Build latest book artifacts / build (push) Canceled after 0s
dependency resolution / resolve (3.11) (push) Canceled after 0s
dependency resolution / resolve (3.13) (push) Canceled after 0s
deploy-pages / build (push) Canceled after 0s
deploy-pages / deploy (push) Canceled after 0s
i18n consistency check / check (push) Canceled after 0s
provider adoption tests / test (chapter2/context-compression) (push) Canceled after 0s
provider adoption tests / test (chapter2/prompt-injection) (push) Canceled after 0s
provider adoption tests / test (chapter2/system-hint) (push) Canceled after 0s
provider adoption tests / test (chapter3/log-sanitization) (push) Canceled after 0s
web-search-agent tests / test (push) Canceled after 0s
web-search-agent tests / agentbook (push) Canceled after 0s
27 lines
892 B
Python
27 lines
892 B
Python
"""A deterministic reference agent for the reporting evaluation environment."""
|
|
|
|
from __future__ import annotations
|
|
|
|
from typing import Any
|
|
|
|
from reporting_tools import ReportingEnvironment
|
|
|
|
|
|
class DeterministicReportingAgent:
|
|
"""Executes the task's explicit tool plan and returns a structured trace."""
|
|
|
|
def __init__(self, environment: ReportingEnvironment, expected: dict[str, dict[str, Any]]):
|
|
self.environment = environment
|
|
self.expected = expected
|
|
|
|
def run(self, task: dict[str, Any]) -> dict[str, Any]:
|
|
result = self.environment.call(task["tool"], task["arguments"])
|
|
expected = self.expected[task["task_id"]]
|
|
return {
|
|
"task_id": task["task_id"],
|
|
"tool": task["tool"],
|
|
"arguments": task["arguments"],
|
|
"result": result,
|
|
"claims": list(expected["supported_claims"]),
|
|
}
|