Merge remote-tracking branch 'origin/main'

README.md

@@ -10,7 +10,7 @@
 
 </picture>
 <br/>
-CodiumAI PR-Agent aims to help efficiently review and handle pull requests, by providing AI feedbacks and suggestions
+CodiumAI PR-Agent aims to help efficiently review and handle pull requests, by providing AI feedback and suggestions
 </div>
 
 [![GitHub license](https://img.shields.io/badge/License-Apache_2.0-blue.svg)](https://github.com/Codium-ai/pr-agent/blob/main/LICENSE)
@@ -18,6 +18,7 @@ CodiumAI PR-Agent aims to help efficiently review and handle pull requests, by p
 [![Static Badge](https://img.shields.io/badge/Code-Benchmark-blue)](https://pr-agent-docs.codium.ai/finetuning_benchmark/)
 [![Discord](https://badgen.net/badge/icon/discord?icon=discord&label&color=purple)](https://discord.com/channels/1057273017547378788/1126104260430528613)
 [![Twitter](https://img.shields.io/twitter/follow/codiumai)](https://twitter.com/codiumai)
+[![Cheat Sheet](https://img.shields.io/badge/Cheat-Sheet-red)](https://www.codium.ai/images/pr_agent/cheat_sheet.pdf)
     <a href="https://github.com/Codium-ai/pr-agent/commits/main">
     <img alt="GitHub" src="https://img.shields.io/github/last-commit/Codium-ai/pr-agent/main?style=for-the-badge" height="20">
     </a>
@@ -42,6 +43,12 @@ CodiumAI PR-Agent aims to help efficiently review and handle pull requests, by p
   
 ## News and Updates
 
+### July 28, 2024
+
+(1) improved support for bitbucket server - [auto commands](https://github.com/Codium-ai/pr-agent/pull/1059) and [direct links](https://github.com/Codium-ai/pr-agent/pull/1061)
+
+(2) custom models are now [supported](https://pr-agent-docs.codium.ai/usage-guide/changing_a_model/#custom-models)
+
 ### July 6, 2024
 
 v0.23 has been released. See full log changes [here](https://github.com/Codium-ai/pr-agent/releases/tag/v0.23).

docs/docs/usage-guide/additional_configurations.md

@@ -47,165 +47,6 @@ However, for very large PRs, or in case you want to emphasize quality over speed
 which divides the PR to chunks, and processes each chunk separately. With this mode, regardless of the model, no compression will be done (but for large PRs, multiple model calls may occur)
 
 
-## Changing a model
-
-See [here](https://github.com/Codium-ai/pr-agent/blob/main/pr_agent/algo/__init__.py) for the list of available models.
-To use a different model than the default (GPT-4), you need to edit [configuration file](https://github.com/Codium-ai/pr-agent/blob/main/pr_agent/settings/configuration.toml#L2).
-For models and environments not from OPENAI, you might need to provide additional keys and other parameters. See below for instructions.
-
-### Azure
-
-To use Azure, set in your `.secrets.toml` (working from CLI), or in the GitHub `Settings > Secrets and variables` (working from GitHub App or GitHub Action):
-```
-[openai]
-key = "" # your azure api key
-api_type = "azure"
-api_version = '2023-05-15'  # Check Azure documentation for the current API version
-api_base = ""  # The base URL for your Azure OpenAI resource. e.g. "https://<your resource name>.openai.azure.com"
-deployment_id = ""  # The deployment name you chose when you deployed the engine
-```
-
-and set in your configuration file:
-```
-[config]
-model="" # the OpenAI model you've deployed on Azure (e.g. gpt-3.5-turbo)
-```
-
-### Hugging Face
-
-**Local**
-You can run Hugging Face models locally through either [VLLM](https://docs.litellm.ai/docs/providers/vllm) or [Ollama](https://docs.litellm.ai/docs/providers/ollama)
-
-E.g. to use a new Hugging Face model locally via Ollama, set:
-```
-[__init__.py]
-MAX_TOKENS = {
-    "model-name-on-ollama": <max_tokens>
-}
-e.g.
-MAX_TOKENS={
-    ...,
-    "ollama/llama2": 4096
-}
-
-
-[config] # in configuration.toml
-model = "ollama/llama2"
-model_turbo = "ollama/llama2"
-
-[ollama] # in .secrets.toml
-api_base = ... # the base url for your Hugging Face inference endpoint
-# e.g. if running Ollama locally, you may use:
-api_base = "http://localhost:11434/"
-```
-
-### Inference Endpoints
-
-To use a new model with Hugging Face Inference Endpoints, for example, set:
-```
-[__init__.py]
-MAX_TOKENS = {
-    "model-name-on-huggingface": <max_tokens>
-}
-e.g.
-MAX_TOKENS={
-    ...,
-    "meta-llama/Llama-2-7b-chat-hf": 4096
-}
-[config] # in configuration.toml
-model = "huggingface/meta-llama/Llama-2-7b-chat-hf"
-model_turbo = "huggingface/meta-llama/Llama-2-7b-chat-hf"
-
-[huggingface] # in .secrets.toml
-key = ... # your Hugging Face api key
-api_base = ... # the base url for your Hugging Face inference endpoint
-```
-(you can obtain a Llama2 key from [here](https://replicate.com/replicate/llama-2-70b-chat/api))
-
-### Replicate
-
-To use Llama2 model with Replicate, for example, set:
-```
-[config] # in configuration.toml
-model = "replicate/llama-2-70b-chat:2c1608e18606fad2812020dc541930f2d0495ce32eee50074220b87300bc16e1"
-model_turbo = "replicate/llama-2-70b-chat:2c1608e18606fad2812020dc541930f2d0495ce32eee50074220b87300bc16e1"
-[replicate] # in .secrets.toml
-key = ...
-```
-(you can obtain a Llama2 key from [here](https://replicate.com/replicate/llama-2-70b-chat/api))
-
-
-Also, review the [AiHandler](https://github.com/Codium-ai/pr-agent/blob/main/pr_agent/algo/ai_handler.py) file for instructions on how to set keys for other models.
-
-### Groq
-
-To use Llama3 model with Groq, for example, set:
-```
-[config] # in configuration.toml
-model = "llama3-70b-8192"
-model_turbo = "llama3-70b-8192"
-fallback_models = ["groq/llama3-70b-8192"] 
-[groq] # in .secrets.toml
-key = ... # your Groq api key
-```
-(you can obtain a Groq key from [here](https://console.groq.com/keys))
-
-### Vertex AI
-
-To use Google's Vertex AI platform and its associated models (chat-bison/codechat-bison) set:
-
-``` 
-[config] # in configuration.toml
-model = "vertex_ai/codechat-bison"
-model_turbo = "vertex_ai/codechat-bison"
-fallback_models="vertex_ai/codechat-bison"
-
-[vertexai] # in .secrets.toml
-vertex_project = "my-google-cloud-project"
-vertex_location = ""
-```
-
-Your [application default credentials](https://cloud.google.com/docs/authentication/application-default-credentials) will be used for authentication so there is no need to set explicit credentials in most environments.
-
-If you do want to set explicit credentials then you can use the `GOOGLE_APPLICATION_CREDENTIALS` environment variable set to a path to a json credentials file.
-
-### Anthropic
-
-To use Anthropic models, set the relevant models in the configuration section of the configuration file:
-```
-[config]
-model="anthropic/claude-3-opus-20240229"
-model_turbo="anthropic/claude-3-opus-20240229"
-fallback_models=["anthropic/claude-3-opus-20240229"]
-```
-
-And also set the api key in the .secrets.toml file:
-```
-[anthropic]
-KEY = "..."
-```
-
-### Amazon Bedrock
-
-To use Amazon Bedrock and its foundational models, add the below configuration:
-
-``` 
-[config] # in configuration.toml
-model="bedrock/anthropic.claude-3-sonnet-20240229-v1:0"
-model_turbo="bedrock/anthropic.claude-3-sonnet-20240229-v1:0"
-fallback_models=["bedrock/anthropic.claude-v2:1"]
-```
-
-Note that you have to add access to foundational models before using them. Please refer to [this document](https://docs.aws.amazon.com/bedrock/latest/userguide/setting-up.html) for more details.
-
-If you are using the claude-3 model, please configure the following settings as there are parameters incompatible with claude-3.
-```
-[litellm]
-drop_params = true
-```
-
-AWS session is automatically authenticated from your environment, but you can also explicitly set `AWS_ACCESS_KEY_ID`, `AWS_SECRET_ACCESS_KEY` and `AWS_REGION_NAME` environment variables. Please refer to [this document](https://litellm.vercel.app/docs/providers/bedrock) for more details.
-
 
 ## Patch Extra Lines
 

docs/docs/usage-guide/changing_a_model.md

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

docs/docs/usage-guide/configuration_options.md

@@ -26,15 +26,15 @@ The advantage of this method is that it allows to set configurations without nee
 
 ![wiki_configuration](https://codium.ai/images/pr_agent/wiki_configuration.png){width=512}
 
-Click [here](https://codium.ai/images/pr_agent/wiki_configuration_pr_agent.mp4) to see a short instructional video. We recommend surrounding the configuration content with triple-quotes, to allow better presentation when displayed in the wiki as markdown.
+Click [here](https://codium.ai/images/pr_agent/wiki_configuration_pr_agent.mp4) to see a short instructional video. We recommend surrounding the configuration content with triple-quotes (or \`\`\`toml), to allow better presentation when displayed in the wiki as markdown.
 An example content:
 
-```
+```toml
 [pr_description]
 generate_ai_title=true
 ```
 
-PR-Agent will know to remove the triple-quotes when reading the configuration content.
+PR-Agent will know to remove the surrounding quotes when reading the configuration content.
 
 ## Local configuration file
 

docs/docs/usage-guide/index.md

@@ -15,6 +15,7 @@ It includes information on how to adjust PR-Agent configurations, define which t
     - [BitBucket App](./automations_and_usage.md#bitbucket-app)
     - [Azure DevOps Provider](./automations_and_usage.md#azure-devops-provider)
 - [Managing Mail Notifications](./mail_notifications.md)
+- [Changing a Model](./changing_a_model.md)
 - [Additional Configurations Walkthrough](./additional_configurations.md)
     - [Ignoring files from analysis](./additional_configurations.md#ignoring-files-from-analysis)
     - [Extra instructions](./additional_configurations.md#extra-instructions)

docs/mkdocs.yml

@@ -21,7 +21,9 @@ nav:
     - Configuration File: 'usage-guide/configuration_options.md'
     - Usage and Automation: 'usage-guide/automations_and_usage.md'
     - Managing Mail Notifications: 'usage-guide/mail_notifications.md'
+    - Changing a Model: 'usage-guide/changing_a_model.md'
     - Additional Configurations: 'usage-guide/additional_configurations.md'
+    - 💎 PR-Agent Pro Models: 'usage-guide/PR_agent_pro_models'
   - Tools:
     - 'tools/index.md'
     - Describe: 'tools/describe.md'

pr_agent/algo/__init__.py

@@ -52,4 +52,10 @@ MAX_TOKENS = {
     'groq/llama-3.1-70b-versatile': 131072,
     'groq/llama-3.1-405b-reasoning': 131072,
     'ollama/llama3': 4096,
+    'watsonx/meta-llama/llama-3-8b-instruct': 4096,
+    "watsonx/meta-llama/llama-3-70b-instruct": 4096,
+    "watsonx/meta-llama/llama-3-405b-instruct": 16384,
+    "watsonx/ibm/granite-13b-chat-v2": 8191,
+    "watsonx/ibm/granite-34b-code-instruct": 8191,
+    "watsonx/mistralai/mistral-large": 32768,
 }

pr_agent/algo/utils.py

@@ -557,7 +557,7 @@ def _fix_key_value(key: str, value: str):
 
 
 def load_yaml(response_text: str, keys_fix_yaml: List[str] = [], first_key="", last_key="") -> dict:
-    response_text = response_text.removeprefix('```yaml').rstrip('`')
+    response_text = response_text.strip('\n').removeprefix('```yaml').rstrip('`')
     try:
         data = yaml.safe_load(response_text)
     except Exception as e:
@@ -693,15 +693,25 @@ def get_user_labels(current_labels: List[str] = None):
 
 
 def get_max_tokens(model):
+    """
+    Get the maximum number of tokens allowed for a model.
+    logic:
+    (1) If the model is in './pr_agent/algo/__init__.py', use the value from there.
+    (2) else, the user needs to define explicitly 'config.custom_model_max_tokens'
+
+    For both cases, we further limit the number of tokens to 'config.max_model_tokens' if it is set.
+    This aims to improve the algorithmic quality, as the AI model degrades in performance when the input is too long.
+    """
     settings = get_settings()
     if model in MAX_TOKENS:
         max_tokens_model = MAX_TOKENS[model]
+    elif settings.config.custom_model_max_tokens > 0:
+        max_tokens_model = settings.config.custom_model_max_tokens
     else:
-        raise Exception(f"MAX_TOKENS must be set for model {model} in ./pr_agent/algo/__init__.py")
+        raise Exception(f"Ensure {model} is defined in MAX_TOKENS in ./pr_agent/algo/__init__.py or set a positive value for it in config.custom_model_max_tokens")
 
-    if settings.config.max_model_tokens:
+    if settings.config.max_model_tokens and settings.config.max_model_tokens > 0:
         max_tokens_model = min(settings.config.max_model_tokens, max_tokens_model)
-        # get_logger().debug(f"limiting max tokens to {max_tokens_model}")
     return max_tokens_model
 
 

pr_agent/settings/configuration.toml

@@ -18,6 +18,8 @@ ai_timeout=120 # 2minutes
 max_description_tokens = 500
 max_commits_tokens = 500
 max_model_tokens = 32000 # Limits the maximum number of tokens that can be used by any model, regardless of the model's default capabilities.
+custom_model_max_tokens=-1 # for models not in the default list
+#
 patch_extra_lines = 1
 secret_provider=""
 cli_mode=false
@@ -251,6 +253,11 @@ pr_commands = [
 # URL to the BitBucket Server instance
 # url = "https://git.bitbucket.com"
 url = ""
+pr_commands = [
+    "/describe",
+    "/review --pr_reviewer.num_code_suggestions=0",
+    "/improve --pr_code_suggestions.commitable_code_suggestions=true --pr_code_suggestions.suggestions_score_threshold=7",
+]
 
 [litellm]
 # use_client = false

pr_agent/tools/pr_code_suggestions.py

@@ -100,8 +100,8 @@ class PRCodeSuggestions:
                 data = {"code_suggestions": []}
 
             if data is None or 'code_suggestions' not in data or not data['code_suggestions']:
-                get_logger().error('No code suggestions found for PR.')
+                get_logger().error('No code suggestions found for the PR.')
-                pr_body = "## PR Code Suggestions ✨\n\nNo code suggestions found for PR."
+                pr_body = "## PR Code Suggestions ✨\n\nNo code suggestions found for the PR."
                 get_logger().debug(f"PR output", artifact=pr_body)
                 if self.progress_response:
                     self.git_provider.edit_comment(self.progress_response, body=pr_body)