v2.2.87

Full Changelog: v2.2.86...v2.2.87

v2.2.86

Full Changelog: v2.2.85...v2.2.86

v2.2.85

Full Changelog: v2.2.84...v2.2.85

v2.2.84

Full Changelog: v2.2.83...v2.2.84

v2.2.83

What's Changed

• fix: Fix RAG integration tests to respect lazy loading pattern by @MervinPraison in #1075
• feat: make XML tool call parsing dynamic and configurable by @MervinPraison in #1079

Full Changelog: v2.2.82...v2.2.83

v2.2.82

Full Changelog: v2.2.81...v2.2.82

v2.2.81

What's Changed

• fix: resolve MongoDB vector search index creation error (missing embedding_model_name) by @github-actions[bot] in #1070
• fix: resolve MongoDB SearchIndexModel missing definition argument by @MervinPraison in #1072

Full Changelog: v2.2.80...v2.2.81

v2.2.80

What's Changed

• fix: enable token tracking by passing metrics parameter from Agent to LLM by @github-actions[bot] in #1067
• fix: comprehensive aiohttp session cleanup to resolve persistent warnings by @github-actions[bot] in #1068

Full Changelog: v2.2.79...v2.2.80

v2.2.79

What's Changed

• feat: Add comprehensive token metrics tracking for PraisonAI agents by @github-actions[bot] in #1055
• feat: Simplify token metrics to Agent(metrics=True) by @MervinPraison in #1056
• fix: reduce monitoring overhead with performance optimizations by @github-actions[bot] in #1058
• fix: add run() method alias to PraisonAIAgents for consistent API by @MervinPraison in #1063
• feat: make performance monitoring disabled by default by @github-actions[bot] in #1061
• perf: optimize telemetry performance with thread pools and queue-based processing by @github-actions[bot] in #1062
• fix: resolve zero token metrics by fixing agent LLM instance access by @MervinPraison in #1064
• fix: properly close aiohttp sessions in MCP HTTP stream transport by @github-actions[bot] in #1066

Full Changelog: v2.2.78...v2.2.79

v2.2.78

Full Changelog: v2.2.77...v2.2.78