fix(nvidia): revert to nemotron-mini, truncate context for 4K limit, enforce precise confidence

apps/api/src/core/prompts.py

@@ -63,6 +63,7 @@ For each optimization suggestion, provide EXECUTABLE kubectl commands:
 ## ⚠️ Output Rules
 - You MUST respond with ONLY valid JSON
 - confidence MUST be between 0.0 and 1.0
+- **CRITICAL**: The `confidence` score MUST be mathematically precise and varied (e.g., 0.82, 0.91, 0.77). Do NOT default to generic numbers ending in 5 or 0 like 0.75, 0.80, 0.85. Calculate it strictly based on data evidence.
 - If confidence < 0.70, set primary_responsibility to "COLLAB"
 - optimization_suggestions MUST contain executable kubectl commands
 - Each suggestion needs: type, description, kubectl_or_config (REQUIRED)