | ✅ |                    | ✅ |                    |
+|       | Actions                                                                                                 | ✅ |✅| ✅ |✅|
 |       |                                                                                                         |                    |                    |                    |              |
 | CORE  | PR compression                                                                                          | ✅ | ✅ | ✅ |      ✅       |
 |       | Repo language prioritization                                                                            | ✅ | ✅ | ✅ |      ✅       |
 |       | Adaptive and token-aware file patch fitting                                                             | ✅ | ✅ | ✅ |      ✅       |
 |       | Multiple models support                                                                                 | ✅ | ✅ | ✅ |      ✅       |
-|       | [Static code analysis](https://pr-agent-docs.codium.ai/core-abilities/#static-code-analysis) 💎         | ✅ | ✅ | ✅ | ✅ |
-|       | [Global and wiki configurations](https://pr-agent-docs.codium.ai/usage-guide/configuration_options/) 💎 | ✅ | ✅ | ✅ | ✅ |
-|       | [PR interactive actions](https://www.codium.ai/images/pr_agent/pr-actions.mp4) 💎                                 | ✅ |                    |                    |                    |
+|       | [Static code analysis](https://pr-agent-docs.codium.ai/core-abilities/#static-code-analysis) 💎         | ✅ | ✅ | ✅ |              |
+|       | [Global and wiki configurations](https://pr-agent-docs.codium.ai/usage-guide/configuration_options/) 💎 | ✅ | ✅ | ✅ |              |
+|       | [PR interactive actions](https://www.codium.ai/images/pr_agent/pr-actions.mp4) 💎                       | ✅ |        ✅           |                    |              |
 - 💎 means this feature is available only in [PR-Agent Pro](https://www.codium.ai/pricing/)

 [//]: # (- Support for additional git providers is described in [here]&#40;./docs/Full_environments.md&#41;)
@ -135,7 +132,7 @@ ___
 \
 ‣ **Analyze 💎 ([`/analyze`](https://pr-agent-docs.codium.ai/tools/analyze/))**: Identify code components that changed in the PR, and enables to interactively generate tests, docs, and code suggestions for each component.
 \
-‣ **Custom Suggestions 💎 ([`/custom_suggestions`](https://pr-agent-docs.codium.ai/tools/custom_suggestions/))**: Automatically generates custom suggestions for improving the PR code, based on specific guidelines defined by the user.
+‣ **Custom Prompt 💎 ([`/custom_prompt`](https://pr-agent-docs.codium.ai/tools/custom_prompt/))**: Automatically generates custom suggestions for improving the PR code, based on specific guidelines defined by the user.
 \
 ‣ **Generate Tests 💎 ([`/test component_name`](https://pr-agent-docs.codium.ai/tools/test/))**: Generates unit tests for a selected component, based on the PR code changes.
 \
@ -230,7 +227,11 @@ For example, add a comment to any pull request with the following text:
 ```
@CodiumAI-Agent /review
 ```
-and the agent will respond with a review of your PR
+and the agent will respond with a review of your PR.
+
+Note that this is a promotional bot, suitable only for initial experimentation.
+It does not have 'edit' access to your repo, for example, so it cannot update the PR description or add labels (`@CodiumAI-Agent /describe` will publish PR description as a comment). In addition, the bot cannot be used on private repositories, as it does not have access to the files there.
+

 ![Review generation process](https://www.codium.ai/images/demo-2.gif)

@ -240,43 +241,6 @@ Note that when you set your own PR-Agent or use CodiumAI hosted PR-Agent, there

 ---

-[//]: # (## Installation)
-
-[//]: # (To use your own version of PR-Agent, you first need to acquire two tokens:)
-
-[//]: # ()
-[//]: # (1. An OpenAI key from [here]&#40;https://platform.openai.com/&#41;, with access to GPT-4.)
-
-[//]: # (2. A GitHub personal access token &#40;classic&#41; with the repo scope.)
-
-[//]: # ()
-[//]: # (There are several ways to use PR-Agent:)
-
-[//]: # ()
-[//]: # (**Locally**)
-
-[//]: # (- [Using pip package]&#40;https://pr-agent-docs.codium.ai/installation/locally/#using-pip-package&#41;)
-
-[//]: # (- [Using Docker image]&#40;https://pr-agent-docs.codium.ai/installation/locally/#using-docker-image&#41;)
-
-[//]: # (- [Run from source]&#40;https://pr-agent-docs.codium.ai/installation/locally/#run-from-source&#41;)
-
-[//]: # ()
-[//]: # (**GitHub specific methods**)
-
-[//]: # (- [Run as a GitHub Action]&#40;https://pr-agent-docs.codium.ai/installation/github/#run-as-a-github-action&#41;)
-
-[//]: # (- [Run as a GitHub App]&#40;https://pr-agent-docs.codium.ai/installation/github/#run-as-a-github-app&#41;)
-
-[//]: # ()
-[//]: # (**GitLab specific methods**)
-
-[//]: # (- [Run a GitLab webhook server]&#40;https://pr-agent-docs.codium.ai/installation/gitlab/&#41;)
-
-[//]: # ()
-[//]: # (**BitBucket specific methods**)
-
-[//]: # (- [Run as a Bitbucket Pipeline]&#40;https://pr-agent-docs.codium.ai/installation/bitbucket/&#41;)

 ## PR-Agent Pro 💎
 [PR-Agent Pro](https://www.codium.ai/pricing/) is a hosted version of PR-Agent, provided by CodiumAI. It is available for a monthly fee, and provides the following benefits:
@ -310,11 +274,22 @@ Here are some advantages of PR-Agent:

 ## Data privacy

-If you host PR-Agent with your OpenAI API key, it is between you and OpenAI. You can read their API data privacy policy here:
+### Self-hosted PR-Agent
+
+- If you host PR-Agent with your OpenAI API key, it is between you and OpenAI. You can read their API data privacy policy here:
 https://openai.com/enterprise-privacy

-When using PR-Agent Pro 💎, hosted by CodiumAI, we will not store any of your data, nor will we use it for training.
-You will also benefit from an OpenAI account with zero data retention.
+### CodiumAI-hosted PR-Agent Pro 💎
+
+- When using PR-Agent Pro 💎, hosted by CodiumAI, we will not store any of your data, nor will we use it for training. You will also benefit from an OpenAI account with zero data retention.
+
+- For certain clients, CodiumAI-hosted PR-Agent Pro will use CodiumAI’s proprietary models — if this is the case, you will be notified.
+
+- No passive collection of Code and Pull Requests’ data — PR-Agent will be active only when you invoke it, and it will then extract and analyze only data relevant to the executed command and queried pull request.
+
+### PR-Agent Chrome extension
+
+- The [PR-Agent Chrome extension](https://chromewebstore.google.com/detail/pr-agent-chrome-extension/ephlnjeghhogofkifjloamocljapahnl) serves solely to modify the visual appearance of a GitHub PR screen. It does not transmit any user's repo or pull request code. Code is only sent for processing when a user submits a GitHub comment that activates a PR-Agent tool, in accordance with the standard privacy policy of PR-Agent.

 ## Links

--- a/codecov.yml
+++ b/codecov.yml
@ -0,0 +1,5 @@
+comment: false
+coverage:
+  status:
+    patch: false
+    project: false
--- a/docker/Dockerfile
+++ b/docker/Dockerfile
@ -1,4 +1,4 @@
-FROM python:3.10 as base
+FROM python:3.12.3 AS base

 WORKDIR /app
 ADD pyproject.toml .
@ -6,36 +6,36 @@ ADD requirements.txt .
 RUN pip install . && rm pyproject.toml requirements.txt
 ENV PYTHONPATH=/app

-FROM base as github_app
+FROM base AS github_app
 ADD pr_agent pr_agent
-CMD ["python", "pr_agent/servers/github_app.py"]
+CMD ["python", "-m", "gunicorn", "-k", "uvicorn.workers.UvicornWorker", "-c", "pr_agent/servers/gunicorn_config.py", "--forwarded-allow-ips", "*", "pr_agent.servers.github_app:app"]

-FROM base as bitbucket_app
+FROM base AS bitbucket_app
 ADD pr_agent pr_agent
 CMD ["python", "pr_agent/servers/bitbucket_app.py"]

-FROM base as bitbucket_server_webhook
+FROM base AS bitbucket_server_webhook
 ADD pr_agent pr_agent
 CMD ["python", "pr_agent/servers/bitbucket_server_webhook.py"]

-FROM base as github_polling
+FROM base AS github_polling
 ADD pr_agent pr_agent
 CMD ["python", "pr_agent/servers/github_polling.py"]

-FROM base as gitlab_webhook
+FROM base AS gitlab_webhook
 ADD pr_agent pr_agent
 CMD ["python", "pr_agent/servers/gitlab_webhook.py"]

-FROM base as azure_devops_webhook
+FROM base AS azure_devops_webhook
 ADD pr_agent pr_agent
 CMD ["python", "pr_agent/servers/azuredevops_server_webhook.py"]

-FROM base as test
+FROM base AS test
 ADD requirements-dev.txt .
 RUN pip install -r requirements-dev.txt && rm requirements-dev.txt
 ADD pr_agent pr_agent
 ADD tests tests

-FROM base as cli
+FROM base AS cli
 ADD pr_agent pr_agent
 ENTRYPOINT ["python", "pr_agent/cli.py"]
--- a/docs/docs/chrome-extension/data_privacy.md
+++ b/docs/docs/chrome-extension/data_privacy.md
@ -0,0 +1,5 @@
+We take your code's security and privacy seriously:
+
+- The Chrome extension will not send your code to any external servers.
+- For private repositories, we will first validate the user's identity and permissions. After authentication, we generate responses using the existing PR-Agent Pro integration.
+
--- a/docs/docs/chrome-extension/features.md
+++ b/docs/docs/chrome-extension/features.md
@ -0,0 +1,47 @@
+
+### PR Chat
+
+The PR-Chat feature allows to freely chat with your PR code, within your GitHub environment.
+It will seamlessly add the PR code as context to your chat session, and provide AI-powered feedback.
+
+To enable private chat, simply install the PR-Agent Chrome extension. After installation, each PR's file-changed tab will include a chat box, where you may ask questions about your code.
+This chat session is **private**, and won't be visible to other users.
+
+All open-source repositories are supported.
+For private repositories, you will also need to install PR-Agent Pro, After installation, make sure to open at least one new PR to fully register your organization. Once done, you can chat with both new and existing PRs across all installed repositories.
+
+<img src="https://codium.ai/images/pr_agent/pr_chat1.png" width="768">
+<img src="https://codium.ai/images/pr_agent/pr_chat2.png" width="768">
+
+
+### Toolbar extension
+With PR-Agent Chrome extension, it's [easier than ever](https://www.youtube.com/watch?v=gT5tli7X4H4) to interactively configure and experiment with the different tools and configuration options.
+
+For private repositories, after you found the setup that works for you, you can also easily export it as a persistent configuration file, and use it for automatic commands.
+
+<img src="https://codium.ai/images/pr_agent/toolbar1.png" width="512">
+
+<img src="https://codium.ai/images/pr_agent/toolbar2.png" width="512">
+
+### PR-Agent filters
+
+PR-Agent filters is a sidepanel option. that allows you to filter different message in the conversation tab.
+
+For example, you can choose to present only message from PR-Agent, or filter those messages, focusing only on user's comments.
+
+<img src="https://codium.ai/images/pr_agent/pr_agent_filters1.png" width="256">
+
+<img src="https://codium.ai/images/pr_agent/pr_agent_filters2.png" width="256">
+
+
+### Enhanced code suggestions
+
+PR-Agent Chrome extension adds the following capabilities to code suggestions tool's comments:
+
+- Auto-expand the table when you are viewing a code block, to avoid clipping.
+- Adding a "quote-and-reply" button, that enables to address and comment on a specific suggestion (for example, asking the author to fix the issue)
+
+
+<img src="https://codium.ai/images/pr_agent/chrome_extension_code_suggestion1.png" width="512">
+
+<img src="https://codium.ai/images/pr_agent/chrome_extension_code_suggestion2.png" width="512">
--- a/docs/docs/chrome-extension/index.md
+++ b/docs/docs/chrome-extension/index.md
@ -0,0 +1,8 @@
+[PR-Agent Chrome extension](https://chromewebstore.google.com/detail/pr-agent-chrome-extension/ephlnjeghhogofkifjloamocljapahnl) is a collection of tools that integrates seamlessly with your GitHub environment, aiming to enhance your Git usage experience, and providing AI-powered capabilities to your PRs.
+
+With a single-click installation you will gain access to a context-aware PR chat with top models, a toolbar extension with multiple AI feedbacks, PR-Agent filters, and additional abilities.
+
+All the extension's features are free to use on public repositories. For private repositories, you will need to install in addition to the extension [PR-Agent Pro](https://github.com/apps/codiumai-pr-agent-pro)  (fast and easy installation with two weeks of trial, no credit card required).
+
+<img src="https://codium.ai/images/pr_agent/pr_chat1.png" width="768">
+<img src="https://codium.ai/images/pr_agent/pr_chat2.png" width="768">
--- a/docs/docs/css/custom.css
+++ b/docs/docs/css/custom.css
@ -4,12 +4,34 @@
    --md-primary-fg-color: #765bfa;
    --md-accent-fg-color: #AEA1F1;
  }
-.md-nav__title, .md-nav__link  {
-    font-size: 16px; 
+
+.md-nav--primary {
+    .md-nav__link {
+    font-size: 18px; /* Change the font size as per your preference */
+    }
 }

+.md-nav--primary {
+    position: relative; /* Ensure the element is positioned */
+}
+
+.md-nav--primary::before {
+    content: "";
+    position: absolute;
+    top: 0;
+    right: 10px; /* Move the border 10 pixels to the right */
+    width: 2px;
+    height: 100%;
+    background-color: #f5f5f5; /* Match the border color */
+}
+/*.md-nav__title, .md-nav__link  {*/
+/*    font-size: 18px;*/
+/*    margin-top: 14px; !* Adjust the space as needed *!*/
+/*    margin-bottom: 14px; !* Adjust the space as needed *!*/
+/*}*/
+
 .md-tabs__link  {
-    font-size: 16px; 
+    font-size: 18px;
 }

 .md-header__title {
--- a/docs/docs/finetuning_benchmark/index.md
+++ b/docs/docs/finetuning_benchmark/index.md
@ -0,0 +1,93 @@
+# PR-Agent Code Fine-tuning Benchmark
+
+On coding tasks, the gap between open-source models and top closed-source models such as GPT4 is significant.
+<br>
+In practice, open-source models are unsuitable for most real-world code tasks, and require further fine-tuning to produce acceptable results.
+
+_PR-Agent fine-tuning benchmark_ aims to benchmark open-source models on their ability to be fine-tuned for a coding task.
+Specifically, we chose to fine-tune open-source models on the task of analyzing a pull request, and providing useful feedback and code suggestions.
+
+Here are the results:
+<br>
+<br>
+
+**Model performance:**
+
+| Model name                  | Model size [B] | Better than gpt-4 rate, after fine-tuning [%] |
+|-----------------------------|----------------|----------------------------------------------|
+| **DeepSeek 34B-instruct**   | **34**         | **40.7**                                     |
+| DeepSeek 34B-base           | 34             | 38.2                                         |
+| Phind-34b                   | 34             | 38                                           |
+| Granite-34B                 | 34             | 37.6                                         |
+| Codestral-22B-v0.1          | 22             | 32.7                                         |
+| QWEN-1.5-32B                | 32             | 29                                           |
+|                             |                |                                              |
+| **CodeQwen1.5-7B**          | **7**          | **35.4**                                     |
+| Llama-3.1-8B-Instruct       | 8              | 35.2                                         |
+| Granite-8b-code-instruct    | 8              | 34.2                                         |
+| CodeLlama-7b-hf             | 7              | 31.8                                         |
+| Gemma-7B                    | 7              | 27.2                                         |
+| DeepSeek coder-7b-instruct  | 7              | 26.8                                         |
+| Llama-3-8B-Instruct         | 8              | 26.8                                         |
+| Mistral-7B-v0.1             | 7              | 16.1                                         |
+
+<br>
+
+**Fine-tuning impact:**
+
+| Model name                | Model size [B] | Fine-tuned | Better than gpt-4 rate [%] |
+|---------------------------|----------------|------------|----------------------------|
+| DeepSeek 34B-instruct     | 34             | yes        | 40.7                       |
+| DeepSeek 34B-instruct     | 34             | no         | 3.6                        |
+
+## Results analysis
+
+- **Fine-tuning is a must** - without fine-tuning, open-source models provide poor results on most real-world code tasks, which include complicated prompt and lengthy context. We clearly see that without fine-tuning, deepseek model was 96.4% of the time inferior to GPT-4, while after fine-tuning, it is better 40.7% of the time.
+- **Always start from a code-dedicated model** — When fine-tuning, always start from a code-dedicated model, and not from a general-usage model. The gaps in downstream results are very big.
+- **Don't believe the hype** —newer models, or models from big-tech companies (Llama3, Gemma, Mistral), are not always better for fine-tuning.
+- **The best large model** - For large 34B code-dedicated models, the gaps when doing proper fine-tuning are small. The current top model is **DeepSeek 34B-instruct**
+- **The best small model** - For small 7B code-dedicated models, the gaps when fine-tuning are much larger. **CodeQWEN 1.5-7B** is by far the best model for fine-tuning.
+- **Base vs. instruct** - For the top model (deepseek), we saw small advantage when starting from the instruct version. However, we recommend testing both versions on each specific task, as the base model is generally considered more suitable for fine-tuning.
+
+## The dataset
+
+### Training dataset
+
+Our training dataset comprises 25,000 pull requests, aggregated from permissive license repos. For each pull request, we generated responses for the three main tools of PR-Agent:
+[Describe](https://pr-agent-docs.codium.ai/tools/describe/), [Review](https://pr-agent-docs.codium.ai/tools/improve/) and [Improve](https://pr-agent-docs.codium.ai/tools/improve/).
+
+On the raw data collected, we employed various automatic and manual cleaning techniques to ensure the outputs were of the highest quality, and suitable for instruct-tuning.
+
+Here are the prompts, and example outputs, used as input-output pairs to fine-tune the models:
+
+| Tool     | Prompt                                                                                                     | Example output |
+|----------|------------------------------------------------------------------------------------------------------------|----------------|
+| Describe | [link](https://github.com/Codium-ai/pr-agent/blob/main/pr_agent/settings/pr_description_prompts.toml) | [link](https://github.com/Codium-ai/pr-agent/pull/910#issue-2303989601)           |
+| Review   | [link](https://github.com/Codium-ai/pr-agent/blob/main/pr_agent/settings/pr_reviewer_prompts.toml) | [link](https://github.com/Codium-ai/pr-agent/pull/910#issuecomment-2118761219)           |
+| Improve  | [link](https://github.com/Codium-ai/pr-agent/blob/main/pr_agent/settings/pr_code_suggestions_prompts.toml) | [link](https://github.com/Codium-ai/pr-agent/pull/910#issuecomment-2118761309)           |
+
+### Evaluation dataset
+
+- For each tool, we aggregated 100 additional examples to be used for evaluation. These examples were not used in the training dataset, and were manually selected to represent diverse real-world use-cases.
+- For each test example, we generated two responses: one from the fine-tuned model, and one from the best code model in the world, `gpt-4-turbo-2024-04-09`.
+
+- We used a third LLM to judge which response better answers the prompt, and will likely be perceived by a human as better response.
+<br>
+
+We experimented with three model as judges: `gpt-4-turbo-2024-04-09`, `gpt-4o`, and `claude-3-opus-20240229`. All three produced similar results, with the same ranking order. This strengthens the validity of our testing protocol.
+The evaluation prompt can be found [here](https://github.com/Codium-ai/pr-agent/blob/main/pr_agent/settings/pr_evaluate_prompt_response.toml)
+
+Here is an example of a judge model feedback:
+
+```
+command: improve
+model1_score: 9,
+model2_score: 6,
+why: |
+  Response 1 is better because it provides more actionable and specific suggestions that directly 
+  enhance the code's maintainability, performance, and best practices. For example, it suggests 
+  using a variable for reusable widget instances and using named routes for navigation, which 
+  are practical improvements. In contrast, Response 2 focuses more on general advice and less 
+  actionable suggestions, such as changing variable names and adding comments, which are less 
+  critical for immediate code improvement."
+```
--- a/docs/docs/index.md
+++ b/docs/docs/index.md
@ -13,22 +13,22 @@ CodiumAI PR-Agent is an open-source tool to help efficiently review and handle p
 PR-Agent offers extensive pull request functionalities across various git providers.

 |       |                                                                                                                       | GitHub | Gitlab | Bitbucket | Azure DevOps |
-|-------|---------------------------------------------------------------------------------------------------------------------|:------:|:------:|:---------:|:------------:|
+|-------|-----------------------------------------------------------------------------------------------------------------------|:------:|:------:|:---------:|:------------:|
 | TOOLS | Review                                                                                                                |   ✅    |   ✅    |   ✅       |      ✅       |
 |       | ⮑ Incremental                                                                                                         |   ✅    |        |            |              |
-|       | ⮑ [SOC2 Compliance](https://pr-agent-docs.codium.ai/tools/review/#soc2-ticket-compliance){:target="_blank"} 💎                                     |   ✅    |   ✅    |   ✅        |      ✅      |
+|       | ⮑ [SOC2 Compliance](https://pr-agent-docs.codium.ai/tools/review/#soc2-ticket-compliance){:target="_blank"} 💎        |   ✅    |   ✅    |   ✅        |              |
 |       | Ask                                                                                                                   |   ✅    |   ✅    |   ✅        |      ✅       |
 |       | Describe                                                                                                              |   ✅    |   ✅    |   ✅        |      ✅       |
-|       | ⮑ [Inline file summary](https://pr-agent-docs.codium.ai/tools/describe/#inline-file-summary){:target="_blank"} 💎                                 |   ✅    |   ✅    |           |      ✅      |
+|       | ⮑ [Inline file summary](https://pr-agent-docs.codium.ai/tools/describe/#inline-file-summary){:target="_blank"} 💎     |   ✅    |   ✅    |           |              |
 |       | Improve                                                                                                               |   ✅    |   ✅    |   ✅        |      ✅       |
 |       | ⮑ Extended                                                                                                            |   ✅    |   ✅    |   ✅        |      ✅       |
-|       | [Custom Suggestions](./tools/custom_suggestions.md){:target="_blank"} 💎                                               |   ✅    |   ✅    |   ✅        |      ✅      |
-|       | Reflect and Review                                                                                                  |   ✅    |   ✅    |   ✅        |      ✅      |
+|       | [Custom Prompt](./tools/custom_prompt.md){:target="_blank"} 💎                                                        |   ✅    |   ✅    |   ✅        |              |
+|       | Reflect and Review                                                                                                    |   ✅    |   ✅    |   ✅        |              |
 |       | Update CHANGELOG.md                                                                                                   |   ✅    |   ✅    |   ✅        |      ️       |
 |       | Find Similar Issue                                                                                                    |   ✅    |        |             |      ️       |
-|       | [Add PR Documentation](./tools/documentation.md){:target="_blank"} 💎                                                  |   ✅    |   ✅    |          |      ✅      |
-|       | [Generate Custom Labels](./tools/describe.md#handle-custom-labels-from-the-repos-labels-page-💎){:target="_blank"} 💎 |   ✅    |   ✅    |            |      ✅      |
-|       | [Analyze PR Components](./tools/analyze.md){:target="_blank"} 💎                                                       |   ✅    |   ✅    |       |      ✅      |
+|       | [Add PR Documentation](./tools/documentation.md){:target="_blank"} 💎                                                 |   ✅    |   ✅    |          |              |
+|       | [Generate Custom Labels](./tools/describe.md#handle-custom-labels-from-the-repos-labels-page-💎){:target="_blank"} 💎 |   ✅    |   ✅    |            |              |
+|       | [Analyze PR Components](./tools/analyze.md){:target="_blank"} 💎                                                      |   ✅    |   ✅    |       |              |
 |       |                                                                                                                       |        |        |            |      ️       |
 | USAGE | CLI                                                                                                                   |   ✅    |   ✅    |   ✅       |      ✅       |
 |       | App / webhook                                                                                                         |   ✅    |   ✅    |    ✅        |      ✅       |
@ -39,8 +39,8 @@ PR-Agent offers extensive pull request functionalities across various git provid
 |       | Adaptive and token-aware file patch fitting                                                                           |   ✅    |   ✅    |   ✅     |      ✅       |
 |       | Multiple models support                                                                                               |   ✅    |   ✅    |   ✅       |      ✅       |
 |       | Incremental PR review                                                                                                 |   ✅    |        |            |              |
-|       | [Static code analysis](./tools/analyze.md/){:target="_blank"} 💎                                                        |   ✅    |   ✅     |    ✅    |   ✅        |
-|       | [Multiple configuration options](./usage-guide/configuration_options.md){:target="_blank"} 💎                           |   ✅    |   ✅     |    ✅    |   ✅        |
+|       | [Static code analysis](./tools/analyze.md/){:target="_blank"} 💎                                                      |   ✅    |   ✅     |    ✅    |              |
+|       | [Multiple configuration options](./usage-guide/configuration_options.md){:target="_blank"} 💎                         |   ✅    |   ✅     |    ✅    |              |

 💎 marks a feature available only in [PR-Agent Pro](https://www.codium.ai/pricing/){:target="_blank"}

@ -79,35 +79,3 @@ The following diagram illustrates PR-Agent tools and their flow:
 ![PR-Agent Tools](https://codium.ai/images/pr_agent/diagram-v0.9.png)

 Check out the [PR Compression strategy](core-abilities/index.md) page for more details on how we convert a code diff to a manageable LLM prompt
-
-
-
-## PR-Agent Pro 💎
-
-[PR-Agent Pro](https://www.codium.ai/pricing/) is a hosted version of PR-Agent, provided by CodiumAI. It is available for a monthly fee, and provides the following benefits:
-
-1. **Fully managed** - We take care of everything for you - hosting, models, regular updates, and more. Installation is as simple as signing up and adding the PR-Agent app to your GitHub\GitLab\BitBucket repo.
-2. **Improved privacy** - No data will be stored or used to train models. PR-Agent Pro will employ zero data retention, and will use an OpenAI account with zero data retention.
-3. **Improved support** - PR-Agent Pro users will receive priority support, and will be able to request new features and capabilities.
-4. **Extra features** -In addition to the benefits listed above, PR-Agent Pro will emphasize more customization, and the usage of static code analysis, in addition to LLM logic, to improve results. It has the following additional tools and features:
-    - (Tool): [**Analyze PR components**](./tools/analyze.md/)
-    - (Tool): [**Custom Code Suggestions**](./tools/custom_suggestions.md/)
-    - (Tool): [**Tests**](./tools/test.md/)
-    - (Tool): [**PR documentation**](./tools/documentation.md/)
-    - (Tool): [**Improve Component**](https://pr-agent-docs.codium.ai/tools/improve_component/)
-    - (Tool): [**Similar code search**](https://pr-agent-docs.codium.ai/tools/similar_code/)
-    - (Tool): [**CI feedback**](./tools/ci_feedback.md/)
-    - (Feature): [**Interactive triggering**](./usage-guide/automations_and_usage.md/#interactive-triggering)
-    - (Feature): [**SOC2 compliance check**](./tools/review.md/#soc2-ticket-compliance)
-    - (Feature): [**Custom labels**](./tools/describe.md/#handle-custom-labels-from-the-repos-labels-page)
-    - (Feature): [**Global and wiki configuration**](./usage-guide/configuration_options.md/#wiki-configuration-file)
-    - (Feature): [**Inline file summary**](https://pr-agent-docs.codium.ai/tools/describe/#inline-file-summary)
-
-   
-## Data Privacy
-
-If you host PR-Agent with your OpenAI API key, it is between you and OpenAI. You can read their API data privacy policy here:
-https://openai.com/enterprise-privacy
-
-When using PR-Agent Pro 💎, hosted by CodiumAI, we will not store any of your data, nor will we use it for training.
-You will also benefit from an OpenAI account with zero data retention.
--- a/docs/docs/installation/azure.md
+++ b/docs/docs/installation/azure.md
@ -1,4 +1,62 @@
-## Azure DevOps provider
+## Azure DevOps Pipeline
+You can use a pre-built Action Docker image to run PR-Agent as an Azure devops pipeline.
+add the following file to your repository under `azure-pipelines.yml`:
+```yaml
+# Opt out of CI triggers
+trigger: none
+
+# Configure PR trigger
+pr:
+  branches:
+    include:
+    - '*'
+  autoCancel: true
+  drafts: false
+
+stages:
+- stage: pr_agent
+  displayName: 'PR Agent Stage'
+  jobs:
+  - job: pr_agent_job
+    displayName: 'PR Agent Job'
+    pool:
+      vmImage: 'ubuntu-latest'
+    container:
+      image: codiumai/pr-agent:latest
+      options: --entrypoint ""
+    variables:
+      - group: pr_agent
+    steps:
+    - script: |
+        echo "Running PR Agent action step"
+
+        # Construct PR_URL
+        PR_URL="${SYSTEM_COLLECTIONURI}${SYSTEM_TEAMPROJECT}/_git/${BUILD_REPOSITORY_NAME}/pullrequest/${SYSTEM_PULLREQUEST_PULLREQUESTID}"
+        echo "PR_URL=$PR_URL"
+
+        # Extract organization URL from System.CollectionUri
+        ORG_URL=$(echo "$(System.CollectionUri)" | sed 's/\/$//') # Remove trailing slash if present
+        echo "Organization URL: $ORG_URL"
+
+        export azure_devops__org="$ORG_URL"
+        export config__git_provider="azure"
+        
+        pr-agent --pr_url="$PR_URL" describe
+        pr-agent --pr_url="$PR_URL" review
+        pr-agent --pr_url="$PR_URL" improve
+      env:
+        azure_devops__pat: $(azure_devops_pat)
+        openai__key: $(OPENAI_KEY)
+      displayName: 'Run PR Agent'
+```
+This script will run PR-Agent on every new merge request, with the `improve`, `review`, and `describe` commands.
+Note that you need to export the `azure_devops__pat` and `OPENAI_KEY` variables in the Azure DevOps pipeline settings (Pipelines -> Library -> + Variable group):
+![PR Agent Pro](https://codium.ai/images/pr_agent/azure_devops_pipeline_secrets.png){width=468}
+
+Make sure to give pipeline permissions to the `pr_agent` variable group.
+
+
+## Azure DevOps from CLI

 To use Azure DevOps provider use the following settings in configuration.toml:
 ```
--- a/docs/docs/installation/bitbucket.md
+++ b/docs/docs/installation/bitbucket.md
@ -27,9 +27,9 @@ You can get a Bitbucket token for your repository by following Repository Settin
 Note that comments on a PR are not supported in Bitbucket Pipeline.


-## Run using CodiumAI-hosted Bitbucket app
+## Run using CodiumAI-hosted Bitbucket app 💎

-Please contact [support@codium.ai](mailto:support@codium.ai) or visit [CodiumAI pricing page](https://www.codium.ai/pricing/) if you're interested in a hosted BitBucket app solution that provides full functionality including PR reviews and comment handling. It's based on the [bitbucket_app.py](https://github.com/Codium-ai/pr-agent/blob/main/pr_agent/git_providers/bitbucket_provider.py) implementation.
+Please contact visit [PR-Agent pro](https://www.codium.ai/pricing/) if you're interested in a hosted BitBucket app solution that provides full functionality including PR reviews and comment handling. It's based on the [bitbucket_app.py](https://github.com/Codium-ai/pr-agent/blob/main/pr_agent/git_providers/bitbucket_provider.py) implementation.


 ## Bitbucket Server and Data Center
--- a/docs/docs/installation/github.md
+++ b/docs/docs/installation/github.md
@ -26,15 +26,28 @@ jobs:
          OPENAI_KEY: ${{ secrets.OPENAI_KEY }}
          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
 ```
-** if you want to pin your action to a specific release (v2.0 for example) for stability reasons, use:
+
+
+if you want to pin your action to a specific release (v0.23 for example) for stability reasons, use:
 ```yaml
 ...
    steps:
      - name: PR Agent action step
        id: pragent
-        uses: Codium-ai/pr-agent@v2.0
+        uses: docker://codiumai/pr-agent:0.23-github_action
 ...
 ```
+
+For enhanced security, you can also specify the Docker image by its [digest](https://hub.docker.com/repository/docker/codiumai/pr-agent/tags):
+```yaml
+...
+    steps:
+      - name: PR Agent action step
+        id: pragent
+        uses: docker://codiumai/pr-agent@sha256:14165e525678ace7d9b51cda8652c2d74abb4e1d76b57c4a6ccaeba84663cc64
+...
+```
+
 2) Add the following secret to your repository under `Settings > Secrets and variables > Actions > New repository secret > Add secret`:

 ```
--- a/docs/docs/installation/gitlab.md
+++ b/docs/docs/installation/gitlab.md
@ -1,3 +1,44 @@
+## Run as a GitLab Pipeline
+You can use a pre-built Action Docker image to run PR-Agent as a GitLab pipeline. This is a simple way to get started with PR-Agent without setting up your own server.
+
+(1) Add the following file to your repository under `.gitlab-ci.yml`:
+```yaml
+stages:
+  - pr_agent
+
+pr_agent_job:
+  stage: pr_agent
+  image: 
+    name: codiumai/pr-agent:latest
+    entrypoint: [""]
+  script:
+    - cd /app
+    - echo "Running PR Agent action step"
+    - export MR_URL="$CI_MERGE_REQUEST_PROJECT_URL/merge_requests/$CI_MERGE_REQUEST_IID"
+    - echo "MR_URL=$MR_URL"
+    - export gitlab__PERSONAL_ACCESS_TOKEN=$GITLAB_PERSONAL_ACCESS_TOKEN 
+    - export config__git_provider="gitlab"
+    - export openai__key=$OPENAI_KEY
+    - python -m pr_agent.cli --pr_url="$MR_URL" describe
+    - python -m pr_agent.cli --pr_url="$MR_URL" review
+    - python -m pr_agent.cli --pr_url="$MR_URL" improve
+  rules:
+    - if: '$CI_PIPELINE_SOURCE == "merge_request_event"'
+```
+This script will run PR-Agent on every new merge request. You can modify the `rules` section to run PR-Agent on different events.
+You can also modify the `script` section to run different PR-Agent commands, or with different parameters by exporting different environment variables.
+
+
+(2) Add the following masked variables to your GitLab repository (CI/CD -> Variables):
+
+- `GITLAB_PERSONAL_ACCESS_TOKEN`: Your GitLab personal access token.
+
+- `OPENAI_KEY`: Your OpenAI key.
+
+Note that if your base branches are not protected, don't set the variables as `protected`, since the pipeline will not have access to them.
+
+
+
 ## Run a GitLab webhook server

 1. From the GitLab workspace or group, create an access token. Enable the "api" scope only.
@ -14,7 +55,7 @@ WEBHOOK_SECRET=$(python -c "import secrets; print(secrets.token_hex(10))")
    - In the [gitlab] section, fill in personal_access_token and shared_secret. The access token can be a personal access token, or a group or project access token.
    - Set deployment_type to 'gitlab' in [configuration.toml](https://github.com/Codium-ai/pr-agent/blob/main/pr_agent/settings/configuration.toml)
   
-5. Create a webhook in GitLab. Set the URL to the URL of your app's server. Set the secret token to the generated secret from step 2.
+5. Create a webhook in GitLab. Set the URL to ```http[s]://<PR_AGENT_HOSTNAME>/webhook```. Set the secret token to the generated secret from step 2.
 In the "Trigger" section, check the ‘comments’ and ‘merge request events’ boxes.

 6. Test your installation by opening a merge request or commenting or a merge request using one of CodiumAI's commands.
--- a/docs/docs/installation/index.md
+++ b/docs/docs/installation/index.md
@ -3,7 +3,7 @@
 ## Self-hosted PR-Agent
 If you choose to host you own PR-Agent, you first need to acquire two tokens:

-1. An OpenAI key from [here](https://platform.openai.com/api-keys), with access to GPT-4 (or a key for [other models](../usage-guide/additional_configurations.md/#changing-a-model), if you prefer).
+1. An OpenAI key from [here](https://platform.openai.com/api-keys), with access to GPT-4 (or a key for other [language models](https://pr-agent-docs.codium.ai/usage-guide/changing_a_model/), if you prefer).
 2. A GitHub\GitLab\BitBucket personal access token (classic), with the repo scope. [GitHub from [here](https://github.com/settings/tokens)]

 There are several ways to use self-hosted PR-Agent:
@ -15,8 +15,7 @@ There are several ways to use self-hosted PR-Agent:
 - [Azure DevOps](./azure.md)

 ## PR-Agent Pro 💎
-PR-Agent Pro, an app for GitHub\GitLab\BitBucket hosted by CodiumAI, is also available. 
+PR-Agent Pro, an app hosted by CodiumAI for GitHub\GitLab\BitBucket, is also available. 
 <br>
-With PR-Agent Pro Installation is as simple as signing up and adding the PR-Agent app to your relevant repo.
-<br>
-See [here](./pr_agent_pro.md) for more details.
+With PR-Agent Pro, installation is as simple as signing up and adding the PR-Agent app to your relevant repo. 
+See [here](https://pr-agent-docs.codium.ai/installation/pr_agent_pro/) for more details.
--- a/docs/docs/installation/pr_agent_pro.md
+++ b/docs/docs/installation/pr_agent_pro.md
@ -16,6 +16,10 @@ Once a user acquires a seat, they gain the flexibility to use PR-Agent Pro acros
 Users without a purchased seat who interact with a repository featuring PR-Agent Pro are entitled to receive up to five complimentary feedbacks.
 Beyond this limit, PR-Agent Pro will cease to respond to their inquiries unless a seat is purchased.

+## Install PR-Agent Pro for GitHub Enterprise Server
+You can install PR-Agent Pro application on your GitHub Enterprise Server, and enjoy two weeks of free trial.
+After the trial period, to continue using PR-Agent Pro, you will need to contact us for an [Enterprise license](https://www.codium.ai/pricing/).
+

 ## Install PR-Agent Pro for GitLab (Teams & Enterprise)

--- a/docs/docs/overview/data_privacy.md
+++ b/docs/docs/overview/data_privacy.md
@ -0,0 +1,16 @@
+## Self-hosted PR-Agent
+
+- If you self-host PR-Agent with your OpenAI (or other LLM provider) API key, it is between you and the provider. We don't send your code data to PR-Agent servers.
+
+## PR-Agent Pro 💎
+
+- When using PR-Agent Pro 💎, hosted by CodiumAI, we will not store any of your data, nor will we use it for training. You will also benefit from an OpenAI account with zero data retention.
+
+- For certain clients, CodiumAI-hosted PR-Agent Pro will use CodiumAI’s proprietary models. If this is the case, you will be notified.
+
+- No passive collection of Code and Pull Requests’ data — PR-Agent will be active only when you invoke it, and it will then extract and analyze only data relevant to the executed command and queried pull request.
+
+
+## PR-Agent Chrome extension
+
+- The [PR-Agent Chrome extension](https://chromewebstore.google.com/detail/pr-agent-chrome-extension/ephlnjeghhogofkifjloamocljapahnl) will not send your code to any external servers.
--- a/docs/docs/overview/index.md
+++ b/docs/docs/overview/index.md
@ -0,0 +1,81 @@
+# Overview
+
+CodiumAI PR-Agent is an open-source tool to help efficiently review and handle pull requests.
+
+- See the [Installation Guide](./installation/index.md) for instructions on installing and running the tool on different git platforms.
+
+- See the [Usage Guide](./usage-guide/index.md) for instructions on running the PR-Agent commands via different interfaces, including _CLI_, _online usage_, or by _automatically triggering_ them when a new PR is opened.
+
+- See the [Tools Guide](./tools/index.md) for a detailed description of the different tools.
+
+
+## PR-Agent Features
+PR-Agent offers extensive pull request functionalities across various git providers.
+
+|       |                                                                                                                       | GitHub | Gitlab | Bitbucket | Azure DevOps |
+|-------|-----------------------------------------------------------------------------------------------------------------------|:------:|:------:|:---------:|:------------:|
+| TOOLS | Review                                                                                                                |   ✅    |   ✅    |   ✅       |      ✅      |
+|       | ⮑ Incremental                                                                                                         |   ✅    |        |            |              |
+|       | ⮑ [SOC2 Compliance](https://pr-agent-docs.codium.ai/tools/review/#soc2-ticket-compliance){:target="_blank"} 💎        |   ✅    |   ✅    |   ✅        |      ✅      |
+|       | Ask                                                                                                                   |   ✅    |   ✅    |   ✅        |      ✅      |
+|       | Describe                                                                                                              |   ✅    |   ✅    |   ✅        |      ✅      |
+|       | ⮑ [Inline file summary](https://pr-agent-docs.codium.ai/tools/describe/#inline-file-summary){:target="_blank"} 💎     |   ✅    |   ✅    |           |      ✅      |
+|       | Improve                                                                                                               |   ✅    |   ✅    |   ✅        |      ✅      |
+|       | ⮑ Extended                                                                                                            |   ✅    |   ✅    |   ✅        |      ✅      |
+|       | [Custom Prompt](./tools/custom_prompt.md){:target="_blank"} 💎                                                        |   ✅    |   ✅    |   ✅        |      ✅      |
+|       | Reflect and Review                                                                                                    |   ✅    |   ✅    |   ✅        |      ✅      |
+|       | Update CHANGELOG.md                                                                                                   |   ✅    |   ✅    |   ✅        |      ️       |
+|       | Find Similar Issue                                                                                                    |   ✅    |        |             |      ️       |
+|       | [Add PR Documentation](./tools/documentation.md){:target="_blank"} 💎                                                 |   ✅    |   ✅    |          |      ✅      |
+|       | [Generate Custom Labels](./tools/describe.md#handle-custom-labels-from-the-repos-labels-page-💎){:target="_blank"} 💎 |   ✅    |   ✅    |            |      ✅      |
+|       | [Analyze PR Components](./tools/analyze.md){:target="_blank"} 💎                                                      |   ✅    |   ✅    |       |      ✅      |
+|       |                                                                                                                       |        |        |            |      ️       |
+| USAGE | CLI                                                                                                                   |   ✅    |   ✅    |   ✅       |      ✅      |
+|       | App / webhook                                                                                                         |   ✅    |   ✅    |    ✅        |      ✅      |
+|       | Actions                                                                                                               |   ✅    |        |            |      ️       |
+|       |                                                                                                                       |        |        |            |
+| CORE  | PR compression                                                                                                        |   ✅    |   ✅    |   ✅       |   ✅        |
+|       | Repo language prioritization                                                                                          |   ✅    |   ✅    |   ✅       |   ✅        |
+|       | Adaptive and token-aware file patch fitting                                                                           |   ✅    |   ✅    |   ✅     |   ✅        |
+|       | Multiple models support                                                                                               |   ✅    |   ✅    |   ✅       |   ✅        |
+|       | Incremental PR review                                                                                                 |   ✅    |        |            |           |
+|       | [Static code analysis](./tools/analyze.md/){:target="_blank"} 💎                                                      |   ✅    |   ✅     |    ✅    |   ✅        |
+|       | [Multiple configuration options](./usage-guide/configuration_options.md){:target="_blank"} 💎                         |   ✅    |   ✅     |    ✅    |   ✅        |
+
+💎 marks a feature available only in [PR-Agent Pro](https://www.codium.ai/pricing/){:target="_blank"}
+
+
+## Example Results
+<hr>
+
+#### [/describe](https://github.com/Codium-ai/pr-agent/pull/530)
+<figure markdown="1">
+![/describe](https://www.codium.ai/images/pr_agent/describe_new_short_main.png){width=512}
+</figure>
+<hr>
+
+#### [/review](https://github.com/Codium-ai/pr-agent/pull/732#issuecomment-1975099151)
+<figure markdown="1">
+![/review](https://www.codium.ai/images/pr_agent/review_new_short_main.png){width=512}
+</figure>
+<hr>
+
+#### [/improve](https://github.com/Codium-ai/pr-agent/pull/732#issuecomment-1975099159)
+<figure markdown="1">
+![/improve](https://www.codium.ai/images/pr_agent/improve_new_short_main.png){width=512}
+</figure>
+<hr>
+
+#### [/generate_labels](https://github.com/Codium-ai/pr-agent/pull/530)
+<figure markdown="1">
+![/generate_labels](https://www.codium.ai/images/pr_agent/geneare_custom_labels_main_short.png){width=300}
+</figure>
+<hr>
+
+## How it Works
+
+The following diagram illustrates PR-Agent tools and their flow:
+
+![PR-Agent Tools](https://codium.ai/images/pr_agent/diagram-v0.9.png)
+
+Check out the [PR Compression strategy](core-abilities/index.md) page for more details on how we convert a code diff to a manageable LLM prompt
--- a/docs/docs/overview/pr_agent_pro.md
+++ b/docs/docs/overview/pr_agent_pro.md
@ -0,0 +1,42 @@
+[PR-Agent Pro](https://www.codium.ai/pricing/) is a hosted version of PR-Agent, provided by CodiumAI. A complimentary two-week trial is offered, followed by a monthly subscription fee.
+PR-Agent Pro is designed for companies and teams that require additional features and capabilities. It provides the following benefits:
+
+1. **Fully managed** - We take care of everything for you - hosting, models, regular updates, and more. Installation is as simple as signing up and adding the PR-Agent app to your GitHub\GitLab\BitBucket repo.
+
+2. **Improved privacy** - No data will be stored or used to train models. PR-Agent Pro will employ zero data retention, and will use an OpenAI account with zero data retention.
+
+3. **Improved support** - PR-Agent Pro users will receive priority support, and will be able to request new features and capabilities.
+
+4. **Supporting self-hosted git servers** - PR-Agent Pro can be installed on GitHub Enterprise Server, GitLab, and BitBucket. For more information, see the [installation guide](https://pr-agent-docs.codium.ai/installation/pr_agent_pro/).
+
+**Additional features:**
+
+Here are some of the additional features and capabilities that PR-Agent Pro offers:
+
+| Feature                                                                                                              | Description                                                                                                                                                      |
+|----------------------------------------------------------------------------------------------------------------------|------------------------------------------------------------------------------------------------------------------------------------------------------------------|
+| [**Model selection**](https://pr-agent-docs.codium.ai/usage-guide/PR_agent_pro_models/#pr-agent-pro-models)          | Choose the model that best fits your needs, among top models like `GPT4` and `Claude-Sonnet-3.5`                                                                 
+| [**Global and wiki configuration**](https://pr-agent-docs.codium.ai/usage-guide/configuration_options/)              | Control configurations for many repositories from a single location; <br>Edit configuration of a single repo without commiting code                              |
+| [**Apply suggestions**](https://pr-agent-docs.codium.ai/tools/improve/#overview)                                     | Generate commitable code from the relevant suggestions interactively by clicking on a checkbox                                                                   |
+| [**Suggestions impact**](https://pr-agent-docs.codium.ai/tools/improve/#assessing-impact)                         | Automatically mark suggestions that were implemented by the user (either directly in GitHub, or indirectly in the IDE) to enable tracking of the impact of the suggestions |
+| [**CI feedback**](https://pr-agent-docs.codium.ai/tools/ci_feedback/) | Automatically analyze failed CI checks on GitHub and provide actionable feedback in the PR conversation, helping to resolve issues quickly |
+| [**Advanced usage statistics**](https://www.codium.ai/contact/#/)                                                    | PR-Agent Pro offers detailed statistics at user, repository, and company levels, including metrics about PR-Agent usage, and also general statistics and insights |
+| [**Incorporating companies' best practices**](https://pr-agent-docs.codium.ai/tools/improve/#best-practices)         | Use the companies' best practices as reference to increase the effectiveness and the relevance of the code suggestions                                           |
+| [**Interactive triggering**](https://pr-agent-docs.codium.ai/tools/analyze/#example-usage)                           | Interactively apply different tools via the `analyze` command                                                                                                    |
+| [**SOC2 compliance check**](https://pr-agent-docs.codium.ai/tools/review/#configuration-options)                     | Ensures the PR contains a ticket to a project management system (e.g., Jira, Asana, Trello, etc.)                                                                
+| [**Custom labels**](https://pr-agent-docs.codium.ai/tools/describe/#handle-custom-labels-from-the-repos-labels-page) | Define custom labels for PR-Agent to assign to the PR                                                                                                            |
+
+**Additional tools:**
+
+Here are additional tools that are available only for PR-Agent Pro users:
+
+| Feature | Description |
+|---------|-------------|
+| [**Custom Prompt Suggestions**](https://pr-agent-docs.codium.ai/tools/custom_prompt/) | Generate code suggestions based on custom prompts from the user |
+| [**Analyze PR components**](https://pr-agent-docs.codium.ai/tools/analyze/) | Identify the components that changed in the PR, and enable to interactively apply different tools to them |
+| [**Tests**](https://pr-agent-docs.codium.ai/tools/test/) | Generate tests for code components that changed in the PR |
+| [**PR documentation**](https://pr-agent-docs.codium.ai/tools/documentation/) | Generate docstring for code components that changed in the PR |
+| [**Improve Component**](https://pr-agent-docs.codium.ai/tools/improve_component/) | Generate code suggestions for code components that changed in the PR |
+| [**Similar code search**](https://pr-agent-docs.codium.ai/tools/similar_code/) | Search for similar code in the repository, organization, or entire GitHub |
+
+
--- a/docs/docs/tools/analyze.md
+++ b/docs/docs/tools/analyze.md
@ -9,6 +9,7 @@ It can be invoked manually by commenting on any PR:
 ```

 ## Example usage
+
 An example result:

 ![Analyze 1](https://codium.ai/images/pr_agent/analyze_1.png){width=750}
--- a/docs/docs/tools/ask.md
+++ b/docs/docs/tools/ask.md
@ -5,7 +5,8 @@ It can be invoked manually by commenting on any PR:
 ```
 /ask "..."
 ```
-For example:
+
+## Example usage

 ![Ask Comment](https://codium.ai/images/pr_agent/ask_comment.png){width=512}

--- a/docs/docs/tools/ci_feedback.md
+++ b/docs/docs/tools/ci_feedback.md
@ -8,6 +8,8 @@ The tool analyzes the failed checks and provides several feedbacks:
 - Failure summary
 - Relevant error logs

+## Example usage
+
 ![Failed Check 1](https://www.codium.ai/images/pr_agent/failed_check1.png){width=768}

 &rarr;
@ -21,6 +23,14 @@ In addition to being automatically triggered, the tool can also be invoked manua
 ```
 where `{repo_name}` is the name of the repository, `{run_number}` is the run number of the failed check, and `{job_number}` is the job number of the failed check.

+## Disabling the tool from running automatically
+
+If you wish to disable the tool from running automatically, you can do so by adding the following configuration to the configuration file:
+```
+[checks]
+enable_auto_checks_feedback = false
+```
+
 ## Configuration options
 - `enable_auto_checks_feedback` - if set to true, the tool will automatically provide feedback when a check is failed. Default is true.
 - `excluded_checks_list` - a list of checks to exclude from the feedback, for example: ["check1", "check2"]. Default is an empty list.
--- a/docs/docs/tools/custom_labels.md
+++ b/docs/docs/tools/custom_labels.md
@ -5,7 +5,8 @@ It can be invoked manually by commenting on any PR:
 ```
 /generate_labels
 ```
-For example:
+
+## Example usage

 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:

--- a/docs/docs/tools/custom_prompt.md
+++ b/docs/docs/tools/custom_prompt.md
@ -0,0 +1,58 @@
+## Overview
+The `custom_prompt` tool scans the PR code changes, and automatically generates suggestions for improving the PR code.
+It shares similarities with the `improve` tool, but with one main difference: the `custom_prompt` tool will **only propose suggestions that follow specific guidelines defined by the prompt** in: `pr_custom_prompt.prompt` configuration.
+
+The tool can be triggered [automatically](../usage-guide/automations_and_usage.md#github-app-automatic-tools-when-a-new-pr-is-opened) every time a new PR is opened, or can be invoked manually by commenting on a PR.
+
+When commenting, use the following template:
+
+```
+/custom_prompt --pr_custom_prompt.prompt="
+The code suggestions should focus only on the following:
+- ...
+- ...
+
+"
+```
+
+With a [configuration file](../usage-guide/automations_and_usage.md#github-app), use the following template:
+
+```
+[pr_custom_prompt]
+prompt="""\
+The suggestions should focus only on the following:
+-...
+-...
+
+"""
+```
+
+Remember - with this tool, you are the prompter. Be specific, clear, and concise in the instructions. Specify relevant aspects that you want the model to focus on. \
+You might benefit from several trial-and-error iterations, until you get the correct prompt for your use case.
+
+## Example usage
+
+Here is an example of a possible prompt, defined in the configuration file:
+```
+[pr_custom_prompt]
+prompt="""\
+The code suggestions should focus only on the following:
+- look for edge cases when implementing a new function
+- make sure every variable has a meaningful name
+- make sure the code is efficient
+"""
+```     
+
+(The instructions above are just an example. We want to emphasize that the prompt should be specific and clear, and be tailored to the needs of your project)
+
+Results obtained with the prompt above:
+
+![Custom prompt results](https://codium.ai/images/pr_agent/custom_suggestions_result.png){width=768}
+
+## Configuration options
+
+`prompt`: the prompt for the tool. It should be a multi-line string.
+
+`num_code_suggestions`: number of code suggestions provided by the 'custom_prompt' tool. Default is 4.
+
+`enable_help_text`: if set to true, the tool will display a help text in the comment. Default is true.
--- a/docs/docs/tools/custom_suggestions.md
+++ b/docs/docs/tools/custom_suggestions.md
@ -1,56 +0,0 @@
-## Overview
-The `custom_suggestions` tool scans the PR code changes, and automatically generates custom suggestions for improving the PR code.
-It shares similarities with the `improve` tool, but with one main difference: the `custom_suggestions` tool will only propose suggestions that follow specific guidelines defined by the prompt in: `pr_custom_suggestions.prompt` configuration.
-
-The tool can be triggered [automatically](../usage-guide/automations_and_usage.md#github-app-automatic-tools-when-a-new-pr-is-opened) every time a new PR is opened, or can be invoked manually by commenting on a PR.
-
-When commenting, use the following template:
-
-```
-/custom_suggestions --pr_custom_suggestions.prompt="The suggestions should focus only on the following:\n-...\n-...\n-..."
-```
-
-With a [configuration file](../usage-guide/automations_and_usage.md#github-app), use the following template:
-
-```
-[pr_custom_suggestions]
-prompt="""\
-The suggestions should focus only on the following:
-...
-...
-...
-"""
-```
-Using a configuration file is recommended, since it allows to use multi-line instructions.
-
-Don't forget - with this tool, you are the prompter. Be specific, clear, and concise in the instructions. Specify relevant aspects that you want the model to focus on. \
-You might benefit from several trial-and-error iterations, until you get the correct prompt for your use case.
-
-## Example usage
-
-Here is an example of a possible prompt:
-```
-[pr_custom_suggestions]
-prompt="""\
-The suggestions should focus only on the following:
- look for edge cases when implementing a new function
- make sure every variable has a meaningful name
- make sure the code is efficient
-"""
-```     
-
-The instructions above are just an example. We want to emphasize that the prompt should be specific and clear, and be tailored to the needs of your project.
-
-Results obtained with the prompt above:
-
-![Custom suggestions prompt](https://codium.ai/images/pr_agent/custom_suggestions_prompt.png){width=512}
-&rarr;
-![Custom suggestions results](https://codium.ai/images/pr_agent/custom_suggestions_result.png){width=768}
-
-## Configuration options
-
-`prompt`: the prompt for the tool. It should be a multi-line string.
-
-`num_code_suggestions`: number of code suggestions provided by the 'custom_suggestions' tool. Default is 4.
-
-`enable_help_text`: if set to true, the tool will display a help text in the comment. Default is true.
--- a/docs/docs/tools/describe.md
+++ b/docs/docs/tools/describe.md
@ -8,7 +8,7 @@ The tool can be triggered automatically every time a new PR is [opened](../usage

 ## Example usage

-### Manual invocation
+### Manual triggering

 Invoke the tool manually by commenting `/describe` on any PR:

@ -18,12 +18,12 @@ After ~30 seconds, the tool will generate a description for the PR:

 ![Describe New](https://codium.ai/images/pr_agent/describe_new.png){width=512}

-If you want to edit [configurations](https://github.com/Codium-ai/pr-agent/blob/main/pr_agent/settings/configuration.toml#L46), add the relevant ones to the command:
+If you want to edit [configurations](#configuration-options), add the relevant ones to the command:
 ```
 /describe --pr_description.some_config1=... --pr_description.some_config2=...
 ```

-### Automatic invocation
+### Automatic triggering

 To run the `describe` automatically when a PR is opened, define in a [configuration file](https://pr-agent-docs.codium.ai/usage-guide/configuration_options/#wiki-configuration-file):
 ```
@ -36,42 +36,69 @@ pr_commands = [
 [pr_description]
 publish_labels = ...
 ...
-
 ```

- The `pr_commands` lists commands that will be executed on every PR.
- The `[pr_description]` section contains the configurations for the `describe` tool you want to edit.
+- The `pr_commands` lists commands that will be executed automatically when a PR is opened.
+- The `[pr_description]` section contains the configurations for the `describe` tool you want to edit (if any).


 ## Configuration options

-### General configurations
-
 !!! example "Possible configurations"

-    - `publish_labels`: if set to true, the tool will publish the labels to the PR. Default is true.
+<table>
+  <tr>
+    <td><b>publish_labels</b></td>
+    <td>If set to true, the tool will publish the labels to the PR. Default is true.</td>
+  </tr>
+  <tr>
+    <td><b>publish_description_as_comment</b></td>
+    <td>If set to true, the tool will publish the description as a comment to the PR. If false, it will overwrite the original description. Default is false.</td>
+  </tr>
+  <tr>
+    <td><b>publish_description_as_comment_persistent</b></td>
+    <td>If set to true and `publish_description_as_comment` is true, the tool will publish the description as a persistent comment to the PR. Default is true.</td>
+  </tr>
+  <tr>
+    <td><b>add_original_user_description</b></td>
+    <td>If set to true, the tool will add the original user description to the generated description. Default is true.</td>
+  </tr>
+  <tr>
+    <td><b>generate_ai_title</b></td>
+    <td>If set to true, the tool will also generate an AI title for the PR. Default is false.</td>
+  </tr>
+  <tr>
+    <td><b>extra_instructions</b></td>
+    <td>Optional extra instructions to the tool. For example: "focus on the changes in the file X. Ignore change in ..."</td>
+  </tr>
+  <tr>
+    <td><b>enable_pr_type</b></td>
+    <td>If set to false, it will not show the `PR type` as a text value in the description content. Default is true.</td>
+  </tr>
+  <tr>
+    <td><b>final_update_message</b></td>
+    <td>If set to true, it will add a comment message [`PR Description updated to latest commit...`](https://github.com/Codium-ai/pr-agent/pull/499#issuecomment-1837412176) after finishing calling `/describe`. Default is false.</td>
+  </tr>
+  <tr>
+    <td><b>enable_semantic_files_types</b></td>
+    <td>If set to true, "Changes walkthrough" section will be generated. Default is true.</td>
+  </tr>
+  <tr>
+    <td><b>collapsible_file_list</b></td>
+    <td>If set to true, the file list in the "Changes walkthrough" section will be collapsible. If set to "adaptive", the file list will be collapsible only if there are more than 8 files. Default is "adaptive".</td>
+  </tr>
+  <tr>
+    <td><b>enable_large_pr_handling</b></td>
+    <td>Pro feature. If set to true, in case of a large PR the tool will make several calls to the AI and combine them to be able to cover more files. Default is true.</td>
+  </tr>
+  <tr>
+    <td><b>enable_help_text</b></td>
+    <td>If set to true, the tool will display a help text in the comment. Default is false.</td>
+  </tr>
+</table>

-    - `publish_description_as_comment`: if set to true, the tool will publish the description as a comment to the PR. If false, it will overwrite the original description. Default is false.

-    - `publish_description_as_comment_persistent`: if set to true and `publish_description_as_comment` is true, the tool will publish the description as a persistent comment to the PR. Default is true.
-
-    - `add_original_user_description`: if set to true, the tool will add the original user description to the generated description. Default is true.
-
-    - `keep_original_user_title`: if set to true, the tool will keep the original PR title, and won't change it. Default is true.
-
-    - `extra_instructions`: Optional extra instructions to the tool. For example: "focus on the changes in the file X. Ignore change in ...".
-
-    - To enable `custom labels`, apply the configuration changes described [here](./custom_labels.md#configuration-options)
-
-    - `enable_pr_type`: if set to false, it will not show the `PR type` as a text value in the description content. Default is true.
-
-    - `final_update_message`: if set to true, it will add a comment message [`PR Description updated to latest commit...`](https://github.com/Codium-ai/pr-agent/pull/499#issuecomment-1837412176) after finishing calling `/describe`. Default is true.
-
-    - `enable_semantic_files_types`: if set to true, "Changes walkthrough" section will be generated. Default is true.
-    - `collapsible_file_list`: if set to true, the file list in the "Changes walkthrough" section will be collapsible. If set to "adaptive", the file list will be collapsible only if there are more than 8 files. Default is "adaptive".
-    - `enable_help_text`: if set to true, the tool will display a help text in the comment. Default is false.
-
-### Inline file summary 💎
+## Inline file summary 💎

 This feature enables you to copy the `changes walkthrough` table to the "Files changed" tab, so you can quickly understand the changes in each file while reviewing the code changes (diff view).

@ -85,7 +112,7 @@ If you prefer to have the file summaries appear in the "Files changed" tab on ev

 ![Diffview table](https://codium.ai/images/pr_agent/diffview-table.png){width=512}

- `true`: A collapsable file comment with changes title and a changes summary for each file in the PR.
+- `true`: A collapsible file comment with changes title and a changes summary for each file in the PR.

 ![Diffview changes](https://codium.ai/images/pr_agent/diffview_changes.png){width=512}

@ -94,7 +121,7 @@ If you prefer to have the file summaries appear in the "Files changed" tab on ev
 **Note**: that this feature is currently available only for GitHub.


-### Markers template
+## Markers template

 To enable markers, set `pr_description.use_description_markers=true`.
 Markers enable to easily integrate user's content and auto-generated content, with a template-like mechanism.
@ -127,30 +154,33 @@ The marker `pr_agent:type` will be replaced with the PR type, `pr_agent:summary`
 - `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.

 ## Custom labels
-
 The default labels of the describe tool are quite generic, since they are meant to be used in any repo: [`Bug fix`, `Tests`, `Enhancement`, `Documentation`, `Other`].

 You can define custom labels that are relevant for your repo and use cases.
 Custom labels can be defined in a [configuration file](https://pr-agent-docs.codium.ai/tools/custom_labels/#configuration-options), or directly in the repo's [labels page](#handle-custom-labels-from-the-repos-labels-page).

-Examples for custom labels:
-
-  - `Main topic:performance` -  pr_agent:The main topic of this PR is performance
-  - `New endpoint` -  pr_agent:A new endpoint was added in this PR
-  - `SQL query` -  pr_agent:A new SQL query was added in this PR
-  - `Dockerfile changes` - pr_agent:The PR contains changes in the Dockerfile
-  - ...
-
-The list above is eclectic, and aims to give an idea of different possibilities. Define custom labels that are relevant for your repo and use cases.
-Note that Labels are not mutually exclusive, so you can add multiple label categories.
-<br>
 Make sure to provide proper title, and a detailed and well-phrased description for each label, so the tool will know when to suggest it.
 Each label description should be a **conditional statement**, that indicates if to add the label to the PR or not, according to the PR content.

+### Handle custom labels from a configuration file
+Example for a custom labels configuration setup in a configuration file:
+```
+[config]
+enable_custom_labels=true
+
+
+[custom_labels."sql_changes"]
+description = "Use when a PR contains changes to SQL queries"
+
+[custom_labels."test"]
+description = "use when a PR primarily contains new tests"
+
+...
+```

 ### Handle custom labels from the Repo's labels page 💎

-You can control  the custom labels that will be suggested by the `describe` tool, from the repo's labels page:
+You can also control the custom labels that will be suggested by the `describe` tool from the repo's labels page:

 * GitHub : go to `https://github.com/{owner}/{repo}/labels` (or click on the "Labels" tab in the issues or PRs page)
 * GitLab : go to `https://gitlab.com/{owner}/{repo}/-/labels` (or click on "Manage" -> "Labels" on the left menu)
@ -160,6 +190,14 @@ Now add/edit the custom labels. they should be formatted as follows:
 * Label name: The name of the custom label.
 * Description: Start the description of with prefix `pr_agent:`, for example: `pr_agent: Description of when AI should suggest this label`.<br>

+Examples for custom labels:
+
+  - `Main topic:performance` -  pr_agent:The main topic of this PR is performance
+  - `New endpoint` -  pr_agent:A new endpoint was added in this PR
+  - `SQL query` -  pr_agent:A new SQL query was added in this PR
+  - `Dockerfile changes` - pr_agent:The PR contains changes in the Dockerfile
+  - ...
+
 The description should be comprehensive and detailed, indicating when to add the desired label. For example:
 ![Add native custom labels](https://codium.ai/images/pr_agent/add_native_custom_labels.png){width=768}

@ -169,18 +207,11 @@ The description should be comprehensive and detailed, indicating when to add the
 !!! tip "Automation"
    - When you first install PR-Agent app, the [default mode](../usage-guide/automations_and_usage.md#github-app) for the describe tool is:
    ```
-    pr_commands = ["/describe --pr_description.add_original_user_description=true" 
-                             "--pr_description.keep_original_user_title=true", ...]
+    pr_commands = ["/describe", ...]
    ```
-    meaning the `describe` tool will run automatically on every PR, will keep the original title, and will add the original user description above the generated description. 
-    <br> This default settings aim to strike a good balance between automation and control:
-        - If you want more automation, just give the PR a title, and the tool will auto-write a full description; If you want more control, you can add a detailed description, and the tool will add the complementary description below it.
-        - For maximal automation, you can change the default mode to:
-        ```
-        pr_commands = ["/describe --pr_description.add_original_user_description=false" 
-                                 "--pr_description.keep_original_user_title=true", ...]
-        ```
-        so the title will be auto-generated as well.
+    meaning the `describe` tool will run automatically on every PR, with the default configurations.
+
+
   - Markers are an alternative way to control the generated description, to give maximal control to the user. If you set:
   ```
   pr_commands = ["/describe --pr_description.use_description_markers=true", ...]
--- a/docs/docs/tools/documentation.md
+++ b/docs/docs/tools/documentation.md
@ -5,14 +5,24 @@ It can be invoked manually by commenting on any PR:
 ```
 /add_docs
 ```
-For example:
+
+## Example usage
+
+Invoke the tool manually by commenting `/add_docs` on any PR:

 ![Docs command](https://codium.ai/images/pr_agent/docs_command.png){width=768}

+The tool will generate documentation for all the components that changed in the PR:
+
 ![Docs component](https://codium.ai/images/pr_agent/docs_components.png){width=768}

 ![Docs single component](https://codium.ai/images/pr_agent/docs_single_component.png){width=768}

+You can state a name of a specific component in the PR to get documentation only for that component:
+```
+/add_docs component_name
+```
+
 ## Configuration options
 - `docs_style`: The exact style of the documentation (for python docstring). you can choose between: `google`, `numpy`, `sphinx`, `restructuredtext`, `plain`. Default is `sphinx`.
 - `extra_instructions`: Optional extra instructions to the tool. For example: "focus on the changes in the file X. Ignore change in ...".
@ -20,5 +30,4 @@ For example:
 **Notes**

 - Language that are currently fully supported: Python, Java, C++, JavaScript, TypeScript, C#.
- For languages that are not fully supported, the tool will suggest documentation only for new components in the PR.
- A previous version of the tool, that offered support only for new components, was deprecated.
+- This tool can also be triggered interactively by using the [`analyze`](./analyze.md) tool.
--- a/docs/docs/tools/improve.md
+++ b/docs/docs/tools/improve.md
@ -1,93 +1,210 @@
 ## Overview
-The `improve` tool scans the PR code changes, and automatically generates suggestions for improving the PR code.
+The `improve` tool scans the PR code changes, and automatically generates [meaningful](https://github.com/Codium-ai/pr-agent/blob/main/pr_agent/settings/pr_code_suggestions_prompts.toml#L41) suggestions for improving the PR code.
 The tool can be triggered automatically every time a new PR is [opened](../usage-guide/automations_and_usage.md#github-app-automatic-tools-when-a-new-pr-is-opened), or it can be invoked manually by commenting on any PR:
 ```
 /improve
 ```

-### Summarized vs committable code suggestions
+![code_suggestions_as_comment_closed.png](https://codium.ai/images/pr_agent/code_suggestions_as_comment_closed.png){width=512}

-The code suggestions can be presented as a single comment (via `pr_code_suggestions.summarize=true`):
+![code_suggestions_as_comment_open.png](https://codium.ai/images/pr_agent/code_suggestions_as_comment_open.png){width=512}

-![code suggestions as comment](https://codium.ai/images/pr_agent/code_suggestions_as_comment.png){width=512}
-
-Or as a separate commitable code comment for each suggestion:
-
-![imporove](https://codium.ai/images/pr_agent/improve.png){width=512}
+Note that the `Apply this suggestion` checkbox, which interactively converts a suggestion into a commitable code comment, is available only for PR-Agent Pro 💎 users.


-Note that a single comment has a significantly smaller PR footprint. We recommend this mode for most cases.
-Also note that collapsible are not supported in _Bitbucket_. Hence, the suggestions are presented there as code comments.
+## Example usage

-### Extended mode
+### Manual triggering

-An extended mode, which does not involve PR Compression and provides more comprehensive suggestions, can be invoked by commenting on any PR:
-```
-/improve --extended
-```
+Invoke the tool manually by commenting `/improve` on any PR. The code suggestions by default are presented as a single comment:

-or by setting:
-```
-[pr_code_suggestions]
-auto_extended_mode=true
-```
-(True by default).
-
-Note that the extended mode divides the PR code changes into chunks, up to the token limits, where each chunk is handled separately (might use multiple calls to GPT-4 for large PRs).
-Hence, the total number of suggestions is proportional to the number of chunks, i.e., the size of the PR.
-
-### Configuration options
-
-To edit [configurations](https://github.com/Codium-ai/pr-agent/blob/main/pr_agent/settings/configuration.toml#L66) related to the improve tool (`pr_code_suggestions` section), use the following template:
+To edit [configurations](#configuration-options) related to the improve tool, use the following template:
 ```
 /improve --pr_code_suggestions.some_config1=... --pr_code_suggestions.some_config2=...
 ```

-!!! example "General options"
+For example, you can choose to present all the suggestions as commitable code comments, by running the following command:
+```
+/improve --pr_code_suggestions.commitable_code_suggestions=true
+```

-    - `num_code_suggestions`: number of code suggestions provided by the 'improve' tool. Default is 4 for CLI, 0 for auto tools.
-    - `extra_instructions`: Optional extra instructions to the tool. For example: "focus on the changes in the file X. Ignore change in ...".
-    - `rank_suggestions`: if set to true, the tool will rank the suggestions, based on importance. Default is false.
-    - `summarize`: if set to true, the tool will display the suggestions in a single comment. Default is true.
-    - `persistent_comment`: if set to true, the improve comment will be persistent, meaning that every new improve request will edit the previous one. Default is false.
-    - `enable_help_text`: if set to true, the tool will display a help text in the comment. Default is true.
+![improve](https://codium.ai/images/pr_agent/improve.png){width=512}

-!!! example "params for '/improve --extended' mode"

-    - `auto_extended_mode`: enable extended mode automatically (no need for the `--extended` option). Default is true.
-    - `num_code_suggestions_per_chunk`: number of code suggestions provided by the 'improve' tool, per chunk. Default is 5.
-    - `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.
+As can be seen, a single table comment has a significantly smaller PR footprint. We recommend this mode for most cases.
+Also note that collapsible are not supported in _Bitbucket_. Hence, the suggestions can only be presented in Bitbucket as code comments.
+
+### Automatic triggering
+
+To run the `improve` automatically when a PR is opened, define in a [configuration file](https://pr-agent-docs.codium.ai/usage-guide/configuration_options/#wiki-configuration-file):
+```
+[github_app]
+pr_commands = [
+    "/improve",
+    ...
+]
+
+[pr_code_suggestions]
+num_code_suggestions_per_chunk = ...
+...
+```
+
+- The `pr_commands` lists commands that will be executed automatically when a PR is opened.
+- The `[pr_code_suggestions]` section contains the configurations for the `improve` tool you want to edit (if any)
+
+### Assessing Impact 💎
+
+Note that PR-Agent pro tracks two types of implementations:
+
+- Direct implementation - when the user directly applies the suggestion by clicking the `Apply` checkbox.
+- Indirect implementation - when the user implements the suggestion in their IDE environment. In this case, PR-Agent will utilize, after each commit, a dedicated logic to identify if a suggestion was implemented, and will mark it as implemented.
+
+![code_suggestions_asses_impact](https://codium.ai/images/pr_agent/code_suggestions_asses_impact.png){width=512}
+
+In post-process, PR-Agent counts the number of suggestions that were implemented, and provides general statistics and insights about the suggestions' impact on the PR process.
+
+![code_suggestions_asses_impact_stats_1](https://codium.ai/images/pr_agent/code_suggestions_asses_impact_stats_1.png){width=512}
+
+![code_suggestions_asses_impact_stats_2](https://codium.ai/images/pr_agent/code_suggestions_asses_impact_stats_2.png){width=512}


 ## Usage Tips

-!!! tip "Extra instructions"
+### Self-review
+If you set in a configuration file:
+```
+[pr_code_suggestions]
+demand_code_suggestions_self_review = true
+```
+The `improve` tool will add a checkbox below the suggestions, prompting user to acknowledge that they have reviewed the suggestions.
+You can set the content of the checkbox text via:
+```
+[pr_code_suggestions]
+code_suggestions_self_review_text = "... (your text here) ..."
+```

-    Extra instructions are very important for the `imrpove` tool, since they enable you to guide the model to suggestions that are more relevant to the specific needs of the project.
+![self_review_1](https://codium.ai/images/pr_agent/self_review_1.png){width=512}

+
+💎 In addition, by setting:
+```
+[pr_code_suggestions]
+approve_pr_on_self_review = true
+```
+the tool can automatically approve the PR when the user checks the self-review checkbox.
+
+!!! tip "Tip - demanding self-review from the PR author"
+    If you set the number of required reviewers for a PR to 2, this effectively means that the PR author must click the self-review checkbox before the PR can be merged (in addition to a human reviewer).
+
+    ![self_review_2](https://codium.ai/images/pr_agent/self_review_2.png){width=512}
+
+### `Extra instructions` and `best practices`
+
+#### Extra instructions
+You can use the `extra_instructions` configuration option to give the AI model additional instructions for the `improve` tool.
 Be specific, clear, and concise in the instructions. With extra instructions, you are the prompter. Specify relevant aspects that you want the model to focus on.
    
-    Examples for extra instructions:
+Examples for possible instructions:
 ```
-    [pr_code_suggestions] # /improve #
+[pr_code_suggestions]
 extra_instructions="""\
-    Emphasize the following aspects:
-    - Does the code logic cover relevant edge cases?
-    - Is the code logic clear and easy to understand?
-    - Is the code logic efficient?
+(1) Answer in japanese
+(2) Don't suggest to add try-excpet block
+(3) Ignore changes in toml files
 ...
 """
 ```
-    Use triple quotes to write multi-line instructions. Use bullet points to make the instructions more readable.
+Use triple quotes to write multi-line instructions. Use bullet points or numbers to make the instructions more readable.

-!!! tip "Review vs. Improve tools comparison"
+#### Best practices 💎
+Another option to give additional guidance to the AI model is by creating a dedicated [**wiki page**](https://github.com/Codium-ai/pr-agent/wiki) called `best_practices.md`. 
+This page can contain a list of best practices, coding standards, and guidelines that are specific to your repo/organization

-    - The [`review`](https://pr-agent-docs.codium.ai/tools/review/) tool includes a section called 'Possible issues', that also provide feedback on the PR Code.
-    In this section, the model is instructed to focus **only** on [major bugs and issues](https://github.com/Codium-ai/pr-agent/blob/main/pr_agent/settings/pr_reviewer_prompts.toml#L71).
-    - The `improve` tool, on the other hand, has a broader mandate, and in addition to bugs and issues, it can also give suggestions for improving code quality and making the code more efficient, readable, and maintainable (see [here](https://github.com/Codium-ai/pr-agent/blob/main/pr_agent/settings/pr_code_suggestions_prompts.toml#L34)).
-    - Hence, if you are interested only in feedback about clear bugs, the `review` tool might suffice. If you want a more detailed feedback, including broader suggestions for improving the PR code, also enable the `improve` tool to run on each PR.
+The AI model will use this page as a reference, and in case the PR code violates any of the guidelines, it will suggest improvements accordingly, with a dedicated label: `Organization
+best practice`. 
+
+Example for a `best_practices.md` content can be found [here](https://github.com/Codium-ai/pr-agent/blob/main/docs/docs/usage-guide/EXAMPLE_BEST_PRACTICE.md) (adapted from Google's [pyguide](https://google.github.io/styleguide/pyguide.html)).
+This file is only an example. Since it is used as a prompt for an AI model, we want to emphasize the following:
+
+- It should be written in a clear and concise manner
+- If needed, it should give short relevant code snippets as examples
+- Up to 800 lines are allowed
+
+
+Example results:
+
+![best_practice](https://codium.ai/images/pr_agent/org_best_practice.png){width=512}
+
+Note that while the `extra instructions` are more related to the way the `improve` tool behaves, the `best_practices.md` file is a general guideline for the way code should be written in the repo.
+Using a combination of both can help the AI model to provide relevant and tailored suggestions.
+
+## Configuration options
+
+!!! example "General options"
+
+<table>
+  <tr>
+    <td><b>num_code_suggestions</b></td>
+    <td>Number of code suggestions provided by the 'improve' tool. Default is 4 for CLI, 0 for auto tools.</td>
+  </tr>
+  <tr>
+    <td><b>extra_instructions</b></td>
+    <td>Optional extra instructions to the tool. For example: "focus on the changes in the file X. Ignore change in ...".</td>
+  </tr>
+  <tr>
+    <td><b>rank_suggestions</b></td>
+    <td>If set to true, the tool will rank the suggestions, based on importance. Default is false.</td>
+  </tr>
+  <tr>
+    <td><b>commitable_code_suggestions</b></td>
+    <td>If set to true, the tool will display the suggestions as commitable code comments. Default is false.</td>
+  </tr>
+  <tr>
+    <td><b>persistent_comment</b></td>
+    <td>If set to true, the improve comment will be persistent, meaning that every new improve request will edit the previous one. Default is false.</td>
+  </tr>
+  <tr>
+    <td><b>self_reflect_on_suggestions</b></td>
+    <td>If set to true, the improve tool will calculate an importance score for each suggestion [1-10], and sort the suggestion labels group based on this score. Default is true.</td>
+  </tr>
+  <tr>
+    <td><b>suggestions_score_threshold</b></td>
+    <td> Any suggestion with importance score less than this threshold will be removed. Default is 0. Highly recommend not to set this value above 7-8, since above it may clip relevant suggestions that can be useful. </td>
+  </tr>
+  <tr>
+    <td><b>apply_suggestions_checkbox</b></td>
+    <td> Enable the checkbox to create a committable suggestion. Default is true.</td>
+  </tr>
+  <tr>
+    <td><b>enable_help_text</b></td>
+    <td>If set to true, the tool will display a help text in the comment. Default is true.</td>
+  </tr>
+</table>
+
+!!! example "params for 'extended' mode"
+
+<table>
+  <tr>
+    <td><b>auto_extended_mode</b></td>
+    <td>Enable extended mode automatically (no need for the --extended option). Default is true.</td>
+  </tr>
+  <tr>
+    <td><b>num_code_suggestions_per_chunk</b></td>
+    <td>Number of code suggestions provided by the 'improve' tool, per chunk. Default is 5.</td>
+  </tr>
+  <tr>
+    <td><b>rank_extended_suggestions</b></td>
+    <td>If set to true, the tool will rank the suggestions, based on importance. Default is true.</td>
+  </tr>
+  <tr>
+    <td><b>max_number_of_calls</b></td>
+    <td>Maximum number of chunks. Default is 5.</td>
+  </tr>
+  <tr>
+    <td><b>final_clip_factor</b></td>
+    <td>Factor to remove suggestions with low confidence. Default is 0.9.</td>
+  </tr>
+</table>

 ## A note on code suggestions quality

@ -98,6 +215,6 @@ To edit [configurations](https://github.com/Codium-ai/pr-agent/blob/main/pr_agen
    - Only if the `Category` header is relevant, the user should move to the summarized suggestion description
    - Only if the summarized suggestion description is relevant, the user should click on the collapsible, to read the full suggestion description with a code preview example.

-In addition, we recommend to use the `exra_instructions` field to guide the model to suggestions that are more relevant to the specific needs of the project. 
+In addition, we recommend to use the `extra_instructions` field to guide the model to suggestions that are more relevant to the specific needs of the project. 
 <br>
-Consider also trying the [Custom Suggestions Tool](./custom_suggestions.md) 💎, that will **only** propose suggestions that follow specific guidelines defined by user.
+Consider also trying the [Custom Prompt Tool](./custom_prompt.md) 💎, that will **only** propose code suggestions that follow specific guidelines defined by user.
--- a/docs/docs/tools/improve_component.md
+++ b/docs/docs/tools/improve_component.md
@ -8,14 +8,19 @@ it can be invoked manually by commenting on any PR:
 To get a list of the components that changed in the PR and choose the relevant component interactively, use the [`analyze`](./analyze.md) tool.


-Example result:
+## Example usage
+
+Invoke the tool manually by commenting `/improve_component` on any PR:

 ![improve_component1](https://codium.ai/images/pr_agent/improve_component1.png){width=768}

+The tool will generate code suggestions for the selected component (if no component is stated, it will generate code suggestions for the largest component):
+
 ![improve_component2](https://codium.ai/images/pr_agent/improve_component2.png){width=768}

 **Notes**
 - Language that are currently supported by the tool: Python, Java, C++, JavaScript, TypeScript, C#.
+- This tool can also be triggered interactively by using the [`analyze`](./analyze.md) tool.

 ## Configuration options
 - `num_code_suggestions`: number of code suggestions to provide. Default is 4
--- a/docs/docs/tools/index.md
+++ b/docs/docs/tools/index.md
@ -14,7 +14,7 @@ Here is a list of PR-Agent tools, each with a dedicated page that explains how t
 | **💎 [Add Documentation (`/add_docs`](./documentation.md))**                             | Generates documentation to methods/functions/classes that changed in the PR                                                                 |
 | **💎 [Generate Custom Labels (`/generate_labels`](./custom_labels.md))**                 | Generates custom labels for the PR, based on specific guidelines defined by the user                                                        |
 | **💎 [Analyze (`/analyze`](./analyze.md))**                                              | Identify code components that changed in the PR, and enables to interactively generate tests, docs, and code suggestions for each component |
-| **💎 [Custom Suggestions (`/custom_suggestions`](./custom_suggestions.md))**             | Automatically generates custom suggestions for improving the PR code, based on specific guidelines defined by the user                      |
+| **💎 [Custom Prompt (`/custom_prompt`](./custom_prompt.md))**                            | Automatically generates custom suggestions for improving the PR code, based on specific guidelines defined by the user                      |
 | **💎 [Generate Tests (`/test component_name`](./test.md))**                              | Automatically generates unit tests for a selected component, based on the PR code changes                                                   |
 | **💎 [Improve Component (`/improve_component component_name`](./improve_component.md))** | Generates code suggestions for a specific code component that changed in the PR                                                             |
 | **💎 [CI Feedback (`/checks ci_job`](./ci_feedback.md))**                                | Automatically generates feedback and analysis for a failed CI job                                                                           |
--- a/docs/docs/tools/review.md
+++ b/docs/docs/tools/review.md
@ -1,89 +1,192 @@
 ## Overview
-The `review` tool scans the PR code changes, and automatically generates a PR review.
+The `review` tool scans the PR code changes, and generates a list of feedbacks about the PR, aiming to aid the reviewing process.
+<br>
 The tool can be triggered automatically every time a new PR is [opened](../usage-guide/automations_and_usage.md#github-app-automatic-tools-when-a-new-pr-is-opened), or can be invoked manually by commenting on any PR:
 ```
 /review
 ```
-For example:
+
+Note that the main purpose of the `review` tool is to provide the **PR reviewer** with useful feedbacks and insights. The PR author, in contrast, may prefer to save time and focus on the output of the [improve](./improve.md) tool, which provides actionable code suggestions.
+
+## Example usage
+
+### Manual triggering
+
+Invoke the tool manually by commenting `/review` on any PR:

 ![review comment](https://codium.ai/images/pr_agent/review_comment.png){width=512}

+After ~30 seconds, the tool will generate a review for the PR:
+
 ![review](https://codium.ai/images/pr_agent/review3.png){width=512}

-
-## Configuration options
-
-### General configurations
-
-To edit [configurations](https://github.com/Codium-ai/pr-agent/blob/main/pr_agent/settings/configuration.toml#L19)  related to the review tool (`pr_reviewer` section), use the following template:
+If you want to edit [configurations](#configuration-options), add the relevant ones to the command:
 ```
 /review --pr_reviewer.some_config1=... --pr_reviewer.some_config2=...
 ```

+### Automatic triggering
+
+To run the `review` automatically when a PR is opened, define in a [configuration file](https://pr-agent-docs.codium.ai/usage-guide/configuration_options/#wiki-configuration-file):
+```
+[github_app]
+pr_commands = [
+    "/review",
+    ...
+]
+
+[pr_reviewer]
+num_code_suggestions = ...
+...
+```
+
+- The `pr_commands` lists commands that will be executed automatically when a PR is opened.
+- The `[pr_reviewer]` section contains the configurations for the `review` tool you want to edit (if any).
+
+[//]: # ()
+[//]: # (### Incremental Mode)
+
+[//]: # (Incremental review only considers changes since the last PR-Agent review. This can be useful when working on the PR in an iterative manner, and you want to focus on the changes since the last review instead of reviewing the entire PR again.)
+
+[//]: # (For invoking the incremental mode, the following command can be used:)
+
+[//]: # (```)
+
+[//]: # (/review -i)
+
+[//]: # (```)
+
+[//]: # (Note that the incremental mode is only available for GitHub.)
+
+[//]: # ()
+[//]: # (![incremental review]&#40;https://codium.ai/images/pr_agent/incremental_review_2.png&#41;{width=512})
+
+[//]: # (### PR Reflection)
+
+[//]: # ()
+[//]: # (By invoking:)
+
+[//]: # (```)
+
+[//]: # (/reflect_and_review)
+
+[//]: # (```)
+
+[//]: # (The tool will first ask the author questions about the PR, and will guide the review based on their answers.)
+
+[//]: # ()
+[//]: # (![reflection questions]&#40;https://codium.ai/images/pr_agent/reflection_questions.png&#41;{width=512})
+
+[//]: # ()
+[//]: # (![reflection answers]&#40;https://codium.ai/images/pr_agent/reflection_answers.png&#41;{width=512})
+
+[//]: # ()
+[//]: # (![reflection insights]&#40;https://codium.ai/images/pr_agent/reflection_insights.png&#41;{width=512})
+
+
+
+## Configuration options
+
 !!! example "General options"
-    - `num_code_suggestions`: number of code suggestions provided by the 'review' tool. For manual comments, default is 4. For [PR-Agent app](https://github.com/Codium-ai/pr-agent/blob/main/pr_agent/settings/configuration.toml#L142) auto tools, default is 0, meaning no code suggestions will be provided by the review tool, unless you manually edit `pr_commands`.
-    - `inline_code_comments`: if set to true, the tool will publish the code suggestions as comments on the code diff. Default is false.
-    - `persistent_comment`: if set to true, the review comment will be persistent, meaning that every new review request will edit the previous one. Default is true.
-    - `extra_instructions`: Optional extra instructions to the tool. For example: "focus on the changes in the file X. Ignore change in ...".
-    - `enable_help_text`: if set to true, the tool will display a help text in the comment. Default is true.

-!!! example "Enable\\disable sub-sections"
-    You can enable or disable specific sub-sections of the review tool:
+<table>
+  <tr>
+    <td><b>num_code_suggestions</b></td>
+    <td>Number of code suggestions provided by the 'review' tool. Default is 0, meaning no code suggestions will be provided by the `review` tool.</td>
+  </tr>
+  <tr>
+    <td><b>inline_code_comments</b></td>
+    <td>If set to true, the tool will publish the code suggestions as comments on the code diff. Default is false. Note that you need to set `num_code_suggestions`>0 to get code suggestions </td>
+  </tr>
+  <tr>
+    <td><b>persistent_comment</b></td>
+    <td>If set to true, the review comment will be persistent, meaning that every new review request will edit the previous one. Default is true.</td>
+  </tr>
+  <tr>
+    <td><b>extra_instructions</b></td>
+    <td>Optional extra instructions to the tool. For example: "focus on the changes in the file X. Ignore change in ...".</td>
+  </tr>
+  <tr>
+    <td><b>enable_help_text</b></td>
+    <td>If set to true, the tool will display a help text in the comment. Default is true.</td>
+  </tr>
+</table>

-    - `require_score_review`: if set to true, the tool will add a section that scores the PR. Default is false.
-    - `require_tests_review`: if set to true, the tool will add a section that checks if the PR contains tests. Default is true.
-    - `require_estimate_effort_to_review`: if set to true, the tool will add a section that estimates the effort needed to review the PR. Default is true.
-    - `require_can_be_split_review`: if set to true, the tool will add a section that checks if the PR contains several themes, and can be split into smaller PRs. Default is false.
+!!! example "Enable\\disable specific sub-sections"
+
+<table>
+  <tr>
+    <td><b>require_score_review</b></td>
+    <td>If set to true, the tool will add a section that scores the PR. Default is false.</td>
+  </tr>
+  <tr>
+    <td><b>require_tests_review</b></td>
+    <td>If set to true, the tool will add a section that checks if the PR contains tests. Default is true.</td>
+  </tr>
+  <tr>
+    <td><b>require_estimate_effort_to_review</b></td>
+    <td>If set to true, the tool will add a section that estimates the effort needed to review the PR. Default is true.</td>
+  </tr>
+  <tr>
+    <td><b>require_can_be_split_review</b></td>
+    <td>If set to true, the tool will add a section that checks if the PR contains several themes, and can be split into smaller PRs. Default is false.</td>
+  </tr>
+  <tr>
+    <td><b>require_security_review</b></td>
+    <td>If set to true, the tool will add a section that checks if the PR contains a possible security or vulnerability issue. Default is true.</td>
+  </tr>
+</table>

 !!! example "SOC2 ticket compliance 💎"

 This sub-tool checks if the PR description properly contains a ticket to a project management system (e.g., Jira, Asana, Trello, etc.), as required by SOC2 compliance. If not, it will add a label to the PR: "Missing SOC2 ticket".
    
-    - `require_soc2_ticket`: If set to true, the SOC2 ticket checker sub-tool will be enabled. Default is false.
-    - `soc2_ticket_prompt`: The prompt for the SOC2 ticket review. Default is: `Does the PR description include a link to ticket in a project management system (e.g., Jira, Asana, Trello, etc.) ?`. Edit this field if your compliance requirements are different.
+<table>
+  <tr>
+    <td><b>require_soc2_ticket</b></td>
+    <td>If set to true, the SOC2 ticket checker sub-tool will be enabled. Default is false.</td>
+  </tr>
+  <tr>
+    <td><b>soc2_ticket_prompt</b></td>
+    <td>The prompt for the SOC2 ticket review. Default is: `Does the PR description include a link to ticket in a project management system (e.g., Jira, Asana, Trello, etc.) ?`. Edit this field if your compliance requirements are different.</td>
+  </tr>
+</table>

 !!! example "Adding PR labels"
-    You can enable the tool to add specific labels to the PR:

-    - `enable_review_labels_security`: if set to true, the tool will publish a 'possible security issue' label if it detects a security issue. Default is true.
-    - `enable_review_labels_effort`: if set to true, the tool will publish a 'Review effort [1-5]: x' label. Default is true.
+You can enable\disable the `review` tool to add specific labels to the PR:
+
+<table>
+  <tr>
+    <td><b>enable_review_labels_security</b></td>
+    <td>If set to true, the tool will publish a 'possible security issue' label if it detects a security issue. Default is true.</td>
+  </tr>
+  <tr>
+    <td><b>enable_review_labels_effort</b></td>
+    <td>If set to true, the tool will publish a 'Review effort [1-5]: x' label. Default is true.</td>
+  </tr>
+</table>

 !!! example "Auto-approval"
-    The review tool can approve a PR when a specific comment, `/review auto_approve` is invoked.

-    - `enable_auto_approval`: if set to true, the tool will approve the PR when invoked with the 'auto_approve' command. Default is false. This flag can be changed only from configuration file.
-    - `maximal_review_effort`: maximal effort level for auto-approval. If the PR's estimated review effort is above this threshold, the auto-approval will not run. Default is 5.
-
-### Incremental Mode
-Incremental review only considers changes since the last PR-Agent review. This can be useful when working on the PR in an iterative manner, and you want to focus on the changes since the last review instead of reviewing the entire PR again.
-For invoking the incremental mode, the following command can be used:
-```
-/review -i
-```
-Note that the incremental mode is only available for GitHub.
-
-![incremental review](https://codium.ai/images/pr_agent/incremental_review_2.png){width=512}
-
-### PR Reflection
-
-By invoking:
-```
-/reflect_and_review
-```
-The tool will first ask the author questions about the PR, and will guide the review based on their answers.
-
-![reflection questions](https://codium.ai/images/pr_agent/reflection_questions.png){width=512}
-
-![reflection answers](https://codium.ai/images/pr_agent/reflection_answers.png){width=512}
-
-![reflection insights](https://codium.ai/images/pr_agent/reflection_insights.png){width=512}
+If enabled, the `review` tool can approve a PR when a specific comment, `/review auto_approve`, is invoked.

+<table>
+  <tr>
+    <td><b>enable_auto_approval</b></td>
+    <td>If set to true, the tool will approve the PR when invoked with the 'auto_approve' command. Default is false. This flag can be changed only from a configuration file.</td>
+  </tr>
+  <tr>
+    <td><b>maximal_review_effort</b></td>
+    <td>Maximal effort level for auto-approval. If the PR's estimated review effort is above this threshold, the auto-approval will not run. Default is 5.</td>
+  </tr>
+</table>

 ## Usage Tips

 !!! tip "General guidelines"

-    The `review` tool provides a collection of possible feedbacks about a PR.
+    The `review` tool provides a collection of configurable feedbacks about a PR.
    It is recommended to review the [Configuration options](#configuration-options) section, and choose the relevant options for your use case.
    
    Some of the features that are disabled by default are quite useful, and should be considered for enabling. For example: 
@ -97,14 +200,7 @@ The tool will first ask the author questions about the PR, and will guide the re
    pr_commands = ["/review --pr_reviewer.num_code_suggestions=0", ...]
    ```
    Meaning the `review` tool will run automatically on every PR, without providing code suggestions.
-    Edit this field to enable/disable the tool, or to change the used configurations.
-
-!!! tip  "Code suggestions"
-
-    If you set `num_code_suggestions`>0 , the `review` tool will also provide code suggestions.
-    
-    Notice If you are interested **only** in the code suggestions, it is recommended to use the [`improve`](./improve.md) feature instead, since it is a dedicated only to code suggestions, and usually gives better results.
-    Use the `review` tool if you want to get more comprehensive feedback, which includes code suggestions as well.
+    Edit this field to enable/disable the tool, or to change the configurations used.

 !!! tip "Possible labels from the review tool"

@ -122,7 +218,7 @@ The tool will first ask the author questions about the PR, and will guide the re
    
    Be specific, clear, and concise in the instructions. With extra instructions, you are the prompter. Specify the relevant sub-tool, and the relevant aspects of the PR that you want to emphasize.
    
-    Examples for extra instructions:
+    Examples of extra instructions:
    ```
    [pr_reviewer]
    extra_instructions="""\
@ -160,3 +256,14 @@ The tool will first ask the author questions about the PR, and will guide the re
    [pr_reviewer]
    maximal_review_effort = 5
    ```
+
+[//]: # (!!! tip  "Code suggestions")
+
+[//]: # ()
+[//]: # (    If you set `num_code_suggestions`>0 , the `review` tool will also provide code suggestions.)
+
+[//]: # (    )
+[//]: # (    Notice If you are interested **only** in the code suggestions, it is recommended to use the [`improve`]&#40;./improve.md&#41; feature instead, since it is a dedicated only to code suggestions, and usually gives better results.)
+
+[//]: # (    Use the `review` tool if you want to get more comprehensive feedback, which includes code suggestions as well.)
+
--- a/docs/docs/tools/similar_issues.md
+++ b/docs/docs/tools/similar_issues.md
@ -4,7 +4,9 @@ It can be invoked manually by commenting on any PR:
 ```
 /similar_issue
 ```
-For example:
+
+
+## Example usage

 ![similar_issue_original_issue](https://codium.ai/images/pr_agent/similar_issue_original_issue.png){width=768}

@ -31,7 +33,7 @@ environment = "..."
 These parameters can be obtained by registering to [Pinecone](https://app.pinecone.io/?sessionType=signup/).


-## How to use:
+## How to use
 - To invoke the 'similar issue' tool from **CLI**, run:
 `python3 cli.py --issue_url=... similar_issue`

--- a/docs/docs/tools/test.md
+++ b/docs/docs/tools/test.md
@ -7,17 +7,23 @@ It can be invoked manually by commenting on any PR:
 where 'component_name' is the name of a specific component in the PR.
 To get a list of the components that changed in the PR and choose the relevant component interactively, use the [`analyze`](./analyze.md) tool.

+## Example usage

-An example [result](https://github.com/Codium-ai/pr-agent/pull/598#issuecomment-1913679429):
+Invoke the tool manually by commenting `/test` on any PR:

 ![test1](https://codium.ai/images/pr_agent/test1.png){width=704}

+The tool will generate tests for the selected component (if no component is stated, it will generate tests for largest component):
+
 ![test2](https://codium.ai/images/pr_agent/test2.png){width=768}

 ![test3](https://codium.ai/images/pr_agent/test3.png){width=768}

+(Example taken from [here](https://github.com/Codium-ai/pr-agent/pull/598#issuecomment-1913679429)):
+
 **Notes**
 - Language that are currently supported by the tool: Python, Java, C++, JavaScript, TypeScript, C#.
+- This tool can also be triggered interactively by using the [`analyze`](./analyze.md) tool.


 ## Configuration options
--- a/docs/docs/tools/update_changelog.md
+++ b/docs/docs/tools/update_changelog.md
@ -4,7 +4,8 @@ It can be invoked manually by commenting on any PR:
 ```
 /update_changelog
 ```
-For example:
+
+## Example usage

 ![update_changelog_comment](https://codium.ai/images/pr_agent/update_changelog_comment.png){width=768}

@ -12,7 +13,7 @@ For example:

 ## Configuration options

-Under the section 'pr_update_changelog', the [configuration file](https://github.com/Codium-ai/pr-agent/blob/main/pr_agent/settings/configuration.toml#L50) contains options to customize the 'update changelog' tool:
+Under the section `pr_update_changelog`, the [configuration file](https://github.com/Codium-ai/pr-agent/blob/main/pr_agent/settings/configuration.toml#L50) contains options to customize the 'update changelog' tool:

 - `push_changelog_changes`: whether to push the changes to CHANGELOG.md, or just print them. Default is false (print only).
 - `extra_instructions`: Optional extra instructions to the tool. For example: "focus on the changes in the file X. Ignore change in ...
--- a/docs/docs/usage-guide/EXAMPLE_BEST_PRACTICE.md
+++ b/docs/docs/usage-guide/EXAMPLE_BEST_PRACTICE.md
@ -0,0 +1,189 @@
+## Recommend Python Best Practices
+This document outlines a series of recommended best practices for Python development. These guidelines aim to improve code quality, maintainability, and readability.
+
+###  Imports
+
+Use  `import`  statements for packages and modules only, not for individual types, classes, or functions.
+
+#### Definition
+
+Reusability mechanism for sharing code from one module to another.
+
+####  Decision
+
+-   Use  `import x`  for importing packages and modules.
+-   Use  `from x import y`  where  `x`  is the package prefix and  `y`  is the module name with no prefix.
+-   Use  `from x import y as z`  in any of the following circumstances:
+    -   Two modules named  `y`  are to be imported.
+    -   `y`  conflicts with a top-level name defined in the current module.
+    -   `y`  conflicts with a common parameter name that is part of the public API (e.g.,  `features`).
+    -   `y`  is an inconveniently long name, or too generic in the context of your code
+-   Use  `import y as z`  only when  `z`  is a standard abbreviation (e.g.,  `import numpy as np`).
+
+For example the module  `sound.effects.echo`  may be imported as follows:
+
+```
+from sound.effects import echo
+...
+echo.EchoFilter(input, output, delay=0.7, atten=4)
+
+```
+
+Do not use relative names in imports. Even if the module is in the same package, use the full package name. This helps prevent unintentionally importing a package twice.
+
+##### Exemptions
+
+Exemptions from this rule:
+
+-   Symbols from the following modules are used to support static analysis and type checking:
+    -   [`typing`  module](https://google.github.io/styleguide/pyguide.html#typing-imports)
+    -   [`collections.abc`  module](https://google.github.io/styleguide/pyguide.html#typing-imports)
+    -   [`typing_extensions`  module](https://github.com/python/typing_extensions/blob/main/README.md)
+-   Redirects from the  [six.moves module](https://six.readthedocs.io/#module-six.moves).
+
+###  Packages
+
+Import each module using the full pathname location of the module.
+
+#### Decision
+
+All new code should import each module by its full package name.
+
+Imports should be as follows:
+
+```
+Yes:
+  # Reference absl.flags in code with the complete name (verbose).
+  import absl.flags
+  from doctor.who import jodie
+
+  _FOO = absl.flags.DEFINE_string(...)
+
+```
+
+```
+Yes:
+  # Reference flags in code with just the module name (common).
+  from absl import flags
+  from doctor.who import jodie
+
+  _FOO = flags.DEFINE_string(...)
+
+```
+
+_(assume this file lives in  `doctor/who/`  where  `jodie.py`  also exists)_
+
+```
+No:
+  # Unclear what module the author wanted and what will be imported.  The actual
+  # import behavior depends on external factors controlling sys.path.
+  # Which possible jodie module did the author intend to import?
+  import jodie
+
+```
+
+The directory the main binary is located in should not be assumed to be in  `sys.path`  despite that happening in some environments. This being the case, code should assume that  `import jodie`  refers to a third-party or top-level package named  `jodie`, not a local  `jodie.py`.
+
+### Default Iterators and Operators
+Use default iterators and operators for types that support them, like lists, dictionaries, and files.
+
+#### Definition
+
+Container types, like dictionaries and lists, define default iterators and membership test operators (“in” and “not in”).
+
+#### Decision
+
+Use default iterators and operators for types that support them, like lists, dictionaries, and files. The built-in types define iterator methods, too. Prefer these methods to methods that return lists, except that you should not mutate a container while iterating over it.
+
+```
+Yes:  for key in adict: ...
+      if obj in alist: ...
+      for line in afile: ...
+      for k, v in adict.items(): ...
+```
+
+```
+No:   for key in adict.keys(): ...
+      for line in afile.readlines(): ...
+```
+
+### Lambda Functions
+
+Okay for one-liners. Prefer generator expressions over  `map()`  or  `filter()`  with a  `lambda`.
+
+#### Decision
+
+Lambdas are allowed. If the code inside the lambda function spans multiple lines or is longer than 60-80 chars, it might be better to define it as a regular  [nested function](https://google.github.io/styleguide/pyguide.html#lexical-scoping).
+
+For common operations like multiplication, use the functions from the  `operator`  module instead of lambda functions. For example, prefer  `operator.mul`  to  `lambda x, y: x * y`.
+
+### Default Argument Values
+
+Okay in most cases.
+
+#### Definition
+
+You can specify values for variables at the end of a function’s parameter list, e.g.,  `def foo(a, b=0):`. If  `foo`  is called with only one argument,  `b`  is set to 0. If it is called with two arguments,  `b`  has the value of the second argument.
+
+####  Decision
+
+Okay to use with the following caveat:
+
+Do not use mutable objects as default values in the function or method definition.
+
+```
+Yes: def foo(a, b=None):
+         if b is None:
+             b = []
+Yes: def foo(a, b: Sequence | None = None):
+         if b is None:
+             b = []
+Yes: def foo(a, b: Sequence = ()):  # Empty tuple OK since tuples are immutable.
+         ...
+```
+
+```
+from absl import flags
+_FOO = flags.DEFINE_string(...)
+
+No:  def foo(a, b=[]):
+         ...
+No:  def foo(a, b=time.time()):  # Is `b` supposed to represent when this module was loaded?
+         ...
+No:  def foo(a, b=_FOO.value):  # sys.argv has not yet been parsed...
+         ...
+No:  def foo(a, b: Mapping = {}):  # Could still get passed to unchecked code.
+         ...
+```
+
+### True/False Evaluations
+
+
+Use the “implicit” false if possible, e.g.,  `if foo:`  rather than  `if foo != []:`
+
+### Lexical Scoping
+
+Okay to use.
+
+An example of the use of this feature is:
+
+```
+def get_adder(summand1: float) -> Callable[[float], float]:
+    """Returns a function that adds numbers to a given number."""
+    def adder(summand2: float) -> float:
+        return summand1 + summand2
+
+    return adder
+```
+#### Decision
+
+Okay to use.
+
+
+### Threading
+
+Do not rely on the atomicity of built-in types.
+
+While Python’s built-in data types such as dictionaries appear to have atomic operations, there are corner cases where they aren’t atomic (e.g. if  `__hash__`  or  `__eq__`  are implemented as Python methods) and their atomicity should not be relied upon. Neither should you rely on atomic variable assignment (since this in turn depends on dictionaries).
+
+Use the  `queue`  module’s  `Queue`  data type as the preferred way to communicate data between threads. Otherwise, use the  `threading`  module and its locking primitives. Prefer condition variables and  `threading.Condition`  instead of using lower-level locks.
--- a/docs/docs/usage-guide/PR_agent_pro_models.md
+++ b/docs/docs/usage-guide/PR_agent_pro_models.md
@ -0,0 +1,30 @@
+## PR-Agent Pro Models
+
+The default models used by PR-Agent Pro are OpenAI's GPT-4 models. We use a combination of GPT-4-Turbo and GPT-4o to strike a balance between speed and quality.
+
+However, users can change the model used by PR-Agent Pro to Claude-3.5-sonnet, which also excels at code tasks. 
+To do so, add the following to your [configuration](https://pr-agent-docs.codium.ai/usage-guide/configuration_options/) file:
+
+```
+[config]
+model="claude-3-5-sonnet"
+```
+
+Note that Claude models tend to give lower scores for each suggestion, so if you are using a [threshold](https://pr-agent-docs.codium.ai/tools/improve/#configuration-options):
+```
+[pr_code_suggestions]
+suggestions_score_threshold=...
+```
+You might need to adjust this value when switching models.
+
+### Dedicated models per tool
+
+You can also use different models for different tools. For example, you can use the Claude-3.5-sonnet model only for the `improve` tool (and keep the default GPT-4 model for the other tools) by adding the following to your configuration file:
+```
+[github_app]
+pr_commands = [
+    "/describe --pr_description.final_update_message=false",
+    "/review --pr_reviewer.num_code_suggestions=0",
+    "/improve --config.model=claude-3-5-sonnet",
+]
+```
--- a/docs/docs/usage-guide/additional_configurations.md
+++ b/docs/docs/usage-guide/additional_configurations.md
@ -2,20 +2,32 @@

 In some cases, you may want to exclude specific files or directories from the analysis performed by CodiumAI PR-Agent. This can be useful, for example, when you have files that are generated automatically or files that shouldn't be reviewed, like vendored code.

-To ignore files or directories, edit the **[ignore.toml](https://github.com/Codium-ai/pr-agent/blob/main/pr_agent/settings/ignore.toml)** configuration file. This setting also exposes the following environment variables:
-
+You can ignore files or folders using the following methods:
 - `IGNORE.GLOB`
 - `IGNORE.REGEX`

-For example, to ignore Python files in a PR with online usage, comment on a PR:
-`/review --ignore.glob=['*.py']`
+which you can edit to ignore files or folders based on glob or regex patterns.

-To ignore Python files in all PRs, set in a configuration file:
+### Example usage
+
+Let's look at an example where we want to ignore all files with `.py` extension from the analysis.
+
+To ignore Python files in a PR with online usage, comment on a PR:
+`/review --ignore.glob="['*.py']"`
+
+
+To ignore Python files in all PRs using `glob` pattern, set in a configuration file:
 ```
 [ignore]
 glob = ['*.py']
 ```

+And to ignore Python files in all PRs using `regex` pattern, set in a configuration file:
+```
+[regex]
+regex = ['.*\.py$']
+```
+
 ## Extra instructions

 All PR-Agent tools have a parameter called `extra_instructions`, that enables to add free-text extra instructions. Example usage:
@ -35,155 +47,6 @@ However, for very large PRs, or in case you want to emphasize quality over speed
 which divides the PR to chunks, and processes each chunk separately. With this mode, regardless of the model, no compression will be done (but for large PRs, multiple model calls may occur)


-## Changing a model
-
-See [here](https://github.com/Codium-ai/pr-agent/blob/main/pr_agent/algo/__init__.py) for the list of available models.
-To use a different model than the default (GPT-4), you need to edit [configuration file](https://github.com/Codium-ai/pr-agent/blob/main/pr_agent/settings/configuration.toml#L2).
-For models and environments not from OPENAI, you might need to provide additional keys and other parameters. See below for instructions.
-
-### Azure
-
-To use Azure, set in your `.secrets.toml` (working from CLI), or in the GitHub `Settings > Secrets and variables` (working from GitHub App or GitHub Action):
-```
-[openai]
-key = "" # your azure api key
-api_type = "azure"
-api_version = '2023-05-15'  # Check Azure documentation for the current API version
-api_base = ""  # The base URL for your Azure OpenAI resource. e.g. "https://<your resource name>.openai.azure.com"
-deployment_id = ""  # The deployment name you chose when you deployed the engine
-```
-
-and set in your configuration file:
-```
-[config]
-model="" # the OpenAI model you've deployed on Azure (e.g. gpt-3.5-turbo)
-```
-
-### Huggingface
-
-**Local**
-You can run Huggingface models locally through either [VLLM](https://docs.litellm.ai/docs/providers/vllm) or [Ollama](https://docs.litellm.ai/docs/providers/ollama)
-
-E.g. to use a new Huggingface model locally via Ollama, set:
-```
-[__init__.py]
-MAX_TOKENS = {
-    "model-name-on-ollama": <max_tokens>
-}
-e.g.
-MAX_TOKENS={
-    ...,
-    "ollama/llama2": 4096
-}
-
-
-[config] # in configuration.toml
-model = "ollama/llama2"
-model_turbo = "ollama/llama2"
-
-[ollama] # in .secrets.toml
-api_base = ... # the base url for your huggingface inference endpoint
-# e.g. if running Ollama locally, you may use:
-api_base = "http://localhost:11434/"
-```
-
-### Inference Endpoints
-
-To use a new model with Huggingface Inference Endpoints, for example, set:
-```
-[__init__.py]
-MAX_TOKENS = {
-    "model-name-on-huggingface": <max_tokens>
-}
-e.g.
-MAX_TOKENS={
-    ...,
-    "meta-llama/Llama-2-7b-chat-hf": 4096
-}
-[config] # in configuration.toml
-model = "huggingface/meta-llama/Llama-2-7b-chat-hf"
-model_turbo = "huggingface/meta-llama/Llama-2-7b-chat-hf"
-
-[huggingface] # in .secrets.toml
-key = ... # your huggingface api key
-api_base = ... # the base url for your huggingface inference endpoint
-```
-(you can obtain a Llama2 key from [here](https://replicate.com/replicate/llama-2-70b-chat/api))
-
-### Replicate
-
-To use Llama2 model with Replicate, for example, set:
-```
-[config] # in configuration.toml
-model = "replicate/llama-2-70b-chat:2c1608e18606fad2812020dc541930f2d0495ce32eee50074220b87300bc16e1"
-model_turbo = "replicate/llama-2-70b-chat:2c1608e18606fad2812020dc541930f2d0495ce32eee50074220b87300bc16e1"
-[replicate] # in .secrets.toml
-key = ...
-```
-(you can obtain a Llama2 key from [here](https://replicate.com/replicate/llama-2-70b-chat/api))
-
-
-Also, review the [AiHandler](https://github.com/Codium-ai/pr-agent/blob/main/pr_agent/algo/ai_handler.py) file for instructions on how to set keys for other models.
-
-### Vertex AI
-
-To use Google's Vertex AI platform and its associated models (chat-bison/codechat-bison) set:
-
-``` 
-[config] # in configuration.toml
-model = "vertex_ai/codechat-bison"
-model_turbo = "vertex_ai/codechat-bison"
-fallback_models="vertex_ai/codechat-bison"
-
-[vertexai] # in .secrets.toml
-vertex_project = "my-google-cloud-project"
-vertex_location = ""
-```
-
-Your [application default credentials](https://cloud.google.com/docs/authentication/application-default-credentials) will be used for authentication so there is no need to set explicit credentials in most environments.
-
-If you do want to set explicit credentials then you can use the `GOOGLE_APPLICATION_CREDENTIALS` environment variable set to a path to a json credentials file.
-
-### Anthropic
-
-To use Anthropic models, set the relevant models in the configuration section of the configuration file:
-```
-[config]
-model="anthropic/claude-3-opus-20240229"
-model_turbo="anthropic/claude-3-opus-20240229"
-fallback_models=["anthropic/claude-3-opus-20240229"]
-```
-
-And also set the api key in the .secrets.toml file:
-```
-[anthropic]
-KEY = "..."
-```
-
-### Amazon Bedrock
-
-To use Amazon Bedrock and its foundational models, add the below configuration:
-
-``` 
-[config] # in configuration.toml
-model="bedrock/anthropic.claude-3-sonnet-20240229-v1:0"
-model_turbo="bedrock/anthropic.claude-3-sonnet-20240229-v1:0"
-fallback_models=["bedrock/anthropic.claude-v2:1"]
-
-[aws] # in .secrets.toml
-bedrock_region = "us-east-1"
-```
-
-Note that you have to add access to foundational models before using them. Please refer to [this document](https://docs.aws.amazon.com/bedrock/latest/userguide/setting-up.html) for more details.
-
-If you are using the claude-3 model, please configure the following settings as there are parameters incompatible with claude-3.
-```
-[litellm]
-drop_params = true
-```
-
-AWS session is automatically authenticated from your environment, but you can also explicitly set `AWS_ACCESS_KEY_ID` and `AWS_SECRET_ACCESS_KEY` environment variables.
-

 ## Patch Extra Lines

@ -203,7 +66,8 @@ By default, around any change in your PR, git patch provides three lines of cont
 For the `review`, `describe`, `ask` and `add_docs` tools, if the token budget allows, PR-Agent tries to increase the number of lines of context, via the parameter:
 ```
 [config]
-patch_extra_lines=3
+patch_extra_lines_before=4
+patch_extra_lines_after=2
 ```

 Increasing this number provides more context to the model, but will also increase the token budget.
@ -227,3 +91,24 @@ user="""
 """
 ```
 Note that the new prompt will need to generate an output compatible with the relevant [post-process function](https://github.com/Codium-ai/pr-agent/blob/main/pr_agent/tools/pr_description.py#L137).
+
+## Integrating with Logging Observability Platforms
+
+Various logging observability tools can be used out-of-the box when using the default LiteLLM AI Handler. Simply configure the LiteLLM callback settings in `configuration.toml` and set environment variables according to the LiteLLM [documentation](https://docs.litellm.ai/docs/).
+
+For example, to use [LangSmith](https://www.langchain.com/langsmith) you can add the following to your `configuration.toml` file:
+```
+[litellm]
+enable_callbacks = true
+success_callback = ["langsmith"]
+failure_callback = ["langsmith"]
+service_callback = []
+```
+
+Then set the following environment variables:
+
+```
+LANGSMITH_API_KEY=<api_key>
+LANGSMITH_PROJECT=<project>
+LANGSMITH_BASE_URL=<url>
+```
--- a/docs/docs/usage-guide/automations_and_usage.md
+++ b/docs/docs/usage-guide/automations_and_usage.md
@ -26,6 +26,16 @@ verbosity_level=2
 ```
 This is useful for debugging or experimenting with different tools.

+(3)
+
+**git provider**: The [git_provider](https://github.com/Codium-ai/pr-agent/blob/main/pr_agent/settings/configuration.toml#L5) field in a configuration file determines the GIT provider that will be used by PR-Agent. Currently, the following providers are supported:
+`
+"github", "gitlab", "bitbucket", "azure", "codecommit", "local", "gerrit"
+`
+
+Default is "github".
+
+

 ### Online usage

@ -34,7 +44,7 @@ Commands for invoking the different tools via comments:

 - **Review**:       `/review`
 - **Describe**:     `/describe`
- **Improve**:      `/improve`
+- **Improve**:      `/improve`  (or `/improve_code` for bitbucket, since `/improve` is sometimes reserved)
 - **Ask**:          `/ask "..."`
 - **Reflect**:      `/reflect`
 - **Update Changelog**:      `/update_changelog`
@ -62,27 +72,26 @@ The configuration parameter `pr_commands` defines the list of tools that will be
 ```
 [github_app]
 pr_commands = [
-    "/describe --pr_description.add_original_user_description=true --pr_description.keep_original_user_title=true --pr_description.final_update_message=false",
+    "/describe --pr_description.final_update_message=false",
    "/review --pr_reviewer.num_code_suggestions=0",
    "/improve",
 ]
 ```
 This means that when a new PR is opened/reopened or marked as ready for review, PR-Agent will run the `describe`, `review` and `improve` tools.  
-For the `describe` tool, for example, the `add_original_user_description` and `keep_original_user_title` parameters will be set to true.
+For the `review` tool, for example, the `num_code_suggestions` parameter will be set to 0.

 You can override the default tool parameters by using one the three options for a [configuration file](https://codium-ai.github.io/Docs-PR-Agent/usage-guide/#configuration-options): **wiki**, **local**, or **global**. 
 For example, if your local `.pr_agent.toml` file contains:
 ```
 [pr_description]
-add_original_user_description = false
-keep_original_user_title = false
+generate_ai_title = true
 ```
-When a new PR is opened, PR-Agent will run the `describe` tool with the above parameters.
+Every time you run the `describe` tool, including automatic runs, the PR title will be generated by the AI.

 To cancel the automatic run of all the tools, set:
 ```
 [github_app]
-handle_pr_actions = []
+pr_commands = []
 ```

 You can also disable automatic runs for PRs with specific titles, by setting the `ignore_pr_titles` parameter with the relevant regex. For example:
@ -102,7 +111,7 @@ The configuration parameter `push_commands` defines the list of tools that will
 [github_app]
 handle_push_trigger = true
 push_commands = [
-    "/describe --pr_description.add_original_user_description=true --pr_description.keep_original_user_title=true",
+    "/describe",
    "/review  --pr_reviewer.num_code_suggestions=0 --pr_reviewer.final_update_message=false",
 ]
 ```
@ -119,7 +128,6 @@ Specifically, start by setting the following environment variables:
        github_action_config.auto_review: "true" # enable\disable auto review
        github_action_config.auto_describe: "true" # enable\disable auto describe
        github_action_config.auto_improve: "true" # enable\disable auto improve
-        github_action_config.enable_output: "true" # enable\disable github actions output parameter
 ```
 `github_action_config.auto_review`, `github_action_config.auto_describe` and `github_action_config.auto_improve` are used to enable/disable automatic tools that run when a new PR is opened.
 If not set, the default configuration is for all three tools to run automatically when a new PR is opened.
@ -138,16 +146,30 @@ publish_labels = false
 to prevent PR-Agent from publishing labels when running the `describe` tool.

 ## GitLab Webhook
-After setting up a GitLab webhook, to control which commands will run automatically when a new PR is opened, you can set the `pr_commands` parameter in the configuration file, similar to the GitHub App:
+After setting up a GitLab webhook, to control which commands will run automatically when a new MR is opened, you can set the `pr_commands` parameter in the configuration file, similar to the GitHub App:
 ```
 [gitlab]
 pr_commands = [
-    "/describe --pr_description.add_original_user_description=true --pr_description.keep_original_user_title=true",
+    "/describe",
    "/review --pr_reviewer.num_code_suggestions=0",
    "/improve",
 ]
 ```

+the GitLab webhook can also respond to new code that is pushed to an open MR.
+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 MR.
+```
+[gitlab]
+handle_push_trigger = true
+push_commands = [
+    "/describe",
+    "/review  --pr_reviewer.num_code_suggestions=0 --pr_reviewer.final_update_message=false",
+]
+```
+
+Note that to use the 'handle_push_trigger' feature, you need to give the gitlab webhook also the "Push events" scope.
+
 ## BitBucket App
 Similar to GitHub app, when running PR-Agent from BitBucket App, the default [configuration file](https://github.com/Codium-ai/pr-agent/blob/main/pr_agent/settings/configuration.toml) from a pre-built docker will be initially loaded.

@ -170,9 +192,11 @@ Specifically, set the following values:
 [bitbucket_app]
 pr_commands = [
    "/review --pr_reviewer.num_code_suggestions=0",
-    "/improve --pr_code_suggestions.summarize=false",
+    "/improve --pr_code_suggestions.commitable_code_suggestions=true --pr_code_suggestions.suggestions_score_threshold=7",
 ]
 ```
+Note that we set specifically for bitbucket, we recommend using: `--pr_code_suggestions.suggestions_score_threshold=7` and that is the default value we set for bitbucket.
+Since this platform only supports inline code suggestions, we want to limit the number of suggestions, and only present a limited number.

 ## Azure DevOps provider

@ -202,7 +226,7 @@ To control which commands will run automatically when a new PR is opened, you ca
 ```
 [azure_devops_server]
 pr_commands = [
-    "/describe --pr_description.add_original_user_description=true --pr_description.keep_original_user_title=true",
+    "/describe",
    "/review --pr_reviewer.num_code_suggestions=0",
    "/improve",
 ]
--- a/docs/docs/usage-guide/changing_a_model.md
+++ b/docs/docs/usage-guide/changing_a_model.md
@ -0,0 +1,189 @@
+## Changing a model
+
+See [here](https://github.com/Codium-ai/pr-agent/blob/main/pr_agent/algo/__init__.py) for a list of available models.
+To use a different model than the default (GPT-4), you need to edit in the [configuration file](https://github.com/Codium-ai/pr-agent/blob/main/pr_agent/settings/configuration.toml#L2) the fields:
+```
+[config]
+model = "..."
+model_turbo = "..."
+fallback_models = ["..."]
+```
+
+For models and environments not from OpenAI, you might need to provide additional keys and other parameters. 
+You can give parameters via a configuration file (see below for instructions), or from environment variables. See [litellm documentation](https://litellm.vercel.app/docs/proxy/quick_start#supported-llms) for the environment variables relevant per model.
+
+### Azure
+
+To use Azure, set in your `.secrets.toml` (working from CLI), or in the GitHub `Settings > Secrets and variables` (working from GitHub App or GitHub Action):
+```
+[openai]
+key = "" # your azure api key
+api_type = "azure"
+api_version = '2023-05-15'  # Check Azure documentation for the current API version
+api_base = ""  # The base URL for your Azure OpenAI resource. e.g. "https://<your resource name>.openai.azure.com"
+deployment_id = ""  # The deployment name you chose when you deployed the engine
+```
+
+and set in your configuration file:
+```
+[config]
+model="" # the OpenAI model you've deployed on Azure (e.g. gpt-3.5-turbo)
+model_turbo="" # the OpenAI model you've deployed on Azure (e.g. gpt-3.5-turbo)
+fallback_models=["..."] # the OpenAI model you've deployed on Azure (e.g. gpt-3.5-turbo)
+```
+
+### Hugging Face
+
+**Local**
+You can run Hugging Face models locally through either [VLLM](https://docs.litellm.ai/docs/providers/vllm) or [Ollama](https://docs.litellm.ai/docs/providers/ollama)
+
+E.g. to use a new Hugging Face model locally via Ollama, set:
+```
+[__init__.py]
+MAX_TOKENS = {
+    "model-name-on-ollama": <max_tokens>
+}
+e.g.
+MAX_TOKENS={
+    ...,
+    "ollama/llama2": 4096
+}
+
+
+[config] # in configuration.toml
+model = "ollama/llama2"
+model_turbo = "ollama/llama2"
+fallback_models=["ollama/llama2"]
+
+[ollama] # in .secrets.toml
+api_base = ... # the base url for your Hugging Face inference endpoint
+# e.g. if running Ollama locally, you may use:
+api_base = "http://localhost:11434/"
+```
+
+### Inference Endpoints
+
+To use a new model with Hugging Face Inference Endpoints, for example, set:
+```
+[__init__.py]
+MAX_TOKENS = {
+    "model-name-on-huggingface": <max_tokens>
+}
+e.g.
+MAX_TOKENS={
+    ...,
+    "meta-llama/Llama-2-7b-chat-hf": 4096
+}
+[config] # in configuration.toml
+model = "huggingface/meta-llama/Llama-2-7b-chat-hf"
+model_turbo = "huggingface/meta-llama/Llama-2-7b-chat-hf"
+fallback_models=["huggingface/meta-llama/Llama-2-7b-chat-hf"]
+
+[huggingface] # in .secrets.toml
+key = ... # your Hugging Face api key
+api_base = ... # the base url for your Hugging Face inference endpoint
+```
+(you can obtain a Llama2 key from [here](https://replicate.com/replicate/llama-2-70b-chat/api))
+
+### Replicate
+
+To use Llama2 model with Replicate, for example, set:
+```
+[config] # in configuration.toml
+model = "replicate/llama-2-70b-chat:2c1608e18606fad2812020dc541930f2d0495ce32eee50074220b87300bc16e1"
+model_turbo = "replicate/llama-2-70b-chat:2c1608e18606fad2812020dc541930f2d0495ce32eee50074220b87300bc16e1"
+fallback_models=["replicate/llama-2-70b-chat:2c1608e18606fad2812020dc541930f2d0495ce32eee50074220b87300bc16e1"]
+[replicate] # in .secrets.toml
+key = ...
+```
+(you can obtain a Llama2 key from [here](https://replicate.com/replicate/llama-2-70b-chat/api))
+
+
+Also, review the [AiHandler](https://github.com/Codium-ai/pr-agent/blob/main/pr_agent/algo/ai_handler.py) file for instructions on how to set keys for other models.
+
+### Groq
+
+To use Llama3 model with Groq, for example, set:
+```
+[config] # in configuration.toml
+model = "llama3-70b-8192"
+model_turbo = "llama3-70b-8192"
+fallback_models = ["groq/llama3-70b-8192"] 
+[groq] # in .secrets.toml
+key = ... # your Groq api key
+```
+(you can obtain a Groq key from [here](https://console.groq.com/keys))
+
+### Vertex AI
+
+To use Google's Vertex AI platform and its associated models (chat-bison/codechat-bison) set:
+
+``` 
+[config] # in configuration.toml
+model = "vertex_ai/codechat-bison"
+model_turbo = "vertex_ai/codechat-bison"
+fallback_models="vertex_ai/codechat-bison"
+
+[vertexai] # in .secrets.toml
+vertex_project = "my-google-cloud-project"
+vertex_location = ""
+```
+
+Your [application default credentials](https://cloud.google.com/docs/authentication/application-default-credentials) will be used for authentication so there is no need to set explicit credentials in most environments.
+
+If you do want to set explicit credentials, then you can use the `GOOGLE_APPLICATION_CREDENTIALS` environment variable set to a path to a json credentials file.
+
+### Anthropic
+
+To use Anthropic models, set the relevant models in the configuration section of the configuration file:
+```
+[config]
+model="anthropic/claude-3-opus-20240229"
+model_turbo="anthropic/claude-3-opus-20240229"
+fallback_models=["anthropic/claude-3-opus-20240229"]
+```
+
+And also set the api key in the .secrets.toml file:
+```
+[anthropic]
+KEY = "..."
+```
+
+### Amazon Bedrock
+
+To use Amazon Bedrock and its foundational models, add the below configuration:
+
+``` 
+[config] # in configuration.toml
+model="bedrock/anthropic.claude-3-sonnet-20240229-v1:0"
+model_turbo="bedrock/anthropic.claude-3-sonnet-20240229-v1:0"
+fallback_models=["bedrock/anthropic.claude-v2:1"]
+```
+
+Note that you have to add access to foundational models before using them. Please refer to [this document](https://docs.aws.amazon.com/bedrock/latest/userguide/setting-up.html) for more details.
+
+If you are using the claude-3 model, please configure the following settings as there are parameters incompatible with claude-3.
+```
+[litellm]
+drop_params = true
+```
+
+AWS session is automatically authenticated from your environment, but you can also explicitly set `AWS_ACCESS_KEY_ID`, `AWS_SECRET_ACCESS_KEY` and `AWS_REGION_NAME` environment variables. Please refer to [this document](https://litellm.vercel.app/docs/providers/bedrock) for more details.
+
+### Custom models
+
+If the relevant model doesn't appear [here](https://github.com/Codium-ai/pr-agent/blob/main/pr_agent/algo/__init__.py), you can still use it as a custom model:
+
+(1) Set the model name in the configuration file:
+```
+[config]
+model="custom_model_name"
+model_turbo="custom_model_name"
+fallback_models=["custom_model_name"]
+```
+(2) Set the maximal tokens for the model:
+```
+[config]
+custom_model_max_tokens= ...
+```
+(3) Go to [litellm documentation](https://litellm.vercel.app/docs/proxy/quick_start#supported-llms), find the model you want to use, and set the relevant environment variables.
--- a/docs/docs/usage-guide/configuration_options.md
+++ b/docs/docs/usage-guide/configuration_options.md
@ -11,25 +11,36 @@ There are three ways to set persistent configurations:

 In terms of precedence, wiki configurations will override local configurations, and local configurations will override global configurations.

+!!! tip "Tip1: edit only what you need"
+    Your configuration file should be minimal, and edit only the relevant values. Don't copy the entire configuration options, since it can lead to legacy problems when something changes.
+!!! tip "Tip2: show relevant configurations"
+    If you set `config.output_relevant_configurations=true`, each tool will also output in a collapsible section its relevant configurations. This can be useful for debugging, or getting to know the configurations better.
+
 ## Wiki configuration file 💎

-Specifically for GitHub, with PR-Agent-Pro you can set configurations by creating a page called `.pr_agent.toml` in the [wiki](https://github.com/Codium-ai/pr-agent/wiki/pr_agent.toml) of the repo. 
+`Platforms supported: GitHub, GitLab`
+
+With PR-Agent-Pro, you can set configurations by creating a page called `.pr_agent.toml` in the [wiki](https://github.com/Codium-ai/pr-agent/wiki/pr_agent.toml) of the repo. 
 The advantage of this method is that it allows to set configurations without needing to commit new content to the repo - just edit the wiki page and **save**.

+
 ![wiki_configuration](https://codium.ai/images/pr_agent/wiki_configuration.png){width=512}

-Click [here](https://codium.ai/images/pr_agent/wiki_configuration_pr_agent.mp4) to see a short instructional video. We recommend surrounding the configuration content with triple-quotes, to allow better presentation when displayed in the wiki as markdown.
+Click [here](https://codium.ai/images/pr_agent/wiki_configuration_pr_agent.mp4) to see a short instructional video. We recommend surrounding the configuration content with triple-quotes (or \`\`\`toml), to allow better presentation when displayed in the wiki as markdown.
 An example content:

-```
+```toml
 [pr_description]
-keep_original_user_title=false
+generate_ai_title=true
 ```

-PR-Agent will know to remove the triple-quotes when reading the configuration content.
+PR-Agent will know to remove the surrounding quotes when reading the configuration content.

 ## Local configuration file

+`Platforms supported: GitHub, GitLab, Bitbucket, Azure DevOps`
+
+
 By uploading a local `.pr_agent.toml` file to the root of the repo's main branch, you can edit and customize any configuration parameter. Note that you need to upload `.pr_agent.toml` prior to creating a PR, in order for the configuration to take effect.

 For example, if you set in `.pr_agent.toml`:
@ -48,9 +59,13 @@ Then you can give a list of extra instructions to the `review` tool.

 ## Global configuration file 💎

+`Platforms supported: GitHub, GitLab, Bitbucket`
+
 If you create a repo called `pr-agent-settings` in your **organization**, it's configuration file `.pr_agent.toml` will be used as a global configuration file for any other repo that belongs to the same organization.
 Parameters from a local `.pr_agent.toml` file, in a specific repo, will override the global configuration parameters.

 For example, in the GitHub organization `Codium-ai`:
- The repo [`https://github.com/Codium-ai/pr-agent-settings`](https://github.com/Codium-ai/pr-agent-settings/blob/main/.pr_agent.toml) contains a `.pr_agent.toml` file that serves as a global configuration file for all the repos in the GitHub organization `Codium-ai`.
+
+- The file [`https://github.com/Codium-ai/pr-agent-settings/.pr_agent.toml`](https://github.com/Codium-ai/pr-agent-settings/blob/main/.pr_agent.toml)  serves as a global configuration file for all the repos in the GitHub organization `Codium-ai`.
+
 - The repo [`https://github.com/Codium-ai/pr-agent`](https://github.com/Codium-ai/pr-agent/blob/main/.pr_agent.toml) inherits the global configuration file from `pr-agent-settings`.
--- a/docs/docs/usage-guide/index.md
+++ b/docs/docs/usage-guide/index.md
@ -1,10 +1,11 @@
 # Usage guide

-This page provides a detailed guide on how to use PR-Agent. It includes information on how to adjust PR-Agent configurations, define which tools will run automatically, manage mail notifications, and other advanced configurations.
+This page provides a detailed guide on how to use PR-Agent. 
+It includes information on how to adjust PR-Agent configurations, define which tools will run automatically, and other advanced configurations.


 - [Introduction](./introduction.md)
- [Configuration Options](./configuration_options.md)
+- [Configuration File](./configuration_options.md)
 - [Usage and Automation](./automations_and_usage.md)
    - [Local Repo (CLI)](./automations_and_usage.md#local-repo-cli)
    - [Online Usage](./automations_and_usage.md#online-usage)
@ -14,6 +15,7 @@ This page provides a detailed guide on how to use PR-Agent. It includes informat
    - [BitBucket App](./automations_and_usage.md#bitbucket-app)
    - [Azure DevOps Provider](./automations_and_usage.md#azure-devops-provider)
 - [Managing Mail Notifications](./mail_notifications.md)
+- [Changing a Model](./changing_a_model.md)
 - [Additional Configurations Walkthrough](./additional_configurations.md)
    - [Ignoring files from analysis](./additional_configurations.md#ignoring-files-from-analysis)
    - [Extra instructions](./additional_configurations.md#extra-instructions)
@ -21,3 +23,4 @@ This page provides a detailed guide on how to use PR-Agent. It includes informat
    - [Changing a model](./additional_configurations.md#changing-a-model)
    - [Patch Extra Lines](./additional_configurations.md#patch-extra-lines)
    - [Editing the prompts](./additional_configurations.md#editing-the-prompts)
+- [PR-Agent Pro Models](./PR_agent_pro_models.md)
--- a/docs/docs/usage-guide/introduction.md
+++ b/docs/docs/usage-guide/introduction.md
@ -1,18 +1,13 @@

-After [installation](https://codium-ai.github.io/Docs-PR-Agent/installation/), there are three basic ways to invoke CodiumAI PR-Agent:
+After [installation](https://pr-agent-docs.codium.ai/installation/), there are three basic ways to invoke CodiumAI PR-Agent:

 1. Locally running a CLI command
 2. Online usage - by [commenting](https://github.com/Codium-ai/pr-agent/pull/229#issuecomment-1695021901) on a PR
 3. Enabling PR-Agent tools to run automatically when a new PR is opened


-Specifically, CLI commands can be issued by invoking a pre-built [docker image](https://codium-ai.github.io/Docs-PR-Agent/installation/#run-from-source), or by invoking a [locally cloned repo](https://codium-ai.github.io/Docs-PR-Agent/installation/#locally).
-For online usage, you will need to setup either a [GitHub App](https://codium-ai.github.io/Docs-PR-Agent/installation/#run-as-a-github-app), or a [GitHub Action](https://codium-ai.github.io/Docs-PR-Agent/installation/#run-as-a-github-action).
-GitHub App and GitHub Action also enable to run PR-Agent specific tool automatically when a new PR is opened.
+Specifically, CLI commands can be issued by invoking a pre-built [docker image](https://pr-agent-docs.codium.ai/installation/locally/#using-docker-image), or by invoking a [locally cloned repo](https://pr-agent-docs.codium.ai/installation/locally/#run-from-source).

-
-**git provider**: The [git_provider](https://github.com/Codium-ai/pr-agent/blob/main/pr_agent/settings/configuration.toml#L4) field in the configuration file determines the GIT provider that will be used by PR-Agent. Currently, the following providers are supported:
-`
-"github", "gitlab", "bitbucket", "azure", "codecommit", "local", "gerrit"
-`
+For online usage, you will need to setup either a [GitHub App](https://pr-agent-docs.codium.ai/installation/github/#run-as-a-github-app) or a [GitHub Action](https://pr-agent-docs.codium.ai/installation/github/#run-as-a-github-action) (GitHub), a [GitLab webhook](https://pr-agent-docs.codium.ai/installation/gitlab/#run-a-gitlab-webhook-server) (GitLab), or a [BitBucket App](https://pr-agent-docs.codium.ai/installation/bitbucket/#run-using-codiumai-hosted-bitbucket-app) (BitBucket).
+These platforms also enable to run PR-Agent specific tools automatically when a new PR is opened, or on each push to a branch.

--- a/docs/mkdocs.yml
+++ b/docs/mkdocs.yml
@ -3,7 +3,10 @@ repo_url: https://github.com/Codium-ai/pr-agent
 repo_name: Codium-ai/pr-agent

 nav:
-  - Overview: 'index.md'
+  - Overview:
+    - 'index.md'
+    - 💎 PR-Agent Pro: 'overview/pr_agent_pro.md'
+    - Data Privacy: 'overview/data_privacy.md'
  - Installation:
    - 'installation/index.md'
    - Locally: 'installation/locally.md'
@ -15,10 +18,12 @@ nav:
  - Usage Guide:
    - 'usage-guide/index.md'
    - Introduction: 'usage-guide/introduction.md'
-    - Configuration Options: 'usage-guide/configuration_options.md'
-    - Managing Mail Notifications: 'usage-guide/mail_notifications.md'
+    - Configuration File: 'usage-guide/configuration_options.md'
    - Usage and Automation: 'usage-guide/automations_and_usage.md'
+    - Managing Mail Notifications: 'usage-guide/mail_notifications.md'
+    - Changing a Model: 'usage-guide/changing_a_model.md'
    - Additional Configurations: 'usage-guide/additional_configurations.md'
+    - 💎 PR-Agent Pro Models: 'usage-guide/PR_agent_pro_models'
  - Tools:
    - 'tools/index.md'
    - Describe: 'tools/describe.md'
@ -33,10 +38,15 @@ nav:
    - 💎 Improve Component: 'tools/improve_component.md'
    - 💎 Documentation: 'tools/documentation.md'
    - 💎 Custom Labels: 'tools/custom_labels.md'
-    - 💎 Custom Suggestions: 'tools/custom_suggestions.md'
+    - 💎 Custom Prompt: 'tools/custom_prompt.md'
    - 💎 CI Feedback: 'tools/ci_feedback.md'
    - 💎 Similar Code: 'tools/similar_code.md'
  - Core Abilities: 'core-abilities/index.md'
+  - Chrome Extension:
+      - PR-Agent Chrome Extension: 'chrome-extension/index.md'
+      - Features: 'chrome-extension/features.md'
+      - Data Privacy: 'chrome-extension/data_privacy.md'
+  - Code Fine-tuning Benchmark: 'finetuning_benchmark/index.md'

 theme:
  logo: assets/logo.svg
@ -56,7 +66,7 @@ theme:
    - content.tabs.link
    - content.code.annotation
    - content.code.copy
-    - toc.integrate
+    - content.tabs.link
  language: en
  custom_dir: overrides

@ -129,5 +139,6 @@ markdown_extensions:
      toc_depth: 3
      permalink: true

+
 copyright: |
  &copy; 2024 <a href="https://www.codium.ai/"  target="_blank" rel="noopener">CodiumAI</a>
--- a/pr_agent/agent/pr_agent.py
+++ b/pr_agent/agent/pr_agent.py
@ -46,6 +46,7 @@ command2class = {

 commands = list(command2class.keys())

+
 class PRAgent:
    def __init__(self, ai_handler: partial[BaseAiHandler,] = LiteLLMAIHandler):
        self.ai_handler = ai_handler  # will be initialized in run_action
@ -68,7 +69,9 @@ class PRAgent:
            for forbidden_arg in self.forbidden_cli_args:
                for arg in args:
                    if forbidden_arg in arg:
-                        get_logger().error(f"CLI argument for param '{forbidden_arg}' is forbidden. Use instead a configuration file.")
+                        get_logger().error(
+                            f"CLI argument for param '{forbidden_arg}' is forbidden. Use instead a configuration file."
+                        )
                        return False
        args = update_settings_from_args(args)

@ -76,7 +79,7 @@ class PRAgent:
        if action not in command2class:
            get_logger().debug(f"Unknown command: {action}")
            return False
-        with get_logger().contextualize(command=action):
+        with get_logger().contextualize(command=action, pr_url=pr_url):
            get_logger().info("PR-Agent request handler started", analytics=True)
            if action == "reflect_and_review":
                get_settings().pr_reviewer.ask_and_reflect = True
@ -94,4 +97,3 @@ class PRAgent:
            else:
                return False
            return True
-
--- a/pr_agent/algo/init.py
+++ b/pr_agent/algo/init.py
@ -1,8 +1,9 @@
 MAX_TOKENS = {
    'text-embedding-ada-002': 8000,
-    'gpt-3.5-turbo': 4000,
+    'gpt-3.5-turbo': 16000,
+    'gpt-3.5-turbo-0125': 16000,
    'gpt-3.5-turbo-0613': 4000,
-    'gpt-3.5-turbo-0301': 4000,
+    'gpt-3.5-turbo-1106': 16000,
    'gpt-3.5-turbo-16k': 16000,
    'gpt-3.5-turbo-16k-0613': 16000,
    'gpt-4': 8000,
@ -10,9 +11,14 @@ MAX_TOKENS = {
    'gpt-4-32k': 32000,
    'gpt-4-1106-preview': 128000,  # 128K, but may be limited by config.max_model_tokens
    'gpt-4-0125-preview': 128000,  # 128K, but may be limited by config.max_model_tokens
+    'gpt-4o': 128000,  # 128K, but may be limited by config.max_model_tokens
+    'gpt-4o-2024-05-13': 128000,  # 128K, but may be limited by config.max_model_tokens
    'gpt-4-turbo-preview': 128000,  # 128K, but may be limited by config.max_model_tokens
    'gpt-4-turbo-2024-04-09': 128000,  # 128K, but may be limited by config.max_model_tokens
    'gpt-4-turbo': 128000,  # 128K, but may be limited by config.max_model_tokens
+    'gpt-4o-mini': 128000,  # 128K, but may be limited by config.max_model_tokens
+    'gpt-4o-mini-2024-07-18': 128000,  # 128K, but may be limited by config.max_model_tokens
+    'gpt-4o-2024-08-06': 128000,  # 128K, but may be limited by config.max_model_tokens
    'claude-instant-1': 100000,
    'claude-2': 100000,
    'command-nightly': 4096,
@ -20,15 +26,38 @@ MAX_TOKENS = {
    'meta-llama/Llama-2-7b-chat-hf': 4096,
    'vertex_ai/codechat-bison': 6144,
    'vertex_ai/codechat-bison-32k': 32000,
+    'vertex_ai/claude-3-haiku@20240307': 100000,
+    'vertex_ai/claude-3-sonnet@20240229': 100000,
+    'vertex_ai/claude-3-opus@20240229': 100000,
+    'vertex_ai/claude-3-5-sonnet@20240620': 100000,
+    'vertex_ai/gemini-1.5-pro': 1048576,
+    'vertex_ai/gemini-1.5-flash': 1048576,
+    'vertex_ai/gemma2': 8200,
    'codechat-bison': 6144,
    'codechat-bison-32k': 32000,
    'anthropic.claude-instant-v1': 100000,
    'anthropic.claude-v1': 100000,
    'anthropic.claude-v2': 100000,
    'anthropic/claude-3-opus-20240229': 100000,
+    'anthropic/claude-3-5-sonnet-20240620': 100000,
    'bedrock/anthropic.claude-instant-v1': 100000,
    'bedrock/anthropic.claude-v2': 100000,
    'bedrock/anthropic.claude-v2:1': 100000,
    'bedrock/anthropic.claude-3-sonnet-20240229-v1:0': 100000,
    'bedrock/anthropic.claude-3-haiku-20240307-v1:0': 100000,
+    'bedrock/anthropic.claude-3-5-sonnet-20240620-v1:0': 100000,
+    'claude-3-5-sonnet': 100000,
+    'groq/llama3-8b-8192': 8192,
+    'groq/llama3-70b-8192': 8192,
+    'groq/mixtral-8x7b-32768': 32768,
+    'groq/llama-3.1-8b-instant': 131072,
+    'groq/llama-3.1-70b-versatile': 131072,
+    'groq/llama-3.1-405b-reasoning': 131072,
+    'ollama/llama3': 4096,
+    'watsonx/meta-llama/llama-3-8b-instruct': 4096,
+    "watsonx/meta-llama/llama-3-70b-instruct": 4096,
+    "watsonx/meta-llama/llama-3-405b-instruct": 16384,
+    "watsonx/ibm/granite-13b-chat-v2": 8191,
+    "watsonx/ibm/granite-34b-code-instruct": 8191,
+    "watsonx/mistralai/mistral-large": 32768,
 }
--- a/pr_agent/algo/ai_handlers/base_ai_handler.py
+++ b/pr_agent/algo/ai_handlers/base_ai_handler.py
@ -1,5 +1,6 @@
 from abc import ABC, abstractmethod

+
 class BaseAiHandler(ABC):
    """
    This class defines the interface for an AI handler to be used by the PR Agents.  
@ -25,4 +26,3 @@ class BaseAiHandler(ABC):
            temperature (float): the temperature to use for the chat completion    
        """
        pass
-
--- a/pr_agent/algo/ai_handlers/langchain_ai_handler.py
+++ b/pr_agent/algo/ai_handlers/langchain_ai_handler.py
@ -1,6 +1,6 @@
 try:
-    from langchain.chat_models import ChatOpenAI, AzureChatOpenAI
-    from langchain.schema import SystemMessage, HumanMessage
+    from langchain_openai import ChatOpenAI, AzureChatOpenAI
+    from langchain_core.messages import SystemMessage, HumanMessage
 except:  # we don't enforce langchain as a dependency, so if it's not installed, just move on
    pass

@ -8,42 +8,25 @@ from pr_agent.algo.ai_handlers.base_ai_handler import BaseAiHandler
 from pr_agent.config_loader import get_settings
 from pr_agent.log import get_logger

-from openai.error import APIError, RateLimitError, Timeout, TryAgain
+from openai import APIError, RateLimitError, Timeout
 from retry import retry
 import functools

 OPENAI_RETRIES = 5

+
 class LangChainOpenAIHandler(BaseAiHandler):
    def __init__(self):
        # Initialize OpenAIHandler specific attributes here
        super().__init__()
        self.azure = get_settings().get("OPENAI.API_TYPE", "").lower() == "azure"
-        try:
-            if self.azure:
-                # using a partial function so we can set the deployment_id later to support fallback_deployments
-                # but still need to access the other settings now so we can raise a proper exception if they're missing
-                self._chat = functools.partial(
-                    lambda **kwargs: AzureChatOpenAI(**kwargs),
-                    openai_api_key=get_settings().openai.key,
-                    openai_api_base=get_settings().openai.api_base,
-                    openai_api_version=get_settings().openai.api_version,
-                )
-            else:
-                self._chat = ChatOpenAI(openai_api_key=get_settings().openai.key)
-        except AttributeError as e:
-            if getattr(e, "name"):
-                raise ValueError(f"OpenAI {e.name} is required") from e
-            else:
-                raise e

-    @property
-    def chat(self):
-        if self.azure:
-            # we must set the deployment_id only here (instead of the __init__ method) to support fallback_deployments
-            return self._chat(deployment_name=self.deployment_id)
-        else:
-            return self._chat
+        # Create a default unused chat object to trigger early validation
+        self._create_chat(self.deployment_id)
+
+    def chat(self, messages: list, model: str, temperature: float):
+        chat = self._create_chat(self.deployment_id)
+        return chat.invoke(input=messages, model=model, temperature=temperature)

    @property
    def deployment_id(self):
@ -51,7 +34,8 @@ class LangChainOpenAIHandler(BaseAiHandler):
        Returns the deployment ID for the OpenAI API.
        """
        return get_settings().get("OPENAI.DEPLOYMENT_ID", None)
-    @retry(exceptions=(APIError, Timeout, TryAgain, AttributeError, RateLimitError),
+
+    @retry(exceptions=(APIError, Timeout, AttributeError, RateLimitError),
           tries=OPENAI_RETRIES, delay=2, backoff=2, jitter=(1, 3))
    async def chat_completion(self, model: str, system: str, user: str, temperature: float = 0.2):
        try:
@ -65,3 +49,28 @@ class LangChainOpenAIHandler(BaseAiHandler):
        except (Exception) as e:
            get_logger().error("Unknown error during OpenAI inference: ", e)
            raise e
+
+    def _create_chat(self, deployment_id=None):
+        try:
+            if self.azure:
+                # using a partial function so we can set the deployment_id later to support fallback_deployments
+                # but still need to access the other settings now so we can raise a proper exception if they're missing
+                return AzureChatOpenAI(
+                    openai_api_key=get_settings().openai.key,
+                    openai_api_version=get_settings().openai.api_version,
+                    azure_deployment=deployment_id,
+                    azure_endpoint=get_settings().openai.api_base,
+                )
+            else:
+                # for llms that compatible with openai, should use custom api base
+                openai_api_base = get_settings().get("OPENAI.API_BASE", None)
+                if openai_api_base is None or len(openai_api_base) == 0:
+                    return ChatOpenAI(openai_api_key=get_settings().openai.key)
+                else:
+                    return ChatOpenAI(openai_api_key=get_settings().openai.key, openai_api_base=openai_api_base)
+        except AttributeError as e:
+            if getattr(e, "name"):
+                raise ValueError(f"OpenAI {e.name} is required") from e
+            else:
+                raise e
+
--- a/pr_agent/algo/ai_handlers/litellm_ai_handler.py
+++ b/pr_agent/algo/ai_handlers/litellm_ai_handler.py
@ -1,10 +1,10 @@
 import os
 import requests
-import boto3
 import litellm
 import openai
 from litellm import acompletion
 from tenacity import retry, retry_if_exception_type, stop_after_attempt
+
 from pr_agent.algo.ai_handlers.base_ai_handler import BaseAiHandler
 from pr_agent.config_loader import get_settings
 from pr_agent.log import get_logger
@ -25,12 +25,18 @@ class LiteLLMAIHandler(BaseAiHandler):
        Raises a ValueError if the OpenAI key is missing.
        """
        self.azure = False
-        self.aws_bedrock_client = None
        self.api_base = None
        self.repetition_penalty = None
        if get_settings().get("OPENAI.KEY", None):
            openai.api_key = get_settings().openai.key
            litellm.openai_key = get_settings().openai.key
+        elif 'OPENAI_API_KEY' not in os.environ:
+            litellm.api_key = "dummy_key"
+        if get_settings().get("aws.AWS_ACCESS_KEY_ID"):
+            assert get_settings().aws.AWS_SECRET_ACCESS_KEY and get_settings().aws.AWS_REGION_NAME, "AWS credentials are incomplete"
+            os.environ["AWS_ACCESS_KEY_ID"] = get_settings().aws.AWS_ACCESS_KEY_ID
+            os.environ["AWS_SECRET_ACCESS_KEY"] = get_settings().aws.AWS_SECRET_ACCESS_KEY
+            os.environ["AWS_REGION_NAME"] = get_settings().aws.AWS_REGION_NAME
        if get_settings().get("litellm.use_client"):
            litellm_token = get_settings().get("litellm.LITELLM_TOKEN")
            assert litellm_token, "LITELLM_TOKEN is required"
@ -38,6 +44,12 @@ class LiteLLMAIHandler(BaseAiHandler):
            litellm.use_client = True
        if get_settings().get("LITELLM.DROP_PARAMS", None):
            litellm.drop_params = get_settings().litellm.drop_params
+        if get_settings().get("LITELLM.SUCCESS_CALLBACK", None):
+            litellm.success_callback = get_settings().litellm.success_callback
+        if get_settings().get("LITELLM.FAILURE_CALLBACK", None):
+            litellm.failure_callback = get_settings().litellm.failure_callback
+        if get_settings().get("LITELLM.SERVICE_CALLBACK", None):
+            litellm.service_callback = get_settings().litellm.service_callback
        if get_settings().get("OPENAI.ORG", None):
            litellm.organization = get_settings().openai.org
        if get_settings().get("OPENAI.API_TYPE", None):
@ -52,8 +64,8 @@ class LiteLLMAIHandler(BaseAiHandler):
            litellm.anthropic_key = get_settings().anthropic.key
        if get_settings().get("COHERE.KEY", None):
            litellm.cohere_key = get_settings().cohere.key
-        if get_settings().get("REPLICATE.KEY", None):
-            litellm.replicate_key = get_settings().replicate.key
+        if get_settings().get("GROQ.KEY", None):
+            litellm.api_key = get_settings().groq.key
        if get_settings().get("REPLICATE.KEY", None):
            litellm.replicate_key = get_settings().replicate.key
        if get_settings().get("HUGGINGFACE.KEY", None):
@ -64,21 +76,13 @@ class LiteLLMAIHandler(BaseAiHandler):
        if get_settings().get("OLLAMA.API_BASE", None):
            litellm.api_base = get_settings().ollama.api_base
            self.api_base = get_settings().ollama.api_base
-        if get_settings().get("HUGGINGFACE.REPITITION_PENALTY", None):
+        if get_settings().get("HUGGINGFACE.REPETITION_PENALTY", None):
            self.repetition_penalty = float(get_settings().huggingface.repetition_penalty)
        if get_settings().get("VERTEXAI.VERTEX_PROJECT", None):
            litellm.vertex_project = get_settings().vertexai.vertex_project
            litellm.vertex_location = get_settings().get(
                "VERTEXAI.VERTEX_LOCATION", None
            )
-        if get_settings().get("AWS.BEDROCK_REGION", None):
-            litellm.AmazonAnthropicConfig.max_tokens_to_sample = 2000
-            litellm.AmazonAnthropicClaude3Config.max_tokens = 2000
-            self.aws_bedrock_client = boto3.client(
-                service_name="bedrock-runtime",
-                region_name=get_settings().aws.bedrock_region,
-            )
-
    def prepare_logs(self, response, system, user, resp, finish_reason):
        response_log = response.dict().copy()
        response_log['system'] = system
@ -91,6 +95,60 @@ class LiteLLMAIHandler(BaseAiHandler):
            response_log['main_pr_language'] = 'unknown'
        return response_log

+    def add_litellm_callbacks(selfs, kwargs) -> dict:
+        captured_extra = []
+
+        def capture_logs(message):
+            # Parsing the log message and context
+            record = message.record
+            log_entry = {}
+            if record.get('extra', None).get('command', None) is not None:
+                log_entry.update({"command": record['extra']["command"]})
+            if record.get('extra', {}).get('pr_url', None) is not None:
+                log_entry.update({"pr_url": record['extra']["pr_url"]})
+
+            # Append the log entry to the captured_logs list
+            captured_extra.append(log_entry)
+
+        # Adding the custom sink to Loguru
+        handler_id = get_logger().add(capture_logs)
+        get_logger().debug("Capturing logs for litellm callbacks")
+        get_logger().remove(handler_id)
+
+        context = captured_extra[0] if len(captured_extra) > 0 else None
+
+        command = context.get("command", "unknown")
+        pr_url = context.get("pr_url", "unknown")
+        git_provider = get_settings().config.git_provider
+
+        metadata = dict()
+        callbacks = litellm.success_callback + litellm.failure_callback + litellm.service_callback
+        if "langfuse" in callbacks:
+            metadata.update({
+                "trace_name": command,
+                "tags": [git_provider, command],
+                "trace_metadata": {
+                    "command": command,
+                    "pr_url": pr_url,
+                },
+            })
+        if "langsmith" in callbacks:
+            metadata.update({
+                "run_name": command,
+                "tags": [git_provider, command],
+                "extra": {
+                    "metadata": {
+                        "command": command,
+                        "pr_url": pr_url,
+                    }
+                },
+            })
+
+        # Adding the captured logs to the kwargs
+        kwargs["metadata"] = metadata
+
+        return kwargs
+
    @property
    def deployment_id(self):
        """
@ -99,7 +157,7 @@ class LiteLLMAIHandler(BaseAiHandler):
        return get_settings().get("OPENAI.DEPLOYMENT_ID", None)

    @retry(
-        retry=retry_if_exception_type((openai.APIError, openai.APIConnectionError, openai.Timeout)), # No retry on RateLimitError
+        retry=retry_if_exception_type((openai.APIError, openai.APIConnectionError, openai.APITimeoutError)), # No retry on RateLimitError
        stop=stop_after_attempt(OPENAI_RETRIES)
    )
    async def chat_completion(self, model: str, system: str, user: str, temperature: float = 0.2, img_path: str = None):
@ -108,6 +166,10 @@ class LiteLLMAIHandler(BaseAiHandler):
            deployment_id = self.deployment_id
            if self.azure:
                model = 'azure/' + model
+            if 'claude' in model and not system:
+                system = "\n"
+                get_logger().warning(
+                    "Empty system prompt for claude model. Adding a newline character to prevent OpenAI API error.")
            messages = [{"role": "system", "content": system}, {"role": "user", "content": user}]
            if img_path:
                try:
@ -128,11 +190,20 @@ class LiteLLMAIHandler(BaseAiHandler):
                "deployment_id": deployment_id,
                "messages": messages,
                "temperature": temperature,
-                "force_timeout": get_settings().config.ai_timeout,
+                "timeout": get_settings().config.ai_timeout,
                "api_base": self.api_base,
            }
-            if self.aws_bedrock_client:
-                kwargs["aws_bedrock_client"] = self.aws_bedrock_client
+
+            if get_settings().litellm.get("enable_callbacks", False):
+                kwargs = self.add_litellm_callbacks(kwargs)
+
+            seed = get_settings().config.get("seed", -1)
+            if temperature > 0 and seed >= 0:
+                raise ValueError(f"Seed ({seed}) is not supported with temperature ({temperature}) > 0")
+            elif seed >= 0:
+                get_logger().info(f"Using fixed seed of {seed}")
+                kwargs["seed"] = seed
+
            if self.repetition_penalty:
                kwargs["repetition_penalty"] = self.repetition_penalty

@ -143,14 +214,14 @@ class LiteLLMAIHandler(BaseAiHandler):
                get_logger().info(f"\nUser prompt:\n{user}")

            response = await acompletion(**kwargs)
-        except (openai.APIError, openai.Timeout) as e:
-            get_logger().error("Error during OpenAI inference: ", e)
+        except (openai.APIError, openai.APITimeoutError) as e:
+            get_logger().warning("Error during OpenAI inference: ", e)
            raise
        except (openai.RateLimitError) as e:
            get_logger().error("Rate limit error during OpenAI inference: ", e)
            raise
        except (Exception) as e:
-            get_logger().error("Unknown error during OpenAI inference: ", e)
+            get_logger().warning("Unknown error during OpenAI inference: ", e)
            raise openai.APIError from e
        if response is None or len(response["choices"]) == 0:
            raise openai.APIError
--- a/pr_agent/algo/ai_handlers/openai_ai_handler.py
+++ b/pr_agent/algo/ai_handlers/openai_ai_handler.py
@ -28,6 +28,7 @@ class OpenAIHandler(BaseAiHandler):

        except AttributeError as e:
            raise ValueError("OpenAI key is required") from e
+
    @property
    def deployment_id(self):
        """
--- a/pr_agent/algo/file_filter.py
+++ b/pr_agent/algo/file_filter.py
@ -3,7 +3,8 @@ import re

 from pr_agent.config_loader import get_settings

-def filter_ignored(files):
+
+def filter_ignored(files, platform = 'github'):
    """
    Filter out files that match the ignore patterns.
    """
@ -27,8 +28,36 @@ def filter_ignored(files):
                pass

        # keep filenames that _don't_ match the ignore regex
+        if files and isinstance(files, list):
            for r in compiled_patterns:
+                if platform == 'github':
                    files = [f for f in files if (f.filename and not r.match(f.filename))]
+                elif platform == 'bitbucket':
+                    # files = [f for f in files if (f.new.path and not r.match(f.new.path))]
+                    files_o = []
+                    for f in files:
+                        if hasattr(f, 'new'):
+                            if f.new and f.new.path and not r.match(f.new.path):
+                                files_o.append(f)
+                                continue
+                        if hasattr(f, 'old'):
+                            if f.old and f.old.path and not r.match(f.old.path):
+                                files_o.append(f)
+                                continue
+                    files = files_o
+                elif platform == 'gitlab':
+                    # files = [f for f in files if (f['new_path'] and not r.match(f['new_path']))]
+                    files_o = []
+                    for f in files:
+                        if 'new_path' in f and f['new_path'] and not r.match(f['new_path']):
+                            files_o.append(f)
+                            continue
+                        if 'old_path' in f and f['old_path'] and not r.match(f['old_path']):
+                            files_o.append(f)
+                            continue
+                    files = files_o
+                elif platform == 'azure':
+                    files = [f for f in files if not r.match(f)]

    except Exception as e:
        print(f"Could not filter file list: {e}")
--- a/pr_agent/algo/git_patch_processing.py
+++ b/pr_agent/algo/git_patch_processing.py
@ -7,25 +7,35 @@ from pr_agent.algo.types import EDIT_TYPE, FilePatchInfo
 from pr_agent.log import get_logger


-def extend_patch(original_file_str, patch_str, num_lines) -> str:
-    """
-    Extends the given patch to include a specified number of surrounding lines.
-    
-    Args:
-        original_file_str (str): The original file to which the patch will be applied.
-        patch_str (str): The patch to be applied to the original file.
-        num_lines (int): The number of surrounding lines to include in the extended patch.
-        
-    Returns:
-        str: The extended patch string.
-    """
-    if not patch_str or num_lines == 0:
+def extend_patch(original_file_str, patch_str, patch_extra_lines_before=0,
+                 patch_extra_lines_after=0, filename: str = "") -> str:
+    if not patch_str or (patch_extra_lines_before == 0 and patch_extra_lines_after == 0) or not original_file_str:
        return patch_str

    if type(original_file_str) == bytes:
+        try:
            original_file_str = original_file_str.decode('utf-8')
+        except UnicodeDecodeError:
+            return ""
+
+    # skip patches
+    patch_extension_skip_types = get_settings().config.patch_extension_skip_types #[".md",".txt"]
+    if patch_extension_skip_types and filename:
+        if any([filename.endswith(skip_type) for skip_type in patch_extension_skip_types]):
+            return patch_str
+
+    # dynamic context settings
+    allow_dynamic_context = get_settings().config.allow_dynamic_context
+    max_extra_lines_before_dynamic_context = get_settings().config.max_extra_lines_before_dynamic_context
+    patch_extra_lines_before_dynamic = patch_extra_lines_before
+    if allow_dynamic_context:
+        if max_extra_lines_before_dynamic_context > patch_extra_lines_before:
+            patch_extra_lines_before_dynamic = max_extra_lines_before_dynamic_context
+        else:
+            get_logger().warning(f"'max_extra_lines_before_dynamic_context' should be greater than 'patch_extra_lines_before'")

    original_lines = original_file_str.splitlines()
+    len_original_lines = len(original_lines)
    patch_lines = patch_str.splitlines()
    extended_patch_lines = []

@ -37,10 +47,11 @@ def extend_patch(original_file_str, patch_str, num_lines) -> str:
            if line.startswith('@@'):
                match = RE_HUNK_HEADER.match(line)
                if match:
-                    # finish previous hunk
-                    if start1 != -1:
-                        extended_patch_lines.extend(
-                            original_lines[start1 + size1 - 1:start1 + size1 - 1 + num_lines])
+                    # finish last hunk
+                    if start1 != -1 and patch_extra_lines_after > 0:
+                        delta_lines = original_lines[start1 + size1 - 1:start1 + size1 - 1 + patch_extra_lines_after]
+                        delta_lines = [f' {line}' for line in delta_lines]
+                        extended_patch_lines.extend(delta_lines)

                    res = list(match.groups())
                    for i in range(len(res)):
@ -52,15 +63,60 @@ def extend_patch(original_file_str, patch_str, num_lines) -> str:
                        start1, size1, size2 = map(int, res[:3])
                        start2 = 0
                    section_header = res[4]
-                    extended_start1 = max(1, start1 - num_lines)
-                    extended_size1 = size1 + (start1 - extended_start1) + num_lines
-                    extended_start2 = max(1, start2 - num_lines)
-                    extended_size2 = size2 + (start2 - extended_start2) + num_lines
+
+                    if patch_extra_lines_before > 0 or patch_extra_lines_after > 0:
+                        def _calc_context_limits(patch_lines_before):
+                            extended_start1 = max(1, start1 - patch_lines_before)
+                            extended_size1 = size1 + (start1 - extended_start1) + patch_extra_lines_after
+                            extended_start2 = max(1, start2 - patch_lines_before)
+                            extended_size2 = size2 + (start2 - extended_start2) + patch_extra_lines_after
+                            if extended_start1 - 1 + extended_size1 > len_original_lines:
+                                # we cannot extend beyond the original file
+                                delta_cap = extended_start1 - 1 + extended_size1 - len_original_lines
+                                extended_size1 = max(extended_size1 - delta_cap, size1)
+                                extended_size2 = max(extended_size2 - delta_cap, size2)
+                            return extended_start1, extended_size1, extended_start2, extended_size2
+
+                        if allow_dynamic_context:
+                            extended_start1, extended_size1, extended_start2, extended_size2 = \
+                                _calc_context_limits(patch_extra_lines_before_dynamic)
+                            lines_before = original_lines[extended_start1 - 1:start1 - 1]
+                            found_header = False
+                            for i,line, in enumerate(lines_before):
+                                if section_header in line:
+                                    found_header = True
+                                    # Update start and size in one line each
+                                    extended_start1, extended_start2 = extended_start1 + i, extended_start2 + i
+                                    extended_size1, extended_size2 = extended_size1 - i, extended_size2 - i
+                                    get_logger().debug(f"Found section header in line {i} before the hunk")
+                                    section_header = ''
+                                    break
+                            if not found_header:
+                                get_logger().debug(f"Section header not found in the extra lines before the hunk")
+                                extended_start1, extended_size1, extended_start2, extended_size2 = \
+                                    _calc_context_limits(patch_extra_lines_before)
+                        else:
+                            extended_start1, extended_size1, extended_start2, extended_size2 = \
+                                _calc_context_limits(patch_extra_lines_before)
+
+                        delta_lines = original_lines[extended_start1 - 1:start1 - 1]
+                        delta_lines = [f' {line}' for line in delta_lines]
+                        if section_header and not allow_dynamic_context:
+                            for line in delta_lines:
+                                if section_header in line:
+                                    section_header = '' # remove section header if it is in the extra delta lines
+                                    break
+                    else:
+                        extended_start1 = start1
+                        extended_size1 = size1
+                        extended_start2 = start2
+                        extended_size2 = size2
+                        delta_lines = []
+                    extended_patch_lines.append('')
                    extended_patch_lines.append(
                        f'@@ -{extended_start1},{extended_size1} '
                        f'+{extended_start2},{extended_size2} @@ {section_header}')
-                    extended_patch_lines.extend(
-                        original_lines[extended_start1 - 1:start1 - 1])  # one to zero based
+                    extended_patch_lines.extend(delta_lines)  # one to zero based
                    continue
            extended_patch_lines.append(line)
    except Exception as e:
@ -68,10 +124,12 @@ def extend_patch(original_file_str, patch_str, num_lines) -> str:
            get_logger().error(f"Failed to extend patch: {e}")
        return patch_str

-    # finish previous hunk
-    if start1 != -1:
-        extended_patch_lines.extend(
-            original_lines[start1 + size1 - 1:start1 + size1 - 1 + num_lines])
+    # finish last hunk
+    if start1 != -1 and patch_extra_lines_after > 0:
+        delta_lines = original_lines[start1 + size1 - 1:start1 + size1 - 1 + patch_extra_lines_after]
+        # add space at the beginning of each extra line
+        delta_lines = [f' {line}' for line in delta_lines]
+        extended_patch_lines.extend(delta_lines)

    extended_patch_str = '\n'.join(extended_patch_lines)
    return extended_patch_str
@ -106,6 +164,7 @@ def omit_deletion_hunks(patch_lines) -> str:
                inside_hunk = True
        else:
            temp_hunk.append(line)
+            if line:
                edit_type = line[0]
                if edit_type == '+':
                    add_hunk = True
@ -133,7 +192,7 @@ def handle_patch_deletions(patch: str, original_file_content_str: str,
        str: The modified patch with deletion hunks omitted.

    """
-    if not new_file_content_str and edit_type != EDIT_TYPE.ADDED:
+    if not new_file_content_str and (edit_type == EDIT_TYPE.DELETED or edit_type == EDIT_TYPE.UNKNOWN):
        # logic for handling deleted files - don't show patch, just show that the file was deleted
        if get_settings().config.verbosity_level > 0:
            get_logger().info(f"Processing file: {file_name}, minimizing deletion file")
@ -180,6 +239,9 @@ __old hunk__
        line6
           ...
    """
+    # if the file was deleted, return a message indicating that the file was deleted
+    if hasattr(file, 'edit_type') and file.edit_type == EDIT_TYPE.DELETED:
+        return f"\n\n## file '{file.filename.strip()}' was deleted\n"

    patch_with_lines_str = f"\n\n## file: '{file.filename.strip()}'\n"
    patch_lines = patch.splitlines()
@ -198,14 +260,18 @@ __old hunk__
        if line.startswith('@@'):
            header_line = line
            match = RE_HUNK_HEADER.match(line)
-            if match and new_content_lines:  # found a new hunk, split the previous lines
-                if new_content_lines:
+            if match and (new_content_lines or old_content_lines):  # found a new hunk, split the previous lines
                if prev_header_line:
                    patch_with_lines_str += f'\n{prev_header_line}\n'
+                if new_content_lines:
+                    is_plus_lines = any([line.startswith('+') for line in new_content_lines])
+                    if is_plus_lines:
                        patch_with_lines_str = patch_with_lines_str.rstrip() + '\n__new hunk__\n'
                        for i, line_new in enumerate(new_content_lines):
                            patch_with_lines_str += f"{start2 + i} {line_new}\n"
                if old_content_lines:
+                    is_minus_lines = any([line.startswith('-') for line in old_content_lines])
+                    if is_minus_lines:
                        patch_with_lines_str = patch_with_lines_str.rstrip() + '\n__old hunk__\n'
                        for line_old in old_content_lines:
                            patch_with_lines_str += f"{line_old}\n"
@ -234,12 +300,16 @@ __old hunk__

    # finishing last hunk
    if match and new_content_lines:
-        if new_content_lines:
        patch_with_lines_str += f'\n{header_line}\n'
+        if new_content_lines:
+            is_plus_lines = any([line.startswith('+') for line in new_content_lines])
+            if is_plus_lines:
                patch_with_lines_str = patch_with_lines_str.rstrip() + '\n__new hunk__\n'
                for i, line_new in enumerate(new_content_lines):
                    patch_with_lines_str += f"{start2 + i} {line_new}\n"
        if old_content_lines:
+            is_minus_lines = any([line.startswith('-') for line in old_content_lines])
+            if is_minus_lines:
                patch_with_lines_str = patch_with_lines_str.rstrip() + '\n__old hunk__\n'
                for line_old in old_content_lines:
                    patch_with_lines_str += f"{line_old}\n"
--- a/pr_agent/algo/language_handler.py
+++ b/pr_agent/algo/language_handler.py
@ -5,17 +5,22 @@ from pr_agent.config_loader import get_settings



+
+def filter_bad_extensions(files):
    # Bad Extensions, source: https://github.com/EleutherAI/github-downloader/blob/345e7c4cbb9e0dc8a0615fd995a08bf9d73b3fe6/download_repo_text.py  # noqa: E501
    bad_extensions = get_settings().bad_extensions.default
    if get_settings().config.use_extra_bad_extensions:
        bad_extensions += get_settings().bad_extensions.extra
+    return [f for f in files if f.filename is not None and is_valid_file(f.filename, bad_extensions)]


-def filter_bad_extensions(files):
-    return [f for f in files if f.filename is not None and is_valid_file(f.filename)]
-
-
-def is_valid_file(filename):
+def is_valid_file(filename:str, bad_extensions=None) -> bool:
+    if not filename:
+        return False
+    if not bad_extensions:
+        bad_extensions = get_settings().bad_extensions.default
+        if get_settings().config.use_extra_bad_extensions:
+            bad_extensions += get_settings().bad_extensions.extra
    return filename.split('.')[-1] not in bad_extensions


--- a/pr_agent/algo/pr_processing.py
+++ b/pr_agent/algo/pr_processing.py
@ -21,33 +21,23 @@ MORE_MODIFIED_FILES_ = "Additional modified files (insufficient token budget to

 ADDED_FILES_ = "Additional added files (insufficient token budget to process):\n"

-OUTPUT_BUFFER_TOKENS_SOFT_THRESHOLD = 1000
-OUTPUT_BUFFER_TOKENS_HARD_THRESHOLD = 600
+OUTPUT_BUFFER_TOKENS_SOFT_THRESHOLD = 1500
+OUTPUT_BUFFER_TOKENS_HARD_THRESHOLD = 1000

-def get_pr_diff(git_provider: GitProvider, token_handler: TokenHandler, model: str,
-                add_line_numbers_to_hunks: bool = False, disable_extra_lines: bool = False) -> str:
-    """
-    Returns a string with the diff of the pull request, applying diff minimization techniques if needed.

-    Args:
-        git_provider (GitProvider): An object of the GitProvider class representing the Git provider used for the pull
-        request.
-        token_handler (TokenHandler): An object of the TokenHandler class used for handling tokens in the context of the
-        pull request.
-        model (str): The name of the model used for tokenization.
-        add_line_numbers_to_hunks (bool, optional): A boolean indicating whether to add line numbers to the hunks in the
-        diff. Defaults to False.
-        disable_extra_lines (bool, optional): A boolean indicating whether to disable the extension of each patch with
-        extra lines of context. Defaults to False.
-
-    Returns:
-        str: A string with the diff of the pull request, applying diff minimization techniques if needed.
-    """

+def get_pr_diff(git_provider: GitProvider, token_handler: TokenHandler,
+                model: str,
+                add_line_numbers_to_hunks: bool = False,
+                disable_extra_lines: bool = False,
+                large_pr_handling=False,
+                return_remaining_files=False):
    if disable_extra_lines:
-        PATCH_EXTRA_LINES = 0
+        PATCH_EXTRA_LINES_BEFORE = 0
+        PATCH_EXTRA_LINES_AFTER = 0
    else:
-        PATCH_EXTRA_LINES = get_settings().config.patch_extra_lines
+        PATCH_EXTRA_LINES_BEFORE = get_settings().config.patch_extra_lines_before
+        PATCH_EXTRA_LINES_AFTER = get_settings().config.patch_extra_lines_after

    try:
        diff_files_original = git_provider.get_diff_files()
@ -76,7 +66,8 @@ def get_pr_diff(git_provider: GitProvider, token_handler: TokenHandler, model: s

    # generate a standard diff string, with patch extension
    patches_extended, total_tokens, patches_extended_tokens = pr_generate_extended_diff(
-        pr_languages, token_handler, add_line_numbers_to_hunks, patch_extra_lines=PATCH_EXTRA_LINES)
+        pr_languages, token_handler, add_line_numbers_to_hunks,
+        patch_extra_lines_before=PATCH_EXTRA_LINES_BEFORE, patch_extra_lines_after=PATCH_EXTRA_LINES_AFTER)

    # if we are under the limit, return the full diff
    if total_tokens + OUTPUT_BUFFER_TOKENS_SOFT_THRESHOLD < get_max_tokens(model):
@ -84,56 +75,110 @@ def get_pr_diff(git_provider: GitProvider, token_handler: TokenHandler, model: s
                          f"returning full diff.")
        return "\n".join(patches_extended)

-    # if we are over the limit, start pruning
+    # if we are over the limit, start pruning (If we got here, we will not extend the patches with extra lines)
    get_logger().info(f"Tokens: {total_tokens}, total tokens over limit: {get_max_tokens(model)}, "
                      f"pruning diff.")
-    patches_compressed, modified_file_names, deleted_file_names, added_file_names, total_tokens_new = \
-        pr_generate_compressed_diff(pr_languages, token_handler, model, add_line_numbers_to_hunks)
+    patches_compressed_list, total_tokens_list, deleted_files_list, remaining_files_list, file_dict, files_in_patches_list = \
+        pr_generate_compressed_diff(pr_languages, token_handler, model, add_line_numbers_to_hunks, large_pr_handling)
+
+    if large_pr_handling and len(patches_compressed_list) > 1:
+        get_logger().info(f"Large PR handling mode, and found {len(patches_compressed_list)} patches with original diff.")
+        return "" # return empty string, as we want to generate multiple patches with a different prompt
+
+    # return the first patch
+    patches_compressed = patches_compressed_list[0]
+    total_tokens_new = total_tokens_list[0]
+    files_in_patch = files_in_patches_list[0]

    # Insert additional information about added, modified, and deleted files if there is enough space
    max_tokens = get_max_tokens(model) - OUTPUT_BUFFER_TOKENS_HARD_THRESHOLD
    curr_token = total_tokens_new  # == token_handler.count_tokens(final_diff)+token_handler.prompt_tokens
    final_diff = "\n".join(patches_compressed)
    delta_tokens = 10
-    if added_file_names and (max_tokens - curr_token) > delta_tokens:
-        added_list_str = ADDED_FILES_ + "\n".join(added_file_names)
+    added_list_str = modified_list_str = deleted_list_str = ""
+    unprocessed_files = []
+    # generate the added, modified, and deleted files lists
+    if (max_tokens - curr_token) > delta_tokens:
+        for filename, file_values in file_dict.items():
+            if filename in files_in_patch:
+                continue
+            if file_values['edit_type'] == EDIT_TYPE.ADDED:
+                unprocessed_files.append(filename)
+                if not added_list_str:
+                    added_list_str = ADDED_FILES_ + f"\n{filename}"
+                else:
+                    added_list_str = added_list_str + f"\n{filename}"
+            elif file_values['edit_type'] in [EDIT_TYPE.MODIFIED, EDIT_TYPE.RENAMED]:
+                unprocessed_files.append(filename)
+                if not modified_list_str:
+                    modified_list_str = MORE_MODIFIED_FILES_ + f"\n{filename}"
+                else:
+                    modified_list_str = modified_list_str + f"\n{filename}"
+            elif file_values['edit_type'] == EDIT_TYPE.DELETED:
+                # unprocessed_files.append(filename) # not needed here, because the file was deleted, so no need to process it
+                if not deleted_list_str:
+                    deleted_list_str = DELETED_FILES_ + f"\n{filename}"
+                else:
+                    deleted_list_str = deleted_list_str + f"\n{filename}"
+
+    # prune the added, modified, and deleted files lists, and add them to the final diff
    added_list_str = clip_tokens(added_list_str, max_tokens - curr_token)
    if added_list_str:
        final_diff = final_diff + "\n\n" + added_list_str
        curr_token += token_handler.count_tokens(added_list_str) + 2
-    if modified_file_names and (max_tokens - curr_token) > delta_tokens:
-        modified_list_str = MORE_MODIFIED_FILES_ + "\n".join(modified_file_names)
    modified_list_str = clip_tokens(modified_list_str, max_tokens - curr_token)
    if modified_list_str:
        final_diff = final_diff + "\n\n" + modified_list_str
        curr_token += token_handler.count_tokens(modified_list_str) + 2
-    if deleted_file_names and (max_tokens - curr_token) > delta_tokens:
-        deleted_list_str = DELETED_FILES_ + "\n".join(deleted_file_names)
    deleted_list_str = clip_tokens(deleted_list_str, max_tokens - curr_token)
    if deleted_list_str:
        final_diff = final_diff + "\n\n" + deleted_list_str
-    try:
+
    get_logger().debug(f"After pruning, added_list_str: {added_list_str}, modified_list_str: {modified_list_str}, "
                       f"deleted_list_str: {deleted_list_str}")
+    if not return_remaining_files:
+        return final_diff
+    else:
+        return final_diff, remaining_files_list
+
+
+def get_pr_diff_multiple_patchs(git_provider: GitProvider, token_handler: TokenHandler, model: str,
+                add_line_numbers_to_hunks: bool = False, disable_extra_lines: bool = False):
+    try:
+        diff_files_original = git_provider.get_diff_files()
+    except RateLimitExceededException as e:
+        get_logger().error(f"Rate limit exceeded for git provider API. original message {e}")
+        raise
+
+    diff_files = filter_ignored(diff_files_original)
+    if diff_files != diff_files_original:
+        try:
+            get_logger().info(f"Filtered out {len(diff_files_original) - len(diff_files)} files")
+            new_names = set([a.filename for a in diff_files])
+            orig_names = set([a.filename for a in diff_files_original])
+            get_logger().info(f"Filtered out files: {orig_names - new_names}")
        except Exception as e:
            pass
-    return final_diff
+
+    # get pr languages
+    pr_languages = sort_files_by_main_languages(git_provider.get_languages(), diff_files)
+    if pr_languages:
+        try:
+            get_logger().info(f"PR main language: {pr_languages[0]['language']}")
+        except Exception as e:
+            pass
+
+    patches_compressed_list, total_tokens_list, deleted_files_list, remaining_files_list, file_dict, files_in_patches_list = \
+        pr_generate_compressed_diff(pr_languages, token_handler, model, add_line_numbers_to_hunks, large_pr_handling=True)
+
+    return patches_compressed_list, total_tokens_list, deleted_files_list, remaining_files_list, file_dict, files_in_patches_list


 def pr_generate_extended_diff(pr_languages: list,
                              token_handler: TokenHandler,
                              add_line_numbers_to_hunks: bool,
-                              patch_extra_lines: int = 0) -> Tuple[list, int, list]:
-    """
-    Generate a standard diff string with patch extension, while counting the number of tokens used and applying diff
-    minimization techniques if needed.
-
-    Args:
-    - pr_languages: A list of dictionaries representing the languages used in the pull request and their corresponding
-      files.
-    - token_handler: An object of the TokenHandler class used for handling tokens in the context of the pull request.
-    - add_line_numbers_to_hunks: A boolean indicating whether to add line numbers to the hunks in the diff.
-    """
+                              patch_extra_lines_before: int = 0,
+                              patch_extra_lines_after: int = 0) -> Tuple[list, int, list]:
    total_tokens = token_handler.prompt_tokens  # initial tokens
    patches_extended = []
    patches_extended_tokens = []
@ -145,8 +190,12 @@ def pr_generate_extended_diff(pr_languages: list,
                continue

            # extend each patch with extra lines of context
-            extended_patch = extend_patch(original_file_content_str, patch, num_lines=patch_extra_lines)
-            full_extended_patch = f"\n\n## {file.filename}\n\n{extended_patch}\n"
+            extended_patch = extend_patch(original_file_content_str, patch,
+                                          patch_extra_lines_before, patch_extra_lines_after, file.filename)
+            if not extended_patch:
+                get_logger().warning(f"Failed to extend patch for file: {file.filename}")
+                continue
+            full_extended_patch = f"\n\n## {file.filename}\n{extended_patch.rstrip()}\n"

            if add_line_numbers_to_hunks:
                full_extended_patch = convert_to_hunks_with_lines_numbers(extended_patch, file)
@ -161,41 +210,17 @@ def pr_generate_extended_diff(pr_languages: list,


 def pr_generate_compressed_diff(top_langs: list, token_handler: TokenHandler, model: str,
-                                convert_hunks_to_line_numbers: bool) -> Tuple[list, list, list, list, int]:
-    """
-    Generate a compressed diff string for a pull request, using diff minimization techniques to reduce the number of
-    tokens used.
-    Args:
-        top_langs (list): A list of dictionaries representing the languages used in the pull request and their
-        corresponding files.
-        token_handler (TokenHandler): An object of the TokenHandler class used for handling tokens in the context of the
-        pull request.
-        model (str): The model used for tokenization.
-        convert_hunks_to_line_numbers (bool): A boolean indicating whether to convert hunks to line numbers in the diff.
-    Returns:
-        Tuple[list, list, list]: A tuple containing the following lists:
-            - patches: A list of compressed diff patches for each file in the pull request.
-            - modified_files_list: A list of file names that were skipped due to large patch size.
-            - deleted_files_list: A list of file names that were deleted in the pull request.
-
-    Minimization techniques to reduce the number of tokens:
-    0. Start from the largest diff patch to smaller ones
-    1. Don't use extend context lines around diff
-    2. Minimize deleted files
-    3. Minimize deleted hunks
-    4. Minimize all remaining files when you reach token limit
-    """
-
-    patches = []
-    added_files_list = []
-    modified_files_list = []
+                                convert_hunks_to_line_numbers: bool,
+                                large_pr_handling: bool) -> Tuple[list, list, list, list, dict, list]:
    deleted_files_list = []
+
    # sort each one of the languages in top_langs by the number of tokens in the diff
    sorted_files = []
    for lang in top_langs:
        sorted_files.extend(sorted(lang['files'], key=lambda x: x.tokens, reverse=True))

-    total_tokens = token_handler.prompt_tokens
+    # generate patches for each file, and count tokens
+    file_dict = {}
    for file in sorted_files:
        original_file_content_str = file.base_file
        new_file_content_str = file.head_file
@ -207,55 +232,87 @@ def pr_generate_compressed_diff(top_langs: list, token_handler: TokenHandler, mo
        patch = handle_patch_deletions(patch, original_file_content_str,
                                       new_file_content_str, file.filename, file.edit_type)
        if patch is None:
-            # if not deleted_files_list:
-            #     total_tokens += token_handler.count_tokens(DELETED_FILES_)
            if file.filename not in deleted_files_list:
                deleted_files_list.append(file.filename)
-            # total_tokens += token_handler.count_tokens(file.filename) + 1
            continue

        if convert_hunks_to_line_numbers:
            patch = convert_to_hunks_with_lines_numbers(patch, file)

        new_patch_tokens = token_handler.count_tokens(patch)
+        file_dict[file.filename] = {'patch': patch, 'tokens': new_patch_tokens, 'edit_type': file.edit_type}
+
+    max_tokens_model = get_max_tokens(model)
+
+    # first iteration
+    files_in_patches_list = []
+    remaining_files_list =  [file.filename for file in sorted_files]
+    patches_list =[]
+    total_tokens_list = []
+    total_tokens, patches, remaining_files_list, files_in_patch_list = generate_full_patch(convert_hunks_to_line_numbers, file_dict,
+                                       max_tokens_model, remaining_files_list, token_handler)
+    patches_list.append(patches)
+    total_tokens_list.append(total_tokens)
+    files_in_patches_list.append(files_in_patch_list)
+
+    # additional iterations (if needed)
+    if large_pr_handling:
+        NUMBER_OF_ALLOWED_ITERATIONS = get_settings().pr_description.max_ai_calls - 1 # one more call is to summarize
+        for i in range(NUMBER_OF_ALLOWED_ITERATIONS-1):
+            if remaining_files_list:
+                total_tokens, patches, remaining_files_list, files_in_patch_list = generate_full_patch(convert_hunks_to_line_numbers,
+                                                                                 file_dict,
+                                                                                  max_tokens_model,
+                                                                                  remaining_files_list, token_handler)
+                if patches:
+                    patches_list.append(patches)
+                    total_tokens_list.append(total_tokens)
+                    files_in_patches_list.append(files_in_patch_list)
+            else:
+                break
+
+    return patches_list, total_tokens_list, deleted_files_list, remaining_files_list, file_dict, files_in_patches_list
+
+
+def generate_full_patch(convert_hunks_to_line_numbers, file_dict, max_tokens_model,remaining_files_list_prev, token_handler):
+    total_tokens = token_handler.prompt_tokens # initial tokens
+    patches = []
+    remaining_files_list_new = []
+    files_in_patch_list = []
+    for filename, data in file_dict.items():
+        if filename not in remaining_files_list_prev:
+            continue
+
+        patch = data['patch']
+        new_patch_tokens = data['tokens']
+        edit_type = data['edit_type']

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

        # If the patch is too large, just show the file name
-        if total_tokens + new_patch_tokens > get_max_tokens(model) - OUTPUT_BUFFER_TOKENS_SOFT_THRESHOLD:
+        if total_tokens + new_patch_tokens > max_tokens_model - OUTPUT_BUFFER_TOKENS_SOFT_THRESHOLD:
            # Current logic is to skip the patch if it's too large
            # TODO: Option for alternative logic to remove hunks from the patch to reduce the number of tokens
            #  until we meet the requirements
            if get_settings().config.verbosity_level >= 2:
-                get_logger().warning(f"Patch too large, minimizing it, {file.filename}")
-            if file.edit_type == EDIT_TYPE.ADDED:
-                # if not added_files_list:
-                #     total_tokens += token_handler.count_tokens(ADDED_FILES_)
-                if file.filename not in added_files_list:
-                    added_files_list.append(file.filename)
-                # total_tokens += token_handler.count_tokens(file.filename) + 1
-            else:
-                # if not modified_files_list:
-                #     total_tokens += token_handler.count_tokens(MORE_MODIFIED_FILES_)
-                if file.filename not in modified_files_list:
-                    modified_files_list.append(file.filename)
-                # total_tokens += token_handler.count_tokens(file.filename) + 1
+                get_logger().warning(f"Patch too large, skipping it, {filename}")
+            remaining_files_list_new.append(filename)
            continue

        if patch:
            if not convert_hunks_to_line_numbers:
-                patch_final = f"\n\n## file: '{file.filename.strip()}\n\n{patch.strip()}\n'"
+                patch_final = f"\n\n## file: '{filename.strip()}\n\n{patch.strip()}\n'"
            else:
                patch_final = "\n\n" + patch.strip()
            patches.append(patch_final)
            total_tokens += token_handler.count_tokens(patch_final)
+            files_in_patch_list.append(filename)
            if get_settings().config.verbosity_level >= 2:
-                get_logger().info(f"Tokens: {total_tokens}, last filename: {file.filename}")
-
-    return patches, modified_files_list, deleted_files_list, added_files_list, total_tokens
+                get_logger().info(f"Tokens: {total_tokens}, last filename: {filename}")
+    return total_tokens, patches, remaining_files_list_new, files_in_patch_list


 async def retry_with_fallback_models(f: Callable, model_type: ModelType = ModelType.REGULAR):
@ -343,12 +400,15 @@ def get_pr_multi_diffs(git_provider: GitProvider,
    for lang in pr_languages:
        sorted_files.extend(sorted(lang['files'], key=lambda x: x.tokens, reverse=True))

-
    # try first a single run with standard diff string, with patch extension, and no deletions
    patches_extended, total_tokens, patches_extended_tokens = pr_generate_extended_diff(
-        pr_languages, token_handler, add_line_numbers_to_hunks=True)
+        pr_languages, token_handler, add_line_numbers_to_hunks=True,
+        patch_extra_lines_before=get_settings().config.patch_extra_lines_before,
+        patch_extra_lines_after=get_settings().config.patch_extra_lines_after)
+
+    # if we are under the limit, return the full diff
    if total_tokens + OUTPUT_BUFFER_TOKENS_SOFT_THRESHOLD < get_max_tokens(model):
-        return ["\n".join(patches_extended)]
+        return ["\n".join(patches_extended)] if patches_extended else []

    patches = []
    final_diff_list = []
@ -374,7 +434,23 @@ def get_pr_multi_diffs(git_provider: GitProvider,
        patch = convert_to_hunks_with_lines_numbers(patch, file)
        new_patch_tokens = token_handler.count_tokens(patch)

-        if patch and (token_handler.prompt_tokens + new_patch_tokens) > get_max_tokens(model) - OUTPUT_BUFFER_TOKENS_SOFT_THRESHOLD:
+        if patch and (token_handler.prompt_tokens + new_patch_tokens) > get_max_tokens(
+                model) - OUTPUT_BUFFER_TOKENS_SOFT_THRESHOLD:
+            if get_settings().config.get('large_patch_policy', 'skip') == 'skip':
+                get_logger().warning(f"Patch too large, skipping: {file.filename}")
+                continue
+            elif get_settings().config.get('large_patch_policy') == 'clip':
+                delta_tokens = get_max_tokens(model) - OUTPUT_BUFFER_TOKENS_SOFT_THRESHOLD - token_handler.prompt_tokens
+                patch_clipped = clip_tokens(patch, delta_tokens, delete_last_line=True, num_input_tokens=new_patch_tokens)
+                new_patch_tokens = token_handler.count_tokens(patch_clipped)
+                if patch_clipped and (token_handler.prompt_tokens + new_patch_tokens) > get_max_tokens(
+                        model) - OUTPUT_BUFFER_TOKENS_SOFT_THRESHOLD:
+                    get_logger().warning(f"Patch too large, skipping: {file.filename}")
+                    continue
+                else:
+                    get_logger().info(f"Clipped large patch for file: {file.filename}")
+                    patch = patch_clipped
+            else:
                get_logger().warning(f"Patch too large, skipping: {file.filename}")
                continue

@ -384,6 +460,10 @@ def get_pr_multi_diffs(git_provider: GitProvider,
            patches = []
            total_tokens = token_handler.prompt_tokens
            call_number += 1
+            if call_number > max_calls: # avoid creating new patches
+                if get_settings().config.verbosity_level >= 2:
+                    get_logger().info(f"Reached max calls ({max_calls})")
+                break
            if get_settings().config.verbosity_level >= 2:
                get_logger().info(f"Call number: {call_number}")

--- a/pr_agent/algo/token_handler.py
+++ b/pr_agent/algo/token_handler.py
@ -3,6 +3,8 @@ from tiktoken import encoding_for_model, get_encoding
 from pr_agent.config_loader import get_settings
 from threading import Lock

+from pr_agent.log import get_logger
+

 class TokenEncoder:
    _encoder_instance = None
@ -62,12 +64,16 @@ class TokenHandler:
        Returns:
        The sum of the number of tokens in the system and user strings.
        """
+        try:
            environment = Environment(undefined=StrictUndefined)
            system_prompt = environment.from_string(system).render(vars)
            user_prompt = environment.from_string(user).render(vars)
            system_prompt_tokens = len(encoder.encode(system_prompt))
            user_prompt_tokens = len(encoder.encode(user_prompt))
            return system_prompt_tokens + user_prompt_tokens
+        except Exception as e:
+            get_logger().error(f"Error in _get_system_user_tokens: {e}")
+            return 0

    def count_tokens(self, patch: str) -> int:
        """
--- a/pr_agent/algo/utils.py
+++ b/pr_agent/algo/utils.py
@ -1,15 +1,19 @@
 from __future__ import annotations

+import html
+import copy
 import difflib
 import json
 import os
 import re
 import textwrap
+import time
 from datetime import datetime
 from enum import Enum
 from typing import Any, List, Tuple

 import yaml
+from pydantic import BaseModel
 from starlette_context import context

 from pr_agent.algo import MAX_TOKENS
@ -18,10 +22,22 @@ from pr_agent.config_loader import get_settings, global_settings
 from pr_agent.algo.types import FilePatchInfo
 from pr_agent.log import get_logger

+class Range(BaseModel):
+    line_start: int  # should be 0-indexed
+    line_end: int
+    column_start: int = -1
+    column_end: int = -1
+
 class ModelType(str, Enum):
    REGULAR = "regular"
    TURBO = "turbo"

+
+class PRReviewHeader(str, Enum):
+    REGULAR = "## PR Reviewer Guide"
+    INCREMENTAL = "## Incremental PR Reviewer Guide"
+
+
 def get_setting(key: str) -> Any:
    try:
        key = key.upper()
@ -30,7 +46,7 @@ def get_setting(key: str) -> Any:
        return global_settings.get(key, None)


-def emphasize_header(text: str) -> str:
+def emphasize_header(text: str, only_markdown=False, reference_link=None) -> str:
    try:
        # Finding the position of the first occurrence of ": "
        colon_position = text.find(": ")
@ -38,7 +54,16 @@ def emphasize_header(text: str) -> str:
        # Splitting the string and wrapping the first part in <strong> tags
        if colon_position != -1:
            # Everything before the colon (inclusive) is wrapped in <strong> tags
-            transformed_string = "<strong>" + text[:colon_position + 1] + "</strong>" + text[colon_position + 1:]
+            if only_markdown:
+                if reference_link:
+                    transformed_string = f"[**{text[:colon_position + 1]}**]({reference_link})\n" + text[colon_position + 1:]
+                else:
+                    transformed_string = f"**{text[:colon_position + 1]}**\n" + text[colon_position + 1:]
+            else:
+                if reference_link:
+                    transformed_string = f"<strong><a href='{reference_link}'>{text[:colon_position + 1]}</a></strong><br>" + text[colon_position + 1:]
+                else:
+                    transformed_string = "<strong>" + text[:colon_position + 1] + "</strong>" +'<br>' + text[colon_position + 1:]
        else:
            # If there's no ": ", return the original string
            transformed_string = text
@ -60,8 +85,10 @@ def unique_strings(input_list: List[str]) -> List[str]:
            seen.add(item)
    return unique_list

-
-def convert_to_markdown(output_data: dict, gfm_supported: bool = True, incremental_review=None) -> str:
+def convert_to_markdown_v2(output_data: dict,
+                           gfm_supported: bool = True,
+                           incremental_review=None,
+                           git_provider=None) -> str:
    """
    Convert a dictionary of data into markdown format.
    Args:
@ -72,10 +99,12 @@ def convert_to_markdown(output_data: dict, gfm_supported: bool = True, increment

    emojis = {
        "Can be split": "🔀",
-        "Possible issues": "🔍",
+        "Possible issues": "⚡",
+        "Key issues to review": "⚡",
        "Score": "🏅",
        "Relevant tests": "🧪",
        "Focused PR": "✨",
+        "Relevant ticket": "🎫",
        "Security concerns": "🔒",
        "Insights from user's answers": "📝",
        "Code feedback": "🤖",
@ -83,58 +112,137 @@ def convert_to_markdown(output_data: dict, gfm_supported: bool = True, increment
    }
    markdown_text = ""
    if not incremental_review:
-        markdown_text += f"## PR Review\n\n"
+        markdown_text += f"{PRReviewHeader.REGULAR.value} 🔍\n\n"
    else:
-        markdown_text += f"## Incremental PR Review\n\n"
+        markdown_text += f"{PRReviewHeader.INCREMENTAL.value} 🔍\n\n"
        markdown_text += f"⏮️ Review for commits since previous PR-Agent review {incremental_review}.\n\n"
-    if gfm_supported:
-        markdown_text += "<table>\n<tr>\n"
-        # markdown_text += """<td> &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;Feedback&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;</td> <td></td></tr>"""
-
    if not output_data or not output_data.get('review', {}):
        return ""

+    if gfm_supported:
+        markdown_text += "<table>\n"
+
    for key, value in output_data['review'].items():
        if value is None or value == '' or value == {} or value == []:
-            if key.lower() != 'can_be_split':
+            if key.lower() not in ['can_be_split', 'key_issues_to_review']:
                continue
        key_nice = key.replace('_', ' ').capitalize()
        emoji = emojis.get(key_nice, "")
-        if gfm_supported:
        if 'Estimated effort to review' in key_nice:
-                key_nice = 'Estimated&nbsp;effort&nbsp;to&nbsp;review [1-5]'
-            if 'security concerns' in key_nice.lower():
+            key_nice = 'Estimated effort to review'
+            value = str(value).strip()
+            if value.isnumeric():
+                value_int = int(value)
+            else:
+                try:
+                    value_int = int(value.split(',')[0])
+                except ValueError:
+                    continue
+            blue_bars = '🔵' * value_int
+            white_bars = '⚪' * (5 - value_int)
+            value = f"{value_int} {blue_bars}{white_bars}"
+            if gfm_supported:
+                markdown_text += f"<tr><td>"
+                markdown_text += f"{emoji}&nbsp;<strong>{key_nice}</strong>: {value}"
+                markdown_text += f"</td></tr>\n"
+            else:
+                markdown_text += f"### {emoji} {key_nice}: {value}\n\n"
+        elif 'relevant tests' in key_nice.lower():
+            value = str(value).strip().lower()
+            if gfm_supported:
+                markdown_text += f"<tr><td>"
+                if is_value_no(value):
+                    markdown_text += f"{emoji}&nbsp;<strong>No relevant tests</strong>"
+                else:
+                    markdown_text += f"{emoji}&nbsp;<strong>PR contains tests</strong>"
+                markdown_text += f"</td></tr>\n"
+            else:
+                if is_value_no(value):
+                    markdown_text += f'### {emoji} No relevant tests\n\n'
+                else:
+                    markdown_text += f"### PR contains tests\n\n"
+        elif 'security concerns' in key_nice.lower():
+            if gfm_supported:
+                markdown_text += f"<tr><td>"
+                if is_value_no(value):
+                    markdown_text += f"{emoji}&nbsp;<strong>No security concerns identified</strong>"
+                else:
+                    markdown_text += f"{emoji}&nbsp;<strong>Security concerns</strong><br><br>\n\n"
                    value = emphasize_header(value.strip())
-                markdown_text += f"<tr><td> {emoji}&nbsp;<strong>{key_nice}</strong></td><td>\n\n{value}\n\n</td></tr>\n"
+                    markdown_text += f"{value}"
+                markdown_text += f"</td></tr>\n"
+            else:
+                if is_value_no(value):
+                    markdown_text += f'### {emoji} No security concerns identified\n\n'
+                else:
+                    markdown_text += f"### {emoji} Security concerns\n\n"
+                    value = emphasize_header(value.strip(), only_markdown=True)
+                    markdown_text += f"{value}\n\n"
        elif 'can be split' in key_nice.lower():
+            if gfm_supported:
+                markdown_text += f"<tr><td>"
                markdown_text += process_can_be_split(emoji, value)
-            elif 'possible issues' in key_nice.lower():
-                value = value.strip()
-                issues = value.split('\n- ')
-                for i, _ in enumerate(issues):
-                    issues[i] = issues[i].strip().strip('-').strip()
-                issues = unique_strings(issues) # remove duplicates
-                number_of_issues = len(issues)
-                if number_of_issues > 1:
-                    markdown_text += f"<tr><td rowspan={number_of_issues}> {emoji}&nbsp;<strong>{key_nice}</strong></td>\n"
+                markdown_text += f"</td></tr>\n"
+        elif 'key issues to review' in key_nice.lower():
+            # value is a list of issues
+            if is_value_no(value):
+                if gfm_supported:
+                    markdown_text += f"<tr><td>"
+                    markdown_text += f"{emoji}&nbsp;<strong>No key issues to review</strong>"
+                    markdown_text += f"</td></tr>\n"
+                else:
+                    markdown_text += f"### {emoji} No key issues to review\n\n"
+            else:
+                # issues = value.split('\n- ')
+                issues =value
+                # for i, _ in enumerate(issues):
+                #     issues[i] = issues[i].strip().strip('-').strip()
+                if gfm_supported:
+                    markdown_text += f"<tr><td>"
+                    markdown_text += f"{emoji}&nbsp;<strong>{key_nice}</strong><br><br>\n\n"
+                else:
+                    markdown_text += f"### {emoji} Key issues to review\n\n#### \n"
                for i, issue in enumerate(issues):
+                    try:
                        if not issue:
                            continue
-                        issue = emphasize_header(issue)
-                        if i == 0:
-                            markdown_text += f"<td>\n\n{issue}</td></tr>\n"
+                        relevant_file = issue.get('relevant_file', '').strip()
+                        issue_header = issue.get('issue_header', '').strip()
+                        issue_content = issue.get('issue_content', '').strip()
+                        start_line = int(str(issue.get('start_line', 0)).strip())
+                        end_line = int(str(issue.get('end_line', 0)).strip())
+                        reference_link = git_provider.get_line_link(relevant_file, start_line, end_line)
+
+                        if gfm_supported:
+                            if get_settings().pr_reviewer.extra_issue_links:
+                                issue_content_linked =copy.deepcopy(issue_content)
+                                referenced_variables_list = issue.get('referenced_variables', [])
+                                for component in referenced_variables_list:
+                                    name = component['variable_name'].strip().strip('`')
+
+                                    ind = issue_content.find(name)
+                                    if ind != -1:
+                                        reference_link_component = git_provider.get_line_link(relevant_file, component['relevant_line'], component['relevant_line'])
+                                        issue_content_linked = issue_content_linked[:ind-1] + f"[`{name}`]({reference_link_component})" + issue_content_linked[ind+len(name)+1:]
                                    else:
-                            markdown_text += f"<tr>\n<td>\n\n{issue}</td></tr>\n"
+                                        get_logger().info(f"Failed to find variable in issue content: {component['variable_name'].strip()}")
+                                issue_content = issue_content_linked
+                            issue_str = f"<a href='{reference_link}'><strong>{issue_header}</strong></a><br>{issue_content}"
                        else:
-                    value = emphasize_header(value.strip('-').strip())
-                    markdown_text += f"<tr><td> {emoji}&nbsp;<strong>{key_nice}</strong></td><td>\n\n{value}\n\n</td></tr>\n"
+                            issue_str = f"[**{issue_header}**]({reference_link})\n\n{issue_content}\n\n"
+                        markdown_text += f"{issue_str}\n\n"
+                    except Exception as e:
+                        get_logger().exception(f"Failed to process key issues to review: {e}")
+                if gfm_supported:
+                    markdown_text += f"</td></tr>\n"
        else:
-                markdown_text += f"<tr><td> {emoji}&nbsp;<strong>{key_nice}</strong></td><td>\n\n{value}\n\n</td></tr>\n"
+            if gfm_supported:
+                markdown_text += f"<tr><td>"
+                markdown_text += f"{emoji}&nbsp;<strong>{key_nice}</strong>: {value}"
+                markdown_text += f"</td></tr>\n"
            else:
-            if len(value.split()) > 1:
-                markdown_text += f"{emoji} **{key_nice}:**\n\n {value}\n\n"
-            else:
-                markdown_text += f"{emoji} **{key_nice}:** {value}\n\n"
+                markdown_text += f"### {emoji} {key_nice}: {value}\n\n"
+
    if gfm_supported:
        markdown_text += "</table>\n"

@ -144,7 +252,7 @@ def convert_to_markdown(output_data: dict, gfm_supported: bool = True, increment
            markdown_text += f"<details><summary> <strong>Code feedback:</strong></summary>\n\n"
            markdown_text += "<hr>"
        else:
-            markdown_text += f"\n\n** Code feedback:**\n\n"
+            markdown_text += f"\n\n### Code feedback:\n\n"
        for i, value in enumerate(output_data['code_feedback']):
            if value is None or value == '' or value == {} or value == []:
                continue
@ -153,41 +261,61 @@ def convert_to_markdown(output_data: dict, gfm_supported: bool = True, increment
            markdown_text= markdown_text[:-4]
        if gfm_supported:
            markdown_text += f"</details>"
-    #print(markdown_text)
-

    return markdown_text


 def process_can_be_split(emoji, value):
+    try:
        # key_nice = "Can this PR be split?"
        key_nice = "Multiple PR themes"
        markdown_text = ""
        if not value or isinstance(value, list) and len(value) == 1:
            value = "No"
-        markdown_text += f"<tr><td> {emoji}&nbsp;<strong>{key_nice}</strong></td><td>\n\n{value}\n\n</td></tr>\n"
+            # markdown_text += f"<tr><td> {emoji}&nbsp;<strong>{key_nice}</strong></td><td>\n\n{value}\n\n</td></tr>\n"
+            # markdown_text += f"### {emoji} No multiple PR themes\n\n"
+            markdown_text += f"{emoji} <strong>No multiple PR themes</strong>\n\n"
        else:
-        number_of_splits = len(value)
-        markdown_text += f"<tr><td rowspan={number_of_splits}> {emoji}&nbsp;<strong>{key_nice}</strong></td>\n"
+            markdown_text += f"{emoji} <strong>{key_nice}</strong><br><br>\n\n"
            for i, split in enumerate(value):
                title = split.get('title', '')
                relevant_files = split.get('relevant_files', [])
-            if i == 0:
-                markdown_text += f"<td><details><summary>\nSub-PR theme: <strong>{title}</strong></summary>\n\n"
-                markdown_text += f"<hr>\n"
-                markdown_text += f"Relevant files:\n"
-                markdown_text += f"<ul>\n"
+                markdown_text += f"<details><summary>\nSub-PR theme: <b>{title}</b></summary>\n\n"
+                markdown_text += f"___\n\nRelevant files:\n\n"
                for file in relevant_files:
-                    markdown_text += f"<li>{file}</li>\n"
-                markdown_text += f"</ul>\n\n</details></td></tr>\n"
-            else:
-                markdown_text += f"<tr>\n<td><details><summary>\nSub-PR theme: <strong>{title}</strong></summary>\n\n"
-                markdown_text += f"<hr>\n"
-                markdown_text += f"Relevant files:\n"
-                markdown_text += f"<ul>\n"
-                for file in relevant_files:
-                    markdown_text += f"<li>{file}</li>\n"
-                markdown_text += f"</ul>\n\n</details></td></tr>\n"
+                    markdown_text += f"- {file}\n"
+                markdown_text += f"___\n\n"
+                markdown_text += f"</details>\n\n"
+
+                # markdown_text += f"#### Sub-PR theme: {title}\n\n"
+                # markdown_text += f"Relevant files:\n\n"
+                # for file in relevant_files:
+                #     markdown_text += f"- {file}\n"
+                # markdown_text += "\n"
+            # number_of_splits = len(value)
+            # markdown_text += f"<tr><td rowspan={number_of_splits}> {emoji}&nbsp;<strong>{key_nice}</strong></td>\n"
+            # for i, split in enumerate(value):
+            #     title = split.get('title', '')
+            #     relevant_files = split.get('relevant_files', [])
+            #     if i == 0:
+            #         markdown_text += f"<td><details><summary>\nSub-PR theme:<br><strong>{title}</strong></summary>\n\n"
+            #         markdown_text += f"<hr>\n"
+            #         markdown_text += f"Relevant files:\n"
+            #         markdown_text += f"<ul>\n"
+            #         for file in relevant_files:
+            #             markdown_text += f"<li>{file}</li>\n"
+            #         markdown_text += f"</ul>\n\n</details></td></tr>\n"
+            #     else:
+            #         markdown_text += f"<tr>\n<td><details><summary>\nSub-PR theme:<br><strong>{title}</strong></summary>\n\n"
+            #         markdown_text += f"<hr>\n"
+            #         markdown_text += f"Relevant files:\n"
+            #         markdown_text += f"<ul>\n"
+            #         for file in relevant_files:
+            #             markdown_text += f"<li>{file}</li>\n"
+            #         markdown_text += f"</ul>\n\n</details></td></tr>\n"
+    except Exception as e:
+        get_logger().exception(f"Failed to process can be split: {e}")
+        return ""
    return markdown_text


@ -356,7 +484,7 @@ def convert_str_to_datetime(date_str):
    return datetime.strptime(date_str, datetime_format)


-def load_large_diff(filename, new_file_content_str: str, original_file_content_str: str) -> str:
+def load_large_diff(filename, new_file_content_str: str, original_file_content_str: str, show_warning: bool = True) -> str:
    """
    Generate a patch for a modified file by comparing the original content of the file with the new content provided as
    input.
@ -375,7 +503,7 @@ def load_large_diff(filename, new_file_content_str: str, original_file_content_s
    try:
        diff = difflib.unified_diff(original_file_content_str.splitlines(keepends=True),
                                    new_file_content_str.splitlines(keepends=True))
-        if get_settings().config.verbosity_level >= 2:
+        if get_settings().config.verbosity_level >= 2 and show_warning:
            get_logger().warning(f"File was modified, but no patch was found. Manually creating patch: {filename}.")
        patch = ''.join(diff)
    except Exception:
@ -429,28 +557,37 @@ def _fix_key_value(key: str, value: str):
    return key, value


-def load_yaml(response_text: str, keys_fix_yaml: List[str] = []) -> dict:
-    response_text = response_text.removeprefix('```yaml').rstrip('`')
+def load_yaml(response_text: str, keys_fix_yaml: List[str] = [], first_key="", last_key="") -> dict:
+    response_text = response_text.strip('\n').removeprefix('```yaml').rstrip().removesuffix('```')
    try:
        data = yaml.safe_load(response_text)
    except Exception as e:
-        get_logger().error(f"Failed to parse AI prediction: {e}")
-        data = try_fix_yaml(response_text, keys_fix_yaml=keys_fix_yaml)
+        get_logger().warning(f"Initial failure to parse AI prediction: {e}")
+        data = try_fix_yaml(response_text, keys_fix_yaml=keys_fix_yaml, first_key=first_key, last_key=last_key)
+        if not data:
+            get_logger().error(f"Failed to parse AI prediction after fallbacks", artifact={'response_text': response_text})
+        else:
+            get_logger().info(f"Successfully parsed AI prediction after fallbacks",
+                              artifact={'response_text': response_text})
    return data


-def try_fix_yaml(response_text: str, keys_fix_yaml: List[str] = []) -> dict:
+
+def try_fix_yaml(response_text: str,
+                 keys_fix_yaml: List[str] = [],
+                 first_key="",
+                 last_key="",) -> dict:
    response_text_lines = response_text.split('\n')

-    keys = ['relevant line:', 'suggestion content:', 'relevant file:', 'existing code:', 'improved code:']
-    keys = keys + keys_fix_yaml
+    keys_yaml = ['relevant line:', 'suggestion content:', 'relevant file:', 'existing code:', 'improved code:']
+    keys_yaml = keys_yaml + keys_fix_yaml
    # first fallback - try to convert 'relevant line: ...' to relevant line: |-\n        ...'
    response_text_lines_copy = response_text_lines.copy()
    for i in range(0, len(response_text_lines_copy)):
-        for key in keys:
-            if key in response_text_lines_copy[i] and not '|-' in response_text_lines_copy[i]:
+        for key in keys_yaml:
+            if key in response_text_lines_copy[i] and not '|' in response_text_lines_copy[i]:
                response_text_lines_copy[i] = response_text_lines_copy[i].replace(f'{key}',
-                                                                                  f'{key} |-\n        ')
+                                                                                  f'{key} |\n        ')
    try:
        data = yaml.safe_load('\n'.join(response_text_lines_copy))
        get_logger().info(f"Successfully parsed AI prediction after adding |-\n")
@ -470,6 +607,7 @@ def try_fix_yaml(response_text: str, keys_fix_yaml: List[str] = []) -> dict:
        except:
            pass

+
    # third fallback - try to remove leading and trailing curly brackets
    response_text_copy = response_text.strip().rstrip().removeprefix('{').removesuffix('}').rstrip(':\n')
    try:
@ -479,7 +617,28 @@ def try_fix_yaml(response_text: str, keys_fix_yaml: List[str] = []) -> dict:
    except:
        pass

-    # fourth fallback - try to remove last lines
+
+    # forth fallback - try to extract yaml snippet by 'first_key' and 'last_key'
+    # note that 'last_key' can be in practice a key that is not the last key in the yaml snippet.
+    # it just needs to be some inner key, so we can look for newlines after it
+    if first_key and last_key:
+        index_start = response_text.find(f"\n{first_key}:")
+        if index_start == -1:
+            index_start = response_text.find(f"{first_key}:")
+        index_last_code = response_text.rfind(f"{last_key}:")
+        index_end = response_text.find("\n\n", index_last_code) # look for newlines after last_key
+        if index_end == -1:
+            index_end = len(response_text)
+        response_text_copy = response_text[index_start:index_end].strip().strip('```yaml').strip('`').strip()
+        try:
+            data = yaml.safe_load(response_text_copy)
+            get_logger().info(f"Successfully parsed AI prediction after extracting yaml snippet")
+            return data
+        except:
+            pass
+
+
+    # fifth fallback - try to remove last lines
    data = {}
    for i in range(1, len(response_text_lines)):
        response_text_lines_tmp = '\n'.join(response_text_lines[:-i])
@ -495,7 +654,7 @@ def set_custom_labels(variables, git_provider=None):
    if not get_settings().config.enable_custom_labels:
        return

-    labels = get_settings().custom_labels
+    labels = get_settings().get('custom_labels', {})
    if not labels:
        # set default labels
        labels = ['Bug fix', 'Tests', 'Bug fix with tests', 'Enhancement', 'Documentation', 'Other']
@ -521,14 +680,16 @@ def get_user_labels(current_labels: List[str] = None):
    Only keep labels that has been added by the user
    """
    try:
+        enable_custom_labels = get_settings().config.get('enable_custom_labels', False)
+        custom_labels = get_settings().get('custom_labels', [])
        if current_labels is None:
            current_labels = []
        user_labels = []
        for label in current_labels:
            if label.lower() in ['bug fix', 'tests', 'enhancement', 'documentation', 'other']:
                continue
-            if get_settings().config.enable_custom_labels:
-                if label in get_settings().custom_labels:
+            if enable_custom_labels:
+                if label in custom_labels:
                    continue
            user_labels.append(label)
        if user_labels:
@ -540,19 +701,29 @@ def get_user_labels(current_labels: List[str] = None):


 def get_max_tokens(model):
+    """
+    Get the maximum number of tokens allowed for a model.
+    logic:
+    (1) If the model is in './pr_agent/algo/__init__.py', use the value from there.
+    (2) else, the user needs to define explicitly 'config.custom_model_max_tokens'
+
+    For both cases, we further limit the number of tokens to 'config.max_model_tokens' if it is set.
+    This aims to improve the algorithmic quality, as the AI model degrades in performance when the input is too long.
+    """
    settings = get_settings()
    if model in MAX_TOKENS:
        max_tokens_model = MAX_TOKENS[model]
+    elif settings.config.custom_model_max_tokens > 0:
+        max_tokens_model = settings.config.custom_model_max_tokens
    else:
-        raise Exception(f"MAX_TOKENS must be set for model {model} in ./pr_agent/algo/__init__.py")
+        raise Exception(f"Ensure {model} is defined in MAX_TOKENS in ./pr_agent/algo/__init__.py or set a positive value for it in config.custom_model_max_tokens")

-    if settings.config.max_model_tokens:
+    if settings.config.max_model_tokens and settings.config.max_model_tokens > 0:
        max_tokens_model = min(settings.config.max_model_tokens, max_tokens_model)
-        # get_logger().debug(f"limiting max tokens to {max_tokens_model}")
    return max_tokens_model


-def clip_tokens(text: str, max_tokens: int, add_three_dots=True) -> str:
+def clip_tokens(text: str, max_tokens: int, add_three_dots=True, num_input_tokens=None, delete_last_line=False) -> str:
    """
    Clip the number of tokens in a string to a maximum number of tokens.

@ -567,16 +738,30 @@ def clip_tokens(text: str, max_tokens: int, add_three_dots=True) -> str:
        return text

    try:
+        if num_input_tokens is None:
            encoder = TokenEncoder.get_token_encoder()
            num_input_tokens = len(encoder.encode(text))
        if num_input_tokens <= max_tokens:
            return text
+        if max_tokens < 0:
+            return ""
+
+        # calculate the number of characters to keep
        num_chars = len(text)
        chars_per_token = num_chars / num_input_tokens
-        num_output_chars = int(chars_per_token * max_tokens)
+        factor = 0.9  # reduce by 10% to be safe
+        num_output_chars = int(factor * chars_per_token * max_tokens)
+
+        # clip the text
+        if num_output_chars > 0:
            clipped_text = text[:num_output_chars]
+            if delete_last_line:
+                clipped_text = clipped_text.rsplit('\n', 1)[0]
            if add_three_dots:
                clipped_text += "\n...(truncated)"
+        else: # if the text is empty
+            clipped_text =  ""
+
        return clipped_text
    except Exception as e:
        get_logger().warning(f"Failed to clip tokens: {e}")
@ -586,6 +771,7 @@ def replace_code_tags(text):
    """
    Replace odd instances of ` with <code> and even instances of ` with </code>
    """
+    text = html.escape(text)
    parts = text.split('`')
    for i in range(1, len(parts), 2):
        parts[i] = '<code>' + parts[i] + '</code>'
@ -602,6 +788,9 @@ def find_line_number_of_relevant_line_in_file(diff_files: List[FilePatchInfo],
    re_hunk_header = re.compile(
        r"^@@ -(\d+)(?:,(\d+))? \+(\d+)(?:,(\d+))? @@[ ]?(.*)")

+    if not diff_files:
+        return position, absolute_position
+
    for file in diff_files:
        if file.filename and (file.filename.strip() == relevant_file):
            patch = file.patch
@ -663,6 +852,57 @@ def find_line_number_of_relevant_line_in_file(diff_files: List[FilePatchInfo],
                            break
    return position, absolute_position

+def validate_and_await_rate_limit(rate_limit_status=None, git_provider=None, get_rate_limit_status_func=None):
+    if git_provider and not rate_limit_status:
+        rate_limit_status = {'resources': git_provider.github_client.get_rate_limit().raw_data}
+
+    if not rate_limit_status:
+        rate_limit_status = get_rate_limit_status_func()
+    # validate that the rate limit is not exceeded
+    is_rate_limit = False
+    for key, value in rate_limit_status['resources'].items():
+        if value['remaining'] == 0:
+            print(f"key: {key}, value: {value}")
+            is_rate_limit = True
+            sleep_time_sec = value['reset'] - datetime.now().timestamp()
+            sleep_time_hour = sleep_time_sec / 3600.0
+            print(f"Rate limit exceeded. Sleeping for {sleep_time_hour} hours")
+            if sleep_time_sec > 0:
+                time.sleep(sleep_time_sec+1)
+
+            if git_provider:
+                rate_limit_status = {'resources': git_provider.github_client.get_rate_limit().raw_data}
+            else:
+                rate_limit_status = get_rate_limit_status_func()
+
+    return is_rate_limit
+
+
+def get_largest_component(pr_url):
+    from pr_agent.tools.pr_analyzer import PRAnalyzer
+    publish_output = get_settings().config.publish_output
+    get_settings().config.publish_output = False  # disable publish output
+    analyzer = PRAnalyzer(pr_url)
+    methods_dict_files = analyzer.run_sync()
+    get_settings().config.publish_output = publish_output
+    max_lines_changed = 0
+    file_b = ""
+    component_name_b = ""
+    for file in methods_dict_files:
+        for method in methods_dict_files[file]:
+            try:
+                if methods_dict_files[file][method]['num_plus_lines'] > max_lines_changed:
+                    max_lines_changed = methods_dict_files[file][method]['num_plus_lines']
+                    file_b = file
+                    component_name_b = method
+            except:
+                pass
+    if component_name_b:
+        get_logger().info(f"Using the largest changed component: '{component_name_b}'")
+        return component_name_b, file_b
+    else:
+        return None, None
+
 def github_action_output(output_data: dict, key_name: str):
    try:
        if not get_settings().get('github_action_config.enable_output', False):
@ -674,3 +914,34 @@ def github_action_output(output_data: dict, key_name: str):
    except Exception as e:
        get_logger().error(f"Failed to write to GitHub Action output: {e}")
    return
+
+
+def show_relevant_configurations(relevant_section: str) -> str:
+    forbidden_keys = ['ai_disclaimer', 'ai_disclaimer_title', 'ANALYTICS_FOLDER', 'secret_provider',
+                      'trial_prefix_message', 'no_eligible_message', 'identity_provider', 'ALLOWED_REPOS','APP_NAME']
+
+    markdown_text = ""
+    markdown_text += "\n<hr>\n<details> <summary><strong>🛠️ Relevant configurations:</strong></summary> \n\n"
+    markdown_text +="<br>These are the relevant [configurations](https://github.com/Codium-ai/pr-agent/blob/main/pr_agent/settings/configuration.toml) for this tool:\n\n"
+    markdown_text += f"**[config**]\n```yaml\n\n"
+    for key, value in get_settings().config.items():
+        if key in forbidden_keys:
+            continue
+        markdown_text += f"{key}: {value}\n"
+    markdown_text += "\n```\n"
+    markdown_text += f"\n**[{relevant_section}]**\n```yaml\n\n"
+    for key, value in get_settings().get(relevant_section, {}).items():
+        if key in forbidden_keys:
+            continue
+        markdown_text += f"{key}: {value}\n"
+    markdown_text += "\n```"
+    markdown_text += "\n</details>\n"
+    return markdown_text
+
+def is_value_no(value):
+    if not value:
+        return True
+    value_str = str(value).strip().lower()
+    if value_str == 'no' or value_str == 'none' or value_str == 'false':
+        return True
+    return False
--- a/pr_agent/cli.py
+++ b/pr_agent/cli.py
@ -4,11 +4,12 @@ import os

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

 log_level = os.environ.get("LOG_LEVEL", "INFO")
 setup_logger(log_level)

+
 def set_parser():
    parser = argparse.ArgumentParser(description='AI based pull request analyzer', usage=
    """\
@ -50,6 +51,7 @@ def set_parser():
    parser.add_argument('rest', nargs=argparse.REMAINDER, default=[])
    return parser

+
 def run_command(pr_url, command):
    # Preparing the command
    run_command_str = f"--pr_url={pr_url} {command.lstrip('/')}"
@ -58,6 +60,7 @@ def run_command(pr_url, command):
    # Run the command. Feedback will appear in GitHub PR comments
    run(args=args)

+
 def run(inargs=None, args=None):
    parser = set_parser()
    if not args:
@ -68,10 +71,21 @@ def run(inargs=None, args=None):

    command = args.command.lower()
    get_settings().set("CONFIG.CLI_MODE", True)
+
+    async def inner():
        if args.issue_url:
-        result = asyncio.run(PRAgent().handle_request(args.issue_url, [command] + args.rest))
+            result = await asyncio.create_task(PRAgent().handle_request(args.issue_url, [command] + args.rest))
        else:
-        result = asyncio.run(PRAgent().handle_request(args.pr_url, [command] + args.rest))
+            result = await asyncio.create_task(PRAgent().handle_request(args.pr_url, [command] + args.rest))
+
+        if get_settings().litellm.get("enable_callbacks", False):
+            # There may be additional events on the event queue from the run above. If there are give them time to complete.
+            get_logger().debug("Waiting for event queue to complete")
+            await asyncio.wait([task for task in asyncio.all_tasks() if task is not asyncio.current_task()])
+
+        return result
+
+    result = asyncio.run(inner())
    if not result:
        parser.print_help()

--- a/pr_agent/config_loader.py
+++ b/pr_agent/config_loader.py
@ -21,6 +21,7 @@ global_settings = Dynaconf(
        "settings/pr_line_questions_prompts.toml",
        "settings/pr_description_prompts.toml",
        "settings/pr_code_suggestions_prompts.toml",
+        "settings/pr_code_suggestions_reflect_prompts.toml",
        "settings/pr_sort_code_suggestions_prompts.toml",
        "settings/pr_information_from_user_prompts.toml",
        "settings/pr_update_changelog_prompts.toml",
@ -33,6 +34,15 @@ global_settings = Dynaconf(


 def get_settings():
+    """
+    Retrieves the current settings.
+
+    This function attempts to fetch the settings from the starlette_context's context object. If it fails,
+    it defaults to the global settings defined outside of this function.
+
+    Returns:
+        Dynaconf: The current settings object, either from the context or the global default.
+    """
    try:
        return context["settings"]
    except Exception:
@ -40,7 +50,7 @@ def get_settings():


 # Add local configuration from pyproject.toml of the project being reviewed
-def _find_repository_root() -> Path:
+def _find_repository_root() -> Optional[Path]:
    """
    Identify project root directory by recursively searching for the .git directory in the parent directories.
    """
@ -60,7 +70,7 @@ def _find_pyproject() -> Optional[Path]:
    """
    repo_root = _find_repository_root()
    if repo_root:
-        pyproject = _find_repository_root() / "pyproject.toml"
+        pyproject = repo_root / "pyproject.toml"
        return pyproject if pyproject.is_file() else None
    return None

--- a/pr_agent/git_providers/init.py
+++ b/pr_agent/git_providers/init.py
@ -2,12 +2,13 @@ from pr_agent.config_loader import get_settings
 from pr_agent.git_providers.bitbucket_provider import BitbucketProvider
 from pr_agent.git_providers.bitbucket_server_provider import BitbucketServerProvider
 from pr_agent.git_providers.codecommit_provider import CodeCommitProvider
+from pr_agent.git_providers.git_provider import GitProvider
 from pr_agent.git_providers.github_provider import GithubProvider
 from pr_agent.git_providers.gitlab_provider import GitLabProvider
 from pr_agent.git_providers.local_git_provider import LocalGitProvider
 from pr_agent.git_providers.azuredevops_provider import AzureDevopsProvider
 from pr_agent.git_providers.gerrit_provider import GerritProvider
-
+from starlette_context import context

 _GIT_PROVIDERS = {
    'github': GithubProvider,
@ -20,6 +21,7 @@ _GIT_PROVIDERS = {
    'gerrit': GerritProvider,
 }

+
 def get_git_provider():
    try:
        provider_id = get_settings().config.git_provider
@ -28,3 +30,33 @@ def get_git_provider():
    if provider_id not in _GIT_PROVIDERS:
        raise ValueError(f"Unknown git provider: {provider_id}")
    return _GIT_PROVIDERS[provider_id]
+
+
+def get_git_provider_with_context(pr_url) -> GitProvider:
+    """
+    Get a GitProvider instance for the given PR URL. If the GitProvider instance is already in the context, return it.
+    """
+
+    is_context_env = None
+    try:
+        is_context_env = context.get("settings", None)
+    except Exception:
+        pass  # we are not in a context environment (CLI)
+
+    # check if context["git_provider"]["pr_url"] exists
+    if is_context_env and context.get("git_provider", {}).get("pr_url", {}):
+        git_provider = context["git_provider"]["pr_url"]
+        # possibly check if the git_provider is still valid, or if some reset is needed
+        # ...
+        return git_provider
+    else:
+        try:
+            provider_id = get_settings().config.git_provider
+            if provider_id not in _GIT_PROVIDERS:
+                raise ValueError(f"Unknown git provider: {provider_id}")
+            git_provider = _GIT_PROVIDERS[provider_id](pr_url)
+            if is_context_env:
+                context["git_provider"] = {pr_url: git_provider}
+            return git_provider
+        except Exception as e:
+            raise ValueError(f"Failed to get git provider for {pr_url}") from e
--- a/pr_agent/git_providers/azuredevops_provider.py
+++ b/pr_agent/git_providers/azuredevops_provider.py
@ -2,6 +2,7 @@ import os
 from typing import Optional, Tuple
 from urllib.parse import urlparse

+from ..algo.file_filter import filter_ignored
 from ..log import get_logger
 from ..algo.language_handler import is_valid_file
 from ..algo.utils import clip_tokens, find_line_number_of_relevant_line_in_file, load_large_diff
@ -26,6 +27,7 @@ try:
        CommentThread,
        GitVersionDescriptor,
        GitPullRequest,
+        GitPullRequestIterationChanges,
    )
 except ImportError:
    AZURE_DEVOPS_AVAILABLE = False
@ -163,7 +165,7 @@ class AzureDevopsProvider(GitProvider):
                    pull_request_id=self.pr_num,
                )
        except Exception as e:
-            get_logger().exception(f"Failed to publish labels, error: {e}")
+            get_logger().warning(f"Failed to publish labels, error: {e}")

    def get_pr_labels(self, update=False):
        try:
@ -230,32 +232,73 @@ class AzureDevopsProvider(GitProvider):
            base_sha = self.pr.last_merge_target_commit
            head_sha = self.pr.last_merge_source_commit

-            commits = self.azure_devops_client.get_pull_request_commits(
-                project=self.workspace_slug,
+            # Get PR iterations
+            iterations = self.azure_devops_client.get_pull_request_iterations(
                repository_id=self.repo_slug,
                pull_request_id=self.pr_num,
+                project=self.workspace_slug
            )
+            changes = None
+            if iterations:
+                iteration_id = iterations[-1].id  # Get the last iteration (most recent changes)

+                # Get changes for the iteration
+                changes = self.azure_devops_client.get_pull_request_iteration_changes(
+                    repository_id=self.repo_slug,
+                    pull_request_id=self.pr_num,
+                    iteration_id=iteration_id,
+                    project=self.workspace_slug
+                )
            diff_files = []
            diffs = []
            diff_types = {}
+            if changes:
+                for change in changes.change_entries:
+                    item = change.additional_properties.get('item', {})
+                    path = item.get('path', None)
+                    if path:
+                        diffs.append(path)
+                        diff_types[path] = change.additional_properties.get('changeType', 'Unknown')

-            for c in commits:
-                changes_obj = self.azure_devops_client.get_changes(
-                    project=self.workspace_slug,
-                    repository_id=self.repo_slug,
-                    commit_id=c.commit_id,
-                )
-                for i in changes_obj.changes:
-                    if i["item"]["gitObjectType"] == "tree":
-                        continue
-                    diffs.append(i["item"]["path"])
-                    diff_types[i["item"]["path"]] = i["changeType"]
+            # wrong implementation - gets all the files that were changed in any commit in the PR
+            # commits = self.azure_devops_client.get_pull_request_commits(
+            #     project=self.workspace_slug,
+            #     repository_id=self.repo_slug,
+            #     pull_request_id=self.pr_num,
+            # )
+            #
+            # diff_files = []
+            # diffs = []
+            # diff_types = {}

-            diffs = list(set(diffs))
+            # for c in commits:
+            #     changes_obj = self.azure_devops_client.get_changes(
+            #         project=self.workspace_slug,
+            #         repository_id=self.repo_slug,
+            #         commit_id=c.commit_id,
+            #     )
+            #     for i in changes_obj.changes:
+            #         if i["item"]["gitObjectType"] == "tree":
+            #             continue
+            #         diffs.append(i["item"]["path"])
+            #         diff_types[i["item"]["path"]] = i["changeType"]
+            #
+            # diffs = list(set(diffs))

+            diffs_original = diffs
+            diffs = filter_ignored(diffs_original, 'azure')
+            if diffs_original != diffs:
+                try:
+                    get_logger().info(f"Filtered out [ignore] files for pull request:", extra=
+                    {"files": diffs_original,  # diffs is just a list of names
+                     "filtered_files": diffs})
+                except Exception:
+                    pass
+
+            invalid_files_names = []
            for file in diffs:
                if not is_valid_file(file):
+                    invalid_files_names.append(file)
                    continue

                version = GitVersionDescriptor(
@ -273,12 +316,13 @@ class AzureDevopsProvider(GitProvider):

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

                edit_type = EDIT_TYPE.MODIFIED
@ -303,17 +347,17 @@ class AzureDevopsProvider(GitProvider):
                    )
                    original_file_content_str = original_file_content_str.content
                except Exception as error:
-                    get_logger().error(
-                        "Failed to retrieve original file content of %s at version %s. Error: %s",
-                        file,
-                        version,
-                        str(error),
-                    )
+                    get_logger().error(f"Failed to retrieve original file content of {file} at version {version}. Error: {str(error)}")
                    original_file_content_str = ""

                patch = load_large_diff(
-                    file, new_file_content_str, original_file_content_str
-                )
+                    file, new_file_content_str, original_file_content_str, show_warning=False
+                ).rstrip()
+
+                # count number of lines added and removed
+                patch_lines = patch.splitlines(keepends=True)
+                num_plus_lines = len([line for line in patch_lines if line.startswith('+')])
+                num_minus_lines = len([line for line in patch_lines if line.startswith('-')])

                diff_files.append(
                    FilePatchInfo(
@ -322,8 +366,12 @@ class AzureDevopsProvider(GitProvider):
                        patch=patch,
                        filename=file,
                        edit_type=edit_type,
+                        num_plus_lines=num_plus_lines,
+                        num_minus_lines=num_minus_lines,
                    )
                )
+            get_logger().info(f"Invalid files: {invalid_files_names}")
+
            self.diff_files = diff_files
            return diff_files
        except Exception as e:
@ -384,7 +432,7 @@ class AzureDevopsProvider(GitProvider):
        except Exception as e:
            get_logger().exception(f"Failed to remove temp comments, error: {e}")

-    def publish_inline_comment(self, body: str, relevant_file: str, relevant_line_in_file: str):
+    def publish_inline_comment(self, body: str, relevant_file: str, relevant_line_in_file: str, original_suggestion=None):
        self.publish_inline_comments([self.create_inline_comment(body, relevant_file, relevant_line_in_file)])


@ -404,7 +452,7 @@ class AzureDevopsProvider(GitProvider):
        return dict(body=body, path=path, position=position, absolute_position=absolute_position) if subject_type == "LINE" else {}

    def publish_inline_comments(self, comments: list[dict], disable_fallback: bool = False):
-            overall_sucess = True
+            overall_success = True
            for comment in comments:
                try:
                    self.publish_comment(comment["body"],
@ -426,8 +474,8 @@ class AzureDevopsProvider(GitProvider):
                except Exception as e:
                    if get_settings().config.verbosity_level >= 2:
                        get_logger().error(f"Failed to publish code suggestion, error: {e}")
-                    overall_sucess = False
-            return overall_sucess
+                    overall_success = False
+            return overall_success

    def get_title(self):
        return self.pr.title
@ -477,10 +525,18 @@ class AzureDevopsProvider(GitProvider):
    def get_user_id(self):
        return 0

+
    def get_issue_comments(self):
-        raise NotImplementedError(
-            "Azure DevOps provider does not support issue comments yet"
-        )
+        threads = self.azure_devops_client.get_threads(repository_id=self.repo_slug, pull_request_id=self.pr_num, project=self.workspace_slug)
+        threads.reverse()
+        comment_list = []
+        for thread in threads:
+            for comment in thread.comments:
+                if comment.content and comment not in comment_list:
+                    comment.body = comment.content
+                    comment.thread_id = thread.id
+                    comment_list.append(comment)
+        return comment_list

    def add_eyes_reaction(self, issue_comment_id: int, disable_eyes: bool = False) -> Optional[int]:
        return True
--- a/pr_agent/git_providers/bitbucket_provider.py
+++ b/pr_agent/git_providers/bitbucket_provider.py
@ -7,10 +7,18 @@ from atlassian.bitbucket import Cloud
 from starlette_context import context

 from pr_agent.algo.types import FilePatchInfo, EDIT_TYPE
+from ..algo.file_filter import filter_ignored
+from ..algo.language_handler import is_valid_file
 from ..algo.utils import find_line_number_of_relevant_line_in_file
 from ..config_loader import get_settings
 from ..log import get_logger
-from .git_provider import GitProvider
+from .git_provider import GitProvider, MAX_FILES_ALLOWED_FULL
+
+
+def _gef_filename(diff):
+    if diff.new.path:
+        return diff.new.path
+    return diff.old.path


 class BitbucketProvider(GitProvider):
@ -28,6 +36,7 @@ class BitbucketProvider(GitProvider):
        s.headers["Content-Type"] = "application/json"
        self.headers = s.headers
        self.bitbucket_client = Cloud(session=s)
+        self.max_comment_length = 31000
        self.workspace_slug = None
        self.repo_slug = None
        self.repo = None
@ -37,6 +46,7 @@ class BitbucketProvider(GitProvider):
        self.temp_comments = []
        self.incremental = incremental
        self.diff_files = None
+        self.git_files = None
        if pr_url:
            self.set_pr(pr_url)
        self.bitbucket_comment_api_url = self.pr._BitbucketBase__data["links"]["comments"]["href"]
@ -106,8 +116,12 @@ class BitbucketProvider(GitProvider):
                get_logger().error(f"Failed to publish code suggestion, error: {e}")
            return False

+    def publish_file_comments(self, file_comments: list) -> bool:
+        pass
+
    def is_supported(self, capability: str) -> bool:
-        if capability in ['get_issue_comments', 'publish_inline_comments', 'get_labels', 'gfm_markdown']:
+        if capability in ['get_issue_comments', 'publish_inline_comments', 'get_labels', 'gfm_markdown',
+                          'publish_file_comments']:
            return False
        return True

@ -116,28 +130,129 @@ class BitbucketProvider(GitProvider):
        self.pr = self._get_pr()

    def get_files(self):
-        return [diff.new.path for diff in self.pr.diffstat()]
+        try:
+            git_files = context.get("git_files", None)
+            if git_files:
+                return git_files
+            self.git_files = [_gef_filename(diff) for diff in self.pr.diffstat()]
+            context["git_files"] = self.git_files
+            return self.git_files
+        except Exception:
+            if not self.git_files:
+                self.git_files = [_gef_filename(diff) for diff in self.pr.diffstat()]
+            return self.git_files

    def get_diff_files(self) -> list[FilePatchInfo]:
        if self.diff_files:
            return self.diff_files

-        diffs = self.pr.diffstat()
-        diff_split = [
-            "diff --git%s" % x for x in self.pr.diff().split("diff --git") if x.strip()
-        ]
+        diffs_original = list(self.pr.diffstat())
+        diffs = filter_ignored(diffs_original, 'bitbucket')
+        if diffs != diffs_original:
+            try:
+                names_original = [d.new.path for d in diffs_original]
+                names_kept = [d.new.path for d in diffs]
+                names_filtered = list(set(names_original) - set(names_kept))
+                get_logger().info(f"Filtered out [ignore] files for PR", extra={
+                    'original_files': names_original,
+                    'names_kept': names_kept,
+                    'names_filtered': names_filtered

+                })
+            except Exception as e:
+                pass
+
+        # get the pr patches
+        try:
+            pr_patches = self.pr.diff()
+        except Exception as e:
+            # Try different encodings if UTF-8 fails
+            get_logger().warning(f"Failed to decode PR patch with utf-8, error: {e}")
+            encodings_to_try = ['iso-8859-1', 'latin-1', 'ascii', 'utf-16']
+            pr_patches = None
+            for encoding in encodings_to_try:
+                try:
+                    pr_patches = self.pr.diff(encoding=encoding)
+                    get_logger().info(f"Successfully decoded PR patch with encoding {encoding}")
+                    break
+                except UnicodeDecodeError:
+                    continue
+
+            if pr_patches is None:
+                raise ValueError(f"Failed to decode PR patch with encodings {encodings_to_try}")
+
+        diff_split = ["diff --git" + x for x in pr_patches.split("diff --git") if x.strip()]
+        # filter all elements of 'diff_split' that are of indices in 'diffs_original' that are not in 'diffs'
+        if len(diff_split) > len(diffs) and len(diffs_original) == len(diff_split):
+            diff_split = [diff_split[i] for i in range(len(diff_split)) if diffs_original[i] in diffs]
+        if len(diff_split) != len(diffs):
+            get_logger().error(f"Error - failed to split the diff into {len(diffs)} parts")
+            return []
+        # bitbucket diff has a header for each file, we need to remove it:
+        # "diff --git filename
+        # new file mode 100644 (optional)
+        #  index caa56f0..61528d7 100644
+        #   --- a/pr_agent/cli_pip.py
+        #  +++ b/pr_agent/cli_pip.py
+        #   @@ -... @@"
+        for i, _ in enumerate(diff_split):
+            diff_split_lines = diff_split[i].splitlines()
+            if (len(diff_split_lines) >= 6) and \
+                    ((diff_split_lines[2].startswith("---") and
+                      diff_split_lines[3].startswith("+++") and
+                      diff_split_lines[4].startswith("@@")) or
+                     (diff_split_lines[3].startswith("---") and  # new or deleted file
+                      diff_split_lines[4].startswith("+++") and
+                      diff_split_lines[5].startswith("@@"))):
+                diff_split[i] = "\n".join(diff_split_lines[4:])
+            else:
+                if diffs[i].data.get('lines_added', 0) == 0 and diffs[i].data.get('lines_removed', 0) == 0:
+                    diff_split[i] = ""
+                elif len(diff_split_lines) <= 3:
+                    diff_split[i] = ""
+                    get_logger().info(f"Disregarding empty diff for file {_gef_filename(diffs[i])}")
+                else:
+                    get_logger().warning(f"Bitbucket failed to get diff for file {_gef_filename(diffs[i])}")
+                    diff_split[i] = ""
+
+        invalid_files_names = []
        diff_files = []
+        counter_valid = 0
+        # get full files
        for index, diff in enumerate(diffs):
+            file_path = _gef_filename(diff)
+            if not is_valid_file(file_path):
+                invalid_files_names.append(file_path)
+                continue
+
+            try:
+                counter_valid += 1
+                if counter_valid < MAX_FILES_ALLOWED_FULL // 2:  # factor 2 because bitbucket has limited API calls
+                    if diff.old.get_data("links"):
                        original_file_content_str = self._get_pr_file_content(
-                diff.old.get_data("links")
-            )
-            new_file_content_str = self._get_pr_file_content(diff.new.get_data("links"))
+                            diff.old.get_data("links")['self']['href'])
+                    else:
+                        original_file_content_str = ""
+                    if diff.new.get_data("links"):
+                        new_file_content_str = self._get_pr_file_content(diff.new.get_data("links")['self']['href'])
+                    else:
+                        new_file_content_str = ""
+                else:
+                    if counter_valid == MAX_FILES_ALLOWED_FULL // 2:
+                        get_logger().info(
+                            f"Bitbucket too many files in PR, will avoid loading full content for rest of files")
+                    original_file_content_str = ""
+                    new_file_content_str = ""
+            except Exception as e:
+                get_logger().exception(f"Error - bitbucket failed to get file content, error: {e}")
+                original_file_content_str = ""
+                new_file_content_str = ""
+
            file_patch_canonic_structure = FilePatchInfo(
                original_file_content_str,
                new_file_content_str,
                diff_split[index],
-                diff.new.path,
+                file_path,
            )

            if diff.data['status'] == 'added':
@ -150,6 +265,8 @@ class BitbucketProvider(GitProvider):
                file_patch_canonic_structure.edit_type = EDIT_TYPE.RENAMED
            diff_files.append(file_patch_canonic_structure)

+        if invalid_files_names:
+            get_logger().info(f"Disregarding files with invalid extensions:\n{invalid_files_names}")

        self.diff_files = diff_files
        return diff_files
@ -172,7 +289,7 @@ class BitbucketProvider(GitProvider):
                    latest_commit_url = self.get_latest_commit_url()
                    comment_url = self.get_comment_url(comment)
                    if update_header:
-                        updated_header = f"{initial_header}\n\n### ({name.capitalize()} updated until commit {latest_commit_url})\n"
+                        updated_header = f"{initial_header}\n\n#### ({name.capitalize()} updated until commit {latest_commit_url})\n"
                        pr_comment_updated = pr_comment.replace(initial_header, updated_header)
                    else:
                        pr_comment_updated = pr_comment
@ -189,6 +306,7 @@ class BitbucketProvider(GitProvider):
        self.publish_comment(pr_comment)

    def publish_comment(self, pr_comment: str, is_temporary: bool = False):
+        pr_comment = self.limit_output_characters(pr_comment, self.max_comment_length)
        comment = self.pr.comment(pr_comment)
        if is_temporary:
            self.temp_comments.append(comment["id"])
@ -196,6 +314,7 @@ class BitbucketProvider(GitProvider):

    def edit_comment(self, comment, body: str):
        try:
+            body = self.limit_output_characters(body, self.max_comment_length)
            comment.update(body)
        except Exception as e:
            get_logger().exception(f"Failed to update comment, error: {e}")
@ -213,11 +332,14 @@ class BitbucketProvider(GitProvider):
        except Exception as e:
            get_logger().exception(f"Failed to remove comment, error: {e}")

-    # funtion to create_inline_comment
-    def create_inline_comment(self, body: str, relevant_file: str, relevant_line_in_file: str, absolute_position: int = None):
+    # function to create_inline_comment
+    def create_inline_comment(self, body: str, relevant_file: str, relevant_line_in_file: str,
+                              absolute_position: int = None):
+        body = self.limit_output_characters(body, self.max_comment_length)
        position, absolute_position = find_line_number_of_relevant_line_in_file(self.get_diff_files(),
                                                                                relevant_file.strip('`'),
-                                                                            relevant_line_in_file, absolute_position)
+                                                                                relevant_line_in_file,
+                                                                                absolute_position)
        if position == -1:
            if get_settings().config.verbosity_level >= 2:
                get_logger().info(f"Could not find position for {relevant_file} {relevant_line_in_file}")
@ -227,8 +349,8 @@ class BitbucketProvider(GitProvider):
        path = relevant_file.strip()
        return dict(body=body, path=path, position=absolute_position) if subject_type == "LINE" else {}

-
-    def publish_inline_comment(self, comment: str, from_line: int, file: str):
+    def publish_inline_comment(self, comment: str, from_line: int, file: str, original_suggestion=None):
+        comment = self.limit_output_characters(comment, self.max_comment_length)
        payload = json.dumps({
            "content": {
                "raw": comment,
@ -292,6 +414,9 @@ class BitbucketProvider(GitProvider):
    def get_pr_branch(self):
        return self.pr.source_branch

+    def get_pr_owner_id(self) -> str | None:
+        return self.workspace_slug
+
    def get_pr_description_full(self):
        return self.pr.description

@ -358,7 +483,6 @@ class BitbucketProvider(GitProvider):
        except Exception:
            return ""

-
    def create_or_update_pr_file(self, file_path: str, branch: str, contents="", message="") -> None:
        url = (f"https://api.bitbucket.org/2.0/repositories/{self.workspace_slug}/{self.repo_slug}/src/")
        if not message:
@ -378,6 +502,13 @@ class BitbucketProvider(GitProvider):
            get_logger().exception(f"Failed to create empty file {file_path} in branch {branch}")

    def _get_pr_file_content(self, remote_link: str):
+        try:
+            response = requests.request("GET", remote_link, headers=self.headers)
+            if response.status_code == 404:  # not found
+                return ""
+            contents = response.text
+            return contents
+        except Exception:
            return ""

    def get_commit_messages(self):
--- a/pr_agent/git_providers/bitbucket_server_provider.py
+++ b/pr_agent/git_providers/bitbucket_server_provider.py
@ -1,13 +1,13 @@
-import json
+from distutils.version import LooseVersion
+from requests.exceptions import HTTPError
 from typing import Optional, Tuple
-from urllib.parse import urlparse
+from urllib.parse import quote_plus, urlparse

-import requests
 from atlassian.bitbucket import Bitbucket
-from starlette_context import context

 from .git_provider import GitProvider
-from pr_agent.algo.types import FilePatchInfo
+from ..algo.types import EDIT_TYPE, FilePatchInfo
+from ..algo.language_handler import is_valid_file
 from ..algo.utils import load_large_diff, find_line_number_of_relevant_line_in_file
 from ..config_loader import get_settings
 from ..log import get_logger
@ -15,19 +15,9 @@ from ..log import get_logger

 class BitbucketServerProvider(GitProvider):
    def __init__(
-        self, pr_url: Optional[str] = None, incremental: Optional[bool] = False
+            self, pr_url: Optional[str] = None, incremental: Optional[bool] = False,
+            bitbucket_client: Optional[Bitbucket] = None,
    ):
-        s = requests.Session()
-        try:
-            bearer = context.get("bitbucket_bearer_token", None)
-            s.headers["Authorization"] = f"Bearer {bearer}"
-        except Exception:
-            s.headers[
-                "Authorization"
-            ] = f'Bearer {get_settings().get("BITBUCKET_SERVER.BEARER_TOKEN", None)}'
-
-        s.headers["Content-Type"] = "application/json"
-        self.headers = s.headers
        self.bitbucket_server_url = None
        self.workspace_slug = None
        self.repo_slug = None
@ -41,24 +31,33 @@ class BitbucketServerProvider(GitProvider):
        self.bitbucket_pull_request_api_url = pr_url

        self.bitbucket_server_url = self._parse_bitbucket_server(url=pr_url)
-        self.bitbucket_client = Bitbucket(url=self.bitbucket_server_url,
-                                          token=get_settings().get("BITBUCKET_SERVER.BEARER_TOKEN", None))
+        self.bitbucket_client = bitbucket_client or Bitbucket(url=self.bitbucket_server_url,
+                                                              token=get_settings().get("BITBUCKET_SERVER.BEARER_TOKEN",
+                                                                                       None))
+        try:
+            self.bitbucket_api_version = LooseVersion(self.bitbucket_client.get("rest/api/1.0/application-properties").get('version'))
+        except Exception:
+            self.bitbucket_api_version = None

        if pr_url:
            self.set_pr(pr_url)

    def get_repo_settings(self):
        try:
-            url = (f"{self.bitbucket_server_url}/projects/{self.workspace_slug}/repos/{self.repo_slug}/src/"
-                   f"{self.pr.destination_branch}/.pr_agent.toml")
-            response = requests.request("GET", url, headers=self.headers)
-            if response.status_code == 404:  # not found
+            content = self.bitbucket_client.get_content_of_file(self.workspace_slug, self.repo_slug, ".pr_agent.toml", self.get_pr_branch())
+
+            return content
+        except Exception as e:
+            if isinstance(e, HTTPError):
+                if e.response.status_code == 404:  # not found
                    return ""
-            contents = response.text.encode('utf-8')
-            return contents
-        except Exception:
+
+            get_logger().error(f"Failed to load .pr_agent.toml file, error: {e}")
            return ""

+    def get_pr_id(self):
+        return self.pr_num
+
    def publish_code_suggestions(self, code_suggestions: list) -> bool:
        """
        Publishes code suggestions as comments on the PR.
@ -87,6 +86,8 @@ class BitbucketServerProvider(GitProvider):
                continue

            if relevant_lines_end > relevant_lines_start:
+                # Bitbucket does not support multi-line suggestions so use a code block instead - https://jira.atlassian.com/browse/BSERV-4553
+                body = body.replace("```suggestion", "```")
                post_parameters = {
                    "body": body,
                    "path": relevant_file,
@ -111,8 +112,11 @@ class BitbucketServerProvider(GitProvider):
                get_logger().error(f"Failed to publish code suggestion, error: {e}")
            return False

+    def publish_file_comments(self, file_comments: list) -> bool:
+        pass
+
    def is_supported(self, capability: str) -> bool:
-        if capability in ['get_issue_comments', 'get_labels', 'gfm_markdown']:
+        if capability in ['get_issue_comments', 'get_labels', 'gfm_markdown', 'publish_file_comments']:
            return False
        return True

@ -127,7 +131,7 @@ class BitbucketServerProvider(GitProvider):
                                                                     self.repo_slug,
                                                                     path,
                                                                     commit_id)
-        except requests.HTTPError as e:
+        except HTTPError as e:
            get_logger().debug(f"File {path} not found at commit id: {commit_id}")
        return file_content

@ -136,18 +140,50 @@ class BitbucketServerProvider(GitProvider):
        diffstat = [change["path"]['toString'] for change in changes]
        return diffstat

+    #gets the best common ancestor: https://git-scm.com/docs/git-merge-base
+    @staticmethod
+    def get_best_common_ancestor(source_commits_list, destination_commits_list, guaranteed_common_ancestor) -> str:
+        destination_commit_hashes = {commit['id'] for commit in destination_commits_list} | {guaranteed_common_ancestor}
+
+        for commit in source_commits_list:
+            for parent_commit in commit['parents']:
+                if parent_commit['id'] in destination_commit_hashes:
+                    return parent_commit['id']
+
+        return guaranteed_common_ancestor
+
    def get_diff_files(self) -> list[FilePatchInfo]:
        if self.diff_files:
            return self.diff_files

-        commits_in_pr = self.bitbucket_client.get_pull_requests_commits(
+        head_sha = self.pr.fromRef['latestCommit']
+
+        # if Bitbucket api version is >= 8.16 then use the merge-base api for 2-way diff calculation
+        if self.bitbucket_api_version is not None and self.bitbucket_api_version >= LooseVersion("8.16"):
+            try:
+                base_sha = self.bitbucket_client.get(self._get_merge_base())['id']
+            except Exception as e:
+                get_logger().error(f"Failed to get the best common ancestor for PR: {self.pr_url}, \nerror: {e}")
+                raise e
+        else:
+            source_commits_list = list(self.bitbucket_client.get_pull_requests_commits(
                self.workspace_slug,
                self.repo_slug,
                self.pr_num
-        )
-
-        commit_list = list(commits_in_pr)
-        base_sha, head_sha = commit_list[0]['parents'][0]['id'], commit_list[-1]['id']
+            ))
+            # if Bitbucket api version is None or < 7.0 then do a simple diff with a guaranteed common ancestor
+            base_sha = source_commits_list[-1]['parents'][0]['id']
+            # if Bitbucket api version is 7.0-8.15 then use 2-way diff functionality for the base_sha
+            if self.bitbucket_api_version is not None and self.bitbucket_api_version >= LooseVersion("7.0"):
+                try:
+                    destination_commits = list(
+                        self.bitbucket_client.get_commits(self.workspace_slug, self.repo_slug, base_sha,
+                                                          self.pr.toRef['latestCommit']))
+                    base_sha = self.get_best_common_ancestor(source_commits_list, destination_commits, base_sha)
+                except Exception as e:
+                    get_logger().error(
+                        f"Failed to get the commit list for calculating best common ancestor for PR: {self.pr_url}, \nerror: {e}")
+                    raise e

        diff_files = []
        original_file_content_str = ""
@ -156,6 +192,10 @@ class BitbucketServerProvider(GitProvider):
        changes = self.bitbucket_client.get_pull_requests_changes(self.workspace_slug, self.repo_slug, self.pr_num)
        for change in changes:
            file_path = change['path']['toString']
+            if not is_valid_file(file_path.split("/")[-1]):
+                get_logger().info(f"Skipping a non-code file: {file_path}")
+                continue
+
            match change['type']:
                case 'ADD':
                    edit_type = EDIT_TYPE.ADDED
@ -209,7 +249,7 @@ class BitbucketServerProvider(GitProvider):
    def remove_comment(self, comment):
        pass

-    # funtion to create_inline_comment
+    # function to create_inline_comment
    def create_inline_comment(self, body: str, relevant_file: str, relevant_line_in_file: str,
                              absolute_position: int = None):

@ -228,7 +268,7 @@ class BitbucketServerProvider(GitProvider):
        path = relevant_file.strip()
        return dict(body=body, path=path, position=absolute_position) if subject_type == "LINE" else {}

-    def publish_inline_comment(self, comment: str, from_line: int, file: str):
+    def publish_inline_comment(self, comment: str, from_line: int, file: str, original_suggestion=None):
        payload = {
            "text": comment,
            "severity": "NORMAL",
@ -241,8 +281,18 @@ class BitbucketServerProvider(GitProvider):
            }
        }

-        response = requests.post(url=self._get_pr_comments_url(), json=payload, headers=self.headers)
-        return response
+        try:
+            self.bitbucket_client.post(self._get_pr_comments_path(), data=payload)
+        except Exception as e:
+            get_logger().error(f"Failed to publish inline comment to '{file}' at line {from_line}, error: {e}")
+            raise e
+
+    def get_line_link(self, relevant_file: str, relevant_line_start: int, relevant_line_end: int = None) -> str:
+        if relevant_line_start == -1:
+            link = f"{self.pr_url}/diff#{quote_plus(relevant_file)}"
+        else:
+            link = f"{self.pr_url}/diff#{quote_plus(relevant_file)}?t={relevant_line_start}"
+        return link

    def generate_link_to_relevant_line_number(self, suggestion) -> str:
        try:
@ -255,18 +305,37 @@ class BitbucketServerProvider(GitProvider):
            position, absolute_position = find_line_number_of_relevant_line_in_file \
                (diff_files, relevant_file, relevant_line_str)

+            if absolute_position != -1:
+                if self.pr:
+                    link = f"{self.pr_url}/diff#{quote_plus(relevant_file)}?t={absolute_position}"
+                    return link
+                else:
+                    if get_settings().config.verbosity_level >= 2:
+                        get_logger().info(f"Failed adding line link to '{relevant_file}' since PR not set")
+            else:
+                if get_settings().config.verbosity_level >= 2:
+                    get_logger().info(f"Failed adding line link to '{relevant_file}' since position not found")
+
            if absolute_position != -1 and self.pr_url:
-                link = f"{self.pr_url}/#L{relevant_file}T{absolute_position}"
+                link = f"{self.pr_url}/diff#{quote_plus(relevant_file)}?t={absolute_position}"
                return link
        except Exception as e:
            if get_settings().config.verbosity_level >= 2:
-                get_logger().info(f"Failed adding line link, error: {e}")
+                get_logger().info(f"Failed adding line link to '{relevant_file}', error: {e}")

        return ""

    def publish_inline_comments(self, comments: list[dict]):
        for comment in comments:
+            if 'position' in comment:
                self.publish_inline_comment(comment['body'], comment['position'], comment['path'])
+            elif 'start_line' in comment:  # multi-line comment
+                # note that bitbucket does not seem to support range - only a comment on a single line - https://community.developer.atlassian.com/t/api-post-endpoint-for-inline-pull-request-comments/60452
+                self.publish_inline_comment(comment['body'], comment['start_line'], comment['path'])
+            elif 'line' in comment:  # single-line comment
+                self.publish_inline_comment(comment['body'], comment['line'], comment['path'])
+            else:
+                get_logger().error(f"Could not publish inline comment: {comment}")

    def get_title(self):
        return self.pr.title
@ -277,8 +346,14 @@ class BitbucketServerProvider(GitProvider):
    def get_pr_branch(self):
        return self.pr.fromRef['displayId']

+    def get_pr_owner_id(self) -> str | None:
+        return self.workspace_slug
+
    def get_pr_description_full(self):
+        if hasattr(self.pr, "description"):
            return self.pr.description
+        else:
+            return None

    def get_user_id(self):
        return 0
@ -296,16 +371,31 @@ class BitbucketServerProvider(GitProvider):

    @staticmethod
    def _parse_bitbucket_server(url: str) -> str:
+        # pr url format: f"{bitbucket_server}/projects/{project_name}/repos/{repository_name}/pull-requests/{pr_id}"
        parsed_url = urlparse(url)
+        server_path = parsed_url.path.split("/projects/")
+        if len(server_path) > 1:
+            server_path = server_path[0].strip("/")
+            return f"{parsed_url.scheme}://{parsed_url.netloc}/{server_path}".strip("/")
        return f"{parsed_url.scheme}://{parsed_url.netloc}"

    @staticmethod
    def _parse_pr_url(pr_url: str) -> Tuple[str, str, int]:
+        # pr url format: f"{bitbucket_server}/projects/{project_name}/repos/{repository_name}/pull-requests/{pr_id}"
        parsed_url = urlparse(pr_url)
+
        path_parts = parsed_url.path.strip("/").split("/")
-        if len(path_parts) < 6 or path_parts[4] != "pull-requests":
+
+        try:
+            projects_index = path_parts.index("projects")
+        except ValueError as e:
+            raise ValueError(f"The provided URL '{pr_url}' does not appear to be a Bitbucket PR URL")
+
+        path_parts = path_parts[projects_index:]
+
+        if len(path_parts) < 6 or path_parts[2] != "repos" or path_parts[4] != "pull-requests":
            raise ValueError(
-                "The provided URL does not appear to be a Bitbucket PR URL"
+                f"The provided URL '{pr_url}' does not appear to be a Bitbucket PR URL"
            )

        workspace_slug = path_parts[1]
@ -313,7 +403,7 @@ class BitbucketServerProvider(GitProvider):
        try:
            pr_number = int(path_parts[5])
        except ValueError as e:
-            raise ValueError("Unable to convert PR number to integer") from e
+            raise ValueError(f"Unable to convert PR number '{path_parts[5]}' to integer") from e

        return workspace_slug, repo_slug, pr_number

@ -323,24 +413,33 @@ class BitbucketServerProvider(GitProvider):
        return self.repo

    def _get_pr(self):
-        pr = self.bitbucket_client.get_pull_request(self.workspace_slug, self.repo_slug, pull_request_id=self.pr_num)
+        try:
+            pr = self.bitbucket_client.get_pull_request(self.workspace_slug, self.repo_slug,
+                                                        pull_request_id=self.pr_num)
            return type('new_dict', (object,), pr)
+        except Exception as e:
+            get_logger().error(f"Failed to get pull request, error: {e}")
+            raise e

    def _get_pr_file_content(self, remote_link: str):
        return ""

    def get_commit_messages(self):
-        def get_commit_messages(self):
-            raise NotImplementedError("Get commit messages function not implemented yet.")
+        return ""
+
    # bitbucket does not support labels
    def publish_description(self, pr_title: str, description: str):
-        payload = json.dumps({
+        payload = {
+            "version": self.pr.version,
            "description": description,
-            "title": pr_title
-        })
-
-        response = requests.put(url=self.bitbucket_pull_request_api_url, headers=self.headers, data=payload)
-        return response
+            "title": pr_title,
+            "reviewers": self.pr.reviewers  # needs to be sent otherwise gets wiped
+        }
+        try:
+            self.bitbucket_client.update_pull_request(self.workspace_slug, self.repo_slug, str(self.pr_num), payload)
+        except Exception as e:
+            get_logger().error(f"Failed to update pull request, error: {e}")
+            raise e

    # bitbucket does not support labels
    def publish_labels(self, pr_types: list):
@ -350,5 +449,8 @@ class BitbucketServerProvider(GitProvider):
    def get_pr_labels(self, update=False):
        pass

-    def _get_pr_comments_url(self):
-        return f"{self.bitbucket_server_url}/rest/api/latest/projects/{self.workspace_slug}/repos/{self.repo_slug}/pull-requests/{self.pr_num}/comments"
+    def _get_pr_comments_path(self):
+        return f"rest/api/latest/projects/{self.workspace_slug}/repos/{self.repo_slug}/pull-requests/{self.pr_num}/comments"
+
+    def _get_merge_base(self):
+        return f"rest/api/latest/projects/{self.workspace_slug}/repos/{self.repo_slug}/pull-requests/{self.pr_num}/merge-base"
--- a/pr_agent/git_providers/codecommit_provider.py
+++ b/pr_agent/git_providers/codecommit_provider.py
@ -225,7 +225,7 @@ class CodeCommitProvider(GitProvider):
    def remove_comment(self, comment):
        return ""  # not implemented yet

-    def publish_inline_comment(self, body: str, relevant_file: str, relevant_line_in_file: str):
+    def publish_inline_comment(self, body: str, relevant_file: str, relevant_line_in_file: str, original_suggestion=None):
        # 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
@ -376,7 +376,7 @@ class GerritProvider(GitProvider):
            'provider')

    def publish_inline_comment(self, body: str, relevant_file: str,
-                               relevant_line_in_file: str):
+                               relevant_line_in_file: str, original_suggestion=None):
        raise NotImplementedError(
            'Publishing inline comments is not implemented for the gerrit '
            'provider')
--- a/pr_agent/git_providers/git_provider.py
+++ b/pr_agent/git_providers/git_provider.py
@ -3,20 +3,28 @@ from abc import ABC, abstractmethod
 # enum EDIT_TYPE (ADDED, DELETED, MODIFIED, RENAMED)
 from typing import Optional

+from pr_agent.algo.utils import Range
 from pr_agent.config_loader import get_settings
 from pr_agent.algo.types import FilePatchInfo
 from pr_agent.log import get_logger
-
+MAX_FILES_ALLOWED_FULL = 50

 class GitProvider(ABC):
    @abstractmethod
    def is_supported(self, capability: str) -> bool:
        pass

+    @abstractmethod
+    def get_files(self) -> list:
+        pass
+
    @abstractmethod
    def get_diff_files(self) -> list[FilePatchInfo]:
        pass

+    def get_incremental_commits(self, is_incremental):
+        pass
+
    @abstractmethod
    def publish_description(self, pr_title: str, pr_body: str):
        pass
@ -44,6 +52,12 @@ class GitProvider(ABC):
    def edit_comment(self, comment, body: str):
        pass

+    def edit_comment_from_comment_id(self, comment_id: int, body: str):
+        pass
+
+    def get_comment_body_from_comment_id(self, comment_id: int) -> str:
+        pass
+
    def reply_to_comment_from_comment_id(self, comment_id: int, body: str):
        pass

@ -67,11 +81,12 @@ class GitProvider(ABC):
        # if the existing description wasn't generated by the pr-agent, just return it as-is
        if not self._is_generated_by_pr_agent(description_lowercase):
            get_logger().info(f"Existing description was not generated by the pr-agent")
+            self.user_description = description
            return description

        # if the existing description was generated by the pr-agent, but it doesn't contain a user description,
        # return nothing (empty string) because it means there is no user description
-        user_description_header = "## **user description**"
+        user_description_header = "### **user description**"
        if user_description_header not in description_lowercase:
            get_logger().info(f"Existing description was generated by the pr-agent, but it doesn't contain a user description")
            return ""
@ -102,8 +117,8 @@ class GitProvider(ABC):
        return original_user_description

    def _possible_headers(self):
-        return ("## **user description**", "## **pr type**", "## **pr description**", "## **pr labels**", "## **type**", "## **description**",
-                "## **labels**", "### 🤖 generated by pr agent")
+        return ("### **user description**", "### **pr type**", "### **pr description**", "### **pr labels**", "### **type**", "### **description**",
+                "### **labels**", "### 🤖 generated by pr agent")

    def _is_generated_by_pr_agent(self, description_lowercase: str) -> bool:
        possible_headers = self._possible_headers()
@ -113,12 +128,18 @@ class GitProvider(ABC):
    def get_repo_settings(self):
        pass

+    def get_workspace_name(self):
+        return ""
+
    def get_pr_id(self):
        return ""

    def get_line_link(self, relevant_file: str, relevant_line_start: int, relevant_line_end: int = None) -> str:
        return ""

+    def get_lines_link_original_file(self, filepath:str, component_range: Range) -> str:
+        return ""
+
    #### comments operations ####
    @abstractmethod
    def publish_comment(self, pr_comment: str, is_temporary: bool = False):
@ -131,8 +152,37 @@ class GitProvider(ABC):
                                   final_update_message=True):
        self.publish_comment(pr_comment)

+    def publish_persistent_comment_full(self, pr_comment: str,
+                                   initial_header: str,
+                                   update_header: bool = True,
+                                   name='review',
+                                   final_update_message=True):
+        try:
+            prev_comments = list(self.get_issue_comments())
+            for comment in prev_comments:
+                if comment.body.startswith(initial_header):
+                    latest_commit_url = self.get_latest_commit_url()
+                    comment_url = self.get_comment_url(comment)
+                    if update_header:
+                        updated_header = f"{initial_header}\n\n#### ({name.capitalize()} updated until commit {latest_commit_url})\n"
+                        pr_comment_updated = pr_comment.replace(initial_header, updated_header)
+                    else:
+                        pr_comment_updated = pr_comment
+                    get_logger().info(f"Persistent mode - updating comment {comment_url} to latest {name} message")
+                    # response = self.mr.notes.update(comment.id, {'body': pr_comment_updated})
+                    self.edit_comment(comment, pr_comment_updated)
+                    if final_update_message:
+                        self.publish_comment(
+                            f"**[Persistent {name}]({comment_url})** updated to latest commit {latest_commit_url}")
+                    return
+        except Exception as e:
+            get_logger().exception(f"Failed to update persistent review, error: {e}")
+            pass
+        self.publish_comment(pr_comment)
+
+
    @abstractmethod
-    def publish_inline_comment(self, body: str, relevant_file: str, relevant_line_in_file: str):
+    def publish_inline_comment(self, body: str, relevant_file: str, relevant_line_in_file: str, original_suggestion=None):
        pass

    def create_inline_comment(self, body: str, relevant_file: str, relevant_line_in_file: str,
@ -203,6 +253,9 @@ class GitProvider(ABC):
        except Exception as e:
            return -1

+    def limit_output_characters(self, output: str, max_chars: int):
+        return output[:max_chars] + '...' if len(output) > max_chars else output
+

 def get_main_pr_language(languages, files) -> str:
    """
@ -273,6 +326,8 @@ def get_main_pr_language(languages, files) -> str:
    return main_language_str


+
+
 class IncrementalPR:
    def __init__(self, is_incremental: bool = False):
        self.is_incremental = is_incremental
--- a/pr_agent/git_providers/github_provider.py
+++ b/pr_agent/git_providers/github_provider.py
@ -1,3 +1,4 @@
+import itertools
 import time
 import hashlib
 from datetime import datetime
@ -8,24 +9,28 @@ from github import AppAuthentication, Auth, Github, GithubException
 from retry import retry
 from starlette_context import context

+from ..algo.file_filter import filter_ignored
 from ..algo.language_handler import is_valid_file
-from ..algo.utils import load_large_diff, clip_tokens, find_line_number_of_relevant_line_in_file
+from ..algo.utils import PRReviewHeader, load_large_diff, clip_tokens, find_line_number_of_relevant_line_in_file, Range
 from ..config_loader import get_settings
 from ..log import get_logger
 from ..servers.utils import RateLimitExceeded
-from .git_provider import GitProvider, IncrementalPR
+from .git_provider import GitProvider, IncrementalPR, MAX_FILES_ALLOWED_FULL
 from pr_agent.algo.types import EDIT_TYPE, FilePatchInfo


 class GithubProvider(GitProvider):
-    def __init__(self, pr_url: Optional[str] = None, incremental=IncrementalPR(False)):
+    def __init__(self, pr_url: Optional[str] = None):
        self.repo_obj = None
        try:
            self.installation_id = context.get("installation_id", None)
        except Exception:
            self.installation_id = None
+        self.max_comment_chars = 65000
        self.base_url = get_settings().get("GITHUB.BASE_URL", "https://api.github.com").rstrip("/")
        self.base_url_html = self.base_url.split("api/")[0].rstrip("/") if "api/" in self.base_url else "https://github.com"
+        self.base_domain = self.base_url.replace("https://", "").replace("http://", "")
+        self.base_domain_html = self.base_url_html.replace("https://", "").replace("http://", "")
        self.github_client = self._get_github_client()
        self.repo = None
        self.pr_num = None
@ -33,18 +38,21 @@ class GithubProvider(GitProvider):
        self.github_user_id = None
        self.diff_files = None
        self.git_files = None
-        self.incremental = incremental
+        self.incremental = IncrementalPR(False)
        if pr_url and 'pull' in pr_url:
            self.set_pr(pr_url)
            self.pr_commits = list(self.pr.get_commits())
-            if self.incremental.is_incremental:
-                self.unreviewed_files_set = dict()
-                self.get_incremental_commits()
            self.last_commit_id = self.pr_commits[-1]
            self.pr_url = self.get_pr_url() # pr_url for github actions can be as api.github.com, so we need to get the url from the pr object
        else:
            self.pr_commits = None

+    def get_incremental_commits(self, incremental=IncrementalPR(False)):
+        self.incremental = incremental
+        if self.incremental.is_incremental:
+            self.unreviewed_files_set = dict()
+            self._get_incremental_commits()
+
    def is_supported(self, capability: str) -> bool:
        return True

@ -55,7 +63,7 @@ class GithubProvider(GitProvider):
        self.repo, self.pr_num = self._parse_pr_url(pr_url)
        self.pr = self._get_pr()

-    def get_incremental_commits(self):
+    def _get_incremental_commits(self):
        if not self.pr_commits:
            self.pr_commits = list(self.pr.get_commits())

@ -92,9 +100,9 @@ class GithubProvider(GitProvider):
            self.comments = list(self.pr.get_issue_comments())
        prefixes = []
        if full:
-            prefixes.append("## PR Review")
+            prefixes.append(PRReviewHeader.REGULAR.value)
        if incremental:
-            prefixes.append("## Incremental PR Review")
+            prefixes.append(PRReviewHeader.INCREMENTAL.value)
        for index in range(len(self.comments) - 1, -1, -1):
            if any(self.comments[index].body.startswith(prefix) for prefix in prefixes):
                return self.comments[index]
@ -106,18 +114,21 @@ class GithubProvider(GitProvider):
            git_files = context.get("git_files", None)
            if git_files:
                return git_files
-            self.git_files = self.pr.get_files()
+            self.git_files = list(self.pr.get_files()) # 'list' to handle pagination
            context["git_files"] = self.git_files
            return self.git_files
        except Exception:
            if not self.git_files:
-                self.git_files = self.pr.get_files()
+                self.git_files = list(self.pr.get_files())
            return self.git_files

    def get_num_of_files(self):
-        if self.git_files:
+        if hasattr(self.git_files, "totalCount"):
            return self.git_files.totalCount
        else:
+            try:
+                return len(self.git_files)
+            except Exception as e:
                return -1

    @retry(exceptions=RateLimitExceeded,
@ -142,20 +153,49 @@ class GithubProvider(GitProvider):
            if self.diff_files:
                return self.diff_files

-            files = self.get_files()
-            diff_files = []
+            # filter files using [ignore] patterns
+            files_original = self.get_files()
+            files = filter_ignored(files_original)
+            if files_original != files:
+                try:
+                    names_original = [file.filename for file in files_original]
+                    names_new = [file.filename for file in files]
+                    get_logger().info(f"Filtered out [ignore] files for pull request:", extra=
+                    {"files": names_original,
+                     "filtered_files": names_new})
+                except Exception:
+                    pass

+            diff_files = []
+            invalid_files_names = []
+            counter_valid = 0
            for file in files:
                if not is_valid_file(file.filename):
+                    invalid_files_names.append(file.filename)
                    continue

-                new_file_content_str = self._get_pr_file_content(file, self.pr.head.sha)  # communication with GitHub
                patch = file.patch

+                # allow only a limited number of files to be fully loaded. We can manage the rest with diffs only
+                counter_valid += 1
+                avoid_load = False
+                if counter_valid >= MAX_FILES_ALLOWED_FULL and patch and not self.incremental.is_incremental:
+                    avoid_load = True
+                    if counter_valid == MAX_FILES_ALLOWED_FULL:
+                        get_logger().info(f"Too many files in PR, will avoid loading full content for rest of files")
+
+                if avoid_load:
+                    new_file_content_str = ""
+                else:
+                    new_file_content_str = self._get_pr_file_content(file, self.pr.head.sha)  # communication with GitHub
+
                if self.incremental.is_incremental and self.unreviewed_files_set:
                    original_file_content_str = self._get_pr_file_content(file, self.incremental.last_seen_commit_sha)
                    patch = load_large_diff(file.filename, new_file_content_str, original_file_content_str)
                    self.unreviewed_files_set[file.filename] = patch
+                else:
+                    if avoid_load:
+                        original_file_content_str = ""
                    else:
                        original_file_content_str = self._get_pr_file_content(file, self.pr.base.sha)
                    if not patch:
@ -182,6 +222,8 @@ class GithubProvider(GitProvider):
                                                               num_plus_lines=num_plus_lines,
                                                               num_minus_lines=num_minus_lines,)
                diff_files.append(file_patch_canonical_structure)
+            if invalid_files_names:
+                get_logger().info(f"Filtered out files with invalid extensions: {invalid_files_names}")

            self.diff_files = diff_files
            try:
@ -209,30 +251,13 @@ class GithubProvider(GitProvider):
                                   update_header: bool = True,
                                   name='review',
                                   final_update_message=True):
-        prev_comments = list(self.pr.get_issue_comments())
-        for comment in prev_comments:
-            body = comment.body
-            if body.startswith(initial_header):
-                latest_commit_url = self.get_latest_commit_url()
-                comment_url = self.get_comment_url(comment)
-                if update_header:
-                    updated_header = f"{initial_header}\n\n### ({name.capitalize()} updated until commit {latest_commit_url})\n"
-                    pr_comment_updated = pr_comment.replace(initial_header, updated_header)
-                else:
-                    pr_comment_updated = pr_comment
-                get_logger().info(f"Persistent mode- updating comment {comment_url} to latest review message")
-                response = comment.edit(pr_comment_updated)
-                if final_update_message:
-                    self.publish_comment(
-                        f"**[Persistent {name}]({comment_url})** updated to latest commit {latest_commit_url}")
-                return
-        self.publish_comment(pr_comment)
+        self.publish_persistent_comment_full(pr_comment, initial_header, update_header, name, final_update_message)

    def publish_comment(self, pr_comment: str, is_temporary: bool = False):
        if is_temporary and not get_settings().config.publish_output_progress:
            get_logger().debug(f"Skipping publish_comment for temporary comment: {pr_comment}")
            return
-
+        pr_comment = self.limit_output_characters(pr_comment, self.max_comment_chars)
        response = self.pr.create_issue_comment(pr_comment)
        if hasattr(response, "user") and hasattr(response.user, "login"):
            self.github_user_id = response.user.login
@ -242,12 +267,14 @@ class GithubProvider(GitProvider):
        self.pr.comments_list.append(response)
        return response

-    def publish_inline_comment(self, body: str, relevant_file: str, relevant_line_in_file: str):
+    def publish_inline_comment(self, body: str, relevant_file: str, relevant_line_in_file: str, original_suggestion=None):
+        body = self.limit_output_characters(body, self.max_comment_chars)
        self.publish_inline_comments([self.create_inline_comment(body, relevant_file, relevant_line_in_file)])


    def create_inline_comment(self, body: str, relevant_file: str, relevant_line_in_file: str,
                              absolute_position: int = None):
+        body = self.limit_output_characters(body, self.max_comment_chars)
        position, absolute_position = find_line_number_of_relevant_line_in_file(self.diff_files,
                                                                                relevant_file.strip('`'),
                                                                                relevant_line_in_file,
@ -420,11 +447,24 @@ class GithubProvider(GitProvider):
            return False

    def edit_comment(self, comment, body: str):
+        body = self.limit_output_characters(body, self.max_comment_chars)
        comment.edit(body=body)

+    def edit_comment_from_comment_id(self, comment_id: int, body: str):
+        try:
+            # self.pr.get_issue_comment(comment_id).edit(body)
+            body = self.limit_output_characters(body, self.max_comment_chars)
+            headers, data_patch = self.pr._requester.requestJsonAndCheck(
+                "PATCH", f"{self.base_url}/repos/{self.repo}/issues/comments/{comment_id}",
+                input={"body": body}
+            )
+        except Exception as e:
+            get_logger().exception(f"Failed to edit comment, error: {e}")
+
    def reply_to_comment_from_comment_id(self, comment_id: int, body: str):
        try:
            # self.pr.get_issue_comment(comment_id).edit(body)
+            body = self.limit_output_characters(body, self.max_comment_chars)
            headers, data_patch = self.pr._requester.requestJsonAndCheck(
                "POST", f"{self.base_url}/repos/{self.repo}/pulls/{self.pr_num}/comments/{comment_id}/replies",
                input={"body": body}
@ -432,6 +472,51 @@ class GithubProvider(GitProvider):
        except Exception as e:
            get_logger().exception(f"Failed to reply comment, error: {e}")

+    def get_comment_body_from_comment_id(self, comment_id: int):
+        try:
+            # self.pr.get_issue_comment(comment_id).edit(body)
+            headers, data_patch = self.pr._requester.requestJsonAndCheck(
+                "GET", f"{self.base_url}/repos/{self.repo}/issues/comments/{comment_id}"
+            )
+            return data_patch.get("body","")
+        except Exception as e:
+            get_logger().exception(f"Failed to edit comment, error: {e}")
+            return None
+
+    def publish_file_comments(self, file_comments: list) -> bool:
+        try:
+            headers, existing_comments = self.pr._requester.requestJsonAndCheck(
+                "GET", f"{self.pr.url}/comments"
+            )
+            for comment in file_comments:
+                comment['commit_id'] = self.last_commit_id.sha
+                comment['body'] = self.limit_output_characters(comment['body'], self.max_comment_chars)
+
+                found = False
+                for existing_comment in existing_comments:
+                    comment['commit_id'] = self.last_commit_id.sha
+                    our_app_name = get_settings().get("GITHUB.APP_NAME", "")
+                    same_comment_creator = False
+                    if self.deployment_type == 'app':
+                        same_comment_creator = our_app_name.lower() in existing_comment['user']['login'].lower()
+                    elif self.deployment_type == 'user':
+                        same_comment_creator = self.github_user_id == existing_comment['user']['login']
+                    if existing_comment['subject_type'] == 'file' and comment['path'] == existing_comment['path'] and same_comment_creator:
+                        headers, data_patch = self.pr._requester.requestJsonAndCheck(
+                            "PATCH", f"{self.base_url}/repos/{self.repo}/pulls/comments/{existing_comment['id']}", input={"body":comment['body']}
+                        )
+                        found = True
+                        break
+                if not found:
+                    headers, data_post = self.pr._requester.requestJsonAndCheck(
+                        "POST", f"{self.pr.url}/comments", input=comment
+                    )
+            return True
+        except Exception as e:
+            if get_settings().config.verbosity_level >= 2:
+                get_logger().error(f"Failed to publish diffview file summary, error: {e}")
+            return False
+
    def remove_initial_comment(self):
        try:
            for comment in getattr(self.pr, 'comments_list', []):
@ -456,6 +541,11 @@ class GithubProvider(GitProvider):
    def get_pr_branch(self):
        return self.pr.head.ref

+    def get_pr_owner_id(self) -> str | None:
+        if not self.repo:
+            return None
+        return self.repo.split('/')[0]
+
    def get_pr_description_full(self):
        return self.pr.body

@ -490,6 +580,9 @@ class GithubProvider(GitProvider):
        except Exception:
            return ""

+    def get_workspace_name(self):
+        return self.repo.split('/')[0]
+
    def add_eyes_reaction(self, issue_comment_id: int, disable_eyes: bool = False) -> Optional[int]:
        if disable_eyes:
            return None
@ -500,7 +593,7 @@ class GithubProvider(GitProvider):
            )
            return data_patch.get("id", None)
        except Exception as e:
-            get_logger().exception(f"Failed to add eyes reaction, error: {e}")
+            get_logger().warning(f"Failed to add eyes reaction, error: {e}")
            return None

    def remove_reaction(self, issue_comment_id: int, reaction_id: str) -> bool:
@ -515,15 +608,11 @@ class GithubProvider(GitProvider):
            get_logger().exception(f"Failed to remove eyes reaction, error: {e}")
            return False

-    @staticmethod
-    def _parse_pr_url(pr_url: str) -> Tuple[str, int]:
+    def _parse_pr_url(self, pr_url: str) -> Tuple[str, int]:
        parsed_url = urlparse(pr_url)

-        if 'github.com' not in parsed_url.netloc:
-            raise ValueError("The provided URL is not a valid GitHub URL")
-
        path_parts = parsed_url.path.strip('/').split('/')
-        if 'api.github.com' in parsed_url.netloc:
+        if self.base_domain in parsed_url.netloc:
            if len(path_parts) < 5 or path_parts[3] != 'pulls':
                raise ValueError("The provided URL does not appear to be a GitHub PR URL")
            repo_name = '/'.join(path_parts[1:3])
@ -544,15 +633,10 @@ class GithubProvider(GitProvider):

        return repo_name, pr_number

-    @staticmethod
-    def _parse_issue_url(issue_url: str) -> Tuple[str, int]:
+    def _parse_issue_url(self, issue_url: str) -> Tuple[str, int]:
        parsed_url = urlparse(issue_url)
-
-        if 'github.com' not in parsed_url.netloc:
-            raise ValueError("The provided URL is not a valid GitHub URL")
-
        path_parts = parsed_url.path.strip('/').split('/')
-        if 'api.github.com' in parsed_url.netloc:
+        if self.base_domain in parsed_url.netloc:
            if len(path_parts) < 5 or path_parts[3] != 'issues':
                raise ValueError("The provided URL does not appear to be a GitHub ISSUE URL")
            repo_name = '/'.join(path_parts[1:3])
@ -653,7 +737,7 @@ class GithubProvider(GitProvider):
                "PUT", f"{self.pr.issue_url}/labels", input=post_parameters
            )
        except Exception as e:
-            get_logger().exception(f"Failed to publish labels, error: {e}")
+            get_logger().warning(f"Failed to publish labels, error: {e}")

    def get_pr_labels(self, update=False):
        try:
@ -671,7 +755,7 @@ class GithubProvider(GitProvider):

    def get_repo_labels(self):
        labels = self.repo_obj.get_labels()
-        return [label for label in labels]
+        return [label for label in itertools.islice(labels, 50)]

    def get_commit_messages(self):
        """
@ -726,6 +810,32 @@ class GithubProvider(GitProvider):
            link = f"{self.base_url_html}/{self.repo}/pull/{self.pr_num}/files#diff-{sha_file}R{relevant_line_start}"
        return link

+    def get_lines_link_original_file(self, filepath: str, component_range: Range) -> str:
+        """
+        Returns the link to the original file on GitHub that corresponds to the given filepath and component range.
+
+        Args:
+            filepath (str): The path of the file.
+            component_range (Range): The range of lines that represent the component.
+
+        Returns:
+            str: The link to the original file on GitHub.
+
+        Example:
+            >>> filepath = "path/to/file.py"
+            >>> component_range = Range(line_start=10, line_end=20)
+            >>> link = get_lines_link_original_file(filepath, component_range)
+            >>> print(link)
+            "https://github.com/{repo}/blob/{commit_sha}/{filepath}/#L11-L21"
+        """
+        line_start = component_range.line_start + 1
+        line_end = component_range.line_end + 1
+        # link = (f"https://github.com/{self.repo}/blob/{self.last_commit_id.sha}/{filepath}/"
+        #         f"#L{line_start}-L{line_end}")
+        link = (f"{self.base_url_html}/{self.repo}/blob/{self.last_commit_id.sha}/{filepath}/"
+                f"#L{line_start}-L{line_end}")
+
+        return link

    def get_pr_id(self):
        try:
--- a/pr_agent/git_providers/gitlab_provider.py
+++ b/pr_agent/git_providers/gitlab_provider.py
@ -4,12 +4,14 @@ from typing import Optional, Tuple
 from urllib.parse import urlparse

 import gitlab
+import requests
 from gitlab import GitlabGetError

+from ..algo.file_filter import filter_ignored
 from ..algo.language_handler import is_valid_file
 from ..algo.utils import load_large_diff, clip_tokens, find_line_number_of_relevant_line_in_file
 from ..config_loader import get_settings
-from .git_provider import GitProvider
+from .git_provider import GitProvider, MAX_FILES_ALLOWED_FULL
 from pr_agent.algo.types import EDIT_TYPE, FilePatchInfo
 from ..log import get_logger

@ -24,6 +26,7 @@ class GitLabProvider(GitProvider):
        gitlab_url = get_settings().get("GITLAB.URL", None)
        if not gitlab_url:
            raise ValueError("GitLab URL is not set in the config file")
+        self.gitlab_url = gitlab_url
        gitlab_access_token = get_settings().get("GITLAB.PERSONAL_ACCESS_TOKEN", None)
        if not gitlab_access_token:
            raise ValueError("GitLab personal access token is not set in the config file")
@ -31,6 +34,7 @@ class GitLabProvider(GitProvider):
            url=gitlab_url,
            oauth_token=gitlab_access_token
        )
+        self.max_comment_chars = 65000
        self.id_project = None
        self.id_mr = None
        self.mr = None
@ -44,7 +48,8 @@ class GitLabProvider(GitProvider):
        self.incremental = incremental

    def is_supported(self, capability: str) -> bool:
-        if capability in ['get_issue_comments', 'create_inline_comment', 'publish_inline_comments']: # gfm_markdown is supported in gitlab !
+        if capability in ['get_issue_comments', 'create_inline_comment', 'publish_inline_comments',
+            'publish_file_comments']: # gfm_markdown is supported in gitlab !
            return False
        return True

@ -84,12 +89,38 @@ class GitLabProvider(GitProvider):
        if self.diff_files:
            return self.diff_files

-        diffs = self.mr.changes()['changes']
+        # filter files using [ignore] patterns
+        diffs_original = self.mr.changes()['changes']
+        diffs = filter_ignored(diffs_original, 'gitlab')
+        if diffs != diffs_original:
+            try:
+                names_original = [diff['new_path'] for diff in diffs_original]
+                names_filtered = [diff['new_path'] for diff in diffs]
+                get_logger().info(f"Filtered out [ignore] files for merge request {self.id_mr}", extra={
+                    'original_files': names_original,
+                    'filtered_files': names_filtered
+                })
+            except Exception as e:
+                pass
+
        diff_files = []
+        invalid_files_names = []
+        counter_valid = 0
        for diff in diffs:
-            if is_valid_file(diff['new_path']):
+            if not is_valid_file(diff['new_path']):
+                invalid_files_names.append(diff['new_path'])
+                continue
+
+            # allow only a limited number of files to be fully loaded. We can manage the rest with diffs only
+            counter_valid += 1
+            if counter_valid < MAX_FILES_ALLOWED_FULL or not diff['diff']:
                original_file_content_str = self.get_pr_file_content(diff['old_path'], self.mr.diff_refs['base_sha'])
                new_file_content_str = self.get_pr_file_content(diff['new_path'], self.mr.diff_refs['head_sha'])
+            else:
+                if counter_valid == MAX_FILES_ALLOWED_FULL:
+                    get_logger().info(f"Too many files in PR, will avoid loading full content for rest of files")
+                original_file_content_str = ''
+                new_file_content_str = ''

            try:
                if isinstance(original_file_content_str, bytes):
@ -126,11 +157,13 @@ class GitLabProvider(GitProvider):
                              old_filename=None if diff['old_path'] == diff['new_path'] else diff['old_path'],
                              num_plus_lines=num_plus_lines,
                              num_minus_lines=num_minus_lines, ))
+        if invalid_files_names:
+            get_logger().info(f"Filtered out files with invalid extensions: {invalid_files_names}")

        self.diff_files = diff_files
        return diff_files

-    def get_files(self):
+    def get_files(self) -> list:
        if not self.git_files:
            self.git_files = [change['new_path'] for change in self.mr.changes()['changes']]
        return self.git_files
@ -154,45 +187,36 @@ class GitLabProvider(GitProvider):
                                   update_header: bool = True,
                                   name='review',
                                   final_update_message=True):
-        try:
-            for comment in self.mr.notes.list(get_all=True)[::-1]:
-                if comment.body.startswith(initial_header):
-                    latest_commit_url = self.get_latest_commit_url()
-                    comment_url = self.get_comment_url(comment)
-                    if update_header:
-                        updated_header = f"{initial_header}\n\n### ({name.capitalize()} updated until commit {latest_commit_url})\n"
-                        pr_comment_updated = pr_comment.replace(initial_header, updated_header)
-                    else:
-                        pr_comment_updated = pr_comment
-                    get_logger().info(f"Persistent mode - updating comment {comment_url} to latest {name} message")
-                    response = self.mr.notes.update(comment.id, {'body': pr_comment_updated})
-                    if final_update_message:
-                        self.publish_comment(
-                            f"**[Persistent {name}]({comment_url})** updated to latest commit {latest_commit_url}")
-                    return
-        except Exception as e:
-            get_logger().exception(f"Failed to update persistent review, error: {e}")
-            pass
-        self.publish_comment(pr_comment)
+        self.publish_persistent_comment_full(pr_comment, initial_header, update_header, name, final_update_message)

    def publish_comment(self, mr_comment: str, is_temporary: bool = False):
+        mr_comment = self.limit_output_characters(mr_comment, self.max_comment_chars)
        comment = self.mr.notes.create({'body': mr_comment})
        if is_temporary:
            self.temp_comments.append(comment)
        return comment

    def edit_comment(self, comment, body: str):
+        body = self.limit_output_characters(body, self.max_comment_chars)
        self.mr.notes.update(comment.id,{'body': body} )

+    def edit_comment_from_comment_id(self, comment_id: int, body: str):
+        body = self.limit_output_characters(body, self.max_comment_chars)
+        comment = self.mr.notes.get(comment_id)
+        comment.body = body
+        comment.save()
+
    def reply_to_comment_from_comment_id(self, comment_id: int, body: str):
+        body = self.limit_output_characters(body, self.max_comment_chars)
        discussion = self.mr.discussions.get(comment_id)
        discussion.notes.create({'body': body})

-    def publish_inline_comment(self, body: str, relevant_file: str, relevant_line_in_file: str):
+    def publish_inline_comment(self, body: str, relevant_file: str, relevant_line_in_file: str, original_suggestion=None):
+        body = self.limit_output_characters(body, self.max_comment_chars)
        edit_type, found, source_line_no, target_file, target_line_no = self.search_line(relevant_file,
                                                                                         relevant_line_in_file)
        self.send_inline_comment(body, edit_type, found, relevant_file, relevant_line_in_file, source_line_no,
-                                 target_file, target_line_no)
+                                 target_file, target_line_no, original_suggestion)

    def create_inline_comment(self, body: str, relevant_file: str, relevant_line_in_file: str, absolute_position: int = None):
        raise NotImplementedError("Gitlab provider does not support creating inline comments yet")
@ -200,8 +224,14 @@ class GitLabProvider(GitProvider):
    def create_inline_comments(self, comments: list[dict]):
        raise NotImplementedError("Gitlab provider does not support publishing inline comments yet")

-    def send_inline_comment(self,body: str,edit_type: str,found: bool,relevant_file: str,relevant_line_in_file: int,
-                            source_line_no: int, target_file: str,target_line_no: int) -> None:
+    def get_comment_body_from_comment_id(self, comment_id: int):
+        comment = self.mr.notes.get(comment_id).body
+        return comment
+
+    def send_inline_comment(self, body: str, edit_type: str, found: bool, relevant_file: str,
+                            relevant_line_in_file: str,
+                            source_line_no: int, target_file: str, target_line_no: int,
+                            original_suggestion=None) -> None:
        if not found:
            get_logger().info(f"Could not find position for {relevant_file} {relevant_line_in_file}")
        else:
@ -221,14 +251,63 @@ class GitLabProvider(GitProvider):
            else:
                pos_obj['new_line'] = target_line_no - 1
                pos_obj['old_line'] = source_line_no - 1
-            get_logger().debug(f"Creating comment in {self.id_mr} with body {body} and position {pos_obj}")
+            get_logger().debug(f"Creating comment in MR {self.id_mr} with body {body} and position {pos_obj}")
            try:
                self.mr.discussions.create({'body': body, 'position': pos_obj})
            except Exception as e:
-                get_logger().debug(
-                    f"Failed to create comment in {self.id_mr} with position {pos_obj} (probably not a '+' line)")
+                try:
+                    # fallback - create a general note on the file in the MR
+                    if 'suggestion_orig_location' in original_suggestion:
+                        line_start = original_suggestion['suggestion_orig_location']['start_line']
+                        line_end = original_suggestion['suggestion_orig_location']['end_line']
+                        old_code_snippet = original_suggestion['prev_code_snippet']
+                        new_code_snippet = original_suggestion['new_code_snippet']
+                        content = original_suggestion['suggestion_summary']
+                        label = original_suggestion['category']
+                        if 'score' in original_suggestion:
+                            score = original_suggestion['score']
+                        else:
+                            score = 7
+                    else:
+                        line_start = original_suggestion['relevant_lines_start']
+                        line_end = original_suggestion['relevant_lines_end']
+                        old_code_snippet = original_suggestion['existing_code']
+                        new_code_snippet = original_suggestion['improved_code']
+                        content = original_suggestion['suggestion_content']
+                        label = original_suggestion['label']
+                        if 'score' in original_suggestion:
+                            score = original_suggestion['score']
+                        else:
+                            score = 7

-    def get_relevant_diff(self, relevant_file: str, relevant_line_in_file: int) -> Optional[dict]:
+                    if hasattr(self, 'main_language'):
+                        language = self.main_language
+                    else:
+                        language = ''
+                    link = self.get_line_link(relevant_file, line_start, line_end)
+                    body_fallback =f"**Suggestion:** {content} [{label}, importance: {score}]\n___\n"
+                    body_fallback +=f"\n\nReplace  lines ([{line_start}-{line_end}]({link}))\n\n```{language}\n{old_code_snippet}\n````\n\n"
+                    body_fallback +=f"with\n\n```{language}\n{new_code_snippet}\n````"
+                    body_fallback += f"\n\n___\n\n`(Cannot implement this suggestion directly, as gitlab API does not enable committing to a non -+ line in a PR)`"
+
+                    # Create a general note on the file in the MR
+                    self.mr.notes.create({
+                        'body': body_fallback,
+                        'position': {
+                            'base_sha': diff.base_commit_sha,
+                            'start_sha': diff.start_commit_sha,
+                            'head_sha': diff.head_commit_sha,
+                            'position_type': 'text',
+                            'file_path': f'{target_file.filename}',
+                        }
+                    })
+
+                    # get_logger().debug(
+                    #     f"Failed to create comment in MR {self.id_mr} with position {pos_obj} (probably not a '+' line)")
+                except Exception as e:
+                    get_logger().exception(f"Failed to create comment in MR {self.id_mr}")
+
+    def get_relevant_diff(self, relevant_file: str, relevant_line_in_file: str) -> Optional[dict]:
        changes = self.mr.changes()  # Retrieve the changes for the merge request once
        if not changes:
            get_logger().error('No changes found for the merge request.')
@ -248,6 +327,10 @@ class GitLabProvider(GitProvider):
    def publish_code_suggestions(self, code_suggestions: list) -> bool:
        for suggestion in code_suggestions:
            try:
+                if suggestion and 'original_suggestion' in suggestion:
+                    original_suggestion = suggestion['original_suggestion']
+                else:
+                    original_suggestion = suggestion
                body = suggestion['body']
                relevant_file = suggestion['relevant_file']
                relevant_lines_start = suggestion['relevant_lines_start']
@ -268,19 +351,22 @@ class GitLabProvider(GitProvider):
                # edit_type, found, source_line_no, target_file, target_line_no = self.find_in_file(target_file,
                #                                                                            relevant_line_in_file)
                # for code suggestions, we want to edit the new code
-                source_line_no = None
+                source_line_no = -1
                target_line_no = relevant_lines_start + 1
                found = True
                edit_type = 'addition'

                self.send_inline_comment(body, edit_type, found, relevant_file, relevant_line_in_file, source_line_no,
-                                         target_file, target_line_no)
+                                         target_file, target_line_no, original_suggestion)
            except Exception as e:
                get_logger().exception(f"Could not publish code suggestion:\nsuggestion: {suggestion}\nerror: {e}")

        # note that we publish suggestions one-by-one. so, if one fails, the rest will still be published
        return True

+    def publish_file_comments(self, file_comments: list) -> bool:
+        pass
+
    def search_line(self, relevant_file, relevant_line_in_file):
        target_file = None

@ -358,11 +444,20 @@ class GitLabProvider(GitProvider):
    def get_pr_branch(self):
        return self.mr.source_branch

+    def get_pr_owner_id(self) -> str | None:
+        if not self.gitlab_url or 'gitlab.com' in self.gitlab_url:
+            if not self.id_project:
+                return None
+            return self.id_project.split('/')[0]
+        # extract host name
+        host = urlparse(self.gitlab_url).hostname
+        return host
+
    def get_pr_description_full(self):
        return self.mr.description

    def get_issue_comments(self):
-        raise NotImplementedError("GitLab provider does not support issue comments yet")
+        return self.mr.notes.list(get_all=True)[::-1]

    def get_repo_settings(self):
        try:
@ -371,6 +466,9 @@ class GitLabProvider(GitProvider):
        except Exception:
            return ""

+    def get_workspace_name(self):
+        return self.id_project.split('/')[0]
+
    def add_eyes_reaction(self, issue_comment_id: int, disable_eyes: bool = False) -> Optional[int]:
        return True

@ -414,7 +512,7 @@ class GitLabProvider(GitProvider):
            self.mr.labels = list(set(pr_types))
            self.mr.save()
        except Exception as e:
-            get_logger().exception(f"Failed to publish labels, error: {e}")
+            get_logger().warning(f"Failed to publish labels, error: {e}")

    def publish_inline_comments(self, comments: list[dict]):
        pass
--- a/pr_agent/git_providers/local_git_provider.py
+++ b/pr_agent/git_providers/local_git_provider.py
@ -119,7 +119,7 @@ class LocalGitProvider(GitProvider):
            # Write the string to the file
            file.write(pr_comment)

-    def publish_inline_comment(self, body: str, relevant_file: str, relevant_line_in_file: str):
+    def publish_inline_comment(self, body: str, relevant_file: str, relevant_line_in_file: str, original_suggestion=None):
        raise NotImplementedError('Publishing inline comments is not implemented for the local git provider')

    def publish_inline_comments(self, comments: list[dict]):
--- a/pr_agent/git_providers/utils.py
+++ b/pr_agent/git_providers/utils.py
@ -5,12 +5,13 @@ import tempfile
 from dynaconf import Dynaconf

 from pr_agent.config_loader import get_settings
-from pr_agent.git_providers import get_git_provider
+from pr_agent.git_providers import get_git_provider, get_git_provider_with_context
 from pr_agent.log import get_logger
 from starlette_context import context


 def apply_repo_settings(pr_url):
+    git_provider = get_git_provider_with_context(pr_url)
    if get_settings().config.use_repo_settings_file:
        repo_settings_file = None
        try:
@ -20,7 +21,6 @@ def apply_repo_settings(pr_url):
                repo_settings = None
                pass
            if repo_settings is None:  # None is different from "", which is a valid value
-                git_provider = get_git_provider()(pr_url)
                repo_settings = git_provider.get_repo_settings()
                try:
                    context["repo_settings"] = repo_settings
@ -47,3 +47,17 @@ def apply_repo_settings(pr_url):
                    os.remove(repo_settings_file)
                except Exception as e:
                    get_logger().error(f"Failed to remove temporary settings file {repo_settings_file}", e)
+
+    # enable switching models with a short definition
+    if get_settings().config.model.lower()=='claude-3-5-sonnet':
+        set_claude_model()
+
+
+def set_claude_model():
+    """
+    set the claude-sonnet-3.5 model easily (even by users), just by stating: --config.model='claude-3-5-sonnet'
+    """
+    model_claude = "bedrock/anthropic.claude-3-5-sonnet-20240620-v1:0"
+    get_settings().set('config.model', model_claude)
+    get_settings().set('config.model_turbo', model_claude)
+    get_settings().set('config.fallback_models', [model_claude])
--- a/pr_agent/secret_providers/google_cloud_storage_secret_provider.py
+++ b/pr_agent/secret_providers/google_cloud_storage_secret_provider.py
@ -22,7 +22,7 @@ class GoogleCloudStorageSecretProvider(SecretProvider):
            blob = self.bucket.blob(secret_name)
            return blob.download_as_string()
        except Exception as e:
-            get_logger().error(f"Failed to get secret {secret_name} from Google Cloud Storage: {e}")
+            get_logger().warning(f"Failed to get secret {secret_name} from Google Cloud Storage: {e}")
            return ""

    def store_secret(self, secret_name: str, secret_value: str):
--- a/pr_agent/servers/azuredevops_server_webhook.py
+++ b/pr_agent/servers/azuredevops_server_webhook.py
@ -26,8 +26,9 @@ from pr_agent.git_providers.utils import apply_repo_settings
 from pr_agent.log import get_logger
 from fastapi import Request, Depends
 from fastapi.security import HTTPBasic, HTTPBasicCredentials
-from pr_agent.log import get_logger
+from pr_agent.log import LoggingFormat, get_logger, setup_logger

+setup_logger(fmt=LoggingFormat.JSON, level="DEBUG")
 security = HTTPBasic()
 router = APIRouter()
 available_commands_rgx = re.compile(r"^\/(" + "|".join(command2class.keys()) + r")\s*")
@ -40,8 +41,15 @@ def handle_request(
 ):
    log_context["action"] = body
    log_context["api_url"] = url
+
+    async def inner():
+        try:
            with get_logger().contextualize(**log_context):
-        background_tasks.add_task(PRAgent().handle_request, url, body)
+                await PRAgent().handle_request(url, body)
+        except Exception as e:
+            get_logger().error(f"Failed to handle webhook: {e}")
+
+    background_tasks.add_task(inner)


 # currently only basic auth is supported with azure webhooks
@ -123,7 +131,7 @@ async def handle_webhook(background_tasks: BackgroundTasks, request: Request):
                content=json.dumps({"message": "Internal server error"}),
            )
    return JSONResponse(
-        status_code=status.HTTP_202_ACCEPTED, content=jsonable_encoder({"message": "webhook triggerd successfully"})
+        status_code=status.HTTP_202_ACCEPTED, content=jsonable_encoder({"message": "webhook triggered successfully"})
    )

@router.get("/")
--- a/pr_agent/servers/bitbucket_app.py
+++ b/pr_agent/servers/bitbucket_app.py
@ -93,7 +93,8 @@ async def _perform_commands_bitbucket(commands_conf: str, agent: PRAgent, api_ur

@router.post("/webhook")
 async def handle_github_webhooks(background_tasks: BackgroundTasks, request: Request):
-    log_context = {"server_type": "bitbucket_app"}
+    app_name = get_settings().get("CONFIG.APP_NAME", "Unknown")
+    log_context = {"server_type": "bitbucket_app", "app_name": app_name}
    get_logger().debug(request.headers)
    jwt_header = request.headers.get("authorization", None)
    if jwt_header:
@ -107,13 +108,18 @@ async def handle_github_webhooks(background_tasks: BackgroundTasks, request: Req
                    return "OK"
            except KeyError:
                get_logger().error("Failed to get actor type, check previous logs, this shouldn't happen.")
+
+            # Get the username of the sender
            try:
-                owner = data["data"]["repository"]["owner"]["username"]
-            except Exception as e:
-                get_logger().error(f"Failed to get owner, will continue: {e}")
-                owner = "unknown"
+                username = data["data"]["actor"]["username"]
+            except KeyError:
+                try:
+                    username = data["data"]["actor"]["display_name"]
+                except KeyError:
+                    username = data["data"]["actor"]["nickname"]
+            log_context["sender"] = username
+
            sender_id = data["data"]["actor"]["account_id"]
-            log_context["sender"] = owner
            log_context["sender_id"] = sender_id
            jwt_parts = input_jwt.split(".")
            claim_part = jwt_parts[1]
--- a/pr_agent/servers/bitbucket_server_webhook.py
+++ b/pr_agent/servers/bitbucket_server_webhook.py
@ -1,5 +1,7 @@
+import ast
 import json
 import os
+from typing import List

 import uvicorn
 from fastapi import APIRouter, FastAPI
@ -10,12 +12,16 @@ from starlette.middleware import Middleware
 from starlette.requests import Request
 from starlette.responses import JSONResponse
 from starlette_context.middleware import RawContextMiddleware
-
 from pr_agent.agent.pr_agent import PRAgent
+from pr_agent.algo.utils import update_settings_from_args
 from pr_agent.config_loader import get_settings
-from pr_agent.log import get_logger
+from pr_agent.git_providers.utils import apply_repo_settings
+from pr_agent.log import LoggingFormat, get_logger, setup_logger
 from pr_agent.servers.utils import verify_signature
+from fastapi.responses import RedirectResponse

+
+setup_logger(fmt=LoggingFormat.JSON, level="DEBUG")
 router = APIRouter()


@ -24,11 +30,21 @@ def handle_request(
 ):
    log_context["action"] = body
    log_context["api_url"] = url
-    with get_logger().contextualize(**log_context):
-        background_tasks.add_task(PRAgent().handle_request, url, body)

+    async def inner():
+        try:
+            with get_logger().contextualize(**log_context):
+                await PRAgent().handle_request(url, body)
+        except Exception as e:
+            get_logger().error(f"Failed to handle webhook: {e}")
+
+    background_tasks.add_task(inner)

@router.post("/")
+async def redirect_to_webhook():
+    return RedirectResponse(url="/webhook")
+
+@router.post("/webhook")
 async def handle_webhook(background_tasks: BackgroundTasks, request: Request):
    log_context = {"server_type": "bitbucket_server"}
    data = await request.json()
@ -37,6 +53,10 @@ async def handle_webhook(background_tasks: BackgroundTasks, request: Request):
    webhook_secret = get_settings().get("BITBUCKET_SERVER.WEBHOOK_SECRET", None)
    if webhook_secret:
        body_bytes = await request.body()
+        if body_bytes.decode('utf-8') == '{"test": true}':
+            return JSONResponse(
+                status_code=status.HTTP_200_OK, content=jsonable_encoder({"message": "connection test successful"})
+            )
        signature_header = request.headers.get("x-hub-signature", None)
        verify_signature(body_bytes, webhook_secret, signature_header)

@ -49,22 +69,81 @@ async def handle_webhook(background_tasks: BackgroundTasks, request: Request):
    log_context["api_url"] = pr_url
    log_context["event"] = "pull_request"

+    commands_to_run = []
+
    if data["eventKey"] == "pr:opened":
-        body = "review"
+        commands_to_run.extend(_get_commands_list_from_settings('BITBUCKET_SERVER.PR_COMMANDS'))
    elif data["eventKey"] == "pr:comment:added":
-        body = data["comment"]["text"]
+        commands_to_run.append(data["comment"]["text"])
    else:
        return JSONResponse(
            status_code=status.HTTP_400_BAD_REQUEST,
            content=json.dumps({"message": "Unsupported event"}),
        )

-    handle_request(background_tasks, pr_url, body, log_context)
+    async def inner():
+        try:
+            await _run_commands_sequentially(commands_to_run, pr_url, log_context)
+        except Exception as e:
+            get_logger().error(f"Failed to handle webhook: {e}")
+
+    background_tasks.add_task(inner)
+
    return JSONResponse(
        status_code=status.HTTP_200_OK, content=jsonable_encoder({"message": "success"})
    )


+async def _run_commands_sequentially(commands: List[str], url: str, log_context: dict):
+    get_logger().info(f"Running commands sequentially: {commands}")
+    if commands is None:
+        return
+
+    for command in commands:
+        try:
+            body = _process_command(command, url)
+
+            log_context["action"] = body
+            log_context["api_url"] = url
+
+            with get_logger().contextualize(**log_context):
+                await PRAgent().handle_request(url, body)
+        except Exception as e:
+            get_logger().error(f"Failed to handle command: {command} , error: {e}")
+
+def _process_command(command: str, url) -> str:
+    # don't think we need this
+    apply_repo_settings(url)
+    # Process the command string
+    split_command = command.split(" ")
+    command = split_command[0]
+    args = split_command[1:]
+    # do I need this? if yes, shouldn't this be done in PRAgent?
+    other_args = update_settings_from_args(args)
+    new_command = ' '.join([command] + other_args)
+    return new_command
+
+
+def _to_list(command_string: str) -> list:
+    try:
+        # Use ast.literal_eval to safely parse the string into a list
+        commands = ast.literal_eval(command_string)
+        # Check if the parsed object is a list of strings
+        if isinstance(commands, list) and all(isinstance(cmd, str) for cmd in commands):
+            return commands
+        else:
+            raise ValueError("Parsed data is not a list of strings.")
+    except (SyntaxError, ValueError, TypeError) as e:
+        raise ValueError(f"Invalid command string: {e}")
+
+
+def _get_commands_list_from_settings(setting_key:str ) -> list:
+    try:
+        return get_settings().get(setting_key, [])
+    except ValueError as e:
+        get_logger().error(f"Failed to get commands list from settings {setting_key}: {e}")
+
+
@router.get("/")
 async def root():
    return {"status": "ok"}
--- a/pr_agent/servers/github_action_runner.py
+++ b/pr_agent/servers/github_action_runner.py
@ -37,7 +37,7 @@ async def run_action():
    OPENAI_KEY = os.environ.get('OPENAI_KEY') or os.environ.get('OPENAI.KEY')
    OPENAI_ORG = os.environ.get('OPENAI_ORG') or os.environ.get('OPENAI.ORG')
    GITHUB_TOKEN = os.environ.get('GITHUB_TOKEN')
-    get_settings().set("CONFIG.PUBLISH_OUTPUT_PROGRESS", False)
+    # get_settings().set("CONFIG.PUBLISH_OUTPUT_PROGRESS", False)

    # Check if required environment variables are set
    if not GITHUB_EVENT_NAME:
@ -99,6 +99,7 @@ async def run_action():

                # invoke by default all three tools
                if auto_describe is None or is_true(auto_describe):
+                    get_settings().pr_description.final_update_message = False  # No final update message when auto_describe is enabled
                    await PRDescription(pr_url).run()
                if auto_review is None or is_true(auto_review):
                    await PRReviewer(pr_url).run()
@ -138,8 +139,11 @@ async def run_action():
                    comment_id = event_payload.get("comment", {}).get("id")
                    provider = get_git_provider()(pr_url=url)
                    if is_pr:
-                        await PRAgent().handle_request(url, body,
-                                    notify=lambda: provider.add_eyes_reaction(comment_id, disable_eyes=disable_eyes))
+                        await PRAgent().handle_request(
+                            url, body, notify=lambda: provider.add_eyes_reaction(
+                                comment_id, disable_eyes=disable_eyes
+                            )
+                        )
                    else:
                        await PRAgent().handle_request(url, body)

--- a/pr_agent/servers/github_app.py
+++ b/pr_agent/servers/github_app.py
@ -7,6 +7,7 @@ from typing import Any, Dict, Tuple

 import uvicorn
 from fastapi import APIRouter, FastAPI, HTTPException, Request, Response
+from starlette.background import BackgroundTasks
 from starlette.middleware import Middleware
 from starlette_context import context
 from starlette_context.middleware import RawContextMiddleware
@ -14,7 +15,7 @@ from starlette_context.middleware import RawContextMiddleware
 from pr_agent.agent.pr_agent import PRAgent
 from pr_agent.algo.utils import update_settings_from_args
 from pr_agent.config_loader import get_settings, global_settings
-from pr_agent.git_providers import get_git_provider
+from pr_agent.git_providers import get_git_provider, get_git_provider_with_context
 from pr_agent.git_providers.git_provider import IncrementalPR
 from pr_agent.git_providers.utils import apply_repo_settings
 from pr_agent.identity_providers import get_identity_provider
@ -34,7 +35,7 @@ router = APIRouter()


@router.post("/api/v1/github_webhooks")
-async def handle_github_webhooks(request: Request, response: Response):
+async def handle_github_webhooks(background_tasks: BackgroundTasks, request: Request, response: Response):
    """
    Receives and processes incoming GitHub webhook requests.
    Verifies the request signature, parses the request body, and passes it to the handle_request function for further
@ -47,9 +48,9 @@ async def handle_github_webhooks(request: Request, response: Response):
    installation_id = body.get("installation", {}).get("id")
    context["installation_id"] = installation_id
    context["settings"] = copy.deepcopy(global_settings)
-
-    response = await handle_request(body, event=request.headers.get("X-GitHub-Event", None))
-    return response or {}
+    context["git_provider"] = {}
+    background_tasks.add_task(handle_request, body, event=request.headers.get("X-GitHub-Event", None))
+    return {}


@router.post("/api/v1/marketplace_webhooks")
@ -110,7 +111,7 @@ async def handle_comments_on_pr(body: Dict[str, Any],
        return {}
    log_context["api_url"] = api_url
    comment_id = body.get("comment", {}).get("id")
-    provider = get_git_provider()(pr_url=api_url)
+    provider = get_git_provider_with_context(pr_url=api_url)
    with get_logger().contextualize(**log_context):
        if get_identity_provider().verify_eligibility("github", sender_id, api_url) is not Eligibility.NOT_ELIGIBLE:
            get_logger().info(f"Processing comment on PR {api_url=}, comment_body={comment_body}")
@ -127,8 +128,16 @@ async def handle_new_pr_opened(body: Dict[str, Any],
                               log_context: Dict[str, Any],
                               agent: PRAgent):
    title = body.get("pull_request", {}).get("title", "")
+    get_settings().config.is_auto_command = True

+
+    pull_request, api_url = _check_pull_request_event(action, body, log_context)
+    if not (pull_request and api_url):
+        get_logger().info(f"Invalid PR event: {action=} {api_url=}")
+        return {}
+    if action in get_settings().github_app.handle_pr_actions:  # ['opened', 'reopened', 'ready_for_review']
        # logic to ignore PRs with specific titles (e.g. "[Auto] ...")
+        apply_repo_settings(api_url)
        ignore_pr_title_re = get_settings().get("GITHUB_APP.IGNORE_PR_TITLE", [])
        if not isinstance(ignore_pr_title_re, list):
            ignore_pr_title_re = [ignore_pr_title_re]
@ -136,11 +145,6 @@ async def handle_new_pr_opened(body: Dict[str, Any],
            get_logger().info(f"Ignoring PR with title '{title}' due to github_app.ignore_pr_title setting")
            return {}

-    pull_request, api_url = _check_pull_request_event(action, body, log_context)
-    if not (pull_request and api_url):
-        get_logger().info(f"Invalid PR event: {action=} {api_url=}")
-        return {}
-    if action in get_settings().github_app.handle_pr_actions:  # ['opened', 'reopened', 'ready_for_review', 'review_requested']
        if get_identity_provider().verify_eligibility("github", sender_id, api_url) is not Eligibility.NOT_ELIGIBLE:
                await _perform_auto_commands_github("pr_commands", agent, body, api_url, log_context)
        else:
@ -199,11 +203,6 @@ async def handle_push_trigger_for_new_commits(body: Dict[str, Any],
            get_logger().info(f"Finished waiting to process push trigger for {api_url=} - continue with flow")

    try:
-        if get_settings().github_app.push_trigger_wait_for_initial_review and not get_git_provider()(api_url,
-                                                                                                     incremental=IncrementalPR(
-                                                                                                             True)).previous_review:
-            get_logger().info(f"Skipping incremental review because there was no initial review for {api_url=} yet")
-            return {}
        if get_identity_provider().verify_eligibility("github", sender_id, api_url) is not Eligibility.NOT_ELIGIBLE:
                get_logger().info(f"Performing incremental review for {api_url=} because of {event=} and {action=}")
                await _perform_auto_commands_github("push_commands", agent, body, api_url, log_context)
@ -267,17 +266,22 @@ async def handle_request(body: Dict[str, Any], event: str):
            get_logger().info(f"Ignoring PR from '{sender=}' because it is a bot")
        return {}

+    if 'check_run' in body: # handle failed checks
+        # get_logger().debug(f'Request body', artifact=body, event=event) # added inside handle_checks
+        pass
    # handle comments on PRs
-    if action == 'created':
+    elif action == 'created':
        get_logger().debug(f'Request body', artifact=body, event=event)
        await handle_comments_on_pr(body, event, sender, sender_id, action, log_context, agent)
    # handle new PRs
    elif event == 'pull_request' and action != 'synchronize' and action != 'closed':
        get_logger().debug(f'Request body', artifact=body, event=event)
        await handle_new_pr_opened(body, event, sender, sender_id, action, log_context, agent)
+    elif event == "issue_comment" and 'edited' in action:
+        pass # handle_checkbox_clicked
    # handle pull_request event with synchronize action - "push trigger" for new commits
    elif event == 'pull_request' and action == 'synchronize':
-        get_logger().debug(f'Request body', artifact=body, event=event)
+        # get_logger().debug(f'Request body', artifact=body, event=event) # added inside handle_push_trigger_for_new_commits
        await handle_push_trigger_for_new_commits(body, event, sender,sender_id,  action, log_context, agent)
    elif event == 'pull_request' and action == 'closed':
        if get_settings().get("CONFIG.ANALYTICS_FOLDER", ""):
@ -325,7 +329,6 @@ async def _perform_auto_commands_github(commands_conf: str, agent: PRAgent, body
    apply_repo_settings(api_url)
    commands = get_settings().get(f"github_app.{commands_conf}")
    if not commands:
-        with get_logger().contextualize(**log_context):
        get_logger().info(f"New PR, but no auto commands configured")
        return
    for command in commands:
@ -334,7 +337,6 @@ async def _perform_auto_commands_github(commands_conf: str, agent: PRAgent, body
        args = split_command[1:]
        other_args = update_settings_from_args(args)
        new_command = ' '.join([command] + other_args)
-        with get_logger().contextualize(**log_context):
        get_logger().info(f"{commands_conf}. Performing auto command '{new_command}', for {api_url=}")
        await agent.handle_request(api_url, new_command)

@ -347,7 +349,7 @@ async def root():
 if get_settings().github_app.override_deployment_type:
    # Override the deployment type to app
    get_settings().set("GITHUB.DEPLOYMENT_TYPE", "app")
-get_settings().set("CONFIG.PUBLISH_OUTPUT_PROGRESS", False)
+# get_settings().set("CONFIG.PUBLISH_OUTPUT_PROGRESS", False)
 middleware = [Middleware(RawContextMiddleware)]
 app = FastAPI(middleware=middleware)
 app.include_router(router)
@ -356,5 +358,6 @@ app.include_router(router)
 def start():
    uvicorn.run(app, host="0.0.0.0", port=int(os.environ.get("PORT", "3000")))

+
 if __name__ == '__main__':
    start()
--- a/pr_agent/servers/github_polling.py
+++ b/pr_agent/servers/github_polling.py
@ -1,4 +1,5 @@
 import asyncio
+import traceback
 from datetime import datetime, timezone

 import aiohttp
@ -35,6 +36,7 @@ async def polling_loop():
    user_id = git_provider.get_user_id()
    agent = PRAgent()
    get_settings().set("CONFIG.PUBLISH_OUTPUT_PROGRESS", False)
+    get_settings().set("pr_description.publish_description_as_comment", True)

    try:
        deployment_type = get_settings().github.deployment_type
@ -78,6 +80,8 @@ async def polling_loop():
                                if 'subject' in notification and notification['subject']['type'] == 'PullRequest':
                                    pr_url = notification['subject']['url']
                                    latest_comment = notification['subject']['latest_comment_url']
+                                    if not latest_comment or not isinstance(latest_comment, str):
+                                        continue
                                    async with session.get(latest_comment, headers=headers) as comment_response:
                                        if comment_response.status == 200:
                                            comment = await comment_response.json()
@ -89,10 +93,13 @@ async def polling_loop():
                                            if 'user' in comment and 'login' in comment['user']:
                                                if comment['user']['login'] == user_id:
                                                    continue
-                                            comment_body = comment['body'] if 'body' in comment else ''
+                                            comment_body = comment.get('body', '')
+                                            if not comment_body:
+                                                continue
                                            commenter_github_user = comment['user']['login'] \
                                                if 'user' in comment else ''
-                                            get_logger().info(f"Commenter: {commenter_github_user}\nComment: {comment_body}")
+                                            get_logger().info(f"Polling, pr_url: {pr_url}",
+                                                              artifact={"comment": comment_body})
                                            user_tag = "@" + user_id
                                            if user_tag not in comment_body:
                                                continue
@ -100,7 +107,8 @@ async def polling_loop():
                                            comment_id = comment['id']
                                            git_provider.set_pr(pr_url)
                                            success = await agent.handle_request(pr_url, rest_of_comment,
-                                                                                 notify=lambda: git_provider.add_eyes_reaction(comment_id))  # noqa E501
+                                                                                 notify=lambda: git_provider.add_eyes_reaction(
+                                                                                     comment_id))  # noqa E501
                                            if not success:
                                                git_provider.set_pr(pr_url)

@ -108,7 +116,8 @@ async def polling_loop():
                        print(f"Failed to fetch notifications. Status code: {response.status}")

            except Exception as e:
-                get_logger().error(f"Exception during processing of a notification: {e}")
+                get_logger().error(f"Polling exception during processing of a notification: {e}",
+                                   artifact={"traceback": traceback.format_exc()})


 if __name__ == '__main__':
--- a/pr_agent/servers/gitlab_webhook.py
+++ b/pr_agent/servers/gitlab_webhook.py
@ -1,5 +1,6 @@
 import copy
 import json
+from datetime import datetime

 import uvicorn
 from fastapi import APIRouter, FastAPI, Request, status
@ -23,15 +24,41 @@ 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):
+async def get_mr_url_from_commit_sha(commit_sha, gitlab_token, project_id):
+    try:
+        import requests
+        headers = {
+            'Private-Token': f'{gitlab_token}'
+        }
+        # API endpoint to find MRs containing the commit
+        gitlab_url = get_settings().get("GITLAB.URL", 'https://gitlab.com')
+        response = requests.get(
+            f'{gitlab_url}/api/v4/projects/{project_id}/repository/commits/{commit_sha}/merge_requests',
+            headers=headers
+        )
+        merge_requests = response.json()
+        if merge_requests and response.status_code == 200:
+            pr_url = merge_requests[0]['web_url']
+            return pr_url
+        else:
+            get_logger().info(f"No merge requests found for commit: {commit_sha}")
+            return None
+    except Exception as e:
+        get_logger().error(f"Failed to get MR url from commit sha: {e}")
+        return None
+
+async def handle_request(api_url: str, body: str, log_context: dict, sender_id: str):
    log_context["action"] = body
    log_context["event"] = "pull_request" if body == "/review" else "comment"
-    log_context["api_url"] = url
+    log_context["api_url"] = api_url
+    log_context["app_name"] = get_settings().get("CONFIG.APP_NAME", "Unknown")
+
    with get_logger().contextualize(**log_context):
-        background_tasks.add_task(PRAgent().handle_request, url, body)
+        await PRAgent().handle_request(api_url, body)


-async def _perform_commands_gitlab(commands_conf: str, agent: PRAgent, api_url: str, log_context: dict):
+async def _perform_commands_gitlab(commands_conf: str, agent: PRAgent, api_url: str,
+                                   log_context: dict):
    apply_repo_settings(api_url)
    commands = get_settings().get(f"gitlab.{commands_conf}", {})
    for command in commands:
@ -48,19 +75,26 @@ async def _perform_commands_gitlab(commands_conf: str, agent: PRAgent, api_url:
            get_logger().error(f"Failed to perform command {command}: {e}")


+
@router.post("/webhook")
 async def gitlab_webhook(background_tasks: BackgroundTasks, request: Request):
+    start_time = datetime.now()
+    request_json = await request.json()
+
+    async def inner(data: dict):
        log_context = {"server_type": "gitlab_app"}
        get_logger().debug("Received a GitLab webhook")
-
-    # Check if the request is authorized
        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)
+            if not secret:
+                get_logger().warning(f"Empty secret retrieved, request_token: {request_token}")
+                return JSONResponse(status_code=status.HTTP_401_UNAUTHORIZED,
+                                    content=jsonable_encoder({"message": "unauthorized"}))
            try:
                secret_dict = json.loads(secret)
                gitlab_token = secret_dict["gitlab_token"]
-            log_context["sender"] = secret_dict.get("token_name", secret_dict.get("id", "unknown"))
+                log_context["token_id"] = secret_dict.get("token_name", secret_dict.get("id", "unknown"))
                context["settings"] = copy.deepcopy(global_settings)
                context["settings"].gitlab.personal_access_token = gitlab_token
            except Exception as e:
@ -69,34 +103,75 @@ async def gitlab_webhook(background_tasks: BackgroundTasks, request: Request):
        elif get_settings().get("GITLAB.SHARED_SECRET"):
            secret = get_settings().get("GITLAB.SHARED_SECRET")
            if not request.headers.get("X-Gitlab-Token") == secret:
-            get_logger().error(f"Failed to validate secret")
+                get_logger().error("Failed to validate secret")
                return JSONResponse(status_code=status.HTTP_401_UNAUTHORIZED, content=jsonable_encoder({"message": "unauthorized"}))
        else:
-        get_logger().error(f"Failed to validate secret")
+            get_logger().error("Failed to validate secret")
            return JSONResponse(status_code=status.HTTP_401_UNAUTHORIZED, content=jsonable_encoder({"message": "unauthorized"}))
        gitlab_token = get_settings().get("GITLAB.PERSONAL_ACCESS_TOKEN", None)
        if not gitlab_token:
-        get_logger().error(f"No gitlab token found")
+            get_logger().error("No gitlab token found")
            return JSONResponse(status_code=status.HTTP_401_UNAUTHORIZED, content=jsonable_encoder({"message": "unauthorized"}))

-    data = await request.json()
        get_logger().info("GitLab data", artifact=data)
+        sender = data.get("user", {}).get("username", "unknown")
+        sender_id = data.get("user", {}).get("id", "unknown")

+        # logic to ignore bot users (unlike Github, no direct flag for bot users in gitlab)
+        sender_name = data.get("user", {}).get("name", "unknown").lower()
+        if 'codium' in sender_name or 'bot_' in sender_name or 'bot-' in sender_name or '_bot' in sender_name or '-bot' in sender_name:
+            get_logger().info(f"Skipping bot user: {sender_name}")
+            return JSONResponse(status_code=status.HTTP_200_OK, content=jsonable_encoder({"message": "success"}))
+
+        log_context["sender"] = sender
        if data.get('object_kind') == 'merge_request' and data['object_attributes'].get('action') in ['open', 'reopen']:
            url = data['object_attributes'].get('url')
+            draft = data['object_attributes'].get('draft')
            get_logger().info(f"New merge request: {url}")
+
+            if draft:
+                get_logger().info(f"Skipping draft MR: {url}")
+                return JSONResponse(status_code=status.HTTP_200_OK, content=jsonable_encoder({"message": "success"}))
+
            await _perform_commands_gitlab("pr_commands", PRAgent(), url, log_context)
-    elif data.get('object_kind') == 'note' and data['event_type'] == 'note': # comment on MR
+        elif data.get('object_kind') == 'note' and data.get('event_type') == 'note': # comment on MR
            if 'merge_request' in data:
                mr = data['merge_request']
                url = mr.get('url')
+                
                get_logger().info(f"A comment has been added to a merge request: {url}")
                body = data.get('object_attributes', {}).get('note')
                if data.get('object_attributes', {}).get('type') == 'DiffNote' and '/ask' in body: # /ask_line
                    body = handle_ask_line(body, data)

-            handle_request(background_tasks, url, body, log_context)
+                await handle_request(url, body, log_context, sender_id)
+        elif data.get('object_kind') == 'push' and data.get('event_name') == 'push':
+            try:
+                project_id = data['project_id']
+                commit_sha = data['checkout_sha']
+                url = await get_mr_url_from_commit_sha(commit_sha, gitlab_token, project_id)
+                if not url:
+                    get_logger().info(f"No MR found for commit: {commit_sha}")
+                    return JSONResponse(status_code=status.HTTP_200_OK,
+                                        content=jsonable_encoder({"message": "success"}))

+                # we need first to apply_repo_settings
+                apply_repo_settings(url)
+                commands_on_push = get_settings().get(f"gitlab.push_commands", {})
+                handle_push_trigger = get_settings().get(f"gitlab.handle_push_trigger", False)
+                if not commands_on_push or not handle_push_trigger:
+                    get_logger().info("Push event, but no push commands found or push trigger is disabled")
+                    return JSONResponse(status_code=status.HTTP_200_OK,
+                                        content=jsonable_encoder({"message": "success"}))
+
+                get_logger().debug(f'A push event has been received: {url}')
+                await _perform_commands_gitlab("push_commands", PRAgent(), url, log_context)
+            except Exception as e:
+                get_logger().error(f"Failed to handle push event: {e}")
+
+    background_tasks.add_task(inner, request_json)
+    end_time = datetime.now()
+    get_logger().info(f"Processing time: {end_time - start_time}", request=request_json)
    return JSONResponse(status_code=status.HTTP_200_OK, content=jsonable_encoder({"message": "success"}))


@ -113,7 +188,7 @@ def handle_ask_line(body, data):
        path = data['object_attributes']['position']['new_path']
        side = 'RIGHT'  # if line_range_['start']['type'] == 'new' else 'LEFT'
        comment_id = data['object_attributes']["discussion_id"]
-        get_logger().info(f"Handling line comment")
+        get_logger().info("Handling line comment")
        body = f"/ask_line --line_start={start_line} --line_end={end_line} --side={side} --file_name={path} --comment_id={comment_id} {question}"
    except Exception as e:
        get_logger().error(f"Failed to handle ask line comment: {e}")
@ -124,7 +199,6 @@ def handle_ask_line(body, data):
 async def root():
    return {"status": "ok"}

-def start():
 gitlab_url = get_settings().get("GITLAB.URL", None)
 if not gitlab_url:
    raise ValueError("GITLAB.URL is not set")
@ -133,6 +207,8 @@ def start():
 app = FastAPI(middleware=middleware)
 app.include_router(router)

+
+def start():
    uvicorn.run(app, host="0.0.0.0", port=3000)


--- a/pr_agent/servers/gunicorn_config.py
+++ b/pr_agent/servers/gunicorn_config.py
@ -0,0 +1,191 @@
+import multiprocessing
+import os
+
+# from prometheus_client import multiprocess
+
+# Sample Gunicorn configuration file.
+
+#
+# Server socket
+#
+#   bind - The socket to bind.
+#
+#       A string of the form: 'HOST', 'HOST:PORT', 'unix:PATH'.
+#       An IP is a valid HOST.
+#
+#   backlog - The number of pending connections. This refers
+#       to the number of clients that can be waiting to be
+#       served. Exceeding this number results in the client
+#       getting an error when attempting to connect. It should
+#       only affect servers under significant load.
+#
+#       Must be a positive integer. Generally set in the 64-2048
+#       range.
+#
+
+# bind = '0.0.0.0:5000'
+bind = '0.0.0.0:3000'
+backlog = 2048
+
+#
+# Worker processes
+#
+#   workers - The number of worker processes that this server
+#       should keep alive for handling requests.
+#
+#       A positive integer generally in the 2-4 x $(NUM_CORES)
+#       range. You'll want to vary this a bit to find the best
+#       for your particular application's work load.
+#
+#   worker_class - The type of workers to use. The default
+#       sync class should handle most 'normal' types of work
+#       loads. You'll want to read
+#       http://docs.gunicorn.org/en/latest/design.html#choosing-a-worker-type
+#       for information on when you might want to choose one
+#       of the other worker classes.
+#
+#       A string referring to a Python path to a subclass of
+#       gunicorn.workers.base.Worker. The default provided values
+#       can be seen at
+#       http://docs.gunicorn.org/en/latest/settings.html#worker-class
+#
+#   worker_connections - For the eventlet and gevent worker classes
+#       this limits the maximum number of simultaneous clients that
+#       a single process can handle.
+#
+#       A positive integer generally set to around 1000.
+#
+#   timeout - If a worker does not notify the master process in this
+#       number of seconds it is killed and a new worker is spawned
+#       to replace it.
+#
+#       Generally set to thirty seconds. Only set this noticeably
+#       higher if you're sure of the repercussions for sync workers.
+#       For the non sync workers it just means that the worker
+#       process is still communicating and is not tied to the length
+#       of time required to handle a single request.
+#
+#   keepalive - The number of seconds to wait for the next request
+#       on a Keep-Alive HTTP connection.
+#
+#       A positive integer. Generally set in the 1-5 seconds range.
+#
+
+if os.getenv('GUNICORN_WORKERS', None):
+    workers = int(os.getenv('GUNICORN_WORKERS'))
+else:
+    cores = multiprocessing.cpu_count()
+    workers = cores * 2 + 1
+worker_connections = 1000
+timeout = 240
+keepalive = 2
+
+#
+#   spew - Install a trace function that spews every line of Python
+#       that is executed when running the server. This is the
+#       nuclear option.
+#
+#       True or False
+#
+
+spew = False
+
+#
+# Server mechanics
+#
+#   daemon - Detach the main Gunicorn process from the controlling
+#       terminal with a standard fork/fork sequence.
+#
+#       True or False
+#
+#   raw_env - Pass environment variables to the execution environment.
+#
+#   pidfile - The path to a pid file to write
+#
+#       A path string or None to not write a pid file.
+#
+#   user - Switch worker processes to run as this user.
+#
+#       A valid user id (as an integer) or the name of a user that
+#       can be retrieved with a call to pwd.getpwnam(value) or None
+#       to not change the worker process user.
+#
+#   group - Switch worker process to run as this group.
+#
+#       A valid group id (as an integer) or the name of a user that
+#       can be retrieved with a call to pwd.getgrnam(value) or None
+#       to change the worker processes group.
+#
+#   umask - A mask for file permissions written by Gunicorn. Note that
+#       this affects unix socket permissions.
+#
+#       A valid value for the os.umask(mode) call or a string
+#       compatible with int(value, 0) (0 means Python guesses
+#       the base, so values like "0", "0xFF", "0022" are valid
+#       for decimal, hex, and octal representations)
+#
+#   tmp_upload_dir - A directory to store temporary request data when
+#       requests are read. This will most likely be disappearing soon.
+#
+#       A path to a directory where the process owner can write. Or
+#       None to signal that Python should choose one on its own.
+#
+
+daemon = False
+raw_env = []
+pidfile = None
+umask = 0
+user = None
+group = None
+tmp_upload_dir = None
+
+#
+#   Logging
+#
+#   logfile - The path to a log file to write to.
+#
+#       A path string. "-" means log to stdout.
+#
+#   loglevel - The granularity of log output
+#
+#       A string of "debug", "info", "warning", "error", "critical"
+#
+
+errorlog = '-'
+loglevel = 'info'
+accesslog = None
+access_log_format = '%(h)s %(l)s %(u)s %(t)s "%(r)s" %(s)s %(b)s "%(f)s" "%(a)s"'
+
+#
+# Process naming
+#
+#   proc_name - A base to use with setproctitle to change the way
+#       that Gunicorn processes are reported in the system process
+#       table. This affects things like 'ps' and 'top'. If you're
+#       going to be running more than one instance of Gunicorn you'll
+#       probably want to set a name to tell them apart. This requires
+#       that you install the setproctitle module.
+#
+#       A string or None to choose a default of something like 'gunicorn'.
+#
+
+proc_name = None
+
+
+#
+# Server hooks
+#
+#   post_fork - Called just after a worker has been forked.
+#
+#       A callable that takes a server and worker instance
+#       as arguments.
+#
+#   pre_fork - Called just prior to forking the worker subprocess.
+#
+#       A callable that accepts the same arguments as after_fork
+#
+#   pre_exec - Called just prior to forking off a secondary
+#       master process during things like config reloading.
+#
+#       A callable that takes a server instance as the sole argument.
+#
--- a/pr_agent/servers/help.py
+++ b/pr_agent/servers/help.py
@ -68,10 +68,9 @@ some_config2=...
        output += """\
 - When you first install the app, the [default mode](https://pr-agent-docs.codium.ai/usage-guide/automations_and_usage/#github-app-automatic-tools-when-a-new-pr-is-opened) for the describe tool is:
 ```
-pr_commands = ["/describe --pr_description.add_original_user_description=true" 
-                         "--pr_description.keep_original_user_title=true", ...]
+pr_commands = ["/describe", ...]
 ```
-meaning the `describe` tool will run automatically on every PR, will keep the original title, and will add the original user description above the generated description. 
+meaning the `describe` tool will run automatically on every PR.

 - Markers are an alternative way to control the generated description, to give maximal control to the user. If you set:
 ```
@ -180,7 +179,7 @@ You can ask questions about the entire PR, about specific code lines, or about a
    @staticmethod
    def get_improve_usage_guide():
        output = "**Overview:**\n"
-        output += "The `improve` tool scans the PR code changes, and automatically generates suggestions for improving the PR code. "
+        output += "The code suggestions tool, named `improve`, scans the PR code changes, and automatically generates code suggestions for improving the PR."
        output += "The tool can be triggered [automatically](https://pr-agent-docs.codium.ai/usage-guide/automations_and_usage/#github-app-automatic-tools-when-a-new-pr-is-opened) every time a new PR is opened, or can be invoked manually by commenting on a PR.\n"
        output += """\
 - When commenting, to edit [configurations](https://github.com/Codium-ai/pr-agent/blob/main/pr_agent/settings/configuration.toml#L78) related to the improve tool (`pr_code_suggestions` section), use the following template:
--- a/pr_agent/settings/.secrets_template.toml
+++ b/pr_agent/settings/.secrets_template.toml
@ -29,6 +29,9 @@ key = "" # Optional, uncomment if you want to use Cohere. Acquire through https:
 [replicate]
 key = "" # Optional, uncomment if you want to use Replicate. Acquire through https://replicate.com/

+[groq]
+key = "" # Acquire through https://console.groq.com/keys
+
 [huggingface]
 key = "" # Optional, uncomment if you want to use Huggingface Inference API. Acquire through https://huggingface.co/docs/api-inference/quicktour
 api_base = "" # the base url for your huggingface inference endpoint
@ -40,9 +43,6 @@ api_base = "" # the base url for your local Llama 2, Code Llama, and other model
 vertex_project = "" # the google cloud platform project name for your vertexai deployment
 vertex_location = "" # the google cloud platform location for your vertexai deployment

-[aws]
-bedrock_region = "" # the AWS region to call Bedrock APIs
-
 [github]
 # ---- Set the following only for deployment type == "user"
 user_token = ""  # A GitHub personal access token with 'repo' scope.
@ -67,7 +67,7 @@ bearer_token = ""

 [bitbucket_server]
 # For Bitbucket Server bearer token
-auth_token = ""
+bearer_token = ""
 webhook_secret = ""

 # For Bitbucket app
--- a/pr_agent/settings/configuration.toml
+++ b/pr_agent/settings/configuration.toml
@ -1,24 +1,40 @@
 [config]
+# models
 model="gpt-4-turbo-2024-04-09"
-model_turbo="gpt-4-turbo-2024-04-09"
-fallback_models=["gpt-4-0125-preview"]
+model_turbo="gpt-4o-2024-08-06"
+fallback_models=["gpt-4o-2024-05-13"]
+# CLI
 git_provider="github"
 publish_output=true
 publish_output_progress=true
 verbosity_level=0 # 0,1,2
 use_extra_bad_extensions=false
+# Configurations
 use_wiki_settings_file=true
 use_repo_settings_file=true
 use_global_settings_file=true
 ai_timeout=120 # 2minutes
+# token limits
 max_description_tokens = 500
 max_commits_tokens = 500
 max_model_tokens = 32000 # Limits the maximum number of tokens that can be used by any model, regardless of the model's default capabilities.
-patch_extra_lines = 1
-secret_provider="google_cloud_storage"
+custom_model_max_tokens=-1 # for models not in the default list
+# patch extension logic
+patch_extension_skip_types =[".md",".txt"]
+allow_dynamic_context=false
+max_extra_lines_before_dynamic_context = 10 # will try to include up to 10 extra lines before the hunk in the patch, until we reach an enclosing function or class
+patch_extra_lines_before = 3 # Number of extra lines (+3 default ones) to include before each hunk in the patch
+patch_extra_lines_after = 1 # Number of extra lines (+3 default ones) to include after each hunk in the patch
+secret_provider=""
 cli_mode=false
 ai_disclaimer_title=""  # Pro feature, title for a collapsible disclaimer to AI outputs
 ai_disclaimer=""  # Pro feature, full text for the AI disclaimer
+output_relevant_configurations=false
+large_patch_policy = "clip" # "clip", "skip"
+is_auto_command=false
+# seed
+seed=-1 # set positive value to fix the seed (and ensure temperature=0)
+temperature=0.2

 [pr_reviewer] # /review #
 # enable/disable features
@ -26,11 +42,13 @@ require_score_review=false
 require_tests_review=true
 require_estimate_effort_to_review=true
 require_can_be_split_review=false
+require_security_review=true
+extra_issue_links=false
 # soc2
 require_soc2_ticket=false
 soc2_ticket_prompt="Does the PR description include a link to ticket in a project management system (e.g., Jira, Asana, Trello, etc.) ?"
 # general options
-num_code_suggestions=4
+num_code_suggestions=0
 inline_code_comments = false
 ask_and_reflect=false
 #automatic_review=true
@ -44,7 +62,7 @@ enable_review_labels_effort=true
 require_all_thresholds_for_incremental_review=false
 minimal_commits_for_incremental_review=0
 minimal_minutes_for_incremental_review=0
-enable_help_text=true # Determines whether to include help text in the PR review. Enabled by default.
+enable_help_text=false # Determines whether to include help text in the PR review. Enabled by default.
 # auto approval
 enable_auto_approval=false
 maximal_review_effort=5
@ -53,7 +71,7 @@ maximal_review_effort=5
 [pr_description] # /describe #
 publish_labels=true
 add_original_user_description=true
-keep_original_user_title=true
+generate_ai_title=false
 use_bullet_points=true
 extra_instructions = ""
 enable_pr_type=true
@ -70,38 +88,70 @@ inline_file_summary=false # false, true, 'table'
 # markers
 use_description_markers=false
 include_generated_by_header=true
-
+# large pr mode 💎
+enable_large_pr_handling=true
+max_ai_calls=4
+async_ai_calls=true
+mention_extra_files=true
 #custom_labels = ['Bug fix', 'Tests', 'Bug fix with tests', 'Enhancement', 'Documentation', 'Other']

 [pr_questions] # /ask #
-enable_help_text=true
+enable_help_text=false


 [pr_code_suggestions] # /improve #
-max_context_tokens=8000
+max_context_tokens=14000
 num_code_suggestions=4
-summarize = true
+commitable_code_suggestions = false
 extra_instructions = ""
 rank_suggestions = false
-enable_help_text=true
-persistent_comment=false
+enable_help_text=false
+persistent_comment=true
+max_history_len=4
+# enable to apply suggestion 💎
+apply_suggestions_checkbox=true
+# suggestions scoring
+self_reflect_on_suggestions=true
+suggestions_score_threshold=0 # [0-10]. highly recommend not to set this value above 8, since above it may clip highly relevant suggestions
 # params for '/improve --extended' mode
 auto_extended_mode=true
-num_code_suggestions_per_chunk=5
+num_code_suggestions_per_chunk=4
 max_number_of_calls = 3
 parallel_calls = true
 rank_extended_suggestions = false
 final_clip_factor = 0.8
+# self-review checkbox
+demand_code_suggestions_self_review=false # add a checkbox for the author to self-review the code suggestions
+code_suggestions_self_review_text= "**Author self-review**: I have reviewed the PR code suggestions, and addressed the relevant ones."
+approve_pr_on_self_review=false # Pro feature. if true, the PR will be auto-approved after the author clicks on the self-review checkbox
+# Suggestion impact
+publish_post_process_suggestion_impact=true
+
+[pr_custom_prompt] # /custom_prompt #
+prompt = """\
+The code suggestions should focus only on the following:
+- ...
+- ...
+...
+"""
+suggestions_score_threshold=0
+num_code_suggestions_per_chunk=4
+self_reflect_on_custom_suggestions=true
+enable_help_text=false
+

 [pr_add_docs] # /add_docs #
 extra_instructions = ""
-docs_style = "Sphinx Style" # "Google Style with Args, Returns, Attributes...etc", "Numpy Style", "Sphinx Style", "PEP257", "reStructuredText"
+docs_style = "Sphinx" # "Google Style with Args, Returns, Attributes...etc", "Numpy Style", "Sphinx Style", "PEP257", "reStructuredText"
+file = ""              # in case there are several components with the same name, you can specify the relevant file
+class_name = ""        # in case there are several methods with the same name in the same file, you can specify the relevant class name

 [pr_update_changelog] # /update_changelog #
 push_changelog_changes=false
 extra_instructions = ""

 [pr_analyze] # /analyze #
+enable_help_text=true

 [pr_test] # /test #
 extra_instructions = ""
@ -110,19 +160,20 @@ num_tests=3            # number of tests to generate. max 5.
 avoid_mocks=true       # if true, the generated tests will prefer to use real objects instead of mocks
 file = ""              # in case there are several components with the same name, you can specify the relevant file
 class_name = ""        # in case there are several methods with the same name in the same file, you can specify the relevant class name
-enable_help_text=true
+enable_help_text=false

 [pr_improve_component] # /improve_component #
 num_code_suggestions=4
 extra_instructions = ""
 file = ""              # in case there are several components with the same name, you can specify the relevant file
-class_name = ""
+class_name = ""        # in case there are several methods with the same name in the same file, you can specify the relevant class name

 [checks] # /checks (pro feature) #
 enable_auto_checks_feedback=true
 excluded_checks_list=["lint"] # list of checks to exclude, for example: ["check1", "check2"]
 persistent_comment=true
 enable_help_text=true
+final_update_message = false

 [pr_help] # /help #

@ -135,22 +186,23 @@ ratelimit_retries = 5
 base_url = "https://api.github.com"
 publish_inline_comments_fallback_with_verification = true
 try_fix_invalid_inline_comments = true
+app_name = "pr-agent"

 [github_action_config]
 # auto_review = true    # set as env var in .github/workflows/pr-agent.yaml
 # auto_describe = true  # set as env var in .github/workflows/pr-agent.yaml
 # auto_improve = true   # set as env var in .github/workflows/pr-agent.yaml
-# enable_output = true   # set as env var in .github/workflows/pr-agent.yaml

 [github_app]
 # these toggles allows running the github app from custom deployments
+bot_user = "github-actions[bot]"
 override_deployment_type = true
 # settings for "pull_request" event
 handle_pr_actions = ['opened', 'reopened', 'ready_for_review']
 pr_commands = [
-    "/describe --pr_description.add_original_user_description=true --pr_description.keep_original_user_title=true",
+    "/describe --pr_description.final_update_message=false",
    "/review --pr_reviewer.num_code_suggestions=0",
-    "/improve --pr_code_suggestions.summarize=true",
+    "/improve",
 ]
 # settings for "pull_request" event with "synchronize" action - used to detect and handle push triggers for new commits
 handle_push_trigger = false
@ -160,24 +212,30 @@ 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",
+    "/describe",
    "/review --pr_reviewer.num_code_suggestions=0",
 ]
 ignore_pr_title = []
 ignore_bot_pr = true

 [gitlab]
-url = "https://gitlab.com" # URL to the gitlab service
+url = "https://gitlab.com"
 pr_commands = [
-    "/describe --pr_description.add_original_user_description=true --pr_description.keep_original_user_title=true",
+    "/describe --pr_description.final_update_message=false",
+    "/review --pr_reviewer.num_code_suggestions=0",
+    "/improve",
+]
+handle_push_trigger = false
+push_commands = [
+    "/describe",
    "/review --pr_reviewer.num_code_suggestions=0",
-    "/improve --pr_code_suggestions.summarize=true",
 ]

 [bitbucket_app]
 pr_commands = [
+    "/describe --pr_description.final_update_message=false",
    "/review --pr_reviewer.num_code_suggestions=0",
-    "/improve --pr_code_suggestions.summarize=false",
+    "/improve --pr_code_suggestions.commitable_code_suggestions=true --pr_code_suggestions.suggestions_score_threshold=7",
 ]


@ -200,10 +258,19 @@ pr_commands = [
 # URL to the BitBucket Server instance
 # url = "https://git.bitbucket.com"
 url = ""
+pr_commands = [
+    "/describe --pr_description.final_update_message=false",
+    "/review --pr_reviewer.num_code_suggestions=0",
+    "/improve --pr_code_suggestions.commitable_code_suggestions=true --pr_code_suggestions.suggestions_score_threshold=7",
+]

 [litellm]
 # use_client = false
 # drop_params = false
+enable_callbacks = false
+success_callback = []
+failure_callback = []
+service_callback = []

 [pr_similar_issue]
 skip_comments = false
@ -211,6 +278,14 @@ force_update_dataset = false
 max_issues_to_scan = 500
 vectordb = "pinecone"

+[pr_find_similar_component]
+class_name = ""
+file = ""
+search_from_org = false
+allow_fallback_less_words = true
+number_of_keywords = 5
+number_of_results = 5
+
 [pinecone]
 # fill and place in .secrets.toml
 #api_key = ...
@ -218,3 +293,7 @@ vectordb = "pinecone"

 [lancedb]
 uri = "./lancedb"
+
+[best_practices]
+content = ""
+max_lines_allowed = 800
--- a/pr_agent/settings/ignore.toml
+++ b/pr_agent/settings/ignore.toml
@ -8,4 +8,5 @@ glob = [
 regex = [
    # Ignore files and directories matching these regex patterns.
    # See https://learnbyexample.github.io/python-regex-cheatsheet/
+    # for example: regex = ['.*\.toml$']
 ]
--- a/pr_agent/settings/language_extensions.toml
+++ b/pr_agent/settings/language_extensions.toml
@ -44,6 +44,7 @@ default = [
    'ss',
    'svg',
    'tar',
+    'tgz',
    'tsv',
    'ttf',
    'war',
--- a/pr_agent/settings/pr_add_docs.toml
+++ b/pr_agent/settings/pr_add_docs.toml
@ -56,7 +56,7 @@ Code Documentation:
  items:
    relevant file:
      type: string
-      description: the relevant file full path
+      description: The full file path of the relevant file.
    relevant line:
      type: integer
      description: |-
--- a/pr_agent/settings/pr_code_suggestions_prompts.toml
+++ b/pr_agent/settings/pr_code_suggestions_prompts.toml
@ -1,20 +1,23 @@
 [pr_code_suggestions_prompt]
-system="""You are PR-Reviewer, a language model that specializes in suggesting code improvements for a Pull Request (PR).
-Your task is to provide meaningful and actionable code suggestions, to improve the new code presented in a PR diff (lines starting with '+').
+system="""You are PR-Reviewer, a language model that specializes in suggesting improvements to a Pull Request (PR) code.
+Your task is to provide meaningful and actionable code suggestions, to improve the new code presented in a PR code diff (lines starting with '+').

-Example for the PR Diff format:
+
+The format we will use to present the PR code diff:
 ======
 ## file: 'src/file1.py'

@@ ... @@ def func1():
 __new hunk__
-12  code line1 that remained unchanged in the PR
-13 +new hunk code line2 added in the PR
-14  code line3 that remained unchanged in the PR
+11  unchanged code line0 in the PR
+12  unchanged code line1 in the PR
+13 +new code line2 added in the PR
+14  unchanged code line3 in the PR
 __old hunk__
- code line1 that remained unchanged in the PR
-old hunk code line2 that was removed in the PR
- code line3 that remained unchanged in the PR
+ unchanged code line0
+ unchanged code line1
+-old code line2 removed in the PR
+ unchanged code line3

@@ ... @@ def func2():
 __new hunk__
@ -27,21 +30,26 @@ __old hunk__
 ...
 ======

+- In this format, we separate each hunk of diff code to '__new hunk__' and '__old hunk__' sections. The '__new hunk__' section contains the new code of the chunk, and the '__old hunk__' section contains the old code, that was removed. If no new code was added in a specific hunk, '__new hunk__' section will not be presented. If no code was removed, '__old hunk__' section will not be presented.
+- We also added line numbers for the '__new hunk__' code, to help you refer to the code lines in your suggestions. These line numbers are not part of the actual code, and should only used for reference.
+- Code lines are prefixed with symbols ('+', '-', ' '). The '+' symbol indicates new code added in the PR, the '-' symbol indicates code removed in the PR, and the ' ' symbol indicates unchanged code. \

-Specific instructions:
- Provide up to {{ num_code_suggestions }} code suggestions. The suggestions should be diverse and insightful.
- The suggestions should refer only to code from the '__new hunk__' sections, and focus on new lines of code (lines starting with '+').
- Prioritize suggestions that address major problems, issues and bugs in the PR code. As a second priority, suggestions should focus on enhancement, best practice, performance, maintainability, and other aspects.
+
+Specific instructions for generating code suggestions:
+- Provide up to {{ num_code_suggestions }} code suggestions.
+- The suggestions should be diverse and insightful. They should focus on improving only the new code introduced in the PR, meaning lines from '__new hunk__' sections, starting with '+' (after the line numbers).
+- Prioritize suggestions that address possible issues, major problems, and bugs in the PR code. Don't repeat changes already present in the PR. If there are no relevant suggestions for the PR, return an empty list.
 - Don't suggest to add docstring, type hints, or comments, or to remove unused imports.
 - Suggestions should not repeat code already present in the '__new hunk__' sections.
- Provide the exact line numbers range (inclusive) for each suggestion.
- When quoting variables or names from the code, use backticks (`) instead of single quote (').
+- Provide the exact line numbers range (inclusive) for each suggestion. Use the line numbers from the '__new hunk__' sections.
+- Every time you cite variables or names from the code, use backticks ('`'). For example: 'ensure that `variable_name` is ...'
+- Take into account that you are reviewing a PR code diff, and that the entire codebase is not available for you as context. Hence, avoid suggestions that might conflict with unseen parts of the codebase.


 {%- if extra_instructions %}


-Extra instructions from the user:
+Extra instructions from the user, that should be taken into account with high priority:
 ======
 {{ extra_instructions }}
 ======
@ -51,20 +59,15 @@ Extra instructions from the user:
 The output must be a YAML object equivalent to type $PRCodeSuggestions, according to the following Pydantic definitions:
 =====
 class CodeSuggestion(BaseModel):
-    relevant_file: str = Field(description="the relevant file full path")
-    language: str = Field(description="the code language of the relevant file")
+    relevant_file: str = Field(description="The full file path of the relevant file")
+    language: str = Field(description="The programming language of the relevant file")
    suggestion_content: str = Field(description="an actionable suggestion for meaningfully improving the new code introduced in the PR")
-{%- if summarize_mode %}
-    existing_code: str = Field(description="a short code snippet from a '__new hunk__' section to illustrate the relevant existing code. Don't show the line numbers.")
-    improved_code: str = Field(description="a short code snippet to illustrate the improved code, after applying the suggestion.")
+    existing_code: str = Field(description="a short code snippet, demonstrating the relevant code lines from a '__new hunk__' section. It must be without line numbers. Quote only full code lines, not partial ones. Use abbreviations ("...") of full lines if needed")
+    improved_code: str = Field(description="a new code snippet, that can be used to replace the relevant 'existing_code' lines in '__new hunk__' code after applying the suggestion")
    one_sentence_summary: str = Field(description="a short summary of the suggestion action, in a single sentence. Focus on the 'what'. Be general, and avoid method or variable names.")
-{%- else %}
-    existing_code: str = Field(description="a code snippet, demonstrating the relevant code lines from a '__new hunk__' section. It must be contiguous, correctly formatted and indented, and without line numbers")
-    improved_code: str = Field(description="a new code snippet, that can be used to replace the relevant lines in '__new hunk__' code. Replacement suggestions should be complete, correctly formatted and indented, and without line numbers")
-{%- endif %}
    relevant_lines_start: int = Field(description="The relevant line number, from a '__new hunk__' section, where the suggestion starts (inclusive). Should be derived from the hunk line numbers, and correspond to the 'existing code' snippet above")
    relevant_lines_end: int = Field(description="The relevant line number, from a '__new hunk__' section, where the suggestion ends (inclusive). Should be derived from the hunk line numbers, and correspond to the 'existing code' snippet above")
-    label: str = Field(description="a single label for the suggestion, to help the user understand the suggestion type. For example: 'security', 'bug', 'performance', 'enhancement', 'possible issue', 'best practice', 'maintainability', etc. Other labels are also allowed")
+    label: str = Field(description="a single label for the suggestion, to help the user understand the suggestion type. For example: 'security', 'possible bug', 'possible issue', 'performance', 'enhancement', 'best practice', 'maintainability', etc. Other labels are also allowed")

 class PRCodeSuggestions(BaseModel):
    code_suggestions: List[CodeSuggestion]
@ -80,7 +83,6 @@ code_suggestions:
    python
  suggestion_content: |
    ...
-{%- if summarize_mode %}
  existing_code: |
    ...
  improved_code: |
@ -89,14 +91,6 @@ code_suggestions:
    ...
  relevant_lines_start: 12
  relevant_lines_end: 13
-{%- else %}
-  existing_code: |
-    ...
-  relevant_lines_start: 12
-  relevant_lines_end: 13
-  improved_code: |
-    ...
-{%- endif %}
  label: |
    ...
 ```
@ -105,7 +99,7 @@ code_suggestions:
 Each YAML output MUST be after a newline, indented, with block scalar indicator ('|').
 """

-user="""PR Info:
+user="""--PR Info--

 Title: '{{title}}'

@ -119,3 +113,105 @@ The PR Diff:
 Response (should be a valid YAML, and nothing else):
 ```yaml
 """
+
+
+[pr_code_suggestions_prompt_claude]
+system="""You are PR-Reviewer, a language model that specializes in suggesting improvements to a Pull Request (PR) code.
+Your task is to provide meaningful and actionable code suggestions, to improve the new code presented in a PR code diff (lines starting with '+').
+
+
+The format we will use to present the PR code diff:
+======
+## file: 'src/file1.py'
+
+@@ ... @@ def func1():
+__new hunk__
+11  unchanged code line0 in the PR
+12  unchanged code line1 in the PR
+13 +new code line2 added in the PR
+14  unchanged code line3 in the PR
+__old hunk__
+ unchanged code line0
+ unchanged code line1
+-old code line2 removed in the PR
+ unchanged code line3
+
+@@ ... @@ def func2():
+__new hunk__
+...
+__old hunk__
+...
+
+
+## file: 'src/file2.py'
+...
+======
+
+- In this format, we separate each hunk of diff code to '__new hunk__' and '__old hunk__' sections. The '__new hunk__' section contains the new code of the chunk, and the '__old hunk__' section contains the old code, that was removed. If no new code was added in a specific hunk, '__new hunk__' section will not be presented. If no code was removed, '__old hunk__' section will not be presented.
+- We also added line numbers for the '__new hunk__' code, to help you refer to the code lines in your suggestions. These line numbers are not part of the actual code, and should only used for reference.
+- Code lines are prefixed with symbols ('+', '-', ' '). The '+' symbol indicates new code added in the PR, the '-' symbol indicates code removed in the PR, and the ' ' symbol indicates unchanged code. \
+
+
+Specific instructions for generating code suggestions:
+- Provide up to {{ num_code_suggestions }} code suggestions.
+- The suggestions should be diverse and insightful. They should focus on improving only the new code introduced in the PR, meaning lines from '__new hunk__' sections, starting with '+' (after the line numbers).
+- Prioritize suggestions that address possible issues, major problems, and bugs in the PR code. Don't repeat changes already present in the PR. If there are no relevant suggestions for the PR, return an empty list.
+- Don't suggest to add docstring, type hints, or comments, or to remove unused imports.
+- Provide the exact line numbers range (inclusive) for each suggestion. Use the line numbers from the '__new hunk__' sections.
+- Every time you cite variables or names from the code, use backticks ('`'). For example: 'ensure that `variable_name` is ...'
+- Take into account that you are recieving as an input only a PR code diff. The entire codebase is not available for you as context. Hence, avoid suggestions that might conflict with unseen parts of the codebase, like imports, global variables, etc.
+
+
+{%- if extra_instructions %}
+
+
+Extra instructions from the user, that should be taken into account with high priority:
+======
+{{ extra_instructions }}
+======
+{%- endif %}
+
+
+The output must be a YAML object equivalent to type $PRCodeSuggestions, according to the following Pydantic definitions:
+=====
+class CodeSuggestion(BaseModel):
+    relevant_file: str = Field(description="The full file path of the relevant file")
+    language: str = Field(description="the programming language of the relevant file")
+    suggestion_content: str = Field(description="an actionable suggestion for meaningfully improving the new code introduced in the PR. Don't present here actual code snippets, just the suggestion. Be short and concise")
+    existing_code: str = Field(description="a short code snippet, demonstrating the relevant code lines from a '__new hunk__' section. It must be without line numbers. Quote only full code lines, not partial ones. Use abbreviations ("...") of full lines if needed")
+    improved_code: str = Field(description="a new code snippet, that can be used to replace the relevant 'existing_code' lines in '__new hunk__' code after applying the suggestion")
+    one_sentence_summary: str = Field(description="a short summary of the suggestion action, in a single sentence. Focus on the 'what'. Be general, and avoid method or variable names.")
+    relevant_lines_start: int = Field(description="The relevant line number, from a '__new hunk__' section, where the suggestion starts (inclusive). Should be derived from the hunk line numbers, and correspond to the 'existing code' snippet above")
+    relevant_lines_end: int = Field(description="The relevant line number, from a '__new hunk__' section, where the suggestion ends (inclusive). Should be derived from the hunk line numbers, and correspond to the 'existing code' snippet above")
+    label: str = Field(description="a single label for the suggestion, to help the user understand the suggestion type. For example: 'security', 'possible bug', 'possible issue', 'performance', 'enhancement', 'best practice', 'maintainability', etc. Other labels are also allowed")
+
+
+class PRCodeSuggestions(BaseModel):
+    code_suggestions: List[CodeSuggestion]
+=====
+
+
+Example output:
+```yaml
+code_suggestions:
+- relevant_file: |
+    src/file1.py
+  language: |
+    python
+  suggestion_content: |
+    ...
+  existing_code: |
+    ...
+  improved_code: |
+    ...
+  one_sentence_summary: |
+    ...
+  relevant_lines_start: 12
+  relevant_lines_end: 13
+  label: |
+    ...
+```
+
+
+Each YAML output MUST be after a newline, indented, with block scalar indicator ('|').
+"""
--- a/pr_agent/settings/pr_code_suggestions_reflect_prompts.toml
+++ b/pr_agent/settings/pr_code_suggestions_reflect_prompts.toml
@ -0,0 +1,90 @@
+[pr_code_suggestions_reflect_prompt]
+system="""You are a language model that specializes in reviewing and evaluating suggestions for a Pull Request (PR) code.
+
+Your input is a PR code, and a list of code suggestions that were generated for the PR.
+Your goal is to inspect, review and score the suggestsions.
+Be aware - the suggestions may not always be correct or accurate, and you should evaluate them in relation to the actual PR code diff presented. Sometimes the suggestion may ignore parts of the actual code diff, and in that case, you should give it a score of 0.
+
+Specific instructions:
+- Carefully review both the suggestion content, and the related PR code diff. Mistakes in the suggestions can occur. Make sure the suggestions are logical and correct, and properly derived from the PR code diff.
+- In addition to the exact code lines mentioned in each suggestion, review the code around them, to ensure that the suggestions are contextually accurate.
+- Check that the 'existing_code' field is valid. The 'existing_code' content should match, or be derived, from code lines from a 'new hunk' section in the PR code diff.
+- Check that the 'improved_code' section correctly reflects the suggestion content.
+- High scores (8 to 10) should be given to correct suggestions that address major bugs and issues, or security concerns. Lower scores (3 to 7) should be for correct suggestions addressing minor issues, code style, code readability, maintainability, etc. Don't give high scores to suggestions that are not crucial, and bring only small improvement or optimization.
+- Order the feedback the same way the suggestions are ordered in the input.
+
+
+The format that is used to present the PR code diff is as follows:
+======
+## file: 'src/file1.py'
+
+@@ ... @@ def func1():
+__new hunk__
+12  code line1 that remained unchanged in the PR
+13 +new code line2 added in the PR
+14  code line3 that remained unchanged in the PR
+__old hunk__
+ code line1 that remained unchanged in the PR
+-old code line2 that was removed in the PR
+ code line3 that remained unchanged in the PR
+
+@@ ... @@ def func2():
+__new hunk__
+...
+__old hunk__
+...
+
+
+## file: 'src/file2.py'
+...
+======
+- In this format, we separated each hunk of code to '__new hunk__' and '__old hunk__' sections. The '__new hunk__' section contains the new code of the chunk, and the '__old hunk__' section contains the old code that was removed.
+- If no new code was added in a specific hunk, '__new hunk__' section will not be presented. If no code was removed, '__old hunk__' section will not be presented.
+- We added line numbers for the '__new hunk__' sections, to help you refer to the code lines in your suggestions. These line numbers are not part of the actual code, and are only used for reference.
+- Code lines are prefixed symbols ('+', '-', ' '). The '+' symbol indicates new code added in the PR, the '-' symbol indicates code removed in the PR, and the ' ' symbol indicates unchanged code.
+
+
+The output must be a YAML object equivalent to type $PRCodeSuggestionsFeedback, according to the following Pydantic definitions:
+=====
+class CodeSuggestionFeedback(BaseModel):
+    suggestion_summary: str = Field(description="repeated from the input")
+    relevant_file: str = Field(description="repeated from the input")
+    suggestion_score: int = Field(description="The actual output - the score of the suggestion, from 0 to 10. Give 0 if the suggestion is wrong. Otherwise, give a score from 1 to 10 (inclusive), where 1 is the lowest and 10 is the highest.")
+    why: str = Field(description="Short and concise explanation of why the suggestion received the score (one to two sentences).")
+
+class PRCodeSuggestionsFeedback(BaseModel):
+    code_suggestions: List[CodeSuggestionFeedback]
+=====
+
+
+Example output:
+```yaml
+code_suggestions:
+- suggestion_summary: |
+    Use a more descriptive variable name here
+  relevant_file: "src/file1.py"
+  suggestion_score: 6
+  why: |
+    The variable name 't' is not descriptive enough
+- ...
+```
+
+
+Each YAML output MUST be after a newline, indented, with block scalar indicator ('|').
+"""
+
+user="""You are given a Pull Request (PR) code diff:
+======
+{{ diff|trim }}
+======
+
+
+And here is a list of corresponding {{ num_code_suggestions }} code suggestions to improve this Pull Request code:
+======
+{{ suggestion_str|trim }}
+======
+
+
+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
@ -37,18 +37,18 @@ class PRType(str, Enum):

 {%- if enable_semantic_files_types %}

-Class FileDescription(BaseModel):
-    filename: str = Field(description="the relevant file full path")
-    language: str = Field(description="the relevant file language")
+class FileDescription(BaseModel):
+    filename: str = Field(description="The full file path of the relevant file.")
+    language: str = Field(description="The programming language of the relevant file.")
    changes_summary: str = Field(description="concise summary of the changes in the relevant file, in bullet points (1-4 bullet points).")
    changes_title: str = Field(description="an informative title for the changes in the files, describing its main theme (5-10 words).")
    label: str = Field(description="a single semantic label that represents a type of code changes that occurred in the File. Possible values (partial list): 'bug fix', 'tests', 'enhancement', 'documentation', 'error handling', 'configuration changes', 'dependencies', 'formatting', 'miscellaneous', ...")
 {%- endif %}

-Class PRDescription(BaseModel):
+class PRDescription(BaseModel):
    type: List[PRType] = Field(description="one or more types that describe the PR content. Return the label member value (e.g. 'Bug fix', not 'bug_fix')")
 {%- if enable_semantic_files_types %}
-    pr_files[List[FileDescription]] = Field(max_items=15, description="a list of the files in the PR, and their changes summary.")
+    pr_files: List[FileDescription] = Field(max_items=15, description="a list of the files in the PR, and summary of their changes")
 {%- endif %}
    description: str = Field(description="an informative and concise description of the PR. Use bullet points. Display first the most significant changes.")
    title: str = Field(description="an informative title for the PR, describing its main theme")
--- a/pr_agent/settings/pr_evaluate_prompt_response.toml
+++ b/pr_agent/settings/pr_evaluate_prompt_response.toml
@ -0,0 +1,68 @@
+[pr_evaluate_prompt]
+prompt="""\
+You are the PR-task-evaluator, a language model that compares and ranks the quality of two responses provided in response to a lengthy task regarding a Pull Request (PR) code diff.
+
+
+The task to be evaluated is:
+
+***** Start of Task *****
+{{pr_task|trim}}
+
+***** End of Task *****
+
+
+
+Response 1 to the task is:
+
+***** Start of Response 1 *****
+
+{{pr_response1|trim}}
+
+***** End of Response 1 *****
+
+
+
+Response 2 to the task is:
+
+***** Start of Response 2 *****
+
+{{pr_response2|trim}}
+
+***** End of Response 2 *****
+
+
+
+Guidelines to evaluate the responses:
+- Thoroughly read the 'Task' part. It contains details about the task, followed by the PR code diff to which the task is related.
+- Thoroughly read 'Response1' and 'Response2' parts. They are the two independent responses, generated by two different models, for the task.
+
+After that, rank each response. Criterions to rank each response:
+- How well does the response follow the specific task instructions and requirements?
+- How well does the response analyze and understand the PR code diff?
+- How well will a person perceive it as a good response that correctly addresses the task?
+- How well does the response prioritize key feedback, related to the task instructions, that a human reader seeing that feedback would also consider as important?
+- Don't necessarily rank higher a response that is longer. A shorter response might be better if it is more concise, and still addresses the task better.
+
+
+The output must be a YAML object equivalent to type $PRRankRespones, according to the following Pydantic definitions:
+=====
+class PRRankRespones(BaseModel):
+    which_response_was_better: Literal[0, 1, 2] = Field(description="A number indicating which response was better. 0 means both responses are equally good.")
+    why: str = Field(description="In a short and concise manner, explain why the chosen response is better than the other. Be specific and give examples if relevant.")
+    score_response1: int = Field(description="A score between 1 and 10, indicating the quality of the response1, based on the criterions mentioned in the prompt.")
+    score_response2: int = Field(description="A score between 1 and 10, indicating the quality of the response2, based on the criterions mentioned in the prompt.")
+=====
+
+
+Example output:
+```yaml
+which_response_was_better: "X"
+why: "Response X is better because it is more practical, and addresses the task requirements better since ..."
+score_response1: ...
+score_response2: ...
+```
+
+
+Response (should be a valid YAML, and nothing else):
+```yaml
+"""
--- a/pr_agent/settings/pr_reviewer_prompts.toml
+++ b/pr_agent/settings/pr_reviewer_prompts.toml
@ -5,20 +5,29 @@ Your task is to provide constructive and concise feedback for the PR, and also p
 {%- else %}
 Your task is to provide constructive and concise feedback for the PR.
 {%- endif %}
-The review should focus on new code added in the PR diff (lines starting with '+')
+The review should focus on new code added in the PR code diff (lines starting with '+')

-Example PR Diff:
+
+The format we will use to present the PR code diff:
 ======
 ## file: 'src/file1.py'

-@@ -12,5 +12,5 @@ def func1():
-code line 1 that remained unchanged in the PR
-code line 2 that remained unchanged in the PR
-code line that was removed in the PR
-+code line added in the PR
-code line 3 that remained unchanged in the PR
+@@ ... @@ def func1():
+__new hunk__
+11  unchanged code line0 in the PR
+12  unchanged code line1 in the PR
+13 +new code line2 added in the PR
+14  unchanged code line3 in the PR
+__old hunk__
+ unchanged code line0
+ unchanged code line1
+-old code line2 removed in the PR
+ unchanged code line3

@@ ... @@ def func2():
+__new hunk__
+...
+__old hunk__
 ...


@ -26,20 +35,26 @@ code line 3 that remained unchanged in the PR
 ...
 ======

+- In this format, we separated each hunk of diff code to '__new hunk__' and '__old hunk__' sections. The '__new hunk__' section contains the new code of the chunk, and the '__old hunk__' section contains the old code, that was removed. If no new code was added in a specific hunk, '__new hunk__' section will not be presented. If no code was removed, '__old hunk__' section will not be presented.
+- We also added line numbers for the '__new hunk__' code, to help you refer to the code lines in your suggestions. These line numbers are not part of the actual code, and should only used for reference.
+- Code lines are prefixed with symbols ('+', '-', ' '). The '+' symbol indicates new code added in the PR, the '-' symbol indicates code removed in the PR, and the ' ' symbol indicates unchanged code. \
+ The review should address new code added in the PR code diff (lines starting with '+')
+- When quoting variables or names from the code, use backticks (`) instead of single quote (').
+
 {%- if num_code_suggestions > 0 %}


 Code suggestions guidelines:
 - 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.
+- 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.
- Suggestions should focus on the new code added in the PR diff (lines starting with '+')
- When quoting variables or names from the code, use backticks (`) instead of single quote (').
+- Suggestions should address the new code added in the PR diff (lines starting with '+')
 {%- endif %}

 {%- if extra_instructions %}

+
 Extra instructions from the user:
 ======
 {{ extra_instructions }}
@ -55,9 +70,25 @@ class SubPR(BaseModel):
    title: str = Field(description="Short and concise title for an independent and meaningful sub-PR, composed only from the relevant files")
 {%- endif %}

+class KeyIssuesComponentLink(BaseModel):
+    relevant_file: str = Field(description="The full file path of the relevant file")
+    issue_header: str = Field(description="one or two word title for the the issue. For example: 'Possible Bug', 'Performance Issue', 'Code Smell', etc.")
+    issue_content: str = Field(description="a short and concise description of the issue that needs to be reviewed")
+    start_line: int = Field(description="the start line that corresponds to this issue in the relevant file")
+    end_line: int = Field(description="the end line that corresponds to this issue in the relevant file")
+{%- if extra_issue_links %}
+    referenced_variables: List[Refs] = Field(description="a list of relevant variables or names that appear in the 'issue_content' output. For each variable, output is name, and the line number where it appears in the relevant file")
+{% endif %}
+
+{%- if extra_issue_links %}
+class Refs(BaseModel):
+    variable_name: str = Field(description="the name of a variable or name that appears in the relevant 'issue_content' output.")
+    relevant_line: int = Field(description="the line number where the variable or name appears in the relevant file")
+{%- endif %}
+
 class Review(BaseModel):
 {%- if require_estimate_effort_to_review %}
-    estimated_effort_to_review_[1-5]: str = Field(description="Estimate, on a scale of 1-5 (inclusive), the time and effort required to review this PR by an experienced and knowledgeable developer. 1 means short and easy review , 5 means long and hard review. Take into account the size, complexity, quality, and the needed changes of the PR code diff. Explain your answer in a short and concise manner.")
+    estimated_effort_to_review_[1-5]: int = Field(description="Estimate, on a scale of 1-5 (inclusive), the time and effort required to review this PR by an experienced and knowledgeable developer. 1 means short and easy review , 5 means long and hard review. Take into account the size, complexity, quality, and the needed changes of the PR code diff.")
 {%- endif %}
 {%- if require_score %}
    score: str = Field(description="Rate this PR on a scale of 0-100 (inclusive), where 0 means the worst possible PR code, and 100 means PR code of the highest quality, without any bugs or performance issues, that is ready to be merged immediately and run in production at scale.")
@ -68,16 +99,18 @@ class Review(BaseModel):
 {%- if question_str %}
    insights_from_user_answers: str = Field(description="shortly summarize the insights you gained from the user's answers to the questions")
 {%- endif %}
-    possible_issues: str = Field(description="Does this PR code introduce clear issues, bugs, or major performance concerns? If there are no apparent issues, respond with 'No'. If there are any issues, describe them briefly. Use bullet points if more than one issue. Be specific, and provide examples if possible. Start each bullet point with a short specific header, such as: "- Possible Bug: ...", etc.")
-    security_concerns: str = Field(description="does this PR code introduce possible vulnerabilities such as exposure of sensitive information (e.g., API keys, secrets, passwords), or security concerns like SQL injection, XSS, CSRF, and others ? Answer 'No' if there are no possible issues. If there are security concerns or issues, start your answer with a short header, such as: 'Sensitive information exposure: ...', 'SQL injection: ...' etc. Explain your answer. Be specific and give examples if possible")
+    key_issues_to_review: List[KeyIssuesComponentLink] = Field("A list of bugs, issue or major performance concerns introduced in this PR, which the PR reviewer should further investigate")
+{%- if require_security_review %}
+    security_concerns: str = Field(description="Does this PR code introduce possible vulnerabilities such as exposure of sensitive information (e.g., API keys, secrets, passwords), or security concerns like SQL injection, XSS, CSRF, and others ? Answer 'No' (without explaining why) if there are no possible issues. If there are security concerns or issues, start your answer with a short header, such as: 'Sensitive information exposure: ...', 'SQL injection: ...' etc. Explain your answer. Be specific and give examples if possible")
+{%- endif %}
 {%- if require_can_be_split_review %}
-    can_be_split: List[SubPR] = Field(min_items=0, max_items=3, description="Can this PR, which contains {{ num_pr_files }} changed files in total, be divided into smaller sub-PRs with distinct tasks that can be reviewed and merged independently, regardless of the order ? Make sure that the sub-PRs are indeed independent, with no code dependencies between them, and that each sub-PR represent a meaningfull independent task. Output an empty list if the PR code does not needd to be split.")
+    can_be_split: List[SubPR] = Field(min_items=0, max_items=3, description="Can this PR, which contains {{ num_pr_files }} changed files in total, be divided into smaller sub-PRs with distinct tasks that can be reviewed and merged independently, regardless of the order ? Make sure that the sub-PRs are indeed independent, with no code dependencies between them, and that each sub-PR represent a meaningful independent task. Output an empty list if the PR code does not need to be split.")
 {%- endif %}
 {%- if num_code_suggestions > 0 %}

 class CodeSuggestion(BaseModel):
-    relevant_file: str = Field(description="the relevant file full path")
-    language: str = Field(description="the language of the relevant file")
+    relevant_file: str = Field(description="The full file path of the relevant file")
+    language: str = Field(description="The programming language of the relevant file")
    suggestion: str = Field(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.")
    relevant_line: str = Field(description="a single code line taken from the relevant file, to which the suggestion applies. The code line should start with a '+'. Make sure to output the line exactly as it appears in the relevant file")
 {%- endif %}
@ -88,6 +121,7 @@ class PRReview(BaseModel):
    code_feedback: List[CodeSuggestion]
 {%- else %}

+
 class PRReview(BaseModel):
    review: Review
 {%- endif %}
@ -99,27 +133,42 @@ Example output:
 review:
 {%- if require_estimate_effort_to_review %}
  estimated_effort_to_review_[1-5]: |
-    3, because ...
+    3
 {%- endif %}
 {%- if require_score %}
  score: 89
 {%- endif %}
  relevant_tests: |
    No
-  possible_issues: |
-    No
+  key_issues_to_review:
+    - relevant_file: |
+        directory/xxx.py
+      issue_header: |
+        Possible Bug
+      issue_content: |
+        ...
+      start_line: 12
+      end_line: 14
+{%- if extra_issue_links %}
+      referenced_variables:
+      - variable_name: |
+          ...
+        relevant_line: 13
+{%- endif %}
+    - ...
  security_concerns: |
    No
 {%- if require_can_be_split_review %}
-    can_be_split: |
+  can_be_split:
  - relevant_files:
    - ...
    - ...
    title: ...
  - ...
 {%- endif %}
+
 {%- if num_code_suggestions > 0 %}
-code_feedback
+code_feedback:
 - relevant_file: |
    directory/xxx.py
  language: |
@ -134,7 +183,7 @@ code_feedback
 Answer should be a valid YAML, and nothing else. Each YAML output MUST be after a newline, with proper indent, and block scalar indicator ('|')
 """

-user="""PR Info:
+user="""--PR Info--

 Title: '{{title}}'

@ -142,7 +191,7 @@ Branch: '{{branch}}'

 {%- if description %}

-Description:
+PR Description:
 ======
 {{ description|trim }}
 ======
@ -163,7 +212,7 @@ User answers:
 {%- endif %}


-The PR Diff:
+The PR code diff:
 ======
 {{ diff|trim }}
 ======
--- a/pr_agent/tools/pr_add_docs.py
+++ b/pr_agent/tools/pr_add_docs.py
@ -71,10 +71,6 @@ 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,
@ -93,8 +89,8 @@ class PRAddDocs:
        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)
+        response, finish_reason = await self.ai_handler.chat_completion(
+            model=model, temperature=get_settings().config.temperature, system=system_prompt, user=user_prompt)

        return response

--- a/pr_agent/tools/pr_code_suggestions.py
+++ b/pr_agent/tools/pr_code_suggestions.py
@ -9,20 +9,23 @@ from pr_agent.algo.ai_handlers.base_ai_handler import BaseAiHandler
 from pr_agent.algo.ai_handlers.litellm_ai_handler import LiteLLMAIHandler
 from pr_agent.algo.pr_processing import get_pr_diff, get_pr_multi_diffs, retry_with_fallback_models
 from pr_agent.algo.token_handler import TokenHandler
-from pr_agent.algo.utils import load_yaml, replace_code_tags, ModelType
+from pr_agent.algo.utils import load_yaml, replace_code_tags, ModelType, show_relevant_configurations
 from pr_agent.config_loader import get_settings
-from pr_agent.git_providers import get_git_provider
+from pr_agent.git_providers import get_git_provider, get_git_provider_with_context, GithubProvider, GitLabProvider, \
+    AzureDevopsProvider
 from pr_agent.git_providers.git_provider import get_main_pr_language
 from pr_agent.log import get_logger
 from pr_agent.servers.help import HelpMessage
 from pr_agent.tools.pr_description import insert_br_after_x_chars
 import difflib
+import re
+

 class PRCodeSuggestions:
    def __init__(self, pr_url: str, cli_mode=False, args: list = None,
                 ai_handler: partial[BaseAiHandler,] = LiteLLMAIHandler):

-        self.git_provider = get_git_provider()(pr_url)
+        self.git_provider = get_git_provider_with_context(pr_url)
        self.main_language = get_main_pr_language(
            self.git_provider.get_languages(), self.git_provider.get_files()
        )
@ -32,9 +35,9 @@ class PRCodeSuggestions:
            MAX_CONTEXT_TOKENS_IMPROVE = get_settings().pr_code_suggestions.max_context_tokens
            if get_settings().config.max_model_tokens > MAX_CONTEXT_TOKENS_IMPROVE:
                get_logger().info(f"Setting max_model_tokens to {MAX_CONTEXT_TOKENS_IMPROVE} for PR improve")
+                get_settings().config.max_model_tokens_original = get_settings().config.max_model_tokens
                get_settings().config.max_model_tokens = MAX_CONTEXT_TOKENS_IMPROVE

-
        # extended mode
        try:
            self.is_extended = self._get_is_extended(args or [])
@ -49,6 +52,7 @@ class PRCodeSuggestions:
        self.ai_handler.main_pr_language = self.main_language
        self.patches_diff = None
        self.prediction = None
+        self.pr_url = pr_url
        self.cli_mode = cli_mode
        self.vars = {
            "title": self.git_provider.pr.title,
@ -57,13 +61,19 @@ class PRCodeSuggestions:
            "language": self.main_language,
            "diff": "",  # empty diff for initial calculation
            "num_code_suggestions": num_code_suggestions,
-            "summarize_mode": get_settings().pr_code_suggestions.summarize,
            "extra_instructions": get_settings().pr_code_suggestions.extra_instructions,
            "commit_messages_str": self.git_provider.get_commit_messages(),
+            "relevant_best_practices": "",
        }
+        if 'claude' in get_settings().config.model:
+            # prompt for Claude, with minor adjustments
+            self.pr_code_suggestions_prompt_system = get_settings().pr_code_suggestions_prompt_claude.system
+        else:
+            self.pr_code_suggestions_prompt_system = get_settings().pr_code_suggestions_prompt.system
+
        self.token_handler = TokenHandler(self.git_provider.pr,
                                          self.vars,
-                                          get_settings().pr_code_suggestions_prompt.system,
+                                          self.pr_code_suggestions_prompt_system,
                                          get_settings().pr_code_suggestions_prompt.user)

        self.progress = f"## Generating PR code suggestions\n\n"
@ -72,25 +82,32 @@ class PRCodeSuggestions:

    async def run(self):
        try:
+            if not self.git_provider.get_files():
+                get_logger().info(f"PR has no files: {self.pr_url}, skipping code suggestions")
+                return None
+
            get_logger().info('Generating code suggestions for PR...')
            relevant_configs = {'pr_code_suggestions': dict(get_settings().pr_code_suggestions),
                                'config': dict(get_settings().config)}
            get_logger().debug("Relevant configs", artifacts=relevant_configs)
-            if get_settings().config.publish_output and get_settings().config.publish_output_progress:
+            if (get_settings().config.publish_output and get_settings().config.publish_output_progress and
+                    not get_settings().config.get('is_auto_command', False)):
                if self.git_provider.is_supported("gfm_markdown"):
                    self.progress_response = self.git_provider.publish_comment(self.progress)
                else:
                    self.git_provider.publish_comment("Preparing suggestions...", is_temporary=True)

            if not self.is_extended:
-                await retry_with_fallback_models(self._prepare_prediction, ModelType.TURBO)
-                data = self._prepare_pr_code_suggestions()
+                data = await retry_with_fallback_models(self._prepare_prediction)
            else:
-                data = await retry_with_fallback_models(self._prepare_prediction_extended, ModelType.TURBO)
+                data = await retry_with_fallback_models(self._prepare_prediction_extended)
+            if not data:
+                data = {"code_suggestions": []}

-            if (not data) or (not 'code_suggestions' in data) or (not data['code_suggestions']):
-                get_logger().error('No code suggestions found for PR.')
-                pr_body = "## PR Code Suggestions\n\nNo code suggestions found for PR."
+            if (data is None or 'code_suggestions' not in data or not data['code_suggestions']
+                    and get_settings().config.publish_output):
+                get_logger().warning('No code suggestions found for the PR.')
+                pr_body = "## PR Code Suggestions ✨\n\nNo code suggestions found for the PR."
                get_logger().debug(f"PR output", artifact=pr_body)
                if self.progress_response:
                    self.git_provider.edit_comment(self.progress_response, body=pr_body)
@ -105,29 +122,40 @@ class PRCodeSuggestions:

            if get_settings().config.publish_output:
                self.git_provider.remove_initial_comment()
-                if get_settings().pr_code_suggestions.summarize and self.git_provider.is_supported("gfm_markdown"):
+                if ((not get_settings().pr_code_suggestions.commitable_code_suggestions) and
+                        self.git_provider.is_supported("gfm_markdown")):

                    # generate summarized suggestions
                    pr_body = self.generate_summarized_suggestions(data)
                    get_logger().debug(f"PR output", artifact=pr_body)

+                    # require self-review
+                    if get_settings().pr_code_suggestions.demand_code_suggestions_self_review:
+                        text = get_settings().pr_code_suggestions.code_suggestions_self_review_text
+                        pr_body += f"\n\n- [ ]  {text}"
+                        if get_settings().pr_code_suggestions.approve_pr_on_self_review:
+                            pr_body += ' <!-- approve pr self-review -->'
+
                    # add usage guide
                    if get_settings().pr_code_suggestions.enable_help_text:
-                        pr_body += "<hr>\n\n<details> <summary><strong>✨ Improve tool usage guide:</strong></summary><hr> \n\n"
+                        pr_body += "<hr>\n\n<details> <summary><strong>💡 Tool usage guide:</strong></summary><hr> \n\n"
                        pr_body += HelpMessage.get_improve_usage_guide()
                        pr_body += "\n</details>\n"

+                    # Output the relevant configurations if enabled
+                    if get_settings().get('config', {}).get('output_relevant_configurations', False):
+                        pr_body += show_relevant_configurations(relevant_section='pr_code_suggestions')
+
                    if get_settings().pr_code_suggestions.persistent_comment:
                        final_update_message = False
-                        self.git_provider.publish_persistent_comment(pr_body,
-                                                                     initial_header="## PR Code Suggestions",
+                        self.publish_persistent_comment_with_history(pr_body,
+                                                                     initial_header="## PR Code Suggestions ✨",
                                                                     update_header=True,
                                                                     name="suggestions",
-                                                                     final_update_message=final_update_message, )
-                        if self.progress_response:
-                            self.progress_response.delete()
+                                                                     final_update_message=final_update_message,
+                                                                     max_previous_comments=get_settings().pr_code_suggestions.max_history_len,
+                                                                     progress_response=self.progress_response)
                    else:
-
                        if self.progress_response:
                            self.git_provider.edit_comment(self.progress_response, body=pr_body)
                        else:
@ -137,8 +165,11 @@ class PRCodeSuggestions:
                    self.push_inline_code_suggestions(data)
                    if self.progress_response:
                        self.progress_response.delete()
+            else:
+                get_logger().info('Code suggestions generated for PR, but not published since publish_output is False.')
        except Exception as e:
            get_logger().error(f"Failed to generate code suggestions for PR, error: {e}")
+            if get_settings().config.publish_output:
                if self.progress_response:
                    self.progress_response.delete()
                else:
@ -148,30 +179,173 @@ class PRCodeSuggestions:
                    except Exception as e:
                        pass

-    async def _prepare_prediction(self, model: str):
+    def publish_persistent_comment_with_history(self, pr_comment: str,
+                                                initial_header: str,
+                                                update_header: bool = True,
+                                                name='review',
+                                                final_update_message=True,
+                                                max_previous_comments=4,
+                                                progress_response=None):
+
+        if isinstance(self.git_provider, AzureDevopsProvider): # get_latest_commit_url is not supported yet
+            if progress_response:
+                self.git_provider.edit_comment(progress_response, pr_comment)
+            else:
+                self.git_provider.publish_comment(pr_comment)
+            return
+
+        history_header = f"#### Previous suggestions\n"
+        last_commit_num = self.git_provider.get_latest_commit_url().split('/')[-1][:7]
+        latest_suggestion_header = f"Latest suggestions up to {last_commit_num}"
+        latest_commit_html_comment = f"<!-- {last_commit_num} -->"
+        found_comment = None
+
+        if max_previous_comments > 0:
+            try:
+                prev_comments = list(self.git_provider.get_issue_comments())
+                for comment in prev_comments:
+                    if comment.body.startswith(initial_header):
+                        prev_suggestions = comment.body
+                        found_comment = comment
+                        comment_url = self.git_provider.get_comment_url(comment)
+
+                        if history_header.strip() not in comment.body:
+                            # no history section
+                            # extract everything between <table> and </table> in comment.body including <table> and </table>
+                            table_index = comment.body.find("<table>")
+                            if table_index == -1:
+                                self.git_provider.edit_comment(comment, pr_comment)
+                                continue
+                            # find http link from comment.body[:table_index]
+                            up_to_commit_txt = self.extract_link(comment.body[:table_index])
+                            prev_suggestion_table = comment.body[
+                                                    table_index:comment.body.rfind("</table>") + len("</table>")]
+
+                            tick = "✅ " if "✅" in prev_suggestion_table else ""
+                            # surround with details tag
+                            prev_suggestion_table = f"<details><summary>{tick}{name.capitalize()}{up_to_commit_txt}</summary>\n<br>{prev_suggestion_table}\n\n</details>"
+
+                            new_suggestion_table = pr_comment.replace(initial_header, "").strip()
+
+                            pr_comment_updated = f"{initial_header}\n{latest_commit_html_comment}\n\n"
+                            pr_comment_updated += f"{latest_suggestion_header}\n{new_suggestion_table}\n\n___\n\n"
+                            pr_comment_updated += f"{history_header}{prev_suggestion_table}\n"
+                        else:
+                            # get the text of the previous suggestions until the latest commit
+                            sections = prev_suggestions.split(history_header.strip())
+                            latest_table = sections[0].strip()
+                            prev_suggestion_table = sections[1].replace(history_header, "").strip()
+
+                            # get text after the latest_suggestion_header in comment.body
+                            table_ind = latest_table.find("<table>")
+                            up_to_commit_txt = self.extract_link(latest_table[:table_ind])
+
+                            latest_table = latest_table[table_ind:latest_table.rfind("</table>") + len("</table>")]
+                            # enforce max_previous_comments
+                            count = prev_suggestions.count(f"\n<details><summary>{name.capitalize()}")
+                            count += prev_suggestions.count(f"\n<details><summary>✅ {name.capitalize()}")
+                            if count >= max_previous_comments:
+                                # remove the oldest suggestion
+                                prev_suggestion_table = prev_suggestion_table[:prev_suggestion_table.rfind(
+                                    f"<details><summary>{name.capitalize()} up to commit")]
+
+                            tick = "✅ " if "✅" in latest_table else ""
+                            # Add to the prev_suggestions section
+                            last_prev_table = f"\n<details><summary>{tick}{name.capitalize()}{up_to_commit_txt}</summary>\n<br>{latest_table}\n\n</details>"
+                            prev_suggestion_table = last_prev_table + "\n" + prev_suggestion_table
+
+                            new_suggestion_table = pr_comment.replace(initial_header, "").strip()
+
+                            pr_comment_updated = f"{initial_header}\n"
+                            pr_comment_updated += f"{latest_commit_html_comment}\n\n"
+                            pr_comment_updated += f"{latest_suggestion_header}\n\n{new_suggestion_table}\n\n"
+                            pr_comment_updated += "___\n\n"
+                            pr_comment_updated += f"{history_header}\n"
+                            pr_comment_updated += f"{prev_suggestion_table}\n"
+
+                        get_logger().info(f"Persistent mode - updating comment {comment_url} to latest {name} message")
+                        if progress_response:  # publish to 'progress_response' comment, because it refreshes immediately
+                            self.git_provider.edit_comment(progress_response, pr_comment_updated)
+                            self.git_provider.remove_comment(comment)
+                        else:
+                            self.git_provider.edit_comment(comment, pr_comment_updated)
+                        return
+            except Exception as e:
+                get_logger().exception(f"Failed to update persistent review, error: {e}")
+                pass
+
+        # if we are here, we did not find a previous comment to update
+        body = pr_comment.replace(initial_header, "").strip()
+        pr_comment = f"{initial_header}\n\n{latest_commit_html_comment}\n\n{body}\n\n"
+        if progress_response:
+            self.git_provider.edit_comment(progress_response, pr_comment)
+        else:
+            self.git_provider.publish_comment(pr_comment)
+
+    def extract_link(self, s):
+        r = re.compile(r"<!--.*?-->")
+        match = r.search(s)
+
+        up_to_commit_txt = ""
+        if match:
+            up_to_commit_txt = f" up to commit {match.group(0)[4:-3].strip()}"
+        return up_to_commit_txt
+
+    async def _prepare_prediction(self, model: str) -> dict:
        self.patches_diff = get_pr_diff(self.git_provider,
                                        self.token_handler,
                                        model,
                                        add_line_numbers_to_hunks=True,
-                                        disable_extra_lines=True)
+                                        disable_extra_lines=False)

        if self.patches_diff:
            get_logger().debug(f"PR diff", artifact=self.patches_diff)
            self.prediction = await self._get_prediction(model, self.patches_diff)
        else:
-            get_logger().error(f"Error getting PR diff")
+            get_logger().warning(f"Empty PR diff")
            self.prediction = None

-    async def _get_prediction(self, model: str, patches_diff: str):
+        data = self.prediction
+        return data
+
+    async def _get_prediction(self, model: str, patches_diff: str) -> dict:
        variables = copy.deepcopy(self.vars)
        variables["diff"] = patches_diff  # update diff
        environment = Environment(undefined=StrictUndefined)
-        system_prompt = environment.from_string(get_settings().pr_code_suggestions_prompt.system).render(variables)
+        system_prompt = environment.from_string(self.pr_code_suggestions_prompt_system).render(variables)
        user_prompt = environment.from_string(get_settings().pr_code_suggestions_prompt.user).render(variables)
-        response, finish_reason = await self.ai_handler.chat_completion(model=model, temperature=0.2,
-                                                                        system=system_prompt, user=user_prompt)
+        response, finish_reason = await self.ai_handler.chat_completion(
+            model=model, temperature=get_settings().config.temperature, system=system_prompt, user=user_prompt)

-        return response
+        # load suggestions from the AI response
+        data = self._prepare_pr_code_suggestions(response)
+
+        # self-reflect on suggestions
+        if get_settings().pr_code_suggestions.self_reflect_on_suggestions:
+            model_turbo = get_settings().config.model_turbo  # use turbo model for self-reflection, since it is an easier task
+            response_reflect = await self.self_reflect_on_suggestions(data["code_suggestions"],
+                                                                      patches_diff, model=model_turbo)
+            if response_reflect:
+                response_reflect_yaml = load_yaml(response_reflect)
+                code_suggestions_feedback = response_reflect_yaml["code_suggestions"]
+                if len(code_suggestions_feedback) == len(data["code_suggestions"]):
+                    for i, suggestion in enumerate(data["code_suggestions"]):
+                        try:
+                            suggestion["score"] = code_suggestions_feedback[i]["suggestion_score"]
+                            suggestion["score_why"] = code_suggestions_feedback[i]["why"]
+                        except Exception as e:  #
+                            get_logger().error(f"Error processing suggestion score {i}",
+                                               artifact={"suggestion": suggestion,
+                                                         "code_suggestions_feedback": code_suggestions_feedback[i]})
+                            suggestion["score"] = 7
+                            suggestion["score_why"] = ""
+            else:
+                # get_logger().error(f"Could not self-reflect on suggestions. using default score 7")
+                for i, suggestion in enumerate(data["code_suggestions"]):
+                    suggestion["score"] = 7
+                    suggestion["score_why"] = ""
+
+        return data

    @staticmethod
    def _truncate_if_needed(suggestion):
@ -185,40 +359,54 @@ class PRCodeSuggestions:
                                  f"characters to {max_code_suggestion_length} characters")
        return suggestion

-    def _prepare_pr_code_suggestions(self) -> Dict:
-        review = self.prediction.strip()
-        data = load_yaml(review,
-                         keys_fix_yaml=["relevant_file", "suggestion_content", "existing_code", "improved_code"])
+    def _prepare_pr_code_suggestions(self, predictions: str) -> Dict:
+        data = load_yaml(predictions.strip(),
+                         keys_fix_yaml=["relevant_file", "suggestion_content", "existing_code", "improved_code"],
+                         first_key="code_suggestions", last_key="label")
        if isinstance(data, list):
            data = {'code_suggestions': data}

-        # remove invalid suggestions
+        # remove or edit invalid suggestions
        suggestion_list = []
        one_sentence_summary_list = []
        for i, suggestion in enumerate(data['code_suggestions']):
            try:
-                if get_settings().pr_code_suggestions.summarize:
-                    if not suggestion or 'one_sentence_summary' not in suggestion or 'label' not in suggestion or 'relevant_file' not in suggestion:
-                        get_logger().debug(f"Skipping suggestion {i + 1}, because it is invalid: {suggestion}")
+                needed_keys = ['one_sentence_summary', 'label', 'relevant_file', 'relevant_lines_start',
+                               'relevant_lines_end']
+                is_valid_keys = True
+                for key in needed_keys:
+                    if key not in suggestion:
+                        is_valid_keys = False
+                        get_logger().debug(
+                            f"Skipping suggestion {i + 1}, because it does not contain '{key}':\n'{suggestion}")
+                        break
+                if not is_valid_keys:
                    continue

                if suggestion['one_sentence_summary'] in one_sentence_summary_list:
                    get_logger().debug(f"Skipping suggestion {i + 1}, because it is a duplicate: {suggestion}")
                    continue

-                if 'const' in suggestion['suggestion_content'] and 'instead' in suggestion['suggestion_content'] and 'let' in suggestion['suggestion_content']:
-                    get_logger().debug(f"Skipping suggestion {i + 1}, because it uses 'const instead let': {suggestion}")
+                if 'const' in suggestion['suggestion_content'] and 'instead' in suggestion[
+                    'suggestion_content'] and 'let' in suggestion['suggestion_content']:
+                    get_logger().debug(
+                        f"Skipping suggestion {i + 1}, because it uses 'const instead let': {suggestion}")
                    continue

-                if ('existing_code' in suggestion) and ('improved_code' in suggestion) and (
-                        suggestion['existing_code'] != suggestion['improved_code']):
+                if ('existing_code' in suggestion) and ('improved_code' in suggestion):
+                    if suggestion['existing_code'] == suggestion['improved_code']:
+                        get_logger().debug(
+                            f"edited improved suggestion {i + 1}, because equal to existing code: {suggestion['existing_code']}")
+                        if get_settings().pr_code_suggestions.commitable_code_suggestions:
+                            suggestion['improved_code'] = ""  # we need 'existing_code' to locate the code in the PR
+                        else:
+                            suggestion['existing_code'] = ""
                    suggestion = self._truncate_if_needed(suggestion)
-                    if get_settings().pr_code_suggestions.summarize:
                    one_sentence_summary_list.append(suggestion['one_sentence_summary'])
                    suggestion_list.append(suggestion)
                else:
-                    get_logger().debug(
-                        f"Skipping suggestion {i + 1}, because existing code is equal to improved code {suggestion['existing_code']}")
+                    get_logger().info(
+                        f"Skipping suggestion {i + 1}, because it does not contain 'existing_code' or 'improved_code': {suggestion}")
            except Exception as e:
                get_logger().error(f"Error processing suggestion {i + 1}: {suggestion}, error: {e}")
        data['code_suggestions'] = suggestion_list
@ -231,12 +419,15 @@ class PRCodeSuggestions:
        if not data['code_suggestions']:
            get_logger().info('No suggestions found to improve this PR.')
            if self.progress_response:
-                return self.git_provider.edit_comment(self.progress_response, body='No suggestions found to improve this PR.')
+                return self.git_provider.edit_comment(self.progress_response,
+                                                      body='No suggestions found to improve this PR.')
            else:
                return self.git_provider.publish_comment('No suggestions found to improve this PR.')

        for d in data['code_suggestions']:
            try:
+                if get_settings().config.verbosity_level >= 2:
+                    get_logger().info(f"suggestion: {d}")
                relevant_file = d['relevant_file'].strip()
                relevant_lines_start = int(d['relevant_lines_start'])  # absolute position
                relevant_lines_end = int(d['relevant_lines_end'])
@ -247,10 +438,14 @@ class PRCodeSuggestions:
                if new_code_snippet:
                    new_code_snippet = self.dedent_code(relevant_file, relevant_lines_start, new_code_snippet)

+                if d.get('score'):
+                    body = f"**Suggestion:** {content} [{label}, importance: {d.get('score')}]\n```suggestion\n" + new_code_snippet + "\n```"
+                else:
                    body = f"**Suggestion:** {content} [{label}]\n```suggestion\n" + new_code_snippet + "\n```"
                code_suggestions.append({'body': body, 'relevant_file': relevant_file,
                                         'relevant_lines_start': relevant_lines_start,
-                                             'relevant_lines_end': relevant_lines_end})
+                                         'relevant_lines_end': relevant_lines_end,
+                                         'original_suggestion': d})
            except Exception:
                get_logger().info(f"Could not parse suggestion: {d}")

@ -267,8 +462,24 @@ class PRCodeSuggestions:
            original_initial_line = None
            for file in self.diff_files:
                if file.filename.strip() == relevant_file:
-                    if file.head_file:  # in bitbucket, head_file is empty. toDo: fix this
-                        original_initial_line = file.head_file.splitlines()[relevant_lines_start - 1]
+                    if file.head_file:
+                        file_lines = file.head_file.splitlines()
+                        if relevant_lines_start > len(file_lines):
+                            get_logger().warning(
+                                "Could not dedent code snippet, because relevant_lines_start is out of range",
+                                artifact={'filename': file.filename,
+                                          'file_content': file.head_file,
+                                          'relevant_lines_start': relevant_lines_start,
+                                          'new_code_snippet': new_code_snippet})
+                            return new_code_snippet
+                        else:
+                            original_initial_line = file_lines[relevant_lines_start - 1]
+                    else:
+                        get_logger().warning("Could not dedent code snippet, because head_file is missing",
+                                             artifact={'filename': file.filename,
+                                                       'relevant_lines_start': relevant_lines_start,
+                                                       'new_code_snippet': new_code_snippet})
+                        return new_code_snippet
                    break
            if original_initial_line:
                suggested_initial_line = new_code_snippet.splitlines()[0]
@ -278,7 +489,7 @@ class PRCodeSuggestions:
                if delta_spaces > 0:
                    new_code_snippet = textwrap.indent(new_code_snippet, delta_spaces * " ").rstrip('\n')
        except Exception as e:
-            get_logger().error(f"Could not dedent code snippet for file {relevant_file}, error: {e}")
+            get_logger().error(f"Error when dedenting code snippet for file {relevant_file}, error: {e}")

        return new_code_snippet

@ -288,7 +499,7 @@ class PRCodeSuggestions:
            get_logger().info("Extended mode is enabled by the `--extended` flag")
            return True
        if get_settings().pr_code_suggestions.auto_extended_mode:
-            get_logger().info("Extended mode is enabled automatically based on the configuration toggle")
+            # get_logger().info("Extended mode is enabled automatically based on the configuration toggle")
            return True
        return False

@ -296,7 +507,8 @@ class PRCodeSuggestions:
        self.patches_diff_list = get_pr_multi_diffs(self.git_provider, self.token_handler, model,
                                                    max_calls=get_settings().pr_code_suggestions.max_number_of_calls)
        if self.patches_diff_list:
-            get_logger().debug(f"PR diff", artifact=self.patches_diff_list)
+            get_logger().info(f"Number of PR chunk calls: {len(self.patches_diff_list)}")
+            get_logger().debug(f"PR diff:", artifact=self.patches_diff_list)

            # parallelize calls to AI:
            if get_settings().pr_code_suggestions.parallel_calls:
@ -309,17 +521,27 @@ class PRCodeSuggestions:
                    prediction = await self._get_prediction(model, patches_diff)
                    prediction_list.append(prediction)

-            data = {}
-            for prediction in prediction_list:
-                self.prediction = prediction
-                data_per_chunk = self._prepare_pr_code_suggestions()
-                if "code_suggestions" in data:
-                    data["code_suggestions"].extend(data_per_chunk["code_suggestions"])
+            data = {"code_suggestions": []}
+            for j, predictions in enumerate(prediction_list):  # each call adds an element to the list
+                if "code_suggestions" in predictions:
+                    score_threshold = max(1, int(get_settings().pr_code_suggestions.suggestions_score_threshold))
+                    for i, prediction in enumerate(predictions["code_suggestions"]):
+                        try:
+                            if get_settings().pr_code_suggestions.self_reflect_on_suggestions:
+                                score = int(prediction.get("score", 1))
+                                if score >= score_threshold:
+                                    data["code_suggestions"].append(prediction)
                                else:
-                    data.update(data_per_chunk)
+                                    get_logger().info(
+                                        f"Removing suggestions {i} from call {j}, because score is {score}, and score_threshold is {score_threshold}",
+                                        artifact=prediction)
+                            else:
+                                data["code_suggestions"].append(prediction)
+                        except Exception as e:
+                            get_logger().error(f"Error getting PR diff for suggestion {i} in call {j}, error: {e}")
            self.data = data
        else:
-            get_logger().error(f"Error getting PR diff")
+            get_logger().warning(f"Empty PR diff list")
            self.data = data = None
        return data

@ -382,7 +604,7 @@ class PRCodeSuggestions:

    def generate_summarized_suggestions(self, data: Dict) -> str:
        try:
-            pr_body = "## PR Code Suggestions\n\n"
+            pr_body = "## PR Code Suggestions ✨\n\n"

            if len(data.get('code_suggestions', [])) == 0:
                pr_body += "No suggestions found to improve this PR."
@ -394,13 +616,16 @@ class PRCodeSuggestions:
                for ext in extensions:
                    extension_to_language[ext] = language

-            pr_body = "## PR Code Suggestions\n\n"
+            pr_body = "## PR Code Suggestions ✨\n\n"

            pr_body += "<table>"
-            header = f"Suggestions"
-            delta = 76
+            header = f"Suggestion"
+            delta = 66
            header += "&nbsp; " * delta
-            pr_body += f"""<thead><tr><td>Category</td><td align=left>{header}</td></tr></thead>"""
+            if get_settings().pr_code_suggestions.self_reflect_on_suggestions:
+                pr_body += f"""<thead><tr><td>Category</td><td align=left>{header}</td><td align=center>Score</td></tr>"""
+            else:
+                pr_body += f"""<thead><tr><td>Category</td><td align=left>{header}</td></tr>"""
            pr_body += """<tbody>"""
            suggestions_labels = dict()
            # add all suggestions related to each label
@ -410,6 +635,15 @@ class PRCodeSuggestions:
                    suggestions_labels[label] = []
                suggestions_labels[label].append(suggestion)

+            # sort suggestions_labels by the suggestion with the highest score
+            if get_settings().pr_code_suggestions.self_reflect_on_suggestions:
+                suggestions_labels = dict(
+                    sorted(suggestions_labels.items(), key=lambda x: max([s['score'] for s in x[1]]), reverse=True))
+                # sort the suggestions inside each label group by score
+                for label, suggestions in suggestions_labels.items():
+                    suggestions_labels[label] = sorted(suggestions, key=lambda x: x['score'], reverse=True)
+
+            counter_suggestions = 0
            for label, suggestions in suggestions_labels.items():
                num_suggestions = len(suggestions)
                pr_body += f"""<tr><td rowspan={num_suggestions}><strong>{label.capitalize()}</strong></td>\n"""
@ -423,13 +657,17 @@ class PRCodeSuggestions:
                        range_str = f"[{relevant_lines_start}]"
                    else:
                        range_str = f"[{relevant_lines_start}-{relevant_lines_end}]"
+
+                    try:
                        code_snippet_link = self.git_provider.get_line_link(relevant_file, relevant_lines_start,
                                                                            relevant_lines_end)
+                    except:
+                        code_snippet_link = ""
                    # add html table for each suggestion

-                    suggestion_content = suggestion['suggestion_content'].rstrip().rstrip()
-
-                    suggestion_content = insert_br_after_x_chars(suggestion_content, 90)
+                    suggestion_content = suggestion['suggestion_content'].rstrip()
+                    CHAR_LIMIT_PER_LINE = 84
+                    suggestion_content = insert_br_after_x_chars(suggestion_content, CHAR_LIMIT_PER_LINE)
                    # pr_body += f"<tr><td><details><summary>{suggestion_content}</summary>"
                    existing_code = suggestion['existing_code'].rstrip() + "\n"
                    improved_code = suggestion['improved_code'].rstrip() + "\n"
@ -445,22 +683,36 @@ class PRCodeSuggestions:
                        pr_body += f"""<td>\n\n"""
                    else:
                        pr_body += f"""<tr><td>\n\n"""
-                    suggestion_summary = suggestion['one_sentence_summary'].strip()
+                    suggestion_summary = suggestion['one_sentence_summary'].strip().rstrip('.')
+                    if "'<" in suggestion_summary and ">'" in suggestion_summary:
+                        # escape the '<' and '>' characters, otherwise they are interpreted as html tags
+                        get_logger().info(f"Escaped suggestion summary: {suggestion_summary}")
+                        suggestion_summary = suggestion_summary.replace("'<", "`<")
+                        suggestion_summary = suggestion_summary.replace(">'", ">`")
                    if '`' in suggestion_summary:
                        suggestion_summary = replace_code_tags(suggestion_summary)
-                    # suggestion_summary = suggestion_summary + max((77-len(suggestion_summary)), 0)*"&nbsp;"
-                    pr_body += f"""\n\n<details><summary>{suggestion_summary}</summary>\n\n___\n\n"""

+                    pr_body += f"""\n\n<details><summary>{suggestion_summary}</summary>\n\n___\n\n"""
                    pr_body += f"""
 **{suggestion_content}**

 [{relevant_file} {range_str}]({code_snippet_link})

-{example_code}                   
+{example_code.rstrip()}                   
 """
+                    if get_settings().pr_code_suggestions.self_reflect_on_suggestions:
+                        pr_body += f"<details><summary>Suggestion importance[1-10]: {suggestion['score']}</summary>\n\n"
+                        pr_body += f"Why: {suggestion['score_why']}\n\n"
                        pr_body += f"</details>"
-                    pr_body += f"</td></tr>"

+                    pr_body += f"</details>"
+
+                    # # add another column for 'score'
+                    if get_settings().pr_code_suggestions.self_reflect_on_suggestions:
+                        pr_body += f"</td><td align=center>{suggestion['score']}\n\n"
+
+                    pr_body += f"</td></tr>"
+                    counter_suggestions += 1

                # pr_body += "</details>"
                # pr_body += """</td></tr>"""
@ -469,3 +721,32 @@ class PRCodeSuggestions:
        except Exception as e:
            get_logger().info(f"Failed to publish summarized code suggestions, error: {e}")
            return ""
+
+    async def self_reflect_on_suggestions(self, suggestion_list: List, patches_diff: str, model: str) -> str:
+        if not suggestion_list:
+            return ""
+
+        try:
+            suggestion_str = ""
+            for i, suggestion in enumerate(suggestion_list):
+                suggestion_str += f"suggestion {i + 1}: " + str(suggestion) + '\n\n'
+
+            variables = {'suggestion_list': suggestion_list,
+                         'suggestion_str': suggestion_str,
+                         "diff": patches_diff,
+                         'num_code_suggestions': len(suggestion_list)}
+            environment = Environment(undefined=StrictUndefined)
+            system_prompt_reflect = environment.from_string(
+                get_settings().pr_code_suggestions_reflect_prompt.system).render(
+                variables)
+            user_prompt_reflect = environment.from_string(
+                get_settings().pr_code_suggestions_reflect_prompt.user).render(variables)
+            with get_logger().contextualize(command="self_reflect_on_suggestions"):
+                response_reflect, finish_reason_reflect = await self.ai_handler.chat_completion(model=model,
+                                                                                                system=system_prompt_reflect,
+                                                                                                user=user_prompt_reflect)
+        except Exception as e:
+            get_logger().info(f"Could not reflect on suggestions, error: {e}")
+            return ""
+        return response_reflect
+
--- a/pr_agent/tools/pr_description.py
+++ b/pr_agent/tools/pr_description.py
@ -1,17 +1,22 @@
+import asyncio
 import copy
 import re
 from functools import partial
 from typing import List, Tuple

+import yaml
 from jinja2 import Environment, StrictUndefined

 from pr_agent.algo.ai_handlers.base_ai_handler import BaseAiHandler
 from pr_agent.algo.ai_handlers.litellm_ai_handler import LiteLLMAIHandler
-from pr_agent.algo.pr_processing import get_pr_diff, retry_with_fallback_models
+from pr_agent.algo.pr_processing import get_pr_diff, retry_with_fallback_models, get_pr_diff_multiple_patchs, \
+    OUTPUT_BUFFER_TOKENS_HARD_THRESHOLD
 from pr_agent.algo.token_handler import TokenHandler
-from pr_agent.algo.utils import load_yaml, set_custom_labels, get_user_labels, ModelType
+from pr_agent.algo.utils import set_custom_labels
+from pr_agent.algo.utils import load_yaml, get_user_labels, ModelType, show_relevant_configurations, get_max_tokens, \
+    clip_tokens
 from pr_agent.config_loader import get_settings
-from pr_agent.git_providers import get_git_provider
+from pr_agent.git_providers import get_git_provider, GithubProvider, get_git_provider_with_context
 from pr_agent.git_providers.git_provider import get_main_pr_language
 from pr_agent.log import get_logger
 from pr_agent.servers.help import HelpMessage
@ -28,7 +33,7 @@ class PRDescription:
            args (list, optional): List of arguments passed to the PRDescription class. Defaults to None.
        """
        # Initialize the git provider and main PR language
-        self.git_provider = get_git_provider()(pr_url)
+        self.git_provider = get_git_provider_with_context(pr_url)
        self.main_pr_language = get_main_pr_language(
            self.git_provider.get_languages(), self.git_provider.get_files()
        )
@ -43,7 +48,6 @@ class PRDescription:
        self.ai_handler = ai_handler()
        self.ai_handler.main_pr_language = self.main_pr_language

-    
        # Initialize the variables dictionary
        self.vars = {
            "title": self.git_provider.pr.title,
@ -57,6 +61,7 @@ class PRDescription:
            "custom_labels_class": "",  # will be filled if necessary in 'set_custom_labels' function
            "enable_semantic_files_types": get_settings().pr_description.enable_semantic_files_types,
        }
+
        self.user_description = self.git_provider.get_user_description()

        # Initialize the token handler
@ -79,15 +84,15 @@ class PRDescription:
            relevant_configs = {'pr_description': dict(get_settings().pr_description),
                                'config': dict(get_settings().config)}
            get_logger().debug("Relevant configs", artifacts=relevant_configs)
-            if get_settings().config.publish_output:
+            if get_settings().config.publish_output and not get_settings().config.get('is_auto_command', False):
                self.git_provider.publish_comment("Preparing PR description...", is_temporary=True)

-            await retry_with_fallback_models(self._prepare_prediction, ModelType.TURBO) # turbo model because larger context
+            await retry_with_fallback_models(self._prepare_prediction, ModelType.TURBO)

            if self.prediction:
                self._prepare_data()
            else:
-                get_logger().error(f"Error getting AI prediction {self.pr_id}")
+                get_logger().warning(f"Empty prediction, PR: {self.pr_id}")
                self.git_provider.remove_initial_comment()
                return None

@ -112,10 +117,14 @@ class PRDescription:
                pr_body += "<hr>\n\n<details> <summary><strong>✨ Describe tool usage guide:</strong></summary><hr> \n\n"
                pr_body += HelpMessage.get_describe_usage_guide()
                pr_body += "\n</details>\n"
-            elif get_settings().pr_description.enable_help_comment:
-                pr_body += "\n\n___\n\n> ✨ **PR-Agent usage**:"
+            elif self.git_provider.is_supported("gfm_markdown") and get_settings().pr_description.enable_help_comment:
+                pr_body += "\n\n___\n\n> 💡 **PR-Agent usage**:"
                pr_body += "\n>Comment `/help` on the PR to get a list of all available PR-Agent tools and their descriptions\n\n"

+            # Output the relevant configurations if enabled
+            if get_settings().get('config', {}).get('output_relevant_configurations', False):
+                pr_body += show_relevant_configurations(relevant_section='pr_description')
+
            if get_settings().config.publish_output:
                # publish labels
                if get_settings().pr_description.publish_labels and self.git_provider.is_supported("get_labels"):
@ -158,38 +167,193 @@ class PRDescription:

    async def _prepare_prediction(self, model: str) -> None:
        if get_settings().pr_description.use_description_markers and 'pr_agent:' not in self.user_description:
+            get_logger().info(
+                "Markers were enabled, but user description does not contain markers. skipping AI prediction")
            return None

-        self.patches_diff = get_pr_diff(self.git_provider, self.token_handler, model)
-        if self.patches_diff:
+        large_pr_handling = get_settings().pr_description.enable_large_pr_handling and "pr_description_only_files_prompts" in get_settings()
+        output = get_pr_diff(self.git_provider, self.token_handler, model, large_pr_handling=large_pr_handling,
+                             return_remaining_files=True)
+        if isinstance(output, tuple):
+            patches_diff, remaining_files_list = output
+        else:
+            patches_diff = output
+            remaining_files_list = []
+        if not large_pr_handling or patches_diff:
+            self.patches_diff = patches_diff
+            if patches_diff:
                get_logger().debug(f"PR diff", artifact=self.patches_diff)
-            self.prediction = await self._get_prediction(model)
+                self.prediction = await self._get_prediction(model, patches_diff, prompt="pr_description_prompt")
+                if (remaining_files_list and 'pr_files' in self.prediction and 'label:' in self.prediction and
+                        get_settings().pr_description.mention_extra_files):
+                    get_logger().debug(f"Extending additional files, {len(remaining_files_list)} files")
+                    self.prediction = await self.extend_additional_files(remaining_files_list)
            else:
                get_logger().error(f"Error getting PR diff {self.pr_id}")
                self.prediction = None
+        else:
+            # get the diff in multiple patches, with the token handler only for the files prompt
+            get_logger().debug('large_pr_handling for describe')
+            token_handler_only_files_prompt = TokenHandler(
+                self.git_provider.pr,
+                self.vars,
+                get_settings().pr_description_only_files_prompts.system,
+                get_settings().pr_description_only_files_prompts.user,
+            )
+            (patches_compressed_list, total_tokens_list, deleted_files_list, remaining_files_list, file_dict,
+             files_in_patches_list) = get_pr_diff_multiple_patchs(
+                self.git_provider, token_handler_only_files_prompt, model)

-    async def _get_prediction(self, model: str) -> str:
+            # get the files prediction for each patch
+            if not get_settings().pr_description.async_ai_calls:
+                results = []
+                for i, patches in enumerate(patches_compressed_list):  # sync calls
+                    patches_diff = "\n".join(patches)
+                    get_logger().debug(f"PR diff number {i + 1} for describe files")
+                    prediction_files = await self._get_prediction(model, patches_diff,
+                                                                  prompt="pr_description_only_files_prompts")
+                    results.append(prediction_files)
+            else:  # async calls
+                tasks = []
+                for i, patches in enumerate(patches_compressed_list):
+                    if patches:
+                        patches_diff = "\n".join(patches)
+                        get_logger().debug(f"PR diff number {i + 1} for describe files")
+                        task = asyncio.create_task(
+                            self._get_prediction(model, patches_diff, prompt="pr_description_only_files_prompts"))
+                        tasks.append(task)
+                # Wait for all tasks to complete
+                results = await asyncio.gather(*tasks)
+            file_description_str_list = []
+            for i, result in enumerate(results):
+                prediction_files = result.strip().removeprefix('```yaml').strip('`').strip()
+                if load_yaml(prediction_files) and prediction_files.startswith('pr_files'):
+                    prediction_files = prediction_files.removeprefix('pr_files:').strip()
+                    file_description_str_list.append(prediction_files)
+                else:
+                    get_logger().debug(f"failed to generate predictions in iteration {i + 1} for describe files")
+
+            # generate files_walkthrough string, with proper token handling
+            token_handler_only_description_prompt = TokenHandler(
+                self.git_provider.pr,
+                self.vars,
+                get_settings().pr_description_only_description_prompts.system,
+                get_settings().pr_description_only_description_prompts.user)
+            files_walkthrough = "\n".join(file_description_str_list)
+            files_walkthrough_prompt = copy.deepcopy(files_walkthrough)
+            MAX_EXTRA_FILES_TO_PROMPT = 50
+            if remaining_files_list:
+                files_walkthrough_prompt += "\n\nNo more token budget. Additional unprocessed files:"
+                for i, file in enumerate(remaining_files_list):
+                    files_walkthrough_prompt += f"\n- {file}"
+                    if i >= MAX_EXTRA_FILES_TO_PROMPT:
+                        get_logger().debug(f"Too many remaining files, clipping to {MAX_EXTRA_FILES_TO_PROMPT}")
+                        files_walkthrough_prompt += f"\n... and {len(remaining_files_list) - MAX_EXTRA_FILES_TO_PROMPT} more"
+                        break
+            if deleted_files_list:
+                files_walkthrough_prompt += "\n\nAdditional deleted files:"
+                for i, file in enumerate(deleted_files_list):
+                    files_walkthrough_prompt += f"\n- {file}"
+                    if i >= MAX_EXTRA_FILES_TO_PROMPT:
+                        get_logger().debug(f"Too many deleted files, clipping to {MAX_EXTRA_FILES_TO_PROMPT}")
+                        files_walkthrough_prompt += f"\n... and {len(deleted_files_list) - MAX_EXTRA_FILES_TO_PROMPT} more"
+                        break
+            tokens_files_walkthrough = len(
+                token_handler_only_description_prompt.encoder.encode(files_walkthrough_prompt))
+            total_tokens = token_handler_only_description_prompt.prompt_tokens + tokens_files_walkthrough
+            max_tokens_model = get_max_tokens(model)
+            if total_tokens > max_tokens_model - OUTPUT_BUFFER_TOKENS_HARD_THRESHOLD:
+                # clip files_walkthrough to git the tokens within the limit
+                files_walkthrough_prompt = clip_tokens(files_walkthrough_prompt,
+                                                       max_tokens_model - OUTPUT_BUFFER_TOKENS_HARD_THRESHOLD - token_handler_only_description_prompt.prompt_tokens,
+                                                       num_input_tokens=tokens_files_walkthrough)
+
+            # PR header inference
+            get_logger().debug(f"PR diff only description", artifact=files_walkthrough_prompt)
+            prediction_headers = await self._get_prediction(model, patches_diff=files_walkthrough_prompt,
+                                                            prompt="pr_description_only_description_prompts")
+            prediction_headers = prediction_headers.strip().removeprefix('```yaml').strip('`').strip()
+
+            # manually add extra files to final prediction
+            MAX_EXTRA_FILES_TO_OUTPUT = 100
+            if get_settings().pr_description.mention_extra_files:
+                for i, file in enumerate(remaining_files_list):
+                    extra_file_yaml = f"""\
+- filename: |
+    {file}
+  changes_summary: |
+    ...
+  changes_title: |
+    ...
+  label: |
+    additional files (token-limit)
 """
-        Generate an AI prediction for the PR description 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.
+                    files_walkthrough = files_walkthrough.strip() + "\n" + extra_file_yaml.strip()
+                    if i >= MAX_EXTRA_FILES_TO_OUTPUT:
+                        files_walkthrough += f"""\
+extra_file_yaml = 
+- filename: |
+    Additional {len(remaining_files_list) - MAX_EXTRA_FILES_TO_OUTPUT} files not shown
+  changes_summary: |
+    ...
+  changes_title: |
+    ...
+  label: |
+    additional files (token-limit)
 """
+                        break
+
+            # final processing
+            self.prediction = prediction_headers + "\n" + "pr_files:\n" + files_walkthrough
+            if not load_yaml(self.prediction):
+                get_logger().error(f"Error getting valid YAML in large PR handling for describe {self.pr_id}")
+                if load_yaml(prediction_headers):
+                    get_logger().debug(f"Using only headers for describe {self.pr_id}")
+                    self.prediction = prediction_headers
+
+    async def extend_additional_files(self, remaining_files_list) -> str:
+        prediction = self.prediction
+        try:
+            original_prediction_dict = load_yaml(self.prediction)
+            prediction_extra = "pr_files:"
+            for file in remaining_files_list:
+                extra_file_yaml = f"""\
+- filename: |
+    {file}
+  changes_summary: |
+    ...
+  changes_title: |
+    ...
+  label: |
+    additional files (token-limit)
+"""
+                prediction_extra = prediction_extra + "\n" + extra_file_yaml.strip()
+            prediction_extra_dict = load_yaml(prediction_extra)
+            # merge the two dictionaries
+            if isinstance(original_prediction_dict, dict) and isinstance(prediction_extra_dict, dict):
+                original_prediction_dict["pr_files"].extend(prediction_extra_dict["pr_files"])
+                new_yaml = yaml.dump(original_prediction_dict)
+                if load_yaml(new_yaml):
+                    prediction = new_yaml
+            return prediction
+        except Exception as e:
+            get_logger().error(f"Error extending additional files {self.pr_id}: {e}")
+            return self.prediction
+
+    async def _get_prediction(self, model: str, patches_diff: str, prompt="pr_description_prompt") -> str:
        variables = copy.deepcopy(self.vars)
-        variables["diff"] = self.patches_diff  # update diff
+        variables["diff"] = patches_diff  # update diff

        environment = Environment(undefined=StrictUndefined)
        set_custom_labels(variables, self.git_provider)
        self.variables = 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)
+
+        system_prompt = environment.from_string(get_settings().get(prompt, {}).get("system", "")).render(self.variables)
+        user_prompt = environment.from_string(get_settings().get(prompt, {}).get("user", "")).render(self.variables)

        response, finish_reason = await self.ai_handler.chat_completion(
            model=model,
-            temperature=0.2,
+            temperature=get_settings().config.temperature,
            system=system_prompt,
            user=user_prompt
        )
@ -217,9 +381,6 @@ class PRDescription:
        if 'pr_files' in self.data:
            self.data['pr_files'] = self.data.pop('pr_files')

-
-
-
    def _prepare_labels(self) -> List[str]:
        pr_types = []

@ -234,6 +395,7 @@ class PRDescription:
                pr_types = self.data['type']
            elif type(self.data['type']) == str:
                pr_types = self.data['type'].split(',')
+        pr_types = [label.strip() for label in pr_types]

        # convert lowercase labels to original case
        try:
@ -301,7 +463,7 @@ class PRDescription:

        # Remove the 'PR Title' key from the dictionary
        ai_title = self.data.pop('title', self.vars["title"])
-        if get_settings().pr_description.keep_original_user_title:
+        if (not get_settings().pr_description.generate_ai_title):
            # Assign the original PR title to the 'title' variable
            title = self.vars["title"]
        else:
@ -317,7 +479,11 @@ class PRDescription:
                value = self.file_label_dict
            else:
                key_publish = key.rstrip(':').replace("_", " ").capitalize()
-                pr_body += f"## **{key_publish}**\n"
+                if key_publish == "Type":
+                    key_publish = "PR Type"
+                # elif key_publish == "Description":
+                #     key_publish = "PR Description"
+                pr_body += f"### **{key_publish}**\n"
            if 'walkthrough' in key.lower():
                if self.git_provider.is_supported("gfm_markdown"):
                    pr_body += "<details> <summary>files:</summary>\n\n"
@ -327,13 +493,13 @@ class PRDescription:
                    pr_body += f'- `{filename}`: {description}\n'
                if self.git_provider.is_supported("gfm_markdown"):
                    pr_body += "</details>\n"
-            elif 'pr_files' in key.lower():
+            elif 'pr_files' in key.lower() and get_settings().pr_description.enable_semantic_files_types:
                changes_walkthrough, pr_file_changes = self.process_pr_files_prediction(changes_walkthrough, value)
-                changes_walkthrough = f"## **Changes walkthrough**\n{changes_walkthrough}"
+                changes_walkthrough = f"### **Changes walkthrough** 📝\n{changes_walkthrough}"
            else:
                # if the value is a list, join its items by comma
                if isinstance(value, list):
-                    value = ', '.join(v for v in value)
+                    value = ', '.join(v.rstrip() for v in value)
                pr_body += f"{value}\n"
            if idx < len(self.data) - 1:
                pr_body += "\n\n___\n\n"
@ -342,12 +508,21 @@ class PRDescription:

    def _prepare_file_labels(self):
        file_label_dict = {}
+        if (not self.data or not isinstance(self.data, dict) or
+                'pr_files' not in self.data or not self.data['pr_files']):
+            return file_label_dict
        for file in self.data['pr_files']:
            try:
+                required_fields = ['changes_summary', 'changes_title', 'filename', 'label']
+                if not all(field in file for field in required_fields):
+                    # can happen for example if a YAML generation was interrupted in the middle (no more tokens)
+                    get_logger().warning(f"Missing required fields in file label dict {self.pr_id}, skipping file",
+                                         artifact={"file": file})
+                    continue
                filename = file['filename'].replace("'", "`").replace('"', '`')
                changes_summary = file['changes_summary']
                changes_title = file['changes_title'].strip()
-                label = file.get('label')
+                label = file.get('label').strip().lower()
                if label not in file_label_dict:
                    file_label_dict[label] = []
                file_label_dict[label].append((filename, changes_title, changes_summary))
@ -368,7 +543,7 @@ class PRDescription:
            use_collapsible_file_list = num_files > self.COLLAPSIBLE_FILE_LIST_THRESHOLD

        if not self.git_provider.is_supported("gfm_markdown"):
-            return pr_body
+            return pr_body, pr_comments
        try:
            pr_body += "<table>"
            header = f"Relevant files"
@ -388,6 +563,7 @@ class PRDescription:
                for filename, file_changes_title, file_change_description in list_tuples:
                    filename = filename.replace("'", "`").rstrip()
                    filename_publish = filename.split("/")[-1]
+
                    file_changes_title_code = f"<code>{file_changes_title}</code>"
                    file_changes_title_code_br = insert_br_after_x_chars(file_changes_title_code, x=(delta - 5)).strip()
                    if len(file_changes_title_code_br) < (delta - 5):
@ -395,9 +571,9 @@ class PRDescription:
                    filename_publish = f"<strong>{filename_publish}</strong><dd>{file_changes_title_code_br}</dd>"
                    diff_plus_minus = ""
                    delta_nbsp = ""
-                    diff_files = self.git_provider.diff_files
+                    diff_files = self.git_provider.get_diff_files()
                    for f in diff_files:
-                        if f.filename.lower() == filename.lower():
+                        if f.filename.lower().strip('/') == filename.lower().strip('/'):
                            num_plus_lines = f.num_plus_lines
                            num_minus_lines = f.num_minus_lines
                            diff_plus_minus += f"+{num_plus_lines}/-{num_minus_lines}"
@ -419,6 +595,7 @@ class PRDescription:
 <hr>

 {filename}
+
 {file_change_description_br}


@ -427,6 +604,7 @@ class PRDescription:

  </td>
  <td><a href="{link}">{diff_plus_minus}</a>{delta_nbsp}</td>
+
 </tr>                    
 """
                if use_collapsible_file_list:
@ -504,6 +682,7 @@ def insert_br_after_x_chars(text, x=70):
            is_inside_code = False
    return ''.join(new_text).strip()

+
 def replace_code_tags(text):
    """
    Replace odd instances of ` with <code> and even instances of ` with </code>
--- a/pr_agent/tools/pr_generate_labels.py
+++ b/pr_agent/tools/pr_generate_labels.py
@ -137,12 +137,13 @@ class PRGenerateLabels:
        environment = Environment(undefined=StrictUndefined)
        set_custom_labels(variables, self.git_provider)
        self.variables = 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)
+
+        system_prompt = environment.from_string(get_settings().pr_custom_labels_prompt.system).render(self.variables)
+        user_prompt = environment.from_string(get_settings().pr_custom_labels_prompt.user).render(self.variables)

        response, finish_reason = await self.ai_handler.chat_completion(
            model=model,
-            temperature=0.2,
+            temperature=get_settings().config.temperature,
            system=system_prompt,
            user=user_prompt
        )
@ -164,6 +165,7 @@ class PRGenerateLabels:
                pr_types = self.data['labels']
            elif type(self.data['labels']) == str:
                pr_types = self.data['labels'].split(',')
+        pr_types = [label.strip() for label in pr_types]

        # convert lowercase labels to original case
        try:
--- a/pr_agent/tools/pr_help_message.py
+++ b/pr_agent/tools/pr_help_message.py
@ -18,8 +18,8 @@ class PRHelpMessage:
            relevant_configs = {'pr_help': dict(get_settings().pr_help),
                                'config': dict(get_settings().config)}
            get_logger().debug("Relevant configs", artifacts=relevant_configs)
-            pr_comment = "## PR Agent Walkthrough\n\n"
-            pr_comment += "🤖 Welcome to the PR Agent, an AI-powered tool for automated pull request analysis, feedback, suggestions and more."""
+            pr_comment = "## PR Agent Walkthrough 🤖\n\n"
+            pr_comment += "Welcome to the PR Agent, an AI-powered tool for automated pull request analysis, feedback, suggestions and more."""
            pr_comment += "\n\nHere is a list of tools you can use to interact with the PR Agent:\n"
            base_path = "https://pr-agent-docs.codium.ai/tools"

@ -35,7 +35,7 @@ class PRHelpMessage:
            tool_names.append(f"[ASK]({base_path}/ask/)")
            tool_names.append(f"[GENERATE CUSTOM LABELS]({base_path}/custom_labels/) 💎")
            tool_names.append(f"[CI FEEDBACK]({base_path}/ci_feedback/) 💎")
-            tool_names.append(f"[CUSTOM SUGGESTIONS]({base_path}/custom_suggestions/) 💎")
+            tool_names.append(f"[CUSTOM PROMPT]({base_path}/custom_prompt/) 💎")
            tool_names.append(f"[SIMILAR ISSUE]({base_path}/similar_issues/)")

            descriptions = []
@ -50,7 +50,7 @@ class PRHelpMessage:
            descriptions.append("Answering free-text questions about the PR")
            descriptions.append("Generates custom labels for the PR, based on specific guidelines defined by the user")
            descriptions.append("Generates feedback and analysis for a failed CI job")
-            descriptions.append("Generates custom suggestions for improving the PR code, based only on specific guidelines defined by the user")
+            descriptions.append("Generates custom suggestions for improving the PR code, derived only from a specific guidelines prompt defined by the user")
            descriptions.append("Automatically retrieves and presents similar issues")

            commands  =[]
@ -65,7 +65,7 @@ class PRHelpMessage:
            commands.append("`/ask`")
            commands.append("`/generate_labels`")
            commands.append("`/checks`")
-            commands.append("`/custom_suggestions`")
+            commands.append("`/custom_prompt`")
            commands.append("`/similar_issue`")

            checkbox_list = []
@ -86,12 +86,12 @@ class PRHelpMessage:
            checkbox_list.append("[*]")
            checkbox_list.append("[*]")

-            if isinstance(self.git_provider, GithubProvider):
+            if isinstance(self.git_provider, GithubProvider) and not get_settings().config.get('disable_checkboxes', False):
                pr_comment += f"<table><tr align='left'><th align='left'>Tool</th><th align='left'>Description</th><th align='left'>Trigger Interactively :gem:</th></tr>"
                for i in range(len(tool_names)):
                    pr_comment += f"\n<tr><td align='left'>\n\n<strong>{tool_names[i]}</strong></td>\n<td>{descriptions[i]}</td>\n<td>\n\n{checkbox_list[i]}\n</td></tr>"
                pr_comment += "</table>\n\n"
-                pr_comment += f"""\n\n(1) Note that each tool be [triggered automatically](https://github.com/Codium-ai/pr-agent/blob/main/Usage.md#github-app-automatic-tools-for-pr-actions) when a new PR is opened, or called manually by [commenting on a PR](https://github.com/Codium-ai/pr-agent/blob/main/Usage.md#online-usage)."""
+                pr_comment += f"""\n\n(1) Note that each tool be [triggered automatically](https://pr-agent-docs.codium.ai/usage-guide/automations_and_usage/#github-app-automatic-tools-when-a-new-pr-is-opened) when a new PR is opened, or called manually by [commenting on a PR](https://pr-agent-docs.codium.ai/usage-guide/automations_and_usage/#online-usage)."""
                pr_comment += f"""\n\n(2) Tools marked with [*] require additional parameters to be passed. For example, to invoke the `/ask` tool, you need to comment on a PR: `/ask "<question content>"`. See the relevant documentation for each tool for more details."""
            else:
                pr_comment += f"<table><tr align='left'><th align='left'>Tool</th><th align='left'>Command</th><th align='left'>Description</th></tr>"
--- a/pr_agent/tools/pr_information_from_user.py
+++ b/pr_agent/tools/pr_information_from_user.py
@ -66,8 +66,8 @@ class PRInformationFromUser:
        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)
+        response, finish_reason = await self.ai_handler.chat_completion(
+            model=model, temperature=get_settings().config.temperature, system=system_prompt, user=user_prompt)
        return response

    def _prepare_pr_answer(self) -> str:
--- a/pr_agent/tools/pr_line_questions.py
+++ b/pr_agent/tools/pr_line_questions.py
@ -102,6 +102,6 @@ class PR_LineQuestions:
            print(f"\nSystem prompt:\n{system_prompt}")
            print(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)
+        response, finish_reason = await self.ai_handler.chat_completion(
+            model=model, temperature=get_settings().config.temperature, system=system_prompt, user=user_prompt)
        return response
--- a/pr_agent/tools/pr_questions.py
+++ b/pr_agent/tools/pr_questions.py
@ -7,6 +7,7 @@ from pr_agent.algo.ai_handlers.base_ai_handler import BaseAiHandler
 from pr_agent.algo.ai_handlers.litellm_ai_handler import LiteLLMAIHandler
 from pr_agent.algo.pr_processing import get_pr_diff, retry_with_fallback_models
 from pr_agent.algo.token_handler import TokenHandler
+from pr_agent.algo.utils import ModelType
 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
@ -58,17 +59,17 @@ class PRQuestions:
            self.git_provider.publish_comment("Preparing answer...", is_temporary=True)

        # identify image
-        img_path = self.idenfity_image_in_comment()
+        img_path = self.identify_image_in_comment()
        if img_path:
            get_logger().debug(f"Image path identified", artifact=img_path)

-        await retry_with_fallback_models(self._prepare_prediction)
+        await retry_with_fallback_models(self._prepare_prediction, model_type=ModelType.TURBO)

        pr_comment = self._prepare_pr_answer()
        get_logger().debug(f"PR output", artifact=pr_comment)

        if self.git_provider.is_supported("gfm_markdown") and get_settings().pr_questions.enable_help_text:
-            pr_comment += "<hr>\n\n<details> <summary><strong>✨ Ask tool usage guide:</strong></summary><hr> \n\n"
+            pr_comment += "<hr>\n\n<details> <summary><strong>💡 Tool usage guide:</strong></summary><hr> \n\n"
            pr_comment += HelpMessage.get_ask_usage_guide()
            pr_comment += "\n</details>\n"

@ -77,7 +78,7 @@ class PRQuestions:
            self.git_provider.remove_initial_comment()
        return ""

-    def idenfity_image_in_comment(self):
+    def identify_image_in_comment(self):
        img_path = ''
        if '![image]' in self.question_str:
            # assuming structure:
@ -107,15 +108,15 @@ class PRQuestions:
        user_prompt = environment.from_string(get_settings().pr_questions_prompt.user).render(variables)
        if 'img_path' in variables:
            img_path = self.vars['img_path']
-            response, finish_reason = await self.ai_handler.chat_completion(model=model, temperature=0.2,
-                                                                            system=system_prompt, user=user_prompt,
-                                                                            img_path=img_path)
+            response, finish_reason = await (self.ai_handler.chat_completion
+                                             (model=model, temperature=get_settings().config.temperature,
+                                              system=system_prompt, user=user_prompt, img_path=img_path))
        else:
-            response, finish_reason = await self.ai_handler.chat_completion(model=model, temperature=0.2,
-                                                                            system=system_prompt, user=user_prompt)
+            response, finish_reason = await self.ai_handler.chat_completion(
+                model=model, temperature=get_settings().config.temperature, system=system_prompt, user=user_prompt)
        return response

    def _prepare_pr_answer(self) -> str:
-        answer_str = f"Question: {self.question_str}\n\n"
-        answer_str += f"Answer:\n{self.prediction.strip()}\n\n"
+        answer_str = f"### **Ask**❓\n{self.question_str}\n\n"
+        answer_str += f"### **Answer:**\n{self.prediction.strip()}\n\n"
        return answer_str
--- a/Show More
+++ b/Show More