litellm/tests/ocr_tests/test_ocr_matrix.py
devin-ai-integration[bot] 0e26edfdb9
test: move 81 legacy live tests in pass-through, spend, batches, audio, search, guardrails, image and ocr dirs offline (#45288)
* test: make legacy live tests in spend, batches, openai endpoints and audio dirs offline (partial)

* test: migrate wave-1b live tests offline (guardrails, images, ocr, search, openai endpoints)

* test: fix wave-1b review items, add responses/ocr integration tests and firecrawl unit test

* test: anthropic messages router/bedrock/openai-bridge unit tests for wave-1b nodes

* test: anthropic messages logging, prompt-caching and tool-search unit tests; drop migrated base nodes

* test: finish pass_through_unit_tests nodes, logging drain fix and mutations

* test: migrate anthropic passthrough tests to integration wire tests

* test: fix passthrough migration wire spend row lookup and wildcard config

* test: migrate hosted vllm and openai file passthrough tests offline

* test: move assemblyai and vertex passthrough nodes to in-process unit tests

* test: restore unlisted router node and fix logging worker drain in passthrough unit tests

* test: drop spend-row BUG skip and sharpen non-streaming skip reason for anthropic messages

* test: use public presidio alias after merge

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

* test: restore the batch and file unit tests the migration rewrote away

* test: restore full legacy intent in anthropic messages router unit tests

Drop the false BUG skip on non-streaming aanthropic_messages logging (success
callbacks do fire; the skipped body filtered on the wrong model), assert the
logged model_group, messages, cost and usage, cover streaming logging for both
Anthropic and Bedrock invoke, assert dict content blocks for Anthropic, Bedrock
invoke and the OpenAI bridge, add the Bedrock invoke leg of the router test,
fall back from a real 401, test system-prompt caching and streaming
message_start cache fields on converse and invoke, send the legacy tool-search
tools and beta header, remove the type: ignore and bare dict helper, and add
in-process native /anthropic passthrough spend logging tests

* test: fix passthrough migration wire tests and drop false native spend BUG skip

The native spend row test read rows by the shared master-key digest, so it
matched other tests' rows; read each row by its own message id instead and
assert tokens, total, spend, tags, provider, api_base and end_user on both the
non-streaming and streaming native routes. Merge the streaming test that never
checked spend, assert exact tags from litellm_metadata, stop rebinding a Final
in a loop, require cost > 0, and add the chat-completions bridge cost case the
legacy test covered

* test: harden the spend, OCR, image, search and guardrail migration replacements

The OCR spend tests now build fresh kwargs per case instead of mutating a
shared fixture, and every payload case asserts the exact logged spend. The
OCR wire test reads its spend row by request id and checks exact page
pricing. Image edit, Nova Canvas, DuckDuckGo, Firecrawl, Bedrock guardrail
and Presidio replacements now fake only the provider HTTP boundary (respx or
an in-process aiohttp server) and assert the outbound request, so the
DuckDuckGo limit, Azure base_model pricing and guardrail masking are proven
rather than assumed

* test: cover Exa and Perplexity search structure and max_results offline and retire the two base search methods

* test: drive batch and file replacements through the provider HTTP boundary and real logging callback

Replace monkeypatched litellm.afile_content and AsyncHTTPHandler doubles with respx routes,
read batch logging metadata from a registered success callback instead of get_logging_payload,
use the real managed-files hook for the GEN-2166 regression, assert outbound request bodies,
pin poller ownership explicitly in the migrated DB-sync tests, and require the scripted
upstream to be hit in the responses error-status wire tests

* test: assert file content download headers pass through the proxy

* test: point spend coverage references at the tests that replaced the retired spend job

* test: assert passthrough identity, spend and route dispatch from the code under test

The AssemblyAI non-admin test asserted metadata it wrote itself and leaked a
background poll to the real AssemblyAI host. It now drives assemblyai_proxy_route
with a real Request and waits for the success callback for its own transcript id.
The Vertex spend test matches its log by call id instead of taking the first event.
The OpenAI files wire test hit the native /{provider}/v1/files route; it now calls
/openai/files so the passthrough is what forwards the upload and delete.

* test: mock only the HTTP boundary in the migrated audio tests

Vertex TTS tests no longer replace _ensure_access_token or AsyncHTTPHandler.post;
the token comes from a mocked Google OAuth endpoint and the synthesize call from
respx. Speech tests assert the outbound body, the transcription cache test polls
for the cache write instead of relying on test ordering, and the model pass-through
test checks the multipart model field per model.

* test: wait on a logger event instead of polling the clock in anthropic messages unit tests

Recorders keep payloads in a rebound tuple and set an asyncio.Event; tests
await it with asyncio.wait_for instead of a sleep-and-deadline poll loop

* test: freeze module-level batch and file response fixtures as Final MappingProxyType

* test: fake the presidio analyzer with an in-memory aiohttp connector

The blocked-entity tests started an aiohttp TestServer, which binds a local
socket. They now hand the guardrail a ClientSession whose connector answers
/analyze and /anonymize in process, so no socket is opened and the outbound
analyze text and entities are still asserted

* test: type anthropic messages router test helpers with LiteLLM's Anthropic TypedDicts

Messages, cached system blocks and tool-search tools now use
AnthropicMessagesUserMessageParam, AnthropicMessagesTextParam,
AnthropicToolSearchToolRegex and AnthropicMessagesTool instead of bare
dict shapes; tools are converted to plain dicts only at the acreate call,
whose tools parameter is list[dict]

* test: type batch limiter helpers with TypedDicts and wait on the logging callback event instead of polling

* test: give the migrated OCR, image and presidio helpers precise types

OCR spend helpers take ReadOnly TypedDicts for kwargs and responses and use
LiteLLM's OCRResponse/OCRUsageInfo instead of local pydantic stand-ins; spend
metadata is validated with a TypeAdapter. The presidio fake uses LiteLLM's
PresidioAnalyzeRequest/ResponseItem types, and the image-edit logger validates
the logged payload instead of storing an untyped dict

* test: signal callback and cache events instead of polling

Recorders keep tuples and set an asyncio.Event, thread-safely, when the payload
for this test's transcript id or upstream URL arrives. The transcription cache
test waits on a Cache subclass that signals after async_add_cache. No clock
polling or sleeps remain in these tests.

* test: assert the batch limiter hook updates the caller's request in place

* test: tolerate model-list probes and read native passthrough rows by owned key

The router's OpenAI-compatible model-info refresh (litellm/router.py:10710)
sends GET /v1/models to configured openai api_bases, so the wire answers it
with an empty list and excludes it from the provider-call assertions. Native
/anthropic spend rows are now read by a per-request virtual key digest and
call_type, then the row's request_id is checked against the message id

* test: expect the OCR alias in the proxy response model

The proxy restamps every OpenAI-compatible response model to the name the
client requested (_override_openai_response_model), so /v1/ocr returns the
scenario alias. The upstream model is now checked on the drained request body
instead of inside the peer, where a failed assert never reached the test

---------

Co-authored-by: yuneng <yuneng@berri.ai>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
2026-10-08 02:38:12 -07:00

302 lines
13 KiB
Python

"""Live provider x auth x input coverage for ``litellm.ocr`` / ``litellm.aocr``.
Each ``Case`` is one hand-picked cell, not the full cross product: every provider
exercises each of its credential kinds in both ``explicit`` (kwargs) and ``env``
(monkeypatched environment) mode at least once, and every input kind a provider
accepts is exercised at least once. Sync and async are spread across the cells.
Every cell also checks the success callback saw the same response and cost.
"""
from __future__ import annotations
import asyncio
import base64
import io
import os
import re
from collections.abc import Callable, Mapping
from dataclasses import dataclass
from datetime import datetime
from pathlib import Path
from types import MappingProxyType
from typing import Final, Literal
import pytest
import litellm
from litellm.integrations.custom_logger import CustomLogger
from litellm.llms.base_llm.ocr.transformation import OCRResponse
Document = Mapping[str, object]
AuthMode = Literal["explicit", "env"]
CallStyle = Literal["sync", "async"]
@dataclass(frozen=True, slots=True)
class LoggedCall:
payload: Mapping[str, object]
response: object
class RecordingLogger(CustomLogger):
def __init__(self) -> None:
super().__init__() # pyright: ignore[reportUnknownMemberType] # CustomLogger.__init__ is untyped
self.calls: Final[list[LoggedCall]] = [] # mutable-ok: append-only sink the callback hooks write into
def _record(self, kwargs: Mapping[str, object], response_obj: object) -> None:
payload: Final = _string_keyed(kwargs.get("standard_logging_object"))
self.calls.append(LoggedCall(payload, response_obj))
def log_success_event(
self, kwargs: Mapping[str, object], response_obj: object, start_time: datetime, end_time: datetime
) -> None:
self._record(kwargs, response_obj)
async def async_log_success_event(
self, kwargs: Mapping[str, object], response_obj: object, start_time: datetime, end_time: datetime
) -> None:
self._record(kwargs, response_obj)
async def wait_for_call(self, timeout: float = 10.0) -> LoggedCall:
deadline: Final = asyncio.get_running_loop().time() + timeout
while not self.calls:
assert asyncio.get_running_loop().time() < deadline, "success callback never fired"
await asyncio.sleep(0.05)
assert len(self.calls) == 1, self.calls
return self.calls[0]
@pytest.fixture
def logger(monkeypatch: pytest.MonkeyPatch) -> RecordingLogger:
recorder: Final = RecordingLogger()
monkeypatch.setattr(litellm, "callbacks", [recorder])
for registry in ("success_callback", "_async_success_callback", "failure_callback", "_async_failure_callback"):
monkeypatch.setattr(litellm, registry, [])
return recorder
TESTS_DIR: Final = Path(__file__).resolve().parents[1]
PDF_PATH: Final = TESTS_DIR / "llm_translation" / "fixtures" / "dummy.pdf"
PNG_PATH: Final = TESTS_DIR / "image_gen_tests" / "test_image.png"
PINNED_CDN: Final = "https://cdn.jsdelivr.net/gh/BerriAI/litellm@d769e81c90d453240c61fc572cdb27fae06a89d0"
PDF_URL: Final = f"{PINNED_CDN}/tests/llm_translation/fixtures/dummy.pdf"
PNG_URL: Final = f"{PINNED_CDN}/tests/image_gen_tests/test_image.png"
PDF_TEXT: Final = "Test PDF File"
PNG_TEXT: Final = "LiteLLM"
class _NamedReader(io.BytesIO):
def __init__(self, path: Path) -> None:
super().__init__(path.read_bytes())
self.name: Final = path.name
def _data_uri(path: Path, mime: str) -> str:
return f"data:{mime};base64,{base64.b64encode(path.read_bytes()).decode()}"
@dataclass(frozen=True, slots=True)
class Input:
id: str
build: Callable[[], Document]
expected_text: str
PDF_BY_URL: Final = Input("pdf_url", lambda: {"type": "document_url", "document_url": PDF_URL}, PDF_TEXT)
PNG_BY_URL: Final = Input("image_url", lambda: {"type": "image_url", "image_url": PNG_URL}, PNG_TEXT)
PDF_DATA_URI: Final = Input(
"pdf_data_uri",
lambda: {"type": "document_url", "document_url": _data_uri(PDF_PATH, "application/pdf")},
PDF_TEXT,
)
PNG_DATA_URI: Final = Input(
"image_data_uri", lambda: {"type": "image_url", "image_url": _data_uri(PNG_PATH, "image/png")}, PNG_TEXT
)
PDF_AS_PATH: Final = Input("pdf_path", lambda: {"type": "file", "file": PDF_PATH}, PDF_TEXT)
PDF_AS_BYTES: Final = Input(
"pdf_bytes", lambda: {"type": "file", "file": PDF_PATH.read_bytes(), "mime_type": "application/pdf"}, PDF_TEXT
)
PNG_AS_BYTES: Final = Input(
"image_bytes", lambda: {"type": "file", "file": PNG_PATH.read_bytes(), "mime_type": "image/png"}, PNG_TEXT
)
PNG_AS_FILE_OBJECT: Final = Input(
"image_file_object", lambda: {"type": "file", "file": _NamedReader(PNG_PATH)}, PNG_TEXT
)
@dataclass(frozen=True, slots=True)
class Secret:
"""One credential value: the ``litellm.ocr`` kwarg it travels in, the env var litellm reads
when the kwarg is omitted, and the env var that holds the value in the test process."""
kwarg: str
env: str
source: str | None = None
@property
def source_env(self) -> str:
return self.source or self.env
@dataclass(frozen=True, slots=True)
class Credential:
id: str
secrets: tuple[Secret, ...]
@dataclass(frozen=True, slots=True)
class Provider:
id: str
model: str
credentials: tuple[Credential, ...]
params: Mapping[str, str] = MappingProxyType({})
@property
def env_vars(self) -> frozenset[str]:
return frozenset(secret.env for credential in self.credentials for secret in credential.secrets)
MISTRAL_KEY: Final = Credential("api_key", (Secret("api_key", "MISTRAL_API_KEY"),))
COHERE_KEY: Final = Credential("api_key", (Secret("api_key", "COHERE_API_KEY"),))
REDUCTO_KEY: Final = Credential("api_key", (Secret("api_key", "REDUCTO_API_KEY"),))
AZURE_ENTRA_SECRETS: Final = (
Secret("tenant_id", "AZURE_TENANT_ID", "AZURE_FOUNDRY_TENANT_ID"),
Secret("client_id", "AZURE_CLIENT_ID", "AZURE_FOUNDRY_ADMIN_CLIENT_ID"),
Secret("client_secret", "AZURE_CLIENT_SECRET", "AZURE_FOUNDRY_ADMIN_CLIENT_SECRET"),
)
AZURE_AI_BASE: Final = Secret("api_base", "AZURE_AI_API_BASE")
AZURE_AI_KEY: Final = Credential("api_key", (AZURE_AI_BASE, Secret("api_key", "AZURE_AI_API_KEY")))
AZURE_AI_ENTRA: Final = Credential("entra", (AZURE_AI_BASE, *AZURE_ENTRA_SECRETS))
AZURE_DI_BASE: Final = Secret("api_base", "AZURE_DOCUMENT_INTELLIGENCE_ENDPOINT")
AZURE_DI_KEY: Final = Credential("api_key", (AZURE_DI_BASE, Secret("api_key", "AZURE_DOCUMENT_INTELLIGENCE_API_KEY")))
AZURE_DI_ENTRA: Final = Credential("entra", (AZURE_DI_BASE, *AZURE_ENTRA_SECRETS))
VERTEX_SERVICE_ACCOUNT: Final = Credential(
"service_account",
(Secret("vertex_credentials", "VERTEXAI_CREDENTIALS"), Secret("vertex_project", "VERTEXAI_PROJECT")),
)
MISTRAL: Final = Provider("mistral", "mistral/mistral-ocr-latest", (MISTRAL_KEY,))
AZURE_AI_MISTRAL: Final = Provider(
"azure_ai_mistral", "azure_ai/mistral-document-ai-2512", (AZURE_AI_KEY, AZURE_AI_ENTRA)
)
AZURE_DOC_INTELLIGENCE: Final = Provider(
"azure_doc_intelligence", "azure_ai/doc-intelligence/prebuilt-layout", (AZURE_DI_KEY, AZURE_DI_ENTRA)
)
COHERE: Final = Provider("cohere", "cohere/parse-v5.0", (COHERE_KEY,))
REDUCTO_V3: Final = Provider("reducto_v3", "reducto/parse-v3", (REDUCTO_KEY,))
REDUCTO_LEGACY: Final = Provider("reducto_legacy", "reducto/parse-legacy", (REDUCTO_KEY,))
VERTEX_MISTRAL: Final = Provider(
"vertex_mistral",
"vertex_ai/mistral-ocr-2505",
(VERTEX_SERVICE_ACCOUNT,),
MappingProxyType({"vertex_location": "us-central1"}),
)
@dataclass(frozen=True, slots=True)
class Case:
provider: Provider
credential: Credential
auth: AuthMode
document: Input
call: CallStyle
@property
def id(self) -> str:
return f"{self.provider.id}-{self.credential.id}-{self.auth}-{self.document.id}-{self.call}"
def bind_credentials(self, monkeypatch: pytest.MonkeyPatch) -> Mapping[str, str]:
"""Clear every env var the provider could fall back to, then supply this case's values via kwargs or env."""
values: Final = {secret: os.environ.get(secret.source_env) for secret in self.credential.secrets}
missing: Final = tuple(secret.source_env for secret, value in values.items() if not value)
if missing:
pytest.skip(f"{', '.join(missing)} not set")
for env_var in self.provider.env_vars:
monkeypatch.delenv(env_var, raising=False)
if self.auth == "explicit":
return {secret.kwarg: value for secret, value in values.items() if value}
for secret, value in values.items():
monkeypatch.setenv(secret.env, value or "")
return {}
async def run(self, credentials: Mapping[str, str]) -> OCRResponse:
kwargs: Final = {**self.provider.params, **credentials}
document: Final = self.document.build()
response: Final = (
await litellm.aocr(model=self.provider.model, document=document, **kwargs) # pyright: ignore[reportUnknownMemberType] # @client erases the signature
if self.call == "async"
else litellm.ocr(model=self.provider.model, document=document, **kwargs)
)
assert isinstance(response, OCRResponse)
return response
CASES: Final = (
Case(MISTRAL, MISTRAL_KEY, "explicit", PDF_BY_URL, "sync"),
Case(MISTRAL, MISTRAL_KEY, "env", PNG_BY_URL, "async"),
Case(MISTRAL, MISTRAL_KEY, "explicit", PDF_AS_PATH, "sync"),
Case(MISTRAL, MISTRAL_KEY, "explicit", PNG_AS_BYTES, "async"),
Case(MISTRAL, MISTRAL_KEY, "explicit", PNG_AS_FILE_OBJECT, "sync"),
Case(AZURE_AI_MISTRAL, AZURE_AI_KEY, "explicit", PDF_BY_URL, "sync"),
Case(AZURE_AI_MISTRAL, AZURE_AI_KEY, "env", PNG_BY_URL, "async"),
Case(AZURE_AI_MISTRAL, AZURE_AI_ENTRA, "explicit", PDF_AS_PATH, "sync"),
Case(AZURE_AI_MISTRAL, AZURE_AI_ENTRA, "env", PDF_DATA_URI, "async"),
Case(AZURE_DOC_INTELLIGENCE, AZURE_DI_KEY, "explicit", PDF_BY_URL, "sync"),
Case(AZURE_DOC_INTELLIGENCE, AZURE_DI_KEY, "env", PNG_AS_BYTES, "async"),
Case(AZURE_DOC_INTELLIGENCE, AZURE_DI_ENTRA, "explicit", PNG_BY_URL, "async"),
Case(AZURE_DOC_INTELLIGENCE, AZURE_DI_ENTRA, "env", PDF_AS_PATH, "sync"),
Case(COHERE, COHERE_KEY, "explicit", PNG_BY_URL, "sync"),
Case(COHERE, COHERE_KEY, "env", PNG_DATA_URI, "async"),
Case(REDUCTO_V3, REDUCTO_KEY, "explicit", PDF_AS_PATH, "sync"),
Case(REDUCTO_V3, REDUCTO_KEY, "env", PNG_AS_BYTES, "async"),
Case(REDUCTO_V3, REDUCTO_KEY, "explicit", PDF_DATA_URI, "async"),
Case(REDUCTO_LEGACY, REDUCTO_KEY, "explicit", PDF_AS_BYTES, "sync"),
Case(VERTEX_MISTRAL, VERTEX_SERVICE_ACCOUNT, "explicit", PDF_BY_URL, "sync"),
Case(VERTEX_MISTRAL, VERTEX_SERVICE_ACCOUNT, "env", PNG_BY_URL, "async"),
)
def _response_cost(response: OCRResponse) -> float:
response_cost: Final[object] = response._hidden_params.get("response_cost") # pyright: ignore[reportPrivateUsage, reportUnknownMemberType, reportUnknownVariableType] # response_cost is only surfaced on _hidden_params
assert isinstance(response_cost, float) and response_cost > 0
return response_cost
def _assert_ocr_response(response: OCRResponse, model: str, expected_text: str) -> None:
assert response.object == "ocr"
assert response.model == model.split("/", 1)[1]
assert [page.index for page in response.pages] == list(range(len(response.pages)))
text: Final = re.sub(r"\s+", " ", " ".join(page.markdown for page in response.pages))
assert expected_text.lower() in text.lower(), text
assert response.usage_info is not None
assert response.usage_info.pages_processed == len(response.pages)
_response_cost(response)
def _string_keyed(value: object) -> Mapping[str, object]:
assert isinstance(value, Mapping), type(value)
items: Final = tuple(value.items()) # pyright: ignore[reportUnknownMemberType, reportUnknownVariableType, reportUnknownArgumentType] # narrowed from object
return MappingProxyType({str(key): value for key, value in items}) # pyright: ignore[reportUnknownVariableType, reportUnknownArgumentType] # narrowed from object
def _assert_logged(logged: LoggedCall, response: OCRResponse, model: str, logged_model: str, call: CallStyle) -> None:
assert isinstance(logged.response, OCRResponse)
assert logged.response.pages == response.pages
assert logged.payload["status"] == "success"
assert logged.payload["call_type"] == ("aocr" if call == "async" else "ocr")
assert logged.payload["custom_llm_provider"] == model.split("/", 1)[0]
assert logged.payload["model"] == logged_model
assert logged.payload["response_cost"] == _response_cost(response)
@pytest.mark.parametrize("case", CASES, ids=[case.id for case in CASES])
async def test_ocr(case: Case, monkeypatch: pytest.MonkeyPatch, logger: RecordingLogger) -> None:
credentials: Final = case.bind_credentials(monkeypatch)
response: Final = await case.run(credentials)
_assert_ocr_response(response, case.provider.model, case.document.expected_text)
_assert_logged(await logger.wait_for_call(), response, case.provider.model, response.model, case.call)