Custom model via ANTHROPIC_BASE_URL: no way to declare a context window >200k (status line & auto-compaction assume 200k)

Summary

When routing to a custom model via ANTHROPIC_BASE_URL (an Anthropic-Messages-compatible gateway) whose real context window is larger than 200k, Claude Code assumes a 200k window and there is no reliable way to tell it the true size. This makes the status line and auto-compaction behave wrongly for large-window models.

Environment

• Claude Code 2.1.177 (native), macOS (arm64).
• Model id is a non-built-in string (e.g. my-gateway/big-model) served via ANTHROPIC_BASE_URL + ANTHROPIC_AUTH_TOKEN.
• The backend model's real context window is large (e.g. ~1M tokens).

Observed

• Status line shows …/200k; the statusline JSON context_window.context_window_size is 200000.
• context_window.used_percentage is computed against 200k, so resuming a session whose context exceeds 200k shows >100% and triggers auto-compaction prematurely — even though the backend supports far more.
• The [1m] suffix works for built-in model names, but there is no equivalent for an unrecognized custom/gateway model id.

Expected

A way to declare a custom model's true context window, so both the status line and the auto-compaction math use it.

Tried (and why it didn't resolve)

• Env vars around max-context / auto-compact window: I could not find a documented, working knob that makes an unrecognized custom model report or use a >200k window (the docs found were unclear/conflicting, and the status line stayed at 200k).
• [1m] suffix: applies only to known Claude model names, not custom ids.

Request (any one would solve it)

• A --model my-gateway/big-model[ctx=1048576]-style suffix for custom ids, or
• a modelOverrides / per-model contextWindow field in settings.json, or
• have gateway model discovery read a context_length / max_input_tokens field from the gateway's GET /v1/models and apply it to both the status line and compaction.