[Bug] Server-gated token budget feature causes sub-agents to prematurely exhaust context and create infinite respawn loops

Bug Description
Since 2.1.290, a server-gated feature gives every sub-agent a <total_tokens> countdown that starts at 100,000 and adds "Each agent you launch has a budget of 100,000 tokens. The budget does not count the context the agent starts with: its system prompt, its tools, and your prompt to it." to the Agent tool description. It was switched on for one of my accounts (Fable 5.1 main session only; Opus and Sonnet main sessions on the same account did not get it, and Fable on my other account did not either). It made delegated work impossible: every sub-agent stopped itself at about 100k tokens of work and reported "ran out of context" or "budget exhausted", and the orchestrator kept respawning 100k-sized agents for hours. If this is an intended experiment, 100k is far below what real codebases need; if it is a rollout mistake, please check the gating.

Environment Info

• Platform: linux
• Terminal: tmux
• Version: 2.1.291
• Feedback ID: 3be2bc2e-63ea-46cc-9a93-1e3364ebf512