Repository Issue Activity (beta)

#2585 Finance + worldview eval datasets

#2440 Nested App / Sub-Agent Tracing (NESTED_RECORD_ROOT)

#2406 Implement HuggingFaceLocal Stub Methods

#2506 Alignment Report Generator

#2524 Feature: Memory recall evaluation metrics for agent systems

#2408 Add Citation / Attribution Evaluator

#2471 Add Unit Tests for Feedback Template Validation

#2502 Few-Shot Example Optimizer for Feedback Functions

#2497 Benchmark LLM Judge Quality Across Providers

#2501 Evaluate gpt-4.1-mini and gpt-4.1-nano as Default LLM Judge Models

#2480 CI/CD Example: Azure Pipelines Eval Gate

#2565 Bedrock provider's default Nova model is serialized with the legacy Titan schema and fails out-of-box

#2496 Integration Test: Score Parsing Through Full Pipeline

#2504 Criteria A/B Testing Utility

#2508 Cross-Model Alignment Matrix

#2503 Score Distribution Analyzer for Feedback Functions

#2469 Add Bedrock Provider Quickstart Notebook

#2505 Golden Set Generator from Production TruLens Records

#2470 Add HuggingFace Local Eval Cookbook

#2494 Integration Test: Feedback Function Pipeline Wiring

#2477 Add Tests for instrument_method() on Third-Party Classes

#2533 Polyfill.io should be removed from the documentation website

#2495 Integration Test: Method-to-Template Wiring Verification

#2483 CI/CD Example: Pre-Commit Hook for Local Eval

#2484 CI/CD Example: CircleCI Eval Gate