feat: Strengthen tool output handling in prompts

Joey Khabierequested to merge
jkhabie_add_system_prompts_clarificatios into main

What does this merge request do and why?

This MR adds instructions to all AI assistant templates for proper tool output handling. A new directive is included at the beginning and end of every assistant prompt template (chat agents, pipeline fixers, security analyzers) to ensure consistent processing of tool responses.

Issue:

Related https://gitlab.com/gitlab-org/modelops/applied-ml/code-suggestions/ai-assist/-/work_items/1721

Merge request checklist

  • Tests added for new functionality. If not, please raise an issue to follow up.
  • Documentation added/updated, if needed.
  • If this change requires executor implementation: verified that issues/MRs exist for both Go executor and Node executor or confirmed that changes are backward-compatible and don't break existing executor functionality.
Edited by Joey Khabie

Merge request reports