mirror of
https://github.com/BerriAI/litellm.git
synced 2026-09-27 01:22:18 +00:00
Some checks are pending
LiteLLM Rust / rust-lint (push) Waiting to run
LiteLLM Rust / rust-test (push) Waiting to run
LiteLLM Rust / rust-wheel (push) Waiting to run
Terraform Modules / fmt, validate, test (aws) (push) Waiting to run
Terraform Modules / fmt, validate, test (gcp) (push) Waiting to run
Terraform Provider / gofmt, vet, build, test (push) Waiting to run
Terraform Provider / Provider endpoints vs proxy OpenAPI schema (push) Waiting to run
* test(integration): saving echoed model_info never persists cost map pricing as a deployment override (Pylon #6870)
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(integration): budget_duration change on /budget/update recomputes budget_reset_at (Pylon #6913)
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(integration): count_tokens on a budgeted key reserves no budget and a later completion still succeeds (Pylon #6966)
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(integration): /cost/estimate reports configured prices for a deployment absent from the cost map (Pylon #7014)
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(integration): cache the team member default budget in Redis as JSON (Pylon #7180)
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(integration): aggregated team daily activity reports whole-range team spend in one page (Pylon #7224)
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(integration): failed daily user rollup commits are retried so spend report and daily activity agree (Pylon #7268)
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(integration): CLI session token without org_id is charged to and capped by the team organization budget (Pylon #7291)
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(integration): gemini passthrough success releases its budget reservation from the spend counter (Pylon #7295)
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(integration): batch retrieval spend row sums reasoning tokens and counts output and error file failures (Pylon #7341)
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(integration): uncostable batches retire from the cost poll page so newer batches are costed (Pylon #7342)
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(integration): charge a team member added without any budget on its membership row (Pylon #7363)
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(integration): failed dispatched requests keep estimated input tokens in spend logs (Pylon #7519)
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(integration): bedrock passthrough converse guardrail ignores tool definitions (Pylon #7524)
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(integration): explicit null budget_duration on /team/new is not replaced by default_team_params (Pylon #7536)
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(integration): PATCH /organization/update with a null limit clears it (Pylon #7577)
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(integration): ultrafast service_tier bills ultrafast rates without leaking pricing fields upstream (Pylon #7587)
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(integration): keep the selected model in the response and spend log for an Azure Model Router alias (Pylon #7636)
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(integration): disconnected Bedrock /v1/messages stream still bills terminal usage (Pylon #7685)
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(integration): databricks cached prompt tokens bill at cache rates (Pylon #7738)
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(integration): completed batch spend row records reasoning tokens and error file failures (Pylon #7928)
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(integration): bill OCR annotation pages at annotation_cost_per_page (Pylon #7958)
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(integration): in-flight count tokens request reserves no key budget so a completion still reaches the provider (Pylon #7307)
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(integration): fail-closed key rejects known estimate over remaining budget before provider (Pylon #7691)
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(integration): streamed /v1/responses success callbacks keep provider response headers (Pylon #7775)
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* Revert "test(integration): fail-closed key rejects known estimate over remaining budget before provider (Pylon #7691)"
This reverts commit 910348be7a.
* 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 budget reset bounds and callback batch accumulation
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(integration): avoid rebinding the cache identity accumulator
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(integration): assert forwarded messages per cache identity call
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
* test(integration): make budget reset and team default tests deterministic
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>
50 lines
2.3 KiB
Python
50 lines
2.3 KiB
Python
import json
|
|
import uuid
|
|
from typing import Final
|
|
|
|
import pytest
|
|
from integration._support.client import Gateway, eventually
|
|
from integration._support.database import read_rows
|
|
from integration._support.wire import Reply, Request, wire_server
|
|
|
|
|
|
@pytest.mark.covers("spend.failed_dispatch.failure_row_records_estimated_input_tokens")
|
|
def test_provider_500_after_dispatch_records_estimated_prompt_tokens_on_failure_row(gateway: Gateway) -> None:
|
|
prompt: Final = "failed dispatch accounting " + uuid.uuid4().hex
|
|
system: Final = "You are a terse accounting assistant"
|
|
|
|
def provider(request: Request) -> Reply:
|
|
assert request.method == "POST" and request.target == "/v1/chat/completions"
|
|
body: Final = json.loads(request.body)
|
|
assert body["model"] == "gpt-4o-mini"
|
|
assert body["messages"] == [{"role": "system", "content": system}, {"role": "user", "content": prompt}]
|
|
return Reply(
|
|
status=500,
|
|
body=b'{"error":{"message":"synthetic provider outage","type":"server_error","code":"500"}}',
|
|
)
|
|
|
|
with wire_server(provider) as wire, gateway.scenario() as scenario:
|
|
model: Final = scenario.model(api_base=wire.url + "/v1", num_retries=0)
|
|
key: Final = scenario.key(models=[model])
|
|
failed: Final = gateway.request(
|
|
"POST",
|
|
"/v1/chat/completions",
|
|
{"model": model, "messages": [{"role": "system", "content": system}, {"role": "user", "content": prompt}]},
|
|
key=key,
|
|
)
|
|
assert failed.status_code == 500 and "synthetic provider outage" in failed.text, failed.text
|
|
call_id: Final = failed.headers["x-litellm-call-id"]
|
|
assert len(wire.drain()) == 1
|
|
rows: Final = eventually(
|
|
lambda: read_rows(
|
|
'SELECT status, spend, prompt_tokens, completion_tokens, total_tokens FROM "LiteLLM_SpendLogs" '
|
|
"WHERE request_id=%s",
|
|
(call_id,),
|
|
),
|
|
lambda values: len(values) == 1,
|
|
seconds=70,
|
|
)
|
|
row: Final = rows[0]
|
|
assert row["status"] == "failure" and float(row["spend"]) == 0 and row["completion_tokens"] == 0, row
|
|
assert row["prompt_tokens"] > 0, f"failure row lost the dispatched input tokens: {row}"
|
|
assert row["total_tokens"] == row["prompt_tokens"], row
|