search_event returns KeyError 'events'

[kun432]

Description

search_event returns KeyError 'events'.

Steps to reproduce

from memobase import MemoBaseClient

client = MemoBaseClient(
    project_url="http://MY_SERVER:8019",
    api_key="secret",
)

uid = client.add_user({"name": "test"})
u = client.get_user(uid)

from memobase import ChatBlob

b = ChatBlob(
    messages=[
        { "role": "user", "content": "Hi! I'm Alex, originally from Canada and now living in Portland. I'm thinking about getting into home coffee roasting—mind giving me a quick starter plan?" },
        { "role": "assistant", "content": "Happy to help! Do you prefer a super simple setup (popcorn popper) or a more controlled entry-level roaster with temperature profiling?" },
        { "role": "user", "content": "Let's start simple. I work from home most days, so I can roast on my balcony on Saturday mornings." },
        { "role": "assistant", "content": "Great. Starter kit: an air popcorn popper dedicated to coffee, a basic digital scale, a metal sieve for cooling, and a timer. Aim for 70–90 grams per batch to keep it even." },
        { "role": "user", "content": "Nice. I like medium roasts for pour-over. Any beginner-friendly beans to order?" },
        { "role": "assistant", "content": "Try a washed Colombia or Ethiopia for clarity, or a Guatemala for balanced sweetness. Start with 1 kg so you can iterate. Store green beans in a cool, dry place." },
        { "role": "user", "content": "Cool. By the way, I'm starting a new data role on Oct 21, so I want something low-maintenance on weekdays. Weekends I also hike in the Columbia River Gorge." },
        { "role": "assistant", "content": "Congrats on the new role! Weekday plan: pre-weigh doses on Sunday night, and use a simple 1:16 brew ratio with a 3–3.5 min total time. For hikes, pack a small grinder and single-serve filters—lightweight and mess-free." },
        { "role": "user", "content": "I’m planning a hike this Sunday—Dog Mountain if the weather holds. Any tips for coffee + hike logistics?" },
        { "role": "assistant", "content": "Roast on Saturday morning, let beans rest 12–24 hours. On Sunday, bring 20–22 g per cup in small zip bags, a collapsible filter cone, and a 500 ml insulated bottle of hot water. Keep gear together in a dry bag; enjoy a medium roast Colombia for a clean cup with views!" }
    ]
)
u.insert(b)
u.flush()

---------------------------------------------------------------------------
KeyError                                  Traceback (most recent call last)
Cell In[9], line 1
----> 1 u.search_event("about coffee")

File [/opt/conda/lib/python3.12/site-packages/memobase/core/entry.py:297](http://localhost:8888/opt/conda/lib/python3.12/site-packages/memobase/core/entry.py#line=296), in User.search_event(self, query, topk, similarity_threshold, time_range_in_days)
    291 params = f"?query={query}&topk={topk}&similarity_threshold={similarity_threshold}&time_range_in_days={time_range_in_days}"
    292 r = unpack_response(
    293     self.project_client.client.get(
    294         f"[/users/event/search/](http://localhost:8888/users/event/search/){self.user_id}{params}"
    295     )
    296 )
--> 297 return [UserEventData.model_validate(e) for e in r.data["events"]]

KeyError: 'events'

Additional Info

get context: OK

print(u.context())

---
# Memory
Unless the user has relevant queries, do not actively mention those memories in the conversation.
## User Current Profile:
- basic_info::name: Alex
- basic_info::nationality: Canada
- contact_info::city: Portland
- work::title: data role
- work::working_industry: data
- work::previous_projects: starting a new data role on October 21, 2025 [mention 2025/09/30, start job in 2025/10/21]
- interest::hobbies: plans to roast coffee on Saturday mornings [mention 2025/09/30, roast coffee in 2025/10/07]; plans to hike in the Columbia River Gorge on weekends
- life_event::hiking: planning a hike to Dog Mountain this Sunday if the weather holds [mention 2025/09/30, plan hike in 2025/10/01]

## Past Events:
- User's alias is Alex. // info
- Alex is originally from Canada and now living in Portland. // info
- Alex works from home most days. // info
- Alex is starting a new data role on October 21, 2025. [mention 2025/09/30, start job in 2025/10/21] // info
- Alex plans to roast coffee on Saturday mornings. [mention 2025/09/30, roast coffee in 2025/10/07] // schedule
- Alex plans to hike in the Columbia River Gorge on weekends. // schedule
- Alex is planning a hike to Dog Mountain this Sunday if the weather holds. [mention 2025/09/30, plan hike in 2025/10/01] // schedule
---

search event gist: OK

u.search_event_gist("about coffee")

[UserEventGistData(id=UUID('1a75b15a-ae36-4ea4-8c4a-025886b3de28'), gist_data=EventGistData(content='- Alex plans to roast coffee on Saturday mornings. [mention 2025/09/30, roast coffee in 2025/10/07] // schedule'), created_at=datetime.datetime(2025, 9, 29, 17, 44, 41, 295587, tzinfo=TzInfo(UTC)), updated_at=datetime.datetime(2025, 9, 29, 17, 44, 41, 295587, tzinfo=TzInfo(UTC)), similarity=0.47585159684112177)]

only search event fails.

Environments

• Memobase PyPI: 0.0.25 (on JupyterLab)
• Memobase Server: 0.0.40 (on Ubuntu-22.04 / Docker-28.3.1 / commit: c76b4fd)