mirror of
https://github.com/bytedance/deer-flow.git
synced 2026-06-10 09:25:57 +00:00
88759015e4
* test(e2e): record/replay front-back contract verification Guards the front-back contract with a deterministic, key-free record/replay harness (mirrors open-design's golden-trace approach): - ReplayChatModel (tests/replay_provider.py): replays recorded LLM turns by a normalized hash of the model input. Strips <system-reminder>/date/uuid/tmp-path so one fixture replays across days and from both the browser and direct-POST paths; a miss raises loudly (no silent divergence). - Recording is record-through-browser (scripts/record_gateway.py + build_fixture_from_jsonl.py + frontend/tests/e2e-record): a real run is driven through the real frontend so captured inputs match exactly what the browser sends; fixtures contain no API key. - Layer 1 — backend golden (tests/test_replay_golden.py): replay through the real gateway, assert the SSE event sequence == committed golden. - Layer 2 — full-stack render (frontend/tests/e2e-real-backend): real Next.js + real gateway (replay model) + Chromium; assert the replayed auto-title and follow-up suggestions render. DOM assertions are the gate; visual regression is a local dev gate (CI uploads the render as an artifact). - CI (.github/workflows/replay-e2e.yml): both layers, triggered on EITHER side of the contract (frontend/** or backend gateway/harness/fixtures). * test(e2e): multi-run render-order cross-stack scenario (#3352) Guards the dangerous front-back class where a backend ordering change silently breaks a frontend assumption while both sides' unit tests stay green. Reproduces issue #3352: backend list_by_thread returns runs newest-first (#2932) and the frontend prepended per-run pages, inverting chronological order once the checkpoint no longer held the older messages. - tests/seed_runs_router.py: test-only seeder, mounted on the replay gateway only when DEERFLOW_ENABLE_TEST_SEED=1 (never in the production app). Seeds a thread with >=2 runs + per-run message events and no checkpoint -- the #3352 precondition -- so the frontend per-run reload path is the sole source of truth and the prepend inversion is observable. - frontend/tests/e2e-real-backend/multi-run-order.spec.ts: drives the real frontend against the real gateway, asserts the first run renders above the second. Reverting the #3354 fix turns it red. - replay-e2e.yml: trigger on the new replay test-infra paths. - docs: REPLAY_E2E.md cross-stack scenario section. * test(e2e): address Copilot review on the replay harness - Fix stale recorder references (scripts/record_traces.py -> scripts/record_gateway.py + scripts/build_fixture_from_jsonl.py) in replay_provider.py, test_replay_golden.py, _replay_fixture.py. - MODE_CONTEXT['ultra']: thinking_enabled False -> True, mirroring the frontend's `context.mode !== 'flash'` (hooks.ts). It did not affect the hashed input (Layer 1 golden still green), but the table now matches the real frontend context it claims to mirror. - replay_provider.py docstring: stop claiming memory is recorded-enabled; the replay config disables memory/summarization for determinism (title stays, as an in-graph deterministic call). - record_gateway.py / run_replay_gateway.py: override DEER_FLOW_HOME instead of setdefault, so an outer value can't leak into the hermetic harness. - record_gateway.py: clear error when DEERFLOW_RECORD_OUT is unset (was a bare KeyError). - playwright.record.config.ts: forward OPENAI_*/DEERFLOW_RECORD_OUT only when set, so the gateway raises a clear 'missing env' error instead of getting ''. * test(e2e): address Copilot review round 2 - seed_runs_router.py: constrain SeedMessage.role to Literal['human','ai'] so a bad value is a clean 422 at the boundary instead of a 500 (KeyError on _EVENT_TYPE). - record-write-read-file.spec.ts: waitForCaptureStable now throws on timeout instead of returning the last count, so a truncated/partial recording can't pass silently. - real-backend-render.spec.ts: guard the suggestions JSON.parse; a bracket-prefixed non-JSON turn falls back to '' so the existing not.toBe('') assertion fails clearly instead of a generic parse throw.
88 lines
3.9 KiB
Python
88 lines
3.9 KiB
Python
"""Layer 1 of the record/replay e2e: replay a recorded trace through the **real
|
|
gateway** with a deterministic ``ReplayChatModel`` (no API key, no network) and
|
|
assert the streamed SSE event sequence matches a committed golden.
|
|
|
|
This catches backend protocol drift: if a change alters the shape/sequence of
|
|
SSE the gateway emits for the recorded scenario, this test goes red. The replay
|
|
model serves the recorded assistant turns by input hash, so the agent graph
|
|
(write_file -> auto-title -> read_file -> final answer) reproduces offline.
|
|
|
|
Fixtures are produced by ``scripts/record_gateway.py`` +
|
|
``scripts/build_fixture_from_jsonl.py`` (manual, needs a key).
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
import json
|
|
import os
|
|
from pathlib import Path
|
|
|
|
import pytest
|
|
from _replay_fixture import REPLAY_MODEL_BLOCK, build_config_yaml, drive_gateway, prepare_hermetic_extras
|
|
|
|
FIXTURE_DIR = Path(__file__).parent / "fixtures" / "replay"
|
|
|
|
|
|
def _reset_process_singletons(monkeypatch: pytest.MonkeyPatch) -> None:
|
|
"""Invalidate process-wide caches so the test-only config/home take effect.
|
|
|
|
Same set the real-server e2e resets (see test_setup_agent_http_e2e_real_server).
|
|
"""
|
|
from deerflow.config import app_config as app_config_module
|
|
from deerflow.config import paths as paths_module
|
|
from deerflow.persistence import engine as engine_module
|
|
|
|
for module, attr in (
|
|
(app_config_module, "_app_config"),
|
|
(app_config_module, "_app_config_path"),
|
|
(app_config_module, "_app_config_mtime"),
|
|
(paths_module, "_paths_singleton"),
|
|
(engine_module, "_engine"),
|
|
(engine_module, "_session_factory"),
|
|
):
|
|
monkeypatch.setattr(module, attr, None, raising=False)
|
|
|
|
|
|
@pytest.mark.no_auto_user
|
|
def test_replay_write_read_file_ultra_matches_golden(tmp_path: Path, monkeypatch: pytest.MonkeyPatch):
|
|
scenario, mode = "write_read_file", "ultra"
|
|
fixture_path = FIXTURE_DIR / f"{scenario}.{mode}.json"
|
|
events_path = FIXTURE_DIR / f"{scenario}.{mode}.events.json"
|
|
fixture = json.loads(fixture_path.read_text(encoding="utf-8"))
|
|
|
|
home = tmp_path / "home"
|
|
home.mkdir()
|
|
monkeypatch.setenv("DEER_FLOW_HOME", str(home))
|
|
monkeypatch.setenv("DEERFLOW_REPLAY_FIXTURE", str(fixture_path))
|
|
|
|
cfg_path = tmp_path / "config.yaml"
|
|
cfg_path.write_text(build_config_yaml(model_block=REPLAY_MODEL_BLOCK, home=home), encoding="utf-8")
|
|
monkeypatch.setenv("DEER_FLOW_CONFIG_PATH", str(cfg_path))
|
|
monkeypatch.setenv("DEER_FLOW_EXTENSIONS_CONFIG_PATH", str(prepare_hermetic_extras(home)))
|
|
|
|
_reset_process_singletons(monkeypatch)
|
|
from deerflow.config import app_config as app_config_module
|
|
|
|
cfg = app_config_module.get_app_config()
|
|
cfg.database.sqlite_dir = str(home / "db")
|
|
|
|
from app.gateway.app import create_app
|
|
|
|
events = drive_gateway(create_app(), prompt=fixture["prompt"], context=fixture["context"])
|
|
|
|
assert events, "replay produced no SSE events"
|
|
assert events[0]["event"] == "metadata", f"first event should be metadata, got {events[0]!r}"
|
|
assert events[-1]["event"] == "end", f"last event should be end (run completed), got {events[-1]!r}"
|
|
|
|
# Regenerate the committed golden after re-recording the fixture:
|
|
# DEERFLOW_WRITE_GOLDEN=1 uv run pytest tests/test_replay_golden.py
|
|
if os.environ.get("DEERFLOW_WRITE_GOLDEN"):
|
|
events_path.write_text(json.dumps({"scenario": scenario, "mode": mode, "events": events}, ensure_ascii=False, indent=2), encoding="utf-8")
|
|
return
|
|
|
|
golden = json.loads(events_path.read_text(encoding="utf-8"))["events"]
|
|
# A replay hash-miss surfaces as the run erroring mid-stream -> the event
|
|
# shape sequence diverges from the golden, so this assertion is the catch-all
|
|
# for both backend SSE drift and replay divergence.
|
|
assert events == golden, f"SSE event-shape sequence drifted from the golden.\ngot ({len(events)}): {[e['event'] for e in events]}\nwant ({len(golden)}): {[e['event'] for e in golden]}"
|