search_sessions_by_id previously fetched up to 10k sessions via list_sessions_rich and filtered them in Python — O(n) per keystroke. Push the id match into SQL instead. - list_sessions_rich gains an optional id_query param: a case-insensitive LIKE pushed into the outer WHERE, matched against each surfaced row's id AND every id in its forward compression chain (via the existing chain CTE). Searching a compression root id or a tip id both resolve to the same projected conversation. LIKE wildcards in the needle are escaped. - search_sessions_by_id now fetches only matching rows (limit*4) and ranks exact > prefix > substring in Python over that small set. - web_server /api/sessions/search: route ID matches and content matches through one lineage-keyed dedup helper so an id-hit and a content-hit on the same conversation collapse to a single result (the contributor's version keyed ID hits by raw sid and content hits by root, which could double-list a compression tip). - command-center haystack also matches _lineage_root_id for parity. E2E verified against a real DB: exact match over 3000+ sessions materializes 1 row in Python (was ~3000), 5ms; root-id resolves to tip; LIKE-wildcard escaping holds. Follow-up to @0xharryriddle's feat(desktop): search sessions by id.
91 lines
2.8 KiB
Python
91 lines
2.8 KiB
Python
import asyncio
|
|
|
|
from hermes_cli import web_server
|
|
|
|
|
|
class _FakeSessionDB:
|
|
"""Fake backing the /api/sessions/search endpoint.
|
|
|
|
The endpoint surfaces direct session-id matches first, then FTS message
|
|
matches, deduping both by compression lineage root. This fake has no
|
|
compression chains (get_session returns no parent), so each session is its
|
|
own lineage root.
|
|
"""
|
|
|
|
closed = False
|
|
|
|
def search_sessions_by_id(self, query, limit=20, include_archived=True):
|
|
assert query == "20260603"
|
|
assert include_archived is True
|
|
return [
|
|
{
|
|
"id": "20260603_090200_exact",
|
|
"preview": "ID match preview",
|
|
"source": "cli",
|
|
"model": "claude",
|
|
"started_at": 100,
|
|
}
|
|
]
|
|
|
|
def search_messages(self, query, limit=20):
|
|
assert query == "20260603*"
|
|
return [
|
|
{
|
|
"session_id": "20260603_090200_exact",
|
|
"snippet": "duplicate content hit should not replace ID hit",
|
|
"role": "user",
|
|
"source": "cli",
|
|
"model": "claude",
|
|
"session_started": 100,
|
|
},
|
|
{
|
|
"session_id": "content_session",
|
|
"snippet": "content hit",
|
|
"role": "assistant",
|
|
"source": "desktop",
|
|
"model": "gpt",
|
|
"session_started": 200,
|
|
},
|
|
]
|
|
|
|
def get_session(self, session_id):
|
|
# No compression chains in this fixture — every session is its own root.
|
|
return {"id": session_id, "parent_session_id": None}
|
|
|
|
def get_compression_tip(self, session_id):
|
|
return session_id
|
|
|
|
def close(self):
|
|
self.closed = True
|
|
|
|
|
|
def test_desktop_session_search_merges_id_matches_before_content_matches(monkeypatch):
|
|
monkeypatch.setattr("hermes_state.SessionDB", _FakeSessionDB)
|
|
|
|
response = asyncio.run(web_server.search_sessions(q="20260603", limit=2))
|
|
|
|
# ID match surfaces first; the content hit on the SAME session is deduped
|
|
# by lineage root (not double-listed); the unrelated content hit follows.
|
|
assert response == {
|
|
"results": [
|
|
{
|
|
"session_id": "20260603_090200_exact",
|
|
"lineage_root": "20260603_090200_exact",
|
|
"snippet": "ID match preview",
|
|
"role": None,
|
|
"source": "cli",
|
|
"model": "claude",
|
|
"session_started": 100,
|
|
},
|
|
{
|
|
"session_id": "content_session",
|
|
"lineage_root": "content_session",
|
|
"snippet": "content hit",
|
|
"role": "assistant",
|
|
"source": "desktop",
|
|
"model": "gpt",
|
|
"session_started": 200,
|
|
},
|
|
]
|
|
}
|