litellm/tests/e2e/codex/setups.py
ryan-crabbe-berri 47afa5759b test(e2e): drive the real Codex CLI through the gateway and add the command round trip row
Adds tests/e2e/codex: a harness that runs codex exec --json with a throwaway HOME and CODEX_HOME, a custom responses provider pointed at the gateway, the model list read from the gateway's /v1/models, the sandbox on and approvals off. Each test registers its setup's deployment via /model/new and calls it with a key scoped to it, both deleted on teardown. The first row checks that a value only a command can print comes back through the gateway on all five setups
2026-10-30 20:52:18 -07:00

84 lines
2.6 KiB
Python

"""The credentials are `os.environ/` references the gateway resolves, the same names the Claude Code matrix's
`test_config.yaml` uses, and Bedrock rides the gateway's default AWS identity."""
from __future__ import annotations
from dataclasses import dataclass
from typing import Final
import pytest
from cli_harness.rate_limiter import RateBucket
from e2e_metadata import Domain, Mode, Provider, Route, Subject, meta
from models import LiteLLMParamsBody
GPT_ON_BEDROCK_MANTLE: Final = "bedrock_mantle/openai.gpt-6.1-sol"
GPT_ON_BEDROCK_RUNTIME: Final = "bedrock/us.openai.gpt-6.1-sol"
GPT_ON_AZURE_OPENAI: Final = "azure/gpt-6.1-sol"
GPT_ON_OPENAI: Final = "openai/gpt-6.1-sol"
CLAUDE_ON_BEDROCK: Final = "bedrock/us.anthropic.claude-sonnet-5-5"
_BEDROCK_REGION: Final = "us-east-1"
@dataclass(frozen=True, slots=True)
class Deployment:
litellm_params: LiteLLMParamsBody
rate_bucket: RateBucket
@dataclass(frozen=True, slots=True)
class ModelSetup:
model: str
rate_bucket: RateBucket
def _drives(provider: Provider, model: str) -> pytest.MarkDecorator:
return meta(
Subject(
domain=Domain.LLM_TRANSLATION,
route=Route.RESPONSES,
providers=(provider,),
models=(model,),
mode=Mode.STREAM,
)
)
SETUPS: Final = (
pytest.param(
Deployment(
LiteLLMParamsBody(model=GPT_ON_BEDROCK_MANTLE, aws_region_name=_BEDROCK_REGION), RateBucket.BEDROCK_MANTLE
),
id="bedrock_mantle",
marks=_drives(Provider.BEDROCK_MANTLE, GPT_ON_BEDROCK_MANTLE),
),
pytest.param(
Deployment(
LiteLLMParamsBody(model=GPT_ON_BEDROCK_RUNTIME, aws_region_name=_BEDROCK_REGION),
RateBucket.BEDROCK_CONVERSE,
),
id="bedrock_runtime",
marks=_drives(Provider.BEDROCK, GPT_ON_BEDROCK_RUNTIME),
),
pytest.param(
Deployment(
LiteLLMParamsBody(
model=GPT_ON_AZURE_OPENAI, api_base="os.environ/AZURE_API_BASE", api_key="os.environ/AZURE_API_KEY"
),
RateBucket.AZURE_OPENAI,
),
id="azure_openai",
marks=_drives(Provider.AZURE, GPT_ON_AZURE_OPENAI),
),
pytest.param(
Deployment(LiteLLMParamsBody(model=GPT_ON_OPENAI, api_key="os.environ/OPENAI_API_KEY"), RateBucket.OPENAI),
id="openai",
marks=_drives(Provider.OPENAI, GPT_ON_OPENAI),
),
pytest.param(
Deployment(
LiteLLMParamsBody(model=CLAUDE_ON_BEDROCK, aws_region_name=_BEDROCK_REGION), RateBucket.BEDROCK_CONVERSE
),
id="claude_bedrock",
marks=_drives(Provider.BEDROCK, CLAUDE_ON_BEDROCK),
),
)