Skip vanished backup list entries (#2006)

_load() returned whatever json.loads() produced without checking it was a
dict; _update() did the same before assigning data[key] = value. If the
oauth_tokens column ever held a JSON array or primitive (DB corruption,
manual edit, migration drift), _load()'s callers crashed with
AttributeError on .get(), and _update() crashed with TypeError trying to
item-assign into a list/string/int.

Validate the parsed value is a dict in both methods, falling back to {}
otherwise - same recovery behavior already used elsewhere in the codebase
for this exact JSON-blob-is-not-a-dict shape (_parse_tool_args,
_is_sensitive_path's siblings).

Adds 3 regression tests for _load, get_tokens, and _update against a
non-dict oauth_tokens value.

Fixes #5082

routes/email_pollers.py

@@ -1068,6 +1068,28 @@ def _scheduled_poll_once() -> dict:
         for r in rows:
             sid = r[0]
             try:
+                # Atomically claim this row before doing any work. Two
+                # pollers can race here (the in-process asyncio task and an
+                # externally cron-driven `odysseus-mail poll-scheduled`, or
+                # an admin running the CLI manually alongside the in-process
+                # one despite the ODYSSEUS_INPROCESS_POLLERS=0 guidance) -
+                # both can SELECT the same 'pending' row before either has
+                # updated its status. The UPDATE...WHERE status='pending' is
+                # the atomicity boundary: only the poller whose UPDATE
+                # actually changes a row (rowcount == 1) proceeds to send;
+                # a loser sees rowcount == 0 and skips it instead of sending
+                # a duplicate.
+                claim_conn = sqlite3.connect(SCHEDULED_DB)
+                claim_cur = claim_conn.execute(
+                    "UPDATE scheduled_emails SET status='sending' WHERE id=? AND status='pending'",
+                    (sid,),
+                )
+                claim_conn.commit()
+                claimed = claim_cur.rowcount == 1
+                claim_conn.close()
+                if not claimed:
+                    continue
+
                 attachments = json.loads(r[8] or "[]")
                 row_account_id = r[9] if len(r) > 9 else None
                 odysseus_kind = r[10] if len(r) > 10 else "scheduled"

routes/email_routes.py

@@ -923,29 +923,32 @@ def _resolve_send_config(account_id: str | None = None, owner: str = "") -> dict
 
 
 def _store_email_flag(conn, uid: str, flag: str, add: bool = True) -> bool:
+    # imaplib's plain store() takes a message SEQUENCE NUMBER, not a UID, so the
+    # old `else` fallback flagged whichever message happened to occupy sequence
+    # position == the UID value. When the UID isn't present, fail safe (callers
+    # surface "Email not found") rather than touch an unrelated message.
+    if not _uid_exists(conn, uid):
+        return False
     op = "+FLAGS" if add else "-FLAGS"
-    if _uid_exists(conn, uid):
-        status, _ = conn.uid("STORE", _uid_bytes(uid), op, flag)
-    else:
-        status, _ = conn.store(_uid_bytes(uid), op, flag)
+    status, _ = conn.uid("STORE", _uid_bytes(uid), op, flag)
     return status == "OK"
 
 
 def _move_email_message(conn, uid: str, dest: str, role: str = "") -> bool:
     dest = _resolve_mail_folder(conn, dest, role or _folder_role_from_name(dest))
-    if _uid_exists(conn, uid):
-        status, _ = conn.uid("MOVE", _uid_bytes(uid), _q(dest))
-        if status == "OK":
-            return True
-        status, _ = conn.uid("COPY", _uid_bytes(uid), _q(dest))
-        if status != "OK":
-            return False
-        status, _ = conn.uid("STORE", _uid_bytes(uid), "+FLAGS", "\\Deleted")
-    else:
-        status, _ = conn.copy(_uid_bytes(uid), _q(dest))
-        if status != "OK":
-            return False
-        status, _ = conn.store(_uid_bytes(uid), "+FLAGS", "\\Deleted")
+    # copy()/store() are SEQUENCE-NUMBER commands; using them with a UID (the old
+    # `else` branch) copied + \Deleted-flagged the wrong message and then
+    # expunge() permanently removed it. There is no valid case where treating a
+    # UID as a sequence number is correct, so fail safe when the UID is absent.
+    if not _uid_exists(conn, uid):
+        return False
+    status, _ = conn.uid("MOVE", _uid_bytes(uid), _q(dest))
+    if status == "OK":
+        return True
+    status, _ = conn.uid("COPY", _uid_bytes(uid), _q(dest))
+    if status != "OK":
+        return False
+    status, _ = conn.uid("STORE", _uid_bytes(uid), "+FLAGS", "\\Deleted")
     if status == "OK":
         conn.expunge()
         return True

scripts/odysseus-backup

@@ -133,18 +133,32 @@ def cmd_list(args):
         emit([], args)
         return
     entries = []
-    for p in sorted(_BACKUP_DIR.iterdir(), key=lambda x: x.stat().st_mtime, reverse=True):
-        if not p.is_file():
-            continue
-        entries.append({
-            "path": str(p),
-            "name": p.name,
-            "bytes": p.stat().st_size,
-            "modified": datetime.fromtimestamp(p.stat().st_mtime).isoformat(),
-        })
+    for p in _BACKUP_DIR.iterdir():
+        entry = _backup_entry(p)
+        if entry is not None:
+            entries.append(entry)
+    entries.sort(key=lambda entry: entry["_mtime"], reverse=True)
+    for entry in entries:
+        entry.pop("_mtime", None)
     emit(entries, args)
 
 
+def _backup_entry(p):
+    try:
+        if not p.is_file():
+            return None
+        st = p.stat()
+    except OSError:
+        return None
+    return {
+        "path": str(p),
+        "name": p.name,
+        "bytes": st.st_size,
+        "modified": datetime.fromtimestamp(st.st_mtime).isoformat(),
+        "_mtime": st.st_mtime,
+    }
+
+
 def cmd_verify(args):
     """Open the tarball read-only and walk its members — confirms
     integrity without extracting anything."""

scripts/odysseus-memory

@@ -90,7 +90,7 @@ def cmd_add(args):
     # add_entry doesn't save by default — the call in chat does it
     # after dedup checks. Persist here so a one-shot CLI add sticks.
     all_entries = _manager().load_all()
-    if not any(e.get("id") == entry.get("id") for e in all_entries):
+    if not any(isinstance(e, dict) and e.get("id") == entry.get("id") for e in all_entries):
         all_entries.append(entry)
         _manager().save(all_entries)
     emit(entry, args)

services/hwfit/models.py

@@ -145,7 +145,7 @@ def is_prequantized(model):
         or re.search(r"(^|[-_/])fp8($|[-_/\s])", text) is not None
         or (not (model.get("is_gguf") or model.get("gguf_sources")) and re.search(r"(^|[-_/])(?:int)?8bit($|[-_/\s])", text) is not None)
         or any(x in text for x in ("awq", "gptq", "mlx"))
-        or any(q.startswith(p) for p in PREQUANTIZED_PREFIXES)
+        or any(isinstance(q, str) and q.startswith(p) for p in PREQUANTIZED_PREFIXES)
     )
 
 
@@ -155,7 +155,7 @@ def params_b(model):
         return raw / 1_000_000_000.0
 
     pc = model.get("parameter_count", "")
-    if pc:
+    if isinstance(pc, str) and pc:
         pc = pc.strip().upper()
         m = re.match(r"^([\d.]+)\s*([BKMGT]?)$", pc)
         if m:

services/tts/tts_service.py

@@ -68,7 +68,7 @@ class TTSService:
         if provider == "local":
             kokoro = self._get_kokoro()
             return kokoro is not None and kokoro.available
-        if provider.startswith("endpoint:"):
+        if isinstance(provider, str) and provider.startswith("endpoint:"):
             return True  # assume reachable; errors surface at synthesis time
         return False
 

src/mcp_oauth.py

@@ -96,7 +96,9 @@ class DbTokenStorage:
         try:
             srv = db.query(McpServer).filter(McpServer.id == self.server_id).first()
             if srv and srv.oauth_tokens:
-                return json.loads(srv.oauth_tokens)
+                parsed = json.loads(srv.oauth_tokens)
+                if isinstance(parsed, dict):
+                    return parsed
         finally:
             db.close()
         return {}
@@ -111,6 +113,8 @@ class DbTokenStorage:
             if srv is None:
                 return
             data = json.loads(srv.oauth_tokens) if srv.oauth_tokens else {}
+            if not isinstance(data, dict):
+                data = {}
             data[key] = value
             srv.oauth_tokens = json.dumps(data)
             db.commit()

src/tools/system.py

@@ -356,7 +356,11 @@ async def do_manage_tasks(content: str, owner: Optional[str] = None) -> Dict:
             task = db.query(ScheduledTask).filter(ScheduledTask.id == task_id).first()
             if not task:
                 return {"error": f"Task {task_id} not found", "exit_code": 1}
-            if owner and task.owner and task.owner != owner:
+            # Strict ownership: the old `task.owner and task.owner != owner`
+            # skipped the check on an owner-less task (created in no-login mode
+            # or before the legacy-owner sweep), letting any authenticated user
+            # reach it. `list` already scopes to an exact owner match.
+            if owner and task.owner != owner:
                 return {"error": "Access denied", "exit_code": 1}
 
             changed = []
@@ -402,7 +406,7 @@ async def do_manage_tasks(content: str, owner: Optional[str] = None) -> Dict:
             task = db.query(ScheduledTask).filter(ScheduledTask.id == task_id).first()
             if not task:
                 return {"error": f"Task {task_id} not found", "exit_code": 1}
-            if owner and task.owner and task.owner != owner:
+            if owner and task.owner != owner:
                 return {"error": "Access denied", "exit_code": 1}
             name = task.name
             db.delete(task)
@@ -416,7 +420,7 @@ async def do_manage_tasks(content: str, owner: Optional[str] = None) -> Dict:
             task = db.query(ScheduledTask).filter(ScheduledTask.id == task_id).first()
             if not task:
                 return {"error": f"Task {task_id} not found", "exit_code": 1}
-            if owner and task.owner and task.owner != owner:
+            if owner and task.owner != owner:
                 return {"error": "Access denied", "exit_code": 1}
 
             if action == "pause":
@@ -437,7 +441,7 @@ async def do_manage_tasks(content: str, owner: Optional[str] = None) -> Dict:
             task = db.query(ScheduledTask).filter(ScheduledTask.id == task_id).first()
             if not task:
                 return {"error": f"Task {task_id} not found", "exit_code": 1}
-            if owner and task.owner and task.owner != owner:
+            if owner and task.owner != owner:
                 return {"error": "Access denied", "exit_code": 1}
 
             from src.event_bus import get_task_scheduler

static/js/keyboard-shortcuts.js

@@ -16,7 +16,7 @@ const _defaultKeybinds = {
 };
 
 export function _matchesCombo(e, combo, isMac = IS_MAC) {
-  if (!combo) return false;
+  if (typeof combo !== 'string' || !combo) return false;
   // Drop AltGr keystrokes so typing characters on non-US layouts can't fire a
   // Ctrl+Alt shortcut — e.g. the destructive delete_session. See platform.js.
   if (isAltGrEvent(e, isMac)) return false;

tests/test_backup_cli_security.py

@@ -25,6 +25,46 @@ def _verify_args(path: Path):
     return SimpleNamespace(path=str(path), pretty=False)
 
 
+def test_backup_entry_skips_files_that_disappear():
+    backup = _load_backup_cli()
+
+    class Vanished:
+        name = "gone.tar.gz"
+
+        def is_file(self):
+            return True
+
+        def stat(self):
+            raise FileNotFoundError("gone")
+
+        def __str__(self):
+            return "backups/gone.tar.gz"
+
+    assert backup._backup_entry(Vanished()) is None
+
+
+def test_backup_list_sorts_by_captured_mtime(monkeypatch):
+    backup = _load_backup_cli()
+    first = SimpleNamespace(name="older.tar.gz")
+    second = SimpleNamespace(name="newer.tar.gz")
+    monkeypatch.setattr(backup, "_BACKUP_DIR", SimpleNamespace(
+        is_dir=lambda: True,
+        iterdir=lambda: [first, second],
+    ))
+    monkeypatch.setattr(backup, "_backup_entry", lambda p: {
+        "name": p.name,
+        "modified": "2026-10-25T01:45:00" if p is first else "2026-10-25T01:15:00",
+        "_mtime": 100 if p is first else 200,
+    })
+    seen = []
+    monkeypatch.setattr(backup, "emit", lambda payload, args: seen.append(payload))
+
+    backup.cmd_list(SimpleNamespace(pretty=False))
+
+    assert [entry["name"] for entry in seen[0]] == ["newer.tar.gz", "older.tar.gz"]
+    assert all("_mtime" not in entry for entry in seen[0])
+
+
 def test_snapshot_rejects_output_inside_data_dir(tmp_path, monkeypatch):
     backup = _load_backup_cli()
     repo = tmp_path / "repo"

tests/test_email_uid_no_seqno_fallback.py

@@ -0,0 +1,88 @@
+"""Email move/flag must never fall back to sequence-number IMAP ops (#1874 sibling).
+
+`imaplib`'s plain `store()` / `copy()` operate on message SEQUENCE NUMBERS, not
+UIDs. `_store_email_flag` / `_move_email_message` (used by the archive / delete /
+move / mark endpoints) had an `else` fallback that, when `_uid_exists` returned
+False, ran `conn.store(uid, …)` / `conn.copy(uid, …)` + `conn.expunge()` — i.e.
+it flagged/copied whichever message occupied sequence position == the UID value
+and then permanently expunged it. A stale cached UID (or a server whose UID
+probe misbehaves) therefore deleted an unrelated email.
+
+The fix fails safe: when the UID isn't present, return False (callers surface
+"Email not found") and never touch a message by sequence number.
+
+This is distinct from #1874, which fixes the auto-spam poller's `_imap_move` in
+`routes/email_helpers.py`; this covers the user-facing endpoints in
+`routes/email_routes.py`.
+"""
+import pytest
+
+from routes import email_routes
+from routes.email_routes import _store_email_flag, _move_email_message
+
+
+class _FakeConn:
+    """Records IMAP calls. `uid_present` controls the FETCH-UID probe result.
+
+    The sequence-number commands (store/copy/expunge) raise if ever called —
+    the whole point of the fix is that they must not be reached.
+    """
+    def __init__(self, uid_present, uid_move_ok=True):
+        self.uid_present = uid_present
+        self.uid_move_ok = uid_move_ok
+        self.uid_calls = []
+        self.seqno_calls = []
+
+    def uid(self, command, *args):
+        self.uid_calls.append((command.upper(), args))
+        cmd = command.upper()
+        if cmd == "FETCH":
+            return ("OK", [b"1 (UID 5031)"] if self.uid_present else [])
+        if cmd == "MOVE":
+            return ("OK" if self.uid_move_ok else "NO", [b""])
+        if cmd in ("COPY", "STORE"):
+            return ("OK", [b""])
+        return ("OK", [b""])
+
+    # Sequence-number APIs — must never be used with a UID.
+    def store(self, *a):
+        self.seqno_calls.append(("store", a)); return ("OK", [b""])
+
+    def copy(self, *a):
+        self.seqno_calls.append(("copy", a)); return ("OK", [b""])
+
+    def expunge(self, *a):
+        self.seqno_calls.append(("expunge", a)); return ("OK", [b""])
+
+
+@pytest.fixture(autouse=True)
+def _no_folder_resolution(monkeypatch):
+    # _move_email_message resolves the destination folder via the connection;
+    # short-circuit it so the test focuses on the UID-vs-seqno behaviour.
+    monkeypatch.setattr(email_routes, "_resolve_mail_folder", lambda conn, dest, role="": dest)
+
+
+def test_store_flag_missing_uid_fails_safe():
+    conn = _FakeConn(uid_present=False)
+    assert _store_email_flag(conn, "5031", "\\Deleted", add=True) is False
+    assert conn.seqno_calls == []  # never touched a message by sequence number
+
+
+def test_move_missing_uid_fails_safe():
+    conn = _FakeConn(uid_present=False)
+    assert _move_email_message(conn, "5031", "Trash", role="trash") is False
+    assert conn.seqno_calls == []  # no copy/store/expunge on a phantom seqno
+
+
+def test_store_flag_present_uid_uses_uid_store():
+    conn = _FakeConn(uid_present=True)
+    assert _store_email_flag(conn, "5031", "\\Seen", add=True) is True
+    assert any(c[0] == "STORE" for c in conn.uid_calls)
+    assert conn.seqno_calls == []
+
+
+def test_move_present_uid_uses_uid_move():
+    conn = _FakeConn(uid_present=True, uid_move_ok=True)
+    assert _move_email_message(conn, "5031", "Archive", role="archive") is True
+    assert any(c[0] == "MOVE" for c in conn.uid_calls)
+    assert conn.seqno_calls == []

tests/test_hwfit_models_nonstring_fields.py

@@ -0,0 +1,31 @@
+"""Harden hwfit model-catalog parsing against non-string field values.
+
+`params_b` and `is_prequantized` read free-form fields straight off the HF
+catalog JSON. `parameter_count` is normally a string like "7B" and
+`quantization` a string like "FP8", but a catalog row can carry a non-string
+(e.g. an integer parameter_count, or a null/number quantization). The code
+called `pc.strip()` / `q.startswith(...)` directly, so one such row raised
+AttributeError and aborted the whole ranking pass (params_b/is_prequantized
+run for every model). Non-strings are now treated as unknown.
+"""
+from services.hwfit.models import params_b, is_prequantized
+
+
+def test_params_b_nonstring_count_does_not_raise():
+    assert params_b({"parameter_count": 7}) == 0.0
+    assert params_b({"parameter_count": ["7B"]}) == 0.0
+
+
+def test_params_b_valid_count_still_parses():
+    assert params_b({"parameter_count": "7B"}) == 7.0
+    assert params_b({"parameters_raw": 7_000_000_000}) == 7.0
+
+
+def test_is_prequantized_nonstring_quantization_does_not_raise():
+    assert is_prequantized({"quantization": 8}) is False
+    assert is_prequantized({"name": "plain-model", "quantization": 123}) is False
+
+
+def test_is_prequantized_still_detects_real_markers():
+    assert is_prequantized({"name": "some-model-awq"}) is True
+    assert is_prequantized({"quantization": "FP8-Mixed"}) is True

tests/test_manage_tasks_owner_scope.py

@@ -0,0 +1,139 @@
+"""manage_tasks mutations must fail closed on owner-less / cross-owner tasks.
+
+The edit/delete/pause/run actions of ``do_manage_tasks`` previously gated with
+``if owner and task.owner and task.owner != owner``. The middle term made the
+check a no-op whenever the task had no owner — the state a scheduled task is in
+when it was created in no-login mode (or via the localhost middleware bypass)
+before the periodic legacy-owner sweep reassigns it to the admin user. So any
+authenticated user's agent could edit, delete, pause, or *run* another tenant's
+owner-less task. The sibling ``list`` action already scopes with an exact
+``ScheduledTask.owner == owner`` filter, so the mutators were strictly more
+permissive than the reader.
+"""
+
+import json
+import tempfile
+
+import pytest
+from sqlalchemy import create_engine
+from sqlalchemy.orm import sessionmaker
+from sqlalchemy.pool import NullPool
+
+from tests.helpers.import_state import clear_fake_database_modules
+
+clear_fake_database_modules()
+
+import core.database as cdb
+from core.database import ScheduledTask
+from src.tools.system import do_manage_tasks
+
+_TMPDB = tempfile.NamedTemporaryFile(suffix=".db", delete=False)
+_ENGINE = create_engine(
+    f"sqlite:///{_TMPDB.name}",
+    connect_args={"check_same_thread": False},
+    poolclass=NullPool,
+)
+cdb.Base.metadata.create_all(_ENGINE)
+_TS = sessionmaker(bind=_ENGINE, autoflush=False, autocommit=False)
+# do_manage_tasks does `from core.database import SessionLocal` at call time,
+# so patching the module attribute is enough to point it at the temp DB.
+cdb.SessionLocal = _TS
+
+
+def _seed(task_id, owner):
+    db = _TS()
+    try:
+        db.add(ScheduledTask(
+            id=task_id, owner=owner, name=task_id, prompt="original",
+            task_type="llm", trigger_type="webhook", status="active",
+            output_target="session",
+        ))
+        db.commit()
+    finally:
+        db.close()
+
+
+def _get(task_id):
+    db = _TS()
+    try:
+        return db.query(ScheduledTask).filter(ScheduledTask.id == task_id).first()
+    finally:
+        db.close()
+
+
+@pytest.mark.asyncio
+async def test_edit_denied_on_ownerless_task_for_authenticated_user():
+    _seed("ownerless-edit", None)
+    out = await do_manage_tasks(
+        json.dumps({"action": "edit", "task_id": "ownerless-edit", "prompt": "pwned"}),
+        owner="alice",
+    )
+    assert out["exit_code"] == 1 and out["error"] == "Access denied"
+    assert _get("ownerless-edit").prompt == "original"
+
+
+@pytest.mark.asyncio
+async def test_delete_denied_on_ownerless_task_for_authenticated_user():
+    _seed("ownerless-del", None)
+    out = await do_manage_tasks(
+        json.dumps({"action": "delete", "task_id": "ownerless-del"}),
+        owner="alice",
+    )
+    assert out["exit_code"] == 1 and out["error"] == "Access denied"
+    assert _get("ownerless-del") is not None
+
+
+@pytest.mark.asyncio
+async def test_pause_denied_on_ownerless_task_for_authenticated_user():
+    _seed("ownerless-pause", None)
+    out = await do_manage_tasks(
+        json.dumps({"action": "pause", "task_id": "ownerless-pause"}),
+        owner="alice",
+    )
+    assert out["exit_code"] == 1 and out["error"] == "Access denied"
+    assert _get("ownerless-pause").status == "active"
+
+
+@pytest.mark.asyncio
+async def test_run_denied_on_ownerless_task_for_authenticated_user():
+    _seed("ownerless-run", None)
+    out = await do_manage_tasks(
+        json.dumps({"action": "run", "task_id": "ownerless-run"}),
+        owner="alice",
+    )
+    assert out["exit_code"] == 1 and out["error"] == "Access denied"
+
+
+@pytest.mark.asyncio
+async def test_edit_denied_on_other_owners_task():
+    _seed("bob-task", "bob")
+    out = await do_manage_tasks(
+        json.dumps({"action": "edit", "task_id": "bob-task", "prompt": "pwned"}),
+        owner="alice",
+    )
+    assert out["exit_code"] == 1 and out["error"] == "Access denied"
+    assert _get("bob-task").prompt == "original"
+
+
+@pytest.mark.asyncio
+async def test_edit_allowed_for_matching_owner():
+    _seed("alice-task", "alice")
+    out = await do_manage_tasks(
+        json.dumps({"action": "edit", "task_id": "alice-task", "prompt": "updated"}),
+        owner="alice",
+    )
+    assert out["exit_code"] == 0
+    assert _get("alice-task").prompt == "updated"
+
+
+@pytest.mark.asyncio
+async def test_edit_allowed_in_no_login_mode():
+    # owner is None when auth is disabled — single-user mode keeps full access
+    # to shared (owner-less) tasks, exactly as `list` returns them unfiltered.
+    _seed("shared-task", None)
+    out = await do_manage_tasks(
+        json.dumps({"action": "edit", "task_id": "shared-task", "prompt": "updated"}),
+        owner=None,
+    )
+    assert out["exit_code"] == 0
+    assert _get("shared-task").prompt == "updated"

tests/test_matchescombo_nonstring_js.py

@@ -0,0 +1,47 @@
+"""Pin _matchesCombo (static/js/keyboard-shortcuts.js) against a non-string
+keybind. Driven through `node --input-type=module` (same approach as
+tests/test_markdown_table_row_js.py); skips when `node` is missing.
+
+Regression: keybinds are merged from the server response of
+`/api/auth/settings` (`{ ..._defaultKeybinds, ...s.keybinds }`). A corrupt
+or malformed `keybinds` value (e.g. a number instead of "ctrl+k") reached
+`combo.split('+')` and threw "combo.split is not a function", breaking the
+whole keydown handler. The guard treats any non-string combo as "no match".
+"""
+import json
+import shutil
+import subprocess
+from pathlib import Path
+
+import pytest
+
+_REPO = Path(__file__).resolve().parent.parent
+_MOD = _REPO / "static" / "js" / "keyboard-shortcuts.js"
+_HAS_NODE = shutil.which("node") is not None
+
+_EVENT = "{key:'k',ctrlKey:false,altKey:false,shiftKey:false,metaKey:false}"
+
+
+def _match(combo_js):
+    js = f"""
+    import {{ _matchesCombo }} from '{_MOD.as_posix()}';
+    console.log(JSON.stringify(_matchesCombo({_EVENT}, {combo_js})));
+    """
+    proc = subprocess.run(
+        ["node", "--input-type=module"],
+        input=js, capture_output=True, text=True, cwd=str(_REPO), timeout=30,
+    )
+    assert proc.returncode == 0, proc.stderr
+    return json.loads(proc.stdout.strip())
+
+
+@pytest.mark.skipif(not _HAS_NODE, reason="node binary not on PATH")
+def test_non_string_combo_is_no_match():
+    assert _match("123") is False
+    assert _match("{}") is False
+    assert _match("null") is False
+
+
+@pytest.mark.skipif(not _HAS_NODE, reason="node binary not on PATH")
+def test_matching_combo_still_fires():
+    assert _match("'k'") is True

tests/test_mcp_oauth.py

@@ -1,4 +1,5 @@
 import asyncio
+import json
 from src import mcp_oauth
 
 
@@ -79,3 +80,53 @@ def test_db_token_storage_round_trip():
     t = asyncio.run(go())
     assert t.access_token == "abc"
     assert srv.oauth_tokens is not None  # persisted as JSON
+
+
+def _fake_storage(oauth_tokens):
+    class FakeSrv:
+        pass
+
+    srv = FakeSrv()
+    srv.oauth_tokens = oauth_tokens
+
+    class FakeQuery:
+        def filter(self, *a):
+            return self
+
+        def first(self):
+            return srv
+
+    class FakeSession:
+        def query(self, *a):
+            return FakeQuery()
+
+        def commit(self):
+            pass
+
+        def close(self):
+            pass
+
+    return srv, mcp_oauth.DbTokenStorage("srv-1", session_factory=lambda: FakeSession())
+
+
+def test_load_falls_back_to_empty_dict_for_non_dict_json():
+    # A corrupted/migrated oauth_tokens column holding a JSON array, not an
+    # object, must not crash _load()'s callers with AttributeError.
+    _srv, storage = _fake_storage('["stale", "data"]')
+    assert storage._load() == {}
+
+
+def test_get_tokens_returns_none_for_non_dict_oauth_tokens():
+    _srv, storage = _fake_storage("42")
+
+    async def go():
+        return await storage.get_tokens()
+
+    assert asyncio.run(go()) is None
+
+
+def test_update_recovers_from_non_dict_oauth_tokens():
+    # _update() must not raise TypeError trying to item-assign into a list.
+    srv, storage = _fake_storage('["stale", "data"]')
+    storage._update("tokens", {"access_token": "new"})
+    assert json.loads(srv.oauth_tokens) == {"tokens": {"access_token": "new"}}

tests/test_memory_cli_add_nondict.py

@@ -0,0 +1,46 @@
+"""cmd_add (scripts/odysseus-memory) must tolerate a non-dict row in the
+existing store. Every other command funnels load_all() through
+`_memory_entries()` (which drops non-dicts), but cmd_add iterated the raw
+list in its dedup check: `any(e.get("id") == ... for e in all_entries)`
+crashed with AttributeError on a corrupt/hand-edited memory.json row that
+is not a dict. The isinstance check short-circuits before `.get`.
+"""
+import importlib.machinery
+import importlib.util
+import sys
+import types
+from pathlib import Path
+from types import SimpleNamespace
+from unittest.mock import MagicMock
+
+ROOT = Path(__file__).resolve().parents[1]
+
+
+def _load_cli(monkeypatch):
+    svc = types.ModuleType("services.memory.memory")
+    svc.MemoryManager = MagicMock()
+    monkeypatch.setitem(sys.modules, "services.memory.memory", svc)
+    path = ROOT / "scripts" / "odysseus-memory"
+    loader = importlib.machinery.SourceFileLoader("odysseus_memory_cli_add", str(path))
+    spec = importlib.util.spec_from_loader(loader.name, loader)
+    module = importlib.util.module_from_spec(spec)
+    loader.exec_module(module)
+    return module
+
+
+def test_cmd_add_tolerates_non_dict_existing_row(monkeypatch):
+    cli = _load_cli(monkeypatch)
+    cli._mgr = MagicMock()
+    cli._mgr.add_entry.return_value = {"id": "m2", "text": "new"}
+    cli._mgr.load_all.return_value = [
+        {"id": "m1", "text": "existing"},
+        "corrupt-row",
+        None,
+    ]
+    emitted = []
+    monkeypatch.setattr(cli, "emit", lambda value, args: emitted.append(value))
+
+    cli.cmd_add(SimpleNamespace(text="new", category="fact", owner=None))
+
+    assert emitted == [{"id": "m2", "text": "new"}]
+    cli._mgr.save.assert_called_once()

tests/test_scheduled_poll_race.py

@@ -0,0 +1,116 @@
+"""Regression: two concurrent callers of `_scheduled_poll_once` (the
+in-process 30s poller and the `odysseus-mail poll-scheduled` CLI, which the
+project's own docstrings warn can race on the same SQLite when
+ODYSSEUS_INPROCESS_POLLERS is left enabled alongside an external cron/systemd
+driver) must not both send the same scheduled email.
+
+The old code selected pending rows, then only updated their status to 'sent'
+*after* the SMTP send completed - two overlapping calls can both SELECT the
+same 'pending' row before either UPDATEs it, so both send it. The fix adds
+an atomic claim step (`UPDATE ... SET status='sending' WHERE status='pending'`)
+before any work happens; only the caller whose UPDATE actually changes a row
+proceeds, the other sees rowcount == 0 and skips it.
+
+This test drives two real threads through the real `_scheduled_poll_once`
+against a shared SQLite file, synchronized with a barrier so both reach the
+SELECT at (as close to) the same moment as possible, and asserts the send
+callback fired exactly once.
+"""
+import sqlite3
+import threading
+import time
+
+
+def test_concurrent_pollers_do_not_double_send(tmp_path, monkeypatch):
+    import routes.email_helpers as email_helpers
+    import routes.email_pollers as email_pollers
+
+    db_path = tmp_path / "scheduled_emails.db"
+    monkeypatch.setattr(email_helpers, "SCHEDULED_DB", db_path)
+    monkeypatch.setattr(email_pollers, "SCHEDULED_DB", db_path)
+    email_helpers._init_scheduled_db()
+
+    conn = sqlite3.connect(db_path)
+    conn.execute(
+        """
+        INSERT INTO scheduled_emails
+        (id, to_addr, subject, body, attachments, send_at, created_at, status, account_id, owner)
+        VALUES (?, ?, ?, ?, ?, ?, ?, 'pending', ?, ?)
+        """,
+        (
+            "sched-race-1",
+            "recipient@example.com",
+            "Subject",
+            "Body",
+            "[]",
+            "2000-01-01T00:00:00",
+            "1999-12-31T00:00:00",
+            "acct-alice",
+            "alice",
+        ),
+    )
+    conn.commit()
+    conn.close()
+
+    send_calls = []
+    send_lock = threading.Lock()
+    barrier = threading.Barrier(2)
+
+    def fake_get_email_config(account_id=None, owner=""):
+        return {
+            "from_address": "alice@example.com",
+            "smtp_host": "smtp.example.com",
+            "smtp_user": "alice@example.com",
+            "smtp_password": "secret",
+        }
+
+    def fake_send_smtp_message(*args, **kwargs):
+        # Widen the window between the claim and the actual send so a
+        # buggy (unclaimed) second poller has every opportunity to also
+        # get past its SELECT and attempt to send.
+        time.sleep(0.05)
+        with send_lock:
+            send_calls.append(threading.get_ident())
+
+    class FakeImap:
+        def __init__(self, account_id=None, owner=""):
+            pass
+
+        def __enter__(self):
+            return self
+
+        def __exit__(self, exc_type, exc, tb):
+            return False
+
+        def append(self, folder, flags, date_time, message):
+            pass
+
+    monkeypatch.setattr(email_pollers, "_get_email_config", fake_get_email_config)
+    monkeypatch.setattr(email_pollers, "_send_smtp_message", fake_send_smtp_message)
+    monkeypatch.setattr(email_pollers, "_imap", FakeImap)
+    monkeypatch.setattr(email_pollers, "_detect_sent_folder", lambda imap: "Sent")
+    monkeypatch.setattr(email_pollers, "_cleanup_compose_uploads", lambda attachments: None)
+
+    results = []
+
+    def _run():
+        barrier.wait()
+        results.append(email_pollers._scheduled_poll_once())
+
+    threads = [threading.Thread(target=_run) for _ in range(2)]
+    for t in threads:
+        t.start()
+    for t in threads:
+        t.join(timeout=5)
+
+    assert len(send_calls) == 1, (
+        f"expected exactly one send for the racing pollers, got {len(send_calls)}: "
+        "the second poller must lose the atomic claim and skip the row"
+    )
+
+    conn = sqlite3.connect(db_path)
+    status = conn.execute(
+        "SELECT status FROM scheduled_emails WHERE id=?", ("sched-race-1",)
+    ).fetchone()[0]
+    conn.close()
+    assert status == "sent"

tests/test_tts_available_nonstring_provider.py

@@ -0,0 +1,17 @@
+from services.tts.tts_service import TTSService
+
+
+def test_available_tolerates_non_string_provider(tmp_path):
+    """A hand-edited/corrupt data/settings.json can store a non-string
+    tts_provider (e.g. null or a number). available reads it and calls
+    provider.startswith("endpoint:"), which raised AttributeError on a
+    non-str. It must instead fall through and report unavailable."""
+    service = TTSService(cache_dir=str(tmp_path))
+    service._load_settings = lambda: {
+        "tts_enabled": True,
+        "tts_provider": 123,
+        "tts_model": "tts-1",
+        "tts_voice": "alloy",
+        "tts_speed": "1",
+    }
+    assert service.available is False