feat: Add vision evaluation capabilities

examples/showcase/vision/.agentv/config.yaml

@@ -0,0 +1,22 @@
+# AgentV Configuration for Vision Examples
+# This configuration specifies directories and settings for vision evaluation examples
+
+# Directory containing evaluation YAML files
+evalsDir: ./datasets
+
+# Directory containing evaluator definitions (LLM judges and code validators)
+evaluatorsDir: ./evaluators
+
+# Test images directory (users should place test images here)
+testImagesDir: ./test-images
+
+# Default settings for vision evaluations
+defaults:
+  # Default model target (can be overridden in YAML)
+  target: openai-gpt4o
+
+  # Default image detail level
+  imageDetail: high
+
+  # Timeout for vision model calls (in milliseconds)
+  timeout: 60000

examples/showcase/vision/.agentv/targets.yaml

@@ -0,0 +1,39 @@
+# Target Model Configurations for Vision Examples
+# Defines available vision-capable models for evaluation
+
+targets:
+  # OpenAI GPT-4o (default, recommended for vision tasks)
+  openai-gpt4o:
+    provider: openai
+    model: gpt-4o
+    apiKey: ${OPENAI_API_KEY}
+    supportsVision: true
+    costPer1kImages:
+      low: 42.50      # $85/1M tokens * 0.5K tokens/image
+      high: 102.00    # $85/1M tokens * 1.2K tokens/image
+      auto: 72.25     # Average
+
+  # Anthropic Claude 3.5 Sonnet
+  anthropic-claude:
+    provider: anthropic
+    model: claude-3-5-sonnet-20241022
+    apiKey: ${ANTHROPIC_API_KEY}
+    supportsVision: true
+    costPer1kImages:
+      low: 120.00     # $3/1M tokens * 40K base + 0.5K image
+      high: 216.00    # $3/1M tokens * 40K base + 1.2K image
+      auto: 168.00    # Average
+
+  # Google Gemini 2.5 Flash
+  google-gemini:
+    provider: google
+    model: gemini-2.0-flash-exp
+    apiKey: ${GOOGLE_API_KEY}
+    supportsVision: true
+    costPer1kImages:
+      low: 1.88       # $0.075/1M tokens * 25K base + 0.5K image
+      high: 2.26      # $0.075/1M tokens * 25K base + 1.2K image
+      auto: 2.07      # Average (most cost-effective)
+
+# Default target
+default: openai-gpt4o