Agenta

What's Changed
* Bump versions by github-actions in https://github.com/Agenta-AI/agenta/pull/1786
* fix(backend): candidate hotfix for failing evals by mmabrouk in https://github.com/Agenta-AI/agenta/pull/1787
* [Bug]: Redirect Issue When Deleting Evaluation in Evaluation Results View by bekossy in https://github.com/Agenta-AI/agenta/pull/1795
* Fix: error when pulling environment configuration by aakrem in https://github.com/Agenta-AI/agenta/pull/1797
* Bump versions by github-actions in https://github.com/Agenta-AI/agenta/pull/1799


**Full Changelog**: https://github.com/Agenta-AI/agenta/compare/v0.17.3...v0.17.4

What's Changed
* Enhancement: Upgrade to Next 14 by bekossy in https://github.com/Agenta-AI/agenta/pull/1784
* Refactor API Endpoints into Services Folder by bekossy in https://github.com/Agenta-AI/agenta/pull/1623


**Full Changelog**: https://github.com/Agenta-AI/agenta/compare/v0.17.2...v0.17.3

What's Changed
* Fix litellm integration by mmabrouk in https://github.com/Agenta-AI/agenta/pull/1726
* [Feature]: Export results in the Evaluation Scenarios view by bekossy in https://github.com/Agenta-AI/agenta/pull/1763
* Bump pymongo from 4.7.2 to 4.7.3 in /agenta-cli by dependabot in https://github.com/Agenta-AI/agenta/pull/1762
* Bump pytest from 8.2.1 to 8.2.2 in /agenta-cli by dependabot in https://github.com/Agenta-AI/agenta/pull/1761
* [Enhancement]: add integration with litellm for observability by aybruhm in https://github.com/Agenta-AI/agenta/pull/1603
* [Hotfix]: resolve ChatCompletionMessage object is not subscriptable by aybruhm in https://github.com/Agenta-AI/agenta/pull/1771
* [Docs]: Update the team management page in the docs by bekossy in https://github.com/Agenta-AI/agenta/pull/1775
* Propagate cost and tokens by mmabrouk in https://github.com/Agenta-AI/agenta/pull/1740
* Bump versions by github-actions in https://github.com/Agenta-AI/agenta/pull/1776


**Full Changelog**: https://github.com/Agenta-AI/agenta/compare/v0.17.1...v0.17.2

What's Changed
* fix (sdk): set default values to FuncResponse sdk type by aybruhm in https://github.com/Agenta-AI/agenta/pull/1766
* Bump versions by github-actions in https://github.com/Agenta-AI/agenta/pull/1769


**Full Changelog**: https://github.com/Agenta-AI/agenta/compare/v0.17.0...v0.17.1

What's Changed
* Bump versions by github-actions in https://github.com/Agenta-AI/agenta/pull/1727
* Eval fixes by aakrem in https://github.com/Agenta-AI/agenta/pull/1728
* [Bug Fix]: Improved conditional logic for creating evaluator by bekossy in https://github.com/Agenta-AI/agenta/pull/1729
* Hotfix evaluation by mmabrouk in https://github.com/Agenta-AI/agenta/pull/1733
* Hotfix to show the correct answers even for evalutors that are not correctly migrated by mmabrouk in https://github.com/Agenta-AI/agenta/pull/1744
* Evaluation fix by mmabrouk in https://github.com/Agenta-AI/agenta/pull/1746
* merge main by aakrem in https://github.com/Agenta-AI/agenta/pull/1748
* fix(migration): add missing correct answer for evaluators by aakrem in https://github.com/Agenta-AI/agenta/pull/1735
* Candidate fix to 1705 (pydantic v2) by mmabrouk in https://github.com/Agenta-AI/agenta/pull/1736
* Bugfix/code-evaluators by mmabrouk in https://github.com/Agenta-AI/agenta/pull/1750
* chore(tools): added better commits for conventional commits by aakrem in https://github.com/Agenta-AI/agenta/pull/1752
* docs: add ashrafchowdury as a contributor for bug, and code by allcontributors in https://github.com/Agenta-AI/agenta/pull/1758
* fix: fixed testset columns naming conventions by ashrafchowdury in https://github.com/Agenta-AI/agenta/pull/1743
* chore: Improved scope for better commit by mmabrouk in https://github.com/Agenta-AI/agenta/pull/1757
* [Migration]: upgrade pydantic to v2 with sdk compatibility by aybruhm in https://github.com/Agenta-AI/agenta/pull/1705
* fix(app): 1747 Fix showing params in the playground by mmabrouk in https://github.com/Agenta-AI/agenta/pull/1756
* Bump versions by github-actions in https://github.com/Agenta-AI/agenta/pull/1759


**Full Changelog**: https://github.com/Agenta-AI/agenta/compare/v0.16.0...v0.17.0

What's Changed
* [Sub issue]: Improve Evaluation comparison view to show all ground truth columns by bekossy in https://github.com/Agenta-AI/agenta/pull/1645
* advanced settings in a separate component by aakrem in https://github.com/Agenta-AI/agenta/pull/1665
* Fix evaluation PR by mmabrouk in https://github.com/Agenta-AI/agenta/pull/1711
* Evaluators can access all columns by aakrem in https://github.com/Agenta-AI/agenta/pull/1606


**Full Changelog**: https://github.com/Agenta-AI/agenta/compare/v0.15.0...v0.16.0