| Name | Modified | Size | Downloads / Week |
|---|---|---|---|
| Parent folder | |||
| README.md | 2026-06-24 | 918 Bytes | |
| v0.1.2 Release source code.tar.gz | 2026-06-24 | 12.3 MB | |
| v0.1.2 Release source code.zip | 2026-06-24 | 12.6 MB | |
| Totals: 3 Items | 24.8 MB | 0 | |
Release Highlights
This release upgrades EvoAgentX core LLM provider support and improves structured output handling.
### LLM Provider Updates
- Updated
OpenAILLMandOpenRouterLLMto support sync/async generation, streaming usage tracking, and tool-call output formatting. - Refactored
AliyunLLMandSiliconFlowLLMto use OpenAI-compatible clients. - Improved
LiteLLMcompatibility with OpenAI-style response and cost handling. - Added streaming cost tracking via usage chunks where providers support it.
- Added fallback behavior for providers that do not return cost data.
### Output Parsing and Schema Handling
- Added optional JSON schema auto-fix behavior in
LLMOutputParser. - Added stricter
Parametervalidation for JSON schema-backed object and array parameters. - Simplified JSON/data parsing utilities and removed unsafe
evalusage in typed parsing.