Files
hyungi_document_server/tests/test_worker_recap_endpoint.py
Hyungi Ahn eae1f48d62 feat(worker-pool): Registry-1C cap 1MB + deterministic compaction
사용자 결정 2026-05-19: 100KB cap 이 운영 7d 데이터 1.36MB 대비 부족 →
cap 상향만으로 raw 비대화 위험. cap 1MB + payload compaction 병행.

fetch_recap_context() 변경:
- memo payload item field 축소 = id/title/ai_tldr/ai_event_kind/created_at (5 필드)
  (ai_bullets/file_type/source_channel/category/extracted_text 등 제외)
- memo top-N = RECAP_MEMO_TOP_N env (default 200) — 초과분은 aggregate 로
- aggregate = memos_by_day + memos_by_kind + omitted_memos
- payload_compacted flag = aggregate fallback 발현 여부
- events 는 raw (운영 7d 데이터에서 통상 0~소량)

internal_worker.py:
- PAYLOAD_MAX_BYTES → _payload_max_bytes() env override
  (WORKER_RECAP_PAYLOAD_MAX_BYTES default 1_000_000)
- JobsRecapResponse 에 payload_compacted / omitted_memos 노출
- 413 detail 에 "after compaction" 명시 + RECAP_MEMO_TOP_N 조정 안내

테스트 3 항목 신규 + 기존 endpoint 413 test 업데이트:
- 700 memo → 200 kept + 500 omitted + compacted=true + < 1MB
- 10 memo → compacted=false + omitted=0
- 비정상 큰 title (compaction 후에도 cap 초과) → 413 유지

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-19 12:55:51 +09:00

141 lines
4.6 KiB
Python

"""PR-Worker-Pool-Registry-1C — /internal/worker/jobs/recap + recap context.
3 항목 (단독 실행 기준 PASS; 같은 파일 sequential 한계 = test fixture isolation follow-up):
1. fetch_recap_context — empty user (memo/event 0) → memo_count=0 + event_count=0 + 타임존 표기
2. /jobs/recap endpoint — 일반 user JWT 로 호출 → 200 + worker_jobs INSERT + payload JSONB
3. payload size guard — fetch_recap_context monkeypatch 로 거대 context 반환 → 413
"""
from __future__ import annotations
import json
import os
import sys
import pytest
import pytest_asyncio
sys.path.insert(0, os.path.join(os.path.dirname(__file__), "..", "app"))
from httpx import ASGITransport, AsyncClient
from sqlalchemy import text
from sqlalchemy.ext.asyncio import async_sessionmaker
from _worker_pool_helpers import (
_make_engine,
cleanup_worker_jobs,
ensure_user,
fetch_worker_job,
get_database_url,
mint_access_token,
)
@pytest_asyncio.fixture
async def env_setup(monkeypatch):
monkeypatch.setenv("LAPTOP_WORKER_BOT_USERNAME", "laptop-worker-bot")
@pytest.mark.asyncio
async def test_fetch_recap_context_shape(env_setup):
"""fetch_recap_context — 시그니처 + 빈 user 시 0/0 + KST 타임존 표기."""
from services.worker_recap_context import fetch_recap_context
owner_id = await ensure_user("test-recap-empty-1c")
engine = _make_engine()
sm = async_sessionmaker(engine, expire_on_commit=False)
try:
async with sm() as session:
ctx = await fetch_recap_context(session, user_id=owner_id, days=7)
finally:
await engine.dispose()
assert ctx["user_id"] == owner_id
assert ctx["days"] == 7
assert ctx["timezone"] == "Asia/Seoul"
assert isinstance(ctx["memos"], list)
assert isinstance(ctx["events"], list)
assert ctx["memo_count"] == len(ctx["memos"])
assert ctx["event_count"] == len(ctx["events"])
# 신규 user 이므로 event 0
assert ctx["event_count"] == 0
@pytest.mark.asyncio
async def test_recap_endpoint_creates_worker_job(env_setup):
"""/jobs/recap 호출 → 200 + worker_jobs INSERT."""
from main import app
owner_id = await ensure_user("test-recap-endpoint-1c")
token = mint_access_token("test-recap-endpoint-1c")
try:
async with AsyncClient(
transport=ASGITransport(app=app), base_url="http://test"
) as c:
r = await c.post(
"/internal/worker/jobs/recap",
json={"days": 7},
headers={"Authorization": f"Bearer {token}"},
)
assert r.status_code == 200, r.text
js = r.json()
assert "job_id" in js
assert js["memo_count"] >= 0
assert js["event_count"] >= 0
assert js["payload_bytes"] > 0
assert "payload_compacted" in js
assert "omitted_memos" in js
# DB verify
job = await fetch_worker_job(js["job_id"])
assert job is not None
# payload 는 JSONB dict 로 저장됨
finally:
await cleanup_worker_jobs("recap")
@pytest.mark.asyncio
async def test_recap_payload_413_when_oversize(env_setup, monkeypatch):
"""payload 1MB 초과 시 413 (사용자 결정 2026-05-19 cap 1MB)."""
from api import internal_worker as iw_mod
from main import app
owner_id = await ensure_user("test-recap-413-1c")
token = mint_access_token("test-recap-413-1c")
async def fake_fetch(session, user_id, days=7):
return {
"user_id": user_id,
"days": days,
"period_start": "2026-05-12T00:00:00+09:00",
"period_end": "2026-05-19T00:00:00+09:00",
"timezone": "Asia/Seoul",
# ~1.2MB raw payload (compaction 후에도 cap 초과 가정)
"memos": [{"id": i, "title": "x" * 6000} for i in range(200)],
"events": [],
"memo_count": 200,
"event_count": 0,
"summary_stats": {
"total_memos": 200,
"memos_kept": 200,
"omitted_memos": 0,
"top_n": 200,
"memos_by_day": {},
"memos_by_kind": {},
},
"payload_compacted": False,
}
monkeypatch.setattr(iw_mod, "fetch_recap_context", fake_fetch)
async with AsyncClient(
transport=ASGITransport(app=app), base_url="http://test"
) as c:
r = await c.post(
"/internal/worker/jobs/recap",
json={"days": 7},
headers={"Authorization": f"Bearer {token}"},
)
assert r.status_code == 413, r.text
assert "bytes" in r.json()["detail"]
assert "after compaction" in r.json()["detail"]