diff --git a/.release-please-manifest.json b/.release-please-manifest.json index 18e9f06a..d0d087a3 100644 --- a/.release-please-manifest.json +++ b/.release-please-manifest.json @@ -1,3 +1,3 @@ { - ".": "1.18.0" + ".": "1.19.0" } diff --git a/CHANGELOG.md b/CHANGELOG.md index abecdec1..1582c5f2 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -1,5 +1,21 @@ # Changelog +## [1.19.0](https://github.com/GoogleCloudPlatform/evalbench/compare/v1.18.0...v1.19.0) (2026-09-14) + + +### Features + +* **mcp_readability:** group style findings per tool ([dae668e](https://github.com/GoogleCloudPlatform/evalbench/commit/dae668e680c8ee940f1058de80bf10311f5accd5)) +* **mcp_readability:** group style findings per tool ([c4541a3](https://github.com/GoogleCloudPlatform/evalbench/commit/c4541a369b7a8a7be00c8aa7933bcf0f0ca48c5e)) + + +### Bug Fixes + +* **agy:** register the cwd as a workspace, not just a declared work_dir ([#599](https://github.com/GoogleCloudPlatform/evalbench/issues/599)) ([40a338b](https://github.com/GoogleCloudPlatform/evalbench/commit/40a338b393fdeb7275c4037ed8cfe4a5fff05205)) +* **claude_code:** measure per-tool latency, which was always reported as 0 ([#601](https://github.com/GoogleCloudPlatform/evalbench/issues/601)) ([e6892c8](https://github.com/GoogleCloudPlatform/evalbench/commit/e6892c81b44f33173815d83ded6cec4b1070202e)) +* **codex_cli:** keep captured stderr when the CLI times out ([#603](https://github.com/GoogleCloudPlatform/evalbench/issues/603)) ([7f7c200](https://github.com/GoogleCloudPlatform/evalbench/commit/7f7c200e5ccef6f0142dd73af663c34e8a2fa2b2)) +* **viewer:** specify UTC timezone in dataset quality last run column ([#602](https://github.com/GoogleCloudPlatform/evalbench/issues/602)) ([b6aeb3c](https://github.com/GoogleCloudPlatform/evalbench/commit/b6aeb3cd3363785106b109412b8c1085314080dd)) + ## [1.18.0](https://github.com/GoogleCloudPlatform/evalbench/compare/v1.17.0...v1.18.0) (2026-09-08) diff --git a/pyproject.toml b/pyproject.toml index bcdb97f1..b25f7777 100644 --- a/pyproject.toml +++ b/pyproject.toml @@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta" [project] name = "google-evalbench" -version = "1.18.0" +version = "1.19.0" requires-python = ">=3.10" description = "Evalbench - evaluation benchmarking framework" readme = "README.md"