Merge pull request #1579 from qodo-ai/response-language-configuration

Add a language configuration to translate language generated by QodoM…

docs/docs/usage-guide/additional_configurations.md

@@ -57,6 +57,22 @@ All Qodo Merge tools have a parameter called `extra_instructions`, that enables
 /update_changelog --pr_update_changelog.extra_instructions="Make sure to update also the version ..."
 ```
 
+## Localization
+
+The default response language for Qodo Merge is **U.S. English**. However, some development teams may prefer to display information in a different language. For example, your team's workflow might improve if PR descriptions and code suggestions are set to your country's native language.  
+
+To configure this, set the `response_language` parameter in the configuration file. This will prompt the model to respond in the specified language. Use a **standard locale code** based on [ISO 3166](https://en.wikipedia.org/wiki/ISO_3166) (country codes) and [ISO 639](https://en.wikipedia.org/wiki/ISO_639) (language codes) to define a language-country pair. See this [comprehensive list of locale codes](https://simplelocalize.io/data/locales/).  
+
+### Example: 
+
+```yaml
+response_language: "he-IL"
+```
+
+This will set the response language globally for [describe](../tools/describe.md), [improve](../tools/improve.md), [add_docs](../tools/documentation.md), [update_changelog](../tools/update_changelog.md), [test](../tools/test.md) commands to Hebrew  
+
+> **Important:** Note that only dynamic text generated by the AI model is translated to the configured language. Static text such as labels and table headers that are  not part of the AI modeles response will remain in US English. 
+
 ## 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.

pr_agent/agent/pr_agent.py

@@ -44,6 +44,7 @@ command2class = {
 commands = list(command2class.keys())
 
 
+
 class PRAgent:
     def __init__(self, ai_handler: partial[BaseAiHandler,] = LiteLLMAIHandler):
         self.ai_handler = ai_handler  # will be initialized in run_action
@@ -72,6 +73,16 @@ class PRAgent:
         # Update settings from args
         args = update_settings_from_args(args)
 
+        # Append the response language in the extra instructions
+        response_language = get_settings().config.response_language
+        if response_language != 'en-us':
+            for key in get_settings():
+                setting = get_settings().get(key)
+                if str(type(setting)) == "<class 'dynaconf.utils.boxing.DynaBox'>":
+                    if hasattr(setting, 'extra_instructions'):
+                        extra_instructions = get_settings()[key.lower()].extra_instructions
+                        get_settings()[key.lower()].extra_instructions = f"{extra_instructions} \n======\n\nLanguage preference from the user\n======\n In your reply only use the lanaguage with locale code: {response_language}"
+
         action = action.lstrip("/").lower()
         if action not in command2class:
             get_logger().error(f"Unknown command: {action}")

pr_agent/settings/configuration.toml

@@ -3,6 +3,7 @@
 model="gpt-4o-2024-11-20"
 fallback_models=["gpt-4o-2024-08-06"]
 #model_weak="gpt-4o-mini-2024-07-18" # optional, a weaker model to use for some easier tasks
+response_language="en-US" # Language locales code for PR responses in ISO 3166 and ISO 639 format (e.g., "en-US", "es-ES", "he-IL", "ar-IL", "zh-CN")
 # CLI
 git_provider="github"
 publish_output=true