mirror of
https://github.com/pewdiepie-archdaemon/odysseus.git
synced 2026-07-12 12:37:32 +00:00
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:
+55
-5
@@ -1904,6 +1904,20 @@ def _migrate_chat_messages_fts():
|
||||
conn = None
|
||||
try:
|
||||
conn = sqlite3.connect(db_path)
|
||||
fts_content_expr_new = (
|
||||
"CASE WHEN instr(COALESCE(new.content, ''), ';base64,') > 0 "
|
||||
"OR instr(COALESCE(new.content, ''), 'data:image/') > 0 "
|
||||
"OR instr(COALESCE(new.content, ''), 'data:audio/') > 0 "
|
||||
"THEN '[inline media omitted from search index]' "
|
||||
"ELSE COALESCE(new.content, '') END"
|
||||
)
|
||||
fts_content_expr_cm = (
|
||||
"CASE WHEN instr(COALESCE(cm.content, ''), ';base64,') > 0 "
|
||||
"OR instr(COALESCE(cm.content, ''), 'data:image/') > 0 "
|
||||
"OR instr(COALESCE(cm.content, ''), 'data:audio/') > 0 "
|
||||
"THEN '[inline media omitted from search index]' "
|
||||
"ELSE COALESCE(cm.content, '') END"
|
||||
)
|
||||
try:
|
||||
conn.execute("CREATE VIRTUAL TABLE IF NOT EXISTS temp._odysseus_fts5_probe USING fts5(content)")
|
||||
conn.execute("DROP TABLE IF EXISTS temp._odysseus_fts5_probe")
|
||||
@@ -1912,7 +1926,7 @@ def _migrate_chat_messages_fts():
|
||||
return
|
||||
|
||||
conn.executescript(
|
||||
"""
|
||||
f"""
|
||||
CREATE VIRTUAL TABLE IF NOT EXISTS chat_messages_fts USING fts5(
|
||||
content,
|
||||
message_id UNINDEXED,
|
||||
@@ -1920,10 +1934,14 @@ def _migrate_chat_messages_fts():
|
||||
role UNINDEXED
|
||||
);
|
||||
|
||||
DROP TRIGGER IF EXISTS chat_messages_fts_ai;
|
||||
DROP TRIGGER IF EXISTS chat_messages_fts_ad;
|
||||
DROP TRIGGER IF EXISTS chat_messages_fts_au;
|
||||
|
||||
CREATE TRIGGER IF NOT EXISTS chat_messages_fts_ai
|
||||
AFTER INSERT ON chat_messages BEGIN
|
||||
INSERT INTO chat_messages_fts(content, message_id, session_id, role)
|
||||
VALUES (COALESCE(new.content, ''), new.id, new.session_id, new.role);
|
||||
VALUES ({fts_content_expr_new}, new.id, new.session_id, new.role);
|
||||
END;
|
||||
|
||||
CREATE TRIGGER IF NOT EXISTS chat_messages_fts_ad
|
||||
@@ -1935,14 +1953,14 @@ def _migrate_chat_messages_fts():
|
||||
AFTER UPDATE ON chat_messages BEGIN
|
||||
DELETE FROM chat_messages_fts WHERE message_id = old.id;
|
||||
INSERT INTO chat_messages_fts(content, message_id, session_id, role)
|
||||
VALUES (COALESCE(new.content, ''), new.id, new.session_id, new.role);
|
||||
VALUES ({fts_content_expr_new}, new.id, new.session_id, new.role);
|
||||
END;
|
||||
"""
|
||||
)
|
||||
conn.execute(
|
||||
"""
|
||||
f"""
|
||||
INSERT INTO chat_messages_fts(content, message_id, session_id, role)
|
||||
SELECT COALESCE(cm.content, ''), cm.id, cm.session_id, cm.role
|
||||
SELECT {fts_content_expr_cm}, cm.id, cm.session_id, cm.role
|
||||
FROM chat_messages cm
|
||||
WHERE NOT EXISTS (
|
||||
SELECT 1 FROM chat_messages_fts fts
|
||||
@@ -1950,6 +1968,7 @@ def _migrate_chat_messages_fts():
|
||||
)
|
||||
"""
|
||||
)
|
||||
_scrub_legacy_chat_message_fts_media(conn)
|
||||
conn.commit()
|
||||
except Exception as e:
|
||||
logging.getLogger(__name__).warning(f"chat_messages FTS migration failed: {e}")
|
||||
@@ -1960,6 +1979,37 @@ def _migrate_chat_messages_fts():
|
||||
pass
|
||||
|
||||
|
||||
def _scrub_legacy_chat_message_fts_media(conn) -> None:
|
||||
"""Replace already-indexed inline media rows with searchable text only."""
|
||||
try:
|
||||
from src.attachment_refs import search_index_text
|
||||
except Exception as e:
|
||||
logging.getLogger(__name__).warning(f"chat_messages FTS media scrub skipped: {e}")
|
||||
return
|
||||
|
||||
try:
|
||||
rows = conn.execute(
|
||||
"""
|
||||
SELECT id, session_id, role, content
|
||||
FROM chat_messages
|
||||
WHERE instr(COALESCE(content, ''), ';base64,') > 0
|
||||
OR instr(COALESCE(content, ''), 'data:image/') > 0
|
||||
OR instr(COALESCE(content, ''), 'data:audio/') > 0
|
||||
"""
|
||||
).fetchall()
|
||||
for message_id, session_id, role, content in rows:
|
||||
conn.execute("DELETE FROM chat_messages_fts WHERE message_id = ?", (message_id,))
|
||||
conn.execute(
|
||||
"""
|
||||
INSERT INTO chat_messages_fts(content, message_id, session_id, role)
|
||||
VALUES (?, ?, ?, ?)
|
||||
""",
|
||||
(search_index_text(content), message_id, session_id, role),
|
||||
)
|
||||
except Exception as e:
|
||||
logging.getLogger(__name__).warning(f"chat_messages FTS media scrub failed: {e}")
|
||||
|
||||
|
||||
def _migrate_add_email_smtp_security():
|
||||
"""Add explicit SMTP security mode for Proton Bridge/custom local SMTP."""
|
||||
import sqlite3
|
||||
|
||||
+47
-21
@@ -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)
|
||||
|
||||
Reference in New Issue
Block a user