[Bug]: Used-up Claude monthly extra-usage budget switches new threads to the fallback model #36483

Before submitting

• I searched existing issues and did not find a duplicate.
• I included enough detail to reproduce or investigate the problem.

Area

packages/contracts or packages/shared

Steps to reproduce

1. Use a Claude subscription with extra usage (overage) enabled and a monthly spend limit.
2. Use up the monthly extra-usage budget. Claude's rate_limit_event then reports overageStatus: "rejected" with overageDisabledReason: "org_level_disabled_until". The 5-hour and weekly windows still have room (status: "allowed").
3. Set a fallback model in Settings → Threads, for example a Codex model.
4. Start a new thread in a project whose default model is a Claude model.

Expected behavior

New threads keep the Claude default model. A used-up extra-usage budget only matters after the plan limits run out, so Claude is not out of usage. The fallback should only apply when a window that actually blocks requests is exhausted.

Actual behavior

The composer switches to the fallback model and shows "Using GPT-6.1-Sol · Claude is out of usage", with no "resets …" time.

The cached Claude provider snapshot at that moment:

[
  { "id": "five_hour", "usedPercent": 18, "resetsAt": "2026-11-14T03:20:00.125Z" },
  { "id": "seven_day", "usedPercent": 4, "resetsAt": "2026-11-20T02:00:00.125Z" },
  { "id": "seven_day_fable", "usedPercent": 0, "resetsAt": "2026-11-20T02:00:00.000Z" },
  { "id": "monthly_spend", "kind": "monthly", "label": "Monthly spend", "usedPercent": 100 }
]

Cause, as I read the 0.1.9 bundle:

• claudeUsageResponseToLimits (apps/server/src/provider/claudeUsageLimits.ts) adds a monthly_spend window from readSpendPercent, with no resetsAt.
• exhaustedUsageWindow (packages/shared/src/usageLimits.ts) treats any window with usedPercent >= 100 as exhausted when its resetsAt is missing or in the future. For claudeAgent it returns that window, so the new-thread fallback kicks in.

The server's own turn-blocking logic is already correct here. It only counts Claude as blocked when status === "rejected" and overage is not allowed. Only the new-thread fallback check disagrees.

Related, but neither fixes this:

• [Bug]: Exhausted Fable weekly limit marks all Claude models as out of usage #32015 / fix(shared): a model-scoped Claude limit no longer blocks other Claude models #32016 exempt model-scoped seven_day_<model> windows. monthly_spend still counts as exhausted.
• fix(usage): Claude monthly spend shows pace and a reset countdown #34162 gives monthly_spend a reset time. That makes the banner read "resets Dec 1", but new threads would still fall back for the rest of the month.

Suggested fix: leave monthly_spend (extra-usage spend) out of exhaustedUsageWindow for claudeAgent, or only count it when the plan windows are also exhausted.

Impact

Major degradation or frequent failure

Version or commit

0.1.9

Environment

Linux server (remote environment), web client, Claude Agent SDK provider on a Claude subscription, fallback model GPT-6.1-Sol (Codex)

Workaround

Click "Use " on the notice or dismiss it, or clear the Fallback model setting.