Added Pipeline to fetch and normalize Jira tickets and also enhanced JQL generation prompt.

[Devanshu1609]

Jira Pipeline Integration and JQL Generation Prompt Enhancements

Summary

This pull request introduces several improvements to the Jira AI Assistant backend and its data processing pipeline. I have enhanced the JQL generation prompt, implemented a validate-and-fix JQL function, and integrated a robust Jira-Pipeline for fetching, cleaning, and normalizing Jira ticket data.

Key Changes

• Improved JQL Generation Prompt: Expanded rules and examples to ensure more accurate natural language to JQL conversion.

• Validate & Fix JQL Function: Automatically detects and corrects common JQL issues such as missing quotes, linked issue syntax, summary searches, IN clauses, and ORDER BY normalization.

• Jira-Pipeline Integration: Fetches Jira tickets, cleans text fields, normalizes dates and priorities, and outputs structured data for summarization.

Assumptions and Simplifications

• Ticket Limits: The pipeline currently fetches up to 100 tickets per query for performance; extendable as needed.

Please review the changes and let me know if you have any questions or feedback. Thanks!

[staru09]

can you do some testing to show how this bot performs wrt to the previous version,

[Devanshu1609]

can you do some testing to show how this bot performs wrt to the previous version,

I’ve tested the updated bot against the previous version. Here’s a quick summary of the results:

Results:

• Test Cases:
  1. List me all open issues
  2. List me all open issues with priority marked as major

-Previous version :
Generated JQL : status = "Open"
Result: Failed with

-Updated Version
Generated JQL (via fallback): 'status = 'Open'' → status = 'Open'
Fix Applied: Introduced validate_and_fix_jql() to automatically sanitize, normalize, and quote field values.
Execution Path: Agent → fallback → JQL fix → JiraPipeline
Result: Successfully fetched 100 issues.

Let me know if you’d like me to run a few more comparison tests.

[staru09]

hi @Devanshu1609 thanks for the PR but I think I need to change these agents myself, I really liked the work that you've done but we are on migration of these agents so I am not merging this one but will instead add you as a co-author there, in the meantime if you want something to work, please take a look at #48