pluginbench 0.5.0__tar.gz → 0.5.1__tar.gz
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- {pluginbench-0.5.0 → pluginbench-0.5.1}/PKG-INFO +9 -3
- {pluginbench-0.5.0 → pluginbench-0.5.1}/README.md +8 -2
- {pluginbench-0.5.0 → pluginbench-0.5.1}/pyproject.toml +1 -1
- {pluginbench-0.5.0 → pluginbench-0.5.1}/src/pluginbench/__init__.py +1 -1
- {pluginbench-0.5.0 → pluginbench-0.5.1}/.gitignore +0 -0
- {pluginbench-0.5.0 → pluginbench-0.5.1}/LICENSE +0 -0
- {pluginbench-0.5.0 → pluginbench-0.5.1}/src/pluginbench/__main__.py +0 -0
- {pluginbench-0.5.0 → pluginbench-0.5.1}/src/pluginbench/assessment-charts.html +0 -0
- {pluginbench-0.5.0 → pluginbench-0.5.1}/src/pluginbench/assessment.py +0 -0
- {pluginbench-0.5.0 → pluginbench-0.5.1}/src/pluginbench/assessment_charts.py +0 -0
- {pluginbench-0.5.0 → pluginbench-0.5.1}/src/pluginbench/assessment_metrics.py +0 -0
- {pluginbench-0.5.0 → pluginbench-0.5.1}/src/pluginbench/assessment_models.py +0 -0
- {pluginbench-0.5.0 → pluginbench-0.5.1}/src/pluginbench/baselines.py +0 -0
- {pluginbench-0.5.0 → pluginbench-0.5.1}/src/pluginbench/claude.py +0 -0
- {pluginbench-0.5.0 → pluginbench-0.5.1}/src/pluginbench/cli.py +0 -0
- {pluginbench-0.5.0 → pluginbench-0.5.1}/src/pluginbench/code_diff.py +0 -0
- {pluginbench-0.5.0 → pluginbench-0.5.1}/src/pluginbench/codex.py +0 -0
- {pluginbench-0.5.0 → pluginbench-0.5.1}/src/pluginbench/codex_events.py +0 -0
- {pluginbench-0.5.0 → pluginbench-0.5.1}/src/pluginbench/collectors.py +0 -0
- {pluginbench-0.5.0 → pluginbench-0.5.1}/src/pluginbench/compare.py +0 -0
- {pluginbench-0.5.0 → pluginbench-0.5.1}/src/pluginbench/components.py +0 -0
- {pluginbench-0.5.0 → pluginbench-0.5.1}/src/pluginbench/coverage_report.py +0 -0
- {pluginbench-0.5.0 → pluginbench-0.5.1}/src/pluginbench/datasets.py +0 -0
- {pluginbench-0.5.0 → pluginbench-0.5.1}/src/pluginbench/evaluation.example.yaml +0 -0
- {pluginbench-0.5.0 → pluginbench-0.5.1}/src/pluginbench/evaluation.py +0 -0
- {pluginbench-0.5.0 → pluginbench-0.5.1}/src/pluginbench/evaluation_report.py +0 -0
- {pluginbench-0.5.0 → pluginbench-0.5.1}/src/pluginbench/fallow_parse.mjs +0 -0
- {pluginbench-0.5.0 → pluginbench-0.5.1}/src/pluginbench/harbor_backend.py +0 -0
- {pluginbench-0.5.0 → pluginbench-0.5.1}/src/pluginbench/isolation.py +0 -0
- {pluginbench-0.5.0 → pluginbench-0.5.1}/src/pluginbench/judge.py +0 -0
- {pluginbench-0.5.0 → pluginbench-0.5.1}/src/pluginbench/language_analysis.py +0 -0
- {pluginbench-0.5.0 → pluginbench-0.5.1}/src/pluginbench/ledger.py +0 -0
- {pluginbench-0.5.0 → pluginbench-0.5.1}/src/pluginbench/measurement_profiles.py +0 -0
- {pluginbench-0.5.0 → pluginbench-0.5.1}/src/pluginbench/native_treatment_runtime.js +0 -0
- {pluginbench-0.5.0 → pluginbench-0.5.1}/src/pluginbench/native_treatments.py +0 -0
- {pluginbench-0.5.0 → pluginbench-0.5.1}/src/pluginbench/observer_data/go-analysis-v1/go.mod +0 -0
- {pluginbench-0.5.0 → pluginbench-0.5.1}/src/pluginbench/observer_data/go-analysis-v1/go.sum +0 -0
- {pluginbench-0.5.0 → pluginbench-0.5.1}/src/pluginbench/observer_data/go-analysis-v1/main.go +0 -0
- {pluginbench-0.5.0 → pluginbench-0.5.1}/src/pluginbench/observer_data/oxc-parser-0.126.0/package-lock.json +0 -0
- {pluginbench-0.5.0 → pluginbench-0.5.1}/src/pluginbench/observer_data/oxc-parser-0.126.0/package.json +0 -0
- {pluginbench-0.5.0 → pluginbench-0.5.1}/src/pluginbench/parallel.py +0 -0
- {pluginbench-0.5.0 → pluginbench-0.5.1}/src/pluginbench/processes.py +0 -0
- {pluginbench-0.5.0 → pluginbench-0.5.1}/src/pluginbench/remeasure.py +0 -0
- {pluginbench-0.5.0 → pluginbench-0.5.1}/src/pluginbench/run_lock.py +0 -0
- {pluginbench-0.5.0 → pluginbench-0.5.1}/src/pluginbench/run_status.py +0 -0
- {pluginbench-0.5.0 → pluginbench-0.5.1}/src/pluginbench/study.py +0 -0
- {pluginbench-0.5.0 → pluginbench-0.5.1}/src/pluginbench/study_review.py +0 -0
- {pluginbench-0.5.0 → pluginbench-0.5.1}/src/pluginbench/submissions.py +0 -0
- {pluginbench-0.5.0 → pluginbench-0.5.1}/src/pluginbench/task_sources.py +0 -0
- {pluginbench-0.5.0 → pluginbench-0.5.1}/src/pluginbench/treatments.py +0 -0
- {pluginbench-0.5.0 → pluginbench-0.5.1}/src/pluginbench/trial_containers.py +0 -0
- {pluginbench-0.5.0 → pluginbench-0.5.1}/src/pluginbench/vendor/ECHARTS-LICENSE +0 -0
- {pluginbench-0.5.0 → pluginbench-0.5.1}/src/pluginbench/vendor/ECHARTS-NOTICE +0 -0
- {pluginbench-0.5.0 → pluginbench-0.5.1}/src/pluginbench/vendor/ZRENDER-LICENSE +0 -0
- {pluginbench-0.5.0 → pluginbench-0.5.1}/src/pluginbench/vendor/echarts.min.js +0 -0
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
Metadata-Version: 2.5
|
|
2
2
|
Name: pluginbench
|
|
3
|
-
Version: 0.5.
|
|
3
|
+
Version: 0.5.1
|
|
4
4
|
Summary: Test whether skills help coding agents make fewer mistakes.
|
|
5
5
|
Project-URL: Homepage, https://github.com/filipgutica/pluginbench
|
|
6
6
|
Project-URL: Documentation, https://github.com/filipgutica/pluginbench/blob/main/docs/running-evaluations.md
|
|
@@ -84,7 +84,14 @@ Some measures and commands need more:
|
|
|
84
84
|
|
|
85
85
|
## Install
|
|
86
86
|
|
|
87
|
-
|
|
87
|
+
```sh
|
|
88
|
+
pipx install pluginbench
|
|
89
|
+
pluginbench --version
|
|
90
|
+
```
|
|
91
|
+
|
|
92
|
+
`uv tool install pluginbench` works too. Either one also installs Harbor 0.24.0. If your default Python is older than 3.12, add `--python python3.12`.
|
|
93
|
+
|
|
94
|
+
To change PluginBench itself, install from a clone instead:
|
|
88
95
|
|
|
89
96
|
```sh
|
|
90
97
|
git clone https://github.com/filipgutica/pluginbench.git
|
|
@@ -92,7 +99,6 @@ cd pluginbench
|
|
|
92
99
|
python3 -m venv .venv
|
|
93
100
|
source .venv/bin/activate
|
|
94
101
|
pip install -e .
|
|
95
|
-
pluginbench --version
|
|
96
102
|
```
|
|
97
103
|
|
|
98
104
|
## Quickstart
|
|
@@ -48,7 +48,14 @@ Some measures and commands need more:
|
|
|
48
48
|
|
|
49
49
|
## Install
|
|
50
50
|
|
|
51
|
-
|
|
51
|
+
```sh
|
|
52
|
+
pipx install pluginbench
|
|
53
|
+
pluginbench --version
|
|
54
|
+
```
|
|
55
|
+
|
|
56
|
+
`uv tool install pluginbench` works too. Either one also installs Harbor 0.24.0. If your default Python is older than 3.12, add `--python python3.12`.
|
|
57
|
+
|
|
58
|
+
To change PluginBench itself, install from a clone instead:
|
|
52
59
|
|
|
53
60
|
```sh
|
|
54
61
|
git clone https://github.com/filipgutica/pluginbench.git
|
|
@@ -56,7 +63,6 @@ cd pluginbench
|
|
|
56
63
|
python3 -m venv .venv
|
|
57
64
|
source .venv/bin/activate
|
|
58
65
|
pip install -e .
|
|
59
|
-
pluginbench --version
|
|
60
66
|
```
|
|
61
67
|
|
|
62
68
|
## Quickstart
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
{pluginbench-0.5.0 → pluginbench-0.5.1}/src/pluginbench/observer_data/go-analysis-v1/main.go
RENAMED
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|