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.

update changelog

thomashebrard21bf7370a0eb
diff --git a/CHANGELOG.md b/CHANGELOG.md
index 1d27209e0..990aef5a1 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -2,23 +2,21 @@
## [v0.16.0] - 2025-11-25
+**Highlights:** - Library manager now supports multiple libraries. You can now have multiple libraries in your project, each with its own set of concepts, pipes, and stuffs.
+You can run the same pipe at the same times as much as you want, with different inputs.
+Side effets: Unit tests now run in 30s.
+
### Fixed
- Fixed some issues with inputs of pipes: The validation methods was not detecting misconceptions with implicit concepts.
-- Fixed validation of pipe inputs: The mulitplicity was not checked properly.
### Changed
- Improved pipe builder by auto-fixing errors, forcing consistency in the inputs and outputs of the pipes.
-- PipeCondition:
- - Moved the expression/expression_template choosing to the factory.
-
-### Feature
-
-- Library manager now supports multiple libraries. You can now have multiple libraries in your project, each with its own set of concepts, pipes, and stuffs.
### Refactor
+- PipeCondition: Moved the expression/expression_template choosing to the factory.
- Moved a lot of validation to blueprints instead of pipe instances.
- Refactored the Blueprint validation errors, and validation functions.
- Refactored the PipelexInterpreter validation errors.