diff --git a/CHANGELOG.md b/CHANGELOG.md index 93073081..039375c7 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -6,10 +6,13 @@ All notable changes to this project will be documented in this file. The format is based on [Keep a Changelog](https://keepachangelog.com/) and this project adheres to [Semantic Versioning](https://semver.org/). -## [Unreleased] +## [0.9.2] - 2026-08-18 ### Added - Added support for the [WebBrain](https://github.com/webbrain-one/webbrain) harness. Thanks to @alectimison-maker. +### Fixed +- Fixed the handling of judge LLM API returns malformed JSON, which caused undetermined behavior when the of the LLM judge. + ## [0.9.1] - 2026-08-04 ### Fixed - Fixed the issue that the x11vnc is not started properly in `--human` mode. diff --git a/CITATION.cff b/CITATION.cff index d3b5d3d5..460199bd 100644 --- a/CITATION.cff +++ b/CITATION.cff @@ -2,7 +2,7 @@ cff-version: 1.2.0 message: "If you use ClawBench, please cite it as below." title: "ClawBench: Can AI Agents Complete Everyday Online Tasks?" type: software -version: "0.9.1" +version: "0.9.2" license: Apache-2.0 url: "https://claw-bench.com" repository-code: "https://github.com/TIGER-AI-Lab/ClawBench" diff --git a/pyproject.toml b/pyproject.toml index 240c7532..5f3789c3 100644 --- a/pyproject.toml +++ b/pyproject.toml @@ -4,7 +4,7 @@ build-backend = "hatchling.build" [project] name = "clawbench-eval" -version = "0.9.1" +version = "0.9.2" description = "Benchmarking framework for evaluating AI web agents on real-world online tasks" readme = "README.md" requires-python = ">=3.11" diff --git a/uv.lock b/uv.lock index e9ae5e3c..7fe12c2b 100644 --- a/uv.lock +++ b/uv.lock @@ -58,7 +58,7 @@ wheels = [ [[package]] name = "clawbench-eval" -version = "0.9.1" +version = "0.9.2" source = { editable = "." } dependencies = [ { name = "fpdf2" },