perf: retry logic

[Shreyas-Microsoft]

Purpose

• ...
  This pull request introduces retry logic and enhanced error handling for agent communication in the CommsManager class and integrates these improvements into the convert_script function. Key changes include adding retry mechanisms, improving JSON parsing for robustness, and updating logging and error reporting.

Enhancements to Communication and Retry Logic:

• Introduced retry logic in CommsManager with configurable parameters such as max_retries, initial_delay, and backoff_factor. Added the async_invoke method to handle retries and error handling during agent communication. [1] [2]
• Updated convert_script to use the new CommsManager for group chat operations, replacing direct calls to chat with comms_manager.group_chat. This ensures retry logic is applied to all communication. [1] [2] [3]

Improved Error Handling:

• Added safe JSON parsing in convert_script to handle malformed or incomplete JSON responses from agents. Fallback values are used to avoid crashes.
• Enhanced error logging and reporting in convert_script. Critical errors during communication now create logs in the batch service and send error status updates to the client.

Codebase Improvements:

• Added utility imports and a class-level logger to CommsManager for better debugging and maintainability. [1] [2]
• Removed temporary asyncio.sleep calls in both convert_script and process_batch_async as they are no longer needed with the new retry logic. [1] [2]

Does this introduce a breaking change?

• Yes
• No

Golden Path Validation

• I have tested the primary workflows (the "golden path") to ensure they function correctly without errors.

Deployment Validation

• I have validated the deployment process successfully and all services are running as expected with this change.

What to Check

Verify that the following are valid

• ...

Other Information