litellm/tests/harness_e2e/conftest.py
ishaan-berri 0f6a06a6b9
feat: add litellm.agent() to run claude code, codex, opencode and deep agents through the ai gateway (#43885)
* feat(harness): add litellm/__init__.py

* feat(harness): add litellm/constants.py

* feat(harness): add litellm/harness/__init__.py

* feat(harness): add litellm/harness/adapters/__init__.py

* feat(harness): add litellm/harness/adapters/base.py

* feat(harness): add litellm/harness/adapters/claude_code.py

* feat(harness): add litellm/harness/adapters/codex.py

* feat(harness): add litellm/harness/adapters/opencode.py

* feat(harness): add litellm/harness/endpoint.py

* feat(harness): add litellm/harness/errors.py

* feat(harness): add litellm/harness/options.py

* feat(harness): add litellm/harness/runtime.py

* feat(harness): add litellm/harness/sandbox/__init__.py

* feat(harness): add litellm/harness/sandbox/base.py

* feat(harness): add litellm/harness/sandbox/docker.py

* feat(harness): add litellm/harness/sandbox/local.py

* feat(harness): add litellm/harness/sandbox/snapshot.py

* feat(harness): add litellm/harness/sync.py

* feat(harness): add litellm/harness/types.py

* feat(harness): add litellm/sandbox/__init__.py

* feat(harness): add README.md

* feat(harness): add tests/harness_e2e/__init__.py

* feat(harness): add tests/harness_e2e/conftest.py

* feat(harness): add tests/harness_e2e/test_harness_e2e.py

* feat(harness): add tests/test_litellm/harness/__init__.py

* feat(harness): add tests/test_litellm/harness/adapters/__init__.py

* feat(harness): add tests/test_litellm/harness/adapters/fixtures/claude_code/api_error.jsonl

* feat(harness): add tests/test_litellm/harness/adapters/fixtures/claude_code/max_turns.jsonl

* feat(harness): add tests/test_litellm/harness/adapters/fixtures/claude_code/resume_turn.jsonl

* feat(harness): add tests/test_litellm/harness/adapters/fixtures/claude_code/structured_output.jsonl

* feat(harness): add tests/test_litellm/harness/adapters/fixtures/claude_code/success_tools.jsonl

* feat(harness): add tests/test_litellm/harness/adapters/fixtures/codex/reasoning.jsonl

* feat(harness): add tests/test_litellm/harness/adapters/fixtures/codex/structured_output.jsonl

* feat(harness): add tests/test_litellm/harness/adapters/fixtures/codex/turn_failed.jsonl

* feat(harness): add tests/test_litellm/harness/adapters/fixtures/codex/turn1_bash.jsonl

* feat(harness): add tests/test_litellm/harness/adapters/fixtures/codex/turn2_resume_apply_patch.jsonl

* feat(harness): add tests/test_litellm/harness/adapters/fixtures/opencode/api_error.jsonl

* feat(harness): add tests/test_litellm/harness/adapters/fixtures/opencode/endpoint_requests.jsonl

* feat(harness): add tests/test_litellm/harness/adapters/fixtures/opencode/readonly_denied_bash.jsonl

* feat(harness): add tests/test_litellm/harness/adapters/fixtures/opencode/turn1_write_read.jsonl

* feat(harness): add tests/test_litellm/harness/adapters/fixtures/opencode/turn2_session_skill.jsonl

* feat(harness): add tests/test_litellm/harness/adapters/test_claude_code.py

* feat(harness): add tests/test_litellm/harness/adapters/test_codex.py

* feat(harness): add tests/test_litellm/harness/adapters/test_opencode.py

* feat(harness): add tests/test_litellm/harness/core_fakes.py

* feat(harness): add tests/test_litellm/harness/sandbox/__init__.py

* feat(harness): add tests/test_litellm/harness/sandbox/test_docker.py

* feat(harness): add tests/test_litellm/harness/sandbox/test_local.py

* feat(harness): add tests/test_litellm/harness/sandbox/test_snapshot.py

* feat(harness): add tests/test_litellm/harness/test_endpoint.py

* feat(harness): add tests/test_litellm/harness/test_init.py

* feat(harness): add tests/test_litellm/harness/test_runtime.py

* feat(harness): add tests/test_litellm/harness/test_sync.py

* feat(harness): add tests/test_litellm/harness/test_types.py

* test(harness): use word recall in stream e2e test

* refactor(harness): update litellm/__init__.py

* refactor(harness): update litellm/constants.py

* refactor(harness): update litellm/harness/__init__.py

* refactor(harness): remove litellm/harness/adapters/__init__.py

* refactor(harness): update litellm/harness/context.py

* refactor(harness): update litellm/harness/endpoint.py

* refactor(harness): update litellm/harness/handlers/__init__.py

* refactor(harness): update litellm/harness/handlers/base.py

* refactor(harness): update litellm/harness/handlers/cli_handler.py

* refactor(harness): update litellm/harness/handlers/deepagents_handler.py

* refactor(harness): update litellm/harness/runtime.py

* refactor(harness): update litellm/harness/sandbox/docker.py

* refactor(harness): update litellm/harness/sandbox/local.py

* refactor(harness): update litellm/harness/sync.py

* refactor(harness): update litellm/harness/types.py

* refactor(harness): update litellm/llms/base_llm/harness/__init__.py

* refactor(harness): update litellm/llms/base_llm/harness/transformation.py

* refactor(harness): update litellm/llms/base_llm/harness/utils.py

* refactor(harness): update litellm/llms/claude_code/__init__.py

* refactor(harness): update litellm/llms/claude_code/harness/__init__.py

* refactor(harness): update litellm/llms/claude_code/harness/transformation.py

* refactor(harness): update litellm/llms/codex/__init__.py

* refactor(harness): update litellm/llms/codex/harness/__init__.py

* refactor(harness): update litellm/llms/codex/harness/transformation.py

* refactor(harness): update litellm/llms/deepagents/__init__.py

* refactor(harness): update litellm/llms/deepagents/harness/__init__.py

* refactor(harness): update litellm/llms/deepagents/harness/sandbox_backend.py

* refactor(harness): update litellm/llms/deepagents/harness/transformation.py

* refactor(harness): update litellm/llms/opencode/__init__.py

* refactor(harness): update litellm/llms/opencode/harness/__init__.py

* refactor(harness): update litellm/llms/opencode/harness/transformation.py

* refactor(harness): update litellm/utils.py

* refactor(harness): update README.md

* refactor(harness): update tests/harness_e2e/conftest.py

* refactor(harness): update tests/harness_e2e/test_harness_e2e.py

* refactor(harness): remove tests/test_litellm/harness/__init__.py

* refactor(harness): remove tests/test_litellm/harness/adapters/__init__.py

* refactor(harness): remove tests/test_litellm/harness/adapters/fixtures/claude_code/api_error.jsonl

* refactor(harness): remove tests/test_litellm/harness/adapters/fixtures/claude_code/max_turns.jsonl

* refactor(harness): remove tests/test_litellm/harness/adapters/fixtures/claude_code/resume_turn.jsonl

* refactor(harness): remove tests/test_litellm/harness/adapters/fixtures/claude_code/structured_output.jsonl

* refactor(harness): remove tests/test_litellm/harness/adapters/fixtures/claude_code/success_tools.jsonl

* refactor(harness): remove tests/test_litellm/harness/adapters/fixtures/codex/reasoning.jsonl

* refactor(harness): remove tests/test_litellm/harness/adapters/fixtures/codex/structured_output.jsonl

* refactor(harness): remove tests/test_litellm/harness/adapters/fixtures/codex/turn_failed.jsonl

* refactor(harness): remove tests/test_litellm/harness/adapters/fixtures/codex/turn1_bash.jsonl

* refactor(harness): remove tests/test_litellm/harness/adapters/fixtures/codex/turn2_resume_apply_patch.jsonl

* refactor(harness): remove tests/test_litellm/harness/adapters/fixtures/opencode/api_error.jsonl

* refactor(harness): remove tests/test_litellm/harness/adapters/fixtures/opencode/endpoint_requests.jsonl

* refactor(harness): remove tests/test_litellm/harness/adapters/fixtures/opencode/readonly_denied_bash.jsonl

* refactor(harness): remove tests/test_litellm/harness/adapters/fixtures/opencode/turn1_write_read.jsonl

* refactor(harness): remove tests/test_litellm/harness/adapters/fixtures/opencode/turn2_session_skill.jsonl

* refactor(harness): remove tests/test_litellm/harness/adapters/test_claude_code.py

* refactor(harness): remove tests/test_litellm/harness/adapters/test_codex.py

* refactor(harness): remove tests/test_litellm/harness/adapters/test_opencode.py

* refactor(harness): remove tests/test_litellm/harness/core_fakes.py

* refactor(harness): remove tests/test_litellm/harness/sandbox/__init__.py

* refactor(harness): remove tests/test_litellm/harness/sandbox/test_docker.py

* refactor(harness): remove tests/test_litellm/harness/sandbox/test_local.py

* refactor(harness): remove tests/test_litellm/harness/sandbox/test_snapshot.py

* refactor(harness): remove tests/test_litellm/harness/test_endpoint.py

* refactor(harness): remove tests/test_litellm/harness/test_init.py

* refactor(harness): remove tests/test_litellm/harness/test_runtime.py

* refactor(harness): remove tests/test_litellm/harness/test_sync.py

* refactor(harness): remove tests/test_litellm/harness/test_types.py

* refactor(harness): update tests/unit/harness/__init__.py

* refactor(harness): update tests/unit/harness/core_fakes.py

* refactor(harness): update tests/unit/harness/handlers/__init__.py

* refactor(harness): update tests/unit/harness/handlers/test_deepagents_handler.py

* refactor(harness): update tests/unit/harness/sandbox/__init__.py

* refactor(harness): update tests/unit/harness/sandbox/test_docker.py

* refactor(harness): update tests/unit/harness/sandbox/test_local.py

* refactor(harness): update tests/unit/harness/sandbox/test_snapshot.py

* refactor(harness): update tests/unit/harness/test_endpoint.py

* refactor(harness): update tests/unit/harness/test_init.py

* refactor(harness): update tests/unit/harness/test_runtime.py

* refactor(harness): update tests/unit/harness/test_sync.py

* refactor(harness): update tests/unit/harness/test_types.py

* refactor(harness): update tests/unit/llms/claude_code/__init__.py

* refactor(harness): update tests/unit/llms/claude_code/harness/__init__.py

* refactor(harness): update tests/unit/llms/claude_code/harness/fixtures/api_error.jsonl

* refactor(harness): update tests/unit/llms/claude_code/harness/fixtures/max_turns.jsonl

* refactor(harness): update tests/unit/llms/claude_code/harness/fixtures/resume_turn.jsonl

* refactor(harness): update tests/unit/llms/claude_code/harness/fixtures/structured_output.jsonl

* refactor(harness): update tests/unit/llms/claude_code/harness/fixtures/success_tools.jsonl

* refactor(harness): update tests/unit/llms/claude_code/harness/test_transformation.py

* refactor(harness): update tests/unit/llms/codex/__init__.py

* refactor(harness): update tests/unit/llms/codex/harness/__init__.py

* refactor(harness): update tests/unit/llms/codex/harness/fixtures/reasoning.jsonl

* refactor(harness): update tests/unit/llms/codex/harness/fixtures/structured_output.jsonl

* refactor(harness): update tests/unit/llms/codex/harness/fixtures/turn1_bash.jsonl

* refactor(harness): update tests/unit/llms/codex/harness/fixtures/turn2_resume_apply_patch.jsonl

* refactor(harness): update tests/unit/llms/codex/harness/fixtures/turn_failed.jsonl

* refactor(harness): update tests/unit/llms/codex/harness/test_transformation.py

* refactor(harness): update tests/unit/llms/deepagents/__init__.py

* refactor(harness): update tests/unit/llms/deepagents/harness/__init__.py

* refactor(harness): update tests/unit/llms/deepagents/harness/test_transformation.py

* refactor(harness): update tests/unit/llms/opencode/__init__.py

* refactor(harness): update tests/unit/llms/opencode/harness/__init__.py

* refactor(harness): update tests/unit/llms/opencode/harness/fixtures/api_error.jsonl

* refactor(harness): update tests/unit/llms/opencode/harness/fixtures/endpoint_requests.jsonl

* refactor(harness): update tests/unit/llms/opencode/harness/fixtures/readonly_denied_bash.jsonl

* refactor(harness): update tests/unit/llms/opencode/harness/fixtures/turn1_write_read.jsonl

* refactor(harness): update tests/unit/llms/opencode/harness/fixtures/turn2_session_skill.jsonl

* refactor(harness): update tests/unit/llms/opencode/harness/test_transformation.py

* ci: allowlist tests/harness_e2e, which needs live runtimes and a gateway

* fix(harness): bound the turn event queue

* fix(harness): bound the turn event queue with backpressure

* style: sort imports in utils

* ci: exclude agent-harness config folders from provider docs check

* refactor(harness): update tests/harness_e2e/conftest.py

* refactor(harness): update tests/harness_e2e/test_harness_e2e.py

* refactor(harness): update tests/unit/harness/core_fakes.py

* refactor(harness): update tests/unit/harness/handlers/test_deepagents_handler.py

* refactor(harness): update tests/unit/harness/test_runtime.py

* refactor(harness): update tests/unit/harness/test_sync.py

* refactor(harness): update tests/unit/llms/deepagents/harness/test_transformation.py

* refactor(harness): update tests/unit/llms/opencode/harness/test_transformation.py

* refactor(harness): update litellm/harness/endpoint.py

* refactor(harness): update litellm/harness/handlers/deepagents_handler.py

* refactor(harness): update litellm/harness/options.py

* refactor(harness): update litellm/harness/runtime.py

* refactor(harness): update litellm/harness/sandbox/snapshot.py

* refactor(harness): update litellm/llms/base_llm/harness/transformation.py

* refactor(harness): update litellm/llms/base_llm/harness/utils.py

* refactor(harness): update litellm/llms/claude_code/harness/transformation.py

* refactor(harness): update litellm/llms/codex/harness/transformation.py

* refactor(harness): update litellm/llms/deepagents/harness/sandbox_backend.py

* refactor(harness): update litellm/llms/deepagents/harness/transformation.py

* refactor(harness): update litellm/llms/opencode/harness/transformation.py

* refactor(harness): update litellm/sandbox/__init__.py

* refactor(harness): update tests/unit/llms/claude_code/harness/test_transformation.py

* refactor(harness): update tests/unit/llms/deepagents/harness/test_sandbox_backend_symlinks.py

* refactor(harness): update tests/unit/llms/opencode/harness/test_transformation.py

* refactor(harness): update litellm/llms/base_llm/harness/utils.py

* refactor(harness): update litellm/llms/codex/harness/transformation.py

* refactor(harness): update tests/code_coverage_tests/recursive_detector.py

* refactor(harness): update tests/unit/llms/base_llm/harness/__init__.py

* refactor(harness): update tests/unit/llms/claude_code/harness/fixtures/__init__.py

* refactor(harness): update tests/unit/llms/codex/harness/fixtures/__init__.py

* refactor(harness): update tests/unit/llms/opencode/harness/fixtures/__init__.py

* refactor(harness): update litellm/harness/__init__.py

* refactor(harness): update litellm/harness/context.py

* refactor(harness): update litellm/harness/endpoint.py

* refactor(harness): update litellm/harness/handlers/__init__.py

* refactor(harness): update litellm/harness/handlers/base.py

* refactor(harness): update litellm/harness/handlers/cli_handler.py

* refactor(harness): update litellm/harness/handlers/deepagents_handler.py

* refactor(harness): update litellm/harness/runtime.py

* refactor(harness): update litellm/harness/sandbox/__init__.py

* refactor(harness): update litellm/harness/sandbox/base.py

* refactor(harness): update litellm/harness/sandbox/docker.py

* refactor(harness): update litellm/harness/sandbox/local.py

* refactor(harness): update litellm/harness/sandbox/snapshot.py

* refactor(harness): update litellm/harness/sync.py

* refactor(harness): update litellm/harness/types.py

* refactor(harness): update litellm/llms/base_llm/harness/transformation.py

* refactor(harness): update litellm/llms/base_llm/harness/utils.py

* refactor(harness): update litellm/llms/claude_code/harness/transformation.py

* refactor(harness): update litellm/llms/codex/harness/transformation.py

* refactor(harness): update litellm/llms/deepagents/harness/sandbox_backend.py

* refactor(harness): update litellm/llms/deepagents/harness/transformation.py

* refactor(harness): update litellm/llms/opencode/harness/transformation.py

* refactor(harness): update litellm/types/llms/custom_http.py

* refactor(harness): update tests/unit/harness/test_endpoint.py

* refactor(harness): update litellm/harness/runtime.py

* refactor(harness): update litellm/llms/deepagents/harness/sandbox_backend.py

* refactor(harness): update tests/unit/harness/test_init.py

* refactor(harness): update tests/unit/harness/test_runtime.py

* refactor(harness): update tests/unit/llms/deepagents/harness/test_sandbox_backend_symlinks.py
2026-10-01 22:27:49 +00:00

74 lines
2.1 KiB
Python

"""Fixtures for the litellm.agent() end-to-end tests.
These run the real harness runtimes (claude, codex, opencode, deepagents) against a real
LiteLLM AI Gateway, routed with the `litellm_proxy/` model prefix. They skip unless
LITELLM_PROXY_API_BASE and LITELLM_PROXY_API_KEY are set. Model groups can be overridden
per harness with HARNESS_E2E_MODEL_<HARNESS>.
"""
import importlib.util
import os
import shutil
from collections.abc import Iterator
from pathlib import Path
import pytest
from litellm import Harness
GATEWAY_BASE = os.environ.get("LITELLM_PROXY_API_BASE", "").strip()
GATEWAY_KEY = os.environ.get("LITELLM_PROXY_API_KEY", "").strip()
DEFAULT_MODEL_GROUPS = {
Harness.CLAUDE_CODE: "claude-haiku-4-5-20251001",
Harness.CODEX: "bedrock_mantle/openai.gpt-5.4",
Harness.OPENCODE: "claude-haiku-4-5-20251001",
Harness.DEEPAGENTS: "claude-haiku-4-5-20251001",
}
BINARIES = {
Harness.CLAUDE_CODE: "claude",
Harness.CODEX: "codex",
Harness.OPENCODE: "opencode",
}
requires_gateway = pytest.mark.skipif(
not (GATEWAY_BASE and GATEWAY_KEY),
reason="LITELLM_PROXY_API_BASE / LITELLM_PROXY_API_KEY not set",
)
def model_for(harness: Harness) -> str:
"""`litellm_proxy/<group>`: every model call goes through the gateway."""
override = os.environ.get(f"HARNESS_E2E_MODEL_{harness.name}", "").strip()
return f"litellm_proxy/{override or DEFAULT_MODEL_GROUPS[harness]}"
def harness_available(harness: Harness) -> bool:
if harness is Harness.DEEPAGENTS:
return all(
importlib.util.find_spec(m) is not None
for m in ("deepagents", "langchain_litellm")
)
return shutil.which(BINARIES[harness]) is not None
def harness_params() -> list:
return [
pytest.param(
h,
id=h.value,
marks=pytest.mark.skipif(
not harness_available(h), reason=f"{h.value} runtime not installed"
),
)
for h in Harness
]
@pytest.fixture
def workspace(tmp_path: Path) -> Iterator[Path]:
repo = tmp_path / "repo"
repo.mkdir()
(repo / "README.md").write_text("# demo\n")
yield repo