response = client.get_agent_success_evaluation_results(
    agent_version=None,
    limit=100
)

# Get all results
response = client.get_agent_success_evaluation_results(limit=100)

# Calculate success rate
total = len(response.agent_success_evaluation_results)
successful = sum(1 for r in response.agent_success_evaluation_results if r.is_success)
print(f"Success rate: {successful/total*100:.1f}%")

# Review failures
print("\nFailure Analysis:")
for result in response.agent_success_evaluation_results:
    if not result.is_success:
        print(f"Session: {result.session_id}")
        print(f"  Failure Type: {result.failure_type}")
        print(f"  Reason: {result.failure_reason}")

# Compare agent versions
v1_results = client.get_agent_success_evaluation_results(
    agent_version="v1.0.0",
    limit=100
)
v2_results = client.get_agent_success_evaluation_results(
    agent_version="v2.0.0",
    limit=100
)

v1_success = sum(1 for r in v1_results.agent_success_evaluation_results if r.is_success)
v2_success = sum(1 for r in v2_results.agent_success_evaluation_results if r.is_success)

print(f"\nVersion Comparison:")
print(f"v1.0.0: {v1_success}/{len(v1_results.agent_success_evaluation_results)} successful")
print(f"v2.0.0: {v2_success}/{len(v2_results.agent_success_evaluation_results)} successful")

# Group failures by type
from collections import Counter
failure_types = Counter(
    r.failure_type for r in response.agent_success_evaluation_results if not r.is_success
)
print("\nFailure Types:")
for failure_type, count in failure_types.most_common():
    print(f"  {failure_type}: {count}")