litellm/tests/integration/management/test_guardrail_usage_config_guardrail.py
devin-ai-integration[bot] 514bc181d6
test(integration): regression tests for July cost tracking, budgeting and spend bugs (#42694)
* test(integration): streamed Bedrock Messages usage cost equals the recorded spend (Pylon #6667)

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* test(integration): echoed cost-map model info is not persisted as deployment overrides (Pylon #6844)

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* test(integration): reset sweep runs on one pod per tick while replicas share the lease (Pylon #6521)

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* test(integration): bedrock post-call guardrail scans streamed Anthropic Messages tool use without 500 (Pylon #6503)

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* test(integration): realtime cached audio tokens bill at the audio cache-read rate (Pylon #6704)

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* test(integration): legacy GET /spend/logs returns at most the 10000 most recent rows and flags truncation (Pylon #6752)

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* test(integration): itemize Responses API cache write tokens as cache creation cost (Pylon #6454)

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* test(integration): migration entrypoint deploys pending migrations before proxy startup (Pylon #6649)

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* test(integration): opted-in team keys stop at the owner's personal budget (Pylon #6641)

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* test(integration): guardrail information stays in the spend log when the caller sends metadata on /v1/messages (Pylon #6614)

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* test(integration): key model allowlist is enforced on Bedrock passthrough routes (Pylon #6419)

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* test(integration): JWT mapped key backfills a null user email from token claims (Pylon #6266)

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* test(integration): scheduled budget reset recovers from a transient DB transport failure (Pylon #6582)

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* test(integration): team key lists models granted through a team access group (Pylon #6044)

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* test(integration): JWT subject without team claim lands in the configured default team (Pylon #5895)

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* test(integration): end-user spend lands for a key without user_id when the auth cache is Redis (Pylon #6021)

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* test(integration): stale-low redis counter still blocks team member over budget (Pylon #5824)

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* test(integration): prompt-carrying spend rows are written in byte-bounded statements (Pylon #6083)

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* test(integration): logs UI session_total_spend sums every round of a multi-round session (Pylon #5928)

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* test(integration): config.yaml guardrails are served by the guardrail usage detail and overview (Pylon #5813)

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* test(integration): plain chat request skips the object permission lookup (Pylon #5965)

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* test(integration): register july accounting regression contracts

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* test(integration): isolate cost map override clear on owned proxy

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* test(integration): make reset lease claim and db relay refusal deterministic

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* test(integration): poll pg_stat settle, bound unbanned relay refusals, clear reset lease on teardown

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* test(integration): bound relay refusals so the budget sweep can reconnect

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

---------

Co-authored-by: kerry <kerry@berri.ai>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
2026-09-23 09:51:56 -07:00

77 lines
3.6 KiB
Python

import uuid
from pathlib import Path
from typing import Final
import pytest
import yaml
from pydantic import JsonValue
from tests.integration._support.client import Gateway, object_value, string_value
from tests.integration._support.process import owned_proxy
WINDOW: Final = {"start_date": "2026-01-01", "end_date": "2026-01-07"}
def listed_guardrail(gateway: Gateway, guardrail_name: str) -> dict[str, JsonValue]:
listed: Final = gateway.get("/v2/guardrails/list")["guardrails"]
assert isinstance(listed, list), listed
matches: Final = tuple(object_value(row) for row in listed if object_value(row)["guardrail_name"] == guardrail_name)
assert len(matches) == 1, f"{guardrail_name} appears {len(matches)} times in {listed}"
return matches[0]
@pytest.mark.covers("mgmt.guardrails.usage.config_yaml_guardrail_has_detail_and_overview_row")
def test_config_yaml_guardrail_is_served_by_usage_detail_and_overview(gateway: Gateway, tmp_path: Path) -> None:
guardrail_name: Final = "tool-permission-" + uuid.uuid4().hex
config: Final = yaml.safe_load(Path("tests/integration/proxy_config.yaml").read_text())
config["guardrails"] = [
{
"guardrail_name": guardrail_name,
"litellm_params": {
"guardrail": "tool_permission",
"mode": "post_call",
"default_on": False,
"rules": [{"id": "deny_delete", "tool_name": "(?i)^.*(delete|drop).*", "decision": "deny"}],
"default_action": "allow",
"on_disallowed_action": "block",
},
"guardrail_info": {"type": "Tool Permission", "description": "declared in config.yaml"},
}
]
path: Final = tmp_path / "guardrail.yaml"
path.write_text(yaml.safe_dump(config))
with owned_proxy(gateway, tmp_path, {}, config=path) as candidate:
guardrail_id: Final = string_value(listed_guardrail(candidate, guardrail_name)["guardrail_id"])
detail: Final = candidate.request("GET", f"/guardrails/usage/detail/{guardrail_id}", params=WINDOW)
assert detail.status_code == 200, detail.text
body: Final = object_value(detail.json())
assert {
"guardrail_id": body["guardrail_id"],
"guardrail_name": body["guardrail_name"],
"provider": body["provider"],
"type": body["type"],
"description": body["description"],
"requestsEvaluated": body["requestsEvaluated"],
"failRate": body["failRate"],
} == {
"guardrail_id": guardrail_id,
"guardrail_name": guardrail_name,
"provider": "tool_permission",
"type": "Tool Permission",
"description": "declared in config.yaml",
"requestsEvaluated": 0,
"failRate": 0.0,
}, detail.text
overview: Final = candidate.request("GET", "/guardrails/usage/overview", params=WINDOW)
assert overview.status_code == 200, overview.text
rows: Final = object_value(overview.json())["rows"]
assert isinstance(rows, list), overview.text
config_rows: Final = tuple(object_value(row) for row in rows if object_value(row)["id"] == guardrail_id)
assert len(config_rows) == 1, overview.text
assert (config_rows[0]["name"], config_rows[0]["provider"], config_rows[0]["requestsEvaluated"]) == (
guardrail_name,
"tool_permission",
0,
), overview.text
missing: Final = candidate.request("GET", f"/guardrails/usage/detail/{uuid.uuid4()}", params=WINDOW)
assert missing.status_code == 404, missing.text