litellm/tests/test_litellm/interactions/test_openapi_compliance.py
Sameer Kankute 80c5a84871
chore: litellm oss staging (#30968)
* fix: correct amazon.titan-embed-text-v2 input price to $0.02/1M tokens (#29693)

* fix: correct amazon.titan-embed-text-v2 input price to $0.02/1M tokens

* test: scope local cost map env var with monkeypatch to avoid test pollution

* fix(sensitive_data_masker): fully mask secrets at or below the reveal threshold (#30764)

* fix(sensitive_data_masker): fully mask secrets at or below the reveal threshold

_mask_value did partial reveal by showing the first visible_prefix and last
visible_suffix characters, but for a value whose length was at or below
visible_prefix + visible_suffix (8 by default) it returned the value verbatim.
A value of exactly 8 chars fell through the length guard and computed
masked_length == 0, reconstructing the original string with no mask characters;
anything shorter hit the early return. Either way short credentials were emitted
in plaintext.

mask_dict routes real secrets through this path, so an 8-char-or-shorter redis
password, api key, or token could be written to logs and the UI unmasked. The
sibling helper mask_sensitive_keys already guards this case; _mask_value now does
the same by fully masking any value at or below the threshold.

* fix(sensitive_data_masker): add mask_short_values opt-out for truncation callers

Fully masking short values is the right default for secret masking, but
CooldownCache reuses the masker purely to truncate exception messages to the
first 50 characters, and it relies on short messages being returned readable.
Masking those blanked out short exception text and broke its tests.

Add a mask_short_values flag (default True, secure) and have CooldownCache pass
False so it keeps the truncation behavior, while every secret-masking caller
still gets short values fully masked.

* fix(mcp_debug): opt out of short-value masking to keep diagnostic token preview

MCPDebug uses the masker to preview auth tokens in debug headers and documents
that values of 10 chars or fewer are shown unchanged so token types stay
distinguishable. Pass mask_short_values=False so that diagnostic behavior is
preserved while secret maskers keep masking short values.

* fix(mcp_debug): mask short auth values in debug headers instead of echoing them

Earlier this masker opted out of short-value masking to keep a token preview, but
that echoes short authorization and token values verbatim in debug response
headers, which is the same leak this change is meant to close. Auth material
should never be emitted in full, so mask short values here too; the first/last
character preview still applies to longer tokens. Only CooldownCache keeps the
opt-out, since it truncates exception text rather than masking secrets.

* test(mcp_debug): assert masked short value preserves length

* refactor(fireworks_ai): remove deprecated audio transcriptions endpoint (#30917)

Fireworks AI deprecated audio inference on 2026-06-10
(https://docs.fireworks.ai/updates/changelog#audio-inference-and-image-generation-deprecation).
Live API testing confirms the endpoint is already non-functional: a valid
Fireworks API key receives HTTP 401 "Unauthorized" from
api.fireworks.ai/inference/v1/audio/transcriptions for every request,
regardless of payload. The audio-prod.api.fireworks.ai host referenced in
the test suite returns 401 for every path; the entire host is decommissioned.

Remove the dead FireworksAIAudioTranscriptionConfig class and every
reference to it across the codebase:

- Delete litellm/llms/fireworks_ai/audio_transcription/ directory (17-line
  config class that inherited from OpenAIWhisperAudioTranscriptionConfig)
- Remove the Fireworks branch from
  ProviderConfigManager.get_provider_audio_transcription_config() in
  litellm/utils.py; update the stale comment in
  get_optional_params_transcription that referenced fireworks ai
- Remove the FireworksAIAudioTranscriptionConfig entries from
  LLM_CONFIG_NAMES and _LLM_CONFIGS_IMPORT_MAP in
  litellm/_lazy_imports_registry.py
- Remove the TYPE_CHECKING re-export in litellm/__init__.py
- Remove the transcription branch in the fireworks_ai case of
  get_supported_openai_params() in
  litellm/litellm_core_utils/get_supported_openai_params.py
- Remove the whisper-v3 and whisper-v3-turbo entries from
  model_prices_and_context_window.json and
  litellm/model_prices_and_context_window_backup.json (both had
  mode: audio_transcription and zero-cost pricing)
- Remove the TestFireworksAIAudioTranscription test class and its
  imports from tests/llm_translation/test_fireworks_ai_translation.py

No other provider is affected. The openai_compatible_providers list,
FireworksAIMixin, and the OpenAI Whisper transcription handler all stay
because they are shared with other Fireworks endpoints and other
providers. The provider_endpoints_support.json registry already had
audio_transcriptions set to false for fireworks_ai.

* feat: add darkbloom provider (#30876)

* feat: add darkbloom provider

* fix: document darkbloom provider endpoints

* fix: address darkbloom review feedback

* fix: update darkbloom tool metadata

* fix: fail fast for non-Postgres database URLs (#30883)

* fix(proxy): fail fast on non-PostgreSQL DATABASE_URL instead of hanging on startup

LiteLLM's Prisma datasource is pinned to provider = 'postgresql', so a sqlite:// or mysql:// DATABASE_URL can never connect.

Today that surfaces as an opaque startup stall where the port never binds, and a separate 'DB not connected' 500 on /key/generate when no DATABASE_URL is set at all leaves operators guessing what to configure.

Validate the DATABASE_URL / DIRECT_URL scheme in run_server before any Prisma call and exit with an actionable message naming the unsupported scheme.

Also reword CommonProxyErrors.db_not_connected_error to tell the operator to set DATABASE_URL to a postgresql:// connection string.

Add regression tests covering postgres acceptance and sqlite/mysql/mssql rejection.

* fix: resolve CI failures and proxy DB URL typing issue

* fix(proxy): fail fast on non-PostgreSQL DATABASE_URLs with clear startup errors instead of hanging

* Validate DIRECT_URL alongside DATABASE_URL startup guards

* fix(bedrock): surface modeled HTTP status for mid-stream error events so 5xx is retryable (#24608) (#30946)

* fix(bedrock): surface modeled HTTP status for mid-stream error events (#24608)

* test(bedrock): mid-stream server errors trigger streaming fallback (#24608)

* style(bedrock): black-format stream-error helper (#24608)

* fix(mcp): re-land native tool preservation with typed annotations (#30645)

* fix(mcp): preserve native tools in semantic filter hook with typed annotations

* fix(mcp): tighten _is_mcp_tool Chat Completions shape check

* fix(sambanova): return embeddings supported params instead of dropping them (#30937)

* fix(router): send fallback metadata when streaming (#30914)

When a streaming request triggers a fallback, there was previously no way to
know it happened. This commit addresses this in a few ways:

1. The response now correctly populates the fallback headers
    (`x-litellm-attempted-fallbacks`) so callers know a fallback happened.
2. The correct model ID is passed in the streaming chunks.
3. A streaming chunk with the fallback error can be optionally sent back
    to the client (opt-in) by passing `include_fallback_errors: true` in
    the request.

The format of the fallback errors while streaming is intentionally OpenAI
compatible to not break existing libraries that parse these events. It was
tested with Vercel's AI SDK (ai-sdk.dev). It is also opt-in, so it is not
delieved unexpectedly to callers by default.

* fix(mistral): drop output-only reasoning fields from input messages (#30884)

LiteLLM attaches reasoning_content and thinking_blocks to assistant
responses. Replaying those assistant turns verbatim forwarded the fields
back to Mistral, whose input schema forbids unknown keys, so the whole
request failed with a 422 extra_forbidden and reasoning models became
unusable across multiple turns.

Strip both fields from assistant messages before the request is built, in
a spot that runs ahead of the image/file branch so it applies on every
path. Fixes #30835

Co-authored-by: Cursor <cursoragent@cursor.com>

* fix(perplexity): bill search queries at the per-request price, not 1/1000 of it (#30652)

* fix(perplexity): bill search queries at the per-request price, not 1/1000

The fallback cost calculator divided search_context_cost_per_query by
1000, but that field stores the per-request price in USD: sonar is
{low: 0.005, medium: 0.008, high: 0.012}, matching Perplexity's published
$5/$8/$12 per 1,000 requests expressed per request. The gemini cost
calculator reads the same field per request with no division (its
docstring calls it "the per-request cost").

The division understated search cost by 1000x on every Perplexity call
that falls back to manual calculation (i.e. when the API does not return
a pre-computed usage.cost). Use the value directly.

Update the tests that had encoded the /1000 factor in their expectations,
and drop an unused import flagged by ruff in the touched test file.

* test(perplexity): update integration test search-cost expectations to per-request

The integration tests still encoded the old /1000 search-cost factor, so
they failed once the fallback calculator was corrected to bill
search_context_cost_per_query per request. Update the four expected-cost
computations (and the high-volume dollar-value comments) to match.

* test(perplexity): drop unused mock imports flagged by ruff

* fix: include model_access_groups when expanding all-team-models in get_team_models (#30622)

* fix(fireworks_ai): return None for transcription in get_supported_openai_params

Fireworks AI deprecated audio inference on 2026-06-10; the endpoint is
decommissioned. Without an explicit transcription branch, requests with
request_type='transcription' fell through to the else and returned
FireworksAIConfig chat-completion params. Return None instead to signal
the provider does not support transcription.

* fix(proxy): gate include_fallback_errors behind expose_fallback_errors_to_caller setting

Without an operator gate, any authenticated caller could set include_fallback_errors=True,
trigger a fallback, and read raw upstream exception messages from the
x-litellm-fallback-errors header and the litellm-fallback-metadata SSE event.

Strip include_fallback_errors from request data in common_processing_pre_call_logic
when expose_fallback_errors_to_caller is not set, so the router never builds the
error list. Also gate _should_include_fallback_errors on the same setting as a
secondary check for the streaming SSE injection path.

* test(proxy): opt in to expose_fallback_errors_to_caller in streaming SSE test

The operator gate added in e7ff3e1 means include_fallback_errors is only
honoured when general_settings.expose_fallback_errors_to_caller is True.
Set that flag via monkeypatch in the test that exercises the emit path.

* test(prompt_templates): make test_convert_url hermetic instead of hitting picsum.photos

test_convert_url called convert_url_to_base64 against a live picsum.photos
URL and asserted nothing, so it added no real signal and broke CI whenever
the host was unreachable (it was returning 522 and blocking this branch).
Replace the live call with a mocked HTTP client and assert the produced
base64 data URL, so the conversion path is exercised deterministically with
no network dependency. This suite runs under VCR, which is why a transport
level mock (respx) does not reliably intercept; mocking the client object
itself is robust regardless.

* fix(interactions): drop role from Interaction response to match Google spec

Google removed the output-only role field from the Interaction schema (it
now lives only on Turn), so the live OpenAPI compliance canary started
failing with 'role' not in spec. Reconcile our generated types by removing
role from Interaction, CreateModelInteractionParams, CreateAgentInteractionParams
and from the LiteLLM InteractionsAPIResponse/InteractionsAPIStreamingResponse,
stop stamping role=model in the responses-to-interactions transformation, and
update the compliance and integration tests accordingly. Turn.role is kept
since the spec still defines it.

* fix: align all-team-models sentinel access

* fix(router): forward include_fallback_errors through multi-hop fallbacks

run_async_fallback received include_fallback_errors as an explicit named
parameter, so it was bound out of **kwargs and never reached the nested
async_function_with_fallbacks call. Multi-hop fallback chains (a fallback
group that itself fails over) therefore stopped collecting fallback errors
beyond the first hop when a caller opted in. Re-inject the flag into kwargs
before the nested call so inner hops keep accumulating errors, which
add_fallback_headers_to_response already merges across levels.

---------

Co-authored-by: Srivatsa Kamballa <skamb10@uic.edu>
Co-authored-by: Ahmad Shahzad <107808273+shzdehmd@users.noreply.github.com>
Co-authored-by: Jeremy Chapeau <113923302+jychp@users.noreply.github.com>
Co-authored-by: KRISH SONI <67964054+krishvsoni@users.noreply.github.com>
Co-authored-by: Kent <72616338+kingdoooo@users.noreply.github.com>
Co-authored-by: Ayush Shekhar <106994833+ayushh0110@users.noreply.github.com>
Co-authored-by: dav nguyxn <hoangson091104@gmail.com>
Co-authored-by: Tal Marian <tal.marian@island.io>
Co-authored-by: Hemant K <51333870+hemant1026@users.noreply.github.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
Co-authored-by: Yash Raj Pandey <55940078+devYRPauli@users.noreply.github.com>
Co-authored-by: Zang Peiyu <166481866+factnn@users.noreply.github.com>
Co-authored-by: mateo-berri <277851410+mateo-berri@users.noreply.github.com>
2026-06-23 07:31:44 -07:00

300 lines
11 KiB
Python

"""
OpenAPI compliance tests for Google Interactions API.
Validates that our SDK requests/responses match the OpenAPI spec at:
https://ai.google.dev/static/api/interactions.openapi.json
Run with: pytest tests/test_litellm/interactions/test_openapi_compliance.py -v
"""
import json
import os
from typing import Any, Dict
from unittest.mock import MagicMock, patch
import httpx
import pytest
from openapi_core import OpenAPI
OPENAPI_SPEC_URL = "https://ai.google.dev/static/api/interactions.openapi.json"
def _load_openapi_spec_dict() -> Dict[str, Any]:
"""
Load the OpenAPI spec JSON.
In CI or offline environments, network access may not be available.
In that case, gracefully skip these tests instead of erroring.
"""
try:
response = httpx.get(OPENAPI_SPEC_URL, timeout=5.0)
response.raise_for_status()
return response.json()
except Exception as e: # pragma: no cover - defensive, env-dependent
pytest.skip(
f"Skipping Google Interactions OpenAPI compliance tests - "
f"unable to load spec from {OPENAPI_SPEC_URL}: {e}"
)
@pytest.fixture(scope="module")
def spec_dict() -> Dict[str, Any]:
"""Load raw spec dict for manual validation."""
return _load_openapi_spec_dict()
@pytest.fixture(scope="module")
def openapi_spec(spec_dict: Dict[str, Any]) -> OpenAPI:
"""Load the OpenAPI spec as an OpenAPI object."""
return OpenAPI.from_dict(spec_dict)
class TestRequestCompliance:
"""Tests that our request bodies match the OpenAPI spec."""
def test_create_model_interaction_request_schema(self, spec_dict):
"""Verify CreateModelInteractionParams schema fields."""
schema = spec_dict["components"]["schemas"]["CreateModelInteractionParams"]
# Required fields per spec
assert "model" in schema["required"]
assert "input" in schema["required"]
# Check our supported optional fields exist in spec
our_optional_fields = [
"tools",
"system_instruction",
"generation_config",
"stream",
"store",
"background",
"response_modalities",
"response_format",
"response_mime_type",
"previous_interaction_id",
]
spec_properties = schema["properties"]
for field in our_optional_fields:
assert field in spec_properties, f"Field '{field}' not in OpenAPI spec"
print(f"✓ Field '{field}' exists in spec")
def test_input_types_match_spec(self, spec_dict):
"""Verify input field supports string, Content, Content[], Turn[]."""
schema = spec_dict["components"]["schemas"]["CreateModelInteractionParams"]
input_schema = schema["properties"]["input"]
# The input property may be inline oneOf or a $ref to InteractionsInput
if "$ref" in input_schema:
ref_name = input_schema["$ref"].split("/")[-1]
input_schema = spec_dict["components"]["schemas"][ref_name]
# Should be oneOf with multiple types
assert "oneOf" in input_schema
input_types = []
for option in input_schema["oneOf"]:
if option.get("type") == "string":
input_types.append("string")
elif option.get("type") == "array":
input_types.append("array")
elif "$ref" in option:
input_types.append(option["$ref"])
print(f"Input supports types: {input_types}")
assert "string" in input_types, "Input should support string"
assert "array" in input_types, "Input should support array"
def test_content_schema_uses_discriminator(self, spec_dict):
"""Verify Content uses type discriminator."""
content_schema = spec_dict["components"]["schemas"]["Content"]
assert "discriminator" in content_schema
assert content_schema["discriminator"]["propertyName"] == "type"
# Check TextContent is an option (via mapping if present, or via oneOf refs)
mapping = content_schema["discriminator"].get("mapping")
if mapping:
assert "text" in mapping
print(f"Content type discriminator mapping: {list(mapping.keys())}")
else:
# Discriminator without explicit mapping — verify via oneOf
one_of = content_schema.get("oneOf", [])
ref_names = [opt["$ref"].split("/")[-1] for opt in one_of if "$ref" in opt]
assert (
"TextContent" in ref_names
), f"TextContent not found in oneOf refs: {ref_names}"
print(f"Content type discriminator (no mapping), oneOf refs: {ref_names}")
def test_text_content_schema(self, spec_dict):
"""Verify TextContent schema."""
text_schema = spec_dict["components"]["schemas"]["TextContent"]
assert "type" in text_schema["required"]
assert "text" in text_schema["properties"]
assert text_schema["properties"]["type"].get("const") == "text"
print("✓ TextContent schema is correct")
def test_turn_schema(self, spec_dict):
"""Verify Turn schema for multi-turn conversations."""
turn_schema = spec_dict["components"]["schemas"]["Turn"]
assert "role" in turn_schema["properties"]
assert "content" in turn_schema["properties"]
# Content can be string or Content[]
content_prop = turn_schema["properties"]["content"]
assert "oneOf" in content_prop
print("✓ Turn schema supports role + content")
class TestResponseCompliance:
"""Tests that our response types match the OpenAPI spec."""
def test_interaction_response_fields(self, spec_dict):
"""Verify our InteractionsAPIResponse has correct fields."""
# The response is the dedicated `Interaction` schema. Google moved the
# output-only fields (notably the `steps` array, formerly `outputs`)
# off `CreateModelInteractionParams` and onto `Interaction`; the request
# schema no longer carries `steps`. Google later moved `role` off
# `Interaction` onto the per-turn `Turn` schema (asserted in
# test_turn_schema), so it is no longer a top-level output field here.
# Keep this aligned with the live spec.
schema = spec_dict["components"]["schemas"]["Interaction"]
# Output fields (readOnly). `role` was removed from the `Interaction`
# schema by Google; it now lives only on `Turn`.
output_fields = [
"id",
"status",
"created",
"updated",
"steps",
"usage",
]
for field in output_fields:
assert field in schema["properties"], f"Output field '{field}' not in spec"
print(f"✓ Output field '{field}' exists in spec")
def test_status_enum_values(self, spec_dict):
"""Verify status enum values match spec."""
# `status` is an output-only field; validate against the response schema.
schema = spec_dict["components"]["schemas"]["Interaction"]
status_prop = schema["properties"]["status"]
# Google Interactions API uses lowercase status values (updated Feb 2026).
# Keep this an exact match: this test intentionally breaks CI when
# Google changes the live spec — that breakage is how we get notified
# to review the change.
expected_statuses = [
"in_progress",
"requires_action",
"completed",
"failed",
"cancelled",
"incomplete",
"budget_exceeded",
]
assert status_prop["enum"] == expected_statuses
print(f"✓ Status enum values: {expected_statuses}")
def test_usage_schema(self, spec_dict):
"""Verify Usage schema fields."""
usage_schema = spec_dict["components"]["schemas"]["Usage"]
# Key usage fields
expected_fields = ["total_input_tokens", "total_output_tokens", "total_tokens"]
for field in expected_fields:
assert (
field in usage_schema["properties"]
), f"Usage field '{field}' not in spec"
print(f"✓ Usage field '{field}' exists")
class TestToolsCompliance:
"""Tests that our tool types match the OpenAPI spec."""
def test_tool_schema(self, spec_dict):
"""Verify Tool schema."""
tool_schema = spec_dict["components"]["schemas"]["Tool"]
# Tool should be oneOf multiple tool types
assert "oneOf" in tool_schema or "properties" in tool_schema
print(f"✓ Tool schema found")
def test_function_declaration_schema(self, spec_dict):
"""Verify FunctionDeclaration schema for function tools."""
if "FunctionDeclaration" in spec_dict["components"]["schemas"]:
func_schema = spec_dict["components"]["schemas"]["FunctionDeclaration"]
assert "name" in func_schema.get(
"properties", {}
) or "name" in func_schema.get("required", [])
print("✓ FunctionDeclaration schema found")
else:
print("⚠ FunctionDeclaration schema not found (may be nested)")
class TestEndpointCompliance:
"""Tests that our endpoints match the OpenAPI spec."""
def test_create_endpoint_exists(self, spec_dict):
"""Verify POST /interactions endpoint exists."""
paths = spec_dict["paths"]
# Find the create interactions endpoint
create_path = None
for path, methods in paths.items():
if "interactions" in path and "post" in methods:
create_path = path
break
assert create_path is not None, "POST /interactions endpoint not found"
print(f"✓ Create endpoint: POST {create_path}")
def test_get_endpoint_exists(self, spec_dict):
"""Verify GET /interactions/{id} endpoint exists."""
paths = spec_dict["paths"]
get_path = None
for path, methods in paths.items():
if "{id}" in path and "interactions" in path and "get" in methods:
get_path = path
break
assert get_path is not None, "GET /interactions/{id} endpoint not found"
print(f"✓ Get endpoint: GET {get_path}")
def test_delete_endpoint_exists(self, spec_dict):
"""Verify DELETE /interactions/{id} endpoint exists."""
paths = spec_dict["paths"]
delete_path = None
for path, methods in paths.items():
if "{id}" in path and "interactions" in path and "delete" in methods:
delete_path = path
break
assert delete_path is not None, "DELETE /interactions/{id} endpoint not found"
print(f"✓ Delete endpoint: DELETE {delete_path}")
if __name__ == "__main__":
# Quick manual test
import httpx
print("Loading OpenAPI spec...")
response = httpx.get(OPENAPI_SPEC_URL)
spec = response.json()
print(f"\nSpec version: {spec.get('openapi')}")
print(f"API title: {spec.get('info', {}).get('title')}")
print(f"\nEndpoints:")
for path, methods in spec.get("paths", {}).items():
for method in methods:
if method in ["get", "post", "delete", "put", "patch"]:
print(f" {method.upper()} {path}")
print(
f"\nSchemas: {list(spec.get('components', {}).get('schemas', {}).keys())[:10]}..."
)