Expose __version__ in agentunit package #44
Conversation
Learn moreAll Green is an AI agent that automatically: ✅ Addresses code review comments ✅ Fixes failing CI checks ✅ Resolves merge conflicts |
WalkthroughAdds local CI instructions to README, extends public exports in Changes
Sequence Diagram(s)(omitted — changes are documentation, API re-exports, and a unit test; no new multi-component control flow) Estimated code review effort🎯 2 (Simple) | ⏱️ ~10 minutes Possibly related issues
Possibly related PRs
Suggested reviewers
Pre-merge checks and finishing touches❌ Failed checks (3 warnings, 1 inconclusive)
✅ Passed checks (1 passed)
✨ Finishing touches
🧪 Generate unit tests (beta)
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 2
🧹 Nitpick comments (3)
src/agentunit/__init__.py (1)
21-22: Implementation approved; version matches pyproject.toml.The
__version__attribute is correctly exposed and meets the acceptance criteria (import agentunit; print(agentunit.__version__)).Consider using importlib.metadata to access metadata of an installed Distribution Package, which would eliminate the need to manually keep this in sync with
pyproject.toml:from importlib.metadata import version __version__ = version("agentunit")tests/test_reporting.py (2)
5-6: Avoid manualsys.pathmanipulation in tests.Modifying
sys.pathis fragile and non-standard for pytest. Instead, ensure the package is installed in development mode (pip install -e .) or configure pytest'spythonpathinpyproject.toml.🔎 Suggested approach
Remove lines 5-6 and configure pytest properly:
# In pyproject.toml [tool.pytest.ini_options] pythonpath = ["src"]Or install the package in editable mode:
pip install -e .
37-38: UTF-8 encoding check should verify no exception is raised.The
encode("utf-8")call discards its result. While calling it will raise if encoding fails, the intent would be clearer with an explicit assertion or a comment explaining the check.🔎 Suggested improvement
# UTF-8 safety - markdown.encode("utf-8") + # Verify markdown can be encoded as UTF-8 (raises UnicodeEncodeError if it cannot) + _ = markdown.encode("utf-8")Or use a try/except to make the assertion explicit:
# UTF-8 safety try: markdown.encode("utf-8") except UnicodeEncodeError: pytest.fail("Markdown output is not valid UTF-8")
📜 Review details
Configuration used: Organization UI
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (11)
README.md(1 hunks)src/agentunit/__init__.py(1 hunks)src/agentunit/adapters/base.py(1 hunks)src/agentunit/core/__init__.py(1 hunks)src/agentunit/core/exceptions.py(1 hunks)src/agentunit/core/replay.py(2 hunks)src/agentunit/core/runner.py(1 hunks)src/agentunit/core/scenario.py(4 hunks)src/agentunit/core/trace.py(3 hunks)src/agentunit/py.typed(0 hunks)tests/test_reporting.py(1 hunks)
💤 Files with no reviewable changes (1)
- src/agentunit/py.typed
🧰 Additional context used
🧬 Code graph analysis (2)
tests/test_reporting.py (4)
src/agentunit/reporting/results.py (1)
SuiteResult(70-129)src/agentunit/comparison/comparator.py (1)
RunResult(21-43)src/agentunit/datasets/base.py (1)
name(38-39)src/agentunit/collaboration/branch.py (1)
status(173-195)
src/agentunit/adapters/base.py (3)
tests/test_runner.py (2)
execute(30-38)cleanup(40-41)src/agentunit/datasets/base.py (1)
DatasetCase(19-27)src/agentunit/core/trace.py (1)
TraceLog(26-78)
⏰ Context from checks skipped due to timeout of 90000ms. You can increase the timeout in your CodeRabbit configuration to a maximum of 15 minutes (900000ms). (1)
- GitHub Check: Test (Python 3.10)
🔇 Additional comments (7)
src/agentunit/core/runner.py (1)
1-3: LGTM!The multi-line docstring format is consistent with Python documentation conventions.
src/agentunit/core/scenario.py (1)
1-3: LGTM!Docstring reformatting to multi-line format improves readability and follows Python documentation conventions consistently across the module.
Also applies to: 24-26, 82-84, 100-102
src/agentunit/core/exceptions.py (1)
1-23: LGTM!Docstring reformatting is consistent with the rest of the PR and follows Python documentation conventions.
src/agentunit/core/trace.py (1)
1-3: LGTM!The multi-line docstring reformatting improves readability and is consistent across the module.
Also applies to: 16-18, 27-29
src/agentunit/core/__init__.py (1)
1-3: LGTM!The multi-line docstring formatting is consistent with other modules in this PR.
src/agentunit/core/replay.py (1)
1-3: LGTM!The multi-line docstring formatting is consistent with the pattern applied across the codebase in this PR.
Also applies to: 13-15
src/agentunit/adapters/base.py (1)
35-42: LGTM!The expanded docstrings with Args and Returns sections improve API documentation for implementers of the
BaseAdapterinterface.Also applies to: 46-55, 58-66
Signed-off-by: Jagriti-student <jagriti7989@gmail.com>
|
Codecov Report❌ Patch coverage is
📢 Thoughts on this report? Let us know! |
There was a problem hiding this comment.
Actionable comments posted: 1
🧹 Nitpick comments (1)
src/agentunit/__init__.py (1)
21-21: Consider usingimportlib.metadatato avoid version drift.The hardcoded version string requires manual updates whenever the version changes in
pyproject.toml, creating a maintenance burden and risk of version drift. Issue #11 mentionedimportlib.metadataas an alternative that automatically reads from package metadata.🔎 Proposed refactor using importlib.metadata
+from importlib.metadata import version, PackageNotFoundError + +try: + __version__ = version("agentunit") +except PackageNotFoundError: + # Fallback for development installs + __version__ = "0.0.0+dev" -__version__ = "0.7.0"This approach eliminates the need to manually sync versions between
pyproject.tomland the source code.
📜 Review details
Configuration used: Path: .coderabbit.yaml
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (3)
report.mdsrc/agentunit/__init__.pytests/test_reporting.py
✅ Files skipped from review due to trivial changes (1)
- report.md
🚧 Files skipped from review as they are similar to previous changes (1)
- tests/test_reporting.py
⏰ Context from checks skipped due to timeout of 90000ms. You can increase the timeout in your CodeRabbit configuration to a maximum of 15 minutes (900000ms). (1)
- GitHub Check: Test (Python 3.10)
| """AgentUnit - pytest-style evaluation harness for agentic AI and RAG workflows.""" | ||
|
|
There was a problem hiding this comment.
Move the module docstring to the correct position.
Module docstrings must be the first statement in a file (immediately after from __future__ imports). When placed after regular imports, the string becomes a discarded literal and won't be accessible via help(agentunit) or agentunit.__doc__.
🔎 Proposed fix
from __future__ import annotations
+"""AgentUnit - pytest-style evaluation harness for agentic AI and RAG workflows."""
+
from .core.runner import Runner, run_suite
from .core.scenario import Scenario
from .datasets.base import DatasetCase, DatasetSource
from .reporting.results import ScenarioResult, SuiteResult
-"""AgentUnit - pytest-style evaluation harness for agentic AI and RAG workflows."""
-
__all__ = [
"DatasetCase",
"DatasetSource",🤖 Prompt for AI Agents
In src/agentunit/__init__.py around lines 9-10, the module docstring is placed
after regular imports so it becomes a discarded literal; move the triple-quoted
docstring to be the very first statement in the file (immediately after any from
__future__ imports if present) so it becomes the module-level docstring
accessible via help() and __doc__.
|
I have solve the issue. |
3 participants
Added version attribute to agentunit package.
Version matches pyproject.toml.
closes #11
Summary by CodeRabbit
Documentation
New Features
Tests
Chores
✏️ Tip: You can customize this high-level summary in your review settings.