From 07c2677eed6ae00af9cedf74623536f54a514b15 Mon Sep 17 00:00:00 2001
From: KDB <937925477@qq.com>
Date: Tue, 28 Jul 2026 13:30:57 +0800
Subject: [PATCH] fix(webui): drop malformed token-usage day keys

normalize_token_usage_state only length-checked persisted day keys, so a
hand-edited or foreign 10-char key (e.g. "not-a-dat3" or "2026-13-01") in
token-usage.json survived reads and atomic rewrites. token_usage_payload
then parsed every day key with an unguarded datetime.fromisoformat, so one
such key failed every /api/settings and /api/settings/usage request until
the file was repaired by hand.

Validate day keys in normalize_token_usage_state, the shared boundary that
every read, record, and rewrite already funnels through. Malformed keys are
dropped like other malformed rows and scrubbed from the file on the next
write; valid state is unchanged.
---
 nanobot/webui/token_usage.py    |  7 +++++
 tests/webui/test_token_usage.py | 55 +++++++++++++++++++++++++++++++++
 2 files changed, 62 insertions(+)

diff --git a/nanobot/webui/token_usage.py b/nanobot/webui/token_usage.py
index 1e72b5e69..f06e9421f 100644
--- a/nanobot/webui/token_usage.py
+++ b/nanobot/webui/token_usage.py
@@ -159,6 +159,13 @@ def normalize_token_usage_state(raw: Any) -> dict[str, Any]:
         if not isinstance(date, str) or len(date) != 10 or not isinstance(row_value, dict):
             continue
         row = cast(dict[str, Any], row_value)
+        try:
+            datetime.fromisoformat(date)
+        except ValueError:
+            # A hand-edited or foreign day key that is not a real date would
+            # otherwise reach token_usage_payload's date parsing and fail every
+            # settings request; drop it like any other malformed row.
+            continue
         normalized = _normalize_usage_row(row)
         if normalized["total_tokens"] <= 0 and normalized["requests"] <= 0:
             continue
diff --git a/tests/webui/test_token_usage.py b/tests/webui/test_token_usage.py
index 470c10230..6514909fa 100644
--- a/tests/webui/test_token_usage.py
+++ b/tests/webui/test_token_usage.py
@@ -1,5 +1,6 @@
 from __future__ import annotations
 
+import json
 from datetime import datetime, timezone
 from types import SimpleNamespace
 
@@ -14,6 +15,60 @@ from nanobot.webui.token_usage import (
 )
 
 
+def _write_state(tmp_path, days: dict) -> None:
+    state_dir = tmp_path / "webui"
+    state_dir.mkdir(parents=True, exist_ok=True)
+    (state_dir / "token-usage.json").write_text(
+        json.dumps({"days": days}), encoding="utf-8"
+    )
+
+
+def test_payload_tolerates_malformed_persisted_day_keys(tmp_path, monkeypatch) -> None:
+    """Day keys that are not real dates must not break settings payloads.
+
+    normalize_token_usage_state only length-checks day keys, so a hand-edited
+    10-char key survives reads and atomic rewrites; token_usage_payload then
+    parsed it with an unguarded fromisoformat, failing every /api/settings and
+    /api/settings/usage request until the file was fixed by hand.
+    """
+    monkeypatch.setattr("nanobot.webui.token_usage.get_webui_dir", lambda: tmp_path / "webui")
+    _write_state(tmp_path, {
+        "not-a-dat3": {"total_tokens": 7, "requests": 1},
+        "2026-13-01": {"total_tokens": 9, "requests": 1},
+        "2026-06-02": {"total_tokens": 5, "requests": 1},
+    })
+
+    payload = token_usage_payload(
+        timezone_name="UTC",
+        now=datetime(2026, 6, 3, 12, 0, tzinfo=timezone.utc),
+    )
+
+    assert payload["total_tokens"] == 5
+    assert payload["total_tokens_30d"] == 5
+    assert payload["requests_30d"] == 1
+    assert payload["active_days_30d"] == 1
+
+
+def test_record_scrubs_malformed_day_keys(tmp_path, monkeypatch) -> None:
+    """Rewrites drop malformed day keys instead of persisting them forever."""
+    monkeypatch.setattr("nanobot.webui.token_usage.get_webui_dir", lambda: tmp_path / "webui")
+    _write_state(tmp_path, {
+        "not-a-dat3": {"total_tokens": 7, "requests": 1},
+        "2026-06-02": {"total_tokens": 5, "requests": 1},
+    })
+
+    record_token_usage(
+        {"prompt_tokens": 1, "completion_tokens": 1},
+        timezone_name="UTC",
+        now=datetime(2026, 6, 3, 12, 0, tzinfo=timezone.utc),
+    )
+
+    raw = json.loads((tmp_path / "webui" / "token-usage.json").read_text(encoding="utf-8"))
+    assert "not-a-dat3" not in raw["days"]
+    assert "2026-06-02" in raw["days"]
+    assert "2026-06-03" in raw["days"]
+
+
 def test_record_token_usage_aggregates_by_local_day(tmp_path, monkeypatch) -> None:
     monkeypatch.setattr("nanobot.webui.token_usage.get_webui_dir", lambda: tmp_path / "webui")