Update setup.py

Refactoring `LiteLLMAIHandler` class for better using reasoning models

Dockerfile.github_action

@@ -3,7 +3,7 @@ FROM python:3.12 as base
 WORKDIR /app
 ADD pyproject.toml .
 ADD requirements.txt .
-RUN pip install . && rm pyproject.toml requirements.txt
+RUN pip install --no-cache-dir . && rm pyproject.toml requirements.txt
 ENV PYTHONPATH=/app
 ADD docs docs
 ADD pr_agent pr_agent

PULL_REQUEST_TEMPLATE.md

@@ -1,48 +0,0 @@
-## 📌 Pull Request Template
-
-### 1️⃣ Short Description
-<!-- Provide a concise summary of the changes in this PR. -->
-
----
-
-### 2️⃣ Related Open Issue
-<!-- Link the related issue(s) this PR is addressing, e.g., Fixes #123 or Closes #456. -->
-Fixes #
-
----
-
-### 3️⃣ PR Type
-<!-- Select one of the following by marking `[x]` -->
-
-- [ ] 🐞 Bug Fix
-- [ ] ✨ New Feature
-- [ ] 🔄 Refactoring
-- [ ] 📖 Documentation Update
-
----
-
-### 4️⃣ Does this PR Introduce a Breaking Change?
-<!-- Mark the applicable option -->
-- [ ] ❌ No
-- [ ] ⚠️ Yes (Explain below)
-
-If **yes**, describe the impact and necessary migration steps:
-<!-- Provide a short explanation of what needs to be changed. -->
-
----
-
-### 5️⃣ Current Behavior (Before Changes)
-<!-- Describe the existing behavior before applying the changes in this PR. -->
-
----
-
-### 6️⃣ New Behavior (After Changes)
-<!-- Explain how the behavior changes with this PR. -->
-
----
-
-### ✅ Checklist
-- [ ] Code follows the project's coding guidelines.
-- [ ] Tests have been added or updated (if applicable).
-- [ ] Documentation has been updated (if applicable).
-- [ ] Ready for review and approval.

README.md

@@ -10,6 +10,12 @@
 
 </picture>
 <br/>
+
+ [Installation Guide](https://qodo-merge-docs.qodo.ai/installation/) | 
+[Usage Guide](https://qodo-merge-docs.qodo.ai/usage-guide/) | 
+[Tools Guide](https://qodo-merge-docs.qodo.ai/tools/) | 
+[Qodo Merge](https://qodo-merge-docs.qodo.ai/overview/pr_agent_pro/) 💎
+
 PR-Agent aims to help efficiently review and handle pull requests, by providing AI feedback and suggestions
 </div>
 
@@ -22,13 +28,16 @@ PR-Agent aims to help efficiently review and handle pull requests, by providing
 </a>
 </div>
 
-### [Documentation](https://qodo-merge-docs.qodo.ai/)
+[//]: # (### [Documentation]&#40;https://qodo-merge-docs.qodo.ai/&#41;)
 
-- See the [Installation Guide](https://qodo-merge-docs.qodo.ai/installation/) for instructions on installing PR-Agent on different platforms.
+[//]: # ()
+[//]: # (- See the [Installation Guide]&#40;https://qodo-merge-docs.qodo.ai/installation/&#41; for instructions on installing PR-Agent on different platforms.)
 
-- See the [Usage Guide](https://qodo-merge-docs.qodo.ai/usage-guide/) for instructions on running PR-Agent tools via different interfaces, such as CLI, PR Comments, or by automatically triggering them when a new PR is opened.
+[//]: # ()
+[//]: # (- See the [Usage Guide]&#40;https://qodo-merge-docs.qodo.ai/usage-guide/&#41; for instructions on running PR-Agent tools via different interfaces, such as CLI, PR Comments, or by automatically triggering them when a new PR is opened.)
 
-- See the [Tools Guide](https://qodo-merge-docs.qodo.ai/tools/) for a detailed description of the different tools, and the available configurations for each tool.
+[//]: # ()
+[//]: # (- See the [Tools Guide]&#40;https://qodo-merge-docs.qodo.ai/tools/&#41; for a detailed description of the different tools, and the available configurations for each tool.)
 
 
 ## Table of Contents
@@ -37,12 +46,17 @@ PR-Agent aims to help efficiently review and handle pull requests, by providing
 - [Overview](#overview)
 - [Example results](#example-results)
 - [Try it now](#try-it-now)
-- [Qodo Merge 💎](https://qodo-merge-docs.qodo.ai/overview/pr_agent_pro/)
+- [Qodo Merge](https://qodo-merge-docs.qodo.ai/overview/pr_agent_pro/)
 - [How it works](#how-it-works)
 - [Why use PR-Agent?](#why-use-pr-agent)
 
 ## News and Updates
 
+### Feb 6, 2025
+New design for the `/improve` tool:
+
+<kbd><img src="https://github.com/user-attachments/assets/26506430-550e-469a-adaa-af0a09b70c6d" width="512"></kbd>
+
 ### Jan 25, 2025
 
 The open-source GitHub organization was updated:
@@ -69,40 +83,7 @@ Update logic and [documentation](https://qodo-merge-docs.qodo.ai/usage-guide/cha
 
 ### December 30, 2024
 
-Following feedback from the community, we have addressed two vulnerabilities identified in the open-source PR-Agent project. The fixes are now included in the newly released version (v0.26), available as of today.
+Following feedback from the community, we have addressed two vulnerabilities identified in the open-source PR-Agent project. The [fixes](https://github.com/qodo-ai/pr-agent/pull/1425) are now included in the newly released version (v0.26), available as of today.
-
-### December 25, 2024
-
-The `review` tool previously included a legacy feature for providing code suggestions (controlled by '--pr_reviewer.num_code_suggestion'). This functionality has been deprecated. Use instead the [`improve`](https://qodo-merge-docs.qodo.ai/tools/improve/) tool, which offers higher quality and more actionable code suggestions.
-
-### December 2, 2024
-
-Open-source repositories can now freely use Qodo Merge, and enjoy easy one-click installation using a marketplace [app](https://github.com/apps/qodo-merge-pro-for-open-source).
-
-<kbd><img src="https://github.com/user-attachments/assets/b0838724-87b9-43b0-ab62-73739a3a855c" width="512"></kbd>
-
-See [here](https://qodo-merge-docs.qodo.ai/installation/pr_agent_pro/) for more details about installing Qodo Merge for private repositories.
-
-
-### November 18, 2024
-
-A new mode was enabled by default for code suggestions - `--pr_code_suggestions.focus_only_on_problems=true`:
-
-- This option reduces the number of code suggestions received
-- The suggestions will focus more on identifying and fixing code problems, rather than style considerations like best practices, maintainability, or readability.
-- The suggestions will be categorized into just two groups: "Possible Issues" and "General".
-
-Still, if you prefer the previous mode, you can set `--pr_code_suggestions.focus_only_on_problems=false` in the [configuration file](https://qodo-merge-docs.qodo.ai/usage-guide/configuration_options/).
-
-**Example results:**
-
-Original mode
-
-<kbd><img src="https://qodo.ai/images/pr_agent/code_suggestions_original_mode.png" width="512"></kbd>
-
-Focused mode
-
-<kbd><img src="https://qodo.ai/images/pr_agent/code_suggestions_focused_mode.png" width="512"></kbd>
 
 
 ## Overview

docs/docs/installation/qodo_merge.md

@@ -15,7 +15,7 @@ Qodo Merge for GitHub cloud is available for installation through the [GitHub Ma
 
 ### GitHub Enterprise Server
 
-To use Qodo Merge application on your private GitHub Enterprise Server, you will need to contact us for starting an [Enterprise](https://www.codium.ai/pricing/) trial.
+To use Qodo Merge application on your private GitHub Enterprise Server, you will need to [contact](https://www.qodo.ai/contact/#pricing) Qodo for starting an Enterprise trial.
 
 ### GitHub Open Source Projects
 
@@ -34,7 +34,9 @@ Qodo Merge for Bitbucket Cloud is available for installation through the followi
 To use Qodo Merge application on your private Bitbucket Server, you will need to contact us for starting an [Enterprise](https://www.qodo.ai/pricing/) trial.
 
 
-## Install Qodo Merge for GitLab (Teams & Enterprise)
+## Install Qodo Merge for GitLab 
+
+### GitLab Cloud
 
 Since GitLab platform does not support apps, installing Qodo Merge for GitLab is a bit more involved, and requires the following steps:
 
@@ -79,3 +81,7 @@ Enable SSL verification: Check the box.
 You’re all set!
 
 Open a new merge request or add a MR comment with one of Qodo Merge’s commands such as /review, /describe or /improve.
+
+### GitLab Server
+
+For a trial period of two weeks on your private GitLab Server, the same [installation steps](#gitlab-cloud) as for GitLab Cloud apply. After the trial period, you will need to [contact](https://www.qodo.ai/contact/#pricing) Qodo for moving to an Enterprise account.

docs/docs/overview/pr_agent_pro.md

@@ -1,6 +1,6 @@
 ### Overview
 
-[Qodo Merge](https://www.codium.ai/pricing/){:target="_blank"} is a hosted version of open-source [PR-Agent](https://github.com/Codium-ai/pr-agent){:target="_blank"}. A complimentary two-week trial is offered, followed by a monthly subscription fee.
+[Qodo Merge](https://www.codium.ai/pricing/){:target="_blank"} is a paid, hosted version of open-source [PR-Agent](https://github.com/Codium-ai/pr-agent){:target="_blank"}. A complimentary two-week trial is offered, followed by a monthly subscription fee.
 Qodo Merge is designed for companies and teams that require additional features and capabilities. It provides the following benefits:
 
 1. **Fully managed** - We take care of everything for you - hosting, models, regular updates, and more. Installation is as simple as signing up and adding the Qodo Merge app to your GitHub\GitLab\BitBucket repo.

docs/docs/usage-guide/changing_a_model.md

@@ -51,7 +51,7 @@ api_base = "http://localhost:11434" # or whatever port you're running Ollama on
     
     Commercial models such as GPT-4, Claude Sonnet, and Gemini have demonstrated robust capabilities in generating structured output for code analysis tasks with large input. In contrast, most open-source models currently available (as of January 2025) face challenges with these complex tasks.
 
-    Based on our testing, local open-source models are suitable for experimentation and learning purposes, but they are not suitable for production-level code analysis tasks.
+    Based on our testing, local open-source models are suitable for experimentation and learning purposes (mainly for the `ask` command), but they are not suitable for production-level code analysis tasks.
     
     Hence, for production workflows and real-world usage, we recommend using commercial models.
 

docs/docs/usage-guide/index.md

@@ -24,4 +24,4 @@ It includes information on how to adjust Qodo Merge configurations, define which
     - [Changing a model](./additional_configurations.md#changing-a-model)
     - [Patch Extra Lines](./additional_configurations.md#patch-extra-lines)
     - [Editing the prompts](./additional_configurations.md#editing-the-prompts)
-- [Qodo Merge Models](./PR_agent_pro_models.md)
+- [Qodo Merge Models](./qodo_merge_models)

docs/docs/usage-guide/qodo_merge_models.md

@@ -1,4 +1,3 @@
-## Qodo Merge Models
 
 The default models used by Qodo Merge are a combination of Claude-3.5-sonnet and  OpenAI's GPT-4 models.
 

docs/mkdocs.yml

@@ -20,7 +20,7 @@ nav:
     - Managing Mail Notifications: 'usage-guide/mail_notifications.md'
     - Changing a Model: 'usage-guide/changing_a_model.md'
     - Additional Configurations: 'usage-guide/additional_configurations.md'
-    - 💎 Qodo Merge Models: 'usage-guide/PR_agent_pro_models'
+    - 💎 Qodo Merge Models: 'usage-guide/qodo_merge_models.md'
   - Tools:
     - 'tools/index.md'
     - Describe: 'tools/describe.md'

pr_agent/algo/__init__.py

@@ -85,11 +85,19 @@ MAX_TOKENS = {
 }
 
 USER_MESSAGE_ONLY_MODELS = [
+    "deepseek/deepseek-reasoner",
+    "o1-mini",
+    "o1-mini-2024-09-12",
+    "o1-preview"
+]
+
+NO_SUPPORT_TEMPERATURE_MODELS = [
     "deepseek/deepseek-reasoner",
     "o1-mini",
     "o1-mini-2024-09-12",
     "o1",
     "o1-2024-12-17",
     "o3-mini",
-    "o3-mini-2025-01-31"
+    "o3-mini-2025-01-31",
+    "o1-preview"
 ]

pr_agent/algo/ai_handlers/litellm_ai_handler.py

@@ -6,7 +6,7 @@ import requests
 from litellm import acompletion
 from tenacity import retry, retry_if_exception_type, stop_after_attempt
 
-from pr_agent.algo import USER_MESSAGE_ONLY_MODELS
+from pr_agent.algo import NO_SUPPORT_TEMPERATURE_MODELS, USER_MESSAGE_ONLY_MODELS
 from pr_agent.algo.ai_handlers.base_ai_handler import BaseAiHandler
 from pr_agent.algo.utils import get_version
 from pr_agent.config_loader import get_settings
@@ -98,6 +98,9 @@ class LiteLLMAIHandler(BaseAiHandler):
         # Models that only use user meessage
         self.user_message_only_models = USER_MESSAGE_ONLY_MODELS
 
+        # Model that doesn't support temperature argument
+        self.no_support_temperature_models = NO_SUPPORT_TEMPERATURE_MODELS
+
     def prepare_logs(self, response, system, user, resp, finish_reason):
         response_log = response.dict().copy()
         response_log['system'] = system
@@ -202,7 +205,7 @@ class LiteLLMAIHandler(BaseAiHandler):
                                           {"type": "image_url", "image_url": {"url": img_path}}]
 
             # Currently, some models do not support a separate system and user prompts
-            if self.user_message_only_models and any(entry.lower() in model.lower() for entry in self.user_message_only_models):
+            if model in self.user_message_only_models:
                 user = f"{system}\n\n\n{user}"
                 system = ""
                 get_logger().info(f"Using model {model}, combining system and user prompts")
@@ -219,11 +222,14 @@ class LiteLLMAIHandler(BaseAiHandler):
                     "model": model,
                     "deployment_id": deployment_id,
                     "messages": messages,
-                    "temperature": temperature,
                     "timeout": get_settings().config.ai_timeout,
                     "api_base": self.api_base,
                 }
 
+            # Add temperature only if model supports it
+            if model not in self.no_support_temperature_models:
+                kwargs["temperature"] = temperature
+
             if get_settings().litellm.get("enable_callbacks", False):
                 kwargs = self.add_litellm_callbacks(kwargs)
 

pr_agent/servers/github_action_runner.py

@@ -81,7 +81,7 @@ async def run_action():
         get_logger().info(f"github action: failed to apply repo settings: {e}")
 
     # Handle pull request opened event
-    if GITHUB_EVENT_NAME == "pull_request":
+    if GITHUB_EVENT_NAME == "pull_request" or GITHUB_EVENT_NAME == "pull_request_target":
         action = event_payload.get("action")
 
         # Retrieve the list of actions from the configuration

pr_agent/settings/pr_help_prompts.toml

@@ -13,7 +13,7 @@ The output must be a YAML object equivalent to type $DocHelper, according to the
 =====
 class relevant_section(BaseModel):
     file_name: str = Field(description="The name of the relevant file")
-    relevant_section_header_string: str = Field(description="From the relevant file, exact text of the relevant section heading. If no markdown heading is relevant, return empty string")
+    relevant_section_header_string: str = Field(description="The exact text of the relevant markdown section heading from the relevant file  (starting with '#', '##', etc.). Return empty string if the entire file is the relevant section, or if the relevant section has no heading")
 
 class DocHelper(BaseModel):
     user_question: str = Field(description="The user's question")

pr_agent/tools/pr_help_message.py

@@ -1,4 +1,5 @@
 import copy
+import re
 from functools import partial
 from pathlib import Path
 
@@ -9,10 +10,9 @@ from pr_agent.algo.ai_handlers.base_ai_handler import BaseAiHandler
 from pr_agent.algo.ai_handlers.litellm_ai_handler import LiteLLMAIHandler
 from pr_agent.algo.pr_processing import retry_with_fallback_models
 from pr_agent.algo.token_handler import TokenHandler
-from pr_agent.algo.utils import ModelType, clip_tokens, load_yaml
+from pr_agent.algo.utils import ModelType, clip_tokens, load_yaml, get_max_tokens
 from pr_agent.config_loader import get_settings
-from pr_agent.git_providers import (BitbucketServerProvider, GithubProvider,
+from pr_agent.git_providers import BitbucketServerProvider, GithubProvider, get_git_provider_with_context
-                                    get_git_provider_with_context)
 from pr_agent.log import get_logger
 
 
@@ -30,10 +30,11 @@ def extract_header(snippet):
     return res
 
 class PRHelpMessage:
-    def __init__(self, pr_url: str, args=None, ai_handler: partial[BaseAiHandler,] = LiteLLMAIHandler):
+    def __init__(self, pr_url: str, args=None, ai_handler: partial[BaseAiHandler,] = LiteLLMAIHandler, return_as_string=False):
         self.git_provider = get_git_provider_with_context(pr_url)
         self.ai_handler = ai_handler()
         self.question_str = self.parse_args(args)
+        self.return_as_string = return_as_string
         self.num_retrieved_snippets = get_settings().get('pr_help.num_retrieved_snippets', 5)
         if self.question_str:
             self.vars = {
@@ -65,6 +66,34 @@ class PRHelpMessage:
             question_str = ""
         return question_str
 
+    def format_markdown_header(self, header: str) -> str:
+        try:
+            # First, strip common characters from both ends
+            cleaned = header.strip('# 💎\n')
+
+            # Define all characters to be removed/replaced in a single pass
+            replacements = {
+                "'": '',
+                "`": '',
+                '(': '',
+                ')': '',
+                ',': '',
+                '.': '',
+                '?': '',
+                '!': '',
+                ' ': '-'
+            }
+
+            # Compile regex pattern for characters to remove
+            pattern = re.compile('|'.join(map(re.escape, replacements.keys())))
+
+            # Perform replacements in a single pass and convert to lowercase
+            return pattern.sub(lambda m: replacements[m.group()], cleaned).lower()
+        except Exception:
+            get_logger().exception(f"Error while formatting markdown header", artifacts={'header': header})
+            return ""
+
+
     async def run(self):
         try:
             if self.question_str:
@@ -106,7 +135,10 @@ class PRHelpMessage:
                 get_logger().debug(f"Token count of full documentation website: {token_count}")
 
                 model = get_settings().config.model
-                max_tokens_full = MAX_TOKENS[model] # note - here we take the actual max tokens, without any reductions. we do aim to get the full documentation website in the prompt
+                if model in MAX_TOKENS:
+                    max_tokens_full = MAX_TOKENS[model] # note - here we take the actual max tokens, without any reductions. we do aim to get the full documentation website in the prompt
+                else:
+                    max_tokens_full = get_max_tokens(model)
                 delta_output = 2000
                 if token_count > max_tokens_full - delta_output:
                     get_logger().info(f"Token count {token_count} exceeds the limit {max_tokens_full - delta_output}. Skipping the PR Help message.")
@@ -114,8 +146,16 @@ class PRHelpMessage:
                 self.vars['snippets'] = docs_prompt.strip()
 
                 # run the AI model
-                response = await retry_with_fallback_models(self._prepare_prediction, model_type=ModelType.WEAK)
+                response = await retry_with_fallback_models(self._prepare_prediction, model_type=ModelType.REGULAR)
                 response_yaml = load_yaml(response)
+                if isinstance(response_yaml, str):
+                    get_logger().warning(f"failing to parse response: {response_yaml}, publishing the response as is")
+                    if get_settings().config.publish_output:
+                        answer_str = f"### Question: \n{self.question_str}\n\n"
+                        answer_str += f"### Answer:\n\n"
+                        answer_str += response_yaml
+                        self.git_provider.publish_comment(answer_str)
+                    return ""
                 response_str = response_yaml.get('response')
                 relevant_sections = response_yaml.get('relevant_sections')
 
@@ -138,7 +178,7 @@ class PRHelpMessage:
                     for section in relevant_sections:
                         file = section.get('file_name').strip().removesuffix('.md')
                         if str(section['relevant_section_header_string']).strip():
-                            markdown_header = section['relevant_section_header_string'].strip().strip('#').strip().lower().replace(' ', '-').replace("'", '').replace('(', '').replace(')', '').replace(',', '').replace('.', '').replace('?', '').replace('!', '')
+                            markdown_header = self.format_markdown_header(section['relevant_section_header_string'])
                             answer_str += f"> - {base_path}{file}#{markdown_header}\n"
                         else:
                             answer_str += f"> - {base_path}{file}\n"

pr_agent/tools/pr_reviewer.py

@@ -371,7 +371,7 @@ class PRReviewer:
                     else:
                         get_logger().warning(f"Unexpected type for estimated_effort: {type(estimated_effort)}")
                     if 1 <= estimated_effort_number <= 5:  # 1, because ...
-                        review_labels.append(f'Review effort [1-5]: {estimated_effort_number}')
+                        review_labels.append(f'Review effort {estimated_effort_number}/5')
                 if get_settings().pr_reviewer.enable_review_labels_security and get_settings().pr_reviewer.require_security_review:
                     security_concerns = data['review']['security_concerns']  # yes, because ...
                     security_concerns_bool = 'yes' in security_concerns.lower() or 'true' in security_concerns.lower()

setup.py

@@ -3,3 +3,5 @@
 from setuptools import setup
 
 setup()
+
+print("Hi")