agents.common.models.grade.binary¶

Binary grading model for pass/fail evaluations.

This module implements a binary grading system suitable for pass/fail, yes/no, correct/incorrect, and similar binary evaluations.

Classes¶

BinaryGrade

Binary grading model for pass/fail evaluations.

Module Contents¶

class agents.common.models.grade.binary.BinaryGrade(/, **data)¶

Bases: haive.agents.common.models.grade.base.Grade

Binary grading model for pass/fail evaluations.

This grade model represents simple binary outcomes such as pass/fail, yes/no, correct/incorrect, acceptable/unacceptable, etc.

Parameters:: data (Any)

value¶: The binary grade value (True for pass/yes, False for fail/no)

grade_type¶: Always GradeType.BINARY

Example

# Passing grade
grade = BinaryGrade(
value=True,
justification="Response correctly identifies all key concepts",
confidence=0.95
)

# Failing grade
grade = BinaryGrade(
value=False,
justification="Response contains factual errors and misses main points",
confidence=0.88
)

# Using string values (automatically converted)
grade = BinaryGrade(
value="pass",  # Converted to True
justification="Meets minimum requirements"
)

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

classmethod convert_value_to_bool(v)¶

Convert various representations to boolean.

Accepts boolean values, strings, and numbers and converts them to appropriate boolean values for grading.

Parameters:: v (Any) – Value to convert to boolean
Returns:: Boolean representation of the value
Raises:: ValueError – If the value cannot be converted to a meaningful boolean
Return type:: bool

classmethod create_fail(justification, confidence=1.0, **kwargs)¶

Convenience method to create a failing grade.

Parameters:

justification (str) – Explanation for the failing grade
confidence (float) – Confidence level (default 1.0)
**kwargs – Additional parameters for the grade

Returns:

BinaryGrade instance with value=False

Return type:

BinaryGrade

classmethod create_pass(justification, confidence=1.0, **kwargs)¶

Convenience method to create a passing grade.

Parameters:

justification (str) – Explanation for the passing grade
confidence (float) – Confidence level (default 1.0)
**kwargs – Additional parameters for the grade

Returns:

BinaryGrade instance with value=True

Return type:

BinaryGrade

flip()¶

Create a new BinaryGrade with the opposite value.

Useful for creating inverse grades or testing scenarios.

Returns:: New BinaryGrade instance with flipped value
Return type:: BinaryGrade

get_display_value()¶

Get a human-readable display value.

Returns:: “Pass” for True, “Fail” for False
Return type:: str

get_emoji_representation()¶

Get an emoji representation of the grade.

Returns:: ✅ for pass, ❌ for fail
Return type:: str

get_normalized_score()¶

Get the grade as a normalized score between 0.0 and 1.0.

Returns:: 1.0 for True (pass), 0.0 for False (fail)
Return type:: float

is_passing(threshold=None)¶

Determine if the grade represents a passing score.

For binary grades, this simply returns the boolean value. The threshold parameter is ignored for binary grades.

Parameters:: threshold (float | None) – Ignored for binary grades
Returns:: The boolean value of the grade
Return type:: bool

to_display_string()¶

Convert grade to a human-readable display string.

Returns:: Formatted string representation of the binary grade
Return type:: str

validate_grade_value(value)¶

Validate that a value can be converted to binary.

Parameters:: value (Any) – The value to validate
Returns:: True if the value can be converted to boolean, False otherwise
Return type:: bool