Assertions

await session.assert_that(Expect.content.contains("Example"), response=resp)

resp = await agent.generate_str("Fetch https://example.com")
await session.assert_that(Expect.content.contains("Example Domain"), response=resp)
await session.assert_that(Expect.content.not_contains("Stack trace"), response=resp)
await session.assert_that(Expect.content.regex(r"Example\\s+Domain"), response=resp)

# Verify a fetch occurred with expected output pattern in first content block
await session.assert_that(
  Expect.tools.output_matches(
    tool_name="fetch",
    expected_output=r"use.*examples",
    match_type="regex",
    case_sensitive=False,
    field_path="content[0].text",
  ),
  name="fetch_output_match",
)

# Verify sequence and counts
await session.assert_that(Expect.tools.sequence(["fetch"], allow_other_calls=True))
await session.assert_that(Expect.tools.count("fetch", 1))
await session.assert_that(Expect.tools.success_rate(1.0, tool_name="fetch"))

await session.assert_that(Expect.performance.max_iterations(3))
await session.assert_that(Expect.performance.response_time_under(10_000))

# Single-criterion rubric
judge = Expect.judge.llm(
  rubric="Response should identify JSON format and summarize main points",
  min_score=0.8,
  include_input=True,
)
await session.assert_that(judge, response=resp, name="quality_check")

# Multi-criteria
from mcp_eval.evaluators import EvaluationCriterion
criteria = [
  EvaluationCriterion(name="accuracy", description="Factual correctness", weight=2.0, min_score=0.8),
  EvaluationCriterion(name="completeness", description="Covers key points", weight=1.5, min_score=0.7),
]
judge_mc = Expect.judge.multi_criteria(criteria, aggregate_method="weighted", use_cot=True)
await session.assert_that(judge_mc, response=resp, name="multi_criteria")

# Enforce exact order and single use of tools
await session.assert_that(
  Expect.path.efficiency(
    expected_tool_sequence=["validate", "process", "save"],
    tool_usage_limits={"validate": 1, "process": 1, "save": 1},
    allow_extra_steps=0,
    penalize_backtracking=True,
  ),
  name="golden_path",
)

# Allow a retry of a fragile step without failing the whole path
await session.assert_that(
  Expect.path.efficiency(
    expected_tool_sequence=["fetch", "parse"],
    tool_usage_limits={"fetch": 2, "parse": 1},
    allow_extra_steps=1,
    penalize_repeated_tools=False,
  ),
  name="robust_path",
)