Files
odysseus/tests/test_replace_messages_multimodal.py
Joshua Valderrama 35b4dd2824 fix: session context drifting — messages leaking between chats (#135) (#267)
* docs: add implementation plan for fixing chat context drifting (#135)

* fix: make Session.history immutable + fix {}.history crash

- Session.history now exposes a COPY of the internal _history list
- add_message() replaces history with a fresh copy each time
- get_context_messages() derives from _history directly
- replace_messages() updates both _history and history
- truncate_messages() updates both _history and history
- _persist_message() line 207: fixed {}.history fallback crash
- Added 11 tests for session isolation and edge cases

Addresses #135 root cause #1: shared mutable references

* fix: task scheduler uses SessionManager methods instead of overwriting sessions

- Added ensure_task_session() to SessionManager (checks cache first)
- Task scheduler now uses ensure_task_session() instead of direct dict assignment
- Task scheduler now uses SessionManager.add_message() for message persistence
- Removed direct sess_obj.history.append() that was silently losing data

Addresses #135 root causes #2 and #3

* fix: add age guard to cleanup_empty_sessions — don't delete sessions <1h old

Prevents the cleanup task from deleting sessions that were just created
and haven't received any messages yet (message_count == 0).

Addresses #135 root cause #5

* test: comprehensive session isolation tests (10/10 passing)

* refactor: consolidate _session_manager into singleton pattern

- Added set_session_manager_instance / get_session_manager_instance to core/models
- kept backward-compat aliases (set_session_manager, get_session_manager)
- session_manager.py re-exports the singleton functions
- ai_interaction.set_session_manager now syncs with the core singleton
- context_compactor uses get_session_manager_instance() instead of getattr hack
- app.py initializes the singleton once

Addresses #135 root cause #4: fragile global wiring

* test: add concurrent session isolation integration tests

Verifies:
- Concurrent add_message to different sessions doesn't cross-contaminate
- Rapid parallel writes maintain isolation
- Read-write concurrent access is safe

All 3 async tests pass, proving the immutable history fix works under concurrency

* fix: pre-import core.models in conftest to prevent test pollution

test_agent_loop.py stubs sys.modules['core.models'] = MagicMock() at
module level during collection. Any test collected after it imports
Session as a MagicMock. Pre-importing core.models in conftest.py
before test_agent_loop.py's module-level code runs prevents this.

* fix: make .history authoritative mutable list, address PR review

Per review feedback: keep .history as the authoritative mutable list so
existing code doing .history.pop(), .history = [...], etc. still works.
Fix the cross-contamination bug by ensuring __post_init__() gives each
Session its OWN unique history list (never shared).

Changes:
- core/models.py: .history IS the authoritative list. _history aliases it.
  Each Session gets its own list in __post_init__.
- core/session_manager.py: add_message() delegates to Session.add_message()
  instead of appending directly — no double-append, single source of truth.
- tests/test_session_manager.py: updated test to reflect that .history
  references see new messages (same list, not a snapshot).
- docs/plans/2026-06-01-fix-chat-context-drifting.md: removed (not for
  shipping — useful design context but too much process/doc to ship).

All 272 tests pass (3 pre-existing failures unrelated).

* Fix session manager message persistence

* Fix session history alias regressions

* Fix session history aliasing and task delivery
2026-06-09 14:12:52 +01:00

84 lines
2.9 KiB
Python

"""replace_messages must JSON-serialize multimodal (list) content.
A chat with an image/audio attachment carries list content. When such a
chat is compacted, the manual-compaction path calls replace_messages with
the retained messages. replace_messages wrote message.content straight into
the Text column, so SQLAlchemy bound the list\'s single-quoted repr. On
reload _parse_msg_content only de-serializes a string that contains the
double-quoted "type", so the repr failed the check and the message came
back as a corrupted string blob - the attachment was destroyed. The
sibling _persist_message json.dumps-es list content; replace_messages did
not.
"""
import uuid
import pytest
import core.database as cdb
from core.models import ChatMessage
from tests.helpers.sqlite_db import make_temp_sqlite
_TS, _ENGINE, _TMPDB = make_temp_sqlite(cdb.Base.metadata)
@pytest.fixture
def manager(monkeypatch):
import core.session_manager as sm
monkeypatch.setattr(sm, "SessionLocal", _TS)
mgr = sm.SessionManager.__new__(sm.SessionManager)
mgr.sessions = {}
return mgr
def _make_session(sid, owner="alice"):
db = _TS()
try:
db.add(cdb.Session(id=sid, owner=owner, name="chat", model="gpt-4o",
endpoint_url="http://localhost:11434",
archived=False, message_count=1))
db.commit()
finally:
db.close()
def test_multimodal_content_round_trips_through_replace_messages(manager):
sid = "sess-" + uuid.uuid4().hex[:8]
_make_session(sid)
multimodal = [
{"type": "text", "text": "what is this?"},
{"type": "image_url", "image_url": {"url": "data:image/png;base64,AAAA"}},
]
msgs = [ChatMessage(role="user", content=multimodal)]
assert manager.replace_messages(sid, msgs) is True
# Drop the in-memory cache so the next read hydrates from the DB.
manager.sessions.clear()
reloaded = manager.get_session(sid)
assert len(reloaded.history) == 1
# Content must come back as the original list, not a repr string blob.
assert reloaded.history[0].content == multimodal
def test_plain_string_content_still_round_trips(manager):
sid = "sess-" + uuid.uuid4().hex[:8]
_make_session(sid)
msgs = [ChatMessage(role="user", content="just text")]
assert manager.replace_messages(sid, msgs) is True
manager.sessions.clear()
reloaded = manager.get_session(sid)
assert reloaded.history[0].content == "just text"
def test_replace_messages_keeps_history_alias_for_context_messages(manager):
sid = "sess-" + uuid.uuid4().hex[:8]
_make_session(sid)
msgs = [ChatMessage(role="user", content="original")]
assert manager.replace_messages(sid, msgs) is True
session = manager.sessions[sid]
assert session.history is session._history
session.history.append(ChatMessage(role="user", content="after direct mutation"))
assert session.get_context_messages()[-1]["content"] == "after direct mutation"