mirror of
https://github.com/BerriAI/litellm.git
synced 2026-09-16 23:41:43 +00:00
Merge pull request #39050 from BerriAI/litellm_lit6314_guardrail_metadata_transfer
fix(guardrails): record not_run evaluation when scoping leaves nothing to scan
This commit is contained in:
commit
91588221cd
18 changed files with 538 additions and 52 deletions
|
|
@ -213,6 +213,17 @@ class OpenAIChatCompletionsHandler(BaseTranslation):
|
|||
task_mappings=tool_call_task_mappings,
|
||||
)
|
||||
|
||||
elif (
|
||||
not images_to_check
|
||||
and not guardrail_to_apply.records_own_guardrail_information
|
||||
and (not_run_reason := self._not_run_reason(messages)) is not None
|
||||
):
|
||||
guardrail_to_apply.add_standard_logging_guardrail_information_to_request_data(
|
||||
guardrail_json_response=not_run_reason,
|
||||
request_data=data,
|
||||
guardrail_status="not_run",
|
||||
)
|
||||
|
||||
verbose_proxy_logger.debug(
|
||||
"OpenAI Chat Completions: Processed input messages: %s",
|
||||
data.get("messages"),
|
||||
|
|
@ -220,6 +231,28 @@ class OpenAIChatCompletionsHandler(BaseTranslation):
|
|||
|
||||
return data
|
||||
|
||||
def _not_run_reason(
|
||||
self,
|
||||
messages: Sequence[dict[str, Any]], # mutable-ok: raw request messages consumed by _extract_inputs
|
||||
) -> str | None:
|
||||
"""Why nothing was scanned, or None when the only unscoped content is images, which this handler never scans."""
|
||||
texts: Final[list[str]] = [] # mutable-ok: filled by _extract_inputs
|
||||
images: Final[list[str]] = [] # mutable-ok: filled by _extract_inputs
|
||||
tool_calls: Final[list[ChatCompletionToolParam]] = [] # mutable-ok: filled by _extract_inputs
|
||||
for msg_idx, message in enumerate(messages):
|
||||
self._extract_inputs(
|
||||
message=message,
|
||||
msg_idx=msg_idx,
|
||||
texts_to_check=texts,
|
||||
images_to_check=images,
|
||||
tool_calls_to_check=tool_calls,
|
||||
text_task_mappings=[], # mutable-ok: required by _extract_inputs, unused here
|
||||
tool_call_task_mappings=[], # mutable-ok: required by _extract_inputs, unused here
|
||||
)
|
||||
if texts or tool_calls:
|
||||
return "no scannable content after message scoping"
|
||||
return None if images else "no scannable content"
|
||||
|
||||
def extract_request_tool_names(self, data: dict) -> list[str]:
|
||||
"""Extract tool names from OpenAI chat completions request (tools[].function.name, functions[].name)."""
|
||||
names: Final[list[str]] = []
|
||||
|
|
|
|||
|
|
@ -26,7 +26,7 @@ class ComplianceChecker:
|
|||
|
||||
def __init__(self, data: ComplianceCheckRequest):
|
||||
self.data = data
|
||||
self.guardrails = data.guardrail_information or []
|
||||
self.guardrails = tuple(g for g in data.guardrail_information or () if g.get("guardrail_status") != "not_run")
|
||||
|
||||
def _get_guardrails_by_mode(self, mode: str) -> list[dict]:
|
||||
"""
|
||||
|
|
|
|||
|
|
@ -42,7 +42,7 @@ if TYPE_CHECKING:
|
|||
router: Final = APIRouter()
|
||||
|
||||
_EMPTY_UNITS: Final[Mapping[str, int]] = MappingProxyType({})
|
||||
_ACTION_SEVERITY: Final[Mapping[str, int]] = MappingProxyType({"passed": 0, "flagged": 1, "blocked": 2})
|
||||
_ACTION_SEVERITY: Final[Mapping[str, int]] = MappingProxyType({"not_run": 0, "passed": 1, "flagged": 2, "blocked": 3})
|
||||
|
||||
_T = TypeVar("_T")
|
||||
|
||||
|
|
@ -325,7 +325,7 @@ class UsageDetailResponse(BaseModel):
|
|||
class UsageLogEntry(BaseModel):
|
||||
id: str
|
||||
timestamp: str
|
||||
action: str # blocked | passed | flagged
|
||||
action: str # blocked | passed | flagged | not_run
|
||||
score: float | None
|
||||
latency_ms: float | None
|
||||
model: str | None
|
||||
|
|
|
|||
|
|
@ -193,10 +193,12 @@ async def _upsert_rows_with_retry(
|
|||
|
||||
|
||||
def guardrail_status_to_action(status: str | None) -> str:
|
||||
"""Map StandardLogging guardrail_status to blocked/passed/flagged."""
|
||||
"""Map StandardLogging guardrail_status to blocked/passed/flagged/not_run."""
|
||||
if not status:
|
||||
return "passed"
|
||||
s: Final = (status or "").lower()
|
||||
if s == "not_run":
|
||||
return "not_run"
|
||||
if "intervened" in s or "block" in s:
|
||||
return "blocked"
|
||||
if "flagged" in s or "fail" in s or "error" in s:
|
||||
|
|
@ -354,37 +356,49 @@ async def process_spend_logs_guardrail_usage(
|
|||
"flagged_count": 0,
|
||||
}
|
||||
)
|
||||
index_rows: Final[list[dict[str, object]]] = []
|
||||
index_rows_by_key: Final[dict[tuple[str, str], dict[str, object]]] = {}
|
||||
|
||||
for payload in logs_to_process:
|
||||
request_id = payload.get("request_id")
|
||||
start_time = _parse_payload_start_time(payload)
|
||||
if not request_id or start_time is None:
|
||||
if not isinstance(request_id, str) or not request_id or start_time is None:
|
||||
continue
|
||||
date_key = _date_str(start_time)
|
||||
|
||||
for entry in _parse_guardrail_info_from_payload(payload):
|
||||
guardrail_id = entry.get("guardrail_id") or entry.get("guardrail_name") or ""
|
||||
if not guardrail_id:
|
||||
entries = _parse_guardrail_info_from_payload(payload)
|
||||
ids_by_name = MappingProxyType(
|
||||
{
|
||||
e["guardrail_name"]: e["guardrail_id"]
|
||||
for e in entries
|
||||
if e.get("guardrail_id") and isinstance(e.get("guardrail_name"), str) and e["guardrail_name"]
|
||||
}
|
||||
)
|
||||
for entry in entries:
|
||||
raw_name = entry.get("guardrail_name")
|
||||
guardrail_name = raw_name if isinstance(raw_name, str) else ""
|
||||
guardrail_id = entry.get("guardrail_id") or ids_by_name.get(guardrail_name) or guardrail_name
|
||||
if not isinstance(guardrail_id, str) or not guardrail_id:
|
||||
continue
|
||||
key = _MetricsKey(guardrail_id, date_key)
|
||||
daily_guardrail[key]["requests_evaluated"] += 1
|
||||
action = guardrail_status_to_action(entry.get("guardrail_status"))
|
||||
if action == "passed":
|
||||
daily_guardrail[key]["passed_count"] += 1
|
||||
elif action == "blocked":
|
||||
daily_guardrail[key]["blocked_count"] += 1
|
||||
else:
|
||||
daily_guardrail[key]["flagged_count"] += 1
|
||||
if action != "not_run":
|
||||
key = _MetricsKey(guardrail_id, date_key)
|
||||
daily_guardrail[key]["requests_evaluated"] += 1
|
||||
if action == "passed":
|
||||
daily_guardrail[key]["passed_count"] += 1
|
||||
elif action == "blocked":
|
||||
daily_guardrail[key]["blocked_count"] += 1
|
||||
else:
|
||||
daily_guardrail[key]["flagged_count"] += 1
|
||||
policy_id = entry.get("policy_id")
|
||||
index_rows.append(
|
||||
{
|
||||
prior = index_rows_by_key.get((request_id, guardrail_id))
|
||||
if prior is None or (prior["policy_id"] is None and policy_id is not None):
|
||||
index_rows_by_key[(request_id, guardrail_id)] = {
|
||||
"request_id": request_id,
|
||||
"guardrail_id": guardrail_id,
|
||||
"policy_id": policy_id,
|
||||
"start_time": start_time,
|
||||
}
|
||||
)
|
||||
index_rows: Final = tuple(index_rows_by_key.values())
|
||||
|
||||
async with pending.lock:
|
||||
pending_metrics: Final = pending.metrics
|
||||
|
|
|
|||
|
|
@ -1893,6 +1893,140 @@ class TestScanOnlyToolResults:
|
|||
assert data["messages"][4]["content"] == "and then?"
|
||||
|
||||
|
||||
class TestNoScannableContentRecordsNotRun:
|
||||
"""LIT-6314: a guardrail whose scoping leaves nothing to scan must still persist an evaluation record"""
|
||||
|
||||
def _system_only_data(self) -> dict:
|
||||
return {"messages": [{"role": "system", "content": "SYSTEM-PROMPT"}]}
|
||||
|
||||
def _recorded_entries(self, data: dict) -> list:
|
||||
metadata = data.get("metadata") or data.get("litellm_metadata") or {}
|
||||
return metadata.get("standard_logging_guardrail_information") or []
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_skipped_scan_records_not_run_entry(self):
|
||||
handler = OpenAIChatCompletionsHandler()
|
||||
guardrail = MockGuardrail(guardrail_name="skip-system-guardrail")
|
||||
guardrail.skip_system_message_in_guardrail = True
|
||||
data = self._system_only_data()
|
||||
|
||||
await handler.process_input_messages(data=data, guardrail_to_apply=guardrail)
|
||||
|
||||
assert guardrail.last_inputs is None, "nothing survived scoping, apply_guardrail must not run"
|
||||
entries = self._recorded_entries(data)
|
||||
assert len(entries) == 1
|
||||
assert entries[0]["guardrail_name"] == "skip-system-guardrail"
|
||||
assert entries[0]["guardrail_status"] == "not_run"
|
||||
assert entries[0]["guardrail_response"] == "no scannable content after message scoping"
|
||||
|
||||
@pytest.mark.asyncio
|
||||
@pytest.mark.parametrize("skip_system", [False, True])
|
||||
async def test_empty_content_does_not_blame_scoping(self, skip_system: bool):
|
||||
handler = OpenAIChatCompletionsHandler()
|
||||
guardrail = MockGuardrail(guardrail_name="unscoped-guardrail")
|
||||
guardrail.skip_system_message_in_guardrail = skip_system
|
||||
data = {"messages": [{"role": "user", "content": None}]}
|
||||
|
||||
await handler.process_input_messages(data=data, guardrail_to_apply=guardrail)
|
||||
|
||||
assert guardrail.last_inputs is None
|
||||
entries = self._recorded_entries(data)
|
||||
assert len(entries) == 1
|
||||
assert entries[0]["guardrail_status"] == "not_run"
|
||||
assert entries[0]["guardrail_response"] == "no scannable content"
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_self_recording_guardrail_is_left_alone(self):
|
||||
handler = OpenAIChatCompletionsHandler()
|
||||
guardrail = MockGuardrail(guardrail_name="self-recording-guardrail")
|
||||
guardrail.skip_system_message_in_guardrail = True
|
||||
guardrail.records_own_guardrail_information = True
|
||||
data = self._system_only_data()
|
||||
|
||||
await handler.process_input_messages(data=data, guardrail_to_apply=guardrail)
|
||||
|
||||
assert guardrail.last_inputs is None
|
||||
assert self._recorded_entries(data) == []
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_scannable_content_records_no_extra_entry(self):
|
||||
handler = OpenAIChatCompletionsHandler()
|
||||
guardrail = MockGuardrail(guardrail_name="normal-guardrail")
|
||||
data = {"messages": [{"role": "user", "content": "hello"}]}
|
||||
|
||||
await handler.process_input_messages(data=data, guardrail_to_apply=guardrail)
|
||||
|
||||
assert guardrail.last_inputs is not None
|
||||
assert all(e.get("guardrail_status") != "not_run" for e in self._recorded_entries(data))
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_image_only_content_is_not_reported_as_not_run(self):
|
||||
"""Images are only scanned alongside text, so an image-only request is a
|
||||
pre-existing scan gap, not a message-scoping skip, and must not be labelled one"""
|
||||
handler = OpenAIChatCompletionsHandler()
|
||||
guardrail = MockGuardrail(guardrail_name="image-guardrail")
|
||||
guardrail.skip_system_message_in_guardrail = True
|
||||
data = {
|
||||
"messages": [
|
||||
{"role": "system", "content": "SYSTEM-PROMPT"},
|
||||
{
|
||||
"role": "user",
|
||||
"content": [{"type": "image_url", "image_url": {"url": "https://example.com/cat.png"}}],
|
||||
},
|
||||
]
|
||||
}
|
||||
|
||||
await handler.process_input_messages(data=data, guardrail_to_apply=guardrail)
|
||||
|
||||
assert self._recorded_entries(data) == []
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_scoped_out_image_only_message_is_not_reported_as_not_run(self):
|
||||
"""An image in a skipped role must behave like any other image-only request"""
|
||||
handler = OpenAIChatCompletionsHandler()
|
||||
guardrail = MockGuardrail(guardrail_name="image-guardrail")
|
||||
guardrail.skip_system_message_in_guardrail = True
|
||||
data = {
|
||||
"messages": [
|
||||
{
|
||||
"role": "system",
|
||||
"content": [{"type": "image_url", "image_url": {"url": "https://example.com/cat.png"}}],
|
||||
},
|
||||
]
|
||||
}
|
||||
|
||||
await handler.process_input_messages(data=data, guardrail_to_apply=guardrail)
|
||||
|
||||
assert guardrail.last_inputs is None
|
||||
assert self._recorded_entries(data) == []
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_scoped_out_text_with_image_records_not_run(self):
|
||||
"""Scoping removed text too, so the skip is recorded even though an image sat beside it"""
|
||||
handler = OpenAIChatCompletionsHandler()
|
||||
guardrail = MockGuardrail(guardrail_name="image-guardrail")
|
||||
guardrail.skip_system_message_in_guardrail = True
|
||||
data = {
|
||||
"messages": [
|
||||
{
|
||||
"role": "system",
|
||||
"content": [
|
||||
{"type": "text", "text": "Describe this picture."},
|
||||
{"type": "image_url", "image_url": {"url": "https://example.com/cat.png"}},
|
||||
],
|
||||
},
|
||||
]
|
||||
}
|
||||
|
||||
await handler.process_input_messages(data=data, guardrail_to_apply=guardrail)
|
||||
|
||||
assert guardrail.last_inputs is None
|
||||
entries = self._recorded_entries(data)
|
||||
assert len(entries) == 1
|
||||
assert entries[0]["guardrail_status"] == "not_run"
|
||||
assert entries[0]["guardrail_response"] == "no scannable content after message scoping"
|
||||
|
||||
|
||||
class ToolDroppingTextGuardrail(CustomGuardrail):
|
||||
"""Answers one text per non-tool message it saw, the way a guardrail that
|
||||
filters tool rows out before scanning does, and hands back only texts."""
|
||||
|
|
|
|||
|
|
@ -682,3 +682,67 @@ async def test_detail_prev_trend_query_is_bounded():
|
|||
prev_wheres = [w for w in wheres if "lt" in w.get("date", {})]
|
||||
assert prev_wheres
|
||||
assert all("gte" in w["date"] for w in prev_wheres)
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_logs_report_not_run_entries_as_not_run_not_passed():
|
||||
"""LIT-6314: a guardrail that never scanned must not be reported as a pass in the drill-down."""
|
||||
index_row = MagicMock()
|
||||
index_row.request_id = "req-nr"
|
||||
index_row.guardrail_id = "db-1"
|
||||
index_row.start_time = datetime(2026, 4, 22)
|
||||
spend_log = MagicMock()
|
||||
spend_log.request_id = "req-nr"
|
||||
spend_log.model = "gpt-4o-mini"
|
||||
spend_log.startTime = datetime(2026, 4, 22)
|
||||
spend_log.metadata = {
|
||||
"guardrail_information": [
|
||||
{"guardrail_name": "db-1", "guardrail_status": "not_run", "duration": 0.0},
|
||||
]
|
||||
}
|
||||
prisma = _prisma(find_unique=_db_row(), index_find_many=[index_row])
|
||||
prisma.db.litellm_spendlogs.find_many = AsyncMock(return_value=[spend_log])
|
||||
handler = _config_handler()
|
||||
p1, p2 = _patches(prisma, handler)
|
||||
with p1, p2:
|
||||
resp = await guardrails_usage_logs(
|
||||
guardrail_id="db-1",
|
||||
policy_id=None,
|
||||
page=1,
|
||||
page_size=50,
|
||||
action=None,
|
||||
start_date=START,
|
||||
end_date=END,
|
||||
user_api_key_dict=ADMIN,
|
||||
)
|
||||
assert [log.action for log in resp.logs] == ["not_run"]
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_logs_action_passed_filter_excludes_not_run_entries():
|
||||
"""LIT-6314: filtering the drill-down for passes must not return unscanned requests."""
|
||||
index_row = MagicMock()
|
||||
index_row.request_id = "req-nr"
|
||||
index_row.guardrail_id = "db-1"
|
||||
index_row.start_time = datetime(2026, 4, 22)
|
||||
spend_log = MagicMock()
|
||||
spend_log.request_id = "req-nr"
|
||||
spend_log.model = "gpt-4o-mini"
|
||||
spend_log.startTime = datetime(2026, 4, 22)
|
||||
spend_log.metadata = {"guardrail_information": [{"guardrail_name": "db-1", "guardrail_status": "not_run"}]}
|
||||
prisma = _prisma(find_unique=_db_row(), index_find_many=[index_row])
|
||||
prisma.db.litellm_spendlogs.find_many = AsyncMock(return_value=[spend_log])
|
||||
handler = _config_handler()
|
||||
p1, p2 = _patches(prisma, handler)
|
||||
with p1, p2:
|
||||
resp = await guardrails_usage_logs(
|
||||
guardrail_id="db-1",
|
||||
policy_id=None,
|
||||
page=1,
|
||||
page_size=50,
|
||||
action="passed",
|
||||
start_date=START,
|
||||
end_date=END,
|
||||
user_api_key_dict=ADMIN,
|
||||
)
|
||||
assert resp.logs == []
|
||||
|
|
|
|||
|
|
@ -349,6 +349,95 @@ async def test_zero_and_non_int_usage_counters_are_skipped():
|
|||
}
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_not_run_entries_are_indexed_but_not_counted_as_evaluations():
|
||||
"""
|
||||
LIT-6314 records a not_run entry when message scoping leaves a guardrail
|
||||
nothing to scan. The guardrail never evaluated the request, so counting it
|
||||
as a passed evaluation would inflate daily pass rates; it still gets an
|
||||
index row so per-request drill-down finds the spend log.
|
||||
"""
|
||||
prisma = _prisma()
|
||||
logs = [_payload("r1", guardrail_status="not_run"), _payload("r2")]
|
||||
|
||||
await process_spend_logs_guardrail_usage(prisma, logs)
|
||||
|
||||
metrics_create = prisma.db.litellm_dailyguardrailmetrics.upsert.call_args.kwargs["data"]["create"]
|
||||
assert metrics_create["requests_evaluated"] == 1
|
||||
assert metrics_create["passed_count"] == 1
|
||||
index_rows = prisma.db.litellm_spendlogguardrailindex.create_many.call_args.kwargs["data"]
|
||||
assert sorted(row["request_id"] for row in index_rows) == ["r1", "r2"]
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_not_run_entry_shares_index_key_with_evaluated_sibling_of_same_name():
|
||||
"""
|
||||
The not_run entry from the shared base guardrail carries only guardrail_name,
|
||||
while the evaluated entry from the same guardrail (e.g. content filter on the
|
||||
output of a logging_only run) carries its guardrail_id. Keying them differently
|
||||
lists one request twice in the monitor, once as not_run and once as passed.
|
||||
"""
|
||||
prisma = _prisma()
|
||||
payload = _payload("r1")
|
||||
payload["metadata"] = json.dumps(
|
||||
{
|
||||
"guardrail_information": [
|
||||
{"guardrail_name": "cf", "guardrail_status": "not_run"},
|
||||
{
|
||||
"guardrail_name": "cf",
|
||||
"guardrail_id": "cf-uuid",
|
||||
"policy_id": "pol-1",
|
||||
"guardrail_status": "success",
|
||||
},
|
||||
{"guardrail_name": "other", "guardrail_status": "not_run"},
|
||||
]
|
||||
}
|
||||
)
|
||||
|
||||
await process_spend_logs_guardrail_usage(prisma, [payload])
|
||||
|
||||
index_rows = prisma.db.litellm_spendlogguardrailindex.create_many.call_args.kwargs["data"]
|
||||
assert sorted((row["guardrail_id"], row["policy_id"]) for row in index_rows) == [
|
||||
("cf-uuid", "pol-1"),
|
||||
("other", None),
|
||||
]
|
||||
metrics_create = prisma.db.litellm_dailyguardrailmetrics.upsert.call_args.kwargs["data"]["create"]
|
||||
assert (metrics_create["guardrail_id"], metrics_create["requests_evaluated"]) == ("cf-uuid", 1)
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_malformed_not_run_entry_does_not_drop_the_batch():
|
||||
prisma = _prisma()
|
||||
payload = _payload("r1")
|
||||
payload["metadata"] = json.dumps(
|
||||
{
|
||||
"guardrail_information": [
|
||||
{"guardrail_name": ["not", "a", "string"], "guardrail_status": "success"},
|
||||
{"guardrail_name": "", "guardrail_id": "cf-uuid", "guardrail_status": "success"},
|
||||
{"guardrail_status": "success"},
|
||||
]
|
||||
}
|
||||
)
|
||||
|
||||
await process_spend_logs_guardrail_usage(prisma, [payload])
|
||||
|
||||
index_rows = prisma.db.litellm_spendlogguardrailindex.create_many.call_args.kwargs["data"]
|
||||
assert [row["guardrail_id"] for row in index_rows] == ["cf-uuid"]
|
||||
metrics_create = prisma.db.litellm_dailyguardrailmetrics.upsert.call_args.kwargs["data"]["create"]
|
||||
assert (metrics_create["guardrail_id"], metrics_create["requests_evaluated"]) == ("cf-uuid", 1)
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_batch_of_only_not_run_entries_writes_no_metrics_row():
|
||||
prisma = _prisma()
|
||||
|
||||
await process_spend_logs_guardrail_usage(prisma, [_payload("r1", guardrail_status="not_run")])
|
||||
|
||||
assert prisma.db.litellm_dailyguardrailmetrics.upsert.call_count == 0
|
||||
index_rows = prisma.db.litellm_spendlogguardrailindex.create_many.call_args.kwargs["data"]
|
||||
assert [row["request_id"] for row in index_rows] == ["r1"]
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_payload_without_request_id_is_skipped_like_the_metrics_path():
|
||||
prisma = _prisma()
|
||||
|
|
|
|||
|
|
@ -2,10 +2,8 @@
|
|||
Unit tests for compliance check endpoints (EU AI Act and GDPR).
|
||||
"""
|
||||
|
||||
|
||||
import pytest
|
||||
|
||||
|
||||
from litellm.proxy.compliance_checks import ComplianceChecker
|
||||
from litellm.types.proxy.compliance_endpoints import ComplianceCheckRequest
|
||||
|
||||
|
|
@ -591,3 +589,37 @@ class TestModeMatching:
|
|||
continue
|
||||
if matched:
|
||||
assert mode in _guaranteed_modes(g_mode), (g_mode, mode)
|
||||
|
||||
|
||||
class TestNotRunGuardrails:
|
||||
"""LIT-6314 logs a not_run entry for a guardrail that message scoping left nothing to scan."""
|
||||
|
||||
def test_not_run_alone_never_evidences_compliance(self):
|
||||
data = ComplianceCheckRequest(
|
||||
request_id="req-601",
|
||||
user_id="user-1",
|
||||
model="gpt-4",
|
||||
timestamp="2026-02-17T00:00:00Z",
|
||||
guardrail_information=[
|
||||
{"guardrail_name": "pii_detection", "guardrail_status": "not_run", "guardrail_mode": "pre_call"},
|
||||
],
|
||||
)
|
||||
results = {c.check_name: c.passed for c in ComplianceChecker(data).check_eu_ai_act()}
|
||||
assert results["Guardrails applied"] is False
|
||||
assert results["Content screened before LLM"] is False
|
||||
assert results["Audit record complete"] is False
|
||||
|
||||
def test_not_run_sibling_does_not_fail_a_passing_request(self):
|
||||
data = ComplianceCheckRequest(
|
||||
request_id="req-602",
|
||||
user_id="user-1",
|
||||
model="gpt-4",
|
||||
timestamp="2026-02-17T00:00:00Z",
|
||||
pii_detected=True,
|
||||
guardrail_information=[
|
||||
{"guardrail_name": "pii_detection", "guardrail_status": "success", "guardrail_mode": "pre_call"},
|
||||
{"guardrail_name": "system_only", "guardrail_status": "not_run", "guardrail_mode": "pre_call"},
|
||||
],
|
||||
)
|
||||
results = {c.check_name: c.passed for c in ComplianceChecker(data).check_gdpr()}
|
||||
assert results["Sensitive data protected"] is True
|
||||
|
|
|
|||
|
|
@ -2322,7 +2322,7 @@
|
|||
},
|
||||
"src/components/view_logs/GuardrailViewer/GuardrailViewer.tsx": {
|
||||
"no-nested-ternary": {
|
||||
"count": 4
|
||||
"count": 3
|
||||
}
|
||||
},
|
||||
"src/components/view_logs/LogDetailsDrawer/LogDetailsDrawer.tsx": {
|
||||
|
|
|
|||
|
|
@ -57,7 +57,7 @@ export function GuardrailDetail({ guardrailId, onBack, accessToken = null, start
|
|||
return list.map((l: Record<string, unknown>) => ({
|
||||
id: l.id as string,
|
||||
timestamp: l.timestamp as string,
|
||||
action: l.action as "blocked" | "passed" | "flagged",
|
||||
action: l.action as LogEntry["action"],
|
||||
score: l.score as number | undefined,
|
||||
model: l.model as string | undefined,
|
||||
input_snippet: l.input_snippet as string | undefined,
|
||||
|
|
|
|||
|
|
@ -2,7 +2,7 @@ import userEvent from "@testing-library/user-event";
|
|||
import React from "react";
|
||||
import { beforeEach, describe, expect, it, vi } from "vitest";
|
||||
|
||||
import { renderWithProviders, screen, testQueryClient, waitFor } from "../../../tests/test-utils";
|
||||
import { renderWithProviders, screen, testQueryClient, waitFor, within } from "../../../tests/test-utils";
|
||||
import type { LogEntry as SpendLogEntry } from "@/components/view_logs/columns";
|
||||
import { LogViewer } from "./LogViewer";
|
||||
|
||||
|
|
@ -95,3 +95,16 @@ describe("GuardrailsMonitor LogViewer drawer", () => {
|
|||
});
|
||||
});
|
||||
});
|
||||
|
||||
describe("GuardrailsMonitor LogViewer not_run rows", () => {
|
||||
it("renders a not_run log as a neutral Not run badge instead of a pass or failure", () => {
|
||||
renderWithProviders(
|
||||
<LogViewer logs={[{ ...guardrailLog, action: "not_run", input_snippet: "system prompt only" }]} />,
|
||||
);
|
||||
|
||||
const row = screen.getByRole("button", { name: /system prompt only/ });
|
||||
expect(within(row).getByText("Not run")).toHaveClass("text-muted-foreground");
|
||||
expect(within(row).queryByText("Passed")).not.toBeInTheDocument();
|
||||
expect(within(row).queryByText("Blocked")).not.toBeInTheDocument();
|
||||
});
|
||||
});
|
||||
|
|
|
|||
|
|
@ -1,4 +1,4 @@
|
|||
import { CircleCheck, ChevronDown, TriangleAlert, X } from "lucide-react";
|
||||
import { CircleCheck, ChevronDown, MinusCircle, TriangleAlert, X } from "lucide-react";
|
||||
import { useQuery } from "@tanstack/react-query";
|
||||
import moment from "moment";
|
||||
import React, { useState } from "react";
|
||||
|
|
@ -10,9 +10,16 @@ import type { LogEntry as ViewLogsLogEntry } from "@/components/view_logs/column
|
|||
import type { LogEntry } from "./mockData";
|
||||
|
||||
const actionConfig: Record<
|
||||
"blocked" | "passed" | "flagged",
|
||||
"blocked" | "passed" | "flagged" | "not_run",
|
||||
{ icon: React.ElementType; color: string; bg: string; border: string; label: string }
|
||||
> = {
|
||||
not_run: {
|
||||
icon: MinusCircle,
|
||||
color: "text-muted-foreground",
|
||||
bg: "bg-muted",
|
||||
border: "border-border",
|
||||
label: "Not run",
|
||||
},
|
||||
blocked: {
|
||||
icon: X,
|
||||
color: "text-destructive",
|
||||
|
|
|
|||
|
|
@ -10,7 +10,7 @@ export interface LogEntry {
|
|||
input_snippet?: string;
|
||||
output_snippet?: string;
|
||||
score?: number;
|
||||
action: "blocked" | "passed" | "flagged";
|
||||
action: "blocked" | "passed" | "flagged" | "not_run";
|
||||
model?: string;
|
||||
reason?: string;
|
||||
latency_ms?: number;
|
||||
|
|
|
|||
|
|
@ -3,6 +3,7 @@ import { describe, it, expect, vi, beforeEach } from "vitest";
|
|||
import userEvent from "@testing-library/user-event";
|
||||
import { renderWithProviders, screen, waitFor } from "../../../../tests/test-utils";
|
||||
import {
|
||||
GuardrailInformation,
|
||||
makeBedrockResponse,
|
||||
makeEntity,
|
||||
makeGuardrailInformation,
|
||||
|
|
@ -14,6 +15,24 @@ import GuardrailViewer from "@/components/view_logs/GuardrailViewer/GuardrailVie
|
|||
const PresidioPath = "@/components/view_logs/GuardrailViewer/PresidioDetectedEntities";
|
||||
const BedrockPath = "@/components/view_logs/GuardrailViewer/BedrockGuardrailDetails";
|
||||
|
||||
const skippedPreCall: Partial<GuardrailInformation> = {
|
||||
guardrail_status: "not_run",
|
||||
guardrail_mode: "pre_call",
|
||||
guardrail_response: "no scannable content after message scoping",
|
||||
start_time: null,
|
||||
end_time: null,
|
||||
duration: null,
|
||||
};
|
||||
|
||||
const ranPostCall: Partial<GuardrailInformation> = {
|
||||
guardrail_name: "ran-rail",
|
||||
guardrail_status: "success",
|
||||
guardrail_mode: "post_call",
|
||||
start_time: 1_700_000_000,
|
||||
end_time: 1_700_000_000.25,
|
||||
duration: 0.25,
|
||||
};
|
||||
|
||||
describe("GuardrailViewer", () => {
|
||||
beforeEach(() => {
|
||||
vi.resetModules();
|
||||
|
|
@ -49,6 +68,36 @@ describe("GuardrailViewer", () => {
|
|||
expect(screen.queryByText("FAILED")).not.toBeInTheDocument();
|
||||
});
|
||||
|
||||
it("renders not_run as NOT RUN (muted) and keeps it out of the evaluated and passed counts", async () => {
|
||||
const user = userEvent.setup();
|
||||
const data = makeGuardrailInformation(skippedPreCall);
|
||||
renderWithProviders(<GuardrailViewer data={data} />);
|
||||
|
||||
expect(screen.getByText(/0 guardrails evaluated/)).toBeInTheDocument();
|
||||
expect(screen.getByText(/0 Passed/)).toHaveClass("text-muted-foreground");
|
||||
expect(screen.getByText(/1 Not run/)).toBeInTheDocument();
|
||||
const badge = screen.getByText("NOT RUN");
|
||||
expect(badge).toHaveClass("text-muted-foreground");
|
||||
expect(screen.queryByText("FAILED")).not.toBeInTheDocument();
|
||||
expect(screen.queryByText(/^T\+/)).not.toBeInTheDocument();
|
||||
|
||||
await user.click(screen.getByText("pii-rail"));
|
||||
expect(screen.getByText("no scannable content after message scoping")).toBeInTheDocument();
|
||||
});
|
||||
|
||||
it("anchors the lifecycle timeline on timed entries when an untimed not_run entry sorts first", () => {
|
||||
const skipped = makeGuardrailInformation({ ...skippedPreCall, guardrail_name: "skipped-rail" });
|
||||
const ran = makeGuardrailInformation(ranPostCall);
|
||||
renderWithProviders(<GuardrailViewer data={[skipped, ran]} />);
|
||||
|
||||
expect(screen.getByText(/1 guardrail evaluated/)).toBeInTheDocument();
|
||||
expect(screen.getByText("Request received").parentElement).toHaveTextContent("T+0ms");
|
||||
expect(screen.getByText(/Post-call guardrail: ran-rail/).parentElement).toHaveTextContent("T+250ms");
|
||||
expect(screen.getByText("Response returned").parentElement).toHaveTextContent("T+251ms");
|
||||
expect(screen.queryByText(/Pre-call guardrail: skipped-rail/)).not.toBeInTheDocument();
|
||||
expect(screen.getByText("—")).toBeInTheDocument();
|
||||
});
|
||||
|
||||
it("calculates and displays masked entity totals", async () => {
|
||||
const user = userEvent.setup();
|
||||
const data = makeGuardrailInformation({
|
||||
|
|
|
|||
|
|
@ -38,9 +38,9 @@ interface MatchDetail {
|
|||
}
|
||||
|
||||
interface GuardrailInformation {
|
||||
duration: number;
|
||||
end_time: number;
|
||||
start_time: number;
|
||||
duration: number | null;
|
||||
end_time: number | null;
|
||||
start_time: number | null;
|
||||
guardrail_mode: string | string[] | Record<string, unknown> | null;
|
||||
guardrail_name: string;
|
||||
guardrail_status: string;
|
||||
|
|
@ -121,7 +121,8 @@ const formatMode = (mode: GuardrailInformation["guardrail_mode"]): string => {
|
|||
return s.replace(/_/g, "-").toUpperCase();
|
||||
};
|
||||
|
||||
const formatDurationMs = (seconds: number): string => {
|
||||
const formatDurationMs = (seconds: number | null): string => {
|
||||
if (seconds == null) return "—";
|
||||
const ms = Math.round(seconds * 1000);
|
||||
return `${ms}ms`;
|
||||
};
|
||||
|
|
@ -133,12 +134,13 @@ const getTotalMasked = (entry: GuardrailInformation): number => {
|
|||
);
|
||||
};
|
||||
|
||||
type EntryOutcome = "passed" | "flagged" | "failed";
|
||||
type EntryOutcome = "passed" | "flagged" | "failed" | "not_run";
|
||||
|
||||
const getEntryOutcome = (entry: GuardrailInformation): EntryOutcome => {
|
||||
const status = (entry.guardrail_status ?? "").toLowerCase();
|
||||
if (status === "success") return "passed";
|
||||
if (status === "guardrail_flagged") return "flagged";
|
||||
if (status === "not_run") return "not_run";
|
||||
return "failed";
|
||||
};
|
||||
|
||||
|
|
@ -148,12 +150,21 @@ const OUTCOME_LABEL: Record<EntryOutcome, string> = {
|
|||
passed: "PASSED",
|
||||
flagged: "FLAGGED",
|
||||
failed: "FAILED",
|
||||
not_run: "NOT RUN",
|
||||
};
|
||||
|
||||
const OUTCOME_BADGE_CLASS: Record<EntryOutcome, string> = {
|
||||
passed: "bg-success/15 text-success border border-success/20",
|
||||
flagged: "bg-warning/15 text-warning border border-warning/20",
|
||||
failed: "bg-destructive/15 text-destructive border border-destructive/20",
|
||||
not_run: "bg-muted text-muted-foreground border border-border",
|
||||
};
|
||||
|
||||
const getHeaderOutcome = (counts: { evaluated: number; passed: number; flagged: number }): EntryOutcome => {
|
||||
if (counts.evaluated === 0) return "not_run";
|
||||
if (counts.passed === counts.evaluated) return "passed";
|
||||
if (counts.passed + counts.flagged === counts.evaluated) return "flagged";
|
||||
return "failed";
|
||||
};
|
||||
|
||||
const getRiskColor = (score: number): string => {
|
||||
|
|
@ -231,6 +242,7 @@ const FlagCircleIcon = ({ className }: { className?: string }) => (
|
|||
const OutcomeIcon = ({ outcome }: { outcome: EntryOutcome }) => {
|
||||
if (outcome === "passed") return <CheckCircleIcon />;
|
||||
if (outcome === "flagged") return <FlagCircleIcon />;
|
||||
if (outcome === "not_run") return <GrayDotIcon />;
|
||||
return <FailCircleIcon />;
|
||||
};
|
||||
|
||||
|
|
@ -353,8 +365,13 @@ interface TimelineEntry {
|
|||
outcome?: EntryOutcome;
|
||||
}
|
||||
|
||||
type TimedGuardrailInformation = GuardrailInformation & { start_time: number; end_time: number };
|
||||
|
||||
const isTimed = (e: GuardrailInformation): e is TimedGuardrailInformation =>
|
||||
typeof e.start_time === "number" && typeof e.end_time === "number";
|
||||
|
||||
const RequestLifecycle = ({ entries }: { entries: GuardrailInformation[] }) => {
|
||||
const sorted = useMemo(() => [...entries].sort((a, b) => (a.start_time ?? 0) - (b.start_time ?? 0)), [entries]);
|
||||
const sorted = useMemo(() => entries.filter(isTimed).sort((a, b) => a.start_time - b.start_time), [entries]);
|
||||
|
||||
const timeline = useMemo(() => {
|
||||
if (sorted.length === 0) return [];
|
||||
|
|
@ -658,6 +675,10 @@ const EvaluationCard = ({ entry }: { entry: GuardrailInformation }) => {
|
|||
</div>
|
||||
)}
|
||||
|
||||
{outcome === "not_run" && typeof guardrailResponse === "string" && (
|
||||
<p className="text-sm text-muted-foreground">{guardrailResponse}</p>
|
||||
)}
|
||||
|
||||
{/* Provider-specific details */}
|
||||
{guardrailProvider === "presidio" && presidioEntities.length > 0 && (
|
||||
<div className="mt-3">
|
||||
|
|
@ -696,12 +717,10 @@ const GuardrailViewer = ({ data, accessToken, logEntry }: GuardrailViewerProps)
|
|||
|
||||
const passedCount = guardrailEntries.filter(isEntrySuccess).length;
|
||||
const flaggedCount = guardrailEntries.filter((e) => getEntryOutcome(e) === "flagged").length;
|
||||
const allPassed = passedCount === guardrailEntries.length;
|
||||
const headerOutcome: EntryOutcome = allPassed
|
||||
? "passed"
|
||||
: passedCount + flaggedCount === guardrailEntries.length
|
||||
? "flagged"
|
||||
: "failed";
|
||||
const notRunCount = guardrailEntries.filter((e) => getEntryOutcome(e) === "not_run").length;
|
||||
const evaluatedCount = guardrailEntries.length - notRunCount;
|
||||
const allPassed = evaluatedCount > 0 && passedCount === evaluatedCount;
|
||||
const headerOutcome = getHeaderOutcome({ evaluated: evaluatedCount, passed: passedCount, flagged: flaggedCount });
|
||||
|
||||
const totalOverheadMs = useMemo(() => {
|
||||
return Math.round(guardrailEntries.reduce((sum, e) => sum + (e.duration ?? 0), 0) * 1000);
|
||||
|
|
@ -733,7 +752,7 @@ const GuardrailViewer = ({ data, accessToken, logEntry }: GuardrailViewerProps)
|
|||
<h3 className="text-lg font-semibold text-foreground">Guardrails & Policy Compliance</h3>
|
||||
<div className="flex items-center gap-2 mt-0.5">
|
||||
<span className="text-sm text-muted-foreground">
|
||||
{guardrailEntries.length} guardrail{guardrailEntries.length !== 1 ? "s" : ""} evaluated
|
||||
{evaluatedCount} guardrail{evaluatedCount !== 1 ? "s" : ""} evaluated
|
||||
</span>
|
||||
<span className="text-muted-foreground">|</span>
|
||||
<span
|
||||
|
|
@ -759,6 +778,13 @@ const GuardrailViewer = ({ data, accessToken, logEntry }: GuardrailViewerProps)
|
|||
{flaggedCount} Flagged
|
||||
</span>
|
||||
)}
|
||||
{notRunCount > 0 && (
|
||||
<span
|
||||
className={`inline-flex items-center px-2 py-0.5 rounded-full text-xs font-semibold ${OUTCOME_BADGE_CLASS.not_run}`}
|
||||
>
|
||||
{notRunCount} Not run
|
||||
</span>
|
||||
)}
|
||||
</div>
|
||||
</div>
|
||||
</div>
|
||||
|
|
|
|||
|
|
@ -20,13 +20,13 @@ export interface GuardrailEntity {
|
|||
}
|
||||
|
||||
export interface GuardrailInformation {
|
||||
duration: number;
|
||||
end_time: number;
|
||||
start_time: number;
|
||||
duration: number | null;
|
||||
end_time: number | null;
|
||||
start_time: number | null;
|
||||
guardrail_mode: string | string[] | Record<string, unknown> | null;
|
||||
guardrail_name: string;
|
||||
guardrail_status: string;
|
||||
guardrail_response: GuardrailEntity[] | BedrockGuardrailResponse;
|
||||
guardrail_response: GuardrailEntity[] | BedrockGuardrailResponse | string;
|
||||
masked_entity_count: Record<string, number>;
|
||||
guardrail_usage?: Record<string, number>;
|
||||
guardrail_cost?: number;
|
||||
|
|
|
|||
|
|
@ -635,4 +635,23 @@ describe("GuardrailJumpLink", () => {
|
|||
expect(pill).toHaveClass(expectedClass);
|
||||
expect(pill).toHaveTextContent(glyph);
|
||||
});
|
||||
|
||||
it.each([
|
||||
[["success", "not_run"], "text-success", "\u2713"],
|
||||
[["guardrail_intervened", "not_run"], "text-destructive", "\u2717"],
|
||||
])("ignores not_run when styling %j as %s", (statuses, expectedClass, glyph) => {
|
||||
render(<GuardrailJumpLink guardrailEntries={statuses.map((s) => ({ guardrail_status: s }))} />);
|
||||
|
||||
const pill = screen.getByText(/1 guardrail evaluated, 1 not run/);
|
||||
expect(pill).toHaveClass(expectedClass);
|
||||
expect(pill).toHaveTextContent(glyph);
|
||||
});
|
||||
|
||||
it("renders an all not_run request as neutral rather than passed", () => {
|
||||
render(<GuardrailJumpLink guardrailEntries={[{ guardrail_status: "not_run" }]} />);
|
||||
|
||||
const pill = screen.getByText(/0 guardrails evaluated, 1 not run/);
|
||||
expect(pill).toHaveClass("text-muted-foreground");
|
||||
expect(pill).not.toHaveTextContent("\u2713");
|
||||
});
|
||||
});
|
||||
|
|
|
|||
|
|
@ -700,20 +700,25 @@ const GUARDRAIL_JUMP_LINK_STYLE = {
|
|||
passed: { className: "border border-success/20 bg-success/10 text-success", glyph: "\u2713" },
|
||||
flagged: { className: "border border-warning/20 bg-warning/10 text-warning", glyph: "\u26A0" },
|
||||
failed: { className: "border border-destructive/20 bg-destructive/10 text-destructive", glyph: "\u2717" },
|
||||
not_run: { className: "border border-border bg-muted text-muted-foreground", glyph: "\u2013" },
|
||||
} as const;
|
||||
|
||||
const isPassedStatus = (status: unknown) => status === "pass" || status === "passed" || status === "success";
|
||||
const isFlaggedStatus = (status: unknown) => status === "flagged" || status === "guardrail_flagged";
|
||||
const isNotRunStatus = (status: unknown) => status === "not_run";
|
||||
|
||||
const guardrailJumpLinkOutcome = (statuses: unknown[]): keyof typeof GUARDRAIL_JUMP_LINK_STYLE => {
|
||||
if (statuses.every(isPassedStatus)) return "passed";
|
||||
if (statuses.every((s) => isPassedStatus(s) || isFlaggedStatus(s))) return "flagged";
|
||||
const guardrailJumpLinkOutcome = (evaluated: unknown[]): keyof typeof GUARDRAIL_JUMP_LINK_STYLE => {
|
||||
if (evaluated.length === 0) return "not_run";
|
||||
if (evaluated.every(isPassedStatus)) return "passed";
|
||||
if (evaluated.every((s) => isPassedStatus(s) || isFlaggedStatus(s))) return "flagged";
|
||||
return "failed";
|
||||
};
|
||||
|
||||
export function GuardrailJumpLink({ guardrailEntries }: { guardrailEntries: any[] }) {
|
||||
const outcome = guardrailJumpLinkOutcome(guardrailEntries.map((e) => e?.guardrail_status || e?.status));
|
||||
const { className, glyph } = GUARDRAIL_JUMP_LINK_STYLE[outcome];
|
||||
const statuses = guardrailEntries.map((e) => e?.guardrail_status || e?.status);
|
||||
const evaluated = statuses.filter((s) => !isNotRunStatus(s));
|
||||
const notRunCount = statuses.length - evaluated.length;
|
||||
const { className, glyph } = GUARDRAIL_JUMP_LINK_STYLE[guardrailJumpLinkOutcome(evaluated)];
|
||||
|
||||
const handleClick = () => {
|
||||
const el = document.getElementById("guardrail-section");
|
||||
|
|
@ -736,8 +741,9 @@ export function GuardrailJumpLink({ guardrailEntries }: { guardrailEntries: any[
|
|||
fontWeight: 500,
|
||||
}}
|
||||
>
|
||||
{glyph} {guardrailEntries.length} guardrail
|
||||
{guardrailEntries.length !== 1 ? "s" : ""} evaluated
|
||||
{glyph} {evaluated.length} guardrail
|
||||
{evaluated.length !== 1 ? "s" : ""} evaluated
|
||||
{notRunCount > 0 ? `, ${notRunCount} not run` : ""}
|
||||
<span style={{ fontSize: 11, opacity: 0.7 }}>{"\u2193"}</span>
|
||||
</div>
|
||||
</div>
|
||||
|
|
|
|||
Loading…
Add table
Reference in a new issue