mirror of
https://github.com/bytedance/deer-flow.git
synced 2026-09-19 19:16:17 +00:00
0745fb268f
* fix(gateway): scope runs read endpoints by data identity, not authorization identity Trusted internal callers are authorized as a synthetic internal user (id "default", or the make_safe_user_id-normalized owner with an owner header), while start_run stamps run rows with the raw trusted-owner value. list_runs / get_run / list_runs_page filtered by the authorization identity, so the store-side user filter never matched and internal callers always saw an empty runs list (or 404) for threads they are authorized to read. The three read endpoints now resolve their filter id through _run_scope_user_id: internal-role callers skip the per-user filter (thread visibility is already authorized by owner_check=True), and browser/API sessions keep the existing per-user filter unchanged. Regression tests cover both identities across the three endpoints (list, keyset page, single get) with a MemoryRunStore seeded with mixed-owner rows; without the fix the four internal-caller cases fail while the browser-session isolation case passes. * fix(gateway): route the message read endpoints through the same data-identity scoping Review follow-up on #5448: list_thread_messages and list_thread_messages_page resolved get_current_user and passed it as the data filter to the event-store scan, hidden-run lookups, turn-duration injection and the feedback queries — the same authorization-vs-data identity conflation fixed for the runs endpoints, leaving the #5437 empty-read symptom in place for lossy owner values. Both endpoints now resolve their filter id through _run_scope_user_id as well. Regression tests extend to the two message endpoints, asserting the resolved filter identity at the runs-store and feedback-repo boundaries (None for internal callers, the session user id for browser sessions). * fix(feedback): deterministic per-run collapse for unfiltered feedback reads Review follow-up on #5448: with _run_scope_user_id returning None for internal callers, the feedback lookups now receive an explicit-None user id, which skips the user_id WHERE in FeedbackRepository. On shared/NULL-owner threads several browser users can hold feedback on the same run, and list_by_thread_grouped / list_by_run_ids collapsed rows per run_id via a dict comprehension over unordered results — the feedback attached to the last AI message would be an arbitrary user's row. Both methods now order by created_at ASC with feedback_id as the tie-break, so the collapse deterministically keeps the most recently created feedback. _run_scope_user_id's docstring now documents that the resolved id also scopes feedback and event-store reads, not just run rows. Regression test seeds multi-user feedback on one run and asserts the collapse outcome is stable across repeated unfiltered reads. * docs(feedback): the collapse keeps the most recently written feedback created_at is refreshed on upsert, so the surviving row per run is the most recently written (created or updated), not the most recently created — align both docstrings with the ordering key's actual semantics.
338 lines
14 KiB
Python
338 lines
14 KiB
Python
"""Tests for FeedbackRepository and follow-up association.
|
|
|
|
Uses temp SQLite DB for ORM tests.
|
|
"""
|
|
|
|
import pytest
|
|
|
|
from deerflow.persistence.feedback import FeedbackRepository
|
|
|
|
|
|
async def _make_feedback_repo(tmp_path):
|
|
from deerflow.persistence.engine import get_session_factory, init_engine
|
|
|
|
url = f"sqlite+aiosqlite:///{tmp_path / 'test.db'}"
|
|
await init_engine("sqlite", url=url, sqlite_dir=str(tmp_path))
|
|
return FeedbackRepository(get_session_factory())
|
|
|
|
|
|
async def _cleanup():
|
|
from deerflow.persistence.engine import close_engine
|
|
|
|
await close_engine()
|
|
|
|
|
|
# -- FeedbackRepository --
|
|
|
|
|
|
class TestFeedbackRepository:
|
|
@pytest.mark.anyio
|
|
async def test_create_positive(self, tmp_path):
|
|
repo = await _make_feedback_repo(tmp_path)
|
|
record = await repo.create(run_id="r1", thread_id="t1", rating=1)
|
|
assert record["feedback_id"]
|
|
assert record["rating"] == 1
|
|
assert record["run_id"] == "r1"
|
|
assert record["thread_id"] == "t1"
|
|
assert "created_at" in record
|
|
await _cleanup()
|
|
|
|
@pytest.mark.anyio
|
|
async def test_create_negative_with_comment(self, tmp_path):
|
|
repo = await _make_feedback_repo(tmp_path)
|
|
record = await repo.create(
|
|
run_id="r1",
|
|
thread_id="t1",
|
|
rating=-1,
|
|
comment="Response was inaccurate",
|
|
)
|
|
assert record["rating"] == -1
|
|
assert record["comment"] == "Response was inaccurate"
|
|
await _cleanup()
|
|
|
|
@pytest.mark.anyio
|
|
async def test_create_with_message_id(self, tmp_path):
|
|
repo = await _make_feedback_repo(tmp_path)
|
|
record = await repo.create(run_id="r1", thread_id="t1", rating=1, message_id="msg-42")
|
|
assert record["message_id"] == "msg-42"
|
|
await _cleanup()
|
|
|
|
@pytest.mark.anyio
|
|
async def test_create_with_owner(self, tmp_path):
|
|
repo = await _make_feedback_repo(tmp_path)
|
|
record = await repo.create(run_id="r1", thread_id="t1", rating=1, user_id="user-1")
|
|
assert record["user_id"] == "user-1"
|
|
await _cleanup()
|
|
|
|
@pytest.mark.anyio
|
|
async def test_create_invalid_rating_zero(self, tmp_path):
|
|
repo = await _make_feedback_repo(tmp_path)
|
|
with pytest.raises(ValueError):
|
|
await repo.create(run_id="r1", thread_id="t1", rating=0)
|
|
await _cleanup()
|
|
|
|
@pytest.mark.anyio
|
|
async def test_create_invalid_rating_five(self, tmp_path):
|
|
repo = await _make_feedback_repo(tmp_path)
|
|
with pytest.raises(ValueError):
|
|
await repo.create(run_id="r1", thread_id="t1", rating=5)
|
|
await _cleanup()
|
|
|
|
@pytest.mark.anyio
|
|
async def test_get(self, tmp_path):
|
|
repo = await _make_feedback_repo(tmp_path)
|
|
created = await repo.create(run_id="r1", thread_id="t1", rating=1)
|
|
fetched = await repo.get(created["feedback_id"])
|
|
assert fetched is not None
|
|
assert fetched["feedback_id"] == created["feedback_id"]
|
|
assert fetched["rating"] == 1
|
|
await _cleanup()
|
|
|
|
@pytest.mark.anyio
|
|
async def test_get_nonexistent(self, tmp_path):
|
|
repo = await _make_feedback_repo(tmp_path)
|
|
assert await repo.get("nonexistent") is None
|
|
await _cleanup()
|
|
|
|
@pytest.mark.anyio
|
|
async def test_list_by_run(self, tmp_path):
|
|
repo = await _make_feedback_repo(tmp_path)
|
|
await repo.create(run_id="r1", thread_id="t1", rating=1, user_id="user-1")
|
|
await repo.create(run_id="r1", thread_id="t1", rating=-1, user_id="user-2")
|
|
await repo.create(run_id="r2", thread_id="t1", rating=1, user_id="user-1")
|
|
results = await repo.list_by_run("t1", "r1", user_id=None)
|
|
assert len(results) == 2
|
|
assert all(r["run_id"] == "r1" for r in results)
|
|
await _cleanup()
|
|
|
|
@pytest.mark.anyio
|
|
async def test_list_by_thread(self, tmp_path):
|
|
repo = await _make_feedback_repo(tmp_path)
|
|
await repo.create(run_id="r1", thread_id="t1", rating=1)
|
|
await repo.create(run_id="r2", thread_id="t1", rating=-1)
|
|
await repo.create(run_id="r3", thread_id="t2", rating=1)
|
|
results = await repo.list_by_thread("t1")
|
|
assert len(results) == 2
|
|
assert all(r["thread_id"] == "t1" for r in results)
|
|
await _cleanup()
|
|
|
|
@pytest.mark.anyio
|
|
async def test_delete(self, tmp_path):
|
|
repo = await _make_feedback_repo(tmp_path)
|
|
created = await repo.create(run_id="r1", thread_id="t1", rating=1)
|
|
deleted = await repo.delete(created["feedback_id"])
|
|
assert deleted is True
|
|
assert await repo.get(created["feedback_id"]) is None
|
|
await _cleanup()
|
|
|
|
@pytest.mark.anyio
|
|
async def test_delete_nonexistent(self, tmp_path):
|
|
repo = await _make_feedback_repo(tmp_path)
|
|
deleted = await repo.delete("nonexistent")
|
|
assert deleted is False
|
|
await _cleanup()
|
|
|
|
@pytest.mark.anyio
|
|
async def test_aggregate_by_run(self, tmp_path):
|
|
repo = await _make_feedback_repo(tmp_path)
|
|
await repo.create(run_id="r1", thread_id="t1", rating=1, user_id="user-1")
|
|
await repo.create(run_id="r1", thread_id="t1", rating=1, user_id="user-2")
|
|
await repo.create(run_id="r1", thread_id="t1", rating=-1, user_id="user-3")
|
|
stats = await repo.aggregate_by_run("t1", "r1")
|
|
assert stats["total"] == 3
|
|
assert stats["positive"] == 2
|
|
assert stats["negative"] == 1
|
|
assert stats["run_id"] == "r1"
|
|
await _cleanup()
|
|
|
|
@pytest.mark.anyio
|
|
async def test_aggregate_empty(self, tmp_path):
|
|
repo = await _make_feedback_repo(tmp_path)
|
|
stats = await repo.aggregate_by_run("t1", "r1")
|
|
assert stats["total"] == 0
|
|
assert stats["positive"] == 0
|
|
assert stats["negative"] == 0
|
|
await _cleanup()
|
|
|
|
@pytest.mark.anyio
|
|
async def test_upsert_creates_new(self, tmp_path):
|
|
repo = await _make_feedback_repo(tmp_path)
|
|
record = await repo.upsert(run_id="r1", thread_id="t1", rating=1, user_id="u1")
|
|
assert record["rating"] == 1
|
|
assert record["feedback_id"]
|
|
assert record["user_id"] == "u1"
|
|
await _cleanup()
|
|
|
|
@pytest.mark.anyio
|
|
async def test_upsert_updates_existing(self, tmp_path):
|
|
repo = await _make_feedback_repo(tmp_path)
|
|
first = await repo.upsert(run_id="r1", thread_id="t1", rating=1, user_id="u1")
|
|
second = await repo.upsert(run_id="r1", thread_id="t1", rating=-1, user_id="u1", comment="changed my mind")
|
|
assert second["feedback_id"] == first["feedback_id"]
|
|
assert second["rating"] == -1
|
|
assert second["comment"] == "changed my mind"
|
|
await _cleanup()
|
|
|
|
@pytest.mark.anyio
|
|
async def test_upsert_different_users_separate(self, tmp_path):
|
|
repo = await _make_feedback_repo(tmp_path)
|
|
r1 = await repo.upsert(run_id="r1", thread_id="t1", rating=1, user_id="u1")
|
|
r2 = await repo.upsert(run_id="r1", thread_id="t1", rating=-1, user_id="u2")
|
|
assert r1["feedback_id"] != r2["feedback_id"]
|
|
assert r1["rating"] == 1
|
|
assert r2["rating"] == -1
|
|
await _cleanup()
|
|
|
|
@pytest.mark.anyio
|
|
async def test_upsert_invalid_rating(self, tmp_path):
|
|
repo = await _make_feedback_repo(tmp_path)
|
|
with pytest.raises(ValueError):
|
|
await repo.upsert(run_id="r1", thread_id="t1", rating=0, user_id="u1")
|
|
await _cleanup()
|
|
|
|
@pytest.mark.anyio
|
|
async def test_delete_by_run(self, tmp_path):
|
|
repo = await _make_feedback_repo(tmp_path)
|
|
await repo.upsert(run_id="r1", thread_id="t1", rating=1, user_id="u1")
|
|
deleted = await repo.delete_by_run(thread_id="t1", run_id="r1", user_id="u1")
|
|
assert deleted is True
|
|
results = await repo.list_by_run("t1", "r1", user_id="u1")
|
|
assert len(results) == 0
|
|
await _cleanup()
|
|
|
|
@pytest.mark.anyio
|
|
async def test_delete_by_run_nonexistent(self, tmp_path):
|
|
repo = await _make_feedback_repo(tmp_path)
|
|
deleted = await repo.delete_by_run(thread_id="t1", run_id="r1", user_id="u1")
|
|
assert deleted is False
|
|
await _cleanup()
|
|
|
|
@pytest.mark.anyio
|
|
async def test_list_by_thread_grouped(self, tmp_path):
|
|
repo = await _make_feedback_repo(tmp_path)
|
|
await repo.upsert(run_id="r1", thread_id="t1", rating=1, user_id="u1")
|
|
await repo.upsert(run_id="r2", thread_id="t1", rating=-1, user_id="u1")
|
|
await repo.upsert(run_id="r3", thread_id="t2", rating=1, user_id="u1")
|
|
grouped = await repo.list_by_thread_grouped("t1", user_id="u1")
|
|
assert "r1" in grouped
|
|
assert "r2" in grouped
|
|
assert "r3" not in grouped
|
|
assert grouped["r1"]["rating"] == 1
|
|
assert grouped["r2"]["rating"] == -1
|
|
await _cleanup()
|
|
|
|
@pytest.mark.anyio
|
|
async def test_list_by_thread_grouped_empty(self, tmp_path):
|
|
repo = await _make_feedback_repo(tmp_path)
|
|
grouped = await repo.list_by_thread_grouped("t1", user_id="u1")
|
|
assert grouped == {}
|
|
await _cleanup()
|
|
|
|
@pytest.mark.anyio
|
|
async def test_list_by_run_ids_is_thread_and_owner_scoped(self, tmp_path):
|
|
repo = await _make_feedback_repo(tmp_path)
|
|
await repo.upsert(run_id="r1", thread_id="t1", rating=1, user_id="u1")
|
|
await repo.upsert(run_id="r2", thread_id="t1", rating=-1, user_id="u1")
|
|
await repo.upsert(run_id="r3", thread_id="t1", rating=1, user_id="u1")
|
|
await repo.upsert(run_id="r1", thread_id="t1", rating=-1, user_id="u2")
|
|
await repo.upsert(run_id="r2", thread_id="t2", rating=1, user_id="u1")
|
|
|
|
grouped = await repo.list_by_run_ids("t1", {"r1", "r2"}, user_id="u1")
|
|
|
|
assert set(grouped) == {"r1", "r2"}
|
|
assert grouped["r1"]["rating"] == 1
|
|
assert grouped["r2"]["rating"] == -1
|
|
await _cleanup()
|
|
|
|
@pytest.mark.anyio
|
|
async def test_unfiltered_reads_collapse_multi_user_feedback_deterministically(self, tmp_path):
|
|
"""Explicit-None reads (internal callers) collapse same-run feedback rows.
|
|
|
|
Several browser users can hold feedback on one run of a shared
|
|
NULL-owner thread; the per-run collapse must be deterministic —
|
|
the most recently created feedback wins, ``feedback_id`` breaks ties.
|
|
"""
|
|
import asyncio
|
|
|
|
repo = await _make_feedback_repo(tmp_path)
|
|
await repo.upsert(run_id="r1", thread_id="t1", rating=1, user_id="u1")
|
|
# Guarantee a strictly later created_at than the first row.
|
|
await asyncio.sleep(0.01)
|
|
second = await repo.upsert(run_id="r1", thread_id="t1", rating=-1, user_id="u2")
|
|
|
|
for _ in range(3):
|
|
grouped = await repo.list_by_thread_grouped("t1", user_id=None)
|
|
by_run_ids = await repo.list_by_run_ids("t1", {"r1"}, user_id=None)
|
|
assert grouped["r1"]["feedback_id"] == second["feedback_id"]
|
|
assert grouped["r1"]["rating"] == -1
|
|
assert grouped["r1"]["user_id"] == "u2"
|
|
assert by_run_ids["r1"]["feedback_id"] == second["feedback_id"]
|
|
await _cleanup()
|
|
|
|
@pytest.mark.anyio
|
|
async def test_list_by_run_ids_empty_skips_query(self, tmp_path):
|
|
repo = await _make_feedback_repo(tmp_path)
|
|
|
|
assert await repo.list_by_run_ids("t1", set(), user_id="u1") == {}
|
|
await _cleanup()
|
|
|
|
|
|
# -- Follow-up association --
|
|
|
|
|
|
class TestFollowUpAssociation:
|
|
@pytest.mark.anyio
|
|
async def test_run_records_follow_up_via_memory_store(self):
|
|
"""MemoryRunStore stores follow_up_to_run_id in kwargs."""
|
|
from deerflow.runtime.runs.store.memory import MemoryRunStore
|
|
|
|
store = MemoryRunStore()
|
|
await store.put("r1", thread_id="t1", status="success")
|
|
# MemoryRunStore doesn't have follow_up_to_run_id as a top-level param,
|
|
# but it can be passed via metadata
|
|
await store.put("r2", thread_id="t1", metadata={"follow_up_to_run_id": "r1"})
|
|
run = await store.get("r2")
|
|
assert run["metadata"]["follow_up_to_run_id"] == "r1"
|
|
|
|
@pytest.mark.anyio
|
|
async def test_human_message_has_follow_up_metadata(self):
|
|
"""human_message event metadata includes follow_up_to_run_id."""
|
|
from deerflow.runtime.events.store.memory import MemoryRunEventStore
|
|
|
|
event_store = MemoryRunEventStore()
|
|
await event_store.put(
|
|
thread_id="t1",
|
|
run_id="r2",
|
|
event_type="human_message",
|
|
category="message",
|
|
content="Tell me more about that",
|
|
metadata={"follow_up_to_run_id": "r1"},
|
|
)
|
|
messages = await event_store.list_messages("t1")
|
|
assert messages[0]["metadata"]["follow_up_to_run_id"] == "r1"
|
|
|
|
@pytest.mark.anyio
|
|
async def test_follow_up_auto_detection_logic(self):
|
|
"""Simulate the auto-detection: latest successful run becomes follow_up_to."""
|
|
from deerflow.runtime.runs.store.memory import MemoryRunStore
|
|
|
|
store = MemoryRunStore()
|
|
await store.put("r1", thread_id="t1", status="success")
|
|
await store.put("r2", thread_id="t1", status="error")
|
|
|
|
# Auto-detect: list_by_thread returns newest first
|
|
recent = await store.list_by_thread("t1", limit=1)
|
|
follow_up = None
|
|
if recent and recent[0].get("status") == "success":
|
|
follow_up = recent[0]["run_id"]
|
|
# r2 (error) is newest, so no follow_up detected
|
|
assert follow_up is None
|
|
|
|
# Now add a successful run
|
|
await store.put("r3", thread_id="t1", status="success")
|
|
recent = await store.list_by_thread("t1", limit=1)
|
|
follow_up = None
|
|
if recent and recent[0].get("status") == "success":
|
|
follow_up = recent[0]["run_id"]
|
|
assert follow_up == "r3"
|