Merge branch 'main' into 10-add-rag-support

.experiments/code_review/code_reviews_20240815_142254/no_eval/pr_335_comments.json

@@ -0,0 +1,17 @@
+[
+  {
+    "topic": "Error Handling",
+    "comment": "Removed parameter 'reeval_response' without handling its previous functionality.",
+    "confidence": "critical",
+    "reason": "The removal of 'reeval_response' may lead to unexpected behavior if the function relies on it.",
+    "solution": "Evaluate the necessity of the 'reeval_response' parameter and ensure that its removal does not affect the logic of the code.",
+    "actual_code": "desc = self._process_full_diff(prompt, user, reeval_response)",
+    "fixed_code": "desc = self._process_full_diff(prompt, user)",
+    "file_name": "kaizen/generator/pr_description.py",
+    "start_line": 54,
+    "end_line": 54,
+    "side": "LEFT",
+    "sentiment": "negative",
+    "severity_level": 8
+  }
+]

.experiments/code_review/code_reviews_20240815_142254/no_eval/pr_335_review.md

@@ -0,0 +1,98 @@
+# 🔍 Code Review Summary
+
+## 📊 Stats
+- Total Issues: 4
+- Critical: 1
+- Important: 2
+- Minor: 1
+- Files Affected: 1
+## 🏆 Code Quality
+[█████████████████░░░] 85% (Good)
+
+## 🚨 Critical Issues
+
+<details>
+<summary><strong>Error Handling (1 issues)</strong></summary>
+
+### 1. Removed parameter 'reeval_response' without handling its previous functionality.
+📁 **File:** `kaizen/generator/pr_description.py:54`
+⚖️ **Severity:** 8/10
+🔍 **Description:** The removal of 'reeval_response' may lead to unexpected behavior if the function relies on it.
+💡 **Solution:** Evaluate the necessity of the 'reeval_response' parameter and ensure that its removal does not affect the logic of the code.
+
+**Current Code:**
+```python
+desc = self._process_full_diff(prompt, user, reeval_response)
+```
+
+**Suggested Code:**
+```python
+desc = self._process_full_diff(prompt, user)
+```
+
+</details>
+
+## 🟠 Important Issues
+
+<details>
+<summary><strong>Imports (2 issues)</strong></summary>
+
+### 1. Inconsistent naming of imported prompts.
+📁 **File:** `kaizen/generator/pr_description.py:8`
+⚖️ **Severity:** 5/10
+🔍 **Description:** The change from `code_review_prompts` to `pr_desc_prompts` may lead to confusion if not documented properly.
+💡 **Solution:** Ensure that the new prompt names are well-documented and consistent across the codebase.
+
+**Current Code:**
+```python
+from kaizen.llms.prompts.code_review_prompts import (
+    PR_DESCRIPTION_PROMPT,
+    MERGE_PR_DESCRIPTION_PROMPT,
+    PR_FILE_DESCRIPTION_PROMPT,
+    PR_DESC_EVALUATION_PROMPT,
+    CODE_REVIEW_SYSTEM_PROMPT,
+)
+```
+
+**Suggested Code:**
+```python
+from kaizen.llms.prompts.pr_desc_prompts import (
+    PR_DESCRIPTION_PROMPT,
+    MERGE_PR_DESCRIPTION_PROMPT,
+    PR_FILE_DESCRIPTION_PROMPT,
+    PR_DESCRIPTION_SYSTEM_PROMPT,
+)
+```
+
+### 2. Inconsistent handling of response extraction.
+📁 **File:** `kaizen/generator/pr_description.py:110`
+⚖️ **Severity:** 7/10
+🔍 **Description:** The change from 'chat_completion_with_json' to 'chat_completion' may alter the expected response format.
+💡 **Solution:** Ensure that the new method returns the same structure as the previous one or update the handling logic accordingly.
+
+**Current Code:**
+```python
+resp, usage = self.provider.chat_completion_with_json(prompt, user=user)
+```
+
+**Suggested Code:**
+```python
+resp, usage = self.provider.chat_completion(prompt, user=user)
+```
+
+</details>
+
+---
+
+> ✨ Generated with love by [Kaizen](https://cloudcode.ai) ❤️
+
+<details>
+<summary>Useful Commands</summary>
+
+- **Feedback:** Reply with `!feedback [your message]`
+- **Ask PR:** Reply with `!ask-pr [your question]`
+- **Review:** Reply with `!review`
+- **Explain:** Reply with `!explain [issue number]` for more details on a specific issue
+- **Ignore:** Reply with `!ignore [issue number]` to mark an issue as false positive
+- **Update Tests:** Reply with `!unittest` to create a PR with test changes
+</details>

.experiments/code_review/code_reviews_20240815_142254/with_eval/pr_335_comments.json

@@ -0,0 +1,17 @@
+[
+  {
+    "topic": "Functionality",
+    "comment": "Changing the method from 'chat_completion_with_json' to 'chat_completion' may alter expected behavior.",
+    "confidence": "critical",
+    "reason": "If 'chat_completion_with_json' was designed to handle specific JSON formatting, switching to 'chat_completion' may lead to data handling issues.",
+    "solution": "Review the implementation of 'chat_completion' to ensure it meets the requirements previously handled by 'chat_completion_with_json'.",
+    "actual_code": "resp, usage = self.provider.chat_completion_with_json(prompt, user=user)",
+    "fixed_code": "resp, usage = self.provider.chat_completion(prompt, user=user)",
+    "file_name": "kaizen/generator/pr_description.py",
+    "start_line": 83,
+    "end_line": 83,
+    "side": "LEFT",
+    "sentiment": "negative",
+    "severity_level": 8
+  }
+]

.experiments/code_review/code_reviews_20240815_142254/with_eval/pr_335_review.md

@@ -0,0 +1,114 @@
+# 🔍 Code Review Summary
+
+## 📊 Stats
+- Total Issues: 5
+- Critical: 1
+- Important: 3
+- Minor: 1
+- Files Affected: 1
+## 🏆 Code Quality
+[████████████████░░░░] 80% (Good)
+
+## 🚨 Critical Issues
+
+<details>
+<summary><strong>Functionality (1 issues)</strong></summary>
+
+### 1. Changing the method from 'chat_completion_with_json' to 'chat_completion' may alter expected behavior.
+📁 **File:** `kaizen/generator/pr_description.py:83`
+⚖️ **Severity:** 8/10
+🔍 **Description:** If 'chat_completion_with_json' was designed to handle specific JSON formatting, switching to 'chat_completion' may lead to data handling issues.
+💡 **Solution:** Review the implementation of 'chat_completion' to ensure it meets the requirements previously handled by 'chat_completion_with_json'.
+
+**Current Code:**
+```python
+resp, usage = self.provider.chat_completion_with_json(prompt, user=user)
+```
+
+**Suggested Code:**
+```python
+resp, usage = self.provider.chat_completion(prompt, user=user)
+```
+
+</details>
+
+## 🟠 Important Issues
+
+<details>
+<summary><strong>Imports (3 issues)</strong></summary>
+
+### 1. Updated import statements may lead to confusion regarding the source of prompts.
+📁 **File:** `kaizen/generator/pr_description.py:8`
+⚖️ **Severity:** 5/10
+🔍 **Description:** Changing the import path for prompts can lead to issues if the new module does not contain the expected constants.
+💡 **Solution:** Ensure that the new import path is correct and that all necessary constants are defined in the new module.
+
+**Current Code:**
+```python
+from kaizen.llms.prompts.code_review_prompts import (
+    PR_DESCRIPTION_PROMPT,
+    MERGE_PR_DESCRIPTION_PROMPT,
+    PR_FILE_DESCRIPTION_PROMPT,
+    PR_DESC_EVALUATION_PROMPT,
+    CODE_REVIEW_SYSTEM_PROMPT,
+)
+```
+
+**Suggested Code:**
+```python
+from kaizen.llms.prompts.pr_desc_prompts import (
+    PR_DESCRIPTION_PROMPT,
+    MERGE_PR_DESCRIPTION_PROMPT,
+    PR_FILE_DESCRIPTION_PROMPT,
+    PR_DESCRIPTION_SYSTEM_PROMPT,
+)
+```
+
+### 2. Raising a generic Exception can obscure the cause of errors.
+📁 **File:** `kaizen/generator/pr_description.py:51`
+⚖️ **Severity:** 7/10
+🔍 **Description:** Using a generic Exception does not provide specific information about the error, making debugging difficult.
+💡 **Solution:** Use a more specific exception type or create a custom exception class to provide better context.
+
+**Current Code:**
+```python
+raise Exception("Both diff_text and pull_request_files are empty!")
+```
+
+**Suggested Code:**
+```python
+raise ValueError("Both diff_text and pull_request_files are empty!")
+```
+
+### 3. Removing 'reeval_response' from multiple function signatures may lead to loss of intended functionality.
+📁 **File:** `kaizen/generator/pr_description.py:40`
+⚖️ **Severity:** 6/10
+🔍 **Description:** If 'reeval_response' was previously used to control logic, its removal could lead to unintended behavior.
+💡 **Solution:** Carefully assess the logic that relies on 'reeval_response' to determine if it should be retained.
+
+**Current Code:**
+```python
+def _process_full_diff(self, prompt: str, user: Optional[str], reeval_response: bool) -> str:
+```
+
+**Suggested Code:**
+```python
+def _process_full_diff(self, prompt: str, user: Optional[str]) -> str:
+```
+
+</details>
+
+---
+
+> ✨ Generated with love by [Kaizen](https://cloudcode.ai) ❤️
+
+<details>
+<summary>Useful Commands</summary>
+
+- **Feedback:** Reply with `!feedback [your message]`
+- **Ask PR:** Reply with `!ask-pr [your question]`
+- **Review:** Reply with `!review`
+- **Explain:** Reply with `!explain [issue number]` for more details on a specific issue
+- **Ignore:** Reply with `!ignore [issue number]` to mark an issue as false positive
+- **Update Tests:** Reply with `!unittest` to create a PR with test changes
+</details>

.experiments/code_review/main.py

@@ -0,0 +1,107 @@
+import os
+import json
+import datetime
+import logging
+from tqdm import tqdm
+from kaizen.reviewer.code_review import CodeReviewer
+from kaizen.llms.provider import LLMProvider
+from github_app.github_helper.utils import get_diff_text, get_pr_files
+from github_app.github_helper.pull_requests import (
+    create_review_comments,
+)
+from kaizen.formatters.code_review_formatter import create_pr_review_text
+
+# Get the directory where the script is located
+SCRIPT_DIR = os.path.dirname(os.path.abspath(__file__))
+
+# Set up logging
+log_file = os.path.join(SCRIPT_DIR, "pr_review.log")
+logging.basicConfig(
+    level=logging.INFO,
+    format="%(asctime)s - %(levelname)s - %(message)s",
+    handlers=[logging.FileHandler(log_file), logging.StreamHandler()],
+)
+logger = logging.getLogger(__name__)
+
+
+def process_pr(pr_url, reeval_response=False):
+    logger.info(f"Processing PR: {pr_url}")
+    pr_diff = f"{pr_url}.patch"
+    pr_files = f"{pr_url}/files".replace("github.com", "api.github.com/repos").replace(
+        "/pull", "/pulls"
+    )
+    pr_title = pr_url.split("/")[-1]  # Use PR number as title for simplicity
+
+    diff_text = get_diff_text(pr_diff, "")
+    pr_files = get_pr_files(pr_files, "")
+
+    reviewer = CodeReviewer(llm_provider=LLMProvider())
+    review_data = reviewer.review_pull_request(
+        diff_text=diff_text,
+        pull_request_title=pr_title,
+        pull_request_desc="",
+        pull_request_files=pr_files,
+        user="kaizen/example",
+        reeval_response=reeval_response,
+    )
+
+    # topics = clean_keys(review_data.topics, "important")
+    logger.info(review_data.topics)
+    review_desc = create_pr_review_text(
+        review_data.issues, code_quality=review_data.code_quality
+    )
+    comments, topics = create_review_comments(review_data.topics)
+    logger.info(f"Model: {review_data.model_name}\nUsage: {review_data.usage}")
+    logger.info(f"Completed processing PR: {pr_url}")
+    return review_desc, comments, topics
+
+
+def save_review(pr_number, review_desc, comments, topics, folder):
+    logger.info(f"Saving review for PR {pr_number} in {folder}")
+    review_file = os.path.join(folder, f"pr_{pr_number}_review.md")
+    comments_file = os.path.join(folder, f"pr_{pr_number}_comments.json")
+
+    with open(review_file, "w") as f:
+        f.write(review_desc)
+
+    with open(comments_file, "w") as f:
+        json.dump(comments, f, indent=2)
+
+    logger.info(f"Saved review files for PR {pr_number}")
+
+
+def main(pr_urls):
+    timestamp = datetime.datetime.now().strftime("%Y%m%d_%H%M%S")
+    base_folder = os.path.join(SCRIPT_DIR, f"code_reviews_{timestamp}")
+    with_eval_folder = os.path.join(base_folder, "with_eval")
+    no_eval_folder = os.path.join(base_folder, "no_eval")
+
+    os.makedirs(with_eval_folder, exist_ok=True)
+    os.makedirs(no_eval_folder, exist_ok=True)
+
+    logger.info(f"Created output folders: {base_folder}")
+
+    for pr_url in tqdm(pr_urls, desc="Processing PRs", unit="PR"):
+        pr_number = pr_url.split("/")[-1]
+
+        logger.info(f"Starting to process PR {pr_number}")
+
+        # Without re-evaluation
+        review_desc, comments, topics = process_pr(pr_url, reeval_response=False)
+        save_review(pr_number, review_desc, comments, topics, no_eval_folder)
+
+        # With re-evaluation
+        review_desc, comments, topics = process_pr(pr_url, reeval_response=True)
+        save_review(pr_number, review_desc, comments, topics, with_eval_folder)
+
+        logger.info(f"Completed processing PR {pr_number}")
+
+    logger.info("All PRs processed successfully")
+
+
+if __name__ == "__main__":
+    pr_urls = [
+        "https://github.com/Cloud-Code-AI/kaizen/pull/335",
+        # Add more PR URLs here
+    ]
+    main(pr_urls)

.github/FUNDING.yml

@@ -0,0 +1,15 @@
+# These are supported funding model platforms
+
+github: # Replace with up to 4 GitHub Sponsors-enabled usernames e.g., [user1, user2]
+patreon: # Replace with a single Patreon username
+open_collective: # Replace with a single Open Collective username
+ko_fi: # Replace with a single Ko-fi username
+tidelift: # Replace with a single Tidelift platform-name/package-name e.g., npm/babel
+community_bridge: # Replace with a single Community Bridge project-name e.g., cloud-foundry
+liberapay: # Replace with a single Liberapay username
+issuehunt: # Replace with a single IssueHunt username
+lfx_crowdfunding: # Replace with a single LFX Crowdfunding project-name e.g., cloud-foundry
+polar: # Replace with a single Polar username
+buy_me_a_coffee: # Replace with a single Buy Me a Coffee username
+thanks_dev: # Replace with a single thanks.dev username
+custom: ["https://buy.stripe.com/3cs6pNf2Wg4o4owcMW"]

README.md

@@ -1,5 +1,5 @@
 <p align="center">
-  <img src="/logo.png" alt="Kaizen Logo" width="200"/>
+  <img src="/assets/logo.png" alt="Kaizen Logo" width="200"/>
 </p>
 
 <h1 align="center">Kaizen: The Ultimate Code Quality Guardian</h1>
@@ -30,6 +30,7 @@ In the ever-evolving world of software development, delivering high-quality code
 ### 🔍 Key Features
 
 - **🤖 AI-Powered Code Reviews**: Automated pull request reviews with insightful summaries and improvement suggestions, catching potential issues before they escalate.
+
 - **🧪 Smart Test Generation**: 
   - End-to-end tests based on your application's code and documentation, ensuring comprehensive coverage.
   - Unit test generation for Python (with TypeScript and React support coming soon!), saving you valuable time and effort.