Use ai_prompts_v2 FF for v2 endpoint in Chain::Requests::AiGateway

Alejandro Rodríguezrequested to merge
duo/feature/552131-ai-prompts-v2-chain-requests-endpoint into master

What does this MR do and why?

Switch the prompts endpoint in Gitlab::Llm::Chain::Requests::AiGateway to use /v2/prompts/chat when the ai_prompts_v2 feature flag is enabled, matching the same pattern already used in Gitlab::Llm::AiGateway::Client#complete_prompt.

Also removes the unused ENDPOINT (/v1/chat/agent) and BASE_ENDPOINT (/v1/chat) constants that were never referenced anywhere.

References

#552131

Screenshots or screen recordings

N/A — backend-only change.

How to set up and validate locally

  1. Enable the feature flag: Feature.enable(:ai_prompts_v2)
  2. Trigger a Duo Chat request and confirm it hits the /v2/prompts/chat/<unit_primitive> endpoint.
  3. Disable the flag: Feature.disable(:ai_prompts_v2)
  4. Confirm requests go to /v1/prompts/chat/<unit_primitive>.

MR acceptance checklist

Evaluate this MR against the MR acceptance checklist. It helps you analyze changes to reduce risks in quality, performance, reliability, security, and maintainability.

Merge request reports