Add ability to work with litellm debugger

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

@@ -24,7 +24,4 @@ jobs:
           OPENAI_KEY: ${{ secrets.OPENAI_KEY }}
           OPENAI_ORG: ${{ secrets.OPENAI_ORG }} # optional
           GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-          PINECONE.API_KEY: ${{ secrets.PINECONE_API_KEY }}
-          PINECONE.ENVIRONMENT: ${{ secrets.PINECONE_ENVIRONMENT }}
-
 

Dockerfile.bitbucket_pipeline

@@ -1,18 +0,0 @@
-FROM python:3.10 as base
-
-ENV OPENAI_API_KEY=${OPENAI_API_KEY} \
-    BITBUCKET_BEARER_TOKEN=${BITBUCKET_BEARER_TOKEN} \
-    BITBUCKET_PR_ID=${BITBUCKET_PR_ID} \
-    BITBUCKET_REPO_SLUG=${BITBUCKET_REPO_SLUG} \
-    BITBUCKET_WORKSPACE=${BITBUCKET_WORKSPACE}
-
-
-WORKDIR /app
-ADD pyproject.toml .
-ADD requirements.txt .
-RUN pip install . && rm pyproject.toml requirements.txt
-ENV PYTHONPATH=/app
-ADD pr_agent pr_agent
-ADD bitbucket_pipeline/entrypoint.sh /
-RUN chmod +x /entrypoint.sh
-ENTRYPOINT ["/entrypoint.sh"]

INSTALL.md

@@ -16,7 +16,6 @@ There are several ways to use PR-Agent:
 - [Method 6: Deploy as a Lambda Function](INSTALL.md#method-6---deploy-as-a-lambda-function)
 - [Method 7: AWS CodeCommit](INSTALL.md#method-7---aws-codecommit-setup)
 - [Method 8: Run a GitLab webhook server](INSTALL.md#method-8---run-a-gitlab-webhook-server)
-- [Method 9: Run as a Bitbucket Pipeline](INSTALL.md#method-9-run-as-a-bitbucket-pipeline)
 ---
 
 ### Method 1: Use Docker image (no installation required)
@@ -25,22 +24,16 @@ To request a review for a PR, or ask a question about a PR, you can run directly
 
 1. To request a review for a PR, run the following command:
 
-For GitHub:
 ```
 docker run --rm -it -e OPENAI.KEY=<your key> -e GITHUB.USER_TOKEN=<your token> codiumai/pr-agent --pr_url <pr_url> review
 ```
-For GitLab:
-```
-docker run --rm -it -e OPENAI.KEY=<your key> -e CONFIG.GIT_PROVIDER=gitlab -e GITLAB.PERSONAL_ACCESS_TOKEN=<your token> codiumai/pr-agent --pr_url <pr_url> review
-```
-For other git providers, update CONFIG.GIT_PROVIDER accordingly, and check the `pr_agent/settings/.secrets_template.toml` file for the environment variables expected names and values.
 
 2. To ask a question about a PR, run the following command:
 
 ```
 docker run --rm -it -e OPENAI.KEY=<your key> -e GITHUB.USER_TOKEN=<your token> codiumai/pr-agent --pr_url <pr_url> ask "<your question>"
 ```
-Note: If you want to ensure you're running a specific version of the Docker image, consider using the image's digest.
+Note: If you want to ensure you're running a specific version of the Docker image, consider using the image's digest. 
 The digest is a unique identifier for a specific version of an image. You can pull and run an image using its digest by referencing it like so: repository@sha256:digest. Always ensure you're using the correct and trusted digest for your operations.
 
 1. To request a review for a PR using a specific digest, run the following command:
@@ -89,17 +82,17 @@ chmod 600 pr_agent/settings/.secrets.toml
 
 ```
 export PYTHONPATH=[$PYTHONPATH:]<PATH to pr_agent folder>
-python3 -m pr_agent.cli --pr_url <pr_url> review
-python3 -m pr_agent.cli --pr_url <pr_url> ask <your question>
-python3 -m pr_agent.cli --pr_url <pr_url> describe
-python3 -m pr_agent.cli --pr_url <pr_url> improve
+python pr_agent/cli.py --pr_url <pr_url> /review
+python pr_agent/cli.py --pr_url <pr_url> /ask <your question>
+python pr_agent/cli.py --pr_url <pr_url> /describe
+python pr_agent/cli.py --pr_url <pr_url> /improve
 ```
 
 ---
 
 ### Method 3: Run as a GitHub Action
 
-You can use our pre-built Github Action Docker image to run PR-Agent as a Github Action.
+You can use our pre-built Github Action Docker image to run PR-Agent as a Github Action. 
 
 1. Add the following file to your repository under `.github/workflows/pr_agent.yml`:
 
@@ -123,7 +116,7 @@ jobs:
           OPENAI_KEY: ${{ secrets.OPENAI_KEY }}
           GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
 ```
-** if you want to pin your action to a specific release (v0.7 for example) for stability reasons, use:
+** if you want to pin your action to a specific commit for stability reasons
 ```yaml
 on:
   pull_request:
@@ -140,7 +133,7 @@ jobs:
     steps:
       - name: PR Agent action step
         id: pragent
-        uses: Codium-ai/pr-agent@v0.7
+        uses: Codium-ai/pr-agent@<commit_sha>
         env:
           OPENAI_KEY: ${{ secrets.OPENAI_KEY }}
           GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
@@ -153,10 +146,10 @@ OPENAI_KEY: <your key>
 
 The GITHUB_TOKEN secret is automatically created by GitHub.
 
-3. Merge this change to your main branch.
+3. Merge this change to your main branch. 
 When you open your next PR, you should see a comment from `github-actions` bot with a review of your PR, and instructions on how to use the rest of the tools.
 
-4. You may configure PR-Agent by adding environment variables under the env section corresponding to any configurable property in the [configuration](pr_agent/settings/configuration.toml) file. Some examples:
+4. You may configure PR-Agent by adding environment variables under the env section corresponding to any configurable property in the [configuration](./Usage.md) file. Some examples:
 ```yaml
       env:
         # ... previous environment values
@@ -221,12 +214,12 @@ git clone https://github.com/Codium-ai/pr-agent.git
    - Copy your app's webhook secret to the webhook_secret field.
    - Set deployment_type to 'app' in [configuration.toml](./pr_agent/settings/configuration.toml)
 
-> The .secrets.toml file is not copied to the Docker image by default, and is only used for local development.
+> The .secrets.toml file is not copied to the Docker image by default, and is only used for local development. 
 > If you want to use the .secrets.toml file in your Docker image, you can add remove it from the .dockerignore file.
-> In most production environments, you would inject the secrets file as environment variables or as mounted volumes.
+> In most production environments, you would inject the secrets file as environment variables or as mounted volumes. 
 > For example, in order to inject a secrets file as a volume in a Kubernetes environment you can update your pod spec to include the following,
 > assuming you have a secret named `pr-agent-settings` with a key named `.secrets.toml`:
-```
+``` 
        volumes:
         - name: settings-volume
           secret:
@@ -322,7 +315,7 @@ Example IAM permissions to that user to allow access to CodeCommit:
                 "codecommit:PostComment*",
                 "codecommit:PutCommentReaction",
                 "codecommit:UpdatePullRequestDescription",
-                "codecommit:UpdatePullRequestTitle"
+                "codecommit:UpdatePullRequestTitle"                
             ],
             "Resource": "*"
         }
@@ -361,73 +354,20 @@ PYTHONPATH="/PATH/TO/PROJECTS/pr-agent" python pr_agent/cli.py \
 ```
 WEBHOOK_SECRET=$(python -c "import secrets; print(secrets.token_hex(10))")
 ```
-3. Follow the instructions to build the Docker image, setup a secrets file and deploy on your own server from [Method 5](#method-5-run-as-a-github-app) steps 4-7.
+3. Follow the instructions to build the Docker image, setup a secrets file and deploy on your own server from [Method 5](#method-5-run-as-a-github-app).
 4. In the secrets file, fill in the following:
     - Your OpenAI key.
     - In the [gitlab] section, fill in personal_access_token and shared_secret. The access token can be a personal access token, or a group or project access token.
     - Set deployment_type to 'gitlab' in [configuration.toml](./pr_agent/settings/configuration.toml)
-5. Create a webhook in GitLab. Set the URL to the URL of your app's server. Set the secret token to the generated secret from step 2.
-In the "Trigger" section, check the ‘comments’ and ‘merge request events’ boxes.
+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. 
+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.
 
+---
 
+### Appendix - **Debugging LLM API Calls**  
+If you're testing your codium/pr-agent server, and need to see if calls were made successfully + the exact call logs, you can use the [LiteLLM Debugger tool](https://docs.litellm.ai/docs/debugging/hosted_debugging). 
 
-### Method 9: Run as a Bitbucket Pipeline
+You can do this by setting `litellm_debugger=true` in configuration.toml. Your Logs will be viewable in real-time @ `admin.litellm.ai/<your_email>`. Set your email in the `.secrets.toml` under 'user_email'.
 
-
-You can use our pre-build Bitbucket-Pipeline docker image to run as Bitbucket-Pipeline.
-
-1. Add the following file in your repository bitbucket_pipelines.yml
-
-```yaml
-  pipelines:
-    pull-requests:
-      '**':
-        - step:
-            name: PR Agent Pipeline
-            caches:
-              - pip
-            image: python:3.8
-            services:
-              - docker
-            script:
-              - git clone https://github.com/Codium-ai/pr-agent.git
-              - cd pr-agent
-              - docker build -t bitbucket_runner:latest -f Dockerfile.bitbucket_pipeline .
-              - docker run -e OPENAI_API_KEY=$OPENAI_API_KEY -e BITBUCKET_BEARER_TOKEN=$BITBUCKET_BEARER_TOKEN -e BITBUCKET_PR_ID=$BITBUCKET_PR_ID -e BITBUCKET_REPO_SLUG=$BITBUCKET_REPO_SLUG -e BITBUCKET_WORKSPACE=$BITBUCKET_WORKSPACE bitbucket_runner:latest
-```
-
-2. Add the following secret to your repository under Repository settings > Pipelines > Repository variables.
-OPENAI_API_KEY: <your key>
-BITBUCKET_BEARER_TOKEN: <your token>
-
-3. To get BITBUCKET_BEARER_TOKEN follow these steps
-  So here is my step by step tutorial
-  i) Insert your workspace name instead of {workspace_name} and go to the following link in order to create an OAuth consumer.
-
-      https://bitbucket.org/{workspace_name}/workspace/settings/api
-
-      set callback URL to http://localhost:8976 (doesn't need to be a real server there)
-      select permissions: repository -> read
-
-  ii) use consumer's Key as a {client_id} and open the following URL in the browser
-
-      https://bitbucket.org/site/oauth2/authorize?client_id={client_id}&response_type=code
-
-  iii)
-      after you press "Grant access" in the browser it will redirect you to
-
-      http://localhost:8976?code=<CODE>
-
-  iv) use the code from the previous step and consumer's Key as a {client_id}, and consumer's Secret as {client_secret}
-
-      curl -X POST -u "{client_id}:{client_secret}" \
-          https://bitbucket.org/site/oauth2/access_token \
-          -d grant_type=authorization_code \
-          -d code={code} \
-
-
-After completing this steps, you just to place this access token in the repository varibles.
-
-
-=======
+<img src="./pics/debugger.png" width="800"/>

PR_COMPRESSION.md

@@ -1,4 +1,4 @@
-# PR Compression Strategy
+# Git Patch Logic
 There are two scenarios:
 1. The PR is small enough to fit in a single prompt (including system and user prompt)
 2. The PR is too large to fit in a single prompt (including system and user prompt)
@@ -16,7 +16,7 @@ We prioritize the languages of the repo based on the following criteria:
 ## Small PR
 In this case, we can fit the entire PR in a single prompt:
 1. Exclude binary files and non code files (e.g. images, pdfs, etc)
-2. We Expand the surrounding context of each patch to 3 lines above and below the patch
+2. We Expand the surrounding context of each patch to 6 lines above and below the patch
 ## Large PR
 
 ### Motivation
@@ -25,7 +25,7 @@ We want to be able to pack as much information as possible in a single LMM promp
 
 
 
-#### Compression strategy
+#### PR compression strategy
 We prioritize additions over deletions:
  - Combine all deleted files into a single list (`deleted files`)
  - File patches are a list of hunks, remove all hunks of type deletion-only from the hunks in the file patch

README.md

@@ -9,34 +9,26 @@ Making pull requests less painful with an AI agent
 
 [![GitHub license](https://img.shields.io/badge/License-Apache_2.0-blue.svg)](https://github.com/Codium-ai/pr-agent/blob/main/LICENSE)
 [![Discord](https://badgen.net/badge/icon/discord?icon=discord&label&color=purple)](https://discord.com/channels/1057273017547378788/1126104260430528613)
-[![Twitter](https://img.shields.io/twitter/follow/codiumai)](https://twitter.com/codiumai)
     <a href="https://github.com/Codium-ai/pr-agent/commits/main">
     <img alt="GitHub" src="https://img.shields.io/github/last-commit/Codium-ai/pr-agent/main?style=for-the-badge" height="20">
     </a>
 </div>
 <div style="text-align:left;">
 
-CodiumAI `PR-Agent` is an open-source tool aiming to help developers review pull requests faster and more efficiently. It automatically analyzes the pull request and can provide several types of commands:
+CodiumAI `PR-Agent` is an open-source tool aiming to help developers review pull requests faster and more efficiently. It automatically analyzes the pull request and can provide several types of PR feedback:
 
-‣ **Auto Description ([`/describe`](./docs/DESCRIBE.md))**: Automatically generating PR description - title, type, summary, code walkthrough and labels.
+**Auto Description (/describe)**: Automatically generating [PR description](https://github.com/Codium-ai/pr-agent/pull/229#issue-1860711415) - title, type, summary, code walkthrough and labels.
 \
-‣ **Auto Review ([`/review`](./docs/REVIEW.md))**: Adjustable feedback about the PR main theme, type, relevant tests, security issues, score, and various suggestions for the PR content.
+**Auto Review (/review)**: [Adjustable feedback](https://github.com/Codium-ai/pr-agent/pull/229#issuecomment-1695022908) about the PR main theme, type, relevant tests, security issues, score, and various suggestions for the PR content.
 \
-‣ **Question Answering ([`/ask ...`](./docs/ASK.md))**: Answering free-text questions about the PR.
+**Question Answering (/ask ...)**: Answering [free-text questions](https://github.com/Codium-ai/pr-agent/pull/229#issuecomment-1695021332) about the PR.
 \
-‣ **Code Suggestions ([`/improve`](./docs/IMPROVE.md))**: Committable code suggestions for improving the PR.
+**Code Suggestions (/improve)**: [Committable code suggestions](https://github.com/Codium-ai/pr-agent/pull/229#discussion_r1306919276) for improving the PR.
 \
-‣ **Update Changelog ([`/update_changelog`](./docs/UPDATE_CHANGELOG.md))**: Automatically updating the CHANGELOG.md file with the PR changes.
-\
-‣ **Find similar issue ([`/similar_issue`](./docs/SIMILAR_ISSUE.md))**: Automatically retrieves and presents similar issues
-\
-‣ **Add Documentation ([`/add_docs`](./docs/ADD_DOCUMENTATION.md))**: Automatically adds documentation to un-documented functions/classes in the PR.
+**Update Changelog (/update_changelog)**: Automatically updating the CHANGELOG.md file with the [PR changes](https://github.com/Codium-ai/pr-agent/pull/168#discussion_r1282077645).
 
-See the [Usage Guide](./Usage.md) for instructions how to run the different tools from _CLI_, _online usage_, Or by _automatically triggering_ them when a new PR is opened.
 
-See the [Tools Guide](./docs/TOOLS_GUIDE.md) for detailed description of the different tools.
-
-See the [Release notes](./RELEASE_NOTES.md) for updates on the latest changes.
+See the [usage guide](./Usage.md) for instructions how to run the different tools from [CLI](./Usage.md#working-from-a-local-repo-cli), or by [online usage](./Usage.md#online-usage).
 
 <h3>Example results:</h3>
 </div>
@@ -95,8 +87,9 @@ See the [Release notes](./RELEASE_NOTES.md) for updates on the latest changes.
 - [Overview](#overview)
 - [Try it now](#try-it-now)
 - [Installation](#installation)
+- [Usage guide](./Usage.md)
 - [How it works](#how-it-works)
-- [Why use PR-Agent?](#why-use-pr-agent)
+- [Why use PR-Agent](#why-use-pr-agent)
 - [Roadmap](#roadmap)
 </div>
 
@@ -106,15 +99,12 @@ See the [Release notes](./RELEASE_NOTES.md) for updates on the latest changes.
 |       |                                             | GitHub | Gitlab | Bitbucket | CodeCommit | Azure DevOps | Gerrit |
 |-------|---------------------------------------------|:------:|:------:|:---------:|:----------:|:----------:|:----------:|
 | TOOLS | Review                                      |   :white_check_mark:    |   :white_check_mark:    |   :white_check_mark:       |   :white_check_mark:    |   :white_check_mark:    |   :white_check_mark:    |
-|       | ⮑ Incremental                              |   :white_check_mark:    |       |           |       |          |     |
 |       | Ask                                         |   :white_check_mark:    |   :white_check_mark:    |   :white_check_mark:          |   :white_check_mark:          | :white_check_mark: |  :white_check_mark:    |
-|       | Auto-Description                            |   :white_check_mark:    |   :white_check_mark:    |   :white_check_mark:        |   :white_check_mark:    |   :white_check_mark:    | :white_check_mark:    |
-|       | Improve Code                                |   :white_check_mark:    |   :white_check_mark:    |   :white_check_mark:        |   :white_check_mark:    |          |    :white_check_mark:    |
-|       | ⮑ Extended                             |   :white_check_mark:    |   :white_check_mark:    |        :white_check_mark:   |   :white_check_mark:    |          | :white_check_mark:    |
-|       | Reflect and Review                          |   :white_check_mark:    |   :white_check_mark:    |   :white_check_mark:        |          |   :white_check_mark:    |    :white_check_mark:    |
-|       | Update CHANGELOG.md                         |   :white_check_mark:    |   :white_check_mark:    |   :white_check_mark:        |   :white_check_mark:    |          |       |
-|       | Find similar issue                          |   :white_check_mark:    |                         |                             |          |          |       |
-|       | Add Documentation                           |   :white_check_mark:    |   :white_check_mark:    |   :white_check_mark:        |   :white_check_mark:    |          |    :white_check_mark:    |
+|       | Auto-Description                            |   :white_check_mark:    |   :white_check_mark:    |           |   :white_check_mark:    |   :white_check_mark:    | :white_check_mark:    |
+|       | Improve Code                                |   :white_check_mark:    |   :white_check_mark:    |           |   :white_check_mark:    |          |    :white_check_mark:    |
+|       | ⮑ Extended                             |   :white_check_mark:    |   :white_check_mark:    |           |   :white_check_mark:    |          | :white_check_mark:    |
+|       | Reflect and Review                          |   :white_check_mark:    |                         |           |          |   :white_check_mark:    |    :white_check_mark:    |
+|       | Update CHANGELOG.md                         |   :white_check_mark:    |                         |           |          |          |       |
 |       |                                             |        |        |      |      |      |
 | USAGE | CLI                                         |   :white_check_mark:    |   :white_check_mark:    |   :white_check_mark:       |   :white_check_mark:    |   :white_check_mark:    |
 |       | App / webhook                               |   :white_check_mark:    |   :white_check_mark:    |           |          |          |
@@ -128,7 +118,7 @@ See the [Release notes](./RELEASE_NOTES.md) for updates on the latest changes.
 |       | Multiple models support |   :white_check_mark:    |   :white_check_mark:    |   :white_check_mark:       | :white_check_mark: |   :white_check_mark:       | :white_check_mark:       |
 |       | Incremental PR Review |   :white_check_mark:    |      |      |      |      |      |
 
-Review the [usage guide](./Usage.md) section for detailed instructions how to use the different tools, select the relevant git provider (GitHub, Gitlab, Bitbucket,...), and adjust the configuration file to your needs.
+Review the **[usage guide](./Usage.md)** section for detailed instructions how to use the different tools, select the relevant git provider (GitHub, Gitlab, Bitbucket,...), and adjust the configuration file to your needs.
 
 ## Try it now
 
@@ -165,13 +155,12 @@ There are several ways to use PR-Agent:
 - [Method 6: Deploy as a Lambda Function](INSTALL.md#method-6---deploy-as-a-lambda-function)
 - [Method 7: AWS CodeCommit](INSTALL.md#method-7---aws-codecommit-setup)
 - [Method 8: Run a GitLab webhook server](INSTALL.md#method-8---run-a-gitlab-webhook-server)
-- [Method 9: Run as a Bitbucket Pipeline](INSTALL.md#method-9-run-as-a-bitbucket-pipeline)
 
 ## How it works
 
 The following diagram illustrates PR-Agent tools and their flow:
 
-![PR-Agent Tools](https://www.codium.ai/wp-content/uploads/2023/10/codiumai-diagram-v5.png)
+![PR-Agent Tools](https://www.codium.ai/wp-content/uploads/2023/07/codiumai-diagram-v4.jpg)
 
 Check out the [PR Compression strategy](./PR_COMPRESSION.md) page for more details on how we convert a code diff to a manageable LLM prompt
 
@@ -193,7 +182,7 @@ Here are some advantages of PR-Agent:
 - [x] Support additional models, as a replacement for OpenAI (see [here](https://github.com/Codium-ai/pr-agent/pull/172))
 - [x] Develop additional logic for handling large PRs (see [here](https://github.com/Codium-ai/pr-agent/pull/229))
 - [ ] Add additional context to the prompt. For example, repo (or relevant files) summarization, with tools such a [ctags](https://github.com/universal-ctags/ctags)
-- [x] PR-Agent for issues
+- [ ] PR-Agent for issues, and just for pull requests
 - [ ] Adding more tools. Possible directions:
   - [x] PR description
   - [x] Inline code suggestions
@@ -201,7 +190,7 @@ Here are some advantages of PR-Agent:
   - [x] Rank the PR (see [here](https://github.com/Codium-ai/pr-agent/pull/89))   
   - [ ] Enforcing CONTRIBUTING.md guidelines
   - [ ] Performance (are there any performance issues)
-  - [x] Documentation (is the PR properly documented)
+  - [ ] Documentation (is the PR properly documented)
   - [ ] ...
 
 ## Similar Projects
@@ -210,14 +199,4 @@ Here are some advantages of PR-Agent:
 - [Aider - GPT powered coding in your terminal](https://github.com/paul-gauthier/aider)
 - [openai-pr-reviewer](https://github.com/coderabbitai/openai-pr-reviewer)
 - [CodeReview BOT](https://github.com/anc95/ChatGPT-CodeReview)
-- [AI-Maintainer](https://github.com/merwanehamadi/AI-Maintainer)
-  
-## Links
-
-[![Join our Discord community](https://raw.githubusercontent.com/Codium-ai/codiumai-vscode-release/main/media/docs/Joincommunity.png)](https://discord.gg/kG35uSHDBc)
-
-- Discord community: https://discord.gg/kG35uSHDBc
-- CodiumAI site: https://codium.ai
-- Blog: https://www.codium.ai/blog/
-- Troubleshooting: https://www.codium.ai/blog/technical-faq-and-troubleshooting/
-- Support: support@codium.ai
+- [AI-Maintainer](https://github.com/merwanehamadi/AI-Maintainer)

RELEASE_NOTES.md

@@ -1,38 +0,0 @@
-## [Version 0.8] - 2023-09-27
-- codiumai/pr-agent:0.8
-- codiumai/pr-agent:0.8-github_app
-- codiumai/pr-agent:0.8-bitbucket-app
-- codiumai/pr-agent:0.8-gitlab_webhook
-- codiumai/pr-agent:0.8-github_polling
-- codiumai/pr-agent:0.8-github_action
-
-### Added::Algo
-- GitHub Action: Can control which tools will run automatically when a new PR is created. (see usage guide: https://github.com/Codium-ai/pr-agent/blob/main/Usage.md#working-with-github-action)
-- Code suggestion tool: Will try to avoid an 'add comments' suggestion  (see https://github.com/Codium-ai/pr-agent/pull/327)
-
-### Fixed
-- Gitlab: Fixed a bug of improper usage of pr_id
-
-
-## [Version 0.7] - 2023-09-20
-
-### Docker Tags
-- codiumai/pr-agent:0.7
-- codiumai/pr-agent:0.7-github_app
-- codiumai/pr-agent:0.7-bitbucket-app
-- codiumai/pr-agent:0.7-gitlab_webhook
-- codiumai/pr-agent:0.7-github_polling
-- codiumai/pr-agent:0.7-github_action
- 
-### Added::Algo
-- New tool /similar_issue - Currently on GitHub app and CLI: indexes the issues in the repo, find the most similar issues to the target issue.
-- Describe markers: Empower the /describe tool with a templating capability (see more details in https://github.com/Codium-ai/pr-agent/pull/273).
-- New feature in the /review tool - added an estimated effort estimation to the review (https://github.com/Codium-ai/pr-agent/pull/306).
-
-### Added::Infrastructure
-- Implementation of a GitLab webhook.
-- Implementation of a BitBucket app.
-
-### Fixed
-- Protection against no code suggestions generated.
-- Resilience to repositories where the languages cannot be automatically detected.

Usage.md

@@ -1,4 +1,4 @@
-## Usage Guide
+## Usage guide
 
 ### Table of Contents
 - [Introduction](#introduction)
@@ -6,19 +6,19 @@
 - [Online usage](#online-usage)
 - [Working with GitHub App](#working-with-github-app)
 - [Working with GitHub Action](#working-with-github-action)
-- [Changing a model](#changing-a-model)
-- [Working with large PRs](#working-with-large-prs)
 - [Appendix - additional configurations walkthrough](#appendix---additional-configurations-walkthrough)
 
 ### Introduction
 
-See the **[installation guide](/INSTALL.md)** for instructions on how to setup PR-Agent. After installation, there are three basic ways to invoke CodiumAI PR-Agent:
+There are 3 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
 
+See the [installation guide](/INSTALL.md) for instructions on how to setup your own PR-Agent.
 
 Specifically, CLI commands can be issued by invoking a pre-built [docker image](/INSTALL.md#running-from-source), or by invoking a [locally cloned repo](INSTALL.md#method-2-run-from-source).
+
 For online usage, you will need to setup either a [GitHub App](INSTALL.md#method-5-run-as-a-github-app), or a [GitHub Action](INSTALL.md#method-3-run-as-a-github-action).
 GitHub App and GitHub Action also enable to run PR-Agent specific tool automatically when a new PR is opened.
 
@@ -27,22 +27,10 @@ GitHub App and GitHub Action also enable to run PR-Agent specific tool automatic
 The different tools and sub-tools used by CodiumAI PR-Agent are adjustable via the **[configuration file](pr_agent/settings/configuration.toml)**.
 In addition to general configuration options, each tool has its own configurations. For example, the `review` tool will use parameters from the [pr_reviewer](/pr_agent/settings/configuration.toml#L16) section in the configuration file.
 
-The [Tools Guide](./docs/TOOLS_GUIDE.md) provides a detailed description of the different tools and their configurations.
-
-#### Ignoring files from analysis
-In some cases, you may want to exclude specific files or directories from the analysis performed by CodiumAI PR-Agent. This can be useful, for example, when you have files that are generated automatically or files that shouldn't be reviewed, like vendored code.
-
-To ignore files or directories, edit the **[ignore.toml](/pr_agent/settings/ignore.toml)** configuration file. This setting is also exposed the following environment variables:
-
- - `IGNORE.GLOB`
- - `IGNORE.REGEX`
-
-See [dynaconf envvars documentation](https://www.dynaconf.com/envvars/).
-
-#### git provider
+**git provider:**
 The [git_provider](pr_agent/settings/configuration.toml#L4) field in the configuration file determines the GIT provider that will be used by PR-Agent. Currently, the following providers are supported:
 `
-"github", "gitlab", "azure", "codecommit", "local", "gerrit"
+"github", "gitlab", "azure", "codecommit", "local"
 `
 
 [//]: # (** online usage:**)
@@ -59,14 +47,15 @@ The [git_provider](pr_agent/settings/configuration.toml#L4) field in the configu
 
 ### Working from a local repo (CLI)
 When running from your local repo (CLI), your local configuration file will be used.
+
 Examples for invoking the different tools via the CLI:
 
-- **Review**:       `python -m pr_agent.cli --pr_url=<pr_url>  review`
-- **Describe**:     `python -m pr_agent.cli --pr_url=<pr_url>  describe`
-- **Improve**:      `python -m pr_agent.cli --pr_url=<pr_url>  improve`
-- **Ask**:          `python -m pr_agent.cli --pr_url=<pr_url>  ask "Write me a poem about this PR"`
-- **Reflect**:      `python -m pr_agent.cli --pr_url=<pr_url>  reflect`
-- **Update Changelog**:      `python -m pr_agent.cli --pr_url=<pr_url>  update_changelog`
+- **Review**:       `python cli.py --pr_url=<pr_url>  /review`
+- **Describe**:     `python cli.py --pr_url=<pr_url>  /describe`
+- **Improve**:      `python cli.py --pr_url=<pr_url>  /improve`
+- **Ask**:          `python cli.py --pr_url=<pr_url>  /ask "Write me a poem about this PR"`
+- **Reflect**:      `python cli.py --pr_url=<pr_url>  /reflect`
+- **Update Changelog**:      `python cli.py --pr_url=<pr_url>  /update_changelog`
 
 `<pr_url>` is the url of the relevant PR (for example: https://github.com/Codium-ai/pr-agent/pull/50).
 
@@ -74,7 +63,7 @@ Examples for invoking the different tools via the CLI:
 
 (1) in addition to editing your local configuration file, you can also change any configuration value by adding it to the command line:
 ```
-python -m pr_agent.cli --pr_url=<pr_url>  /review --pr_reviewer.extra_instructions="focus on the file: ..."
+python cli.py --pr_url=<pr_url>  /review --pr_reviewer.extra_instructions="focus on the file: ..."
 ```
 
 (2) You can print results locally, without publishing them, by setting in `configuration.toml`:
@@ -104,15 +93,15 @@ For example if you want to edit the `review` tool configurations, you can run:
 ```
 /review --pr_reviewer.extra_instructions="..." --pr_reviewer.require_score_review=false
 ```
-Any configuration value in [configuration file](pr_agent/settings/configuration.toml) file can be similarly edited. comment `/config` to see the list of available configurations.
+Any configuration value in [configuration file](pr_agent/settings/configuration.toml) file can be similarly edited.
 
 
 ### Working with GitHub App
-When running PR-Agent from [GitHub App](INSTALL.md#method-5-run-as-a-github-app), the default configurations from a pre-built docker will be initially loaded.
+When running PR-Agent from [GitHub App](INSTALL.md#method-5-run-as-a-github-app), the default configurations from a pre-built repo will be initially loaded.
 
 #### GitHub app automatic tools
-The [github_app](pr_agent/settings/configuration.toml#L56) section defines GitHub app specific configurations.
-An important parameter is `pr_commands`, which is a list of tools that will be **run automatically** when a new PR is opened:
+The [github_app](pr_agent/settings/configuration.toml#L56) section defines GitHub app specific configurations. 
+An important parameter is `pr_commands`, which is a list of tools that will be **run automatically when a new PR is opened**:
 ```
 [github_app]
 pr_commands = [
@@ -123,7 +112,7 @@ pr_commands = [
 This means that when a new PR is opened, PR-Agent will run the `describe` and `auto_review` tools.
 For the describe tool, the `add_original_user_description` and `keep_original_user_title` parameters will be set to true.
 
-You can override the default tool parameters by uploading a local configuration file called `.pr_agent.toml` to the root of your repo.
+However, you can override the default tool parameters by uploading a local configuration file called `.pr_agent.toml` to the root of your repo.
 For example, if your local `.pr_agent.toml` file contains:
 ```
 [pr_description]
@@ -132,18 +121,12 @@ keep_original_user_title = false
 ```
 When a new PR is opened, PR-Agent will run the `describe` tool with the above parameters.
 
-To cancel the automatic run of all the tools, set:
-```
-[github_app]
-pr_commands = ""
-```
-
-
 Note that a local `.pr_agent.toml` file enables you to edit and customize the default parameters of any tool, not just the ones that are run automatically.
 
 #### Editing the prompts
 The prompts for the various PR-Agent tools are defined in the `pr_agent/settings` folder.
-In practice, the prompts are loaded and stored as a standard setting object.
+
+In practice, the prompts are loaded and stored as a standard setting object. 
 Hence, editing them is similar to editing any other configuration value - just place the relevant key in `.pr_agent.toml`file, and override the default value.
 
 For example, if you want to edit the prompts of the [describe](./pr_agent/settings/pr_description_prompts.toml) tool, you can add the following to your `.pr_agent.toml` file:
@@ -159,149 +142,30 @@ user="""
 Note that the new prompt will need to generate an output compatible with the relevant [post-process function](./pr_agent/tools/pr_description.py#L137).
 
 ### Working with GitHub Action
-You can configure settings in GitHub action by adding environment variables under the env section in `.github/workflows/pr_agent.yml` file. Some examples:
-```yaml
-      env:
-        # ... previous environment values
-        OPENAI.ORG: "<Your organization name under your OpenAI account>"
-        PR_REVIEWER.REQUIRE_TESTS_REVIEW: "false" # Disable tests review
-        PR_CODE_SUGGESTIONS.NUM_CODE_SUGGESTIONS: 6 # Increase number of code suggestions
-        github_action.auto_review: "true" # Enable auto review
-        github_action.auto_describe: "true" # Enable auto describe
-        github_action.auto_improve: "false" # Disable auto improve
-```
-specifically, `github_action.auto_review`, `github_action.auto_describe` and `github_action.auto_improve` are used to enable/disable automatic tools that run when a new PR is opened.
+TBD
 
-If not set, the default option is that only the `review` tool will run automatically when a new PR is opened.
-
-### Changing a model
+### Appendix - additional configurations walkthrough
 
+#### Changing a model
 See [here](pr_agent/algo/__init__.py) for the list of available models.
-To use a different model than the default (GPT-4), you need to edit [configuration file](pr_agent/settings/configuration.toml#L2).
-For models and environments not from OPENAI, you might need to provide additional keys and other parameters. See below for instructions.
 
-#### Azure
-To use Azure, set in your .secrets.toml:
-```
-api_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"
-openai.deployment_id = ""  # The deployment name you chose when you deployed the engine
-```
-
-and
+To use Llama2 model, for example, set:
 ```
 [config]
-model="" # the OpenAI model you've deployed on Azure (e.g. gpt-3.5-turbo)
-```
-in the configuration.toml
-
-#### 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={
-    ...,
-    "llama2": 4096
-}
-
-
-[config] # in configuration.toml
-model = "ollama/llama2"
-
-[ollama] # in .secrets.toml
-api_base = ... # the base url for your huggingface inference endpoint
-```
-
-**Inference Endpoints**
-
-To use a new model with Huggingface Inference Endpoints, for example, set:
-```
-[__init__.py]
-MAX_TOKENS = {
-    "model-name-on-huggingface": <max_tokens>
-}
-e.g.
-MAX_TOKENS={
-    ...,
-    "meta-llama/Llama-2-7b-chat-hf": 4096
-}
-[config] # in configuration.toml
-model = "huggingface/meta-llama/Llama-2-7b-chat-hf"
-
-[huggingface] # in .secrets.toml
-key = ... # your huggingface api key
-api_base = ... # the base url for your huggingface inference endpoint
-```
-(you can obtain a Llama2 key from [here](https://replicate.com/replicate/llama-2-70b-chat/api))
-
-#### Replicate
-
-To use Llama2 model with Replicate, for example, set:
-```
-[config] # in configuration.toml
 model = "replicate/llama-2-70b-chat:2c1608e18606fad2812020dc541930f2d0495ce32eee50074220b87300bc16e1"
-[replicate] # in .secrets.toml
+[replicate]
 key = ...
 ```
 (you can obtain a Llama2 key from [here](https://replicate.com/replicate/llama-2-70b-chat/api))
 
-
 Also review the [AiHandler](pr_agent/algo/ai_handler.py) file for instruction how to set keys for other models.
 
-### Working with large PRs
-
-The default mode of CodiumAI is to have a single call per tool, using GPT-4, which has a token limit of 8000 tokens.
-This mode provide a very good speed-quality-cost tradeoff, and can handle most PRs successfully.
-When the PR is above the token limit, it employs a [PR Compression strategy](./PR_COMPRESSION.md).
-
-However, for very large PRs, or in case you want to emphasize quality over speed and cost, there are 2 possible solutions:
-1) [Use a model](#changing-a-model) with larger context, like GPT-32K, or claude-100K. This solution will be applicable for all the tools.
-2) For the `/improve` tool, there is an ['extended' mode](./docs/IMPROVE.md) (`/improve --extended`),
-which divides the PR to chunks, and process each chunk separately. With this mode, regardless of the model, no compression will be done (but for large PRs, multiple model calls may occur)
-
-### Appendix - additional configurations walkthrough
-
-
 #### Extra instructions
 All PR-Agent tools have a parameter called `extra_instructions`, that enables to add free-text extra instructions. Example usage:
 ```
 /update_changelog --pr_update_changelog.extra_instructions="Make sure to update also the version ..."
 ```
 
-#### Patch Extra Lines
-By default, around any change in your PR, git patch provides 3 lines of context above and below the change.
-```
-@@ -12,5 +12,5 @@ def func1():
- code line that already existed in the file...
- code line that already existed in the file...
- code line that already existed in the file....
--code line that was removed in the PR
-+new code line added in the PR
- code line that already existed in the file...
- code line that already existed in the file...
- code line that already existed in the file...
-```
-
-For the `review`, `describe`, `ask` and `add_docs` tools, if the token budget allows, PR-Agent tries to increase the number of lines of context, via the parameter:
-```
-[config]
-patch_extra_lines=3
-```
-
-Increasing this number provides more context to the model, but will also increase the token budget.
-If the PR is too large (see [PR Compression strategy](./PR_COMPRESSION.md)), PR-Agent automatically sets this number to 0, using the original git patch.
-
-
 #### Azure DevOps provider
 To use Azure DevOps provider use the following settings in configuration.toml:
 ```
@@ -315,4 +179,4 @@ And use the following settings (you have to replace the values) in .secrets.toml
 [azure_devops]
 org = "https://dev.azure.com/YOUR_ORGANIZATION/"
 pat = "YOUR_PAT_TOKEN"
-```
+```

bitbucket_pipeline/entrypoint.sh

@@ -1,2 +0,0 @@
-#!/bin/bash
-python /app/pr_agent/servers/bitbucket_pipeline_runner.py

docs/ADD_DOCUMENTATION.md

@@ -1,15 +0,0 @@
-# Add Documentation Tool
-The `add_docs` tool scans the PR code changes, and automatically suggests documentation for the undocumented code components (functions, classes, etc.).
-
-It can be invoked manually by commenting on any PR:
-```
-/add_docs
-```
-For example:
-
-<kbd><img src=./../pics/add_docs_comment.png width="768"></kbd>
-<kbd><img src=./../pics/add_docs.png width="768"></kbd>
-
-### Configuration options
- - `docs_style`: The exact style of the documentation (for python docstring). you can choose between: `google`, `numpy`, `sphinx`, `restructuredtext`, `plain`. Default is `sphinx`.
- - `extra_instructions`: Optional extra instructions to the tool. For example: "focus on the changes in the file X. Ignore change in ...".

docs/ASK.md

@@ -1,11 +0,0 @@
-# ASK Tool
-
-The `ask` tool answers questions about the PR, based on the PR code changes.
-It can be invoked manually by commenting on any PR:
-```
-/ask "..."
-```
-For example:
-
-<kbd><img src=./../pics/ask_comment.png width="768"></kbd>
-<kbd><img src=./../pics/ask.png width="768"></kbd>

docs/DESCRIBE.md

@@ -1,51 +0,0 @@
-# Describe Tool
-
-The `describe` tool scans the PR code changes, and automatically generates PR description - title, type, summary, code walkthrough and labels.
-It can be invoked manually by commenting on any PR:
-```
-/describe
-```
-For example:
-
-<kbd><img src=./../pics/describe_comment.png width="768"></kbd>
-
-<kbd><img src=./../pics/describe.png width="768"></kbd>
-
-The `describe` tool can also be triggered automatically every time a new PR is opened. See examples for automatic triggers for [GitHub App](https://github.com/Codium-ai/pr-agent/blob/main/Usage.md#github-app-automatic-tools) and [GitHub Action](https://github.com/Codium-ai/pr-agent/blob/main/Usage.md#working-with-github-action)
-
-### Configuration options
-
-Under the section 'pr_description', the [configuration file](./../pr_agent/settings/configuration.toml#L28) contains options to customize the 'describe' tool:
-
-- `publish_labels`: if set to true, the tool will publish the labels to the PR. Default is true.
-
-- `publish_description_as_comment`: if set to true, the tool will publish the description as a comment to the PR. If false, it will overwrite the origianl description. Default is false.
-
-- `add_original_user_description`: if set to true, the tool will add the original user description to the generated description. Default is false.
-
-- `keep_original_user_title`: if set to true, the tool will keep the original PR title, and won't change it. Default is false.
-
-- `extra_instructions`: Optional extra instructions to the tool. For example: "focus on the changes in the file X. Ignore change in ...".
-
-#### Markers template
-
-markers enable to easily integrate user's content and auto-generated content, with a template-like mechanism.
-
-- `use_description_markers`: if set to true, the tool will use markers template. It replaces every marker of the form `pr_agent:marker_name` with the relevant content. Default is false.
-
-For example, if the PR original description was:
-```
-User content...
-
-## PR Type:
-pr_agent:pr_type
-
-## PR Description:
-pr_agent:summary
-
-## PR Walkthrough:
-pr_agent:walkthrough
-```
-The marker `pr_agent:pr_type` will be replaced with the PR type, `pr_agent:summary` will be replaced with the PR summary, and `pr_agent:walkthrough` will be replaced with the PR walkthrough.
-
-- `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.

docs/IMPROVE.md

@@ -1,34 +0,0 @@
-# Improve Tool
-
-The `improve` tool scans the PR code changes, and automatically generate committable suggestions for improving the PR code.
-It can be invoked manually by commenting on any PR:
-```
-/improve
-```
-For example:
-
-<kbd><img src=./../pics/improve_comment.png width="768"></kbd>
-<kbd><img src=./../pics/improve.png width="768"></kbd>
-
-The `improve` tool can also be triggered automatically every time a new PR is opened. See examples for automatic triggers for [GitHub App](https://github.com/Codium-ai/pr-agent/blob/main/Usage.md#github-app-automatic-tools) and [GitHub Action](https://github.com/Codium-ai/pr-agent/blob/main/Usage.md#working-with-github-action)
-
-An extended mode, which does not involve PR Compression and provides more comprehensive suggestions, can be invoked by commenting on any PR:
-```
-/improve --extended
-```
-Note that the extended mode divides the PR code changes into chunks, up to the token limits, where each chunk is handled separately (multiple calls to GPT-4).
-Hence, the total number of suggestions is proportional to the number of chunks, i.e. the size of the PR.
-
-### Configuration options
-
-Under the section 'pr_code_suggestions', the [configuration file](./../pr_agent/settings/configuration.toml#L40) contains options to customize the 'improve' tool:
-
-- `num_code_suggestions`: number of code suggestions provided by the 'improve' tool. Default is 4.
-- `extra_instructions`: Optional extra instructions to the tool. For example: "focus on the changes in the file X. Ignore change in ...".
-- `rank_suggestions`: if set to true, the tool will rank the suggestions, based on importance. Default is false.
-
-#### params for '/improve --extended' mode
-- `num_code_suggestions_per_chunk`: number of code suggestions provided by the 'improve' tool, per chunk. Default is 8.
-- `rank_extended_suggestions`: if set to true, the tool will rank the suggestions, based on importance. Default is true.
-- `max_number_of_calls`: maximum number of chunks. Default is 5.
-- `final_clip_factor`: factor to remove suggestions with low confidence. Default is 0.9.

docs/REVIEW.md

@@ -1,46 +0,0 @@
-# Review Tool
-
-The `review` tool scans the PR code changes, and automatically generates a PR review.
-It can be invoked manually by commenting on any PR:
-```
-/review
-```
-For example:
-
-<kbd><img src=./../pics/review_comment.png width="768"></kbd>
-<kbd><img src=./../pics/describe.png width="768"></kbd>
-
-The `review` tool can also be triggered automatically every time a new PR is opened. See examples for automatic triggers for [GitHub App](https://github.com/Codium-ai/pr-agent/blob/main/Usage.md#github-app-automatic-tools) and [GitHub Action](https://github.com/Codium-ai/pr-agent/blob/main/Usage.md#working-with-github-action)
-
-### Configuration options
-
-Under the section 'pr_reviewer', the [configuration file](./../pr_agent/settings/configuration.toml#L16) contains options to customize the 'review' tool:
-
-- `require_focused_review`: if set to true, the tool will add a section - 'is the PR a focused one'. Default is false.
-- `require_score_review`: if set to true, the tool will add a section that scores the PR. Default is false.
-- `require_tests_review`: if set to true, the tool will add a section that checks if the PR contains tests. Default is true.
-- `require_security_review`: if set to true, the tool will add a section that checks if the PR contains security issues. Default is true.
-- `require_estimate_effort_to_review`: if set to true, the tool will add a section that estimates thed effort needed to review the PR. Default is true.
-- `num_code_suggestions`: number of code suggestions provided by the 'review' tool. Default is 4.
-- `inline_code_comments`: if set to true, the tool will publish the code suggestions as comments on the code diff. Default is false.
-- `automatic_review`: if set to false, no automatic reviews will be done. Default is true.
-- `extra_instructions`: Optional extra instructions to the tool. For example: "focus on the changes in the file X. Ignore change in ...".
-####  Incremental Mode
-For an incremental review, which only considers changes since the last PR-Agent review, this can be useful when working on the PR in an iterative manner, and you want to focus on the changes since the last review instead of reviewing the entire PR again, the following command can be used:
-```
-/improve -i
-```
-Note that the incremental mode is only available for GitHub.
-
-<kbd><img src=./../pics/incremental_review.png width="768"></kbd>
-
-#### 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 his answers.
-
-<kbd><img src=./../pics/reflection_questions.png width="768"></kbd>
-<kbd><img src=./../pics/reflection_answers.png width="768"></kbd>
-<kbd><img src=./../pics/reflection_insights.png width="768"></kbd>

docs/SIMILAR_ISSUE.md

@@ -1,31 +0,0 @@
-# Similar Issue Tool
-The similar issue tool retrieves the most similar issues to the current issue.
-It can be invoked manually by commenting on any PR:
-```
-/similar_issue
-```
-For example:
-
-<kbd><img src=./../pics/similar_issue_original_issue.png width="768"></kbd>
-<kbd><img src=./../pics/similar_issue_comment.png width="768"></kbd>
-<kbd><img src=./../pics/similar_issue.png width="768"></kbd>
-
-Note that to perform retrieval, the `similar_issue` tool indexes all the repo previous issues (once).
-
-To enable usage of the '**similar issue**' tool, you need to set the following keys in `.secrets.toml` (or in the relevant environment variables):
-```
-[pinecone]
-api_key = "..."
-environment = "..."
-```
-These parameters can be obtained by registering to [Pinecone](https://app.pinecone.io/?sessionType=signup/).
-
-
-### How to use:
-- To invoke the 'similar issue' tool from **CLI**, run:
-`python3 cli.py --issue_url=... similar_issue`
-
-- To invoke the 'similar' issue tool via online usage, [comment](https://github.com/Codium-ai/pr-agent/issues/178#issuecomment-1716934893) on a PR:
-`/similar_issue`
-
-- You can also enable the 'similar issue' tool to run automatically when a new issue is opened, by adding it to the [pr_commands list in the github_app section](https://github.com/Codium-ai/pr-agent/blob/main/pr_agent/settings/configuration.toml#L66)

docs/TOOLS_GUIDE.md

@@ -1,10 +0,0 @@
-## Tools Guide
-- [DESCRIBE](./DESCRIBE.md)
-- [REVIEW](./REVIEW.md)
-- [IMPROVE](./IMPROVE.md)
-- [ASK](./ASK.md)
-- [SIMILAR_ISSUE](./SIMILAR_ISSUE.md)
-- [UPDATE CHANGELOG](./UPDATE_CHANGELOG.md)
-- [ADD DOCUMENTATION](./ADD_DOCUMENTATION.md)
-
-See the **[installation guide](/INSTALL.md)** for instructions on how to setup PR-Agent.

docs/UPDATE_CHANGELOG.md

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

pr_agent/agent/pr_agent.py

@@ -1,17 +1,18 @@
+import logging
+import os
 import shlex
+import tempfile
 
 from pr_agent.algo.utils import update_settings_from_args
 from pr_agent.config_loader import get_settings
-from pr_agent.git_providers.utils import apply_repo_settings
-from pr_agent.tools.pr_add_docs import PRAddDocs
+from pr_agent.git_providers import get_git_provider
 from pr_agent.tools.pr_code_suggestions import PRCodeSuggestions
-from pr_agent.tools.pr_config import PRConfig
 from pr_agent.tools.pr_description import PRDescription
 from pr_agent.tools.pr_information_from_user import PRInformationFromUser
 from pr_agent.tools.pr_questions import PRQuestions
 from pr_agent.tools.pr_reviewer import PRReviewer
-from pr_agent.tools.pr_similar_issue import PRSimilarIssue
 from pr_agent.tools.pr_update_changelog import PRUpdateChangelog
+from pr_agent.tools.pr_config import PRConfig
 
 command2class = {
     "auto_review": PRReviewer,
@@ -29,8 +30,6 @@ command2class = {
     "update_changelog": PRUpdateChangelog,
     "config": PRConfig,
     "settings": PRConfig,
-    "similar_issue": PRSimilarIssue,
-    "add_docs": PRAddDocs,
 }
 
 commands = list(command2class.keys())
@@ -41,7 +40,22 @@ class PRAgent:
 
     async def handle_request(self, pr_url, request, notify=None) -> bool:
         # First, apply repo specific settings if exists
-        apply_repo_settings(pr_url)
+        if get_settings().config.use_repo_settings_file:
+            repo_settings_file = None
+            try:
+                git_provider = get_git_provider()(pr_url)
+                repo_settings = git_provider.get_repo_settings()
+                if repo_settings:
+                    repo_settings_file = None
+                    fd, repo_settings_file = tempfile.mkstemp(suffix='.toml')
+                    os.write(fd, repo_settings)
+                    get_settings().load_file(repo_settings_file)
+            finally:
+                if repo_settings_file:
+                    try:
+                        os.remove(repo_settings_file)
+                    except Exception as e:
+                        logging.error(f"Failed to remove temporary settings file {repo_settings_file}", e)
 
         # Then, apply user specific settings if exists
         request = request.replace("'", "\\'")
@@ -51,8 +65,8 @@ class PRAgent:
         args = update_settings_from_args(args)
 
         action = action.lstrip("/").lower()
-        if action == "reflect_and_review":
-            get_settings().pr_reviewer.ask_and_reflect = True
+        if action == "reflect_and_review" and not get_settings().pr_reviewer.ask_and_reflect:
+            action = "review"
         if action == "answer":
             if notify:
                 notify()
@@ -66,4 +80,3 @@ class PRAgent:
         else:
             return False
         return True
-

pr_agent/algo/__init__.py

@@ -1,5 +1,4 @@
 MAX_TOKENS = {
-    'text-embedding-ada-002': 8000,
     'gpt-3.5-turbo': 4000,
     'gpt-3.5-turbo-0613': 4000,
     'gpt-3.5-turbo-0301': 4000,
@@ -12,5 +11,4 @@ MAX_TOKENS = {
     'claude-2': 100000,
     'command-nightly': 4096,
     'replicate/llama-2-70b-chat:2c1608e18606fad2812020dc541930f2d0495ce32eee50074220b87300bc16e1': 4096,
-    'meta-llama/Llama-2-7b-chat-hf': 4096
 }

pr_agent/algo/ai_handler.py

@@ -1,12 +1,12 @@
-import os
+import logging
 
 import litellm
 import openai
 from litellm import acompletion
 from openai.error import APIError, RateLimitError, Timeout, TryAgain
 from retry import retry
+
 from pr_agent.config_loader import get_settings
-from pr_agent.log import get_logger
 
 OPENAI_RETRIES = 5
 
@@ -26,11 +26,7 @@ class AiHandler:
         try:
             openai.api_key = get_settings().openai.key
             litellm.openai_key = get_settings().openai.key
-            if get_settings().get("litellm.use_client"):
-                litellm_token = get_settings().get("litellm.LITELLM_TOKEN")
-                assert litellm_token, "LITELLM_TOKEN is required"
-                os.environ["LITELLM_TOKEN"] = litellm_token
-                litellm.use_client = True
+            litellm.debugger = get_settings().litellm.debugger
             self.azure = False
             if get_settings().get("OPENAI.ORG", None):
                 litellm.organization = get_settings().openai.org
@@ -52,8 +48,8 @@ class AiHandler:
                 litellm.replicate_key = get_settings().replicate.key
             if get_settings().get("HUGGINGFACE.KEY", None):
                 litellm.huggingface_key = get_settings().huggingface.key
-                if get_settings().get("HUGGINGFACE.API_BASE", None):
-                    litellm.api_base = get_settings().huggingface.api_base
+            if get_settings().get("LITELLM.DEBUGGER") and get_settings().get("LITELLM.EMAIL"):
+                litellm.email = get_settings().get("LITELLM.EMAIL", None)
         except AttributeError as e:
             raise ValueError("OpenAI key is required") from e
 
@@ -89,34 +85,33 @@ class AiHandler:
         try:
             deployment_id = self.deployment_id
             if get_settings().config.verbosity_level >= 2:
-                get_logger().debug(
+                logging.debug(
                     f"Generating completion with {model}"
                     f"{(' from deployment ' + deployment_id) if deployment_id else ''}"
                 )
-            if self.azure:
-                model = 'azure/' + model
-            messages = [{"role": "system", "content": system}, {"role": "user", "content": user}]
             response = await acompletion(
                 model=model,
                 deployment_id=deployment_id,
-                messages=messages,
+                messages=[
+                    {"role": "system", "content": system},
+                    {"role": "user", "content": user}
+                ],
                 temperature=temperature,
+                azure=self.azure,
                 force_timeout=get_settings().config.ai_timeout
             )
         except (APIError, Timeout, TryAgain) as e:
-            get_logger().error("Error during OpenAI inference: ", e)
+            logging.error("Error during OpenAI inference: ", e)
             raise
         except (RateLimitError) as e:
-            get_logger().error("Rate limit error during OpenAI inference: ", e)
+            logging.error("Rate limit error during OpenAI inference: ", e)
             raise
         except (Exception) as e:
-            get_logger().error("Unknown error during OpenAI inference: ", e)
+            logging.error("Unknown error during OpenAI inference: ", e)
             raise TryAgain from e
         if response is None or len(response["choices"]) == 0:
             raise TryAgain
         resp = response["choices"][0]['message']['content']
         finish_reason = response["choices"][0]["finish_reason"]
-        usage = response.get("usage")
-        get_logger().info("AI response", response=resp, messages=messages, finish_reason=finish_reason,
-                          model=model, usage=usage)
+        print(resp, finish_reason)
         return resp, finish_reason

pr_agent/algo/file_filter.py

@@ -1,31 +0,0 @@
-import fnmatch
-import re
-
-from pr_agent.config_loader import get_settings
-
-def filter_ignored(files):
-    """
-    Filter out files that match the ignore patterns.
-    """
-
-    try:
-        # load regex patterns, and translate glob patterns to regex
-        patterns = get_settings().ignore.regex
-        patterns += [fnmatch.translate(glob) for glob in get_settings().ignore.glob]
-
-        # compile all valid patterns
-        compiled_patterns = []
-        for r in patterns:
-            try:
-                compiled_patterns.append(re.compile(r))
-            except re.error:
-                pass
-
-        # keep filenames that _don't_ match the ignore regex
-        for r in compiled_patterns:
-            files = [f for f in files if not r.match(f.filename)]
-
-    except Exception as e:
-        print(f"Could not filter file list: {e}")
-
-    return files

pr_agent/algo/git_patch_processing.py

@@ -1,9 +1,8 @@
 from __future__ import annotations
-
+import logging
 import re
 
 from pr_agent.config_loader import get_settings
-from pr_agent.log import get_logger
 
 
 def extend_patch(original_file_str, patch_str, num_lines) -> str:
@@ -41,16 +40,12 @@ def extend_patch(original_file_str, patch_str, num_lines) -> str:
                         extended_patch_lines.extend(
                             original_lines[start1 + size1 - 1:start1 + size1 - 1 + num_lines])
 
-                    res = list(match.groups())
-                    for i in range(len(res)):
-                        if res[i] is None:
-                            res[i] = 0
                     try:
-                        start1, size1, start2, size2 = map(int, res[:4])
+                        start1, size1, start2, size2 = map(int, match.groups()[:4])
                     except:  # '@@ -0,0 +1 @@' case
-                        start1, size1, size2 = map(int, res[:3])
+                        start1, size1, size2 = map(int, match.groups()[:3])
                         start2 = 0
-                    section_header = res[4]
+                    section_header = match.groups()[4]
                     extended_start1 = max(1, start1 - num_lines)
                     extended_size1 = size1 + (start1 - extended_start1) + num_lines
                     extended_start2 = max(1, start2 - num_lines)
@@ -64,7 +59,7 @@ def extend_patch(original_file_str, patch_str, num_lines) -> str:
             extended_patch_lines.append(line)
     except Exception as e:
         if get_settings().config.verbosity_level >= 2:
-            get_logger().error(f"Failed to extend patch: {e}")
+            logging.error(f"Failed to extend patch: {e}")
         return patch_str
 
     # finish previous hunk
@@ -135,14 +130,14 @@ def handle_patch_deletions(patch: str, original_file_content_str: str,
     if not new_file_content_str:
         # logic for handling deleted files - don't show patch, just show that the file was deleted
         if get_settings().config.verbosity_level > 0:
-            get_logger().info(f"Processing file: {file_name}, minimizing deletion file")
+            logging.info(f"Processing file: {file_name}, minimizing deletion file")
         patch = None # file was deleted
     else:
         patch_lines = patch.splitlines()
         patch_new = omit_deletion_hunks(patch_lines)
         if patch != patch_new:
             if get_settings().config.verbosity_level > 0:
-                get_logger().info(f"Processing file: {file_name}, hunks were deleted")
+                logging.info(f"Processing file: {file_name}, hunks were deleted")
             patch = patch_new
     return patch
 
@@ -212,15 +207,10 @@ __old hunk__
                 old_content_lines = []
             if match:
                 prev_header_line = header_line
-
-            res = list(match.groups())
-            for i in range(len(res)):
-                if res[i] is None:
-                    res[i] = 0
             try:
-                start1, size1, start2, size2 = map(int, res[:4])
+                start1, size1, start2, size2 = map(int, match.groups()[:4])
             except: # '@@ -0,0 +1 @@' case
-                start1, size1, size2 = map(int, res[:3])
+                start1, size1, size2 = map(int, match.groups()[:3])
                 start2 = 0
 
         elif line.startswith('+'):

pr_agent/algo/language_handler.py

@@ -42,11 +42,6 @@ def sort_files_by_main_languages(languages: Dict, files: list):
     files_sorted = []
     rest_files = {}
 
-    # if no languages detected, put all files in the "Other" category
-    if not languages:
-        files_sorted = [({"language": "Other", "files": list(files_filtered)})]
-        return files_sorted
-
     main_extensions_flat = []
     for ext in main_extensions:
         main_extensions_flat.extend(ext)

pr_agent/algo/pr_processing.py

@@ -1,6 +1,7 @@
 from __future__ import annotations
 
 import difflib
+import logging
 import re
 import traceback
 from typing import Any, Callable, List, Tuple
@@ -10,11 +11,9 @@ from github import RateLimitExceededException
 from pr_agent.algo import MAX_TOKENS
 from pr_agent.algo.git_patch_processing import convert_to_hunks_with_lines_numbers, extend_patch, handle_patch_deletions
 from pr_agent.algo.language_handler import sort_files_by_main_languages
-from pr_agent.algo.file_filter import filter_ignored
 from pr_agent.algo.token_handler import TokenHandler, get_token_encoder
 from pr_agent.config_loader import get_settings
 from pr_agent.git_providers.git_provider import FilePatchInfo, GitProvider
-from pr_agent.log import get_logger
 
 DELETED_FILES_ = "Deleted files:\n"
 
@@ -22,6 +21,7 @@ MORE_MODIFIED_FILES_ = "More modified files:\n"
 
 OUTPUT_BUFFER_TOKENS_SOFT_THRESHOLD = 1000
 OUTPUT_BUFFER_TOKENS_HARD_THRESHOLD = 600
+PATCH_EXTRA_LINES = 3
 
 def get_pr_diff(git_provider: GitProvider, token_handler: TokenHandler, model: str,
                 add_line_numbers_to_hunks: bool = False, disable_extra_lines: bool = False) -> str:
@@ -44,24 +44,21 @@ def get_pr_diff(git_provider: GitProvider, token_handler: TokenHandler, model: s
     """
 
     if disable_extra_lines:
+        global PATCH_EXTRA_LINES
         PATCH_EXTRA_LINES = 0
-    else:
-        PATCH_EXTRA_LINES = get_settings().config.patch_extra_lines
 
     try:
         diff_files = git_provider.get_diff_files()
     except RateLimitExceededException as e:
-        get_logger().error(f"Rate limit exceeded for git provider API. original message {e}")
+        logging.error(f"Rate limit exceeded for git provider API. original message {e}")
         raise
 
-    diff_files = filter_ignored(diff_files)
-
     # get pr languages
     pr_languages = sort_files_by_main_languages(git_provider.get_languages(), diff_files)
 
     # generate a standard diff string, with patch extension
-    patches_extended, total_tokens, patches_extended_tokens = pr_generate_extended_diff(
-        pr_languages, token_handler, add_line_numbers_to_hunks, patch_extra_lines=PATCH_EXTRA_LINES)
+    patches_extended, total_tokens, patches_extended_tokens = pr_generate_extended_diff(pr_languages, token_handler,
+                                                               add_line_numbers_to_hunks)
 
     # if we are under the limit, return the full diff
     if total_tokens + OUTPUT_BUFFER_TOKENS_SOFT_THRESHOLD < MAX_TOKENS[model]:
@@ -83,8 +80,7 @@ def get_pr_diff(git_provider: GitProvider, token_handler: TokenHandler, model: s
 
 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]:
+                              add_line_numbers_to_hunks: bool) -> 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.
@@ -106,7 +102,7 @@ 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)
+            extended_patch = extend_patch(original_file_content_str, patch, num_lines=PATCH_EXTRA_LINES)
             full_extended_patch = f"\n\n## {file.filename}\n\n{extended_patch}\n"
 
             if add_line_numbers_to_hunks:
@@ -180,7 +176,7 @@ def pr_generate_compressed_diff(top_langs: list, token_handler: TokenHandler, mo
 
         # Hard Stop, no more tokens
         if total_tokens > MAX_TOKENS[model] - OUTPUT_BUFFER_TOKENS_HARD_THRESHOLD:
-            get_logger().warning(f"File was fully skipped, no more tokens: {file.filename}.")
+            logging.warning(f"File was fully skipped, no more tokens: {file.filename}.")
             continue
 
         # If the patch is too large, just show the file name
@@ -189,7 +185,7 @@ def pr_generate_compressed_diff(top_langs: list, token_handler: TokenHandler, mo
             # TODO: Option for alternative logic to remove hunks from the patch to reduce the number of tokens
             #  until we meet the requirements
             if get_settings().config.verbosity_level >= 2:
-                get_logger().warning(f"Patch too large, minimizing it, {file.filename}")
+                logging.warning(f"Patch too large, minimizing it, {file.filename}")
             if not modified_files_list:
                 total_tokens += token_handler.count_tokens(MORE_MODIFIED_FILES_)
             modified_files_list.append(file.filename)
@@ -204,7 +200,7 @@ def pr_generate_compressed_diff(top_langs: list, token_handler: TokenHandler, mo
             patches.append(patch_final)
             total_tokens += token_handler.count_tokens(patch_final)
             if get_settings().config.verbosity_level >= 2:
-                get_logger().info(f"Tokens: {total_tokens}, last filename: {file.filename}")
+                logging.info(f"Tokens: {total_tokens}, last filename: {file.filename}")
 
     return patches, modified_files_list, deleted_files_list
 
@@ -218,7 +214,7 @@ async def retry_with_fallback_models(f: Callable):
             get_settings().set("openai.deployment_id", deployment_id)
             return await f(model)
         except Exception as e:
-            get_logger().warning(
+            logging.warning(
                 f"Failed to generate prediction with {model}"
                 f"{(' from deployment ' + deployment_id) if deployment_id else ''}: "
                 f"{traceback.format_exc()}"
@@ -340,7 +336,7 @@ def clip_tokens(text: str, max_tokens: int) -> str:
         clipped_text = text[:num_output_chars]
         return clipped_text
     except Exception as e:
-        get_logger().warning(f"Failed to clip tokens: {e}")
+        logging.warning(f"Failed to clip tokens: {e}")
         return text
 
 
@@ -351,27 +347,25 @@ def get_pr_multi_diffs(git_provider: GitProvider,
     """
     Retrieves the diff files from a Git provider, sorts them by main language, and generates patches for each file.
     The patches are split into multiple groups based on the maximum number of tokens allowed for the given model.
-
+    
     Args:
         git_provider (GitProvider): An object that provides access to Git provider APIs.
         token_handler (TokenHandler): An object that handles tokens in the context of a pull request.
         model (str): The name of the model.
         max_calls (int, optional): The maximum number of calls to retrieve diff files. Defaults to 5.
-
+    
     Returns:
         List[str]: A list of final diff strings, split into multiple groups based on the maximum number of tokens allowed for the given model.
-
+    
     Raises:
         RateLimitExceededException: If the rate limit for the Git provider API is exceeded.
     """
     try:
         diff_files = git_provider.get_diff_files()
     except RateLimitExceededException as e:
-        get_logger().error(f"Rate limit exceeded for git provider API. original message {e}")
+        logging.error(f"Rate limit exceeded for git provider API. original message {e}")
         raise
 
-    diff_files = filter_ignored(diff_files)
-
     # Sort files by main language
     pr_languages = sort_files_by_main_languages(git_provider.get_languages(), diff_files)
 
@@ -387,7 +381,7 @@ def get_pr_multi_diffs(git_provider: GitProvider,
     for file in sorted_files:
         if call_number > max_calls:
             if get_settings().config.verbosity_level >= 2:
-                get_logger().info(f"Reached max calls ({max_calls})")
+                logging.info(f"Reached max calls ({max_calls})")
             break
 
         original_file_content_str = file.base_file
@@ -410,13 +404,13 @@ def get_pr_multi_diffs(git_provider: GitProvider,
             total_tokens = token_handler.prompt_tokens
             call_number += 1
             if get_settings().config.verbosity_level >= 2:
-                get_logger().info(f"Call number: {call_number}")
+                logging.info(f"Call number: {call_number}")
 
         if patch:
             patches.append(patch)
             total_tokens += new_patch_tokens
             if get_settings().config.verbosity_level >= 2:
-                get_logger().info(f"Tokens: {total_tokens}, last filename: {file.filename}")
+                logging.info(f"Tokens: {total_tokens}, last filename: {file.filename}")
 
     # Add the last chunk
     if patches:

pr_agent/algo/token_handler.py

@@ -21,7 +21,7 @@ class TokenHandler:
       method.
     """
 
-    def __init__(self, pr=None, vars: dict = {}, system="", user=""):
+    def __init__(self, pr, vars: dict, system, user):
         """
         Initializes the TokenHandler object.
 
@@ -32,8 +32,7 @@ class TokenHandler:
         - user: The user string.
         """
         self.encoder = get_token_encoder()
-        if pr is not None:
-            self.prompt_tokens = self._get_system_user_tokens(pr, self.encoder, vars, system, user)
+        self.prompt_tokens = self._get_system_user_tokens(pr, self.encoder, vars, system, user)
 
     def _get_system_user_tokens(self, pr, encoder, vars: dict, system, user):
         """

pr_agent/algo/utils.py

@@ -2,6 +2,7 @@ from __future__ import annotations
 
 import difflib
 import json
+import logging
 import re
 import textwrap
 from datetime import datetime
@@ -10,7 +11,6 @@ from typing import Any, List
 import yaml
 from starlette_context import context
 from pr_agent.config_loader import get_settings, global_settings
-from pr_agent.log import get_logger
 
 
 def get_setting(key: str) -> Any:
@@ -20,7 +20,7 @@ def get_setting(key: str) -> Any:
     except Exception:
         return global_settings.get(key, None)
 
-def convert_to_markdown(output_data: dict, gfm_supported: bool=True) -> str:
+def convert_to_markdown(output_data: dict) -> str:
     """
     Convert a dictionary of data into markdown format.
     Args:
@@ -42,7 +42,6 @@ def convert_to_markdown(output_data: dict, gfm_supported: bool=True) -> str:
         "General suggestions": "💡",
         "Insights from user's answers": "📝",
         "Code feedback": "🤖",
-        "Estimated effort to review [1-5]": "⏱️",
     }
 
     for key, value in output_data.items():
@@ -50,33 +49,27 @@ def convert_to_markdown(output_data: dict, gfm_supported: bool=True) -> str:
             continue
         if isinstance(value, dict):
             markdown_text += f"## {key}\n\n"
-            markdown_text += convert_to_markdown(value, gfm_supported)
+            markdown_text += convert_to_markdown(value)
         elif isinstance(value, list):
             emoji = emojis.get(key, "")
             if key.lower() == 'code feedback':
-                if gfm_supported:
-                    markdown_text += f"\n\n- **<details><summary> { emoji } Code feedback:**</summary>\n\n"
-                else:
-                    markdown_text += f"\n\n- **{emoji} Code feedback:**\n\n"
+                markdown_text += f"\n\n- **<details><summary> { emoji } Code feedback:**</summary>\n\n"
             else:
                 markdown_text += f"- {emoji} **{key}:**\n\n"
             for item in value:
                 if isinstance(item, dict) and key.lower() == 'code feedback':
-                    markdown_text += parse_code_suggestion(item, gfm_supported)
+                    markdown_text += parse_code_suggestion(item)
                 elif item:
                     markdown_text += f"  - {item}\n"
             if key.lower() == 'code feedback':
-                if gfm_supported:
-                    markdown_text += "</details>\n\n"
-                else:
-                    markdown_text += "\n\n"
+                markdown_text += "</details>\n\n"
         elif value != 'n/a':
             emoji = emojis.get(key, "")
             markdown_text += f"- {emoji} **{key}:** {value}\n"
     return markdown_text
 
 
-def parse_code_suggestion(code_suggestions: dict, gfm_supported: bool=True) -> str:
+def parse_code_suggestion(code_suggestions: dict) -> str:
     """
     Convert a dictionary of data into markdown format.
 
@@ -99,9 +92,6 @@ def parse_code_suggestion(code_suggestions: dict, gfm_supported: bool=True) -> s
                 markdown_text += f"\n  - **{sub_key}:** {sub_value}\n"
             else:
                 markdown_text += f"   **{sub_key}:** {sub_value}\n"
-            if not gfm_supported:
-                if "relevant line" not in sub_key.lower(): # nicer presentation
-                        markdown_text = markdown_text.rstrip('\n') + "\\\n"
 
     markdown_text += "\n"
     return markdown_text
@@ -159,7 +149,7 @@ def try_fix_json(review, max_iter=10, code_suggestions=False):
                 iter_count += 1
 
         if not valid_json:
-            get_logger().error("Unable to decode JSON response from AI")
+            logging.error("Unable to decode JSON response from AI")
             data = {}
 
     return data
@@ -178,7 +168,7 @@ def fix_json_escape_char(json_message=None):
     Raises:
         None
 
-    """
+    """    
     try:
         result = json.loads(json_message)
     except Exception as e:
@@ -205,7 +195,7 @@ def convert_str_to_datetime(date_str):
     Example:
         >>> convert_str_to_datetime('Mon, 01 Jan 2022 12:00:00 UTC')
         datetime.datetime(2022, 1, 1, 12, 0, 0)
-    """
+    """    
     datetime_format = '%a, %d %b %Y %H:%M:%S %Z'
     return datetime.strptime(date_str, datetime_format)
 
@@ -230,7 +220,7 @@ def load_large_diff(filename, new_file_content_str: str, original_file_content_s
         diff = difflib.unified_diff(original_file_content_str.splitlines(keepends=True),
                                     new_file_content_str.splitlines(keepends=True))
         if get_settings().config.verbosity_level >= 2:
-            get_logger().warning(f"File was modified, but no patch was found. Manually creating patch: {filename}.")
+            logging.warning(f"File was modified, but no patch was found. Manually creating patch: {filename}.")
         patch = ''.join(diff)
     except Exception:
         pass
@@ -262,12 +252,12 @@ def update_settings_from_args(args: List[str]) -> List[str]:
                 vals = arg.split('=', 1)
                 if len(vals) != 2:
                     if len(vals) > 2: # --extended is a valid argument
-                        get_logger().error(f'Invalid argument format: {arg}')
+                        logging.error(f'Invalid argument format: {arg}')
                     other_args.append(arg)
                     continue
                 key, value = _fix_key_value(*vals)
                 get_settings().set(key, value)
-                get_logger().info(f'Updated setting {key} to: "{value}"')
+                logging.info(f'Updated setting {key} to: "{value}"')
             else:
                 other_args.append(arg)
     return other_args
@@ -279,7 +269,7 @@ def _fix_key_value(key: str, value: str):
     try:
         value = yaml.safe_load(value)
     except Exception as e:
-        get_logger().error(f"Failed to parse YAML for config override {key}={value}", exc_info=e)
+        logging.error(f"Failed to parse YAML for config override {key}={value}", exc_info=e)
     return key, value
 
 
@@ -288,7 +278,7 @@ def load_yaml(review_text: str) -> dict:
     try:
         data = yaml.safe_load(review_text)
     except Exception as e:
-        get_logger().error(f"Failed to parse AI prediction: {e}")
+        logging.error(f"Failed to parse AI prediction: {e}")
         data = try_fix_yaml(review_text)
     return data
 
@@ -299,7 +289,7 @@ def try_fix_yaml(review_text: str) -> dict:
         review_text_lines_tmp = '\n'.join(review_text_lines[:-i])
         try:
             data = yaml.load(review_text_lines_tmp, Loader=yaml.SafeLoader)
-            get_logger().info(f"Successfully parsed AI prediction after removing {i} lines")
+            logging.info(f"Successfully parsed AI prediction after removing {i} lines")
             break
         except:
             pass

pr_agent/cli.py

@@ -1,12 +1,11 @@
 import argparse
 import asyncio
+import logging
 import os
 
 from pr_agent.agent.pr_agent import PRAgent, commands
 from pr_agent.config_loader import get_settings
-from pr_agent.log import setup_logger
 
-setup_logger()
 
 def run(inargs=None):
     parser = argparse.ArgumentParser(description='AI based pull request analyzer', usage=
@@ -18,7 +17,6 @@ For example:
 - cli.py --pr_url=... improve
 - cli.py --pr_url=... ask "write me a poem about this PR"
 - cli.py --pr_url=... reflect
-- cli.py --issue_url=... similar_issue
 
 Supported commands:
 -review / review_pr - Add a review that includes a summary of the PR and specific suggestions for improvement.
@@ -39,21 +37,14 @@ Configuration:
 To edit any configuration parameter from 'configuration.toml', just add -config_path=<value>.
 For example: 'python cli.py --pr_url=... review --pr_reviewer.extra_instructions="focus on the file: ..."'
 """)
-    parser.add_argument('--pr_url', type=str, help='The URL of the PR to review', default=None)
-    parser.add_argument('--issue_url', type=str, help='The URL of the Issue to review', default=None)
+    parser.add_argument('--pr_url', type=str, help='The URL of the PR to review', required=True)
     parser.add_argument('command', type=str, help='The', choices=commands, default='review')
     parser.add_argument('rest', nargs=argparse.REMAINDER, default=[])
     args = parser.parse_args(inargs)
-    if not args.pr_url and not args.issue_url:
-        parser.print_help()
-        return
-
+    logging.basicConfig(level=os.environ.get("LOGLEVEL", "INFO"))
     command = args.command.lower()
     get_settings().set("CONFIG.CLI_MODE", True)
-    if args.issue_url:
-        result = asyncio.run(PRAgent().handle_request(args.issue_url, command + " " + " ".join(args.rest)))
-    else:
-        result = asyncio.run(PRAgent().handle_request(args.pr_url, command + " " + " ".join(args.rest)))
+    result = asyncio.run(PRAgent().handle_request(args.pr_url, command + " " + " ".join(args.rest)))
     if not result:
         parser.print_help()
 

pr_agent/config_loader.py

@@ -14,7 +14,6 @@ global_settings = Dynaconf(
     settings_files=[join(current_dir, f) for f in [
         "settings/.secrets.toml",
         "settings/configuration.toml",
-        "settings/ignore.toml",
         "settings/language_extensions.toml",
         "settings/pr_reviewer_prompts.toml",
         "settings/pr_questions_prompts.toml",
@@ -23,7 +22,6 @@ global_settings = Dynaconf(
         "settings/pr_sort_code_suggestions_prompts.toml",
         "settings/pr_information_from_user_prompts.toml",
         "settings/pr_update_changelog_prompts.toml",
-        "settings/pr_add_docs.toml",
         "settings_prod/.secrets.toml"
     ]]
 )

pr_agent/git_providers/azuredevops_provider.py

@@ -1,11 +1,10 @@
 import json
+import logging
 from typing import Optional, Tuple
 from urllib.parse import urlparse
 
 import os
 
-from ..log import get_logger
-
 AZURE_DEVOPS_AVAILABLE = True
 try:
     from msrest.authentication import BasicAuthentication
@@ -39,8 +38,7 @@ class AzureDevopsProvider:
             self.set_pr(pr_url)
 
     def is_supported(self, capability: str) -> bool:
-        if capability in ['get_issue_comments', 'create_inline_comment', 'publish_inline_comments', 'get_labels',
-                          'remove_initial_comment', 'gfm_markdown']:
+        if capability in ['get_issue_comments', 'create_inline_comment', 'publish_inline_comments', 'get_labels', 'remove_initial_comment']:
             return False
         return True
 
@@ -56,7 +54,7 @@ class AzureDevopsProvider:
                                                                  path=".pr_agent.toml")
             return contents
         except Exception as e:
-            get_logger().exception("get repo settings error")
+            logging.exception("get repo settings error")
             return ""
 
     def get_files(self):
@@ -89,8 +87,6 @@ class AzureDevopsProvider:
                 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']
 
@@ -101,18 +97,14 @@ class AzureDevopsProvider:
                     continue
 
                 version = GitVersionDescriptor(version=head_sha.commit_id, version_type='commit')
-                try:
-                    new_file_content_str = self.azure_devops_client.get_item(repository_id=self.repo_slug,
-                                                                            path=file,
-                                                                            project=self.workspace_slug,
-                                                                            version_descriptor=version,
-                                                                            download=False,
-                                                                            include_content=True)
+                new_file_content_str = self.azure_devops_client.get_item(repository_id=self.repo_slug,
+                                                                         path=file,
+                                                                         project=self.workspace_slug,
+                                                                         version_descriptor=version,
+                                                                         download=False,
+                                                                         include_content=True)
 
-                    new_file_content_str = new_file_content_str.content
-                except Exception as error:
-                    get_logger().error("Failed to retrieve new file content of %s at version %s. Error: %s", file, version, str(error))
-                    new_file_content_str = ""
+                new_file_content_str = new_file_content_str.content
 
                 edit_type = EDIT_TYPE.MODIFIED
                 if diff_types[file] == 'add':
@@ -123,17 +115,13 @@ class AzureDevopsProvider:
                     edit_type = EDIT_TYPE.RENAMED
 
                 version = GitVersionDescriptor(version=base_sha.commit_id, version_type='commit')
-                try:
-                    original_file_content_str = self.azure_devops_client.get_item(repository_id=self.repo_slug,
+                original_file_content_str = self.azure_devops_client.get_item(repository_id=self.repo_slug,
                                                                               path=file,
                                                                               project=self.workspace_slug,
                                                                               version_descriptor=version,
                                                                               download=False,
                                                                               include_content=True)
-                    original_file_content_str = original_file_content_str.content
-                except Exception as error:
-                    get_logger().error("Failed to retrieve original file content of %s at version %s. Error: %s", file, version, str(error))
-                    original_file_content_str = ""
+                original_file_content_str = original_file_content_str.content
 
                 patch = load_large_diff(file, new_file_content_str, original_file_content_str)
 
@@ -167,7 +155,7 @@ class AzureDevopsProvider:
                                                          pull_request_id=self.pr_num,
                                                          git_pull_request_to_update=updated_pr)
         except Exception as e:
-            get_logger().exception(f"Could not update pull request {self.pr_num} description: {e}")
+            logging.exception(f"Could not update pull request {self.pr_num} description: {e}")
 
     def remove_initial_comment(self):
         return ""  # not implemented yet

pr_agent/git_providers/bitbucket_provider.py

@@ -1,4 +1,5 @@
 import json
+import logging
 from typing import Optional, Tuple
 from urllib.parse import urlparse
 
@@ -6,9 +7,7 @@ import requests
 from atlassian.bitbucket import Cloud
 from starlette_context import context
 
-from ..algo.pr_processing import find_line_number_of_relevant_line_in_file
 from ..config_loader import get_settings
-from ..log import get_logger
 from .git_provider import FilePatchInfo, GitProvider
 
 
@@ -36,8 +35,9 @@ class BitbucketProvider(GitProvider):
         self.incremental = incremental
         if pr_url:
             self.set_pr(pr_url)
-        self.bitbucket_comment_api_url = self.pr._BitbucketBase__data["links"]["comments"]["href"]
-        self.bitbucket_pull_request_api_url = self.pr._BitbucketBase__data["links"]['self']['href']
+        self.bitbucket_comment_api_url = self.pr._BitbucketBase__data["links"][
+            "comments"
+        ]["href"]
 
     def get_repo_settings(self):
         try:
@@ -61,14 +61,14 @@ class BitbucketProvider(GitProvider):
 
             if not relevant_lines_start or relevant_lines_start == -1:
                 if get_settings().config.verbosity_level >= 2:
-                    get_logger().exception(
+                    logging.exception(
                         f"Failed to publish code suggestion, relevant_lines_start is {relevant_lines_start}"
                     )
                 continue
 
             if relevant_lines_end < relevant_lines_start:
                 if get_settings().config.verbosity_level >= 2:
-                    get_logger().exception(
+                    logging.exception(
                         f"Failed to publish code suggestion, "
                         f"relevant_lines_end is {relevant_lines_end} and "
                         f"relevant_lines_start is {relevant_lines_start}"
@@ -97,11 +97,16 @@ class BitbucketProvider(GitProvider):
             return True
         except Exception as e:
             if get_settings().config.verbosity_level >= 2:
-                get_logger().error(f"Failed to publish code suggestion, error: {e}")
+                logging.error(f"Failed to publish code suggestion, error: {e}")
             return False
 
     def is_supported(self, capability: str) -> bool:
-        if capability in ['get_issue_comments', 'publish_inline_comments', 'get_labels', 'gfm_markdown']:
+        if capability in [
+            "get_issue_comments",
+            "create_inline_comment",
+            "publish_inline_comments",
+            "get_labels",
+        ]:
             return False
         return True
 
@@ -144,32 +149,19 @@ class BitbucketProvider(GitProvider):
             for comment in self.temp_comments:
                 self.pr.delete(f"comments/{comment}")
         except Exception as e:
-            get_logger().exception(f"Failed to remove temp comments, error: {e}")
+            logging.exception(f"Failed to remove temp comments, error: {e}")
 
-
-    # funtion to create_inline_comment
-    def create_inline_comment(self, body: str, relevant_file: str, relevant_line_in_file: str):
-        position, absolute_position = find_line_number_of_relevant_line_in_file(self.get_diff_files(), relevant_file.strip('`'), relevant_line_in_file)
-        if position == -1:
-            if get_settings().config.verbosity_level >= 2:
-                get_logger().info(f"Could not find position for {relevant_file} {relevant_line_in_file}")
-            subject_type = "FILE"
-        else:
-            subject_type = "LINE"
-        path = relevant_file.strip()
-        return dict(body=body, path=path, position=absolute_position) if subject_type == "LINE" else {}
-
-
-    def publish_inline_comment(self, comment: str, from_line: int, file: str):
-        payload = json.dumps( {
-            "content": {
-                "raw": comment,
-            },
-            "inline": {
-                "to": from_line,
-                "path": file
-            },
-        })
+    def publish_inline_comment(
+        self, comment: str, from_line: int, to_line: int, file: str
+    ):
+        payload = json.dumps(
+            {
+                "content": {
+                    "raw": comment,
+                },
+                "inline": {"to": from_line, "path": file},
+            }
+        )
         response = requests.request(
             "POST", self.bitbucket_comment_api_url, data=payload, headers=self.headers
         )
@@ -177,7 +169,9 @@ class BitbucketProvider(GitProvider):
 
     def publish_inline_comments(self, comments: list[dict]):
         for comment in comments:
-            self.publish_inline_comment(comment['body'], comment['start_line'], comment['path'])
+            self.publish_inline_comment(
+                comment["body"], comment["start_line"], comment["line"], comment["path"]
+            )
 
     def get_title(self):
         return self.pr.title
@@ -244,22 +238,16 @@ class BitbucketProvider(GitProvider):
 
     def get_commit_messages(self):
         return ""  # not implemented yet
-    
-    # bitbucket does not support labels
-    def publish_description(self, pr_title: str, description: str):
-        payload = json.dumps({
-            "description": description,
-            "title": pr_title
 
-            })
-
-        response = requests.request("PUT", self.bitbucket_pull_request_api_url, headers=self.headers, data=payload)
-        return response
-
-    # bitbucket does not support labels
-    def publish_labels(self, pr_types: list):
+    def publish_description(self, pr_title: str, pr_body: str):
         pass
-    
-    # bitbucket does not support labels
+    def create_inline_comment(
+        self, body: str, relevant_file: str, relevant_line_in_file: str
+    ):
+        pass
+
+    def publish_labels(self, labels):
+        pass
+
     def get_labels(self):
         pass

pr_agent/git_providers/codecommit_client.py

@@ -54,16 +54,11 @@ class CodeCommitClient:
     def __init__(self):
         self.boto_client = None
 
-    def is_supported(self, capability: str) -> bool:
-        if capability in ["gfm_markdown"]:
-            return False
-        return True
-
     def _connect_boto_client(self):
         try:
             self.boto_client = boto3.client("codecommit")
         except Exception as e:
-            raise ValueError(f"Failed to connect to AWS CodeCommit: {e}") from e
+            raise ValueError(f"Failed to connect to AWS CodeCommit: {e}")
 
     def get_differences(self, repo_name: int, destination_commit: str, source_commit: str):
         """

pr_agent/git_providers/codecommit_provider.py

@@ -1,15 +1,16 @@
+import logging
 import os
 import re
 from collections import Counter
 from typing import List, Optional, Tuple
 from urllib.parse import urlparse
 
-from pr_agent.git_providers.codecommit_client import CodeCommitClient
-
 from ..algo.language_handler import is_valid_file, language_extension_map
+from ..algo.pr_processing import clip_tokens
 from ..algo.utils import load_large_diff
-from .git_provider import EDIT_TYPE, FilePatchInfo, GitProvider
-from ..log import get_logger
+from ..config_loader import get_settings
+from .git_provider import EDIT_TYPE, FilePatchInfo, GitProvider, IncrementalPR
+from pr_agent.git_providers.codecommit_client import CodeCommitClient
 
 
 class PullRequestCCMimic:
@@ -73,7 +74,6 @@ class CodeCommitProvider(GitProvider):
             "create_inline_comment",
             "publish_inline_comments",
             "get_labels",
-            "gfm_markdown"
         ]:
             return False
         return True
@@ -165,7 +165,7 @@ class CodeCommitProvider(GitProvider):
 
     def publish_comment(self, pr_comment: str, is_temporary: bool = False):
         if is_temporary:
-            get_logger().info(pr_comment)
+            logging.info(pr_comment)
             return
 
         pr_comment = CodeCommitProvider._remove_markdown_html(pr_comment)
@@ -187,12 +187,12 @@ class CodeCommitProvider(GitProvider):
         for suggestion in code_suggestions:
             # Verify that each suggestion has the required keys
             if not all(key in suggestion for key in ["body", "relevant_file", "relevant_lines_start"]):
-                get_logger().warning(f"Skipping code suggestion #{counter}: Each suggestion must have 'body', 'relevant_file', 'relevant_lines_start' keys")
+                logging.warning(f"Skipping code suggestion #{counter}: Each suggestion must have 'body', 'relevant_file', 'relevant_lines_start' keys")
                 continue
        
             # Publish the code suggestion to CodeCommit
             try:
-                get_logger().debug(f"Code Suggestion #{counter} in file: {suggestion['relevant_file']}: {suggestion['relevant_lines_start']}")
+                logging.debug(f"Code Suggestion #{counter} in file: {suggestion['relevant_file']}: {suggestion['relevant_lines_start']}")
                 self.codecommit_client.publish_comment(
                     repo_name=self.repo_name,
                     pr_number=self.pr_num,
@@ -232,20 +232,8 @@ class CodeCommitProvider(GitProvider):
         raise NotImplementedError("CodeCommit provider does not support publishing inline comments yet")
 
     def get_title(self):
-        return self.pr.title
+        return self.pr.get("title", "")
 
-    def get_pr_id(self):
-        """
-        Returns the PR ID in the format: "repo_name/pr_number".
-        Note: This is an internal identifier for PR-Agent, 
-        and is not the same as the CodeCommit PR identifier.
-        """
-        try:
-            pr_id = f"{self.repo_name}/{self.pr_num}"
-            return pr_id
-        except:
-            return ""
-        
     def get_languages(self):
         """
         Returns a dictionary of languages, containing the percentage of each language used in the PR.
@@ -295,11 +283,11 @@ class CodeCommitProvider(GitProvider):
         return self.codecommit_client.get_file(self.repo_name, settings_filename, self.pr.source_commit, optional=True)
 
     def add_eyes_reaction(self, issue_comment_id: int) -> Optional[int]:
-        get_logger().info("CodeCommit provider does not support eyes reaction yet")
+        logging.info("CodeCommit provider does not support eyes reaction yet")
         return True
 
     def remove_reaction(self, issue_comment_id: int, reaction_id: int) -> bool:
-        get_logger().info("CodeCommit provider does not support removing reactions yet")
+        logging.info("CodeCommit provider does not support removing reactions yet")
         return True
 
     @staticmethod
@@ -365,7 +353,7 @@ class CodeCommitProvider(GitProvider):
         # TODO: implement support for multiple targets in one CodeCommit PR
         #       for now, we are only using the first target in the PR
         if len(response.targets) > 1:
-            get_logger().warning(
+            logging.warning(
                 "Multiple targets in one PR is not supported for CodeCommit yet. Continuing, using the first target only..."
             )
 

pr_agent/git_providers/gerrit_provider.py

@@ -1,4 +1,5 @@
 import json
+import logging
 import os
 import pathlib
 import shutil
@@ -6,16 +7,18 @@ import subprocess
 import uuid
 from collections import Counter, namedtuple
 from pathlib import Path
-from tempfile import NamedTemporaryFile, mkdtemp
+from tempfile import mkdtemp, NamedTemporaryFile
 
 import requests
 import urllib3.util
 from git import Repo
 
 from pr_agent.config_loader import get_settings
-from pr_agent.git_providers.git_provider import EDIT_TYPE, FilePatchInfo, GitProvider
+from pr_agent.git_providers.git_provider import GitProvider, FilePatchInfo, \
+    EDIT_TYPE
 from pr_agent.git_providers.local_git_provider import PullRequestMimic
-from pr_agent.log import get_logger
+
+logger = logging.getLogger(__name__)
 
 
 def _call(*command, **kwargs) -> (int, str, str):
@@ -30,42 +33,42 @@ def _call(*command, **kwargs) -> (int, str, str):
 
 
 def clone(url, directory):
-    get_logger().info("Cloning %s to %s", url, directory)
+    logger.info("Cloning %s to %s", url, directory)
     stdout = _call('git', 'clone', "--depth", "1", url, directory)
-    get_logger().info(stdout)
+    logger.info(stdout)
 
 
 def fetch(url, refspec, cwd):
-    get_logger().info("Fetching %s %s", url, refspec)
+    logger.info("Fetching %s %s", url, refspec)
     stdout = _call(
         'git', 'fetch', '--depth', '2', url, refspec,
         cwd=cwd
     )
-    get_logger().info(stdout)
+    logger.info(stdout)
 
 
 def checkout(cwd):
-    get_logger().info("Checking out")
+    logger.info("Checking out")
     stdout = _call('git', 'checkout', "FETCH_HEAD", cwd=cwd)
-    get_logger().info(stdout)
+    logger.info(stdout)
 
 
 def show(*args, cwd=None):
-    get_logger().info("Show")
+    logger.info("Show")
     return _call('git', 'show', *args, cwd=cwd)
 
 
 def diff(*args, cwd=None):
-    get_logger().info("Diff")
+    logger.info("Diff")
     patch = _call('git', 'diff', *args, cwd=cwd)
     if not patch:
-        get_logger().warning("No changes found")
+        logger.warning("No changes found")
         return
     return patch
 
 
 def reset_local_changes(cwd):
-    get_logger().info("Reset local changes")
+    logger.info("Reset local changes")
     _call('git', 'checkout', "--force", cwd=cwd)
 
 
@@ -112,14 +115,7 @@ def adopt_to_gerrit_message(message):
     lines = message.splitlines()
     buf = []
     for line in lines:
-        # remove markdown formatting
-        line = (line.replace("*", "")
-                .replace("``", "`")
-                .replace("<details>", "")
-                .replace("</details>", "")
-                .replace("<summary>", "")
-                .replace("</summary>", ""))
-
+        line = line.replace("*", "").replace("``", "`")
         line = line.strip()
         if line.startswith('#'):
             buf.append("\n" +
@@ -223,12 +219,10 @@ class GerritProvider(GitProvider):
         return [self.repo.head.commit.message]
 
     def get_repo_settings(self):
-        try:
-            with open(self.repo_path / ".pr_agent.toml", 'rb') as f:
-                contents = f.read()
-            return contents
-        except OSError:
-            return b""
+        """
+        TODO: Implement support of .pr_agent.toml
+        """
+        return ""
 
     def get_diff_files(self) -> list[FilePatchInfo]:
         diffs = self.repo.head.commit.diff(
@@ -310,8 +304,7 @@ class GerritProvider(GitProvider):
             # 'get_issue_comments',
             'create_inline_comment',
             'publish_inline_comments',
-            'get_labels',
-            'gfm_markdown'
+            'get_labels'
         ]:
             return False
         return True

pr_agent/git_providers/git_provider.py

@@ -1,3 +1,4 @@
+import logging
 from abc import ABC, abstractmethod
 from dataclasses import dataclass
 
@@ -5,8 +6,6 @@ from dataclasses import dataclass
 from enum import Enum
 from typing import Optional
 
-from pr_agent.log import get_logger
-
 
 class EDIT_TYPE(Enum):
     ADDED = 1
@@ -128,18 +127,11 @@ class GitProvider(ABC):
     def get_commit_messages(self):
         pass
 
-    def get_pr_id(self):
-        return ""
-
 def get_main_pr_language(languages, files) -> str:
     """
     Get the main language of the commit. Return an empty string if cannot determine.
     """
     main_language_str = ""
-    if not languages:
-        get_logger().info("No languages detected")
-        return main_language_str
-
     try:
         top_language = max(languages, key=languages.get).lower()
 
@@ -173,7 +165,7 @@ def get_main_pr_language(languages, files) -> str:
             main_language_str = top_language
 
     except Exception as e:
-        get_logger().exception(e)
+        logging.exception(e)
         pass
 
     return main_language_str

pr_agent/git_providers/github_provider.py

@@ -1,19 +1,20 @@
+import logging
 import hashlib
+
 from datetime import datetime
-from typing import Optional, Tuple
+from typing import Optional, Tuple, Any
 from urllib.parse import urlparse
 
-from github import AppAuthentication, Auth, Github, GithubException
+from github import AppAuthentication, Auth, Github, GithubException, Reaction
 from retry import retry
 from starlette_context import context
 
-from ..algo.language_handler import is_valid_file
-from ..algo.pr_processing import clip_tokens, find_line_number_of_relevant_line_in_file
-from ..algo.utils import load_large_diff
-from ..config_loader import get_settings
-from ..log import get_logger
-from ..servers.utils import RateLimitExceeded
 from .git_provider import FilePatchInfo, GitProvider, IncrementalPR
+from ..algo.language_handler import is_valid_file
+from ..algo.utils import load_large_diff
+from ..algo.pr_processing import find_line_number_of_relevant_line_in_file, clip_tokens
+from ..config_loader import get_settings
+from ..servers.utils import RateLimitExceeded
 
 
 class GithubProvider(GitProvider):
@@ -31,7 +32,7 @@ class GithubProvider(GitProvider):
         self.diff_files = None
         self.git_files = None
         self.incremental = incremental
-        if pr_url and 'pull' in pr_url:
+        if pr_url:
             self.set_pr(pr_url)
             self.last_commit_id = list(self.pr.get_commits())[-1]
 
@@ -57,7 +58,7 @@ class GithubProvider(GitProvider):
             self.file_set = dict()
             for commit in self.incremental.commits_range:
                 if commit.commit.message.startswith(f"Merge branch '{self._get_repo().default_branch}'"):
-                    get_logger().info(f"Skipping merge commit {commit.commit.message}")
+                    logging.info(f"Skipping merge commit {commit.commit.message}")
                     continue
                 self.file_set.update({file.filename: file for file in commit.files})
 
@@ -129,7 +130,7 @@ class GithubProvider(GitProvider):
             return diff_files
 
         except GithubException.RateLimitExceededException as e:
-            get_logger().error(f"Rate limit exceeded for GitHub API. Original message: {e}")
+            logging.error(f"Rate limit exceeded for GitHub API. Original message: {e}")
             raise RateLimitExceeded("Rate limit exceeded for GitHub API.") from e
 
     def publish_description(self, pr_title: str, pr_body: str):
@@ -137,7 +138,7 @@ class GithubProvider(GitProvider):
 
     def publish_comment(self, pr_comment: str, is_temporary: bool = False):
         if is_temporary and not get_settings().config.publish_output_progress:
-            get_logger().debug(f"Skipping publish_comment for temporary comment: {pr_comment}")
+            logging.debug(f"Skipping publish_comment for temporary comment: {pr_comment}")
             return
         response = self.pr.create_issue_comment(pr_comment)
         if hasattr(response, "user") and hasattr(response.user, "login"):
@@ -155,7 +156,7 @@ class GithubProvider(GitProvider):
         position, absolute_position = find_line_number_of_relevant_line_in_file(self.diff_files, relevant_file.strip('`'), relevant_line_in_file)
         if position == -1:
             if get_settings().config.verbosity_level >= 2:
-                get_logger().info(f"Could not find position for {relevant_file} {relevant_line_in_file}")
+                logging.info(f"Could not find position for {relevant_file} {relevant_line_in_file}")
             subject_type = "FILE"
         else:
             subject_type = "LINE"
@@ -178,13 +179,13 @@ class GithubProvider(GitProvider):
 
             if not relevant_lines_start or relevant_lines_start == -1:
                 if get_settings().config.verbosity_level >= 2:
-                    get_logger().exception(
+                    logging.exception(
                         f"Failed to publish code suggestion, relevant_lines_start is {relevant_lines_start}")
                 continue
 
             if relevant_lines_end < relevant_lines_start:
                 if get_settings().config.verbosity_level >= 2:
-                    get_logger().exception(f"Failed to publish code suggestion, "
+                    logging.exception(f"Failed to publish code suggestion, "
                                       f"relevant_lines_end is {relevant_lines_end} and "
                                       f"relevant_lines_start is {relevant_lines_start}")
                 continue
@@ -211,7 +212,7 @@ class GithubProvider(GitProvider):
             return True
         except Exception as e:
             if get_settings().config.verbosity_level >= 2:
-                get_logger().error(f"Failed to publish code suggestion, error: {e}")
+                logging.error(f"Failed to publish code suggestion, error: {e}")
             return False
 
     def remove_initial_comment(self):
@@ -220,7 +221,7 @@ class GithubProvider(GitProvider):
                 if comment.is_temporary:
                     comment.delete()
         except Exception as e:
-            get_logger().exception(f"Failed to remove initial comment, error: {e}")
+            logging.exception(f"Failed to remove initial comment, error: {e}")
 
     def get_title(self):
         return self.pr.title
@@ -238,10 +239,9 @@ class GithubProvider(GitProvider):
     def get_user_id(self):
         if not self.github_user_id:
             try:
-                self.github_user_id = self.github_client.get_user().raw_data['login']
+                self.github_user_id = self.github_client.get_user().login
             except Exception as e:
-                self.github_user_id = ""
-                # logging.exception(f"Failed to get user id, error: {e}")
+                logging.exception(f"Failed to get user id, error: {e}")
         return self.github_user_id
 
     def get_notifications(self, since: datetime):
@@ -268,7 +268,7 @@ class GithubProvider(GitProvider):
             reaction = self.pr.get_issue_comment(issue_comment_id).create_reaction("eyes")
             return reaction.id
         except Exception as e:
-            get_logger().exception(f"Failed to add eyes reaction, error: {e}")
+            logging.exception(f"Failed to add eyes reaction, error: {e}")
             return None
 
     def remove_reaction(self, issue_comment_id: int, reaction_id: int) -> bool:
@@ -276,7 +276,7 @@ class GithubProvider(GitProvider):
             self.pr.get_issue_comment(issue_comment_id).delete_reaction(reaction_id)
             return True
         except Exception as e:
-            get_logger().exception(f"Failed to remove eyes reaction, error: {e}")
+            logging.exception(f"Failed to remove eyes reaction, error: {e}")
             return False
 
 
@@ -309,35 +309,6 @@ class GithubProvider(GitProvider):
 
         return repo_name, pr_number
 
-    @staticmethod
-    def _parse_issue_url(issue_url: str) -> Tuple[str, int]:
-        parsed_url = urlparse(issue_url)
-
-        if 'github.com' not in parsed_url.netloc:
-            raise ValueError("The provided URL is not a valid GitHub URL")
-
-        path_parts = parsed_url.path.strip('/').split('/')
-        if 'api.github.com' in parsed_url.netloc:
-            if len(path_parts) < 5 or path_parts[3] != 'issues':
-                raise ValueError("The provided URL does not appear to be a GitHub ISSUE URL")
-            repo_name = '/'.join(path_parts[1:3])
-            try:
-                issue_number = int(path_parts[4])
-            except ValueError as e:
-                raise ValueError("Unable to convert issue number to integer") from e
-            return repo_name, issue_number
-
-        if len(path_parts) < 4 or path_parts[2] != 'issues':
-            raise ValueError("The provided URL does not appear to be a GitHub PR issue")
-
-        repo_name = '/'.join(path_parts[:2])
-        try:
-            issue_number = int(path_parts[3])
-        except ValueError as e:
-            raise ValueError("Unable to convert issue number to integer") from e
-
-        return repo_name, issue_number
-
     def _get_github_client(self):
         deployment_type = get_settings().get("GITHUB.DEPLOYMENT_TYPE", "user")
 
@@ -395,13 +366,13 @@ 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}")
+            logging.exception(f"Failed to publish labels, error: {e}")
 
     def get_labels(self):
         try:
             return [label.name for label in self.pr.labels]
         except Exception as e:
-            get_logger().exception(f"Failed to get labels, error: {e}")
+            logging.exception(f"Failed to get labels, error: {e}")
             return []
 
     def get_commit_messages(self):
@@ -443,13 +414,6 @@ class GithubProvider(GitProvider):
                 return link
         except Exception as e:
             if get_settings().config.verbosity_level >= 2:
-                get_logger().info(f"Failed adding line link, error: {e}")
+                logging.info(f"Failed adding line link, error: {e}")
 
         return ""
-
-    def get_pr_id(self):
-        try:
-            pr_id = f"{self.repo}/{self.pr_num}"
-            return pr_id
-        except:
-            return ""

pr_agent/git_providers/gitlab_provider.py

@@ -1,4 +1,4 @@
-import hashlib
+import logging
 import re
 from typing import Optional, Tuple
 from urllib.parse import urlparse
@@ -7,12 +7,12 @@ import gitlab
 from gitlab import GitlabGetError
 
 from ..algo.language_handler import is_valid_file
-from ..algo.pr_processing import clip_tokens, find_line_number_of_relevant_line_in_file
+from ..algo.pr_processing import clip_tokens
 from ..algo.utils import load_large_diff
 from ..config_loader import get_settings
 from .git_provider import EDIT_TYPE, FilePatchInfo, GitProvider
-from ..log import get_logger
 
+logger = logging.getLogger()
 
 class DiffNotFoundError(Exception):
     """Raised when the diff for a merge request cannot be found."""
@@ -43,7 +43,7 @@ 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']:
+        if capability in ['get_issue_comments', 'create_inline_comment', 'publish_inline_comments']:
             return False
         return True
 
@@ -58,7 +58,7 @@ class GitLabProvider(GitProvider):
         try:
             self.last_diff = self.mr.diffs.list(get_all=True)[-1]
         except IndexError as e:
-            get_logger().error(f"Could not get diff for merge request {self.id_mr}")
+            logger.error(f"Could not get diff for merge request {self.id_mr}")
             raise DiffNotFoundError(f"Could not get diff for merge request {self.id_mr}") from e
 
 
@@ -98,7 +98,7 @@ class GitLabProvider(GitProvider):
                     if isinstance(new_file_content_str, bytes):
                         new_file_content_str = bytes.decode(new_file_content_str, 'utf-8')
                 except UnicodeDecodeError:
-                    get_logger().warning(
+                    logging.warning(
                         f"Cannot decode file {diff['old_path']} or {diff['new_path']} in merge request {self.id_mr}")
 
                 edit_type = EDIT_TYPE.MODIFIED
@@ -134,7 +134,7 @@ class GitLabProvider(GitProvider):
             self.mr.description = pr_body
             self.mr.save()
         except Exception as e:
-            get_logger().exception(f"Could not update merge request {self.id_mr} description: {e}")
+            logging.exception(f"Could not update merge request {self.id_mr} description: {e}")
 
     def publish_comment(self, mr_comment: str, is_temporary: bool = False):
         comment = self.mr.notes.create({'body': mr_comment})
@@ -156,12 +156,12 @@ class GitLabProvider(GitProvider):
     def send_inline_comment(self,body: str,edit_type: str,found: bool,relevant_file: str,relevant_line_in_file: int,
                             source_line_no: int, target_file: str,target_line_no: int) -> None:
         if not found:
-            get_logger().info(f"Could not find position for {relevant_file} {relevant_line_in_file}")
+            logging.info(f"Could not find position for {relevant_file} {relevant_line_in_file}")
         else:
             # in order to have exact sha's we have to find correct diff for this change
             diff = self.get_relevant_diff(relevant_file, relevant_line_in_file)
             if diff is None:
-                get_logger().error(f"Could not get diff for merge request {self.id_mr}")
+                logger.error(f"Could not get diff for merge request {self.id_mr}")
                 raise DiffNotFoundError(f"Could not get diff for merge request {self.id_mr}")
             pos_obj = {'position_type': 'text',
                        'new_path': target_file.filename,
@@ -174,23 +174,24 @@ 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}")
-            self.mr.discussions.create({'body': body, 'position': pos_obj})
+            logging.debug(f"Creating comment in {self.id_mr} with body {body} and position {pos_obj}")
+            self.mr.discussions.create({'body': body,
+                                        'position': pos_obj})
 
     def get_relevant_diff(self, relevant_file: str, relevant_line_in_file: int) -> Optional[dict]:
         changes = self.mr.changes()  # Retrieve the changes for the merge request once
         if not changes:
-            get_logger().error('No changes found for the merge request.')
+            logging.error('No changes found for the merge request.')
             return None
         all_diffs = self.mr.diffs.list(get_all=True)
         if not all_diffs:
-            get_logger().error('No diffs found for the merge request.')
+            logging.error('No diffs found for the merge request.')
             return None
         for diff in all_diffs:
             for change in changes['changes']:
                 if change['new_path'] == relevant_file and relevant_line_in_file in change['diff']:
                     return diff
-            get_logger().debug(
+            logging.debug(
                 f'No relevant diff found for {relevant_file} {relevant_line_in_file}. Falling back to last diff.')
         return self.last_diff  # fallback to last_diff if no relevant diff is found
 
@@ -225,10 +226,7 @@ class GitLabProvider(GitProvider):
                 self.send_inline_comment(body, edit_type, found, relevant_file, relevant_line_in_file, source_line_no,
                                          target_file, target_line_no)
             except Exception as e:
-                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
+                logging.exception(f"Could not publish code suggestion:\nsuggestion: {suggestion}\nerror: {e}")
 
     def search_line(self, relevant_file, relevant_line_in_file):
         target_file = None
@@ -289,7 +287,7 @@ class GitLabProvider(GitProvider):
             for comment in self.temp_comments:
                 comment.delete()
         except Exception as e:
-            get_logger().exception(f"Failed to remove temp comments, error: {e}")
+            logging.exception(f"Failed to remove temp comments, error: {e}")
 
     def get_title(self):
         return self.mr.title
@@ -357,7 +355,7 @@ 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}")
+            logging.exception(f"Failed to publish labels, error: {e}")
 
     def publish_inline_comments(self, comments: list[dict]):
         pass
@@ -380,35 +378,4 @@ class GitLabProvider(GitProvider):
             commit_messages_str = ""
         if max_tokens:
             commit_messages_str = clip_tokens(commit_messages_str, max_tokens)
-        return commit_messages_str
-
-    def get_pr_id(self):
-        try:
-            pr_id = self.mr.web_url
-            return pr_id
-        except:
-            return ""
-
-    def generate_link_to_relevant_line_number(self, suggestion) -> str:
-        try:
-            relevant_file = suggestion['relevant file'].strip('`').strip("'")
-            relevant_line_str = suggestion['relevant line']
-            if not relevant_line_str:
-                return ""
-
-            position, absolute_position = find_line_number_of_relevant_line_in_file \
-                (self.diff_files, relevant_file, relevant_line_str)
-
-            if absolute_position != -1:
-                # link to right file only
-                link = f"https://gitlab.com/codiumai/pr-agent/-/blob/{self.mr.source_branch}/{relevant_file}?ref_type=heads#L{absolute_position}"
-
-                # # link to diff
-                # sha_file = hashlib.sha1(relevant_file.encode('utf-8')).hexdigest()
-                # link = f"{self.pr.web_url}/diffs#{sha_file}_{absolute_position}_{absolute_position}"
-                return link
-        except Exception as e:
-            if get_settings().config.verbosity_level >= 2:
-                get_logger().info(f"Failed adding line link, error: {e}")
-
-        return ""
+        return commit_messages_str

pr_agent/git_providers/local_git_provider.py

@@ -1,3 +1,4 @@
+import logging
 from collections import Counter
 from pathlib import Path
 from typing import List
@@ -6,7 +7,6 @@ from git import Repo
 
 from pr_agent.config_loader import _find_repository_root, get_settings
 from pr_agent.git_providers.git_provider import EDIT_TYPE, FilePatchInfo, GitProvider
-from pr_agent.log import get_logger
 
 
 class PullRequestMimic:
@@ -49,15 +49,14 @@ class LocalGitProvider(GitProvider):
         """
         Prepare the repository for PR-mimic generation.
         """
-        get_logger().debug('Preparing repository for PR-mimic generation...')
+        logging.debug('Preparing repository for PR-mimic generation...')
         if self.repo.is_dirty():
             raise ValueError('The repository is not in a clean state. Please commit or stash pending changes.')
         if self.target_branch_name not in self.repo.heads:
             raise KeyError(f'Branch: {self.target_branch_name} does not exist')
 
     def is_supported(self, capability: str) -> bool:
-        if capability in ['get_issue_comments', 'create_inline_comment', 'publish_inline_comments', 'get_labels',
-                          'gfm_markdown']:
+        if capability in ['get_issue_comments', 'create_inline_comment', 'publish_inline_comments', 'get_labels']:
             return False
         return True
 

pr_agent/git_providers/utils.py

@@ -1,35 +0,0 @@
-import copy
-import os
-import tempfile
-
-from dynaconf import Dynaconf
-
-from pr_agent.config_loader import get_settings
-from pr_agent.git_providers import get_git_provider
-from pr_agent.log import get_logger
-
-
-def apply_repo_settings(pr_url):
-    if get_settings().config.use_repo_settings_file:
-        repo_settings_file = None
-        try:
-            git_provider = get_git_provider()(pr_url)
-            repo_settings = git_provider.get_repo_settings()
-            if repo_settings:
-                repo_settings_file = None
-                fd, repo_settings_file = tempfile.mkstemp(suffix='.toml')
-                os.write(fd, repo_settings)
-                new_settings = Dynaconf(settings_files=[repo_settings_file])
-                for section, contents in new_settings.as_dict().items():
-                    section_dict = copy.deepcopy(get_settings().as_dict().get(section, {}))
-                    for key, value in contents.items():
-                        section_dict[key] = value
-                    get_settings().unset(section)
-                    get_settings().set(section, section_dict, merge=False)
-
-        finally:
-            if repo_settings_file:
-                try:
-                    os.remove(repo_settings_file)
-                except Exception as e:
-                    get_logger().error(f"Failed to remove temporary settings file {repo_settings_file}", e)

pr_agent/log/__init__.py

@@ -1,40 +0,0 @@
-import json
-import logging
-import sys
-from enum import Enum
-
-from loguru import logger
-
-
-class LoggingFormat(str, Enum):
-    CONSOLE = "CONSOLE"
-    JSON = "JSON"
-
-
-def json_format(record: dict) -> str:
-    return record["message"]
-
-
-def setup_logger(level: str = "INFO", fmt: LoggingFormat = LoggingFormat.CONSOLE):
-    level: int = logging.getLevelName(level.upper())
-    if type(level) is not int:
-        level = logging.INFO
-
-    if fmt == LoggingFormat.JSON:
-        logger.remove(None)
-        logger.add(
-            sys.stdout,
-            level=level,
-            format="{message}",
-            colorize=False,
-            serialize=True,
-        )
-    elif fmt == LoggingFormat.CONSOLE:
-        logger.remove(None)
-        logger.add(sys.stdout, level=level, colorize=True)
-
-    return logger
-
-
-def get_logger(*args, **kwargs):
-    return logger

pr_agent/servers/bitbucket_app.py

@@ -1,7 +1,9 @@
 import copy
 import hashlib
 import json
+import logging
 import os
+import sys
 import time
 
 import jwt
@@ -16,10 +18,9 @@ from starlette_context.middleware import RawContextMiddleware
 
 from pr_agent.agent.pr_agent import PRAgent
 from pr_agent.config_loader import get_settings, global_settings
-from pr_agent.log import LoggingFormat, get_logger, setup_logger
 from pr_agent.secret_providers import get_secret_provider
 
-setup_logger(fmt=LoggingFormat.JSON)
+logging.basicConfig(stream=sys.stdout, level=logging.INFO)
 router = APIRouter()
 secret_provider = get_secret_provider()
 
@@ -48,7 +49,7 @@ async def get_bearer_token(shared_secret: str, client_key: str):
         bearer_token = response.json()["access_token"]
         return bearer_token
     except Exception as e:
-        get_logger().error(f"Failed to get bearer token: {e}")
+        logging.error(f"Failed to get bearer token: {e}")
         raise e
 
 @router.get("/")
@@ -59,7 +60,7 @@ async def handle_manifest(request: Request, response: Response):
         manifest = manifest.replace("app_key", get_settings().bitbucket.app_key)
         manifest = manifest.replace("base_url", get_settings().bitbucket.base_url)
     except:
-        get_logger().error("Failed to replace api_key in Bitbucket manifest, trying to continue")
+        logging.error("Failed to replace api_key in Bitbucket manifest, trying to continue")
     manifest_obj = json.loads(manifest)
     return JSONResponse(manifest_obj)
 
@@ -91,7 +92,7 @@ async def handle_github_webhooks(background_tasks: BackgroundTasks, request: Req
                 comment_body = data["data"]["comment"]["content"]["raw"]
                 await agent.handle_request(pr_url, comment_body)
         except Exception as e:
-            get_logger().error(f"Failed to handle webhook: {e}")
+            logging.error(f"Failed to handle webhook: {e}")
     background_tasks.add_task(inner)
     return "OK"
 
@@ -114,7 +115,7 @@ async def handle_installed_webhooks(request: Request, response: Response):
         }
         secret_provider.store_secret(username, json.dumps(secrets))
     except Exception as e:
-        get_logger().error(f"Failed to register user: {e}")
+        logging.error(f"Failed to register user: {e}")
         return JSONResponse({"error": "Unable to register user"}, status_code=500)
 
 @router.post("/uninstalled")

pr_agent/servers/bitbucket_pipeline_runner.py

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

pr_agent/servers/gerrit_server.py

@@ -1,4 +1,6 @@
 import copy
+import logging
+import sys
 from enum import Enum
 from json import JSONDecodeError
 
@@ -10,10 +12,9 @@ from starlette_context import context
 from starlette_context.middleware import RawContextMiddleware
 
 from pr_agent.agent.pr_agent import PRAgent
-from pr_agent.config_loader import get_settings, global_settings
-from pr_agent.log import get_logger, setup_logger
+from pr_agent.config_loader import global_settings, get_settings
 
-setup_logger()
+logging.basicConfig(stream=sys.stdout, level=logging.DEBUG)
 router = APIRouter()
 
 
@@ -34,7 +35,7 @@ class Item(BaseModel):
 
 @router.post("/api/v1/gerrit/{action}")
 async def handle_gerrit_request(action: Action, item: Item):
-    get_logger().debug("Received a Gerrit request")
+    logging.debug("Received a Gerrit request")
     context["settings"] = copy.deepcopy(global_settings)
 
     if action == Action.ask:
@@ -53,7 +54,7 @@ async def get_body(request):
     try:
         body = await request.json()
     except JSONDecodeError as e:
-        get_logger().error("Error parsing request body", e)
+        logging.error("Error parsing request body", e)
         return {}
     return body
 

pr_agent/servers/github_action_runner.py

@@ -5,8 +5,6 @@ import os
 from pr_agent.agent.pr_agent import PRAgent
 from pr_agent.config_loader import get_settings
 from pr_agent.git_providers import get_git_provider
-from pr_agent.tools.pr_code_suggestions import PRCodeSuggestions
-from pr_agent.tools.pr_description import PRDescription
 from pr_agent.tools.pr_reviewer import PRReviewer
 
 
@@ -14,8 +12,8 @@ async def run_action():
     # Get environment variables
     GITHUB_EVENT_NAME = os.environ.get('GITHUB_EVENT_NAME')
     GITHUB_EVENT_PATH = os.environ.get('GITHUB_EVENT_PATH')
-    OPENAI_KEY = os.environ.get('OPENAI_KEY') or os.environ.get('OPENAI.KEY')
-    OPENAI_ORG = os.environ.get('OPENAI_ORG') or os.environ.get('OPENAI.ORG')
+    OPENAI_KEY = os.environ.get('OPENAI_KEY')
+    OPENAI_ORG = os.environ.get('OPENAI_ORG')
     GITHUB_TOKEN = os.environ.get('GITHUB_TOKEN')
     get_settings().set("CONFIG.PUBLISH_OUTPUT_PROGRESS", False)
 
@@ -55,15 +53,7 @@ async def run_action():
         if action in ["opened", "reopened"]:
             pr_url = event_payload.get("pull_request", {}).get("url")
             if pr_url:
-                auto_review = os.environ.get('github_action.auto_review', None)
-                if auto_review is None or (isinstance(auto_review, str) and auto_review.lower() == 'true'):
-                    await PRReviewer(pr_url).run()
-                auto_describe = os.environ.get('github_action.auto_describe', None)
-                if isinstance(auto_describe, str) and auto_describe.lower() == 'true':
-                    await PRDescription(pr_url).run()
-                auto_improve = os.environ.get('github_action.auto_improve', None)
-                if isinstance(auto_improve, str) and auto_improve.lower() == 'true':
-                    await PRCodeSuggestions(pr_url).run()
+                await PRReviewer(pr_url).run()
 
     # Handle issue comment event
     elif GITHUB_EVENT_NAME == "issue_comment":
@@ -71,21 +61,12 @@ async def run_action():
         if action in ["created", "edited"]:
             comment_body = event_payload.get("comment", {}).get("body")
             if comment_body:
-                is_pr = False
-                # check if issue is pull request
-                if event_payload.get("issue", {}).get("pull_request"):
-                    url = event_payload.get("issue", {}).get("pull_request", {}).get("url")
-                    is_pr = True
-                else:
-                    url = event_payload.get("issue", {}).get("url")
-                if url:
+                pr_url = event_payload.get("issue", {}).get("pull_request", {}).get("url")
+                if pr_url:
                     body = comment_body.strip().lower()
                     comment_id = event_payload.get("comment", {}).get("id")
-                    provider = get_git_provider()(pr_url=url)
-                    if is_pr:
-                        await PRAgent().handle_request(url, body, notify=lambda: provider.add_eyes_reaction(comment_id))
-                    else:
-                        await PRAgent().handle_request(url, body)
+                    provider = get_git_provider()(pr_url=pr_url)
+                    await PRAgent().handle_request(pr_url, body, notify=lambda: provider.add_eyes_reaction(comment_id))
 
 
 if __name__ == '__main__':

pr_agent/servers/github_app.py

@@ -1,4 +1,6 @@
 import copy
+import logging
+import sys
 import os
 import time
 from typing import Any, Dict
@@ -13,12 +15,9 @@ from pr_agent.agent.pr_agent import PRAgent
 from pr_agent.algo.utils import update_settings_from_args
 from pr_agent.config_loader import get_settings, global_settings
 from pr_agent.git_providers import get_git_provider
-from pr_agent.git_providers.utils import apply_repo_settings
-from pr_agent.log import LoggingFormat, get_logger, setup_logger
 from pr_agent.servers.utils import verify_signature
 
-setup_logger(fmt=LoggingFormat.JSON)
-
+logging.basicConfig(stream=sys.stdout, level=logging.INFO)
 router = APIRouter()
 
 
@@ -29,11 +28,11 @@ async def handle_github_webhooks(request: Request, response: Response):
     Verifies the request signature, parses the request body, and passes it to the handle_request function for further
     processing.
     """
-    get_logger().debug("Received a GitHub webhook")
+    logging.debug("Received a GitHub webhook")
 
     body = await get_body(request)
 
-    get_logger().debug(f'Request body:\n{body}')
+    logging.debug(f'Request body:\n{body}')
     installation_id = body.get("installation", {}).get("id")
     context["installation_id"] = installation_id
     context["settings"] = copy.deepcopy(global_settings)
@@ -45,13 +44,13 @@ async def handle_github_webhooks(request: Request, response: Response):
 @router.post("/api/v1/marketplace_webhooks")
 async def handle_marketplace_webhooks(request: Request, response: Response):
     body = await get_body(request)
-    get_logger().info(f'Request body:\n{body}')
+    logging.info(f'Request body:\n{body}')
 
 async def get_body(request):
     try:
         body = await request.json()
     except Exception as e:
-        get_logger().error("Error parsing request body", e)
+        logging.error("Error parsing request body", e)
         raise HTTPException(status_code=400, detail="Error parsing request body") from e
     webhook_secret = getattr(get_settings().github, 'webhook_secret', None)
     if webhook_secret:
@@ -77,8 +76,8 @@ async def handle_request(body: Dict[str, Any], event: str):
         return {}
     agent = PRAgent()
     bot_user = get_settings().github_app.bot_user
-    sender = body.get("sender", {}).get("login")
-    log_context = {"action": action, "event": event, "sender": sender, "server_type": "github_app"}
+    logging.info(f"action: '{action}'")
+    logging.info(f"event: '{event}'")
 
     if get_settings().github_app.duplicate_requests_cache and _is_duplicate_request(body):
         return {}
@@ -88,23 +87,22 @@ async def handle_request(body: Dict[str, Any], event: str):
         if "comment" not in body:
             return {}
         comment_body = body.get("comment", {}).get("body")
+        sender = body.get("sender", {}).get("login")
         if sender and bot_user in sender:
-            get_logger().info(f"Ignoring comment from {bot_user} user")
+            logging.info(f"Ignoring comment from {bot_user} user")
             return {}
-        get_logger().info(f"Processing comment from {sender} user")
+        logging.info(f"Processing comment from {sender} user")
         if "issue" in body and "pull_request" in body["issue"] and "url" in body["issue"]["pull_request"]:
             api_url = body["issue"]["pull_request"]["url"]
         elif "comment" in body and "pull_request_url" in body["comment"]:
             api_url = body["comment"]["pull_request_url"]
         else:
             return {}
-        log_context["api_url"] = api_url
-        get_logger().info(body)
-        get_logger().info(f"Handling comment because of event={event} and action={action}")
+        logging.info(body)
+        logging.info(f"Handling comment because of event={event} and action={action}")
         comment_id = body.get("comment", {}).get("id")
         provider = get_git_provider()(pr_url=api_url)
-        with get_logger().contextualize(**log_context):
-            await agent.handle_request(api_url, comment_body, notify=lambda: provider.add_eyes_reaction(comment_id))
+        await agent.handle_request(api_url, comment_body, notify=lambda: provider.add_eyes_reaction(comment_id))
 
     # handle pull_request event:
     #   automatically review opened/reopened/ready_for_review PRs as long as they're not in draft,
@@ -116,7 +114,6 @@ async def handle_request(body: Dict[str, Any], event: str):
         api_url = pull_request.get("url")
         if not api_url:
             return {}
-        log_context["api_url"] = api_url
         if pull_request.get("draft", True) or pull_request.get("state") != "open" or pull_request.get("user", {}).get("login", "") == bot_user:
             return {}
         if action in get_settings().github_app.handle_pr_actions:
@@ -126,20 +123,18 @@ async def handle_request(body: Dict[str, Any], event: str):
                 if pull_request.get("created_at") == pull_request.get("updated_at"):
                     # avoid double reviews when opening a PR for the first time
                     return {}
-            get_logger().info(f"Performing review because of event={event} and action={action}")
-            apply_repo_settings(api_url)
+            logging.info(f"Performing review because of event={event} and action={action}")
             for command in get_settings().github_app.pr_commands:
                 split_command = command.split(" ")
                 command = split_command[0]
                 args = split_command[1:]
                 other_args = update_settings_from_args(args)
                 new_command = ' '.join([command] + other_args)
-                get_logger().info(body)
-                get_logger().info(f"Performing command: {new_command}")
-                with get_logger().contextualize(**log_context):
-                    await agent.handle_request(api_url, new_command)
+                logging.info(body)
+                logging.info(f"Performing command: {new_command}")
+                await agent.handle_request(api_url, new_command)
 
-    get_logger().info("event or action does not require handling")
+    logging.info("event or action does not require handling")
     return {}
 
 
@@ -149,7 +144,7 @@ def _is_duplicate_request(body: Dict[str, Any]) -> bool:
     This function checks if the request is duplicate and if so - ignores it.
     """
     request_hash = hash(str(body))
-    get_logger().info(f"request_hash: {request_hash}")
+    logging.info(f"request_hash: {request_hash}")
     request_time = time.monotonic()
     ttl = get_settings().github_app.duplicate_requests_cache_ttl  # in seconds
     to_delete = [key for key, key_time in _duplicate_requests_cache.items() if request_time - key_time > ttl]
@@ -158,7 +153,7 @@ def _is_duplicate_request(body: Dict[str, Any]) -> bool:
     is_duplicate = request_hash in _duplicate_requests_cache
     _duplicate_requests_cache[request_hash] = request_time
     if is_duplicate:
-        get_logger().info(f"Ignoring duplicate request {request_hash}")
+        logging.info(f"Ignoring duplicate request {request_hash}")
     return is_duplicate
 
 

pr_agent/servers/github_polling.py

@@ -1,4 +1,6 @@
 import asyncio
+import logging
+import sys
 from datetime import datetime, timezone
 
 import aiohttp
@@ -6,10 +8,9 @@ import aiohttp
 from pr_agent.agent.pr_agent import PRAgent
 from pr_agent.config_loader import get_settings
 from pr_agent.git_providers import get_git_provider
-from pr_agent.log import LoggingFormat, get_logger, setup_logger
 from pr_agent.servers.help import bot_help_text
 
-setup_logger(fmt=LoggingFormat.JSON)
+logging.basicConfig(stream=sys.stdout, level=logging.DEBUG)
 NOTIFICATION_URL = "https://api.github.com/notifications"
 
 
@@ -93,7 +94,7 @@ async def polling_loop():
                                             comment_body = comment['body'] if 'body' in comment else ''
                                             commenter_github_user = comment['user']['login'] \
                                                 if 'user' in comment else ''
-                                            get_logger().info(f"Commenter: {commenter_github_user}\nComment: {comment_body}")
+                                            logging.info(f"Commenter: {commenter_github_user}\nComment: {comment_body}")
                                             user_tag = "@" + user_id
                                             if user_tag not in comment_body:
                                                 continue
@@ -111,7 +112,7 @@ 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}")
+                logging.error(f"Exception during processing of a notification: {e}")
 
 
 if __name__ == '__main__':

pr_agent/servers/gitlab_webhook.py

@@ -1,5 +1,7 @@
 import copy
 import json
+import logging
+import sys
 
 import uvicorn
 from fastapi import APIRouter, FastAPI, Request, status
@@ -12,10 +14,9 @@ from starlette_context.middleware import RawContextMiddleware
 
 from pr_agent.agent.pr_agent import PRAgent
 from pr_agent.config_loader import get_settings, global_settings
-from pr_agent.log import get_logger, setup_logger
 from pr_agent.secret_providers import get_secret_provider
 
-setup_logger()
+logging.basicConfig(stream=sys.stdout, level=logging.INFO)
 router = APIRouter()
 
 secret_provider = get_secret_provider() if get_settings().get("CONFIG.SECRET_PROVIDER") else None
@@ -32,7 +33,7 @@ async def gitlab_webhook(background_tasks: BackgroundTasks, request: Request):
             context["settings"] = copy.deepcopy(global_settings)
             context["settings"].gitlab.personal_access_token = gitlab_token
         except Exception as e:
-            get_logger().error(f"Failed to validate secret {request_token}: {e}")
+            logging.error(f"Failed to validate secret {request_token}: {e}")
             return JSONResponse(status_code=status.HTTP_401_UNAUTHORIZED, content=jsonable_encoder({"message": "unauthorized"}))
     elif get_settings().get("GITLAB.SHARED_SECRET"):
         secret = get_settings().get("GITLAB.SHARED_SECRET")
@@ -44,9 +45,9 @@ async def gitlab_webhook(background_tasks: BackgroundTasks, request: Request):
     if not gitlab_token:
         return JSONResponse(status_code=status.HTTP_401_UNAUTHORIZED, content=jsonable_encoder({"message": "unauthorized"}))
     data = await request.json()
-    get_logger().info(json.dumps(data))
+    logging.info(json.dumps(data))
     if data.get('object_kind') == 'merge_request' and data['object_attributes'].get('action') in ['open', 'reopen']:
-        get_logger().info(f"A merge request has been opened: {data['object_attributes'].get('title')}")
+        logging.info(f"A merge request has been opened: {data['object_attributes'].get('title')}")
         url = data['object_attributes'].get('url')
         background_tasks.add_task(PRAgent().handle_request, url, "/review")
     elif data.get('object_kind') == 'note' and data['event_type'] == 'note':

pr_agent/servers/serverless.py

@@ -1,10 +1,12 @@
+import logging
+
 from fastapi import FastAPI
 from mangum import Mangum
 
-from pr_agent.log import setup_logger
 from pr_agent.servers.github_app import router
 
-setup_logger()
+logger = logging.getLogger()
+logger.setLevel(logging.DEBUG)
 
 app = FastAPI()
 app.include_router(router)

pr_agent/settings/.secrets_template.toml

@@ -16,10 +16,6 @@ key = ""  # Acquire through https://platform.openai.com
 #deployment_id = ""  # The deployment name you chose when you deployed the engine
 #fallback_deployments = []  # For each fallback model specified in configuration.toml in the [config] section, specify the appropriate deployment_id
 
-[pinecone]
-api_key = "..."
-environment = "gcp-starter"
-
 [anthropic]
 key = "" # Optional, uncomment if you want to use Anthropic. Acquire through https://www.anthropic.com/
 
@@ -28,14 +24,6 @@ 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/
-
-[huggingface]
-key = "" # Optional, uncomment if you want to use Huggingface Inference API. Acquire through https://huggingface.co/docs/api-inference/quicktour
-api_base = "" # the base url for your huggingface inference endpoint 
-
-[ollama]
-api_base = "" # the base url for your huggingface inference endpoint 
-
 [github]
 # ---- Set the following only for deployment type == "user"
 user_token = ""  # A GitHub personal access token with 'repo' scope.
@@ -55,12 +43,5 @@ webhook_secret = "<WEBHOOK SECRET>"  # Optional, may be commented out.
 personal_access_token = ""
 
 [bitbucket]
-# For Bitbucket personal/repository bearer token
+# Bitbucket personal bearer token
 bearer_token = ""
-
-# For Bitbucket app
-app_key = ""
-base_url = ""
-
-[litellm]
-LITELLM_TOKEN = "" # see https://docs.litellm.ai/docs/debugging/hosted_debugging for details and instructions on how to get a token

pr_agent/settings/configuration.toml

@@ -10,16 +10,13 @@ use_repo_settings_file=true
 ai_timeout=180
 max_description_tokens = 500
 max_commits_tokens = 500
-patch_extra_lines = 3
 secret_provider="google_cloud_storage"
-cli_mode=false
 
 [pr_reviewer] # /review #
 require_focused_review=false
 require_score_review=false
 require_tests_review=true
 require_security_review=true
-require_estimate_effort_to_review=true
 num_code_suggestions=4
 inline_code_comments = false
 ask_and_reflect=false
@@ -27,14 +24,10 @@ automatic_review=true
 extra_instructions = ""
 
 [pr_description] # /describe #
-publish_labels=true
 publish_description_as_comment=false
 add_original_user_description=false
 keep_original_user_title=false
 extra_instructions = ""
-# markers
-use_description_markers=false
-include_generated_by_header=true
 
 [pr_questions] # /ask #
 
@@ -48,10 +41,6 @@ rank_extended_suggestions = true
 max_number_of_calls = 5
 final_clip_factor = 0.9
 
-[pr_add_docs] # /add_docs #
-extra_instructions = ""
-docs_style = "Sphinx Style" # "Google Style with Args, Returns, Attributes...etc", "Numpy Style", "Sphinx Style", "PEP257", "reStructuredText"
-
 [pr_update_changelog] # /update_changelog #
 push_changelog_changes=false
 extra_instructions = ""
@@ -63,11 +52,6 @@ extra_instructions = ""
 deployment_type = "user"
 ratelimit_retries = 5
 
-[github_action]
-# auto_review = true    # set as env var in .github/workflows/pr-agent.yaml
-# auto_describe = true  # set as env var in .github/workflows/pr-agent.yaml
-# auto_improve = true   # set as env var in .github/workflows/pr-agent.yaml
-
 [github_app]
 # these toggles allows running the github app from custom deployments
 bot_user = "github-actions[bot]"
@@ -112,14 +96,5 @@ polling_interval_seconds = 30
 # patch_server_token = ""
 
 [litellm]
-#use_client = false
-
-[pr_similar_issue]
-skip_comments = false
-force_update_dataset = false
-max_issues_to_scan = 500
-
-[pinecone]
-# fill and place in .secrets.toml
-#api_key = ...
-# environment = "gcp-starter"
+debugger=false
+#email="youremail@example.com"

pr_agent/settings/ignore.toml

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

pr_agent/settings/language_extensions.toml

@@ -53,8 +53,7 @@ default = [
     'xz',
     'zip',
     'zst',
-    'snap',
-    'lockb'
+    'snap'
 ]
 extra = [
     'md',

pr_agent/settings/pr_add_docs.toml

@@ -1,117 +0,0 @@
-[pr_add_docs_prompt]
-system="""You are a language model called PR-Code-Documentation Agent, that specializes in generating documentation for code.
-Your task is to generate meaningfull {{ docs_for_language }} to a PR (the '+' lines).
-
-Example for a PR Diff input:
-'
-## src/file1.py
-
-@@ -12,3 +12,5 @@ def func1():
-__new hunk__
-12  code line that already existed in the file...
-13  code line that already existed in the file....
-14 +new code line1 added in the PR
-15 +new code line2 added in the PR
-16  code line that already existed in the file...
-__old hunk__
- code line that already existed in the file...
--code line that was removed in the PR
- code line that already existed in the file...
-
-
-@@ ... @@ def func2():
-__new hunk__
-...
-__old hunk__
-...
-
-
-## src/file2.py
-...
-'
-
-Specific instructions:
-- Try to identify edited/added code components (classes/functions/methods...) that are undocumented. and generate {{ docs_for_language }} for each one.
-- If there are documented (any type of {{ language }} documentation) code components in the PR, Don't generate {{ docs_for_language }} for them.
-- Ignore code components that don't appear fully in the '__new hunk__' section. For example. you must see the component header and body,
-- Make sure the {{ docs_for_language }} starts and ends with standart {{ language }} {{ docs_for_language }} signs.
-- The {{ docs_for_language }} should be in standard format.
-- Provide the exact line number (inclusive) where the {{ docs_for_language }} should be added.
-
-
-{%- if extra_instructions %}
-
-Extra instructions from the user:
-'
-{{ extra_instructions }}
-'
-{%- endif %}
-
-You must use the following YAML schema to format your answer:
-```yaml
-Code Documentation:
-  type: array
-  uniqueItems: true
-  items:
-    relevant file:
-      type: string
-      description: the relevant file full path
-    relevant line:
-      type: integer
-      description: |-
-        The relevant line number from a '__new hunk__' section where the {{ docs_for_language }} should be added.
-    doc placement:
-      type: string
-      enum:
-        - before
-        - after
-      description: |-
-        The {{ docs_for_language }} placement relative to the relevant line (code component).
-    documentation:
-      type: string
-      description: |-
-        The {{ docs_for_language }} content. It should be complete, correctly formatted and indented, and without line numbers.
-```
-
-Example output:
-```yaml
-Code Documentation:
--   relevant file: |-
-        src/file1.py
-    relevant lines: 12
-    doc placement: after
-    documentation: |-
-        \"\"\"
-        This is a python docstring for func1.
-        \"\"\"
-- ...
-...
-```
-
-
-Each YAML output MUST be after a newline, indented, with block scalar indicator ('|-').
-Don't repeat the prompt in the answer, and avoid outputting the 'type' and 'description' fields.
-"""
-
-user="""PR Info:
-
-Title: '{{ title }}'
-
-Branch: '{{ branch }}'
-
-Description: '{{description}}'
-
-{%- if language %}
-
-Main language: {{language}}
-{%- endif %}
-
-
-The PR Diff:
-```
-{{- diff|trim }}
-```
-
-Response (should be a valid YAML, and nothing else):
-```yaml
-"""

pr_agent/settings/pr_code_suggestions_prompts.toml

@@ -1,6 +1,6 @@
 [pr_code_suggestions_prompt]
 system="""You are a language model called PR-Code-Reviewer, that specializes in suggesting code improvements for Pull Request (PR).
-Your task is to provide meaningful and actionable code suggestions, to improve the new code presented in a PR (the '+' lines in the diff).
+Your task is to provide meaningful and actionable code suggestions, to improve the new code presented in a PR.
 
 Example for a PR Diff input:
 '
@@ -31,13 +31,14 @@ __old hunk__
 '
 
 Specific instructions:
-- Provide up to {{ num_code_suggestions }} code suggestions. Try to provide diverse and insightful suggestions.
+- Provide up to {{ num_code_suggestions }} code suggestions.
 - Prioritize suggestions that address major problems, issues and bugs in the code.
   As a second priority, suggestions should focus on best practices, code readability, maintainability, enhancments, performance, and other aspects.
-- Don't suggest to add docstring, type hints, or comments.
+  Don't suggest to add docstring or type hints.
+  Try to provide diverse and insightful suggestions.
 - Suggestions should refer only to code from the '__new hunk__' sections, and focus on new lines of code (lines starting with '+').
-- 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 '__new hunk__' code.
-- For each suggestion, make sure to take into consideration also the context, meaning the lines before and after the relevant code.
+  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 '__new hunk__' code.
+  For each suggestion, make sure to take into consideration also the context, meaning the lines before and after the relevant code.
 - Provide the exact line numbers range (inclusive) for each issue.
 - Assume there is additional relevant code, that is not included in the diff.
 
@@ -45,9 +46,7 @@ Specific instructions:
 {%- if extra_instructions %}
 
 Extra instructions from the user:
-'
 {{ extra_instructions }}
-'
 {%- endif %}
 
 You must use the following YAML schema to format your answer:

pr_agent/settings/pr_description_prompts.toml

@@ -7,9 +7,7 @@ Your task is to provide full description of the PR content.
 {%- if extra_instructions %}
 
 Extra instructions from the user:
-'
 {{ extra_instructions }}
-'
 {% endif %}
 
 You must use the following YAML schema to format your answer:

pr_agent/settings/pr_reviewer_prompts.toml

@@ -22,22 +22,20 @@ code line that already existed in the file....
 ...
 '
 
-The review should focus on new code added in the PR (lines starting with '+'), and not on code that already existed in the file (lines starting with '-', or without prefix).
+Thre review should focus on new code added in the PR (lines starting with '+'), and not on code that already existed in the file (lines starting with '-', or without prefix).
 
 {%- if num_code_suggestions > 0 %}
 - Provide up to {{ num_code_suggestions }} code suggestions.
 - 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.
+- Don't suggest to add docstring or type hints.
 - Suggestions should focus on improving the new code added in the PR (lines starting with '+')
 {%- endif %}
 
 {%- if extra_instructions %}
 
 Extra instructions from the user:
-'
 {{ extra_instructions }}
-'
 {% endif %}
 
 You must use the following YAML schema to format your answer:
@@ -87,14 +85,6 @@ PR Analysis:
       code diff changes are too scattered, then the PR is not focused. Explain
       your answer shortly.
 {%- endif %}
-{%- if require_estimate_effort_to_review %}
-  Estimated effort to review [1-5]:
-    type: string
-    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 shortly (1-2 sentences).
-{%- endif %}
 PR Feedback:
   General suggestions:
     type: string
@@ -131,7 +121,8 @@ PR Feedback:
   Security concerns:
     type: string
     description: >-
-      yes\\no question: 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 ? If answered 'yes', explain your answer briefly.
+      yes\\no question: does this PR code introduce possible security concerns or
+      issues, like SQL injection, XSS, CSRF, and others ? If answered 'yes',explain your answer shortly
 {%- endif %}
 ```
 
@@ -152,9 +143,6 @@ PR Analysis:
 {%- if require_focused %}
   Focused PR: no, because ...
 {%- endif %}
-{%- if require_estimate_effort_to_review %}
-  Estimated effort to review [1-5]: 3, because ...
-{%- endif %}
 PR Feedback:
   General PR suggestions: |-
     ...
@@ -197,9 +185,7 @@ Here are questions to better understand the PR. Use the answers to provide bette
 {{question_str|trim}}
 
 User answers:
-'
 {{answer_str|trim}}
-'
 ######
 {%- endif %}
 

pr_agent/settings/pr_update_changelog_prompts.toml

@@ -8,9 +8,7 @@ Your task is to update the CHANGELOG.md file of the project, to shortly summariz
 {%- if extra_instructions %}
 
 Extra instructions from the user:
-'
 {{ extra_instructions }}
-'
 {%- endif %}
 """
 

pr_agent/tools/pr_add_docs.py

@@ -1,174 +0,0 @@
-import copy
-import textwrap
-from typing import Dict
-
-from jinja2 import Environment, StrictUndefined
-
-from pr_agent.algo.ai_handler import AiHandler
-from pr_agent.algo.pr_processing import get_pr_diff, retry_with_fallback_models
-from pr_agent.algo.token_handler import TokenHandler
-from pr_agent.algo.utils import load_yaml
-from pr_agent.config_loader import get_settings
-from pr_agent.git_providers import get_git_provider
-from pr_agent.git_providers.git_provider import get_main_pr_language
-from pr_agent.log import get_logger
-
-
-class PRAddDocs:
-    def __init__(self, pr_url: str, cli_mode=False, args: list = None):
-
-        self.git_provider = get_git_provider()(pr_url)
-        self.main_language = get_main_pr_language(
-            self.git_provider.get_languages(), self.git_provider.get_files()
-        )
-
-        self.ai_handler = AiHandler()
-        self.patches_diff = None
-        self.prediction = None
-        self.cli_mode = cli_mode
-        self.vars = {
-            "title": self.git_provider.pr.title,
-            "branch": self.git_provider.get_pr_branch(),
-            "description": self.git_provider.get_pr_description(),
-            "language": self.main_language,
-            "diff": "",  # empty diff for initial calculation
-            "extra_instructions": get_settings().pr_add_docs.extra_instructions,
-            "commit_messages_str": self.git_provider.get_commit_messages(),
-            'docs_for_language': get_docs_for_language(self.main_language,
-                                                       get_settings().pr_add_docs.docs_style),
-        }
-        self.token_handler = TokenHandler(self.git_provider.pr,
-                                          self.vars,
-                                          get_settings().pr_add_docs_prompt.system,
-                                          get_settings().pr_add_docs_prompt.user)
-
-    async def run(self):
-        try:
-            get_logger().info('Generating code Docs for PR...')
-            if get_settings().config.publish_output:
-                self.git_provider.publish_comment("Generating Documentation...", is_temporary=True)
-
-            get_logger().info('Preparing PR documentation...')
-            await retry_with_fallback_models(self._prepare_prediction)
-            data = self._prepare_pr_code_docs()
-            if (not data) or (not 'Code Documentation' in data):
-                get_logger().info('No code documentation found for PR.')
-                return
-
-            if get_settings().config.publish_output:
-                get_logger().info('Pushing PR documentation...')
-                self.git_provider.remove_initial_comment()
-                get_logger().info('Pushing inline code documentation...')
-                self.push_inline_docs(data)
-        except Exception as e:
-            get_logger().error(f"Failed to generate code documentation for PR, error: {e}")
-
-    async def _prepare_prediction(self, model: str):
-        get_logger().info('Getting PR diff...')
-        self.patches_diff = get_pr_diff(self.git_provider,
-                                        self.token_handler,
-                                        model,
-                                        add_line_numbers_to_hunks=True,
-                                        disable_extra_lines=False)
-
-        get_logger().info('Getting AI prediction...')
-        self.prediction = await self._get_prediction(model)
-
-    async def _get_prediction(self, model: str):
-        variables = copy.deepcopy(self.vars)
-        variables["diff"] = self.patches_diff  # update diff
-        environment = Environment(undefined=StrictUndefined)
-        system_prompt = environment.from_string(get_settings().pr_add_docs_prompt.system).render(variables)
-        user_prompt = environment.from_string(get_settings().pr_add_docs_prompt.user).render(variables)
-        if get_settings().config.verbosity_level >= 2:
-            get_logger().info(f"\nSystem prompt:\n{system_prompt}")
-            get_logger().info(f"\nUser prompt:\n{user_prompt}")
-        response, finish_reason = await self.ai_handler.chat_completion(model=model, temperature=0.2,
-                                                                        system=system_prompt, user=user_prompt)
-
-        return response
-
-    def _prepare_pr_code_docs(self) -> Dict:
-        docs = self.prediction.strip()
-        data = load_yaml(docs)
-        if isinstance(data, list):
-            data = {'Code Documentation': data}
-        return data
-
-    def push_inline_docs(self, data):
-        docs = []
-
-        if not data['Code Documentation']:
-            return self.git_provider.publish_comment('No code documentation found to improve this PR.')
-
-        for d in data['Code Documentation']:
-            try:
-                if get_settings().config.verbosity_level >= 2:
-                    get_logger().info(f"add_docs: {d}")
-                relevant_file = d['relevant file'].strip()
-                relevant_line = int(d['relevant line'])  # absolute position
-                documentation = d['documentation']
-                doc_placement = d['doc placement'].strip()
-                if documentation:
-                    new_code_snippet = self.dedent_code(relevant_file, relevant_line, documentation, doc_placement,
-                                                        add_original_line=True)
-
-                    body = f"**Suggestion:** Proposed documentation\n```suggestion\n" + new_code_snippet + "\n```"
-                    docs.append({'body': body, 'relevant_file': relevant_file,
-                                             'relevant_lines_start': relevant_line,
-                                             'relevant_lines_end': relevant_line})
-            except Exception:
-                if get_settings().config.verbosity_level >= 2:
-                    get_logger().info(f"Could not parse code docs: {d}")
-
-        is_successful = self.git_provider.publish_code_suggestions(docs)
-        if not is_successful:
-            get_logger().info("Failed to publish code docs, trying to publish each docs separately")
-            for doc_suggestion in docs:
-                self.git_provider.publish_code_suggestions([doc_suggestion])
-
-    def dedent_code(self, relevant_file, relevant_lines_start, new_code_snippet, doc_placement='after',
-                    add_original_line=False):
-        try:  # dedent code snippet
-            self.diff_files = self.git_provider.diff_files if self.git_provider.diff_files \
-                else self.git_provider.get_diff_files()
-            original_initial_line = None
-            for file in self.diff_files:
-                if file.filename.strip() == relevant_file:
-                    original_initial_line = file.head_file.splitlines()[relevant_lines_start - 1]
-                    break
-            if original_initial_line:
-                if doc_placement == 'after':
-                    line = file.head_file.splitlines()[relevant_lines_start]
-                else:
-                    line = original_initial_line
-                suggested_initial_line = new_code_snippet.splitlines()[0]
-                original_initial_spaces = len(line) - len(line.lstrip())
-                suggested_initial_spaces = len(suggested_initial_line) - len(suggested_initial_line.lstrip())
-                delta_spaces = original_initial_spaces - suggested_initial_spaces
-                if delta_spaces > 0:
-                    new_code_snippet = textwrap.indent(new_code_snippet, delta_spaces * " ").rstrip('\n')
-                if add_original_line:
-                    if doc_placement == 'after':
-                        new_code_snippet = original_initial_line + "\n" + new_code_snippet
-                    else:
-                        new_code_snippet = new_code_snippet.rstrip() + "\n" + original_initial_line
-        except Exception as e:
-            if get_settings().config.verbosity_level >= 2:
-                get_logger().info(f"Could not dedent code snippet for file {relevant_file}, error: {e}")
-
-        return new_code_snippet
-
-
-def get_docs_for_language(language, style):
-    language = language.lower()
-    if language == 'java':
-        return "Javadocs"
-    elif language in ['python', 'lisp', 'clojure']:
-        return f"Docstring ({style})"
-    elif language in ['javascript', 'typescript']:
-        return "JSdocs"
-    elif language == 'c++':
-        return "Doxygen"
-    else:
-        return "Docs"

pr_agent/tools/pr_code_suggestions.py

@@ -1,17 +1,16 @@
 import copy
+import logging
 import textwrap
-from typing import Dict, List
-
+from typing import List, Dict
 from jinja2 import Environment, StrictUndefined
 
 from pr_agent.algo.ai_handler import AiHandler
-from pr_agent.algo.pr_processing import get_pr_diff, get_pr_multi_diffs, retry_with_fallback_models
+from pr_agent.algo.pr_processing import get_pr_diff, retry_with_fallback_models, get_pr_multi_diffs
 from pr_agent.algo.token_handler import TokenHandler
 from pr_agent.algo.utils import load_yaml
 from pr_agent.config_loader import get_settings
-from pr_agent.git_providers import get_git_provider
+from pr_agent.git_providers import BitbucketProvider, get_git_provider
 from pr_agent.git_providers.git_provider import get_main_pr_language
-from pr_agent.log import get_logger
 
 
 class PRCodeSuggestions:
@@ -23,10 +22,7 @@ class PRCodeSuggestions:
         )
 
         # extended mode
-        try:
-            self.is_extended = any(["extended" in arg for arg in args])
-        except:
-            self.is_extended = False
+        self.is_extended = any(["extended" in arg for arg in args])
         if self.is_extended:
             num_code_suggestions = get_settings().pr_code_suggestions.num_code_suggestions_per_chunk
         else:
@@ -52,43 +48,37 @@ class PRCodeSuggestions:
                                           get_settings().pr_code_suggestions_prompt.user)
 
     async def run(self):
-        try:
-            get_logger().info('Generating code suggestions for PR...')
-            if get_settings().config.publish_output:
-                self.git_provider.publish_comment("Preparing review...", is_temporary=True)
+        logging.info('Generating code suggestions for PR...')
+        if get_settings().config.publish_output:
+            self.git_provider.publish_comment("Preparing review...", is_temporary=True)
 
-            get_logger().info('Preparing PR review...')
-            if not self.is_extended:
-                await retry_with_fallback_models(self._prepare_prediction)
-                data = self._prepare_pr_code_suggestions()
-            else:
-                data = await retry_with_fallback_models(self._prepare_prediction_extended)
-            if (not data) or (not 'Code suggestions' in data):
-                get_logger().info('No code suggestions found for PR.')
-                return
+        logging.info('Preparing PR review...')
+        if not self.is_extended:
+            await retry_with_fallback_models(self._prepare_prediction)
+            data = self._prepare_pr_code_suggestions()
+        else:
+            data = await retry_with_fallback_models(self._prepare_prediction_extended)
 
-            if (not self.is_extended and get_settings().pr_code_suggestions.rank_suggestions) or \
-                    (self.is_extended and get_settings().pr_code_suggestions.rank_extended_suggestions):
-                get_logger().info('Ranking Suggestions...')
-                data['Code suggestions'] = await self.rank_suggestions(data['Code suggestions'])
+        if (not self.is_extended and get_settings().pr_code_suggestions.rank_suggestions) or \
+                (self.is_extended and get_settings().pr_code_suggestions.rank_extended_suggestions):
+            logging.info('Ranking Suggestions...')
+            data['Code suggestions'] = await self.rank_suggestions(data['Code suggestions'])
 
-            if get_settings().config.publish_output:
-                get_logger().info('Pushing PR review...')
-                self.git_provider.remove_initial_comment()
-                get_logger().info('Pushing inline code suggestions...')
-                self.push_inline_code_suggestions(data)
-        except Exception as e:
-            get_logger().error(f"Failed to generate code suggestions for PR, error: {e}")
+        if get_settings().config.publish_output:
+            logging.info('Pushing PR review...')
+            self.git_provider.remove_initial_comment()
+            logging.info('Pushing inline code suggestions...')
+            self.push_inline_code_suggestions(data)
 
     async def _prepare_prediction(self, model: str):
-        get_logger().info('Getting PR diff...')
+        logging.info('Getting PR diff...')
         self.patches_diff = get_pr_diff(self.git_provider,
                                         self.token_handler,
                                         model,
                                         add_line_numbers_to_hunks=True,
                                         disable_extra_lines=True)
 
-        get_logger().info('Getting AI prediction...')
+        logging.info('Getting AI prediction...')
         self.prediction = await self._get_prediction(model)
 
     async def _get_prediction(self, model: str):
@@ -98,8 +88,8 @@ class PRCodeSuggestions:
         system_prompt = environment.from_string(get_settings().pr_code_suggestions_prompt.system).render(variables)
         user_prompt = environment.from_string(get_settings().pr_code_suggestions_prompt.user).render(variables)
         if get_settings().config.verbosity_level >= 2:
-            get_logger().info(f"\nSystem prompt:\n{system_prompt}")
-            get_logger().info(f"\nUser prompt:\n{user_prompt}")
+            logging.info(f"\nSystem prompt:\n{system_prompt}")
+            logging.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)
 
@@ -121,7 +111,7 @@ class PRCodeSuggestions:
         for d in data['Code suggestions']:
             try:
                 if get_settings().config.verbosity_level >= 2:
-                    get_logger().info(f"suggestion: {d}")
+                    logging.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'])
@@ -137,11 +127,11 @@ class PRCodeSuggestions:
                                          'relevant_lines_end': relevant_lines_end})
             except Exception:
                 if get_settings().config.verbosity_level >= 2:
-                    get_logger().info(f"Could not parse suggestion: {d}")
+                    logging.info(f"Could not parse suggestion: {d}")
 
         is_successful = self.git_provider.publish_code_suggestions(code_suggestions)
         if not is_successful:
-            get_logger().info("Failed to publish code suggestions, trying to publish each suggestion separately")
+            logging.info("Failed to publish code suggestions, trying to publish each suggestion separately")
             for code_suggestion in code_suggestions:
                 self.git_provider.publish_code_suggestions([code_suggestion])
 
@@ -163,19 +153,19 @@ class PRCodeSuggestions:
                     new_code_snippet = textwrap.indent(new_code_snippet, delta_spaces * " ").rstrip('\n')
         except Exception as e:
             if get_settings().config.verbosity_level >= 2:
-                get_logger().info(f"Could not dedent code snippet for file {relevant_file}, error: {e}")
+                logging.info(f"Could not dedent code snippet for file {relevant_file}, error: {e}")
 
         return new_code_snippet
 
     async def _prepare_prediction_extended(self, model: str) -> dict:
-        get_logger().info('Getting PR diff...')
+        logging.info('Getting PR diff...')
         patches_diff_list = get_pr_multi_diffs(self.git_provider, self.token_handler, model,
                                                max_calls=get_settings().pr_code_suggestions.max_number_of_calls)
 
-        get_logger().info('Getting multi AI predictions...')
+        logging.info('Getting multi AI predictions...')
         prediction_list = []
         for i, patches_diff in enumerate(patches_diff_list):
-            get_logger().info(f"Processing chunk {i + 1} of {len(patches_diff_list)}")
+            logging.info(f"Processing chunk {i + 1} of {len(patches_diff_list)}")
             self.patches_diff = patches_diff
             prediction = await self._get_prediction(model)
             prediction_list.append(prediction)
@@ -223,8 +213,8 @@ class PRCodeSuggestions:
                 variables)
             user_prompt = environment.from_string(get_settings().pr_sort_code_suggestions_prompt.user).render(variables)
             if get_settings().config.verbosity_level >= 2:
-                get_logger().info(f"\nSystem prompt:\n{system_prompt}")
-                get_logger().info(f"\nUser prompt:\n{user_prompt}")
+                logging.info(f"\nSystem prompt:\n{system_prompt}")
+                logging.info(f"\nUser prompt:\n{user_prompt}")
             response, finish_reason = await self.ai_handler.chat_completion(model=model, system=system_prompt,
                                                                             user=user_prompt)
 
@@ -239,7 +229,7 @@ class PRCodeSuggestions:
                 data_sorted = data_sorted[:new_len]
         except Exception as e:
             if get_settings().config.verbosity_level >= 1:
-                get_logger().info(f"Could not sort suggestions, error: {e}")
+                logging.info(f"Could not sort suggestions, error: {e}")
             data_sorted = suggestion_list
 
         return data_sorted

pr_agent/tools/pr_config.py

@@ -1,6 +1,7 @@
+import logging
+
 from pr_agent.config_loader import get_settings
 from pr_agent.git_providers import get_git_provider
-from pr_agent.log import get_logger
 
 
 class PRConfig:
@@ -18,11 +19,11 @@ class PRConfig:
         self.git_provider = get_git_provider()(pr_url)
 
     async def run(self):
-        get_logger().info('Getting configuration settings...')
-        get_logger().info('Preparing configs...')
+        logging.info('Getting configuration settings...')
+        logging.info('Preparing configs...')
         pr_comment = self._prepare_pr_configs()
         if get_settings().config.publish_output:
-            get_logger().info('Pushing configs...')
+            logging.info('Pushing configs...')
             self.git_provider.publish_comment(pr_comment)
             self.git_provider.remove_initial_comment()
         return ""
@@ -43,5 +44,5 @@ class PRConfig:
                 comment_str += f"\n{header.lower()}.{key.lower()} = {repr(value) if isinstance(value, str) else value}"
                 comment_str += "  "
         if get_settings().config.verbosity_level >= 2:
-            get_logger().info(f"comment_str:\n{comment_str}")
+            logging.info(f"comment_str:\n{comment_str}")
         return comment_str

pr_agent/tools/pr_description.py

@@ -1,5 +1,6 @@
 import copy
-import re
+import json
+import logging
 from typing import List, Tuple
 
 from jinja2 import Environment, StrictUndefined
@@ -11,7 +12,6 @@ from pr_agent.algo.utils import load_yaml
 from pr_agent.config_loader import get_settings
 from pr_agent.git_providers import get_git_provider
 from pr_agent.git_providers.git_provider import get_main_pr_language
-from pr_agent.log import get_logger
 
 
 class PRDescription:
@@ -28,7 +28,6 @@ class PRDescription:
         self.main_pr_language = get_main_pr_language(
             self.git_provider.get_languages(), self.git_provider.get_files()
         )
-        self.pr_id = self.git_provider.get_pr_id()
 
         # Initialize the AI handler
         self.ai_handler = AiHandler()
@@ -62,44 +61,27 @@ class PRDescription:
         """
         Generates a PR description using an AI model and publishes it to the PR.
         """
-
-        try:
-            get_logger().info(f"Generating a PR description {self.pr_id}")
-            if get_settings().config.publish_output:
-                self.git_provider.publish_comment("Preparing PR description...", is_temporary=True)
-
-            await retry_with_fallback_models(self._prepare_prediction)
-
-            get_logger().info(f"Preparing answer {self.pr_id}")
-            if self.prediction:
-                self._prepare_data()
+        logging.info('Generating a PR description...')
+        if get_settings().config.publish_output:
+            self.git_provider.publish_comment("Preparing pr description...", is_temporary=True)
+        
+        await retry_with_fallback_models(self._prepare_prediction)
+        
+        logging.info('Preparing answer...')
+        pr_title, pr_body, pr_types, markdown_text = self._prepare_pr_answer()
+        
+        if get_settings().config.publish_output:
+            logging.info('Pushing answer...')
+            if get_settings().pr_description.publish_description_as_comment:
+                self.git_provider.publish_comment(markdown_text)
             else:
-                return None
-
-            pr_labels = []
-            if get_settings().pr_description.publish_labels:
-                pr_labels = self._prepare_labels()
-
-            if get_settings().pr_description.use_description_markers:
-                pr_title, pr_body = self._prepare_pr_answer_with_markers()
-            else:
-                pr_title, pr_body,  = self._prepare_pr_answer()
-            full_markdown_description = f"## Title\n\n{pr_title}\n\n___\n{pr_body}"
-
-            if get_settings().config.publish_output:
-                get_logger().info(f"Pushing answer {self.pr_id}")
-                if get_settings().pr_description.publish_description_as_comment:
-                    self.git_provider.publish_comment(full_markdown_description)
-                else:
-                    self.git_provider.publish_description(pr_title, pr_body)
-                    if get_settings().pr_description.publish_labels and self.git_provider.is_supported("get_labels"):
-                        current_labels = self.git_provider.get_labels()
-                        if current_labels is None:
-                            current_labels = []
-                        self.git_provider.publish_labels(pr_labels + current_labels)
-                self.git_provider.remove_initial_comment()
-        except Exception as e:
-            get_logger().error(f"Error generating PR description {self.pr_id}: {e}")
+                self.git_provider.publish_description(pr_title, pr_body)
+                if self.git_provider.is_supported("get_labels"):
+                    current_labels = self.git_provider.get_labels()
+                    if current_labels is None:
+                        current_labels = []
+                    self.git_provider.publish_labels(pr_types + current_labels)
+            self.git_provider.remove_initial_comment()
         
         return ""
 
@@ -117,12 +99,9 @@ class PRDescription:
             Any exceptions raised by the 'get_pr_diff' and '_get_prediction' functions.
 
         """
-        if get_settings().pr_description.use_description_markers and 'pr_agent:' not in self.user_description:
-            return None
-
-        get_logger().info(f"Getting PR diff {self.pr_id}")
+        logging.info('Getting PR diff...')
         self.patches_diff = get_pr_diff(self.git_provider, self.token_handler, model)
-        get_logger().info(f"Getting AI prediction {self.pr_id}")
+        logging.info('Getting AI prediction...')
         self.prediction = await self._get_prediction(model)
 
     async def _get_prediction(self, model: str) -> str:
@@ -143,8 +122,8 @@ class PRDescription:
         user_prompt = environment.from_string(get_settings().pr_description_prompt.user).render(variables)
 
         if get_settings().config.verbosity_level >= 2:
-            get_logger().info(f"\nSystem prompt:\n{system_prompt}")
-            get_logger().info(f"\nUser prompt:\n{user_prompt}")
+            logging.info(f"\nSystem prompt:\n{system_prompt}")
+            logging.info(f"\nUser prompt:\n{user_prompt}")
 
         response, finish_reason = await self.ai_handler.chat_completion(
             model=model,
@@ -155,71 +134,34 @@ class PRDescription:
 
         return response
 
-
-    def _prepare_data(self):
-        # Load the AI prediction data into a dictionary
-        self.data = load_yaml(self.prediction.strip())
-
-        if get_settings().pr_description.add_original_user_description and self.user_description:
-            self.data["User Description"] = self.user_description
-
-
-    def _prepare_labels(self) -> List[str]:
-        pr_types = []
-
-        # If the 'PR Type' key is present in the dictionary, split its value by comma and assign it to 'pr_types'
-        if 'PR Type' in self.data:
-            if type(self.data['PR Type']) == list:
-                pr_types = self.data['PR Type']
-            elif type(self.data['PR Type']) == str:
-                pr_types = self.data['PR Type'].split(',')
-
-        return pr_types
-
-    def _prepare_pr_answer_with_markers(self) -> Tuple[str, str]:
-        get_logger().info(f"Using description marker replacements {self.pr_id}")
-        title = self.vars["title"]
-        body = self.user_description
-        if get_settings().pr_description.include_generated_by_header:
-            ai_header = f"### 🤖 Generated by PR Agent at {self.git_provider.last_commit_id.sha}\n\n"
-        else:
-            ai_header = ""
-
-        ai_summary = self.data.get('PR Description')
-        if ai_summary and not re.search(r'<!--\s*pr_agent:summary\s*-->', body):
-            summary = f"{ai_header}{ai_summary}"
-            body = body.replace('pr_agent:summary', summary)
-
-        if not re.search(r'<!--\s*pr_agent:walkthrough\s*-->', body):
-            ai_walkthrough = self.data.get('PR Main Files Walkthrough')
-            if ai_walkthrough:
-                walkthrough = str(ai_header)
-                for file in ai_walkthrough:
-                    filename = file['filename'].replace("'", "`")
-                    description = file['changes in file'].replace("'", "`")
-                    walkthrough += f'- `{filename}`: {description}\n'
-
-                body = body.replace('pr_agent:walkthrough', walkthrough)
-
-        return title, body
-
-    def _prepare_pr_answer(self) -> Tuple[str, str]:
+    def _prepare_pr_answer(self) -> Tuple[str, str, List[str], str]:
         """
         Prepare the PR description based on the AI prediction data.
 
         Returns:
         - title: a string containing the PR title.
-        - pr_body: a string containing the PR description body in a markdown format.
+        - pr_body: a string containing the PR body in a markdown format.
+        - pr_types: a list of strings containing the PR types.
+        - markdown_text: a string containing the AI prediction data in a markdown format. used for publishing a comment
         """
+        # Load the AI prediction data into a dictionary
+        data = load_yaml(self.prediction.strip())
 
-        # Iterate over the dictionary items and append the key and value to 'markdown_text' in a markdown format
-        markdown_text = ""
-        for key, value in self.data.items():
-            markdown_text += f"## {key}\n\n"
-            markdown_text += f"{value}\n\n"
+        if get_settings().pr_description.add_original_user_description and self.user_description:
+            data["User Description"] = self.user_description
+
+        # Initialization
+        pr_types = []
+
+        # If the 'PR Type' key is present in the dictionary, split its value by comma and assign it to 'pr_types'
+        if 'PR Type' in data:
+            if type(data['PR Type']) == list:
+                pr_types = data['PR Type']
+            elif type(data['PR Type']) == str:
+                pr_types = data['PR Type'].split(',')
 
         # Remove the 'PR Title' key from the dictionary
-        ai_title = self.data.pop('PR Title', self.vars["title"])
+        ai_title = data.pop('PR Title')
         if get_settings().pr_description.keep_original_user_title:
             # Assign the original PR title to the 'title' variable
             title = self.vars["title"]
@@ -230,27 +172,25 @@ class PRDescription:
         # Iterate over the remaining dictionary items and append the key and value to 'pr_body' in a markdown format,
         # except for the items containing the word 'walkthrough'
         pr_body = ""
-        for idx, (key, value) in enumerate(self.data.items()):
+        for idx, (key, value) in enumerate(data.items()):
             pr_body += f"## {key}:\n"
             if 'walkthrough' in key.lower():
                 # for filename, description in value.items():
-                if self.git_provider.is_supported("gfm_markdown"):
-                    pr_body += "<details> <summary>files:</summary>\n\n"
                 for file in value:
                     filename = file['filename'].replace("'", "`")
                     description = file['changes in file']
                     pr_body += f'`{filename}`: {description}\n'
-                if self.git_provider.is_supported("gfm_markdown"):
-                    pr_body +="</details>\n"
             else:
                 # if the value is a list, join its items by comma
                 if type(value) == list:
                     value = ', '.join(v for v in value)
                 pr_body += f"{value}\n"
-            if idx < len(self.data) - 1:
+            if idx < len(data) - 1:
                 pr_body += "\n___\n"
 
-        if get_settings().config.verbosity_level >= 2:
-            get_logger().info(f"title:\n{title}\n{pr_body}")
+        markdown_text = f"## Title\n\n{title}\n\n___\n{pr_body}"
 
-        return title, pr_body
+        if get_settings().config.verbosity_level >= 2:
+            logging.info(f"title:\n{title}\n{pr_body}")
+
+        return title, pr_body, pr_types, markdown_text

pr_agent/tools/pr_information_from_user.py

@@ -1,4 +1,5 @@
 import copy
+import logging
 
 from jinja2 import Environment, StrictUndefined
 
@@ -8,7 +9,6 @@ from pr_agent.algo.token_handler import TokenHandler
 from pr_agent.config_loader import get_settings
 from pr_agent.git_providers import get_git_provider
 from pr_agent.git_providers.git_provider import get_main_pr_language
-from pr_agent.log import get_logger
 
 
 class PRInformationFromUser:
@@ -34,22 +34,22 @@ class PRInformationFromUser:
         self.prediction = None
 
     async def run(self):
-        get_logger().info('Generating question to the user...')
+        logging.info('Generating question to the user...')
         if get_settings().config.publish_output:
             self.git_provider.publish_comment("Preparing questions...", is_temporary=True)
         await retry_with_fallback_models(self._prepare_prediction)
-        get_logger().info('Preparing questions...')
+        logging.info('Preparing questions...')
         pr_comment = self._prepare_pr_answer()
         if get_settings().config.publish_output:
-            get_logger().info('Pushing questions...')
+            logging.info('Pushing questions...')
             self.git_provider.publish_comment(pr_comment)
             self.git_provider.remove_initial_comment()
         return ""
 
     async def _prepare_prediction(self, model):
-        get_logger().info('Getting PR diff...')
+        logging.info('Getting PR diff...')
         self.patches_diff = get_pr_diff(self.git_provider, self.token_handler, model)
-        get_logger().info('Getting AI prediction...')
+        logging.info('Getting AI prediction...')
         self.prediction = await self._get_prediction(model)
 
     async def _get_prediction(self, model: str):
@@ -59,8 +59,8 @@ class PRInformationFromUser:
         system_prompt = environment.from_string(get_settings().pr_information_from_user_prompt.system).render(variables)
         user_prompt = environment.from_string(get_settings().pr_information_from_user_prompt.user).render(variables)
         if get_settings().config.verbosity_level >= 2:
-            get_logger().info(f"\nSystem prompt:\n{system_prompt}")
-            get_logger().info(f"\nUser prompt:\n{user_prompt}")
+            logging.info(f"\nSystem prompt:\n{system_prompt}")
+            logging.info(f"\nUser prompt:\n{user_prompt}")
         response, finish_reason = await self.ai_handler.chat_completion(model=model, temperature=0.2,
                                                                         system=system_prompt, user=user_prompt)
         return response
@@ -68,7 +68,7 @@ class PRInformationFromUser:
     def _prepare_pr_answer(self) -> str:
         model_output = self.prediction.strip()
         if get_settings().config.verbosity_level >= 2:
-            get_logger().info(f"answer_str:\n{model_output}")
+            logging.info(f"answer_str:\n{model_output}")
         answer_str = f"{model_output}\n\n Please respond to the questions above in the following format:\n\n" +\
                      "\n>/answer\n>1) ...\n>2) ...\n>...\n"
         return answer_str

pr_agent/tools/pr_questions.py

@@ -1,4 +1,5 @@
 import copy
+import logging
 
 from jinja2 import Environment, StrictUndefined
 
@@ -8,7 +9,6 @@ from pr_agent.algo.token_handler import TokenHandler
 from pr_agent.config_loader import get_settings
 from pr_agent.git_providers import get_git_provider
 from pr_agent.git_providers.git_provider import get_main_pr_language
-from pr_agent.log import get_logger
 
 
 class PRQuestions:
@@ -44,22 +44,22 @@ class PRQuestions:
         return question_str
 
     async def run(self):
-        get_logger().info('Answering a PR question...')
+        logging.info('Answering a PR question...')
         if get_settings().config.publish_output:
             self.git_provider.publish_comment("Preparing answer...", is_temporary=True)
         await retry_with_fallback_models(self._prepare_prediction)
-        get_logger().info('Preparing answer...')
+        logging.info('Preparing answer...')
         pr_comment = self._prepare_pr_answer()
         if get_settings().config.publish_output:
-            get_logger().info('Pushing answer...')
+            logging.info('Pushing answer...')
             self.git_provider.publish_comment(pr_comment)
             self.git_provider.remove_initial_comment()
         return ""
 
     async def _prepare_prediction(self, model: str):
-        get_logger().info('Getting PR diff...')
+        logging.info('Getting PR diff...')
         self.patches_diff = get_pr_diff(self.git_provider, self.token_handler, model)
-        get_logger().info('Getting AI prediction...')
+        logging.info('Getting AI prediction...')
         self.prediction = await self._get_prediction(model)
 
     async def _get_prediction(self, model: str):
@@ -69,8 +69,8 @@ class PRQuestions:
         system_prompt = environment.from_string(get_settings().pr_questions_prompt.system).render(variables)
         user_prompt = environment.from_string(get_settings().pr_questions_prompt.user).render(variables)
         if get_settings().config.verbosity_level >= 2:
-            get_logger().info(f"\nSystem prompt:\n{system_prompt}")
-            get_logger().info(f"\nUser prompt:\n{user_prompt}")
+            logging.info(f"\nSystem prompt:\n{system_prompt}")
+            logging.info(f"\nUser prompt:\n{user_prompt}")
         response, finish_reason = await self.ai_handler.chat_completion(model=model, temperature=0.2,
                                                                         system=system_prompt, user=user_prompt)
         return response
@@ -79,5 +79,5 @@ class PRQuestions:
         answer_str = f"Question: {self.question_str}\n\n"
         answer_str += f"Answer:\n{self.prediction.strip()}\n\n"
         if get_settings().config.verbosity_level >= 2:
-            get_logger().info(f"answer_str:\n{answer_str}")
+            logging.info(f"answer_str:\n{answer_str}")
         return answer_str

pr_agent/tools/pr_reviewer.py

@@ -1,4 +1,6 @@
 import copy
+import json
+import logging
 from collections import OrderedDict
 from typing import List, Tuple
 
@@ -7,13 +9,13 @@ from jinja2 import Environment, StrictUndefined
 from yaml import SafeLoader
 
 from pr_agent.algo.ai_handler import AiHandler
-from pr_agent.algo.pr_processing import get_pr_diff, retry_with_fallback_models
+from pr_agent.algo.pr_processing import get_pr_diff, retry_with_fallback_models, \
+    find_line_number_of_relevant_line_in_file, clip_tokens
 from pr_agent.algo.token_handler import TokenHandler
-from pr_agent.algo.utils import convert_to_markdown, load_yaml, try_fix_yaml
+from pr_agent.algo.utils import convert_to_markdown, try_fix_json, try_fix_yaml, load_yaml
 from pr_agent.config_loader import get_settings
 from pr_agent.git_providers import get_git_provider
 from pr_agent.git_providers.git_provider import IncrementalPR, get_main_pr_language
-from pr_agent.log import get_logger
 from pr_agent.servers.help import actions_help_text, bot_help_text
 
 
@@ -57,7 +59,6 @@ class PRReviewer:
             "require_tests": get_settings().pr_reviewer.require_tests_review,
             "require_security": get_settings().pr_reviewer.require_security_review,
             "require_focused": get_settings().pr_reviewer.require_focused_review,
-            "require_estimate_effort_to_review": get_settings().pr_reviewer.require_estimate_effort_to_review,
             'num_code_suggestions': get_settings().pr_reviewer.num_code_suggestions,
             'question_str': question_str,
             'answer_str': answer_str,
@@ -93,32 +94,28 @@ class PRReviewer:
         """
         Review the pull request and generate feedback.
         """
+        if self.is_auto and not get_settings().pr_reviewer.automatic_review:
+            logging.info(f'Automatic review is disabled {self.pr_url}')
+            return None
 
-        try:
-            if self.is_auto and not get_settings().pr_reviewer.automatic_review:
-                get_logger().info(f'Automatic review is disabled {self.pr_url}')
-                return None
+        logging.info(f'Reviewing PR: {self.pr_url} ...')
 
-            get_logger().info(f'Reviewing PR: {self.pr_url} ...')
-
-            if get_settings().config.publish_output:
-                self.git_provider.publish_comment("Preparing review...", is_temporary=True)
-
-            await retry_with_fallback_models(self._prepare_prediction)
-
-            get_logger().info('Preparing PR review...')
-            pr_comment = self._prepare_pr_review()
-
-            if get_settings().config.publish_output:
-                get_logger().info('Pushing PR review...')
-                self.git_provider.publish_comment(pr_comment)
-                self.git_provider.remove_initial_comment()
-
-                if get_settings().pr_reviewer.inline_code_comments:
-                    get_logger().info('Pushing inline code comments...')
-                    self._publish_inline_code_comments()
-        except Exception as e:
-            get_logger().error(f"Failed to review PR: {e}")
+        if get_settings().config.publish_output:
+            self.git_provider.publish_comment("Preparing review...", is_temporary=True)
+    
+        await retry_with_fallback_models(self._prepare_prediction)
+    
+        logging.info('Preparing PR review...')
+        pr_comment = self._prepare_pr_review()
+    
+        if get_settings().config.publish_output:
+            logging.info('Pushing PR review...')
+            self.git_provider.publish_comment(pr_comment)
+            self.git_provider.remove_initial_comment()
+        
+            if get_settings().pr_reviewer.inline_code_comments:
+                logging.info('Pushing inline code comments...')
+                self._publish_inline_code_comments()
 
     async def _prepare_prediction(self, model: str) -> None:
         """
@@ -130,9 +127,9 @@ class PRReviewer:
         Returns:
             None
         """
-        get_logger().info('Getting PR diff...')
+        logging.info('Getting PR diff...')
         self.patches_diff = get_pr_diff(self.git_provider, self.token_handler, model)
-        get_logger().info('Getting AI prediction...')
+        logging.info('Getting AI prediction...')
         self.prediction = await self._get_prediction(model)
 
     async def _get_prediction(self, model: str) -> str:
@@ -153,8 +150,8 @@ class PRReviewer:
         user_prompt = environment.from_string(get_settings().pr_review_prompt.user).render(variables)
 
         if get_settings().config.verbosity_level >= 2:
-            get_logger().info(f"\nSystem prompt:\n{system_prompt}")
-            get_logger().info(f"\nUser prompt:\n{user_prompt}")
+            logging.info(f"\nSystem prompt:\n{system_prompt}")
+            logging.info(f"\nUser prompt:\n{user_prompt}")
 
         response, finish_reason = await self.ai_handler.chat_completion(
             model=model,
@@ -207,22 +204,6 @@ class PRReviewer:
                         link = self.git_provider.generate_link_to_relevant_line_number(suggestion)
                         if link:
                             suggestion['relevant line'] = f"[{suggestion['relevant line']}]({link})"
-                    else:
-                        pass
-                        # try:
-                        #     relevant_file = suggestion['relevant file'].strip('`').strip("'")
-                        #     relevant_line_str = suggestion['relevant line']
-                        #     if not relevant_line_str:
-                        #         return ""
-                        #
-                        #     position, absolute_position = find_line_number_of_relevant_line_in_file(
-                        #         self.git_provider.diff_files, relevant_file, relevant_line_str)
-                        #     if absolute_position != -1:
-                        #         suggestion[
-                        #             'relevant line'] = f"{suggestion['relevant line']} (line {absolute_position})"
-                        # except:
-                        #     pass
-
 
         # Add incremental review section
         if self.incremental.is_incremental:
@@ -233,21 +214,20 @@ class PRReviewer:
                 "⏮️ Review for commits since previous PR-Agent review": f"Starting from commit {last_commit_url}"}})
             data.move_to_end('Incremental PR Review', last=False)
 
-        markdown_text = convert_to_markdown(data, self.git_provider.is_supported("gfm_markdown"))
+        markdown_text = convert_to_markdown(data)
         user = self.git_provider.get_user_id()
 
         # Add help text if not in CLI mode
         if not get_settings().get("CONFIG.CLI_MODE", False):
             markdown_text += "\n### How to use\n"
-            bot_user = "[bot]" if get_settings().github_app.override_deployment_type else get_settings().github_app.bot_user
-            if user and bot_user not in user:
+            if user and '[bot]' not in user:
                 markdown_text += bot_help_text(user)
             else:
                 markdown_text += actions_help_text
 
         # Log markdown response if verbosity level is high
         if get_settings().config.verbosity_level >= 2:
-            get_logger().info(f"Markdown response:\n{markdown_text}")
+            logging.info(f"Markdown response:\n{markdown_text}")
 
         if markdown_text == None or len(markdown_text) == 0:
             markdown_text = ""
@@ -266,7 +246,7 @@ class PRReviewer:
         try:
             data = yaml.load(review_text, Loader=SafeLoader)
         except Exception as e:
-            get_logger().error(f"Failed to parse AI prediction: {e}")
+            logging.error(f"Failed to parse AI prediction: {e}")
             data = try_fix_yaml(review_text)
 
         comments: List[str] = []
@@ -275,7 +255,7 @@ class PRReviewer:
             relevant_line_in_file = suggestion.get('relevant line', '').strip()
             content = suggestion.get('suggestion', '')
             if not relevant_file or not relevant_line_in_file or not content:
-                get_logger().info("Skipping inline comment with missing file/line/content")
+                logging.info("Skipping inline comment with missing file/line/content")
                 continue
 
             if self.git_provider.is_supported("create_inline_comment"):
@@ -286,7 +266,7 @@ class PRReviewer:
                 self.git_provider.publish_inline_comment(content, relevant_file, relevant_line_in_file)
 
         if comments:
-                self.git_provider.publish_inline_comments(comments)
+            self.git_provider.publish_inline_comments(comments)
 
     def _get_user_answers(self) -> Tuple[str, str]:
         """

pr_agent/tools/pr_similar_issue.py

@@ -1,275 +0,0 @@
-from enum import Enum
-from typing import List
-
-import openai
-import pandas as pd
-import pinecone
-from pinecone_datasets import Dataset, DatasetMetadata
-from pydantic import BaseModel, Field
-
-from pr_agent.algo import MAX_TOKENS
-from pr_agent.algo.token_handler import TokenHandler
-from pr_agent.config_loader import get_settings
-from pr_agent.git_providers import get_git_provider
-from pr_agent.log import get_logger
-
-MODEL = "text-embedding-ada-002"
-
-
-class PRSimilarIssue:
-    def __init__(self, issue_url: str, args: list = None):
-        if get_settings().config.git_provider != "github":
-            raise Exception("Only github is supported for similar issue tool")
-
-        self.cli_mode = get_settings().CONFIG.CLI_MODE
-        self.max_issues_to_scan = get_settings().pr_similar_issue.max_issues_to_scan
-        self.issue_url = issue_url
-        self.git_provider = get_git_provider()()
-        repo_name, issue_number = self.git_provider._parse_issue_url(issue_url.split('=')[-1])
-        self.git_provider.repo = repo_name
-        self.git_provider.repo_obj = self.git_provider.github_client.get_repo(repo_name)
-        self.token_handler = TokenHandler()
-        repo_obj = self.git_provider.repo_obj
-        repo_name_for_index = self.repo_name_for_index = repo_obj.full_name.lower().replace('/', '-').replace('_/', '-')
-        index_name = self.index_name = "codium-ai-pr-agent-issues"
-
-        # assuming pinecone api key and environment are set in secrets file
-        try:
-            api_key = get_settings().pinecone.api_key
-            environment = get_settings().pinecone.environment
-        except Exception:
-            if not self.cli_mode:
-                repo_name, original_issue_number = self.git_provider._parse_issue_url(self.issue_url.split('=')[-1])
-                issue_main = self.git_provider.repo_obj.get_issue(original_issue_number)
-                issue_main.create_comment("Please set pinecone api key and environment in secrets file")
-            raise Exception("Please set pinecone api key and environment in secrets file")
-
-        # check if index exists, and if repo is already indexed
-        run_from_scratch = False
-        upsert = True
-        pinecone.init(api_key=api_key, environment=environment)
-        if not index_name in pinecone.list_indexes():
-            run_from_scratch = True
-            upsert = False
-        else:
-            if get_settings().pr_similar_issue.force_update_dataset:
-                upsert = True
-            else:
-                pinecone_index = pinecone.Index(index_name=index_name)
-                res = pinecone_index.fetch([f"example_issue_{repo_name_for_index}"]).to_dict()
-                if res["vectors"]:
-                    upsert = False
-
-        if run_from_scratch or upsert:  # index the entire repo
-            get_logger().info('Indexing the entire repo...')
-
-            get_logger().info('Getting issues...')
-            issues = list(repo_obj.get_issues(state='all'))
-            get_logger().info('Done')
-            self._update_index_with_issues(issues, repo_name_for_index, upsert=upsert)
-        else:  # update index if needed
-            pinecone_index = pinecone.Index(index_name=index_name)
-            issues_to_update = []
-            issues_paginated_list = repo_obj.get_issues(state='all')
-            counter = 1
-            for issue in issues_paginated_list:
-                if issue.pull_request:
-                    continue
-                issue_str, comments, number = self._process_issue(issue)
-                issue_key = f"issue_{number}"
-                id = issue_key + "." + "issue"
-                res = pinecone_index.fetch([id]).to_dict()
-                is_new_issue = True
-                for vector in res["vectors"].values():
-                    if vector['metadata']['repo'] == repo_name_for_index:
-                        is_new_issue = False
-                        break
-                if is_new_issue:
-                    counter += 1
-                    issues_to_update.append(issue)
-                else:
-                    break
-
-            if issues_to_update:
-                get_logger().info(f'Updating index with {counter} new issues...')
-                self._update_index_with_issues(issues_to_update, repo_name_for_index, upsert=True)
-            else:
-                get_logger().info('No new issues to update')
-
-    async def run(self):
-        get_logger().info('Getting issue...')
-        repo_name, original_issue_number = self.git_provider._parse_issue_url(self.issue_url.split('=')[-1])
-        issue_main = self.git_provider.repo_obj.get_issue(original_issue_number)
-        issue_str, comments, number = self._process_issue(issue_main)
-        openai.api_key = get_settings().openai.key
-        get_logger().info('Done')
-
-        get_logger().info('Querying...')
-        res = openai.Embedding.create(input=[issue_str], engine=MODEL)
-        embeds = [record['embedding'] for record in res['data']]
-        pinecone_index = pinecone.Index(index_name=self.index_name)
-        res = pinecone_index.query(embeds[0],
-                                   top_k=5,
-                                   filter={"repo": self.repo_name_for_index},
-                                   include_metadata=True).to_dict()
-        relevant_issues_number_list = []
-        relevant_comment_number_list = []
-        score_list = []
-        for r in res['matches']:
-            issue_number = int(r["id"].split('.')[0].split('_')[-1])
-            if original_issue_number == issue_number:
-                continue
-            if issue_number not in relevant_issues_number_list:
-                relevant_issues_number_list.append(issue_number)
-            if 'comment' in r["id"]:
-                relevant_comment_number_list.append(int(r["id"].split('.')[1].split('_')[-1]))
-            else:
-                relevant_comment_number_list.append(-1)
-            score_list.append(str("{:.2f}".format(r['score'])))
-        get_logger().info('Done')
-
-        get_logger().info('Publishing response...')
-        similar_issues_str = "### Similar Issues\n___\n\n"
-        for i, issue_number_similar in enumerate(relevant_issues_number_list):
-            issue = self.git_provider.repo_obj.get_issue(issue_number_similar)
-            title = issue.title
-            url = issue.html_url
-            if relevant_comment_number_list[i] != -1:
-                url = list(issue.get_comments())[relevant_comment_number_list[i]].html_url
-            similar_issues_str += f"{i + 1}. **[{title}]({url})** (score={score_list[i]})\n\n"
-        if get_settings().config.publish_output:
-            response = issue_main.create_comment(similar_issues_str)
-        get_logger().info(similar_issues_str)
-        get_logger().info('Done')
-
-    def _process_issue(self, issue):
-        header = issue.title
-        body = issue.body
-        number = issue.number
-        if get_settings().pr_similar_issue.skip_comments:
-            comments = []
-        else:
-            comments = list(issue.get_comments())
-        issue_str = f"Issue Header: \"{header}\"\n\nIssue Body:\n{body}"
-        return issue_str, comments, number
-
-    def _update_index_with_issues(self, issues_list, repo_name_for_index, upsert=False):
-        get_logger().info('Processing issues...')
-        corpus = Corpus()
-        example_issue_record = Record(
-            id=f"example_issue_{repo_name_for_index}",
-            text="example_issue",
-            metadata=Metadata(repo=repo_name_for_index)
-        )
-        corpus.append(example_issue_record)
-
-        counter = 0
-        for issue in issues_list:
-            if issue.pull_request:
-                continue
-
-            counter += 1
-            if counter % 100 == 0:
-                get_logger().info(f"Scanned {counter} issues")
-            if counter >= self.max_issues_to_scan:
-                get_logger().info(f"Scanned {self.max_issues_to_scan} issues, stopping")
-                break
-
-            issue_str, comments, number = self._process_issue(issue)
-            issue_key = f"issue_{number}"
-            username = issue.user.login
-            created_at = str(issue.created_at)
-            if len(issue_str) < 8000 or \
-                    self.token_handler.count_tokens(issue_str) < MAX_TOKENS[MODEL]:  # fast reject first
-                issue_record = Record(
-                    id=issue_key + "." + "issue",
-                    text=issue_str,
-                    metadata=Metadata(repo=repo_name_for_index,
-                                      username=username,
-                                      created_at=created_at,
-                                      level=IssueLevel.ISSUE)
-                )
-                corpus.append(issue_record)
-                if comments:
-                    for j, comment in enumerate(comments):
-                        comment_body = comment.body
-                        num_words_comment = len(comment_body.split())
-                        if num_words_comment < 10 or not isinstance(comment_body, str):
-                            continue
-
-                        if len(comment_body) < 8000 or \
-                                self.token_handler.count_tokens(comment_body) < MAX_TOKENS[MODEL]:
-                            comment_record = Record(
-                                id=issue_key + ".comment_" + str(j + 1),
-                                text=comment_body,
-                                metadata=Metadata(repo=repo_name_for_index,
-                                                  username=username,  # use issue username for all comments
-                                                  created_at=created_at,
-                                                  level=IssueLevel.COMMENT)
-                            )
-                            corpus.append(comment_record)
-        df = pd.DataFrame(corpus.dict()["documents"])
-        get_logger().info('Done')
-
-        get_logger().info('Embedding...')
-        openai.api_key = get_settings().openai.key
-        list_to_encode = list(df["text"].values)
-        try:
-            res = openai.Embedding.create(input=list_to_encode, engine=MODEL)
-            embeds = [record['embedding'] for record in res['data']]
-        except:
-            embeds = []
-            get_logger().error('Failed to embed entire list, embedding one by one...')
-            for i, text in enumerate(list_to_encode):
-                try:
-                    res = openai.Embedding.create(input=[text], engine=MODEL)
-                    embeds.append(res['data'][0]['embedding'])
-                except:
-                    embeds.append([0] * 1536)
-        df["values"] = embeds
-        meta = DatasetMetadata.empty()
-        meta.dense_model.dimension = len(embeds[0])
-        ds = Dataset.from_pandas(df, meta)
-        get_logger().info('Done')
-
-        api_key = get_settings().pinecone.api_key
-        environment = get_settings().pinecone.environment
-        if not upsert:
-            get_logger().info('Creating index from scratch...')
-            ds.to_pinecone_index(self.index_name, api_key=api_key, environment=environment)
-        else:
-            get_logger().info('Upserting index...')
-            namespace = ""
-            batch_size: int = 100
-            concurrency: int = 10
-            pinecone.init(api_key=api_key, environment=environment)
-            ds._upsert_to_index(self.index_name, namespace, batch_size, concurrency)
-        get_logger().info('Done')
-
-
-class IssueLevel(str, Enum):
-    ISSUE = "issue"
-    COMMENT = "comment"
-
-
-class Metadata(BaseModel):
-    repo: str
-    username: str = Field(default="@codium")
-    created_at: str = Field(default="01-01-1970 00:00:00.00000")
-    level: IssueLevel = Field(default=IssueLevel.ISSUE)
-
-    class Config:
-        use_enum_values = True
-
-
-class Record(BaseModel):
-    id: str
-    text: str
-    metadata: Metadata
-
-
-class Corpus(BaseModel):
-    documents: List[Record] = Field(default=[])
-
-    def append(self, r: Record):
-        self.documents.append(r)

pr_agent/tools/pr_update_changelog.py

@@ -1,4 +1,5 @@
 import copy
+import logging
 from datetime import date
 from time import sleep
 from typing import Tuple
@@ -9,9 +10,8 @@ from pr_agent.algo.ai_handler import AiHandler
 from pr_agent.algo.pr_processing import get_pr_diff, retry_with_fallback_models
 from pr_agent.algo.token_handler import TokenHandler
 from pr_agent.config_loader import get_settings
-from pr_agent.git_providers import get_git_provider
+from pr_agent.git_providers import GithubProvider, get_git_provider
 from pr_agent.git_providers.git_provider import get_main_pr_language
-from pr_agent.log import get_logger
 
 CHANGELOG_LINES = 50
 
@@ -46,28 +46,28 @@ class PRUpdateChangelog:
                                           get_settings().pr_update_changelog_prompt.user)
 
     async def run(self):
-        # assert type(self.git_provider) == GithubProvider, "Currently only Github is supported"
+        assert type(self.git_provider) == GithubProvider, "Currently only Github is supported"
 
-        get_logger().info('Updating the changelog...')
+        logging.info('Updating the changelog...')
         if get_settings().config.publish_output:
             self.git_provider.publish_comment("Preparing changelog updates...", is_temporary=True)
         await retry_with_fallback_models(self._prepare_prediction)
-        get_logger().info('Preparing PR changelog updates...')
+        logging.info('Preparing PR changelog updates...')
         new_file_content, answer = self._prepare_changelog_update()
         if get_settings().config.publish_output:
             self.git_provider.remove_initial_comment()
-            get_logger().info('Publishing changelog updates...')
+            logging.info('Publishing changelog updates...')
             if self.commit_changelog:
-                get_logger().info('Pushing PR changelog updates to repo...')
+                logging.info('Pushing PR changelog updates to repo...')
                 self._push_changelog_update(new_file_content, answer)
             else:
-                get_logger().info('Publishing PR changelog as comment...')
+                logging.info('Publishing PR changelog as comment...')
                 self.git_provider.publish_comment(f"**Changelog updates:**\n\n{answer}")
 
     async def _prepare_prediction(self, model: str):
-        get_logger().info('Getting PR diff...')
+        logging.info('Getting PR diff...')
         self.patches_diff = get_pr_diff(self.git_provider, self.token_handler, model)
-        get_logger().info('Getting AI prediction...')
+        logging.info('Getting AI prediction...')
         self.prediction = await self._get_prediction(model)
 
     async def _get_prediction(self, model: str):
@@ -77,8 +77,8 @@ class PRUpdateChangelog:
         system_prompt = environment.from_string(get_settings().pr_update_changelog_prompt.system).render(variables)
         user_prompt = environment.from_string(get_settings().pr_update_changelog_prompt.user).render(variables)
         if get_settings().config.verbosity_level >= 2:
-            get_logger().info(f"\nSystem prompt:\n{system_prompt}")
-            get_logger().info(f"\nUser prompt:\n{user_prompt}")
+            logging.info(f"\nSystem prompt:\n{system_prompt}")
+            logging.info(f"\nUser prompt:\n{user_prompt}")
         response, finish_reason = await self.ai_handler.chat_completion(model=model, temperature=0.2,
                                                                         system=system_prompt, user=user_prompt)
 
@@ -100,7 +100,7 @@ class PRUpdateChangelog:
                       "\n>'/update_changelog --pr_update_changelog.push_changelog_changes=true'\n"
 
         if get_settings().config.verbosity_level >= 2:
-            get_logger().info(f"answer:\n{answer}")
+            logging.info(f"answer:\n{answer}")
 
         return new_file_content, answer
 
@@ -149,7 +149,7 @@ Example:
         except Exception:
             self.changelog_file_str = ""
             if self.commit_changelog:
-                get_logger().info("No CHANGELOG.md file found in the repository. Creating one...")
+                logging.info("No CHANGELOG.md file found in the repository. Creating one...")
                 changelog_file = self.git_provider.repo_obj.create_file(path="CHANGELOG.md",
                                                                              message='add CHANGELOG.md',
                                                                              content="",

requirements.txt

@@ -7,18 +7,15 @@ Jinja2==3.1.2
 tiktoken==0.4.0
 uvicorn==0.22.0
 python-gitlab==3.15.0
-pytest==7.4.0
-aiohttp==3.8.4
+pytest~=7.4.0
+aiohttp~=3.8.4
 atlassian-python-api==3.39.0
-GitPython==3.1.32
+GitPython~=3.1.32
 PyYAML==6.0
 starlette-context==0.3.6
-litellm~=0.1.574
-boto3==1.28.25
+litellm~=0.1.504
+boto3~=1.28.25
 google-cloud-storage==2.10.0
 ujson==5.8.0
 azure-devops==7.1.0b3
-msrest==0.7.1
-pinecone-client
-pinecone-datasets @ git+https://github.com/mrT23/pinecone-datasets.git@main
-loguru==0.7.2
+msrest==0.7.1

tests/unittest/test_codecommit_client.py

@@ -110,7 +110,7 @@ class TestCodeCommitProvider:
         # Mock the response from the AWS client for get_pull_request method
         api.boto_client.get_pull_request.return_value = {
             "pullRequest": {
-                "pullRequestId": "321",
+                "pullRequestId": "3",
                 "title": "My PR",
                 "description": "My PR description",
                 "pullRequestTargets": [

tests/unittest/test_codecommit_provider.py

@@ -1,8 +1,6 @@
 import pytest
-from unittest.mock import patch
 from pr_agent.git_providers.codecommit_provider import CodeCommitFile
 from pr_agent.git_providers.codecommit_provider import CodeCommitProvider
-from pr_agent.git_providers.codecommit_provider import PullRequestCCMimic
 from pr_agent.git_providers.git_provider import EDIT_TYPE
 
 
@@ -27,21 +25,6 @@ class TestCodeCommitFile:
 
 
 class TestCodeCommitProvider:
-    def test_get_title(self):
-        # Test that the get_title() function returns the PR title
-        with patch.object(CodeCommitProvider, "__init__", lambda x, y: None):
-            provider = CodeCommitProvider(None)
-            provider.pr = PullRequestCCMimic("My Test PR Title", [])
-            assert provider.get_title() == "My Test PR Title"
-
-    def test_get_pr_id(self):
-        # Test that the get_pr_id() function returns the correct ID
-        with patch.object(CodeCommitProvider, "__init__", lambda x, y: None):
-            provider = CodeCommitProvider(None)
-            provider.repo_name = "my_test_repo"
-            provider.pr_num = 321
-            assert provider.get_pr_id() == "my_test_repo/321"
-
     def test_parse_pr_url(self):
         # Test that the _parse_pr_url() function can extract the repo name and PR number from a CodeCommit URL
         url = "https://us-east-1.console.aws.amazon.com/codesuite/codecommit/repositories/my_test_repo/pull-requests/321"
@@ -186,4 +169,4 @@ class TestCodeCommitProvider:
     def test_remove_markdown_html(self):
         input = "## PR Feedback\n<details><summary>Code feedback:</summary>\nfile foo\n</summary>\n"
         expect = "## PR Feedback\nCode feedback:\nfile foo\n\n"
-        assert CodeCommitProvider._remove_markdown_html(input) == expect
+        assert CodeCommitProvider._remove_markdown_html(input) == expect

tests/unittest/test_file_filter.py

@@ -1,80 +0,0 @@
-import pytest
-from pr_agent.algo.file_filter import filter_ignored
-from pr_agent.config_loader import global_settings
-
-class TestIgnoreFilter:
-    def test_no_ignores(self):
-        """
-        Test no files are ignored when no patterns are specified.
-        """
-        files = [
-            type('', (object,), {'filename': 'file1.py'})(),
-            type('', (object,), {'filename': 'file2.java'})(),
-            type('', (object,), {'filename': 'file3.cpp'})(),
-            type('', (object,), {'filename': 'file4.py'})(),
-            type('', (object,), {'filename': 'file5.py'})()
-        ]
-        assert filter_ignored(files) == files, "Expected all files to be returned when no ignore patterns are given."
-
-    def test_glob_ignores(self, monkeypatch):
-        """
-        Test files are ignored when glob patterns are specified.
-        """
-        monkeypatch.setattr(global_settings.ignore, 'glob', ['*.py'])
-
-        files = [
-            type('', (object,), {'filename': 'file1.py'})(),
-            type('', (object,), {'filename': 'file2.java'})(),
-            type('', (object,), {'filename': 'file3.cpp'})(),
-            type('', (object,), {'filename': 'file4.py'})(),
-            type('', (object,), {'filename': 'file5.py'})()
-        ]
-        expected = [
-            files[1],
-            files[2]
-        ]
-
-        filtered_files = filter_ignored(files)
-        assert filtered_files == expected, f"Expected {[file.filename for file in expected]}, but got {[file.filename for file in filtered_files]}."
-
-    def test_regex_ignores(self, monkeypatch):
-        """
-        Test files are ignored when regex patterns are specified.
-        """
-        monkeypatch.setattr(global_settings.ignore, 'regex', ['^file[2-4]\..*$'])
-
-        files = [
-            type('', (object,), {'filename': 'file1.py'})(),
-            type('', (object,), {'filename': 'file2.java'})(),
-            type('', (object,), {'filename': 'file3.cpp'})(),
-            type('', (object,), {'filename': 'file4.py'})(),
-            type('', (object,), {'filename': 'file5.py'})()
-        ]
-        expected = [
-            files[0],
-            files[4]
-        ]
-
-        filtered_files = filter_ignored(files)
-        assert filtered_files == expected, f"Expected {[file.filename for file in expected]}, but got {[file.filename for file in filtered_files]}."
-
-    def test_invalid_regex(self, monkeypatch):
-        """
-        Test invalid patterns are quietly ignored.
-        """
-        monkeypatch.setattr(global_settings.ignore, 'regex', ['(((||', '^file[2-4]\..*$'])
-
-        files = [
-            type('', (object,), {'filename': 'file1.py'})(),
-            type('', (object,), {'filename': 'file2.java'})(),
-            type('', (object,), {'filename': 'file3.cpp'})(),
-            type('', (object,), {'filename': 'file4.py'})(),
-            type('', (object,), {'filename': 'file5.py'})()
-        ]
-        expected = [
-            files[0],
-            files[4]
-        ]
-
-        filtered_files = filter_ignored(files)
-        assert filtered_files == expected, f"Expected {[file.filename for file in expected]}, but got {[file.filename for file in filtered_files]}."

tests/unittest/test_handle_patch_deletions.py

@@ -43,6 +43,18 @@ class TestHandlePatchDeletions:
         assert handle_patch_deletions(patch, original_file_content_str, new_file_content_str,
                                       file_name) == patch.rstrip()
 
+    # Tests that handle_patch_deletions logs a message when verbosity_level is greater than 0
+    def test_handle_patch_deletions_happy_path_verbosity_level_greater_than_0(self, caplog):
+        patch = '--- a/file.py\n+++ b/file.py\n@@ -1,2 +1,2 @@\n-foo\n-bar\n+baz\n'
+        original_file_content_str = 'foo\nbar\n'
+        new_file_content_str = ''
+        file_name = 'file.py'
+        get_settings().config.verbosity_level = 1
+
+        with caplog.at_level(logging.INFO):
+            handle_patch_deletions(patch, original_file_content_str, new_file_content_str, file_name)
+            assert any("Processing file" in message for message in caplog.messages)
+
     # Tests that handle_patch_deletions returns 'File was deleted' when new_file_content_str is empty
     def test_handle_patch_deletions_edge_case_new_file_content_empty(self):
         patch = '--- a/file.py\n+++ b/file.py\n@@ -1,2 +1,2 @@\n-foo\n-bar\n'

tests/unittest/test_language_handler.py

@@ -61,7 +61,7 @@ class TestSortFilesByMainLanguages:
             type('', (object,), {'filename': 'file1.py'})(),
             type('', (object,), {'filename': 'file2.java'})()
         ]
-        expected_output = [{'language': 'Other', 'files': files}]
+        expected_output = [{'language': 'Other', 'files': []}]
         assert sort_files_by_main_languages(languages, files) == expected_output
 
     # Tests that function handles empty files list