litellm/tests/e2e_harness/claude_code/test_request_determinism.py
ryan-crabbe-berri 048a1500df
test(e2e): move the harness self-tests out of tests/e2e (#45172)
* test(e2e): move the harness self-tests out of tests/e2e

The nightly Buildkite run copies tests/e2e into the runner image and runs
bare pytest, so the 672 tests of the harness itself (fixture parsing, JUnit
properties, the stack lock, the load aggregators, the Claude Code driver)
counted as e2e tests on the status page even though none of them reaches a
proxy. They now live in tests/e2e_harness, mirroring the tests/e2e layout,
and run in the GitHub Actions lint job and the CircleCI
provider_replay_harness job instead

* fix(ci): point the providers replay controls at tests/e2e_harness

The providers integration job still selected the four replay-control
tests under tests/e2e/test_provider_edge.py, so pytest exited before
they ran. The raw-HTTP check's file walk also drops to one loop per
comprehension

* style(tests): mark the raw-HTTP check's bindings Final
2026-10-07 22:20:02 +00:00

162 lines
6 KiB
Python

"""The CLI must send the same request bytes from one build to the next.
Markerless harness test: it drives the real `claude` binary against a local
stub instead of a proxy, so it carries no `e2e` marker. The binary is a
prerequisite of this whole suite, so a missing one is a failure rather than a
skip.
Two builds differ in ways the driver does not control: a fresh pod, so no CLI
state survives, and a different candidate checked out at a different commit.
Both used to reach the request body, through the memory path the system prompt
names and through the git block the CLI adds for its working directory, so the
shared provider cache missed on every Claude Code cell. This replays those two
differences across a pair of invocations and holds the bytes equal.
A pinned session id is what makes the second test necessary. The matrix runs
its cells across xdist workers, and the CLI refuses to start a session id that
another live process already holds, so pinning one without also opting out of
session persistence turns most of a parallel run red.
"""
from __future__ import annotations
import json
import os
import shutil
import subprocess
import threading
from collections import Counter
from concurrent.futures import ThreadPoolExecutor
from http.server import BaseHTTPRequestHandler, ThreadingHTTPServer
from pathlib import Path
from typing import List, Tuple
import pytest
from claude_code.cli_driver import _FIXED_CLI_USER_ID, _seed_cli_identity, _stable_cli_state, run_claude
from claude_code.rate_limiter import RateLimiter
pytestmark = pytest.mark.cli_determinism
_STUB_REPLY = {
"id": "msg_stub",
"type": "message",
"role": "assistant",
"model": "claude-haiku-4-5",
"content": [{"type": "text", "text": "ok"}],
"stop_reason": "end_turn",
"usage": {"input_tokens": 10, "output_tokens": 2},
}
def _make_repo(root: Path, subject: str) -> Path:
root.mkdir(parents=True, exist_ok=True)
identity = {"NAME": "t", "EMAIL": "t@e2e"}
env = dict(
os.environ,
**{f"GIT_{role}_{key}": value for role in ("AUTHOR", "COMMITTER") for key, value in identity.items()},
)
(root / "file.txt").write_text(subject, encoding="utf-8")
for args in (["init", "-q"], ["add", "."], ["commit", "-q", "-m", subject]):
subprocess.run(["git", *args], cwd=root, env=env, check=True, capture_output=True)
return root
@pytest.fixture(name="captured")
def _captured() -> Tuple[str, List[bytes]]:
bodies: List[bytes] = []
lock = threading.Lock()
class Handler(BaseHTTPRequestHandler):
protocol_version = "HTTP/1.1"
def do_POST(self) -> None:
raw = self.rfile.read(int(self.headers.get("content-length") or 0))
if "count_tokens" not in self.path:
with lock:
bodies.append(raw)
payload = json.dumps({"input_tokens": 10} if "count_tokens" in self.path else _STUB_REPLY).encode()
self.send_response(200)
self.send_header("content-type", "application/json")
self.send_header("content-length", str(len(payload)))
self.end_headers()
self.wfile.write(payload)
def log_message(self, *_args: object) -> None:
return
server = ThreadingHTTPServer(("127.0.0.1", 0), Handler)
threading.Thread(target=server.serve_forever, daemon=True).start()
try:
yield f"http://127.0.0.1:{server.server_address[1]}", bodies
finally:
server.shutdown()
def test_two_builds_send_the_same_request_bytes(captured: Tuple[str, List[bytes]], tmp_path: Path) -> None:
base_url, bodies = captured
limiter = RateLimiter(state_dir=tmp_path / "limiter")
checkouts = (_make_repo(tmp_path / "build-1", "first"), _make_repo(tmp_path / "build-2", "second"))
origin = Path.cwd()
sent = []
for checkout in checkouts:
shutil.rmtree(Path(_stable_cli_state()[0]).parent, ignore_errors=True)
os.chdir(checkout)
try:
before = len(bodies)
run_claude(
prompt="say ok",
model="claude-haiku-4-5",
base_url=base_url,
api_key="stub",
extra_env={"CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC": "1"},
rate_limiter=limiter,
)
sent.append(bodies[before:])
finally:
os.chdir(origin)
assert sent[0], "the CLI sent no request to the stub, so there is nothing to compare"
assert sent[0] == sent[1]
def test_concurrent_cells_do_not_collide_on_the_pinned_session(
captured: Tuple[str, List[bytes]], tmp_path: Path
) -> None:
base_url, bodies = captured
limiter = RateLimiter(state_dir=tmp_path / "limiter")
def one(_index: int) -> int:
return run_claude(
prompt="say ok",
model="claude-haiku-4-5",
base_url=base_url,
api_key="stub",
extra_env={"CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC": "1"},
rate_limiter=limiter,
).exit_code
with ThreadPoolExecutor(max_workers=4) as pool:
codes = list(pool.map(one, range(4)))
assert codes == [0, 0, 0, 0]
assert bodies, "the CLI sent no request to the stub, so there is nothing to compare"
assert set(Counter(bodies).values()) == {4}
def test_seeding_the_device_id_survives_threads_racing_on_the_same_directory(tmp_path: Path) -> None:
"""`run_claude_models_parallel` drives several models from one process, so the
seed's staged file has to be unique per thread and not merely per process."""
config_dir = tmp_path / "config"
config_dir.mkdir()
seeded = config_dir / ".claude.json"
for _round in range(20):
seeded.unlink(missing_ok=True)
with ThreadPoolExecutor(max_workers=16) as pool:
for outcome in [pool.submit(_seed_cli_identity, str(config_dir)) for _ in range(16)]:
outcome.result()
assert json.loads(seeded.read_text(encoding="utf-8"))["userID"] == _FIXED_CLI_USER_ID
assert sorted(entry.name for entry in config_dir.iterdir()) == [".claude.json"]