Skip to content

Conversation

karangattu
Copy link
Collaborator

Extended CLI and internal logic to support 'bedrock-anthropic' as a provider for test generation. Updated help messages, provider validation, and model handling to accommodate Bedrock Anthropic, including AWS credential requirements and model ID usage. Integrated ChatBedrockAnthropic client and adjusted model validation and selection accordingly.

Extended CLI and internal logic to support 'bedrock-anthropic' as a provider for test generation. Updated help messages, provider validation, and model handling to accommodate Bedrock Anthropic, including AWS credential requirements and model ID usage. Integrated ChatBedrockAnthropic client and adjusted model validation and selection accordingly.
Copy link

github-actions bot commented Sep 9, 2025

Test Generation Evaluation Results (Averaged across 3 attempts)

🔍 Inspect AI Test Quality Evaluation

  • Complete (C): 8.3
  • Partial (P): 0.7
  • Incomplete (I): 0.0
  • Passing Rate: 9.0/9.0 (100.0%)
  • Quality Gate: ✅ PASSED (≥80% required)

🎯 Overall Result

✅ PASSED - Quality gate based on Inspect AI results


Results are averaged across 3 evaluation attempts for improved reliability.

@karangattu karangattu marked this pull request as ready for review October 2, 2025 04:16
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant