fix(stabilization): harden attachment lifecycle and agent guard signals (#5420)

* fix: harden stabilization attachment and agent guards

* fix(uploads): preserve durable references during cleanup

* fix(uploads): close cleanup and compaction races
This commit is contained in:
falabellamichael
2026-07-11 10:14:14 -04:00
committed by GitHub
parent 6b8f84553c
commit d16b849c3e
29 changed files with 2718 additions and 189 deletions
+47 -21
View File
@@ -16,6 +16,8 @@ from typing import Dict, Optional
from .database import Session as DbSession, ChatMessage as DbChatMessage, Document as DbDocument, SessionLocal, utcnow_naive
from .models import Session, ChatMessage
from src.attachment_refs import persistable_message_content
from src.upload_handler import reserve_message_upload_references
# Re-export singleton accessors from models for convenience
from .models import set_session_manager_instance, get_session_manager_instance
@@ -72,6 +74,7 @@ class SessionManager:
def __init__(self, sessions_file: str = None):
# sessions_file kept for backward compat, not used
self.sessions: Dict[str, Session] = {}
self.upload_handler = None
self.load_sessions()
# ------------------------------------------------------------------
@@ -230,17 +233,26 @@ class SessionManager:
logger.warning("Dropping message for deleted session %s", session_id)
return
missing_upload_id = reserve_message_upload_references(
getattr(self, "upload_handler", None),
getattr(db_session, "owner", None),
message.content,
message.metadata,
)
if missing_upload_id:
raise ValueError(
f"Referenced upload is no longer available: {missing_upload_id}"
)
msg_id = str(uuid.uuid4())
msg_time = datetime.utcnow()
if message.metadata is None:
message.metadata = {}
message.metadata.setdefault('timestamp', _message_timestamp_iso(msg_time))
# Multimodal content (image/audio attachments) is a list — serialize
# to JSON so the Text column can store it. On reload, _db_to_session
# detects the JSON-array prefix and parses it back.
_content = message.content
if isinstance(_content, list):
_content = json.dumps(_content)
# Multimodal content may contain provider data URLs for the live
# model call. Persist only readable text plus attachment references
# so chat_messages/FTS do not duplicate upload bytes.
_content = persistable_message_content(message.content, message.metadata)
db_message = DbChatMessage(
id=msg_id,
session_id=session_id,
@@ -322,6 +334,28 @@ class SessionManager:
session = self.get_session(session_id)
db = SessionLocal()
try:
db_session = db.query(DbSession).filter(DbSession.id == session_id).first()
if db_session is None:
logger.warning("Cannot replace history for missing session %s", session_id)
return False
# Reserve every incoming attachment before removing any durable
# message row. reserve_upload() shares the upload lifecycle lock
# with cleanup, so an upload cannot be deleted between this
# ownership check/access touch and the replacement transaction.
# A failed reservation must leave the existing transcript intact.
for message in messages:
missing_upload_id = reserve_message_upload_references(
getattr(self, "upload_handler", None),
getattr(db_session, "owner", None),
message.content,
message.metadata,
)
if missing_upload_id:
raise ValueError(
f"Referenced upload is no longer available: {missing_upload_id}"
)
db.query(DbChatMessage).filter(DbChatMessage.session_id == session_id).delete()
now = datetime.now(timezone.utc)
for i, message in enumerate(messages):
@@ -330,15 +364,9 @@ class SessionManager:
id=msg_id,
session_id=session_id,
role=message.role,
# Multimodal content (image/audio attachments) is a list;
# serialize to JSON so the Text column round-trips via
# _parse_msg_content. Storing the raw list let SQLAlchemy
# bind its single-quoted repr, which _parse_msg_content
# cannot parse (it looks for double-quoted "type"), so the
# attachment was destroyed on reload. Mirrors _persist_message.
content=(json.dumps(message.content)
if isinstance(message.content, list)
else message.content),
# Mirrors _persist_message: keep raw media bytes out of the
# persisted transcript and search index.
content=persistable_message_content(message.content, message.metadata),
meta_data=json.dumps(message.metadata) if message.metadata else None,
timestamp=now + timedelta(microseconds=i),
)
@@ -347,12 +375,10 @@ class SessionManager:
message.metadata = {}
message.metadata["_db_id"] = msg_id
db_session = db.query(DbSession).filter(DbSession.id == session_id).first()
if db_session:
db_session.message_count = len(messages)
db_session.updated_at = now
db_session.last_accessed = now
db_session.last_message_at = now
db_session.message_count = len(messages)
db_session.updated_at = now
db_session.last_accessed = now
db_session.last_message_at = now
db.commit()
session.history = list(messages)