[BUG] Model opusplan still using 200K context for either mode

Preflight Checklist

• [x] I have searched existing issues and this hasn't been reported yet
• [x] This is a single bug report (please file separate reports for different bugs)
• [x] I am using the latest version of Claude Code

What's Wrong?

I'm on latest version of CC

current: 2.1.76 · latest: 2.1.76

I'm using /model opusplan, which is to use Opus 4.6 for plan mode, Sonnet 4.6 for other usage, but I'm still seeing 200K context size for either mode/model. Please update to give me the full 1M as I'm expecting, after https://claude.com/blog/1m-context-ga

What Should Happen?

I'm expecting the max context available to be 1M after this change for Max plan users like I am https://claude.com/blog/1m-context-ga

Error Messages/Logs

Steps to Reproduce

❯ /model

─────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────
Select model
Switch between Claude models. Applies to this session and future Claude Code sessions. For other/previous model names, specify with --model.

1. Default (recommended)Opus 4.6 with 1M context [NEW] · Most capable for complex work
2. SonnetSonnet 4.6 · Best for everyday tasks
3. HaikuHaiku 4.5 · Fastest for quick answers
❯ 4. Opus Plan Mode ✔Use Opus 4.6 in plan mode, Sonnet 4.6 otherwise

Plan mode:

❯ /context
⎿Context Usage
⛁ ⛁ ⛁ ⛁ ⛁ ⛁ ⛁ ⛀ ⛁ ⛁claude-opus-4-6 · 27k/200k tokens (14%)
⛁ ⛁ ⛁ ⛁ ⛶ ⛶ ⛶ ⛶ ⛶ ⛶
⛶ ⛶ ⛶ ⛶ ⛶ ⛶ ⛶ ⛶ ⛶ ⛶Estimated usage by category
⛶ ⛶ ⛶ ⛶ ⛶ ⛶ ⛶ ⛶ ⛶ ⛶⛁ System prompt: 5.4k tokens (2.7%)
⛶ ⛶ ⛶ ⛶ ⛶ ⛶ ⛶ ⛶ ⛶ ⛶⛁ System tools: 7.9k tokens (4.0%)
⛶ ⛶ ⛶ ⛶ ⛶ ⛶ ⛶ ⛶ ⛶ ⛶⛁ Custom agents: 808 tokens (0.4%)
⛶ ⛶ ⛶ ⛶ ⛶ ⛶ ⛶ ⛶ ⛶ ⛶⛁ Memory files: 2.4k tokens (1.2%)
⛶ ⛶ ⛶ ⛶ ⛶ ⛶ ⛶ ⛶ ⛶ ⛶⛁ Skills: 2.1k tokens (1.0%)
⛶ ⛶ ⛶ ⛝ ⛝ ⛝ ⛝ ⛝ ⛝ ⛝⛁ Messages: 8.9k tokens (4.4%)
⛝ ⛝ ⛝ ⛝ ⛝ ⛝ ⛝ ⛝ ⛝ ⛝⛶ Free space: 140k (69.8%)
⛝ Autocompact buffer: 33k tokens (16.5%)

Non-plan mode:

❯ /context
⎿Context Usage
⛁ ⛁ ⛁ ⛁ ⛁ ⛁ ⛁ ⛀ ⛁ ⛁claude-sonnet-4-6 · 29k/200k tokens (15%)
⛁ ⛁ ⛁ ⛁ ⛁ ⛶ ⛶ ⛶ ⛶ ⛶
⛶ ⛶ ⛶ ⛶ ⛶ ⛶ ⛶ ⛶ ⛶ ⛶Estimated usage by category
⛶ ⛶ ⛶ ⛶ ⛶ ⛶ ⛶ ⛶ ⛶ ⛶⛁ System prompt: 5.4k tokens (2.7%)
⛶ ⛶ ⛶ ⛶ ⛶ ⛶ ⛶ ⛶ ⛶ ⛶⛁ System tools: 7.9k tokens (4.0%)
⛶ ⛶ ⛶ ⛶ ⛶ ⛶ ⛶ ⛶ ⛶ ⛶⛁ Custom agents: 808 tokens (0.4%)
⛶ ⛶ ⛶ ⛶ ⛶ ⛶ ⛶ ⛶ ⛶ ⛶⛁ Memory files: 2.4k tokens (1.2%)
⛶ ⛶ ⛶ ⛶ ⛶ ⛶ ⛶ ⛶ ⛶ ⛶⛁ Skills: 2.1k tokens (1.0%)
⛶ ⛶ ⛶ ⛝ ⛝ ⛝ ⛝ ⛝ ⛝ ⛝⛁ Messages: 10.9k tokens (5.4%)
⛝ ⛝ ⛝ ⛝ ⛝ ⛝ ⛝ ⛝ ⛝ ⛝⛶ Free space: 138k (68.8%)
⛝ Autocompact buffer: 33k tokens (16.5%)

Claude Model

Not sure / Multiple models

Is this a regression?

I don't know

Last Working Version

_No response_

Claude Code Version

2.1.76

Platform

Anthropic API

Operating System

Ubuntu/Debian Linux

Terminal/Shell

Other

Additional Information

_No response_