Files
cleveragents-core/features/steps/structural_validation_steps.py
T
HAL9000 2f29f8352f
CI / push-validation (push) Successful in 29s
CI / helm (push) Successful in 39s
CI / build (push) Successful in 1m9s
CI / lint (push) Successful in 1m23s
CI / typecheck (push) Successful in 1m34s
CI / quality (push) Successful in 1m39s
CI / security (push) Successful in 1m46s
CI / e2e_tests (push) Successful in 52s
CI / benchmark-regression (push) Failing after 40s
CI / integration_tests (push) Successful in 5m6s
CI / unit_tests (push) Successful in 6m7s
CI / docker (push) Successful in 1m28s
CI / coverage (push) Successful in 10m46s
CI / status-check (push) Successful in 7s
CI / benchmark-publish (push) Failing after 45m49s
CI / helm (pull_request) Successful in 45s
CI / build (pull_request) Successful in 1m8s
CI / lint (pull_request) Successful in 1m45s
CI / quality (pull_request) Successful in 1m39s
CI / security (pull_request) Successful in 2m11s
CI / typecheck (pull_request) Successful in 2m21s
CI / push-validation (pull_request) Successful in 22s
CI / integration_tests (pull_request) Successful in 4m19s
CI / unit_tests (pull_request) Successful in 5m5s
CI / docker (pull_request) Successful in 1m47s
CI / coverage (pull_request) Successful in 11m53s
CI / status-check (pull_request) Successful in 3s
chore: resolve merge conflicts and apply cosmetic fixes
- Resolve CHANGELOG.md conflict to include both entries, referencing issue #8164 instead of PR #11161
- Resolve CONTRIBUTORS.md conflict, fix leading space in new entry
- Remove duplicate create_sequence_node function (dead code)
Merges master into feat/structural-output-validation branch
2026-05-14 18:14:48 +00:00

677 lines
23 KiB
Python

"""Step definitions for structural component output validation.
Tests for features/structural_validation.feature - validates all four
validators covering plan tree nodes, decision CLI dicts, structured
output envelopes, and the unified dispatcher.
"""
from __future__ import annotations
from typing import Any
from behave import given, then, when # type: ignore[import-untyped]
from behave.runner import Context # type: ignore[import-untyped]
from cleveragents.core.validation import (
ValidationError,
validate_decision_dict,
validate_plan_tree,
validate_structured_component_output,
validate_structured_output,
)
# Helper: valid ULID strings for test data
VALID_ULID_A = "01ARZ3NDEKTSV4XXFFJFRC889A"
VALID_ULID_B = "01ARZ3NDEKTSV4XXFFJFRC889B"
VALID_ULID_C = "01ARZ3NDEKTSV4XXFFJFRC889C"
# ────────────────────────────────────────────────────────────
# Plan tree scenarios
# ────────────────────────────────────────────────────────────
@given("the plan tree contains 1 node(s)")
def step_plan_tree_1_node(ctx: Context) -> None:
"""Create a single-node plan tree."""
ctx.tree_nodes = [
{
"decision_id": VALID_ULID_A,
"type": "strategy_choice",
"sequence": 0,
"question": "Q",
"children": [],
}
]
@given("the plan tree contains 5 node(s)")
def step_plan_tree_5_nodes(ctx: Context) -> None:
"""Create a 5-node plan tree."""
ctx.tree_nodes = [
{
"decision_id": f"01ARZ3NDEKTSV4XXFFJFRC{str(i).zfill(4)}",
"type": "strategy_choice",
"sequence": i,
"question": f"Decision question #{i}",
"children": [],
**({"parent_decision_id": VALID_ULID_A} if i > 0 else {}),
}
for i in range(5)
]
@given("the plan tree contains 20 node(s)")
def step_plan_tree_20_nodes(ctx: Context) -> None:
"""Create a 20-node plan tree."""
ctx.tree_nodes = [
{
"decision_id": f"01ARZ3NDEKTSV4XXFFJFRC{str(i).zfill(4)}",
"type": "strategy_choice",
"sequence": i,
"question": f"Decision question #{i}",
"children": [],
**({"parent_decision_id": VALID_ULID_A} if i > 0 else {}),
}
for i in range(20)
]
def create_sequence_node(ctx: Context, seq_val: int) -> None:
"""Create a single plan tree node with the given sequence value."""
ctx.tree_nodes = [
{
"decision_id": VALID_ULID_A,
"type": "strategy_choice",
"sequence": seq_val,
"question": "Q",
"children": [],
}
]
@given('the plan tree contains a node missing "decision_id"')
def step_node_missing_decision_id(ctx: Context) -> None:
"""Create a node missing the required decision_id field."""
ctx.tree_nodes = [
{
"type": "strategy_choice",
"sequence": 0,
"question": "Missing ID",
"children": [],
}
]
@given('the plan tree contains a node with invalid ULID "not-a-ulid-12345"')
def step_node_invalid_ulid(ctx: Context) -> None:
"""Create a node with an invalid decision_id."""
ctx.tree_nodes = [
{
"decision_id": "not-a-ulid-12345",
"type": "strategy_choice",
"sequence": 0,
"question": "Invalid ULID test",
"children": [],
}
]
@given('the plan tree contains a node with empty "children" list')
def step_node_empty_children(ctx: Context) -> None:
"""Create a node with an empty children list - should be valid."""
ctx.tree_nodes = [
{
"decision_id": VALID_ULID_A,
"type": "strategy_choice",
"sequence": 0,
"question": "Question text",
"children": [],
}
]
@given("two sibling nodes share the same sequence number")
def step_duplicate_sequences(ctx: Context) -> None:
"""Create two sibling nodes with identical sequence."""
ctx.tree_nodes = [
{
"decision_id": VALID_ULID_A,
"type": "strategy_choice",
"sequence": 5,
"question": "First",
"children": [],
"parent_decision_id": VALID_ULID_B,
},
{
"decision_id": VALID_ULID_C,
"type": "implementation_choice",
"sequence": 5,
"question": "Second",
"children": [],
"parent_decision_id": VALID_ULID_B,
},
]
@given('a plan tree node with sequence "0"')
def step_node_sequence_zero(ctx: Context) -> None:
create_sequence_node(ctx, 0)
@given('a plan tree node with sequence "1"')
def step_node_sequence_one(ctx: Context) -> None:
create_sequence_node(ctx, 1)
@given('a plan tree node with sequence "100"')
def step_node_sequence_100(ctx: Context) -> None:
create_sequence_node(ctx, 100)
@given('a plan tree node with sequence "-1"')
def step_node_sequence_negative(ctx: Context) -> None:
create_sequence_node(ctx, -1)
# ────────────────────────────────────────────────────────────
# Decision dict scenarios
# ────────────────────────────────────────────────────────────
def _parse_value(raw: str) -> Any:
"""Parse a behave value string into Python type."""
stripped = raw.strip().strip('"').strip("'")
if stripped in ("null", "none", "None"):
return None
if stripped == "true":
return True
if stripped == "false":
return False
try:
return int(stripped)
except ValueError:
pass
try:
return float(stripped)
except ValueError:
pass
return stripped
def _ensure_decision_dict(ctx: Context) -> dict:
"""Ensure ctx.decision_dict exists with defaults."""
if not hasattr(ctx, "decision_dict"):
ctx.decision_dict = {
"decision_id": VALID_ULID_A,
"plan_id": VALID_ULID_B,
"type": "strategy_choice",
"sequence": 1,
"question": "Which approach?",
"chosen": "Option A",
"confidence": 0.75,
"parent": "(root)",
"is_correction": False,
"superseded": False,
}
return ctx.decision_dict # type: ignore[return-value]
@given('I have a decision dict with "decision_id" set to 01ARZ3NDEKTSV4XXFFJFRC889A')
def step_decision_dict_field_decision_id(ctx: Context) -> None:
d = _ensure_decision_dict(ctx)
d["decision_id"] = "01ARZ3NDEKTSV4XXFFJFRC889A"
@given('I have a decision dict with "plan_id" set to 01ARZ3NDEKTSV4XXFFJFRC889B')
def step_decision_dict_field_plan_id(ctx: Context) -> None:
d = _ensure_decision_dict(ctx)
d["plan_id"] = "01ARZ3NDEKTSV4XXFFJFRC889B"
@given('I have a decision dict with "type" set to strategy_choice')
def step_decision_dict_field_type(ctx: Context) -> None:
d = _ensure_decision_dict(ctx)
d["type"] = "strategy_choice"
@given('I have a decision dict with "sequence" set to 5')
def step_decision_dict_field_sequence(ctx: Context) -> None:
d = _ensure_decision_dict(ctx)
d["sequence"] = 5
@given('I have a decision dict with "question" set to Which approach?')
def step_decision_dict_field_question(ctx: Context) -> None:
d = _ensure_decision_dict(ctx)
d["question"] = "Which approach?"
@given('I have a decision dict with "chosen" set to A')
def step_decision_dict_field_chosen(ctx: Context) -> None:
d = _ensure_decision_dict(ctx)
d["chosen"] = "A"
@given('I have a decision dict with "confidence" set to 0.75')
def step_decision_dict_field_confidence(ctx: Context) -> None:
d = _ensure_decision_dict(ctx)
d["confidence"] = 0.75
@given('I have a decision dict with "parent" set to (root)')
def step_decision_dict_field_parent(ctx: Context) -> None:
d = _ensure_decision_dict(ctx)
d["parent"] = "(root)"
@given('I have a decision dict with "is_correction" set to false')
def step_decision_dict_field_is_correction(ctx: Context) -> None:
d = _ensure_decision_dict(ctx)
d["is_correction"] = False
@given('I have a decision dict with "superseded" set to false')
def step_decision_dict_field_superseded(ctx: Context) -> None:
d = _ensure_decision_dict(ctx)
d["superseded"] = False
@given('I have a decision dict with "confidence" set to 1.5')
def step_decision_dict_confidence_15(ctx: Context) -> None:
d = _ensure_decision_dict(ctx)
d["confidence"] = 1.5
@given('I have a decision dict with "confidence" set to null')
def step_decision_dict_confidence_null(ctx: Context) -> None:
d = _ensure_decision_dict(ctx)
d["confidence"] = None
@given('I have a decision dict with "question" set to 42')
def step_decision_dict_question_42(ctx: Context) -> None:
d = _ensure_decision_dict(ctx)
d["question"] = 42
@given('I have a decision dict with "parent" set to "random-string"')
def step_decision_dict_parent_random(ctx: Context) -> None:
d = _ensure_decision_dict(ctx)
d["parent"] = "random-string"
@given('I have a decision dict with "is_correction" set to "yes"')
def step_decision_dict_is_correction_yes(ctx: Context) -> None:
d = _ensure_decision_dict(ctx)
d["is_correction"] = "yes"
@given("I have a valid decision dict")
@when("I validate the decision dict")
def step_validate_decision(ctx: Context) -> None:
"""Validate and store results."""
d = _ensure_decision_dict(ctx)
ctx.validation_result = validate_decision_dict(d)
# ────────────────────────────────────────────────────────────
# Structured output scenarios
# ────────────────────────────────────────────────────────────
def _ensure_struct_output(ctx: Context) -> dict:
"""Ensure ctx.struct_output exists with defaults."""
if not hasattr(ctx, "struct_output"):
ctx.struct_output = {
"command": "agents plan list",
"session_id": VALID_ULID_A,
"status": "ok",
"exit_code": 0,
"elements": [],
}
return ctx.struct_output # type: ignore[return-value]
@given("I have a valid structured output with all required fields")
@when("I validate the structured output")
def step_validate_structured(ctx: Context) -> None:
"""Validate and store results."""
o = _ensure_struct_output(ctx)
ctx.validation_result = validate_structured_output(o)
@given(
'I have a structured output with "command" set to agents plan list (and all other required fields present)'
)
def step_structured_output_command(ctx: Context) -> None:
o = _ensure_struct_output(ctx)
o["command"] = "agents plan list"
@given(
'I have a structured output with "session_id" set to 01ARZ3NDEKTSV4XXFFJFRC889A (and all other required fields present)'
)
def step_structured_output_session_id(ctx: Context) -> None:
o = _ensure_struct_output(ctx)
o["session_id"] = "01ARZ3NDEKTSV4XXFFJFRC889A"
@given(
'I have a structured output with "status" set to ok (and all other required fields present)'
)
def step_structured_output_status_ok(ctx: Context) -> None:
o = _ensure_struct_output(ctx)
o["status"] = "ok"
@given(
'I have a structured output with "exit_code" set to 0 (and all other required fields present)'
)
def step_structured_output_exit_code_0(ctx: Context) -> None:
o = _ensure_struct_output(ctx)
o["exit_code"] = 0
@given(
'I have a structured output with "status" set to "running" (and all other required fields present)'
)
def step_structured_output_status_running(ctx: Context) -> None:
o = _ensure_struct_output(ctx)
o["status"] = "running"
@given(
'I have a structured output with "exit_code" set to "-1" (and all other required fields present)'
)
def step_structured_output_exit_code_neg1(ctx: Context) -> None:
o = _ensure_struct_output(ctx)
o["exit_code"] = -1
@given(
'I have a structured output with empty "elements" list (and all other fields valid)'
)
def step_empty_elements(ctx: Context) -> None:
"""Empty elements is valid."""
o = _ensure_struct_output(ctx)
o["elements"] = []
@given('I have a structured output with an element missing "kind" field')
def step_invalid_element(ctx: Context) -> None:
"""Create an invalid element."""
o = _ensure_struct_output(ctx)
o["elements"] = [{"not_kind": "panel"}]
# ────────────────────────────────────────────────────────────
# Dispatcher scenarios
# ────────────────────────────────────────────────────────────
@given('I target validation for "plan_tree" with valid data')
def step_dispatcher_target_plan_tree(ctx: Context) -> None:
ctx.target_type = "plan_tree"
ctx.validator_data = [
{
"decision_id": VALID_ULID_A,
"type": "strategy_choice",
"sequence": 0,
"question": "Q",
"children": [],
}
]
@given('I target validation for "decision" with valid data')
def step_dispatcher_target_decision(ctx: Context) -> None:
ctx.target_type = "decision"
ctx.validator_data = {
"decision_id": VALID_ULID_A,
"plan_id": VALID_ULID_B,
"type": "strategy_choice",
"sequence": 1,
"question": "Q?",
"chosen": "A",
"confidence": 0.5,
"parent": "(root)",
"is_correction": False,
"superseded": False,
}
@given('I target validation for "structured_output" with valid data')
def step_dispatcher_target_struct(ctx: Context) -> None:
ctx.target_type = "structured_output"
ctx.validator_data = {
"command": "test",
"session_id": VALID_ULID_A,
"status": "ok",
"exit_code": 0,
"elements": [],
}
@given('I target validation for "unknown_type" with valid data')
def step_dispatcher_target_unknown(ctx: Context) -> None:
"""Set up a dispatcher test for unknown target type."""
ctx.target_type = "unknown_type"
ctx.validator_data = {}
@when("I call validate_structured_component_output")
def step_call_dispatcher(ctx: Context) -> None:
"""Call the dispatcher."""
target = ctx.target_type if hasattr(ctx, "target_type") else "plan_tree" # type: ignore[attr-defined]
data = ctx.validator_data if hasattr(ctx, "validator_data") else {} # type: ignore[attr-defined]
try:
ctx.dispatcher_result = validate_structured_component_output(target, data) # type: ignore[arg-type]
ctx.dispatcher_error = None
except ValidationError as exc:
ctx.dispatcher_result = None
ctx.dispatcher_error = exc
# ────────────────────────────────────────────────────────────
# Shared scenarios
# ────────────────────────────────────────────────────────────
@given("the plan tree has {node_count:d} valid nodes")
def step_valid_tree(ctx: Context, node_count: int = 3) -> None:
"""Set up a default valid tree."""
if not hasattr(ctx, "tree_nodes"):
ctx.tree_nodes = [
{
"decision_id": f"01ARZ3NDEKTSV4XXFFJFRC{str(i).zfill(4)}",
"type": "strategy_choice",
"sequence": i,
"question": f"Q{i}",
"children": [],
}
for i in range(node_count)
]
@given("I have a plan tree with valid nodes")
def step_valid_nodes_default(ctx: Context) -> None:
"""Set default valid tree if no tree defined."""
@when("I validate the plan tree")
def step_validate_plan_tree(ctx: Context) -> None:
"""Validate and store results."""
nodes = (
ctx.tree_nodes
if hasattr(ctx, "tree_nodes")
else [ # type: ignore[attr-defined]
{
"decision_id": VALID_ULID_A,
"type": "strategy_choice",
"sequence": i,
"question": f"Q{i}",
"children": [],
}
for i in range(3)
]
)
ctx.validation_result = validate_plan_tree(nodes)
@when("I validate the plan tree structure")
def step_validate_structure(ctx: Context) -> None:
"""Run plan_tree validation."""
nodes = ctx.tree_nodes if hasattr(ctx, "tree_nodes") else [] # type: ignore[attr-defined]
ctx.validation_result = validate_plan_tree(nodes)
@given("I have a decision dict where whitespace may vary between fields")
def step_whitespace_dict(ctx: Context) -> None:
"""Whitespace in string values - structure still valid."""
ctx.decision_dict = {
"decision_id": VALID_ULID_A,
"plan_id": VALID_ULID_B,
"type": " strategy_choice ",
"sequence": 1,
"question": "Which approach? ",
"chosen": " Option A ",
"confidence": 0.75,
"parent": "(root)",
"is_correction": False,
"superseded": False,
}
@given("a plan tree with parent and child node references connected by ULID")
def step_parent_child_tree(ctx: Context) -> None:
"""Parent-decoy pattern - root plus children."""
ctx.tree_nodes = [
{
"decision_id": VALID_ULID_A,
"type": "prompt_definition",
"sequence": 0,
"question": "Root question",
"children": [{"decision_id": VALID_ULID_B}, {"decision_id": VALID_ULID_C}],
"parent_decision_id": None,
},
{
"decision_id": VALID_ULID_B,
"type": "strategy_choice",
"sequence": 1,
"question": "Child A",
"children": [],
"parent_decision_id": VALID_ULID_A,
},
{
"decision_id": VALID_ULID_C,
"type": "strategy_choice",
"sequence": 2,
"question": "Child B",
"children": [],
"parent_decision_id": VALID_ULID_A,
},
]
@given("I have invalid plan tree data")
def step_invalid_tree_data(ctx: Context) -> None:
"""Create invalid plan tree node."""
ctx.tree_nodes = [
{"not_a_key": "value"}, # missing required fields entirely
]
# ────────────────────────────────────────────────────────────
# Assertions (shared / cross-scenario)
# ────────────────────────────────────────────────────────────
@then("it should be structurally valid")
def step_should_be_valid(ctx: Context) -> None:
"""Assert validation passed."""
result = getattr(ctx, "validation_result", {}) or {"valid": True}
assert result["valid"], f"Expected valid but got errors: {result.get('errors', [])}"
@then("it should be structurally invalid")
def step_should_be_invalid(ctx: Context) -> None:
"""Assert validation failed."""
result = getattr(ctx, "validation_result", {}) or {"valid": True}
assert not result["valid"], "Expected invalid but got valid"
@then("it should report no errors")
def step_no_errors(ctx: Context) -> None:
"""Assert no error messages."""
result = getattr(ctx, "validation_result", {}) or {}
errs = result.get("errors", [])
assert len(errs) == 0, f"Expected no errors but got: {errs}"
@then('it should report errors including "{text}"')
def step_errors_include(ctx: Context, text: str) -> None:
"""Assert at least one error contains the given substring."""
result = getattr(ctx, "validation_result", {}) or {}
errs = result.get("errors", [])
assert any(text in e for e in errs), f"'{text}' not found in errors: {errs}"
@then('error message must include "{text}"')
@then('error must include "{text}"')
def step_error_contains(ctx: Context, text: str) -> None:
"""Assert an error contains substring."""
result = getattr(ctx, "validation_result", {}) or {}
errs = result.get("errors", [])
assert any(text in e for e in errs), f"'{text}' not found in errors: {errs}"
@then('the first error message should identify "{prefix}" and the specific field issue')
def step_first_error_identifies(ctx: Context, prefix: str) -> None:
"""Assert first error contains prefix."""
result = getattr(ctx, "validation_result", {}) or {}
errs = result.get("errors", [])
assert len(errs) > 0, "Expected at least one error"
assert prefix in errs[0], f"First error '{errs[0]}' should contain '{prefix}'"
@then('it should raise a ValidationError with message containing "{text}"')
def step_raise_error_with_text(ctx: Context, text: str) -> None:
"""Assert dispatcher raised specific error."""
err = getattr(ctx, "dispatcher_error", None)
assert err is not None, "Expected a ValidationError"
assert isinstance(err, ValidationError), (
f"Expected ValidationError, got {type(err)}"
)
assert text in str(err), f"'{text}' not in error message: {err}"
@then("it should dispatch to the matching validator")
@then("return a valid result")
def step_dispatcher_valid(ctx: Context) -> None:
"""Assert dispatcher succeeded and returned valid."""
err = getattr(ctx, "dispatcher_error", None)
res = getattr(ctx, "dispatcher_result", None)
assert err is None, f"Dispatcher raised: {err}"
assert res is not None, "Expected a result dict"
assert res.get("valid"), f"Result not valid: {res}"
@then("validation should pass (structure matched, not exact characters)")
def step_structure_matched(ctx: Context) -> None:
"""Whitespace-tolerant structural validation passes."""
d = getattr(ctx, "decision_dict", {})
ctx.validation_result = validate_decision_dict(d) # type: ignore[attr-defined]
assert ctx.validation_result["valid"], (
f"Structural validation failed: {ctx.validation_result.get('errors', [])}"
) # type: ignore[attr-defined]
@then("parent-child relationships should be validly connected")
def step_relationships_valid(ctx: Context) -> None:
"""Parent-child nodes validate without errors."""
result = ctx.validation_result if hasattr(ctx, "validation_result") else {} # type: ignore[attr-defined]
assert result.get("valid", False), (
f"Relation validation failed: {result.get('errors', [])}"
)