Skip to content

Build AI methods with your coding agent, then run them anywhere: as an MCP for chatbots, as a webapp for people, or via API for your software.

Changelog release/v0.10.2

Louis Choquel9d6750d12c17
diff --git a/CHANGELOG.md b/CHANGELOG.md
index d188ab875..881d2d47e 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -1,6 +1,6 @@
# Changelog
-## Unreleased
+## [v0.10.2] - 2025-09-18
### Added
@@ -11,14 +11,14 @@
### Changed
-- ⚠️ Breaking change: Renamed `ocr_handle` to `ocr_model` in `PipeOcrBlueprint`
+- ⚠️ Breaking change: Renamed `ocr_handle` to `ocr_model` in `PipeOcr` blueprint, so you'll need to update your PLX code accordingly
- OCR system now uses InferenceModelSpec with unified model handles
- Renamed `get_llm_deck()` to `get_model_deck()` and updated parameter names from `llm_handle` to `model_handle`
- Simplified OCR worker factory using plugin SDK matching
- Enhanced plugin system compatibility with InferenceModelSpec
- Improved error messages throughout system
- Updated .env.example file with slightly modified key names (more standard).
-- Improved management of placeholder environment variables for unit tests.
+- Improved management of placeholder environment variables for unit tests
### Removed