mirror of
https://github.com/BerriAI/litellm.git
synced 2026-09-26 01:12:21 +00:00
* test(integration): Bedrock batch files upload completions and responses records as user messages (Pylon #6882)
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(integration): client Anthropic OAuth token never replaces Bedrock SigV4 authorization (Pylon #6888)
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(integration): bridge /v1/messages and /v1/responses streams through empty-choices chunks (Pylon #6992)
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(integration): prepend azure content-filter metadata chunk to the messages stream (Pylon #6992)
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(integration): fireworks routers/ slug reaches the provider as accounts/fireworks/routers/<id> (Pylon #7030)
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(integration): bedrock hidden thinking tokens are not reported as text tokens (Pylon #7067)
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(integration): azure_ai FLUX.2-flex image generation targets the flex provider path with the BFL body (Pylon #7092)
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(integration): keep Databricks streaming usage and cache reads in the client stream and spend log (Pylon #7094)
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(integration): openai-compatible image edits forward provider-specific form fields to the backend (Pylon #7122)
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(integration): replayed intercepted web search turn reaches Bedrock as text through /v1/messages (Pylon #7181)
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(integration): streamed web search turn capped by max_agentic_loops ends the turn with snippets and ordered blocks (Pylon #7230)
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(integration): bedrock rerank keeps forwarded client headers out of the SigV4 signature (Pylon #7284)
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(integration): azure_ai rerank authenticates with an Entra token when no api key is set (Pylon #7303)
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(integration): perplexity stream with cost breakdown object completes and bills total_cost (Pylon #7331)
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(integration): azure_ai strips Anthropic message fields before the Foundry request (Pylon #7336)
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(integration): capped intercepted web search ends the turn without an internal tool_use block (Pylon #7378)
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(integration): Bedrock passthrough converse-stream keeps event-stream content-type (Pylon #7482)
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(integration): v1/messages success exposes v3 priority rate limit headers (Pylon #7532)
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(integration): config deployment dropped by a stale boot cost map is restored after reload (Pylon #7564)
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(integration): Bedrock Mantle project id reaches the provider as anthropic-workspace-id (Pylon #7583)
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(integration): prefixed Opus 4.8 reasoning_effort reaches Bedrock as adaptive thinking (Pylon #7586)
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(integration): dashscope chat forwards reasoning_effort to the provider (Pylon #7606)
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(integration): failing stream logging callback still releases the max_parallel_requests slot (Pylon #7608)
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(integration): gen 5 Claude Bedrock Invoke tool search sends the Bedrock beta field (Pylon #7642)
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(integration): databricks ai gateway api_base requests OAuth token from workspace origin (Pylon #7724)
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(integration): deepseek vision image content list reaches the provider unchanged (Pylon #7729)
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(integration): Bedrock Mantle context overflow surfaces as 400 prompt is too long (Pylon #7732)
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(integration): Codex history items reach Bedrock Mantle as supported Responses input types (Pylon #7783)
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(integration): chat over responses deployment returns finish_reason length when output tokens run out (Pylon #7784)
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(integration): bedrock_mantle rewrites Codex history items before the Responses wire (Pylon #7812)
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(integration): advisor sub-call on /v1/messages uses the configured advisor deployment (Pylon #7828)
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(integration): tencent thinking reaches the provider body instead of failing the request (Pylon #7834)
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(integration): xAI chat web search reaches /v1/responses with instructions and nested filters (Pylon #7835)
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(integration): send Bedrock Converse config blocks once at top level (Pylon #7839)
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(integration): bedrock converse sends gpt-5 reasoning_effort as reasoning.effort (Pylon #7850)
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(integration): bedrock cohere.embed-english-v3 embeddings accept encoding_format and dimensions (Pylon #7963)
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(integration): streamed chat completions emit SSE keepalive pings while the upstream is silent before its first token (Pylon #7987)
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* style(integration): format the TTFT keepalive regression test (Pylon #7987)
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(integration): openai chat drops tool_choice when the request has no tools (Pylon #8022)
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(integration): stream whose first chunk has no choices falls back and bills the fallback (Pylon #8006)
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* Revert "test(integration): Bedrock Mantle project id reaches the provider as anthropic-workspace-id (Pylon #7583)"
This reverts commit 864b65811f.
* test(integration): reconcile contracts manifest for bundled regression tests
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(integration): isolate proxy config writes in bundled regression tests
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(integration): address review feedback on keepalive, cost map reload and websearch order
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>
62 lines
2.8 KiB
Python
62 lines
2.8 KiB
Python
import json
|
|
import threading
|
|
import uuid
|
|
from collections.abc import Callable, Iterable, Iterator
|
|
from typing import Final
|
|
|
|
import pytest
|
|
from integration._support.client import Gateway
|
|
from integration._support.wire import Reply, Request, wire_server
|
|
from integration.streaming.test_stream_contracts import text_stream
|
|
|
|
KEEPALIVE_SECONDS: Final = 1
|
|
|
|
|
|
def _reply_after_first_ping(identity: str, first_ping_seen: threading.Event) -> Callable[[Request], Reply]:
|
|
def respond(_request: Request) -> Reply:
|
|
first_ping_seen.wait(timeout=10)
|
|
return Reply(content_type="text/event-stream", chunks=text_stream(identity))
|
|
|
|
return respond
|
|
|
|
|
|
def _frames_setting(first_ping_seen: threading.Event, lines: Iterable[str]) -> Iterator[str]:
|
|
for line in lines:
|
|
if line == ": ping":
|
|
first_ping_seen.set()
|
|
yield line
|
|
|
|
|
|
@pytest.mark.covers("streaming.keepalive.sse_pings_fill_silent_time_to_first_token")
|
|
def test_stream_emits_sse_ping_comments_before_the_first_data_frame_while_upstream_is_silent(
|
|
gateway: Gateway,
|
|
) -> None:
|
|
identity: Final = "stream-ttft-keepalive-" + uuid.uuid4().hex
|
|
first_ping_seen: Final = threading.Event()
|
|
with gateway.scenario() as scenario:
|
|
with wire_server(_reply_after_first_ping(identity, first_ping_seen)) as wire:
|
|
model: Final = scenario.model(api_base=wire.url + "/v1", keepalive_seconds=KEEPALIVE_SECONDS)
|
|
with gateway.client.stream(
|
|
"POST",
|
|
"/v1/chat/completions",
|
|
json={"model": model, "messages": [{"role": "user", "content": identity}], "stream": True},
|
|
headers={"Authorization": f"Bearer {gateway.key}"},
|
|
) as response:
|
|
assert response.status_code == 200, response.read().decode()
|
|
frames: Final = tuple(
|
|
_frames_setting(first_ping_seen, (line for line in response.iter_lines() if line))
|
|
)
|
|
first_data: Final = next(index for index, line in enumerate(frames) if line.startswith("data:"))
|
|
assert first_data >= 1, f"No keepalive reached the client before the first data frame: {frames}"
|
|
assert frames[:first_data] == (": ping",) * first_data, frames
|
|
assert frames[-1] == "data: [DONE]", frames
|
|
deltas: Final = tuple(json.loads(line.removeprefix("data: ")) for line in frames[first_data:-1])
|
|
assert (
|
|
"".join(choice["delta"].get("content", "") for chunk in deltas for choice in chunk["choices"])
|
|
== "Hello 雪 café"
|
|
), frames
|
|
requests: Final = wire.drain()
|
|
assert len(requests) == 1
|
|
outbound: Final = json.loads(requests[0].body)
|
|
assert outbound["model"] == "gpt-4o-mini" and outbound["stream"] is True, outbound
|
|
assert "keepalive_seconds" not in outbound, outbound
|