Evaluation: Update improve-prompt to v2

[AkhileshNegi]

Is your feature request related to a problem?
The improve-prompt currently uses v1, which relies on cosine scores. This limits the ability to provide users with a more comprehensive recommendation based on better metrics available in v2.

Describe the solution you'd like

• Redirect app/api/evaluations/[id]/improve-prompt/route.ts to POST /api/v2/evaluations/{evaluation_id}/improve-prompt
• Maintain existing callback_url resolution and /api/webhooks/prompt-improvement receiver with unchanged body shape
• Implement handling for PromptRecommendationJobPublic callback: recommendation_type: "prompt"
• Restrict action to judged runs; return 422 not_a_judge_run for v1 runs

Original issue

Is your feature request related to a problem?
Improve-prompt proxies to v1, which drafts from cosine scores. v2 drafts from the three-metric judge trace (score + reasoning per metric) and returns a typed recommendation, so the console gets a better prompt and a reason for it.

Describe the solution you'd like

• Point app/api/evaluations/[id]/improve-prompt/route.ts at POST /api/v2/evaluations/{evaluation_id}/improve-prompt
• Keep the existing callback_url resolution and /api/webhooks/prompt-improvement receiver — the body shape is unchanged
• Handle the PromptRecommendationJobPublic callback: recommendation_type: "prompt" (widening to a union later)
• Only offer the action on judged runs; surface 422 not_a_judge_run if it's attempted on a v1 run

Parent: #265