57be5868f9* Studio: fix OpenAI- and Anthropic-compatible API spec compliance * Studio: fix API spec-compliance gaps on passthrough and streaming paths * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Studio: carry context_length_exceeded through the OpenAI passthrough error path * Studio: count tool-schema tokens in the Anthropic server-tool stream, and small stream-handling guards * Studio: guard message_delta usage against None and normalize developer role before proxying * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Studio: honor max_completion_tokens on the external-provider proxy path * Studio: forward llama-server cached_tokens into OpenAI prompt_tokens_details * Studio: sanitize messages in count_tokens to match the /v1/messages prompt * Studio: report max_tokens for truncated tool calls and guard null usage in metadata events * Studio: drop the request-id middleware (headers aren't declared in either spec) * Studio: include the required request_id field in Anthropic error bodies * Studio: honor max_completion_tokens on the audio (TTS / audio-input) paths * Studio: add the _effective_max_tokens helper and route all max-token sites through it * Studio: align API compatibility edge cases * Studio: clarify multi-choice chat support * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Studio: clarify logprobs chat support * Studio: opt the local chat UI into the streaming usage chunk so the context bar and tok/s repopulate * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Studio: forward seed to llama-server, and fix Anthropic server-tool stop_reason, tool_result id correlation, and parallel-tool execution cap * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Studio: align OpenAI chat completion spec edge cases * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Studio: align backend API compatibility tests * Studio: honor tool caps and internal stream usage * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Studio: coerce nullable stream usage counts * Studio: preserve system prompts with developer messages --------- Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> Co-authored-by: wasimysaid <wasimysdev@gmail.com>
86 lines
2.7 KiB
Python
86 lines
2.7 KiB
Python
# SPDX-License-Identifier: AGPL-3.0-only
|
|
# Copyright 2026-present the Unsloth AI Inc. team. All rights reserved.
|
|
|
|
"""Regression tests for GGUF non-streaming chat completion usage."""
|
|
|
|
from fastapi import FastAPI
|
|
from fastapi.testclient import TestClient
|
|
|
|
from auth.authentication import get_current_subject
|
|
import routes.inference as inference_route
|
|
|
|
|
|
class _GgufBackend:
|
|
is_loaded = True
|
|
model_identifier = "test/model.gguf"
|
|
_is_audio = False
|
|
is_vision = False
|
|
supports_tools = False
|
|
|
|
def __init__(self, usage):
|
|
self.usage = usage
|
|
|
|
def generate_chat_completion(self, **kwargs):
|
|
yield "answer"
|
|
yield {
|
|
"type": "metadata",
|
|
"usage": self.usage,
|
|
"timings": {"prompt_n": 23, "predicted_n": 1283},
|
|
}
|
|
|
|
|
|
def _request_completion(monkeypatch, usage):
|
|
monkeypatch.setattr(inference_route, "get_llama_cpp_backend", lambda: _GgufBackend(usage))
|
|
monkeypatch.setattr(inference_route, "_effective_enable_tools", lambda payload: False)
|
|
|
|
app = FastAPI()
|
|
app.include_router(inference_route.router)
|
|
app.dependency_overrides[get_current_subject] = lambda: "test-user"
|
|
|
|
return TestClient(app).post(
|
|
"/chat/completions",
|
|
json = {
|
|
"messages": [{"role": "user", "content": "Why is the sky blue?"}],
|
|
"stream": False,
|
|
},
|
|
)
|
|
|
|
|
|
def test_non_streaming_gguf_completion_includes_generated_usage(monkeypatch):
|
|
response = _request_completion(
|
|
monkeypatch,
|
|
{"prompt_tokens": 23, "completion_tokens": 1283, "total_tokens": 1306},
|
|
)
|
|
|
|
assert response.status_code == 200
|
|
usage = response.json()["usage"]
|
|
assert usage["prompt_tokens"] == 23
|
|
assert usage["completion_tokens"] == 1283
|
|
assert usage["total_tokens"] == 1306
|
|
assert usage["prompt_tokens_details"] == {"cached_tokens": 0, "audio_tokens": 0}
|
|
assert usage["completion_tokens_details"] == {
|
|
"reasoning_tokens": 0,
|
|
"audio_tokens": 0,
|
|
"accepted_prediction_tokens": 0,
|
|
"rejected_prediction_tokens": 0,
|
|
}
|
|
|
|
|
|
def test_non_streaming_gguf_completion_defaults_nullable_usage_to_zero(monkeypatch):
|
|
response = _request_completion(
|
|
monkeypatch,
|
|
{"prompt_tokens": None, "completion_tokens": 1283, "total_tokens": None},
|
|
)
|
|
|
|
assert response.status_code == 200
|
|
usage = response.json()["usage"]
|
|
assert usage["prompt_tokens"] == 0
|
|
assert usage["completion_tokens"] == 1283
|
|
assert usage["total_tokens"] == 1283
|
|
assert usage["prompt_tokens_details"] == {"cached_tokens": 0, "audio_tokens": 0}
|
|
assert usage["completion_tokens_details"] == {
|
|
"reasoning_tokens": 0,
|
|
"audio_tokens": 0,
|
|
"accepted_prediction_tokens": 0,
|
|
"rejected_prediction_tokens": 0,
|
|
}
|