Class swarmauri_evaluator_subprocess.SubprocessEvaluator.SubprocessEvaluator
swarmauri_evaluator_subprocess.SubprocessEvaluator.SubprocessEvaluator
Bases: EvaluatorBase
Evaluator that runs programs in isolated subprocesses and measures their performance.
This evaluator executes programs in sandboxed subprocesses, capturing stdout, stderr, exit code, and runtime metrics. It provides security through resource limits and timeout constraints to prevent malicious or poorly written code from affecting the host system.
type
class-attribute
instance-attribute
type = 'SubprocessEvaluator'
timeout
class-attribute
instance-attribute
timeout = Field(
default=30.0,
description="Maximum execution time in seconds",
)
max_memory_mb
class-attribute
instance-attribute
max_memory_mb = Field(
default=512, description="Maximum memory usage in MB"
)
max_processes
class-attribute
instance-attribute
max_processes = Field(
default=64, description="Maximum number of processes"
)
max_file_size_mb
class-attribute
instance-attribute
max_file_size_mb = Field(
default=10, description="Maximum file size in MB"
)
working_dir
class-attribute
instance-attribute
working_dir = Field(
default=None,
description="Working directory for execution",
)
env_vars
class-attribute
instance-attribute
env_vars = Field(
default_factory=dict,
description="Environment variables for the subprocess",
)
success_exit_codes
class-attribute
instance-attribute
success_exit_codes = Field(
default=[0],
description="Exit codes considered successful",
)
score_on_timeout
class-attribute
instance-attribute
score_on_timeout = Field(
default=0.0, description="Score to assign on timeout"
)
score_on_error
class-attribute
instance-attribute
score_on_error = Field(
default=0.0,
description="Score to assign on execution error",
)
model_config
class-attribute
instance-attribute
model_config = ConfigDict(
extra="allow", arbitrary_types_allowed=True
)
id
class-attribute
instance-attribute
id = Field(default_factory=generate_id)
members
class-attribute
instance-attribute
members = None
owners
class-attribute
instance-attribute
owners = None
host
class-attribute
instance-attribute
host = None
default_logger
class-attribute
default_logger = None
logger
class-attribute
instance-attribute
logger = None
name
class-attribute
instance-attribute
name = None
version
class-attribute
instance-attribute
version = '0.1.0'
aggregate_scores
aggregate_scores(scores, metadata_list)
Aggregate multiple evaluation scores and their metadata.
This implementation extends the base aggregation with subprocess-specific metrics.
PARAMETER | DESCRIPTION |
---|---|
scores
|
List of individual scores to aggregate
TYPE:
|
metadata_list
|
List of metadata dictionaries corresponding to each score
TYPE:
|
RETURNS | DESCRIPTION |
---|---|
Tuple[float, Dict[str, Any]]
|
A tuple containing: - float: The aggregated score - Dict[str, Any]: Aggregated metadata with execution statistics |
Source code in swarmauri_evaluator_subprocess/SubprocessEvaluator.py
343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 |
|
register_model
classmethod
register_model()
Decorator to register a base model in the unified registry.
RETURNS | DESCRIPTION |
---|---|
Callable
|
A decorator function that registers the model class.
TYPE:
|
Source code in swarmauri_base/DynamicBase.py
562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 |
|
register_type
classmethod
register_type(resource_type=None, type_name=None)
Decorator to register a subtype under one or more base models in the unified registry.
PARAMETER | DESCRIPTION |
---|---|
resource_type
|
The base model(s) under which to register the subtype. If None, all direct base classes (except DynamicBase) are used.
TYPE:
|
type_name
|
An optional custom type name for the subtype.
TYPE:
|
RETURNS | DESCRIPTION |
---|---|
Callable
|
A decorator function that registers the subtype.
TYPE:
|
Source code in swarmauri_base/DynamicBase.py
587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 |
|
model_validate_toml
classmethod
model_validate_toml(toml_data)
Validate a model from a TOML string.
Source code in swarmauri_base/TomlMixin.py
12 13 14 15 16 17 18 19 20 21 22 23 24 |
|
model_dump_toml
model_dump_toml(
fields_to_exclude=None, api_key_placeholder=None
)
Return a TOML representation of the model.
Source code in swarmauri_base/TomlMixin.py
26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 |
|
model_validate_yaml
classmethod
model_validate_yaml(yaml_data)
Validate a model from a YAML string.
Source code in swarmauri_base/YamlMixin.py
11 12 13 14 15 16 17 18 19 20 21 22 23 |
|
model_dump_yaml
model_dump_yaml(
fields_to_exclude=None, api_key_placeholder=None
)
Return a YAML representation of the model.
Source code in swarmauri_base/YamlMixin.py
25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 |
|
model_post_init
model_post_init(logger=None)
Assign a logger instance after model initialization.
Source code in swarmauri_base/LoggerMixin.py
23 24 25 26 27 28 |
|
evaluate
evaluate(program, **kwargs)
Evaluate a program and return a fitness score with metadata.
This method wraps the concrete _compute_score implementation, capturing execution time and handling exceptions.
PARAMETER | DESCRIPTION |
---|---|
program
|
The program to evaluate
TYPE:
|
**kwargs
|
Additional parameters for the evaluation process
DEFAULT:
|
RETURNS | DESCRIPTION |
---|---|
Tuple[float, Dict[str, Any]]
|
A tuple containing: - float: A scalar fitness score (higher is better) - Dict[str, Any]: Metadata about the evaluation, including feature dimensions |
RAISES | DESCRIPTION |
---|---|
EvaluationError
|
If the evaluation process fails |
TypeError
|
If the program is not of the expected type |
Source code in swarmauri_base/evaluators/EvaluatorBase.py
27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 |
|
reset
reset()
Reset the evaluator to its initial state.
This method is called to clear any internal state or cached data before a new evaluation cycle begins.
Source code in swarmauri_base/evaluators/EvaluatorBase.py
139 140 141 142 143 144 145 146 147 148 |
|