mood-bench 0.0.1__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.
- mood_bench-0.0.1/.github/workflows/publish.yml +121 -0
- mood_bench-0.0.1/.github/workflows/version-check.yml +89 -0
- mood_bench-0.0.1/.gitignore +216 -0
- mood_bench-0.0.1/PKG-INFO +293 -0
- mood_bench-0.0.1/README.md +266 -0
- mood_bench-0.0.1/examples/analysis.py +151 -0
- mood_bench-0.0.1/examples/guard.py +53 -0
- mood_bench-0.0.1/examples/guard_ensemble.py +82 -0
- mood_bench-0.0.1/examples/mixture_guard_perplexity.py +99 -0
- mood_bench-0.0.1/mood_bench/__init__.py +98 -0
- mood_bench-0.0.1/mood_bench/_output.py +93 -0
- mood_bench-0.0.1/mood_bench/_prompts.py +27 -0
- mood_bench-0.0.1/mood_bench/aggregator.py +173 -0
- mood_bench-0.0.1/mood_bench/cli/__init__.py +57 -0
- mood_bench-0.0.1/mood_bench/cli/_common.py +103 -0
- mood_bench-0.0.1/mood_bench/cli/analyze.py +186 -0
- mood_bench-0.0.1/mood_bench/cli/guard.py +102 -0
- mood_bench-0.0.1/mood_bench/cli/instruction_tuned.py +105 -0
- mood_bench-0.0.1/mood_bench/cli/mahalanobis.py +184 -0
- mood_bench-0.0.1/mood_bench/cli/perplexity.py +73 -0
- mood_bench-0.0.1/mood_bench/core.py +246 -0
- mood_bench-0.0.1/mood_bench/data.py +75 -0
- mood_bench-0.0.1/mood_bench/metrics.py +73 -0
- mood_bench-0.0.1/mood_bench/pipeline/__init__.py +14 -0
- mood_bench-0.0.1/mood_bench/pipeline/base.py +23 -0
- mood_bench-0.0.1/mood_bench/pipeline/guard.py +50 -0
- mood_bench-0.0.1/mood_bench/pipeline/instruction_tuned.py +316 -0
- mood_bench-0.0.1/mood_bench/pipeline/mahalanobis.py +155 -0
- mood_bench-0.0.1/mood_bench/pipeline/perplexity.py +126 -0
- mood_bench-0.0.1/mood_bench/prompts/constitution.txt +40 -0
- mood_bench-0.0.1/mood_bench/prompts/default_chat_template.jinja +1 -0
- mood_bench-0.0.1/mood_bench/prompts/instruction_grading_icl.jinja +20 -0
- mood_bench-0.0.1/mood_bench/prompts/instruction_grading_no_icl.jinja +14 -0
- mood_bench-0.0.1/mood_bench/prompts/scoring_rubric_alignment.jinja +5 -0
- mood_bench-0.0.1/mood_bench/prompts/scoring_rubric_uncertainty.jinja +5 -0
- mood_bench-0.0.1/mood_bench/py.typed +0 -0
- mood_bench-0.0.1/mood_bench/tokenize.py +80 -0
- mood_bench-0.0.1/pyproject.toml +61 -0
- mood_bench-0.0.1/tests/conftest.py +216 -0
- mood_bench-0.0.1/tests/e2e/test_guard.py +61 -0
- mood_bench-0.0.1/tests/e2e/test_instruction_tuned.py +138 -0
- mood_bench-0.0.1/tests/e2e/test_mahalanobis.py +75 -0
- mood_bench-0.0.1/tests/e2e/test_perplexity.py +55 -0
- mood_bench-0.0.1/tests/run_tests.sh +24 -0
- mood_bench-0.0.1/tests/test_analysis.py +215 -0
- mood_bench-0.0.1/tests/test_cli.py +756 -0
- mood_bench-0.0.1/uv.lock +2653 -0
|
@@ -0,0 +1,121 @@
|
|
|
1
|
+
name: Publish to PyPI
|
|
2
|
+
|
|
3
|
+
on:
|
|
4
|
+
push:
|
|
5
|
+
branches: [main]
|
|
6
|
+
workflow_dispatch:
|
|
7
|
+
|
|
8
|
+
permissions:
|
|
9
|
+
contents: read
|
|
10
|
+
|
|
11
|
+
jobs:
|
|
12
|
+
verify-version-bump:
|
|
13
|
+
name: Verify version was bumped
|
|
14
|
+
runs-on: ubuntu-latest
|
|
15
|
+
outputs:
|
|
16
|
+
version: ${{ steps.check.outputs.version }}
|
|
17
|
+
steps:
|
|
18
|
+
- uses: actions/checkout@v4
|
|
19
|
+
with:
|
|
20
|
+
# Need at least HEAD and HEAD~1 to compare versions.
|
|
21
|
+
fetch-depth: 2
|
|
22
|
+
|
|
23
|
+
- uses: actions/setup-python@v5
|
|
24
|
+
with:
|
|
25
|
+
python-version: "3.12"
|
|
26
|
+
|
|
27
|
+
- name: Install version-check dependencies
|
|
28
|
+
run: python -m pip install --upgrade packaging
|
|
29
|
+
|
|
30
|
+
- name: Verify pyproject.toml version was bumped vs previous commit
|
|
31
|
+
id: check
|
|
32
|
+
shell: bash
|
|
33
|
+
run: |
|
|
34
|
+
python <<'PY'
|
|
35
|
+
import os
|
|
36
|
+
import subprocess
|
|
37
|
+
import sys
|
|
38
|
+
import tomllib
|
|
39
|
+
from packaging.version import InvalidVersion, Version
|
|
40
|
+
|
|
41
|
+
def read_version(blob: bytes) -> str | None:
|
|
42
|
+
data = tomllib.loads(blob.decode())
|
|
43
|
+
return data.get("project", {}).get("version")
|
|
44
|
+
|
|
45
|
+
with open("pyproject.toml", "rb") as f:
|
|
46
|
+
new_version_str = read_version(f.read())
|
|
47
|
+
if not new_version_str:
|
|
48
|
+
sys.exit("pyproject.toml is missing [project].version")
|
|
49
|
+
|
|
50
|
+
try:
|
|
51
|
+
new_version = Version(new_version_str)
|
|
52
|
+
except InvalidVersion as e:
|
|
53
|
+
sys.exit(f"Invalid new version {new_version_str!r}: {e}")
|
|
54
|
+
|
|
55
|
+
try:
|
|
56
|
+
prev_blob = subprocess.check_output(
|
|
57
|
+
["git", "show", "HEAD~1:pyproject.toml"],
|
|
58
|
+
stderr=subprocess.DEVNULL,
|
|
59
|
+
)
|
|
60
|
+
except subprocess.CalledProcessError:
|
|
61
|
+
print(f"No previous pyproject.toml found; treating {new_version} as first publish.")
|
|
62
|
+
prev_version = None
|
|
63
|
+
else:
|
|
64
|
+
prev_version_str = read_version(prev_blob)
|
|
65
|
+
if not prev_version_str:
|
|
66
|
+
print("Previous pyproject.toml had no version; allowing publish.")
|
|
67
|
+
prev_version = None
|
|
68
|
+
else:
|
|
69
|
+
try:
|
|
70
|
+
prev_version = Version(prev_version_str)
|
|
71
|
+
except InvalidVersion as e:
|
|
72
|
+
sys.exit(f"Invalid previous version {prev_version_str!r}: {e}")
|
|
73
|
+
|
|
74
|
+
if prev_version is not None and new_version <= prev_version:
|
|
75
|
+
sys.exit(
|
|
76
|
+
f"::error::Version was not bumped: {prev_version} -> {new_version}. "
|
|
77
|
+
"Update pyproject.toml [project].version before pushing to main."
|
|
78
|
+
)
|
|
79
|
+
|
|
80
|
+
print(f"Version check OK: {prev_version} -> {new_version}")
|
|
81
|
+
with open(os.environ["GITHUB_OUTPUT"], "a") as out:
|
|
82
|
+
out.write(f"version={new_version}\n")
|
|
83
|
+
PY
|
|
84
|
+
|
|
85
|
+
build-and-publish:
|
|
86
|
+
name: Build and publish to PyPI
|
|
87
|
+
needs: verify-version-bump
|
|
88
|
+
runs-on: ubuntu-latest
|
|
89
|
+
|
|
90
|
+
# Required for PyPI trusted publishing (OIDC).
|
|
91
|
+
permissions:
|
|
92
|
+
id-token: write
|
|
93
|
+
contents: read
|
|
94
|
+
|
|
95
|
+
# Tie publishes to a GitHub "pypi" environment so you can add
|
|
96
|
+
# required reviewers / protection rules later.
|
|
97
|
+
environment:
|
|
98
|
+
name: pypi
|
|
99
|
+
url: https://pypi.org/project/mood-bench/${{ needs.verify-version-bump.outputs.version }}/
|
|
100
|
+
|
|
101
|
+
steps:
|
|
102
|
+
- uses: actions/checkout@v4
|
|
103
|
+
|
|
104
|
+
- uses: actions/setup-python@v5
|
|
105
|
+
with:
|
|
106
|
+
python-version: "3.12"
|
|
107
|
+
|
|
108
|
+
- name: Install build tooling
|
|
109
|
+
run: python -m pip install --upgrade build
|
|
110
|
+
|
|
111
|
+
- name: Build sdist and wheel
|
|
112
|
+
run: python -m build
|
|
113
|
+
|
|
114
|
+
- name: Inspect built artifacts
|
|
115
|
+
run: ls -la dist/
|
|
116
|
+
|
|
117
|
+
- name: Publish to PyPI
|
|
118
|
+
uses: pypa/gh-action-pypi-publish@release/v1
|
|
119
|
+
# No `with:` block needed when using trusted publishing.
|
|
120
|
+
# PyPI rejects re-uploads of the same version, so this also
|
|
121
|
+
# acts as a second line of defense against accidental republish.
|
|
@@ -0,0 +1,89 @@
|
|
|
1
|
+
name: Version bump check
|
|
2
|
+
|
|
3
|
+
on:
|
|
4
|
+
pull_request:
|
|
5
|
+
branches: [main]
|
|
6
|
+
paths:
|
|
7
|
+
# Re-run only when something that could affect a publish changes.
|
|
8
|
+
# Keep this broad so the check is a hard gate, not opt-in.
|
|
9
|
+
- "**"
|
|
10
|
+
- "!**/*.md"
|
|
11
|
+
- "!.github/**"
|
|
12
|
+
|
|
13
|
+
permissions:
|
|
14
|
+
contents: read
|
|
15
|
+
|
|
16
|
+
jobs:
|
|
17
|
+
verify-version-bump:
|
|
18
|
+
name: Verify pyproject.toml version is bumped
|
|
19
|
+
runs-on: ubuntu-latest
|
|
20
|
+
steps:
|
|
21
|
+
- uses: actions/checkout@v4
|
|
22
|
+
with:
|
|
23
|
+
# Need both PR head and the base branch to compare.
|
|
24
|
+
fetch-depth: 0
|
|
25
|
+
|
|
26
|
+
- uses: actions/setup-python@v5
|
|
27
|
+
with:
|
|
28
|
+
python-version: "3.12"
|
|
29
|
+
|
|
30
|
+
- name: Install dependencies
|
|
31
|
+
run: python -m pip install --upgrade packaging
|
|
32
|
+
|
|
33
|
+
- name: Compare versions
|
|
34
|
+
shell: bash
|
|
35
|
+
env:
|
|
36
|
+
BASE_REF: ${{ github.event.pull_request.base.ref }}
|
|
37
|
+
BASE_SHA: ${{ github.event.pull_request.base.sha }}
|
|
38
|
+
run: |
|
|
39
|
+
python <<'PY'
|
|
40
|
+
import os
|
|
41
|
+
import subprocess
|
|
42
|
+
import sys
|
|
43
|
+
import tomllib
|
|
44
|
+
from packaging.version import InvalidVersion, Version
|
|
45
|
+
|
|
46
|
+
base_sha = os.environ["BASE_SHA"]
|
|
47
|
+
base_ref = os.environ["BASE_REF"]
|
|
48
|
+
|
|
49
|
+
def read_version(blob: bytes) -> str | None:
|
|
50
|
+
return tomllib.loads(blob.decode()).get("project", {}).get("version")
|
|
51
|
+
|
|
52
|
+
with open("pyproject.toml", "rb") as f:
|
|
53
|
+
new_version_str = read_version(f.read())
|
|
54
|
+
if not new_version_str:
|
|
55
|
+
sys.exit("pyproject.toml is missing [project].version")
|
|
56
|
+
try:
|
|
57
|
+
new_version = Version(new_version_str)
|
|
58
|
+
except InvalidVersion as e:
|
|
59
|
+
sys.exit(f"Invalid PR-head version {new_version_str!r}: {e}")
|
|
60
|
+
|
|
61
|
+
try:
|
|
62
|
+
base_blob = subprocess.check_output(
|
|
63
|
+
["git", "show", f"{base_sha}:pyproject.toml"],
|
|
64
|
+
stderr=subprocess.DEVNULL,
|
|
65
|
+
)
|
|
66
|
+
except subprocess.CalledProcessError:
|
|
67
|
+
print(
|
|
68
|
+
f"No pyproject.toml on base {base_ref}@{base_sha[:8]}; "
|
|
69
|
+
f"treating {new_version} as first publish."
|
|
70
|
+
)
|
|
71
|
+
sys.exit(0)
|
|
72
|
+
|
|
73
|
+
base_version_str = read_version(base_blob)
|
|
74
|
+
if not base_version_str:
|
|
75
|
+
print("Base branch has no [project].version; allowing.")
|
|
76
|
+
sys.exit(0)
|
|
77
|
+
try:
|
|
78
|
+
base_version = Version(base_version_str)
|
|
79
|
+
except InvalidVersion as e:
|
|
80
|
+
sys.exit(f"Invalid base version {base_version_str!r}: {e}")
|
|
81
|
+
|
|
82
|
+
if new_version <= base_version:
|
|
83
|
+
sys.exit(
|
|
84
|
+
f"::error file=pyproject.toml::Version was not bumped: "
|
|
85
|
+
f"{base_version} (on {base_ref}) -> {new_version} (PR head). "
|
|
86
|
+
"Bump pyproject.toml [project].version before merging."
|
|
87
|
+
)
|
|
88
|
+
print(f"Version bump OK: {base_version} -> {new_version}")
|
|
89
|
+
PY
|
|
@@ -0,0 +1,216 @@
|
|
|
1
|
+
# Byte-compiled / optimized / DLL files
|
|
2
|
+
__pycache__/
|
|
3
|
+
*.py[codz]
|
|
4
|
+
*$py.class
|
|
5
|
+
|
|
6
|
+
# C extensions
|
|
7
|
+
*.so
|
|
8
|
+
|
|
9
|
+
# Distribution / packaging
|
|
10
|
+
.Python
|
|
11
|
+
build/
|
|
12
|
+
develop-eggs/
|
|
13
|
+
dist/
|
|
14
|
+
downloads/
|
|
15
|
+
eggs/
|
|
16
|
+
.eggs/
|
|
17
|
+
lib/
|
|
18
|
+
lib64/
|
|
19
|
+
parts/
|
|
20
|
+
sdist/
|
|
21
|
+
var/
|
|
22
|
+
wheels/
|
|
23
|
+
share/python-wheels/
|
|
24
|
+
*.egg-info/
|
|
25
|
+
.installed.cfg
|
|
26
|
+
*.egg
|
|
27
|
+
MANIFEST
|
|
28
|
+
|
|
29
|
+
# PyInstaller
|
|
30
|
+
# Usually these files are written by a python script from a template
|
|
31
|
+
# before PyInstaller builds the exe, so as to inject date/other infos into it.
|
|
32
|
+
*.manifest
|
|
33
|
+
*.spec
|
|
34
|
+
|
|
35
|
+
# Installer logs
|
|
36
|
+
pip-log.txt
|
|
37
|
+
pip-delete-this-directory.txt
|
|
38
|
+
|
|
39
|
+
# Unit test / coverage reports
|
|
40
|
+
htmlcov/
|
|
41
|
+
.tox/
|
|
42
|
+
.nox/
|
|
43
|
+
.coverage
|
|
44
|
+
.coverage.*
|
|
45
|
+
.cache
|
|
46
|
+
nosetests.xml
|
|
47
|
+
coverage.xml
|
|
48
|
+
*.cover
|
|
49
|
+
*.py.cover
|
|
50
|
+
.hypothesis/
|
|
51
|
+
.pytest_cache/
|
|
52
|
+
cover/
|
|
53
|
+
|
|
54
|
+
# Translations
|
|
55
|
+
*.mo
|
|
56
|
+
*.pot
|
|
57
|
+
|
|
58
|
+
# Django stuff:
|
|
59
|
+
*.log
|
|
60
|
+
local_settings.py
|
|
61
|
+
db.sqlite3
|
|
62
|
+
db.sqlite3-journal
|
|
63
|
+
|
|
64
|
+
# Flask stuff:
|
|
65
|
+
instance/
|
|
66
|
+
.webassets-cache
|
|
67
|
+
|
|
68
|
+
# Scrapy stuff:
|
|
69
|
+
.scrapy
|
|
70
|
+
|
|
71
|
+
# Sphinx documentation
|
|
72
|
+
docs/_build/
|
|
73
|
+
|
|
74
|
+
# PyBuilder
|
|
75
|
+
.pybuilder/
|
|
76
|
+
target/
|
|
77
|
+
|
|
78
|
+
# Jupyter Notebook
|
|
79
|
+
.ipynb_checkpoints
|
|
80
|
+
|
|
81
|
+
# IPython
|
|
82
|
+
profile_default/
|
|
83
|
+
ipython_config.py
|
|
84
|
+
|
|
85
|
+
# pyenv
|
|
86
|
+
# For a library or package, you might want to ignore these files since the code is
|
|
87
|
+
# intended to run in multiple environments; otherwise, check them in:
|
|
88
|
+
# .python-version
|
|
89
|
+
|
|
90
|
+
# pipenv
|
|
91
|
+
# According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
|
|
92
|
+
# However, in case of collaboration, if having platform-specific dependencies or dependencies
|
|
93
|
+
# having no cross-platform support, pipenv may install dependencies that don't work, or not
|
|
94
|
+
# install all needed dependencies.
|
|
95
|
+
#Pipfile.lock
|
|
96
|
+
|
|
97
|
+
# UV
|
|
98
|
+
# Similar to Pipfile.lock, it is generally recommended to include uv.lock in version control.
|
|
99
|
+
# This is especially recommended for binary packages to ensure reproducibility, and is more
|
|
100
|
+
# commonly ignored for libraries.
|
|
101
|
+
#uv.lock
|
|
102
|
+
|
|
103
|
+
# poetry
|
|
104
|
+
# Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
|
|
105
|
+
# This is especially recommended for binary packages to ensure reproducibility, and is more
|
|
106
|
+
# commonly ignored for libraries.
|
|
107
|
+
# https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
|
|
108
|
+
#poetry.lock
|
|
109
|
+
#poetry.toml
|
|
110
|
+
|
|
111
|
+
# pdm
|
|
112
|
+
# Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
|
|
113
|
+
# pdm recommends including project-wide configuration in pdm.toml, but excluding .pdm-python.
|
|
114
|
+
# https://pdm-project.org/en/latest/usage/project/#working-with-version-control
|
|
115
|
+
#pdm.lock
|
|
116
|
+
#pdm.toml
|
|
117
|
+
.pdm-python
|
|
118
|
+
.pdm-build/
|
|
119
|
+
|
|
120
|
+
# pixi
|
|
121
|
+
# Similar to Pipfile.lock, it is generally recommended to include pixi.lock in version control.
|
|
122
|
+
#pixi.lock
|
|
123
|
+
# Pixi creates a virtual environment in the .pixi directory, just like venv module creates one
|
|
124
|
+
# in the .venv directory. It is recommended not to include this directory in version control.
|
|
125
|
+
.pixi
|
|
126
|
+
|
|
127
|
+
# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
|
|
128
|
+
__pypackages__/
|
|
129
|
+
|
|
130
|
+
# Celery stuff
|
|
131
|
+
celerybeat-schedule
|
|
132
|
+
celerybeat.pid
|
|
133
|
+
|
|
134
|
+
# SageMath parsed files
|
|
135
|
+
*.sage.py
|
|
136
|
+
|
|
137
|
+
# Environments
|
|
138
|
+
.env
|
|
139
|
+
.envrc
|
|
140
|
+
.venv
|
|
141
|
+
env/
|
|
142
|
+
venv/
|
|
143
|
+
ENV/
|
|
144
|
+
env.bak/
|
|
145
|
+
venv.bak/
|
|
146
|
+
|
|
147
|
+
# Spyder project settings
|
|
148
|
+
.spyderproject
|
|
149
|
+
.spyproject
|
|
150
|
+
|
|
151
|
+
# Rope project settings
|
|
152
|
+
.ropeproject
|
|
153
|
+
|
|
154
|
+
# mkdocs documentation
|
|
155
|
+
/site
|
|
156
|
+
|
|
157
|
+
# mypy
|
|
158
|
+
.mypy_cache/
|
|
159
|
+
.dmypy.json
|
|
160
|
+
dmypy.json
|
|
161
|
+
|
|
162
|
+
# Pyre type checker
|
|
163
|
+
.pyre/
|
|
164
|
+
|
|
165
|
+
# pytype static type analyzer
|
|
166
|
+
.pytype/
|
|
167
|
+
|
|
168
|
+
# Cython debug symbols
|
|
169
|
+
cython_debug/
|
|
170
|
+
|
|
171
|
+
# PyCharm
|
|
172
|
+
# JetBrains specific template is maintained in a separate JetBrains.gitignore that can
|
|
173
|
+
# be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
|
|
174
|
+
# and can be added to the global gitignore or merged into this file. For a more nuclear
|
|
175
|
+
# option (not recommended) you can uncomment the following to ignore the entire idea folder.
|
|
176
|
+
#.idea/
|
|
177
|
+
|
|
178
|
+
# Abstra
|
|
179
|
+
# Abstra is an AI-powered process automation framework.
|
|
180
|
+
# Ignore directories containing user credentials, local state, and settings.
|
|
181
|
+
# Learn more at https://abstra.io/docs
|
|
182
|
+
.abstra/
|
|
183
|
+
|
|
184
|
+
# Visual Studio Code
|
|
185
|
+
# Visual Studio Code specific template is maintained in a separate VisualStudioCode.gitignore
|
|
186
|
+
# that can be found at https://github.com/github/gitignore/blob/main/Global/VisualStudioCode.gitignore
|
|
187
|
+
# and can be added to the global gitignore or merged into this file. However, if you prefer,
|
|
188
|
+
# you could uncomment the following to ignore the entire vscode folder
|
|
189
|
+
# .vscode/
|
|
190
|
+
|
|
191
|
+
# Ruff stuff:
|
|
192
|
+
.ruff_cache/
|
|
193
|
+
|
|
194
|
+
# PyPI configuration file
|
|
195
|
+
.pypirc
|
|
196
|
+
|
|
197
|
+
# Cursor
|
|
198
|
+
# Cursor is an AI-powered code editor. `.cursorignore` specifies files/directories to
|
|
199
|
+
# exclude from AI features like autocomplete and code analysis. Recommended for sensitive data
|
|
200
|
+
# refer to https://docs.cursor.com/context/ignore-files
|
|
201
|
+
.cursorignore
|
|
202
|
+
.cursorindexingignore
|
|
203
|
+
|
|
204
|
+
# Marimo
|
|
205
|
+
marimo/_static/
|
|
206
|
+
marimo/_lsp/
|
|
207
|
+
__marimo__/
|
|
208
|
+
|
|
209
|
+
mood-bench-results*/
|
|
210
|
+
tests/results/
|
|
211
|
+
function-calling-missing-results/
|
|
212
|
+
mahalanobis-stats-cache/
|
|
213
|
+
models/
|
|
214
|
+
old-models/
|
|
215
|
+
scripts/
|
|
216
|
+
old/
|